xdp: Move devmap bulk queue into struct net_device

Commit 96360004b862 ("xdp: Make devmap flush_list common for all map
instances"), changed devmap flushing to be a global operation instead of a
per-map operation. However, the queue structure used for bulking was still
allocated as part of the containing map.

This patch moves the devmap bulk queue into struct net_device. The
motivation for this is reusing it for the non-map variant of XDP_REDIRECT,
which will be changed in a subsequent commit.  To avoid other fields of
struct net_device moving to different cache lines, we also move a couple of
other members around.

We defer the actual allocation of the bulk queue structure until the
NETDEV_REGISTER notification devmap.c. This makes it possible to check for
ndo_xdp_xmit support before allocating the structure, which is not possible
at the time struct net_device is allocated. However, we keep the freeing in
free_netdev() to avoid adding another RCU callback on NETDEV_UNREGISTER.

Because of this change, we lose the reference back to the map that
originated the redirect, so change the tracepoint to always return 0 as the
map ID and index. Otherwise no functional change is intended with this
patch.

After this patch, the relevant part of struct net_device looks like this,
according to pahole:

	/* --- cacheline 14 boundary (896 bytes) --- */
	struct netdev_queue *      _tx __attribute__((__aligned__(64))); /*   896     8 */
	unsigned int               num_tx_queues;        /*   904     4 */
	unsigned int               real_num_tx_queues;   /*   908     4 */
	struct Qdisc *             qdisc;                /*   912     8 */
	unsigned int               tx_queue_len;         /*   920     4 */
	spinlock_t                 tx_global_lock;       /*   924     4 */
	struct xdp_dev_bulk_queue * xdp_bulkq;           /*   928     8 */
	struct xps_dev_maps *      xps_cpus_map;         /*   936     8 */
	struct xps_dev_maps *      xps_rxqs_map;         /*   944     8 */
	struct mini_Qdisc *        miniq_egress;         /*   952     8 */
	/* --- cacheline 15 boundary (960 bytes) --- */
	struct hlist_head  qdisc_hash[16];               /*   960   128 */
	/* --- cacheline 17 boundary (1088 bytes) --- */
	struct timer_list  watchdog_timer;               /*  1088    40 */

	/* XXX last struct has 4 bytes of padding */

	int                        watchdog_timeo;       /*  1128     4 */

	/* XXX 4 bytes hole, try to pack */

	struct list_head   todo_list;                    /*  1136    16 */
	/* --- cacheline 18 boundary (1152 bytes) --- */

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/157918768397.1458396.12673224324627072349.stgit@toke.dk

1 files changed, 8 insertions, 5 deletions

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;