On Fri, 10 Jan 2020 at 15:22, Toke Høiland-Jørgensen <toke@xxxxxxxxxx> wrote:
>
> From: Toke Høiland-Jørgensen <toke@xxxxxxxxxx>
>
> Since the bulk queue used by XDP_REDIRECT now lives in struct net_device,
> we can re-use the bulking for the non-map version of the bpf_redirect()
> helper. This is a simple matter of having xdp_do_redirect_slow() queue the
> frame on the bulk queue instead of sending it out with __bpf_tx_xdp().
>
> Unfortunately we can't make the bpf_redirect() helper return an error if
> the ifindex doesn't exit (as bpf_redirect_map() does), because we don't
> have a reference to the network namespace of the ingress device at the time
> the helper is called. So we have to leave it as-is and keep the device
> lookup in xdp_do_redirect_slow().
>
> With this change, the performance of the xdp_redirect sample program goes
> from 5Mpps to 8.4Mpps (a 68% increase).
>
After these changes, does the noinline (commit 47b123ed9e99 ("xdp:
split code for map vs non-map redirect")) still make sense?
> Signed-off-by: Toke Høiland-Jørgensen <toke@xxxxxxxxxx>
> ---
> include/linux/bpf.h | 13 +++++++++++--
> kernel/bpf/devmap.c | 31 ++++++++++++++++++++++---------
> net/core/filter.c | 30 ++----------------------------
> 3 files changed, 35 insertions(+), 39 deletions(-)
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index b14e51d56a82..25c050202536 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -962,7 +962,9 @@ 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,
> @@ -1071,13 +1073,20 @@ 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)
> diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
> index bcb05cb6b728..adbb82770d02 100644
> --- a/kernel/bpf/devmap.c
> +++ b/kernel/bpf/devmap.c
> @@ -81,7 +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);
>
> @@ -357,16 +357,16 @@ static int bq_xmit_all(struct xdp_dev_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_map() 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 list_head *flush_list = this_cpu_ptr(&dev_flush_list);
> struct xdp_dev_bulk_queue *bq, *tmp;
>
> rcu_read_lock();
> @@ -398,7 +398,7 @@ 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 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))
> @@ -419,10 +419,9 @@ static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
> return 0;
> }
>
> -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
> - struct net_device *dev_rx)
> +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;
>
> @@ -440,6 +439,20 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
> 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);
> +}
> +
dev_xdp_enqueue, and dev_map_enqueue are *very* similar. Can these be
combined, and maybe fold the xdp_do_redirect_slow() into
xdp_do_direct_map? OTOH the TP are different, so maybe combining the
two functions will be messy... It's only that with your changes the
map/ifindex redirect are very similar. Just an idea, might be messy.
:-P
> +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,
> struct bpf_prog *xdp_prog)
> {
> @@ -760,7 +773,7 @@ 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;
> }
>
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 42fd17c48c5f..550488162fe1 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -3458,32 +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)
> @@ -3499,7 +3473,7 @@ xdp_do_redirect_slow(struct net_device *dev, struct xdp_buff *xdp,
> goto err;
> }
>
> - err = __bpf_tx_xdp(fwd, NULL, xdp, 0);
> + err = dev_xdp_enqueue(fwd, xdp, dev);
> if (unlikely(err))
> goto err;
>
> @@ -3529,7 +3503,7 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
>
> void xdp_do_flush_map(void)
> {
> - __dev_map_flush();
> + __dev_flush();
> __cpu_map_flush();
> __xsk_map_flush();
> }
>
