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

Pull networking updates from David Miller:

 1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan.

 2) Support UDP segmentation in code TSO code, from Eric Dumazet.

 3) Allow flashing different flash images in cxgb4 driver, from Vishal
    Kulkarni.

 4) Add drop frames counter and flow status to tc flower offloading,
    from Po Liu.

 5) Support n-tuple filters in cxgb4, from Vishal Kulkarni.

 6) Various new indirect call avoidance, from Eric Dumazet and Brian
    Vazquez.

 7) Fix BPF verifier failures on 32-bit pointer arithmetic, from
    Yonghong Song.

 8) Support querying and setting hardware address of a port function via
    devlink, use this in mlx5, from Parav Pandit.

 9) Support hw ipsec offload on bonding slaves, from Jarod Wilson.

10) Switch qca8k driver over to phylink, from Jonathan McDowell.

11) In bpftool, show list of processes holding BPF FD references to
    maps, programs, links, and btf objects. From Andrii Nakryiko.

12) Several conversions over to generic power management, from Vaibhav
    Gupta.

13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry
    Yakunin.

14) Various https url conversions, from Alexander A. Klimov.

15) Timestamping and PHC support for mscc PHY driver, from Antoine
    Tenart.

16) Support bpf iterating over tcp and udp sockets, from Yonghong Song.

17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov.

18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan.

19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several
    drivers. From Luc Van Oostenryck.

20) XDP support for xen-netfront, from Denis Kirjanov.

21) Support receive buffer autotuning in MPTCP, from Florian Westphal.

22) Support EF100 chip in sfc driver, from Edward Cree.

23) Add XDP support to mvpp2 driver, from Matteo Croce.

24) Support MPTCP in sock_diag, from Paolo Abeni.

25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic
    infrastructure, from Jakub Kicinski.

26) Several pci_ --> dma_ API conversions, from Christophe JAILLET.

27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel.

28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki.

29) Refactor a lot of networking socket option handling code in order to
    avoid set_fs() calls, from Christoph Hellwig.

30) Add rfc4884 support to icmp code, from Willem de Bruijn.

31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei.

32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin.

33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin.

34) Support TCP syncookies in MPTCP, from Flowian Westphal.

35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano
    Brivio.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits)
  net: thunderx: initialize VF's mailbox mutex before first usage
  usb: hso: remove bogus check for EINPROGRESS
  usb: hso: no complaint about kmalloc failure
  hso: fix bailout in error case of probe
  ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM
  selftests/net: relax cpu affinity requirement in msg_zerocopy test
  mptcp: be careful on subflow creation
  selftests: rtnetlink: make kci_test_encap() return sub-test result
  selftests: rtnetlink: correct the final return value for the test
  net: dsa: sja1105: use detected device id instead of DT one on mismatch
  tipc: set ub->ifindex for local ipv6 address
  ipv6: add ipv6_dev_find()
  net: openvswitch: silence suspicious RCU usage warning
  Revert "vxlan: fix tos value before xmit"
  ptp: only allow phase values lower than 1 period
  farsync: switch from 'pci_' to 'dma_' API
  wan: wanxl: switch from 'pci_' to 'dma_' API
  hv_netvsc: do not use VF device if link is down
  dpaa2-eth: Fix passing zero to 'PTR_ERR' warning
  net: macb: Properly handle phylink on at91sam9x
  ...

1 files changed, 426 insertions, 57 deletions

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index c47bdc65de8e..65303664417e 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -1,10 +1,11 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (C) 2017-2018 Netronome Systems, Inc. */
 
+#define _GNU_SOURCE
 #include <ctype.h>
 #include <errno.h>
 #include <fcntl.h>
-#include <fts.h>
+#include <ftw.h>
 #include <libgen.h>
 #include <mntent.h>
 #include <stdbool.h>
@@ -29,6 +30,44 @@
 #define BPF_FS_MAGIC		0xcafe4a11
 #endif
 
+const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = {
+	[BPF_CGROUP_INET_INGRESS]	= "ingress",
+	[BPF_CGROUP_INET_EGRESS]	= "egress",
+	[BPF_CGROUP_INET_SOCK_CREATE]	= "sock_create",
+	[BPF_CGROUP_INET_SOCK_RELEASE]	= "sock_release",
+	[BPF_CGROUP_SOCK_OPS]		= "sock_ops",
+	[BPF_CGROUP_DEVICE]		= "device",
+	[BPF_CGROUP_INET4_BIND]		= "bind4",
+	[BPF_CGROUP_INET6_BIND]		= "bind6",
+	[BPF_CGROUP_INET4_CONNECT]	= "connect4",
+	[BPF_CGROUP_INET6_CONNECT]	= "connect6",
+	[BPF_CGROUP_INET4_POST_BIND]	= "post_bind4",
+	[BPF_CGROUP_INET6_POST_BIND]	= "post_bind6",
+	[BPF_CGROUP_INET4_GETPEERNAME]	= "getpeername4",
+	[BPF_CGROUP_INET6_GETPEERNAME]	= "getpeername6",
+	[BPF_CGROUP_INET4_GETSOCKNAME]	= "getsockname4",
+	[BPF_CGROUP_INET6_GETSOCKNAME]	= "getsockname6",
+	[BPF_CGROUP_UDP4_SENDMSG]	= "sendmsg4",
+	[BPF_CGROUP_UDP6_SENDMSG]	= "sendmsg6",
+	[BPF_CGROUP_SYSCTL]		= "sysctl",
+	[BPF_CGROUP_UDP4_RECVMSG]	= "recvmsg4",
+	[BPF_CGROUP_UDP6_RECVMSG]	= "recvmsg6",
+	[BPF_CGROUP_GETSOCKOPT]		= "getsockopt",
+	[BPF_CGROUP_SETSOCKOPT]		= "setsockopt",
+
+	[BPF_SK_SKB_STREAM_PARSER]	= "sk_skb_stream_parser",
+	[BPF_SK_SKB_STREAM_VERDICT]	= "sk_skb_stream_verdict",
+	[BPF_SK_MSG_VERDICT]		= "sk_msg_verdict",
+	[BPF_LIRC_MODE2]		= "lirc_mode2",
+	[BPF_FLOW_DISSECTOR]		= "flow_dissector",
+	[BPF_TRACE_RAW_TP]		= "raw_tp",
+	[BPF_TRACE_FENTRY]		= "fentry",
+	[BPF_TRACE_FEXIT]		= "fexit",
+	[BPF_MODIFY_RETURN]		= "mod_ret",
+	[BPF_LSM_MAC]			= "lsm_mac",
+	[BPF_SK_LOOKUP]			= "sk_lookup",
+};
+
 void p_err(const char *fmt, ...)
 {
 	va_list ap;
@@ -123,24 +162,35 @@ int mount_tracefs(const char *target)
 	return err;
 }
 
-int open_obj_pinned(char *path, bool quiet)
+int open_obj_pinned(const char *path, bool quiet)
 {
-	int fd;
+	char *pname;
+	int fd = -1;
+
+	pname = strdup(path);
+	if (!pname) {
+		if (!quiet)
+			p_err("mem alloc failed");
+		goto out_ret;
+	}
 
-	fd = bpf_obj_get(path);
+	fd = bpf_obj_get(pname);
 	if (fd < 0) {
 		if (!quiet)
-			p_err("bpf obj get (%s): %s", path,
-			      errno == EACCES && !is_bpffs(dirname(path)) ?
+			p_err("bpf obj get (%s): %s", pname,
+			      errno == EACCES && !is_bpffs(dirname(pname)) ?
 			    "directory not in bpf file system (bpffs)" :
 			    strerror(errno));
-		return -1;
+		goto out_free;
 	}
 
+out_free:
+	free(pname);
+out_ret:
 	return fd;
 }
 
-int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
+int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type)
 {
 	enum bpf_obj_type type;
 	int fd;
@@ -330,71 +380,82 @@ void print_hex_data_json(uint8_t *data, size_t len)
 	jsonw_end_array(json_wtr);
 }
 
+/* extra params for nftw cb */
+static struct pinned_obj_table *build_fn_table;
+static enum bpf_obj_type build_fn_type;
+
+static int do_build_table_cb(const char *fpath, const struct stat *sb,
+			     int typeflag, struct FTW *ftwbuf)
+{
+	struct bpf_prog_info pinned_info;
+	__u32 len = sizeof(pinned_info);
+	struct pinned_obj *obj_node;
+	enum bpf_obj_type objtype;
+	int fd, err = 0;
+
+	if (typeflag != FTW_F)
+		goto out_ret;
+
+	fd = open_obj_pinned(fpath, true);
+	if (fd < 0)
+		goto out_ret;
+
+	objtype = get_fd_type(fd);
+	if (objtype != build_fn_type)
+		goto out_close;
+
+	memset(&pinned_info, 0, sizeof(pinned_info));
+	if (bpf_obj_get_info_by_fd(fd, &pinned_info, &len))
+		goto out_close;
+
+	obj_node = calloc(1, sizeof(*obj_node));
+	if (!obj_node) {
+		err = -1;
+		goto out_close;
+	}
+
+	obj_node->id = pinned_info.id;
+	obj_node->path = strdup(fpath);
+	if (!obj_node->path) {
+		err = -1;
+		free(obj_node);
+		goto out_close;
+	}
+
+	hash_add(build_fn_table->table, &obj_node->hash, obj_node->id);
+out_close:
+	close(fd);
+out_ret:
+	return err;
+}
+
 int build_pinned_obj_table(struct pinned_obj_table *tab,
 			   enum bpf_obj_type type)
 {
-	struct bpf_prog_info pinned_info = {};
-	struct pinned_obj *obj_node = NULL;
-	__u32 len = sizeof(pinned_info);
 	struct mntent *mntent = NULL;
-	enum bpf_obj_type objtype;
 	FILE *mntfile = NULL;
-	FTSENT *ftse = NULL;
-	FTS *fts = NULL;
-	int fd, err;
+	int flags = FTW_PHYS;
+	int nopenfd = 16;
+	int err = 0;
 
 	mntfile = setmntent("/proc/mounts", "r");
 	if (!mntfile)
 		return -1;
 
+	build_fn_table = tab;
+	build_fn_type = type;
+
 	while ((mntent = getmntent(mntfile))) {
-		char *path[] = { mntent->mnt_dir, NULL };
+		char *path = mntent->mnt_dir;
 
 		if (strncmp(mntent->mnt_type, "bpf", 3) != 0)
 			continue;
-
-		fts = fts_open(path, 0, NULL);
-		if (!fts)
-			continue;
-
-		while ((ftse = fts_read(fts))) {
-			if (!(ftse->fts_info & FTS_F))
-				continue;
-			fd = open_obj_pinned(ftse->fts_path, true);
-			if (fd < 0)
-				continue;
-
-			objtype = get_fd_type(fd);
-			if (objtype != type) {
-				close(fd);
-				continue;
-			}
-			memset(&pinned_info, 0, sizeof(pinned_info));
-			err = bpf_obj_get_info_by_fd(fd, &pinned_info, &len);
-			if (err) {
-				close(fd);
-				continue;
-			}
-
-			obj_node = malloc(sizeof(*obj_node));
-			if (!obj_node) {
-				close(fd);
-				fts_close(fts);
-				fclose(mntfile);
-				return -1;
-			}
-
-			memset(obj_node, 0, sizeof(*obj_node));
-			obj_node->id = pinned_info.id;
-			obj_node->path = strdup(ftse->fts_path);
-			hash_add(tab->table, &obj_node->hash, obj_node->id);
-
-			close(fd);
-		}
-		fts_close(fts);
+		err = nftw(path, do_build_table_cb, nopenfd, flags);
+		if (err)
+			break;
 	}
 	fclose(mntfile);
-	return 0;
+	return err;
 }
 
 void delete_pinned_obj_table(struct pinned_obj_table *tab)
@@ -581,3 +642,311 @@ print_all_levels(__maybe_unused enum libbpf_print_level level,
 {
 	return vfprintf(stderr, format, args);
 }
+
+static int prog_fd_by_nametag(void *nametag, int **fds, bool tag)
+{
+	unsigned int id = 0;
+	int fd, nb_fds = 0;
+	void *tmp;
+	int err;
+
+	while (true) {
+		struct bpf_prog_info info = {};
+		__u32 len = sizeof(info);
+
+		err = bpf_prog_get_next_id(id, &id);
+		if (err) {
+			if (errno != ENOENT) {
+				p_err("%s", strerror(errno));
+				goto err_close_fds;
+			}
+			return nb_fds;
+		}
+
+		fd = bpf_prog_get_fd_by_id(id);
+		if (fd < 0) {
+			p_err("can't get prog by id (%u): %s",
+			      id, strerror(errno));
+			goto err_close_fds;
+		}
+
+		err = bpf_obj_get_info_by_fd(fd, &info, &len);
+		if (err) {
+			p_err("can't get prog info (%u): %s",
+			      id, strerror(errno));
+			goto err_close_fd;
+		}
+
+		if ((tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) ||
+		    (!tag && strncmp(nametag, info.name, BPF_OBJ_NAME_LEN))) {
+			close(fd);
+			continue;
+		}
+
+		if (nb_fds > 0) {
+			tmp = realloc(*fds, (nb_fds + 1) * sizeof(int));
+			if (!tmp) {
+				p_err("failed to realloc");
+				goto err_close_fd;
+			}
+			*fds = tmp;
+		}
+		(*fds)[nb_fds++] = fd;
+	}
+
+err_close_fd:
+	close(fd);
+err_close_fds:
+	while (--nb_fds >= 0)
+		close((*fds)[nb_fds]);
+	return -1;
+}
+
+int prog_parse_fds(int *argc, char ***argv, int **fds)
+{
+	if (is_prefix(**argv, "id")) {
+		unsigned int id;
+		char *endptr;
+
+		NEXT_ARGP();
+
+		id = strtoul(**argv, &endptr, 0);
+		if (*endptr) {
+			p_err("can't parse %s as ID", **argv);
+			return -1;
+		}
+		NEXT_ARGP();
+
+		(*fds)[0] = bpf_prog_get_fd_by_id(id);
+		if ((*fds)[0] < 0) {
+			p_err("get by id (%u): %s", id, strerror(errno));
+			return -1;
+		}
+		return 1;
+	} else if (is_prefix(**argv, "tag")) {
+		unsigned char tag[BPF_TAG_SIZE];
+
+		NEXT_ARGP();
+
+		if (sscanf(**argv, BPF_TAG_FMT, tag, tag + 1, tag + 2,
+			   tag + 3, tag + 4, tag + 5, tag + 6, tag + 7)
+		    != BPF_TAG_SIZE) {
+			p_err("can't parse tag");
+			return -1;
+		}
+		NEXT_ARGP();
+
+		return prog_fd_by_nametag(tag, fds, true);
+	} else if (is_prefix(**argv, "name")) {
+		char *name;
+
+		NEXT_ARGP();
+
+		name = **argv;
+		if (strlen(name) > BPF_OBJ_NAME_LEN - 1) {
+			p_err("can't parse name");
+			return -1;
+		}
+		NEXT_ARGP();
+
+		return prog_fd_by_nametag(name, fds, false);
+	} else if (is_prefix(**argv, "pinned")) {
+		char *path;
+
+		NEXT_ARGP();
+
+		path = **argv;
+		NEXT_ARGP();
+
+		(*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG);
+		if ((*fds)[0] < 0)
+			return -1;
+		return 1;
+	}
+
+	p_err("expected 'id', 'tag', 'name' or 'pinned', got: '%s'?", **argv);
+	return -1;
+}
+
+int prog_parse_fd(int *argc, char ***argv)
+{
+	int *fds = NULL;
+	int nb_fds, fd;
+
+	fds = malloc(sizeof(int));
+	if (!fds) {
+		p_err("mem alloc failed");
+		return -1;
+	}
+	nb_fds = prog_parse_fds(argc, argv, &fds);
+	if (nb_fds != 1) {
+		if (nb_fds > 1) {
+			p_err("several programs match this handle");
+			while (nb_fds--)
+				close(fds[nb_fds]);
+		}
+		fd = -1;
+		goto exit_free;
+	}
+
+	fd = fds[0];
+exit_free:
+	free(fds);
+	return fd;
+}
+
+static int map_fd_by_name(char *name, int **fds)
+{
+	unsigned int id = 0;
+	int fd, nb_fds = 0;
+	void *tmp;
+	int err;
+
+	while (true) {
+		struct bpf_map_info info = {};
+		__u32 len = sizeof(info);
+
+		err = bpf_map_get_next_id(id, &id);
+		if (err) {
+			if (errno != ENOENT) {
+				p_err("%s", strerror(errno));
+				goto err_close_fds;
+			}
+			return nb_fds;
+		}
+
+		fd = bpf_map_get_fd_by_id(id);
+		if (fd < 0) {
+			p_err("can't get map by id (%u): %s",
+			      id, strerror(errno));
+			goto err_close_fds;
+		}
+
+		err = bpf_obj_get_info_by_fd(fd, &info, &len);
+		if (err) {
+			p_err("can't get map info (%u): %s",
+			      id, strerror(errno));
+			goto err_close_fd;
+		}
+
+		if (strncmp(name, info.name, BPF_OBJ_NAME_LEN)) {
+			close(fd);
+			continue;
+		}
+
+		if (nb_fds > 0) {
+			tmp = realloc(*fds, (nb_fds + 1) * sizeof(int));
+			if (!tmp) {
+				p_err("failed to realloc");
+				goto err_close_fd;
+			}
+			*fds = tmp;
+		}
+		(*fds)[nb_fds++] = fd;
+	}
+
+err_close_fd:
+	close(fd);
+err_close_fds:
+	while (--nb_fds >= 0)
+		close((*fds)[nb_fds]);
+	return -1;
+}
+
+int map_parse_fds(int *argc, char ***argv, int **fds)
+{
+	if (is_prefix(**argv, "id")) {
+		unsigned int id;
+		char *endptr;
+
+		NEXT_ARGP();
+
+		id = strtoul(**argv, &endptr, 0);
+		if (*endptr) {
+			p_err("can't parse %s as ID", **argv);
+			return -1;
+		}
+		NEXT_ARGP();
+
+		(*fds)[0] = bpf_map_get_fd_by_id(id);
+		if ((*fds)[0] < 0) {
+			p_err("get map by id (%u): %s", id, strerror(errno));
+			return -1;
+		}
+		return 1;
+	} else if (is_prefix(**argv, "name")) {
+		char *name;
+
+		NEXT_ARGP();
+
+		name = **argv;
+		if (strlen(name) > BPF_OBJ_NAME_LEN - 1) {
+			p_err("can't parse name");
+			return -1;
+		}
+		NEXT_ARGP();
+
+		return map_fd_by_name(name, fds);
+	} else if (is_prefix(**argv, "pinned")) {
+		char *path;
+
+		NEXT_ARGP();
+
+		path = **argv;
+		NEXT_ARGP();
+
+		(*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP);
+		if ((*fds)[0] < 0)
+			return -1;
+		return 1;
+	}
+
+	p_err("expected 'id', 'name' or 'pinned', got: '%s'?", **argv);
+	return -1;
+}
+
+int map_parse_fd(int *argc, char ***argv)
+{
+	int *fds = NULL;
+	int nb_fds, fd;
+
+	fds = malloc(sizeof(int));
+	if (!fds) {
+		p_err("mem alloc failed");
+		return -1;
+	}
+	nb_fds = map_parse_fds(argc, argv, &fds);
+	if (nb_fds != 1) {
+		if (nb_fds > 1) {
+			p_err("several maps match this handle");
+			while (nb_fds--)
+				close(fds[nb_fds]);
+		}
+		fd = -1;
+		goto exit_free;
+	}
+
+	fd = fds[0];
+exit_free:
+	free(fds);
+	return fd;
+}
+
+int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
+{
+	int err;
+	int fd;
+
+	fd = map_parse_fd(argc, argv);
+	if (fd < 0)
+		return -1;
+
+	err = bpf_obj_get_info_by_fd(fd, info, info_len);
+	if (err) {
+		p_err("can't get map info: %s", strerror(errno));
+		close(fd);
+		return err;
+	}
+
+	return fd;
+}