Re: 回复: [External Mail][PATCH 6.18.y v2] mm: shmem: fix potential livelock issue for shmem direct swapin

[Baolin Wang]

On 7/13/26 7:55 PM, 马超 wrote:
> > When skipping swapcache for synchronous IO swap devices, swapcache_prepare() is used to prevent parallel swapin from proceeding with the swap cache flag.
> > However, on PREEMPT kernels this can lead to a livelock, as reported by Chao[1]:
> >
> > Thread A starts direct swapin of a shmem folio and calls swapcache_prepare() to set SWAP_HAS_CACHE. It may then be preempted inside workingset_refault().
> > Meanwhile, a higher priority thread B also attempts direct swapin of the same shmem swap entry. Since swapcache_prepare() already marks the entry, thread B repeatedly gets -EEXIST and busy-loops waiting for thread A to finish. But as thread B runs at higher priority, thread A cannot preempt it, resulting in starvation and a livelock.
> >
> > Fix it by yielding the CPU with schedule_timeout_uninterruptible(1) when
> > swapcache_prepare() fails, following the same approach used in commit 029c4628b2eb ("mm: swap: get rid of livelock in swapin readahead") and commit 13ddaf26be32 ("mm/swap: fix race when skipping swapcache").
> >
> > However, commit 01626a1823 ("mm: avoid unconditional one-tick sleep when swapcache_prepare fails") found that the unconditional one-tick sleep can cause UI stuttering on latency-sensitive Android devices. So we can follow the same approach by adding a waitqueue to wake up tasks when needed, instead of always sleeping for a full tick.
> >
> > Note that mainline does not have this potential issue, which has already been resolved by Kairui's swap refactoring work[2].
> >
> > [1] https://lore.kernel.org/all/700a2cbf90a2484f979aac858f08f5d4@xxxxxxxxxx/
> > [2] https://lore.kernel.org/all/20260517-swap-table-p4-v5-0-88ae43e064c7@xxxxxxxxxxx/
> > Fixes: 1dd44c0af4fa ("mm: shmem: skip swapcache for swapin of synchronous swap device")
> > Reported-by: Ma Chao <machao26@xxxxxxxxxx>
> > Closes: https://lore.kernel.org/all/700a2cbf90a2484f979aac858f08f5d4@xxxxxxxxxx/
> > Signed-off-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
> > ---
> > Changes from v1:
> > - Add a waitqueue to wake up tasks when needed.
> >
> > Hi Chao, could you try this patch to check if fix your issue? Thanks.
> > ---
> > mm/shmem.c | 14 +++++++++++++-
> > 1 file changed, 13 insertions(+), 1 deletion(-)
> >
> > diff --git a/mm/shmem.c b/mm/shmem.c
> > index 94c5b0d78ac3..3c329b794ae4 100644
> > --- a/mm/shmem.c
> > +++ b/mm/shmem.c
> > @@ -2005,11 +2005,14 @@ static struct folio *shmem_alloc_and_add_folio(struct vm_fault *vmf,
> >         return ERR_PTR(error);
> > }
> >
> > +static DECLARE_WAIT_QUEUE_HEAD(shmem_swapcache_wq);
> > +
> > static struct folio *shmem_swap_alloc_folio(struct inode *inode,
> >                 struct vm_area_struct *vma, pgoff_t index,
> >                 swp_entry_t entry, int order, gfp_t gfp)  {
> >         struct shmem_inode_info *info = SHMEM_I(inode);
> > +       DECLARE_WAITQUEUE(wait, current);
> >         int nr_pages = 1 << order;
> >         struct folio *new;
> >         gfp_t alloc_gfp;
> > @@ -2066,6 +2069,10 @@ static struct folio *shmem_swap_alloc_folio(struct inode *inode,
> >         if (swapcache_prepare(entry, nr_pages)) {
> >                 folio_put(new);
> >                 new = ERR_PTR(-EEXIST);
> > +               /* Relax a bit to prevent rapid repeated page faults */
> > +               add_wait_queue(&shmem_swapcache_wq, &wait);
> > +               schedule_timeout_uninterruptible(1);
> > +               remove_wait_queue(&shmem_swapcache_wq, &wait);
> >                 /* Try smaller folio to avoid cache conflict */
> >                 goto fallback;
> >         }
> > @@ -2423,6 +2430,8 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
> >         if (skip_swapcache) {
> >                 folio->swap.val = 0;
> >                 swapcache_clear(si, swap, nr_pages);
> > +               if (waitqueue_active(&shmem_swapcache_wq))
> > +                       wake_up(&shmem_swapcache_wq);
> >         } else {
> >                 swap_cache_del_folio(folio);
> >         }
> > @@ -2442,8 +2451,11 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
> >         if (folio)
> >                 folio_unlock(folio);
> > failed_nolock:
> > -       if (skip_swapcache)
> > +       if (skip_swapcache) {
> >                 swapcache_clear(si, folio->swap, folio_nr_pages(folio));
> > +               if (waitqueue_active(&shmem_swapcache_wq))
> > +                       wake_up(&shmem_swapcache_wq);
> > +       }
> >         if (folio)
> >                 folio_put(folio);
> >         put_swap_device(si);
> > --
> > 2.47.3
>
> We have conducted stress tests on over 10 pcs for 40 hours each, and no relevant issues have been reproduced.

Thanks for testing. Could you add your 'Tested-by:' tag?