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, 79 insertions, 43 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 5b30f8baaf02..5d141f16f6fa 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -180,19 +180,6 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr)
 	map->numa_node = bpf_map_attr_numa_node(attr);
 }
 
-int bpf_map_precharge_memlock(u32 pages)
-{
-	struct user_struct *user = get_current_user();
-	unsigned long memlock_limit, cur;
-
-	memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-	cur = atomic_long_read(&user->locked_vm);
-	free_uid(user);
-	if (cur + pages > memlock_limit)
-		return -EPERM;
-	return 0;
-}
-
 static int bpf_charge_memlock(struct user_struct *user, u32 pages)
 {
 	unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
@@ -206,45 +193,62 @@ static int bpf_charge_memlock(struct user_struct *user, u32 pages)
 
 static void bpf_uncharge_memlock(struct user_struct *user, u32 pages)
 {
-	atomic_long_sub(pages, &user->locked_vm);
+	if (user)
+		atomic_long_sub(pages, &user->locked_vm);
 }
 
-static int bpf_map_init_memlock(struct bpf_map *map)
+int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size)
 {
-	struct user_struct *user = get_current_user();
+	u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT;
+	struct user_struct *user;
 	int ret;
 
-	ret = bpf_charge_memlock(user, map->pages);
+	if (size >= U32_MAX - PAGE_SIZE)
+		return -E2BIG;
+
+	user = get_current_user();
+	ret = bpf_charge_memlock(user, pages);
 	if (ret) {
 		free_uid(user);
 		return ret;
 	}
-	map->user = user;
-	return ret;
+
+	mem->pages = pages;
+	mem->user = user;
+
+	return 0;
 }
 
-static void bpf_map_release_memlock(struct bpf_map *map)
+void bpf_map_charge_finish(struct bpf_map_memory *mem)
 {
-	struct user_struct *user = map->user;
-	bpf_uncharge_memlock(user, map->pages);
-	free_uid(user);
+	bpf_uncharge_memlock(mem->user, mem->pages);
+	free_uid(mem->user);
+}
+
+void bpf_map_charge_move(struct bpf_map_memory *dst,
+			 struct bpf_map_memory *src)
+{
+	*dst = *src;
+
+	/* Make sure src will not be used for the redundant uncharging. */
+	memset(src, 0, sizeof(struct bpf_map_memory));
 }
 
 int bpf_map_charge_memlock(struct bpf_map *map, u32 pages)
 {
 	int ret;
 
-	ret = bpf_charge_memlock(map->user, pages);
+	ret = bpf_charge_memlock(map->memory.user, pages);
 	if (ret)
 		return ret;
-	map->pages += pages;
+	map->memory.pages += pages;
 	return ret;
 }
 
 void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages)
 {
-	bpf_uncharge_memlock(map->user, pages);
-	map->pages -= pages;
+	bpf_uncharge_memlock(map->memory.user, pages);
+	map->memory.pages -= pages;
 }
 
 static int bpf_map_alloc_id(struct bpf_map *map)
@@ -295,11 +299,13 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
 static void bpf_map_free_deferred(struct work_struct *work)
 {
 	struct bpf_map *map = container_of(work, struct bpf_map, work);
+	struct bpf_map_memory mem;
 
-	bpf_map_release_memlock(map);
+	bpf_map_charge_move(&mem, &map->memory);
 	security_bpf_map_free(map);
 	/* implementation dependent freeing */
 	map->ops->map_free(map);
+	bpf_map_charge_finish(&mem);
 }
 
 static void bpf_map_put_uref(struct bpf_map *map)
@@ -387,7 +393,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 		   map->value_size,
 		   map->max_entries,
 		   map->map_flags,
-		   map->pages * 1ULL << PAGE_SHIFT,
+		   map->memory.pages * 1ULL << PAGE_SHIFT,
 		   map->id,
 		   READ_ONCE(map->frozen));
 
@@ -541,6 +547,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 static int map_create(union bpf_attr *attr)
 {
 	int numa_node = bpf_map_attr_numa_node(attr);
+	struct bpf_map_memory mem;
 	struct bpf_map *map;
 	int f_flags;
 	int err;
@@ -565,7 +572,7 @@ static int map_create(union bpf_attr *attr)
 
 	err = bpf_obj_name_cpy(map->name, attr->map_name);
 	if (err)
-		goto free_map_nouncharge;
+		goto free_map;
 
 	atomic_set(&map->refcnt, 1);
 	atomic_set(&map->usercnt, 1);
@@ -575,20 +582,20 @@ static int map_create(union bpf_attr *attr)
 
 		if (!attr->btf_value_type_id) {
 			err = -EINVAL;
-			goto free_map_nouncharge;
+			goto free_map;
 		}
 
 		btf = btf_get_by_fd(attr->btf_fd);
 		if (IS_ERR(btf)) {
 			err = PTR_ERR(btf);
-			goto free_map_nouncharge;
+			goto free_map;
 		}
 
 		err = map_check_btf(map, btf, attr->btf_key_type_id,
 				    attr->btf_value_type_id);
 		if (err) {
 			btf_put(btf);
-			goto free_map_nouncharge;
+			goto free_map;
 		}
 
 		map->btf = btf;
@@ -600,15 +607,11 @@ static int map_create(union bpf_attr *attr)
 
 	err = security_bpf_map_alloc(map);
 	if (err)
-		goto free_map_nouncharge;
-
-	err = bpf_map_init_memlock(map);
-	if (err)
-		goto free_map_sec;
+		goto free_map;
 
 	err = bpf_map_alloc_id(map);
 	if (err)
-		goto free_map;
+		goto free_map_sec;
 
 	err = bpf_map_new_fd(map, f_flags);
 	if (err < 0) {
@@ -624,13 +627,13 @@ static int map_create(union bpf_attr *attr)
 
 	return err;
 
-free_map:
-	bpf_map_release_memlock(map);
 free_map_sec:
 	security_bpf_map_free(map);
-free_map_nouncharge:
+free_map:
 	btf_put(map->btf);
+	bpf_map_charge_move(&mem, &map->memory);
 	map->ops->map_free(map);
+	bpf_map_charge_finish(&mem);
 	return err;
 }
 
@@ -1579,6 +1582,22 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type,
 		default:
 			return -EINVAL;
 		}
+	case BPF_PROG_TYPE_CGROUP_SKB:
+		switch (expected_attach_type) {
+		case BPF_CGROUP_INET_INGRESS:
+		case BPF_CGROUP_INET_EGRESS:
+			return 0;
+		default:
+			return -EINVAL;
+		}
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+		switch (expected_attach_type) {
+		case BPF_CGROUP_SETSOCKOPT:
+		case BPF_CGROUP_GETSOCKOPT:
+			return 0;
+		default:
+			return -EINVAL;
+		}
 	default:
 		return 0;
 	}
@@ -1598,7 +1617,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	if (CHECK_ATTR(BPF_PROG_LOAD))
 		return -EINVAL;
 
-	if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT))
+	if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT |
+				 BPF_F_ANY_ALIGNMENT |
+				 BPF_F_TEST_RND_HI32))
 		return -EINVAL;
 
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
@@ -1827,7 +1848,12 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 	switch (prog->type) {
 	case BPF_PROG_TYPE_CGROUP_SOCK:
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 		return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
+	case BPF_PROG_TYPE_CGROUP_SKB:
+		return prog->enforce_expected_attach_type &&
+			prog->expected_attach_type != attach_type ?
+			-EINVAL : 0;
 	default:
 		return 0;
 	}
@@ -1895,6 +1921,10 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	case BPF_CGROUP_SYSCTL:
 		ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
 		break;
+	case BPF_CGROUP_GETSOCKOPT:
+	case BPF_CGROUP_SETSOCKOPT:
+		ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1978,6 +2008,10 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	case BPF_CGROUP_SYSCTL:
 		ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
 		break;
+	case BPF_CGROUP_GETSOCKOPT:
+	case BPF_CGROUP_SETSOCKOPT:
+		ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -2014,6 +2048,8 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_SOCK_OPS:
 	case BPF_CGROUP_DEVICE:
 	case BPF_CGROUP_SYSCTL:
+	case BPF_CGROUP_GETSOCKOPT:
+	case BPF_CGROUP_SETSOCKOPT:
 		break;
 	case BPF_LIRC_MODE2:
 		return lirc_prog_query(attr, uattr);