[PATCH net-next 0/4] Generic XDP improvements

@@ -3984,6 +3984,8 @@ static inline void dev_consume_skb_any(struct sk_buff *skb)
 	__dev_kfree_skb_any(skb, SKB_REASON_CONSUMED);
 }

+u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
+			     struct bpf_prog *xdp_prog);
 void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog);
 int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
 int netif_rx(struct sk_buff *skb);

@@ -4717,44 +4717,17 @@ static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb)
 	return rxqueue;
 }

-static u32 netif_receive_generic_xdp(struct sk_buff *skb,
-				     struct xdp_buff *xdp,
-				     struct bpf_prog *xdp_prog)
+u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
+			     struct bpf_prog *xdp_prog)
 {
 	void *orig_data, *orig_data_end, *hard_start;
 	struct netdev_rx_queue *rxqueue;
-	u32 metalen, act = XDP_DROP;
 	bool orig_bcast, orig_host;
 	u32 mac_len, frame_sz;
 	__be16 orig_eth_type;
 	struct ethhdr *eth;
-	int off;
-
-	/* Reinjected packets coming from act_mirred or similar should
-	 * not get XDP generic processing.
-	 */
-	if (skb_is_redirected(skb))
-		return XDP_PASS;
-
-	/* XDP packets must be linear and must have sufficient headroom
-	 * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
-	 * native XDP provides, thus we need to do it here as well.
-	 */
-	if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
-	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
-		int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
-		int troom = skb->tail + skb->data_len - skb->end;
-
-		/* In case we have to go down the path and also linearize,
-		 * then lets do the pskb_expand_head() work just once here.
-		 */
-		if (pskb_expand_head(skb,
-				     hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
-				     troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
-			goto do_drop;
-		if (skb_linearize(skb))
-			goto do_drop;
-	}
+	u32 act = XDP_DROP;
+	int off, metalen;

 	/* The XDP program wants to see the packet starting at the MAC
 	 * header.

@@ -4810,6 +4783,13 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 		skb->protocol = eth_type_trans(skb, skb->dev);
 	}

+	/* Redirect/Tx gives L2 packet, code that will reuse skb must __skb_pull
+	 * before calling us again on redirect path. We do not call do_redirect
+	 * as we leave that up to the caller.
+	 *
+	 * Caller is responsible for managing lifetime of skb (i.e. calling
+	 * kfree_skb in response to actions it cannot handle/XDP_DROP).
+	 */
 	switch (act) {
 	case XDP_REDIRECT:
 	case XDP_TX:

@@ -4820,6 +4800,49 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 		if (metalen)
 			skb_metadata_set(skb, metalen);
 		break;
+	}
+
+	return act;
+}
+
+static u32 netif_receive_generic_xdp(struct sk_buff *skb,
+				     struct xdp_buff *xdp,
+				     struct bpf_prog *xdp_prog)
+{
+	u32 act = XDP_DROP;
+
+	/* Reinjected packets coming from act_mirred or similar should
+	 * not get XDP generic processing.
+	 */
+	if (skb_is_redirected(skb))
+		return XDP_PASS;
+
+	/* XDP packets must be linear and must have sufficient headroom
+	 * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
+	 * native XDP provides, thus we need to do it here as well.
+	 */
+	if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
+	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
+		int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
+		int troom = skb->tail + skb->data_len - skb->end;
+
+		/* In case we have to go down the path and also linearize,
+		 * then lets do the pskb_expand_head() work just once here.
+		 */
+		if (pskb_expand_head(skb,
+				     hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
+				     troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
+			goto do_drop;
+		if (skb_linearize(skb))
+			goto do_drop;
+	}
+
+	act = bpf_prog_run_generic_xdp(skb, xdp, xdp_prog);
+	switch (act) {
+	case XDP_REDIRECT:
+	case XDP_TX:
+	case XDP_PASS:
+		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 		fallthrough;

@@ -5285,7 +5308,6 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 			ret = NET_RX_DROP;
 			goto out;
 		}
-		skb_reset_mac_len(skb);
 	}

 	if (eth_type_vlan(skb->protocol)) {
--

@@ -1513,6 +1513,8 @@ 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,
 		    struct net_device *dev_rx);
+int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu,
+			     struct sk_buff *skb);
 bool cpu_map_prog_allowed(struct bpf_map *map);
 
 /* Return map's numa specified by userspace */

@@ -1710,6 +1712,12 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
 	return 0;
 }
 
+static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu,
+					   struct sk_buff *skb)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline bool cpu_map_prog_allowed(struct bpf_map *map)
 {
 	return false;

@@ -863,8 +863,8 @@ struct sk_buff {
 	__u8			tc_skip_classify:1;
 	__u8			tc_at_ingress:1;
 #endif
-#ifdef CONFIG_NET_REDIRECT
 	__u8			redirected:1;
+#ifdef CONFIG_NET_REDIRECT
 	__u8			from_ingress:1;
 #endif
 #ifdef CONFIG_TLS_DEVICE

@@ -4664,17 +4664,13 @@ static inline __wsum lco_csum(struct sk_buff *skb)
 
 static inline bool skb_is_redirected(const struct sk_buff *skb)
 {
-#ifdef CONFIG_NET_REDIRECT
 	return skb->redirected;
-#else
-	return false;
-#endif
 }
 
 static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress)
 {
-#ifdef CONFIG_NET_REDIRECT
 	skb->redirected = 1;
+#ifdef CONFIG_NET_REDIRECT
 	skb->from_ingress = from_ingress;
 	if (skb->from_ingress)
 		skb->tstamp = 0;

@@ -4683,9 +4679,7 @@ static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress)
 
 static inline void skb_reset_redirect(struct sk_buff *skb)
 {
-#ifdef CONFIG_NET_REDIRECT
 	skb->redirected = 0;
-#endif
 }
 
 static inline bool skb_csum_is_sctp(struct sk_buff *skb)

@@ -16,6 +16,7 @@
  * netstack, and assigning dedicated CPUs for this stage.  This
  * basically allows for 10G wirespeed pre-filtering via bpf.
  */
+#include <linux/bitops.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/ptr_ring.h>

@@ -79,6 +80,29 @@ struct bpf_cpu_map {
 
 static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list);
 
+static void *__ptr_set_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr |= BIT(bit);
+	return (void *)__ptr;
+}
+
+static void *__ptr_clear_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr &= ~BIT(bit);
+	return (void *)__ptr;
+}
+
+static int __ptr_test_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	return __ptr & BIT(bit);
+}
+
 static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 {
 	u32 value_size = attr->value_size;

@@ -168,6 +192,64 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
 	}
 }
 
+static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
+				    void **frames, int skb_n,
+				    struct xdp_cpumap_stats *stats,
+				    struct list_head *listp)
+{
+	struct xdp_rxq_info rxq = {};
+	struct xdp_buff xdp;
+	int err, i;
+	u32 act;
+
+	xdp.rxq = &rxq;
+
+	if (!rcpu->prog)
+		goto insert;
+
+	for (i = 0; i < skb_n; i++) {
+		struct sk_buff *skb = frames[i];
+
+		rxq.dev = skb->dev;
+
+		act = bpf_prog_run_generic_xdp(skb, &xdp, rcpu->prog);
+		switch (act) {
+		case XDP_PASS:
+			list_add_tail(&skb->list, listp);
+			break;
+		case XDP_REDIRECT:
+			err = xdp_do_generic_redirect(skb->dev, skb, &xdp,
+						      rcpu->prog);
+			if (unlikely(err)) {
+				kfree_skb(skb);
+				stats->drop++;
+			} else {
+				stats->redirect++;
+			}
+			return;
+		default:
+			bpf_warn_invalid_xdp_action(act);
+			fallthrough;
+		case XDP_ABORTED:
+			trace_xdp_exception(skb->dev, rcpu->prog, act);
+			fallthrough;
+		case XDP_DROP:
+			kfree_skb(skb);
+			stats->drop++;
+			return;
+		}
+	}
+
+	return;
+
+insert:
+	for (i = 0; i < skb_n; i++) {
+		struct sk_buff *skb = frames[i];
+
+		list_add_tail(&skb->list, listp);
+	}
+}
+
 static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 				    void **frames, int n,
 				    struct xdp_cpumap_stats *stats)

@@ -179,8 +261,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 	if (!rcpu->prog)
 		return n;
 
-	rcu_read_lock_bh();
-
 	xdp_set_return_frame_no_direct();
 	xdp.rxq = &rxq;
 

@@ -227,17 +307,36 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 		}
 	}
 
+	xdp_clear_return_frame_no_direct();
+
+	return nframes;
+}
+
+#define CPUMAP_BATCH 8
+
+static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu,
+				void **frames, int xdp_n, int skb_n,
+				struct xdp_cpumap_stats *stats,
+				struct list_head *list)
+{
+	int nframes;
+
+	rcu_read_lock_bh();
+
+	nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, xdp_n, stats);
+
 	if (stats->redirect)
-		xdp_do_flush_map();
+		xdp_do_flush();
 
-	xdp_clear_return_frame_no_direct();
+	if (unlikely(skb_n))
+		cpu_map_bpf_prog_run_skb(rcpu, frames + CPUMAP_BATCH, skb_n,
+					 stats, list);
 
-	rcu_read_unlock_bh(); /* resched point, may call do_softirq() */
+	rcu_read_unlock_bh();
 
 	return nframes;
 }
 
-#define CPUMAP_BATCH 8
 
 static int cpu_map_kthread_run(void *data)
 {

@@ -254,9 +353,9 @@ static int cpu_map_kthread_run(void *data)
 		struct xdp_cpumap_stats stats = {}; /* zero stats */
 		unsigned int kmem_alloc_drops = 0, sched = 0;
 		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
-		void *frames[CPUMAP_BATCH];
+		int i, n, m, nframes, xdp_n, skb_n;
+		void *frames[CPUMAP_BATCH * 2];
 		void *skbs[CPUMAP_BATCH];
-		int i, n, m, nframes;
 		LIST_HEAD(list);
 
 		/* Release CPU reschedule checks */

@@ -280,9 +379,17 @@ static int cpu_map_kthread_run(void *data)
 		 */
 		n = __ptr_ring_consume_batched(rcpu->queue, frames,
 					       CPUMAP_BATCH);
-		for (i = 0; i < n; i++) {
+		for (i = 0, xdp_n = 0, skb_n = 0; i < n; i++) {
 			void *f = frames[i];
-			struct page *page = virt_to_page(f);
+			struct page *page;
+
+			if (unlikely(__ptr_test_bit(f, 0))) {
+				frames[CPUMAP_BATCH + skb_n++] = __ptr_clear_bit(f, 0);
+				continue;
+			}
+
+			frames[xdp_n++] = f;
+			page = virt_to_page(f);
 
 			/* Bring struct page memory area to curr CPU. Read by
 			 * build_skb_around via page_is_pfmemalloc(), and when

@@ -292,7 +399,7 @@ static int cpu_map_kthread_run(void *data)
 		}
 
 		/* Support running another XDP prog on this CPU */
-		nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, n, &stats);
+		nframes = cpu_map_bpf_prog_run(rcpu, frames, xdp_n, skb_n, &stats, &list);
 		if (nframes) {
 			m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs);
 			if (unlikely(m == 0)) {

@@ -316,6 +423,7 @@ static int cpu_map_kthread_run(void *data)
 
 			list_add_tail(&skb->list, &list);
 		}
+
 		netif_receive_skb_list(&list);
 
 		/* Feedback loop via tracepoint */

@@ -333,7 +441,8 @@ static int cpu_map_kthread_run(void *data)
 bool cpu_map_prog_allowed(struct bpf_map *map)
 {
 	return map->map_type == BPF_MAP_TYPE_CPUMAP &&
-	       map->value_size != offsetofend(struct bpf_cpumap_val, qsize);
+	       map->value_size != offsetofend(struct bpf_cpumap_val, qsize) &&
+	       map->value_size != offsetofend(struct bpf_cpumap_val, bpf_prog.fd);
 }
 
 static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)

@@ -696,6 +805,24 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
 	return 0;
 }
 
+int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu,
+			     struct sk_buff *skb)
+{
+	int ret;
+
+	__skb_pull(skb, skb->mac_len);
+	skb_set_redirected(skb, false);
+
+	ret = ptr_ring_produce(rcpu->queue, __ptr_set_bit(skb, 0));
+	if (ret < 0)
+		goto trace;
+
+	wake_up_process(rcpu->kthread);
+trace:
+	trace_xdp_cpumap_enqueue(rcpu->map_id, !ret, !!ret, rcpu->cpu);
+	return ret;
+}
+
 void __cpu_map_flush(void)
 {
 	struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list);

@@ -4038,8 +4038,12 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 			goto err;
 		consume_skb(skb);
 		break;
+	case BPF_MAP_TYPE_CPUMAP:
+		err = cpu_map_generic_redirect(fwd, skb);
+		if (unlikely(err))
+			goto err;
+		break;
 	default:
-		/* TODO: Handle BPF_MAP_TYPE_CPUMAP */
 		err = -EBADRQC;
 		goto err;
 	}

@@ -322,7 +322,8 @@ 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))
+	    map->value_size != offsetofend(struct bpf_devmap_val, ifindex) &&
+	    map->value_size != offsetofend(struct bpf_devmap_val, bpf_prog.fd))
 		return true;
 
 	return false;

@@ -499,6 +500,37 @@ 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_prog *xdp_prog)
+{
+	struct xdp_txq_info txq = { .dev = skb->dev };
+	struct xdp_buff xdp;
+	u32 act;
+
+	if (!xdp_prog)
+		return XDP_PASS;
+
+	__skb_pull(skb, skb->mac_len);
+	xdp.txq = &txq;
+
+	act = bpf_prog_run_generic_xdp(skb, &xdp, 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(skb->dev, 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)
 {

@@ -615,6 +647,14 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 	if (unlikely(err))
 		return err;
 	skb->dev = dst->dev;
+
+	/* 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_prog) != XDP_PASS)
+		return 0;
+
 	generic_xdp_tx(skb, xdp_prog);
 
 	return 0;

@@ -29,8 +29,8 @@ void test_xdp_with_cpumap_helpers(void)
 	 */
 	prog_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
 	err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE);
-	CHECK(err == 0, "Generic attach of program with 8-byte CPUMAP",
-	      "should have failed\n");
+	CHECK(err, "Generic attach of program with 8-byte CPUMAP",
+	      "shouldn't have failed\n");
 
 	prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm);
 	map_fd = bpf_map__fd(skel->maps.cpu_map);

@@ -31,8 +31,8 @@ void test_xdp_with_devmap_helpers(void)
 	 */
 	dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
 	err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE);
-	CHECK(err == 0, "Generic attach of program with 8-byte devmap",
-	      "should have failed\n");
+	CHECK(err, "Generic attach of program with 8-byte devmap",
+	      "shouldn't have failed\n");
 
 	dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm);
 	map_fd = bpf_map__fd(skel->maps.dm_ports);