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

Pull networking updates from David Miller:

 1) Add TX fast path in mac80211, from Johannes Berg.

 2) Add TSO/GRO support to ibmveth, from Thomas Falcon

 3) Move away from cached routes in ipv6, just like ipv4, from Martin
    KaFai Lau.

 4) Lots of new rhashtable tests, from Thomas Graf.

 5) Run ingress qdisc lockless, from Alexei Starovoitov.

 6) Allow servers to fetch TCP packet headers for SYN packets of new
    connections, for fingerprinting.  From Eric Dumazet.

 7) Add mode parameter to pktgen, for testing receive.  From Alexei
    Starovoitov.

 8) Cache access optimizations via simplifications of build_skb(), from
    Alexander Duyck.

 9) Move page frag allocator under mm/, also from Alexander.

10) Add xmit_more support to hv_netvsc, from KY Srinivasan.

11) Add a counter guard in case we try to perform endless reclassify
    loops in the packet scheduler.

12) Extern flow dissector to be programmable and use it in new "Flower"
    classifier.  From Jiri Pirko.

13) AF_PACKET fanout rollover fixes, performance improvements, and new
    statistics.  From Willem de Bruijn.

14) Add netdev driver for GENEVE tunnels, from John W Linville.

15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso.

16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet.

17) Add an ECN retry fallback for the initial TCP handshake, from Daniel
    Borkmann.

18) Add tail call support to BPF, from Alexei Starovoitov.

19) Add several pktgen helper scripts, from Jesper Dangaard Brouer.

20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa.

21) Favor even port numbers for allocation to connect() requests, and
    odd port numbers for bind(0), in an effort to help avoid
    ip_local_port_range exhaustion.  From Eric Dumazet.

22) Add Cavium ThunderX driver, from Sunil Goutham.

23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata,
    from Alexei Starovoitov.

24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai.

25) Double TCP Small Queues default to 256K to accomodate situations
    like the XEN driver and wireless aggregation.  From Wei Liu.

26) Add more entropy inputs to flow dissector, from Tom Herbert.

27) Add CDG congestion control algorithm to TCP, from Kenneth Klette
    Jonassen.

28) Convert ipset over to RCU locking, from Jozsef Kadlecsik.

29) Track and act upon link status of ipv4 route nexthops, from Andy
    Gospodarek.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits)
  bridge: vlan: flush the dynamically learned entries on port vlan delete
  bridge: multicast: add a comment to br_port_state_selection about blocking state
  net: inet_diag: export IPV6_V6ONLY sockopt
  stmmac: troubleshoot unexpected bits in des0 & des1
  net: ipv4 sysctl option to ignore routes when nexthop link is down
  net: track link-status of ipv4 nexthops
  net: switchdev: ignore unsupported bridge flags
  net: Cavium: Fix MAC address setting in shutdown state
  drivers: net: xgene: fix for ACPI support without ACPI
  ip: report the original address of ICMP messages
  net/mlx5e: Prefetch skb data on RX
  net/mlx5e: Pop cq outside mlx5e_get_cqe
  net/mlx5e: Remove mlx5e_cq.sqrq back-pointer
  net/mlx5e: Remove extra spaces
  net/mlx5e: Avoid TX CQE generation if more xmit packets expected
  net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion
  net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq()
  net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them
  net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues
  net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device
  ...

7 files changed, 413 insertions, 118 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 8a6616583f38..cb31229a6fa4 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -14,12 +14,7 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
-
-struct bpf_array {
-	struct bpf_map map;
-	u32 elem_size;
-	char value[0] __aligned(8);
-};
+#include <linux/filter.h>
 
 /* Called from syscall */
 static struct bpf_map *array_map_alloc(union bpf_attr *attr)
@@ -154,3 +149,109 @@ static int __init register_array_map(void)
 	return 0;
 }
 late_initcall(register_array_map);
+
+static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+{
+	/* only bpf_prog file descriptors can be stored in prog_array map */
+	if (attr->value_size != sizeof(u32))
+		return ERR_PTR(-EINVAL);
+	return array_map_alloc(attr);
+}
+
+static void prog_array_map_free(struct bpf_map *map)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	int i;
+
+	synchronize_rcu();
+
+	/* make sure it's empty */
+	for (i = 0; i < array->map.max_entries; i++)
+		BUG_ON(array->prog[i] != NULL);
+	kvfree(array);
+}
+
+static void *prog_array_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return NULL;
+}
+
+/* only called from syscall */
+static int prog_array_map_update_elem(struct bpf_map *map, void *key,
+				      void *value, u64 map_flags)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct bpf_prog *prog, *old_prog;
+	u32 index = *(u32 *)key, ufd;
+
+	if (map_flags != BPF_ANY)
+		return -EINVAL;
+
+	if (index >= array->map.max_entries)
+		return -E2BIG;
+
+	ufd = *(u32 *)value;
+	prog = bpf_prog_get(ufd);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	if (!bpf_prog_array_compatible(array, prog)) {
+		bpf_prog_put(prog);
+		return -EINVAL;
+	}
+
+	old_prog = xchg(array->prog + index, prog);
+	if (old_prog)
+		bpf_prog_put_rcu(old_prog);
+
+	return 0;
+}
+
+static int prog_array_map_delete_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct bpf_prog *old_prog;
+	u32 index = *(u32 *)key;
+
+	if (index >= array->map.max_entries)
+		return -E2BIG;
+
+	old_prog = xchg(array->prog + index, NULL);
+	if (old_prog) {
+		bpf_prog_put_rcu(old_prog);
+		return 0;
+	} else {
+		return -ENOENT;
+	}
+}
+
+/* decrement refcnt of all bpf_progs that are stored in this map */
+void bpf_prog_array_map_clear(struct bpf_map *map)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	int i;
+
+	for (i = 0; i < array->map.max_entries; i++)
+		prog_array_map_delete_elem(map, &i);
+}
+
+static const struct bpf_map_ops prog_array_ops = {
+	.map_alloc = prog_array_map_alloc,
+	.map_free = prog_array_map_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = prog_array_map_lookup_elem,
+	.map_update_elem = prog_array_map_update_elem,
+	.map_delete_elem = prog_array_map_delete_elem,
+};
+
+static struct bpf_map_type_list prog_array_type __read_mostly = {
+	.ops = &prog_array_ops,
+	.type = BPF_MAP_TYPE_PROG_ARRAY,
+};
+
+static int __init register_prog_array_map(void)
+{
+	bpf_register_map_type(&prog_array_type);
+	return 0;
+}
+late_initcall(register_prog_array_map);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 54f0e7fcd0e2..c5bedc82bc1c 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -26,9 +26,10 @@
 #include <linux/vmalloc.h>
 #include <linux/random.h>
 #include <linux/moduleloader.h>
-#include <asm/unaligned.h>
 #include <linux/bpf.h>
 
+#include <asm/unaligned.h>
+
 /* Registers */
 #define BPF_R0	regs[BPF_REG_0]
 #define BPF_R1	regs[BPF_REG_1]
@@ -62,6 +63,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
 		ptr = skb_network_header(skb) + k - SKF_NET_OFF;
 	else if (k >= SKF_LL_OFF)
 		ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
+
 	if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
 		return ptr;
 
@@ -244,6 +246,7 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn)
 		[BPF_ALU64 | BPF_NEG] = &&ALU64_NEG,
 		/* Call instruction */
 		[BPF_JMP | BPF_CALL] = &&JMP_CALL,
+		[BPF_JMP | BPF_CALL | BPF_X] = &&JMP_TAIL_CALL,
 		/* Jumps */
 		[BPF_JMP | BPF_JA] = &&JMP_JA,
 		[BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X,
@@ -286,6 +289,7 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn)
 		[BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B,
 		[BPF_LD | BPF_IMM | BPF_DW] = &&LD_IMM_DW,
 	};
+	u32 tail_call_cnt = 0;
 	void *ptr;
 	int off;
 
@@ -431,6 +435,30 @@ select_insn:
 						       BPF_R4, BPF_R5);
 		CONT;
 
+	JMP_TAIL_CALL: {
+		struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2;
+		struct bpf_array *array = container_of(map, struct bpf_array, map);
+		struct bpf_prog *prog;
+		u64 index = BPF_R3;
+
+		if (unlikely(index >= array->map.max_entries))
+			goto out;
+
+		if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT))
+			goto out;
+
+		tail_call_cnt++;
+
+		prog = READ_ONCE(array->prog[index]);
+		if (unlikely(!prog))
+			goto out;
+
+		ARG1 = BPF_R1;
+		insn = prog->insnsi;
+		goto select_insn;
+out:
+		CONT;
+	}
 	/* JMP */
 	JMP_JA:
 		insn += insn->off;
@@ -615,25 +643,63 @@ load_byte:
 		return 0;
 }
 
-void __weak bpf_int_jit_compile(struct bpf_prog *prog)
+bool bpf_prog_array_compatible(struct bpf_array *array,
+			       const struct bpf_prog *fp)
 {
+	if (!array->owner_prog_type) {
+		/* There's no owner yet where we could check for
+		 * compatibility.
+		 */
+		array->owner_prog_type = fp->type;
+		array->owner_jited = fp->jited;
+
+		return true;
+	}
+
+	return array->owner_prog_type == fp->type &&
+	       array->owner_jited == fp->jited;
+}
+
+static int bpf_check_tail_call(const struct bpf_prog *fp)
+{
+	struct bpf_prog_aux *aux = fp->aux;
+	int i;
+
+	for (i = 0; i < aux->used_map_cnt; i++) {
+		struct bpf_map *map = aux->used_maps[i];
+		struct bpf_array *array;
+
+		if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
+			continue;
+
+		array = container_of(map, struct bpf_array, map);
+		if (!bpf_prog_array_compatible(array, fp))
+			return -EINVAL;
+	}
+
+	return 0;
 }
 
 /**
- *	bpf_prog_select_runtime - select execution runtime for BPF program
+ *	bpf_prog_select_runtime - select exec runtime for BPF program
  *	@fp: bpf_prog populated with internal BPF program
  *
- * try to JIT internal BPF program, if JIT is not available select interpreter
- * BPF program will be executed via BPF_PROG_RUN() macro
+ * Try to JIT eBPF program, if JIT is not available, use interpreter.
+ * The BPF program will be executed via BPF_PROG_RUN() macro.
  */
-void bpf_prog_select_runtime(struct bpf_prog *fp)
+int bpf_prog_select_runtime(struct bpf_prog *fp)
 {
 	fp->bpf_func = (void *) __bpf_prog_run;
 
-	/* Probe if internal BPF can be JITed */
 	bpf_int_jit_compile(fp);
-	/* Lock whole bpf_prog as read-only */
 	bpf_prog_lock_ro(fp);
+
+	/* The tail call compatibility check can only be done at
+	 * this late stage as we need to determine, if we deal
+	 * with JITed or non JITed program concatenations and not
+	 * all eBPF JITs might immediately support all features.
+	 */
+	return bpf_check_tail_call(fp);
 }
 EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
 
@@ -663,6 +729,29 @@ const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
 
 const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
 const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
+const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
+const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
+const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak;
+const struct bpf_func_proto bpf_get_current_comm_proto __weak;
+const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
+{
+	return NULL;
+}
+
+/* Always built-in helper functions. */
+const struct bpf_func_proto bpf_tail_call_proto = {
+	.func		= NULL,
+	.gpl_only	= false,
+	.ret_type	= RET_VOID,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+/* For classic BPF JITs that don't implement bpf_int_jit_compile(). */
+void __weak bpf_int_jit_compile(struct bpf_prog *prog)
+{
+}
 
 /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call
  * skb_copy_bits(), so provide a weak definition of it for NET-less config.
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index bd7f5988ed9c..1447ec09421e 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -13,6 +13,9 @@
 #include <linux/rcupdate.h>
 #include <linux/random.h>
 #include <linux/smp.h>
+#include <linux/ktime.h>
+#include <linux/sched.h>
+#include <linux/uidgid.h>
 
 /* If kernel subsystem is allowing eBPF programs to call this function,
  * inside its own verifier_ops->get_func_proto() callback it should return
@@ -44,11 +47,11 @@ static u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 }
 
 const struct bpf_func_proto bpf_map_lookup_elem_proto = {
-	.func = bpf_map_lookup_elem,
-	.gpl_only = false,
-	.ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
-	.arg1_type = ARG_CONST_MAP_PTR,
-	.arg2_type = ARG_PTR_TO_MAP_KEY,
+	.func		= bpf_map_lookup_elem,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_MAP_KEY,
 };
 
 static u64 bpf_map_update_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
@@ -63,13 +66,13 @@ static u64 bpf_map_update_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 }
 
 const struct bpf_func_proto bpf_map_update_elem_proto = {
-	.func = bpf_map_update_elem,
-	.gpl_only = false,
-	.ret_type = RET_INTEGER,
-	.arg1_type = ARG_CONST_MAP_PTR,
-	.arg2_type = ARG_PTR_TO_MAP_KEY,
-	.arg3_type = ARG_PTR_TO_MAP_VALUE,
-	.arg4_type = ARG_ANYTHING,
+	.func		= bpf_map_update_elem,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_MAP_KEY,
+	.arg3_type	= ARG_PTR_TO_MAP_VALUE,
+	.arg4_type	= ARG_ANYTHING,
 };
 
 static u64 bpf_map_delete_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
@@ -83,11 +86,11 @@ static u64 bpf_map_delete_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 }
 
 const struct bpf_func_proto bpf_map_delete_elem_proto = {
-	.func = bpf_map_delete_elem,
-	.gpl_only = false,
-	.ret_type = RET_INTEGER,
-	.arg1_type = ARG_CONST_MAP_PTR,
-	.arg2_type = ARG_PTR_TO_MAP_KEY,
+	.func		= bpf_map_delete_elem,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_MAP_KEY,
 };
 
 static u64 bpf_get_prandom_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
@@ -111,3 +114,71 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 };
+
+static u64 bpf_ktime_get_ns(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	/* NMI safe access to clock monotonic */
+	return ktime_get_mono_fast_ns();
+}
+
+const struct bpf_func_proto bpf_ktime_get_ns_proto = {
+	.func		= bpf_ktime_get_ns,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+};
+
+static u64 bpf_get_current_pid_tgid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	struct task_struct *task = current;
+
+	if (!task)
+		return -EINVAL;
+
+	return (u64) task->tgid << 32 | task->pid;
+}
+
+const struct bpf_func_proto bpf_get_current_pid_tgid_proto = {
+	.func		= bpf_get_current_pid_tgid,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+static u64 bpf_get_current_uid_gid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	struct task_struct *task = current;
+	kuid_t uid;
+	kgid_t gid;
+
+	if (!task)
+		return -EINVAL;
+
+	current_uid_gid(&uid, &gid);
+	return (u64) from_kgid(&init_user_ns, gid) << 32 |
+		from_kuid(&init_user_ns, uid);
+}
+
+const struct bpf_func_proto bpf_get_current_uid_gid_proto = {
+	.func		= bpf_get_current_uid_gid,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+static u64 bpf_get_current_comm(u64 r1, u64 size, u64 r3, u64 r4, u64 r5)
+{
+	struct task_struct *task = current;
+	char *buf = (char *) (long) r1;
+
+	if (!task)
+		return -EINVAL;
+
+	memcpy(buf, task->comm, min_t(size_t, size, sizeof(task->comm)));
+	return 0;
+}
+
+const struct bpf_func_proto bpf_get_current_comm_proto = {
+	.func		= bpf_get_current_comm,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_STACK,
+	.arg2_type	= ARG_CONST_STACK_SIZE,
+};
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 3bae6c591914..a1b14d197a4f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -68,6 +68,12 @@ static int bpf_map_release(struct inode *inode, struct file *filp)
 {
 	struct bpf_map *map = filp->private_data;
 
+	if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
+		/* prog_array stores refcnt-ed bpf_prog pointers
+		 * release them all when user space closes prog_array_fd
+		 */
+		bpf_prog_array_map_clear(map);
+
 	bpf_map_put(map);
 	return 0;
 }
@@ -392,6 +398,19 @@ static void fixup_bpf_calls(struct bpf_prog *prog)
 			 */
 			BUG_ON(!prog->aux->ops->get_func_proto);
 
+			if (insn->imm == BPF_FUNC_tail_call) {
+				/* mark bpf_tail_call as different opcode
+				 * to avoid conditional branch in
+				 * interpeter for every normal call
+				 * and to prevent accidental JITing by
+				 * JIT compiler that doesn't support
+				 * bpf_tail_call yet
+				 */
+				insn->imm = 0;
+				insn->code |= BPF_X;
+				continue;
+			}
+
 			fn = prog->aux->ops->get_func_proto(insn->imm);
 			/* all functions that have prototype and verifier allowed
 			 * programs to call them, must be real in-kernel functions
@@ -413,6 +432,23 @@ static void free_used_maps(struct bpf_prog_aux *aux)
 	kfree(aux->used_maps);
 }
 
+static void __prog_put_rcu(struct rcu_head *rcu)
+{
+	struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
+
+	free_used_maps(aux);
+	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);
+	}
+}
+
 void bpf_prog_put(struct bpf_prog *prog)
 {
 	if (atomic_dec_and_test(&prog->aux->refcnt)) {
@@ -426,7 +462,7 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
 {
 	struct bpf_prog *prog = filp->private_data;
 
-	bpf_prog_put(prog);
+	bpf_prog_put_rcu(prog);
 	return 0;
 }
 
@@ -532,7 +568,9 @@ static int bpf_prog_load(union bpf_attr *attr)
 	fixup_bpf_calls(prog);
 
 	/* eBPF program is ready to be JITed */
-	bpf_prog_select_runtime(prog);
+	err = bpf_prog_select_runtime(prog);
+	if (err < 0)
+		goto free_used_maps;
 
 	err = anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC);
 	if (err < 0)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 47dcd3aa6e23..039d866fd36a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -907,6 +907,23 @@ static int check_call(struct verifier_env *env, int func_id)
 			fn->ret_type, func_id);
 		return -EINVAL;
 	}
+
+	if (map && map->map_type == BPF_MAP_TYPE_PROG_ARRAY &&
+	    func_id != BPF_FUNC_tail_call)
+		/* prog_array map type needs extra care:
+		 * only allow to pass it into bpf_tail_call() for now.
+		 * bpf_map_delete_elem() can be allowed in the future,
+		 * while bpf_map_update_elem() must only be done via syscall
+		 */
+		return -EINVAL;
+
+	if (func_id == BPF_FUNC_tail_call &&
+	    map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
+		/* don't allow any other map type to be passed into
+		 * bpf_tail_call()
+		 */
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -1675,6 +1692,8 @@ static int do_check(struct verifier_env *env)
 			}
 
 		} else if (class == BPF_STX) {
+			enum bpf_reg_type dst_reg_type;
+
 			if (BPF_MODE(insn->code) == BPF_XADD) {
 				err = check_xadd(env, insn);
 				if (err)
@@ -1683,11 +1702,6 @@ static int do_check(struct verifier_env *env)
 				continue;
 			}
 
-			if (BPF_MODE(insn->code) != BPF_MEM ||
-			    insn->imm != 0) {
-				verbose("BPF_STX uses reserved fields\n");
-				return -EINVAL;
-			}
 			/* check src1 operand */
 			err = check_reg_arg(regs, insn->src_reg, SRC_OP);
 			if (err)
@@ -1697,6 +1711,8 @@ static int do_check(struct verifier_env *env)
 			if (err)
 				return err;
 
+			dst_reg_type = regs[insn->dst_reg].type;
+
 			/* check that memory (dst_reg + off) is writeable */
 			err = check_mem_access(env, insn->dst_reg, insn->off,
 					       BPF_SIZE(insn->code), BPF_WRITE,
@@ -1704,6 +1720,15 @@ static int do_check(struct verifier_env *env)
 			if (err)
 				return err;
 
+			if (insn->imm == 0) {
+				insn->imm = dst_reg_type;
+			} else if (dst_reg_type != insn->imm &&
+				   (dst_reg_type == PTR_TO_CTX ||
+				    insn->imm == PTR_TO_CTX)) {
+				verbose("same insn cannot be used with different pointers\n");
+				return -EINVAL;
+			}
+
 		} else if (class == BPF_ST) {
 			if (BPF_MODE(insn->code) != BPF_MEM ||
 			    insn->src_reg != BPF_REG_0) {
@@ -1822,12 +1847,18 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
 		if (BPF_CLASS(insn->code) == BPF_LDX &&
-		    (BPF_MODE(insn->code) != BPF_MEM ||
-		     insn->imm != 0)) {
+		    (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
 			verbose("BPF_LDX uses reserved fields\n");
 			return -EINVAL;
 		}
 
+		if (BPF_CLASS(insn->code) == BPF_STX &&
+		    ((BPF_MODE(insn->code) != BPF_MEM &&
+		      BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) {
+			verbose("BPF_STX uses reserved fields\n");
+			return -EINVAL;
+		}
+
 		if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
 			struct bpf_map *map;
 			struct fd f;
@@ -1950,12 +1981,17 @@ static int convert_ctx_accesses(struct verifier_env *env)
 	struct bpf_prog *new_prog;
 	u32 cnt;
 	int i;
+	enum bpf_access_type type;
 
 	if (!env->prog->aux->ops->convert_ctx_access)
 		return 0;
 
 	for (i = 0; i < insn_cnt; i++, insn++) {
-		if (insn->code != (BPF_LDX | BPF_MEM | BPF_W))
+		if (insn->code == (BPF_LDX | BPF_MEM | BPF_W))
+			type = BPF_READ;
+		else if (insn->code == (BPF_STX | BPF_MEM | BPF_W))
+			type = BPF_WRITE;
+		else
 			continue;
 
 		if (insn->imm != PTR_TO_CTX) {
@@ -1965,7 +2001,7 @@ static int convert_ctx_accesses(struct verifier_env *env)
 		}
 
 		cnt = env->prog->aux->ops->
-			convert_ctx_access(insn->dst_reg, insn->src_reg,
+			convert_ctx_access(type, insn->dst_reg, insn->src_reg,
 					   insn->off, insn_buf);
 		if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
 			verbose("bpf verifier is misconfigured\n");
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 4f44028943e6..245df6b32b81 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -346,16 +346,13 @@ static inline void seccomp_sync_threads(void)
  */
 static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
 {
-	struct seccomp_filter *filter;
-	unsigned long fp_size;
-	struct sock_filter *fp;
-	int new_len;
-	long ret;
+	struct seccomp_filter *sfilter;
+	int ret;
 
 	if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
 		return ERR_PTR(-EINVAL);
+
 	BUG_ON(INT_MAX / fprog->len < sizeof(struct sock_filter));
-	fp_size = fprog->len * sizeof(struct sock_filter);
 
 	/*
 	 * Installing a seccomp filter requires that the task has
@@ -368,60 +365,21 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
 				     CAP_SYS_ADMIN) != 0)
 		return ERR_PTR(-EACCES);
 
-	fp = kzalloc(fp_size, GFP_KERNEL|__GFP_NOWARN);
-	if (!fp)
-		return ERR_PTR(-ENOMEM);
-
-	/* Copy the instructions from fprog. */
-	ret = -EFAULT;
-	if (copy_from_user(fp, fprog->filter, fp_size))
-		goto free_prog;
-
-	/* Check and rewrite the fprog via the skb checker */
-	ret = bpf_check_classic(fp, fprog->len);
-	if (ret)
-		goto free_prog;
-
-	/* Check and rewrite the fprog for seccomp use */
-	ret = seccomp_check_filter(fp, fprog->len);
-	if (ret)
-		goto free_prog;
-
-	/* Convert 'sock_filter' insns to 'bpf_insn' insns */
-	ret = bpf_convert_filter(fp, fprog->len, NULL, &new_len);
-	if (ret)
-		goto free_prog;
-
 	/* Allocate a new seccomp_filter */
-	ret = -ENOMEM;
-	filter = kzalloc(sizeof(struct seccomp_filter),
-			 GFP_KERNEL|__GFP_NOWARN);
-	if (!filter)
-		goto free_prog;
-
-	filter->prog = bpf_prog_alloc(bpf_prog_size(new_len), __GFP_NOWARN);
-	if (!filter->prog)
-		goto free_filter;
-
-	ret = bpf_convert_filter(fp, fprog->len, filter->prog->insnsi, &new_len);
-	if (ret)
-		goto free_filter_prog;
-
-	kfree(fp);
-	atomic_set(&filter->usage, 1);
-	filter->prog->len = new_len;
+	sfilter = kzalloc(sizeof(*sfilter), GFP_KERNEL | __GFP_NOWARN);
+	if (!sfilter)
+		return ERR_PTR(-ENOMEM);
 
-	bpf_prog_select_runtime(filter->prog);
+	ret = bpf_prog_create_from_user(&sfilter->prog, fprog,
+					seccomp_check_filter);
+	if (ret < 0) {
+		kfree(sfilter);
+		return ERR_PTR(ret);
+	}
 
-	return filter;
+	atomic_set(&sfilter->usage, 1);
 
-free_filter_prog:
-	__bpf_prog_free(filter->prog);
-free_filter:
-	kfree(filter);
-free_prog:
-	kfree(fp);
-	return ERR_PTR(ret);
+	return sfilter;
 }
 
 /**
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 2d56ce501632..88a041adee90 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -79,18 +79,6 @@ static const struct bpf_func_proto bpf_probe_read_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-static u64 bpf_ktime_get_ns(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
-{
-	/* NMI safe access to clock monotonic */
-	return ktime_get_mono_fast_ns();
-}
-
-static const struct bpf_func_proto bpf_ktime_get_ns_proto = {
-	.func		= bpf_ktime_get_ns,
-	.gpl_only	= true,
-	.ret_type	= RET_INTEGER,
-};
-
 /*
  * limited trace_printk()
  * only %d %u %x %ld %lu %lx %lld %llu %llx %p conversion specifiers allowed
@@ -159,6 +147,17 @@ static const struct bpf_func_proto bpf_trace_printk_proto = {
 	.arg2_type	= ARG_CONST_STACK_SIZE,
 };
 
+const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
+{
+	/*
+	 * this program might be calling bpf_trace_printk,
+	 * so allocate per-cpu printk buffers
+	 */
+	trace_printk_init_buffers();
+
+	return &bpf_trace_printk_proto;
+}
+
 static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -172,15 +171,18 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 		return &bpf_probe_read_proto;
 	case BPF_FUNC_ktime_get_ns:
 		return &bpf_ktime_get_ns_proto;
-
+	case BPF_FUNC_tail_call:
+		return &bpf_tail_call_proto;
+	case BPF_FUNC_get_current_pid_tgid:
+		return &bpf_get_current_pid_tgid_proto;
+	case BPF_FUNC_get_current_uid_gid:
+		return &bpf_get_current_uid_gid_proto;
+	case BPF_FUNC_get_current_comm:
+		return &bpf_get_current_comm_proto;
 	case BPF_FUNC_trace_printk:
-		/*
-		 * this program might be calling bpf_trace_printk,
-		 * so allocate per-cpu printk buffers
-		 */
-		trace_printk_init_buffers();
-
-		return &bpf_trace_printk_proto;
+		return bpf_get_trace_printk_proto();
+	case BPF_FUNC_get_smp_processor_id:
+		return &bpf_get_smp_processor_id_proto;
 	default:
 		return NULL;
 	}