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

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-01-29

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

The main changes are:

1) Teach verifier dead code removal, this also allows for optimizing /
   removing conditional branches around dead code and to shrink the
   resulting image. Code store constrained architectures like nfp would
   have hard time doing this at JIT level, from Jakub.

2) Add JMP32 instructions to BPF ISA in order to allow for optimizing
   code generation for 32-bit sub-registers. Evaluation shows that this
   can result in code reduction of ~5-20% compared to 64 bit-only code
   generation. Also add implementation for most JITs, from Jiong.

3) Add support for __int128 types in BTF which is also needed for
   vmlinux's BTF conversion to work, from Yonghong.

4) Add a new command to bpftool in order to dump a list of BPF-related
   parameters from the system or for a specific network device e.g. in
   terms of available prog/map types or helper functions, from Quentin.

5) Add AF_XDP sock_diag interface for querying sockets from user
   space which provides information about the RX/TX/fill/completion
   rings, umem, memory usage etc, from Björn.

6) Add skb context access for skb_shared_info->gso_segs field, from Eric.

7) Add support for testing flow dissector BPF programs by extending
   existing BPF_PROG_TEST_RUN infrastructure, from Stanislav.

8) Split BPF kselftest's test_verifier into various subgroups of tests
   in order better deal with merge conflicts in this area, from Jakub.

9) Add support for queue/stack manipulations in bpftool, from Stanislav.

10) Document BTF, from Yonghong.

11) Dump supported ELF section names in libbpf on program load
    failure, from Taeung.

12) Silence a false positive compiler warning in verifier's BTF
    handling, from Peter.

13) Fix help string in bpftool's feature probing, from Prashant.

14) Remove duplicate includes in BPF kselftests, from Yue.
====================

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

6 files changed, 309 insertions, 19 deletions

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 197b40f5b5c6..bfd9bfc82c3b 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o bpf_prog_linfo.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o bpf_prog_linfo.o libbpf_probes.o
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 34d9c3619c96..847916273696 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -14,21 +14,6 @@ srctree := $(patsubst %/,%,$(dir $(srctree)))
 #$(info Determined 'srctree' to be $(srctree))
 endif
 
-# Makefiles suck: This macro sets a default value of $(2) for the
-# variable named by $(1), unless the variable has been set by
-# environment or command line. This is necessary for CC and AR
-# because make sets default values, so the simpler ?= approach
-# won't work as expected.
-define allow-override
-  $(if $(or $(findstring environment,$(origin $(1))),\
-            $(findstring command line,$(origin $(1)))),,\
-    $(eval $(1) = $(2)))
-endef
-
-# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
-$(call allow-override,CC,$(CROSS_COMPILE)gcc)
-$(call allow-override,AR,$(CROSS_COMPILE)ar)
-
 INSTALL = install
 
 # Use DESTDIR for installing into a different root directory.
@@ -54,7 +39,7 @@ man_dir_SQ = '$(subst ','\'',$(man_dir))'
 export man_dir man_dir_SQ INSTALL
 export DESTDIR DESTDIR_SQ
 
-include ../../scripts/Makefile.include
+include $(srctree)/tools/scripts/Makefile.include
 
 # copy a bit from Linux kbuild
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 169e347c76f6..2ccde17957e6 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2667,9 +2667,38 @@ static const struct {
 #undef BPF_EAPROG_SEC
 #undef BPF_APROG_COMPAT
 
+#define MAX_TYPE_NAME_SIZE 32
+
+static char *libbpf_get_type_names(bool attach_type)
+{
+	int i, len = ARRAY_SIZE(section_names) * MAX_TYPE_NAME_SIZE;
+	char *buf;
+
+	buf = malloc(len);
+	if (!buf)
+		return NULL;
+
+	buf[0] = '\0';
+	/* Forge string buf with all available names */
+	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
+		if (attach_type && !section_names[i].is_attachable)
+			continue;
+
+		if (strlen(buf) + strlen(section_names[i].sec) + 2 > len) {
+			free(buf);
+			return NULL;
+		}
+		strcat(buf, " ");
+		strcat(buf, section_names[i].sec);
+	}
+
+	return buf;
+}
+
 int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 			     enum bpf_attach_type *expected_attach_type)
 {
+	char *type_names;
 	int i;
 
 	if (!name)
@@ -2682,12 +2711,20 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
 		*expected_attach_type = section_names[i].expected_attach_type;
 		return 0;
 	}
+	pr_warning("failed to guess program type based on ELF section name '%s'\n", name);
+	type_names = libbpf_get_type_names(false);
+	if (type_names != NULL) {
+		pr_info("supported section(type) names are:%s\n", type_names);
+		free(type_names);
+	}
+
 	return -EINVAL;
 }
 
 int libbpf_attach_type_by_name(const char *name,
 			       enum bpf_attach_type *attach_type)
 {
+	char *type_names;
 	int i;
 
 	if (!name)
@@ -2701,6 +2738,13 @@ int libbpf_attach_type_by_name(const char *name,
 		*attach_type = section_names[i].attach_type;
 		return 0;
 	}
+	pr_warning("failed to guess attach type based on ELF section name '%s'\n", name);
+	type_names = libbpf_get_type_names(true);
+	if (type_names != NULL) {
+		pr_info("attachable section(type) names are:%s\n", type_names);
+		free(type_names);
+	}
+
 	return -EINVAL;
 }
 
@@ -2907,8 +2951,6 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 			err = bpf_program__identify_section(prog, &prog_type,
 							    &expected_attach_type);
 			if (err < 0) {
-				pr_warning("failed to guess program type based on section name %s\n",
-					   prog->section_name);
 				bpf_object__close(obj);
 				return -EINVAL;
 			}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 5f68d7b75215..62ae6cb93da1 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -355,6 +355,20 @@ LIBBPF_API const struct bpf_line_info *
 bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo,
 		      __u32 insn_off, __u32 nr_skip);
 
+/*
+ * Probe for supported system features
+ *
+ * Note that running many of these probes in a short amount of time can cause
+ * the kernel to reach the maximal size of lockable memory allowed for the
+ * user, causing subsequent probes to fail. In this case, the caller may want
+ * to adjust that limit with setrlimit().
+ */
+LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type,
+				    __u32 ifindex);
+LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex);
+LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id,
+				 enum bpf_prog_type prog_type, __u32 ifindex);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index cd02cd4e2cc3..266bc95d0142 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -124,3 +124,10 @@ LIBBPF_0.0.1 {
 	local:
 		*;
 };
+
+LIBBPF_0.0.2 {
+	global:
+		bpf_probe_helper;
+		bpf_probe_map_type;
+		bpf_probe_prog_type;
+} LIBBPF_0.0.1;
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
new file mode 100644
index 000000000000..8c3a1c04dcb2
--- /dev/null
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/* Copyright (c) 2019 Netronome Systems, Inc. */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <net/if.h>
+#include <sys/utsname.h>
+
+#include <linux/filter.h>
+#include <linux/kernel.h>
+
+#include "bpf.h"
+#include "libbpf.h"
+
+static bool grep(const char *buffer, const char *pattern)
+{
+	return !!strstr(buffer, pattern);
+}
+
+static int get_vendor_id(int ifindex)
+{
+	char ifname[IF_NAMESIZE], path[64], buf[8];
+	ssize_t len;
+	int fd;
+
+	if (!if_indextoname(ifindex, ifname))
+		return -1;
+
+	snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname);
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return -1;
+
+	len = read(fd, buf, sizeof(buf));
+	close(fd);
+	if (len < 0)
+		return -1;
+	if (len >= (ssize_t)sizeof(buf))
+		return -1;
+	buf[len] = '\0';
+
+	return strtol(buf, NULL, 0);
+}
+
+static int get_kernel_version(void)
+{
+	int version, subversion, patchlevel;
+	struct utsname utsn;
+
+	/* Return 0 on failure, and attempt to probe with empty kversion */
+	if (uname(&utsn))
+		return 0;
+
+	if (sscanf(utsn.release, "%d.%d.%d",
+		   &version, &subversion, &patchlevel) != 3)
+		return 0;
+
+	return (version << 16) + (subversion << 8) + patchlevel;
+}
+
+static void
+probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
+	   size_t insns_cnt, char *buf, size_t buf_len, __u32 ifindex)
+{
+	struct bpf_load_program_attr xattr = {};
+	int fd;
+
+	switch (prog_type) {
+	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+		xattr.expected_attach_type = BPF_CGROUP_INET4_CONNECT;
+		break;
+	case BPF_PROG_TYPE_KPROBE:
+		xattr.kern_version = get_kernel_version();
+		break;
+	case BPF_PROG_TYPE_UNSPEC:
+	case BPF_PROG_TYPE_SOCKET_FILTER:
+	case BPF_PROG_TYPE_SCHED_CLS:
+	case BPF_PROG_TYPE_SCHED_ACT:
+	case BPF_PROG_TYPE_TRACEPOINT:
+	case BPF_PROG_TYPE_XDP:
+	case BPF_PROG_TYPE_PERF_EVENT:
+	case BPF_PROG_TYPE_CGROUP_SKB:
+	case BPF_PROG_TYPE_CGROUP_SOCK:
+	case BPF_PROG_TYPE_LWT_IN:
+	case BPF_PROG_TYPE_LWT_OUT:
+	case BPF_PROG_TYPE_LWT_XMIT:
+	case BPF_PROG_TYPE_SOCK_OPS:
+	case BPF_PROG_TYPE_SK_SKB:
+	case BPF_PROG_TYPE_CGROUP_DEVICE:
+	case BPF_PROG_TYPE_SK_MSG:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
+	case BPF_PROG_TYPE_LIRC_MODE2:
+	case BPF_PROG_TYPE_SK_REUSEPORT:
+	case BPF_PROG_TYPE_FLOW_DISSECTOR:
+	default:
+		break;
+	}
+
+	xattr.prog_type = prog_type;
+	xattr.insns = insns;
+	xattr.insns_cnt = insns_cnt;
+	xattr.license = "GPL";
+	xattr.prog_ifindex = ifindex;
+
+	fd = bpf_load_program_xattr(&xattr, buf, buf_len);
+	if (fd >= 0)
+		close(fd);
+}
+
+bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
+{
+	struct bpf_insn insns[2] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN()
+	};
+
+	if (ifindex && prog_type == BPF_PROG_TYPE_SCHED_CLS)
+		/* nfp returns -EINVAL on exit(0) with TC offload */
+		insns[0].imm = 2;
+
+	errno = 0;
+	probe_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex);
+
+	return errno != EINVAL && errno != EOPNOTSUPP;
+}
+
+bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
+{
+	int key_size, value_size, max_entries, map_flags;
+	struct bpf_create_map_attr attr = {};
+	int fd = -1, fd_inner;
+
+	key_size	= sizeof(__u32);
+	value_size	= sizeof(__u32);
+	max_entries	= 1;
+	map_flags	= 0;
+
+	switch (map_type) {
+	case BPF_MAP_TYPE_STACK_TRACE:
+		value_size	= sizeof(__u64);
+		break;
+	case BPF_MAP_TYPE_LPM_TRIE:
+		key_size	= sizeof(__u64);
+		value_size	= sizeof(__u64);
+		map_flags	= BPF_F_NO_PREALLOC;
+		break;
+	case BPF_MAP_TYPE_CGROUP_STORAGE:
+	case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
+		key_size	= sizeof(struct bpf_cgroup_storage_key);
+		value_size	= sizeof(__u64);
+		max_entries	= 0;
+		break;
+	case BPF_MAP_TYPE_QUEUE:
+	case BPF_MAP_TYPE_STACK:
+		key_size	= 0;
+		break;
+	case BPF_MAP_TYPE_UNSPEC:
+	case BPF_MAP_TYPE_HASH:
+	case BPF_MAP_TYPE_ARRAY:
+	case BPF_MAP_TYPE_PROG_ARRAY:
+	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+	case BPF_MAP_TYPE_PERCPU_HASH:
+	case BPF_MAP_TYPE_PERCPU_ARRAY:
+	case BPF_MAP_TYPE_CGROUP_ARRAY:
+	case BPF_MAP_TYPE_LRU_HASH:
+	case BPF_MAP_TYPE_LRU_PERCPU_HASH:
+	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
+	case BPF_MAP_TYPE_HASH_OF_MAPS:
+	case BPF_MAP_TYPE_DEVMAP:
+	case BPF_MAP_TYPE_SOCKMAP:
+	case BPF_MAP_TYPE_CPUMAP:
+	case BPF_MAP_TYPE_XSKMAP:
+	case BPF_MAP_TYPE_SOCKHASH:
+	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
+	default:
+		break;
+	}
+
+	if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS ||
+	    map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+		/* TODO: probe for device, once libbpf has a function to create
+		 * map-in-map for offload
+		 */
+		if (ifindex)
+			return false;
+
+		fd_inner = bpf_create_map(BPF_MAP_TYPE_HASH,
+					  sizeof(__u32), sizeof(__u32), 1, 0);
+		if (fd_inner < 0)
+			return false;
+		fd = bpf_create_map_in_map(map_type, NULL, sizeof(__u32),
+					   fd_inner, 1, 0);
+		close(fd_inner);
+	} else {
+		/* Note: No other restriction on map type probes for offload */
+		attr.map_type = map_type;
+		attr.key_size = key_size;
+		attr.value_size = value_size;
+		attr.max_entries = max_entries;
+		attr.map_flags = map_flags;
+		attr.map_ifindex = ifindex;
+
+		fd = bpf_create_map_xattr(&attr);
+	}
+	if (fd >= 0)
+		close(fd);
+
+	return fd >= 0;
+}
+
+bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type,
+		      __u32 ifindex)
+{
+	struct bpf_insn insns[2] = {
+		BPF_EMIT_CALL(id),
+		BPF_EXIT_INSN()
+	};
+	char buf[4096] = {};
+	bool res;
+
+	probe_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf),
+		   ifindex);
+	res = !grep(buf, "invalid func ") && !grep(buf, "unknown func ");
+
+	if (ifindex) {
+		switch (get_vendor_id(ifindex)) {
+		case 0x19ee: /* Netronome specific */
+			res = res && !grep(buf, "not supported by FW") &&
+				!grep(buf, "unsupported function id");
+			break;
+		default:
+			break;
+		}
+	}
+
+	return res;
+}