[PATCH 2/2] membarrier: riscv: Provide core serializing command

[Mathieu Desnoyers]

On 2023-11-29 16:25, Andrea Parri wrote:
>>> As regards the Fixes: tag, I guess it boils down to what we want or we
>>> need to take for commit "riscv: Support membarrier private cmd".  :-)
>>
>> I'm not seeing this commit in the Linux master branch, am I missing
>> something ?
> 
> I don't think you're missing something: I was wondering "what/where is
> this commit"?  Sorry for the confusion.
> 
> 
>>> FWIW, a quick git-log search confirmed that MEMBARRIER has been around
>>> for quite some time in the RISC-V world (though I'm not familiar with
>>> any of its mainstream uses): commit 1464d00b27b2 says (at least) since
>>> 93917ad50972 ("RISC-V: Add support for restartable sequence").  I am
>>> currently inclined to pick the latter commit (and check it w/ Palmer),
>>> but other suggestions are welcome.
>>
>> Supporting membarrier private expedited is not optional since Linux 4.14:
>>
>> see kernel/sched/core.c:
>>
>>                  membarrier_switch_mm(rq, prev->active_mm, next->mm);
>>                  /*
>>                   * sys_membarrier() requires an smp_mb() between setting
>>                   * rq->curr / membarrier_switch_mm() and returning to userspace.
>>                   *
>>                   * The below provides this either through switch_mm(), or in
>>                   * case 'prev->active_mm == next->mm' through
>>                   * finish_task_switch()'s mmdrop().
>>                   */
>>                  switch_mm_irqs_off(prev->active_mm, next->mm, next);
>>
>> Failure to provide the required barrier is a bug in the architecture's
>> switch_mm implementation when CONFIG_MEMBARRIER=y.
>>
>> We should probably introduce a new
>> Documentation/features/sched/membarrier/arch-support.txt
>> to clarify this requirement.
>>
>> Userspace code such as liburcu [1] heavily relies on membarrier private
>> expedited (when available) to speed up RCU read-side critical sections.
>> Various DNS servers, including BIND 9, use liburcu.
> 
> Thanks for the information.
> 
> So I should probably stick to 93917ad50972, which apparently selected
> CONFIG_MEMBARRIER on RISC-V, for the Fixes: tag in question.

I think it goes further than that, because you can explicitly
CONFIG_MEMBARRIER=y, see init/Kconfig:

config MEMBARRIER
         bool "Enable membarrier() system call" if EXPERT
         default y
         help
           Enable the membarrier() system call that allows issuing memory
           barriers across all running threads, which can be used to distribute
           the cost of user-space memory barriers asymmetrically by transforming
           pairs of memory barriers into pairs consisting of membarrier() and a
           compiler barrier.

           If unsure, say Y.

Before 1464d00b27b2, riscv just happened to set it to =n in the defconfig.

I suspect the initial port of riscv merged after v4.14 was already broken.

> I'll look into adding the membarrier feature you mention (as a final/
> follow-up patch), unless you or someone else want to take care of it.

I'll be happy to review it :)

Thanks,

Mathieu

-- 
Mathieu Desnoyers
EfficiOS Inc.
https://www.efficios.com