diff --git a/Documentation/bpf/bpf_devel_QA.txt b/Documentation/bpf/bpf_devel_QA.txt
index 1a0b704e1a38..da57601153a0 100644
--- a/Documentation/bpf/bpf_devel_QA.txt
+++ b/Documentation/bpf/bpf_devel_QA.txt
@@ -557,6 +557,14 @@ A: Although LLVM IR generation and optimization try to stay architecture
        pulls in some header files containing file scope host assembly codes.
      - You can add "-fno-jump-tables" to work around the switch table issue.
 
-   Otherwise, you can use bpf target.
+   Otherwise, you can use bpf target. Additionally, you _must_ use bpf target
+   when:
+
+     - Your program uses data structures with pointer or long / unsigned long
+       types that interface with BPF helpers or context data structures. Access
+       into these structures is verified by the BPF verifier and may result
+       in verification failures if the native architecture is not aligned with
+       the BPF architecture, e.g. 64-bit. An example of this is
+       BPF_PROG_TYPE_SK_MSG require '-target bpf'
 
 Happy BPF hacking!
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index b725154182cc..abce27ceb411 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1027,7 +1027,17 @@ emit_cond_jmp:		/* convert BPF opcode to x86 */
 			break;
 
 		case BPF_JMP | BPF_JA:
-			jmp_offset = addrs[i + insn->off] - addrs[i];
+			if (insn->off == -1)
+				/* -1 jmp instructions will always jump
+				 * backwards two bytes. Explicitly handling
+				 * this case avoids wasting too many passes
+				 * when there are long sequences of replaced
+				 * dead code.
+				 */
+				jmp_offset = -2;
+			else
+				jmp_offset = addrs[i + insn->off] - addrs[i];
+
 			if (!jmp_offset)
 				/* optimize out nop jumps */
 				break;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 486e65e3db26..469b20e1dd7e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -31,6 +31,7 @@ struct bpf_map_ops {
 	void (*map_release)(struct bpf_map *map, struct file *map_file);
 	void (*map_free)(struct bpf_map *map);
 	int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
+	void (*map_release_uref)(struct bpf_map *map);
 
 	/* funcs callable from userspace and from eBPF programs */
 	void *(*map_lookup_elem)(struct bpf_map *map, void *key);
@@ -351,6 +352,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 		struct bpf_prog **_prog, *__prog;	\
 		struct bpf_prog_array *_array;		\
 		u32 _ret = 1;				\
+		preempt_disable();			\
 		rcu_read_lock();			\
 		_array = rcu_dereference(array);	\
 		if (unlikely(check_non_null && !_array))\
@@ -362,6 +364,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 		}					\
 _out:							\
 		rcu_read_unlock();			\
+		preempt_enable_no_resched();		\
 		_ret;					\
 	 })
 
@@ -434,7 +437,6 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
 int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
 				 void *key, void *value, u64 map_flags);
 int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
-void bpf_fd_array_map_clear(struct bpf_map *map);
 int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
 				void *key, void *value, u64 map_flags);
 int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 14750e7c5ee4..027107f4be53 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -476,7 +476,7 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr)
 }
 
 /* decrement refcnt of all bpf_progs that are stored in this map */
-void bpf_fd_array_map_clear(struct bpf_map *map)
+static void bpf_fd_array_map_clear(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
@@ -495,6 +495,7 @@ const struct bpf_map_ops prog_array_map_ops = {
 	.map_fd_get_ptr = prog_fd_array_get_ptr,
 	.map_fd_put_ptr = prog_fd_array_put_ptr,
 	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
+	.map_release_uref = bpf_fd_array_map_clear,
 };
 
 static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index a3b21385e947..634415c7fbcd 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -43,6 +43,7 @@
 #include <net/tcp.h>
 #include <linux/ptr_ring.h>
 #include <net/inet_common.h>
+#include <linux/sched/signal.h>
 
 #define SOCK_CREATE_FLAG_MASK \
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
@@ -523,8 +524,6 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
 	i = md->sg_start;
 
 	do {
-		r->sg_data[i] = md->sg_data[i];
-
 		size = (apply && apply_bytes < md->sg_data[i].length) ?
 			apply_bytes : md->sg_data[i].length;
 
@@ -535,6 +534,7 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes,
 		}
 
 		sk_mem_charge(sk, size);
+		r->sg_data[i] = md->sg_data[i];
 		r->sg_data[i].length = size;
 		md->sg_data[i].length -= size;
 		md->sg_data[i].offset += size;
@@ -732,6 +732,26 @@ out_err:
 	return err;
 }
 
+static int bpf_wait_data(struct sock *sk,
+			 struct smap_psock *psk, int flags,
+			 long timeo, int *err)
+{
+	int rc;
+
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+	add_wait_queue(sk_sleep(sk), &wait);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	rc = sk_wait_event(sk, &timeo,
+			   !list_empty(&psk->ingress) ||
+			   !skb_queue_empty(&sk->sk_receive_queue),
+			   &wait);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+	remove_wait_queue(sk_sleep(sk), &wait);
+
+	return rc;
+}
+
 static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			   int nonblock, int flags, int *addr_len)
 {
@@ -755,6 +775,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 
 	lock_sock(sk);
+bytes_ready:
 	while (copied != len) {
 		struct scatterlist *sg;
 		struct sk_msg_buff *md;
@@ -809,6 +830,28 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 	}
 
+	if (!copied) {
+		long timeo;
+		int data;
+		int err = 0;
+
+		timeo = sock_rcvtimeo(sk, nonblock);
+		data = bpf_wait_data(sk, psock, flags, timeo, &err);
+
+		if (data) {
+			if (!skb_queue_empty(&sk->sk_receive_queue)) {
+				release_sock(sk);
+				smap_release_sock(psock, sk);
+				copied = tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+				return copied;
+			}
+			goto bytes_ready;
+		}
+
+		if (err)
+			copied = err;
+	}
+
 	release_sock(sk);
 	smap_release_sock(psock, sk);
 	return copied;
@@ -1831,7 +1874,7 @@ static int sock_map_update_elem(struct bpf_map *map,
 	return err;
 }
 
-static void sock_map_release(struct bpf_map *map, struct file *map_file)
+static void sock_map_release(struct bpf_map *map)
 {
 	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
 	struct bpf_prog *orig;
@@ -1855,7 +1898,7 @@ const struct bpf_map_ops sock_map_ops = {
 	.map_get_next_key = sock_map_get_next_key,
 	.map_update_elem = sock_map_update_elem,
 	.map_delete_elem = sock_map_delete_elem,
-	.map_release = sock_map_release,
+	.map_release_uref = sock_map_release,
 };
 
 BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4ca46df19c9a..ebfe9f29dae8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -257,8 +257,8 @@ static void bpf_map_free_deferred(struct work_struct *work)
 static void bpf_map_put_uref(struct bpf_map *map)
 {
 	if (atomic_dec_and_test(&map->usercnt)) {
-		if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
-			bpf_fd_array_map_clear(map);
+		if (map->ops->map_release_uref)
+			map->ops->map_release_uref(map);
 	}
 }
 
diff --git a/net/core/filter.c b/net/core/filter.c
index d31aff93270d..e77c30ca491d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3240,6 +3240,7 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
 	skb_dst_set(skb, (struct dst_entry *) md);
 
 	info = &md->u.tun_info;
+	memset(info, 0, sizeof(*info));
 	info->mode = IP_TUNNEL_INFO_TX;
 
 	info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE;
diff --git a/samples/sockmap/Makefile b/samples/sockmap/Makefile
index 9bf2881bd11b..fa53f4d77834 100644
--- a/samples/sockmap/Makefile
+++ b/samples/sockmap/Makefile
@@ -65,11 +65,14 @@ $(src)/*.c: verify_target_bpf
 # asm/sysreg.h - inline assembly used by it is incompatible with llvm.
 # But, there is no easy way to fix it, so just exclude it since it is
 # useless for BPF samples.
+#
+# -target bpf option required with SK_MSG programs, this is to ensure
+#  reading 'void *' data types for data and data_end are __u64 reads.
 $(obj)/%.o: $(src)/%.c
 	$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
 		-D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
 		-Wno-compare-distinct-pointer-types \
 		-Wno-gnu-variable-sized-type-not-at-end \
 		-Wno-address-of-packed-member -Wno-tautological-compare \
-		-Wno-unknown-warning-option \
-		-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
+		-Wno-unknown-warning-option -O2 -target bpf \
+		-emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index 1ea545965ee3..53b60ad452f5 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -76,6 +76,8 @@ $(OUTPUT)bpf_asm: $(OUTPUT)bpf_asm.o $(OUTPUT)bpf_exp.yacc.o $(OUTPUT)bpf_exp.le
 	$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $^
 
 $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c
+$(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c
+$(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c
 
 clean: bpftool_clean
 	$(call QUIET_CLEAN, bpf-progs)