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

Pull networking updates from David Millar:
 "Here are some highlights from the 2065 networking commits that
  happened this development cycle:

   1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)

   2) Add a generic XDP driver, so that anyone can test XDP even if they
      lack a networking device whose driver has explicit XDP support
      (me).

   3) Sparc64 now has an eBPF JIT too (me)

   4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
      Starovoitov)

   5) Make netfitler network namespace teardown less expensive (Florian
      Westphal)

   6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)

   7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)

   8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)

   9) Multiqueue support in stmmac driver (Joao Pinto)

  10) Remove TCP timewait recycling, it never really could possibly work
      well in the real world and timestamp randomization really zaps any
      hint of usability this feature had (Soheil Hassas Yeganeh)

  11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
      Aleksandrov)

  12) Add socket busy poll support to epoll (Sridhar Samudrala)

  13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
      and several others)

  14) IPSEC hw offload infrastructure (Steffen Klassert)"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
  tipc: refactor function tipc_sk_recv_stream()
  tipc: refactor function tipc_sk_recvmsg()
  net: thunderx: Optimize page recycling for XDP
  net: thunderx: Support for XDP header adjustment
  net: thunderx: Add support for XDP_TX
  net: thunderx: Add support for XDP_DROP
  net: thunderx: Add basic XDP support
  net: thunderx: Cleanup receive buffer allocation
  net: thunderx: Optimize CQE_TX handling
  net: thunderx: Optimize RBDR descriptor handling
  net: thunderx: Support for page recycling
  ipx: call ipxitf_put() in ioctl error path
  net: sched: add helpers to handle extended actions
  qed*: Fix issues in the ptp filter config implementation.
  qede: Fix concurrency issue in PTP Tx path processing.
  stmmac: Add support for SIMATIC IOT2000 platform
  net: hns: fix ethtool_get_strings overflow in hns driver
  tcp: fix wraparound issue in tcp_lp
  bpf, arm64: fix jit branch offset related to ldimm64
  bpf, arm64: implement jiting of BPF_XADD
  ...

14 files changed, 1168 insertions, 107 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 09e9d535bd74..6c7468eb3684 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -34,6 +34,8 @@ hostprogs-y += sampleip
 hostprogs-y += tc_l2_redirect
 hostprogs-y += lwt_len_hist
 hostprogs-y += xdp_tx_iptunnel
+hostprogs-y += test_map_in_map
+hostprogs-y += per_socket_stats_example
 
 # Libbpf dependencies
 LIBBPF := ../../tools/lib/bpf/bpf.o
@@ -72,6 +74,8 @@ sampleip-objs := bpf_load.o $(LIBBPF) sampleip_user.o
 tc_l2_redirect-objs := bpf_load.o $(LIBBPF) tc_l2_redirect_user.o
 lwt_len_hist-objs := bpf_load.o $(LIBBPF) lwt_len_hist_user.o
 xdp_tx_iptunnel-objs := bpf_load.o $(LIBBPF) xdp_tx_iptunnel_user.o
+test_map_in_map-objs := bpf_load.o $(LIBBPF) test_map_in_map_user.o
+per_socket_stats_example-objs := $(LIBBPF) cookie_uid_helper_example.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -105,6 +109,8 @@ always += trace_event_kern.o
 always += sampleip_kern.o
 always += lwt_len_hist_kern.o
 always += xdp_tx_iptunnel_kern.o
+always += test_map_in_map_kern.o
+always += cookie_uid_helper_example.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -139,6 +145,7 @@ HOSTLOADLIBES_sampleip += -lelf
 HOSTLOADLIBES_tc_l2_redirect += -l elf
 HOSTLOADLIBES_lwt_len_hist += -l elf
 HOSTLOADLIBES_xdp_tx_iptunnel += -lelf
+HOSTLOADLIBES_test_map_in_map += -lelf
 
 # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
 #  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
@@ -182,4 +189,5 @@ $(obj)/%.o: $(src)/%.c
 		-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 $@
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index faaffe2e139a..9a9c95f2c9fb 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -80,6 +80,7 @@ struct bpf_map_def {
 	unsigned int value_size;
 	unsigned int max_entries;
 	unsigned int map_flags;
+	unsigned int inner_map_idx;
 };
 
 static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
@@ -145,11 +146,30 @@ static int (*bpf_skb_change_head)(void *, int len, int flags) =
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->nip)
 
+#elif defined(__sparc__)
+
+#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
+#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
+#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2])
+#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3])
+#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4])
+#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
+#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
+#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
+#if defined(__arch64__)
+#define PT_REGS_IP(x) ((x)->tpc)
+#else
+#define PT_REGS_IP(x) ((x)->pc)
+#endif
+
 #endif
 
 #ifdef __powerpc__
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
+#elif defined(__sparc__)
+#define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
+#define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
 #else
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({				\
 		bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index b86ee54da2d1..4221dc359453 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -14,6 +14,7 @@
 #include <linux/perf_event.h>
 #include <linux/netlink.h>
 #include <linux/rtnetlink.h>
+#include <linux/types.h>
 #include <sys/types.h>
 #include <sys/socket.h>
 #include <sys/syscall.h>
@@ -21,6 +22,7 @@
 #include <sys/mman.h>
 #include <poll.h>
 #include <ctype.h>
+#include <assert.h>
 #include "libbpf.h"
 #include "bpf_load.h"
 #include "perf-sys.h"
@@ -37,14 +39,6 @@ int event_fd[MAX_PROGS];
 int prog_cnt;
 int prog_array_fd = -1;
 
-struct bpf_map_def {
-	unsigned int type;
-	unsigned int key_size;
-	unsigned int value_size;
-	unsigned int max_entries;
-	unsigned int map_flags;
-};
-
 static int populate_prog_array(const char *event, int prog_fd)
 {
 	int ind = atoi(event), err;
@@ -192,17 +186,35 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 	return 0;
 }
 
-static int load_maps(struct bpf_map_def *maps, int len)
+static int load_maps(struct bpf_map_def *maps, int nr_maps,
+		     const char **map_names, fixup_map_cb fixup_map)
 {
 	int i;
-
-	for (i = 0; i < len / sizeof(struct bpf_map_def); i++) {
-
-		map_fd[i] = bpf_create_map(maps[i].type,
-					   maps[i].key_size,
-					   maps[i].value_size,
-					   maps[i].max_entries,
-					   maps[i].map_flags);
+	/*
+	 * Warning: Using "maps" pointing to ELF data_maps->d_buf as
+	 * an array of struct bpf_map_def is a wrong assumption about
+	 * the ELF maps section format.
+	 */
+	for (i = 0; i < nr_maps; i++) {
+		if (fixup_map)
+			fixup_map(&maps[i], map_names[i], i);
+
+		if (maps[i].type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+		    maps[i].type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+			int inner_map_fd = map_fd[maps[i].inner_map_idx];
+
+			map_fd[i] = bpf_create_map_in_map(maps[i].type,
+							  maps[i].key_size,
+							  inner_map_fd,
+							  maps[i].max_entries,
+							  maps[i].map_flags);
+		} else {
+			map_fd[i] = bpf_create_map(maps[i].type,
+						   maps[i].key_size,
+						   maps[i].value_size,
+						   maps[i].max_entries,
+						   maps[i].map_flags);
+		}
 		if (map_fd[i] < 0) {
 			printf("failed to create a map: %d %s\n",
 			       errno, strerror(errno));
@@ -262,20 +274,74 @@ static int parse_relo_and_apply(Elf_Data *data, Elf_Data *symbols,
 			return 1;
 		}
 		insn[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+		/*
+		 * Warning: Using sizeof(struct bpf_map_def) here is a
+		 * wrong assumption about ELF maps section format
+		 */
 		insn[insn_idx].imm = map_fd[sym.st_value / sizeof(struct bpf_map_def)];
 	}
 
 	return 0;
 }
 
-int load_bpf_file(char *path)
+static int cmp_symbols(const void *l, const void *r)
 {
-	int fd, i;
+	const GElf_Sym *lsym = (const GElf_Sym *)l;
+	const GElf_Sym *rsym = (const GElf_Sym *)r;
+
+	if (lsym->st_value < rsym->st_value)
+		return -1;
+	else if (lsym->st_value > rsym->st_value)
+		return 1;
+	else
+		return 0;
+}
+
+static int get_sorted_map_names(Elf *elf, Elf_Data *symbols, int maps_shndx,
+				int strtabidx, char **map_names)
+{
+	GElf_Sym map_symbols[MAX_MAPS];
+	int i, nr_maps = 0;
+
+	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+		assert(nr_maps < MAX_MAPS);
+		if (!gelf_getsym(symbols, i, &map_symbols[nr_maps]))
+			continue;
+		if (map_symbols[nr_maps].st_shndx != maps_shndx)
+			continue;
+		nr_maps++;
+	}
+
+	qsort(map_symbols, nr_maps, sizeof(GElf_Sym), cmp_symbols);
+
+	for (i = 0; i < nr_maps; i++) {
+		char *map_name;
+
+		map_name = elf_strptr(elf, strtabidx, map_symbols[i].st_name);
+		if (!map_name) {
+			printf("cannot get map symbol\n");
+			return -1;
+		}
+
+		map_names[i] = strdup(map_name);
+		if (!map_names[i]) {
+			printf("strdup(%s): %s(%d)\n", map_name,
+			       strerror(errno), errno);
+			return -1;
+		}
+	}
+
+	return nr_maps;
+}
+
+static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map)
+{
+	int fd, i, ret, maps_shndx = -1, strtabidx = -1;
 	Elf *elf;
 	GElf_Ehdr ehdr;
 	GElf_Shdr shdr, shdr_prog;
-	Elf_Data *data, *data_prog, *symbols = NULL;
-	char *shname, *shname_prog;
+	Elf_Data *data, *data_prog, *data_maps = NULL, *symbols = NULL;
+	char *shname, *shname_prog, *map_names[MAX_MAPS] = { NULL };
 
 	/* reset global variables */
 	kern_version = 0;
@@ -323,14 +389,47 @@ int load_bpf_file(char *path)
 			}
 			memcpy(&kern_version, data->d_buf, sizeof(int));
 		} else if (strcmp(shname, "maps") == 0) {
-			processed_sec[i] = true;
-			if (load_maps(data->d_buf, data->d_size))
-				return 1;
+			maps_shndx = i;
+			data_maps = data;
 		} else if (shdr.sh_type == SHT_SYMTAB) {
+			strtabidx = shdr.sh_link;
 			symbols = data;
 		}
 	}
 
+	ret = 1;
+
+	if (!symbols) {
+		printf("missing SHT_SYMTAB section\n");
+		goto done;
+	}
+
+	if (data_maps) {
+		int nr_maps;
+		int prog_elf_map_sz;
+
+		nr_maps = get_sorted_map_names(elf, symbols, maps_shndx,
+					       strtabidx, map_names);
+		if (nr_maps < 0)
+			goto done;
+
+		/* Deduce map struct size stored in ELF maps section */
+		prog_elf_map_sz = data_maps->d_size / nr_maps;
+		if (prog_elf_map_sz != sizeof(struct bpf_map_def)) {
+			printf("Error: ELF maps sec wrong size (%d/%lu),"
+			       " old kern.o file?\n",
+			       prog_elf_map_sz, sizeof(struct bpf_map_def));
+			ret = 1;
+			goto done;
+		}
+
+		if (load_maps(data_maps->d_buf, nr_maps,
+			      (const char **)map_names, fixup_map))
+			goto done;
+
+		processed_sec[maps_shndx] = true;
+	}
+
 	/* load programs that need map fixup (relocations) */
 	for (i = 1; i < ehdr.e_shnum; i++) {
 		if (processed_sec[i])
@@ -387,8 +486,22 @@ int load_bpf_file(char *path)
 			load_and_attach(shname, data->d_buf, data->d_size);
 	}
 
+	ret = 0;
+done:
+	for (i = 0; i < MAX_MAPS; i++)
+		free(map_names[i]);
 	close(fd);
-	return 0;
+	return ret;
+}
+
+int load_bpf_file(char *path)
+{
+	return do_load_bpf_file(path, NULL);
+}
+
+int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map)
+{
+	return do_load_bpf_file(path, fixup_map);
 }
 
 void read_trace_pipe(void)
@@ -473,7 +586,7 @@ struct ksym *ksym_search(long key)
 	return &syms[0];
 }
 
-int set_link_xdp_fd(int ifindex, int fd)
+int set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 {
 	struct sockaddr_nl sa;
 	int sock, seq = 0, len, ret = -1;
@@ -509,15 +622,28 @@ int set_link_xdp_fd(int ifindex, int fd)
 	req.nh.nlmsg_seq = ++seq;
 	req.ifinfo.ifi_family = AF_UNSPEC;
 	req.ifinfo.ifi_index = ifindex;
+
+	/* started nested attribute for XDP */
 	nla = (struct nlattr *)(((char *)&req)
 				+ NLMSG_ALIGN(req.nh.nlmsg_len));
 	nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;
+	nla->nla_len = NLA_HDRLEN;
 
-	nla_xdp = (struct nlattr *)((char *)nla + NLA_HDRLEN);
+	/* add XDP fd */
+	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
 	nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
 	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
 	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
-	nla->nla_len = NLA_HDRLEN + nla_xdp->nla_len;
+	nla->nla_len += nla_xdp->nla_len;
+
+	/* if user passed in any flags, add those too */
+	if (flags) {
+		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+		nla_xdp->nla_type = 3/*IFLA_XDP_FLAGS*/;
+		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
+		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
+		nla->nla_len += nla_xdp->nla_len;
+	}
 
 	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
 
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
index c827827299b3..05822f83173a 100644
--- a/samples/bpf/bpf_load.h
+++ b/samples/bpf/bpf_load.h
@@ -6,6 +6,18 @@
 #define MAX_MAPS 32
 #define MAX_PROGS 32
 
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+	unsigned int map_flags;
+	unsigned int inner_map_idx;
+};
+
+typedef void (*fixup_map_cb)(struct bpf_map_def *map, const char *map_name,
+			     int idx);
+
 extern int map_fd[MAX_MAPS];
 extern int prog_fd[MAX_PROGS];
 extern int event_fd[MAX_PROGS];
@@ -25,6 +37,7 @@ extern int prog_cnt;
  * returns zero on success
  */
 int load_bpf_file(char *path);
+int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map);
 
 void read_trace_pipe(void);
 struct ksym {
@@ -34,5 +47,5 @@ struct ksym {
 
 int load_kallsyms(void);
 struct ksym *ksym_search(long key);
-int set_link_xdp_fd(int ifindex, int fd);
+int set_link_xdp_fd(int ifindex, int fd, __u32 flags);
 #endif
diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c
new file mode 100644
index 000000000000..b08ab4e88929
--- /dev/null
+++ b/samples/bpf/cookie_uid_helper_example.c
@@ -0,0 +1,321 @@
+/* This test is a demo of using get_socket_uid and get_socket_cookie
+ * helper function to do per socket based network traffic monitoring.
+ * It requires iptables version higher then 1.6.1. to load pinned eBPF
+ * program into the xt_bpf match.
+ *
+ * TEST:
+ * ./run_cookie_uid_helper_example.sh -option
+ * option:
+ *	-t: do traffic monitoring test, the program will continuously
+ * print out network traffic happens after program started A sample
+ * output is shown below:
+ *
+ * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058
+ * cookie: 132, uid: 0x0, Pakcet Count: 2, Bytes Count: 286
+ * cookie: 812, uid: 0x3e8, Pakcet Count: 3, Bytes Count: 1726
+ * cookie: 802, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104
+ * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058
+ * cookie: 831, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104
+ * cookie: 0, uid: 0x0, Pakcet Count: 6, Bytes Count: 712
+ * cookie: 880, uid: 0xfffe, Pakcet Count: 1, Bytes Count: 70
+ *
+ *	-s: do getsockopt SO_COOKIE test, the program will set up a pair of
+ * UDP sockets and send packets between them. And read out the traffic data
+ * directly from the ebpf map based on the socket cookie.
+ *
+ * Clean up: if using shell script, the script file will delete the iptables
+ * rule and unmount the bpf program when exit. Else the iptables rule need
+ * to be deleted by hand, see run_cookie_uid_helper_example.sh for detail.
+ */
+
+#define _GNU_SOURCE
+
+#define offsetof(type, member)	__builtin_offsetof(type, member)
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <limits.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <net/if.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include "libbpf.h"
+
+#define PORT 8888
+
+struct stats {
+	uint32_t uid;
+	uint64_t packets;
+	uint64_t bytes;
+};
+
+static int map_fd, prog_fd;
+
+static bool test_finish;
+
+static void maps_create(void)
+{
+	map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(uint32_t),
+				sizeof(struct stats), 100, 0);
+	if (map_fd < 0)
+		error(1, errno, "map create failed!\n");
+}
+
+static void prog_load(void)
+{
+	static char log_buf[1 << 16];
+
+	struct bpf_insn prog[] = {
+		/*
+		 * Save sk_buff for future usage. value stored in R6 to R10 will
+		 * not be reset after a bpf helper function call.
+		 */
+		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+		/*
+		 * pc1: BPF_FUNC_get_socket_cookie takes one parameter,
+		 * R1: sk_buff
+		 */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_get_socket_cookie),
+		/* pc2-4: save &socketCookie to r7 for future usage*/
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+		BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+		/*
+		 * pc5-8: set up the registers for BPF_FUNC_map_lookup_elem,
+		 * it takes two parameters (R1: map_fd,  R2: &socket_cookie)
+		 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_map_lookup_elem),
+		/*
+		 * pc9. if r0 != 0x0, go to pc+14, since we have the cookie
+		 * stored already
+		 * Otherwise do pc10-22 to setup a new data entry.
+		 */
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 14),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_get_socket_uid),
+		/*
+		 * Place a struct stats in the R10 stack and sequentially
+		 * place the member value into the memory. Packets value
+		 * is set by directly place a IMM value 1 into the stack.
+		 */
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0,
+			    -32 + (__s16)offsetof(struct stats, uid)),
+		BPF_ST_MEM(BPF_DW, BPF_REG_10,
+			   -32 + (__s16)offsetof(struct stats, packets), 1),
+		/*
+		 * __sk_buff is a special struct used for eBPF program to
+		 * directly access some sk_buff field.
+		 */
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1,
+			    -32 + (__s16)offsetof(struct stats, bytes)),
+		/*
+		 * add new map entry using BPF_FUNC_map_update_elem, it takes
+		 * 4 parameters (R1: map_fd, R2: &socket_cookie, R3: &stats,
+		 * R4: flags)
+		 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+		BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -32),
+		BPF_MOV64_IMM(BPF_REG_4, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_map_update_elem),
+		BPF_JMP_IMM(BPF_JA, 0, 0, 5),
+		/*
+		 * pc24-30 update the packet info to a exist data entry, it can
+		 * be done by directly write to pointers instead of using
+		 * BPF_FUNC_map_update_elem helper function
+		 */
+		BPF_MOV64_REG(BPF_REG_9, BPF_REG_0),
+		BPF_MOV64_IMM(BPF_REG_1, 1),
+		BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1,
+				offsetof(struct stats, packets)),
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_STX_XADD(BPF_DW, BPF_REG_9, BPF_REG_1,
+				offsetof(struct stats, bytes)),
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_EXIT_INSN(),
+	};
+	prog_fd = bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog,
+					ARRAY_SIZE(prog), "GPL", 0,
+					log_buf, sizeof(log_buf));
+	if (prog_fd < 0)
+		error(1, errno, "failed to load prog\n%s\n", log_buf);
+}
+
+static void prog_attach_iptables(char *file)
+{
+	int ret;
+	char rules[100];
+
+	if (bpf_obj_pin(prog_fd, file))
+		error(1, errno, "bpf_obj_pin");
+	if (strlen(file) > 50) {
+		printf("file path too long: %s\n", file);
+		exit(1);
+	}
+	sprintf(rules, "iptables -A OUTPUT -m bpf --object-pinned %s -j ACCEPT",
+		file);
+	ret = system(rules);
+	if (ret < 0) {
+		printf("iptables rule update failed: %d/n", WEXITSTATUS(ret));
+		exit(1);
+	}
+}
+
+static void print_table(void)
+{
+	struct stats curEntry;
+	uint32_t curN = UINT32_MAX;
+	uint32_t nextN;
+	int res;
+
+	while (bpf_map_get_next_key(map_fd, &curN, &nextN) > -1) {
+		curN = nextN;
+		res = bpf_map_lookup_elem(map_fd, &curN, &curEntry);
+		if (res < 0) {
+			error(1, errno, "fail to get entry value of Key: %u\n",
+				curN);
+		} else {
+			printf("cookie: %u, uid: 0x%x, Packet Count: %lu,"
+				" Bytes Count: %lu\n", curN, curEntry.uid,
+				curEntry.packets, curEntry.bytes);
+		}
+	}
+}
+
+static void udp_client(void)
+{
+	struct sockaddr_in si_other = {0};
+	struct sockaddr_in si_me = {0};
+	struct stats dataEntry;
+	int s_rcv, s_send, i, recv_len;
+	char message = 'a';
+	char buf;
+	uint64_t cookie;
+	int res;
+	socklen_t cookie_len = sizeof(cookie);
+	socklen_t slen = sizeof(si_other);
+
+	s_rcv = socket(PF_INET, SOCK_DGRAM, 0);
+	if (s_rcv < 0)
+		error(1, errno, "rcv socket creat failed!\n");
+	si_other.sin_family = AF_INET;
+	si_other.sin_port = htons(PORT);
+	if (inet_aton("127.0.0.1", &si_other.sin_addr) == 0)
+		error(1, errno, "inet_aton\n");
+	if (bind(s_rcv, (struct sockaddr *)&si_other, sizeof(si_other)) == -1)
+		error(1, errno, "bind\n");
+	s_send = socket(PF_INET, SOCK_DGRAM, 0);
+	if (s_send < 0)
+		error(1, errno, "send socket creat failed!\n");
+	res = getsockopt(s_send, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len);
+	if (res < 0)
+		printf("get cookie failed: %s\n", strerror(errno));
+	res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry);
+	if (res != -1)
+		error(1, errno, "socket stat found while flow not active\n");
+	for (i = 0; i < 10; i++) {
+		res = sendto(s_send, &message, sizeof(message), 0,
+			     (struct sockaddr *)&si_other, slen);
+		if (res == -1)
+			error(1, errno, "send\n");
+		if (res != sizeof(message))
+			error(1, 0, "%uB != %luB\n", res, sizeof(message));
+		recv_len = recvfrom(s_rcv, &buf, sizeof(buf), 0,
+			     (struct sockaddr *)&si_me, &slen);
+		if (recv_len < 0)
+			error(1, errno, "revieve\n");
+		res = memcmp(&(si_other.sin_addr), &(si_me.sin_addr),
+			   sizeof(si_me.sin_addr));
+		if (res != 0)
+			error(1, EFAULT, "sender addr error: %d\n", res);
+		printf("Message received: %c\n", buf);
+		res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry);
+		if (res < 0)
+			error(1, errno, "lookup sk stat failed, cookie: %lu\n",
+			      cookie);
+		printf("cookie: %lu, uid: 0x%x, Packet Count: %lu,"
+			" Bytes Count: %lu\n\n", cookie, dataEntry.uid,
+			dataEntry.packets, dataEntry.bytes);
+	}
+	close(s_send);
+	close(s_rcv);
+}
+
+static int usage(void)
+{
+	printf("Usage: ./run_cookie_uid_helper_example.sh"
+		" bpfObjName -option\n"
+		"	-t	traffic monitor test\n"
+		"	-s	getsockopt cookie test\n");
+	return 1;
+}
+
+static void finish(int ret)
+{
+	test_finish = true;
+}
+
+int main(int argc, char *argv[])
+{
+	int opt;
+	bool cfg_test_traffic = false;
+	bool cfg_test_cookie = false;
+
+	if (argc != 3)
+		return usage();
+	while ((opt = getopt(argc, argv, "ts")) != -1) {
+		switch (opt) {
+		case 't':
+			cfg_test_traffic = true;
+			break;
+		case 's':
+			cfg_test_cookie = true;
+			break;
+
+		default:
+			printf("unknown option %c\n", opt);
+			usage();
+			return -1;
+		}
+	}
+	maps_create();
+	prog_load();
+	prog_attach_iptables(argv[2]);
+	if (cfg_test_traffic) {
+		if (signal(SIGINT, finish) == SIG_ERR)
+			error(1, errno, "register handler failed");
+		while (!test_finish) {
+			print_table();
+			printf("\n");
+			sleep(1);
+		};
+	} else if (cfg_test_cookie) {
+		udp_client();
+	}
+	close(prog_fd);
+	close(map_fd);
+	return 0;
+}
diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h
index 3705fba453a0..8ab36a04c174 100644
--- a/samples/bpf/libbpf.h
+++ b/samples/bpf/libbpf.h
@@ -135,6 +135,16 @@ struct bpf_insn;
 		.off   = OFF,					\
 		.imm   = 0 })
 
+/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
+
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 /* Memory store, *(uint *) (dst_reg + off16) = imm32 */
 
 #define BPF_ST_MEM(SIZE, DST, OFF, IMM)				\
diff --git a/samples/bpf/map_perf_test_kern.c b/samples/bpf/map_perf_test_kern.c
index a91872a97742..245165817fbe 100644
--- a/samples/bpf/map_perf_test_kern.c
+++ b/samples/bpf/map_perf_test_kern.c
@@ -11,6 +11,7 @@
 #include "bpf_helpers.h"
 
 #define MAX_ENTRIES 1000
+#define MAX_NR_CPUS 1024
 
 struct bpf_map_def SEC("maps") hash_map = {
 	.type = BPF_MAP_TYPE_HASH,
@@ -26,7 +27,7 @@ struct bpf_map_def SEC("maps") lru_hash_map = {
 	.max_entries = 10000,
 };
 
-struct bpf_map_def SEC("maps") percpu_lru_hash_map = {
+struct bpf_map_def SEC("maps") nocommon_lru_hash_map = {
 	.type = BPF_MAP_TYPE_LRU_HASH,
 	.key_size = sizeof(u32),
 	.value_size = sizeof(long),
@@ -34,6 +35,19 @@ struct bpf_map_def SEC("maps") percpu_lru_hash_map = {
 	.map_flags = BPF_F_NO_COMMON_LRU,
 };
 
+struct bpf_map_def SEC("maps") inner_lru_hash_map = {
+	.type = BPF_MAP_TYPE_LRU_HASH,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(long),
+	.max_entries = MAX_ENTRIES,
+};
+
+struct bpf_map_def SEC("maps") array_of_lru_hashs = {
+	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	.key_size = sizeof(u32),
+	.max_entries = MAX_NR_CPUS,
+};
+
 struct bpf_map_def SEC("maps") percpu_hash_map = {
 	.type = BPF_MAP_TYPE_PERCPU_HASH,
 	.key_size = sizeof(u32),
@@ -65,6 +79,13 @@ struct bpf_map_def SEC("maps") lpm_trie_map_alloc = {
 	.map_flags = BPF_F_NO_PREALLOC,
 };
 
+struct bpf_map_def SEC("maps") array_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(long),
+	.max_entries = MAX_ENTRIES,
+};
+
 SEC("kprobe/sys_getuid")
 int stress_hmap(struct pt_regs *ctx)
 {
@@ -93,6 +114,7 @@ int stress_percpu_hmap(struct pt_regs *ctx)
 		bpf_map_delete_elem(&percpu_hash_map, &key);
 	return 0;
 }
+
 SEC("kprobe/sys_getgid")
 int stress_hmap_alloc(struct pt_regs *ctx)
 {
@@ -121,24 +143,56 @@ int stress_percpu_hmap_alloc(struct pt_regs *ctx)
 	return 0;
 }
 
-SEC("kprobe/sys_getpid")
+SEC("kprobe/sys_connect")
 int stress_lru_hmap_alloc(struct pt_regs *ctx)
 {
-	u32 key = bpf_get_prandom_u32();
+	struct sockaddr_in6 *in6;
+	u16 test_case, dst6[8];
+	int addrlen, ret;
+	char fmt[] = "Failed at stress_lru_hmap_alloc. ret:%d\n";
 	long val = 1;
+	u32 key = bpf_get_prandom_u32();
 
-	bpf_map_update_elem(&lru_hash_map, &key, &val, BPF_ANY);
+	in6 = (struct sockaddr_in6 *)PT_REGS_PARM2(ctx);
+	addrlen = (int)PT_REGS_PARM3(ctx);
 
-	return 0;
-}
+	if (addrlen != sizeof(*in6))
+		return 0;
 
-SEC("kprobe/sys_getppid")
-int stress_percpu_lru_hmap_alloc(struct pt_regs *ctx)
-{
-	u32 key = bpf_get_prandom_u32();
-	long val = 1;
+	ret = bpf_probe_read(dst6, sizeof(dst6), &in6->sin6_addr);
+	if (ret)
+		goto done;
 
-	bpf_map_update_elem(&percpu_lru_hash_map, &key, &val, BPF_ANY);
+	if (dst6[0] != 0xdead || dst6[1] != 0xbeef)
+		return 0;
+
+	test_case = dst6[7];
+
+	if (test_case == 0) {
+		ret = bpf_map_update_elem(&lru_hash_map, &key, &val, BPF_ANY);
+	} else if (test_case == 1) {
+		ret = bpf_map_update_elem(&nocommon_lru_hash_map, &key, &val,
+					  BPF_ANY);
+	} else if (test_case == 2) {
+		void *nolocal_lru_map;
+		int cpu = bpf_get_smp_processor_id();
+
+		nolocal_lru_map = bpf_map_lookup_elem(&array_of_lru_hashs,
+						      &cpu);
+		if (!nolocal_lru_map) {
+			ret = -ENOENT;
+			goto done;
+		}
+
+		ret = bpf_map_update_elem(nolocal_lru_map, &key, &val,
+					  BPF_ANY);
+	} else {
+		ret = -EINVAL;
+	}
+
+done:
+	if (ret)
+		bpf_trace_printk(fmt, sizeof(fmt), ret);
 
 	return 0;
 }
@@ -165,5 +219,31 @@ int stress_lpm_trie_map_alloc(struct pt_regs *ctx)
 	return 0;
 }
 
+SEC("kprobe/sys_getpgid")
+int stress_hash_map_lookup(struct pt_regs *ctx)
+{
+	u32 key = 1, i;
+	long *value;
+
+#pragma clang loop unroll(full)
+	for (i = 0; i < 64; ++i)
+		value = bpf_map_lookup_elem(&hash_map, &key);
+
+	return 0;
+}
+
+SEC("kprobe/sys_getpgrp")
+int stress_array_map_lookup(struct pt_regs *ctx)
+{
+	u32 key = 1, i;
+	long *value;
+
+#pragma clang loop unroll(full)
+	for (i = 0; i < 64; ++i)
+		value = bpf_map_lookup_elem(&array_map, &key);
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
 u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c
index 680260a91f50..6ac778153315 100644
--- a/samples/bpf/map_perf_test_user.c
+++ b/samples/bpf/map_perf_test_user.c
@@ -18,10 +18,14 @@
 #include <string.h>
 #include <time.h>
 #include <sys/resource.h>
+#include <arpa/inet.h>
+#include <errno.h>
+
 #include "libbpf.h"
 #include "bpf_load.h"
 
-#define MAX_CNT 1000000
+#define TEST_BIT(t) (1U << (t))
+#define MAX_NR_CPUS 1024
 
 static __u64 time_get_ns(void)
 {
@@ -31,15 +35,44 @@ static __u64 time_get_ns(void)
 	return ts.tv_sec * 1000000000ull + ts.tv_nsec;
 }
 
-#define HASH_PREALLOC		(1 << 0)
-#define PERCPU_HASH_PREALLOC	(1 << 1)
-#define HASH_KMALLOC		(1 << 2)
-#define PERCPU_HASH_KMALLOC	(1 << 3)
-#define LRU_HASH_PREALLOC	(1 << 4)
-#define PERCPU_LRU_HASH_PREALLOC	(1 << 5)
-#define LPM_KMALLOC		(1 << 6)
+enum test_type {
+	HASH_PREALLOC,
+	PERCPU_HASH_PREALLOC,
+	HASH_KMALLOC,
+	PERCPU_HASH_KMALLOC,
+	LRU_HASH_PREALLOC,
+	NOCOMMON_LRU_HASH_PREALLOC,
+	LPM_KMALLOC,
+	HASH_LOOKUP,
+	ARRAY_LOOKUP,
+	INNER_LRU_HASH_PREALLOC,
+	NR_TESTS,
+};
+
+const char *test_map_names[NR_TESTS] = {
+	[HASH_PREALLOC] = "hash_map",
+	[PERCPU_HASH_PREALLOC] = "percpu_hash_map",
+	[HASH_KMALLOC] = "hash_map_alloc",
+	[PERCPU_HASH_KMALLOC] = "percpu_hash_map_alloc",
+	[LRU_HASH_PREALLOC] = "lru_hash_map",
+	[NOCOMMON_LRU_HASH_PREALLOC] = "nocommon_lru_hash_map",
+	[LPM_KMALLOC] = "lpm_trie_map_alloc",
+	[HASH_LOOKUP] = "hash_map",
+	[ARRAY_LOOKUP] = "array_map",
+	[INNER_LRU_HASH_PREALLOC] = "inner_lru_hash_map",
+};
 
 static int test_flags = ~0;
+static uint32_t num_map_entries;
+static uint32_t inner_lru_hash_size;
+static int inner_lru_hash_idx = -1;
+static int array_of_lru_hashs_idx = -1;
+static uint32_t max_cnt = 1000000;
+
+static int check_test_flags(enum test_type t)
+{
+	return test_flags & TEST_BIT(t);
+}
 
 static void test_hash_prealloc(int cpu)
 {
@@ -47,34 +80,89 @@ static void test_hash_prealloc(int cpu)
 	int i;
 
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
+	for (i = 0; i < max_cnt; i++)
 		syscall(__NR_getuid);
 	printf("%d:hash_map_perf pre-alloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
 }
 
-static void test_lru_hash_prealloc(int cpu)
+static void do_test_lru(enum test_type test, int cpu)
 {
+	static int inner_lru_map_fds[MAX_NR_CPUS];
+
+	struct sockaddr_in6 in6 = { .sin6_family = AF_INET6 };
+	const char *test_name;
 	__u64 start_time;
-	int i;
+	int i, ret;
+
+	if (test == INNER_LRU_HASH_PREALLOC) {
+		int outer_fd = map_fd[array_of_lru_hashs_idx];
+
+		assert(cpu < MAX_NR_CPUS);
+
+		if (cpu) {
+			inner_lru_map_fds[cpu] =
+				bpf_create_map(BPF_MAP_TYPE_LRU_HASH,
+					       sizeof(uint32_t), sizeof(long),
+					       inner_lru_hash_size, 0);
+			if (inner_lru_map_fds[cpu] == -1) {
+				printf("cannot create BPF_MAP_TYPE_LRU_HASH %s(%d)\n",
+				       strerror(errno), errno);
+				exit(1);
+			}
+		} else {
+			inner_lru_map_fds[cpu] = map_fd[inner_lru_hash_idx];
+		}
+
+		ret = bpf_map_update_elem(outer_fd, &cpu,
+					  &inner_lru_map_fds[cpu],
+					  BPF_ANY);
+		if (ret) {
+			printf("cannot update ARRAY_OF_LRU_HASHS with key:%u. %s(%d)\n",
+			       cpu, strerror(errno), errno);
+			exit(1);
+		}
+	}
+
+	in6.sin6_addr.s6_addr16[0] = 0xdead;
+	in6.sin6_addr.s6_addr16[1] = 0xbeef;
+
+	if (test == LRU_HASH_PREALLOC) {
+		test_name = "lru_hash_map_perf";
+		in6.sin6_addr.s6_addr16[7] = 0;
+	} else if (test == NOCOMMON_LRU_HASH_PREALLOC) {
+		test_name = "nocommon_lru_hash_map_perf";
+		in6.sin6_addr.s6_addr16[7] = 1;
+	} else if (test == INNER_LRU_HASH_PREALLOC) {
+		test_name = "inner_lru_hash_map_perf";
+		in6.sin6_addr.s6_addr16[7] = 2;
+	} else {
+		assert(0);
+	}
 
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
-		syscall(__NR_getpid);
-	printf("%d:lru_hash_map_perf pre-alloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+	for (i = 0; i < max_cnt; i++) {
+		ret = connect(-1, (const struct sockaddr *)&in6, sizeof(in6));
+		assert(ret == -1 && errno == EBADF);
+	}
+	printf("%d:%s pre-alloc %lld events per sec\n",
+	       cpu, test_name,
+	       max_cnt * 1000000000ll / (time_get_ns() - start_time));
+}
+
+static void test_lru_hash_prealloc(int cpu)
+{
+	do_test_lru(LRU_HASH_PREALLOC, cpu);
 }
 
-static void test_percpu_lru_hash_prealloc(int cpu)
+static void test_nocommon_lru_hash_prealloc(int cpu)
 {
-	__u64 start_time;
-	int i;
+	do_test_lru(NOCOMMON_LRU_HASH_PREALLOC, cpu);
+}
 
-	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
-		syscall(__NR_getppid);
-	printf("%d:lru_hash_map_perf pre-alloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+static void test_inner_lru_hash_prealloc(int cpu)
+{
+	do_test_lru(INNER_LRU_HASH_PREALLOC, cpu);
 }
 
 static void test_percpu_hash_prealloc(int cpu)
@@ -83,10 +171,10 @@ static void test_percpu_hash_prealloc(int cpu)
 	int i;
 
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
+	for (i = 0; i < max_cnt; i++)
 		syscall(__NR_geteuid);
 	printf("%d:percpu_hash_map_perf pre-alloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
 }
 
 static void test_hash_kmalloc(int cpu)
@@ -95,10 +183,10 @@ static void test_hash_kmalloc(int cpu)
 	int i;
 
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
+	for (i = 0; i < max_cnt; i++)
 		syscall(__NR_getgid);
 	printf("%d:hash_map_perf kmalloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
 }
 
 static void test_percpu_hash_kmalloc(int cpu)
@@ -107,10 +195,10 @@ static void test_percpu_hash_kmalloc(int cpu)
 	int i;
 
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
+	for (i = 0; i < max_cnt; i++)
 		syscall(__NR_getegid);
 	printf("%d:percpu_hash_map_perf kmalloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
 }
 
 static void test_lpm_kmalloc(int cpu)
@@ -119,40 +207,63 @@ static void test_lpm_kmalloc(int cpu)
 	int i;
 
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
+	for (i = 0; i < max_cnt; i++)
 		syscall(__NR_gettid);
 	printf("%d:lpm_perf kmalloc %lld events per sec\n",
-	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
 }
 
-static void loop(int cpu)
+static void test_hash_lookup(int cpu)
 {
-	cpu_set_t cpuset;
-
-	CPU_ZERO(&cpuset);
-	CPU_SET(cpu, &cpuset);
-	sched_setaffinity(0, sizeof(cpuset), &cpuset);
+	__u64 start_time;
+	int i;
 
-	if (test_flags & HASH_PREALLOC)
-		test_hash_prealloc(cpu);
+	start_time = time_get_ns();
+	for (i = 0; i < max_cnt; i++)
+		syscall(__NR_getpgid, 0);
+	printf("%d:hash_lookup %lld lookups per sec\n",
+	       cpu, max_cnt * 1000000000ll * 64 / (time_get_ns() - start_time));
+}
 
-	if (test_flags & PERCPU_HASH_PREALLOC)
-		test_percpu_hash_prealloc(cpu);
+static void test_array_lookup(int cpu)
+{
+	__u64 start_time;
+	int i;
 
-	if (test_flags & HASH_KMALLOC)
-		test_hash_kmalloc(cpu);
+	start_time = time_get_ns();
+	for (i = 0; i < max_cnt; i++)
+		syscall(__NR_getpgrp, 0);
+	printf("%d:array_lookup %lld lookups per sec\n",
+	       cpu, max_cnt * 1000000000ll * 64 / (time_get_ns() - start_time));
+}
 
-	if (test_flags & PERCPU_HASH_KMALLOC)
-		test_percpu_hash_kmalloc(cpu);
+typedef void (*test_func)(int cpu);
+const test_func test_funcs[] = {
+	[HASH_PREALLOC] = test_hash_prealloc,
+	[PERCPU_HASH_PREALLOC] = test_percpu_hash_prealloc,
+	[HASH_KMALLOC] = test_hash_kmalloc,
+	[PERCPU_HASH_KMALLOC] = test_percpu_hash_kmalloc,
+	[LRU_HASH_PREALLOC] = test_lru_hash_prealloc,
+	[NOCOMMON_LRU_HASH_PREALLOC] = test_nocommon_lru_hash_prealloc,
+	[LPM_KMALLOC] = test_lpm_kmalloc,
+	[HASH_LOOKUP] = test_hash_lookup,
+	[ARRAY_LOOKUP] = test_array_lookup,
+	[INNER_LRU_HASH_PREALLOC] = test_inner_lru_hash_prealloc,
+};
 
-	if (test_flags & LRU_HASH_PREALLOC)
-		test_lru_hash_prealloc(cpu);
+static void loop(int cpu)
+{
+	cpu_set_t cpuset;
+	int i;
 
-	if (test_flags & PERCPU_LRU_HASH_PREALLOC)
-		test_percpu_lru_hash_prealloc(cpu);
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpu, &cpuset);
+	sched_setaffinity(0, sizeof(cpuset), &cpuset);
 
-	if (test_flags & LPM_KMALLOC)
-		test_lpm_kmalloc(cpu);
+	for (i = 0; i < NR_TESTS; i++) {
+		if (check_test_flags(i))
+			test_funcs[i](cpu);
+	}
 }
 
 static void run_perf_test(int tasks)
@@ -209,6 +320,38 @@ static void fill_lpm_trie(void)
 	assert(!r);
 }
 
+static void fixup_map(struct bpf_map_def *map, const char *name, int idx)
+{
+	int i;
+
+	if (!strcmp("inner_lru_hash_map", name)) {
+		inner_lru_hash_idx = idx;
+		inner_lru_hash_size = map->max_entries;
+	}
+
+	if (!strcmp("array_of_lru_hashs", name)) {
+		if (inner_lru_hash_idx == -1) {
+			printf("inner_lru_hash_map must be defined before array_of_lru_hashs\n");
+			exit(1);
+		}
+		map->inner_map_idx = inner_lru_hash_idx;
+		array_of_lru_hashs_idx = idx;
+	}
+
+	if (num_map_entries <= 0)
+		return;
+
+	inner_lru_hash_size = num_map_entries;
+
+	/* Only change the max_entries for the enabled test(s) */
+	for (i = 0; i < NR_TESTS; i++) {
+		if (!strcmp(test_map_names[i], name) &&
+		    (check_test_flags(i))) {
+			map->max_entries = num_map_entries;
+		}
+	}
+}
+
 int main(int argc, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
@@ -224,7 +367,13 @@ int main(int argc, char **argv)
 	if (argc > 2)
 		num_cpu = atoi(argv[2]) ? : num_cpu;
 
-	if (load_bpf_file(filename)) {
+	if (argc > 3)
+		num_map_entries = atoi(argv[3]);
+
+	if (argc > 4)
+		max_cnt = atoi(argv[4]);
+
+	if (load_bpf_file_fixup_map(filename, fixup_map)) {
 		printf("%s", bpf_log_buf);
 		return 1;
 	}
diff --git a/samples/bpf/run_cookie_uid_helper_example.sh b/samples/bpf/run_cookie_uid_helper_example.sh
new file mode 100755
index 000000000000..f898cfa2b1aa
--- /dev/null
+++ b/samples/bpf/run_cookie_uid_helper_example.sh
@@ -0,0 +1,14 @@
+#!/bin/bash
+local_dir="$(pwd)"
+root_dir=$local_dir/../..
+mnt_dir=$(mktemp -d --tmp)
+
+on_exit() {
+	iptables -D OUTPUT -m bpf --object-pinned ${mnt_dir}/bpf_prog -j ACCEPT
+	umount ${mnt_dir}
+	rm -r ${mnt_dir}
+}
+
+trap on_exit EXIT
+mount -t bpf bpf ${mnt_dir}
+./per_socket_stats_example ${mnt_dir}/bpf_prog $1
diff --git a/samples/bpf/test_lru_dist.c b/samples/bpf/test_lru_dist.c
index d96dc88d3b04..73c357142268 100644
--- a/samples/bpf/test_lru_dist.c
+++ b/samples/bpf/test_lru_dist.c
@@ -25,7 +25,9 @@
 #include "bpf_util.h"
 
 #define min(a, b) ((a) < (b) ? (a) : (b))
-#define offsetof(TYPE, MEMBER)	((size_t)&((TYPE *)0)->MEMBER)
+#ifndef offsetof
+# define offsetof(TYPE, MEMBER)	((size_t)&((TYPE *)0)->MEMBER)
+#endif
 #define container_of(ptr, type, member) ({			\
 	const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
 	(type *)( (char *)__mptr - offsetof(type,member) );})
diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c
new file mode 100644
index 000000000000..42c44d091dd1
--- /dev/null
+++ b/samples/bpf/test_map_in_map_kern.c
@@ -0,0 +1,173 @@
+/*
+ * Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#define KBUILD_MODNAME "foo"
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/in6.h>
+#include "bpf_helpers.h"
+
+#define MAX_NR_PORTS 65536
+
+/* map #0 */
+struct bpf_map_def SEC("maps") port_a = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(int),
+	.max_entries = MAX_NR_PORTS,
+};
+
+/* map #1 */
+struct bpf_map_def SEC("maps") port_h = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(int),
+	.max_entries = 1,
+};
+
+/* map #2 */
+struct bpf_map_def SEC("maps") reg_result_h = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(int),
+	.max_entries = 1,
+};
+
+/* map #3 */
+struct bpf_map_def SEC("maps") inline_result_h = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(int),
+	.max_entries = 1,
+};
+
+/* map #4 */ /* Test case #0 */
+struct bpf_map_def SEC("maps") a_of_port_a = {
+	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	.key_size = sizeof(u32),
+	.inner_map_idx = 0, /* map_fd[0] is port_a */
+	.max_entries = MAX_NR_PORTS,
+};
+
+/* map #5 */ /* Test case #1 */
+struct bpf_map_def SEC("maps") h_of_port_a = {
+	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
+	.key_size = sizeof(u32),
+	.inner_map_idx = 0, /* map_fd[0] is port_a */
+	.max_entries = 1,
+};
+
+/* map #6 */ /* Test case #2 */
+struct bpf_map_def SEC("maps") h_of_port_h = {
+	.type = BPF_MAP_TYPE_HASH_OF_MAPS,
+	.key_size = sizeof(u32),
+	.inner_map_idx = 1, /* map_fd[1] is port_h */
+	.max_entries = 1,
+};
+
+static __always_inline int do_reg_lookup(void *inner_map, u32 port)
+{
+	int *result;
+
+	result = bpf_map_lookup_elem(inner_map, &port);
+	return result ? *result : -ENOENT;
+}
+
+static __always_inline int do_inline_array_lookup(void *inner_map, u32 port)
+{
+	int *result;
+
+	if (inner_map != &port_a)
+		return -EINVAL;
+
+	result = bpf_map_lookup_elem(&port_a, &port);
+	return result ? *result : -ENOENT;
+}
+
+static __always_inline int do_inline_hash_lookup(void *inner_map, u32 port)
+{
+	int *result;
+
+	if (inner_map != &port_h)
+		return -EINVAL;
+
+	result = bpf_map_lookup_elem(&port_h, &port);
+	return result ? *result : -ENOENT;
+}
+
+SEC("kprobe/sys_connect")
+int trace_sys_connect(struct pt_regs *ctx)
+{
+	struct sockaddr_in6 *in6;
+	u16 test_case, port, dst6[8];
+	int addrlen, ret, inline_ret, ret_key = 0;
+	u32 port_key;
+	void *outer_map, *inner_map;
+	bool inline_hash = false;
+
+	in6 = (struct sockaddr_in6 *)PT_REGS_PARM2(ctx);
+	addrlen = (int)PT_REGS_PARM3(ctx);
+
+	if (addrlen != sizeof(*in6))
+		return 0;
+
+	ret = bpf_probe_read(dst6, sizeof(dst6), &in6->sin6_addr);
+	if (ret) {
+		inline_ret = ret;
+		goto done;
+	}
+
+	if (dst6[0] != 0xdead || dst6[1] != 0xbeef)
+		return 0;
+
+	test_case = dst6[7];
+
+	ret = bpf_probe_read(&port, sizeof(port), &in6->sin6_port);
+	if (ret) {
+		inline_ret = ret;
+		goto done;
+	}
+
+	port_key = port;
+
+	ret = -ENOENT;
+	if (test_case == 0) {
+		outer_map = &a_of_port_a;
+	} else if (test_case == 1) {
+		outer_map = &h_of_port_a;
+	} else if (test_case == 2) {
+		outer_map = &h_of_port_h;
+	} else {
+		ret = __LINE__;
+		inline_ret = ret;
+		goto done;
+	}
+
+	inner_map = bpf_map_lookup_elem(outer_map, &port_key);
+	if (!inner_map) {
+		ret = __LINE__;
+		inline_ret = ret;
+		goto done;
+	}
+
+	ret = do_reg_lookup(inner_map, port_key);
+
+	if (test_case == 0 || test_case == 1)
+		inline_ret = do_inline_array_lookup(inner_map, port_key);
+	else
+		inline_ret = do_inline_hash_lookup(inner_map, port_key);
+
+done:
+	bpf_map_update_elem(&reg_result_h, &ret_key, &ret, BPF_ANY);
+	bpf_map_update_elem(&inline_result_h, &ret_key, &inline_ret, BPF_ANY);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/test_map_in_map_user.c b/samples/bpf/test_map_in_map_user.c
new file mode 100644
index 000000000000..f62fdc2bd428
--- /dev/null
+++ b/samples/bpf/test_map_in_map_user.c
@@ -0,0 +1,116 @@
+/*
+ * Copyright (c) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include <stdint.h>
+#include <assert.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#define PORT_A		(map_fd[0])
+#define PORT_H		(map_fd[1])
+#define REG_RESULT_H	(map_fd[2])
+#define INLINE_RESULT_H	(map_fd[3])
+#define A_OF_PORT_A	(map_fd[4]) /* Test case #0 */
+#define H_OF_PORT_A	(map_fd[5]) /* Test case #1 */
+#define H_OF_PORT_H	(map_fd[6]) /* Test case #2 */
+
+static const char * const test_names[] = {
+	"Array of Array",
+	"Hash of Array",
+	"Hash of Hash",
+};
+
+#define NR_TESTS (sizeof(test_names) / sizeof(*test_names))
+
+static void populate_map(uint32_t port_key, int magic_result)
+{
+	int ret;
+
+	ret = bpf_map_update_elem(PORT_A, &port_key, &magic_result, BPF_ANY);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(PORT_H, &port_key, &magic_result,
+				  BPF_NOEXIST);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(A_OF_PORT_A, &port_key, &PORT_A, BPF_ANY);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(H_OF_PORT_A, &port_key, &PORT_A, BPF_NOEXIST);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(H_OF_PORT_H, &port_key, &PORT_H, BPF_NOEXIST);
+	assert(!ret);
+}
+
+static void test_map_in_map(void)
+{
+	struct sockaddr_in6 in6 = { .sin6_family = AF_INET6 };
+	uint32_t result_key = 0, port_key;
+	int result, inline_result;
+	int magic_result = 0xfaceb00c;
+	int ret;
+	int i;
+
+	port_key = rand() & 0x00FF;
+	populate_map(port_key, magic_result);
+
+	in6.sin6_addr.s6_addr16[0] = 0xdead;
+	in6.sin6_addr.s6_addr16[1] = 0xbeef;
+	in6.sin6_port = port_key;
+
+	for (i = 0; i < NR_TESTS; i++) {
+		printf("%s: ", test_names[i]);
+
+		in6.sin6_addr.s6_addr16[7] = i;
+		ret = connect(-1, (struct sockaddr *)&in6, sizeof(in6));
+		assert(ret == -1 && errno == EBADF);
+
+		ret = bpf_map_lookup_elem(REG_RESULT_H, &result_key, &result);
+		assert(!ret);
+
+		ret = bpf_map_lookup_elem(INLINE_RESULT_H, &result_key,
+					  &inline_result);
+		assert(!ret);
+
+		if (result != magic_result || inline_result != magic_result) {
+			printf("Error. result:%d inline_result:%d\n",
+			       result, inline_result);
+			exit(1);
+		}
+
+		bpf_map_delete_elem(REG_RESULT_H, &result_key);
+		bpf_map_delete_elem(INLINE_RESULT_H, &result_key);
+
+		printf("Pass\n");
+	}
+}
+
+int main(int argc, char **argv)
+{
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	char filename[256];
+
+	assert(!setrlimit(RLIMIT_MEMLOCK, &r));
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	test_map_in_map();
+
+	return 0;
+}
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index d2be65d1fd86..378850c70eb8 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -5,6 +5,7 @@
  * License as published by the Free Software Foundation.
  */
 #include <linux/bpf.h>
+#include <linux/if_link.h>
 #include <assert.h>
 #include <errno.h>
 #include <signal.h>
@@ -12,16 +13,18 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <libgen.h>
 
 #include "bpf_load.h"
 #include "bpf_util.h"
 #include "libbpf.h"
 
 static int ifindex;
+static __u32 xdp_flags;
 
 static void int_exit(int sig)
 {
-	set_link_xdp_fd(ifindex, -1);
+	set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(0);
 }
 
@@ -54,18 +57,39 @@ static void poll_stats(int interval)
 	}
 }
 
-int main(int ac, char **argv)
+static void usage(const char *prog)
 {
-	char filename[256];
+	fprintf(stderr,
+		"usage: %s [OPTS] IFINDEX\n\n"
+		"OPTS:\n"
+		"    -S    use skb-mode\n",
+		prog);
+}
 
-	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+int main(int argc, char **argv)
+{
+	const char *optstr = "S";
+	char filename[256];
+	int opt;
+
+	while ((opt = getopt(argc, argv, optstr)) != -1) {
+		switch (opt) {
+		case 'S':
+			xdp_flags |= XDP_FLAGS_SKB_MODE;
+			break;
+		default:
+			usage(basename(argv[0]));
+			return 1;
+		}
+	}
 
-	if (ac != 2) {
-		printf("usage: %s IFINDEX\n", argv[0]);
+	if (optind == argc) {
+		usage(basename(argv[0]));
 		return 1;
 	}
+	ifindex = strtoul(argv[optind], NULL, 0);
 
-	ifindex = strtoul(argv[1], NULL, 0);
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
 
 	if (load_bpf_file(filename)) {
 		printf("%s", bpf_log_buf);
@@ -79,7 +103,7 @@ int main(int ac, char **argv)
 
 	signal(SIGINT, int_exit);
 
-	if (set_link_xdp_fd(ifindex, prog_fd[0]) < 0) {
+	if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
 		printf("link set xdp fd failed\n");
 		return 1;
 	}
diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c
index 70e192fc61aa..92b8bde9337c 100644
--- a/samples/bpf/xdp_tx_iptunnel_user.c
+++ b/samples/bpf/xdp_tx_iptunnel_user.c
@@ -5,6 +5,7 @@
  * License as published by the Free Software Foundation.
  */
 #include <linux/bpf.h>
+#include <linux/if_link.h>
 #include <assert.h>
 #include <errno.h>
 #include <signal.h>
@@ -24,11 +25,12 @@
 #define STATS_INTERVAL_S 2U
 
 static int ifindex = -1;
+static __u32 xdp_flags = 0;
 
 static void int_exit(int sig)
 {
 	if (ifindex > -1)
-		set_link_xdp_fd(ifindex, -1);
+		set_link_xdp_fd(ifindex, -1, xdp_flags);
 	exit(0);
 }
 
@@ -136,7 +138,7 @@ int main(int argc, char **argv)
 {
 	unsigned char opt_flags[256] = {};
 	unsigned int kill_after_s = 0;
-	const char *optstr = "i:a:p:s:d:m:T:P:h";
+	const char *optstr = "i:a:p:s:d:m:T:P:Sh";
 	int min_port = 0, max_port = 0;
 	struct iptnl_info tnl = {};
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
@@ -201,6 +203,9 @@ int main(int argc, char **argv)
 		case 'T':
 			kill_after_s = atoi(optarg);
 			break;
+		case 'S':
+			xdp_flags |= XDP_FLAGS_SKB_MODE;
+			break;
 		default:
 			usage(argv[0]);
 			return 1;
@@ -243,14 +248,14 @@ int main(int argc, char **argv)
 		}
 	}
 
-	if (set_link_xdp_fd(ifindex, prog_fd[0]) < 0) {
+	if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
 		printf("link set xdp fd failed\n");
 		return 1;
 	}
 
 	poll_stats(kill_after_s);
 
-	set_link_xdp_fd(ifindex, -1);
+	set_link_xdp_fd(ifindex, -1, xdp_flags);
 
 	return 0;
 }