microsoft
/
WSL2-Linux-Kernel
зеркало из https://github.com/microsoft/WSL2-Linux-Kernel.git
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность

Merge patch series "riscv: Optimize function trace" 

guoren@kernel.org <guoren@kernel.org> says:

From: Guo Ren <guoren@linux.alibaba.com>

The previous ftrace detour implementation fc76b8b8011 ("riscv: Using
PATCHABLE_FUNCTION_ENTRY instead of MCOUNT") contain three problems.

 - The most horrible bug is preemption panic which found by Andy [1].
   Let's disable preemption for ftrace first, and Andy could continue
   the ftrace preemption work.
 - The "-fpatchable-function-entry= CFLAG" wasted code size
   !RISCV_ISA_C.
 - The ftrace detour implementation wasted code size.
 - When livepatching, the trampoline (ftrace_regs_caller) would not
   return to <func_prolog+12> but would rather jump to the new function.
   So, "REG_L ra, -SZREG(sp)" would not run and the original return
   address would not be restored. The kernel is likely to hang or crash
   as a result. (Found by Evgenii Shatokhin [4])

[Palmer: The first three patches in this series are pretty concrete
fixes, so I'm pulling them ahead of the rest of the series.]

* b4-shazam-merge:
  riscv: ftrace: Reduce the detour code size to half
  riscv: ftrace: Remove wasted nops for !RISCV_ISA_C
  riscv: ftrace: Fixup panic by disabling preemption

Link: https://lore.kernel.org/r/20230112090603.1295340-1-guoren@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
This commit is contained in:
Palmer Dabbelt 2023-02-15 10:57:13 -08:00
Родитель 9a5c09dd97 6724a76cff
Коммит ec6311919e
Не найден ключ, соответствующий данной подписи
Идентификатор ключа GPG: 2E1319F35FBB1889
5 изменённых файлов: 79 добавлений и 86 удалений
Показать статистику Скачать Patch файл Скачать Diff файл Показать все файлы Свернуть все файлы

2
arch/riscv/Kconfig
Просмотреть файл

@ -138,7 +138,7 @@ config RISCV
select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER if !XIP_KERNEL
select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION
config ARCH_MMAP_RND_BITS_MIN
default 18 if 64BIT

6
arch/riscv/Makefile
Просмотреть файл

@ -11,7 +11,11 @@ LDFLAGS_vmlinux :=
ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
LDFLAGS_vmlinux := --no-relax
KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
CC_FLAGS_FTRACE := -fpatchable-function-entry=8
ifeq ($(CONFIG_RISCV_ISA_C),y)
CC_FLAGS_FTRACE := -fpatchable-function-entry=4
else
CC_FLAGS_FTRACE := -fpatchable-function-entry=2
endif
endif
ifeq ($(CONFIG_CMODEL_MEDLOW),y)

50
arch/riscv/include/asm/ftrace.h
Просмотреть файл

@ -42,6 +42,14 @@ struct dyn_arch_ftrace {
* 2) jalr: setting low-12 offset to ra, jump to ra, and set ra to
* return address (original pc + 4)
*
*<ftrace enable>:
* 0: auipc t0/ra, 0x?
* 4: jalr t0/ra, ?(t0/ra)
*
*<ftrace disable>:
* 0: nop
* 4: nop
*
* Dynamic ftrace generates probes to call sites, so we must deal with
* both auipc and jalr at the same time.
*/
@ -52,25 +60,43 @@ struct dyn_arch_ftrace {
#define AUIPC_OFFSET_MASK (0xfffff000)
#define AUIPC_PAD (0x00001000)
#define JALR_SHIFT 20
#define JALR_BASIC (0x000080e7)
#define AUIPC_BASIC (0x00000097)
#define JALR_RA (0x000080e7)
#define AUIPC_RA (0x00000097)
#define JALR_T0 (0x000282e7)
#define AUIPC_T0 (0x00000297)
#define NOP4 (0x00000013)
#define make_call(caller, callee, call) \
#define to_jalr_t0(offset) \
(((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_T0)
#define to_auipc_t0(offset) \
((offset & JALR_SIGN_MASK) ? \
(((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_T0) : \
((offset & AUIPC_OFFSET_MASK) | AUIPC_T0))
#define make_call_t0(caller, callee, call) \
do { \
call[0] = to_auipc_insn((unsigned int)((unsigned long)callee - \
(unsigned long)caller)); \
call[1] = to_jalr_insn((unsigned int)((unsigned long)callee - \
(unsigned long)caller)); \
unsigned int offset = \
(unsigned long) callee - (unsigned long) caller; \
call[0] = to_auipc_t0(offset); \
call[1] = to_jalr_t0(offset); \
} while (0)
#define to_jalr_insn(offset) \
(((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_BASIC)
#define to_jalr_ra(offset) \
(((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_RA)
#define to_auipc_insn(offset) \
#define to_auipc_ra(offset) \
((offset & JALR_SIGN_MASK) ? \
(((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_BASIC) : \
((offset & AUIPC_OFFSET_MASK) | AUIPC_BASIC))
(((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_RA) : \
((offset & AUIPC_OFFSET_MASK) | AUIPC_RA))
#define make_call_ra(caller, callee, call) \
do { \
unsigned int offset = \
(unsigned long) callee - (unsigned long) caller; \
call[0] = to_auipc_ra(offset); \
call[1] = to_jalr_ra(offset); \
} while (0)
/*
* Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here.

65
arch/riscv/kernel/ftrace.c
Просмотреть файл

@ -55,12 +55,15 @@ static int ftrace_check_current_call(unsigned long hook_pos,
}
static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target,
bool enable)
bool enable, bool ra)
{
unsigned int call[2];
unsigned int nops[2] = {NOP4, NOP4};
make_call(hook_pos, target, call);
if (ra)
make_call_ra(hook_pos, target, call);
else
make_call_t0(hook_pos, target, call);
/* Replace the auipc-jalr pair at once. Return -EPERM on write error. */
if (patch_text_nosync
@ -70,42 +73,13 @@ static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target,
return 0;
}
/*
* Put 5 instructions with 16 bytes at the front of function within
* patchable function entry nops' area.
*
* 0: REG_S ra, -SZREG(sp)
* 1: auipc ra, 0x?
* 2: jalr -?(ra)
* 3: REG_L ra, -SZREG(sp)
*
* So the opcodes is:
* 0: 0xfe113c23 (sd)/0xfe112e23 (sw)
* 1: 0x???????? -> auipc
* 2: 0x???????? -> jalr
* 3: 0xff813083 (ld)/0xffc12083 (lw)
*/
#if __riscv_xlen == 64
#define INSN0 0xfe113c23
#define INSN3 0xff813083
#elif __riscv_xlen == 32
#define INSN0 0xfe112e23
#define INSN3 0xffc12083
#endif
#define FUNC_ENTRY_SIZE 16
#define FUNC_ENTRY_JMP 4
int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned int call[4] = {INSN0, 0, 0, INSN3};
unsigned long target = addr;
unsigned long caller = rec->ip + FUNC_ENTRY_JMP;
unsigned int call[2];
call[1] = to_auipc_insn((unsigned int)(target - caller));
call[2] = to_jalr_insn((unsigned int)(target - caller));
make_call_t0(rec->ip, addr, call);
if (patch_text_nosync((void *)rec->ip, call, FUNC_ENTRY_SIZE))
if (patch_text_nosync((void *)rec->ip, call, MCOUNT_INSN_SIZE))
return -EPERM;
return 0;
@ -114,15 +88,14 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
unsigned long addr)
{
unsigned int nops[4] = {NOP4, NOP4, NOP4, NOP4};
unsigned int nops[2] = {NOP4, NOP4};
if (patch_text_nosync((void *)rec->ip, nops, FUNC_ENTRY_SIZE))
if (patch_text_nosync((void *)rec->ip, nops, MCOUNT_INSN_SIZE))
return -EPERM;
return 0;
}
/*
* This is called early on, and isn't wrapped by
* ftrace_arch_code_modify_{prepare,post_process}() and therefor doesn't hold
@ -144,10 +117,10 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
int ftrace_update_ftrace_func(ftrace_func_t func)
{
int ret = __ftrace_modify_call((unsigned long)&ftrace_call,
(unsigned long)func, true);
(unsigned long)func, true, true);
if (!ret) {
ret = __ftrace_modify_call((unsigned long)&ftrace_regs_call,
(unsigned long)func, true);
(unsigned long)func, true, true);
}
return ret;
@ -159,16 +132,16 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr)
{
unsigned int call[2];
unsigned long caller = rec->ip + FUNC_ENTRY_JMP;
unsigned long caller = rec->ip;
int ret;
make_call(caller, old_addr, call);
make_call_t0(caller, old_addr, call);
ret = ftrace_check_current_call(caller, call);
if (ret)
return ret;
return __ftrace_modify_call(caller, addr, true);
return __ftrace_modify_call(caller, addr, true, false);
}
#endif
@ -203,12 +176,12 @@ int ftrace_enable_ftrace_graph_caller(void)
int ret;
ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
(unsigned long)&prepare_ftrace_return, true);
(unsigned long)&prepare_ftrace_return, true, true);
if (ret)
return ret;
return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
(unsigned long)&prepare_ftrace_return, true);
(unsigned long)&prepare_ftrace_return, true, true);
}
int ftrace_disable_ftrace_graph_caller(void)
@ -216,12 +189,12 @@ int ftrace_disable_ftrace_graph_caller(void)
int ret;
ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
(unsigned long)&prepare_ftrace_return, false);
(unsigned long)&prepare_ftrace_return, false, true);
if (ret)
return ret;
return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
(unsigned long)&prepare_ftrace_return, false);
(unsigned long)&prepare_ftrace_return, false, true);
}
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */

42
arch/riscv/kernel/mcount-dyn.S
Просмотреть файл

@ -13,8 +13,8 @@
.text
#define FENTRY_RA_OFFSET 12
#define ABI_SIZE_ON_STACK 72
#define FENTRY_RA_OFFSET 8
#define ABI_SIZE_ON_STACK 80
#define ABI_A0 0
#define ABI_A1 8
#define ABI_A2 16
@ -23,10 +23,10 @@
#define ABI_A5 40
#define ABI_A6 48
#define ABI_A7 56
#define ABI_RA 64
#define ABI_T0 64
#define ABI_RA 72
.macro SAVE_ABI
addi sp, sp, -SZREG
addi sp, sp, -ABI_SIZE_ON_STACK
REG_S a0, ABI_A0(sp)
@ -37,6 +37,7 @@
REG_S a5, ABI_A5(sp)
REG_S a6, ABI_A6(sp)
REG_S a7, ABI_A7(sp)
REG_S t0, ABI_T0(sp)
REG_S ra, ABI_RA(sp)
.endm
@ -49,24 +50,18 @@
REG_L a5, ABI_A5(sp)
REG_L a6, ABI_A6(sp)
REG_L a7, ABI_A7(sp)
REG_L t0, ABI_T0(sp)
REG_L ra, ABI_RA(sp)
addi sp, sp, ABI_SIZE_ON_STACK
addi sp, sp, SZREG
.endm
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
.macro SAVE_ALL
addi sp, sp, -SZREG
addi sp, sp, -PT_SIZE_ON_STACK
REG_S x1, PT_EPC(sp)
addi sp, sp, PT_SIZE_ON_STACK
REG_L x1, (sp)
addi sp, sp, -PT_SIZE_ON_STACK
REG_S t0, PT_EPC(sp)
REG_S x1, PT_RA(sp)
REG_L x1, PT_EPC(sp)
REG_S x2, PT_SP(sp)
REG_S x3, PT_GP(sp)
REG_S x4, PT_TP(sp)
@ -100,15 +95,11 @@
.endm
.macro RESTORE_ALL
REG_L t0, PT_EPC(sp)
REG_L x1, PT_RA(sp)
addi sp, sp, PT_SIZE_ON_STACK
REG_S x1, (sp)
addi sp, sp, -PT_SIZE_ON_STACK
REG_L x1, PT_EPC(sp)
REG_L x2, PT_SP(sp)
REG_L x3, PT_GP(sp)
REG_L x4, PT_TP(sp)
REG_L x5, PT_T0(sp)
REG_L x6, PT_T1(sp)
REG_L x7, PT_T2(sp)
REG_L x8, PT_S0(sp)
@ -137,17 +128,16 @@
REG_L x31, PT_T6(sp)
addi sp, sp, PT_SIZE_ON_STACK
addi sp, sp, SZREG
.endm
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
ENTRY(ftrace_caller)
SAVE_ABI
addi a0, ra, -FENTRY_RA_OFFSET
addi a0, t0, -FENTRY_RA_OFFSET
la a1, function_trace_op
REG_L a2, 0(a1)
REG_L a1, ABI_SIZE_ON_STACK(sp)
mv a1, ra
mv a3, sp
ftrace_call:
@ -155,8 +145,8 @@ ftrace_call:
call ftrace_stub
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
addi a0, sp, ABI_SIZE_ON_STACK
REG_L a1, ABI_RA(sp)
addi a0, sp, ABI_RA
REG_L a1, ABI_T0(sp)
addi a1, a1, -FENTRY_RA_OFFSET
#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
mv a2, s0
@ -166,17 +156,17 @@ ftrace_graph_call:
call ftrace_stub
#endif
RESTORE_ABI
ret
jr t0
ENDPROC(ftrace_caller)
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
ENTRY(ftrace_regs_caller)
SAVE_ALL
addi a0, ra, -FENTRY_RA_OFFSET
addi a0, t0, -FENTRY_RA_OFFSET
la a1, function_trace_op
REG_L a2, 0(a1)
REG_L a1, PT_SIZE_ON_STACK(sp)
mv a1, ra
mv a3, sp
ftrace_regs_call:
@ -196,6 +186,6 @@ ftrace_graph_regs_call:
#endif
RESTORE_ALL
ret
jr t0
ENDPROC(ftrace_regs_caller)
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */