1 files changed, 99 insertions, 34 deletions

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 65877967f414..17fb69c0e0dc 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -10,6 +10,7 @@
 #include <linux/random.h>
 #include <uapi/linux/btf.h>
 #include <linux/rcupdate_trace.h>
+#include <linux/btf_ids.h>
 #include "percpu_freelist.h"
 #include "bpf_lru_list.h"
 #include "map_in_map.h"
@@ -139,7 +140,7 @@ static inline bool htab_use_raw_lock(const struct bpf_htab *htab)
 
 static void htab_init_buckets(struct bpf_htab *htab)
 {
-	unsigned i;
+	unsigned int i;
 
 	for (i = 0; i < htab->n_buckets; i++) {
 		INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
@@ -238,7 +239,7 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab)
 	u32 num_entries = htab->map.max_entries;
 	int i;
 
-	if (likely(!map_value_has_timer(&htab->map)))
+	if (!map_value_has_timer(&htab->map))
 		return;
 	if (htab_has_extra_elems(htab))
 		num_entries += num_possible_cpus();
@@ -254,6 +255,25 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab)
 	}
 }
 
+static void htab_free_prealloced_kptrs(struct bpf_htab *htab)
+{
+	u32 num_entries = htab->map.max_entries;
+	int i;
+
+	if (!map_value_has_kptrs(&htab->map))
+		return;
+	if (htab_has_extra_elems(htab))
+		num_entries += num_possible_cpus();
+
+	for (i = 0; i < num_entries; i++) {
+		struct htab_elem *elem;
+
+		elem = get_htab_elem(htab, i);
+		bpf_map_free_kptrs(&htab->map, elem->key + round_up(htab->map.key_size, 8));
+		cond_resched();
+	}
+}
+
 static void htab_free_elems(struct bpf_htab *htab)
 {
 	int i;
@@ -725,12 +745,15 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map,
 	return insn - insn_buf;
 }
 
-static void check_and_free_timer(struct bpf_htab *htab, struct htab_elem *elem)
+static void check_and_free_fields(struct bpf_htab *htab,
+				  struct htab_elem *elem)
 {
-	if (unlikely(map_value_has_timer(&htab->map)))
-		bpf_timer_cancel_and_free(elem->key +
-					  round_up(htab->map.key_size, 8) +
-					  htab->map.timer_off);
+	void *map_value = elem->key + round_up(htab->map.key_size, 8);
+
+	if (map_value_has_timer(&htab->map))
+		bpf_timer_cancel_and_free(map_value + htab->map.timer_off);
+	if (map_value_has_kptrs(&htab->map))
+		bpf_map_free_kptrs(&htab->map, map_value);
 }
 
 /* It is called from the bpf_lru_list when the LRU needs to delete
@@ -738,7 +761,7 @@ static void check_and_free_timer(struct bpf_htab *htab, struct htab_elem *elem)
  */
 static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 {
-	struct bpf_htab *htab = (struct bpf_htab *)arg;
+	struct bpf_htab *htab = arg;
 	struct htab_elem *l = NULL, *tgt_l;
 	struct hlist_nulls_head *head;
 	struct hlist_nulls_node *n;
@@ -757,7 +780,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
 	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
 		if (l == tgt_l) {
 			hlist_nulls_del_rcu(&l->hash_node);
-			check_and_free_timer(htab, l);
+			check_and_free_fields(htab, l);
 			break;
 		}
 
@@ -829,7 +852,7 @@ static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l)
 {
 	if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
 		free_percpu(htab_elem_get_ptr(l, htab->map.key_size));
-	check_and_free_timer(htab, l);
+	check_and_free_fields(htab, l);
 	kfree(l);
 }
 
@@ -857,7 +880,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 	htab_put_fd_value(htab, l);
 
 	if (htab_is_prealloc(htab)) {
-		check_and_free_timer(htab, l);
+		check_and_free_fields(htab, l);
 		__pcpu_freelist_push(&htab->freelist, &l->fnode);
 	} else {
 		atomic_dec(&htab->count);
@@ -1104,7 +1127,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		if (!htab_is_prealloc(htab))
 			free_htab_elem(htab, l_old);
 		else
-			check_and_free_timer(htab, l_old);
+			check_and_free_fields(htab, l_old);
 	}
 	ret = 0;
 err:
@@ -1114,7 +1137,7 @@ err:
 
 static void htab_lru_push_free(struct bpf_htab *htab, struct htab_elem *elem)
 {
-	check_and_free_timer(htab, elem);
+	check_and_free_fields(htab, elem);
 	bpf_lru_push_free(&htab->lru, &elem->lru_node);
 }
 
@@ -1419,8 +1442,14 @@ static void htab_free_malloced_timers(struct bpf_htab *htab)
 		struct hlist_nulls_node *n;
 		struct htab_elem *l;
 
-		hlist_nulls_for_each_entry(l, n, head, hash_node)
-			check_and_free_timer(htab, l);
+		hlist_nulls_for_each_entry(l, n, head, hash_node) {
+			/* We don't reset or free kptr on uref dropping to zero,
+			 * hence just free timer.
+			 */
+			bpf_timer_cancel_and_free(l->key +
+						  round_up(htab->map.key_size, 8) +
+						  htab->map.timer_off);
+		}
 		cond_resched_rcu();
 	}
 	rcu_read_unlock();
@@ -1430,7 +1459,8 @@ static void htab_map_free_timers(struct bpf_map *map)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
 
-	if (likely(!map_value_has_timer(&htab->map)))
+	/* We don't reset or free kptr on uref dropping to zero. */
+	if (!map_value_has_timer(&htab->map))
 		return;
 	if (!htab_is_prealloc(htab))
 		htab_free_malloced_timers(htab);
@@ -1453,11 +1483,14 @@ static void htab_map_free(struct bpf_map *map)
 	 * not have executed. Wait for them.
 	 */
 	rcu_barrier();
-	if (!htab_is_prealloc(htab))
+	if (!htab_is_prealloc(htab)) {
 		delete_all_elements(htab);
-	else
+	} else {
+		htab_free_prealloced_kptrs(htab);
 		prealloc_destroy(htab);
+	}
 
+	bpf_map_free_kptr_off_tab(map);
 	free_percpu(htab->extra_elems);
 	bpf_map_area_free(htab->buckets);
 	for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++)
@@ -1594,7 +1627,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 	void __user *uvalues = u64_to_user_ptr(attr->batch.values);
 	void __user *ukeys = u64_to_user_ptr(attr->batch.keys);
 	void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch);
-	u32 batch, max_count, size, bucket_size;
+	u32 batch, max_count, size, bucket_size, map_id;
 	struct htab_elem *node_to_free = NULL;
 	u64 elem_map_flags, map_flags;
 	struct hlist_nulls_head *head;
@@ -1719,6 +1752,14 @@ again_nocopy:
 			}
 		} else {
 			value = l->key + roundup_key_size;
+			if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+				struct bpf_map **inner_map = value;
+
+				 /* Actual value is the id of the inner map */
+				map_id = map->ops->map_fd_sys_lookup_elem(*inner_map);
+				value = &map_id;
+			}
+
 			if (elem_map_flags & BPF_F_LOCK)
 				copy_map_value_locked(map, dst_val, value,
 						      true);
@@ -2105,7 +2146,7 @@ out:
 	return num_elems;
 }
 
-static int htab_map_btf_id;
+BTF_ID_LIST_SINGLE(htab_map_btf_ids, struct, bpf_htab)
 const struct bpf_map_ops htab_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = htab_map_alloc_check,
@@ -2122,12 +2163,10 @@ const struct bpf_map_ops htab_map_ops = {
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
 	BATCH_OPS(htab),
-	.map_btf_name = "bpf_htab",
-	.map_btf_id = &htab_map_btf_id,
+	.map_btf_id = &htab_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
 };
 
-static int htab_lru_map_btf_id;
 const struct bpf_map_ops htab_lru_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = htab_map_alloc_check,
@@ -2145,8 +2184,7 @@ const struct bpf_map_ops htab_lru_map_ops = {
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
 	BATCH_OPS(htab_lru),
-	.map_btf_name = "bpf_htab",
-	.map_btf_id = &htab_lru_map_btf_id,
+	.map_btf_id = &htab_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
 };
 
@@ -2161,6 +2199,20 @@ static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key)
 		return NULL;
 }
 
+static void *htab_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu)
+{
+	struct htab_elem *l;
+
+	if (cpu >= nr_cpu_ids)
+		return NULL;
+
+	l = __htab_map_lookup_elem(map, key);
+	if (l)
+		return per_cpu_ptr(htab_elem_get_ptr(l, map->key_size), cpu);
+	else
+		return NULL;
+}
+
 static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	struct htab_elem *l = __htab_map_lookup_elem(map, key);
@@ -2173,6 +2225,22 @@ static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key)
 	return NULL;
 }
 
+static void *htab_lru_percpu_map_lookup_percpu_elem(struct bpf_map *map, void *key, u32 cpu)
+{
+	struct htab_elem *l;
+
+	if (cpu >= nr_cpu_ids)
+		return NULL;
+
+	l = __htab_map_lookup_elem(map, key);
+	if (l) {
+		bpf_lru_node_set_ref(&l->lru_node);
+		return per_cpu_ptr(htab_elem_get_ptr(l, map->key_size), cpu);
+	}
+
+	return NULL;
+}
+
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
 {
 	struct htab_elem *l;
@@ -2252,7 +2320,6 @@ static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key,
 	rcu_read_unlock();
 }
 
-static int htab_percpu_map_btf_id;
 const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = htab_map_alloc_check,
@@ -2263,16 +2330,15 @@ const struct bpf_map_ops htab_percpu_map_ops = {
 	.map_lookup_and_delete_elem = htab_percpu_map_lookup_and_delete_elem,
 	.map_update_elem = htab_percpu_map_update_elem,
 	.map_delete_elem = htab_map_delete_elem,
+	.map_lookup_percpu_elem = htab_percpu_map_lookup_percpu_elem,
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
 	BATCH_OPS(htab_percpu),
-	.map_btf_name = "bpf_htab",
-	.map_btf_id = &htab_percpu_map_btf_id,
+	.map_btf_id = &htab_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
 };
 
-static int htab_lru_percpu_map_btf_id;
 const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc_check = htab_map_alloc_check,
@@ -2283,12 +2349,12 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = {
 	.map_lookup_and_delete_elem = htab_lru_percpu_map_lookup_and_delete_elem,
 	.map_update_elem = htab_lru_percpu_map_update_elem,
 	.map_delete_elem = htab_lru_map_delete_elem,
+	.map_lookup_percpu_elem = htab_lru_percpu_map_lookup_percpu_elem,
 	.map_seq_show_elem = htab_percpu_map_seq_show_elem,
 	.map_set_for_each_callback_args = map_set_for_each_callback_args,
 	.map_for_each_callback = bpf_for_each_hash_elem,
 	BATCH_OPS(htab_lru_percpu),
-	.map_btf_name = "bpf_htab",
-	.map_btf_id = &htab_lru_percpu_map_btf_id,
+	.map_btf_id = &htab_map_btf_ids[0],
 	.iter_seq_info = &iter_seq_info,
 };
 
@@ -2412,7 +2478,6 @@ static void htab_of_map_free(struct bpf_map *map)
 	fd_htab_map_free(map);
 }
 
-static int htab_of_maps_map_btf_id;
 const struct bpf_map_ops htab_of_maps_map_ops = {
 	.map_alloc_check = fd_htab_map_alloc_check,
 	.map_alloc = htab_of_map_alloc,
@@ -2425,6 +2490,6 @@ const struct bpf_map_ops htab_of_maps_map_ops = {
 	.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
 	.map_gen_lookup = htab_of_map_gen_lookup,
 	.map_check_btf = map_check_no_btf,
-	.map_btf_name = "bpf_htab",
-	.map_btf_id = &htab_of_maps_map_btf_id,
+	BATCH_OPS(htab),
+	.map_btf_id = &htab_map_btf_ids[0],
 };