1 files changed, 273 insertions, 143 deletions

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 70f71b154fa5..b5ba34ddd4b6 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -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>
@@ -26,8 +27,9 @@
 #include <linux/kthread.h>
 #include <linux/capability.h>
 #include <trace/events/xdp.h>
+#include <linux/btf_ids.h>
 
-#include <linux/netdevice.h>   /* netif_receive_skb_core */
+#include <linux/netdevice.h>   /* netif_receive_skb_list */
 #include <linux/etherdevice.h> /* eth_type_trans */
 
 /* General idea: XDP packets getting XDP redirected to another CPU,
@@ -52,7 +54,6 @@ struct xdp_bulk_queue {
 struct bpf_cpu_map_entry {
 	u32 cpu;    /* kthread CPU and map index */
 	int map_id; /* Back reference to map */
-	u32 qsize;  /* Queue size placeholder for map lookup */
 
 	/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
 	struct xdp_bulk_queue __percpu *bulkq;
@@ -62,38 +63,41 @@ struct bpf_cpu_map_entry {
 	/* Queue with potential multi-producers, and single-consumer kthread */
 	struct ptr_ring *queue;
 	struct task_struct *kthread;
-	struct work_struct kthread_stop_wq;
+
+	struct bpf_cpumap_val value;
+	struct bpf_prog *prog;
 
 	atomic_t refcnt; /* Control when this struct can be free'ed */
 	struct rcu_head rcu;
+
+	struct work_struct kthread_stop_wq;
 };
 
 struct bpf_cpu_map {
 	struct bpf_map map;
 	/* Below members specific for map type */
-	struct bpf_cpu_map_entry **cpu_map;
+	struct bpf_cpu_map_entry __rcu **cpu_map;
 };
 
 static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list);
 
-static int bq_flush_to_queue(struct xdp_bulk_queue *bq);
-
 static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 {
+	u32 value_size = attr->value_size;
 	struct bpf_cpu_map *cmap;
 	int err = -ENOMEM;
-	u64 cost;
-	int ret;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!bpf_capable())
 		return ERR_PTR(-EPERM);
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+	    (value_size != offsetofend(struct bpf_cpumap_val, qsize) &&
+	     value_size != offsetofend(struct bpf_cpumap_val, bpf_prog.fd)) ||
+	    attr->map_flags & ~BPF_F_NUMA_NODE)
 		return ERR_PTR(-EINVAL);
 
-	cmap = kzalloc(sizeof(*cmap), GFP_USER);
+	cmap = bpf_map_area_alloc(sizeof(*cmap), NUMA_NO_NODE);
 	if (!cmap)
 		return ERR_PTR(-ENOMEM);
 
@@ -105,28 +109,16 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 		goto free_cmap;
 	}
 
-	/* make sure page count doesn't overflow */
-	cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *);
-
-	/* Notice returns -EPERM on if map size is larger than memlock limit */
-	ret = bpf_map_charge_init(&cmap->map.memory, cost);
-	if (ret) {
-		err = ret;
-		goto free_cmap;
-	}
-
 	/* Alloc array for possible remote "destination" CPUs */
 	cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries *
 					   sizeof(struct bpf_cpu_map_entry *),
 					   cmap->map.numa_node);
 	if (!cmap->cpu_map)
-		goto free_charge;
+		goto free_cmap;
 
 	return &cmap->map;
-free_charge:
-	bpf_map_charge_finish(&cmap->map.memory);
 free_cmap:
-	kfree(cmap);
+	bpf_map_area_free(cmap);
 	return ERR_PTR(err);
 }
 
@@ -151,65 +143,6 @@ static void cpu_map_kthread_stop(struct work_struct *work)
 	kthread_stop(rcpu->kthread);
 }
 
-static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
-					 struct xdp_frame *xdpf,
-					 struct sk_buff *skb)
-{
-	unsigned int hard_start_headroom;
-	unsigned int frame_size;
-	void *pkt_data_start;
-
-	/* Part of headroom was reserved to xdpf */
-	hard_start_headroom = sizeof(struct xdp_frame) +  xdpf->headroom;
-
-	/* build_skb need to place skb_shared_info after SKB end, and
-	 * also want to know the memory "truesize".  Thus, need to
-	 * know the memory frame size backing xdp_buff.
-	 *
-	 * XDP was designed to have PAGE_SIZE frames, but this
-	 * assumption is not longer true with ixgbe and i40e.  It
-	 * would be preferred to set frame_size to 2048 or 4096
-	 * depending on the driver.
-	 *   frame_size = 2048;
-	 *   frame_len  = frame_size - sizeof(*xdp_frame);
-	 *
-	 * Instead, with info avail, skb_shared_info in placed after
-	 * packet len.  This, unfortunately fakes the truesize.
-	 * Another disadvantage of this approach, the skb_shared_info
-	 * is not at a fixed memory location, with mixed length
-	 * packets, which is bad for cache-line hotness.
-	 */
-	frame_size = SKB_DATA_ALIGN(xdpf->len + hard_start_headroom) +
-		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-
-	pkt_data_start = xdpf->data - hard_start_headroom;
-	skb = build_skb_around(skb, pkt_data_start, frame_size);
-	if (unlikely(!skb))
-		return NULL;
-
-	skb_reserve(skb, hard_start_headroom);
-	__skb_put(skb, xdpf->len);
-	if (xdpf->metasize)
-		skb_metadata_set(skb, xdpf->metasize);
-
-	/* Essential SKB info: protocol and skb->dev */
-	skb->protocol = eth_type_trans(skb, xdpf->dev_rx);
-
-	/* Optional SKB info, currently missing:
-	 * - HW checksum info		(skb->ip_summed)
-	 * - HW RX hash			(skb_set_hash)
-	 * - RX ring dev queue index	(skb_record_rx_queue)
-	 */
-
-	/* Until page_pool get SKB return path, release DMA here */
-	xdp_release_frame(xdpf);
-
-	/* Allow SKB to reuse area used by xdp_frame */
-	xdp_scrub_frame(xdpf);
-
-	return skb;
-}
-
 static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
 {
 	/* The tear-down procedure should have made sure that queue is
@@ -227,6 +160,8 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
 static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
 {
 	if (atomic_dec_and_test(&rcpu->refcnt)) {
+		if (rcpu->prog)
+			bpf_prog_put(rcpu->prog);
 		/* The queue should be empty at this point */
 		__cpu_map_ring_cleanup(rcpu->queue);
 		ptr_ring_cleanup(rcpu->queue, NULL);
@@ -235,8 +170,132 @@ 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,
+				     struct list_head *listp,
+				     struct xdp_cpumap_stats *stats)
+{
+	struct sk_buff *skb, *tmp;
+	struct xdp_buff xdp;
+	u32 act;
+	int err;
+
+	list_for_each_entry_safe(skb, tmp, listp, list) {
+		act = bpf_prog_run_generic_xdp(skb, &xdp, rcpu->prog);
+		switch (act) {
+		case XDP_PASS:
+			break;
+		case XDP_REDIRECT:
+			skb_list_del_init(skb);
+			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(NULL, rcpu->prog, act);
+			fallthrough;
+		case XDP_ABORTED:
+			trace_xdp_exception(skb->dev, rcpu->prog, act);
+			fallthrough;
+		case XDP_DROP:
+			skb_list_del_init(skb);
+			kfree_skb(skb);
+			stats->drop++;
+			return;
+		}
+	}
+}
+
+static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
+				    void **frames, int n,
+				    struct xdp_cpumap_stats *stats)
+{
+	struct xdp_rxq_info rxq;
+	struct xdp_buff xdp;
+	int i, nframes = 0;
+
+	xdp_set_return_frame_no_direct();
+	xdp.rxq = &rxq;
+
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+		u32 act;
+		int err;
+
+		rxq.dev = xdpf->dev_rx;
+		rxq.mem = xdpf->mem;
+		/* TODO: report queue_index to xdp_rxq_info */
+
+		xdp_convert_frame_to_buff(xdpf, &xdp);
+
+		act = bpf_prog_run_xdp(rcpu->prog, &xdp);
+		switch (act) {
+		case XDP_PASS:
+			err = xdp_update_frame_from_buff(&xdp, xdpf);
+			if (err < 0) {
+				xdp_return_frame(xdpf);
+				stats->drop++;
+			} else {
+				frames[nframes++] = xdpf;
+				stats->pass++;
+			}
+			break;
+		case XDP_REDIRECT:
+			err = xdp_do_redirect(xdpf->dev_rx, &xdp,
+					      rcpu->prog);
+			if (unlikely(err)) {
+				xdp_return_frame(xdpf);
+				stats->drop++;
+			} else {
+				stats->redirect++;
+			}
+			break;
+		default:
+			bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act);
+			fallthrough;
+		case XDP_DROP:
+			xdp_return_frame(xdpf);
+			stats->drop++;
+			break;
+		}
+	}
+
+	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, struct xdp_cpumap_stats *stats,
+				struct list_head *list)
+{
+	int nframes;
+
+	if (!rcpu->prog)
+		return xdp_n;
+
+	rcu_read_lock_bh();
+
+	nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, xdp_n, stats);
+
+	if (stats->redirect)
+		xdp_do_flush();
+
+	if (unlikely(!list_empty(list)))
+		cpu_map_bpf_prog_run_skb(rcpu, list, stats);
+
+	rcu_read_unlock_bh(); /* resched point, may call do_softirq() */
+
+	return nframes;
+}
+
+
 static int cpu_map_kthread_run(void *data)
 {
 	struct bpf_cpu_map_entry *rcpu = data;
@@ -249,11 +308,13 @@ static int cpu_map_kthread_run(void *data)
 	 * kthread_stop signal until queue is empty.
 	 */
 	while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
-		unsigned int drops = 0, sched = 0;
+		struct xdp_cpumap_stats stats = {}; /* zero stats */
+		unsigned int kmem_alloc_drops = 0, sched = 0;
+		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
+		int i, n, m, nframes, xdp_n;
 		void *frames[CPUMAP_BATCH];
 		void *skbs[CPUMAP_BATCH];
-		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
-		int i, n, m;
+		LIST_HEAD(list);
 
 		/* Release CPU reschedule checks */
 		if (__ptr_ring_empty(rcpu->queue)) {
@@ -274,11 +335,22 @@ static int cpu_map_kthread_run(void *data)
 		 * kthread CPU pinned. Lockless access to ptr_ring
 		 * consume side valid as no-resize allowed of queue.
 		 */
-		n = ptr_ring_consume_batched(rcpu->queue, frames, CPUMAP_BATCH);
-
-		for (i = 0; i < n; i++) {
+		n = __ptr_ring_consume_batched(rcpu->queue, frames,
+					       CPUMAP_BATCH);
+		for (i = 0, xdp_n = 0; i < n; i++) {
 			void *f = frames[i];
-			struct page *page = virt_to_page(f);
+			struct page *page;
+
+			if (unlikely(__ptr_test_bit(0, &f))) {
+				struct sk_buff *skb = f;
+
+				__ptr_clear_bit(0, &skb);
+				list_add_tail(&skb->list, &list);
+				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
@@ -287,32 +359,36 @@ static int cpu_map_kthread_run(void *data)
 			prefetchw(page);
 		}
 
-		m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, n, skbs);
-		if (unlikely(m == 0)) {
-			for (i = 0; i < n; i++)
-				skbs[i] = NULL; /* effect: xdp_return_frame */
-			drops = n;
+		/* Support running another XDP prog on this CPU */
+		nframes = cpu_map_bpf_prog_run(rcpu, frames, xdp_n, &stats, &list);
+		if (nframes) {
+			m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs);
+			if (unlikely(m == 0)) {
+				for (i = 0; i < nframes; i++)
+					skbs[i] = NULL; /* effect: xdp_return_frame */
+				kmem_alloc_drops += nframes;
+			}
 		}
 
 		local_bh_disable();
-		for (i = 0; i < n; i++) {
+		for (i = 0; i < nframes; i++) {
 			struct xdp_frame *xdpf = frames[i];
 			struct sk_buff *skb = skbs[i];
-			int ret;
 
-			skb = cpu_map_build_skb(rcpu, xdpf, skb);
+			skb = __xdp_build_skb_from_frame(xdpf, skb,
+							 xdpf->dev_rx);
 			if (!skb) {
 				xdp_return_frame(xdpf);
 				continue;
 			}
 
-			/* Inject into network stack */
-			ret = netif_receive_skb_core(skb);
-			if (ret == NET_RX_DROP)
-				drops++;
+			list_add_tail(&skb->list, &list);
 		}
+		netif_receive_skb_list(&list);
+
 		/* Feedback loop via tracepoint */
-		trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched);
+		trace_xdp_cpumap_kthread(rcpu->map_id, n, kmem_alloc_drops,
+					 sched, &stats);
 
 		local_bh_enable(); /* resched point, may call do_softirq() */
 	}
@@ -322,24 +398,46 @@ static int cpu_map_kthread_run(void *data)
 	return 0;
 }
 
-static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
-						       int map_id)
+static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu,
+				      struct bpf_map *map, int fd)
 {
+	struct bpf_prog *prog;
+
+	prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	if (prog->expected_attach_type != BPF_XDP_CPUMAP ||
+	    !bpf_prog_map_compatible(map, prog)) {
+		bpf_prog_put(prog);
+		return -EINVAL;
+	}
+
+	rcpu->value.bpf_prog.id = prog->aux->id;
+	rcpu->prog = prog;
+
+	return 0;
+}
+
+static struct bpf_cpu_map_entry *
+__cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
+		      u32 cpu)
+{
+	int numa, err, i, fd = value->bpf_prog.fd;
 	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
 	struct bpf_cpu_map_entry *rcpu;
 	struct xdp_bulk_queue *bq;
-	int numa, err, i;
 
 	/* Have map->numa_node, but choose node of redirect target CPU */
 	numa = cpu_to_node(cpu);
 
-	rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa);
+	rcpu = bpf_map_kmalloc_node(map, sizeof(*rcpu), gfp | __GFP_ZERO, numa);
 	if (!rcpu)
 		return NULL;
 
 	/* Alloc percpu bulkq */
-	rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq),
-					 sizeof(void *), gfp);
+	rcpu->bulkq = bpf_map_alloc_percpu(map, sizeof(*rcpu->bulkq),
+					   sizeof(void *), gfp);
 	if (!rcpu->bulkq)
 		goto free_rcu;
 
@@ -349,23 +447,28 @@ static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
 	}
 
 	/* Alloc queue */
-	rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa);
+	rcpu->queue = bpf_map_kmalloc_node(map, sizeof(*rcpu->queue), gfp,
+					   numa);
 	if (!rcpu->queue)
 		goto free_bulkq;
 
-	err = ptr_ring_init(rcpu->queue, qsize, gfp);
+	err = ptr_ring_init(rcpu->queue, value->qsize, gfp);
 	if (err)
 		goto free_queue;
 
 	rcpu->cpu    = cpu;
-	rcpu->map_id = map_id;
-	rcpu->qsize  = qsize;
+	rcpu->map_id = map->id;
+	rcpu->value.qsize  = value->qsize;
+
+	if (fd > 0 && __cpu_map_load_bpf_program(rcpu, map, fd))
+		goto free_ptr_ring;
 
 	/* Setup kthread */
 	rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
-					       "cpumap/%d/map:%d", cpu, map_id);
+					       "cpumap/%d/map:%d", cpu,
+					       map->id);
 	if (IS_ERR(rcpu->kthread))
-		goto free_ptr_ring;
+		goto free_prog;
 
 	get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
 	get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */
@@ -376,6 +479,9 @@ static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
 
 	return rcpu;
 
+free_prog:
+	if (rcpu->prog)
+		bpf_prog_put(rcpu->prog);
 free_ptr_ring:
 	ptr_ring_cleanup(rcpu->queue, NULL);
 free_queue:
@@ -427,7 +533,7 @@ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
 {
 	struct bpf_cpu_map_entry *old_rcpu;
 
-	old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu);
+	old_rcpu = unrcu_pointer(xchg(&cmap->cpu_map[key_cpu], RCU_INITIALIZER(rcpu)));
 	if (old_rcpu) {
 		call_rcu(&old_rcpu->rcu, __cpu_map_entry_free);
 		INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop);
@@ -452,12 +558,12 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
 			       u64 map_flags)
 {
 	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+	struct bpf_cpumap_val cpumap_value = {};
 	struct bpf_cpu_map_entry *rcpu;
-
 	/* Array index key correspond to CPU number */
 	u32 key_cpu = *(u32 *)key;
-	/* Value is the queue size */
-	u32 qsize = *(u32 *)value;
+
+	memcpy(&cpumap_value, value, map->value_size);
 
 	if (unlikely(map_flags > BPF_EXIST))
 		return -EINVAL;
@@ -465,18 +571,18 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -E2BIG;
 	if (unlikely(map_flags == BPF_NOEXIST))
 		return -EEXIST;
-	if (unlikely(qsize > 16384)) /* sanity limit on qsize */
+	if (unlikely(cpumap_value.qsize > 16384)) /* sanity limit on qsize */
 		return -EOVERFLOW;
 
 	/* Make sure CPU is a valid possible cpu */
-	if (!cpu_possible(key_cpu))
+	if (key_cpu >= nr_cpumask_bits || !cpu_possible(key_cpu))
 		return -ENODEV;
 
-	if (qsize == 0) {
+	if (cpumap_value.qsize == 0) {
 		rcpu = NULL; /* Same as deleting */
 	} else {
 		/* Updating qsize cause re-allocation of bpf_cpu_map_entry */
-		rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id);
+		rcpu = __cpu_map_entry_alloc(map, &cpumap_value, key_cpu);
 		if (!rcpu)
 			return -ENOMEM;
 		rcpu->cmap = cmap;
@@ -501,7 +607,6 @@ static void cpu_map_free(struct bpf_map *map)
 	 * complete.
 	 */
 
-	bpf_clear_redirect_map(map);
 	synchronize_rcu();
 
 	/* For cpu_map the remote CPUs can still be using the entries
@@ -510,7 +615,7 @@ static void cpu_map_free(struct bpf_map *map)
 	for (i = 0; i < cmap->map.max_entries; i++) {
 		struct bpf_cpu_map_entry *rcpu;
 
-		rcpu = READ_ONCE(cmap->cpu_map[i]);
+		rcpu = rcu_dereference_raw(cmap->cpu_map[i]);
 		if (!rcpu)
 			continue;
 
@@ -518,10 +623,14 @@ static void cpu_map_free(struct bpf_map *map)
 		__cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
 	}
 	bpf_map_area_free(cmap->cpu_map);
-	kfree(cmap);
+	bpf_map_area_free(cmap);
 }
 
-struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
+/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
+ * by local_bh_disable() (from XDP calls inside NAPI). The
+ * rcu_read_lock_bh_held() below makes lockdep accept both.
+ */
+static void *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
 {
 	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
 	struct bpf_cpu_map_entry *rcpu;
@@ -529,7 +638,8 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
 	if (key >= map->max_entries)
 		return NULL;
 
-	rcpu = READ_ONCE(cmap->cpu_map[key]);
+	rcpu = rcu_dereference_check(cmap->cpu_map[key],
+				     rcu_read_lock_bh_held());
 	return rcpu;
 }
 
@@ -538,7 +648,7 @@ static void *cpu_map_lookup_elem(struct bpf_map *map, void *key)
 	struct bpf_cpu_map_entry *rcpu =
 		__cpu_map_lookup_elem(map, *(u32 *)key);
 
-	return rcpu ? &rcpu->qsize : NULL;
+	return rcpu ? &rcpu->value : NULL;
 }
 
 static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
@@ -558,7 +668,15 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
+static int cpu_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
+{
+	return __bpf_xdp_redirect_map(map, ifindex, flags, 0,
+				      __cpu_map_lookup_elem);
+}
+
+BTF_ID_LIST_SINGLE(cpu_map_btf_ids, struct, bpf_cpu_map)
 const struct bpf_map_ops cpu_map_ops = {
+	.map_meta_equal		= bpf_map_meta_equal,
 	.map_alloc		= cpu_map_alloc,
 	.map_free		= cpu_map_free,
 	.map_delete_elem	= cpu_map_delete_elem,
@@ -566,9 +684,11 @@ const struct bpf_map_ops cpu_map_ops = {
 	.map_lookup_elem	= cpu_map_lookup_elem,
 	.map_get_next_key	= cpu_map_get_next_key,
 	.map_check_btf		= map_check_no_btf,
+	.map_btf_id		= &cpu_map_btf_ids[0],
+	.map_redirect		= cpu_map_redirect,
 };
 
-static int bq_flush_to_queue(struct xdp_bulk_queue *bq)
+static void bq_flush_to_queue(struct xdp_bulk_queue *bq)
 {
 	struct bpf_cpu_map_entry *rcpu = bq->obj;
 	unsigned int processed = 0, drops = 0;
@@ -577,7 +697,7 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq)
 	int i;
 
 	if (unlikely(!bq->count))
-		return 0;
+		return;
 
 	q = rcpu->queue;
 	spin_lock(&q->producer_lock);
@@ -600,13 +720,12 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq)
 
 	/* Feedback loop via tracepoints */
 	trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu);
-	return 0;
 }
 
 /* Runs under RCU-read-side, plus in softirq under NAPI protection.
  * Thus, safe percpu variable access.
  */
-static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
+static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 {
 	struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list);
 	struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
@@ -627,19 +746,11 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 
 	if (!bq->flush_node.prev)
 		list_add(&bq->flush_node, flush_list);
-
-	return 0;
 }
 
-int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx)
 {
-	struct xdp_frame *xdpf;
-
-	xdpf = convert_to_xdp_frame(xdp);
-	if (unlikely(!xdpf))
-		return -EOVERFLOW;
-
 	/* Info needed when constructing SKB on remote CPU */
 	xdpf->dev_rx = dev_rx;
 
@@ -647,6 +758,25 @@ 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);
+	__ptr_set_bit(0, &skb);
+
+	ret = ptr_ring_produce(rcpu->queue, skb);
+	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);