Merge branch 'xdp_redirect-bulking'

Toke Høiland-Jørgensen says:

====================
Since commit 96360004b862 ("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>

3 files changed, 27 insertions, 9 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3517e32149a4..8e3b8f4ad183 100644
--- a/include/linux/bpf.h
+++ b/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,
@@ -1169,7 +1171,7 @@ 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)
 {
 }
 
@@ -1177,6 +1179,13 @@ 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)
 {
diff --git a/include/linux/filter.h b/include/linux/filter.h
index a366a0b64a57..f349e2c0884c 100644
--- a/include/linux/filter.h
+++ b/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);
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2741aa35bec6..5ec3537fbdb1 100644
--- a/include/linux/netdevice.h
+++ b/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;