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

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

1 files changed, 373 insertions, 0 deletions

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
new file mode 100644
index 000000000000..8c54a4b6f187
--- /dev/null
+++ b/tools/lib/bpf/btf.c
@@ -0,0 +1,373 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <linux/err.h>
+#include <linux/btf.h>
+#include "btf.h"
+#include "bpf.h"
+
+#define elog(fmt, ...) { if (err_log) err_log(fmt, ##__VA_ARGS__); }
+#define max(a, b) ((a) > (b) ? (a) : (b))
+#define min(a, b) ((a) < (b) ? (a) : (b))
+
+#define BTF_MAX_NR_TYPES 65535
+
+static struct btf_type btf_void;
+
+struct btf {
+	union {
+		struct btf_header *hdr;
+		void *data;
+	};
+	struct btf_type **types;
+	const char *strings;
+	void *nohdr_data;
+	uint32_t nr_types;
+	uint32_t types_size;
+	uint32_t data_size;
+	int fd;
+};
+
+static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset)
+{
+	if (offset < btf->hdr->str_len)
+		return &btf->strings[offset];
+	else
+		return NULL;
+}
+
+static int btf_add_type(struct btf *btf, struct btf_type *t)
+{
+	if (btf->types_size - btf->nr_types < 2) {
+		struct btf_type **new_types;
+		u32 expand_by, new_size;
+
+		if (btf->types_size == BTF_MAX_NR_TYPES)
+			return -E2BIG;
+
+		expand_by = max(btf->types_size >> 2, 16);
+		new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by);
+
+		new_types = realloc(btf->types, sizeof(*new_types) * new_size);
+		if (!new_types)
+			return -ENOMEM;
+
+		if (btf->nr_types == 0)
+			new_types[0] = &btf_void;
+
+		btf->types = new_types;
+		btf->types_size = new_size;
+	}
+
+	btf->types[++(btf->nr_types)] = t;
+
+	return 0;
+}
+
+static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log)
+{
+	const struct btf_header *hdr = btf->hdr;
+	u32 meta_left;
+
+	if (btf->data_size < sizeof(struct btf_header)) {
+		elog("BTF header not found\n");
+		return -EINVAL;
+	}
+
+	if (hdr->magic != BTF_MAGIC) {
+		elog("Invalid BTF magic:%x\n", hdr->magic);
+		return -EINVAL;
+	}
+
+	if (hdr->version != BTF_VERSION) {
+		elog("Unsupported BTF version:%u\n", hdr->version);
+		return -ENOTSUP;
+	}
+
+	if (hdr->flags) {
+		elog("Unsupported BTF flags:%x\n", hdr->flags);
+		return -ENOTSUP;
+	}
+
+	meta_left = btf->data_size - sizeof(*hdr);
+	if (!meta_left) {
+		elog("BTF has no data\n");
+		return -EINVAL;
+	}
+
+	if (meta_left < hdr->type_off) {
+		elog("Invalid BTF type section offset:%u\n", hdr->type_off);
+		return -EINVAL;
+	}
+
+	if (meta_left < hdr->str_off) {
+		elog("Invalid BTF string section offset:%u\n", hdr->str_off);
+		return -EINVAL;
+	}
+
+	if (hdr->type_off >= hdr->str_off) {
+		elog("BTF type section offset >= string section offset. No type?\n");
+		return -EINVAL;
+	}
+
+	if (hdr->type_off & 0x02) {
+		elog("BTF type section is not aligned to 4 bytes\n");
+		return -EINVAL;
+	}
+
+	btf->nohdr_data = btf->hdr + 1;
+
+	return 0;
+}
+
+static int btf_parse_str_sec(struct btf *btf, btf_print_fn_t err_log)
+{
+	const struct btf_header *hdr = btf->hdr;
+	const char *start = btf->nohdr_data + hdr->str_off;
+	const char *end = start + btf->hdr->str_len;
+
+	if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET ||
+	    start[0] || end[-1]) {
+		elog("Invalid BTF string section\n");
+		return -EINVAL;
+	}
+
+	btf->strings = start;
+
+	return 0;
+}
+
+static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
+{
+	struct btf_header *hdr = btf->hdr;
+	void *nohdr_data = btf->nohdr_data;
+	void *next_type = nohdr_data + hdr->type_off;
+	void *end_type = nohdr_data + hdr->str_off;
+
+	while (next_type < end_type) {
+		struct btf_type *t = next_type;
+		uint16_t vlen = BTF_INFO_VLEN(t->info);
+		int err;
+
+		next_type += sizeof(*t);
+		switch (BTF_INFO_KIND(t->info)) {
+		case BTF_KIND_INT:
+			next_type += sizeof(int);
+			break;
+		case BTF_KIND_ARRAY:
+			next_type += sizeof(struct btf_array);
+			break;
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION:
+			next_type += vlen * sizeof(struct btf_member);
+			break;
+		case BTF_KIND_ENUM:
+			next_type += vlen * sizeof(struct btf_enum);
+			break;
+		case BTF_KIND_TYPEDEF:
+		case BTF_KIND_PTR:
+		case BTF_KIND_FWD:
+		case BTF_KIND_VOLATILE:
+		case BTF_KIND_CONST:
+		case BTF_KIND_RESTRICT:
+			break;
+		default:
+			elog("Unsupported BTF_KIND:%u\n",
+			     BTF_INFO_KIND(t->info));
+			return -EINVAL;
+		}
+
+		err = btf_add_type(btf, t);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static const struct btf_type *btf_type_by_id(const struct btf *btf,
+					     uint32_t type_id)
+{
+	if (type_id > btf->nr_types)
+		return NULL;
+
+	return btf->types[type_id];
+}
+
+static bool btf_type_is_void(const struct btf_type *t)
+{
+	return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
+}
+
+static bool btf_type_is_void_or_null(const struct btf_type *t)
+{
+	return !t || btf_type_is_void(t);
+}
+
+static int64_t btf_type_size(const struct btf_type *t)
+{
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_INT:
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+	case BTF_KIND_ENUM:
+		return t->size;
+	case BTF_KIND_PTR:
+		return sizeof(void *);
+	default:
+		return -EINVAL;
+	}
+}
+
+#define MAX_RESOLVE_DEPTH 32
+
+int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id)
+{
+	const struct btf_array *array;
+	const struct btf_type *t;
+	uint32_t nelems = 1;
+	int64_t size = -1;
+	int i;
+
+	t = btf_type_by_id(btf, type_id);
+	for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
+	     i++) {
+		size = btf_type_size(t);
+		if (size >= 0)
+			break;
+
+		switch (BTF_INFO_KIND(t->info)) {
+		case BTF_KIND_TYPEDEF:
+		case BTF_KIND_VOLATILE:
+		case BTF_KIND_CONST:
+		case BTF_KIND_RESTRICT:
+			type_id = t->type;
+			break;
+		case BTF_KIND_ARRAY:
+			array = (const struct btf_array *)(t + 1);
+			if (nelems && array->nelems > UINT32_MAX / nelems)
+				return -E2BIG;
+			nelems *= array->nelems;
+			type_id = array->type;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		t = btf_type_by_id(btf, type_id);
+	}
+
+	if (size < 0)
+		return -EINVAL;
+
+	if (nelems && size > UINT32_MAX / nelems)
+		return -E2BIG;
+
+	return nelems * size;
+}
+
+int32_t btf__find_by_name(const struct btf *btf, const char *type_name)
+{
+	uint32_t i;
+
+	if (!strcmp(type_name, "void"))
+		return 0;
+
+	for (i = 1; i <= btf->nr_types; i++) {
+		const struct btf_type *t = btf->types[i];
+		const char *name = btf_name_by_offset(btf, t->name_off);
+
+		if (name && !strcmp(type_name, name))
+			return i;
+	}
+
+	return -ENOENT;
+}
+
+void btf__free(struct btf *btf)
+{
+	if (!btf)
+		return;
+
+	if (btf->fd != -1)
+		close(btf->fd);
+
+	free(btf->data);
+	free(btf->types);
+	free(btf);
+}
+
+struct btf *btf__new(uint8_t *data, uint32_t size,
+		     btf_print_fn_t err_log)
+{
+	uint32_t log_buf_size = 0;
+	char *log_buf = NULL;
+	struct btf *btf;
+	int err;
+
+	btf = calloc(1, sizeof(struct btf));
+	if (!btf)
+		return ERR_PTR(-ENOMEM);
+
+	btf->fd = -1;
+
+	if (err_log) {
+		log_buf = malloc(BPF_LOG_BUF_SIZE);
+		if (!log_buf) {
+			err = -ENOMEM;
+			goto done;
+		}
+		*log_buf = 0;
+		log_buf_size = BPF_LOG_BUF_SIZE;
+	}
+
+	btf->data = malloc(size);
+	if (!btf->data) {
+		err = -ENOMEM;
+		goto done;
+	}
+
+	memcpy(btf->data, data, size);
+	btf->data_size = size;
+
+	btf->fd = bpf_load_btf(btf->data, btf->data_size,
+			       log_buf, log_buf_size, false);
+
+	if (btf->fd == -1) {
+		err = -errno;
+		elog("Error loading BTF: %s(%d)\n", strerror(errno), errno);
+		if (log_buf && *log_buf)
+			elog("%s\n", log_buf);
+		goto done;
+	}
+
+	err = btf_parse_hdr(btf, err_log);
+	if (err)
+		goto done;
+
+	err = btf_parse_str_sec(btf, err_log);
+	if (err)
+		goto done;
+
+	err = btf_parse_type_sec(btf, err_log);
+
+done:
+	free(log_buf);
+
+	if (err) {
+		btf__free(btf);
+		return ERR_PTR(err);
+	}
+
+	return btf;
+}
+
+int btf__fd(const struct btf *btf)
+{
+	return btf->fd;
+}