RDMA/mlx5: Change the cache structure to an RB-tree

Currently, the cache structure is a static linear array. Therefore, his
size is limited to the number of entries in it and is not expandable.  The
entries are dedicated to mkeys of size 2^x and no access_flags. Mkeys with
different properties are not cacheable.

In this patch, we change the cache structure to an RB-tree.  This will
allow to extend the cache to support more entries with different mkey
properties.

Link: https://lore.kernel.org/r/20230125222807.6921-4-michaelgur@nvidia.com
Signed-off-by: Michael Guralnik <michaelgur@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

3 files changed, 132 insertions, 47 deletions

diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 8d985f792367..eec16db2d536 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -741,6 +741,8 @@ struct mlx5_cache_ent {
 	u32			access_mode;
 	unsigned int		ndescs;
 
+	struct rb_node		node;
+
 	u8 disabled:1;
 	u8 fill_to_high_water:1;
 
@@ -770,8 +772,9 @@ struct mlx5r_async_create_mkey {
 
 struct mlx5_mkey_cache {
 	struct workqueue_struct *wq;
-	struct mlx5_cache_ent	ent[MAX_MKEY_CACHE_ENTRIES];
-	struct dentry		*root;
+	struct rb_root		rb_root;
+	struct mutex		rb_lock;
+	struct dentry		*fs_root;
 	unsigned long		last_add;
 };
 
@@ -1316,11 +1319,15 @@ void mlx5_ib_copy_pas(u64 *old, u64 *new, int step, int num);
 int mlx5_ib_get_cqe_size(struct ib_cq *ibcq);
 int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev);
 int mlx5_mkey_cache_cleanup(struct mlx5_ib_dev *dev);
+struct mlx5_cache_ent *mlx5r_cache_create_ent(struct mlx5_ib_dev *dev,
+					      int order);
 
 struct mlx5_ib_mr *mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev,
 				       struct mlx5_cache_ent *ent,
 				       int access_flags);
 
+struct mlx5_ib_mr *mlx5_mr_cache_alloc_order(struct mlx5_ib_dev *dev, u32 order,
+					     int access_flags);
 int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
 			    struct ib_mr_status *mr_status);
 struct ib_wq *mlx5_ib_create_wq(struct ib_pd *pd,
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 356c99d7ec9a..5cc618db277f 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -515,18 +515,22 @@ static const struct file_operations limit_fops = {
 
 static bool someone_adding(struct mlx5_mkey_cache *cache)
 {
-	unsigned int i;
-
-	for (i = 0; i < MAX_MKEY_CACHE_ENTRIES; i++) {
-		struct mlx5_cache_ent *ent = &cache->ent[i];
-		bool ret;
+	struct mlx5_cache_ent *ent;
+	struct rb_node *node;
+	bool ret;
 
+	mutex_lock(&cache->rb_lock);
+	for (node = rb_first(&cache->rb_root); node; node = rb_next(node)) {
+		ent = rb_entry(node, struct mlx5_cache_ent, node);
 		xa_lock_irq(&ent->mkeys);
 		ret = ent->stored < ent->limit;
 		xa_unlock_irq(&ent->mkeys);
-		if (ret)
+		if (ret) {
+			mutex_unlock(&cache->rb_lock);
 			return true;
+		}
 	}
+	mutex_unlock(&cache->rb_lock);
 	return false;
 }
 
@@ -637,6 +641,59 @@ static void delayed_cache_work_func(struct work_struct *work)
 	__cache_work_func(ent);
 }
 
+static int mlx5_cache_ent_insert(struct mlx5_mkey_cache *cache,
+				 struct mlx5_cache_ent *ent)
+{
+	struct rb_node **new = &cache->rb_root.rb_node, *parent = NULL;
+	struct mlx5_cache_ent *cur;
+
+	mutex_lock(&cache->rb_lock);
+	/* Figure out where to put new node */
+	while (*new) {
+		cur = rb_entry(*new, struct mlx5_cache_ent, node);
+		parent = *new;
+		if (ent->order < cur->order)
+			new = &((*new)->rb_left);
+		if (ent->order > cur->order)
+			new = &((*new)->rb_right);
+		if (ent->order == cur->order) {
+			mutex_unlock(&cache->rb_lock);
+			return -EEXIST;
+		}
+	}
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&ent->node, parent, new);
+	rb_insert_color(&ent->node, &cache->rb_root);
+
+	mutex_unlock(&cache->rb_lock);
+	return 0;
+}
+
+static struct mlx5_cache_ent *mkey_cache_ent_from_order(struct mlx5_ib_dev *dev,
+							unsigned int order)
+{
+	struct rb_node *node = dev->cache.rb_root.rb_node;
+	struct mlx5_cache_ent *cur, *smallest = NULL;
+
+	/*
+	 * Find the smallest ent with order >= requested_order.
+	 */
+	while (node) {
+		cur = rb_entry(node, struct mlx5_cache_ent, node);
+		if (cur->order > order) {
+			smallest = cur;
+			node = node->rb_left;
+		}
+		if (cur->order < order)
+			node = node->rb_right;
+		if (cur->order == order)
+			return cur;
+	}
+
+	return smallest;
+}
+
 struct mlx5_ib_mr *mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev,
 				       struct mlx5_cache_ent *ent,
 				       int access_flags)
@@ -677,10 +734,16 @@ struct mlx5_ib_mr *mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev,
 	return mr;
 }
 
-static void clean_keys(struct mlx5_ib_dev *dev, int c)
+struct mlx5_ib_mr *mlx5_mr_cache_alloc_order(struct mlx5_ib_dev *dev,
+					     u32 order, int access_flags)
+{
+	struct mlx5_cache_ent *ent = mkey_cache_ent_from_order(dev, order);
+
+	return mlx5_mr_cache_alloc(dev, ent, access_flags);
+}
+
+static void clean_keys(struct mlx5_ib_dev *dev, struct mlx5_cache_ent *ent)
 {
-	struct mlx5_mkey_cache *cache = &dev->cache;
-	struct mlx5_cache_ent *ent = &cache->ent[c];
 	u32 mkey;
 
 	cancel_delayed_work(&ent->dwork);
@@ -699,8 +762,8 @@ static void mlx5_mkey_cache_debugfs_cleanup(struct mlx5_ib_dev *dev)
 	if (!mlx5_debugfs_root || dev->is_rep)
 		return;
 
-	debugfs_remove_recursive(dev->cache.root);
-	dev->cache.root = NULL;
+	debugfs_remove_recursive(dev->cache.fs_root);
+	dev->cache.fs_root = NULL;
 }
 
 static void mlx5_mkey_cache_debugfs_init(struct mlx5_ib_dev *dev)
@@ -713,12 +776,13 @@ static void mlx5_mkey_cache_debugfs_init(struct mlx5_ib_dev *dev)
 	if (!mlx5_debugfs_root || dev->is_rep)
 		return;
 
-	cache->root = debugfs_create_dir("mr_cache", mlx5_debugfs_get_dev_root(dev->mdev));
+	dir = mlx5_debugfs_get_dev_root(dev->mdev);
+	cache->fs_root = debugfs_create_dir("mr_cache", dir);
 
 	for (i = 0; i < MAX_MKEY_CACHE_ENTRIES; i++) {
-		ent = &cache->ent[i];
+		ent = mkey_cache_ent_from_order(dev, i);
 		sprintf(ent->name, "%d", ent->order);
-		dir = debugfs_create_dir(ent->name, cache->root);
+		dir = debugfs_create_dir(ent->name, cache->fs_root);
 		debugfs_create_file("size", 0600, dir, ent, &size_fops);
 		debugfs_create_file("limit", 0600, dir, ent, &limit_fops);
 		debugfs_create_ulong("cur", 0400, dir, &ent->stored);
@@ -733,6 +797,30 @@ static void delay_time_func(struct timer_list *t)
 	WRITE_ONCE(dev->fill_delay, 0);
 }
 
+struct mlx5_cache_ent *mlx5r_cache_create_ent(struct mlx5_ib_dev *dev,
+					      int order)
+{
+	struct mlx5_cache_ent *ent;
+	int ret;
+
+	ent = kzalloc(sizeof(*ent), GFP_KERNEL);
+	if (!ent)
+		return ERR_PTR(-ENOMEM);
+
+	xa_init_flags(&ent->mkeys, XA_FLAGS_LOCK_IRQ);
+	ent->order = order;
+	ent->dev = dev;
+
+	INIT_DELAYED_WORK(&ent->dwork, delayed_cache_work_func);
+
+	ret = mlx5_cache_ent_insert(&dev->cache, ent);
+	if (ret) {
+		kfree(ent);
+		return ERR_PTR(ret);
+	}
+	return ent;
+}
+
 int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_mkey_cache *cache = &dev->cache;
@@ -740,6 +828,8 @@ int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev)
 	int i;
 
 	mutex_init(&dev->slow_path_mutex);
+	mutex_init(&dev->cache.rb_lock);
+	dev->cache.rb_root = RB_ROOT;
 	cache->wq = alloc_ordered_workqueue("mkey_cache", WQ_MEM_RECLAIM);
 	if (!cache->wq) {
 		mlx5_ib_warn(dev, "failed to create work queue\n");
@@ -749,13 +839,7 @@ int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev)
 	mlx5_cmd_init_async_ctx(dev->mdev, &dev->async_ctx);
 	timer_setup(&dev->delay_timer, delay_time_func, 0);
 	for (i = 0; i < MAX_MKEY_CACHE_ENTRIES; i++) {
-		ent = &cache->ent[i];
-		xa_init_flags(&ent->mkeys, XA_FLAGS_LOCK_IRQ);
-		ent->order = i + 2;
-		ent->dev = dev;
-		ent->limit = 0;
-
-		INIT_DELAYED_WORK(&ent->dwork, delayed_cache_work_func);
+		ent = mlx5r_cache_create_ent(dev, i);
 
 		if (i > MKEY_CACHE_LAST_STD_ENTRY) {
 			mlx5_odp_init_mkey_cache_entry(ent);
@@ -785,14 +869,16 @@ int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev)
 
 int mlx5_mkey_cache_cleanup(struct mlx5_ib_dev *dev)
 {
-	unsigned int i;
+	struct rb_root *root = &dev->cache.rb_root;
+	struct mlx5_cache_ent *ent;
+	struct rb_node *node;
 
 	if (!dev->cache.wq)
 		return 0;
 
-	for (i = 0; i < MAX_MKEY_CACHE_ENTRIES; i++) {
-		struct mlx5_cache_ent *ent = &dev->cache.ent[i];
-
+	mutex_lock(&dev->cache.rb_lock);
+	for (node = rb_first(root); node; node = rb_next(node)) {
+		ent = rb_entry(node, struct mlx5_cache_ent, node);
 		xa_lock_irq(&ent->mkeys);
 		ent->disabled = true;
 		xa_unlock_irq(&ent->mkeys);
@@ -802,8 +888,15 @@ int mlx5_mkey_cache_cleanup(struct mlx5_ib_dev *dev)
 	mlx5_mkey_cache_debugfs_cleanup(dev);
 	mlx5_cmd_cleanup_async_ctx(&dev->async_ctx);
 
-	for (i = 0; i < MAX_MKEY_CACHE_ENTRIES; i++)
-		clean_keys(dev, i);
+	node = rb_first(root);
+	while (node) {
+		ent = rb_entry(node, struct mlx5_cache_ent, node);
+		node = rb_next(node);
+		clean_keys(dev, ent);
+		rb_erase(&ent->node, root);
+		kfree(ent);
+	}
+	mutex_unlock(&dev->cache.rb_lock);
 
 	destroy_workqueue(dev->cache.wq);
 	del_timer_sync(&dev->delay_timer);
@@ -876,19 +969,6 @@ static int mkey_cache_max_order(struct mlx5_ib_dev *dev)
 	return MLX5_MAX_UMR_SHIFT;
 }
 
-static struct mlx5_cache_ent *mkey_cache_ent_from_order(struct mlx5_ib_dev *dev,
-							unsigned int order)
-{
-	struct mlx5_mkey_cache *cache = &dev->cache;
-
-	if (order < cache->ent[0].order)
-		return &cache->ent[0];
-	order = order - cache->ent[0].order;
-	if (order > MKEY_CACHE_LAST_STD_ENTRY)
-		return NULL;
-	return &cache->ent[order];
-}
-
 static void set_mr_fields(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr,
 			  u64 length, int access_flags, u64 iova)
 {
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 72044f8ec883..71c3c611e10a 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -419,8 +419,7 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr,
 		return ERR_CAST(odp);
 
 	BUILD_BUG_ON(order > MKEY_CACHE_LAST_STD_ENTRY);
-	mr = mlx5_mr_cache_alloc(dev, &dev->cache.ent[order],
-				 imr->access_flags);
+	mr = mlx5_mr_cache_alloc_order(dev, order, imr->access_flags);
 	if (IS_ERR(mr)) {
 		ib_umem_odp_release(odp);
 		return mr;
@@ -494,9 +493,8 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd,
 	if (IS_ERR(umem_odp))
 		return ERR_CAST(umem_odp);
 
-	imr = mlx5_mr_cache_alloc(dev,
-				  &dev->cache.ent[MLX5_IMR_KSM_CACHE_ENTRY],
-				  access_flags);
+	imr = mlx5_mr_cache_alloc_order(dev, MLX5_IMR_KSM_CACHE_ENTRY,
+					access_flags);
 	if (IS_ERR(imr)) {
 		ib_umem_odp_release(umem_odp);
 		return imr;