[PATCH bpf-next 00/17] Clean up and document RCU-based object protection for XDP_REDIRECT

@@ -363,6 +363,20 @@ static inline void rcu_preempt_sleep_check(void) { }
 #define rcu_check_sparse(p, space)
 #endif /* #else #ifdef __CHECKER__ */
 
+/**
+ * unrcu_pointer - mark a pointer as not being RCU protected
+ * @p: pointer needing to lose its __rcu property
+ *
+ * Converts @p from an __rcu pointer to a __kernel pointer.
+ * This allows an __rcu pointer to be used with xchg() and friends.
+ */
+#define unrcu_pointer(p)						\
+({									\
+	typeof(*p) *_________p1 = (typeof(*p) *__force)(p);		\
+	rcu_check_sparse(p, __rcu); 					\
+	((typeof(*p) __force __kernel *)(_________p1)); 		\
+})
+
 #define __rcu_access_pointer(p, space) \
 ({ \
 	typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \

@@ -596,7 +596,8 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
 	struct htab_elem *l;
 	u32 hash, key_size;
 
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 
 	key_size = map->key_size;
 

@@ -989,7 +990,8 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
 		/* unknown flags */
 		return -EINVAL;
 
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 
 	key_size = map->key_size;
 

@@ -1082,7 +1084,8 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,
 		/* unknown flags */
 		return -EINVAL;
 
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 
 	key_size = map->key_size;
 

@@ -1148,7 +1151,8 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 		/* unknown flags */
 		return -EINVAL;
 
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 
 	key_size = map->key_size;
 

@@ -1202,7 +1206,8 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 		/* unknown flags */
 		return -EINVAL;
 
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 
 	key_size = map->key_size;
 

@@ -1276,7 +1281,8 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key)
 	u32 hash, key_size;
 	int ret;
 
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 
 	key_size = map->key_size;
 

@@ -1311,7 +1317,8 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key)
 	u32 hash, key_size;
 	int ret;
 
-	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() &&
+		     !rcu_read_lock_bh_held());
 
 	key_size = map->key_size;
 

@@ -28,7 +28,7 @@
  */
 BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
 	return (unsigned long) map->ops->map_lookup_elem(map, key);
 }
 

@@ -44,7 +44,7 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto = {
 BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key,
 	   void *, value, u64, flags)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
 	return map->ops->map_update_elem(map, key, value, flags);
 }
 

@@ -61,7 +61,7 @@ const struct bpf_func_proto bpf_map_update_elem_proto = {
 
 BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
 	return map->ops->map_delete_elem(map, key);
 }
 

@@ -232,7 +232,8 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key)
 
 	/* Start walking the trie from the root node ... */
 
-	for (node = rcu_dereference(trie->root); node;) {
+	for (node = rcu_dereference_check(trie->root, rcu_read_lock_bh_held());
+	     node;) {
 		unsigned int next_bit;
 		size_t matchlen;
 

@@ -264,7 +265,8 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key)
 		 * traverse down.
 		 */
 		next_bit = extract_bit(key->data, node->prefixlen);
-		node = rcu_dereference(node->child[next_bit]);
+		node = rcu_dereference_check(node->child[next_bit],
+					     rcu_read_lock_bh_held());
 	}
 
 	if (!found)

@@ -138,9 +138,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 	xdp_prepare_buff(&xdp, *data_ptr - offset, offset, *len, false);
 	orig_data = xdp.data;
 
-	rcu_read_lock();
 	act = bpf_prog_run_xdp(xdp_prog, &xdp);
-	rcu_read_unlock();
 
 	tx_avail = bnxt_tx_avail(bp, txr);
 	/* If the tx ring is not full, we must not update the rx producer yet

@@ -385,7 +385,6 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
 	u64 *xdp_stat;
 	int qid;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_bpf_prog);
 
 	if (!xdp_prog)

@@ -443,8 +442,6 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
 
 	ena_increase_stat(xdp_stat, 1, &rx_ring->syncp);
 out:
-	rcu_read_unlock();
-
 	return verdict;
 }
 

@@ -37,7 +37,7 @@ struct xdp_umem {
 struct xsk_map {
 	struct bpf_map map;
 	spinlock_t lock; /* Synchronize map updates */
-	struct xdp_sock *xsk_map[];
+	struct xdp_sock __rcu *xsk_map[];
 };
 
 struct xdp_sock {

@@ -74,7 +74,7 @@ struct bpf_cpu_map_entry {
 struct bpf_cpu_map {
 	struct bpf_map map;
 	/* Below members specific for map type */
-	struct bpf_cpu_map_entry **cpu_map;
+	struct bpf_cpu_map_entry __rcu **cpu_map;
 };
 
 static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list);

@@ -469,7 +469,7 @@ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
 {
 	struct bpf_cpu_map_entry *old_rcpu;
 
-	old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu);
+	old_rcpu = unrcu_pointer(xchg(&cmap->cpu_map[key_cpu], RCU_INITIALIZER(rcpu)));
 	if (old_rcpu) {
 		call_rcu(&old_rcpu->rcu, __cpu_map_entry_free);
 		INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop);

@@ -551,7 +551,8 @@ static void cpu_map_free(struct bpf_map *map)
 	for (i = 0; i < cmap->map.max_entries; i++) {
 		struct bpf_cpu_map_entry *rcpu;
 
-		rcpu = READ_ONCE(cmap->cpu_map[i]);
+		rcpu = rcu_dereference_check(cmap->cpu_map[i],
+					     rcu_read_lock_bh_held());
 		if (!rcpu)
 			continue;
 

@@ -562,6 +563,10 @@ static void cpu_map_free(struct bpf_map *map)
 	kfree(cmap);
 }
 
+/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
+ * by local_bh_disable() (from XDP calls inside NAPI). The
+ * rcu_read_lock_bh_held() below makes lockdep accept both.
+ */
 static void *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
 {
 	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);

@@ -570,7 +575,8 @@ static void *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
 	if (key >= map->max_entries)
 		return NULL;
 
-	rcpu = READ_ONCE(cmap->cpu_map[key]);
+	rcpu = rcu_dereference_check(cmap->cpu_map[key],
+				     rcu_read_lock_bh_held());
 	return rcpu;
 }
 

@@ -73,7 +73,7 @@ struct bpf_dtab_netdev {
 
 struct bpf_dtab {
 	struct bpf_map map;
-	struct bpf_dtab_netdev **netdev_map; /* DEVMAP type only */
+	struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */
 	struct list_head list;
 
 	/* these are only used for DEVMAP_HASH type maps */

@@ -226,7 +226,7 @@ static void dev_map_free(struct bpf_map *map)
 		for (i = 0; i < dtab->map.max_entries; i++) {
 			struct bpf_dtab_netdev *dev;
 
-			dev = dtab->netdev_map[i];
+			dev = rcu_dereference_raw(dtab->netdev_map[i]);
 			if (!dev)
 				continue;
 

@@ -259,6 +259,10 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
+/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
+ * by local_bh_disable() (from XDP calls inside NAPI). The
+ * rcu_read_lock_bh_held() below makes lockdep accept both.
+ */
 static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);

@@ -266,7 +270,8 @@ static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key)
 	struct bpf_dtab_netdev *dev;
 
 	hlist_for_each_entry_rcu(dev, head, index_hlist,
-				 lockdep_is_held(&dtab->index_lock))
+				 (lockdep_is_held(&dtab->index_lock) ||
+				  rcu_read_lock_bh_held()))
 		if (dev->idx == key)
 			return dev;
 

@@ -410,15 +415,9 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
 	trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err);
 }
 
-/* __dev_flush is called from xdp_do_flush() which _must_ be signaled
- * from the driver before returning from its napi->poll() routine. The poll()
- * routine is called either from busy_poll context or net_rx_action signaled
- * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the
- * net device can be torn down. On devmap tear down we ensure the flush list
- * is empty before completing to ensure all flush operations have completed.
- * When drivers update the bpf program they may need to ensure any flush ops
- * are also complete. Using synchronize_rcu or call_rcu will suffice for this
- * because both wait for napi context to exit.
+/* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the
+ * driver before returning from its napi->poll() routine. See the comment above
+ * xdp_do_flush() in filter.c.
  */
 void __dev_flush(void)
 {

@@ -433,9 +432,9 @@ void __dev_flush(void)
 	}
 }
 
-/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or
- * update happens in parallel here a dev_put won't happen until after reading
- * the ifindex.
+/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
+ * by local_bh_disable() (from XDP calls inside NAPI). The
+ * rcu_read_lock_bh_held() below makes lockdep accept both.
  */
 static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
 {

@@ -445,12 +444,14 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
 	if (key >= map->max_entries)
 		return NULL;
 
-	obj = READ_ONCE(dtab->netdev_map[key]);
+	obj = rcu_dereference_check(dtab->netdev_map[key],
+				    rcu_read_lock_bh_held());
 	return obj;
 }
 
-/* Runs under RCU-read-side, plus in softirq under NAPI protection.
- * Thus, safe percpu variable access.
+/* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu
+ * variable access, and map elements stick around. See comment above
+ * xdp_do_flush() in filter.c.
  */
 static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 		       struct net_device *dev_rx, struct bpf_prog *xdp_prog)

@@ -735,14 +736,7 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key)
 	if (k >= map->max_entries)
 		return -EINVAL;
 
-	/* Use call_rcu() here to ensure any rcu critical sections have
-	 * completed as well as any flush operations because call_rcu
-	 * will wait for preempt-disable region to complete, NAPI in this
-	 * context.  And additionally, the driver tear down ensures all
-	 * soft irqs are complete before removing the net device in the
-	 * case of dev_put equals zero.
-	 */
-	old_dev = xchg(&dtab->netdev_map[k], NULL);
+	old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL));
 	if (old_dev)
 		call_rcu(&old_dev->rcu, __dev_map_entry_free);
 	return 0;

@@ -851,7 +845,7 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map,
 	 * Remembering the driver side flush operation will happen before the
 	 * net device is removed.
 	 */
-	old_dev = xchg(&dtab->netdev_map[i], dev);
+	old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev)));
 	if (old_dev)
 		call_rcu(&old_dev->rcu, __dev_map_entry_free);
 

@@ -1031,10 +1025,10 @@ static int dev_map_notification(struct notifier_block *notifier,
 			for (i = 0; i < dtab->map.max_entries; i++) {
 				struct bpf_dtab_netdev *dev, *odev;
 
-				dev = READ_ONCE(dtab->netdev_map[i]);
+				dev = rcu_dereference(dtab->netdev_map[i]);
 				if (!dev || netdev != dev->dev)
 					continue;
-				odev = cmpxchg(&dtab->netdev_map[i], dev, NULL);
+				odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL));
 				if (dev == odev)
 					call_rcu(&dev->rcu,
 						 __dev_map_entry_free);

@@ -3922,6 +3922,34 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+/* XDP_REDIRECT works by a three-step process, implemented in the functions
+ * below:
+ *
+ * 1. The bpf_redirect() and bpf_redirect_map() helpers will lookup the target
+ *    of the redirect and store it (along with some other metadata) in a per-CPU
+ *    struct bpf_redirect_info.
+ *
+ * 2. When the program returns the XDP_REDIRECT return code, the driver will
+ *    call xdp_do_redirect() which will use the information in struct
+ *    bpf_redirect_info to actually enqueue the frame into a map type-specific
+ *    bulk queue structure.
+ *
+ * 3. Before exiting its NAPI poll loop, the driver will call xdp_do_flush(),
+ *    which will flush all the different bulk queues, thus completing the
+ *    redirect.
+ *
+ * Pointers to the map entries will be kept around for this whole sequence of
+ * steps, protected by RCU. However, there is no top-level rcu_read_lock() in
+ * the core code; instead, the RCU protection relies on everything happening
+ * inside a single NAPI poll sequence, which means it's between a pair of calls
+ * to local_bh_disable()/local_bh_enable().
+ *
+ * The map entries are marked as __rcu and the map code makes sure to
+ * dereference those pointers with rcu_dereference_check() in a way that works
+ * for both sections that to hold an rcu_read_lock() and sections that are
+ * called from NAPI without a separate rcu_read_lock(). The code below does not
+ * use RCU annotations, but relies on those in the map code.
+ */
 void xdp_do_flush(void)
 {
 	__dev_flush();

@@ -749,7 +749,7 @@ static void xsk_unbind_dev(struct xdp_sock *xs)
 }
 
 static struct xsk_map *xsk_get_map_list_entry(struct xdp_sock *xs,
-					      struct xdp_sock ***map_entry)
+					      struct xdp_sock __rcu ***map_entry)
 {
 	struct xsk_map *map = NULL;
 	struct xsk_map_node *node;

@@ -785,7 +785,7 @@ static void xsk_delete_from_maps(struct xdp_sock *xs)
 	 * might be updates to the map between
 	 * xsk_get_map_list_entry() and xsk_map_try_sock_delete().
 	 */
-	struct xdp_sock **map_entry = NULL;
+	struct xdp_sock __rcu **map_entry = NULL;
 	struct xsk_map *map;
 
 	while ((map = xsk_get_map_list_entry(xs, &map_entry))) {

@@ -31,7 +31,7 @@ struct xdp_mmap_offsets_v1 {
 struct xsk_map_node {
 	struct list_head node;
 	struct xsk_map *map;
-	struct xdp_sock **map_entry;
+	struct xdp_sock __rcu **map_entry;
 };
 
 static inline struct xdp_sock *xdp_sk(struct sock *sk)

@@ -40,7 +40,7 @@ static inline struct xdp_sock *xdp_sk(struct sock *sk)
 }
 
 void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
-			     struct xdp_sock **map_entry);
+			     struct xdp_sock __rcu **map_entry);
 void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id);
 int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
 			u16 queue_id);

@@ -12,7 +12,7 @@
 #include "xsk.h"
 
 static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map,
-					       struct xdp_sock **map_entry)
+					       struct xdp_sock __rcu **map_entry)
 {
 	struct xsk_map_node *node;
 

@@ -42,7 +42,7 @@ static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node)
 }
 
 static void xsk_map_sock_delete(struct xdp_sock *xs,
-				struct xdp_sock **map_entry)
+				struct xdp_sock __rcu **map_entry)
 {
 	struct xsk_map_node *n, *tmp;
 

@@ -124,6 +124,10 @@ static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 	return insn - insn_buf;
 }
 
+/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
+ * by local_bh_disable() (from XDP calls inside NAPI). The
+ * rcu_read_lock_bh_held() below makes lockdep accept both.
+ */
 static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);

@@ -131,12 +135,11 @@ static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
 	if (key >= map->max_entries)
 		return NULL;
 
-	return READ_ONCE(m->xsk_map[key]);
+	return rcu_dereference_check(m->xsk_map[key], rcu_read_lock_bh_held());
 }
 
 static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held());
 	return __xsk_map_lookup_elem(map, *(u32 *)key);
 }
 

@@ -149,7 +152,8 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 			       u64 map_flags)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	struct xdp_sock *xs, *old_xs, **map_entry;
+	struct xdp_sock __rcu **map_entry;
+	struct xdp_sock *xs, *old_xs;
 	u32 i = *(u32 *)key, fd = *(u32 *)value;
 	struct xsk_map_node *node;
 	struct socket *sock;

@@ -179,7 +183,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 	}
 
 	spin_lock_bh(&m->lock);
-	old_xs = READ_ONCE(*map_entry);
+	old_xs = rcu_dereference_check(*map_entry, rcu_read_lock_bh_held());
 	if (old_xs == xs) {
 		err = 0;
 		goto out;

@@ -191,7 +195,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 		goto out;
 	}
 	xsk_map_sock_add(xs, node);
-	WRITE_ONCE(*map_entry, xs);
+	rcu_assign_pointer(*map_entry, xs);
 	if (old_xs)
 		xsk_map_sock_delete(old_xs, map_entry);
 	spin_unlock_bh(&m->lock);

@@ -208,7 +212,8 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 static int xsk_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
-	struct xdp_sock *old_xs, **map_entry;
+	struct xdp_sock __rcu **map_entry;
+	struct xdp_sock *old_xs;
 	int k = *(u32 *)key;
 
 	if (k >= map->max_entries)

@@ -216,7 +221,7 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
 
 	spin_lock_bh(&m->lock);
 	map_entry = &m->xsk_map[k];
-	old_xs = xchg(map_entry, NULL);
+	old_xs = unrcu_pointer(xchg(map_entry, NULL));
 	if (old_xs)
 		xsk_map_sock_delete(old_xs, map_entry);
 	spin_unlock_bh(&m->lock);

@@ -231,11 +236,11 @@ static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
 }
 
 void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
-			     struct xdp_sock **map_entry)
+			     struct xdp_sock __rcu **map_entry)
 {
 	spin_lock_bh(&map->lock);
-	if (READ_ONCE(*map_entry) == xs) {
-		WRITE_ONCE(*map_entry, NULL);
+	if (rcu_dereference(*map_entry) == xs) {
+		rcu_assign_pointer(*map_entry, NULL);
 		xsk_map_sock_delete(xs, map_entry);
 	}
 	spin_unlock_bh(&map->lock);

@@ -1002,7 +1002,7 @@ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex)
 	struct net_device *dev;
 	struct hlist_head *head = dev_index_hash(net, ifindex);
 
-	hlist_for_each_entry_rcu(dev, head, index_hlist)
+	hlist_for_each_entry_rcu(dev, head, index_hlist, rcu_read_lock_bh_held())
 		if (dev->ifindex == ifindex)
 			return dev;
 

@@ -2298,7 +2298,6 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 	struct bpf_prog *xdp_prog;
 	u32 act;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 
 	if (!xdp_prog)

@@ -2329,7 +2328,6 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 		break;
 	}
 xdp_out:
-	rcu_read_unlock();
 	return result;
 }
 

@@ -153,7 +153,6 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 	struct bpf_prog *xdp_prog;
 	u32 act;
 
-	rcu_read_lock();
 	/* NB! xdp_prog will always be !NULL, due to the fact that
 	 * this path is enabled by setting an XDP program.
 	 */

@@ -162,9 +161,7 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 
 	if (likely(act == XDP_REDIRECT)) {
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
-		rcu_read_unlock();
-		return result;
+		return !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
 	}
 
 	switch (act) {

@@ -184,7 +181,6 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 		result = I40E_XDP_CONSUMED;
 		break;
 	}
-	rcu_read_unlock();
 	return result;
 }
 

@@ -1129,15 +1129,11 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		xdp.frame_sz = ice_rx_frame_truesize(rx_ring, size);
 #endif
 
-		rcu_read_lock();
 		xdp_prog = READ_ONCE(rx_ring->xdp_prog);
-		if (!xdp_prog) {
-			rcu_read_unlock();
+		if (!xdp_prog)
 			goto construct_skb;
-		}
 
 		xdp_res = ice_run_xdp(rx_ring, &xdp, xdp_prog);
-		rcu_read_unlock();
 		if (!xdp_res)
 			goto construct_skb;
 		if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) {

@@ -463,7 +463,6 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
 	struct ice_ring *xdp_ring;
 	u32 act;
 
-	rcu_read_lock();
 	/* ZC patch is enabled only when XDP program is set,
 	 * so here it can not be NULL
 	 */

@@ -473,9 +472,7 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
 
 	if (likely(act == XDP_REDIRECT)) {
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED;
-		rcu_read_unlock();
-		return result;
+		return !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED;
 	}
 
 	switch (act) {

@@ -496,7 +493,6 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
 		break;
 	}
 
-	rcu_read_unlock();
 	return result;
 }
 

@@ -8387,7 +8387,6 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter,
 	struct bpf_prog *xdp_prog;
 	u32 act;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 
 	if (!xdp_prog)

@@ -8420,7 +8419,6 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter,
 		break;
 	}
 xdp_out:
-	rcu_read_unlock();
 	return ERR_PTR(-result);
 }
 

@@ -2175,18 +2175,15 @@ static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter,
 	struct bpf_prog *prog;
 	int res;
 
-	rcu_read_lock();
-
 	prog = READ_ONCE(adapter->xdp_prog);
 	if (!prog) {
 		res = IGC_XDP_PASS;
-		goto unlock;
+		goto out;
 	}
 
 	res = __igc_xdp_run_prog(adapter, prog, xdp);
 
-unlock:
-	rcu_read_unlock();
+out:
 	return ERR_PTR(-res);
 }
 

@@ -2199,7 +2199,6 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 	struct xdp_frame *xdpf;
 	u32 act;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 
 	if (!xdp_prog)

@@ -2237,7 +2236,6 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 		break;
 	}
 xdp_out:
-	rcu_read_unlock();
 	return ERR_PTR(-result);
 }
 

@@ -100,15 +100,12 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 	struct xdp_frame *xdpf;
 	u32 act;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 
 	if (likely(act == XDP_REDIRECT)) {
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED;
-		rcu_read_unlock();
-		return result;
+		return !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED;
 	}
 
 	switch (act) {

@@ -132,7 +129,6 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 		result = IXGBE_XDP_CONSUMED;
 		break;
 	}
-	rcu_read_unlock();
 	return result;
 }
 

@@ -1054,7 +1054,6 @@ static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter,
 	struct bpf_prog *xdp_prog;
 	u32 act;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 
 	if (!xdp_prog)

@@ -1079,7 +1078,6 @@ static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter,
 		break;
 	}
 xdp_out:
-	rcu_read_unlock();
 	return ERR_PTR(-result);
 }
 

@@ -555,9 +555,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 	xdp_prepare_buff(&xdp, hard_start, data - hard_start, len, false);
 	orig_data = xdp.data;
 
-	rcu_read_lock();
 	action = bpf_prog_run_xdp(prog, &xdp);
-	rcu_read_unlock();
 
 	len = xdp.data_end - xdp.data;
 	/* Check if XDP program has changed headers */

@@ -2558,13 +2558,9 @@ static u32 dpaa_run_xdp(struct dpaa_priv *priv, struct qm_fd *fd, void *vaddr,
 	u32 xdp_act;
 	int err;
 
-	rcu_read_lock();
-
 	xdp_prog = READ_ONCE(priv->xdp_prog);
-	if (!xdp_prog) {
-		rcu_read_unlock();
+	if (!xdp_prog)
 		return XDP_PASS;
-	}
 
 	xdp_init_buff(&xdp, DPAA_BP_RAW_SIZE - DPAA_TX_PRIV_DATA_SIZE,
 		      &dpaa_fq->xdp_rxq);

@@ -2638,8 +2634,6 @@ static u32 dpaa_run_xdp(struct dpaa_priv *priv, struct qm_fd *fd, void *vaddr,
 		break;
 	}
 
-	rcu_read_unlock();
-
 	return xdp_act;
 }
 

@@ -352,8 +352,6 @@ static u32 dpaa2_eth_run_xdp(struct dpaa2_eth_priv *priv,
 	u32 xdp_act = XDP_PASS;
 	int err, offset;
 
-	rcu_read_lock();
-
 	xdp_prog = READ_ONCE(ch->xdp.prog);
 	if (!xdp_prog)
 		goto out;

@@ -414,7 +412,6 @@ static u32 dpaa2_eth_run_xdp(struct dpaa2_eth_priv *priv,
 
 	ch->xdp.res |= xdp_act;
 out:
-	rcu_read_unlock();
 	return xdp_act;
 }
 

@@ -4654,7 +4654,6 @@ static int stmmac_xdp_xmit_back(struct stmmac_priv *priv,
 	return res;
 }
 
-/* This function assumes rcu_read_lock() is held by the caller. */
 static int __stmmac_xdp_run_prog(struct stmmac_priv *priv,
 				 struct bpf_prog *prog,
 				 struct xdp_buff *xdp)

@@ -4696,17 +4695,14 @@ static struct sk_buff *stmmac_xdp_run_prog(struct stmmac_priv *priv,
 	struct bpf_prog *prog;
 	int res;
 
-	rcu_read_lock();
-
 	prog = READ_ONCE(priv->xdp_prog);
 	if (!prog) {
 		res = STMMAC_XDP_PASS;
-		goto unlock;
+		goto out;
 	}
 
 	res = __stmmac_xdp_run_prog(priv, prog, xdp);
-unlock:
-	rcu_read_unlock();
+out:
 	return ERR_PTR(-res);
 }
 

@@ -4976,10 +4972,8 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue)
 		buf->xdp->data_end = buf->xdp->data + buf1_len;
 		xsk_buff_dma_sync_for_cpu(buf->xdp, rx_q->xsk_pool);
 
-		rcu_read_lock();
 		prog = READ_ONCE(priv->xdp_prog);
 		res = __stmmac_xdp_run_prog(priv, prog, buf->xdp);
-		rcu_read_unlock();
 
 		switch (res) {
 		case STMMAC_XDP_PASS:

@@ -958,7 +958,6 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 
 	xdp_init_buff(&xdp, PAGE_SIZE, &dring->xdp_rxq);
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(priv->xdp_prog);
 	dma_dir = page_pool_get_dma_dir(dring->page_pool);
 

@@ -1069,8 +1068,6 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 	}
 	netsec_finalize_xdp_rx(priv, xdp_act, xdp_xmit);
 
-	rcu_read_unlock();
-
 	return done;
 }
 

@@ -260,18 +260,14 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel,
 	s16 offset;
 	int err;
 
-	rcu_read_lock();
-	xdp_prog = rcu_dereference(efx->xdp_prog);
-	if (!xdp_prog) {
-		rcu_read_unlock();
+	xdp_prog = rcu_dereference_bh(efx->xdp_prog);
+	if (!xdp_prog)
 		return true;
-	}
 
 	rx_queue = efx_channel_get_rx_queue(channel);
 
 	if (unlikely(channel->rx_pkt_n_frags > 1)) {
 		/* We can't do XDP on fragmented packets - drop. */
-		rcu_read_unlock();
 		efx_free_rx_buffers(rx_queue, rx_buf,
 				    channel->rx_pkt_n_frags);
 		if (net_ratelimit())

@@ -296,7 +292,6 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel,
 			 rx_buf->len, false);
 
 	xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp);
-	rcu_read_unlock();
 
 	offset = (u8 *)xdp.data - *ehp;
 

@@ -1328,13 +1328,9 @@ int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp,
 	struct bpf_prog *prog;
 	u32 act;
 
-	rcu_read_lock();
-
 	prog = READ_ONCE(priv->xdp_prog);
-	if (!prog) {
-		ret = CPSW_XDP_PASS;
-		goto out;
-	}
+	if (!prog)
+		return CPSW_XDP_PASS;
 
 	act = bpf_prog_run_xdp(prog, xdp);
 	/* XDP prog might have changed packet data and boundaries */

@@ -1378,10 +1374,8 @@ int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp,
 	ndev->stats.rx_bytes += *len;
 	ndev->stats.rx_packets++;
 out:
-	rcu_read_unlock();
 	return ret;
 drop:
-	rcu_read_unlock();
 	page_pool_recycle_direct(cpsw->page_pool[ch], page);
 	return ret;
 }

@@ -679,9 +679,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 
 	ring = priv->rx_ring[cq_ring];
 
-	/* Protect accesses to: ring->xdp_prog, priv->mac_hash list */
-	rcu_read_lock();
-	xdp_prog = rcu_dereference(ring->xdp_prog);
+	xdp_prog = rcu_dereference_bh(ring->xdp_prog);
 	xdp_init_buff(&xdp, priv->frag_info[0].frag_stride, &ring->xdp_rxq);
 	doorbell_pending = false;
 

@@ -744,7 +742,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 				/* Drop the packet, since HW loopback-ed it */
 				mac_hash = ethh->h_source[MLX4_EN_MAC_HASH_IDX];
 				bucket = &priv->mac_hash[mac_hash];
-				hlist_for_each_entry_rcu(entry, bucket, hlist) {
+				hlist_for_each_entry_rcu_bh(entry, bucket, hlist) {
 					if (ether_addr_equal_64bits(entry->mac,
 								    ethh->h_source))
 						goto next;

@@ -899,8 +897,6 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			break;
 	}
 
-	rcu_read_unlock();
-
 	if (likely(polled)) {
 		if (doorbell_pending) {
 			priv->tx_cq[TX_XDP][cq_ring]->xdp_busy = true;

@@ -1819,7 +1819,6 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 	struct xdp_buff xdp;
 	int idx;
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(dp->xdp_prog);
 	true_bufsz = xdp_prog ? PAGE_SIZE : dp->fl_bufsz;
 	xdp_init_buff(&xdp, PAGE_SIZE - NFP_NET_RX_BUF_HEADROOM,

@@ -2036,7 +2035,6 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 			if (!nfp_net_xdp_complete(tx_ring))
 				pkts_polled = budget;
 	}
-	rcu_read_unlock();
 
 	return pkts_polled;
 }

@@ -1089,13 +1089,7 @@ static bool qede_rx_xdp(struct qede_dev *edev,
 	xdp_prepare_buff(&xdp, page_address(bd->data), *data_offset,
 			 *len, false);
 
-	/* Queues always have a full reset currently, so for the time
-	 * being until there's atomic program replace just mark read
-	 * side for map helpers.
-	 */
-	rcu_read_lock();
 	act = bpf_prog_run_xdp(prog, &xdp);
-	rcu_read_unlock();
 
 	/* Recalculate, as XDP might have changed the headers */
 	*data_offset = xdp.data - xdp.data_hard_start;

@@ -2370,7 +2370,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 	/* Get number of received packets */
 	rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq);
 
-	rcu_read_lock();
 	xdp_prog = READ_ONCE(pp->xdp_prog);
 
 	/* Fairness NAPI loop */

@@ -2448,7 +2447,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 		xdp_buf.data_hard_start = NULL;
 		sinfo.nr_frags = 0;
 	}
-	rcu_read_unlock();
 
 	if (xdp_buf.data_hard_start)
 		mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);

@@ -3852,8 +3852,6 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 	int rx_done = 0;
 	u32 xdp_ret = 0;
 
-	rcu_read_lock();
-
 	xdp_prog = READ_ONCE(port->xdp_prog);
 
 	/* Get number of received packets and clamp the to-do */