github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-09-23 05:04:02 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

x86/kcfi: Optimize call sequence

Browse Source 
As noted in commit 85a2d4a890 ("x86,ibt: Use UDB instead of 0xEA") Jcc should
be assumed not-taken, however the normal kCFI (ABI) emits the following sequence:

   movl	$(-hash), %r10d
   addl	-15(%r11), %r10d
   je 1f
   ud2
1: cs call __x86_indirect_thunk_r11

(when used in conjunction with -mretpoline-external-thunk).

Notably, the Jcc here is always taken, resulting in lower throughput than would
be ideal. Replace it with the following sequence on boot:

   movl	$(-hash), %r10d
   addl	-15(%r11), %r10d
   jne . + 3
   test $0xd6, %al
   cs call __x86_indirect_thunk_r11

This jumps to the UDB instruction used as an immediate byte in the test
instruction. The test instruction will clobber eflags, but that is immaterial,
eflags is already changed by the preceding addl.

Intel recommends the FineIBT sequence on platforms that support IBT; older
platforms are still widely used and would benefit from this.

An earlier PoC was benchmarked by Scott:

Indirect branch miss rate (br_misp_retired.indirect:k / br_inst_retired.indirect:k)

BHI_DIS_S=1

  Benchmark            Baseline             IBT            kCFI        kCFI-opt
  -----------------------------------------------------------------------------
  iperf3 UDP           0.103764        0.103180        0.104311        0.102945
  hackbench            0.000885        0.000876        0.001996        0.000826
  lmbench syscall      0.005089        0.004486        0.016990        0.005852
  lmbench fork+exit    0.018454        0.019176        0.031085        0.015153
  lmbench fork+exec    0.017147        0.021613        0.029129        0.016337
  redis                0.032220        0.032655        0.045540        0.027946
  nginx+wrk            0.109033        0.112765        0.132557        0.102417
  fio randread         0.009704        0.009620        0.008548        0.000962
  fio seqwrite         0.006927        0.006707        0.019372        0.004590
  kbuild               0.056748        0.057324        0.064640        0.048136

BHI_DIS_S=0

  Benchmark            Baseline             IBT            kCFI        kCFI-opt
  -----------------------------------------------------------------------------
  iperf3 UDP           0.000077        0.000106        0.000186        0.000073
  hackbench            0.000123        0.000132        0.000367        0.000097
  lmbench syscall      0.023259        0.018319        0.040903        0.012772
  lmbench fork+exit    0.011494        0.011887        0.029079        0.016415
  lmbench fork+exec    0.037782        0.038994        0.055378        0.026381
  redis                0.002481        0.003152        0.017073        0.000184
  nginx+wrk            0.015478        0.016266        0.033637        0.000268
  fio randread         0.009836        0.007949        0.007096        0.000143
  fio seqwrite         0.014587        0.014165        0.041792        0.002157
  kbuild               0.055774        0.055249        0.062590        0.046546

Suggested-by: Scott D Constable <scott.d.constable@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Borislav Petkov (AMD) <bp@alien8.de>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Link: https://patch.msgid.link/20260612071506.GQ187714%40noisy.programming.kicks-ass.net
This commit is contained in:
Peter Zijlstra 2026-06-11 21:51:13 +02:00
parent f5098b6bae
commit b2250d63e6
2 changed files with 29 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
arch/x86/kernel/alternative.c
View File

@ -1356,6 +1356,20 @@ early_param("cfi", cfi_parse_cmdline);
* "Make conditional jumps most often not taken: The efficiency and throughput
* for not-taken branches is better than for taken branches on most
* processors. Therefore, it is good to place the most frequent branch first"
*
* NOTE: Update the kCFI caller sequence to make use of this observation:
*
* kCFI kCFI-OPT
*
* caller: caller:
* movl $(-0x12345678),%r10d // 6 movl $(-0x12345678),%r10d // 6
* addl $-15(%r11),%r10d // 4 addl $-15(%r11),%r10d // 4
* je 1f // 2 jne . + 3 // 2
* ud2 // 2 test $0xd6, %al // 2
* 1: cs call __x86_indirect_thunk_r11 // 6 1: cs call __x86_indirect_thunk_r11 // 6
*
* This new test clobbers eflags, but those are clobbered by the hash test
* anyway.
*/
/*
@ -1518,8 +1532,9 @@ static int cfi_disable_callers(s32 *start, s32 *end)
static int cfi_enable_callers(s32 *start, s32 *end)
{
/*
* Re-enable kCFI, undo what cfi_disable_callers() did.
* Re-enable (and update) kCFI, undo what cfi_disable_callers() did.
*/
const u8 udne[] = { 0x75, 0x01, 0xa8, 0xd6 };
const u8 mov[] = { 0x41, 0xba };
s32 *s;
@ -1532,6 +1547,10 @@ static int cfi_enable_callers(s32 *start, s32 *end)
if (!hash) /* nocfi callers */
continue;
/*
* See the kCFI/FineIBT comment above -- update note.
*/
text_poke_early(addr + 10, udne, 4);
text_poke_early(addr, mov, 2);
}

11
arch/x86/kernel/cfi.c
View File

@ -72,8 +72,15 @@ enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
switch (cfi_mode) {
case CFI_KCFI:
if (!is_cfi_trap(addr))
return BUG_TRAP_TYPE_NONE;
if (!is_cfi_trap(addr)) {
/*
* The updated kCFI sequence has "test $0xd6, %al" instead of
* "ud2", adjust the offset.
*/
addr -= 1;
if (!is_cfi_trap(addr))
return BUG_TRAP_TYPE_NONE;
}
if (!decode_cfi_insn(regs, &target, &type))
return report_cfi_failure_noaddr(regs, addr);