diff options
Diffstat (limited to 'arch/x86/kernel/alternative.c')
| -rw-r--r-- | arch/x86/kernel/alternative.c | 578 |
1 files changed, 340 insertions, 238 deletions
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index aae7456ece07..c71b575bf229 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -30,6 +30,7 @@ #include <asm/fixmap.h> #include <asm/paravirt.h> #include <asm/asm-prototypes.h> +#include <asm/cfi.h> int __read_mostly alternatives_patched; @@ -44,7 +45,7 @@ EXPORT_SYMBOL_GPL(alternatives_patched); #define DA_ENDBR 0x08 #define DA_SMP 0x10 -static unsigned int __initdata_or_module debug_alternative; +static unsigned int debug_alternative; static int __init debug_alt(char *str) { @@ -124,6 +125,20 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] = }; /* + * Nomenclature for variable names to simplify and clarify this code and ease + * any potential staring at it: + * + * @instr: source address of the original instructions in the kernel text as + * generated by the compiler. + * + * @buf: temporary buffer on which the patching operates. This buffer is + * eventually text-poked into the kernel image. + * + * @replacement/@repl: pointer to the opcodes which are replacing @instr, located + * in the .altinstr_replacement section. + */ + +/* * Fill the buffer with a single effective instruction of size @len. * * In order not to issue an ORC stack depth tracking CFI entry (Call Frame Info) @@ -132,35 +147,34 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] = * each single-byte NOPs). If @len to fill out is > ASM_NOP_MAX, pad with INT3 and * *jump* over instead of executing long and daft NOPs. */ -static void __init_or_module add_nop(u8 *instr, unsigned int len) +static void add_nop(u8 *buf, unsigned int len) { - u8 *target = instr + len; + u8 *target = buf + len; if (!len) return; if (len <= ASM_NOP_MAX) { - memcpy(instr, x86_nops[len], len); + memcpy(buf, x86_nops[len], len); return; } if (len < 128) { - __text_gen_insn(instr, JMP8_INSN_OPCODE, instr, target, JMP8_INSN_SIZE); - instr += JMP8_INSN_SIZE; + __text_gen_insn(buf, JMP8_INSN_OPCODE, buf, target, JMP8_INSN_SIZE); + buf += JMP8_INSN_SIZE; } else { - __text_gen_insn(instr, JMP32_INSN_OPCODE, instr, target, JMP32_INSN_SIZE); - instr += JMP32_INSN_SIZE; + __text_gen_insn(buf, JMP32_INSN_OPCODE, buf, target, JMP32_INSN_SIZE); + buf += JMP32_INSN_SIZE; } - for (;instr < target; instr++) - *instr = INT3_INSN_OPCODE; + for (;buf < target; buf++) + *buf = INT3_INSN_OPCODE; } extern s32 __retpoline_sites[], __retpoline_sites_end[]; extern s32 __return_sites[], __return_sites_end[]; extern s32 __cfi_sites[], __cfi_sites_end[]; extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[]; -extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; void text_poke_early(void *addr, const void *opcode, size_t len); @@ -187,12 +201,12 @@ static bool insn_is_nop(struct insn *insn) * Find the offset of the first non-NOP instruction starting at @offset * but no further than @len. */ -static int skip_nops(u8 *instr, int offset, int len) +static int skip_nops(u8 *buf, int offset, int len) { struct insn insn; for (; offset < len; offset += insn.length) { - if (insn_decode_kernel(&insn, &instr[offset])) + if (insn_decode_kernel(&insn, &buf[offset])) break; if (!insn_is_nop(&insn)) @@ -203,66 +217,32 @@ static int skip_nops(u8 *instr, int offset, int len) } /* - * Optimize a sequence of NOPs, possibly preceded by an unconditional jump - * to the end of the NOP sequence into a single NOP. - */ -static bool __init_or_module -__optimize_nops(u8 *instr, size_t len, struct insn *insn, int *next, int *prev, int *target) -{ - int i = *next - insn->length; - - switch (insn->opcode.bytes[0]) { - case JMP8_INSN_OPCODE: - case JMP32_INSN_OPCODE: - *prev = i; - *target = *next + insn->immediate.value; - return false; - } - - if (insn_is_nop(insn)) { - int nop = i; - - *next = skip_nops(instr, *next, len); - if (*target && *next == *target) - nop = *prev; - - add_nop(instr + nop, *next - nop); - DUMP_BYTES(ALT, instr, len, "%px: [%d:%d) optimized NOPs: ", instr, nop, *next); - return true; - } - - *target = 0; - return false; -} - -/* * "noinline" to cause control flow change and thus invalidate I$ and * cause refetch after modification. */ -static void __init_or_module noinline optimize_nops(u8 *instr, size_t len) +static void noinline optimize_nops(const u8 * const instr, u8 *buf, size_t len) { - int prev, target = 0; - for (int next, i = 0; i < len; i = next) { struct insn insn; - if (insn_decode_kernel(&insn, &instr[i])) + if (insn_decode_kernel(&insn, &buf[i])) return; next = i + insn.length; - __optimize_nops(instr, len, &insn, &next, &prev, &target); - } -} + if (insn_is_nop(&insn)) { + int nop = i; -static void __init_or_module noinline optimize_nops_inplace(u8 *instr, size_t len) -{ - unsigned long flags; + /* Has the NOP already been optimized? */ + if (i + insn.length == len) + return; - local_irq_save(flags); - optimize_nops(instr, len); - sync_core(); - local_irq_restore(flags); + next = skip_nops(buf, next, len); + + add_nop(buf + nop, next - nop); + DUMP_BYTES(ALT, buf, len, "%px: [%d:%d) optimized NOPs: ", instr, nop, next); + } + } } /* @@ -335,12 +315,9 @@ bool need_reloc(unsigned long offset, u8 *src, size_t src_len) return (target < src || target > src + src_len); } -static void __init_or_module noinline -apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) +static void __apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len) { - int prev, target = 0; - - for (int next, i = 0; i < len; i = next) { + for (int next, i = 0; i < instrlen; i = next) { struct insn insn; if (WARN_ON_ONCE(insn_decode_kernel(&insn, &buf[i]))) @@ -348,9 +325,6 @@ apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) next = i + insn.length; - if (__optimize_nops(buf, len, &insn, &next, &prev, &target)) - continue; - switch (insn.opcode.bytes[0]) { case 0x0f: if (insn.opcode.bytes[1] < 0x80 || @@ -362,10 +336,10 @@ apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) case JMP8_INSN_OPCODE: case JMP32_INSN_OPCODE: case CALL_INSN_OPCODE: - if (need_reloc(next + insn.immediate.value, src, src_len)) { + if (need_reloc(next + insn.immediate.value, repl, repl_len)) { apply_reloc(insn.immediate.nbytes, buf + i + insn_offset_immediate(&insn), - src - dest); + repl - instr); } /* @@ -373,7 +347,7 @@ apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) */ if (insn.opcode.bytes[0] == JMP32_INSN_OPCODE) { s32 imm = insn.immediate.value; - imm += src - dest; + imm += repl - instr; imm += JMP32_INSN_SIZE - JMP8_INSN_SIZE; if ((imm >> 31) == (imm >> 7)) { buf[i+0] = JMP8_INSN_OPCODE; @@ -386,15 +360,85 @@ apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) } if (insn_rip_relative(&insn)) { - if (need_reloc(next + insn.displacement.value, src, src_len)) { + if (need_reloc(next + insn.displacement.value, repl, repl_len)) { apply_reloc(insn.displacement.nbytes, buf + i + insn_offset_displacement(&insn), - src - dest); + repl - instr); } } } } +void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len) +{ + __apply_relocation(buf, instr, instrlen, repl, repl_len); + optimize_nops(instr, buf, instrlen); +} + +/* Low-level backend functions usable from alternative code replacements. */ +DEFINE_ASM_FUNC(nop_func, "", .entry.text); +EXPORT_SYMBOL_GPL(nop_func); + +noinstr void BUG_func(void) +{ + BUG(); +} +EXPORT_SYMBOL(BUG_func); + +#define CALL_RIP_REL_OPCODE 0xff +#define CALL_RIP_REL_MODRM 0x15 + +/* + * Rewrite the "call BUG_func" replacement to point to the target of the + * indirect pv_ops call "call *disp(%ip)". + */ +static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a, + struct module *mod) +{ + u8 *wr_instr = module_writable_address(mod, instr); + void *target, *bug = &BUG_func; + s32 disp; + + if (a->replacementlen != 5 || insn_buff[0] != CALL_INSN_OPCODE) { + pr_err("ALT_FLAG_DIRECT_CALL set for a non-call replacement instruction\n"); + BUG(); + } + + if (a->instrlen != 6 || + wr_instr[0] != CALL_RIP_REL_OPCODE || + wr_instr[1] != CALL_RIP_REL_MODRM) { + pr_err("ALT_FLAG_DIRECT_CALL set for unrecognized indirect call\n"); + BUG(); + } + + /* Skip CALL_RIP_REL_OPCODE and CALL_RIP_REL_MODRM */ + disp = *(s32 *)(wr_instr + 2); +#ifdef CONFIG_X86_64 + /* ff 15 00 00 00 00 call *0x0(%rip) */ + /* target address is stored at "next instruction + disp". */ + target = *(void **)(instr + a->instrlen + disp); +#else + /* ff 15 00 00 00 00 call *0x0 */ + /* target address is stored at disp. */ + target = *(void **)disp; +#endif + if (!target) + target = bug; + + /* (BUG_func - .) + (target - BUG_func) := target - . */ + *(s32 *)(insn_buff + 1) += target - bug; + + if (target == &nop_func) + return 0; + + return 5; +} + +static inline u8 * instr_va(struct alt_instr *i) +{ + return (u8 *)&i->instr_offset + i->instr_offset; +} + /* * Replace instructions with better alternatives for this CPU type. This runs * before SMP is initialized to avoid SMP problems with self modifying code. @@ -406,11 +450,12 @@ apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) * to refetch changed I$ lines. */ void __init_or_module noinline apply_alternatives(struct alt_instr *start, - struct alt_instr *end) + struct alt_instr *end, + struct module *mod) { - struct alt_instr *a; - u8 *instr, *replacement; u8 insn_buff[MAX_PATCH_LEN]; + u8 *instr, *replacement; + struct alt_instr *a, *b; DPRINTK(ALT, "alt table %px, -> %px", start, end); @@ -435,9 +480,25 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, */ for (a = start; a < end; a++) { int insn_buff_sz = 0; + u8 *wr_instr, *wr_replacement; + + /* + * In case of nested ALTERNATIVE()s the outer alternative might + * add more padding. To ensure consistent patching find the max + * padding for all alt_instr entries for this site (nested + * alternatives result in consecutive entries). + */ + for (b = a+1; b < end && instr_va(b) == instr_va(a); b++) { + u8 len = max(a->instrlen, b->instrlen); + a->instrlen = b->instrlen = len; + } + + instr = instr_va(a); + wr_instr = module_writable_address(mod, instr); - instr = (u8 *)&a->instr_offset + a->instr_offset; replacement = (u8 *)&a->repl_offset + a->repl_offset; + wr_replacement = module_writable_address(mod, replacement); + BUG_ON(a->instrlen > sizeof(insn_buff)); BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32); @@ -448,30 +509,38 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, * patch if feature is *NOT* present. */ if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) { - optimize_nops_inplace(instr, a->instrlen); + memcpy(insn_buff, wr_instr, a->instrlen); + optimize_nops(instr, insn_buff, a->instrlen); + text_poke_early(wr_instr, insn_buff, a->instrlen); continue; } - DPRINTK(ALT, "feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d)", - (a->flags & ALT_FLAG_NOT) ? "!" : "", + DPRINTK(ALT, "feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d) flags: 0x%x", a->cpuid >> 5, a->cpuid & 0x1f, instr, instr, a->instrlen, - replacement, a->replacementlen); + replacement, a->replacementlen, a->flags); - memcpy(insn_buff, replacement, a->replacementlen); + memcpy(insn_buff, wr_replacement, a->replacementlen); insn_buff_sz = a->replacementlen; + if (a->flags & ALT_FLAG_DIRECT_CALL) { + insn_buff_sz = alt_replace_call(instr, insn_buff, a, + mod); + if (insn_buff_sz < 0) + continue; + } + for (; insn_buff_sz < a->instrlen; insn_buff_sz++) insn_buff[insn_buff_sz] = 0x90; - apply_relocation(insn_buff, a->instrlen, instr, replacement, a->replacementlen); + apply_relocation(insn_buff, instr, a->instrlen, replacement, a->replacementlen); - DUMP_BYTES(ALT, instr, a->instrlen, "%px: old_insn: ", instr); + DUMP_BYTES(ALT, wr_instr, a->instrlen, "%px: old_insn: ", instr); DUMP_BYTES(ALT, replacement, a->replacementlen, "%px: rpl_insn: ", replacement); DUMP_BYTES(ALT, insn_buff, insn_buff_sz, "%px: final_insn: ", instr); - text_poke_early(instr, insn_buff, insn_buff_sz); + text_poke_early(wr_instr, insn_buff, insn_buff_sz); } kasan_enable_current(); @@ -483,7 +552,7 @@ static inline bool is_jcc32(struct insn *insn) return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80; } -#if defined(CONFIG_RETPOLINE) && defined(CONFIG_OBJTOOL) +#if defined(CONFIG_MITIGATION_RETPOLINE) && defined(CONFIG_OBJTOOL) /* * CALL/JMP *%\reg @@ -647,8 +716,8 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) /* * The compiler is supposed to EMIT an INT3 after every unconditional * JMP instruction due to AMD BTC. However, if the compiler is too old - * or SLS isn't enabled, we still need an INT3 after indirect JMPs - * even on Intel. + * or MITIGATION_SLS isn't enabled, we still need an INT3 after + * indirect JMPs even on Intel. */ if (op == JMP32_INSN_OPCODE && i < insn->length) bytes[i++] = INT3_INSN_OPCODE; @@ -662,18 +731,20 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) /* * Generated by 'objtool --retpoline'. */ -void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) +void __init_or_module noinline apply_retpolines(s32 *start, s32 *end, + struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr = module_writable_address(mod, addr); struct insn insn; int len, ret; u8 bytes[16]; u8 op1, op2; - ret = insn_decode_kernel(&insn, addr); + ret = insn_decode_kernel(&insn, wr_addr); if (WARN_ON_ONCE(ret < 0)) continue; @@ -700,15 +771,15 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) len = patch_retpoline(addr, &insn, bytes); if (len == insn.length) { - optimize_nops(bytes, len); - DUMP_BYTES(RETPOLINE, ((u8*)addr), len, "%px: orig: ", addr); + optimize_nops(addr, bytes, len); + DUMP_BYTES(RETPOLINE, ((u8*)wr_addr), len, "%px: orig: ", addr); DUMP_BYTES(RETPOLINE, ((u8*)bytes), len, "%px: repl: ", addr); - text_poke_early(addr, bytes, len); + text_poke_early(wr_addr, bytes, len); } } } -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK /* * Rewrite the compiler generated return thunk tail-calls. @@ -739,7 +810,8 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) return i; } -void __init_or_module noinline apply_returns(s32 *start, s32 *end) +void __init_or_module noinline apply_returns(s32 *start, s32 *end, + struct module *mod) { s32 *s; @@ -748,12 +820,13 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) for (s = start; s < end; s++) { void *dest = NULL, *addr = (void *)s + *s; + void *wr_addr = module_writable_address(mod, addr); struct insn insn; int len, ret; u8 bytes[16]; u8 op; - ret = insn_decode_kernel(&insn, addr); + ret = insn_decode_kernel(&insn, wr_addr); if (WARN_ON_ONCE(ret < 0)) continue; @@ -773,32 +846,35 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) len = patch_return(addr, &insn, bytes); if (len == insn.length) { - DUMP_BYTES(RET, ((u8*)addr), len, "%px: orig: ", addr); + DUMP_BYTES(RET, ((u8*)wr_addr), len, "%px: orig: ", addr); DUMP_BYTES(RET, ((u8*)bytes), len, "%px: repl: ", addr); - text_poke_early(addr, bytes, len); + text_poke_early(wr_addr, bytes, len); } } } #else -void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } -#endif /* CONFIG_RETHUNK */ +void __init_or_module noinline apply_returns(s32 *start, s32 *end, + struct module *mod) { } +#endif /* CONFIG_MITIGATION_RETHUNK */ -#else /* !CONFIG_RETPOLINE || !CONFIG_OBJTOOL */ +#else /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */ -void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { } -void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } +void __init_or_module noinline apply_retpolines(s32 *start, s32 *end, + struct module *mod) { } +void __init_or_module noinline apply_returns(s32 *start, s32 *end, + struct module *mod) { } -#endif /* CONFIG_RETPOLINE && CONFIG_OBJTOOL */ +#endif /* CONFIG_MITIGATION_RETPOLINE && CONFIG_OBJTOOL */ #ifdef CONFIG_X86_KERNEL_IBT -static void poison_cfi(void *addr); +static void poison_cfi(void *addr, void *wr_addr); -static void __init_or_module poison_endbr(void *addr, bool warn) +static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn) { u32 endbr, poison = gen_endbr_poison(); - if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr))) + if (WARN_ON_ONCE(get_kernel_nofault(endbr, wr_addr))) return; if (!is_endbr(endbr)) { @@ -813,7 +889,7 @@ static void __init_or_module poison_endbr(void *addr, bool warn) */ DUMP_BYTES(ENDBR, ((u8*)addr), 4, "%px: orig: ", addr); DUMP_BYTES(ENDBR, ((u8*)&poison), 4, "%px: repl: ", addr); - text_poke_early(addr, &poison, 4); + text_poke_early(wr_addr, &poison, 4); } /* @@ -822,35 +898,103 @@ static void __init_or_module poison_endbr(void *addr, bool warn) * Seal the functions for indirect calls by clobbering the ENDBR instructions * and the kCFI hash value. */ -void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end) +void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end, struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr = module_writable_address(mod, addr); - poison_endbr(addr, true); + poison_endbr(addr, wr_addr, true); if (IS_ENABLED(CONFIG_FINEIBT)) - poison_cfi(addr - 16); + poison_cfi(addr - 16, wr_addr - 16); } } #else -void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { } +void __init_or_module apply_seal_endbr(s32 *start, s32 *end, struct module *mod) { } #endif /* CONFIG_X86_KERNEL_IBT */ -#ifdef CONFIG_FINEIBT +#ifdef CONFIG_CFI_AUTO_DEFAULT +#define __CFI_DEFAULT CFI_AUTO +#elif defined(CONFIG_CFI_CLANG) +#define __CFI_DEFAULT CFI_KCFI +#else +#define __CFI_DEFAULT CFI_OFF +#endif -enum cfi_mode { - CFI_DEFAULT, - CFI_OFF, - CFI_KCFI, - CFI_FINEIBT, -}; +enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT; + +#ifdef CONFIG_CFI_CLANG +struct bpf_insn; + +/* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */ +extern unsigned int __bpf_prog_runX(const void *ctx, + const struct bpf_insn *insn); + +/* + * Force a reference to the external symbol so the compiler generates + * __kcfi_typid. + */ +__ADDRESSABLE(__bpf_prog_runX); + +/* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */ +asm ( +" .pushsection .data..ro_after_init,\"aw\",@progbits \n" +" .type cfi_bpf_hash,@object \n" +" .globl cfi_bpf_hash \n" +" .p2align 2, 0x0 \n" +"cfi_bpf_hash: \n" +" .long __kcfi_typeid___bpf_prog_runX \n" +" .size cfi_bpf_hash, 4 \n" +" .popsection \n" +); + +/* Must match bpf_callback_t */ +extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64); + +__ADDRESSABLE(__bpf_callback_fn); + +/* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */ +asm ( +" .pushsection .data..ro_after_init,\"aw\",@progbits \n" +" .type cfi_bpf_subprog_hash,@object \n" +" .globl cfi_bpf_subprog_hash \n" +" .p2align 2, 0x0 \n" +"cfi_bpf_subprog_hash: \n" +" .long __kcfi_typeid___bpf_callback_fn \n" +" .size cfi_bpf_subprog_hash, 4 \n" +" .popsection \n" +); + +u32 cfi_get_func_hash(void *func) +{ + u32 hash; + + func -= cfi_get_offset(); + switch (cfi_mode) { + case CFI_FINEIBT: + func += 7; + break; + case CFI_KCFI: + func += 1; + break; + default: + return 0; + } + + if (get_kernel_nofault(hash, func)) + return 0; + + return hash; +} +#endif + +#ifdef CONFIG_FINEIBT -static enum cfi_mode cfi_mode __ro_after_init = CFI_DEFAULT; static bool cfi_rand __ro_after_init = true; static u32 cfi_seed __ro_after_init; @@ -883,7 +1027,7 @@ static __init int cfi_parse_cmdline(char *str) } if (!strcmp(str, "auto")) { - cfi_mode = CFI_DEFAULT; + cfi_mode = CFI_AUTO; } else if (!strcmp(str, "off")) { cfi_mode = CFI_OFF; cfi_rand = false; @@ -992,7 +1136,7 @@ static u32 decode_caller_hash(void *addr) } /* .retpoline_sites */ -static int cfi_disable_callers(s32 *start, s32 *end) +static int cfi_disable_callers(s32 *start, s32 *end, struct module *mod) { /* * Disable kCFI by patching in a JMP.d8, this leaves the hash immediate @@ -1004,20 +1148,23 @@ static int cfi_disable_callers(s32 *start, s32 *end) for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr; u32 hash; addr -= fineibt_caller_size; - hash = decode_caller_hash(addr); + wr_addr = module_writable_address(mod, addr); + hash = decode_caller_hash(wr_addr); + if (!hash) /* nocfi callers */ continue; - text_poke_early(addr, jmp, 2); + text_poke_early(wr_addr, jmp, 2); } return 0; } -static int cfi_enable_callers(s32 *start, s32 *end) +static int cfi_enable_callers(s32 *start, s32 *end, struct module *mod) { /* * Re-enable kCFI, undo what cfi_disable_callers() did. @@ -1027,106 +1174,115 @@ static int cfi_enable_callers(s32 *start, s32 *end) for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr; u32 hash; addr -= fineibt_caller_size; - hash = decode_caller_hash(addr); + wr_addr = module_writable_address(mod, addr); + hash = decode_caller_hash(wr_addr); if (!hash) /* nocfi callers */ continue; - text_poke_early(addr, mov, 2); + text_poke_early(wr_addr, mov, 2); } return 0; } /* .cfi_sites */ -static int cfi_rand_preamble(s32 *start, s32 *end) +static int cfi_rand_preamble(s32 *start, s32 *end, struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr = module_writable_address(mod, addr); u32 hash; - hash = decode_preamble_hash(addr); + hash = decode_preamble_hash(wr_addr); if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n", addr, addr, 5, addr)) return -EINVAL; hash = cfi_rehash(hash); - text_poke_early(addr + 1, &hash, 4); + text_poke_early(wr_addr + 1, &hash, 4); } return 0; } -static int cfi_rewrite_preamble(s32 *start, s32 *end) +static int cfi_rewrite_preamble(s32 *start, s32 *end, struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr = module_writable_address(mod, addr); u32 hash; - hash = decode_preamble_hash(addr); + hash = decode_preamble_hash(wr_addr); if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n", addr, addr, 5, addr)) return -EINVAL; - text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size); - WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678); - text_poke_early(addr + fineibt_preamble_hash, &hash, 4); + text_poke_early(wr_addr, fineibt_preamble_start, fineibt_preamble_size); + WARN_ON(*(u32 *)(wr_addr + fineibt_preamble_hash) != 0x12345678); + text_poke_early(wr_addr + fineibt_preamble_hash, &hash, 4); } return 0; } -static void cfi_rewrite_endbr(s32 *start, s32 *end) +static void cfi_rewrite_endbr(s32 *start, s32 *end, struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr = module_writable_address(mod, addr); - poison_endbr(addr+16, false); + poison_endbr(addr + 16, wr_addr + 16, false); } } /* .retpoline_sites */ -static int cfi_rand_callers(s32 *start, s32 *end) +static int cfi_rand_callers(s32 *start, s32 *end, struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr; u32 hash; addr -= fineibt_caller_size; - hash = decode_caller_hash(addr); + wr_addr = module_writable_address(mod, addr); + hash = decode_caller_hash(wr_addr); if (hash) { hash = -cfi_rehash(hash); - text_poke_early(addr + 2, &hash, 4); + text_poke_early(wr_addr + 2, &hash, 4); } } return 0; } -static int cfi_rewrite_callers(s32 *start, s32 *end) +static int cfi_rewrite_callers(s32 *start, s32 *end, struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr; u32 hash; addr -= fineibt_caller_size; - hash = decode_caller_hash(addr); + wr_addr = module_writable_address(mod, addr); + hash = decode_caller_hash(wr_addr); if (hash) { - text_poke_early(addr, fineibt_caller_start, fineibt_caller_size); - WARN_ON(*(u32 *)(addr + fineibt_caller_hash) != 0x12345678); - text_poke_early(addr + fineibt_caller_hash, &hash, 4); + text_poke_early(wr_addr, fineibt_caller_start, fineibt_caller_size); + WARN_ON(*(u32 *)(wr_addr + fineibt_caller_hash) != 0x12345678); + text_poke_early(wr_addr + fineibt_caller_hash, &hash, 4); } /* rely on apply_retpolines() */ } @@ -1135,15 +1291,16 @@ static int cfi_rewrite_callers(s32 *start, s32 *end) } static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, - s32 *start_cfi, s32 *end_cfi, bool builtin) + s32 *start_cfi, s32 *end_cfi, struct module *mod) { + bool builtin = mod ? false : true; int ret; if (WARN_ONCE(fineibt_preamble_size != 16, "FineIBT preamble wrong size: %ld", fineibt_preamble_size)) return; - if (cfi_mode == CFI_DEFAULT) { + if (cfi_mode == CFI_AUTO) { cfi_mode = CFI_KCFI; if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT)) cfi_mode = CFI_FINEIBT; @@ -1154,19 +1311,22 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, * rewrite them. This disables all CFI. If this succeeds but any of the * later stages fails, we're without CFI. */ - ret = cfi_disable_callers(start_retpoline, end_retpoline); + ret = cfi_disable_callers(start_retpoline, end_retpoline, mod); if (ret) goto err; if (cfi_rand) { - if (builtin) + if (builtin) { cfi_seed = get_random_u32(); + cfi_bpf_hash = cfi_rehash(cfi_bpf_hash); + cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash); + } - ret = cfi_rand_preamble(start_cfi, end_cfi); + ret = cfi_rand_preamble(start_cfi, end_cfi, mod); if (ret) goto err; - ret = cfi_rand_callers(start_retpoline, end_retpoline); + ret = cfi_rand_callers(start_retpoline, end_retpoline, mod); if (ret) goto err; } @@ -1178,7 +1338,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, return; case CFI_KCFI: - ret = cfi_enable_callers(start_retpoline, end_retpoline); + ret = cfi_enable_callers(start_retpoline, end_retpoline, mod); if (ret) goto err; @@ -1188,17 +1348,17 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, case CFI_FINEIBT: /* place the FineIBT preamble at func()-16 */ - ret = cfi_rewrite_preamble(start_cfi, end_cfi); + ret = cfi_rewrite_preamble(start_cfi, end_cfi, mod); if (ret) goto err; /* rewrite the callers to target func()-16 */ - ret = cfi_rewrite_callers(start_retpoline, end_retpoline); + ret = cfi_rewrite_callers(start_retpoline, end_retpoline, mod); if (ret) goto err; /* now that nobody targets func()+0, remove ENDBR there */ - cfi_rewrite_endbr(start_cfi, end_cfi); + cfi_rewrite_endbr(start_cfi, end_cfi, mod); if (builtin) pr_info("Using FineIBT CFI\n"); @@ -1217,7 +1377,7 @@ static inline void poison_hash(void *addr) *(u32 *)addr = 0; } -static void poison_cfi(void *addr) +static void poison_cfi(void *addr, void *wr_addr) { switch (cfi_mode) { case CFI_FINEIBT: @@ -1229,8 +1389,8 @@ static void poison_cfi(void *addr) * ud2 * 1: nop */ - poison_endbr(addr, false); - poison_hash(addr + fineibt_preamble_hash); + poison_endbr(addr, wr_addr, false); + poison_hash(wr_addr + fineibt_preamble_hash); break; case CFI_KCFI: @@ -1239,7 +1399,7 @@ static void poison_cfi(void *addr) * movl $0, %eax * .skip 11, 0x90 */ - poison_hash(addr + 1); + poison_hash(wr_addr + 1); break; default: @@ -1250,22 +1410,21 @@ static void poison_cfi(void *addr) #else static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, - s32 *start_cfi, s32 *end_cfi, bool builtin) + s32 *start_cfi, s32 *end_cfi, struct module *mod) { } #ifdef CONFIG_X86_KERNEL_IBT -static void poison_cfi(void *addr) { } +static void poison_cfi(void *addr, void *wr_addr) { } #endif #endif void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, - s32 *start_cfi, s32 *end_cfi) + s32 *start_cfi, s32 *end_cfi, struct module *mod) { return __apply_fineibt(start_retpoline, end_retpoline, - start_cfi, end_cfi, - /* .builtin = */ false); + start_cfi, end_cfi, mod); } #ifdef CONFIG_SMP @@ -1421,46 +1580,6 @@ int alternatives_text_reserved(void *start, void *end) } #endif /* CONFIG_SMP */ -#ifdef CONFIG_PARAVIRT - -/* Use this to add nops to a buffer, then text_poke the whole buffer. */ -static void __init_or_module add_nops(void *insns, unsigned int len) -{ - while (len > 0) { - unsigned int noplen = len; - if (noplen > ASM_NOP_MAX) - noplen = ASM_NOP_MAX; - memcpy(insns, x86_nops[noplen], noplen); - insns += noplen; - len -= noplen; - } -} - -void __init_or_module apply_paravirt(struct paravirt_patch_site *start, - struct paravirt_patch_site *end) -{ - struct paravirt_patch_site *p; - char insn_buff[MAX_PATCH_LEN]; - - for (p = start; p < end; p++) { - unsigned int used; - - BUG_ON(p->len > MAX_PATCH_LEN); - /* prep the buffer with the original instructions */ - memcpy(insn_buff, p->instr, p->len); - used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len); - - BUG_ON(used > p->len); - - /* Pad the rest with nops */ - add_nops(insn_buff + used, p->len - used); - text_poke_early(p->instr, insn_buff, p->len); - } -} -extern struct paravirt_patch_site __start_parainstructions[], - __stop_parainstructions[]; -#endif /* CONFIG_PARAVIRT */ - /* * Self-test for the INT3 based CALL emulation code. * @@ -1567,7 +1686,7 @@ static noinline void __init alt_reloc_selftest(void) */ asm_inline volatile ( ALTERNATIVE("", "lea %[mem], %%" _ASM_ARG1 "; call __alt_reloc_selftest;", X86_FEATURE_ALWAYS) - : /* output */ + : ASM_CALL_CONSTRAINT : [mem] "m" (__alt_reloc_selftest_addr) : _ASM_ARG1 ); @@ -1596,43 +1715,22 @@ void __init alternative_instructions(void) */ /* - * Paravirt patching and alternative patching can be combined to - * replace a function call with a short direct code sequence (e.g. - * by setting a constant return value instead of doing that in an - * external function). - * In order to make this work the following sequence is required: - * 1. set (artificial) features depending on used paravirt - * functions which can later influence alternative patching - * 2. apply paravirt patching (generally replacing an indirect - * function call with a direct one) - * 3. apply alternative patching (e.g. replacing a direct function - * call with a custom code sequence) - * Doing paravirt patching after alternative patching would clobber - * the optimization of the custom code with a function call again. + * Make sure to set (artificial) features depending on used paravirt + * functions which can later influence alternative patching. */ paravirt_set_cap(); - /* - * First patch paravirt functions, such that we overwrite the indirect - * call with the direct call. - */ - apply_paravirt(__parainstructions, __parainstructions_end); - __apply_fineibt(__retpoline_sites, __retpoline_sites_end, - __cfi_sites, __cfi_sites_end, true); + __cfi_sites, __cfi_sites_end, NULL); /* * Rewrite the retpolines, must be done before alternatives since * those can rewrite the retpoline thunks. */ - apply_retpolines(__retpoline_sites, __retpoline_sites_end); - apply_returns(__return_sites, __return_sites_end); + apply_retpolines(__retpoline_sites, __retpoline_sites_end, NULL); + apply_returns(__return_sites, __return_sites_end, NULL); - /* - * Then patch alternatives, such that those paravirt calls that are in - * alternatives can be overwritten by their immediate fragments. - */ - apply_alternatives(__alt_instructions, __alt_instructions_end); + apply_alternatives(__alt_instructions, __alt_instructions_end, NULL); /* * Now all calls are established. Apply the call thunks if @@ -1643,7 +1741,7 @@ void __init alternative_instructions(void) /* * Seal all functions that do not have their address taken. */ - apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end); + apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end, NULL); #ifdef CONFIG_SMP /* Patch to UP if other cpus not imminent. */ @@ -1734,7 +1832,7 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm) * restoring the previous mm. */ if (this_cpu_read(cpu_tlbstate_shared.is_lazy)) - leave_mm(smp_processor_id()); + leave_mm(); temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm); switch_mm_irqs_off(NULL, mm, current); @@ -1756,11 +1854,18 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm) return temp_state; } +__ro_after_init struct mm_struct *poking_mm; +__ro_after_init unsigned long poking_addr; + static inline void unuse_temporary_mm(temp_mm_state_t prev_state) { lockdep_assert_irqs_disabled(); + switch_mm_irqs_off(NULL, prev_state.mm, current); + /* Clear the cpumask, to indicate no TLB flushing is needed anywhere */ + cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(poking_mm)); + /* * Restore the breakpoints if they were disabled before the temporary mm * was loaded. @@ -1769,9 +1874,6 @@ static inline void unuse_temporary_mm(temp_mm_state_t prev_state) hw_breakpoint_restore(); } -__ro_after_init struct mm_struct *poking_mm; -__ro_after_init unsigned long poking_addr; - static void text_poke_memcpy(void *dst, const void *src, size_t len) { memcpy(dst, src, len); @@ -1906,7 +2008,7 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l * Note that the caller must ensure that if the modified code is part of a * module, the module would not be removed during poking. This can be achieved * by registering a module notifier, and ordering module removal and patching - * trough a mutex. + * through a mutex. */ void *text_poke(void *addr, const void *opcode, size_t len) { |