diff options
Diffstat (limited to 'arch/arm64')
| -rw-r--r-- | arch/arm64/Kconfig | 2 | ||||
| -rw-r--r-- | arch/arm64/Makefile | 5 | ||||
| -rw-r--r-- | arch/arm64/include/asm/ftrace.h | 23 | ||||
| -rw-r--r-- | arch/arm64/include/asm/insn.h | 3 | ||||
| -rw-r--r-- | arch/arm64/include/asm/module.h | 2 | ||||
| -rw-r--r-- | arch/arm64/kernel/asm-offsets.c | 1 | ||||
| -rw-r--r-- | arch/arm64/kernel/entry-ftrace.S | 140 | ||||
| -rw-r--r-- | arch/arm64/kernel/ftrace.c | 123 | ||||
| -rw-r--r-- | arch/arm64/kernel/insn.c | 13 | ||||
| -rw-r--r-- | arch/arm64/kernel/module-plts.c | 3 | ||||
| -rw-r--r-- | arch/arm64/kernel/module.c | 57 |
11 files changed, 307 insertions, 65 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index ea9c6b6c58a0..2901d6656c45 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -143,6 +143,8 @@ config ARM64 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE + select HAVE_DYNAMIC_FTRACE_WITH_REGS \ + if $(cc-option,-fpatchable-function-entry=2) select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 2c0238ce0551..1fbe24d4fdb6 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -95,6 +95,11 @@ ifeq ($(CONFIG_ARM64_MODULE_PLTS),y) KBUILD_LDS_MODULE += $(srctree)/arch/arm64/kernel/module.lds endif +ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y) + KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY + CC_FLAGS_FTRACE := -fpatchable-function-entry=2 +endif + # Default value head-y := arch/arm64/kernel/head.o diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index d48667b04c41..91fa4baa1a93 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -11,9 +11,20 @@ #include <asm/insn.h> #define HAVE_FUNCTION_GRAPH_FP_TEST + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#define ARCH_SUPPORTS_FTRACE_OPS 1 +#else #define MCOUNT_ADDR ((unsigned long)_mcount) +#endif + +/* The BL at the callsite's adjusted rec->ip */ #define MCOUNT_INSN_SIZE AARCH64_INSN_SIZE +#define FTRACE_PLT_IDX 0 +#define FTRACE_REGS_PLT_IDX 1 +#define NR_FTRACE_PLTS 2 + /* * Currently, gcc tends to save the link register after the local variables * on the stack. This causes the max stack tracer to report the function @@ -44,12 +55,24 @@ 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_REGS)) + return addr + AARCH64_INSN_SIZE; + /* * addr is the address of the mcount call instruction. * recordmcount does the necessary offset calculation. */ return addr; } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +struct dyn_ftrace; +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); +#define ftrace_init_nop ftrace_init_nop +#endif + #define ftrace_return_address(n) return_address(n) /* diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 39e7780bedd6..bb313dde58a4 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -440,6 +440,9 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, int shift, enum aarch64_insn_variant variant, enum aarch64_insn_logic_type type); +u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_variant variant); u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type, enum aarch64_insn_variant variant, enum aarch64_insn_register Rn, diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h index f80e13cbf8ec..1e93de68c044 100644 --- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -21,7 +21,7 @@ struct mod_arch_specific { struct mod_plt_sec init; /* for CONFIG_DYNAMIC_FTRACE */ - struct plt_entry *ftrace_trampoline; + struct plt_entry *ftrace_trampolines; }; #endif diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 214685760e1c..a5bdce8af65b 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -56,6 +56,7 @@ int main(void) DEFINE(S_X24, offsetof(struct pt_regs, regs[24])); DEFINE(S_X26, offsetof(struct pt_regs, regs[26])); DEFINE(S_X28, offsetof(struct pt_regs, regs[28])); + DEFINE(S_FP, offsetof(struct pt_regs, regs[29])); DEFINE(S_LR, offsetof(struct pt_regs, regs[30])); DEFINE(S_SP, offsetof(struct pt_regs, sp)); DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate)); diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 33d003d80121..4fe1514fcbfd 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -7,10 +7,137 @@ */ #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 x19-x30 are + * live, and x9-x18 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, #(S_FRAME_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, #(S_FRAME_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, #S_FRAME_SIZE] + add x29, sp, #S_FRAME_SIZE + + /* Create our frame record within pt_regs. */ + stp x29, x30, [sp, #S_STACKFRAME] + add x29, sp, #S_STACKFRAME + .endm + +ENTRY(ftrace_regs_caller) + ftrace_regs_entry 1 + b ftrace_common +ENDPROC(ftrace_regs_caller) + +ENTRY(ftrace_caller) + ftrace_regs_entry 0 + b ftrace_common +ENDPROC(ftrace_caller) + +ENTRY(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 + +GLOBAL(ftrace_call) + bl ftrace_stub + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +GLOBAL(ftrace_graph_call) // 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, #S_FRAME_SIZE + 16 + + ret x9 +ENDPROC(ftrace_common) + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(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, #S_FRAME_SIZE] // parent fp (callsite's FP) + bl prepare_ftrace_return + b ftrace_common_return +ENDPROC(ftrace_graph_caller) +#else +#endif + +#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + /* * Gcc with -pg will put the following code in the beginning of each function: * mov x0, x30 @@ -160,11 +287,6 @@ GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); mcount_exit ENDPROC(ftrace_caller) -#endif /* CONFIG_DYNAMIC_FTRACE */ - -ENTRY(ftrace_stub) - ret -ENDPROC(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* @@ -184,7 +306,15 @@ ENTRY(ftrace_graph_caller) mcount_exit ENDPROC(ftrace_graph_caller) +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + +ENTRY(ftrace_stub) + ret +ENDPROC(ftrace_stub) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER /* * void return_to_handler(void) * diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 06e56b470315..8618faa82e6d 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -62,6 +62,19 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return ftrace_modify_code(pc, 0, new, false); } +static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr) +{ +#ifdef CONFIG_ARM64_MODULE_PLTS + struct plt_entry *plt = mod->arch.ftrace_trampolines; + + if (addr == FTRACE_ADDR) + return &plt[FTRACE_PLT_IDX]; + if (addr == FTRACE_REGS_ADDR && IS_ENABLED(CONFIG_FTRACE_WITH_REGS)) + return &plt[FTRACE_REGS_PLT_IDX]; +#endif + return NULL; +} + /* * Turn on the call to ftrace_caller() in instrumented function */ @@ -72,9 +85,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) long offset = (long)pc - (long)addr; if (offset < -SZ_128M || offset >= SZ_128M) { -#ifdef CONFIG_ARM64_MODULE_PLTS - struct plt_entry trampoline, *dst; struct module *mod; + struct plt_entry *plt; + + if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) + return -EINVAL; /* * On kernels that support module PLTs, the offset between the @@ -93,49 +108,13 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (WARN_ON(!mod)) return -EINVAL; - /* - * There is only one ftrace trampoline per module. For now, - * this is not a problem since on arm64, all dynamic ftrace - * invocations are routed via ftrace_caller(). This will need - * to be revisited if support for multiple ftrace entry points - * is added in the future, but for now, the pr_err() below - * deals with a theoretical issue only. - * - * Note that PLTs are place relative, and plt_entries_equal() - * checks whether they point to the same target. Here, we need - * to check if the actual opcodes are in fact identical, - * regardless of the offset in memory so use memcmp() instead. - */ - dst = mod->arch.ftrace_trampoline; - trampoline = get_plt_entry(addr, dst); - if (memcmp(dst, &trampoline, sizeof(trampoline))) { - if (plt_entry_is_initialized(dst)) { - pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n"); - return -EINVAL; - } - - /* point the trampoline to our ftrace entry point */ - module_disable_ro(mod); - *dst = trampoline; - module_enable_ro(mod, true); - - /* - * Ensure updated trampoline is visible to instruction - * fetch before we patch in the branch. Although the - * architecture doesn't require an IPI in this case, - * Neoverse-N1 erratum #1542419 does require one - * if the TLB maintenance in module_enable_ro() is - * skipped due to rodata_enabled. It doesn't seem worth - * it to make it conditional given that this is - * certainly not a fast-path. - */ - flush_icache_range((unsigned long)&dst[0], - (unsigned long)&dst[1]); + plt = get_ftrace_plt(mod, addr); + if (!plt) { + pr_err("ftrace: no module PLT for %ps\n", (void *)addr); + return -EINVAL; } - addr = (unsigned long)dst; -#else /* CONFIG_ARM64_MODULE_PLTS */ - return -EINVAL; -#endif /* CONFIG_ARM64_MODULE_PLTS */ + + addr = (unsigned long)plt; } old = aarch64_insn_gen_nop(); @@ -144,6 +123,55 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return ftrace_modify_code(pc, old, new, true); } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + unsigned long pc = rec->ip; + u32 old, new; + + old = aarch64_insn_gen_branch_imm(pc, old_addr, + AARCH64_INSN_BRANCH_LINK); + new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); + + return ftrace_modify_code(pc, old, new, true); +} + +/* + * The compiler has inserted two NOPs before the regular function prologue. + * All instrumented functions follow the AAPCS, so x0-x8 and x19-x30 are live, + * and x9-x18 are free for our use. + * + * At runtime we want to be able to swing a single NOP <-> BL to enable or + * disable the ftrace call. The BL requires us to save the original LR value, + * so here we insert a <MOV X9, LR> over the first NOP so the instructions + * before the regular prologue are: + * + * | Compiled | Disabled | Enabled | + * +----------+------------+------------+ + * | NOP | MOV X9, LR | MOV X9, LR | + * | NOP | NOP | BL <entry> | + * + * The LR value will be recovered by ftrace_regs_entry, and restored into LR + * before returning to the regular function prologue. When a function is not + * being traced, the MOV is not harmful given x9 is not live per the AAPCS. + * + * Note: ftrace_process_locs() has pre-adjusted rec->ip to be the address of + * the BL. + */ +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + unsigned long pc = rec->ip - AARCH64_INSN_SIZE; + u32 old, new; + + old = aarch64_insn_gen_nop(); + new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9, + AARCH64_INSN_REG_LR, + AARCH64_INSN_VARIANT_64BIT); + return ftrace_modify_code(pc, old, new, true); +} +#endif + /* * Turn off the call to ftrace_caller() in instrumented function */ @@ -156,9 +184,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, long offset = (long)pc - (long)addr; if (offset < -SZ_128M || offset >= SZ_128M) { -#ifdef CONFIG_ARM64_MODULE_PLTS u32 replaced; + if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) + return -EINVAL; + /* * 'mod' is only set at module load time, but if we end up * dealing with an out-of-range condition, we can assume it @@ -189,9 +219,6 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return -EINVAL; validate = false; -#else /* CONFIG_ARM64_MODULE_PLTS */ - return -EINVAL; -#endif /* CONFIG_ARM64_MODULE_PLTS */ } else { old = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index d801a7094076..513b29c3e735 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -1268,6 +1268,19 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift); } +/* + * MOV (register) is architecturally an alias of ORR (shifted register) where + * MOV <*d>, <*m> is equivalent to ORR <*d>, <*ZR>, <*m> + */ +u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_variant variant) +{ + return aarch64_insn_gen_logical_shifted_reg(dst, AARCH64_INSN_REG_ZR, + src, 0, variant, + AARCH64_INSN_LOGIC_ORR); +} + u32 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr, enum aarch64_insn_register reg, enum aarch64_insn_adr_type type) diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index b182442b87a3..65b08a74aec6 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -4,6 +4,7 @@ */ #include <linux/elf.h> +#include <linux/ftrace.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/sort.h> @@ -330,7 +331,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, tramp->sh_type = SHT_NOBITS; tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC; tramp->sh_addralign = __alignof__(struct plt_entry); - tramp->sh_size = sizeof(struct plt_entry); + tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry); } return 0; diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 03ff15bffbb6..1cd1a4d0ed30 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -9,6 +9,7 @@ #include <linux/bitops.h> #include <linux/elf.h> +#include <linux/ftrace.h> #include <linux/gfp.h> #include <linux/kasan.h> #include <linux/kernel.h> @@ -470,22 +471,58 @@ overflow: return -ENOEXEC; } -int module_finalize(const Elf_Ehdr *hdr, - const Elf_Shdr *sechdrs, - struct module *me) +static const Elf_Shdr *find_section(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + const char *name) { const Elf_Shdr *s, *se; const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) { - if (strcmp(".altinstructions", secstrs + s->sh_name) == 0) - apply_alternatives_module((void *)s->sh_addr, s->sh_size); -#ifdef CONFIG_ARM64_MODULE_PLTS - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) && - !strcmp(".text.ftrace_trampoline", secstrs + s->sh_name)) - me->arch.ftrace_trampoline = (void *)s->sh_addr; -#endif + if (strcmp(name, secstrs + s->sh_name) == 0) + return s; } + return NULL; +} + +static inline void __init_plt(struct plt_entry *plt, unsigned long addr) +{ + *plt = get_plt_entry(addr, plt); +} + +static int module_init_ftrace_plt(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *mod) +{ +#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE) + const Elf_Shdr *s; + struct plt_entry *plts; + + s = find_section(hdr, sechdrs, ".text.ftrace_trampoline"); + if (!s) + return -ENOEXEC; + + plts = (void *)s->sh_addr; + + __init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR); + + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + __init_plt(&plts[FTRACE_REGS_PLT_IDX], FTRACE_REGS_ADDR); + + mod->arch.ftrace_trampolines = plts; +#endif return 0; } + +int module_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + const Elf_Shdr *s; + s = find_section(hdr, sechdrs, ".altinstructions"); + if (s) + apply_alternatives_module((void *)s->sh_addr, s->sh_size); + + return module_init_ftrace_plt(hdr, sechdrs, me); +} |