1 files changed, 43 insertions, 111 deletions

diff --git a/mm/z3fold.c b/mm/z3fold.c
index 75b7962439ff..05bdf90646e7 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -41,7 +41,6 @@
 #include <linux/workqueue.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
-#include <linux/wait.h>
 #include <linux/zpool.h>
 #include <linux/magic.h>
 
@@ -146,8 +145,6 @@ struct z3fold_header {
  * @release_wq:	workqueue for safe page release
  * @work:	work_struct for safe page release
  * @inode:	inode for z3fold pseudo filesystem
- * @destroying: bool to stop migration once we start destruction
- * @isolated: int to count the number of pages currently in isolation
  *
  * This structure is allocated at pool creation time and maintains metadata
  * pertaining to a particular z3fold pool.
@@ -166,11 +163,8 @@ struct z3fold_pool {
 	const struct zpool_ops *zpool_ops;
 	struct workqueue_struct *compact_wq;
 	struct workqueue_struct *release_wq;
-	struct wait_queue_head isolate_wait;
 	struct work_struct work;
 	struct inode *inode;
-	bool destroying;
-	int isolated;
 };
 
 /*
@@ -301,14 +295,11 @@ static void z3fold_unregister_migration(struct z3fold_pool *pool)
  }
 
 /* Initializes the z3fold header of a newly allocated z3fold page */
-static struct z3fold_header *init_z3fold_page(struct page *page,
+static struct z3fold_header *init_z3fold_page(struct page *page, bool headless,
 					struct z3fold_pool *pool, gfp_t gfp)
 {
 	struct z3fold_header *zhdr = page_address(page);
-	struct z3fold_buddy_slots *slots = alloc_slots(pool, gfp);
-
-	if (!slots)
-		return NULL;
+	struct z3fold_buddy_slots *slots;
 
 	INIT_LIST_HEAD(&page->lru);
 	clear_bit(PAGE_HEADLESS, &page->private);
@@ -316,6 +307,12 @@ static struct z3fold_header *init_z3fold_page(struct page *page,
 	clear_bit(NEEDS_COMPACTING, &page->private);
 	clear_bit(PAGE_STALE, &page->private);
 	clear_bit(PAGE_CLAIMED, &page->private);
+	if (headless)
+		return zhdr;
+
+	slots = alloc_slots(pool, gfp);
+	if (!slots)
+		return NULL;
 
 	spin_lock_init(&zhdr->page_lock);
 	kref_init(&zhdr->refcount);
@@ -372,9 +369,10 @@ static inline int __idx(struct z3fold_header *zhdr, enum buddy bud)
  * Encodes the handle of a particular buddy within a z3fold page
  * Pool lock should be held as this function accesses first_num
  */
-static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud)
+static unsigned long __encode_handle(struct z3fold_header *zhdr,
+				struct z3fold_buddy_slots *slots,
+				enum buddy bud)
 {
-	struct z3fold_buddy_slots *slots;
 	unsigned long h = (unsigned long)zhdr;
 	int idx = 0;
 
@@ -391,11 +389,15 @@ static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud)
 	if (bud == LAST)
 		h |= (zhdr->last_chunks << BUDDY_SHIFT);
 
-	slots = zhdr->slots;
 	slots->slot[idx] = h;
 	return (unsigned long)&slots->slot[idx];
 }
 
+static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud)
+{
+	return __encode_handle(zhdr, zhdr->slots, bud);
+}
+
 /* Returns the z3fold page where a given handle is stored */
 static inline struct z3fold_header *handle_to_z3fold_header(unsigned long h)
 {
@@ -630,6 +632,7 @@ static void do_compact_page(struct z3fold_header *zhdr, bool locked)
 	}
 
 	if (unlikely(PageIsolated(page) ||
+		     test_bit(PAGE_CLAIMED, &page->private) ||
 		     test_bit(PAGE_STALE, &page->private))) {
 		z3fold_page_unlock(zhdr);
 		return;
@@ -775,7 +778,6 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp,
 		goto out_c;
 	spin_lock_init(&pool->lock);
 	spin_lock_init(&pool->stale_lock);
-	init_waitqueue_head(&pool->isolate_wait);
 	pool->unbuddied = __alloc_percpu(sizeof(struct list_head)*NCHUNKS, 2);
 	if (!pool->unbuddied)
 		goto out_pool;
@@ -815,15 +817,6 @@ out:
 	return NULL;
 }
 
-static bool pool_isolated_are_drained(struct z3fold_pool *pool)
-{
-	bool ret;
-
-	spin_lock(&pool->lock);
-	ret = pool->isolated == 0;
-	spin_unlock(&pool->lock);
-	return ret;
-}
 /**
  * z3fold_destroy_pool() - destroys an existing z3fold pool
  * @pool:	the z3fold pool to be destroyed
@@ -833,22 +826,6 @@ static bool pool_isolated_are_drained(struct z3fold_pool *pool)
 static void z3fold_destroy_pool(struct z3fold_pool *pool)
 {
 	kmem_cache_destroy(pool->c_handle);
-	/*
-	 * We set pool-> destroying under lock to ensure that
-	 * z3fold_page_isolate() sees any changes to destroying. This way we
-	 * avoid the need for any memory barriers.
-	 */
-
-	spin_lock(&pool->lock);
-	pool->destroying = true;
-	spin_unlock(&pool->lock);
-
-	/*
-	 * We need to ensure that no pages are being migrated while we destroy
-	 * these workqueues, as migration can queue work on either of the
-	 * workqueues.
-	 */
-	wait_event(pool->isolate_wait, !pool_isolated_are_drained(pool));
 
 	/*
 	 * We need to destroy pool->compact_wq before pool->release_wq,
@@ -956,7 +933,7 @@ retry:
 	if (!page)
 		return -ENOMEM;
 
-	zhdr = init_z3fold_page(page, pool, gfp);
+	zhdr = init_z3fold_page(page, bud == HEADLESS, pool, gfp);
 	if (!zhdr) {
 		__free_page(page);
 		return -ENOMEM;
@@ -1132,6 +1109,7 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 	struct z3fold_header *zhdr = NULL;
 	struct page *page = NULL;
 	struct list_head *pos;
+	struct z3fold_buddy_slots slots;
 	unsigned long first_handle = 0, middle_handle = 0, last_handle = 0;
 
 	spin_lock(&pool->lock);
@@ -1150,16 +1128,22 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 			/* this bit could have been set by free, in which case
 			 * we pass over to the next page in the pool.
 			 */
-			if (test_and_set_bit(PAGE_CLAIMED, &page->private))
+			if (test_and_set_bit(PAGE_CLAIMED, &page->private)) {
+				page = NULL;
 				continue;
+			}
 
-			if (unlikely(PageIsolated(page)))
+			if (unlikely(PageIsolated(page))) {
+				clear_bit(PAGE_CLAIMED, &page->private);
+				page = NULL;
 				continue;
+			}
+			zhdr = page_address(page);
 			if (test_bit(PAGE_HEADLESS, &page->private))
 				break;
 
-			zhdr = page_address(page);
 			if (!z3fold_page_trylock(zhdr)) {
+				clear_bit(PAGE_CLAIMED, &page->private);
 				zhdr = NULL;
 				continue; /* can't evict at this point */
 			}
@@ -1177,26 +1161,30 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 
 		if (!test_bit(PAGE_HEADLESS, &page->private)) {
 			/*
-			 * We need encode the handles before unlocking, since
-			 * we can race with free that will set
-			 * (first|last)_chunks to 0
+			 * We need encode the handles before unlocking, and
+			 * use our local slots structure because z3fold_free
+			 * can zero out zhdr->slots and we can't do much
+			 * about that
 			 */
 			first_handle = 0;
 			last_handle = 0;
 			middle_handle = 0;
 			if (zhdr->first_chunks)
-				first_handle = encode_handle(zhdr, FIRST);
+				first_handle = __encode_handle(zhdr, &slots,
+								FIRST);
 			if (zhdr->middle_chunks)
-				middle_handle = encode_handle(zhdr, MIDDLE);
+				middle_handle = __encode_handle(zhdr, &slots,
+								MIDDLE);
 			if (zhdr->last_chunks)
-				last_handle = encode_handle(zhdr, LAST);
+				last_handle = __encode_handle(zhdr, &slots,
+								LAST);
 			/*
 			 * it's safe to unlock here because we hold a
 			 * reference to this page
 			 */
 			z3fold_page_unlock(zhdr);
 		} else {
-			first_handle = encode_handle(zhdr, HEADLESS);
+			first_handle = __encode_handle(zhdr, &slots, HEADLESS);
 			last_handle = middle_handle = 0;
 		}
 
@@ -1226,9 +1214,9 @@ next:
 			spin_lock(&pool->lock);
 			list_add(&page->lru, &pool->lru);
 			spin_unlock(&pool->lock);
+			clear_bit(PAGE_CLAIMED, &page->private);
 		} else {
 			z3fold_page_lock(zhdr);
-			clear_bit(PAGE_CLAIMED, &page->private);
 			if (kref_put(&zhdr->refcount,
 					release_z3fold_page_locked)) {
 				atomic64_dec(&pool->pages_nr);
@@ -1243,6 +1231,7 @@ next:
 			list_add(&page->lru, &pool->lru);
 			spin_unlock(&pool->lock);
 			z3fold_page_unlock(zhdr);
+			clear_bit(PAGE_CLAIMED, &page->private);
 		}
 
 		/* We started off locked to we need to lock the pool back */
@@ -1339,28 +1328,6 @@ static u64 z3fold_get_pool_size(struct z3fold_pool *pool)
 	return atomic64_read(&pool->pages_nr);
 }
 
-/*
- * z3fold_dec_isolated() expects to be called while pool->lock is held.
- */
-static void z3fold_dec_isolated(struct z3fold_pool *pool)
-{
-	assert_spin_locked(&pool->lock);
-	VM_BUG_ON(pool->isolated <= 0);
-	pool->isolated--;
-
-	/*
-	 * If we have no more isolated pages, we have to see if
-	 * z3fold_destroy_pool() is waiting for a signal.
-	 */
-	if (pool->isolated == 0 && waitqueue_active(&pool->isolate_wait))
-		wake_up_all(&pool->isolate_wait);
-}
-
-static void z3fold_inc_isolated(struct z3fold_pool *pool)
-{
-	pool->isolated++;
-}
-
 static bool z3fold_page_isolate(struct page *page, isolate_mode_t mode)
 {
 	struct z3fold_header *zhdr;
@@ -1369,7 +1336,8 @@ static bool z3fold_page_isolate(struct page *page, isolate_mode_t mode)
 	VM_BUG_ON_PAGE(!PageMovable(page), page);
 	VM_BUG_ON_PAGE(PageIsolated(page), page);
 
-	if (test_bit(PAGE_HEADLESS, &page->private))
+	if (test_bit(PAGE_HEADLESS, &page->private) ||
+	    test_bit(PAGE_CLAIMED, &page->private))
 		return false;
 
 	zhdr = page_address(page);
@@ -1387,34 +1355,6 @@ static bool z3fold_page_isolate(struct page *page, isolate_mode_t mode)
 		spin_lock(&pool->lock);
 		if (!list_empty(&page->lru))
 			list_del(&page->lru);
-		/*
-		 * We need to check for destruction while holding pool->lock, as
-		 * otherwise destruction could see 0 isolated pages, and
-		 * proceed.
-		 */
-		if (unlikely(pool->destroying)) {
-			spin_unlock(&pool->lock);
-			/*
-			 * If this page isn't stale, somebody else holds a
-			 * reference to it. Let't drop our refcount so that they
-			 * can call the release logic.
-			 */
-			if (unlikely(kref_put(&zhdr->refcount,
-					      release_z3fold_page_locked))) {
-				/*
-				 * If we get here we have kref problems, so we
-				 * should freak out.
-				 */
-				WARN(1, "Z3fold is experiencing kref problems\n");
-				z3fold_page_unlock(zhdr);
-				return false;
-			}
-			z3fold_page_unlock(zhdr);
-			return false;
-		}
-
-
-		z3fold_inc_isolated(pool);
 		spin_unlock(&pool->lock);
 		z3fold_page_unlock(zhdr);
 		return true;
@@ -1483,10 +1423,6 @@ static int z3fold_page_migrate(struct address_space *mapping, struct page *newpa
 
 	queue_work_on(new_zhdr->cpu, pool->compact_wq, &new_zhdr->work);
 
-	spin_lock(&pool->lock);
-	z3fold_dec_isolated(pool);
-	spin_unlock(&pool->lock);
-
 	page_mapcount_reset(page);
 	put_page(page);
 	return 0;
@@ -1506,14 +1442,10 @@ static void z3fold_page_putback(struct page *page)
 	INIT_LIST_HEAD(&page->lru);
 	if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) {
 		atomic64_dec(&pool->pages_nr);
-		spin_lock(&pool->lock);
-		z3fold_dec_isolated(pool);
-		spin_unlock(&pool->lock);
 		return;
 	}
 	spin_lock(&pool->lock);
 	list_add(&page->lru, &pool->lru);
-	z3fold_dec_isolated(pool);
 	spin_unlock(&pool->lock);
 	z3fold_page_unlock(zhdr);
 }