diff options
Diffstat (limited to 'arch/arm64')
-rw-r--r-- | arch/arm64/Kconfig | 3 | ||||
-rw-r--r-- | arch/arm64/Makefile | 5 | ||||
-rw-r--r-- | arch/arm64/include/asm/ftrace.h | 15 | ||||
-rw-r--r-- | arch/arm64/kernel/asm-offsets.c | 4 | ||||
-rw-r--r-- | arch/arm64/kernel/entry-ftrace.S | 32 | ||||
-rw-r--r-- | arch/arm64/kernel/ftrace.c | 156 |
6 files changed, 195 insertions, 20 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 6914f6bf41e2..6f6f37161cf6 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -124,6 +124,7 @@ config ARM64 select EDAC_SUPPORT select FRAME_POINTER select FUNCTION_ALIGNMENT_4B + select FUNCTION_ALIGNMENT_8B if DYNAMIC_FTRACE_WITH_CALL_OPS select GENERIC_ALLOCATOR select GENERIC_ARCH_TOPOLOGY select GENERIC_CLOCKEVENTS_BROADCAST @@ -187,6 +188,8 @@ config ARM64 select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_ARGS \ if $(cc-option,-fpatchable-function-entry=2) + select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \ + if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_ARGS select HAVE_EFFICIENT_UNALIGNED_ACCESS diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index d62bd221828f..4c3be442fbb3 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -139,7 +139,10 @@ endif CHECKFLAGS += -D__aarch64__ -ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_ARGS),y) +ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS),y) + KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY + CC_FLAGS_FTRACE := -fpatchable-function-entry=4,2 +else ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_ARGS),y) KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY CC_FLAGS_FTRACE := -fpatchable-function-entry=2 endif diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 5664729800ae..1c2672bbbf37 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -62,20 +62,7 @@ extern unsigned long ftrace_graph_call; extern void return_to_handler(void); -static inline unsigned long ftrace_call_adjust(unsigned long addr) -{ - /* - * Adjust addr to point at the BL in the callsite. - * See ftrace_init_nop() for the callsite sequence. - */ - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS)) - return addr + AARCH64_INSN_SIZE; - /* - * addr is the address of the mcount call instruction. - * recordmcount does the necessary offset calculation. - */ - return addr; -} +unsigned long ftrace_call_adjust(unsigned long addr); #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS struct dyn_ftrace; diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 2234624536d9..ae345b06e9f7 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -9,6 +9,7 @@ #include <linux/arm_sdei.h> #include <linux/sched.h> +#include <linux/ftrace.h> #include <linux/kexec.h> #include <linux/mm.h> #include <linux/dma-mapping.h> @@ -194,5 +195,8 @@ int main(void) DEFINE(KIMAGE_START, offsetof(struct kimage, start)); BLANK(); #endif +#ifdef CONFIG_FUNCTION_TRACER + DEFINE(FTRACE_OPS_FUNC, offsetof(struct ftrace_ops, func)); +#endif return 0; } diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 3b625f76ffba..350ed81324ac 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -65,13 +65,35 @@ SYM_CODE_START(ftrace_caller) stp x29, x30, [sp, #FREGS_SIZE] add x29, sp, #FREGS_SIZE - 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 + /* Prepare arguments for the the tracer func */ + sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn) + mov x1, x9 // parent_ip (callsite's LR) + mov x3, sp // regs + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + /* + * The literal pointer to the ops is at an 8-byte aligned boundary + * which is either 12 or 16 bytes before the BL instruction in the call + * site. See ftrace_call_adjust() for details. + * + * Therefore here the LR points at `literal + 16` or `literal + 20`, + * and we can find the address of the literal in either case by + * aligning to an 8-byte boundary and subtracting 16. We do the + * alignment first as this allows us to fold the subtraction into the + * LDR. + */ + bic x2, x30, 0x7 + ldr x2, [x2, #-16] // op + + ldr x4, [x2, #FTRACE_OPS_FUNC] // op->func + blr x4 // op->func(ip, parent_ip, op, regs) + +#else + ldr_l x2, function_trace_op // op SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) - bl ftrace_stub + bl ftrace_stub // func(ip, parent_ip, op, regs) +#endif /* * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 38ebdf063255..5545fe1a9012 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -60,6 +60,89 @@ int ftrace_regs_query_register_offset(const char *name) } #endif +unsigned long ftrace_call_adjust(unsigned long addr) +{ + /* + * When using mcount, addr is the address of the mcount call + * instruction, and no adjustment is necessary. + */ + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS)) + return addr; + + /* + * When using patchable-function-entry without pre-function NOPS, addr + * is the address of the first NOP after the function entry point. + * + * The compiler has either generated: + * + * addr+00: func: NOP // To be patched to MOV X9, LR + * addr+04: NOP // To be patched to BL <caller> + * + * Or: + * + * addr-04: BTI C + * addr+00: func: NOP // To be patched to MOV X9, LR + * addr+04: NOP // To be patched to BL <caller> + * + * We must adjust addr to the address of the NOP which will be patched + * to `BL <caller>`, which is at `addr + 4` bytes in either case. + * + */ + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + return addr + AARCH64_INSN_SIZE; + + /* + * When using patchable-function-entry with pre-function NOPs, addr is + * the address of the first pre-function NOP. + * + * Starting from an 8-byte aligned base, the compiler has either + * generated: + * + * addr+00: NOP // Literal (first 32 bits) + * addr+04: NOP // Literal (last 32 bits) + * addr+08: func: NOP // To be patched to MOV X9, LR + * addr+12: NOP // To be patched to BL <caller> + * + * Or: + * + * addr+00: NOP // Literal (first 32 bits) + * addr+04: NOP // Literal (last 32 bits) + * addr+08: func: BTI C + * addr+12: NOP // To be patched to MOV X9, LR + * addr+16: NOP // To be patched to BL <caller> + * + * We must adjust addr to the address of the NOP which will be patched + * to `BL <caller>`, which is at either addr+12 or addr+16 depending on + * whether there is a BTI. + */ + + if (!IS_ALIGNED(addr, sizeof(unsigned long))) { + WARN_RATELIMIT(1, "Misaligned patch-site %pS\n", + (void *)(addr + 8)); + return 0; + } + + /* Skip the NOPs placed before the function entry point */ + addr += 2 * AARCH64_INSN_SIZE; + + /* Skip any BTI */ + if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) { + u32 insn = le32_to_cpu(*(__le32 *)addr); + + if (aarch64_insn_is_bti(insn)) { + addr += AARCH64_INSN_SIZE; + } else if (insn != aarch64_insn_gen_nop()) { + WARN_RATELIMIT(1, "unexpected insn in patch-site %pS: 0x%08x\n", + (void *)addr, insn); + } + } + + /* Skip the first NOP after function entry */ + addr += AARCH64_INSN_SIZE; + + return addr; +} + /* * Replace a single instruction, which may be a branch or NOP. * If @validate == true, a replaced instruction is checked against 'old'. @@ -98,6 +181,13 @@ int ftrace_update_ftrace_func(ftrace_func_t func) unsigned long pc; u32 new; + /* + * When using CALL_OPS, the function to call is associated with the + * call site, and we don't have a global function pointer to update. + */ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + return 0; + pc = (unsigned long)ftrace_call; new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func, AARCH64_INSN_BRANCH_LINK); @@ -176,6 +266,44 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, return true; } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS +static const struct ftrace_ops *arm64_rec_get_ops(struct dyn_ftrace *rec) +{ + const struct ftrace_ops *ops = NULL; + + if (rec->flags & FTRACE_FL_CALL_OPS_EN) { + ops = ftrace_find_unique_ops(rec); + WARN_ON_ONCE(!ops); + } + + if (!ops) + ops = &ftrace_list_ops; + + return ops; +} + +static int ftrace_rec_set_ops(const struct dyn_ftrace *rec, + const struct ftrace_ops *ops) +{ + unsigned long literal = ALIGN_DOWN(rec->ip - 12, 8); + return aarch64_insn_write_literal_u64((void *)literal, + (unsigned long)ops); +} + +static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) +{ + return ftrace_rec_set_ops(rec, &ftrace_nop_ops); +} + +static int ftrace_rec_update_ops(struct dyn_ftrace *rec) +{ + return ftrace_rec_set_ops(rec, arm64_rec_get_ops(rec)); +} +#else +static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) { return 0; } +static int ftrace_rec_update_ops(struct dyn_ftrace *rec) { return 0; } +#endif + /* * Turn on the call to ftrace_caller() in instrumented function */ @@ -183,6 +311,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { unsigned long pc = rec->ip; u32 old, new; + int ret; + + ret = ftrace_rec_update_ops(rec); + if (ret) + return ret; if (!ftrace_find_callable_addr(rec, NULL, &addr)) return -EINVAL; @@ -193,6 +326,19 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return ftrace_modify_code(pc, old, new, true); } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + if (WARN_ON_ONCE(old_addr != (unsigned long)ftrace_caller)) + return -EINVAL; + if (WARN_ON_ONCE(addr != (unsigned long)ftrace_caller)) + return -EINVAL; + + return ftrace_rec_update_ops(rec); +} +#endif + #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS /* * The compiler has inserted two NOPs before the regular function prologue. @@ -220,6 +366,11 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) { unsigned long pc = rec->ip - AARCH64_INSN_SIZE; u32 old, new; + int ret; + + ret = ftrace_rec_set_nop_ops(rec); + if (ret) + return ret; old = aarch64_insn_gen_nop(); new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9, @@ -237,9 +388,14 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, { unsigned long pc = rec->ip; u32 old = 0, new; + int ret; new = aarch64_insn_gen_nop(); + ret = ftrace_rec_set_nop_ops(rec); + if (ret) + return ret; + /* * When using mcount, callsites in modules may have been initalized to * call an arbitrary module PLT (which redirects to the _mcount stub) |