This is a note to let you know that I've just added the patch titled
x86/alternatives: Optimize optimize_nops()
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:
x86-alternatives-optimize-optimize_nops.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 16:12:01 +0100
Subject: x86/alternatives: Optimize optimize_nops()
From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
commit 23c1ad538f4f371bdb67d8a112314842d5db7e5a upstream.
Currently, optimize_nops() scans to see if the alternative starts with
NOPs. However, the emit pattern is:
141: \oldinstr
142: .skip (len-(142b-141b)), 0x90
That is, when 'oldinstr' is short, the tail is padded with NOPs. This case
never gets optimized.
Rewrite optimize_nops() to replace any trailing string of NOPs inside
the alternative to larger NOPs. Also run it irrespective of patching,
replacing NOPs in both the original and replaced code.
A direct consequence is that 'padlen' becomes superfluous, so remove it.
[ bp:
- Adjust commit message
- remove a stale comment about needing to pad
- add a comment in optimize_nops()
- exit early if the NOP verif. loop catches a mismatch - function
should not not add NOPs in that case
- fix the "optimized NOPs" offsets output ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Link: https://lkml.kernel.org/r/20210326151259.442992235@xxxxxxxxxxxxx
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/include/asm/alternative.h | 17 ++-------
arch/x86/kernel/alternative.c | 49 ++++++++++++++++----------
tools/objtool/arch/x86/include/arch_special.h | 2 -
3 files changed, 37 insertions(+), 31 deletions(-)
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -65,7 +65,6 @@ struct alt_instr {
u16 cpuid; /* cpuid bit set for replacement */
u8 instrlen; /* length of original instruction */
u8 replacementlen; /* length of new instruction */
- u8 padlen; /* length of build-time padding */
} __packed;
/*
@@ -104,7 +103,6 @@ static inline int alternatives_text_rese
#define alt_end_marker "663"
#define alt_slen "662b-661b"
-#define alt_pad_len alt_end_marker"b-662b"
#define alt_total_slen alt_end_marker"b-661b"
#define alt_rlen(num) e_replacement(num)"f-"b_replacement(num)"f"
@@ -151,8 +149,7 @@ static inline int alternatives_text_rese
" .long " b_replacement(num)"f - .\n" /* new instruction */ \
" .word " __stringify(feature) "\n" /* feature bit */ \
" .byte " alt_total_slen "\n" /* source len */ \
- " .byte " alt_rlen(num) "\n" /* replacement len */ \
- " .byte " alt_pad_len "\n" /* pad len */
+ " .byte " alt_rlen(num) "\n" /* replacement len */
#define ALTINSTR_REPLACEMENT(newinstr, feature, num) /* replacement */ \
"# ALT: replacement " #num "\n" \
@@ -224,9 +221,6 @@ static inline int alternatives_text_rese
* Peculiarities:
* No memory clobber here.
* Argument numbers start with 1.
- * Best is to use constraints that are fixed size (like (%1) ... "r")
- * If you use variable sized constraints like "m" or "g" in the
- * replacement make sure to pad to the worst case length.
* Leaving an unused argument 0 to keep API compatibility.
*/
#define alternative_input(oldinstr, newinstr, feature, input...) \
@@ -315,13 +309,12 @@ static inline int alternatives_text_rese
* enough information for the alternatives patching code to patch an
* instruction. See apply_alternatives().
*/
-.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
+.macro altinstruction_entry orig alt feature orig_len alt_len
.long \orig - .
.long \alt - .
.word \feature
.byte \orig_len
.byte \alt_len
- .byte \pad_len
.endm
/*
@@ -338,7 +331,7 @@ static inline int alternatives_text_rese
142:
.pushsection .altinstructions,"a"
- altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
+ altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f
.popsection
.pushsection .altinstr_replacement,"ax"
@@ -375,8 +368,8 @@ static inline int alternatives_text_rese
142:
.pushsection .altinstructions,"a"
- altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
- altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
+ altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f
+ altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f
.popsection
.pushsection .altinstr_replacement,"ax"
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -344,19 +344,35 @@ done:
static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr)
{
unsigned long flags;
- int i;
+ struct insn insn;
+ int nop, i = 0;
- for (i = 0; i < a->padlen; i++) {
- if (instr[i] != 0x90)
+ /*
+ * Jump over the non-NOP insns, the remaining bytes must be single-byte
+ * NOPs, optimize them.
+ */
+ for (;;) {
+ if (insn_decode_kernel(&insn, &instr[i]))
+ return;
+
+ if (insn.length == 1 && insn.opcode.bytes[0] == 0x90)
+ break;
+
+ if ((i += insn.length) >= a->instrlen)
+ return;
+ }
+
+ for (nop = i; i < a->instrlen; i++) {
+ if (WARN_ONCE(instr[i] != 0x90, "Not a NOP at 0x%px\n", &instr[i]))
return;
}
local_irq_save(flags);
- add_nops(instr + (a->instrlen - a->padlen), a->padlen);
+ add_nops(instr + nop, i - nop);
local_irq_restore(flags);
DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ",
- instr, a->instrlen - a->padlen, a->padlen);
+ instr, nop, a->instrlen);
}
/*
@@ -402,19 +418,15 @@ void __init_or_module noinline apply_alt
* - feature not present but ALTINSTR_FLAG_INV is set to mean,
* patch if feature is *NOT* present.
*/
- if (!boot_cpu_has(feature) == !(a->cpuid & ALTINSTR_FLAG_INV)) {
- if (a->padlen > 1)
- optimize_nops(a, instr);
-
- continue;
- }
+ if (!boot_cpu_has(feature) == !(a->cpuid & ALTINSTR_FLAG_INV))
+ goto next;
- DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
+ DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d)",
(a->cpuid & ALTINSTR_FLAG_INV) ? "!" : "",
feature >> 5,
feature & 0x1f,
instr, instr, a->instrlen,
- replacement, a->replacementlen, a->padlen);
+ replacement, a->replacementlen);
DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr);
DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement);
@@ -438,14 +450,15 @@ void __init_or_module noinline apply_alt
if (a->replacementlen && is_jmp(replacement[0]))
recompute_jump(a, instr, replacement, insn_buff);
- if (a->instrlen > a->replacementlen) {
- add_nops(insn_buff + a->replacementlen,
- a->instrlen - a->replacementlen);
- insn_buff_sz += a->instrlen - a->replacementlen;
- }
+ for (; insn_buff_sz < a->instrlen; insn_buff_sz++)
+ insn_buff[insn_buff_sz] = 0x90;
+
DUMP_BYTES(insn_buff, insn_buff_sz, "%px: final_insn: ", instr);
text_poke_early(instr, insn_buff, insn_buff_sz);
+
+next:
+ optimize_nops(a, instr);
}
}
--- a/tools/objtool/arch/x86/include/arch_special.h
+++ b/tools/objtool/arch/x86/include/arch_special.h
@@ -10,7 +10,7 @@
#define JUMP_ORIG_OFFSET 0
#define JUMP_NEW_OFFSET 4
-#define ALT_ENTRY_SIZE 13
+#define ALT_ENTRY_SIZE 12
#define ALT_ORIG_OFFSET 0
#define ALT_NEW_OFFSET 4
#define ALT_FEATURE_OFFSET 8
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
