linux/arch/arm64/kernel/entry-ftrace.S
Mark Brown 742a15b1a2 arm64: Use BTI C directly and unconditionally
Now we have a macro for BTI C that looks like a regular instruction change
all the users of the current BTI_C macro to just emit a BTI C directly and
remove the macro.

This does mean that we now unconditionally BTI annotate all assembly
functions, meaning that they are worse in this respect than code generated
by the compiler. The overhead should be minimal for implementations with a
reasonable HINT implementation.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20211214152714.2380849-4-broonie@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2021-12-14 18:12:58 +00:00

348 lines
9.6 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* arch/arm64/kernel/entry-ftrace.S
*
* Copyright (C) 2013 Linaro Limited
* Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
*/
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#include <asm/assembler.h>
#include <asm/ftrace.h>
#include <asm/insn.h>
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
/*
* Due to -fpatchable-function-entry=2, the compiler has placed two NOPs before
* the regular function prologue. For an enabled callsite, ftrace_init_nop() and
* ftrace_make_call() have patched those NOPs to:
*
* MOV X9, LR
* BL <entry>
*
* ... where <entry> is either ftrace_caller or ftrace_regs_caller.
*
* Each instrumented function follows the AAPCS, so here x0-x8 and x18-x30 are
* live (x18 holds the Shadow Call Stack pointer), and x9-x17 are safe to
* clobber.
*
* We save the callsite's context into a pt_regs before invoking any ftrace
* callbacks. So that we can get a sensible backtrace, we create a stack record
* for the callsite and the ftrace entry assembly. This is not sufficient for
* reliable stacktrace: until we create the callsite stack record, its caller
* is missing from the LR and existing chain of frame records.
*/
.macro ftrace_regs_entry, allregs=0
/* Make room for pt_regs, plus a callee frame */
sub sp, sp, #(PT_REGS_SIZE + 16)
/* Save function arguments (and x9 for simplicity) */
stp x0, x1, [sp, #S_X0]
stp x2, x3, [sp, #S_X2]
stp x4, x5, [sp, #S_X4]
stp x6, x7, [sp, #S_X6]
stp x8, x9, [sp, #S_X8]
/* Optionally save the callee-saved registers, always save the FP */
.if \allregs == 1
stp x10, x11, [sp, #S_X10]
stp x12, x13, [sp, #S_X12]
stp x14, x15, [sp, #S_X14]
stp x16, x17, [sp, #S_X16]
stp x18, x19, [sp, #S_X18]
stp x20, x21, [sp, #S_X20]
stp x22, x23, [sp, #S_X22]
stp x24, x25, [sp, #S_X24]
stp x26, x27, [sp, #S_X26]
stp x28, x29, [sp, #S_X28]
.else
str x29, [sp, #S_FP]
.endif
/* Save the callsite's SP and LR */
add x10, sp, #(PT_REGS_SIZE + 16)
stp x9, x10, [sp, #S_LR]
/* Save the PC after the ftrace callsite */
str x30, [sp, #S_PC]
/* Create a frame record for the callsite above pt_regs */
stp x29, x9, [sp, #PT_REGS_SIZE]
add x29, sp, #PT_REGS_SIZE
/* Create our frame record within pt_regs. */
stp x29, x30, [sp, #S_STACKFRAME]
add x29, sp, #S_STACKFRAME
.endm
SYM_CODE_START(ftrace_regs_caller)
bti c
ftrace_regs_entry 1
b ftrace_common
SYM_CODE_END(ftrace_regs_caller)
SYM_CODE_START(ftrace_caller)
bti c
ftrace_regs_entry 0
b ftrace_common
SYM_CODE_END(ftrace_caller)
SYM_CODE_START(ftrace_common)
sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn)
mov x1, x9 // parent_ip (callsite's LR)
ldr_l x2, function_trace_op // op
mov x3, sp // regs
SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
bl ftrace_stub
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller();
nop // If enabled, this will be replaced
// "b ftrace_graph_caller"
#endif
/*
* At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved
* x19-x29 per the AAPCS, and we created frame records upon entry, so we need
* to restore x0-x8, x29, and x30.
*/
ftrace_common_return:
/* Restore function arguments */
ldp x0, x1, [sp]
ldp x2, x3, [sp, #S_X2]
ldp x4, x5, [sp, #S_X4]
ldp x6, x7, [sp, #S_X6]
ldr x8, [sp, #S_X8]
/* Restore the callsite's FP, LR, PC */
ldr x29, [sp, #S_FP]
ldr x30, [sp, #S_LR]
ldr x9, [sp, #S_PC]
/* Restore the callsite's SP */
add sp, sp, #PT_REGS_SIZE + 16
ret x9
SYM_CODE_END(ftrace_common)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
SYM_CODE_START(ftrace_graph_caller)
ldr x0, [sp, #S_PC]
sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn)
add x1, sp, #S_LR // parent_ip (callsite's LR)
ldr x2, [sp, #PT_REGS_SIZE] // parent fp (callsite's FP)
bl prepare_ftrace_return
b ftrace_common_return
SYM_CODE_END(ftrace_graph_caller)
#endif
#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
/*
* Gcc with -pg will put the following code in the beginning of each function:
* mov x0, x30
* bl _mcount
* [function's body ...]
* "bl _mcount" may be replaced to "bl ftrace_caller" or NOP if dynamic
* ftrace is enabled.
*
* Please note that x0 as an argument will not be used here because we can
* get lr(x30) of instrumented function at any time by winding up call stack
* as long as the kernel is compiled without -fomit-frame-pointer.
* (or CONFIG_FRAME_POINTER, this is forced on arm64)
*
* stack layout after mcount_enter in _mcount():
*
* current sp/fp => 0:+-----+
* in _mcount() | x29 | -> instrumented function's fp
* +-----+
* | x30 | -> _mcount()'s lr (= instrumented function's pc)
* old sp => +16:+-----+
* when instrumented | |
* function calls | ... |
* _mcount() | |
* | |
* instrumented => +xx:+-----+
* function's fp | x29 | -> parent's fp
* +-----+
* | x30 | -> instrumented function's lr (= parent's pc)
* +-----+
* | ... |
*/
.macro mcount_enter
stp x29, x30, [sp, #-16]!
mov x29, sp
.endm
.macro mcount_exit
ldp x29, x30, [sp], #16
ret
.endm
.macro mcount_adjust_addr rd, rn
sub \rd, \rn, #AARCH64_INSN_SIZE
.endm
/* for instrumented function's parent */
.macro mcount_get_parent_fp reg
ldr \reg, [x29]
ldr \reg, [\reg]
.endm
/* for instrumented function */
.macro mcount_get_pc0 reg
mcount_adjust_addr \reg, x30
.endm
.macro mcount_get_pc reg
ldr \reg, [x29, #8]
mcount_adjust_addr \reg, \reg
.endm
.macro mcount_get_lr reg
ldr \reg, [x29]
ldr \reg, [\reg, #8]
.endm
.macro mcount_get_lr_addr reg
ldr \reg, [x29]
add \reg, \reg, #8
.endm
#ifndef CONFIG_DYNAMIC_FTRACE
/*
* void _mcount(unsigned long return_address)
* @return_address: return address to instrumented function
*
* This function makes calls, if enabled, to:
* - tracer function to probe instrumented function's entry,
* - ftrace_graph_caller to set up an exit hook
*/
SYM_FUNC_START(_mcount)
mcount_enter
ldr_l x2, ftrace_trace_function
adr x0, ftrace_stub
cmp x0, x2 // if (ftrace_trace_function
b.eq skip_ftrace_call // != ftrace_stub) {
mcount_get_pc x0 // function's pc
mcount_get_lr x1 // function's lr (= parent's pc)
blr x2 // (*ftrace_trace_function)(pc, lr);
skip_ftrace_call: // }
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ldr_l x2, ftrace_graph_return
cmp x0, x2 // if ((ftrace_graph_return
b.ne ftrace_graph_caller // != ftrace_stub)
ldr_l x2, ftrace_graph_entry // || (ftrace_graph_entry
adr_l x0, ftrace_graph_entry_stub // != ftrace_graph_entry_stub))
cmp x0, x2
b.ne ftrace_graph_caller // ftrace_graph_caller();
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
mcount_exit
SYM_FUNC_END(_mcount)
EXPORT_SYMBOL(_mcount)
NOKPROBE(_mcount)
#else /* CONFIG_DYNAMIC_FTRACE */
/*
* _mcount() is used to build the kernel with -pg option, but all the branch
* instructions to _mcount() are replaced to NOP initially at kernel start up,
* and later on, NOP to branch to ftrace_caller() when enabled or branch to
* NOP when disabled per-function base.
*/
SYM_FUNC_START(_mcount)
ret
SYM_FUNC_END(_mcount)
EXPORT_SYMBOL(_mcount)
NOKPROBE(_mcount)
/*
* void ftrace_caller(unsigned long return_address)
* @return_address: return address to instrumented function
*
* This function is a counterpart of _mcount() in 'static' ftrace, and
* makes calls to:
* - tracer function to probe instrumented function's entry,
* - ftrace_graph_caller to set up an exit hook
*/
SYM_FUNC_START(ftrace_caller)
mcount_enter
mcount_get_pc0 x0 // function's pc
mcount_get_lr x1 // function's lr
SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) // tracer(pc, lr);
nop // This will be replaced with "bl xxx"
// where xxx can be any kind of tracer.
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller();
nop // If enabled, this will be replaced
// "b ftrace_graph_caller"
#endif
mcount_exit
SYM_FUNC_END(ftrace_caller)
#endif /* CONFIG_DYNAMIC_FTRACE */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/*
* void ftrace_graph_caller(void)
*
* Called from _mcount() or ftrace_caller() when function_graph tracer is
* selected.
* This function w/ prepare_ftrace_return() fakes link register's value on
* the call stack in order to intercept instrumented function's return path
* and run return_to_handler() later on its exit.
*/
SYM_FUNC_START(ftrace_graph_caller)
mcount_get_pc x0 // function's pc
mcount_get_lr_addr x1 // pointer to function's saved lr
mcount_get_parent_fp x2 // parent's fp
bl prepare_ftrace_return // prepare_ftrace_return(pc, &lr, fp)
mcount_exit
SYM_FUNC_END(ftrace_graph_caller)
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
SYM_FUNC_START(ftrace_stub)
ret
SYM_FUNC_END(ftrace_stub)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/*
* void return_to_handler(void)
*
* Run ftrace_return_to_handler() before going back to parent.
* @fp is checked against the value passed by ftrace_graph_caller().
*/
SYM_CODE_START(return_to_handler)
/* save return value regs */
sub sp, sp, #64
stp x0, x1, [sp]
stp x2, x3, [sp, #16]
stp x4, x5, [sp, #32]
stp x6, x7, [sp, #48]
mov x0, x29 // parent's fp
bl ftrace_return_to_handler// addr = ftrace_return_to_hander(fp);
mov x30, x0 // restore the original return address
/* restore return value regs */
ldp x0, x1, [sp]
ldp x2, x3, [sp, #16]
ldp x4, x5, [sp, #32]
ldp x6, x7, [sp, #48]
add sp, sp, #64
ret
SYM_CODE_END(return_to_handler)
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */