Re: [REGRESSION] 6.7.1: md: raid5 hang and unresponsive system; successfully bisected

[Dan Moulding <dan@danm.net>]

> How about the following patch?
> 
> Thanks,
> Kuai
> 
> diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
> index 3ad5f3c7f91e..0b2e6060f2c9 100644
> --- a/drivers/md/raid5.c
> +++ b/drivers/md/raid5.c
> @@ -6720,7 +6720,6 @@ static void raid5d(struct md_thread *thread)
> 
>          md_check_recovery(mddev);
> 
> -       blk_start_plug(&plug);
>          handled = 0;
>          spin_lock_irq(&conf->device_lock);
>          while (1) {
> @@ -6728,6 +6727,14 @@ static void raid5d(struct md_thread *thread)
>                  int batch_size, released;
>                  unsigned int offset;
> 
> +               /*
> +                * md_check_recovery() can't clear sb_flags, usually 
> because of
> +                * 'reconfig_mutex' can't be grabbed, wait for 
> mddev_unlock() to
> +                * wake up raid5d().
> +                */
> +               if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
> +                       goto skip;
> +
>                  released = release_stripe_list(conf, 
> conf->temp_inactive_list);
>                  if (released)
>                          clear_bit(R5_DID_ALLOC, &conf->cache_state);
> @@ -6766,8 +6773,8 @@ static void raid5d(struct md_thread *thread)
>                          spin_lock_irq(&conf->device_lock);
>                  }
>          }
> +skip:
>          pr_debug("%d stripes handled\n", handled);
> -
>          spin_unlock_irq(&conf->device_lock);
>          if (test_and_clear_bit(R5_ALLOC_MORE, &conf->cache_state) &&
>              mutex_trylock(&conf->cache_size_mutex)) {
> @@ -6779,6 +6786,7 @@ static void raid5d(struct md_thread *thread)
>                  mutex_unlock(&conf->cache_size_mutex);
>          }
> 
> +       blk_start_plug(&plug);
>          flush_deferred_bios(conf);
> 
>          r5l_flush_stripe_to_raid(conf->log);

I can confirm that this patch also works. I'm unable to reproduce the
hang after applying this instead of the first patch provided by
Junxiao. So looks like both ways are succesful in avoiding the hang.

-- Dan