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

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-04-28

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

The main changes are:

1) Introduce BPF socket local storage map so that BPF programs can store
   private data they associate with a socket (instead of e.g. separate hash
   table), from Martin.

2) Add support for bpftool to dump BTF types. This is done through a new
   `bpftool btf dump` sub-command, from Andrii.

3) Enable BPF-based flow dissector for skb-less eth_get_headlen() calls which
   was currently not supported since skb was used to lookup netns, from Stanislav.

4) Add an opt-in interface for tracepoints to expose a writable context
   for attached BPF programs, used here for NBD sockets, from Matt.

5) BPF xadd related arm64 JIT fixes and scalability improvements, from Daniel.

6) Change the skb->protocol for bpf_skb_adjust_room() helper in order to
   support tunnels such as sit. Add selftests as well, from Willem.

7) Various smaller misc fixes.
====================

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

3 files changed, 165 insertions, 17 deletions

diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index ff2506fe6bd2..9593fec75652 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -26,6 +26,7 @@
 #include <linux/bpf.h>
 #include <stdbool.h>
 #include <stddef.h>
+#include <stdint.h>
 
 #ifdef __cplusplus
 extern "C" {
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d817bf20f3d6..11a65db4b93f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -126,6 +126,8 @@ static inline __u64 ptr_to_u64(const void *ptr)
 struct bpf_capabilities {
 	/* v4.14: kernel support for program & map names. */
 	__u32 name:1;
+	/* v5.2: kernel support for global data sections. */
+	__u32 global_data:1;
 };
 
 /*
@@ -854,12 +856,15 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
 	 *
 	 * TODO: Detect array of map and report error.
 	 */
-	if (obj->efile.data_shndx >= 0)
-		nr_maps_glob++;
-	if (obj->efile.rodata_shndx >= 0)
-		nr_maps_glob++;
-	if (obj->efile.bss_shndx >= 0)
-		nr_maps_glob++;
+	if (obj->caps.global_data) {
+		if (obj->efile.data_shndx >= 0)
+			nr_maps_glob++;
+		if (obj->efile.rodata_shndx >= 0)
+			nr_maps_glob++;
+		if (obj->efile.bss_shndx >= 0)
+			nr_maps_glob++;
+	}
+
 	for (i = 0; data && i < nr_syms; i++) {
 		GElf_Sym sym;
 
@@ -870,14 +875,14 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
 		nr_maps++;
 	}
 
-	/* Alloc obj->maps and fill nr_maps. */
-	pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path,
-		 nr_maps, data->d_size);
 	if (!nr_maps && !nr_maps_glob)
 		return 0;
 
 	/* Assume equally sized map definitions */
 	if (data) {
+		pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path,
+			 nr_maps, data->d_size);
+
 		map_def_sz = data->d_size / nr_maps;
 		if (!data->d_size || (data->d_size % nr_maps) != 0) {
 			pr_warning("unable to determine map definition size "
@@ -971,6 +976,9 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
 		map_idx++;
 	}
 
+	if (!obj->caps.global_data)
+		goto finalize;
+
 	/*
 	 * Populate rest of obj->maps with libbpf internal maps.
 	 */
@@ -988,6 +996,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
 		ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
 						    LIBBPF_MAP_BSS,
 						    obj->efile.bss, NULL);
+finalize:
 	if (!ret)
 		qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
 		      compare_bpf_map);
@@ -1333,11 +1342,17 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 		if (bpf_object__shndx_is_maps(obj, shdr_idx) ||
 		    bpf_object__shndx_is_data(obj, shdr_idx)) {
 			type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx);
-			if (type != LIBBPF_MAP_UNSPEC &&
-			    GELF_ST_BIND(sym.st_info) == STB_GLOBAL) {
-				pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n",
-					   name, insn_idx, insns[insn_idx].code);
-				return -LIBBPF_ERRNO__RELOC;
+			if (type != LIBBPF_MAP_UNSPEC) {
+				if (GELF_ST_BIND(sym.st_info) == STB_GLOBAL) {
+					pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n",
+						   name, insn_idx, insns[insn_idx].code);
+					return -LIBBPF_ERRNO__RELOC;
+				}
+				if (!obj->caps.global_data) {
+					pr_warning("bpf: relocation: kernel does not support global \'%s\' variable access in insns[%d]\n",
+						   name, insn_idx);
+					return -LIBBPF_ERRNO__RELOC;
+				}
 			}
 
 			for (map_idx = 0; map_idx < nr_maps; map_idx++) {
@@ -1496,9 +1511,67 @@ bpf_object__probe_name(struct bpf_object *obj)
 }
 
 static int
+bpf_object__probe_global_data(struct bpf_object *obj)
+{
+	struct bpf_load_program_attr prg_attr;
+	struct bpf_create_map_attr map_attr;
+	char *cp, errmsg[STRERR_BUFSIZE];
+	struct bpf_insn insns[] = {
+		BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16),
+		BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int ret, map;
+
+	memset(&map_attr, 0, sizeof(map_attr));
+	map_attr.map_type = BPF_MAP_TYPE_ARRAY;
+	map_attr.key_size = sizeof(int);
+	map_attr.value_size = 32;
+	map_attr.max_entries = 1;
+
+	map = bpf_create_map_xattr(&map_attr);
+	if (map < 0) {
+		cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+		pr_warning("Error in %s():%s(%d). Couldn't create simple array map.\n",
+			   __func__, cp, errno);
+		return -errno;
+	}
+
+	insns[0].imm = map;
+
+	memset(&prg_attr, 0, sizeof(prg_attr));
+	prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+	prg_attr.insns = insns;
+	prg_attr.insns_cnt = ARRAY_SIZE(insns);
+	prg_attr.license = "GPL";
+
+	ret = bpf_load_program_xattr(&prg_attr, NULL, 0);
+	if (ret >= 0) {
+		obj->caps.global_data = 1;
+		close(ret);
+	}
+
+	close(map);
+	return 0;
+}
+
+static int
 bpf_object__probe_caps(struct bpf_object *obj)
 {
-	return bpf_object__probe_name(obj);
+	int (*probe_fn[])(struct bpf_object *obj) = {
+		bpf_object__probe_name,
+		bpf_object__probe_global_data,
+	};
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(probe_fn); i++) {
+		ret = probe_fn[i](obj);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
 }
 
 static int
@@ -2063,6 +2136,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
 	case BPF_PROG_TYPE_UNSPEC:
 	case BPF_PROG_TYPE_TRACEPOINT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 	case BPF_PROG_TYPE_PERF_EVENT:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
 		return false;
@@ -2100,6 +2174,7 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
 
 	CHECK_ERR(bpf_object__elf_init(obj), err, out);
 	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
+	CHECK_ERR(bpf_object__probe_caps(obj), err, out);
 	CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out);
 	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
 	CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
@@ -2193,7 +2268,6 @@ int bpf_object__load(struct bpf_object *obj)
 
 	obj->loaded = true;
 
-	CHECK_ERR(bpf_object__probe_caps(obj), err, out);
 	CHECK_ERR(bpf_object__create_maps(obj), err, out);
 	CHECK_ERR(bpf_object__relocate(obj), err, out);
 	CHECK_ERR(bpf_object__load_progs(obj), err, out);
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index 0f25541632e3..a2c64a9ce1a6 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -9,6 +9,7 @@
 #include <net/if.h>
 #include <sys/utsname.h>
 
+#include <linux/btf.h>
 #include <linux/filter.h>
 #include <linux/kernel.h>
 
@@ -93,6 +94,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns,
 	case BPF_PROG_TYPE_CGROUP_DEVICE:
 	case BPF_PROG_TYPE_SK_MSG:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
 	case BPF_PROG_TYPE_LIRC_MODE2:
 	case BPF_PROG_TYPE_SK_REUSEPORT:
@@ -130,11 +132,65 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex)
 	return errno != EINVAL && errno != EOPNOTSUPP;
 }
 
+static int load_btf(void)
+{
+#define BTF_INFO_ENC(kind, kind_flag, vlen) \
+	((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
+#define BTF_TYPE_ENC(name, info, size_or_type) \
+	(name), (info), (size_or_type)
+#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \
+	((encoding) << 24 | (bits_offset) << 16 | (nr_bits))
+#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \
+	BTF_INT_ENC(encoding, bits_offset, bits)
+#define BTF_MEMBER_ENC(name, type, bits_offset) \
+	(name), (type), (bits_offset)
+
+	const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l";
+	/* struct bpf_spin_lock {
+	 *   int val;
+	 * };
+	 * struct val {
+	 *   int cnt;
+	 *   struct bpf_spin_lock l;
+	 * };
+	 */
+	__u32 btf_raw_types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* struct bpf_spin_lock */                      /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4),
+		BTF_MEMBER_ENC(15, 1, 0), /* int val; */
+		/* struct val */                                /* [3] */
+		BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
+		BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */
+		BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */
+	};
+	struct btf_header btf_hdr = {
+		.magic = BTF_MAGIC,
+		.version = BTF_VERSION,
+		.hdr_len = sizeof(struct btf_header),
+		.type_len = sizeof(btf_raw_types),
+		.str_off = sizeof(btf_raw_types),
+		.str_len = sizeof(btf_str_sec),
+	};
+	__u8 raw_btf[sizeof(struct btf_header) + sizeof(btf_raw_types) +
+		     sizeof(btf_str_sec)];
+
+	memcpy(raw_btf, &btf_hdr, sizeof(btf_hdr));
+	memcpy(raw_btf + sizeof(btf_hdr), btf_raw_types, sizeof(btf_raw_types));
+	memcpy(raw_btf + sizeof(btf_hdr) + sizeof(btf_raw_types),
+	       btf_str_sec, sizeof(btf_str_sec));
+
+	return bpf_load_btf(raw_btf, sizeof(raw_btf), 0, 0, 0);
+}
+
 bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 {
 	int key_size, value_size, max_entries, map_flags;
+	__u32 btf_key_type_id = 0, btf_value_type_id = 0;
 	struct bpf_create_map_attr attr = {};
-	int fd = -1, fd_inner;
+	int fd = -1, btf_fd = -1, fd_inner;
 
 	key_size	= sizeof(__u32);
 	value_size	= sizeof(__u32);
@@ -160,6 +216,16 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 	case BPF_MAP_TYPE_STACK:
 		key_size	= 0;
 		break;
+	case BPF_MAP_TYPE_SK_STORAGE:
+		btf_key_type_id = 1;
+		btf_value_type_id = 3;
+		value_size = 8;
+		max_entries = 0;
+		map_flags = BPF_F_NO_PREALLOC;
+		btf_fd = load_btf();
+		if (btf_fd < 0)
+			return false;
+		break;
 	case BPF_MAP_TYPE_UNSPEC:
 	case BPF_MAP_TYPE_HASH:
 	case BPF_MAP_TYPE_ARRAY:
@@ -205,11 +271,18 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex)
 		attr.max_entries = max_entries;
 		attr.map_flags = map_flags;
 		attr.map_ifindex = ifindex;
+		if (btf_fd >= 0) {
+			attr.btf_fd = btf_fd;
+			attr.btf_key_type_id = btf_key_type_id;
+			attr.btf_value_type_id = btf_value_type_id;
+		}
 
 		fd = bpf_create_map_xattr(&attr);
 	}
 	if (fd >= 0)
 		close(fd);
+	if (btf_fd >= 0)
+		close(btf_fd);
 
 	return fd >= 0;
 }