1 files changed, 177 insertions, 378 deletions

diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c
index 2e80bb6aa957..f50620f5a0a1 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.c
+++ b/drivers/infiniband/sw/rxe/rxe_pool.c
@@ -5,499 +5,298 @@
  */
 
 #include "rxe.h"
-#include "rxe_loc.h"
+
+#define RXE_POOL_TIMEOUT	(200)
+#define RXE_POOL_ALIGN		(16)
 
 static const struct rxe_type_info {
 	const char *name;
 	size_t size;
 	size_t elem_offset;
-	void (*cleanup)(struct rxe_pool_entry *obj);
-	enum rxe_pool_flags flags;
+	void (*cleanup)(struct rxe_pool_elem *elem);
 	u32 min_index;
 	u32 max_index;
-	size_t key_offset;
-	size_t key_size;
+	u32 max_elem;
 } rxe_type_info[RXE_NUM_TYPES] = {
 	[RXE_TYPE_UC] = {
-		.name		= "rxe-uc",
+		.name		= "uc",
 		.size		= sizeof(struct rxe_ucontext),
-		.elem_offset	= offsetof(struct rxe_ucontext, pelem),
-		.flags          = RXE_POOL_NO_ALLOC,
+		.elem_offset	= offsetof(struct rxe_ucontext, elem),
+		.min_index	= 1,
+		.max_index	= UINT_MAX,
+		.max_elem	= UINT_MAX,
 	},
 	[RXE_TYPE_PD] = {
-		.name		= "rxe-pd",
+		.name		= "pd",
 		.size		= sizeof(struct rxe_pd),
-		.elem_offset	= offsetof(struct rxe_pd, pelem),
-		.flags		= RXE_POOL_NO_ALLOC,
+		.elem_offset	= offsetof(struct rxe_pd, elem),
+		.min_index	= 1,
+		.max_index	= UINT_MAX,
+		.max_elem	= UINT_MAX,
 	},
 	[RXE_TYPE_AH] = {
-		.name		= "rxe-ah",
+		.name		= "ah",
 		.size		= sizeof(struct rxe_ah),
-		.elem_offset	= offsetof(struct rxe_ah, pelem),
-		.flags		= RXE_POOL_INDEX | RXE_POOL_NO_ALLOC,
+		.elem_offset	= offsetof(struct rxe_ah, elem),
 		.min_index	= RXE_MIN_AH_INDEX,
 		.max_index	= RXE_MAX_AH_INDEX,
+		.max_elem	= RXE_MAX_AH_INDEX - RXE_MIN_AH_INDEX + 1,
 	},
 	[RXE_TYPE_SRQ] = {
-		.name		= "rxe-srq",
+		.name		= "srq",
 		.size		= sizeof(struct rxe_srq),
-		.elem_offset	= offsetof(struct rxe_srq, pelem),
-		.flags		= RXE_POOL_INDEX | RXE_POOL_NO_ALLOC,
+		.elem_offset	= offsetof(struct rxe_srq, elem),
+		.cleanup	= rxe_srq_cleanup,
 		.min_index	= RXE_MIN_SRQ_INDEX,
 		.max_index	= RXE_MAX_SRQ_INDEX,
+		.max_elem	= RXE_MAX_SRQ_INDEX - RXE_MIN_SRQ_INDEX + 1,
 	},
 	[RXE_TYPE_QP] = {
-		.name		= "rxe-qp",
+		.name		= "qp",
 		.size		= sizeof(struct rxe_qp),
-		.elem_offset	= offsetof(struct rxe_qp, pelem),
+		.elem_offset	= offsetof(struct rxe_qp, elem),
 		.cleanup	= rxe_qp_cleanup,
-		.flags		= RXE_POOL_INDEX | RXE_POOL_NO_ALLOC,
 		.min_index	= RXE_MIN_QP_INDEX,
 		.max_index	= RXE_MAX_QP_INDEX,
+		.max_elem	= RXE_MAX_QP_INDEX - RXE_MIN_QP_INDEX + 1,
 	},
 	[RXE_TYPE_CQ] = {
-		.name		= "rxe-cq",
+		.name		= "cq",
 		.size		= sizeof(struct rxe_cq),
-		.elem_offset	= offsetof(struct rxe_cq, pelem),
-		.flags          = RXE_POOL_NO_ALLOC,
+		.elem_offset	= offsetof(struct rxe_cq, elem),
 		.cleanup	= rxe_cq_cleanup,
+		.min_index	= 1,
+		.max_index	= UINT_MAX,
+		.max_elem	= UINT_MAX,
 	},
 	[RXE_TYPE_MR] = {
-		.name		= "rxe-mr",
+		.name		= "mr",
 		.size		= sizeof(struct rxe_mr),
-		.elem_offset	= offsetof(struct rxe_mr, pelem),
+		.elem_offset	= offsetof(struct rxe_mr, elem),
 		.cleanup	= rxe_mr_cleanup,
-		.flags		= RXE_POOL_INDEX,
 		.min_index	= RXE_MIN_MR_INDEX,
 		.max_index	= RXE_MAX_MR_INDEX,
+		.max_elem	= RXE_MAX_MR_INDEX - RXE_MIN_MR_INDEX + 1,
 	},
 	[RXE_TYPE_MW] = {
-		.name		= "rxe-mw",
+		.name		= "mw",
 		.size		= sizeof(struct rxe_mw),
-		.elem_offset	= offsetof(struct rxe_mw, pelem),
+		.elem_offset	= offsetof(struct rxe_mw, elem),
 		.cleanup	= rxe_mw_cleanup,
-		.flags		= RXE_POOL_INDEX | RXE_POOL_NO_ALLOC,
 		.min_index	= RXE_MIN_MW_INDEX,
 		.max_index	= RXE_MAX_MW_INDEX,
-	},
-	[RXE_TYPE_MC_GRP] = {
-		.name		= "rxe-mc_grp",
-		.size		= sizeof(struct rxe_mc_grp),
-		.elem_offset	= offsetof(struct rxe_mc_grp, pelem),
-		.cleanup	= rxe_mc_cleanup,
-		.flags		= RXE_POOL_KEY,
-		.key_offset	= offsetof(struct rxe_mc_grp, mgid),
-		.key_size	= sizeof(union ib_gid),
-	},
-	[RXE_TYPE_MC_ELEM] = {
-		.name		= "rxe-mc_elem",
-		.size		= sizeof(struct rxe_mc_elem),
-		.elem_offset	= offsetof(struct rxe_mc_elem, pelem),
+		.max_elem	= RXE_MAX_MW_INDEX - RXE_MIN_MW_INDEX + 1,
 	},
 };
 
-static inline const char *pool_name(struct rxe_pool *pool)
-{
-	return rxe_type_info[pool->type].name;
-}
-
-static int rxe_pool_init_index(struct rxe_pool *pool, u32 max, u32 min)
-{
-	int err = 0;
-
-	if ((max - min + 1) < pool->max_elem) {
-		pr_warn("not enough indices for max_elem\n");
-		err = -EINVAL;
-		goto out;
-	}
-
-	pool->index.max_index = max;
-	pool->index.min_index = min;
-
-	pool->index.table = bitmap_zalloc(max - min + 1, GFP_KERNEL);
-	if (!pool->index.table) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-out:
-	return err;
-}
-
-int rxe_pool_init(
-	struct rxe_dev		*rxe,
-	struct rxe_pool		*pool,
-	enum rxe_elem_type	type,
-	unsigned int		max_elem)
+void rxe_pool_init(struct rxe_dev *rxe, struct rxe_pool *pool,
+		   enum rxe_elem_type type)
 {
-	int			err = 0;
-	size_t			size = rxe_type_info[type].size;
+	const struct rxe_type_info *info = &rxe_type_info[type];
 
 	memset(pool, 0, sizeof(*pool));
 
 	pool->rxe		= rxe;
+	pool->name		= info->name;
 	pool->type		= type;
-	pool->max_elem		= max_elem;
-	pool->elem_size		= ALIGN(size, RXE_POOL_ALIGN);
-	pool->flags		= rxe_type_info[type].flags;
-	pool->index.tree	= RB_ROOT;
-	pool->key.tree		= RB_ROOT;
-	pool->cleanup		= rxe_type_info[type].cleanup;
+	pool->max_elem		= info->max_elem;
+	pool->elem_size		= ALIGN(info->size, RXE_POOL_ALIGN);
+	pool->elem_offset	= info->elem_offset;
+	pool->cleanup		= info->cleanup;
 
 	atomic_set(&pool->num_elem, 0);
 
-	rwlock_init(&pool->pool_lock);
-
-	if (rxe_type_info[type].flags & RXE_POOL_INDEX) {
-		err = rxe_pool_init_index(pool,
-					  rxe_type_info[type].max_index,
-					  rxe_type_info[type].min_index);
-		if (err)
-			goto out;
-	}
-
-	if (rxe_type_info[type].flags & RXE_POOL_KEY) {
-		pool->key.key_offset = rxe_type_info[type].key_offset;
-		pool->key.key_size = rxe_type_info[type].key_size;
-	}
-
-out:
-	return err;
+	xa_init_flags(&pool->xa, XA_FLAGS_ALLOC);
+	pool->limit.min = info->min_index;
+	pool->limit.max = info->max_index;
 }
 
 void rxe_pool_cleanup(struct rxe_pool *pool)
 {
-	if (atomic_read(&pool->num_elem) > 0)
-		pr_warn("%s pool destroyed with unfree'd elem\n",
-			pool_name(pool));
-
-	bitmap_free(pool->index.table);
-}
-
-static u32 alloc_index(struct rxe_pool *pool)
-{
-	u32 index;
-	u32 range = pool->index.max_index - pool->index.min_index + 1;
-
-	index = find_next_zero_bit(pool->index.table, range, pool->index.last);
-	if (index >= range)
-		index = find_first_zero_bit(pool->index.table, range);
-
-	WARN_ON_ONCE(index >= range);
-	set_bit(index, pool->index.table);
-	pool->index.last = index;
-	return index + pool->index.min_index;
-}
-
-static int rxe_insert_index(struct rxe_pool *pool, struct rxe_pool_entry *new)
-{
-	struct rb_node **link = &pool->index.tree.rb_node;
-	struct rb_node *parent = NULL;
-	struct rxe_pool_entry *elem;
-
-	while (*link) {
-		parent = *link;
-		elem = rb_entry(parent, struct rxe_pool_entry, index_node);
-
-		if (elem->index == new->index) {
-			pr_warn("element already exists!\n");
-			return -EINVAL;
-		}
-
-		if (elem->index > new->index)
-			link = &(*link)->rb_left;
-		else
-			link = &(*link)->rb_right;
-	}
-
-	rb_link_node(&new->index_node, parent, link);
-	rb_insert_color(&new->index_node, &pool->index.tree);
-
-	return 0;
-}
-
-static int rxe_insert_key(struct rxe_pool *pool, struct rxe_pool_entry *new)
-{
-	struct rb_node **link = &pool->key.tree.rb_node;
-	struct rb_node *parent = NULL;
-	struct rxe_pool_entry *elem;
-	int cmp;
-
-	while (*link) {
-		parent = *link;
-		elem = rb_entry(parent, struct rxe_pool_entry, key_node);
-
-		cmp = memcmp((u8 *)elem + pool->key.key_offset,
-			     (u8 *)new + pool->key.key_offset, pool->key.key_size);
-
-		if (cmp == 0) {
-			pr_warn("key already exists!\n");
-			return -EINVAL;
-		}
-
-		if (cmp > 0)
-			link = &(*link)->rb_left;
-		else
-			link = &(*link)->rb_right;
-	}
-
-	rb_link_node(&new->key_node, parent, link);
-	rb_insert_color(&new->key_node, &pool->key.tree);
-
-	return 0;
-}
-
-int __rxe_add_key_locked(struct rxe_pool_entry *elem, void *key)
-{
-	struct rxe_pool *pool = elem->pool;
-	int err;
-
-	memcpy((u8 *)elem + pool->key.key_offset, key, pool->key.key_size);
-	err = rxe_insert_key(pool, elem);
-
-	return err;
-}
-
-int __rxe_add_key(struct rxe_pool_entry *elem, void *key)
-{
-	struct rxe_pool *pool = elem->pool;
-	unsigned long flags;
-	int err;
-
-	write_lock_irqsave(&pool->pool_lock, flags);
-	err = __rxe_add_key_locked(elem, key);
-	write_unlock_irqrestore(&pool->pool_lock, flags);
-
-	return err;
-}
-
-void __rxe_drop_key_locked(struct rxe_pool_entry *elem)
-{
-	struct rxe_pool *pool = elem->pool;
-
-	rb_erase(&elem->key_node, &pool->key.tree);
-}
-
-void __rxe_drop_key(struct rxe_pool_entry *elem)
-{
-	struct rxe_pool *pool = elem->pool;
-	unsigned long flags;
-
-	write_lock_irqsave(&pool->pool_lock, flags);
-	__rxe_drop_key_locked(elem);
-	write_unlock_irqrestore(&pool->pool_lock, flags);
+	WARN_ON(!xa_empty(&pool->xa));
 }
 
-int __rxe_add_index_locked(struct rxe_pool_entry *elem)
-{
-	struct rxe_pool *pool = elem->pool;
-	int err;
-
-	elem->index = alloc_index(pool);
-	err = rxe_insert_index(pool, elem);
-
-	return err;
-}
-
-int __rxe_add_index(struct rxe_pool_entry *elem)
+void *rxe_alloc(struct rxe_pool *pool)
 {
-	struct rxe_pool *pool = elem->pool;
-	unsigned long flags;
+	struct rxe_pool_elem *elem;
+	void *obj;
 	int err;
 
-	write_lock_irqsave(&pool->pool_lock, flags);
-	err = __rxe_add_index_locked(elem);
-	write_unlock_irqrestore(&pool->pool_lock, flags);
-
-	return err;
-}
-
-void __rxe_drop_index_locked(struct rxe_pool_entry *elem)
-{
-	struct rxe_pool *pool = elem->pool;
-
-	clear_bit(elem->index - pool->index.min_index, pool->index.table);
-	rb_erase(&elem->index_node, &pool->index.tree);
-}
-
-void __rxe_drop_index(struct rxe_pool_entry *elem)
-{
-	struct rxe_pool *pool = elem->pool;
-	unsigned long flags;
-
-	write_lock_irqsave(&pool->pool_lock, flags);
-	__rxe_drop_index_locked(elem);
-	write_unlock_irqrestore(&pool->pool_lock, flags);
-}
-
-void *rxe_alloc_locked(struct rxe_pool *pool)
-{
-	const struct rxe_type_info *info = &rxe_type_info[pool->type];
-	struct rxe_pool_entry *elem;
-	u8 *obj;
+	if (WARN_ON(!(pool->type == RXE_TYPE_MR)))
+		return NULL;
 
 	if (atomic_inc_return(&pool->num_elem) > pool->max_elem)
-		goto out_cnt;
+		goto err_cnt;
 
-	obj = kzalloc(info->size, GFP_ATOMIC);
+	obj = kzalloc(pool->elem_size, GFP_KERNEL);
 	if (!obj)
-		goto out_cnt;
+		goto err_cnt;
 
-	elem = (struct rxe_pool_entry *)(obj + info->elem_offset);
+	elem = (struct rxe_pool_elem *)((u8 *)obj + pool->elem_offset);
 
 	elem->pool = pool;
+	elem->obj = obj;
 	kref_init(&elem->ref_cnt);
+	init_completion(&elem->complete);
+
+	/* allocate index in array but leave pointer as NULL so it
+	 * can't be looked up until rxe_finalize() is called
+	 */
+	err = xa_alloc_cyclic(&pool->xa, &elem->index, NULL, pool->limit,
+			      &pool->next, GFP_KERNEL);
+	if (err < 0)
+		goto err_free;
 
 	return obj;
 
-out_cnt:
+err_free:
+	kfree(obj);
+err_cnt:
 	atomic_dec(&pool->num_elem);
 	return NULL;
 }
 
-void *rxe_alloc(struct rxe_pool *pool)
+int __rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_elem *elem,
+				bool sleepable)
 {
-	const struct rxe_type_info *info = &rxe_type_info[pool->type];
-	struct rxe_pool_entry *elem;
-	u8 *obj;
-
-	if (atomic_inc_return(&pool->num_elem) > pool->max_elem)
-		goto out_cnt;
+	int err;
+	gfp_t gfp_flags;
 
-	obj = kzalloc(info->size, GFP_KERNEL);
-	if (!obj)
-		goto out_cnt;
+	if (WARN_ON(pool->type == RXE_TYPE_MR))
+		return -EINVAL;
 
-	elem = (struct rxe_pool_entry *)(obj + info->elem_offset);
+	if (atomic_inc_return(&pool->num_elem) > pool->max_elem)
+		goto err_cnt;
 
 	elem->pool = pool;
+	elem->obj = (u8 *)elem - pool->elem_offset;
 	kref_init(&elem->ref_cnt);
+	init_completion(&elem->complete);
 
-	return obj;
-
-out_cnt:
-	atomic_dec(&pool->num_elem);
-	return NULL;
-}
-
-int __rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_entry *elem)
-{
-	if (atomic_inc_return(&pool->num_elem) > pool->max_elem)
-		goto out_cnt;
+	/* AH objects are unique in that the create_ah verb
+	 * can be called in atomic context. If the create_ah
+	 * call is not sleepable use GFP_ATOMIC.
+	 */
+	gfp_flags = sleepable ? GFP_KERNEL : GFP_ATOMIC;
 
-	elem->pool = pool;
-	kref_init(&elem->ref_cnt);
+	if (sleepable)
+		might_sleep();
+	err = xa_alloc_cyclic(&pool->xa, &elem->index, NULL, pool->limit,
+			      &pool->next, gfp_flags);
+	if (err < 0)
+		goto err_cnt;
 
 	return 0;
 
-out_cnt:
+err_cnt:
 	atomic_dec(&pool->num_elem);
 	return -EINVAL;
 }
 
-void rxe_elem_release(struct kref *kref)
+void *rxe_pool_get_index(struct rxe_pool *pool, u32 index)
 {
-	struct rxe_pool_entry *elem =
-		container_of(kref, struct rxe_pool_entry, ref_cnt);
-	struct rxe_pool *pool = elem->pool;
-	const struct rxe_type_info *info = &rxe_type_info[pool->type];
-	u8 *obj;
+	struct rxe_pool_elem *elem;
+	struct xarray *xa = &pool->xa;
+	void *obj;
+
+	rcu_read_lock();
+	elem = xa_load(xa, index);
+	if (elem && kref_get_unless_zero(&elem->ref_cnt))
+		obj = elem->obj;
+	else
+		obj = NULL;
+	rcu_read_unlock();
 
-	if (pool->cleanup)
-		pool->cleanup(elem);
+	return obj;
+}
 
-	if (!(pool->flags & RXE_POOL_NO_ALLOC)) {
-		obj = (u8 *)elem - info->elem_offset;
-		kfree(obj);
-	}
+static void rxe_elem_release(struct kref *kref)
+{
+	struct rxe_pool_elem *elem = container_of(kref, typeof(*elem), ref_cnt);
 
-	atomic_dec(&pool->num_elem);
+	complete(&elem->complete);
 }
 
-void *rxe_pool_get_index_locked(struct rxe_pool *pool, u32 index)
+int __rxe_cleanup(struct rxe_pool_elem *elem, bool sleepable)
 {
-	const struct rxe_type_info *info = &rxe_type_info[pool->type];
-	struct rb_node *node;
-	struct rxe_pool_entry *elem;
-	u8 *obj;
-
-	node = pool->index.tree.rb_node;
-
-	while (node) {
-		elem = rb_entry(node, struct rxe_pool_entry, index_node);
-
-		if (elem->index > index)
-			node = node->rb_left;
-		else if (elem->index < index)
-			node = node->rb_right;
-		else
-			break;
-	}
-
-	if (node) {
-		kref_get(&elem->ref_cnt);
-		obj = (u8 *)elem - info->elem_offset;
+	struct rxe_pool *pool = elem->pool;
+	struct xarray *xa = &pool->xa;
+	static int timeout = RXE_POOL_TIMEOUT;
+	int ret, err = 0;
+	void *xa_ret;
+
+	if (sleepable)
+		might_sleep();
+
+	/* erase xarray entry to prevent looking up
+	 * the pool elem from its index
+	 */
+	xa_ret = xa_erase(xa, elem->index);
+	WARN_ON(xa_err(xa_ret));
+
+	/* if this is the last call to rxe_put complete the
+	 * object. It is safe to touch obj->elem after this since
+	 * it is freed below
+	 */
+	__rxe_put(elem);
+
+	/* wait until all references to the object have been
+	 * dropped before final object specific cleanup and
+	 * return to rdma-core
+	 */
+	if (sleepable) {
+		if (!completion_done(&elem->complete) && timeout) {
+			ret = wait_for_completion_timeout(&elem->complete,
+					timeout);
+
+			/* Shouldn't happen. There are still references to
+			 * the object but, rather than deadlock, free the
+			 * object or pass back to rdma-core.
+			 */
+			if (WARN_ON(!ret))
+				err = -EINVAL;
+		}
 	} else {
-		obj = NULL;
+		unsigned long until = jiffies + timeout;
+
+		/* AH objects are unique in that the destroy_ah verb
+		 * can be called in atomic context. This delay
+		 * replaces the wait_for_completion call above
+		 * when the destroy_ah call is not sleepable
+		 */
+		while (!completion_done(&elem->complete) &&
+				time_before(jiffies, until))
+			mdelay(1);
+
+		if (WARN_ON(!completion_done(&elem->complete)))
+			err = -EINVAL;
 	}
 
-	return obj;
-}
+	if (pool->cleanup)
+		pool->cleanup(elem);
 
-void *rxe_pool_get_index(struct rxe_pool *pool, u32 index)
-{
-	u8 *obj;
-	unsigned long flags;
+	if (pool->type == RXE_TYPE_MR)
+		kfree_rcu(elem->obj);
 
-	read_lock_irqsave(&pool->pool_lock, flags);
-	obj = rxe_pool_get_index_locked(pool, index);
-	read_unlock_irqrestore(&pool->pool_lock, flags);
+	atomic_dec(&pool->num_elem);
 
-	return obj;
+	return err;
 }
 
-void *rxe_pool_get_key_locked(struct rxe_pool *pool, void *key)
+int __rxe_get(struct rxe_pool_elem *elem)
 {
-	const struct rxe_type_info *info = &rxe_type_info[pool->type];
-	struct rb_node *node;
-	struct rxe_pool_entry *elem;
-	u8 *obj;
-	int cmp;
-
-	node = pool->key.tree.rb_node;
-
-	while (node) {
-		elem = rb_entry(node, struct rxe_pool_entry, key_node);
-
-		cmp = memcmp((u8 *)elem + pool->key.key_offset,
-			     key, pool->key.key_size);
-
-		if (cmp > 0)
-			node = node->rb_left;
-		else if (cmp < 0)
-			node = node->rb_right;
-		else
-			break;
-	}
-
-	if (node) {
-		kref_get(&elem->ref_cnt);
-		obj = (u8 *)elem - info->elem_offset;
-	} else {
-		obj = NULL;
-	}
-
-	return obj;
+	return kref_get_unless_zero(&elem->ref_cnt);
 }
 
-void *rxe_pool_get_key(struct rxe_pool *pool, void *key)
+int __rxe_put(struct rxe_pool_elem *elem)
 {
-	u8 *obj;
-	unsigned long flags;
+	return kref_put(&elem->ref_cnt, rxe_elem_release);
+}
 
-	read_lock_irqsave(&pool->pool_lock, flags);
-	obj = rxe_pool_get_key_locked(pool, key);
-	read_unlock_irqrestore(&pool->pool_lock, flags);
+void __rxe_finalize(struct rxe_pool_elem *elem)
+{
+	void *xa_ret;
 
-	return obj;
+	xa_ret = xa_store(&elem->pool->xa, elem->index, elem, GFP_KERNEL);
+	WARN_ON(xa_err(xa_ret));
 }