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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 57 insertions, 67 deletions

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index cd8297b3bdb9..d83cf8ccc872 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -17,9 +17,8 @@
  * datapath always has a valid copy. However, the datapath does a "flush"
  * operation that pushes any pending packets in the driver outside the RCU
  * critical section. Each bpf_dtab_netdev tracks these pending operations using
- * an atomic per-cpu bitmap. The bpf_dtab_netdev object will not be destroyed
- * until all bits are cleared indicating outstanding flush operations have
- * completed.
+ * a per-cpu flush list. The bpf_dtab_netdev object will not be destroyed  until
+ * this list is empty, indicating outstanding flush operations have completed.
  *
  * BPF syscalls may race with BPF program calls on any of the update, delete
  * or lookup operations. As noted above the xchg() operation also keep the
@@ -48,9 +47,13 @@
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
 
 #define DEV_MAP_BULK_SIZE 16
+struct bpf_dtab_netdev;
+
 struct xdp_bulk_queue {
 	struct xdp_frame *q[DEV_MAP_BULK_SIZE];
+	struct list_head flush_node;
 	struct net_device *dev_rx;
+	struct bpf_dtab_netdev *obj;
 	unsigned int count;
 };
 
@@ -65,22 +68,17 @@ struct bpf_dtab_netdev {
 struct bpf_dtab {
 	struct bpf_map map;
 	struct bpf_dtab_netdev **netdev_map;
-	unsigned long __percpu *flush_needed;
+	struct list_head __percpu *flush_list;
 	struct list_head list;
 };
 
 static DEFINE_SPINLOCK(dev_map_lock);
 static LIST_HEAD(dev_map_list);
 
-static u64 dev_map_bitmap_size(const union bpf_attr *attr)
-{
-	return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long);
-}
-
 static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 {
 	struct bpf_dtab *dtab;
-	int err = -EINVAL;
+	int err, cpu;
 	u64 cost;
 
 	if (!capable(CAP_NET_ADMIN))
@@ -91,6 +89,11 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	    attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
+	/* Lookup returns a pointer straight to dev->ifindex, so make sure the
+	 * verifier prevents writes from the BPF side
+	 */
+	attr->map_flags |= BPF_F_RDONLY_PROG;
+
 	dtab = kzalloc(sizeof(*dtab), GFP_USER);
 	if (!dtab)
 		return ERR_PTR(-ENOMEM);
@@ -99,39 +102,39 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 
 	/* make sure page count doesn't overflow */
 	cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *);
-	cost += dev_map_bitmap_size(attr) * num_possible_cpus();
-	if (cost >= U32_MAX - PAGE_SIZE)
-		goto free_dtab;
-
-	dtab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+	cost += sizeof(struct list_head) * num_possible_cpus();
 
-	/* if map size is larger than memlock limit, reject it early */
-	err = bpf_map_precharge_memlock(dtab->map.pages);
+	/* if map size is larger than memlock limit, reject it */
+	err = bpf_map_charge_init(&dtab->map.memory, cost);
 	if (err)
 		goto free_dtab;
 
 	err = -ENOMEM;
 
-	/* A per cpu bitfield with a bit per possible net device */
-	dtab->flush_needed = __alloc_percpu_gfp(dev_map_bitmap_size(attr),
-						__alignof__(unsigned long),
-						GFP_KERNEL | __GFP_NOWARN);
-	if (!dtab->flush_needed)
-		goto free_dtab;
+	dtab->flush_list = alloc_percpu(struct list_head);
+	if (!dtab->flush_list)
+		goto free_charge;
+
+	for_each_possible_cpu(cpu)
+		INIT_LIST_HEAD(per_cpu_ptr(dtab->flush_list, cpu));
 
 	dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries *
 					      sizeof(struct bpf_dtab_netdev *),
 					      dtab->map.numa_node);
 	if (!dtab->netdev_map)
-		goto free_dtab;
+		goto free_percpu;
 
 	spin_lock(&dev_map_lock);
 	list_add_tail_rcu(&dtab->list, &dev_map_list);
 	spin_unlock(&dev_map_lock);
 
 	return &dtab->map;
+
+free_percpu:
+	free_percpu(dtab->flush_list);
+free_charge:
+	bpf_map_charge_finish(&dtab->map.memory);
 free_dtab:
-	free_percpu(dtab->flush_needed);
 	kfree(dtab);
 	return ERR_PTR(err);
 }
@@ -160,14 +163,14 @@ static void dev_map_free(struct bpf_map *map)
 	rcu_barrier();
 
 	/* To ensure all pending flush operations have completed wait for flush
-	 * bitmap to indicate all flush_needed bits to be zero on _all_ cpus.
+	 * list to empty on _all_ cpus.
 	 * Because the above synchronize_rcu() ensures the map is disconnected
-	 * from the program we can assume no new bits will be set.
+	 * from the program we can assume no new items will be added.
 	 */
 	for_each_online_cpu(cpu) {
-		unsigned long *bitmap = per_cpu_ptr(dtab->flush_needed, cpu);
+		struct list_head *flush_list = per_cpu_ptr(dtab->flush_list, cpu);
 
-		while (!bitmap_empty(bitmap, dtab->map.max_entries))
+		while (!list_empty(flush_list))
 			cond_resched();
 	}
 
@@ -183,7 +186,7 @@ static void dev_map_free(struct bpf_map *map)
 		kfree(dev);
 	}
 
-	free_percpu(dtab->flush_needed);
+	free_percpu(dtab->flush_list);
 	bpf_map_area_free(dtab->netdev_map);
 	kfree(dtab);
 }
@@ -205,18 +208,10 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
-void __dev_map_insert_ctx(struct bpf_map *map, u32 bit)
-{
-	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
-	unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed);
-
-	__set_bit(bit, bitmap);
-}
-
-static int bq_xmit_all(struct bpf_dtab_netdev *obj,
-		       struct xdp_bulk_queue *bq, u32 flags,
+static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags,
 		       bool in_napi_ctx)
 {
+	struct bpf_dtab_netdev *obj = bq->obj;
 	struct net_device *dev = obj->dev;
 	int sent = 0, drops = 0, err = 0;
 	int i;
@@ -243,6 +238,7 @@ out:
 	trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit,
 			      sent, drops, bq->dev_rx, dev, err);
 	bq->dev_rx = NULL;
+	__list_del_clearprev(&bq->flush_node);
 	return 0;
 error:
 	/* If ndo_xdp_xmit fails with an errno, no frames have been
@@ -265,31 +261,18 @@ error:
  * from the driver before returning from its napi->poll() routine. The poll()
  * routine is called either from busy_poll context or net_rx_action signaled
  * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the
- * net device can be torn down. On devmap tear down we ensure the ctx bitmap
- * is zeroed before completing to ensure all flush operations have completed.
+ * net device can be torn down. On devmap tear down we ensure the flush list
+ * is empty before completing to ensure all flush operations have completed.
  */
 void __dev_map_flush(struct bpf_map *map)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
-	unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed);
-	u32 bit;
+	struct list_head *flush_list = this_cpu_ptr(dtab->flush_list);
+	struct xdp_bulk_queue *bq, *tmp;
 
 	rcu_read_lock();
-	for_each_set_bit(bit, bitmap, map->max_entries) {
-		struct bpf_dtab_netdev *dev = READ_ONCE(dtab->netdev_map[bit]);
-		struct xdp_bulk_queue *bq;
-
-		/* This is possible if the dev entry is removed by user space
-		 * between xdp redirect and flush op.
-		 */
-		if (unlikely(!dev))
-			continue;
-
-		bq = this_cpu_ptr(dev->bulkq);
-		bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true);
-
-		__clear_bit(bit, bitmap);
-	}
+	list_for_each_entry_safe(bq, tmp, flush_list, flush_node)
+		bq_xmit_all(bq, XDP_XMIT_FLUSH, true);
 	rcu_read_unlock();
 }
 
@@ -316,10 +299,11 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
 		      struct net_device *dev_rx)
 
 {
+	struct list_head *flush_list = this_cpu_ptr(obj->dtab->flush_list);
 	struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq);
 
 	if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
-		bq_xmit_all(obj, bq, 0, true);
+		bq_xmit_all(bq, 0, true);
 
 	/* Ingress dev_rx will be the same for all xdp_frame's in
 	 * bulk_queue, because bq stored per-CPU and must be flushed
@@ -329,6 +313,10 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
 		bq->dev_rx = dev_rx;
 
 	bq->q[bq->count++] = xdpf;
+
+	if (!bq->flush_node.prev)
+		list_add(&bq->flush_node, flush_list);
+
 	return 0;
 }
 
@@ -379,17 +367,12 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev)
 {
 	if (dev->dev->netdev_ops->ndo_xdp_xmit) {
 		struct xdp_bulk_queue *bq;
-		unsigned long *bitmap;
-
 		int cpu;
 
 		rcu_read_lock();
 		for_each_online_cpu(cpu) {
-			bitmap = per_cpu_ptr(dev->dtab->flush_needed, cpu);
-			__clear_bit(dev->bit, bitmap);
-
 			bq = per_cpu_ptr(dev->bulkq, cpu);
-			bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false);
+			bq_xmit_all(bq, XDP_XMIT_FLUSH, false);
 		}
 		rcu_read_unlock();
 	}
@@ -436,8 +419,10 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value,
 	struct net *net = current->nsproxy->net_ns;
 	gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN;
 	struct bpf_dtab_netdev *dev, *old_dev;
-	u32 i = *(u32 *)key;
 	u32 ifindex = *(u32 *)value;
+	struct xdp_bulk_queue *bq;
+	u32 i = *(u32 *)key;
+	int cpu;
 
 	if (unlikely(map_flags > BPF_EXIST))
 		return -EINVAL;
@@ -460,6 +445,11 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value,
 			return -ENOMEM;
 		}
 
+		for_each_possible_cpu(cpu) {
+			bq = per_cpu_ptr(dev->bulkq, cpu);
+			bq->obj = dev;
+		}
+
 		dev->dev = dev_get_by_index(net, ifindex);
 		if (!dev->dev) {
 			free_percpu(dev->bulkq);