bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
To: netdev@vger.kernel.org
Cc: "Kumar Kartikeya Dwivedi" <memxor@gmail.com>,
	"Toke Høiland-Jørgensen" <toke@redhat.com>,
	"Alexei Starovoitov" <ast@kernel.org>,
	"Daniel Borkmann" <daniel@iogearbox.net>,
	"Andrii Nakryiko" <andrii@kernel.org>,
	"Jesper Dangaard Brouer" <brouer@redhat.com>,
	"David S. Miller" <davem@davemloft.net>,
	"Jakub Kicinski" <kuba@kernel.org>,
	"John Fastabend" <john.fastabend@gmail.com>,
	"Martin KaFai Lau" <kafai@fb.com>,
	bpf@vger.kernel.org
Subject: [PATCH net-next v5 4/5] bpf: devmap: implement devmap prog execution for generic XDP
Date: Thu,  1 Jul 2021 05:57:58 +0530	[thread overview]
Message-ID: <20210701002759.381983-5-memxor@gmail.com> (raw)
In-Reply-To: <20210701002759.381983-1-memxor@gmail.com>

This lifts the restriction on running devmap BPF progs in generic
redirect mode. To match native XDP behavior, it is invoked right before
generic_xdp_tx is called, and only supports XDP_PASS/XDP_ABORTED/
XDP_DROP actions.

We also return 0 even if devmap program drops the packet, as
semantically redirect has already succeeded and the devmap prog is the
last point before TX of the packet to device where it can deliver a
verdict on the packet.

This also means it must take care of freeing the skb, as
xdp_do_generic_redirect callers only do that in case an error is
returned.

Since devmap entry prog is supported, remove the check in
generic_xdp_install entirely.

Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
---
 include/linux/bpf.h |  1 -
 kernel/bpf/devmap.c | 49 ++++++++++++++++++++++++++++++++++++---------
 net/core/dev.c      | 18 -----------------
 3 files changed, 39 insertions(+), 29 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 095aaa104c56..4afbff308ca3 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1508,7 +1508,6 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
 			   struct bpf_prog *xdp_prog, struct bpf_map *map,
 			   bool exclude_ingress);
-bool dev_map_can_have_prog(struct bpf_map *map);
 
 void __cpu_map_flush(void);
 int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 2a75e6c2d27d..49f03e8e5561 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -318,16 +318,6 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,
 	return -ENOENT;
 }
 
-bool dev_map_can_have_prog(struct bpf_map *map)
-{
-	if ((map->map_type == BPF_MAP_TYPE_DEVMAP ||
-	     map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) &&
-	    map->value_size != offsetofend(struct bpf_devmap_val, ifindex))
-		return true;
-
-	return false;
-}
-
 static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,
 				struct xdp_frame **frames, int n,
 				struct net_device *dev)
@@ -499,6 +489,37 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
 	return 0;
 }
 
+static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst)
+{
+	struct xdp_txq_info txq = { .dev = dst->dev };
+	struct xdp_buff xdp;
+	u32 act;
+
+	if (!dst->xdp_prog)
+		return XDP_PASS;
+
+	__skb_pull(skb, skb->mac_len);
+	xdp.txq = &txq;
+
+	act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog);
+	switch (act) {
+	case XDP_PASS:
+		__skb_push(skb, skb->mac_len);
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		fallthrough;
+	case XDP_ABORTED:
+		trace_xdp_exception(dst->dev, dst->xdp_prog, act);
+		fallthrough;
+	case XDP_DROP:
+		kfree_skb(skb);
+		break;
+	}
+
+	return act;
+}
+
 int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
 		    struct net_device *dev_rx)
 {
@@ -614,6 +635,14 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 	err = xdp_ok_fwd_dev(dst->dev, skb->len);
 	if (unlikely(err))
 		return err;
+
+	/* Redirect has already succeeded semantically at this point, so we just
+	 * return 0 even if packet is dropped. Helper below takes care of
+	 * freeing skb.
+	 */
+	if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS)
+		return 0;
+
 	skb->dev = dst->dev;
 	generic_xdp_tx(skb, xdp_prog);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 8521936414f2..c674fe191e8a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5656,24 +5656,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 	struct bpf_prog *new = xdp->prog;
 	int ret = 0;
 
-	if (new) {
-		u32 i;
-
-		mutex_lock(&new->aux->used_maps_mutex);
-
-		/* generic XDP does not work with DEVMAPs that can
-		 * have a bpf_prog installed on an entry
-		 */
-		for (i = 0; i < new->aux->used_map_cnt; i++) {
-			if (dev_map_can_have_prog(new->aux->used_maps[i])) {
-				mutex_unlock(&new->aux->used_maps_mutex);
-				return -EINVAL;
-			}
-		}
-
-		mutex_unlock(&new->aux->used_maps_mutex);
-	}
-
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		rcu_assign_pointer(dev->xdp_prog, new);
-- 
2.31.1


  parent reply	other threads:[~2021-07-01  0:30 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-01  0:27 [PATCH net-next v5 0/5] Generic XDP improvements Kumar Kartikeya Dwivedi
2021-07-01  0:27 ` [PATCH net-next v5 1/5] net: core: split out code to run generic XDP prog Kumar Kartikeya Dwivedi
2021-07-01  0:27 ` [PATCH net-next v5 2/5] bitops: add non-atomic bitops for pointers Kumar Kartikeya Dwivedi
2021-07-01  0:27 ` [PATCH net-next v5 3/5] bpf: cpumap: implement generic cpumap Kumar Kartikeya Dwivedi
2021-07-01  9:16   ` Jesper Dangaard Brouer
2021-07-02 11:18     ` Kumar Kartikeya Dwivedi
2021-07-01  0:27 ` Kumar Kartikeya Dwivedi [this message]
2021-07-01  0:27 ` [PATCH net-next v5 5/5] bpf: tidy xdp attach selftests Kumar Kartikeya Dwivedi

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210701002759.381983-5-memxor@gmail.com \
    --to=memxor@gmail.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brouer@redhat.com \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=john.fastabend@gmail.com \
    --cc=kafai@fb.com \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=toke@redhat.com \
    --subject='Re: [PATCH net-next v5 4/5] bpf: devmap: implement devmap prog execution for generic XDP' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).