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
  ...

1 files changed, 154 insertions, 28 deletions

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);