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

Pull networking updates from David Miller:

Changes of note:

 1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.

 2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
    David Ahern.

 3) Allow the user to ask for the statistics to be filtered out of
    ipv4/ipv6 address netlink dumps.  From Sowmini Varadhan.

 4) More work to pass the network namespace context around deep into
    various packet path APIs, starting with the netfilter hooks.  From
    Eric W Biederman.

 5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
    Richter.

 6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.

 7) Support Very High Throughput in wireless MESH code, from Bob
    Copeland.

 8) Allow setting the ageing_time in switchdev/rocker.  From Scott
    Feldman.

 9) Properly autoload L2TP type modules, from Stephen Hemminger.

10) Fix and enable offload features by default in 8139cp driver, from
    David Woodhouse.

11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
    Jiri Benc.

12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
    Opstad.

13) Fix IPSEC flowcache overflows on large systems, from Steffen
    Klassert.

14) Convert bridging to track VLANs using rhashtable entries rather than
    a bitmap.  From Nikolay Aleksandrov.

15) Make TCP listener handling completely lockless, this is a major
    accomplishment.  Incoming request sockets now live in the
    established hash table just like any other socket too.

    From Eric Dumazet.

15) Provide more bridging attributes to netlink, from Nikolay
    Aleksandrov.

16) Use hash based algorithm for ipv4 multipath routing, this was very
    long overdue.  From Peter Nørlund.

17) Several y2038 cures, mostly avoiding timespec.  From Arnd Bergmann.

18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.

19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet.  This
    influences the port binding selection logic used by SO_REUSEPORT.

20) Add ipv6 support to VRF, from David Ahern.

21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.

22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.

23) Implement RACK loss recovery in TCP, from Yuchung Cheng.

24) Support multipath routes in MPLS, from Roopa Prabhu.

25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
    Dumazet.

26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
    Sudarsana Kalluru.

27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
    Sowa.

28) Support ipv6 geneve tunnels, from John W Linville.

29) Add flood control support to switchdev layer, from Ido Schimmel.

30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
    Hannes Frederic Sowa.

31) Support persistent maps and progs in bpf, from Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
  sh_eth: use DMA barriers
  switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
  net: sched: kill dead code in sch_choke.c
  irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
  net: dsa: mv88e6xxx: include DSA ports in VLANs
  net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
  net/core: fix for_each_netdev_feature
  vlan: Invoke driver vlan hooks only if device is present
  arcnet/com20020: add LEDS_CLASS dependency
  bpf, verifier: annotate verbose printer with __printf
  dp83640: Only wait for timestamps for packets with timestamping enabled.
  ptp: Change ptp_class to a proper bitmask
  dp83640: Prune rx timestamp list before reading from it
  dp83640: Delay scheduled work.
  dp83640: Include hash in timestamp/packet matching
  ipv6: fix tunnel error handling
  net/mlx5e: Fix LSO vlan insertion
  net/mlx5e: Re-eanble client vlan TX acceleration
  net/mlx5e: Return error in case mlx5e_set_features() fails
  net/mlx5e: Don't allow more than max supported channels
  ...

1 files changed, 139 insertions, 35 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 35bac8e8b071..0d3313d02a7e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -18,6 +18,8 @@
 #include <linux/filter.h>
 #include <linux/version.h>
 
+int sysctl_unprivileged_bpf_disabled __read_mostly;
+
 static LIST_HEAD(bpf_map_types);
 
 static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
@@ -44,11 +46,38 @@ void bpf_register_map_type(struct bpf_map_type_list *tl)
 	list_add(&tl->list_node, &bpf_map_types);
 }
 
+static int bpf_map_charge_memlock(struct bpf_map *map)
+{
+	struct user_struct *user = get_current_user();
+	unsigned long memlock_limit;
+
+	memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+
+	atomic_long_add(map->pages, &user->locked_vm);
+
+	if (atomic_long_read(&user->locked_vm) > memlock_limit) {
+		atomic_long_sub(map->pages, &user->locked_vm);
+		free_uid(user);
+		return -EPERM;
+	}
+	map->user = user;
+	return 0;
+}
+
+static void bpf_map_uncharge_memlock(struct bpf_map *map)
+{
+	struct user_struct *user = map->user;
+
+	atomic_long_sub(map->pages, &user->locked_vm);
+	free_uid(user);
+}
+
 /* called from workqueue */
 static void bpf_map_free_deferred(struct work_struct *work)
 {
 	struct bpf_map *map = container_of(work, struct bpf_map, work);
 
+	bpf_map_uncharge_memlock(map);
 	/* implementation dependent freeing */
 	map->ops->map_free(map);
 }
@@ -82,6 +111,12 @@ static const struct file_operations bpf_map_fops = {
 	.release = bpf_map_release,
 };
 
+int bpf_map_new_fd(struct bpf_map *map)
+{
+	return anon_inode_getfd("bpf-map", &bpf_map_fops, map,
+				O_RDWR | O_CLOEXEC);
+}
+
 /* helper macro to check that unused fields 'union bpf_attr' are zero */
 #define CHECK_ATTR(CMD) \
 	memchr_inv((void *) &attr->CMD##_LAST_FIELD + \
@@ -108,8 +143,11 @@ static int map_create(union bpf_attr *attr)
 
 	atomic_set(&map->refcnt, 1);
 
-	err = anon_inode_getfd("bpf-map", &bpf_map_fops, map, O_RDWR | O_CLOEXEC);
+	err = bpf_map_charge_memlock(map);
+	if (err)
+		goto free_map;
 
+	err = bpf_map_new_fd(map);
 	if (err < 0)
 		/* failed to allocate fd */
 		goto free_map;
@@ -124,19 +162,29 @@ free_map:
 /* if error is returned, fd is released.
  * On success caller should complete fd access with matching fdput()
  */
-struct bpf_map *bpf_map_get(struct fd f)
+struct bpf_map *__bpf_map_get(struct fd f)
 {
-	struct bpf_map *map;
-
 	if (!f.file)
 		return ERR_PTR(-EBADF);
-
 	if (f.file->f_op != &bpf_map_fops) {
 		fdput(f);
 		return ERR_PTR(-EINVAL);
 	}
 
-	map = f.file->private_data;
+	return f.file->private_data;
+}
+
+struct bpf_map *bpf_map_get(u32 ufd)
+{
+	struct fd f = fdget(ufd);
+	struct bpf_map *map;
+
+	map = __bpf_map_get(f);
+	if (IS_ERR(map))
+		return map;
+
+	atomic_inc(&map->refcnt);
+	fdput(f);
 
 	return map;
 }
@@ -164,7 +212,7 @@ static int map_lookup_elem(union bpf_attr *attr)
 		return -EINVAL;
 
 	f = fdget(ufd);
-	map = bpf_map_get(f);
+	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
@@ -223,7 +271,7 @@ static int map_update_elem(union bpf_attr *attr)
 		return -EINVAL;
 
 	f = fdget(ufd);
-	map = bpf_map_get(f);
+	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
@@ -276,7 +324,7 @@ static int map_delete_elem(union bpf_attr *attr)
 		return -EINVAL;
 
 	f = fdget(ufd);
-	map = bpf_map_get(f);
+	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
@@ -317,7 +365,7 @@ static int map_get_next_key(union bpf_attr *attr)
 		return -EINVAL;
 
 	f = fdget(ufd);
-	map = bpf_map_get(f);
+	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
@@ -402,6 +450,10 @@ static void fixup_bpf_calls(struct bpf_prog *prog)
 			 */
 			BUG_ON(!prog->aux->ops->get_func_proto);
 
+			if (insn->imm == BPF_FUNC_get_route_realm)
+				prog->dst_needed = 1;
+			if (insn->imm == BPF_FUNC_get_prandom_u32)
+				bpf_user_rnd_init_once();
 			if (insn->imm == BPF_FUNC_tail_call) {
 				/* mark bpf_tail_call as different opcode
 				 * to avoid conditional branch in
@@ -436,29 +488,51 @@ static void free_used_maps(struct bpf_prog_aux *aux)
 	kfree(aux->used_maps);
 }
 
-static void __prog_put_rcu(struct rcu_head *rcu)
+static int bpf_prog_charge_memlock(struct bpf_prog *prog)
+{
+	struct user_struct *user = get_current_user();
+	unsigned long memlock_limit;
+
+	memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+
+	atomic_long_add(prog->pages, &user->locked_vm);
+	if (atomic_long_read(&user->locked_vm) > memlock_limit) {
+		atomic_long_sub(prog->pages, &user->locked_vm);
+		free_uid(user);
+		return -EPERM;
+	}
+	prog->aux->user = user;
+	return 0;
+}
+
+static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
+{
+	struct user_struct *user = prog->aux->user;
+
+	atomic_long_sub(prog->pages, &user->locked_vm);
+	free_uid(user);
+}
+
+static void __prog_put_common(struct rcu_head *rcu)
 {
 	struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
 
 	free_used_maps(aux);
+	bpf_prog_uncharge_memlock(aux->prog);
 	bpf_prog_free(aux->prog);
 }
 
 /* version of bpf_prog_put() that is called after a grace period */
 void bpf_prog_put_rcu(struct bpf_prog *prog)
 {
-	if (atomic_dec_and_test(&prog->aux->refcnt)) {
-		prog->aux->prog = prog;
-		call_rcu(&prog->aux->rcu, __prog_put_rcu);
-	}
+	if (atomic_dec_and_test(&prog->aux->refcnt))
+		call_rcu(&prog->aux->rcu, __prog_put_common);
 }
 
 void bpf_prog_put(struct bpf_prog *prog)
 {
-	if (atomic_dec_and_test(&prog->aux->refcnt)) {
-		free_used_maps(prog->aux);
-		bpf_prog_free(prog);
-	}
+	if (atomic_dec_and_test(&prog->aux->refcnt))
+		__prog_put_common(&prog->aux->rcu);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_put);
 
@@ -474,21 +548,22 @@ static const struct file_operations bpf_prog_fops = {
         .release = bpf_prog_release,
 };
 
-static struct bpf_prog *get_prog(struct fd f)
+int bpf_prog_new_fd(struct bpf_prog *prog)
 {
-	struct bpf_prog *prog;
+	return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog,
+				O_RDWR | O_CLOEXEC);
+}
 
+static struct bpf_prog *__bpf_prog_get(struct fd f)
+{
 	if (!f.file)
 		return ERR_PTR(-EBADF);
-
 	if (f.file->f_op != &bpf_prog_fops) {
 		fdput(f);
 		return ERR_PTR(-EINVAL);
 	}
 
-	prog = f.file->private_data;
-
-	return prog;
+	return f.file->private_data;
 }
 
 /* called by sockets/tracing/seccomp before attaching program to an event
@@ -499,13 +574,13 @@ struct bpf_prog *bpf_prog_get(u32 ufd)
 	struct fd f = fdget(ufd);
 	struct bpf_prog *prog;
 
-	prog = get_prog(f);
-
+	prog = __bpf_prog_get(f);
 	if (IS_ERR(prog))
 		return prog;
 
 	atomic_inc(&prog->aux->refcnt);
 	fdput(f);
+
 	return prog;
 }
 EXPORT_SYMBOL_GPL(bpf_prog_get);
@@ -540,11 +615,18 @@ static int bpf_prog_load(union bpf_attr *attr)
 	    attr->kern_version != LINUX_VERSION_CODE)
 		return -EINVAL;
 
+	if (type != BPF_PROG_TYPE_SOCKET_FILTER && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	/* plain bpf_prog allocation */
 	prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER);
 	if (!prog)
 		return -ENOMEM;
 
+	err = bpf_prog_charge_memlock(prog);
+	if (err)
+		goto free_prog_nouncharge;
+
 	prog->len = attr->insn_cnt;
 
 	err = -EFAULT;
@@ -553,10 +635,10 @@ static int bpf_prog_load(union bpf_attr *attr)
 		goto free_prog;
 
 	prog->orig_prog = NULL;
-	prog->jited = false;
+	prog->jited = 0;
 
 	atomic_set(&prog->aux->refcnt, 1);
-	prog->gpl_compatible = is_gpl;
+	prog->gpl_compatible = is_gpl ? 1 : 0;
 
 	/* find program type: socket_filter vs tracing_filter */
 	err = find_prog_type(type, prog);
@@ -576,7 +658,7 @@ static int bpf_prog_load(union bpf_attr *attr)
 	if (err < 0)
 		goto free_used_maps;
 
-	err = anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC);
+	err = bpf_prog_new_fd(prog);
 	if (err < 0)
 		/* failed to allocate fd */
 		goto free_used_maps;
@@ -586,20 +668,36 @@ static int bpf_prog_load(union bpf_attr *attr)
 free_used_maps:
 	free_used_maps(prog->aux);
 free_prog:
+	bpf_prog_uncharge_memlock(prog);
+free_prog_nouncharge:
 	bpf_prog_free(prog);
 	return err;
 }
 
+#define BPF_OBJ_LAST_FIELD bpf_fd
+
+static int bpf_obj_pin(const union bpf_attr *attr)
+{
+	if (CHECK_ATTR(BPF_OBJ))
+		return -EINVAL;
+
+	return bpf_obj_pin_user(attr->bpf_fd, u64_to_ptr(attr->pathname));
+}
+
+static int bpf_obj_get(const union bpf_attr *attr)
+{
+	if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0)
+		return -EINVAL;
+
+	return bpf_obj_get_user(u64_to_ptr(attr->pathname));
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr = {};
 	int err;
 
-	/* the syscall is limited to root temporarily. This restriction will be
-	 * lifted when security audit is clean. Note that eBPF+tracing must have
-	 * this restriction, since it may pass kernel data to user space
-	 */
-	if (!capable(CAP_SYS_ADMIN))
+	if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled)
 		return -EPERM;
 
 	if (!access_ok(VERIFY_READ, uattr, 1))
@@ -654,6 +752,12 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_PROG_LOAD:
 		err = bpf_prog_load(&attr);
 		break;
+	case BPF_OBJ_PIN:
+		err = bpf_obj_pin(&attr);
+		break;
+	case BPF_OBJ_GET:
+		err = bpf_obj_get(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;