netdev - [PATCH net-next v2 4/5] bpf: devmap: implement devmap prog execution for generic XDP

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20210622195527.1110497-5-memxor@gmail.com>
Date:   Wed, 23 Jun 2021 01:25:26 +0530
From:   Kumar Kartikeya Dwivedi <memxor@...il.com>
To:     netdev@...r.kernel.org
Cc:     Kumar Kartikeya Dwivedi <memxor@...il.com>,
        Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Andrii Nakryiko <andrii@...nel.org>,
        Toke Høiland-Jørgensen <toke@...hat.com>,
        Jesper Dangaard Brouer <brouer@...hat.com>,
        "David S. Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>,
        John Fastabend <john.fastabend@...il.com>,
        Martin KaFai Lau <kafai@...com>, bpf@...r.kernel.org
Subject: [PATCH net-next v2 4/5] bpf: devmap: implement devmap prog execution for generic XDP

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.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@...il.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 a00421e9ee16..9d9c78496459 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5633,24 +5633,6 @@ 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