Re: Crashes/hung tasks with z3pool under memory pressure

[Vitaly Wool]

Hi Guenter,

> [ ... ]
> > Ugh. Could you please keep that patch and apply this on top:
> > 
> > diff --git a/mm/z3fold.c b/mm/z3fold.c
> > index c0bca6153b95..e8a80d044d9e 100644
> > --- a/mm/z3fold.c
> > +++ b/mm/z3fold.c
> > @@ -840,6 +840,7 @@ static int z3fold_reclaim_page(struct z3fold_pool 
> > *pool, unsigned int retries)
> >                       kref_get(&zhdr->refcount);
> >                       list_del_init(&zhdr->buddy);
> >                       zhdr->cpu = -1;
> > +                     break;
> >               }
> >               list_del_init(&page->lru);
> > 
> Much better, in a way. The system now takes much longer to crash,
> and the crash reason is a bit different. The log is too long to attach,
> so I copied it to [1].
> 
> crashdump.0002                  Latest log
> 000[12]-Fix-attempt-[12].patch  Patches applied on top of v4.17.0-rc1.

thanks for the update. Let's start from a clean sheet. I believe this patch has 
to be applied anyway so could you please check if it solves the problem. 

diff --git a/mm/z3fold.c b/mm/z3fold.c
index c0bca6153b95..059fb3d5ca86 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -144,7 +144,8 @@ enum z3fold_page_flags {
        PAGE_HEADLESS = 0,
        MIDDLE_CHUNK_MAPPED,
        NEEDS_COMPACTING,
-       PAGE_STALE
+       PAGE_STALE,
+       UNDER_RECLAIM
 };
 
 /*****************
@@ -173,6 +174,7 @@ static struct z3fold_header *init_z3fold_page(struct page 
*page,
        clear_bit(MIDDLE_CHUNK_MAPPED, &page->private);
        clear_bit(NEEDS_COMPACTING, &page->private);
        clear_bit(PAGE_STALE, &page->private);
+       clear_bit(UNDER_RECLAIM, &page->private);
 
        spin_lock_init(&zhdr->page_lock);
        kref_init(&zhdr->refcount);
@@ -756,6 +758,10 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned 
long handle)
                atomic64_dec(&pool->pages_nr);
                return;
        }
+       if (test_bit(UNDER_RECLAIM, &page->private)) {
+               z3fold_page_unlock(zhdr);
+               return;
+       }
        if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) {
                z3fold_page_unlock(zhdr);
                return;
@@ -840,6 +846,8 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, 
unsigned int retries)
                        kref_get(&zhdr->refcount);
                        list_del_init(&zhdr->buddy);
                        zhdr->cpu = -1;
+                       set_bit(UNDER_RECLAIM, &page->private);
+                       break;
                }
 
                list_del_init(&page->lru);
@@ -888,6 +896,7 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, 
unsigned int retries)
                }
 next:
                spin_lock(&pool->lock);
+               clear_bit(UNDER_RECLAIM, &page->private);
                if (test_bit(PAGE_HEADLESS, &page->private)) {
                        if (ret == 0) {
                                spin_unlock(&pool->lock);