diff mbox series

[net-next,v3,4/5] bpf: devmap: implement devmap prog execution for generic XDP

Message ID 20210622202835.1151230-5-memxor@gmail.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series Generic XDP improvements | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for net-next
netdev/subject_prefix success Link
netdev/cc_maintainers warning 8 maintainers not CCed: yhs@fb.com hawk@kernel.org kpsingh@kernel.org ap420073@gmail.com songliubraving@fb.com alobakin@pm.me atenart@kernel.org weiwan@google.com
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 9849 this patch: 9849
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch warning WARNING: line length of 85 exceeds 80 columns
netdev/build_allmodconfig_warn success Errors and warnings before: 10257 this patch: 10257
netdev/header_inline success Link

Commit Message

Kumar Kartikeya Dwivedi June 22, 2021, 8:28 p.m. UTC
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@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 mbox series

Patch

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);