mirror of
https://github.com/torvalds/linux.git
synced 2026-10-07 05:31:08 -04:00
Mark Rutland
26299b3f6b
This commit replaces arm64's support for FTRACE_WITH_REGS with support
for FTRACE_WITH_ARGS. This removes some overhead and complexity, and
removes some latent issues with inconsistent presentation of struct
pt_regs (which can only be reliably saved/restored at exception
boundaries).
FTRACE_WITH_REGS has been supported on arm64 since commit:
3b23e4991f ("arm64: implement ftrace with regs")
As noted in the commit message, the major reasons for implementing
FTRACE_WITH_REGS were:
(1) To make it possible to use the ftrace graph tracer with pointer
authentication, where it's necessary to snapshot/manipulate the LR
before it is signed by the instrumented function.
(2) To make it possible to implement LIVEPATCH in future, where we need
to hook function entry before an instrumented function manipulates
the stack or argument registers. Practically speaking, we need to
preserve the argument/return registers, PC, LR, and SP.
Neither of these need a struct pt_regs, and only require the set of
registers which are live at function call/return boundaries. Our calling
convention is defined by "Procedure Call Standard for the Arm® 64-bit
Architecture (AArch64)" (AKA "AAPCS64"), which can currently be found
at:
https://github.com/ARM-software/abi-aa/blob/main/aapcs64/aapcs64.rst
Per AAPCS64, all function call argument and return values are held in
the following GPRs:
* X0 - X7 : parameter / result registers
* X8 : indirect result location register
* SP : stack pointer (AKA SP)
Additionally, ad function call boundaries, the following GPRs hold
context/return information:
* X29 : frame pointer (AKA FP)
* X30 : link register (AKA LR)
... and for ftrace we need to capture the instrumented address:
* PC : program counter
No other GPRs are relevant, as none of the other arguments hold
parameters or return values:
* X9 - X17 : temporaries, may be clobbered
* X18 : shadow call stack pointer (or temorary)
* X19 - X28 : callee saved
This patch implements FTRACE_WITH_ARGS for arm64, only saving/restoring
the minimal set of registers necessary. This is always sufficient to
manipulate control flow (e.g. for live-patching) or to manipulate
function arguments and return values.
This reduces the necessary stack usage from 336 bytes for pt_regs down
to 112 bytes for ftrace_regs + 32 bytes for two frame records, freeing
up 188 bytes. This could be reduced further with changes to the
unwinder.
As there is no longer a need to save different sets of registers for
different features, we no longer need distinct `ftrace_caller` and
`ftrace_regs_caller` trampolines. This allows the trampoline assembly to
be simpler, and simplifies code which previously had to handle the two
trampolines.
I've tested this with the ftrace selftests, where there are no
unexpected failures.
Co-developed-by: Florent Revest <[email protected]>
Signed-off-by: Mark Rutland <[email protected]>
Signed-off-by: Florent Revest <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Masami Hiramatsu <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Will Deacon <[email protected]>
Reviewed-by: Masami Hiramatsu (Google) <[email protected]>
Reviewed-by: Steven Rostedt (Google) <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>
216 lines
7.1 KiB
Makefile
216 lines
7.1 KiB
Makefile
#
|
|
# arch/arm64/Makefile
|
|
#
|
|
# This file is included by the global makefile so that you can add your own
|
|
# architecture-specific flags and dependencies.
|
|
#
|
|
# 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) 1995-2001 by Russell King
|
|
|
|
LDFLAGS_vmlinux :=--no-undefined -X
|
|
|
|
ifeq ($(CONFIG_RELOCATABLE), y)
|
|
# Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour
|
|
# for relative relocs, since this leads to better Image compression
|
|
# with the relocation offsets always being zero.
|
|
LDFLAGS_vmlinux += -shared -Bsymbolic -z notext \
|
|
$(call ld-option, --no-apply-dynamic-relocs)
|
|
endif
|
|
|
|
ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
|
|
ifeq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y)
|
|
LDFLAGS_vmlinux += --fix-cortex-a53-843419
|
|
endif
|
|
endif
|
|
|
|
cc_has_k_constraint := $(call try-run,echo \
|
|
'int main(void) { \
|
|
asm volatile("and w0, w0, %w0" :: "K" (4294967295)); \
|
|
return 0; \
|
|
}' | $(CC) -S -x c -o "$$TMP" -,,-DCONFIG_CC_HAS_K_CONSTRAINT=1)
|
|
|
|
ifeq ($(CONFIG_BROKEN_GAS_INST),y)
|
|
$(warning Detected assembler with broken .inst; disassembly will be unreliable)
|
|
endif
|
|
|
|
KBUILD_CFLAGS += -mgeneral-regs-only \
|
|
$(compat_vdso) $(cc_has_k_constraint)
|
|
KBUILD_CFLAGS += $(call cc-disable-warning, psabi)
|
|
KBUILD_AFLAGS += $(compat_vdso)
|
|
|
|
KBUILD_CFLAGS += $(call cc-option,-mabi=lp64)
|
|
KBUILD_AFLAGS += $(call cc-option,-mabi=lp64)
|
|
|
|
# Avoid generating .eh_frame* sections.
|
|
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
|
|
KBUILD_AFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
|
|
|
|
ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y)
|
|
prepare: stack_protector_prepare
|
|
stack_protector_prepare: prepare0
|
|
$(eval KBUILD_CFLAGS += -mstack-protector-guard=sysreg \
|
|
-mstack-protector-guard-reg=sp_el0 \
|
|
-mstack-protector-guard-offset=$(shell \
|
|
awk '{if ($$2 == "TSK_STACK_CANARY") print $$3;}' \
|
|
include/generated/asm-offsets.h))
|
|
endif
|
|
|
|
ifeq ($(CONFIG_AS_HAS_ARMV8_2), y)
|
|
# make sure to pass the newest target architecture to -march.
|
|
asm-arch := armv8.2-a
|
|
endif
|
|
|
|
# Ensure that if the compiler supports branch protection we default it
|
|
# off, this will be overridden if we are using branch protection.
|
|
branch-prot-flags-y += $(call cc-option,-mbranch-protection=none)
|
|
|
|
ifeq ($(CONFIG_ARM64_PTR_AUTH_KERNEL),y)
|
|
branch-prot-flags-$(CONFIG_CC_HAS_SIGN_RETURN_ADDRESS) := -msign-return-address=all
|
|
# We enable additional protection for leaf functions as there is some
|
|
# narrow potential for ROP protection benefits and no substantial
|
|
# performance impact has been observed.
|
|
ifeq ($(CONFIG_ARM64_BTI_KERNEL),y)
|
|
branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET_BTI) := -mbranch-protection=pac-ret+leaf+bti
|
|
else
|
|
branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=pac-ret+leaf
|
|
endif
|
|
# -march=armv8.3-a enables the non-nops instructions for PAC, to avoid the
|
|
# compiler to generate them and consequently to break the single image contract
|
|
# we pass it only to the assembler. This option is utilized only in case of non
|
|
# integrated assemblers.
|
|
ifeq ($(CONFIG_AS_HAS_PAC), y)
|
|
asm-arch := armv8.3-a
|
|
endif
|
|
endif
|
|
|
|
KBUILD_CFLAGS += $(branch-prot-flags-y)
|
|
|
|
ifeq ($(CONFIG_AS_HAS_ARMV8_4), y)
|
|
# make sure to pass the newest target architecture to -march.
|
|
asm-arch := armv8.4-a
|
|
endif
|
|
|
|
ifeq ($(CONFIG_AS_HAS_ARMV8_5), y)
|
|
# make sure to pass the newest target architecture to -march.
|
|
asm-arch := armv8.5-a
|
|
endif
|
|
|
|
ifdef asm-arch
|
|
KBUILD_CFLAGS += -Wa,-march=$(asm-arch) \
|
|
-DARM64_ASM_ARCH='"$(asm-arch)"'
|
|
endif
|
|
|
|
ifeq ($(CONFIG_SHADOW_CALL_STACK), y)
|
|
KBUILD_CFLAGS += -ffixed-x18
|
|
endif
|
|
|
|
ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
|
|
KBUILD_CPPFLAGS += -mbig-endian
|
|
CHECKFLAGS += -D__AARCH64EB__
|
|
# Prefer the baremetal ELF build target, but not all toolchains include
|
|
# it so fall back to the standard linux version if needed.
|
|
KBUILD_LDFLAGS += -EB $(call ld-option, -maarch64elfb, -maarch64linuxb -z norelro)
|
|
UTS_MACHINE := aarch64_be
|
|
else
|
|
KBUILD_CPPFLAGS += -mlittle-endian
|
|
CHECKFLAGS += -D__AARCH64EL__
|
|
# Same as above, prefer ELF but fall back to linux target if needed.
|
|
KBUILD_LDFLAGS += -EL $(call ld-option, -maarch64elf, -maarch64linux -z norelro)
|
|
UTS_MACHINE := aarch64
|
|
endif
|
|
|
|
ifeq ($(CONFIG_LD_IS_LLD), y)
|
|
KBUILD_LDFLAGS += -z norelro
|
|
endif
|
|
|
|
CHECKFLAGS += -D__aarch64__
|
|
|
|
ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_ARGS),y)
|
|
KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
|
|
CC_FLAGS_FTRACE := -fpatchable-function-entry=2
|
|
endif
|
|
|
|
ifeq ($(CONFIG_KASAN_SW_TAGS), y)
|
|
KASAN_SHADOW_SCALE_SHIFT := 4
|
|
else ifeq ($(CONFIG_KASAN_GENERIC), y)
|
|
KASAN_SHADOW_SCALE_SHIFT := 3
|
|
endif
|
|
|
|
KBUILD_CFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT)
|
|
KBUILD_CPPFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT)
|
|
KBUILD_AFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT)
|
|
|
|
libs-y := arch/arm64/lib/ $(libs-y)
|
|
libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
|
|
|
|
# Default target when executing plain make
|
|
boot := arch/arm64/boot
|
|
|
|
ifeq ($(CONFIG_EFI_ZBOOT),)
|
|
KBUILD_IMAGE := $(boot)/Image.gz
|
|
else
|
|
KBUILD_IMAGE := $(boot)/vmlinuz.efi
|
|
endif
|
|
|
|
all: $(notdir $(KBUILD_IMAGE))
|
|
|
|
|
|
Image vmlinuz.efi: vmlinux
|
|
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
|
|
|
|
Image.%: Image
|
|
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
|
|
|
|
install: KBUILD_IMAGE := $(boot)/Image
|
|
install zinstall:
|
|
$(call cmd,install)
|
|
|
|
PHONY += vdso_install
|
|
vdso_install:
|
|
$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@
|
|
$(if $(CONFIG_COMPAT_VDSO), \
|
|
$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@)
|
|
|
|
archprepare:
|
|
$(Q)$(MAKE) $(build)=arch/arm64/tools kapi
|
|
ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
|
|
ifneq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y)
|
|
@echo "warning: ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum" >&2
|
|
endif
|
|
endif
|
|
ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS),y)
|
|
ifneq ($(CONFIG_ARM64_LSE_ATOMICS),y)
|
|
@echo "warning: LSE atomics not supported by binutils" >&2
|
|
endif
|
|
endif
|
|
|
|
ifeq ($(KBUILD_EXTMOD),)
|
|
# We need to generate vdso-offsets.h before compiling certain files in kernel/.
|
|
# In order to do that, we should use the archprepare target, but we can't since
|
|
# asm-offsets.h is included in some files used to generate vdso-offsets.h, and
|
|
# asm-offsets.h is built in prepare0, for which archprepare is a dependency.
|
|
# Therefore we need to generate the header after prepare0 has been made, hence
|
|
# this hack.
|
|
prepare: vdso_prepare
|
|
vdso_prepare: prepare0
|
|
$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso \
|
|
include/generated/vdso-offsets.h arch/arm64/kernel/vdso/vdso.so
|
|
ifdef CONFIG_COMPAT_VDSO
|
|
$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 \
|
|
include/generated/vdso32-offsets.h arch/arm64/kernel/vdso32/vdso.so
|
|
endif
|
|
endif
|
|
|
|
define archhelp
|
|
echo '* Image.gz - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)'
|
|
echo ' Image - Uncompressed kernel image (arch/$(ARCH)/boot/Image)'
|
|
echo ' install - Install uncompressed kernel'
|
|
echo ' zinstall - Install compressed kernel'
|
|
echo ' Install using (your) ~/bin/installkernel or'
|
|
echo ' (distribution) /sbin/installkernel or'
|
|
echo ' install to $$(INSTALL_PATH) and run lilo'
|
|
endef
|