Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:

 1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan.

 2) Support UDP segmentation in code TSO code, from Eric Dumazet.

 3) Allow flashing different flash images in cxgb4 driver, from Vishal
    Kulkarni.

 4) Add drop frames counter and flow status to tc flower offloading,
    from Po Liu.

 5) Support n-tuple filters in cxgb4, from Vishal Kulkarni.

 6) Various new indirect call avoidance, from Eric Dumazet and Brian
    Vazquez.

 7) Fix BPF verifier failures on 32-bit pointer arithmetic, from
    Yonghong Song.

 8) Support querying and setting hardware address of a port function via
    devlink, use this in mlx5, from Parav Pandit.

 9) Support hw ipsec offload on bonding slaves, from Jarod Wilson.

10) Switch qca8k driver over to phylink, from Jonathan McDowell.

11) In bpftool, show list of processes holding BPF FD references to
    maps, programs, links, and btf objects. From Andrii Nakryiko.

12) Several conversions over to generic power management, from Vaibhav
    Gupta.

13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry
    Yakunin.

14) Various https url conversions, from Alexander A. Klimov.

15) Timestamping and PHC support for mscc PHY driver, from Antoine
    Tenart.

16) Support bpf iterating over tcp and udp sockets, from Yonghong Song.

17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov.

18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan.

19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several
    drivers. From Luc Van Oostenryck.

20) XDP support for xen-netfront, from Denis Kirjanov.

21) Support receive buffer autotuning in MPTCP, from Florian Westphal.

22) Support EF100 chip in sfc driver, from Edward Cree.

23) Add XDP support to mvpp2 driver, from Matteo Croce.

24) Support MPTCP in sock_diag, from Paolo Abeni.

25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic
    infrastructure, from Jakub Kicinski.

26) Several pci_ --> dma_ API conversions, from Christophe JAILLET.

27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel.

28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki.

29) Refactor a lot of networking socket option handling code in order to
    avoid set_fs() calls, from Christoph Hellwig.

30) Add rfc4884 support to icmp code, from Willem de Bruijn.

31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei.

32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin.

33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin.

34) Support TCP syncookies in MPTCP, from Flowian Westphal.

35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano
    Brivio.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits)
  net: thunderx: initialize VF's mailbox mutex before first usage
  usb: hso: remove bogus check for EINPROGRESS
  usb: hso: no complaint about kmalloc failure
  hso: fix bailout in error case of probe
  ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM
  selftests/net: relax cpu affinity requirement in msg_zerocopy test
  mptcp: be careful on subflow creation
  selftests: rtnetlink: make kci_test_encap() return sub-test result
  selftests: rtnetlink: correct the final return value for the test
  net: dsa: sja1105: use detected device id instead of DT one on mismatch
  tipc: set ub->ifindex for local ipv6 address
  ipv6: add ipv6_dev_find()
  net: openvswitch: silence suspicious RCU usage warning
  Revert "vxlan: fix tos value before xmit"
  ptp: only allow phase values lower than 1 period
  farsync: switch from 'pci_' to 'dma_' API
  wan: wanxl: switch from 'pci_' to 'dma_' API
  hv_netvsc: do not use VF device if link is down
  dpaa2-eth: Fix passing zero to 'PTR_ERR' warning
  net: macb: Properly handle phylink on at91sam9x
  ...

1 files changed, 143 insertions, 27 deletions

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 27595fc6da56..f1c46529929b 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -52,7 +52,6 @@ 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;
@@ -62,10 +61,14 @@ 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 {
@@ -80,6 +83,7 @@ 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;
@@ -90,7 +94,9 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 
 	/* 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);
@@ -212,6 +218,8 @@ 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);
@@ -220,6 +228,75 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
 	}
 }
 
+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;
+
+	if (!rcpu->prog)
+		return n;
+
+	rcu_read_lock_bh();
+
+	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(act);
+			/* fallthrough */
+		case XDP_DROP:
+			xdp_return_frame(xdpf);
+			stats->drop++;
+			break;
+		}
+	}
+
+	if (stats->redirect)
+		xdp_do_flush_map();
+
+	xdp_clear_return_frame_no_direct();
+
+	rcu_read_unlock_bh(); /* resched point, may call do_softirq() */
+
+	return nframes;
+}
+
 #define CPUMAP_BATCH 8
 
 static int cpu_map_kthread_run(void *data)
@@ -234,11 +311,12 @@ static int cpu_map_kthread_run(void *data)
 	 * kthread_stop signal until queue is empty.
 	 */
 	while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
+		struct xdp_cpumap_stats stats = {}; /* zero stats */
+		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
 		unsigned int drops = 0, sched = 0;
 		void *frames[CPUMAP_BATCH];
 		void *skbs[CPUMAP_BATCH];
-		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
-		int i, n, m;
+		int i, n, m, nframes;
 
 		/* Release CPU reschedule checks */
 		if (__ptr_ring_empty(rcpu->queue)) {
@@ -259,8 +337,8 @@ 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);
-
+		n = __ptr_ring_consume_batched(rcpu->queue, frames,
+					       CPUMAP_BATCH);
 		for (i = 0; i < n; i++) {
 			void *f = frames[i];
 			struct page *page = virt_to_page(f);
@@ -272,15 +350,19 @@ 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_xdp(rcpu, frames, n, &stats);
+		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 */
+				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;
@@ -297,7 +379,7 @@ static int cpu_map_kthread_run(void *data)
 				drops++;
 		}
 		/* Feedback loop via tracepoint */
-		trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched);
+		trace_xdp_cpumap_kthread(rcpu->map_id, n, drops, sched, &stats);
 
 		local_bh_enable(); /* resched point, may call do_softirq() */
 	}
@@ -307,13 +389,38 @@ 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)
+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)
+{
+	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_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_cpumap_val *value, u32 cpu, int map_id)
+{
+	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);
@@ -338,19 +445,22 @@ static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
 	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->value.qsize  = value->qsize;
+
+	if (fd > 0 && __cpu_map_load_bpf_program(rcpu, 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);
 	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 */
@@ -361,6 +471,9 @@ 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:
@@ -437,12 +550,12 @@ 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;
@@ -450,18 +563,18 @@ 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 (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(&cpumap_value, key_cpu, map->id);
 		if (!rcpu)
 			return -ENOMEM;
 		rcpu->cmap = cmap;
@@ -523,7 +636,7 @@ 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)
@@ -543,6 +656,7 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
+static int cpu_map_btf_id;
 const struct bpf_map_ops cpu_map_ops = {
 	.map_alloc		= cpu_map_alloc,
 	.map_free		= cpu_map_free,
@@ -551,6 +665,8 @@ 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,
 };
 
 static int bq_flush_to_queue(struct xdp_bulk_queue *bq)