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, 294 insertions, 79 deletions

diff --git a/net/mptcp/token.c b/net/mptcp/token.c
index 33352dd99d4d..8b47c4bb1c6b 100644
--- a/net/mptcp/token.c
+++ b/net/mptcp/token.c
@@ -24,7 +24,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/radix-tree.h>
+#include <linux/memblock.h>
 #include <linux/ip.h>
 #include <linux/tcp.h>
 #include <net/sock.h>
@@ -33,10 +33,67 @@
 #include <net/mptcp.h>
 #include "protocol.h"
 
-static RADIX_TREE(token_tree, GFP_ATOMIC);
-static RADIX_TREE(token_req_tree, GFP_ATOMIC);
-static DEFINE_SPINLOCK(token_tree_lock);
-static int token_used __read_mostly;
+#define TOKEN_MAX_RETRIES	4
+#define TOKEN_MAX_CHAIN_LEN	4
+
+struct token_bucket {
+	spinlock_t		lock;
+	int			chain_len;
+	struct hlist_nulls_head	req_chain;
+	struct hlist_nulls_head	msk_chain;
+};
+
+static struct token_bucket *token_hash __read_mostly;
+static unsigned int token_mask __read_mostly;
+
+static struct token_bucket *token_bucket(u32 token)
+{
+	return &token_hash[token & token_mask];
+}
+
+/* called with bucket lock held */
+static struct mptcp_subflow_request_sock *
+__token_lookup_req(struct token_bucket *t, u32 token)
+{
+	struct mptcp_subflow_request_sock *req;
+	struct hlist_nulls_node *pos;
+
+	hlist_nulls_for_each_entry_rcu(req, pos, &t->req_chain, token_node)
+		if (req->token == token)
+			return req;
+	return NULL;
+}
+
+/* called with bucket lock held */
+static struct mptcp_sock *
+__token_lookup_msk(struct token_bucket *t, u32 token)
+{
+	struct hlist_nulls_node *pos;
+	struct sock *sk;
+
+	sk_nulls_for_each_rcu(sk, pos, &t->msk_chain)
+		if (mptcp_sk(sk)->token == token)
+			return mptcp_sk(sk);
+	return NULL;
+}
+
+static bool __token_bucket_busy(struct token_bucket *t, u32 token)
+{
+	return !token || t->chain_len >= TOKEN_MAX_CHAIN_LEN ||
+	       __token_lookup_req(t, token) || __token_lookup_msk(t, token);
+}
+
+static void mptcp_crypto_key_gen_sha(u64 *key, u32 *token, u64 *idsn)
+{
+	/* we might consider a faster version that computes the key as a
+	 * hash of some information available in the MPTCP socket. Use
+	 * random data at the moment, as it's probably the safest option
+	 * in case multiple sockets are opened in different namespaces at
+	 * the same time.
+	 */
+	get_random_bytes(key, sizeof(u64));
+	mptcp_crypto_key_sha(*key, token, idsn);
+}
 
 /**
  * mptcp_token_new_request - create new key/idsn/token for subflow_request
@@ -52,30 +109,28 @@ static int token_used __read_mostly;
 int mptcp_token_new_request(struct request_sock *req)
 {
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
-	int err;
-
-	while (1) {
-		u32 token;
-
-		mptcp_crypto_key_gen_sha(&subflow_req->local_key,
-					 &subflow_req->token,
-					 &subflow_req->idsn);
-		pr_debug("req=%p local_key=%llu, token=%u, idsn=%llu\n",
-			 req, subflow_req->local_key, subflow_req->token,
-			 subflow_req->idsn);
-
-		token = subflow_req->token;
-		spin_lock_bh(&token_tree_lock);
-		if (!radix_tree_lookup(&token_req_tree, token) &&
-		    !radix_tree_lookup(&token_tree, token))
-			break;
-		spin_unlock_bh(&token_tree_lock);
+	struct token_bucket *bucket;
+	u32 token;
+
+	mptcp_crypto_key_sha(subflow_req->local_key,
+			     &subflow_req->token,
+			     &subflow_req->idsn);
+	pr_debug("req=%p local_key=%llu, token=%u, idsn=%llu\n",
+		 req, subflow_req->local_key, subflow_req->token,
+		 subflow_req->idsn);
+
+	token = subflow_req->token;
+	bucket = token_bucket(token);
+	spin_lock_bh(&bucket->lock);
+	if (__token_bucket_busy(bucket, token)) {
+		spin_unlock_bh(&bucket->lock);
+		return -EBUSY;
 	}
 
-	err = radix_tree_insert(&token_req_tree,
-				subflow_req->token, &token_used);
-	spin_unlock_bh(&token_tree_lock);
-	return err;
+	hlist_nulls_add_head_rcu(&subflow_req->token_node, &bucket->req_chain);
+	bucket->chain_len++;
+	spin_unlock_bh(&bucket->lock);
+	return 0;
 }
 
 /**
@@ -97,48 +152,82 @@ int mptcp_token_new_request(struct request_sock *req)
 int mptcp_token_new_connect(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-	struct sock *mptcp_sock = subflow->conn;
-	int err;
-
-	while (1) {
-		u32 token;
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	int retries = TOKEN_MAX_RETRIES;
+	struct token_bucket *bucket;
 
-		mptcp_crypto_key_gen_sha(&subflow->local_key, &subflow->token,
-					 &subflow->idsn);
+	pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n",
+		 sk, subflow->local_key, subflow->token, subflow->idsn);
 
-		pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n",
-			 sk, subflow->local_key, subflow->token, subflow->idsn);
+again:
+	mptcp_crypto_key_gen_sha(&subflow->local_key, &subflow->token,
+				 &subflow->idsn);
 
-		token = subflow->token;
-		spin_lock_bh(&token_tree_lock);
-		if (!radix_tree_lookup(&token_req_tree, token) &&
-		    !radix_tree_lookup(&token_tree, token))
-			break;
-		spin_unlock_bh(&token_tree_lock);
+	bucket = token_bucket(subflow->token);
+	spin_lock_bh(&bucket->lock);
+	if (__token_bucket_busy(bucket, subflow->token)) {
+		spin_unlock_bh(&bucket->lock);
+		if (!--retries)
+			return -EBUSY;
+		goto again;
 	}
-	err = radix_tree_insert(&token_tree, subflow->token, mptcp_sock);
-	spin_unlock_bh(&token_tree_lock);
 
-	return err;
+	WRITE_ONCE(msk->token, subflow->token);
+	__sk_nulls_add_node_rcu((struct sock *)msk, &bucket->msk_chain);
+	bucket->chain_len++;
+	spin_unlock_bh(&bucket->lock);
+	return 0;
 }
 
 /**
- * mptcp_token_new_accept - insert token for later processing
- * @token: the token to insert to the tree
- * @conn: the just cloned socket linked to the new connection
+ * mptcp_token_accept - replace a req sk with full sock in token hash
+ * @req: the request socket to be removed
+ * @msk: the just cloned socket linked to the new connection
  *
  * Called when a SYN packet creates a new logical connection, i.e.
  * is not a join request.
  */
-int mptcp_token_new_accept(u32 token, struct sock *conn)
+void mptcp_token_accept(struct mptcp_subflow_request_sock *req,
+			struct mptcp_sock *msk)
 {
-	int err;
+	struct mptcp_subflow_request_sock *pos;
+	struct token_bucket *bucket;
 
-	spin_lock_bh(&token_tree_lock);
-	err = radix_tree_insert(&token_tree, token, conn);
-	spin_unlock_bh(&token_tree_lock);
+	bucket = token_bucket(req->token);
+	spin_lock_bh(&bucket->lock);
 
-	return err;
+	/* pedantic lookup check for the moved token */
+	pos = __token_lookup_req(bucket, req->token);
+	if (!WARN_ON_ONCE(pos != req))
+		hlist_nulls_del_init_rcu(&req->token_node);
+	__sk_nulls_add_node_rcu((struct sock *)msk, &bucket->msk_chain);
+	spin_unlock_bh(&bucket->lock);
+}
+
+bool mptcp_token_exists(u32 token)
+{
+	struct hlist_nulls_node *pos;
+	struct token_bucket *bucket;
+	struct mptcp_sock *msk;
+	struct sock *sk;
+
+	rcu_read_lock();
+	bucket = token_bucket(token);
+
+again:
+	sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) {
+		msk = mptcp_sk(sk);
+		if (READ_ONCE(msk->token) == token)
+			goto found;
+	}
+	if (get_nulls_value(pos) != (token & token_mask))
+		goto again;
+
+	rcu_read_unlock();
+	return false;
+found:
+	rcu_read_unlock();
+	return true;
 }
 
 /**
@@ -152,45 +241,171 @@ int mptcp_token_new_accept(u32 token, struct sock *conn)
  */
 struct mptcp_sock *mptcp_token_get_sock(u32 token)
 {
-	struct sock *conn;
-
-	spin_lock_bh(&token_tree_lock);
-	conn = radix_tree_lookup(&token_tree, token);
-	if (conn) {
-		/* token still reserved? */
-		if (conn == (struct sock *)&token_used)
-			conn = NULL;
-		else
-			sock_hold(conn);
+	struct hlist_nulls_node *pos;
+	struct token_bucket *bucket;
+	struct mptcp_sock *msk;
+	struct sock *sk;
+
+	rcu_read_lock();
+	bucket = token_bucket(token);
+
+again:
+	sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) {
+		msk = mptcp_sk(sk);
+		if (READ_ONCE(msk->token) != token)
+			continue;
+		if (!refcount_inc_not_zero(&sk->sk_refcnt))
+			goto not_found;
+		if (READ_ONCE(msk->token) != token) {
+			sock_put(sk);
+			goto again;
+		}
+		goto found;
+	}
+	if (get_nulls_value(pos) != (token & token_mask))
+		goto again;
+
+not_found:
+	msk = NULL;
+
+found:
+	rcu_read_unlock();
+	return msk;
+}
+EXPORT_SYMBOL_GPL(mptcp_token_get_sock);
+
+/**
+ * mptcp_token_iter_next - iterate over the token container from given pos
+ * @net: namespace to be iterated
+ * @s_slot: start slot number
+ * @s_num: start number inside the given lock
+ *
+ * This function returns the first mptcp connection structure found inside the
+ * token container starting from the specified position, or NULL.
+ *
+ * On successful iteration, the iterator is move to the next position and the
+ * the acquires a reference to the returned socket.
+ */
+struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot,
+					 long *s_num)
+{
+	struct mptcp_sock *ret = NULL;
+	struct hlist_nulls_node *pos;
+	int slot, num;
+
+	for (slot = *s_slot; slot <= token_mask; *s_num = 0, slot++) {
+		struct token_bucket *bucket = &token_hash[slot];
+		struct sock *sk;
+
+		num = 0;
+
+		if (hlist_nulls_empty(&bucket->msk_chain))
+			continue;
+
+		rcu_read_lock();
+		sk_nulls_for_each_rcu(sk, pos, &bucket->msk_chain) {
+			++num;
+			if (!net_eq(sock_net(sk), net))
+				continue;
+
+			if (num <= *s_num)
+				continue;
+
+			if (!refcount_inc_not_zero(&sk->sk_refcnt))
+				continue;
+
+			if (!net_eq(sock_net(sk), net)) {
+				sock_put(sk);
+				continue;
+			}
+
+			ret = mptcp_sk(sk);
+			rcu_read_unlock();
+			goto out;
+		}
+		rcu_read_unlock();
 	}
-	spin_unlock_bh(&token_tree_lock);
 
-	return mptcp_sk(conn);
+out:
+	*s_slot = slot;
+	*s_num = num;
+	return ret;
 }
+EXPORT_SYMBOL_GPL(mptcp_token_iter_next);
 
 /**
  * mptcp_token_destroy_request - remove mptcp connection/token
- * @token: token of mptcp connection to remove
+ * @req: mptcp request socket dropping the token
  *
- * Remove not-yet-fully-established incoming connection identified
- * by @token.
+ * Remove the token associated to @req.
  */
-void mptcp_token_destroy_request(u32 token)
+void mptcp_token_destroy_request(struct request_sock *req)
 {
-	spin_lock_bh(&token_tree_lock);
-	radix_tree_delete(&token_req_tree, token);
-	spin_unlock_bh(&token_tree_lock);
+	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
+	struct mptcp_subflow_request_sock *pos;
+	struct token_bucket *bucket;
+
+	if (hlist_nulls_unhashed(&subflow_req->token_node))
+		return;
+
+	bucket = token_bucket(subflow_req->token);
+	spin_lock_bh(&bucket->lock);
+	pos = __token_lookup_req(bucket, subflow_req->token);
+	if (!WARN_ON_ONCE(pos != subflow_req)) {
+		hlist_nulls_del_init_rcu(&pos->token_node);
+		bucket->chain_len--;
+	}
+	spin_unlock_bh(&bucket->lock);
 }
 
 /**
  * mptcp_token_destroy - remove mptcp connection/token
- * @token: token of mptcp connection to remove
+ * @msk: mptcp connection dropping the token
  *
- * Remove the connection identified by @token.
+ * Remove the token associated to @msk
  */
-void mptcp_token_destroy(u32 token)
+void mptcp_token_destroy(struct mptcp_sock *msk)
 {
-	spin_lock_bh(&token_tree_lock);
-	radix_tree_delete(&token_tree, token);
-	spin_unlock_bh(&token_tree_lock);
+	struct token_bucket *bucket;
+	struct mptcp_sock *pos;
+
+	if (sk_unhashed((struct sock *)msk))
+		return;
+
+	bucket = token_bucket(msk->token);
+	spin_lock_bh(&bucket->lock);
+	pos = __token_lookup_msk(bucket, msk->token);
+	if (!WARN_ON_ONCE(pos != msk)) {
+		__sk_nulls_del_node_init_rcu((struct sock *)pos);
+		bucket->chain_len--;
+	}
+	spin_unlock_bh(&bucket->lock);
 }
+
+void __init mptcp_token_init(void)
+{
+	int i;
+
+	token_hash = alloc_large_system_hash("MPTCP token",
+					     sizeof(struct token_bucket),
+					     0,
+					     20,/* one slot per 1MB of memory */
+					     HASH_ZERO,
+					     NULL,
+					     &token_mask,
+					     0,
+					     64 * 1024);
+	for (i = 0; i < token_mask + 1; ++i) {
+		INIT_HLIST_NULLS_HEAD(&token_hash[i].req_chain, i);
+		INIT_HLIST_NULLS_HEAD(&token_hash[i].msk_chain, i);
+		spin_lock_init(&token_hash[i].lock);
+	}
+}
+
+#if IS_MODULE(CONFIG_MPTCP_KUNIT_TESTS)
+EXPORT_SYMBOL_GPL(mptcp_token_new_request);
+EXPORT_SYMBOL_GPL(mptcp_token_new_connect);
+EXPORT_SYMBOL_GPL(mptcp_token_accept);
+EXPORT_SYMBOL_GPL(mptcp_token_destroy_request);
+EXPORT_SYMBOL_GPL(mptcp_token_destroy);
+#endif