This is a note to let you know that I've just added the patch titled objtool/x86: Rewrite retpoline thunk calls to the 5.10-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: objtool-x86-rewrite-retpoline-thunk-calls.patch and it can be found in the queue-5.10 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From foo@baz Tue Jul 12 05:07:35 PM CEST 2022 From: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Date: Fri, 26 Mar 2021 16:12:15 +0100 Subject: objtool/x86: Rewrite retpoline thunk calls From: Peter Zijlstra <peterz@xxxxxxxxxxxxx> commit 9bc0bb50727c8ac69fbb33fb937431cf3518ff37 upstream. When the compiler emits: "CALL __x86_indirect_thunk_\reg" for an indirect call, have objtool rewrite it to: ALTERNATIVE "call __x86_indirect_thunk_\reg", "call *%reg", ALT_NOT(X86_FEATURE_RETPOLINE) Additionally, in order to not emit endless identical .altinst_replacement chunks, use a global symbol for them, see __x86_indirect_alt_*. This also avoids objtool from having to do code generation. Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx> Signed-off-by: Borislav Petkov <bp@xxxxxxx> Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx> Reviewed-by: Miroslav Benes <mbenes@xxxxxxx> Link: https://lkml.kernel.org/r/20210326151300.320177914@xxxxxxxxxxxxx [bwh: Backported to 5.10: include "arch_elf.h" instead of "arch/elf.h"] Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- arch/x86/include/asm/asm-prototypes.h | 12 ++- arch/x86/lib/retpoline.S | 41 +++++++++++ tools/objtool/arch/x86/decode.c | 117 ++++++++++++++++++++++++++++++++++ 3 files changed, 167 insertions(+), 3 deletions(-) --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -19,11 +19,19 @@ extern void cmpxchg8b_emu(void); #ifdef CONFIG_RETPOLINE -#define DECL_INDIRECT_THUNK(reg) \ +#undef GEN +#define GEN(reg) \ extern asmlinkage void __x86_indirect_thunk_ ## reg (void); +#include <asm/GEN-for-each-reg.h> + +#undef GEN +#define GEN(reg) \ + extern asmlinkage void __x86_indirect_alt_call_ ## reg (void); +#include <asm/GEN-for-each-reg.h> #undef GEN -#define GEN(reg) DECL_INDIRECT_THUNK(reg) +#define GEN(reg) \ + extern asmlinkage void __x86_indirect_alt_jmp_ ## reg (void); #include <asm/GEN-for-each-reg.h> #endif /* CONFIG_RETPOLINE */ --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -10,6 +10,8 @@ #include <asm/unwind_hints.h> #include <asm/frame.h> + .section .text.__x86.indirect_thunk + .macro RETPOLINE reg ANNOTATE_INTRA_FUNCTION_CALL call .Ldo_rop_\@ @@ -25,9 +27,9 @@ .endm .macro THUNK reg - .section .text.__x86.indirect_thunk .align 32 + SYM_FUNC_START(__x86_indirect_thunk_\reg) ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ @@ -39,6 +41,32 @@ SYM_FUNC_END(__x86_indirect_thunk_\reg) .endm /* + * This generates .altinstr_replacement symbols for use by objtool. They, + * however, must not actually live in .altinstr_replacement since that will be + * discarded after init, but module alternatives will also reference these + * symbols. + * + * Their names matches the "__x86_indirect_" prefix to mark them as retpolines. + */ +.macro ALT_THUNK reg + + .align 1 + +SYM_FUNC_START_NOALIGN(__x86_indirect_alt_call_\reg) + ANNOTATE_RETPOLINE_SAFE +1: call *%\reg +2: .skip 5-(2b-1b), 0x90 +SYM_FUNC_END(__x86_indirect_alt_call_\reg) + +SYM_FUNC_START_NOALIGN(__x86_indirect_alt_jmp_\reg) + ANNOTATE_RETPOLINE_SAFE +1: jmp *%\reg +2: .skip 5-(2b-1b), 0x90 +SYM_FUNC_END(__x86_indirect_alt_jmp_\reg) + +.endm + +/* * Despite being an assembler file we can't just use .irp here * because __KSYM_DEPS__ only uses the C preprocessor and would * only see one instance of "__x86_indirect_thunk_\reg" rather @@ -61,3 +89,14 @@ SYM_FUNC_END(__x86_indirect_thunk_\reg) #define GEN(reg) EXPORT_THUNK(reg) #include <asm/GEN-for-each-reg.h> +#undef GEN +#define GEN(reg) ALT_THUNK reg +#include <asm/GEN-for-each-reg.h> + +#undef GEN +#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_call_ ## reg) +#include <asm/GEN-for-each-reg.h> + +#undef GEN +#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_jmp_ ## reg) +#include <asm/GEN-for-each-reg.h> --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -16,6 +16,7 @@ #include "../../arch.h" #include "../../warn.h" #include <asm/orc_types.h> +#include "arch_elf.h" static unsigned char op_to_cfi_reg[][2] = { {CFI_AX, CFI_R8}, @@ -585,6 +586,122 @@ const char *arch_nop_insn(int len) return nops[len-1]; } +/* asm/alternative.h ? */ + +#define ALTINSTR_FLAG_INV (1 << 15) +#define ALT_NOT(feat) ((feat) | ALTINSTR_FLAG_INV) + +struct alt_instr { + s32 instr_offset; /* original instruction */ + s32 repl_offset; /* offset to replacement instruction */ + u16 cpuid; /* cpuid bit set for replacement */ + u8 instrlen; /* length of original instruction */ + u8 replacementlen; /* length of new instruction */ +} __packed; + +static int elf_add_alternative(struct elf *elf, + struct instruction *orig, struct symbol *sym, + int cpuid, u8 orig_len, u8 repl_len) +{ + const int size = sizeof(struct alt_instr); + struct alt_instr *alt; + struct section *sec; + Elf_Scn *s; + + sec = find_section_by_name(elf, ".altinstructions"); + if (!sec) { + sec = elf_create_section(elf, ".altinstructions", + SHF_WRITE, size, 0); + + if (!sec) { + WARN_ELF("elf_create_section"); + return -1; + } + } + + s = elf_getscn(elf->elf, sec->idx); + if (!s) { + WARN_ELF("elf_getscn"); + return -1; + } + + sec->data = elf_newdata(s); + if (!sec->data) { + WARN_ELF("elf_newdata"); + return -1; + } + + sec->data->d_size = size; + sec->data->d_align = 1; + + alt = sec->data->d_buf = malloc(size); + if (!sec->data->d_buf) { + perror("malloc"); + return -1; + } + memset(sec->data->d_buf, 0, size); + + if (elf_add_reloc_to_insn(elf, sec, sec->sh.sh_size, + R_X86_64_PC32, orig->sec, orig->offset)) { + WARN("elf_create_reloc: alt_instr::instr_offset"); + return -1; + } + + if (elf_add_reloc(elf, sec, sec->sh.sh_size + 4, + R_X86_64_PC32, sym, 0)) { + WARN("elf_create_reloc: alt_instr::repl_offset"); + return -1; + } + + alt->cpuid = cpuid; + alt->instrlen = orig_len; + alt->replacementlen = repl_len; + + sec->sh.sh_size += size; + sec->changed = true; + + return 0; +} + +#define X86_FEATURE_RETPOLINE ( 7*32+12) + +int arch_rewrite_retpolines(struct objtool_file *file) +{ + struct instruction *insn; + struct reloc *reloc; + struct symbol *sym; + char name[32] = ""; + + list_for_each_entry(insn, &file->retpoline_call_list, call_node) { + + if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk")) + continue; + + reloc = insn->reloc; + + sprintf(name, "__x86_indirect_alt_%s_%s", + insn->type == INSN_JUMP_DYNAMIC ? "jmp" : "call", + reloc->sym->name + 21); + + sym = find_symbol_by_name(file->elf, name); + if (!sym) { + sym = elf_create_undef_symbol(file->elf, name); + if (!sym) { + WARN("elf_create_undef_symbol"); + return -1; + } + } + + if (elf_add_alternative(file->elf, insn, sym, + ALT_NOT(X86_FEATURE_RETPOLINE), 5, 5)) { + WARN("elf_add_alternative"); + return -1; + } + } + + return 0; +} + int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg) { struct cfi_reg *cfa = &insn->cfi.cfa; Patches currently in stable-queue which might be from peterz@xxxxxxxxxxxxx are queue-5.10/objtool-cache-instruction-relocs.patch queue-5.10/x86-sev-avoid-using-__x86_return_thunk.patch queue-5.10/objtool-add-elf_create_undef_symbol.patch queue-5.10/x86-ftrace-use-alternative-ret-encoding.patch queue-5.10/objtool-re-add-unwind_hint_-save_restore.patch queue-5.10/x86-bugs-add-retbleed-ibpb.patch queue-5.10/x86-bugs-enable-stibp-for-jmp2ret.patch queue-5.10/x86-retpoline-cleanup-some-ifdefery.patch queue-5.10/objtool-handle-__sanitize_cov-tail-calls.patch queue-5.10/x86-prepare-asm-files-for-straight-line-speculation.patch queue-5.10/kvm-vmx-flatten-__vmx_vcpu_run.patch queue-5.10/x86-kvm-vmx-make-noinstr-clean.patch queue-5.10/objtool-x86-replace-alternatives-with-.retpoline_sites.patch queue-5.10/objtool-skip-magical-retpoline-.altinstr_replacement.patch queue-5.10/x86-retbleed-add-fine-grained-kconfig-knobs.patch queue-5.10/x86-cpu-amd-add-spectral-chicken.patch queue-5.10/objtool-add-straight-line-speculation-validation.patch queue-5.10/kvm-vmx-fix-ibrs-handling-after-vmexit.patch queue-5.10/kvm-vmx-prevent-guest-rsb-poisoning-attacks-with-eibrs.patch queue-5.10/x86-vsyscall_emu-64-don-t-use-ret-in-vsyscall-emulation.patch queue-5.10/tools-arch-update-arch-x86-lib-mem-cpy-set-_64.s-copies-used-in-perf-bench-mem-memcpy.patch queue-5.10/x86-add-straight-line-speculation-mitigation.patch queue-5.10/x86-add-magic-amd-return-thunk.patch queue-5.10/x86-bugs-keep-a-per-cpu-ia32_spec_ctrl-value.patch queue-5.10/x86-alternatives-optimize-optimize_nops.patch queue-5.10/x86-objtool-create-.return_sites.patch queue-5.10/crypto-x86-poly1305-fixup-sls.patch queue-5.10/x86-alternative-handle-jcc-__x86_indirect_thunk_-reg.patch queue-5.10/x86-kvm-fix-setcc-emulation-for-return-thunks.patch queue-5.10/objtool-fix-objtool-regression-on-x32-systems.patch queue-5.10/x86-alternative-relax-text_poke_bp-constraint.patch queue-5.10/x86-retpoline-swizzle-retpoline-thunk.patch queue-5.10/objtool-rework-the-elf_rebuild_reloc_section-logic.patch queue-5.10/x86-speculation-fix-firmware-entry-spec_ctrl-handling.patch queue-5.10/x86-retpoline-remove-unused-replacement-symbols.patch queue-5.10/objtool-fix-symbol-creation.patch queue-5.10/x86-speculation-add-spectre_v2-ibrs-option-to-support-kernel-ibrs.patch queue-5.10/bpf-x86-respect-x86_feature_retpoline.patch queue-5.10/objtool-fix-type-of-reloc-addend.patch queue-5.10/objtool-x86-rewrite-retpoline-thunk-calls.patch queue-5.10/x86-undo-return-thunk-damage.patch queue-5.10/x86-prepare-inline-asm-for-straight-line-speculation.patch queue-5.10/x86-alternative-support-alternative_ternary.patch queue-5.10/kvm-emulate-fix-setcc-emulation-function-offsets-with-sls.patch queue-5.10/objtool-handle-per-arch-retpoline-naming.patch queue-5.10/x86-retpoline-create-a-retpoline-thunk-array.patch queue-5.10/x86-retpoline-simplify-retpolines.patch queue-5.10/x86-asm-fix-register-order.patch queue-5.10/x86-speculation-fill-rsb-on-vmexit-for-ibrs.patch queue-5.10/objtool-add-entry-unret-validation.patch queue-5.10/objtool-keep-track-of-retpoline-call-sites.patch queue-5.10/kvm-vmx-convert-launched-argument-to-flags.patch queue-5.10/objtool-add-elf_create_reloc-helper.patch queue-5.10/objtool-make-.altinstructions-section-entry-size-consistent.patch queue-5.10/x86-bpf-use-alternative-ret-encoding.patch queue-5.10/x86-common-stamp-out-the-stepping-madness.patch queue-5.10/x86-bugs-split-spectre_v2_select_mitigation-and-spectre_v2_user_select_mitigation.patch queue-5.10/x86-bugs-report-intel-retbleed-vulnerability.patch queue-5.10/bpf-x86-simplify-computing-label-offsets.patch queue-5.10/x86-cpufeatures-move-retpoline-flags-to-word-11.patch queue-5.10/x86-speculation-fix-spec_ctrl-write-on-smt-state-change.patch queue-5.10/x86-retpoline-use-mfunction-return.patch queue-5.10/x86-xen-rename-sys-entry-points.patch queue-5.10/objtool-only-rewrite-unconditional-retpoline-thunk-calls.patch queue-5.10/x86-bugs-optimize-spec_ctrl-msr-writes.patch queue-5.10/x86-alternative-optimize-single-byte-nops-at-an-arbitrary-position.patch queue-5.10/objtool-fix-code-relocs-vs-weak-symbols.patch queue-5.10/x86-bugs-report-amd-retbleed-vulnerability.patch queue-5.10/x86-static_call-use-alternative-ret-encoding.patch queue-5.10/x86-speculation-fix-rsb-filling-with-config_retpoline-n.patch queue-5.10/x86-asm-fixup-odd-gen-for-each-reg.h-usage.patch queue-5.10/x86-alternative-add-debug-prints-to-apply_retpolines.patch queue-5.10/objtool-extract-elf_symbol_add.patch queue-5.10/x86-use-return-thunk-in-asm-code.patch queue-5.10/objtool-remove-reloc-symbol-type-checks-in-get_alt_entry.patch queue-5.10/objtool-classify-symbols.patch queue-5.10/intel_idle-disable-ibrs-during-long-idle.patch queue-5.10/objtool-correctly-handle-retpoline-thunk-calls.patch queue-5.10/objtool-fix-.symtab_shndx-handling-for-elf_create_undef_symbol.patch queue-5.10/x86-retpoline-move-the-retpoline-thunk-declarations-to-nospec-branch.h.patch queue-5.10/objtool-support-asm-jump-tables.patch queue-5.10/x86-alternative-implement-.retpoline_sites-support.patch queue-5.10/objtool-x86-ignore-__x86_indirect_alt_-symbols.patch queue-5.10/objtool-fix-sls-validation-for-kcov-tail-call-replacement.patch queue-5.10/x86-alternative-try-inline-spectre_v2-retpoline-amd.patch queue-5.10/x86-entry-remove-skip_r11rcx.patch queue-5.10/objtool-explicitly-avoid-self-modifying-code-in-.altinstr_replacement.patch queue-5.10/x86-speculation-use-cached-host-spec_ctrl-value-for-guest-entry-exit.patch queue-5.10/x86-bugs-add-amd-retbleed-boot-parameter.patch queue-5.10/objtool-create-reloc-sections-implicitly.patch queue-5.10/x86-entry-add-kernel-ibrs-implementation.patch queue-5.10/objtool-treat-.text.__x86.-as-noinstr.patch queue-5.10/x86-lib-atomic64_386_32-rename-things.patch queue-5.10/objtool-introduce-cfi-hash.patch queue-5.10/objtool-default-ignore-int3-for-unreachable.patch queue-5.10/objtool-extract-elf_strtab_concat.patch queue-5.10/objtool-teach-get_alt_entry-about-more-relocation-types.patch queue-5.10/objtool-update-retpoline-validation.patch