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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-05-17

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

The main changes are:

1) Provide a new BPF helper for doing a FIB and neighbor lookup
   in the kernel tables from an XDP or tc BPF program. The helper
   provides a fast-path for forwarding packets. The API supports
   IPv4, IPv6 and MPLS protocols, but currently IPv4 and IPv6 are
   implemented in this initial work, from David (Ahern).

2) Just a tiny diff but huge feature enabled for nfp driver by
   extending the BPF offload beyond a pure host processing offload.
   Offloaded XDP programs are allowed to set the RX queue index and
   thus opening the door for defining a fully programmable RSS/n-tuple
   filter replacement. Once BPF decided on a queue already, the device
   data-path will skip the conventional RSS processing completely,
   from Jakub.

3) The original sockmap implementation was array based similar to
   devmap. However unlike devmap where an ifindex has a 1:1 mapping
   into the map there are use cases with sockets that need to be
   referenced using longer keys. Hence, sockhash map is added reusing
   as much of the sockmap code as possible, from John.

4) Introduce BTF ID. The ID is allocatd through an IDR similar as
   with BPF maps and progs. It also makes BTF accessible to user
   space via BPF_BTF_GET_FD_BY_ID and adds exposure of the BTF data
   through BPF_OBJ_GET_INFO_BY_FD, from Martin.

5) Enable BPF stackmap with build_id also in NMI context. Due to the
   up_read() of current->mm->mmap_sem build_id cannot be parsed.
   This work defers the up_read() via a per-cpu irq_work so that
   at least limited support can be enabled, from Song.

6) Various BPF JIT follow-up cleanups and fixups after the LD_ABS/LD_IND
   JIT conversion as well as implementation of an optimized 32/64 bit
   immediate load in the arm64 JIT that allows to reduce the number of
   emitted instructions; in case of tested real-world programs they
   were shrinking by three percent, from Daniel.

7) Add ifindex parameter to the libbpf loader in order to enable
   BPF offload support. Right now only iproute2 can load offloaded
   BPF and this will also enable libbpf for direct integration into
   other applications, from David (Beckett).

8) Convert the plain text documentation under Documentation/bpf/ into
   RST format since this is the appropriate standard the kernel is
   moving to for all documentation. Also add an overview README.rst,
   from Jesper.

9) Add __printf verification attribute to the bpf_verifier_vlog()
   helper. Though it uses va_list we can still allow gcc to check
   the format string, from Mathieu.

10) Fix a bash reference in the BPF selftest's Makefile. The '|& ...'
    is a bash 4.0+ feature which is not guaranteed to be available
    when calling out to shell, therefore use a more portable variant,
    from Joe.

11) Fix a 64 bit division in xdp_umem_reg() by using div_u64()
    instead of relying on the gcc built-in, from Björn.

12) Fix a sock hashmap kmalloc warning reported by syzbot when an
    overly large key size is used in hashmap then causing overflows
    in htab->elem_size. Reject bogus attr->key_size early in the
    sock_hash_alloc(), from Yonghong.

13) Ensure in BPF selftests when urandom_read is being linked that
    --build-id is always enabled so that test_stacktrace_build_id[_nmi]
    won't be failing, from Alexei.

14) Add bitsperlong.h as well as errno.h uapi headers into the tools
    header infrastructure which point to one of the arch specific
    uapi headers. This was needed in order to fix a build error on
    some systems for the BPF selftests, from Sirio.

15) Allow for short options to be used in the xdp_monitor BPF sample
    code. And also a bpf.h tools uapi header sync in order to fix a
    selftest build failure. Both from Prashant.

16) More formally clarify the meaning of ID in the direct packet access
    section of the BPF documentation, from Wang.
====================

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

1 files changed, 115 insertions, 10 deletions

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7bcdca13083a..3dbe217bf23e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -31,6 +31,7 @@
 #include <unistd.h>
 #include <fcntl.h>
 #include <errno.h>
+#include <perf-sys.h>
 #include <asm/unistd.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
@@ -177,6 +178,7 @@ struct bpf_program {
 	/* Index in elf obj file, for relocation use. */
 	int idx;
 	char *name;
+	int prog_ifindex;
 	char *section_name;
 	struct bpf_insn *insns;
 	size_t insns_cnt, main_prog_cnt;
@@ -212,6 +214,7 @@ struct bpf_map {
 	int fd;
 	char *name;
 	size_t offset;
+	int map_ifindex;
 	struct bpf_map_def def;
 	uint32_t btf_key_id;
 	uint32_t btf_value_id;
@@ -1090,6 +1093,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 		int *pfd = &map->fd;
 
 		create_attr.name = map->name;
+		create_attr.map_ifindex = map->map_ifindex;
 		create_attr.map_type = def->type;
 		create_attr.map_flags = def->map_flags;
 		create_attr.key_size = def->key_size;
@@ -1272,7 +1276,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 static int
 load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
 	     const char *name, struct bpf_insn *insns, int insns_cnt,
-	     char *license, u32 kern_version, int *pfd)
+	     char *license, u32 kern_version, int *pfd, int prog_ifindex)
 {
 	struct bpf_load_program_attr load_attr;
 	char *log_buf;
@@ -1286,6 +1290,7 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
 	load_attr.insns_cnt = insns_cnt;
 	load_attr.license = license;
 	load_attr.kern_version = kern_version;
+	load_attr.prog_ifindex = prog_ifindex;
 
 	if (!load_attr.insns || !load_attr.insns_cnt)
 		return -EINVAL;
@@ -1367,7 +1372,8 @@ bpf_program__load(struct bpf_program *prog,
 		}
 		err = load_program(prog->type, prog->expected_attach_type,
 				   prog->name, prog->insns, prog->insns_cnt,
-				   license, kern_version, &fd);
+				   license, kern_version, &fd,
+				   prog->prog_ifindex);
 		if (!err)
 			prog->instances.fds[0] = fd;
 		goto out;
@@ -1398,7 +1404,8 @@ bpf_program__load(struct bpf_program *prog,
 		err = load_program(prog->type, prog->expected_attach_type,
 				   prog->name, result.new_insn_ptr,
 				   result.new_insn_cnt,
-				   license, kern_version, &fd);
+				   license, kern_version, &fd,
+				   prog->prog_ifindex);
 
 		if (err) {
 			pr_warning("Loading the %dth instance of program '%s' failed\n",
@@ -1437,9 +1444,37 @@ bpf_object__load_progs(struct bpf_object *obj)
 	return 0;
 }
 
-static int bpf_object__validate(struct bpf_object *obj)
+static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
+{
+	switch (type) {
+	case BPF_PROG_TYPE_SOCKET_FILTER:
+	case BPF_PROG_TYPE_SCHED_CLS:
+	case BPF_PROG_TYPE_SCHED_ACT:
+	case BPF_PROG_TYPE_XDP:
+	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_CGROUP_SOCK_ADDR:
+		return false;
+	case BPF_PROG_TYPE_UNSPEC:
+	case BPF_PROG_TYPE_KPROBE:
+	case BPF_PROG_TYPE_TRACEPOINT:
+	case BPF_PROG_TYPE_PERF_EVENT:
+	case BPF_PROG_TYPE_RAW_TRACEPOINT:
+	default:
+		return true;
+	}
+}
+
+static int bpf_object__validate(struct bpf_object *obj, bool needs_kver)
 {
-	if (obj->kern_version == 0) {
+	if (needs_kver && obj->kern_version == 0) {
 		pr_warning("%s doesn't provide kernel version\n",
 			   obj->path);
 		return -LIBBPF_ERRNO__KVERSION;
@@ -1448,7 +1483,8 @@ static int bpf_object__validate(struct bpf_object *obj)
 }
 
 static struct bpf_object *
-__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz)
+__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz,
+		   bool needs_kver)
 {
 	struct bpf_object *obj;
 	int err;
@@ -1466,7 +1502,7 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz)
 	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
 	CHECK_ERR(bpf_object__elf_collect(obj), err, out);
 	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
-	CHECK_ERR(bpf_object__validate(obj), err, out);
+	CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out);
 
 	bpf_object__elf_finish(obj);
 	return obj;
@@ -1483,7 +1519,7 @@ struct bpf_object *bpf_object__open(const char *path)
 
 	pr_debug("loading %s\n", path);
 
-	return __bpf_object__open(path, NULL, 0);
+	return __bpf_object__open(path, NULL, 0, true);
 }
 
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
@@ -1506,7 +1542,7 @@ struct bpf_object *bpf_object__open_buffer(void *obj_buf,
 	pr_debug("loading object '%s' from buffer\n",
 		 name);
 
-	return __bpf_object__open(name, obj_buf, obj_buf_sz);
+	return __bpf_object__open(name, obj_buf, obj_buf_sz, true);
 }
 
 int bpf_object__unload(struct bpf_object *obj)
@@ -2158,13 +2194,17 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 	enum bpf_attach_type expected_attach_type;
 	enum bpf_prog_type prog_type;
 	struct bpf_object *obj;
+	struct bpf_map *map;
 	int section_idx;
 	int err;
 
 	if (!attr)
 		return -EINVAL;
+	if (!attr->file)
+		return -EINVAL;
 
-	obj = bpf_object__open(attr->file);
+	obj = __bpf_object__open(attr->file, NULL, 0,
+				 bpf_prog_type__needs_kver(attr->prog_type));
 	if (IS_ERR(obj))
 		return -ENOENT;
 
@@ -2174,6 +2214,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 		 * section name.
 		 */
 		prog_type = attr->prog_type;
+		prog->prog_ifindex = attr->ifindex;
 		expected_attach_type = attr->expected_attach_type;
 		if (prog_type == BPF_PROG_TYPE_UNSPEC) {
 			section_idx = bpf_program__identify_section(prog);
@@ -2194,6 +2235,10 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 			first_prog = prog;
 	}
 
+	bpf_map__for_each(map, obj) {
+		map->map_ifindex = attr->ifindex;
+	}
+
 	if (!first_prog) {
 		pr_warning("object file doesn't contain bpf program\n");
 		bpf_object__close(obj);
@@ -2210,3 +2255,63 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 	*prog_fd = bpf_program__fd(first_prog);
 	return 0;
 }
+
+enum bpf_perf_event_ret
+bpf_perf_event_read_simple(void *mem, unsigned long size,
+			   unsigned long page_size, void **buf, size_t *buf_len,
+			   bpf_perf_event_print_t fn, void *priv)
+{
+	volatile struct perf_event_mmap_page *header = mem;
+	__u64 data_tail = header->data_tail;
+	__u64 data_head = header->data_head;
+	void *base, *begin, *end;
+	int ret;
+
+	asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */
+	if (data_head == data_tail)
+		return LIBBPF_PERF_EVENT_CONT;
+
+	base = ((char *)header) + page_size;
+
+	begin = base + data_tail % size;
+	end = base + data_head % size;
+
+	while (begin != end) {
+		struct perf_event_header *ehdr;
+
+		ehdr = begin;
+		if (begin + ehdr->size > base + size) {
+			long len = base + size - begin;
+
+			if (*buf_len < ehdr->size) {
+				free(*buf);
+				*buf = malloc(ehdr->size);
+				if (!*buf) {
+					ret = LIBBPF_PERF_EVENT_ERROR;
+					break;
+				}
+				*buf_len = ehdr->size;
+			}
+
+			memcpy(*buf, begin, len);
+			memcpy(*buf + len, base, ehdr->size - len);
+			ehdr = (void *)*buf;
+			begin = base + ehdr->size - len;
+		} else if (begin + ehdr->size == base + size) {
+			begin = base;
+		} else {
+			begin += ehdr->size;
+		}
+
+		ret = fn(ehdr, priv);
+		if (ret != LIBBPF_PERF_EVENT_CONT)
+			break;
+
+		data_tail += ehdr->size;
+	}
+
+	__sync_synchronize(); /* smp_mb() */
+	header->data_tail = data_tail;
+
+	return ret;
+}