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

Daniel Borkmann says:

====================
pull-request: bpf-next 2021-02-16

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

There's a small merge conflict between 7eeba1706eba ("tcp: Add receive timestamp
support for receive zerocopy.") from net-next tree and 9cacf81f8161 ("bpf: Remove
extra lock_sock for TCP_ZEROCOPY_RECEIVE") from bpf-next tree. Resolve as follows:

  [...]
                lock_sock(sk);
                err = tcp_zerocopy_receive(sk, &zc, &tss);
                err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname,
                                                          &zc, &len, err);
                release_sock(sk);
  [...]

We've added 116 non-merge commits during the last 27 day(s) which contain
a total of 156 files changed, 5662 insertions(+), 1489 deletions(-).

The main changes are:

1) Adds support of pointers to types with known size among global function
   args to overcome the limit on max # of allowed args, from Dmitrii Banshchikov.

2) Add bpf_iter for task_vma which can be used to generate information similar
   to /proc/pid/maps, from Song Liu.

3) Enable bpf_{g,s}etsockopt() from all sock_addr related program hooks. Allow
   rewriting bind user ports from BPF side below the ip_unprivileged_port_start
   range, both from Stanislav Fomichev.

4) Prevent recursion on fentry/fexit & sleepable programs and allow map-in-map
   as well as per-cpu maps for the latter, from Alexei Starovoitov.

5) Add selftest script to run BPF CI locally. Also enable BPF ringbuffer
   for sleepable programs, both from KP Singh.

6) Extend verifier to enable variable offset read/write access to the BPF
   program stack, from Andrei Matei.

7) Improve tc & XDP MTU handling and add a new bpf_check_mtu() helper to
   query device MTU from programs, from Jesper Dangaard Brouer.

8) Allow bpf_get_socket_cookie() helper also be called from [sleepable] BPF
   tracing programs, from Florent Revest.

9) Extend x86 JIT to pad JMPs with NOPs for helping image to converge when
   otherwise too many passes are required, from Gary Lin.

10) Verifier fixes on atomics with BPF_FETCH as well as function-by-function
    verification both related to zero-extension handling, from Ilya Leoshkevich.

11) Better kernel build integration of resolve_btfids tool, from Jiri Olsa.

12) Batch of AF_XDP selftest cleanups and small performance improvement
    for libbpf's xsk map redirect for newer kernels, from Björn Töpel.

13) Follow-up BPF doc and verifier improvements around atomics with
    BPF_FETCH, from Brendan Jackman.

14) Permit zero-sized data sections e.g. if ELF .rodata section contains
    read-only data from local variables, from Yonghong Song.

15) veth driver skb bulk-allocation for ndo_xdp_xmit, from Lorenzo Bianconi.
====================

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

5 files changed, 104 insertions, 61 deletions

diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index 8a81b3679d2b..5d4cfac671d5 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 libbpf_version.h
 libbpf.pc
-FEATURE-DUMP.libbpf
 libbpf.so.*
 TAGS
 tags
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 55bd78b3496f..887a494ad5fc 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -58,28 +58,7 @@ ifndef VERBOSE
   VERBOSE = 0
 endif
 
-FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf zlib bpf
-FEATURE_DISPLAY = libelf zlib bpf
-
 INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi
-FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES)
-
-check_feat := 1
-NON_CHECK_FEAT_TARGETS := clean TAGS tags cscope help
-ifdef MAKECMDGOALS
-ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),)
-  check_feat := 0
-endif
-endif
-
-ifeq ($(check_feat),1)
-ifeq ($(FEATURES_DUMP),)
-include $(srctree)/tools/build/Makefile.feature
-else
-include $(FEATURES_DUMP)
-endif
-endif
 
 export prefix libdir src obj
 
@@ -157,7 +136,7 @@ all: fixdep
 
 all_cmd: $(CMD_TARGETS) check
 
-$(BPF_IN_SHARED): force elfdep zdep bpfdep $(BPF_HELPER_DEFS)
+$(BPF_IN_SHARED): force $(BPF_HELPER_DEFS)
 	@(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
 	(diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true
@@ -175,7 +154,7 @@ $(BPF_IN_SHARED): force elfdep zdep bpfdep $(BPF_HELPER_DEFS)
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)"
 
-$(BPF_IN_STATIC): force elfdep zdep bpfdep $(BPF_HELPER_DEFS)
+$(BPF_IN_STATIC): force $(BPF_HELPER_DEFS)
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
 
 $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
@@ -264,34 +243,16 @@ install_pkgconfig: $(PC_FILE)
 
 install: install_lib install_pkgconfig install_headers
 
-### Cleaning rules
-
-config-clean:
-	$(call QUIET_CLEAN, feature-detect)
-	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
-
-clean: config-clean
+clean:
 	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS)		     \
 		*~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS)		     \
 		$(SHARED_OBJDIR) $(STATIC_OBJDIR)			     \
 		$(addprefix $(OUTPUT),					     \
 			    *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc)
-	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
-
-
 
-PHONY += force elfdep zdep bpfdep cscope tags
+PHONY += force cscope tags
 force:
 
-elfdep:
-	@if [ "$(feature-libelf)" != "1" ]; then echo "No libelf found"; exit 1 ; fi
-
-zdep:
-	@if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi
-
-bpfdep:
-	@if [ "$(feature-bpf)" != "1" ]; then echo "BPF API too old"; exit 1 ; fi
-
 cscope:
 	ls *.c *.h > cscope.files
 	cscope -b -q -I $(srctree)/include -f cscope.out
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 9970a288dda5..d9c10830d749 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -858,6 +858,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 	Elf_Scn *scn = NULL;
 	Elf *elf = NULL;
 	GElf_Ehdr ehdr;
+	size_t shstrndx;
 
 	if (elf_version(EV_CURRENT) == EV_NONE) {
 		pr_warn("failed to init libelf for %s\n", path);
@@ -882,7 +883,14 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 		pr_warn("failed to get EHDR from %s\n", path);
 		goto done;
 	}
-	if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) {
+
+	if (elf_getshdrstrndx(elf, &shstrndx)) {
+		pr_warn("failed to get section names section index for %s\n",
+			path);
+		goto done;
+	}
+
+	if (!elf_rawdata(elf_getscn(elf, shstrndx), NULL)) {
 		pr_warn("failed to get e_shstrndx from %s\n", path);
 		goto done;
 	}
@@ -897,7 +905,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 				idx, path);
 			goto done;
 		}
-		name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
+		name = elf_strptr(elf, shstrndx, sh.sh_name);
 		if (!name) {
 			pr_warn("failed to get section(%d) name from %s\n",
 				idx, path);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2abbc3800568..d43cc3f29dae 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -884,24 +884,24 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map,
 		if (btf_is_ptr(mtype)) {
 			struct bpf_program *prog;
 
-			mtype = skip_mods_and_typedefs(btf, mtype->type, &mtype_id);
+			prog = st_ops->progs[i];
+			if (!prog)
+				continue;
+
 			kern_mtype = skip_mods_and_typedefs(kern_btf,
 							    kern_mtype->type,
 							    &kern_mtype_id);
-			if (!btf_is_func_proto(mtype) ||
-			    !btf_is_func_proto(kern_mtype)) {
-				pr_warn("struct_ops init_kern %s: non func ptr %s is not supported\n",
+
+			/* mtype->type must be a func_proto which was
+			 * guaranteed in bpf_object__collect_st_ops_relos(),
+			 * so only check kern_mtype for func_proto here.
+			 */
+			if (!btf_is_func_proto(kern_mtype)) {
+				pr_warn("struct_ops init_kern %s: kernel member %s is not a func ptr\n",
 					map->name, mname);
 				return -ENOTSUP;
 			}
 
-			prog = st_ops->progs[i];
-			if (!prog) {
-				pr_debug("struct_ops init_kern %s: func ptr %s is not set\n",
-					 map->name, mname);
-				continue;
-			}
-
 			prog->attach_btf_id = kern_type_id;
 			prog->expected_attach_type = kern_member_idx;
 
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index e3e41ceeb1bc..ffbb588724d8 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -46,6 +46,11 @@
  #define PF_XDP AF_XDP
 #endif
 
+enum xsk_prog {
+	XSK_PROG_FALLBACK,
+	XSK_PROG_REDIRECT_FLAGS,
+};
+
 struct xsk_umem {
 	struct xsk_ring_prod *fill_save;
 	struct xsk_ring_cons *comp_save;
@@ -351,6 +356,54 @@ int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area,
 COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2)
 DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4)
 
+static enum xsk_prog get_xsk_prog(void)
+{
+	enum xsk_prog detected = XSK_PROG_FALLBACK;
+	struct bpf_load_program_attr prog_attr;
+	struct bpf_create_map_attr map_attr;
+	__u32 size_out, retval, duration;
+	char data_in = 0, data_out;
+	struct bpf_insn insns[] = {
+		BPF_LD_MAP_FD(BPF_REG_1, 0),
+		BPF_MOV64_IMM(BPF_REG_2, 0),
+		BPF_MOV64_IMM(BPF_REG_3, XDP_PASS),
+		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd, map_fd, ret;
+
+	memset(&map_attr, 0, sizeof(map_attr));
+	map_attr.map_type = BPF_MAP_TYPE_XSKMAP;
+	map_attr.key_size = sizeof(int);
+	map_attr.value_size = sizeof(int);
+	map_attr.max_entries = 1;
+
+	map_fd = bpf_create_map_xattr(&map_attr);
+	if (map_fd < 0)
+		return detected;
+
+	insns[0].imm = map_fd;
+
+	memset(&prog_attr, 0, sizeof(prog_attr));
+	prog_attr.prog_type = BPF_PROG_TYPE_XDP;
+	prog_attr.insns = insns;
+	prog_attr.insns_cnt = ARRAY_SIZE(insns);
+	prog_attr.license = "GPL";
+
+	prog_fd = bpf_load_program_xattr(&prog_attr, NULL, 0);
+	if (prog_fd < 0) {
+		close(map_fd);
+		return detected;
+	}
+
+	ret = bpf_prog_test_run(prog_fd, 0, &data_in, 1, &data_out, &size_out, &retval, &duration);
+	if (!ret && retval == XDP_PASS)
+		detected = XSK_PROG_REDIRECT_FLAGS;
+	close(prog_fd);
+	close(map_fd);
+	return detected;
+}
+
 static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 {
 	static const int log_buf_size = 16 * 1024;
@@ -358,7 +411,7 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 	char log_buf[log_buf_size];
 	int err, prog_fd;
 
-	/* This is the C-program:
+	/* This is the fallback C-program:
 	 * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
 	 * {
 	 *     int ret, index = ctx->rx_queue_index;
@@ -414,9 +467,31 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 		/* The jumps are to this instruction */
 		BPF_EXIT_INSN(),
 	};
-	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
 
-	prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, prog, insns_cnt,
+	/* This is the post-5.3 kernel C-program:
+	 * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
+	 * {
+	 *     return bpf_redirect_map(&xsks_map, ctx->rx_queue_index, XDP_PASS);
+	 * }
+	 */
+	struct bpf_insn prog_redirect_flags[] = {
+		/* r2 = *(u32 *)(r1 + 16) */
+		BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 16),
+		/* r1 = xskmap[] */
+		BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd),
+		/* r3 = XDP_PASS */
+		BPF_MOV64_IMM(BPF_REG_3, 2),
+		/* call bpf_redirect_map */
+		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt[] = {sizeof(prog) / sizeof(struct bpf_insn),
+			      sizeof(prog_redirect_flags) / sizeof(struct bpf_insn),
+	};
+	struct bpf_insn *progs[] = {prog, prog_redirect_flags};
+	enum xsk_prog option = get_xsk_prog();
+
+	prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, progs[option], insns_cnt[option],
 				   "LGPL-2.1 or BSD-2-Clause", 0, log_buf,
 				   log_buf_size);
 	if (prog_fd < 0) {
@@ -442,7 +517,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 	struct ifreq ifr = {};
 	int fd, err, ret;
 
-	fd = socket(AF_INET, SOCK_DGRAM, 0);
+	fd = socket(AF_LOCAL, SOCK_DGRAM, 0);
 	if (fd < 0)
 		return -errno;