[PATCH RFC v2 riscv/for-next 3/5] riscv: ftrace: use indirect jump to work with kernel preemption
Evgenii Shatokhin
e.shatokhin at yadro.com
Tue Feb 20 06:17:02 PST 2024
Hi,
On 13.09.2022 12:42, Andy Chiu wrote:
> In RISCV, we must use an AUIPC + JALR pair to encode an immediate,
> forming a jump that jumps to an address over 4K. This may cause errors
> if we want to enable kernel preemption and remove dependency from
> patching code with stop_machine(). For example, if a task was switched
> out on auipc. And, if we changed the ftrace function before it was
> switched back, then it would jump to an address that has updated 11:0
> bits mixing with previous XLEN:12 part.
>
> p: patched area performed by dynamic ftrace
> ftrace_prologue:
> p| REG_S ra, -SZREG(sp)
> p| auipc ra, 0x? ------------> preempted
> ...
> change ftrace function
> ...
> p| jalr -?(ra) <------------- switched back
> p| REG_L ra, -SZREG(sp)
> func:
> xxx
> ret
>
> To prevent such condition, we proposed a way to load or store target
> addresses atomically. We store a 8 bytes aligned full-width absolute
> address into each ftrace prologue and use a jump at front to decide
> whether we should take ftrace detour. To reduce footprint of ftrace
> prologues, we clobber t0, and we move ra (re-)storing into
> ftrace_{regs_}caller. This is similar to ARM64, which also clobbers x9 at
> each prologue.
>
> Also, we initialize the target at startup to take care of a case where
> REG_L happened before the update of the ftrace target.
>
> .align 2 # if it happen to be 8B-aligned
> ftrace_prologue:
> p| {j func} | {auipc t0}
> j ftrace_cont
> p| .dword 0x? <=== storing the address to a 8B aligned space can be
> considered atomic to read sides using REG_L
> ftrace_cont:
> REG_L t0, 8(t0) <=== read side
> jalr t0, t0
> func:
> xxx
> ret
>
> .align 2 # if it is 4B but not 8B-aligned
> ftrace_prologue:
> p| {j func} | {auipc t0}
> REG_L t0, 0xc(t0) <=== read side
> j ftrace_cont
> p| .dword 0x? <=== the target address
> ftrace_cont:
> jalr t0, t0
> func:
> xxx
> ret
>
> Signed-off-by: Andy Chiu <andy.chiu at sifive.com>
> Reviewed-by: Greentime Hu <greentime.hu at sifive.com>
> ---
> arch/riscv/include/asm/ftrace.h | 24 -----
> arch/riscv/kernel/ftrace.c | 173 ++++++++++++++++++++++----------
> arch/riscv/kernel/mcount-dyn.S | 69 ++++++++++---
> 3 files changed, 176 insertions(+), 90 deletions(-)
>
> diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
> index 04dad3380041..eaa611e491fc 100644
> --- a/arch/riscv/include/asm/ftrace.h
> +++ b/arch/riscv/include/asm/ftrace.h
> @@ -47,30 +47,6 @@ struct dyn_arch_ftrace {
> */
>
> #define MCOUNT_ADDR ((unsigned long)MCOUNT_NAME)
> -#define JALR_SIGN_MASK (0x00000800)
> -#define JALR_OFFSET_MASK (0x00000fff)
> -#define AUIPC_OFFSET_MASK (0xfffff000)
> -#define AUIPC_PAD (0x00001000)
> -#define JALR_SHIFT 20
> -#define JALR_BASIC (0x000080e7)
> -#define AUIPC_BASIC (0x00000097)
> -#define NOP4 (0x00000013)
> -
> -#define make_call(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)); \
> -} while (0)
> -
> -#define to_jalr_insn(offset) \
> - (((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_BASIC)
> -
> -#define to_auipc_insn(offset) \
> - ((offset & JALR_SIGN_MASK) ? \
> - (((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_BASIC) : \
> - ((offset & AUIPC_OFFSET_MASK) | AUIPC_BASIC))
>
> /*
> * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here.
> diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
> index 2086f6585773..84b9e280dd1f 100644
> --- a/arch/riscv/kernel/ftrace.c
> +++ b/arch/riscv/kernel/ftrace.c
> @@ -23,31 +23,29 @@ void ftrace_arch_code_modify_post_process(void) __releases(&text_mutex)
> }
>
> static int ftrace_check_current_call(unsigned long hook_pos,
> - unsigned int *expected)
> + unsigned long expected_addr)
> {
> - unsigned int replaced[2];
> - unsigned int nops[2] = {NOP4, NOP4};
> + unsigned long replaced;
>
> - /* we expect nops at the hook position */
> - if (!expected)
> - expected = nops;
> + /* we expect ftrace_stub at the hook position */
> + if (!expected_addr)
> + expected_addr = (unsigned long) ftrace_stub;
>
> /*
> * Read the text we want to modify;
> * return must be -EFAULT on read error
> */
> - if (copy_from_kernel_nofault(replaced, (void *)hook_pos,
> - MCOUNT_INSN_SIZE))
> + if (copy_from_kernel_nofault(&replaced, (void *)hook_pos,
> + (sizeof(unsigned long))))
> return -EFAULT;
>
> /*
> * Make sure it is what we expect it to be;
> * return must be -EINVAL on failed comparison
> */
> - if (memcmp(expected, replaced, sizeof(replaced))) {
> - pr_err("%p: expected (%08x %08x) but got (%08x %08x)\n",
> - (void *)hook_pos, expected[0], expected[1], replaced[0],
> - replaced[1]);
> + if (expected_addr != replaced) {
> + pr_err("%p: expected (%016lx) but got (%016lx)\n",
> + (void *)hook_pos, expected_addr, replaced);
> return -EINVAL;
> }
>
> @@ -57,55 +55,96 @@ static int ftrace_check_current_call(unsigned long hook_pos,
> static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target,
> bool enable)
> {
> - unsigned int call[2];
> - unsigned int nops[2] = {NOP4, NOP4};
> + unsigned long call = target;
> + unsigned long nops = (unsigned long)ftrace_stub;
>
> - make_call(hook_pos, target, call);
> -
> - /* Replace the auipc-jalr pair at once. Return -EPERM on write error. */
> + /* Replace the target address at once. Return -EPERM on write error. */
> if (patch_text_nosync
> - ((void *)hook_pos, enable ? call : nops, MCOUNT_INSN_SIZE))
> + ((void *)hook_pos, enable ? &call : &nops, sizeof(unsigned long)))
> return -EPERM;
>
> 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)
> + * Place 4 instructions and a destination address in the patchable function
> + * entry.
> *
> * So the opcodes is:
> - * 0: 0xfe113c23 (sd)/0xfe112e23 (sw)
> - * 1: 0x???????? -> auipc
> - * 2: 0x???????? -> jalr
> - * 3: 0xff813083 (ld)/0xffc12083 (lw)
> + * INSN_SKIPALL : J PC + 0x18 (when disabled, jump to the function)
> + * INSN_AUIPC : AUIPC T0, 0 (when enabled, load address of trampoline)
> + * INSN_LOAD(off): REG_L T0, off(T0) (load address stored in the tramp)
> + * INSN_SKIPTRAMP: J PC + 0x10 (skip tramp since they are not instructions)
> + * INSN_JALR : JALR T0, T0 (jump to the destination)
> + *
> + * At runtime, we want to patch the jump target atomically in order to work with
> + * kernel preemption. If we patched with a pair of AUIPC + JALR and a task was
> + * preempted after loading upper bits with AUIPC. Then things would mess up if
> + * we updated the jump target before the task were switched back.
> + *
> + * We also want to align all patchable function entries to 4-byte boundaries and,
> + * the jump target to a 8 Bytes aligned address so that each of them could be
> + * natually updated and observed by patching and running cores.
> + *
> + * To make sure target addresses are 8-byte aligned, we have to consider
> + * following scenarios:
> + *
> + * First if the starting address of the patchable entry is aligned to an 8-byte
> + * boundary:
> + * | ADDR | COMPILED | DISABLED | ENABLED |
> + * +--------+----------+------------------+------------------------+
> + * | 0x00 | NOP | J FUNC | AUIPC T0, 0 |
> + * | 0x04 | NOP | J 0x10 |
> + * | 0x08 | NOP | 8-byte aligned target address (low) |
> + * | 0x0C | NOP | (high) |
> + * | 0x10 | NOP | REG_L T0, 8(T0) |
> + * | 0x14 | NOP | JALR T0, T0 |
> + * | FUNC | X |
> + *
> + * If not, then it starts at a 4- but not 8-byte aligned address. In such cases,
> + * We re-arrange code and the trampoline in order to natually align it.
> + * | ADDR | COMPILED | DISABLED | ENABLED |
> + * +--------+----------+------------------+------------------------+
> + * | 0x04 | NOP | J FUNC | AUIPC T0, 0 |
> + * | 0x08 | NOP | REG_L T0, 0xC(T0) |
> + * | 0x0C | NOP | J 0x18 |
> + * | 0x10 | NOP | 8-byte aligned target address (low) |
> + * | 0x14 | NOP | (high) |
> + * | 0x18 | NOP | JALR T0, T0 |
> + * | FUNC | X |
> */
> +
> #if __riscv_xlen == 64
> -#define INSN0 0xfe113c23
> -#define INSN3 0xff813083
> -#elif __riscv_xlen == 32
> -#define INSN0 0xfe112e23
> -#define INSN3 0xffc12083
> +#define INSN_LD_T0_OFF(off) ((0x2b283) | ((off) << 20))
> +# elif __riscv_xlen == 32
> +#define INSN_LD_T0_OFF(off) ((0x2a283) | ((off) << 20))
> #endif
>
> -#define FUNC_ENTRY_SIZE 16
> -#define FUNC_ENTRY_JMP 4
> +#define INSN_SKIPALL 0x0180006f
> +#define INSN_AUIPC 0x00000297
> +#define INSN_LOAD(off) INSN_LD_T0_OFF(off)
> +#define INSN_SKIPTRAMP 0x00c0006f
> +#define INSN_JALR 0x000282e7
> +#define INSN_SIZE 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;
> -
> - call[1] = to_auipc_insn((unsigned int)(target - caller));
> - call[2] = to_jalr_insn((unsigned int)(target - caller));
> + unsigned int call[1] = {INSN_AUIPC};
> + void *tramp;
> + unsigned long patch_addr = rec->ip;
> +
> + if (IS_ALIGNED(patch_addr, 8)) {
> + tramp = (void *) (patch_addr + 0x8);
> + } else if (IS_ALIGNED(patch_addr, 4)) {
> + tramp = (void *) (patch_addr + 0xc);
> + } else {
> + pr_warn("cannot patch: function must be 4-Byte or 8-Byte aligned\n");
> + return -EINVAL;
> + }
> + WARN_ON(!IS_ALIGNED((unsigned long)tramp, 8));
> + patch_insn_write(tramp, &addr, sizeof(unsigned long));
>
> - if (patch_text_nosync((void *)rec->ip, call, FUNC_ENTRY_SIZE))
> + if (patch_text_nosync((void *)patch_addr, &call, INSN_SIZE))
> return -EPERM;
>
> return 0;
> @@ -114,14 +153,49 @@ 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[1] = {INSN_SKIPALL};
> + unsigned long patch_addr = rec->ip;
>
> - if (patch_text_nosync((void *)rec->ip, nops, FUNC_ENTRY_SIZE))
> + if (patch_text_nosync((void *)patch_addr, nops, INSN_SIZE))
> return -EPERM;
>
> return 0;
> }
>
> +extern void ftrace_no_caller(void);
> +static void ftrace_make_default_tramp(unsigned int *tramp)
> +{
> + *((unsigned long *)tramp) = (unsigned long) &ftrace_no_caller;
> +}
> +
> +int __ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec,
> + unsigned long addr)
> +{
> + unsigned int nops[6];
> + unsigned int *tramp;
> + unsigned long patch_addr = rec->ip;
> +
> + nops[0] = INSN_SKIPALL;
> + if (IS_ALIGNED(patch_addr, 8)) {
> + nops[1] = INSN_SKIPTRAMP;
> + nops[4] = INSN_LOAD(0x8);
> + tramp = &nops[2];
> + } else if (IS_ALIGNED(patch_addr, 4)) {
> + nops[1] = INSN_LOAD(0xc);
> + nops[2] = INSN_SKIPTRAMP;
> + tramp = &nops[3];
> + } else {
> + pr_warn("start address must be 4-Byte aligned\n");
> + return -EINVAL;
> + }
> + ftrace_make_default_tramp(tramp);
> + nops[5] = INSN_JALR;
> +
> + if (patch_text_nosync((void *)patch_addr, nops, sizeof(nops)))
> + return -EPERM;
> +
> + return 0;
> +}
>
> /*
> * This is called early on, and isn't wrapped by
> @@ -135,7 +209,7 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
> int out;
>
> ftrace_arch_code_modify_prepare();
> - out = ftrace_make_nop(mod, rec, MCOUNT_ADDR);
> + out = __ftrace_init_nop(mod, rec, MCOUNT_ADDR);
> ftrace_arch_code_modify_post_process();
>
> return out;
> @@ -158,17 +232,14 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
> 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;
> int ret;
>
> - make_call(caller, old_addr, call);
> - ret = ftrace_check_current_call(caller, call);
> + ret = ftrace_check_current_call(rec->ip, old_addr);
I suppose, the location of the handler's address should be used here,
rather than the start address of the function. I mean, rec->ip + 8 or
rec->ip + 12, depending on the alignment of the function.
Without this fix, the boottime function graph test fails as follows:
[ 39.360356] Testing tracer function_graph:
[ 44.648661] (____ptrval____): expected (ffffffff8000d838) but got
(00c0006f00000297)
[ 44.649805] ------------[ ftrace bug ]------------
[ 44.650102] ftrace failed to modify
[ 44.650135] [<ffffffff800fdba0>]
trace_selftest_dynamic_test_func+0x0/0x28
[ 44.650966] actual: 97:02:00:00:6f:00:c0:00
[ 44.651684] Updating ftrace call site to call a different ftrace function
[ 44.652366] ftrace record flags: e1180002
[ 44.652798] (2) R
expected tramp: ffffffff8000d73c
The byte sequence 97:02:00:00:6f:00:c0:00 is the pair of instructions
"auipc t0,0x0; j 0x10" rather than the address of the Ftrace trampoline.
>
> if (ret)
> return ret;
>
> - return __ftrace_modify_call(caller, addr, true);
> + return __ftrace_modify_call(rec->ip, addr, true);
Same here.
I am currently testing a rebased version of the patchset with the kernel
6.8.0-rc4.
With the following fix the issue goes away and all boottime tests of the
tracers pass in QEMU:
-----------------------
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index ad9eebfad0d5..cc89b0927622 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -142,20 +142,30 @@ static int __ftrace_modify_call(unsigned long
hook_pos, unsigned long target,
#define INSN_JALR 0x000282e7
#define INSN_SIZE 4
-int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+static inline unsigned long ftrace_tramp_addr(struct dyn_ftrace *rec)
{
- unsigned int call[1] = {INSN_AUIPC};
- void *tramp;
unsigned long patch_addr = rec->ip;
if (IS_ALIGNED(patch_addr, 8)) {
- tramp = (void *) (patch_addr + 0x8);
+ return patch_addr + 0x8;
} else if (IS_ALIGNED(patch_addr, 4)) {
- tramp = (void *) (patch_addr + 0xc);
+ return patch_addr + 0xc;
} else {
- pr_warn("cannot patch: function must be 4-Byte or 8-Byte aligned\n");
- return -EINVAL;
+ pr_warn("cannot patch: start of the function must be 4-byte aligned\n");
+ return 0;
}
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned int call[1] = {INSN_AUIPC};
+ void *tramp;
+ unsigned long patch_addr = rec->ip;
+
+ tramp = (void *)ftrace_tramp_addr(rec);
+ if (!tramp)
+ return -EINVAL;
+
WARN_ON(!IS_ALIGNED((unsigned long)tramp, 8));
patch_insn_write(tramp, &addr, sizeof(unsigned long));
@@ -248,13 +257,18 @@ int ftrace_modify_call(struct dyn_ftrace *rec,
unsigned long old_addr,
unsigned long addr)
{
int ret;
+ unsigned long tramp;
+
+ tramp = ftrace_tramp_addr(rec);
+ if (!tramp)
+ return -EINVAL;
- ret = ftrace_check_current_call(rec->ip, old_addr);
+ ret = ftrace_check_current_call(tramp, old_addr);
if (ret)
return ret;
- return __ftrace_modify_call(rec->ip, addr, true);
+ return __ftrace_modify_call(tramp, addr, true);
}
#endif
-----------------------
> }
> #endif
>
> diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
> index d171eca623b6..f8ee63e4314b 100644
> --- a/arch/riscv/kernel/mcount-dyn.S
> +++ b/arch/riscv/kernel/mcount-dyn.S
> @@ -13,7 +13,7 @@
>
> .text
>
> -#define FENTRY_RA_OFFSET 12
> +#define FENTRY_RA_OFFSET 24
> #define ABI_SIZE_ON_STACK 72
> #define ABI_A0 0
> #define ABI_A1 8
> @@ -25,7 +25,12 @@
> #define ABI_A7 56
> #define ABI_RA 64
>
> +# t0 points to return of ftrace
> +# ra points to the return address of traced function
> +
> .macro SAVE_ABI
> + REG_S ra, -SZREG(sp)
> + mv ra, t0
> addi sp, sp, -SZREG
> addi sp, sp, -ABI_SIZE_ON_STACK
>
> @@ -53,10 +58,14 @@
>
> addi sp, sp, ABI_SIZE_ON_STACK
> addi sp, sp, SZREG
> + mv t0, ra
> + REG_L ra, -SZREG(sp)
> .endm
>
> #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
> .macro SAVE_ALL
> + REG_S ra, -SZREG(sp)
> + mv ra, t0
> addi sp, sp, -SZREG
> addi sp, sp, -PT_SIZE_ON_STACK
>
> @@ -138,9 +147,18 @@
>
> addi sp, sp, PT_SIZE_ON_STACK
> addi sp, sp, SZREG
> + mv t0, ra # t0 is equal to ra here
> + REG_L ra, -SZREG(sp)
> .endm
> #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
>
> +# perform a full fence before re-running the ftrae entry if we run into this
> +ENTRY(ftrace_no_caller)
> + fence rw, rw
> + fence.i
> + jr -FENTRY_RA_OFFSET(t0)
> +ENDPROC(ftrace_no_caller)
> +
> ENTRY(ftrace_caller)
> SAVE_ABI
>
> @@ -150,9 +168,9 @@ ENTRY(ftrace_caller)
> REG_L a1, ABI_SIZE_ON_STACK(sp)
> mv a3, sp
>
> -ftrace_call:
> - .global ftrace_call
> - call ftrace_stub
> +ftrace_call_site:
> + REG_L ra, ftrace_call
> + jalr 0(ra)
>
> #ifdef CONFIG_FUNCTION_GRAPH_TRACER
> addi a0, sp, ABI_SIZE_ON_STACK
> @@ -161,12 +179,12 @@ ftrace_call:
> #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
> mv a2, s0
> #endif
> -ftrace_graph_call:
> - .global ftrace_graph_call
> - call ftrace_stub
> +ftrace_graph_call_site:
> + REG_L ra, ftrace_graph_call
> + jalr 0(ra)
> #endif
> RESTORE_ABI
> - ret
> + jr t0
> ENDPROC(ftrace_caller)
>
> #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
> @@ -179,9 +197,9 @@ ENTRY(ftrace_regs_caller)
> REG_L a1, PT_SIZE_ON_STACK(sp)
> mv a3, sp
>
> -ftrace_regs_call:
> - .global ftrace_regs_call
> - call ftrace_stub
> +ftrace_regs_call_site:
> + REG_L ra, ftrace_regs_call
> + jalr 0(ra)
>
> #ifdef CONFIG_FUNCTION_GRAPH_TRACER
> addi a0, sp, PT_RA
> @@ -190,12 +208,33 @@ ftrace_regs_call:
> #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
> mv a2, s0
> #endif
> -ftrace_graph_regs_call:
> - .global ftrace_graph_regs_call
> - call ftrace_stub
> +ftrace_graph_regs_call_site:
> + REG_L ra, ftrace_graph_regs_call
> + jalr 0(ra)
> #endif
>
> RESTORE_ALL
> - ret
> + jr t0
> ENDPROC(ftrace_regs_caller)
> #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
> +
> +.align RISCV_LGPTR
> +ftrace_call:
> + .global ftrace_call
> + RISCV_PTR ftrace_stub
> +
> +.align RISCV_LGPTR
> +ftrace_graph_call:
> + .global ftrace_graph_call
> + RISCV_PTR ftrace_stub
> +
> +.align RISCV_LGPTR
> +ftrace_regs_call:
> + .global ftrace_regs_call
> + RISCV_PTR ftrace_stub
> +
> +.align RISCV_LGPTR
> +ftrace_graph_regs_call:
> + .global ftrace_graph_regs_call
> + RISCV_PTR ftrace_stub
> +
Regards,
Evgenii
More information about the linux-riscv
mailing list