xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths

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().

Since this leaves less reason to have the non-map redirect code in a
separate function, so we get rid of the xdp_do_redirect_slow() function
entirely. This does lose us the tracepoint disambiguation, but fortunately
the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint
entry structures. This means both can contain a map index, so we can just
amend the tracepoint definitions so we always emit the xdp_redirect(_err)
tracepoints, but with the map ID only populated if a map is present. This
means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep
the definitions around in case someone is still listening for them.

With this change, the performance of the xdp_redirect sample program goes
from 5Mpps to 8.4Mpps (a 68% increase).

Since the flush functions are no longer map-specific, rename the flush()
functions to drop _map from their names. One of the renamed functions is
the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To
keep from having to update all drivers, use a #define to keep the old name
working, and only update the virtual drivers in this patch.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk

1 files changed, 19 insertions, 71 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index d6f58dc4e1c4..17de6747d9e3 100644
--- a/net/core/filter.c
+++ b/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);
 
-	err = __bpf_tx_xdp_map(dev, fwd, map, xdp);
+	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 @@ err:
 	_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,