diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-27 10:05:51 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-27 10:05:51 +0000 |
commit | 5d1646d90e1f2cceb9f0828f4b28318cd0ec7744 (patch) | |
tree | a94efe259b9009378be6d90eb30d2b019d95c194 /arch/x86/kernel/kprobes | |
parent | Initial commit. (diff) | |
download | linux-upstream.tar.xz linux-upstream.zip |
Adding upstream version 5.10.209.upstream/5.10.209upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'arch/x86/kernel/kprobes')
-rw-r--r-- | arch/x86/kernel/kprobes/Makefile | 8 | ||||
-rw-r--r-- | arch/x86/kernel/kprobes/common.h | 108 | ||||
-rw-r--r-- | arch/x86/kernel/kprobes/core.c | 1152 | ||||
-rw-r--r-- | arch/x86/kernel/kprobes/ftrace.c | 63 | ||||
-rw-r--r-- | arch/x86/kernel/kprobes/opt.c | 556 |
5 files changed, 1887 insertions, 0 deletions
diff --git a/arch/x86/kernel/kprobes/Makefile b/arch/x86/kernel/kprobes/Makefile new file mode 100644 index 000000000..8a753432b --- /dev/null +++ b/arch/x86/kernel/kprobes/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for kernel probes +# + +obj-$(CONFIG_KPROBES) += core.o +obj-$(CONFIG_OPTPROBES) += opt.o +obj-$(CONFIG_KPROBES_ON_FTRACE) += ftrace.o diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h new file mode 100644 index 000000000..7d3a2e2da --- /dev/null +++ b/arch/x86/kernel/kprobes/common.h @@ -0,0 +1,108 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_KERNEL_KPROBES_COMMON_H +#define __X86_KERNEL_KPROBES_COMMON_H + +/* Kprobes and Optprobes common header */ + +#include <asm/asm.h> +#include <asm/frame.h> + +#ifdef CONFIG_X86_64 + +#define SAVE_REGS_STRING \ + /* Skip cs, ip, orig_ax. */ \ + " subq $24, %rsp\n" \ + " pushq %rdi\n" \ + " pushq %rsi\n" \ + " pushq %rdx\n" \ + " pushq %rcx\n" \ + " pushq %rax\n" \ + " pushq %r8\n" \ + " pushq %r9\n" \ + " pushq %r10\n" \ + " pushq %r11\n" \ + " pushq %rbx\n" \ + " pushq %rbp\n" \ + " pushq %r12\n" \ + " pushq %r13\n" \ + " pushq %r14\n" \ + " pushq %r15\n" \ + ENCODE_FRAME_POINTER + +#define RESTORE_REGS_STRING \ + " popq %r15\n" \ + " popq %r14\n" \ + " popq %r13\n" \ + " popq %r12\n" \ + " popq %rbp\n" \ + " popq %rbx\n" \ + " popq %r11\n" \ + " popq %r10\n" \ + " popq %r9\n" \ + " popq %r8\n" \ + " popq %rax\n" \ + " popq %rcx\n" \ + " popq %rdx\n" \ + " popq %rsi\n" \ + " popq %rdi\n" \ + /* Skip orig_ax, ip, cs */ \ + " addq $24, %rsp\n" +#else + +#define SAVE_REGS_STRING \ + /* Skip cs, ip, orig_ax and gs. */ \ + " subl $4*4, %esp\n" \ + " pushl %fs\n" \ + " pushl %es\n" \ + " pushl %ds\n" \ + " pushl %eax\n" \ + " pushl %ebp\n" \ + " pushl %edi\n" \ + " pushl %esi\n" \ + " pushl %edx\n" \ + " pushl %ecx\n" \ + " pushl %ebx\n" \ + ENCODE_FRAME_POINTER + +#define RESTORE_REGS_STRING \ + " popl %ebx\n" \ + " popl %ecx\n" \ + " popl %edx\n" \ + " popl %esi\n" \ + " popl %edi\n" \ + " popl %ebp\n" \ + " popl %eax\n" \ + /* Skip ds, es, fs, gs, orig_ax, ip, and cs. */\ + " addl $7*4, %esp\n" +#endif + +/* Ensure if the instruction can be boostable */ +extern int can_boost(struct insn *insn, void *orig_addr); +/* Recover instruction if given address is probed */ +extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, + unsigned long addr); +/* + * Copy an instruction and adjust the displacement if the instruction + * uses the %rip-relative addressing mode. + */ +extern int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn); + +/* Generate a relative-jump/call instruction */ +extern void synthesize_reljump(void *dest, void *from, void *to); +extern void synthesize_relcall(void *dest, void *from, void *to); + +#ifdef CONFIG_OPTPROBES +extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter); +extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr); +#else /* !CONFIG_OPTPROBES */ +static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) +{ + return 0; +} +static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) +{ + return addr; +} +#endif + +#endif diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c new file mode 100644 index 000000000..e7edc9e4c --- /dev/null +++ b/arch/x86/kernel/kprobes/core.c @@ -0,0 +1,1152 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Kernel Probes (KProbes) + * + * Copyright (C) IBM Corporation, 2002, 2004 + * + * 2002-Oct Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel + * Probes initial implementation ( includes contributions from + * Rusty Russell). + * 2004-July Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes + * interface to access function arguments. + * 2004-Oct Jim Keniston <jkenisto@us.ibm.com> and Prasanna S Panchamukhi + * <prasanna@in.ibm.com> adapted for x86_64 from i386. + * 2005-Mar Roland McGrath <roland@redhat.com> + * Fixed to handle %rip-relative addressing mode correctly. + * 2005-May Hien Nguyen <hien@us.ibm.com>, Jim Keniston + * <jkenisto@us.ibm.com> and Prasanna S Panchamukhi + * <prasanna@in.ibm.com> added function-return probes. + * 2005-May Rusty Lynch <rusty.lynch@intel.com> + * Added function return probes functionality + * 2006-Feb Masami Hiramatsu <hiramatu@sdl.hitachi.co.jp> added + * kprobe-booster and kretprobe-booster for i386. + * 2007-Dec Masami Hiramatsu <mhiramat@redhat.com> added kprobe-booster + * and kretprobe-booster for x86-64 + * 2007-Dec Masami Hiramatsu <mhiramat@redhat.com>, Arjan van de Ven + * <arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com> + * unified x86 kprobes code. + */ +#include <linux/kprobes.h> +#include <linux/ptrace.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/hardirq.h> +#include <linux/preempt.h> +#include <linux/sched/debug.h> +#include <linux/perf_event.h> +#include <linux/extable.h> +#include <linux/kdebug.h> +#include <linux/kallsyms.h> +#include <linux/kgdb.h> +#include <linux/ftrace.h> +#include <linux/kasan.h> +#include <linux/moduleloader.h> +#include <linux/objtool.h> +#include <linux/vmalloc.h> +#include <linux/pgtable.h> + +#include <asm/text-patching.h> +#include <asm/cacheflush.h> +#include <asm/desc.h> +#include <linux/uaccess.h> +#include <asm/alternative.h> +#include <asm/insn.h> +#include <asm/debugreg.h> +#include <asm/set_memory.h> + +#include "common.h" + +DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; +DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + +#define stack_addr(regs) ((unsigned long *)regs->sp) + +#define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\ + (((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) | \ + (b4##UL << 0x4)|(b5##UL << 0x5)|(b6##UL << 0x6)|(b7##UL << 0x7) | \ + (b8##UL << 0x8)|(b9##UL << 0x9)|(ba##UL << 0xa)|(bb##UL << 0xb) | \ + (bc##UL << 0xc)|(bd##UL << 0xd)|(be##UL << 0xe)|(bf##UL << 0xf)) \ + << (row % 32)) + /* + * Undefined/reserved opcodes, conditional jump, Opcode Extension + * Groups, and some special opcodes can not boost. + * This is non-const and volatile to keep gcc from statically + * optimizing it out, as variable_test_bit makes gcc think only + * *(unsigned long*) is used. + */ +static volatile u32 twobyte_is_boostable[256 / 32] = { + /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ + /* ---------------------------------------------- */ + W(0x00, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0) | /* 00 */ + W(0x10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1) , /* 10 */ + W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 20 */ + W(0x30, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */ + W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */ + W(0x50, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 50 */ + W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1) | /* 60 */ + W(0x70, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */ + W(0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 80 */ + W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */ + W(0xa0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* a0 */ + W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1) , /* b0 */ + W(0xc0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */ + W(0xd0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) , /* d0 */ + W(0xe0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* e0 */ + W(0xf0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0) /* f0 */ + /* ----------------------------------------------- */ + /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ +}; +#undef W + +struct kretprobe_blackpoint kretprobe_blacklist[] = { + {"__switch_to", }, /* This function switches only current task, but + doesn't switch kernel stack.*/ + {NULL, NULL} /* Terminator */ +}; + +const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist); + +static nokprobe_inline void +__synthesize_relative_insn(void *dest, void *from, void *to, u8 op) +{ + struct __arch_relative_insn { + u8 op; + s32 raddr; + } __packed *insn; + + insn = (struct __arch_relative_insn *)dest; + insn->raddr = (s32)((long)(to) - ((long)(from) + 5)); + insn->op = op; +} + +/* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ +void synthesize_reljump(void *dest, void *from, void *to) +{ + __synthesize_relative_insn(dest, from, to, JMP32_INSN_OPCODE); +} +NOKPROBE_SYMBOL(synthesize_reljump); + +/* Insert a call instruction at address 'from', which calls address 'to'.*/ +void synthesize_relcall(void *dest, void *from, void *to) +{ + __synthesize_relative_insn(dest, from, to, CALL_INSN_OPCODE); +} +NOKPROBE_SYMBOL(synthesize_relcall); + +/* + * Returns non-zero if INSN is boostable. + * RIP relative instructions are adjusted at copying time in 64 bits mode + */ +int can_boost(struct insn *insn, void *addr) +{ + kprobe_opcode_t opcode; + insn_byte_t prefix; + int i; + + if (search_exception_tables((unsigned long)addr)) + return 0; /* Page fault may occur on this address. */ + + /* 2nd-byte opcode */ + if (insn->opcode.nbytes == 2) + return test_bit(insn->opcode.bytes[1], + (unsigned long *)twobyte_is_boostable); + + if (insn->opcode.nbytes != 1) + return 0; + + for_each_insn_prefix(insn, i, prefix) { + insn_attr_t attr; + + attr = inat_get_opcode_attribute(prefix); + /* Can't boost Address-size override prefix and CS override prefix */ + if (prefix == 0x2e || inat_is_address_size_prefix(attr)) + return 0; + } + + opcode = insn->opcode.bytes[0]; + + switch (opcode) { + case 0x62: /* bound */ + case 0x70 ... 0x7f: /* Conditional jumps */ + case 0x9a: /* Call far */ + case 0xc0 ... 0xc1: /* Grp2 */ + case 0xcc ... 0xce: /* software exceptions */ + case 0xd0 ... 0xd3: /* Grp2 */ + case 0xd6: /* (UD) */ + case 0xd8 ... 0xdf: /* ESC */ + case 0xe0 ... 0xe3: /* LOOP*, JCXZ */ + case 0xe8 ... 0xe9: /* near Call, JMP */ + case 0xeb: /* Short JMP */ + case 0xf0 ... 0xf4: /* LOCK/REP, HLT */ + case 0xf6 ... 0xf7: /* Grp3 */ + case 0xfe: /* Grp4 */ + /* ... are not boostable */ + return 0; + case 0xff: /* Grp5 */ + /* Only indirect jmp is boostable */ + return X86_MODRM_REG(insn->modrm.bytes[0]) == 4; + default: + return 1; + } +} + +static unsigned long +__recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) +{ + struct kprobe *kp; + unsigned long faddr; + + kp = get_kprobe((void *)addr); + faddr = ftrace_location(addr); + /* + * Addresses inside the ftrace location are refused by + * arch_check_ftrace_location(). Something went terribly wrong + * if such an address is checked here. + */ + if (WARN_ON(faddr && faddr != addr)) + return 0UL; + /* + * Use the current code if it is not modified by Kprobe + * and it cannot be modified by ftrace. + */ + if (!kp && !faddr) + return addr; + + /* + * Basically, kp->ainsn.insn has an original instruction. + * However, RIP-relative instruction can not do single-stepping + * at different place, __copy_instruction() tweaks the displacement of + * that instruction. In that case, we can't recover the instruction + * from the kp->ainsn.insn. + * + * On the other hand, in case on normal Kprobe, kp->opcode has a copy + * of the first byte of the probed instruction, which is overwritten + * by int3. And the instruction at kp->addr is not modified by kprobes + * except for the first byte, we can recover the original instruction + * from it and kp->opcode. + * + * In case of Kprobes using ftrace, we do not have a copy of + * the original instruction. In fact, the ftrace location might + * be modified at anytime and even could be in an inconsistent state. + * Fortunately, we know that the original code is the ideal 5-byte + * long NOP. + */ + if (copy_from_kernel_nofault(buf, (void *)addr, + MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) + return 0UL; + + if (faddr) + memcpy(buf, ideal_nops[NOP_ATOMIC5], 5); + else + buf[0] = kp->opcode; + return (unsigned long)buf; +} + +/* + * Recover the probed instruction at addr for further analysis. + * Caller must lock kprobes by kprobe_mutex, or disable preemption + * for preventing to release referencing kprobes. + * Returns zero if the instruction can not get recovered (or access failed). + */ +unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) +{ + unsigned long __addr; + + __addr = __recover_optprobed_insn(buf, addr); + if (__addr != addr) + return __addr; + + return __recover_probed_insn(buf, addr); +} + +/* Check if paddr is at an instruction boundary */ +static int can_probe(unsigned long paddr) +{ + unsigned long addr, __addr, offset = 0; + struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + + if (!kallsyms_lookup_size_offset(paddr, NULL, &offset)) + return 0; + + /* Decode instructions */ + addr = paddr - offset; + while (addr < paddr) { + int ret; + + /* + * Check if the instruction has been modified by another + * kprobe, in which case we replace the breakpoint by the + * original instruction in our buffer. + * Also, jump optimization will change the breakpoint to + * relative-jump. Since the relative-jump itself is + * normally used, we just go through if there is no kprobe. + */ + __addr = recover_probed_instruction(buf, addr); + if (!__addr) + return 0; + + ret = insn_decode(&insn, (void *)__addr, MAX_INSN_SIZE, INSN_MODE_KERN); + if (ret < 0) + return 0; + +#ifdef CONFIG_KGDB + /* + * If there is a dynamically installed kgdb sw breakpoint, + * this function should not be probed. + */ + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE && + kgdb_has_hit_break(addr)) + return 0; +#endif + addr += insn.length; + } + + return (addr == paddr); +} + +/* + * Copy an instruction with recovering modified instruction by kprobes + * and adjust the displacement if the instruction uses the %rip-relative + * addressing mode. Note that since @real will be the final place of copied + * instruction, displacement must be adjust by @real, not @dest. + * This returns the length of copied instruction, or 0 if it has an error. + */ +int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) +{ + kprobe_opcode_t buf[MAX_INSN_SIZE]; + unsigned long recovered_insn = recover_probed_instruction(buf, (unsigned long)src); + int ret; + + if (!recovered_insn || !insn) + return 0; + + /* This can access kernel text if given address is not recovered */ + if (copy_from_kernel_nofault(dest, (void *)recovered_insn, + MAX_INSN_SIZE)) + return 0; + + ret = insn_decode(insn, dest, MAX_INSN_SIZE, INSN_MODE_KERN); + if (ret < 0) + return 0; + + /* We can not probe force emulate prefixed instruction */ + if (insn_has_emulate_prefix(insn)) + return 0; + + /* Another subsystem puts a breakpoint, failed to recover */ + if (insn->opcode.bytes[0] == INT3_INSN_OPCODE) + return 0; + + /* We should not singlestep on the exception masking instructions */ + if (insn_masking_exception(insn)) + return 0; + +#ifdef CONFIG_X86_64 + /* Only x86_64 has RIP relative instructions */ + if (insn_rip_relative(insn)) { + s64 newdisp; + u8 *disp; + /* + * The copied instruction uses the %rip-relative addressing + * mode. Adjust the displacement for the difference between + * the original location of this instruction and the location + * of the copy that will actually be run. The tricky bit here + * is making sure that the sign extension happens correctly in + * this calculation, since we need a signed 32-bit result to + * be sign-extended to 64 bits when it's added to the %rip + * value and yield the same 64-bit result that the sign- + * extension of the original signed 32-bit displacement would + * have given. + */ + newdisp = (u8 *) src + (s64) insn->displacement.value + - (u8 *) real; + if ((s64) (s32) newdisp != newdisp) { + pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp); + return 0; + } + disp = (u8 *) dest + insn_offset_displacement(insn); + *(s32 *) disp = (s32) newdisp; + } +#endif + return insn->length; +} + +/* Prepare reljump or int3 right after instruction */ +static int prepare_singlestep(kprobe_opcode_t *buf, struct kprobe *p, + struct insn *insn) +{ + int len = insn->length; + + if (!IS_ENABLED(CONFIG_PREEMPTION) && + !p->post_handler && can_boost(insn, p->addr) && + MAX_INSN_SIZE - len >= JMP32_INSN_SIZE) { + /* + * These instructions can be executed directly if it + * jumps back to correct address. + */ + synthesize_reljump(buf + len, p->ainsn.insn + len, + p->addr + insn->length); + len += JMP32_INSN_SIZE; + p->ainsn.boostable = 1; + } else { + /* Otherwise, put an int3 for trapping singlestep */ + if (MAX_INSN_SIZE - len < INT3_INSN_SIZE) + return -ENOSPC; + + buf[len] = INT3_INSN_OPCODE; + len += INT3_INSN_SIZE; + } + + return len; +} + +/* Make page to RO mode when allocate it */ +void *alloc_insn_page(void) +{ + void *page; + + page = module_alloc(PAGE_SIZE); + if (!page) + return NULL; + + set_vm_flush_reset_perms(page); + /* + * First make the page read-only, and only then make it executable to + * prevent it from being W+X in between. + */ + set_memory_ro((unsigned long)page, 1); + + /* + * TODO: Once additional kernel code protection mechanisms are set, ensure + * that the page was not maliciously altered and it is still zeroed. + */ + set_memory_x((unsigned long)page, 1); + + return page; +} + +/* Recover page to RW mode before releasing it */ +void free_insn_page(void *page) +{ + module_memfree(page); +} + +/* Kprobe x86 instruction emulation - only regs->ip or IF flag modifiers */ + +static void kprobe_emulate_ifmodifiers(struct kprobe *p, struct pt_regs *regs) +{ + switch (p->ainsn.opcode) { + case 0xfa: /* cli */ + regs->flags &= ~(X86_EFLAGS_IF); + break; + case 0xfb: /* sti */ + regs->flags |= X86_EFLAGS_IF; + break; + case 0x9c: /* pushf */ + int3_emulate_push(regs, regs->flags); + break; + case 0x9d: /* popf */ + regs->flags = int3_emulate_pop(regs); + break; + } + regs->ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size; +} +NOKPROBE_SYMBOL(kprobe_emulate_ifmodifiers); + +static void kprobe_emulate_ret(struct kprobe *p, struct pt_regs *regs) +{ + int3_emulate_ret(regs); +} +NOKPROBE_SYMBOL(kprobe_emulate_ret); + +static void kprobe_emulate_call(struct kprobe *p, struct pt_regs *regs) +{ + unsigned long func = regs->ip - INT3_INSN_SIZE + p->ainsn.size; + + func += p->ainsn.rel32; + int3_emulate_call(regs, func); +} +NOKPROBE_SYMBOL(kprobe_emulate_call); + +static nokprobe_inline +void __kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs, bool cond) +{ + unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size; + + if (cond) + ip += p->ainsn.rel32; + int3_emulate_jmp(regs, ip); +} + +static void kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs) +{ + __kprobe_emulate_jmp(p, regs, true); +} +NOKPROBE_SYMBOL(kprobe_emulate_jmp); + +static const unsigned long jcc_mask[6] = { + [0] = X86_EFLAGS_OF, + [1] = X86_EFLAGS_CF, + [2] = X86_EFLAGS_ZF, + [3] = X86_EFLAGS_CF | X86_EFLAGS_ZF, + [4] = X86_EFLAGS_SF, + [5] = X86_EFLAGS_PF, +}; + +static void kprobe_emulate_jcc(struct kprobe *p, struct pt_regs *regs) +{ + bool invert = p->ainsn.jcc.type & 1; + bool match; + + if (p->ainsn.jcc.type < 0xc) { + match = regs->flags & jcc_mask[p->ainsn.jcc.type >> 1]; + } else { + match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^ + ((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT); + if (p->ainsn.jcc.type >= 0xe) + match = match || (regs->flags & X86_EFLAGS_ZF); + } + __kprobe_emulate_jmp(p, regs, (match && !invert) || (!match && invert)); +} +NOKPROBE_SYMBOL(kprobe_emulate_jcc); + +static void kprobe_emulate_loop(struct kprobe *p, struct pt_regs *regs) +{ + bool match; + + if (p->ainsn.loop.type != 3) { /* LOOP* */ + if (p->ainsn.loop.asize == 32) + match = ((*(u32 *)®s->cx)--) != 0; +#ifdef CONFIG_X86_64 + else if (p->ainsn.loop.asize == 64) + match = ((*(u64 *)®s->cx)--) != 0; +#endif + else + match = ((*(u16 *)®s->cx)--) != 0; + } else { /* JCXZ */ + if (p->ainsn.loop.asize == 32) + match = *(u32 *)(®s->cx) == 0; +#ifdef CONFIG_X86_64 + else if (p->ainsn.loop.asize == 64) + match = *(u64 *)(®s->cx) == 0; +#endif + else + match = *(u16 *)(®s->cx) == 0; + } + + if (p->ainsn.loop.type == 0) /* LOOPNE */ + match = match && !(regs->flags & X86_EFLAGS_ZF); + else if (p->ainsn.loop.type == 1) /* LOOPE */ + match = match && (regs->flags & X86_EFLAGS_ZF); + + __kprobe_emulate_jmp(p, regs, match); +} +NOKPROBE_SYMBOL(kprobe_emulate_loop); + +static const int addrmode_regoffs[] = { + offsetof(struct pt_regs, ax), + offsetof(struct pt_regs, cx), + offsetof(struct pt_regs, dx), + offsetof(struct pt_regs, bx), + offsetof(struct pt_regs, sp), + offsetof(struct pt_regs, bp), + offsetof(struct pt_regs, si), + offsetof(struct pt_regs, di), +#ifdef CONFIG_X86_64 + offsetof(struct pt_regs, r8), + offsetof(struct pt_regs, r9), + offsetof(struct pt_regs, r10), + offsetof(struct pt_regs, r11), + offsetof(struct pt_regs, r12), + offsetof(struct pt_regs, r13), + offsetof(struct pt_regs, r14), + offsetof(struct pt_regs, r15), +#endif +}; + +static void kprobe_emulate_call_indirect(struct kprobe *p, struct pt_regs *regs) +{ + unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg]; + + int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + p->ainsn.size); + int3_emulate_jmp(regs, regs_get_register(regs, offs)); +} +NOKPROBE_SYMBOL(kprobe_emulate_call_indirect); + +static void kprobe_emulate_jmp_indirect(struct kprobe *p, struct pt_regs *regs) +{ + unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg]; + + int3_emulate_jmp(regs, regs_get_register(regs, offs)); +} +NOKPROBE_SYMBOL(kprobe_emulate_jmp_indirect); + +static int prepare_emulation(struct kprobe *p, struct insn *insn) +{ + insn_byte_t opcode = insn->opcode.bytes[0]; + + switch (opcode) { + case 0xfa: /* cli */ + case 0xfb: /* sti */ + case 0x9c: /* pushfl */ + case 0x9d: /* popf/popfd */ + /* + * IF modifiers must be emulated since it will enable interrupt while + * int3 single stepping. + */ + p->ainsn.emulate_op = kprobe_emulate_ifmodifiers; + p->ainsn.opcode = opcode; + break; + case 0xc2: /* ret/lret */ + case 0xc3: + case 0xca: + case 0xcb: + p->ainsn.emulate_op = kprobe_emulate_ret; + break; + case 0x9a: /* far call absolute -- segment is not supported */ + case 0xea: /* far jmp absolute -- segment is not supported */ + case 0xcc: /* int3 */ + case 0xcf: /* iret -- in-kernel IRET is not supported */ + return -EOPNOTSUPP; + break; + case 0xe8: /* near call relative */ + p->ainsn.emulate_op = kprobe_emulate_call; + if (insn->immediate.nbytes == 2) + p->ainsn.rel32 = *(s16 *)&insn->immediate.value; + else + p->ainsn.rel32 = *(s32 *)&insn->immediate.value; + break; + case 0xeb: /* short jump relative */ + case 0xe9: /* near jump relative */ + p->ainsn.emulate_op = kprobe_emulate_jmp; + if (insn->immediate.nbytes == 1) + p->ainsn.rel32 = *(s8 *)&insn->immediate.value; + else if (insn->immediate.nbytes == 2) + p->ainsn.rel32 = *(s16 *)&insn->immediate.value; + else + p->ainsn.rel32 = *(s32 *)&insn->immediate.value; + break; + case 0x70 ... 0x7f: + /* 1 byte conditional jump */ + p->ainsn.emulate_op = kprobe_emulate_jcc; + p->ainsn.jcc.type = opcode & 0xf; + p->ainsn.rel32 = *(char *)insn->immediate.bytes; + break; + case 0x0f: + opcode = insn->opcode.bytes[1]; + if ((opcode & 0xf0) == 0x80) { + /* 2 bytes Conditional Jump */ + p->ainsn.emulate_op = kprobe_emulate_jcc; + p->ainsn.jcc.type = opcode & 0xf; + if (insn->immediate.nbytes == 2) + p->ainsn.rel32 = *(s16 *)&insn->immediate.value; + else + p->ainsn.rel32 = *(s32 *)&insn->immediate.value; + } else if (opcode == 0x01 && + X86_MODRM_REG(insn->modrm.bytes[0]) == 0 && + X86_MODRM_MOD(insn->modrm.bytes[0]) == 3) { + /* VM extensions - not supported */ + return -EOPNOTSUPP; + } + break; + case 0xe0: /* Loop NZ */ + case 0xe1: /* Loop */ + case 0xe2: /* Loop */ + case 0xe3: /* J*CXZ */ + p->ainsn.emulate_op = kprobe_emulate_loop; + p->ainsn.loop.type = opcode & 0x3; + p->ainsn.loop.asize = insn->addr_bytes * 8; + p->ainsn.rel32 = *(s8 *)&insn->immediate.value; + break; + case 0xff: + /* + * Since the 0xff is an extended group opcode, the instruction + * is determined by the MOD/RM byte. + */ + opcode = insn->modrm.bytes[0]; + if ((opcode & 0x30) == 0x10) { + if ((opcode & 0x8) == 0x8) + return -EOPNOTSUPP; /* far call */ + /* call absolute, indirect */ + p->ainsn.emulate_op = kprobe_emulate_call_indirect; + } else if ((opcode & 0x30) == 0x20) { + if ((opcode & 0x8) == 0x8) + return -EOPNOTSUPP; /* far jmp */ + /* jmp near absolute indirect */ + p->ainsn.emulate_op = kprobe_emulate_jmp_indirect; + } else + break; + + if (insn->addr_bytes != sizeof(unsigned long)) + return -EOPNOTSUPP; /* Don't support differnt size */ + if (X86_MODRM_MOD(opcode) != 3) + return -EOPNOTSUPP; /* TODO: support memory addressing */ + + p->ainsn.indirect.reg = X86_MODRM_RM(opcode); +#ifdef CONFIG_X86_64 + if (X86_REX_B(insn->rex_prefix.value)) + p->ainsn.indirect.reg += 8; +#endif + break; + default: + break; + } + p->ainsn.size = insn->length; + + return 0; +} + +static int arch_copy_kprobe(struct kprobe *p) +{ + struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + int ret, len; + + /* Copy an instruction with recovering if other optprobe modifies it.*/ + len = __copy_instruction(buf, p->addr, p->ainsn.insn, &insn); + if (!len) + return -EINVAL; + + /* Analyze the opcode and setup emulate functions */ + ret = prepare_emulation(p, &insn); + if (ret < 0) + return ret; + + /* Add int3 for single-step or booster jmp */ + len = prepare_singlestep(buf, p, &insn); + if (len < 0) + return len; + + /* Also, displacement change doesn't affect the first byte */ + p->opcode = buf[0]; + + p->ainsn.tp_len = len; + perf_event_text_poke(p->ainsn.insn, NULL, 0, buf, len); + + /* OK, write back the instruction(s) into ROX insn buffer */ + text_poke(p->ainsn.insn, buf, len); + + return 0; +} + +int arch_prepare_kprobe(struct kprobe *p) +{ + int ret; + + if (alternatives_text_reserved(p->addr, p->addr)) + return -EINVAL; + + if (!can_probe((unsigned long)p->addr)) + return -EILSEQ; + + memset(&p->ainsn, 0, sizeof(p->ainsn)); + + /* insn: must be on special executable page on x86. */ + p->ainsn.insn = get_insn_slot(); + if (!p->ainsn.insn) + return -ENOMEM; + + ret = arch_copy_kprobe(p); + if (ret) { + free_insn_slot(p->ainsn.insn, 0); + p->ainsn.insn = NULL; + } + + return ret; +} + +void arch_arm_kprobe(struct kprobe *p) +{ + u8 int3 = INT3_INSN_OPCODE; + + text_poke(p->addr, &int3, 1); + text_poke_sync(); + perf_event_text_poke(p->addr, &p->opcode, 1, &int3, 1); +} + +void arch_disarm_kprobe(struct kprobe *p) +{ + u8 int3 = INT3_INSN_OPCODE; + + perf_event_text_poke(p->addr, &int3, 1, &p->opcode, 1); + text_poke(p->addr, &p->opcode, 1); + text_poke_sync(); +} + +void arch_remove_kprobe(struct kprobe *p) +{ + if (p->ainsn.insn) { + /* Record the perf event before freeing the slot */ + perf_event_text_poke(p->ainsn.insn, p->ainsn.insn, + p->ainsn.tp_len, NULL, 0); + free_insn_slot(p->ainsn.insn, p->ainsn.boostable); + p->ainsn.insn = NULL; + } +} + +static nokprobe_inline void +save_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + kcb->prev_kprobe.kp = kprobe_running(); + kcb->prev_kprobe.status = kcb->kprobe_status; + kcb->prev_kprobe.old_flags = kcb->kprobe_old_flags; + kcb->prev_kprobe.saved_flags = kcb->kprobe_saved_flags; +} + +static nokprobe_inline void +restore_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); + kcb->kprobe_status = kcb->prev_kprobe.status; + kcb->kprobe_old_flags = kcb->prev_kprobe.old_flags; + kcb->kprobe_saved_flags = kcb->prev_kprobe.saved_flags; +} + +static nokprobe_inline void +set_current_kprobe(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + __this_cpu_write(current_kprobe, p); + kcb->kprobe_saved_flags = kcb->kprobe_old_flags + = (regs->flags & X86_EFLAGS_IF); +} + +void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) +{ + unsigned long *sara = stack_addr(regs); + + ri->ret_addr = (kprobe_opcode_t *) *sara; + ri->fp = sara; + + /* Replace the return addr with trampoline addr */ + *sara = (unsigned long) &kretprobe_trampoline; +} +NOKPROBE_SYMBOL(arch_prepare_kretprobe); + +static void kprobe_post_process(struct kprobe *cur, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + /* Restore back the original saved kprobes variables and continue. */ + if (kcb->kprobe_status == KPROBE_REENTER) { + /* This will restore both kcb and current_kprobe */ + restore_previous_kprobe(kcb); + } else { + /* + * Always update the kcb status because + * reset_curent_kprobe() doesn't update kcb. + */ + kcb->kprobe_status = KPROBE_HIT_SSDONE; + if (cur->post_handler) + cur->post_handler(cur, regs, 0); + reset_current_kprobe(); + } +} +NOKPROBE_SYMBOL(kprobe_post_process); + +static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb, int reenter) +{ + if (setup_detour_execution(p, regs, reenter)) + return; + +#if !defined(CONFIG_PREEMPTION) + if (p->ainsn.boostable) { + /* Boost up -- we can execute copied instructions directly */ + if (!reenter) + reset_current_kprobe(); + /* + * Reentering boosted probe doesn't reset current_kprobe, + * nor set current_kprobe, because it doesn't use single + * stepping. + */ + regs->ip = (unsigned long)p->ainsn.insn; + return; + } +#endif + if (reenter) { + save_previous_kprobe(kcb); + set_current_kprobe(p, regs, kcb); + kcb->kprobe_status = KPROBE_REENTER; + } else + kcb->kprobe_status = KPROBE_HIT_SS; + + if (p->ainsn.emulate_op) { + p->ainsn.emulate_op(p, regs); + kprobe_post_process(p, regs, kcb); + return; + } + + /* Disable interrupt, and set ip register on trampoline */ + regs->flags &= ~X86_EFLAGS_IF; + regs->ip = (unsigned long)p->ainsn.insn; +} +NOKPROBE_SYMBOL(setup_singlestep); + +/* + * Called after single-stepping. p->addr is the address of the + * instruction whose first byte has been replaced by the "int3" + * instruction. To avoid the SMP problems that can occur when we + * temporarily put back the original opcode to single-step, we + * single-stepped a copy of the instruction. The address of this + * copy is p->ainsn.insn. We also doesn't use trap, but "int3" again + * right after the copied instruction. + * Different from the trap single-step, "int3" single-step can not + * handle the instruction which changes the ip register, e.g. jmp, + * call, conditional jmp, and the instructions which changes the IF + * flags because interrupt must be disabled around the single-stepping. + * Such instructions are software emulated, but others are single-stepped + * using "int3". + * + * When the 2nd "int3" handled, the regs->ip and regs->flags needs to + * be adjusted, so that we can resume execution on correct code. + */ +static void resume_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + unsigned long copy_ip = (unsigned long)p->ainsn.insn; + unsigned long orig_ip = (unsigned long)p->addr; + + /* Restore saved interrupt flag and ip register */ + regs->flags |= kcb->kprobe_saved_flags; + /* Note that regs->ip is executed int3 so must be a step back */ + regs->ip += (orig_ip - copy_ip) - INT3_INSN_SIZE; +} +NOKPROBE_SYMBOL(resume_singlestep); + +/* + * We have reentered the kprobe_handler(), since another probe was hit while + * within the handler. We save the original kprobes variables and just single + * step on the instruction of the new probe without calling any user handlers. + */ +static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + switch (kcb->kprobe_status) { + case KPROBE_HIT_SSDONE: + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SS: + kprobes_inc_nmissed_count(p); + setup_singlestep(p, regs, kcb, 1); + break; + case KPROBE_REENTER: + /* A probe has been hit in the codepath leading up to, or just + * after, single-stepping of a probed instruction. This entire + * codepath should strictly reside in .kprobes.text section. + * Raise a BUG or we'll continue in an endless reentering loop + * and eventually a stack overflow. + */ + pr_err("Unrecoverable kprobe detected.\n"); + dump_kprobe(p); + BUG(); + default: + /* impossible cases */ + WARN_ON(1); + return 0; + } + + return 1; +} +NOKPROBE_SYMBOL(reenter_kprobe); + +static nokprobe_inline int kprobe_is_ss(struct kprobe_ctlblk *kcb) +{ + return (kcb->kprobe_status == KPROBE_HIT_SS || + kcb->kprobe_status == KPROBE_REENTER); +} + +/* + * Interrupts are disabled on entry as trap3 is an interrupt gate and they + * remain disabled throughout this function. + */ +int kprobe_int3_handler(struct pt_regs *regs) +{ + kprobe_opcode_t *addr; + struct kprobe *p; + struct kprobe_ctlblk *kcb; + + if (user_mode(regs)) + return 0; + + addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t)); + /* + * We don't want to be preempted for the entire duration of kprobe + * processing. Since int3 and debug trap disables irqs and we clear + * IF while singlestepping, it must be no preemptible. + */ + + kcb = get_kprobe_ctlblk(); + p = get_kprobe(addr); + + if (p) { + if (kprobe_running()) { + if (reenter_kprobe(p, regs, kcb)) + return 1; + } else { + set_current_kprobe(p, regs, kcb); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + + /* + * If we have no pre-handler or it returned 0, we + * continue with normal processing. If we have a + * pre-handler and it returned non-zero, that means + * user handler setup registers to exit to another + * instruction, we must skip the single stepping. + */ + if (!p->pre_handler || !p->pre_handler(p, regs)) + setup_singlestep(p, regs, kcb, 0); + else + reset_current_kprobe(); + return 1; + } + } else if (kprobe_is_ss(kcb)) { + p = kprobe_running(); + if ((unsigned long)p->ainsn.insn < regs->ip && + (unsigned long)p->ainsn.insn + MAX_INSN_SIZE > regs->ip) { + /* Most provably this is the second int3 for singlestep */ + resume_singlestep(p, regs, kcb); + kprobe_post_process(p, regs, kcb); + return 1; + } + } + + if (*addr != INT3_INSN_OPCODE) { + /* + * The breakpoint instruction was removed right + * after we hit it. Another cpu has removed + * either a probepoint or a debugger breakpoint + * at this address. In either case, no further + * handling of this interrupt is appropriate. + * Back up over the (now missing) int3 and run + * the original instruction. + */ + regs->ip = (unsigned long)addr; + return 1; + } /* else: not a kprobe fault; let the kernel handle it */ + + return 0; +} +NOKPROBE_SYMBOL(kprobe_int3_handler); + +/* + * When a retprobed function returns, this code saves registers and + * calls trampoline_handler() runs, which calls the kretprobe's handler. + */ +asm( + ".text\n" + ".global kretprobe_trampoline\n" + ".type kretprobe_trampoline, @function\n" + "kretprobe_trampoline:\n" + /* We don't bother saving the ss register */ +#ifdef CONFIG_X86_64 + " pushq %rsp\n" + " pushfq\n" + SAVE_REGS_STRING + " movq %rsp, %rdi\n" + " call trampoline_handler\n" + /* Replace saved sp with true return address. */ + " movq %rax, 19*8(%rsp)\n" + RESTORE_REGS_STRING + " popfq\n" +#else + " pushl %esp\n" + " pushfl\n" + SAVE_REGS_STRING + " movl %esp, %eax\n" + " call trampoline_handler\n" + /* Replace saved sp with true return address. */ + " movl %eax, 15*4(%esp)\n" + RESTORE_REGS_STRING + " popfl\n" +#endif + ASM_RET + ".size kretprobe_trampoline, .-kretprobe_trampoline\n" +); +NOKPROBE_SYMBOL(kretprobe_trampoline); +STACK_FRAME_NON_STANDARD(kretprobe_trampoline); + + +/* + * Called from kretprobe_trampoline + */ +__used __visible void *trampoline_handler(struct pt_regs *regs) +{ + /* fixup registers */ + regs->cs = __KERNEL_CS; +#ifdef CONFIG_X86_32 + regs->gs = 0; +#endif + regs->ip = (unsigned long)&kretprobe_trampoline; + regs->orig_ax = ~0UL; + + return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, ®s->sp); +} +NOKPROBE_SYMBOL(trampoline_handler); + +int kprobe_fault_handler(struct pt_regs *regs, int trapnr) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + if (unlikely(regs->ip == (unsigned long)cur->ainsn.insn)) { + /* This must happen on single-stepping */ + WARN_ON(kcb->kprobe_status != KPROBE_HIT_SS && + kcb->kprobe_status != KPROBE_REENTER); + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the ip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + regs->ip = (unsigned long)cur->addr; + + /* + * If the IF flag was set before the kprobe hit, + * don't touch it: + */ + regs->flags |= kcb->kprobe_old_flags; + + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else + reset_current_kprobe(); + } else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE || + kcb->kprobe_status == KPROBE_HIT_SSDONE) { + /* + * We increment the nmissed count for accounting, + * we can also use npre/npostfault count for accounting + * these specific fault cases. + */ + kprobes_inc_nmissed_count(cur); + + /* + * We come here because instructions in the pre/post + * handler caused the page_fault, this could happen + * if handler tries to access user space by + * copy_from_user(), get_user() etc. Let the + * user-specified handler try to fix it first. + */ + if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) + return 1; + } + + return 0; +} +NOKPROBE_SYMBOL(kprobe_fault_handler); + +int __init arch_populate_kprobe_blacklist(void) +{ + return kprobe_add_area_blacklist((unsigned long)__entry_text_start, + (unsigned long)__entry_text_end); +} + +int __init arch_init_kprobes(void) +{ + return 0; +} + +int arch_trampoline_kprobe(struct kprobe *p) +{ + return 0; +} diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c new file mode 100644 index 000000000..681a4b36e --- /dev/null +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Dynamic Ftrace based Kprobes Optimization + * + * Copyright (C) Hitachi Ltd., 2012 + */ +#include <linux/kprobes.h> +#include <linux/ptrace.h> +#include <linux/hardirq.h> +#include <linux/preempt.h> +#include <linux/ftrace.h> + +#include "common.h" + +/* Ftrace callback handler for kprobes -- called under preepmt disabed */ +void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) +{ + struct kprobe *p; + struct kprobe_ctlblk *kcb; + + /* Preempt is disabled by ftrace */ + p = get_kprobe((kprobe_opcode_t *)ip); + if (unlikely(!p) || kprobe_disabled(p)) + return; + + kcb = get_kprobe_ctlblk(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(p); + } else { + unsigned long orig_ip = regs->ip; + /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */ + regs->ip = ip + sizeof(kprobe_opcode_t); + + __this_cpu_write(current_kprobe, p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + if (!p->pre_handler || !p->pre_handler(p, regs)) { + /* + * Emulate singlestep (and also recover regs->ip) + * as if there is a 5byte nop + */ + regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE; + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + regs->ip = orig_ip; + } + /* + * If pre_handler returns !0, it changes regs->ip. We have to + * skip emulating post_handler. + */ + __this_cpu_write(current_kprobe, NULL); + } +} +NOKPROBE_SYMBOL(kprobe_ftrace_handler); + +int arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + p->ainsn.insn = NULL; + p->ainsn.boostable = false; + return 0; +} diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c new file mode 100644 index 000000000..e37e5e824 --- /dev/null +++ b/arch/x86/kernel/kprobes/opt.c @@ -0,0 +1,556 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Kernel Probes Jump Optimization (Optprobes) + * + * Copyright (C) IBM Corporation, 2002, 2004 + * Copyright (C) Hitachi Ltd., 2012 + */ +#include <linux/kprobes.h> +#include <linux/perf_event.h> +#include <linux/ptrace.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/hardirq.h> +#include <linux/preempt.h> +#include <linux/extable.h> +#include <linux/kdebug.h> +#include <linux/kallsyms.h> +#include <linux/kgdb.h> +#include <linux/ftrace.h> +#include <linux/objtool.h> +#include <linux/pgtable.h> +#include <linux/static_call.h> + +#include <asm/text-patching.h> +#include <asm/cacheflush.h> +#include <asm/desc.h> +#include <linux/uaccess.h> +#include <asm/alternative.h> +#include <asm/insn.h> +#include <asm/debugreg.h> +#include <asm/set_memory.h> +#include <asm/sections.h> +#include <asm/nospec-branch.h> + +#include "common.h" + +unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) +{ + struct optimized_kprobe *op; + struct kprobe *kp; + long offs; + int i; + + for (i = 0; i < JMP32_INSN_SIZE; i++) { + kp = get_kprobe((void *)addr - i); + /* This function only handles jump-optimized kprobe */ + if (kp && kprobe_optimized(kp)) { + op = container_of(kp, struct optimized_kprobe, kp); + /* If op is optimized or under unoptimizing */ + if (list_empty(&op->list) || optprobe_queued_unopt(op)) + goto found; + } + } + + return addr; +found: + /* + * If the kprobe can be optimized, original bytes which can be + * overwritten by jump destination address. In this case, original + * bytes must be recovered from op->optinsn.copied_insn buffer. + */ + if (copy_from_kernel_nofault(buf, (void *)addr, + MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) + return 0UL; + + if (addr == (unsigned long)kp->addr) { + buf[0] = kp->opcode; + memcpy(buf + 1, op->optinsn.copied_insn, DISP32_SIZE); + } else { + offs = addr - (unsigned long)kp->addr - 1; + memcpy(buf, op->optinsn.copied_insn + offs, DISP32_SIZE - offs); + } + + return (unsigned long)buf; +} + +static void synthesize_clac(kprobe_opcode_t *addr) +{ + /* + * Can't be static_cpu_has() due to how objtool treats this feature bit. + * This isn't a fast path anyway. + */ + if (!boot_cpu_has(X86_FEATURE_SMAP)) + return; + + /* Replace the NOP3 with CLAC */ + addr[0] = 0x0f; + addr[1] = 0x01; + addr[2] = 0xca; +} + +/* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */ +static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) +{ +#ifdef CONFIG_X86_64 + *addr++ = 0x48; + *addr++ = 0xbf; +#else + *addr++ = 0xb8; +#endif + *(unsigned long *)addr = val; +} + +asm ( + ".pushsection .rodata\n" + "optprobe_template_func:\n" + ".global optprobe_template_entry\n" + "optprobe_template_entry:\n" +#ifdef CONFIG_X86_64 + /* We don't bother saving the ss register */ + " pushq %rsp\n" + " pushfq\n" + ".global optprobe_template_clac\n" + "optprobe_template_clac:\n" + ASM_NOP3 + SAVE_REGS_STRING + " movq %rsp, %rsi\n" + ".global optprobe_template_val\n" + "optprobe_template_val:\n" + ASM_NOP5 + ASM_NOP5 + ".global optprobe_template_call\n" + "optprobe_template_call:\n" + ASM_NOP5 + /* Move flags to rsp */ + " movq 18*8(%rsp), %rdx\n" + " movq %rdx, 19*8(%rsp)\n" + RESTORE_REGS_STRING + /* Skip flags entry */ + " addq $8, %rsp\n" + " popfq\n" +#else /* CONFIG_X86_32 */ + " pushl %esp\n" + " pushfl\n" + ".global optprobe_template_clac\n" + "optprobe_template_clac:\n" + ASM_NOP3 + SAVE_REGS_STRING + " movl %esp, %edx\n" + ".global optprobe_template_val\n" + "optprobe_template_val:\n" + ASM_NOP5 + ".global optprobe_template_call\n" + "optprobe_template_call:\n" + ASM_NOP5 + /* Move flags into esp */ + " movl 14*4(%esp), %edx\n" + " movl %edx, 15*4(%esp)\n" + RESTORE_REGS_STRING + /* Skip flags entry */ + " addl $4, %esp\n" + " popfl\n" +#endif + ".global optprobe_template_end\n" + "optprobe_template_end:\n" + ".popsection\n"); + +void optprobe_template_func(void); +STACK_FRAME_NON_STANDARD(optprobe_template_func); + +#define TMPL_CLAC_IDX \ + ((long)optprobe_template_clac - (long)optprobe_template_entry) +#define TMPL_MOVE_IDX \ + ((long)optprobe_template_val - (long)optprobe_template_entry) +#define TMPL_CALL_IDX \ + ((long)optprobe_template_call - (long)optprobe_template_entry) +#define TMPL_END_IDX \ + ((long)optprobe_template_end - (long)optprobe_template_entry) + +/* Optimized kprobe call back function: called from optinsn */ +static void +optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) +{ + /* This is possible if op is under delayed unoptimizing */ + if (kprobe_disabled(&op->kp)) + return; + + preempt_disable(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(&op->kp); + } else { + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + /* Save skipped registers */ + regs->cs = __KERNEL_CS; +#ifdef CONFIG_X86_32 + regs->gs = 0; +#endif + regs->ip = (unsigned long)op->kp.addr + INT3_INSN_SIZE; + regs->orig_ax = ~0UL; + + __this_cpu_write(current_kprobe, &op->kp); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + opt_pre_handler(&op->kp, regs); + __this_cpu_write(current_kprobe, NULL); + } + preempt_enable(); +} +NOKPROBE_SYMBOL(optimized_callback); + +static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real) +{ + struct insn insn; + int len = 0, ret; + + while (len < JMP32_INSN_SIZE) { + ret = __copy_instruction(dest + len, src + len, real + len, &insn); + if (!ret || !can_boost(&insn, src + len)) + return -EINVAL; + len += ret; + } + /* Check whether the address range is reserved */ + if (ftrace_text_reserved(src, src + len - 1) || + alternatives_text_reserved(src, src + len - 1) || + jump_label_text_reserved(src, src + len - 1) || + static_call_text_reserved(src, src + len - 1)) + return -EBUSY; + + return len; +} + +/* Check whether insn is indirect jump */ +static int __insn_is_indirect_jump(struct insn *insn) +{ + return ((insn->opcode.bytes[0] == 0xff && + (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ + insn->opcode.bytes[0] == 0xea); /* Segment based jump */ +} + +/* Check whether insn jumps into specified address range */ +static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) +{ + unsigned long target = 0; + + switch (insn->opcode.bytes[0]) { + case 0xe0: /* loopne */ + case 0xe1: /* loope */ + case 0xe2: /* loop */ + case 0xe3: /* jcxz */ + case 0xe9: /* near relative jump */ + case 0xeb: /* short relative jump */ + break; + case 0x0f: + if ((insn->opcode.bytes[1] & 0xf0) == 0x80) /* jcc near */ + break; + return 0; + default: + if ((insn->opcode.bytes[0] & 0xf0) == 0x70) /* jcc short */ + break; + return 0; + } + target = (unsigned long)insn->next_byte + insn->immediate.value; + + return (start <= target && target <= start + len); +} + +static int insn_is_indirect_jump(struct insn *insn) +{ + int ret = __insn_is_indirect_jump(insn); + +#ifdef CONFIG_RETPOLINE + /* + * Jump to x86_indirect_thunk_* is treated as an indirect jump. + * Note that even with CONFIG_RETPOLINE=y, the kernel compiled with + * older gcc may use indirect jump. So we add this check instead of + * replace indirect-jump check. + */ + if (!ret) + ret = insn_jump_into_range(insn, + (unsigned long)__indirect_thunk_start, + (unsigned long)__indirect_thunk_end - + (unsigned long)__indirect_thunk_start); +#endif + return ret; +} + +/* Decode whole function to ensure any instructions don't jump into target */ +static int can_optimize(unsigned long paddr) +{ + unsigned long addr, size = 0, offset = 0; + struct insn insn; + kprobe_opcode_t buf[MAX_INSN_SIZE]; + + /* Lookup symbol including addr */ + if (!kallsyms_lookup_size_offset(paddr, &size, &offset)) + return 0; + + /* + * Do not optimize in the entry code due to the unstable + * stack handling and registers setup. + */ + if (((paddr >= (unsigned long)__entry_text_start) && + (paddr < (unsigned long)__entry_text_end))) + return 0; + + /* Check there is enough space for a relative jump. */ + if (size - offset < JMP32_INSN_SIZE) + return 0; + + /* Decode instructions */ + addr = paddr - offset; + while (addr < paddr - offset + size) { /* Decode until function end */ + unsigned long recovered_insn; + int ret; + + if (search_exception_tables(addr)) + /* + * Since some fixup code will jumps into this function, + * we can't optimize kprobe in this function. + */ + return 0; + recovered_insn = recover_probed_instruction(buf, addr); + if (!recovered_insn) + return 0; + + ret = insn_decode(&insn, (void *)recovered_insn, MAX_INSN_SIZE, INSN_MODE_KERN); + if (ret < 0) + return 0; +#ifdef CONFIG_KGDB + /* + * If there is a dynamically installed kgdb sw breakpoint, + * this function should not be probed. + */ + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE && + kgdb_has_hit_break(addr)) + return 0; +#endif + /* Recover address */ + insn.kaddr = (void *)addr; + insn.next_byte = (void *)(addr + insn.length); + /* Check any instructions don't jump into target */ + if (insn_is_indirect_jump(&insn) || + insn_jump_into_range(&insn, paddr + INT3_INSN_SIZE, + DISP32_SIZE)) + return 0; + addr += insn.length; + } + + return 1; +} + +/* Check optimized_kprobe can actually be optimized. */ +int arch_check_optimized_kprobe(struct optimized_kprobe *op) +{ + int i; + struct kprobe *p; + + for (i = 1; i < op->optinsn.size; i++) { + p = get_kprobe(op->kp.addr + i); + if (p && !kprobe_disarmed(p)) + return -EEXIST; + } + + return 0; +} + +/* Check the addr is within the optimized instructions. */ +int arch_within_optimized_kprobe(struct optimized_kprobe *op, + unsigned long addr) +{ + return ((unsigned long)op->kp.addr <= addr && + (unsigned long)op->kp.addr + op->optinsn.size > addr); +} + +/* Free optimized instruction slot */ +static +void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) +{ + u8 *slot = op->optinsn.insn; + if (slot) { + int len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE; + + /* Record the perf event before freeing the slot */ + if (dirty) + perf_event_text_poke(slot, slot, len, NULL, 0); + + free_optinsn_slot(slot, dirty); + op->optinsn.insn = NULL; + op->optinsn.size = 0; + } +} + +void arch_remove_optimized_kprobe(struct optimized_kprobe *op) +{ + __arch_remove_optimized_kprobe(op, 1); +} + +/* + * Copy replacing target instructions + * Target instructions MUST be relocatable (checked inside) + * This is called when new aggr(opt)probe is allocated or reused. + */ +int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, + struct kprobe *__unused) +{ + u8 *buf = NULL, *slot; + int ret, len; + long rel; + + if (!can_optimize((unsigned long)op->kp.addr)) + return -EILSEQ; + + buf = kzalloc(MAX_OPTINSN_SIZE, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + op->optinsn.insn = slot = get_optinsn_slot(); + if (!slot) { + ret = -ENOMEM; + goto out; + } + + /* + * Verify if the address gap is in 2GB range, because this uses + * a relative jump. + */ + rel = (long)slot - (long)op->kp.addr + JMP32_INSN_SIZE; + if (abs(rel) > 0x7fffffff) { + ret = -ERANGE; + goto err; + } + + /* Copy arch-dep-instance from template */ + memcpy(buf, optprobe_template_entry, TMPL_END_IDX); + + /* Copy instructions into the out-of-line buffer */ + ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr, + slot + TMPL_END_IDX); + if (ret < 0) + goto err; + op->optinsn.size = ret; + len = TMPL_END_IDX + op->optinsn.size; + + synthesize_clac(buf + TMPL_CLAC_IDX); + + /* Set probe information */ + synthesize_set_arg1(buf + TMPL_MOVE_IDX, (unsigned long)op); + + /* Set probe function call */ + synthesize_relcall(buf + TMPL_CALL_IDX, + slot + TMPL_CALL_IDX, optimized_callback); + + /* Set returning jmp instruction at the tail of out-of-line buffer */ + synthesize_reljump(buf + len, slot + len, + (u8 *)op->kp.addr + op->optinsn.size); + len += JMP32_INSN_SIZE; + + /* + * Note len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE is also + * used in __arch_remove_optimized_kprobe(). + */ + + /* We have to use text_poke() for instruction buffer because it is RO */ + perf_event_text_poke(slot, NULL, 0, buf, len); + text_poke(slot, buf, len); + + ret = 0; +out: + kfree(buf); + return ret; + +err: + __arch_remove_optimized_kprobe(op, 0); + goto out; +} + +/* + * Replace breakpoints (INT3) with relative jumps (JMP.d32). + * Caller must call with locking kprobe_mutex and text_mutex. + * + * The caller will have installed a regular kprobe and after that issued + * syncrhonize_rcu_tasks(), this ensures that the instruction(s) that live in + * the 4 bytes after the INT3 are unused and can now be overwritten. + */ +void arch_optimize_kprobes(struct list_head *oplist) +{ + struct optimized_kprobe *op, *tmp; + u8 insn_buff[JMP32_INSN_SIZE]; + + list_for_each_entry_safe(op, tmp, oplist, list) { + s32 rel = (s32)((long)op->optinsn.insn - + ((long)op->kp.addr + JMP32_INSN_SIZE)); + + WARN_ON(kprobe_disabled(&op->kp)); + + /* Backup instructions which will be replaced by jump address */ + memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_INSN_SIZE, + DISP32_SIZE); + + insn_buff[0] = JMP32_INSN_OPCODE; + *(s32 *)(&insn_buff[1]) = rel; + + text_poke_bp(op->kp.addr, insn_buff, JMP32_INSN_SIZE, NULL); + + list_del_init(&op->list); + } +} + +/* + * Replace a relative jump (JMP.d32) with a breakpoint (INT3). + * + * After that, we can restore the 4 bytes after the INT3 to undo what + * arch_optimize_kprobes() scribbled. This is safe since those bytes will be + * unused once the INT3 lands. + */ +void arch_unoptimize_kprobe(struct optimized_kprobe *op) +{ + u8 new[JMP32_INSN_SIZE] = { INT3_INSN_OPCODE, }; + u8 old[JMP32_INSN_SIZE]; + u8 *addr = op->kp.addr; + + memcpy(old, op->kp.addr, JMP32_INSN_SIZE); + memcpy(new + INT3_INSN_SIZE, + op->optinsn.copied_insn, + JMP32_INSN_SIZE - INT3_INSN_SIZE); + + text_poke(addr, new, INT3_INSN_SIZE); + text_poke_sync(); + text_poke(addr + INT3_INSN_SIZE, + new + INT3_INSN_SIZE, + JMP32_INSN_SIZE - INT3_INSN_SIZE); + text_poke_sync(); + + perf_event_text_poke(op->kp.addr, old, JMP32_INSN_SIZE, new, JMP32_INSN_SIZE); +} + +/* + * Recover original instructions and breakpoints from relative jumps. + * Caller must call with locking kprobe_mutex. + */ +extern void arch_unoptimize_kprobes(struct list_head *oplist, + struct list_head *done_list) +{ + struct optimized_kprobe *op, *tmp; + + list_for_each_entry_safe(op, tmp, oplist, list) { + arch_unoptimize_kprobe(op); + list_move(&op->list, done_list); + } +} + +int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) +{ + struct optimized_kprobe *op; + + if (p->flags & KPROBE_FLAG_OPTIMIZED) { + /* This kprobe is really able to run optimized path. */ + op = container_of(p, struct optimized_kprobe, kp); + /* Detour through copied instructions */ + regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX; + if (!reenter) + reset_current_kprobe(); + return 1; + } + return 0; +} +NOKPROBE_SYMBOL(setup_detour_execution); |