commit 91ff28ae6d050e0ca01ac13eb8ba31d744cf672f
author Eric Dumazet <edumazet@google.com> Fri Dec 19 11:20:07 2025 +0000
committer Linus Torvalds <torvalds@linux-foundation.org> Sat Dec 20 14:47:12 2025 -0800
tree 6a0bd86ab9a5a9e666879032ccfc1ca712b23a56
parent 4cc5373f2e749a6c96e8b9fa971931a4dd852860

x86/irqflags: Use ASM_OUTPUT_RM in native_save_fl()

clang is generating very inefficient code for native_save_fl() which is
used for local_irq_save() in critical spots.

Allowing the "pop %0" to use memory:

 1) forces the compiler to add annoying stack canaries when
    CONFIG_STACKPROTECTOR_STRONG=y in many places.

 2) Almost always is followed by an immediate "move memory,register"

One good example is _raw_spin_lock_irqsave, with 8 extra instructions

  ffffffff82067a30 <_raw_spin_lock_irqsave>:
  ffffffff82067a30:		...
  ffffffff82067a39:		53						push   %rbx

  // Three instructions to ajust the stack, read the per-cpu canary
  // and copy it to 8(%rsp)
  ffffffff82067a3a:		48 83 ec 10 			sub    $0x10,%rsp
  ffffffff82067a3e:		65 48 8b 05 da 15 45 02 mov    %gs:0x24515da(%rip),%rax 	   # <__stack_chk_guard>
  ffffffff82067a46:		48 89 44 24 08			mov    %rax,0x8(%rsp)

  ffffffff82067a4b:		9c						pushf

  // instead of pop %rbx, compiler uses 2 instructions.
  ffffffff82067a4c:		8f 04 24				pop    (%rsp)
  ffffffff82067a4f:		48 8b 1c 24 			mov    (%rsp),%rbx

  ffffffff82067a53:		fa						cli
  ffffffff82067a54:		b9 01 00 00 00			mov    $0x1,%ecx
  ffffffff82067a59:		31 c0					xor    %eax,%eax
  ffffffff82067a5b:		f0 0f b1 0f 			lock cmpxchg %ecx,(%rdi)
  ffffffff82067a5f:		75 1d					jne    ffffffff82067a7e <_raw_spin_lock_irqsave+0x4e>

  // three instructions to check the stack canary
  ffffffff82067a61:		65 48 8b 05 b7 15 45 02 mov    %gs:0x24515b7(%rip),%rax 	   # <__stack_chk_guard>
  ffffffff82067a69:		48 3b 44 24 08			cmp    0x8(%rsp),%rax
  ffffffff82067a6e:		75 17					jne    ffffffff82067a87

  ...

  // One extra instruction to adjust the stack.
  ffffffff82067a73:		48 83 c4 10 			add    $0x10,%rsp
  ...

  // One more instruction in case the stack was mangled.
  ffffffff82067a87:		e8 a4 35 ff ff			call   ffffffff8205b030 <__stack_chk_fail>

This patch changes nothing for gcc, but for clang saves ~20000 bytes of text
even though more functions are inlined.

  $ size vmlinux.gcc.before vmlinux.gcc.after vmlinux.clang.before vmlinux.clang.after
     text	   data		bss		dec		hex	filename
  45565821	25005462	4704800	75276083	47c9f33	vmlinux.gcc.before
  45565821	25005462	4704800	75276083	47c9f33	vmlinux.gcc.after
  45121072	24638617	5533040	75292729	47ce039	vmlinux.clang.before
  45093887	24638633	5536808	75269328	47c84d0	vmlinux.clang.after

  $ scripts/bloat-o-meter -t vmlinux.clang.before vmlinux.clang.after
  add/remove: 1/2 grow/shrink: 21/533 up/down: 2250/-22112 (-19862)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>