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

Pull networking updates from David Miller:

 1) Platform regulatory domain support for ath10k, from Bartosz
    Markowski.

 2) Centralize min/max MTU checking, thus removing tons of duplicated
    code all of the the various drivers. From Jarod Wilson.

 3) Support ingress actions in act_mirred, from Shmulik Ladkani.

 4) Improve device adjacency tracking, from David Ahern.

 5) Add support for LED triggers on PHY link state changes, from Zach
    Brown.

 6) Improve UDP socket memory accounting, from Paolo Abeni.

 7) Set SK_MEM_QUANTUM to a fixed size of 4096, instead of PAGE_SIZE.
    From Eric Dumazet.

 8) Collapse TCP SKBs at retransmit time even if the right side SKB has
    frags. Also from Eric Dumazet.

 9) Add IP_RECVFRAGSIZE and IPV6_RECVFRAGSIZE cmsgs, from Willem de
    Bruijn.

10) Support routing by UID, from Lorenzo Colitti.

11) Handle L3 domain binding (ie. VRF) for RAW sockets, from David
    Ahern.

12) tcp_get_info() can run lockless, from Eric Dumazet.

13) 4-tuple UDP hashing in SFC driver, from Edward Cree.

14) Avoid reorders in GRO code, from Eric Dumazet.

15) IPV6 Segment Routing support, from David Lebrun.

16) Support MPLS push and pop for L3 packets in openvswitch, from Jiri
    Benc.

17) Add LRU datastructure support for BPF, Martin KaFai Lau.

18) VF support in liquidio driver, from Raghu Vatsavayi.

19) Multiqueue support in alx driver, from Tobias Regnery.

20) Networking cgroup BPF support, from Daniel Mack.

21) TCP chronograph measurements, from Francis Yan.

22) XDP support for qed driver, from Yuval Mintz.

23) BPF based lwtunnels, from Thomas Graf.

24) Consistent FIB dumping to offloading drivers, from Ido Schimmel.

25) Many optimizations for UDP under high load, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1522 commits)
  netfilter: nft_counter: rework atomic dump and reset
  e1000: use disable_hardirq() for e1000_netpoll()
  i40e: don't truncate match_method assignment
  net: ethernet: ti: netcp: add support of cpts
  net: phy: phy drivers should not set SUPPORTED_[Asym_]Pause
  net: l2tp: ppp: change PPPOL2TP_MSG_* => L2TP_MSG_*
  net: l2tp: deprecate PPPOL2TP_MSG_* in favour of L2TP_MSG_*
  net: l2tp: export debug flags to UAPI
  net: ethernet: stmmac: remove private tx queue lock
  net: ethernet: sxgbe: remove private tx queue lock
  net: bridge: shorten ageing time on topology change
  net: bridge: add helper to set topology change
  net: bridge: add helper to offload ageing time
  net: nicvf: use new api ethtool_{get|set}_link_ksettings
  net: ethernet: ti: cpsw: sync rates for channels in dual emac mode
  net: ethernet: ti: cpsw: re-split res only when speed is changed
  net: ethernet: ti: cpsw: combine budget and weight split and check
  net: ethernet: ti: cpsw: don't start queue twice
  net: ethernet: ti: cpsw: use same macros to get active slave
  net: mvneta: select GENERIC_ALLOCATOR
  ...

1 files changed, 158 insertions, 24 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 237f3d6a7ddc..4819ec9d95f6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -17,6 +17,7 @@
 #include <linux/license.h>
 #include <linux/filter.h>
 #include <linux/version.h>
+#include <linux/kernel.h>
 
 DEFINE_PER_CPU(int, bpf_prog_active);
 
@@ -137,18 +138,31 @@ static int bpf_map_release(struct inode *inode, struct file *filp)
 static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 {
 	const struct bpf_map *map = filp->private_data;
+	const struct bpf_array *array;
+	u32 owner_prog_type = 0;
+
+	if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
+		array = container_of(map, struct bpf_array, map);
+		owner_prog_type = array->owner_prog_type;
+	}
 
 	seq_printf(m,
 		   "map_type:\t%u\n"
 		   "key_size:\t%u\n"
 		   "value_size:\t%u\n"
 		   "max_entries:\t%u\n"
-		   "map_flags:\t%#x\n",
+		   "map_flags:\t%#x\n"
+		   "memlock:\t%llu\n",
 		   map->map_type,
 		   map->key_size,
 		   map->value_size,
 		   map->max_entries,
-		   map->map_flags);
+		   map->map_flags,
+		   map->pages * 1ULL << PAGE_SHIFT);
+
+	if (owner_prog_type)
+		seq_printf(m, "owner_prog_type:\t%u\n",
+			   owner_prog_type);
 }
 #endif
 
@@ -254,12 +268,6 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd)
 	return map;
 }
 
-/* helper to convert user pointers passed inside __aligned_u64 fields */
-static void __user *u64_to_ptr(__u64 val)
-{
-	return (void __user *) (unsigned long) val;
-}
-
 int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
 {
 	return -ENOTSUPP;
@@ -270,8 +278,8 @@ int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
 
 static int map_lookup_elem(union bpf_attr *attr)
 {
-	void __user *ukey = u64_to_ptr(attr->key);
-	void __user *uvalue = u64_to_ptr(attr->value);
+	void __user *ukey = u64_to_user_ptr(attr->key);
+	void __user *uvalue = u64_to_user_ptr(attr->value);
 	int ufd = attr->map_fd;
 	struct bpf_map *map;
 	void *key, *value, *ptr;
@@ -297,6 +305,7 @@ static int map_lookup_elem(union bpf_attr *attr)
 		goto free_key;
 
 	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
 	    map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
 		value_size = round_up(map->value_size, 8) * num_possible_cpus();
 	else
@@ -307,7 +316,8 @@ static int map_lookup_elem(union bpf_attr *attr)
 	if (!value)
 		goto free_key;
 
-	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) {
+	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
 		err = bpf_percpu_hash_copy(map, key, value);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
 		err = bpf_percpu_array_copy(map, key, value);
@@ -344,8 +354,8 @@ err_put:
 
 static int map_update_elem(union bpf_attr *attr)
 {
-	void __user *ukey = u64_to_ptr(attr->key);
-	void __user *uvalue = u64_to_ptr(attr->value);
+	void __user *ukey = u64_to_user_ptr(attr->key);
+	void __user *uvalue = u64_to_user_ptr(attr->value);
 	int ufd = attr->map_fd;
 	struct bpf_map *map;
 	void *key, *value;
@@ -371,6 +381,7 @@ static int map_update_elem(union bpf_attr *attr)
 		goto free_key;
 
 	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
 	    map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
 		value_size = round_up(map->value_size, 8) * num_possible_cpus();
 	else
@@ -390,7 +401,8 @@ static int map_update_elem(union bpf_attr *attr)
 	 */
 	preempt_disable();
 	__this_cpu_inc(bpf_prog_active);
-	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) {
+	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
 		err = bpf_percpu_hash_update(map, key, value, attr->flags);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
 		err = bpf_percpu_array_update(map, key, value, attr->flags);
@@ -422,7 +434,7 @@ err_put:
 
 static int map_delete_elem(union bpf_attr *attr)
 {
-	void __user *ukey = u64_to_ptr(attr->key);
+	void __user *ukey = u64_to_user_ptr(attr->key);
 	int ufd = attr->map_fd;
 	struct bpf_map *map;
 	struct fd f;
@@ -466,8 +478,8 @@ err_put:
 
 static int map_get_next_key(union bpf_attr *attr)
 {
-	void __user *ukey = u64_to_ptr(attr->key);
-	void __user *unext_key = u64_to_ptr(attr->next_key);
+	void __user *ukey = u64_to_user_ptr(attr->key);
+	void __user *unext_key = u64_to_user_ptr(attr->next_key);
 	int ufd = attr->map_fd;
 	struct bpf_map *map;
 	void *key, *next_key;
@@ -567,6 +579,8 @@ static void fixup_bpf_calls(struct bpf_prog *prog)
 				prog->dst_needed = 1;
 			if (insn->imm == BPF_FUNC_get_prandom_u32)
 				bpf_user_rnd_init_once();
+			if (insn->imm == BPF_FUNC_xdp_adjust_head)
+				prog->xdp_adjust_head = 1;
 			if (insn->imm == BPF_FUNC_tail_call) {
 				/* mark bpf_tail_call as different opcode
 				 * to avoid conditional branch in
@@ -650,8 +664,30 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+#ifdef CONFIG_PROC_FS
+static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
+{
+	const struct bpf_prog *prog = filp->private_data;
+	char prog_digest[sizeof(prog->digest) * 2 + 1] = { };
+
+	bin2hex(prog_digest, prog->digest, sizeof(prog->digest));
+	seq_printf(m,
+		   "prog_type:\t%u\n"
+		   "prog_jited:\t%u\n"
+		   "prog_digest:\t%s\n"
+		   "memlock:\t%llu\n",
+		   prog->type,
+		   prog->jited,
+		   prog_digest,
+		   prog->pages * 1ULL << PAGE_SHIFT);
+}
+#endif
+
 static const struct file_operations bpf_prog_fops = {
-        .release = bpf_prog_release,
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= bpf_prog_show_fdinfo,
+#endif
+	.release	= bpf_prog_release,
 };
 
 int bpf_prog_new_fd(struct bpf_prog *prog)
@@ -682,10 +718,22 @@ struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_add);
 
+void bpf_prog_sub(struct bpf_prog *prog, int i)
+{
+	/* Only to be used for undoing previous bpf_prog_add() in some
+	 * error path. We still know that another entity in our call
+	 * path holds a reference to the program, thus atomic_sub() can
+	 * be safely used in such cases!
+	 */
+	WARN_ON(atomic_sub_return(i, &prog->aux->refcnt) == 0);
+}
+EXPORT_SYMBOL_GPL(bpf_prog_sub);
+
 struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
 {
 	return bpf_prog_add(prog, 1);
 }
+EXPORT_SYMBOL_GPL(bpf_prog_inc);
 
 static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type)
 {
@@ -732,7 +780,7 @@ static int bpf_prog_load(union bpf_attr *attr)
 		return -EINVAL;
 
 	/* copy eBPF program license from user space */
-	if (strncpy_from_user(license, u64_to_ptr(attr->license),
+	if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
 			      sizeof(license) - 1) < 0)
 		return -EFAULT;
 	license[sizeof(license) - 1] = 0;
@@ -740,8 +788,8 @@ static int bpf_prog_load(union bpf_attr *attr)
 	/* eBPF programs must be GPL compatible to use GPL-ed functions */
 	is_gpl = license_is_gpl_compatible(license);
 
-	if (attr->insn_cnt >= BPF_MAXINSNS)
-		return -EINVAL;
+	if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS)
+		return -E2BIG;
 
 	if (type == BPF_PROG_TYPE_KPROBE &&
 	    attr->kern_version != LINUX_VERSION_CODE)
@@ -762,7 +810,7 @@ static int bpf_prog_load(union bpf_attr *attr)
 	prog->len = attr->insn_cnt;
 
 	err = -EFAULT;
-	if (copy_from_user(prog->insns, u64_to_ptr(attr->insns),
+	if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns),
 			   prog->len * sizeof(struct bpf_insn)) != 0)
 		goto free_prog;
 
@@ -813,7 +861,7 @@ 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));
+	return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname));
 }
 
 static int bpf_obj_get(const union bpf_attr *attr)
@@ -821,8 +869,84 @@ 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));
+	return bpf_obj_get_user(u64_to_user_ptr(attr->pathname));
+}
+
+#ifdef CONFIG_CGROUP_BPF
+
+#define BPF_PROG_ATTACH_LAST_FIELD attach_type
+
+static int bpf_prog_attach(const union bpf_attr *attr)
+{
+	struct bpf_prog *prog;
+	struct cgroup *cgrp;
+	enum bpf_prog_type ptype;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (CHECK_ATTR(BPF_PROG_ATTACH))
+		return -EINVAL;
+
+	switch (attr->attach_type) {
+	case BPF_CGROUP_INET_INGRESS:
+	case BPF_CGROUP_INET_EGRESS:
+		ptype = BPF_PROG_TYPE_CGROUP_SKB;
+		break;
+	case BPF_CGROUP_INET_SOCK_CREATE:
+		ptype = BPF_PROG_TYPE_CGROUP_SOCK;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	cgrp = cgroup_get_from_fd(attr->target_fd);
+	if (IS_ERR(cgrp)) {
+		bpf_prog_put(prog);
+		return PTR_ERR(cgrp);
+	}
+
+	cgroup_bpf_update(cgrp, prog, attr->attach_type);
+	cgroup_put(cgrp);
+
+	return 0;
+}
+
+#define BPF_PROG_DETACH_LAST_FIELD attach_type
+
+static int bpf_prog_detach(const union bpf_attr *attr)
+{
+	struct cgroup *cgrp;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (CHECK_ATTR(BPF_PROG_DETACH))
+		return -EINVAL;
+
+	switch (attr->attach_type) {
+	case BPF_CGROUP_INET_INGRESS:
+	case BPF_CGROUP_INET_EGRESS:
+	case BPF_CGROUP_INET_SOCK_CREATE:
+		cgrp = cgroup_get_from_fd(attr->target_fd);
+		if (IS_ERR(cgrp))
+			return PTR_ERR(cgrp);
+
+		cgroup_bpf_update(cgrp, NULL, attr->attach_type);
+		cgroup_put(cgrp);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
 }
+#endif /* CONFIG_CGROUP_BPF */
 
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
@@ -890,6 +1014,16 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_OBJ_GET:
 		err = bpf_obj_get(&attr);
 		break;
+
+#ifdef CONFIG_CGROUP_BPF
+	case BPF_PROG_ATTACH:
+		err = bpf_prog_attach(&attr);
+		break;
+	case BPF_PROG_DETACH:
+		err = bpf_prog_detach(&attr);
+		break;
+#endif
+
 	default:
 		err = -EINVAL;
 		break;