123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666 |
- // SPDX-License-Identifier: GPL-2.0
- /*
- * Dynamic function tracing support.
- *
- * Copyright (C) 2007-2008 Steven Rostedt <[email protected]>
- *
- * Thanks goes to Ingo Molnar, for suggesting the idea.
- * Mathieu Desnoyers, for suggesting postponing the modifications.
- * Arjan van de Ven, for keeping me straight, and explaining to me
- * the dangers of modifying code on the run.
- */
- #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
- #include <linux/spinlock.h>
- #include <linux/hardirq.h>
- #include <linux/uaccess.h>
- #include <linux/ftrace.h>
- #include <linux/percpu.h>
- #include <linux/sched.h>
- #include <linux/slab.h>
- #include <linux/init.h>
- #include <linux/list.h>
- #include <linux/module.h>
- #include <linux/memory.h>
- #include <linux/vmalloc.h>
- #include <trace/syscall.h>
- #include <asm/set_memory.h>
- #include <asm/kprobes.h>
- #include <asm/ftrace.h>
- #include <asm/nops.h>
- #include <asm/text-patching.h>
- #ifdef CONFIG_DYNAMIC_FTRACE
- static int ftrace_poke_late = 0;
- void ftrace_arch_code_modify_prepare(void)
- __acquires(&text_mutex)
- {
- /*
- * Need to grab text_mutex to prevent a race from module loading
- * and live kernel patching from changing the text permissions while
- * ftrace has it set to "read/write".
- */
- mutex_lock(&text_mutex);
- ftrace_poke_late = 1;
- }
- void ftrace_arch_code_modify_post_process(void)
- __releases(&text_mutex)
- {
- /*
- * ftrace_make_{call,nop}() may be called during
- * module load, and we need to finish the text_poke_queue()
- * that they do, here.
- */
- text_poke_finish();
- ftrace_poke_late = 0;
- mutex_unlock(&text_mutex);
- }
- static const char *ftrace_nop_replace(void)
- {
- return x86_nops[5];
- }
- static const char *ftrace_call_replace(unsigned long ip, unsigned long addr)
- {
- return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr);
- }
- static int ftrace_verify_code(unsigned long ip, const char *old_code)
- {
- char cur_code[MCOUNT_INSN_SIZE];
- /*
- * Note:
- * We are paranoid about modifying text, as if a bug was to happen, it
- * could cause us to read or write to someplace that could cause harm.
- * Carefully read and modify the code with probe_kernel_*(), and make
- * sure what we read is what we expected it to be before modifying it.
- */
- /* read the text we want to modify */
- if (copy_from_kernel_nofault(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) {
- WARN_ON(1);
- return -EFAULT;
- }
- /* Make sure it is what we expect it to be */
- if (memcmp(cur_code, old_code, MCOUNT_INSN_SIZE) != 0) {
- ftrace_expected = old_code;
- WARN_ON(1);
- return -EINVAL;
- }
- return 0;
- }
- /*
- * Marked __ref because it calls text_poke_early() which is .init.text. That is
- * ok because that call will happen early, during boot, when .init sections are
- * still present.
- */
- static int __ref
- ftrace_modify_code_direct(unsigned long ip, const char *old_code,
- const char *new_code)
- {
- int ret = ftrace_verify_code(ip, old_code);
- if (ret)
- return ret;
- /* replace the text with the new text */
- if (ftrace_poke_late)
- text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL);
- else
- text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE);
- return 0;
- }
- int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr)
- {
- unsigned long ip = rec->ip;
- const char *new, *old;
- old = ftrace_call_replace(ip, addr);
- new = ftrace_nop_replace();
- /*
- * On boot up, and when modules are loaded, the MCOUNT_ADDR
- * is converted to a nop, and will never become MCOUNT_ADDR
- * again. This code is either running before SMP (on boot up)
- * or before the code will ever be executed (module load).
- * We do not want to use the breakpoint version in this case,
- * just modify the code directly.
- */
- if (addr == MCOUNT_ADDR)
- return ftrace_modify_code_direct(ip, old, new);
- /*
- * x86 overrides ftrace_replace_code -- this function will never be used
- * in this case.
- */
- WARN_ONCE(1, "invalid use of ftrace_make_nop");
- return -EINVAL;
- }
- int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
- {
- unsigned long ip = rec->ip;
- const char *new, *old;
- old = ftrace_nop_replace();
- new = ftrace_call_replace(ip, addr);
- /* Should only be called when module is loaded */
- return ftrace_modify_code_direct(rec->ip, old, new);
- }
- /*
- * Should never be called:
- * As it is only called by __ftrace_replace_code() which is called by
- * ftrace_replace_code() that x86 overrides, and by ftrace_update_code()
- * which is called to turn mcount into nops or nops into function calls
- * but not to convert a function from not using regs to one that uses
- * regs, which ftrace_modify_call() is for.
- */
- int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
- unsigned long addr)
- {
- WARN_ON(1);
- return -EINVAL;
- }
- int ftrace_update_ftrace_func(ftrace_func_t func)
- {
- unsigned long ip;
- const char *new;
- ip = (unsigned long)(&ftrace_call);
- new = ftrace_call_replace(ip, (unsigned long)func);
- text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
- ip = (unsigned long)(&ftrace_regs_call);
- new = ftrace_call_replace(ip, (unsigned long)func);
- text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
- return 0;
- }
- void ftrace_replace_code(int enable)
- {
- struct ftrace_rec_iter *iter;
- struct dyn_ftrace *rec;
- const char *new, *old;
- int ret;
- for_ftrace_rec_iter(iter) {
- rec = ftrace_rec_iter_record(iter);
- switch (ftrace_test_record(rec, enable)) {
- case FTRACE_UPDATE_IGNORE:
- default:
- continue;
- case FTRACE_UPDATE_MAKE_CALL:
- old = ftrace_nop_replace();
- break;
- case FTRACE_UPDATE_MODIFY_CALL:
- case FTRACE_UPDATE_MAKE_NOP:
- old = ftrace_call_replace(rec->ip, ftrace_get_addr_curr(rec));
- break;
- }
- ret = ftrace_verify_code(rec->ip, old);
- if (ret) {
- ftrace_expected = old;
- ftrace_bug(ret, rec);
- ftrace_expected = NULL;
- return;
- }
- }
- for_ftrace_rec_iter(iter) {
- rec = ftrace_rec_iter_record(iter);
- switch (ftrace_test_record(rec, enable)) {
- case FTRACE_UPDATE_IGNORE:
- default:
- continue;
- case FTRACE_UPDATE_MAKE_CALL:
- case FTRACE_UPDATE_MODIFY_CALL:
- new = ftrace_call_replace(rec->ip, ftrace_get_addr_new(rec));
- break;
- case FTRACE_UPDATE_MAKE_NOP:
- new = ftrace_nop_replace();
- break;
- }
- text_poke_queue((void *)rec->ip, new, MCOUNT_INSN_SIZE, NULL);
- ftrace_update_record(rec, enable);
- }
- text_poke_finish();
- }
- void arch_ftrace_update_code(int command)
- {
- ftrace_modify_all_code(command);
- }
- /* Currently only x86_64 supports dynamic trampolines */
- #ifdef CONFIG_X86_64
- #ifdef CONFIG_MODULES
- #include <linux/moduleloader.h>
- /* Module allocation simplifies allocating memory for code */
- static inline void *alloc_tramp(unsigned long size)
- {
- return module_alloc(size);
- }
- static inline void tramp_free(void *tramp)
- {
- module_memfree(tramp);
- }
- #else
- /* Trampolines can only be created if modules are supported */
- static inline void *alloc_tramp(unsigned long size)
- {
- return NULL;
- }
- static inline void tramp_free(void *tramp) { }
- #endif
- /* Defined as markers to the end of the ftrace default trampolines */
- extern void ftrace_regs_caller_end(void);
- extern void ftrace_regs_caller_ret(void);
- extern void ftrace_caller_end(void);
- extern void ftrace_caller_op_ptr(void);
- extern void ftrace_regs_caller_op_ptr(void);
- extern void ftrace_regs_caller_jmp(void);
- /* movq function_trace_op(%rip), %rdx */
- /* 0x48 0x8b 0x15 <offset-to-ftrace_trace_op (4 bytes)> */
- #define OP_REF_SIZE 7
- /*
- * The ftrace_ops is passed to the function callback. Since the
- * trampoline only services a single ftrace_ops, we can pass in
- * that ops directly.
- *
- * The ftrace_op_code_union is used to create a pointer to the
- * ftrace_ops that will be passed to the callback function.
- */
- union ftrace_op_code_union {
- char code[OP_REF_SIZE];
- struct {
- char op[3];
- int offset;
- } __attribute__((packed));
- };
- #define RET_SIZE (IS_ENABLED(CONFIG_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_SLS))
- static unsigned long
- create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
- {
- unsigned long start_offset;
- unsigned long end_offset;
- unsigned long op_offset;
- unsigned long call_offset;
- unsigned long jmp_offset;
- unsigned long offset;
- unsigned long npages;
- unsigned long size;
- unsigned long *ptr;
- void *trampoline;
- void *ip;
- /* 48 8b 15 <offset> is movq <offset>(%rip), %rdx */
- unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
- unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE };
- union ftrace_op_code_union op_ptr;
- int ret;
- if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
- start_offset = (unsigned long)ftrace_regs_caller;
- end_offset = (unsigned long)ftrace_regs_caller_end;
- op_offset = (unsigned long)ftrace_regs_caller_op_ptr;
- call_offset = (unsigned long)ftrace_regs_call;
- jmp_offset = (unsigned long)ftrace_regs_caller_jmp;
- } else {
- start_offset = (unsigned long)ftrace_caller;
- end_offset = (unsigned long)ftrace_caller_end;
- op_offset = (unsigned long)ftrace_caller_op_ptr;
- call_offset = (unsigned long)ftrace_call;
- jmp_offset = 0;
- }
- size = end_offset - start_offset;
- /*
- * Allocate enough size to store the ftrace_caller code,
- * the iret , as well as the address of the ftrace_ops this
- * trampoline is used for.
- */
- trampoline = alloc_tramp(size + RET_SIZE + sizeof(void *));
- if (!trampoline)
- return 0;
- *tramp_size = size + RET_SIZE + sizeof(void *);
- npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
- /* Copy ftrace_caller onto the trampoline memory */
- ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size);
- if (WARN_ON(ret < 0))
- goto fail;
- ip = trampoline + size;
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
- __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, &__x86_return_thunk, JMP32_INSN_SIZE);
- else
- memcpy(ip, retq, sizeof(retq));
- /* No need to test direct calls on created trampolines */
- if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
- /* NOP the jnz 1f; but make sure it's a 2 byte jnz */
- ip = trampoline + (jmp_offset - start_offset);
- if (WARN_ON(*(char *)ip != 0x75))
- goto fail;
- ret = copy_from_kernel_nofault(ip, x86_nops[2], 2);
- if (ret < 0)
- goto fail;
- }
- /*
- * The address of the ftrace_ops that is used for this trampoline
- * is stored at the end of the trampoline. This will be used to
- * load the third parameter for the callback. Basically, that
- * location at the end of the trampoline takes the place of
- * the global function_trace_op variable.
- */
- ptr = (unsigned long *)(trampoline + size + RET_SIZE);
- *ptr = (unsigned long)ops;
- op_offset -= start_offset;
- memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE);
- /* Are we pointing to the reference? */
- if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0))
- goto fail;
- /* Load the contents of ptr into the callback parameter */
- offset = (unsigned long)ptr;
- offset -= (unsigned long)trampoline + op_offset + OP_REF_SIZE;
- op_ptr.offset = offset;
- /* put in the new offset to the ftrace_ops */
- memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
- /* put in the call to the function */
- mutex_lock(&text_mutex);
- call_offset -= start_offset;
- memcpy(trampoline + call_offset,
- text_gen_insn(CALL_INSN_OPCODE,
- trampoline + call_offset,
- ftrace_ops_get_func(ops)), CALL_INSN_SIZE);
- mutex_unlock(&text_mutex);
- /* ALLOC_TRAMP flags lets us know we created it */
- ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
- set_vm_flush_reset_perms(trampoline);
- if (likely(system_state != SYSTEM_BOOTING))
- set_memory_ro((unsigned long)trampoline, npages);
- set_memory_x((unsigned long)trampoline, npages);
- return (unsigned long)trampoline;
- fail:
- tramp_free(trampoline);
- return 0;
- }
- void set_ftrace_ops_ro(void)
- {
- struct ftrace_ops *ops;
- unsigned long start_offset;
- unsigned long end_offset;
- unsigned long npages;
- unsigned long size;
- do_for_each_ftrace_op(ops, ftrace_ops_list) {
- if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
- continue;
- if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
- start_offset = (unsigned long)ftrace_regs_caller;
- end_offset = (unsigned long)ftrace_regs_caller_end;
- } else {
- start_offset = (unsigned long)ftrace_caller;
- end_offset = (unsigned long)ftrace_caller_end;
- }
- size = end_offset - start_offset;
- size = size + RET_SIZE + sizeof(void *);
- npages = DIV_ROUND_UP(size, PAGE_SIZE);
- set_memory_ro((unsigned long)ops->trampoline, npages);
- } while_for_each_ftrace_op(ops);
- }
- static unsigned long calc_trampoline_call_offset(bool save_regs)
- {
- unsigned long start_offset;
- unsigned long call_offset;
- if (save_regs) {
- start_offset = (unsigned long)ftrace_regs_caller;
- call_offset = (unsigned long)ftrace_regs_call;
- } else {
- start_offset = (unsigned long)ftrace_caller;
- call_offset = (unsigned long)ftrace_call;
- }
- return call_offset - start_offset;
- }
- void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
- {
- ftrace_func_t func;
- unsigned long offset;
- unsigned long ip;
- unsigned int size;
- const char *new;
- if (!ops->trampoline) {
- ops->trampoline = create_trampoline(ops, &size);
- if (!ops->trampoline)
- return;
- ops->trampoline_size = size;
- return;
- }
- /*
- * The ftrace_ops caller may set up its own trampoline.
- * In such a case, this code must not modify it.
- */
- if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
- return;
- offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS);
- ip = ops->trampoline + offset;
- func = ftrace_ops_get_func(ops);
- mutex_lock(&text_mutex);
- /* Do a safe modify in case the trampoline is executing */
- new = ftrace_call_replace(ip, (unsigned long)func);
- text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
- mutex_unlock(&text_mutex);
- }
- /* Return the address of the function the trampoline calls */
- static void *addr_from_call(void *ptr)
- {
- union text_poke_insn call;
- int ret;
- ret = copy_from_kernel_nofault(&call, ptr, CALL_INSN_SIZE);
- if (WARN_ON_ONCE(ret < 0))
- return NULL;
- /* Make sure this is a call */
- if (WARN_ON_ONCE(call.opcode != CALL_INSN_OPCODE)) {
- pr_warn("Expected E8, got %x\n", call.opcode);
- return NULL;
- }
- return ptr + CALL_INSN_SIZE + call.disp;
- }
- void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
- unsigned long frame_pointer);
- /*
- * If the ops->trampoline was not allocated, then it probably
- * has a static trampoline func, or is the ftrace caller itself.
- */
- static void *static_tramp_func(struct ftrace_ops *ops, struct dyn_ftrace *rec)
- {
- unsigned long offset;
- bool save_regs = rec->flags & FTRACE_FL_REGS_EN;
- void *ptr;
- if (ops && ops->trampoline) {
- #if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) && \
- defined(CONFIG_FUNCTION_GRAPH_TRACER)
- /*
- * We only know about function graph tracer setting as static
- * trampoline.
- */
- if (ops->trampoline == FTRACE_GRAPH_ADDR)
- return (void *)prepare_ftrace_return;
- #endif
- return NULL;
- }
- offset = calc_trampoline_call_offset(save_regs);
- if (save_regs)
- ptr = (void *)FTRACE_REGS_ADDR + offset;
- else
- ptr = (void *)FTRACE_ADDR + offset;
- return addr_from_call(ptr);
- }
- void *arch_ftrace_trampoline_func(struct ftrace_ops *ops, struct dyn_ftrace *rec)
- {
- unsigned long offset;
- /* If we didn't allocate this trampoline, consider it static */
- if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
- return static_tramp_func(ops, rec);
- offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS);
- return addr_from_call((void *)ops->trampoline + offset);
- }
- void arch_ftrace_trampoline_free(struct ftrace_ops *ops)
- {
- if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
- return;
- tramp_free((void *)ops->trampoline);
- ops->trampoline = 0;
- }
- #endif /* CONFIG_X86_64 */
- #endif /* CONFIG_DYNAMIC_FTRACE */
- #ifdef CONFIG_FUNCTION_GRAPH_TRACER
- #if defined(CONFIG_DYNAMIC_FTRACE) && !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS)
- extern void ftrace_graph_call(void);
- static const char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
- {
- return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr);
- }
- static int ftrace_mod_jmp(unsigned long ip, void *func)
- {
- const char *new;
- new = ftrace_jmp_replace(ip, (unsigned long)func);
- text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
- return 0;
- }
- int ftrace_enable_ftrace_graph_caller(void)
- {
- unsigned long ip = (unsigned long)(&ftrace_graph_call);
- return ftrace_mod_jmp(ip, &ftrace_graph_caller);
- }
- int ftrace_disable_ftrace_graph_caller(void)
- {
- unsigned long ip = (unsigned long)(&ftrace_graph_call);
- return ftrace_mod_jmp(ip, &ftrace_stub);
- }
- #endif /* CONFIG_DYNAMIC_FTRACE && !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
- /*
- * Hook the return address and push it in the stack of return addrs
- * in current thread info.
- */
- void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
- unsigned long frame_pointer)
- {
- unsigned long return_hooker = (unsigned long)&return_to_handler;
- int bit;
- /*
- * When resuming from suspend-to-ram, this function can be indirectly
- * called from early CPU startup code while the CPU is in real mode,
- * which would fail miserably. Make sure the stack pointer is a
- * virtual address.
- *
- * This check isn't as accurate as virt_addr_valid(), but it should be
- * good enough for this purpose, and it's fast.
- */
- if (unlikely((long)__builtin_frame_address(0) >= 0))
- return;
- if (unlikely(ftrace_graph_is_dead()))
- return;
- if (unlikely(atomic_read(¤t->tracing_graph_pause)))
- return;
- bit = ftrace_test_recursion_trylock(ip, *parent);
- if (bit < 0)
- return;
- if (!function_graph_enter(*parent, ip, frame_pointer, parent))
- *parent = return_hooker;
- ftrace_test_recursion_unlock(bit);
- }
- #ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
- void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op, struct ftrace_regs *fregs)
- {
- struct pt_regs *regs = &fregs->regs;
- unsigned long *stack = (unsigned long *)kernel_stack_pointer(regs);
- prepare_ftrace_return(ip, (unsigned long *)stack, 0);
- }
- #endif
- #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
|