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

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-11-20

The following pull-request contains BPF updates for your *net-next* tree.

We've added 81 non-merge commits during the last 17 day(s) which contain
a total of 120 files changed, 4958 insertions(+), 1081 deletions(-).

There are 3 trivial conflicts, resolve it by always taking the chunk from
196e8ca74886c433:

<<<<<<< HEAD
=======
void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
>>>>>>> 196e8ca74886c433dcfc64a809707074b936aaf5

<<<<<<< HEAD
void *bpf_map_area_alloc(u64 size, int numa_node)
=======
static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)
>>>>>>> 196e8ca74886c433dcfc64a809707074b936aaf5

<<<<<<< HEAD
        if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
=======
        /* kmalloc()'ed memory can't be mmap()'ed */
        if (!mmapable && size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
>>>>>>> 196e8ca74886c433dcfc64a809707074b936aaf5

The main changes are:

1) Addition of BPF trampoline which works as a bridge between kernel functions,
   BPF programs and other BPF programs along with two new use cases: i) fentry/fexit
   BPF programs for tracing with practically zero overhead to call into BPF (as
   opposed to k[ret]probes) and ii) attachment of the former to networking related
   programs to see input/output of networking programs (covering xdpdump use case),
   from Alexei Starovoitov.

2) BPF array map mmap support and use in libbpf for global data maps; also a big
   batch of libbpf improvements, among others, support for reading bitfields in a
   relocatable manner (via libbpf's CO-RE helper API), from Andrii Nakryiko.

3) Extend s390x JIT with usage of relative long jumps and loads in order to lift
   the current 64/512k size limits on JITed BPF programs there, from Ilya Leoshkevich.

4) Add BPF audit support and emit messages upon successful prog load and unload in
   order to have a timeline of events, from Daniel Borkmann and Jiri Olsa.

5) Extension to libbpf and xdpsock sample programs to demo the shared umem mode
   (XDP_SHARED_UMEM) as well as RX-only and TX-only sockets, from Magnus Karlsson.

6) Several follow-up bug fixes for libbpf's auto-pinning code and a new API
   call named bpf_get_link_xdp_info() for retrieving the full set of prog
   IDs attached to XDP, from Toke Høiland-Jørgensen.

7) Add BTF support for array of int, array of struct and multidimensional arrays
   and enable it for skb->cb[] access in kfree_skb test, from Martin KaFai Lau.

8) Fix AF_XDP by using the correct number of channels from ethtool, from Luigi Rizzo.

9) Two fixes for BPF selftest to get rid of a hang in test_tc_tunnel and to avoid
   xdping to be run as standalone, from Jiri Benc.

10) Various BPF selftest fixes when run with latest LLVM trunk, from Yonghong Song.

11) Fix a memory leak in BPF fentry test run data, from Colin Ian King.

12) Various smaller misc cleanups and improvements mostly all over BPF selftests and
    samples, from Daniel T. Lee, Andre Guedes, Anders Roxell, Mao Wenan, Yue Haibing.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

21 files changed, 339 insertions, 228 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 8e32a4d29a38..1fc42ad8ff49 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -167,6 +167,7 @@ always += xdp_sample_pkts_kern.o
 always += ibumad_kern.o
 always += hbm_out_kern.o
 always += hbm_edt_kern.o
+always += xdpsock_kern.o
 
 ifeq ($(ARCH), arm)
 # Strip all except -D__LINUX_ARM_ARCH__ option needed to handle linux
diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c
index e0fbab9bec83..829b68d87687 100644
--- a/samples/bpf/hbm.c
+++ b/samples/bpf/hbm.c
@@ -147,7 +147,7 @@ static int prog_load(char *prog)
 	}
 
 	if (ret) {
-		printf("ERROR: load_bpf_file failed for: %s\n", prog);
+		printf("ERROR: bpf_prog_load_xattr failed for: %s\n", prog);
 		printf("  Output from verifier:\n%s\n------\n", bpf_log_buf);
 		ret = -1;
 	} else {
diff --git a/samples/bpf/sockex1_kern.c b/samples/bpf/sockex1_kern.c
index f96943f443ab..2408dbfb7a21 100644
--- a/samples/bpf/sockex1_kern.c
+++ b/samples/bpf/sockex1_kern.c
@@ -5,12 +5,12 @@
 #include "bpf_helpers.h"
 #include "bpf_legacy.h"
 
-struct bpf_map_def SEC("maps") my_map = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = 256,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 256);
+} my_map SEC(".maps");
 
 SEC("socket1")
 int bpf_prog1(struct __sk_buff *skb)
diff --git a/samples/bpf/sockex2_kern.c b/samples/bpf/sockex2_kern.c
index 5566fa7d92fa..a7bcd03bf529 100644
--- a/samples/bpf/sockex2_kern.c
+++ b/samples/bpf/sockex2_kern.c
@@ -190,12 +190,12 @@ struct pair {
 	long bytes;
 };
 
-struct bpf_map_def SEC("maps") hash_map = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(__be32),
-	.value_size = sizeof(struct pair),
-	.max_entries = 1024,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __be32);
+	__type(value, struct pair);
+	__uint(max_entries, 1024);
+} hash_map SEC(".maps");
 
 SEC("socket2")
 int bpf_prog2(struct __sk_buff *skb)
diff --git a/samples/bpf/xdp1_kern.c b/samples/bpf/xdp1_kern.c
index 219742106bfd..db6870aee42c 100644
--- a/samples/bpf/xdp1_kern.c
+++ b/samples/bpf/xdp1_kern.c
@@ -14,12 +14,12 @@
 #include <linux/ipv6.h>
 #include "bpf_helpers.h"
 
-struct bpf_map_def SEC("maps") rxcnt = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = 256,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 256);
+} rxcnt SEC(".maps");
 
 static int parse_ipv4(void *data, u64 nh_off, void *data_end)
 {
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index a8e5fa02e8a8..3e553eed95a7 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -139,7 +139,7 @@ int main(int argc, char **argv)
 	map_fd = bpf_map__fd(map);
 
 	if (!prog_fd) {
-		printf("load_bpf_file: %s\n", strerror(errno));
+		printf("bpf_prog_load_xattr: %s\n", strerror(errno));
 		return 1;
 	}
 
diff --git a/samples/bpf/xdp2_kern.c b/samples/bpf/xdp2_kern.c
index e01288867d15..c74b52c6d945 100644
--- a/samples/bpf/xdp2_kern.c
+++ b/samples/bpf/xdp2_kern.c
@@ -14,12 +14,12 @@
 #include <linux/ipv6.h>
 #include "bpf_helpers.h"
 
-struct bpf_map_def SEC("maps") rxcnt = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = 256,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 256);
+} rxcnt SEC(".maps");
 
 static void swap_src_dst_mac(void *data)
 {
diff --git a/samples/bpf/xdp_adjust_tail_kern.c b/samples/bpf/xdp_adjust_tail_kern.c
index c616508befb9..0f707e0fb375 100644
--- a/samples/bpf/xdp_adjust_tail_kern.c
+++ b/samples/bpf/xdp_adjust_tail_kern.c
@@ -28,12 +28,12 @@
 /* volatile to prevent compiler optimizations */
 static volatile __u32 max_pcktsz = MAX_PCKT_SIZE;
 
-struct bpf_map_def SEC("maps") icmpcnt = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u64),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u64);
+	__uint(max_entries, 1);
+} icmpcnt SEC(".maps");
 
 static __always_inline void count_icmp(void)
 {
diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c
index 701a30f258b1..d013029aeaa2 100644
--- a/samples/bpf/xdp_fwd_kern.c
+++ b/samples/bpf/xdp_fwd_kern.c
@@ -23,13 +23,12 @@
 
 #define IPV6_FLOWINFO_MASK              cpu_to_be32(0x0FFFFFFF)
 
-/* For TX-traffic redirect requires net_device ifindex to be in this devmap */
-struct bpf_map_def SEC("maps") xdp_tx_ports = {
-	.type = BPF_MAP_TYPE_DEVMAP,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 64,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+	__uint(max_entries, 64);
+} xdp_tx_ports SEC(".maps");
 
 /* from include/net/ip.h */
 static __always_inline int ip_decrease_ttl(struct iphdr *iph)
diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
index a306d1c75622..cfcc31e51197 100644
--- a/samples/bpf/xdp_redirect_cpu_kern.c
+++ b/samples/bpf/xdp_redirect_cpu_kern.c
@@ -18,12 +18,12 @@
 #define MAX_CPUS 64 /* WARNING - sync with _user.c */
 
 /* Special map type that can XDP_REDIRECT frames to another CPU */
-struct bpf_map_def SEC("maps") cpu_map = {
-	.type		= BPF_MAP_TYPE_CPUMAP,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(u32),
-	.max_entries	= MAX_CPUS,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_CPUMAP);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u32));
+	__uint(max_entries, MAX_CPUS);
+} cpu_map SEC(".maps");
 
 /* Common stats data record to keep userspace more simple */
 struct datarec {
@@ -35,67 +35,67 @@ struct datarec {
 /* Count RX packets, as XDP bpf_prog doesn't get direct TX-success
  * feedback.  Redirect TX errors can be caught via a tracepoint.
  */
-struct bpf_map_def SEC("maps") rx_cnt = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, 1);
+} rx_cnt SEC(".maps");
 
 /* Used by trace point */
-struct bpf_map_def SEC("maps") redirect_err_cnt = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= 2,
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, 2);
 	/* TODO: have entries for all possible errno's */
-};
+} redirect_err_cnt SEC(".maps");
 
 /* Used by trace point */
-struct bpf_map_def SEC("maps") cpumap_enqueue_cnt = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= MAX_CPUS,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, MAX_CPUS);
+} cpumap_enqueue_cnt SEC(".maps");
 
 /* Used by trace point */
-struct bpf_map_def SEC("maps") cpumap_kthread_cnt = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, 1);
+} cpumap_kthread_cnt SEC(".maps");
 
 /* Set of maps controlling available CPU, and for iterating through
  * selectable redirect CPUs.
  */
-struct bpf_map_def SEC("maps") cpus_available = {
-	.type		= BPF_MAP_TYPE_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(u32),
-	.max_entries	= MAX_CPUS,
-};
-struct bpf_map_def SEC("maps") cpus_count = {
-	.type		= BPF_MAP_TYPE_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(u32),
-	.max_entries	= 1,
-};
-struct bpf_map_def SEC("maps") cpus_iterator = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(u32),
-	.max_entries	= 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, u32);
+	__uint(max_entries, MAX_CPUS);
+} cpus_available SEC(".maps");
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, u32);
+	__uint(max_entries, 1);
+} cpus_count SEC(".maps");
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, u32);
+	__uint(max_entries, 1);
+} cpus_iterator SEC(".maps");
 
 /* Used by trace point */
-struct bpf_map_def SEC("maps") exception_cnt = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, 1);
+} exception_cnt SEC(".maps");
 
 /* Helper parse functions */
 
diff --git a/samples/bpf/xdp_redirect_kern.c b/samples/bpf/xdp_redirect_kern.c
index 8abb151e385f..1f0b7d05abb2 100644
--- a/samples/bpf/xdp_redirect_kern.c
+++ b/samples/bpf/xdp_redirect_kern.c
@@ -19,22 +19,22 @@
 #include <linux/ipv6.h>
 #include "bpf_helpers.h"
 
-struct bpf_map_def SEC("maps") tx_port = {
-	.type = BPF_MAP_TYPE_ARRAY,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+} tx_port SEC(".maps");
 
 /* Count RX packets, as XDP bpf_prog doesn't get direct TX-success
  * feedback.  Redirect TX errors can be caught via a tracepoint.
  */
-struct bpf_map_def SEC("maps") rxcnt = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 1);
+} rxcnt SEC(".maps");
 
 static void swap_src_dst_mac(void *data)
 {
diff --git a/samples/bpf/xdp_redirect_map_kern.c b/samples/bpf/xdp_redirect_map_kern.c
index 740a529ba84f..4631b484c432 100644
--- a/samples/bpf/xdp_redirect_map_kern.c
+++ b/samples/bpf/xdp_redirect_map_kern.c
@@ -19,22 +19,22 @@
 #include <linux/ipv6.h>
 #include "bpf_helpers.h"
 
-struct bpf_map_def SEC("maps") tx_port = {
-	.type = BPF_MAP_TYPE_DEVMAP,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 100,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+	__uint(max_entries, 100);
+} tx_port SEC(".maps");
 
 /* Count RX packets, as XDP bpf_prog doesn't get direct TX-success
  * feedback.  Redirect TX errors can be caught via a tracepoint.
  */
-struct bpf_map_def SEC("maps") rxcnt = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(long),
-	.max_entries = 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 1);
+} rxcnt SEC(".maps");
 
 static void swap_src_dst_mac(void *data)
 {
diff --git a/samples/bpf/xdp_router_ipv4_kern.c b/samples/bpf/xdp_router_ipv4_kern.c
index 993f56bc7b9a..bf11efc8e949 100644
--- a/samples/bpf/xdp_router_ipv4_kern.c
+++ b/samples/bpf/xdp_router_ipv4_kern.c
@@ -42,44 +42,44 @@ struct direct_map {
 };
 
 /* Map for trie implementation*/
-struct bpf_map_def SEC("maps") lpm_map = {
-	.type = BPF_MAP_TYPE_LPM_TRIE,
-	.key_size = 8,
-	.value_size = sizeof(struct trie_value),
-	.max_entries = 50,
-	.map_flags = BPF_F_NO_PREALLOC,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_LPM_TRIE);
+	__uint(key_size, 8);
+	__uint(value_size, sizeof(struct trie_value));
+	__uint(max_entries, 50);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} lpm_map SEC(".maps");
 
 /* Map for counter*/
-struct bpf_map_def SEC("maps") rxcnt = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(u32),
-	.value_size = sizeof(u64),
-	.max_entries = 256,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, u64);
+	__uint(max_entries, 256);
+} rxcnt SEC(".maps");
 
 /* Map for ARP table*/
-struct bpf_map_def SEC("maps") arp_table = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(__be32),
-	.value_size = sizeof(__be64),
-	.max_entries = 50,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __be32);
+	__type(value, __be64);
+	__uint(max_entries, 50);
+} arp_table SEC(".maps");
 
 /* Map to keep the exact match entries in the route table*/
-struct bpf_map_def SEC("maps") exact_match = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(__be32),
-	.value_size = sizeof(struct direct_map),
-	.max_entries = 50,
-};
-
-struct bpf_map_def SEC("maps") tx_port = {
-	.type = BPF_MAP_TYPE_DEVMAP,
-	.key_size = sizeof(int),
-	.value_size = sizeof(int),
-	.max_entries = 100,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __be32);
+	__type(value, struct direct_map);
+	__uint(max_entries, 50);
+} exact_match SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+	__uint(max_entries, 100);
+} tx_port SEC(".maps");
 
 /* Function to set source and destination mac of the packet */
 static inline void set_src_dst_mac(void *data, void *src, void *dst)
diff --git a/samples/bpf/xdp_rxq_info_kern.c b/samples/bpf/xdp_rxq_info_kern.c
index 222a83eed1cb..272d0f82a6b5 100644
--- a/samples/bpf/xdp_rxq_info_kern.c
+++ b/samples/bpf/xdp_rxq_info_kern.c
@@ -23,12 +23,13 @@ enum cfg_options_flags {
 	READ_MEM = 0x1U,
 	SWAP_MAC = 0x2U,
 };
-struct bpf_map_def SEC("maps") config_map = {
-	.type		= BPF_MAP_TYPE_ARRAY,
-	.key_size	= sizeof(int),
-	.value_size	= sizeof(struct config),
-	.max_entries	= 1,
-};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct config);
+	__uint(max_entries, 1);
+} config_map SEC(".maps");
 
 /* Common stats data record (shared with userspace) */
 struct datarec {
@@ -36,22 +37,22 @@ struct datarec {
 	__u64 issue;
 };
 
-struct bpf_map_def SEC("maps") stats_global_map = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, 1);
+} stats_global_map SEC(".maps");
 
 #define MAX_RXQs 64
 
 /* Stats per rx_queue_index (per CPU) */
-struct bpf_map_def SEC("maps") rx_queue_index_map = {
-	.type		= BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size	= sizeof(u32),
-	.value_size	= sizeof(struct datarec),
-	.max_entries	= MAX_RXQs + 1,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, u32);
+	__type(value, struct datarec);
+	__uint(max_entries, MAX_RXQs + 1);
+} rx_queue_index_map SEC(".maps");
 
 static __always_inline
 void swap_src_dst_mac(void *data)
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
index c7e4e45d824a..51e0d810e070 100644
--- a/samples/bpf/xdp_rxq_info_user.c
+++ b/samples/bpf/xdp_rxq_info_user.c
@@ -51,8 +51,8 @@ static const struct option long_options[] = {
 	{"sec",		required_argument,	NULL, 's' },
 	{"no-separators", no_argument,		NULL, 'z' },
 	{"action",	required_argument,	NULL, 'a' },
-	{"readmem", 	no_argument,		NULL, 'r' },
-	{"swapmac", 	no_argument,		NULL, 'm' },
+	{"readmem",	no_argument,		NULL, 'r' },
+	{"swapmac",	no_argument,		NULL, 'm' },
 	{"force",	no_argument,		NULL, 'F' },
 	{0, 0, NULL,  0 }
 };
@@ -499,7 +499,7 @@ int main(int argc, char **argv)
 	map_fd = bpf_map__fd(map);
 
 	if (!prog_fd) {
-		fprintf(stderr, "ERR: load_bpf_file: %s\n", strerror(errno));
+		fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n", strerror(errno));
 		return EXIT_FAIL;
 	}
 
diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c
index 3002714e3cd5..a5760e8bf2c4 100644
--- a/samples/bpf/xdp_sample_pkts_user.c
+++ b/samples/bpf/xdp_sample_pkts_user.c
@@ -150,7 +150,7 @@ int main(int argc, char **argv)
 		return 1;
 
 	if (!prog_fd) {
-		printf("load_bpf_file: %s\n", strerror(errno));
+		printf("bpf_prog_load_xattr: %s\n", strerror(errno));
 		return 1;
 	}
 
diff --git a/samples/bpf/xdp_tx_iptunnel_kern.c b/samples/bpf/xdp_tx_iptunnel_kern.c
index 0f4f6e8c8611..6db450a5c1ca 100644
--- a/samples/bpf/xdp_tx_iptunnel_kern.c
+++ b/samples/bpf/xdp_tx_iptunnel_kern.c
@@ -19,19 +19,19 @@
 #include "bpf_helpers.h"
 #include "xdp_tx_iptunnel_common.h"
 
-struct bpf_map_def SEC("maps") rxcnt = {
-	.type = BPF_MAP_TYPE_PERCPU_ARRAY,
-	.key_size = sizeof(__u32),
-	.value_size = sizeof(__u64),
-	.max_entries = 256,
-};
-
-struct bpf_map_def SEC("maps") vip2tnl = {
-	.type = BPF_MAP_TYPE_HASH,
-	.key_size = sizeof(struct vip),
-	.value_size = sizeof(struct iptnl_info),
-	.max_entries = MAX_IPTNL_ENTRIES,
-};
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, __u32);
+	__type(value, __u64);
+	__uint(max_entries, 256);
+} rxcnt SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, struct vip);
+	__type(value, struct iptnl_info);
+	__uint(max_entries, MAX_IPTNL_ENTRIES);
+} vip2tnl SEC(".maps");
 
 static __always_inline void count_tx(u32 protocol)
 {
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index dfb68582e243..2fe4c7f5ffe5 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/samples/bpf/xdp_tx_iptunnel_user.c
@@ -268,7 +268,7 @@ int main(int argc, char **argv)
 		return 1;
 
 	if (!prog_fd) {
-		printf("load_bpf_file: %s\n", strerror(errno));
+		printf("bpf_prog_load_xattr: %s\n", strerror(errno));
 		return 1;
 	}
 
diff --git a/samples/bpf/xdpsock.h b/samples/bpf/xdpsock.h
new file mode 100644
index 000000000000..b7eca15c78cc
--- /dev/null
+++ b/samples/bpf/xdpsock.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright(c) 2019 Intel Corporation.
+ */
+
+#ifndef XDPSOCK_H_
+#define XDPSOCK_H_
+
+#define MAX_SOCKS 4
+
+#endif /* XDPSOCK_H */
diff --git a/samples/bpf/xdpsock_kern.c b/samples/bpf/xdpsock_kern.c
new file mode 100644
index 000000000000..a06177c262cd
--- /dev/null
+++ b/samples/bpf/xdpsock_kern.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#include "xdpsock.h"
+
+/* This XDP program is only needed for the XDP_SHARED_UMEM mode.
+ * If you do not use this mode, libbpf can supply an XDP program for you.
+ */
+
+struct {
+	__uint(type, BPF_MAP_TYPE_XSKMAP);
+	__uint(max_entries, MAX_SOCKS);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} xsks_map SEC(".maps");
+
+static unsigned int rr;
+
+SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
+{
+	rr = (rr + 1) & (MAX_SOCKS - 1);
+
+	return bpf_redirect_map(&xsks_map, rr, XDP_DROP);
+}
diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 405c4e091f8b..a15480010828 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -29,6 +29,7 @@
 
 #include "libbpf.h"
 #include "xsk.h"
+#include "xdpsock.h"
 #include <bpf/bpf.h>
 
 #ifndef SOL_XDP
@@ -47,7 +48,6 @@
 #define BATCH_SIZE 64
 
 #define DEBUG_HEXDUMP 0
-#define MAX_SOCKS 8
 
 typedef __u64 u64;
 typedef __u32 u32;
@@ -75,7 +75,8 @@ static u32 opt_xdp_bind_flags;
 static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
 static int opt_timeout = 1000;
 static bool opt_need_wakeup = true;
-static __u32 prog_id;
+static u32 opt_num_xsks = 1;
+static u32 prog_id;
 
 struct xsk_umem_info {
 	struct xsk_ring_prod fq;
@@ -179,7 +180,7 @@ static void *poller(void *arg)
 
 static void remove_xdp_program(void)
 {
-	__u32 curr_prog_id = 0;
+	u32 curr_prog_id = 0;
 
 	if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) {
 		printf("bpf_get_link_xdp_id failed\n");
@@ -196,11 +197,11 @@ static void remove_xdp_program(void)
 static void int_exit(int sig)
 {
 	struct xsk_umem *umem = xsks[0]->umem->umem;
-
-	(void)sig;
+	int i;
 
 	dump_stats();
-	xsk_socket__delete(xsks[0]->xsk);
+	for (i = 0; i < num_socks; i++)
+		xsk_socket__delete(xsks[i]->xsk);
 	(void)xsk_umem__delete(umem);
 	remove_xdp_program();
 
@@ -290,7 +291,6 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 		.frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM,
 		.flags = opt_umem_flags
 	};
-
 	int ret;
 
 	umem = calloc(1, sizeof(*umem));
@@ -299,7 +299,6 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 
 	ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq,
 			       &cfg);
-
 	if (ret)
 		exit_with_error(-ret);
 
@@ -307,13 +306,29 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
 	return umem;
 }
 
-static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
+static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
+{
+	int ret, i;
+	u32 idx;
+
+	ret = xsk_ring_prod__reserve(&umem->fq,
+				     XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
+	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
+		exit_with_error(-ret);
+	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
+		*xsk_ring_prod__fill_addr(&umem->fq, idx++) =
+			i * opt_xsk_frame_size;
+	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
+}
+
+static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem,
+						    bool rx, bool tx)
 {
 	struct xsk_socket_config cfg;
 	struct xsk_socket_info *xsk;
+	struct xsk_ring_cons *rxr;
+	struct xsk_ring_prod *txr;
 	int ret;
-	u32 idx;
-	int i;
 
 	xsk = calloc(1, sizeof(*xsk));
 	if (!xsk)
@@ -322,11 +337,17 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
 	xsk->umem = umem;
 	cfg.rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
-	cfg.libbpf_flags = 0;
+	if (opt_num_xsks > 1)
+		cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD;
+	else
+		cfg.libbpf_flags = 0;
 	cfg.xdp_flags = opt_xdp_flags;
 	cfg.bind_flags = opt_xdp_bind_flags;
+
+	rxr = rx ? &xsk->rx : NULL;
+	txr = tx ? &xsk->tx : NULL;
 	ret = xsk_socket__create(&xsk->xsk, opt_if, opt_queue, umem->umem,
-				 &xsk->rx, &xsk->tx, &cfg);
+				 rxr, txr, &cfg);
 	if (ret)
 		exit_with_error(-ret);
 
@@ -334,17 +355,6 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem)
 	if (ret)
 		exit_with_error(-ret);
 
-	ret = xsk_ring_prod__reserve(&xsk->umem->fq,
-				     XSK_RING_PROD__DEFAULT_NUM_DESCS,
-				     &idx);
-	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
-		exit_with_error(-ret);
-	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
-		*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx++) =
-			i * opt_xsk_frame_size;
-	xsk_ring_prod__submit(&xsk->umem->fq,
-			      XSK_RING_PROD__DEFAULT_NUM_DESCS);
-
 	return xsk;
 }
 
@@ -363,6 +373,8 @@ static struct option long_options[] = {
 	{"frame-size", required_argument, 0, 'f'},
 	{"no-need-wakeup", no_argument, 0, 'm'},
 	{"unaligned", no_argument, 0, 'u'},
+	{"shared-umem", no_argument, 0, 'M'},
+	{"force", no_argument, 0, 'F'},
 	{0, 0, 0, 0}
 };
 
@@ -382,10 +394,11 @@ static void usage(const char *prog)
 		"  -n, --interval=n	Specify statistics update interval (default 1 sec).\n"
 		"  -z, --zero-copy      Force zero-copy mode.\n"
 		"  -c, --copy           Force copy mode.\n"
-		"  -f, --frame-size=n   Set the frame size (must be a power of two, default is %d).\n"
 		"  -m, --no-need-wakeup Turn off use of driver need wakeup flag.\n"
 		"  -f, --frame-size=n   Set the frame size (must be a power of two in aligned mode, default is %d).\n"
 		"  -u, --unaligned	Enable unaligned chunk placement\n"
+		"  -M, --shared-umem	Enable XDP_SHARED_UMEM\n"
+		"  -F, --force		Force loading the XDP prog\n"
 		"\n";
 	fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE);
 	exit(EXIT_FAILURE);
@@ -398,7 +411,7 @@ static void parse_command_line(int argc, char **argv)
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:mu",
+		c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:muM",
 				long_options, &option_index);
 		if (c == -1)
 			break;
@@ -448,11 +461,14 @@ static void parse_command_line(int argc, char **argv)
 			break;
 		case 'f':
 			opt_xsk_frame_size = atoi(optarg);
+			break;
 		case 'm':
 			opt_need_wakeup = false;
 			opt_xdp_bind_flags &= ~XDP_USE_NEED_WAKEUP;
 			break;
-
+		case 'M':
+			opt_num_xsks = MAX_SOCKS;
+			break;
 		default:
 			usage(basename(argv[0]));
 		}
@@ -586,11 +602,9 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds)
 
 static void rx_drop_all(void)
 {
-	struct pollfd fds[MAX_SOCKS + 1];
+	struct pollfd fds[MAX_SOCKS] = {};
 	int i, ret;
 
-	memset(fds, 0, sizeof(fds));
-
 	for (i = 0; i < num_socks; i++) {
 		fds[i].fd = xsk_socket__fd(xsks[i]->xsk);
 		fds[i].events = POLLIN;
@@ -633,11 +647,10 @@ static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb)
 
 static void tx_only_all(void)
 {
-	struct pollfd fds[MAX_SOCKS];
+	struct pollfd fds[MAX_SOCKS] = {};
 	u32 frame_nb[MAX_SOCKS] = {};
 	int i, ret;
 
-	memset(fds, 0, sizeof(fds));
 	for (i = 0; i < num_socks; i++) {
 		fds[0].fd = xsk_socket__fd(xsks[i]->xsk);
 		fds[0].events = POLLOUT;
@@ -706,11 +719,9 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds)
 
 static void l2fwd_all(void)
 {
-	struct pollfd fds[MAX_SOCKS];
+	struct pollfd fds[MAX_SOCKS] = {};
 	int i, ret;
 
-	memset(fds, 0, sizeof(fds));
-
 	for (i = 0; i < num_socks; i++) {
 		fds[i].fd = xsk_socket__fd(xsks[i]->xsk);
 		fds[i].events = POLLOUT | POLLIN;
@@ -728,13 +739,66 @@ static void l2fwd_all(void)
 	}
 }
 
+static void load_xdp_program(char **argv, struct bpf_object **obj)
+{
+	struct bpf_prog_load_attr prog_load_attr = {
+		.prog_type      = BPF_PROG_TYPE_XDP,
+	};
+	char xdp_filename[256];
+	int prog_fd;
+
+	snprintf(xdp_filename, sizeof(xdp_filename), "%s_kern.o", argv[0]);
+	prog_load_attr.file = xdp_filename;
+
+	if (bpf_prog_load_xattr(&prog_load_attr, obj, &prog_fd))
+		exit(EXIT_FAILURE);
+	if (prog_fd < 0) {
+		fprintf(stderr, "ERROR: no program found: %s\n",
+			strerror(prog_fd));
+		exit(EXIT_FAILURE);
+	}
+
+	if (bpf_set_link_xdp_fd(opt_ifindex, prog_fd, opt_xdp_flags) < 0) {
+		fprintf(stderr, "ERROR: link set xdp fd failed\n");
+		exit(EXIT_FAILURE);
+	}
+}
+
+static void enter_xsks_into_map(struct bpf_object *obj)
+{
+	struct bpf_map *map;
+	int i, xsks_map;
+
+	map = bpf_object__find_map_by_name(obj, "xsks_map");
+	xsks_map = bpf_map__fd(map);
+	if (xsks_map < 0) {
+		fprintf(stderr, "ERROR: no xsks map found: %s\n",
+			strerror(xsks_map));
+			exit(EXIT_FAILURE);
+	}
+
+	for (i = 0; i < num_socks; i++) {
+		int fd = xsk_socket__fd(xsks[i]->xsk);
+		int key, ret;
+
+		key = i;
+		ret = bpf_map_update_elem(xsks_map, &key, &fd, 0);
+		if (ret) {
+			fprintf(stderr, "ERROR: bpf_map_update_elem %d\n", i);
+			exit(EXIT_FAILURE);
+		}
+	}
+}
+
 int main(int argc, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	bool rx = false, tx = false;
 	struct xsk_umem_info *umem;
+	struct bpf_object *obj;
 	pthread_t pt;
+	int i, ret;
 	void *bufs;
-	int ret;
 
 	parse_command_line(argc, argv);
 
@@ -744,6 +808,9 @@ int main(int argc, char **argv)
 		exit(EXIT_FAILURE);
 	}
 
+	if (opt_num_xsks > 1)
+		load_xdp_program(argv, &obj);
+
 	/* Reserve memory for the umem. Use hugepages if unaligned chunk mode */
 	bufs = mmap(NULL, NUM_FRAMES * opt_xsk_frame_size,
 		    PROT_READ | PROT_WRITE,
@@ -752,16 +819,24 @@ int main(int argc, char **argv)
 		printf("ERROR: mmap failed\n");
 		exit(EXIT_FAILURE);
 	}
-       /* Create sockets... */
-	umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size);
-	xsks[num_socks++] = xsk_configure_socket(umem);
 
-	if (opt_bench == BENCH_TXONLY) {
-		int i;
+	/* Create sockets... */
+	umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size);
+	if (opt_bench == BENCH_RXDROP || opt_bench == BENCH_L2FWD) {
+		rx = true;
+		xsk_populate_fill_ring(umem);
+	}
+	if (opt_bench == BENCH_L2FWD || opt_bench == BENCH_TXONLY)
+		tx = true;
+	for (i = 0; i < opt_num_xsks; i++)
+		xsks[num_socks++] = xsk_configure_socket(umem, rx, tx);
 
+	if (opt_bench == BENCH_TXONLY)
 		for (i = 0; i < NUM_FRAMES; i++)
-			(void)gen_eth_frame(umem, i * opt_xsk_frame_size);
-	}
+			gen_eth_frame(umem, i * opt_xsk_frame_size);
+
+	if (opt_num_xsks > 1 && opt_bench != BENCH_TXONLY)
+		enter_xsks_into_map(obj);
 
 	signal(SIGINT, int_exit);
 	signal(SIGTERM, int_exit);