Commit 2183a5c8 authored by Mateusz Guzik's avatar Mateusz Guzik Committed by Jakub Kicinski
Browse files

af_unix: annotate unix_gc_lock with __cacheline_aligned_in_smp 

Otherwise the lock is susceptible to ever-changing false-sharing due to
unrelated changes. This in particular popped up here where an unrelated
change improved performance:
https://lore.kernel.org/oe-lkp/202511281306.51105b46-lkp@intel.com/



Stabilize it with an explicit annotation which also has a side effect
of furher improving scalability:
> in our oiginal report, 284922f4 has a 6.1% performance improvement comparing
> to parent 17d85f33.
> we applied your patch directly upon 284922f4. as below, now by
> "284922f4 + your patch"
> we observe a 12.8% performance improvements (still comparing to 17d85f33).

Note nothing was done for the other fields, so some fluctuation is still
possible.

Tested-by: default avatarkernel test robot <oliver.sang@intel.com>
Signed-off-by: default avatarMateusz Guzik <mjguzik@gmail.com>
Reviewed-by: default avatarKuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251203100122.291550-1-mjguzik@gmail.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 0373d5c3

net/unix/garbage.c

+1 −1
Original line number Diff line number Diff line
@@ -199,7 +199,7 @@ static void unix_free_vertices(struct scm_fp_list *fpl) 
	}

}



static DEFINE_SPINLOCK(unix_gc_lock);

static __cacheline_aligned_in_smp DEFINE_SPINLOCK(unix_gc_lock);



void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver)

{