1 files changed, 235 insertions, 218 deletions

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 747313698178..774accbd4a22 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -4,30 +4,36 @@
  * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
  */
 
-/* The 'cpumap' is primarily used as a backend map for XDP BPF helper
+/**
+ * DOC: cpu map
+ * The 'cpumap' is primarily used as a backend map for XDP BPF helper
  * call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'.
  *
- * Unlike devmap which redirects XDP frames out another NIC device,
+ * Unlike devmap which redirects XDP frames out to another NIC device,
  * this map type redirects raw XDP frames to another CPU.  The remote
  * CPU will do SKB-allocation and call the normal network stack.
- *
+ */
+/*
  * This is a scalability and isolation mechanism, that allow
  * separating the early driver network XDP layer, from the rest of the
  * 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>
 #include <net/xdp.h>
+#include <net/hotdata.h>
 
 #include <linux/sched.h>
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
-#include <linux/capability.h>
+#include <linux/completion.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,
@@ -56,8 +62,6 @@ struct bpf_cpu_map_entry {
 	/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
 	struct xdp_bulk_queue __percpu *bulkq;
 
-	struct bpf_cpu_map *cmap;
-
 	/* Queue with potential multi-producers, and single-consumer kthread */
 	struct ptr_ring *queue;
 	struct task_struct *kthread;
@@ -65,28 +69,20 @@ struct bpf_cpu_map_entry {
 	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 completion kthread_running;
+	struct rcu_work free_work;
 };
 
 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 struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 {
 	u32 value_size = attr->value_size;
 	struct bpf_cpu_map *cmap;
-	int err = -ENOMEM;
-
-	if (!bpf_capable())
-		return ERR_PTR(-EPERM);
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
@@ -95,93 +91,26 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 	    attr->map_flags & ~BPF_F_NUMA_NODE)
 		return ERR_PTR(-EINVAL);
 
-	cmap = kzalloc(sizeof(*cmap), GFP_USER | __GFP_ACCOUNT);
+	/* Pre-limit array size based on NR_CPUS, not final CPU check */
+	if (attr->max_entries > NR_CPUS)
+		return ERR_PTR(-E2BIG);
+
+	cmap = bpf_map_area_alloc(sizeof(*cmap), NUMA_NO_NODE);
 	if (!cmap)
 		return ERR_PTR(-ENOMEM);
 
 	bpf_map_init_from_attr(&cmap->map, attr);
 
-	/* Pre-limit array size based on NR_CPUS, not final CPU check */
-	if (cmap->map.max_entries > NR_CPUS) {
-		err = -E2BIG;
-		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_cmap;
+	if (!cmap->cpu_map) {
+		bpf_map_area_free(cmap);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	return &cmap->map;
-free_cmap:
-	kfree(cmap);
-	return ERR_PTR(err);
-}
-
-static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
-{
-	atomic_inc(&rcpu->refcnt);
-}
-
-/* called from workqueue, to workaround syscall using preempt_disable */
-static void cpu_map_kthread_stop(struct work_struct *work)
-{
-	struct bpf_cpu_map_entry *rcpu;
-
-	rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
-
-	/* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
-	 * as it waits until all in-flight call_rcu() callbacks complete.
-	 */
-	rcu_barrier();
-
-	/* kthread_stop will wake_up_process and wait for it to complete */
-	kthread_stop(rcpu->kthread);
-}
-
-static struct sk_buff *cpu_map_build_skb(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;
-
-	/* Memory size backing xdp_frame data already have reserved
-	 * room for build_skb to place skb_shared_info in tailroom.
-	 */
-	frame_size = xdpf->frame_sz;
-
-	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)
@@ -191,23 +120,56 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
 	 * invoked cpu_map_kthread_stop(). Catch any broken behaviour
 	 * gracefully and warn once.
 	 */
-	struct xdp_frame *xdpf;
+	void *ptr;
 
-	while ((xdpf = ptr_ring_consume(ring)))
-		if (WARN_ON_ONCE(xdpf))
-			xdp_return_frame(xdpf);
+	while ((ptr = ptr_ring_consume(ring))) {
+		WARN_ON_ONCE(1);
+		if (unlikely(__ptr_test_bit(0, &ptr))) {
+			__ptr_clear_bit(0, &ptr);
+			kfree_skb(ptr);
+			continue;
+		}
+		xdp_return_frame(ptr);
+	}
 }
 
-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)
 {
-	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);
-		kfree(rcpu->queue);
-		kfree(rcpu);
+	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;
+		}
 	}
 }
 
@@ -215,15 +177,10 @@ 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_rxq_info rxq = {};
 	struct xdp_buff xdp;
 	int i, nframes = 0;
 
-	if (!rcpu->prog)
-		return n;
-
-	rcu_read_lock_bh();
-
 	xdp_set_return_frame_no_direct();
 	xdp.rxq = &rxq;
 
@@ -233,7 +190,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 		int err;
 
 		rxq.dev = xdpf->dev_rx;
-		rxq.mem = xdpf->mem;
+		rxq.mem.type = xdpf->mem_type;
 		/* TODO: report queue_index to xdp_rxq_info */
 
 		xdp_convert_frame_to_buff(xdpf, &xdp);
@@ -261,7 +218,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 			}
 			break;
 		default:
-			bpf_warn_invalid_xdp_action(act);
+			bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act);
 			fallthrough;
 		case XDP_DROP:
 			xdp_return_frame(xdpf);
@@ -270,22 +227,46 @@ 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, struct xdp_cpumap_stats *stats,
+				struct list_head *list)
+{
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
+	int nframes;
+
+	if (!rcpu->prog)
+		return xdp_n;
+
+	rcu_read_lock_bh();
+	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
+
+	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(!list_empty(list)))
+		cpu_map_bpf_prog_run_skb(rcpu, list, stats);
 
+	bpf_net_ctx_clear(bpf_net_ctx);
 	rcu_read_unlock_bh(); /* resched point, may call do_softirq() */
 
 	return nframes;
 }
 
-#define CPUMAP_BATCH 8
-
 static int cpu_map_kthread_run(void *data)
 {
 	struct bpf_cpu_map_entry *rcpu = data;
+	unsigned long last_qs = jiffies;
 
+	complete(&rcpu->kthread_running);
 	set_current_state(TASK_INTERRUPTIBLE);
 
 	/* When kthread gives stop order, then rcpu have been disconnected
@@ -295,11 +276,12 @@ static int cpu_map_kthread_run(void *data)
 	 */
 	while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
 		struct xdp_cpumap_stats stats = {}; /* zero stats */
+		unsigned int kmem_alloc_drops = 0, sched = 0;
 		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
-		unsigned int drops = 0, sched = 0;
+		int i, n, m, nframes, xdp_n;
 		void *frames[CPUMAP_BATCH];
 		void *skbs[CPUMAP_BATCH];
-		int i, n, m, nframes;
+		LIST_HEAD(list);
 
 		/* Release CPU reschedule checks */
 		if (__ptr_ring_empty(rcpu->queue)) {
@@ -308,10 +290,12 @@ static int cpu_map_kthread_run(void *data)
 			if (__ptr_ring_empty(rcpu->queue)) {
 				schedule();
 				sched = 1;
+				last_qs = jiffies;
 			} else {
 				__set_current_state(TASK_RUNNING);
 			}
 		} else {
+			rcu_softirq_qs_periodic(last_qs);
 			sched = cond_resched();
 		}
 
@@ -322,9 +306,20 @@ 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; 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
@@ -334,13 +329,14 @@ 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, &stats, &list);
 		if (nframes) {
-			m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs);
+			m = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
+						  gfp, nframes, skbs);
 			if (unlikely(m == 0)) {
 				for (i = 0; i < nframes; i++)
 					skbs[i] = NULL; /* effect: xdp_return_frame */
-				drops += nframes;
+				kmem_alloc_drops += nframes;
 			}
 		}
 
@@ -348,37 +344,33 @@ static int cpu_map_kthread_run(void *data)
 		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(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);
 		}
-		/* Feedback loop via tracepoint */
-		trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched, &stats);
 
+		/* Feedback loop via tracepoint.
+		 * NB: keep before recv to allow measuring enqueue/dequeue latency.
+		 */
+		trace_xdp_cpumap_kthread(rcpu->map_id, n, kmem_alloc_drops,
+					 sched, &stats);
+
+		netif_receive_skb_list(&list);
 		local_bh_enable(); /* resched point, may call do_softirq() */
 	}
 	__set_current_state(TASK_RUNNING);
 
-	put_cpu_map_entry(rcpu);
 	return 0;
 }
 
-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);
-}
-
-static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)
+static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu,
+				      struct bpf_map *map, int fd)
 {
 	struct bpf_prog *prog;
 
@@ -386,7 +378,8 @@ static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	if (prog->expected_attach_type != BPF_XDP_CPUMAP) {
+	if (prog->expected_attach_type != BPF_XDP_CPUMAP ||
+	    !bpf_prog_map_compatible(map, prog)) {
 		bpf_prog_put(prog);
 		return -EINVAL;
 	}
@@ -438,23 +431,27 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
 	rcpu->map_id = map->id;
 	rcpu->value.qsize  = value->qsize;
 
-	if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd))
+	if (fd > 0 && __cpu_map_load_bpf_program(rcpu, map, fd))
 		goto free_ptr_ring;
 
 	/* Setup kthread */
+	init_completion(&rcpu->kthread_running);
 	rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
 					       "cpumap/%d/map:%d", cpu,
 					       map->id);
 	if (IS_ERR(rcpu->kthread))
 		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 */
-
 	/* Make sure kthread runs on a single CPU */
 	kthread_bind(rcpu->kthread, cpu);
 	wake_up_process(rcpu->kthread);
 
+	/* Make sure kthread has been running, so kthread_stop() will not
+	 * stop the kthread prematurely and all pending frames or skbs
+	 * will be handled by the kthread before kthread_stop() returns.
+	 */
+	wait_for_completion(&rcpu->kthread_running);
+
 	return rcpu;
 
 free_prog:
@@ -471,55 +468,54 @@ free_rcu:
 	return NULL;
 }
 
-static void __cpu_map_entry_free(struct rcu_head *rcu)
+static void __cpu_map_entry_free(struct work_struct *work)
 {
 	struct bpf_cpu_map_entry *rcpu;
 
 	/* This cpu_map_entry have been disconnected from map and one
-	 * RCU grace-period have elapsed.  Thus, XDP cannot queue any
+	 * RCU grace-period have elapsed. Thus, XDP cannot queue any
 	 * new packets and cannot change/set flush_needed that can
 	 * find this entry.
 	 */
-	rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu);
+	rcpu = container_of(to_rcu_work(work), struct bpf_cpu_map_entry, free_work);
 
+	/* kthread_stop will wake_up_process and wait for it to complete.
+	 * cpu_map_kthread_run() makes sure the pointer ring is empty
+	 * before exiting.
+	 */
+	kthread_stop(rcpu->kthread);
+
+	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);
+	kfree(rcpu->queue);
 	free_percpu(rcpu->bulkq);
-	/* Cannot kthread_stop() here, last put free rcpu resources */
-	put_cpu_map_entry(rcpu);
+	kfree(rcpu);
 }
 
-/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to
- * ensure any driver rcu critical sections have completed, but this
- * does not guarantee a flush has happened yet. Because driver side
- * rcu_read_lock/unlock only protects the running XDP program.  The
- * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a
- * pending flush op doesn't fail.
- *
- * The bpf_cpu_map_entry is still used by the kthread, and there can
- * still be pending packets (in queue and percpu bulkq).  A refcnt
- * makes sure to last user (kthread_stop vs. call_rcu) free memory
- * resources.
- *
- * The rcu callback __cpu_map_entry_free flush remaining packets in
- * percpu bulkq to queue.  Due to caller map_delete_elem() disable
- * preemption, cannot call kthread_stop() to make sure queue is empty.
- * Instead a work_queue is started for stopping kthread,
- * cpu_map_kthread_stop, which waits for an RCU grace period before
- * stopping kthread, emptying the queue.
+/* After the xchg of the bpf_cpu_map_entry pointer, we need to make sure the old
+ * entry is no longer in use before freeing. We use queue_rcu_work() to call
+ * __cpu_map_entry_free() in a separate workqueue after waiting for an RCU grace
+ * period. This means that (a) all pending enqueue and flush operations have
+ * completed (because of the RCU callback), and (b) we are in a workqueue
+ * context where we can stop the kthread and wait for it to exit before freeing
+ * everything.
  */
 static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
 				    u32 key_cpu, struct bpf_cpu_map_entry *rcpu)
 {
 	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);
-		schedule_work(&old_rcpu->kthread_stop_wq);
+		INIT_RCU_WORK(&old_rcpu->free_work, __cpu_map_entry_free);
+		queue_rcu_work(system_wq, &old_rcpu->free_work);
 	}
 }
 
-static int cpu_map_delete_elem(struct bpf_map *map, void *key)
+static long cpu_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
 	u32 key_cpu = *(u32 *)key;
@@ -527,13 +523,13 @@ static int cpu_map_delete_elem(struct bpf_map *map, void *key)
 	if (key_cpu >= map->max_entries)
 		return -EINVAL;
 
-	/* notice caller map_delete_elem() use preempt_disable() */
+	/* notice caller map_delete_elem() uses rcu_read_lock() */
 	__cpu_map_entry_replace(cmap, key_cpu, NULL);
 	return 0;
 }
 
-static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
-			       u64 map_flags)
+static long 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 = {};
@@ -563,7 +559,6 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
 		rcpu = __cpu_map_entry_alloc(map, &cpumap_value, key_cpu);
 		if (!rcpu)
 			return -ENOMEM;
-		rcpu->cmap = cmap;
 	}
 	rcu_read_lock();
 	__cpu_map_entry_replace(cmap, key_cpu, rcpu);
@@ -579,33 +574,35 @@ static void cpu_map_free(struct bpf_map *map)
 	/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
 	 * so the bpf programs (can be more than one that used this map) were
 	 * disconnected from events. Wait for outstanding critical sections in
-	 * these programs to complete. The rcu critical section only guarantees
-	 * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map.
-	 * It does __not__ ensure pending flush operations (if any) are
-	 * complete.
+	 * these programs to complete. synchronize_rcu() below not only
+	 * guarantees no further "XDP/bpf-side" reads against
+	 * bpf_cpu_map->cpu_map, but also ensure pending flush operations
+	 * (if any) are completed.
 	 */
-
-	bpf_clear_redirect_map(map);
 	synchronize_rcu();
 
-	/* For cpu_map the remote CPUs can still be using the entries
-	 * (struct bpf_cpu_map_entry).
+	/* The only possible user of bpf_cpu_map_entry is
+	 * cpu_map_kthread_run().
 	 */
 	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;
 
-		/* bq flush and cleanup happens after RCU grace-period */
-		__cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
+		/* Stop kthread and cleanup entry directly */
+		__cpu_map_entry_free(&rcpu->free_work.work);
 	}
 	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;
@@ -613,7 +610,8 @@ 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;
 }
 
@@ -642,7 +640,22 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
-static int cpu_map_btf_id;
+static long cpu_map_redirect(struct bpf_map *map, u64 index, u64 flags)
+{
+	return __bpf_xdp_redirect_map(map, index, flags, 0,
+				      __cpu_map_lookup_elem);
+}
+
+static u64 cpu_map_mem_usage(const struct bpf_map *map)
+{
+	u64 usage = sizeof(struct bpf_cpu_map);
+
+	/* Currently the dynamically allocated elements are not counted */
+	usage += (u64)map->max_entries * sizeof(struct bpf_cpu_map_entry *);
+	return usage;
+}
+
+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,
@@ -652,8 +665,9 @@ 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_name		= "bpf_cpu_map",
-	.map_btf_id		= &cpu_map_btf_id,
+	.map_mem_usage		= cpu_map_mem_usage,
+	.map_btf_id		= &cpu_map_btf_ids[0],
+	.map_redirect		= cpu_map_redirect,
 };
 
 static void bq_flush_to_queue(struct xdp_bulk_queue *bq)
@@ -695,7 +709,6 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq)
  */
 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);
 
 	if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
@@ -712,19 +725,16 @@ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 	 */
 	bq->q[bq->count++] = xdpf;
 
-	if (!bq->flush_node.prev)
+	if (!bq->flush_node.prev) {
+		struct list_head *flush_list = bpf_net_ctx_get_cpu_map_flush_list();
+
 		list_add(&bq->flush_node, flush_list);
+	}
 }
 
-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 = xdp_convert_buff_to_frame(xdp);
-	if (unlikely(!xdpf))
-		return -EOVERFLOW;
-
 	/* Info needed when constructing SKB on remote CPU */
 	xdpf->dev_rx = dev_rx;
 
@@ -732,9 +742,27 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
 	return 0;
 }
 
-void __cpu_map_flush(void)
+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(struct list_head *flush_list)
 {
-	struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list);
 	struct xdp_bulk_queue *bq, *tmp;
 
 	list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
@@ -744,14 +772,3 @@ void __cpu_map_flush(void)
 		wake_up_process(bq->obj->kthread);
 	}
 }
-
-static int __init cpu_map_init(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		INIT_LIST_HEAD(&per_cpu(cpu_map_flush_list, cpu));
-	return 0;
-}
-
-subsys_initcall(cpu_map_init);