Merge branch 'xdp_redirect-bulking'

Toke Høiland-Jørgensen says:

====================
Since commit 96360004 ("xdp: Make devmap flush_list common for all map
instances"), devmap flushing is a global operation instead of tied to a
particular map. This means that with a bit of refactoring, we can finally fix
the performance delta between the bpf_redirect_map() and bpf_redirect() helper
functions, by introducing bulking for the latter as well.

This series makes this change by moving the data structure used for the bulking
into struct net_device itself, so we can access it even when there is not
devmap. Once this is done, moving the bpf_redirect() helper to use the bulking
mechanism becomes quite trivial, and brings bpf_redirect() up to the same as
bpf_redirect_map():

                       Before:   After:
1 CPU:
bpf_redirect_map:      8.4 Mpps  8.4 Mpps  (no change)
bpf_redirect:          5.0 Mpps  8.4 Mpps  (+68%)
2 CPUs:
bpf_redirect_map:     15.9 Mpps  16.1 Mpps  (+1% or ~no change)
bpf_redirect:          9.5 Mpps  15.9 Mpps  (+67%)

After this patch series, the only semantics different between the two variants
of the bpf() helper (apart from the absence of a map argument, obviously) is
that the _map() variant will return an error if passed an invalid map index,
whereas the bpf_redirect() helper will succeed, but drop packets on
xdp_do_redirect(). This is because the helper has no reference to the calling
netdev, so unfortunately we can't do the ifindex lookup directly in the helper.

Changelog:

v3:
  - Switch two more fields to avoid a list_head spanning two cache lines
  - Include Jesper's tracepoint patch
  - Also rename xdp_do_flush_map()
  - Fix a few nits from Maciej

v2:
  - Consolidate code paths and tracepoints for map and non-map redirect variants
    (Björn)
  - Add performance data for 2-CPU test (Jesper)
  - Move fields to avoid shifting cache lines in struct net_device (Eric)
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

drivers/net/tun.c

@@ -1718,7 +1718,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 		if (err < 0)
 			goto err_xdp;
 		if (err == XDP_REDIRECT)
-			xdp_do_flush_map();
+			xdp_do_flush();
 		if (err != XDP_PASS)
 			goto out;
 
@@ -2549,7 +2549,7 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 		}
 
 		if (flush)
-			xdp_do_flush_map();
+			xdp_do_flush();
 
 		rcu_read_unlock();
 		local_bh_enable();

drivers/net/veth.c

@@ -769,7 +769,7 @@ static int veth_poll(struct napi_struct *napi, int budget)
 	if (xdp_xmit & VETH_XDP_TX)
 		veth_xdp_flush(rq->dev, &bq);
 	if (xdp_xmit & VETH_XDP_REDIR)
-		xdp_do_flush_map();
+		xdp_do_flush();
 	xdp_clear_return_frame_no_direct();
 
 	return done;

drivers/net/virtio_net.c

@@ -1432,7 +1432,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 		virtqueue_napi_complete(napi, rq->vq, received);
 
 	if (xdp_xmit & VIRTIO_XDP_REDIR)
-		xdp_do_flush_map();
+		xdp_do_flush();
 
 	if (xdp_xmit & VIRTIO_XDP_TX) {
 		sq = virtnet_xdp_sq(vi);

include/linux/bpf.h

@@ -1056,7 +1056,9 @@ struct sk_buff;
 
 struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
 struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key);
-void __dev_map_flush(void);
+void __dev_flush(void);
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+		    struct net_device *dev_rx);
 int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
 int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
@@ -1169,13 +1171,20 @@ static inline struct net_device  *__dev_map_hash_lookup_elem(struct bpf_map *map
 	return NULL;
 }
 
-static inline void __dev_map_flush(void)
+static inline void __dev_flush(void)
 {
 }
 
 struct xdp_buff;
 struct bpf_dtab_netdev;
 
+static inline
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+		    struct net_device *dev_rx)
+{
+	return 0;
+}
+
 static inline
 int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 		    struct net_device *dev_rx)

include/linux/filter.h

@@ -918,7 +918,7 @@ static inline int xdp_ok_fwd_dev(const struct net_device *fwd,
 	return 0;
 }
 
-/* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the
+/* The pair of xdp_do_redirect and xdp_do_flush MUST be called in the
  * same cpu context. Further for best results no more than a single map
  * for the do_redirect/do_flush pair should be used. This limitation is
  * because we only track one map and force a flush when the map changes.
@@ -929,7 +929,13 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 int xdp_do_redirect(struct net_device *dev,
 		    struct xdp_buff *xdp,
 		    struct bpf_prog *prog);
-void xdp_do_flush_map(void);
+void xdp_do_flush(void);
+
+/* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as
+ * it is no longer only flushing maps. Keep this define for compatibility
+ * until all drivers are updated - do not use xdp_do_flush_map() in new code!
+ */
+#define xdp_do_flush_map xdp_do_flush
 
 void bpf_warn_invalid_xdp_action(u32 act);
 

include/linux/netdevice.h

@@ -876,6 +876,7 @@ enum bpf_netdev_command {
 struct bpf_prog_offload_ops;
 struct netlink_ext_ack;
 struct xdp_umem;
+struct xdp_dev_bulk_queue;
 
 struct netdev_bpf {
 	enum bpf_netdev_command command;
@@ -1986,12 +1987,10 @@ struct net_device {
 	unsigned int		num_tx_queues;
 	unsigned int		real_num_tx_queues;
 	struct Qdisc		*qdisc;
-#ifdef CONFIG_NET_SCHED
-	DECLARE_HASHTABLE	(qdisc_hash, 4);
-#endif
 	unsigned int		tx_queue_len;
 	spinlock_t		tx_global_lock;
-	int			watchdog_timeo;
+
+	struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
 
 #ifdef CONFIG_XPS
 	struct xps_dev_maps __rcu *xps_cpus_map;
@@ -2001,11 +2000,15 @@ struct net_device {
 	struct mini_Qdisc __rcu	*miniq_egress;
 #endif
 
+#ifdef CONFIG_NET_SCHED
+	DECLARE_HASHTABLE	(qdisc_hash, 4);
+#endif
 	/* These may be needed for future network-power-down code. */
 	struct timer_list	watchdog_timer;
+	int			watchdog_timeo;
 
-	int __percpu		*pcpu_refcnt;
 	struct list_head	todo_list;
+	int __percpu		*pcpu_refcnt;
 
 	struct list_head	link_watch_list;
 

include/trace/events/xdp.h

@@ -79,14 +79,26 @@ TRACE_EVENT(xdp_bulk_tx,
 		  __entry->sent, __entry->drops, __entry->err)
 );
 
+#ifndef __DEVMAP_OBJ_TYPE
+#define __DEVMAP_OBJ_TYPE
+struct _bpf_dtab_netdev {
+	struct net_device *dev;
+};
+#endif /* __DEVMAP_OBJ_TYPE */
+
+#define devmap_ifindex(tgt, map)				\
+	(((map->map_type == BPF_MAP_TYPE_DEVMAP ||	\
+		  map->map_type == BPF_MAP_TYPE_DEVMAP_HASH)) ? \
+	  ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex : 0)
+
 DECLARE_EVENT_CLASS(xdp_redirect_template,
 
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
-		 int to_ifindex, int err,
-		 const struct bpf_map *map, u32 map_index),
+		 const void *tgt, int err,
+		 const struct bpf_map *map, u32 index),
 
-	TP_ARGS(dev, xdp, to_ifindex, err, map, map_index),
+	TP_ARGS(dev, xdp, tgt, err, map, index),
 
 	TP_STRUCT__entry(
 		__field(int, prog_id)
@@ -103,90 +115,65 @@ DECLARE_EVENT_CLASS(xdp_redirect_template,
 		__entry->act		= XDP_REDIRECT;
 		__entry->ifindex	= dev->ifindex;
 		__entry->err		= err;
-		__entry->to_ifindex	= to_ifindex;
+		__entry->to_ifindex	= map ? devmap_ifindex(tgt, map) :
+						index;
 		__entry->map_id		= map ? map->id : 0;
-		__entry->map_index	= map_index;
+		__entry->map_index	= map ? index : 0;
 	),
 
-	TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d",
+	TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
+		  " map_id=%d map_index=%d",
 		  __entry->prog_id,
 		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
 		  __entry->ifindex, __entry->to_ifindex,
-		  __entry->err)
+		  __entry->err, __entry->map_id, __entry->map_index)
 );
 
 DEFINE_EVENT(xdp_redirect_template, xdp_redirect,
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
-		 int to_ifindex, int err,
-		 const struct bpf_map *map, u32 map_index),
-	TP_ARGS(dev, xdp, to_ifindex, err, map, map_index)
+		 const void *tgt, int err,
+		 const struct bpf_map *map, u32 index),
+	TP_ARGS(dev, xdp, tgt, err, map, index)
 );
 
 DEFINE_EVENT(xdp_redirect_template, xdp_redirect_err,
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
-		 int to_ifindex, int err,
-		 const struct bpf_map *map, u32 map_index),
-	TP_ARGS(dev, xdp, to_ifindex, err, map, map_index)
+		 const void *tgt, int err,
+		 const struct bpf_map *map, u32 index),
+	TP_ARGS(dev, xdp, tgt, err, map, index)
 );
 
 #define _trace_xdp_redirect(dev, xdp, to)		\
-	 trace_xdp_redirect(dev, xdp, to, 0, NULL, 0);
+	 trace_xdp_redirect(dev, xdp, NULL, 0, NULL, to);
 
 #define _trace_xdp_redirect_err(dev, xdp, to, err)	\
-	 trace_xdp_redirect_err(dev, xdp, to, err, NULL, 0);
+	 trace_xdp_redirect_err(dev, xdp, NULL, err, NULL, to);
 
-DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map,
+#define _trace_xdp_redirect_map(dev, xdp, to, map, index)		\
+	 trace_xdp_redirect(dev, xdp, to, 0, map, index);
+
+#define _trace_xdp_redirect_map_err(dev, xdp, to, map, index, err)	\
+	 trace_xdp_redirect_err(dev, xdp, to, err, map, index);
+
+/* not used anymore, but kept around so as not to break old programs */
+DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map,
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
-		 int to_ifindex, int err,
-		 const struct bpf_map *map, u32 map_index),
-	TP_ARGS(dev, xdp, to_ifindex, err, map, map_index),
-	TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
-		  " map_id=%d map_index=%d",
-		  __entry->prog_id,
-		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
-		  __entry->ifindex, __entry->to_ifindex,
-		  __entry->err,
-		  __entry->map_id, __entry->map_index)
+		 const void *tgt, int err,
+		 const struct bpf_map *map, u32 index),
+	TP_ARGS(dev, xdp, tgt, err, map, index)
 );
 
-DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
+DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err,
 	TP_PROTO(const struct net_device *dev,
 		 const struct bpf_prog *xdp,
-		 int to_ifindex, int err,
-		 const struct bpf_map *map, u32 map_index),
-	TP_ARGS(dev, xdp, to_ifindex, err, map, map_index),
-	TP_printk("prog_id=%d action=%s ifindex=%d to_ifindex=%d err=%d"
-		  " map_id=%d map_index=%d",
-		  __entry->prog_id,
-		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
-		  __entry->ifindex, __entry->to_ifindex,
-		  __entry->err,
-		  __entry->map_id, __entry->map_index)
+		 const void *tgt, int err,
+		 const struct bpf_map *map, u32 index),
+	TP_ARGS(dev, xdp, tgt, err, map, index)
 );
 
-#ifndef __DEVMAP_OBJ_TYPE
-#define __DEVMAP_OBJ_TYPE
-struct _bpf_dtab_netdev {
-	struct net_device *dev;
-};
-#endif /* __DEVMAP_OBJ_TYPE */
-
-#define devmap_ifindex(fwd, map)				\
-	((map->map_type == BPF_MAP_TYPE_DEVMAP ||		\
-	  map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) ?		\
-	  ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0)
-
-#define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx)		\
-	 trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map),	\
-				0, map, idx)
-
-#define _trace_xdp_redirect_map_err(dev, xdp, fwd, map, idx, err)	\
-	 trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map),	\
-				    err, map, idx)
-
 TRACE_EVENT(xdp_cpumap_kthread,
 
 	TP_PROTO(int map_id, unsigned int processed,  unsigned int drops,
@@ -259,43 +246,38 @@ TRACE_EVENT(xdp_cpumap_enqueue,
 
 TRACE_EVENT(xdp_devmap_xmit,
 
-	TP_PROTO(const struct bpf_map *map, u32 map_index,
-		 int sent, int drops,
-		 const struct net_device *from_dev,
-		 const struct net_device *to_dev, int err),
+	TP_PROTO(const struct net_device *from_dev,
+		 const struct net_device *to_dev,
+		 int sent, int drops, int err),
 
-	TP_ARGS(map, map_index, sent, drops, from_dev, to_dev, err),
+	TP_ARGS(from_dev, to_dev, sent, drops, err),
 
 	TP_STRUCT__entry(
-		__field(int, map_id)
+		__field(int, from_ifindex)
 		__field(u32, act)
-		__field(u32, map_index)
+		__field(int, to_ifindex)
 		__field(int, drops)
 		__field(int, sent)
-		__field(int, from_ifindex)
-		__field(int, to_ifindex)
 		__field(int, err)
 	),
 
 	TP_fast_assign(
-		__entry->map_id		= map->id;
+		__entry->from_ifindex	= from_dev->ifindex;
 		__entry->act		= XDP_REDIRECT;
-		__entry->map_index	= map_index;
+		__entry->to_ifindex	= to_dev->ifindex;
 		__entry->drops		= drops;
 		__entry->sent		= sent;
-		__entry->from_ifindex	= from_dev->ifindex;
-		__entry->to_ifindex	= to_dev->ifindex;
 		__entry->err		= err;
 	),
 
 	TP_printk("ndo_xdp_xmit"
-		  " map_id=%d map_index=%d action=%s"
+		  " from_ifindex=%d to_ifindex=%d action=%s"
 		  " sent=%d drops=%d"
-		  " from_ifindex=%d to_ifindex=%d err=%d",
-		  __entry->map_id, __entry->map_index,
+		  " err=%d",
+		  __entry->from_ifindex, __entry->to_ifindex,
 		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
 		  __entry->sent, __entry->drops,
-		  __entry->from_ifindex, __entry->to_ifindex, __entry->err)
+		  __entry->err)
 );
 
 /* Expect users already include <net/xdp.h>, but not xdp_priv.h */

kernel/bpf/devmap.c

@@ -53,13 +53,11 @@
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
 
 #define DEV_MAP_BULK_SIZE 16
-struct bpf_dtab_netdev;
-
-struct xdp_bulk_queue {
+struct xdp_dev_bulk_queue {
 	struct xdp_frame *q[DEV_MAP_BULK_SIZE];
 	struct list_head flush_node;
+	struct net_device *dev;
 	struct net_device *dev_rx;
-	struct bpf_dtab_netdev *obj;
 	unsigned int count;
 };
 
@@ -67,9 +65,8 @@ struct bpf_dtab_netdev {
 	struct net_device *dev; /* must be first member, due to tracepoint */
 	struct hlist_node index_hlist;
 	struct bpf_dtab *dtab;
-	struct xdp_bulk_queue __percpu *bulkq;
 	struct rcu_head rcu;
-	unsigned int idx; /* keep track of map index for tracepoint */
+	unsigned int idx;
 };
 
 struct bpf_dtab {
@@ -84,7 +81,7 @@ struct bpf_dtab {
 	u32 n_buckets;
 };
 
-static DEFINE_PER_CPU(struct list_head, dev_map_flush_list);
+static DEFINE_PER_CPU(struct list_head, dev_flush_list);
 static DEFINE_SPINLOCK(dev_map_lock);
 static LIST_HEAD(dev_map_list);
 
@@ -219,7 +216,6 @@ static void dev_map_free(struct bpf_map *map)
 
 			hlist_for_each_entry_safe(dev, next, head, index_hlist) {
 				hlist_del_rcu(&dev->index_hlist);
-				free_percpu(dev->bulkq);
 				dev_put(dev->dev);
 				kfree(dev);
 			}
@@ -234,7 +230,6 @@ static void dev_map_free(struct bpf_map *map)
 			if (!dev)
 				continue;
 
-			free_percpu(dev->bulkq);
 			dev_put(dev->dev);
 			kfree(dev);
 		}
@@ -320,10 +315,9 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
 	return -ENOENT;
 }
 
-static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags)
+static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
 {
-	struct bpf_dtab_netdev *obj = bq->obj;
-	struct net_device *dev = obj->dev;
+	struct net_device *dev = bq->dev;
 	int sent = 0, drops = 0, err = 0;
 	int i;
 
@@ -346,8 +340,7 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags)
 out:
 	bq->count = 0;
 
-	trace_xdp_devmap_xmit(&obj->dtab->map, obj->idx,
-			      sent, drops, bq->dev_rx, dev, err);
+	trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, drops, err);
 	bq->dev_rx = NULL;
 	__list_del_clearprev(&bq->flush_node);
 	return 0;
@@ -364,17 +357,17 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags)
 	goto out;
 }
 
-/* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled
+/* __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.
  */
-void __dev_map_flush(void)
+void __dev_flush(void)
 {
-	struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list);
-	struct xdp_bulk_queue *bq, *tmp;
+	struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
+	struct xdp_dev_bulk_queue *bq, *tmp;
 
 	rcu_read_lock();
 	list_for_each_entry_safe(bq, tmp, flush_list, flush_node)
@@ -401,12 +394,11 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
 /* Runs under RCU-read-side, plus in softirq under NAPI protection.
  * Thus, safe percpu variable access.
  */
-static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
+static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 		      struct net_device *dev_rx)
-
 {
-	struct list_head *flush_list = this_cpu_ptr(&dev_map_flush_list);
-	struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq);
+	struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
+	struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
 
 	if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
 		bq_xmit_all(bq, 0);
@@ -426,10 +418,9 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
 	return 0;
 }
 
-int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
+static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
 			       struct net_device *dev_rx)
 {
-	struct net_device *dev = dst->dev;
 	struct xdp_frame *xdpf;
 	int err;
 
@@ -444,7 +435,21 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 	if (unlikely(!xdpf))
 		return -EOVERFLOW;
 
-	return bq_enqueue(dst, xdpf, dev_rx);
+	return bq_enqueue(dev, xdpf, dev_rx);
+}
+
+int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
+		    struct net_device *dev_rx)
+{
+	return __xdp_enqueue(dev, xdp, dev_rx);
+}
+
+int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
+		    struct net_device *dev_rx)
+{
+	struct net_device *dev = dst->dev;
+
+	return __xdp_enqueue(dev, xdp, dev_rx);
 }
 
 int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
@@ -483,7 +488,6 @@ static void __dev_map_entry_free(struct rcu_head *rcu)
 	struct bpf_dtab_netdev *dev;
 
 	dev = container_of(rcu, struct bpf_dtab_netdev, rcu);
-	free_percpu(dev->bulkq);
 	dev_put(dev->dev);
 	kfree(dev);
 }
@@ -538,30 +542,15 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net,
 						    u32 ifindex,
 						    unsigned int idx)
 {
-	gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN;
 	struct bpf_dtab_netdev *dev;
-	struct xdp_bulk_queue *bq;
-	int cpu;
 
-	dev = kmalloc_node(sizeof(*dev), gfp, dtab->map.numa_node);
+	dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN,
+			   dtab->map.numa_node);
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq),
-					sizeof(void *), gfp);
-	if (!dev->bulkq) {
-		kfree(dev);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	for_each_possible_cpu(cpu) {
-		bq = per_cpu_ptr(dev->bulkq, cpu);
-		bq->obj = dev;
-	}
-
 	dev->dev = dev_get_by_index(net, ifindex);
 	if (!dev->dev) {
-		free_percpu(dev->bulkq);
 		kfree(dev);
 		return ERR_PTR(-EINVAL);
 	}
@@ -721,9 +710,23 @@ static int dev_map_notification(struct notifier_block *notifier,
 {
 	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
 	struct bpf_dtab *dtab;
-	int i;
+	int i, cpu;
 
 	switch (event) {
+	case NETDEV_REGISTER:
+		if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq)
+			break;
+
+		/* will be freed in free_netdev() */
+		netdev->xdp_bulkq =
+			__alloc_percpu_gfp(sizeof(struct xdp_dev_bulk_queue),
+					   sizeof(void *), GFP_ATOMIC);
+		if (!netdev->xdp_bulkq)
+			return NOTIFY_BAD;
+
+		for_each_possible_cpu(cpu)
+			per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev;
+		break;
 	case NETDEV_UNREGISTER:
 		/* This rcu_read_lock/unlock pair is needed because
 		 * dev_map_list is an RCU list AND to ensure a delete
@@ -771,7 +774,7 @@ static int __init dev_map_init(void)
 	register_netdevice_notifier(&dev_map_notifier);
 
 	for_each_possible_cpu(cpu)
-		INIT_LIST_HEAD(&per_cpu(dev_map_flush_list, cpu));
+		INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu));
 	return 0;
 }
 

net/core/dev.c

@@ -9847,6 +9847,8 @@ void free_netdev(struct net_device *dev)
 
 	free_percpu(dev->pcpu_refcnt);
 	dev->pcpu_refcnt = NULL;
+	free_percpu(dev->xdp_bulkq);
+	dev->xdp_bulkq = NULL;
 
 	netdev_unregister_lockdep_key(dev);
 

net/core/filter.c

@@ -3458,58 +3458,6 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
-static int __bpf_tx_xdp(struct net_device *dev,
-			struct bpf_map *map,
-			struct xdp_buff *xdp,
-			u32 index)
-{
-	struct xdp_frame *xdpf;
-	int err, sent;
-
-	if (!dev->netdev_ops->ndo_xdp_xmit) {
-		return -EOPNOTSUPP;
-	}
-
-	err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
-	if (unlikely(err))
-		return err;
-
-	xdpf = convert_to_xdp_frame(xdp);
-	if (unlikely(!xdpf))
-		return -EOVERFLOW;
-
-	sent = dev->netdev_ops->ndo_xdp_xmit(dev, 1, &xdpf, XDP_XMIT_FLUSH);
-	if (sent <= 0)
-		return sent;
-	return 0;
-}
-
-static noinline int
-xdp_do_redirect_slow(struct net_device *dev, struct xdp_buff *xdp,
-		     struct bpf_prog *xdp_prog, struct bpf_redirect_info *ri)
-{
-	struct net_device *fwd;
-	u32 index = ri->tgt_index;
-	int err;
-
-	fwd = dev_get_by_index_rcu(dev_net(dev), index);
-	ri->tgt_index = 0;
-	if (unlikely(!fwd)) {
-		err = -EINVAL;
-		goto err;
-	}
-
-	err = __bpf_tx_xdp(fwd, NULL, xdp, 0);
-	if (unlikely(err))
-		goto err;
-
-	_trace_xdp_redirect(dev, xdp_prog, index);
-	return 0;
-err:
-	_trace_xdp_redirect_err(dev, xdp_prog, index, err);
-	return err;
-}
-
 static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
 			    struct bpf_map *map, struct xdp_buff *xdp)
 {
@@ -3527,13 +3475,13 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
 	return 0;
 }
 
-void xdp_do_flush_map(void)
+void xdp_do_flush(void)
 {
-	__dev_map_flush();
+	__dev_flush();
 	__cpu_map_flush();
 	__xsk_map_flush();
 }
-EXPORT_SYMBOL_GPL(xdp_do_flush_map);
+EXPORT_SYMBOL_GPL(xdp_do_flush);
 
 static inline void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
 {
@@ -3568,10 +3516,11 @@ void bpf_clear_redirect_map(struct bpf_map *map)
 	}
 }
 
-static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
-			       struct bpf_prog *xdp_prog, struct bpf_map *map,
-			       struct bpf_redirect_info *ri)
+int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
+		    struct bpf_prog *xdp_prog)
 {
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_map *map = READ_ONCE(ri->map);
 	u32 index = ri->tgt_index;
 	void *fwd = ri->tgt_value;
 	int err;
@@ -3580,7 +3529,18 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
 	ri->tgt_value = NULL;
 	WRITE_ONCE(ri->map, NULL);
 
+	if (unlikely(!map)) {
+		fwd = dev_get_by_index_rcu(dev_net(dev), index);
+		if (unlikely(!fwd)) {
+			err = -EINVAL;
+			goto err;
+		}
+
+		err = dev_xdp_enqueue(fwd, xdp, dev);
+	} else {
 		err = __bpf_tx_xdp_map(dev, fwd, map, xdp);
+	}
+
 	if (unlikely(err))
 		goto err;
 
@@ -3590,18 +3550,6 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
 	_trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
 	return err;
 }
-
-int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
-		    struct bpf_prog *xdp_prog)
-{
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-	struct bpf_map *map = READ_ONCE(ri->map);
-
-	if (likely(map))
-		return xdp_do_redirect_map(dev, xdp, xdp_prog, map, ri);
-
-	return xdp_do_redirect_slow(dev, xdp, xdp_prog, ri);
-}
 EXPORT_SYMBOL_GPL(xdp_do_redirect);
 
 static int xdp_do_generic_redirect_map(struct net_device *dev,

samples/bpf/xdp_monitor_kern.c

@@ -222,14 +222,12 @@ struct bpf_map_def SEC("maps") devmap_xmit_cnt = {
  */
 struct devmap_xmit_ctx {
 	u64 __pad;		// First 8 bytes are not accessible by bpf code
-	int map_id;		//	offset:8;  size:4; signed:1;
+	int from_ifindex;	//	offset:8;  size:4; signed:1;
 	u32 act;		//	offset:12; size:4; signed:0;
-	u32 map_index;		//	offset:16; size:4; signed:0;
+	int to_ifindex; 	//	offset:16; size:4; signed:1;
 	int drops;		//	offset:20; size:4; signed:1;
 	int sent;		//	offset:24; size:4; signed:1;
-	int from_ifindex;	//	offset:28; size:4; signed:1;
-	int to_ifindex;		//	offset:32; size:4; signed:1;
-	int err;		//	offset:36; size:4; signed:1;
+	int err;		//	offset:28; size:4; signed:1;
 };
 
 SEC("tracepoint/xdp/xdp_devmap_xmit")