[PATCH] seqlock: annotate spinning as unlikely() in __read_seqcount_begin

From: Mateusz Guzik
Date: Thu Jul 27 2023 - 14:04:08 EST


Annotation already used to be there, but got lost in 52ac39e5db5148f7
("seqlock: seqcount_t: Implement all read APIs as statement expressions").
Does not look like it was intentional.

Without it gcc 12 decides to compile the following in path_init:
nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount);
nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount);

into 2 cases of conditional jumps forward if the value is even, aka
branch prediction miss by default in the common case on x86-64.

With the patch jumps are only for odd values.

before:
[snip]
mov 0x104fe96(%rip),%eax # 0xffffffff82409680 <mount_lock>
test $0x1,%al
je 0xffffffff813b97fa <path_init+122>
pause
mov 0x104fe8a(%rip),%eax # 0xffffffff82409680 <mount_lock>
test $0x1,%al
jne 0xffffffff813b97ee <path_init+110>
mov %eax,0x48(%rbx)
mov 0x104fdfd(%rip),%eax # 0xffffffff82409600 <rename_lock>
test $0x1,%al
je 0xffffffff813b9813 <path_init+147>
pause
mov 0x104fdf1(%rip),%eax # 0xffffffff82409600 <rename_lock>
test $0x1,%al
jne 0xffffffff813b9807 <path_init+135>
[/snip]

after:
[snip]
mov 0x104fec6(%rip),%eax # 0xffffffff82409680 <mount_lock>
test $0x1,%al
jne 0xffffffff813b99af <path_init+607>
mov %eax,0x48(%rbx)
mov 0x104fe35(%rip),%eax # 0xffffffff82409600 <rename_lock>
test $0x1,%al
jne 0xffffffff813b999d <path_init+589>
[/snip]

Interestingly .text gets slightly smaller (as reported by size(1)):
before: 20702563
after: 20702429

Signed-off-by: Mateusz Guzik <mjguzik@xxxxxxxxx>
---
include/linux/seqlock.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 987a59d977c5..225eb1db35b8 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -326,7 +326,7 @@ SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock, mutex
({ \
unsigned __seq; \
\
- while ((__seq = seqprop_sequence(s)) & 1) \
+ while (unlikely((__seq = seqprop_sequence(s)) & 1)) \
cpu_relax(); \
\
kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \
--
2.39.2