On 24/06/2026 15:15, Kunwu Chan wrote:
> On 6/23/26 00:38, Usama Arif wrote:
>> __csd_lock_record() publishes per-CPU CSD debug state that is read by
>> csd_lock_wait_toolong() on another CPU. The remote side first reads
>> cur_csd with smp_load_acquire() and, when non-NULL, may then read the
>> matching cur_csd_func and cur_csd_info fields.
>>
>> Use smp_store_release() when publishing cur_csd so that the preceding
>> cur_csd_func and cur_csd_info stores are ordered before the pointer
>> that csd_lock_wait_toolong() acquires. This replaces the open-coded
>> smp_wmb() plus plain cur_csd store with the release operation that
>> matches the smp_load_acquire() in csd_lock_wait_toolong().
>>
>> For the clear path, use smp_store_release(&cur_csd, NULL) so that
>> clearing the diagnostic state remains ordered after the preceding
>> callback/unlock work, without requiring a full barrier before the
>> store. On x86 this removes the locked full barrier from the clear
>> path; on weaker memory models it uses the release operation needed by
>> the smp_load_acquire() in csd_lock_wait_toolong().
>>
>> The old code also had smp_mb() calls around cur_csd updates. Those would
>> only be needed if cur_csd were treated as an exact live-state marker whose
>> publication had to be observed before callback execution or CSD unlock.
> The original comments around those updates seem to suggest a stronger
> relationship:
> /* Update cur_csd before function call. */
> /* NULL cur_csd after unlock. */
>
> The changelog characterizes cur_csd as best-effort diagnostic context.
>
> Is there prior consensus that cur_csd carries no ordering relationship
> to callback execution / unlock state,
>
> or is this patch effectively relaxing that historical assumption?
>
>
> Thanks, Kunwu
Thanks for the review Kunwu!
The patch preserves the ordering that reader actually needs:
csd_lock_wait_toolong() observes non-NULL cur_csd, the matching func/info have
been published. If it observes NULL, the prior callback/unlock work is ordered
before the clear.
So yes, this relaxes the historical implementation ordering around the
diagnostic marker, but not the CSD execution/reuse ordering.
>
>> CSD stall warnings do not currently have RCU-style stall-ended checks, so
>> they already allow the stall to end while diagnostics are being assembled.
>> The cur_csd record is therefore best-effort diagnostic context, not a
>> precise completion/stall boundary.
>>
>> Signed-off-by: Usama Arif <[email protected]>
>> ---
>> v1 -> v2:
>> https://lore.kernel.org/all/[email protected]/
>> - Document where the smp_store_release() synchronizes with (Alan Stern,
>> Randy Dunlap and Paul McKenney).
>> ---
>> kernel/smp.c | 18 ++++++++++++------
>> 1 file changed, 12 insertions(+), 6 deletions(-)
>>
>> diff --git a/kernel/smp.c b/kernel/smp.c
>> index a0bb56bd8dda..685829875a3e 100644
>> --- a/kernel/smp.c
>> +++ b/kernel/smp.c
>> @@ -182,16 +182,22 @@ static atomic_t csd_bug_count = ATOMIC_INIT(0);
>> static void __csd_lock_record(call_single_data_t *csd)
>> {
>> if (!csd) {
>> - smp_mb(); /* NULL cur_csd after unlock. */
>> - __this_cpu_write(cur_csd, NULL);
>> + /*
>> + * Pairs with smp_load_acquire() of cur_csd in
>> + * csd_lock_wait_toolong(): orders any preceding CSD
>> + * callback/unlock before a remote reader observes NULL.
>> + */
>> + smp_store_release(this_cpu_ptr(&cur_csd), NULL);
>> return;
>> }
>> __this_cpu_write(cur_csd_func, csd->func);
>> __this_cpu_write(cur_csd_info, csd->info);
>> - smp_wmb(); /* func and info before csd. */
>> - __this_cpu_write(cur_csd, csd);
>> - smp_mb(); /* Update cur_csd before function call. */
>> - /* Or before unlock, as the case may be. */
>> + /*
>> + * Pairs with smp_load_acquire() of cur_csd in
>> + * csd_lock_wait_toolong(): publishes cur_csd_func and
>> + * cur_csd_info before the non-NULL pointer becomes visible.
>> + */
>> + smp_store_release(this_cpu_ptr(&cur_csd), csd);
>> }
>>
>> static __always_inline void csd_lock_record(call_single_data_t *csd)
