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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-06-19

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

The main changes are:

1) new SO_REUSEPORT_DETACH_BPF setsocktopt, from Martin.

2) BTF based map definition, from Andrii.

3) support bpf_map_lookup_elem for xskmap, from Jonathan.

4) bounded loops and scalar precision logic in the verifier, from Alexei.
====================

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

68 files changed, 3053 insertions, 755 deletions

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index f7261fad45c1..5215e0870bcb 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -21,6 +21,7 @@
 #include <sys/vfs.h>
 
 #include <bpf.h>
+#include <libbpf.h> /* libbpf_num_possible_cpus */
 
 #include "main.h"
 
@@ -439,57 +440,13 @@ unsigned int get_page_size(void)
 
 unsigned int get_possible_cpus(void)
 {
-	static unsigned int result;
-	char buf[128];
-	long int n;
-	char *ptr;
-	int fd;
-
-	if (result)
-		return result;
-
-	fd = open("/sys/devices/system/cpu/possible", O_RDONLY);
-	if (fd < 0) {
-		p_err("can't open sysfs possible cpus");
-		exit(-1);
-	}
-
-	n = read(fd, buf, sizeof(buf));
-	if (n < 2) {
-		p_err("can't read sysfs possible cpus");
-		exit(-1);
-	}
-	close(fd);
+	int cpus = libbpf_num_possible_cpus();
 
-	if (n == sizeof(buf)) {
-		p_err("read sysfs possible cpus overflow");
+	if (cpus < 0) {
+		p_err("Can't get # of possible cpus: %s", strerror(-cpus));
 		exit(-1);
 	}
-
-	ptr = buf;
-	n = 0;
-	while (*ptr && *ptr != '\n') {
-		unsigned int a, b;
-
-		if (sscanf(ptr, "%u-%u", &a, &b) == 2) {
-			n += b - a + 1;
-
-			ptr = strchr(ptr, '-') + 1;
-		} else if (sscanf(ptr, "%u", &a) == 1) {
-			n++;
-		} else {
-			assert(0);
-		}
-
-		while (isdigit(*ptr))
-			ptr++;
-		if (*ptr == ',')
-			ptr++;
-	}
-
-	result = n;
-
-	return result;
+	return cpus;
 }
 
 static char *
diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h
new file mode 100644
index 000000000000..77f7c1638eb1
--- /dev/null
+++ b/tools/include/uapi/asm-generic/socket.h
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_SOCKET_H
+#define __ASM_GENERIC_SOCKET_H
+
+#include <linux/posix_types.h>
+#include <asm/sockios.h>
+
+/* For setsockopt(2) */
+#define SOL_SOCKET	1
+
+#define SO_DEBUG	1
+#define SO_REUSEADDR	2
+#define SO_TYPE		3
+#define SO_ERROR	4
+#define SO_DONTROUTE	5
+#define SO_BROADCAST	6
+#define SO_SNDBUF	7
+#define SO_RCVBUF	8
+#define SO_SNDBUFFORCE	32
+#define SO_RCVBUFFORCE	33
+#define SO_KEEPALIVE	9
+#define SO_OOBINLINE	10
+#define SO_NO_CHECK	11
+#define SO_PRIORITY	12
+#define SO_LINGER	13
+#define SO_BSDCOMPAT	14
+#define SO_REUSEPORT	15
+#ifndef SO_PASSCRED /* powerpc only differs in these */
+#define SO_PASSCRED	16
+#define SO_PEERCRED	17
+#define SO_RCVLOWAT	18
+#define SO_SNDLOWAT	19
+#define SO_RCVTIMEO_OLD	20
+#define SO_SNDTIMEO_OLD	21
+#endif
+
+/* Security levels - as per NRL IPv6 - don't actually do anything */
+#define SO_SECURITY_AUTHENTICATION		22
+#define SO_SECURITY_ENCRYPTION_TRANSPORT	23
+#define SO_SECURITY_ENCRYPTION_NETWORK		24
+
+#define SO_BINDTODEVICE	25
+
+/* Socket filtering */
+#define SO_ATTACH_FILTER	26
+#define SO_DETACH_FILTER	27
+#define SO_GET_FILTER		SO_ATTACH_FILTER
+
+#define SO_PEERNAME		28
+
+#define SO_ACCEPTCONN		30
+
+#define SO_PEERSEC		31
+#define SO_PASSSEC		34
+
+#define SO_MARK			36
+
+#define SO_PROTOCOL		38
+#define SO_DOMAIN		39
+
+#define SO_RXQ_OVFL             40
+
+#define SO_WIFI_STATUS		41
+#define SCM_WIFI_STATUS	SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
+
+/* Instruct lower device to use last 4-bytes of skb data as FCS */
+#define SO_NOFCS		43
+
+#define SO_LOCK_FILTER		44
+
+#define SO_SELECT_ERR_QUEUE	45
+
+#define SO_BUSY_POLL		46
+
+#define SO_MAX_PACING_RATE	47
+
+#define SO_BPF_EXTENSIONS	48
+
+#define SO_INCOMING_CPU		49
+
+#define SO_ATTACH_BPF		50
+#define SO_DETACH_BPF		SO_DETACH_FILTER
+
+#define SO_ATTACH_REUSEPORT_CBPF	51
+#define SO_ATTACH_REUSEPORT_EBPF	52
+
+#define SO_CNX_ADVICE		53
+
+#define SCM_TIMESTAMPING_OPT_STATS	54
+
+#define SO_MEMINFO		55
+
+#define SO_INCOMING_NAPI_ID	56
+
+#define SO_COOKIE		57
+
+#define SCM_TIMESTAMPING_PKTINFO	58
+
+#define SO_PEERGROUPS		59
+
+#define SO_ZEROCOPY		60
+
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
+#define SO_BINDTOIFINDEX	62
+
+#define SO_TIMESTAMP_OLD        29
+#define SO_TIMESTAMPNS_OLD      35
+#define SO_TIMESTAMPING_OLD     37
+
+#define SO_TIMESTAMP_NEW        63
+#define SO_TIMESTAMPNS_NEW      64
+#define SO_TIMESTAMPING_NEW     65
+
+#define SO_RCVTIMEO_NEW         66
+#define SO_SNDTIMEO_NEW         67
+
+#define SO_DETACH_REUSEPORT_BPF 68
+
+#if !defined(__KERNEL__)
+
+#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
+/* on 64-bit and x32, avoid the ?: operator */
+#define SO_TIMESTAMP		SO_TIMESTAMP_OLD
+#define SO_TIMESTAMPNS		SO_TIMESTAMPNS_OLD
+#define SO_TIMESTAMPING		SO_TIMESTAMPING_OLD
+
+#define SO_RCVTIMEO		SO_RCVTIMEO_OLD
+#define SO_SNDTIMEO		SO_SNDTIMEO_OLD
+#else
+#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW)
+#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW)
+#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW)
+
+#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW)
+#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW)
+#endif
+
+#define SCM_TIMESTAMP           SO_TIMESTAMP
+#define SCM_TIMESTAMPNS         SO_TIMESTAMPNS
+#define SCM_TIMESTAMPING        SO_TIMESTAMPING
+
+#endif
+
+#endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0e879721f75a..b077507efa3f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3085,6 +3085,10 @@ struct bpf_sock_tuple {
 	};
 };
 
+struct bpf_xdp_sock {
+	__u32 queue_id;
+};
+
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
@@ -3245,6 +3249,7 @@ struct bpf_sock_addr {
 	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
 				 * Stored in network byte order.
 				 */
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 /* User bpf_sock_ops struct to access socket values and specify request ops
@@ -3296,6 +3301,7 @@ struct bpf_sock_ops {
 	__u32 sk_txhash;
 	__u64 bytes_received;
 	__u64 bytes_acked;
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 0d4b4fe10a84..c7d7993c44bb 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -26,10 +26,11 @@
 #include <memory.h>
 #include <unistd.h>
 #include <asm/unistd.h>
+#include <errno.h>
 #include <linux/bpf.h>
 #include "bpf.h"
 #include "libbpf.h"
-#include <errno.h>
+#include "libbpf_internal.h"
 
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
@@ -53,10 +54,6 @@
 # endif
 #endif
 
-#ifndef min
-#define min(x, y) ((x) < (y) ? (x) : (y))
-#endif
-
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c
index 6978314ea7f6..8c67561c93b0 100644
--- a/tools/lib/bpf/bpf_prog_linfo.c
+++ b/tools/lib/bpf/bpf_prog_linfo.c
@@ -6,10 +6,7 @@
 #include <linux/err.h>
 #include <linux/bpf.h>
 #include "libbpf.h"
-
-#ifndef min
-#define min(x, y) ((x) < (y) ? (x) : (y))
-#endif
+#include "libbpf_internal.h"
 
 struct bpf_prog_linfo {
 	void *raw_linfo;
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index b2478e98c367..467224feb43b 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -16,9 +16,6 @@
 #include "libbpf_internal.h"
 #include "hashmap.h"
 
-#define max(a, b) ((a) > (b) ? (a) : (b))
-#define min(a, b) ((a) < (b) ? (a) : (b))
-
 #define BTF_MAX_NR_TYPES 0x7fffffff
 #define BTF_MAX_STR_OFFSET 0x7fffffff
 
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index ba4ffa831aa4..88a52ae56fc6 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -17,6 +17,7 @@ extern "C" {
 
 #define BTF_ELF_SEC ".BTF"
 #define BTF_EXT_ELF_SEC ".BTF.ext"
+#define MAPS_ELF_SEC ".maps"
 
 struct btf;
 struct btf_ext;
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 4b22db77e2cc..7065bb5b2752 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -18,9 +18,6 @@
 #include "libbpf.h"
 #include "libbpf_internal.h"
 
-#define min(x, y) ((x) < (y) ? (x) : (y))
-#define max(x, y) ((x) < (y) ? (y) : (x))
-
 static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t";
 static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1;
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index c8fbc050fd78..4259c9f0cfe7 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -207,7 +207,8 @@ static const char * const libbpf_type_to_btf_name[] = {
 struct bpf_map {
 	int fd;
 	char *name;
-	size_t offset;
+	int sec_idx;
+	size_t sec_offset;
 	int map_ifindex;
 	int inner_map_fd;
 	struct bpf_map_def def;
@@ -234,6 +235,7 @@ struct bpf_object {
 	size_t nr_programs;
 	struct bpf_map *maps;
 	size_t nr_maps;
+	size_t maps_cap;
 	struct bpf_secdata sections;
 
 	bool loaded;
@@ -260,6 +262,7 @@ struct bpf_object {
 		} *reloc;
 		int nr_reloc;
 		int maps_shndx;
+		int btf_maps_shndx;
 		int text_shndx;
 		int data_shndx;
 		int rodata_shndx;
@@ -512,6 +515,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 	obj->efile.obj_buf = obj_buf;
 	obj->efile.obj_buf_sz = obj_buf_sz;
 	obj->efile.maps_shndx = -1;
+	obj->efile.btf_maps_shndx = -1;
 	obj->efile.data_shndx = -1;
 	obj->efile.rodata_shndx = -1;
 	obj->efile.bss_shndx = -1;
@@ -646,7 +650,9 @@ static int compare_bpf_map(const void *_a, const void *_b)
 	const struct bpf_map *a = _a;
 	const struct bpf_map *b = _b;
 
-	return a->offset - b->offset;
+	if (a->sec_idx != b->sec_idx)
+		return a->sec_idx - b->sec_idx;
+	return a->sec_offset - b->sec_offset;
 }
 
 static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
@@ -763,24 +769,55 @@ int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
 	return -ENOENT;
 }
 
-static bool bpf_object__has_maps(const struct bpf_object *obj)
+static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
 {
-	return obj->efile.maps_shndx >= 0 ||
-	       obj->efile.data_shndx >= 0 ||
-	       obj->efile.rodata_shndx >= 0 ||
-	       obj->efile.bss_shndx >= 0;
+	struct bpf_map *new_maps;
+	size_t new_cap;
+	int i;
+
+	if (obj->nr_maps < obj->maps_cap)
+		return &obj->maps[obj->nr_maps++];
+
+	new_cap = max(4ul, obj->maps_cap * 3 / 2);
+	new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps));
+	if (!new_maps) {
+		pr_warning("alloc maps for object failed\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	obj->maps_cap = new_cap;
+	obj->maps = new_maps;
+
+	/* zero out new maps */
+	memset(obj->maps + obj->nr_maps, 0,
+	       (obj->maps_cap - obj->nr_maps) * sizeof(*obj->maps));
+	/*
+	 * fill all fd with -1 so won't close incorrect fd (fd=0 is stdin)
+	 * when failure (zclose won't close negative fd)).
+	 */
+	for (i = obj->nr_maps; i < obj->maps_cap; i++) {
+		obj->maps[i].fd = -1;
+		obj->maps[i].inner_map_fd = -1;
+	}
+
+	return &obj->maps[obj->nr_maps++];
 }
 
 static int
-bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map,
-			      enum libbpf_map_type type, Elf_Data *data,
-			      void **data_buff)
+bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
+			      int sec_idx, Elf_Data *data, void **data_buff)
 {
-	struct bpf_map_def *def = &map->def;
 	char map_name[BPF_OBJ_NAME_LEN];
+	struct bpf_map_def *def;
+	struct bpf_map *map;
+
+	map = bpf_object__add_map(obj);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
 
 	map->libbpf_type = type;
-	map->offset = ~(typeof(map->offset))0;
+	map->sec_idx = sec_idx;
+	map->sec_offset = 0;
 	snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name,
 		 libbpf_type_to_btf_name[type]);
 	map->name = strdup(map_name);
@@ -788,7 +825,10 @@ bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map,
 		pr_warning("failed to alloc map name\n");
 		return -ENOMEM;
 	}
+	pr_debug("map '%s' (global data): at sec_idx %d, offset %zu.\n",
+		 map_name, map->sec_idx, map->sec_offset);
 
+	def = &map->def;
 	def->type = BPF_MAP_TYPE_ARRAY;
 	def->key_size = sizeof(int);
 	def->value_size = data->d_size;
@@ -808,29 +848,61 @@ bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map,
 	return 0;
 }
 
-static int bpf_object__init_maps(struct bpf_object *obj, int flags)
+static int bpf_object__init_global_data_maps(struct bpf_object *obj)
+{
+	int err;
+
+	if (!obj->caps.global_data)
+		return 0;
+	/*
+	 * Populate obj->maps with libbpf internal maps.
+	 */
+	if (obj->efile.data_shndx >= 0) {
+		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA,
+						    obj->efile.data_shndx,
+						    obj->efile.data,
+						    &obj->sections.data);
+		if (err)
+			return err;
+	}
+	if (obj->efile.rodata_shndx >= 0) {
+		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA,
+						    obj->efile.rodata_shndx,
+						    obj->efile.rodata,
+						    &obj->sections.rodata);
+		if (err)
+			return err;
+	}
+	if (obj->efile.bss_shndx >= 0) {
+		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS,
+						    obj->efile.bss_shndx,
+						    obj->efile.bss, NULL);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 {
-	int i, map_idx, map_def_sz = 0, nr_syms, nr_maps = 0, nr_maps_glob = 0;
-	bool strict = !(flags & MAPS_RELAX_COMPAT);
 	Elf_Data *symbols = o