Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Thu, 8 Jun 2023 13:04:59 -0400
From:   Johannes Weiner <hannes@cmpxchg.org>
To:     Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Cc:     vitaly.wool@konsulko.com, minchan@kernel.org,
        senozhatsky@chromium.org, yosryahmed@google.com,
        linux-mm@kvack.org, ddstreet@ieee.org, sjenning@redhat.com,
        nphamcs@gmail.com, akpm@linux-foundation.org,
        linux-kernel@vger.kernel.org, kernel-team@meta.com
Subject: Re: [RFC PATCH v2 1/7] mm: zswap: add pool shrinking mechanism
Message-ID: <20230608170459.GH352940@cmpxchg.org>
References: <20230606145611.704392-1-cerasuolodomenico@gmail.com>
 <20230606145611.704392-2-cerasuolodomenico@gmail.com>
 <20230608165250.GG352940@cmpxchg.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20230608165250.GG352940@cmpxchg.org>
Precedence: bulk

On Thu, Jun 08, 2023 at 12:52:51PM -0400, Johannes Weiner wrote:
> On Tue, Jun 06, 2023 at 04:56:05PM +0200, Domenico Cerasuolo wrote:
> > @@ -584,14 +601,70 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor)
> >  	return NULL;
> >  }
> >  
> > +static int zswap_shrink(struct zswap_pool *pool)
> > +{
> > +	struct zswap_entry *lru_entry, *tree_entry = NULL;
> > +	struct zswap_header *zhdr;
> > +	struct zswap_tree *tree;
> > +	int swpoffset;
> > +	int ret;
> > +
> > +	/* get a reclaimable entry from LRU */
> > +	spin_lock(&pool->lru_lock);
> > +	if (list_empty(&pool->lru)) {
> > +		spin_unlock(&pool->lru_lock);
> > +		return -EINVAL;
> > +	}
> > +	lru_entry = list_last_entry(&pool->lru, struct zswap_entry, lru);
> > +	list_del_init(&lru_entry->lru);
> > +	zhdr = zpool_map_handle(pool->zpool, lru_entry->handle, ZPOOL_MM_RO);
> > +	tree = zswap_trees[swp_type(zhdr->swpentry)];
> > +	zpool_unmap_handle(pool->zpool, lru_entry->handle);
> > +	/*
> > +	 * Once the pool lock is dropped, the lru_entry might get freed. The
> > +	 * swpoffset is copied to the stack, and lru_entry isn't deref'd again
> > +	 * until the entry is verified to still be alive in the tree.
> > +	 */
> > +	swpoffset = swp_offset(zhdr->swpentry);
> > +	spin_unlock(&pool->lru_lock);
> > +
> > +	/* hold a reference from tree so it won't be freed during writeback */
> > +	spin_lock(&tree->lock);
> > +	tree_entry = zswap_entry_find_get(&tree->rbroot, swpoffset);
> > +	if (tree_entry != lru_entry) {
> > +		if (tree_entry)
> > +			zswap_entry_put(tree, tree_entry);
> > +		spin_unlock(&tree->lock);
> > +		return -EAGAIN;
> > +	}
> > +	spin_unlock(&tree->lock);
> > +
> > +	ret = zswap_writeback_entry(pool->zpool, lru_entry->handle);
> > +
> > +	spin_lock(&tree->lock);
> > +	if (ret) {
> > +		spin_lock(&pool->lru_lock);
> > +		list_move(&lru_entry->lru, &pool->lru);
> > +		spin_unlock(&pool->lru_lock);
> > +	}
> > +	zswap_entry_put(tree, tree_entry);
> 
> On re-reading this, I find the lru_entry vs tree_entry distinction
> unnecessarily complicated. Once it's known that the thing coming off
> the LRU is the same thing as in the tree, there is only "the entry".
> 
> How about 'entry' and 'tree_entry', and after validation use 'entry'
> throughout the rest of the function?

Even better, safe the tree_entry entirely by getting the reference
from the LRU already, and then just search the tree for a match:

	/* Get an entry off the LRU */
	spin_lock(&pool->lru_lock);
	entry = list_last_entry();
	list_del(&entry->lru);
	zswap_entry_get(entry);
	spin_unlock(&pool->lru_lock);

	/* Check for invalidate() race */
	spin_lock(&tree->lock);
	if (entry != zswap_rb_search(&tree->rbroot, swpoffset)) {
		ret = -EAGAIN;
		goto put_unlock;
	}
	spin_unlock(&tree->lock);

	ret = zswap_writeback_entry();

	spin_lock(&tree->lock);
	if (ret) {
		put_back_on_lru();
		goto put_unlock;
	}

	/* Check for invalidate() race */
	if (entry != zswap_rb_search(&tree->rbroot, swpoffset))
		goto put_unlock;

	/* Drop base reference */
	zswap_entry_put(tree, entry);

put_unlock:
	/* Drop local reference */
	zswap_entry_put(tree, entry);
	spin_unlock(&tree->lock);

	return ret ? -EAGAIN : 0;