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

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

1 files changed, 363 insertions, 0 deletions

diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
new file mode 100644
index 000000000000..18e225de80ff
--- /dev/null
+++ b/kernel/bpf/reuseport_array.c
@@ -0,0 +1,363 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Facebook
+ */
+#include <linux/bpf.h>
+#include <linux/err.h>
+#include <linux/sock_diag.h>
+#include <net/sock_reuseport.h>
+
+struct reuseport_array {
+	struct bpf_map map;
+	struct sock __rcu *ptrs[];
+};
+
+static struct reuseport_array *reuseport_array(struct bpf_map *map)
+{
+	return (struct reuseport_array *)map;
+}
+
+/* The caller must hold the reuseport_lock */
+void bpf_sk_reuseport_detach(struct sock *sk)
+{
+	struct sock __rcu **socks;
+
+	write_lock_bh(&sk->sk_callback_lock);
+	socks = sk->sk_user_data;
+	if (socks) {
+		WRITE_ONCE(sk->sk_user_data, NULL);
+		/*
+		 * Do not move this NULL assignment outside of
+		 * sk->sk_callback_lock because there is
+		 * a race with reuseport_array_free()
+		 * which does not hold the reuseport_lock.
+		 */
+		RCU_INIT_POINTER(*socks, NULL);
+	}
+	write_unlock_bh(&sk->sk_callback_lock);
+}
+
+static int reuseport_array_alloc_check(union bpf_attr *attr)
+{
+	if (attr->value_size != sizeof(u32) &&
+	    attr->value_size != sizeof(u64))
+		return -EINVAL;
+
+	return array_map_alloc_check(attr);
+}
+
+static void *reuseport_array_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	u32 index = *(u32 *)key;
+
+	if (unlikely(index >= array->map.max_entries))
+		return NULL;
+
+	return rcu_dereference(array->ptrs[index]);
+}
+
+/* Called from syscall only */
+static int reuseport_array_delete_elem(struct bpf_map *map, void *key)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	u32 index = *(u32 *)key;
+	struct sock *sk;
+	int err;
+
+	if (index >= map->max_entries)
+		return -E2BIG;
+
+	if (!rcu_access_pointer(array->ptrs[index]))
+		return -ENOENT;
+
+	spin_lock_bh(&reuseport_lock);
+
+	sk = rcu_dereference_protected(array->ptrs[index],
+				       lockdep_is_held(&reuseport_lock));
+	if (sk) {
+		write_lock_bh(&sk->sk_callback_lock);
+		WRITE_ONCE(sk->sk_user_data, NULL);
+		RCU_INIT_POINTER(array->ptrs[index], NULL);
+		write_unlock_bh(&sk->sk_callback_lock);
+		err = 0;
+	} else {
+		err = -ENOENT;
+	}
+
+	spin_unlock_bh(&reuseport_lock);
+
+	return err;
+}
+
+static void reuseport_array_free(struct bpf_map *map)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	struct sock *sk;
+	u32 i;
+
+	synchronize_rcu();
+
+	/*
+	 * ops->map_*_elem() will not be able to access this
+	 * array now. Hence, this function only races with
+	 * bpf_sk_reuseport_detach() which was triggerred by
+	 * close() or disconnect().
+	 *
+	 * This function and bpf_sk_reuseport_detach() are
+	 * both removing sk from "array".  Who removes it
+	 * first does not matter.
+	 *
+	 * The only concern here is bpf_sk_reuseport_detach()
+	 * may access "array" which is being freed here.
+	 * bpf_sk_reuseport_detach() access this "array"
+	 * through sk->sk_user_data _and_ with sk->sk_callback_lock
+	 * held which is enough because this "array" is not freed
+	 * until all sk->sk_user_data has stopped referencing this "array".
+	 *
+	 * Hence, due to the above, taking "reuseport_lock" is not
+	 * needed here.
+	 */
+
+	/*
+	 * Since reuseport_lock is not taken, sk is accessed under
+	 * rcu_read_lock()
+	 */
+	rcu_read_lock();
+	for (i = 0; i < map->max_entries; i++) {
+		sk = rcu_dereference(array->ptrs[i]);
+		if (sk) {
+			write_lock_bh(&sk->sk_callback_lock);
+			/*
+			 * No need for WRITE_ONCE(). At this point,
+			 * no one is reading it without taking the
+			 * sk->sk_callback_lock.
+			 */
+			sk->sk_user_data = NULL;
+			write_unlock_bh(&sk->sk_callback_lock);
+			RCU_INIT_POINTER(array->ptrs[i], NULL);
+		}
+	}
+	rcu_read_unlock();
+
+	/*
+	 * Once reaching here, all sk->sk_user_data is not
+	 * referenceing this "array".  "array" can be freed now.
+	 */
+	bpf_map_area_free(array);
+}
+
+static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr)
+{
+	int err, numa_node = bpf_map_attr_numa_node(attr);
+	struct reuseport_array *array;
+	u64 cost, array_size;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	array_size = sizeof(*array);
+	array_size += (u64)attr->max_entries * sizeof(struct sock *);
+
+	/* make sure there is no u32 overflow later in round_up() */
+	cost = array_size;
+	if (cost >= U32_MAX - PAGE_SIZE)
+		return ERR_PTR(-ENOMEM);
+	cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	err = bpf_map_precharge_memlock(cost);
+	if (err)
+		return ERR_PTR(err);
+
+	/* allocate all map elements and zero-initialize them */
+	array = bpf_map_area_alloc(array_size, numa_node);
+	if (!array)
+		return ERR_PTR(-ENOMEM);
+
+	/* copy mandatory map attributes */
+	bpf_map_init_from_attr(&array->map, attr);
+	array->map.pages = cost;
+
+	return &array->map;
+}
+
+int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
+				       void *value)
+{
+	struct sock *sk;
+	int err;
+
+	if (map->value_size != sizeof(u64))
+		return -ENOSPC;
+
+	rcu_read_lock();
+	sk = reuseport_array_lookup_elem(map, key);
+	if (sk) {
+		*(u64 *)value = sock_gen_cookie(sk);
+		err = 0;
+	} else {
+		err = -ENOENT;
+	}
+	rcu_read_unlock();
+
+	return err;
+}
+
+static int
+reuseport_array_update_check(const struct reuseport_array *array,
+			     const struct sock *nsk,
+			     const struct sock *osk,
+			     const struct sock_reuseport *nsk_reuse,
+			     u32 map_flags)
+{
+	if (osk && map_flags == BPF_NOEXIST)
+		return -EEXIST;
+
+	if (!osk && map_flags == BPF_EXIST)
+		return -ENOENT;
+
+	if (nsk->sk_protocol != IPPROTO_UDP && nsk->sk_protocol != IPPROTO_TCP)
+		return -ENOTSUPP;
+
+	if (nsk->sk_family != AF_INET && nsk->sk_family != AF_INET6)
+		return -ENOTSUPP;
+
+	if (nsk->sk_type != SOCK_STREAM && nsk->sk_type != SOCK_DGRAM)
+		return -ENOTSUPP;
+
+	/*
+	 * sk must be hashed (i.e. listening in the TCP case or binded
+	 * in the UDP case) and
+	 * it must also be a SO_REUSEPORT sk (i.e. reuse cannot be NULL).
+	 *
+	 * Also, sk will be used in bpf helper that is protected by
+	 * rcu_read_lock().
+	 */
+	if (!sock_flag(nsk, SOCK_RCU_FREE) || !sk_hashed(nsk) || !nsk_reuse)
+		return -EINVAL;
+
+	/* READ_ONCE because the sk->sk_callback_lock may not be held here */
+	if (READ_ONCE(nsk->sk_user_data))
+		return -EBUSY;
+
+	return 0;
+}
+
+/*
+ * Called from syscall only.
+ * The "nsk" in the fd refcnt.
+ * The "osk" and "reuse" are protected by reuseport_lock.
+ */
+int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
+				       void *value, u64 map_flags)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	struct sock *free_osk = NULL, *osk, *nsk;
+	struct sock_reuseport *reuse;
+	u32 index = *(u32 *)key;
+	struct socket *socket;
+	int err, fd;
+
+	if (map_flags > BPF_EXIST)
+		return -EINVAL;
+
+	if (index >= map->max_entries)
+		return -E2BIG;
+
+	if (map->value_size == sizeof(u64)) {
+		u64 fd64 = *(u64 *)value;
+
+		if (fd64 > S32_MAX)
+			return -EINVAL;
+		fd = fd64;
+	} else {
+		fd = *(int *)value;
+	}
+
+	socket = sockfd_lookup(fd, &err);
+	if (!socket)
+		return err;
+
+	nsk = socket->sk;
+	if (!nsk) {
+		err = -EINVAL;
+		goto put_file;
+	}
+
+	/* Quick checks before taking reuseport_lock */
+	err = reuseport_array_update_check(array, nsk,
+					   rcu_access_pointer(array->ptrs[index]),
+					   rcu_access_pointer(nsk->sk_reuseport_cb),
+					   map_flags);
+	if (err)
+		goto put_file;
+
+	spin_lock_bh(&reuseport_lock);
+	/*
+	 * Some of the checks only need reuseport_lock
+	 * but it is done under sk_callback_lock also
+	 * for simplicity reason.
+	 */
+	write_lock_bh(&nsk->sk_callback_lock);
+
+	osk = rcu_dereference_protected(array->ptrs[index],
+					lockdep_is_held(&reuseport_lock));
+	reuse = rcu_dereference_protected(nsk->sk_reuseport_cb,
+					  lockdep_is_held(&reuseport_lock));
+	err = reuseport_array_update_check(array, nsk, osk, reuse, map_flags);
+	if (err)
+		goto put_file_unlock;
+
+	/* Ensure reuse->reuseport_id is set */
+	err = reuseport_get_id(reuse);
+	if (err < 0)
+		goto put_file_unlock;
+
+	WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]);
+	rcu_assign_pointer(array->ptrs[index], nsk);
+	free_osk = osk;
+	err = 0;
+
+put_file_unlock:
+	write_unlock_bh(&nsk->sk_callback_lock);
+
+	if (free_osk) {
+		write_lock_bh(&free_osk->sk_callback_lock);
+		WRITE_ONCE(free_osk->sk_user_data, NULL);
+		write_unlock_bh(&free_osk->sk_callback_lock);
+	}
+
+	spin_unlock_bh(&reuseport_lock);
+put_file:
+	fput(socket->file);
+	return err;
+}
+
+/* Called from syscall */
+static int reuseport_array_get_next_key(struct bpf_map *map, void *key,
+					void *next_key)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	u32 index = key ? *(u32 *)key : U32_MAX;
+	u32 *next = (u32 *)next_key;
+
+	if (index >= array->map.max_entries) {
+		*next = 0;
+		return 0;
+	}
+
+	if (index == array->map.max_entries - 1)
+		return -ENOENT;
+
+	*next = index + 1;
+	return 0;
+}
+
+const struct bpf_map_ops reuseport_array_ops = {
+	.map_alloc_check = reuseport_array_alloc_check,
+	.map_alloc = reuseport_array_alloc,
+	.map_free = reuseport_array_free,
+	.map_lookup_elem = reuseport_array_lookup_elem,
+	.map_get_next_key = reuseport_array_get_next_key,
+	.map_delete_elem = reuseport_array_delete_elem,
+};