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

Daniel Borkmann says:

====================
pull-request: bpf 2020-08-15

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

We've added 23 non-merge commits during the last 4 day(s) which contain
a total of 32 files changed, 421 insertions(+), 141 deletions(-).

The main changes are:

1) Fix sock_ops ctx access splat due to register override, from John Fastabend.

2) Batch of various fixes to libbpf, bpftool, and selftests when testing build
   in 32-bit mode, from Andrii Nakryiko.

3) Fix vmlinux.h generation on ARM by mapping GCC built-in types (__Poly*_t)
   to equivalent ones clang can work with, from Jean-Philippe Brucker.

4) Fix build_id lookup in bpf_get_stackid() helper by walking all NOTE ELF
   sections instead of just first, from Jiri Olsa.

5) Avoid use of __builtin_offsetof() in libbpf for CO-RE, from Yonghong Song.

6) Fix segfault in test_mmap due to inconsistent length params, from Jianlin Lv.

7) Don't override errno in libbpf when logging errors, from Toke Høiland-Jørgensen.

8) Fix v4_to_v6 sockaddr conversion in sk_lookup test, from Stanislav Fomichev.

9) Add link to bpf-helpers(7) man page to BPF doc, from Joe Stringer.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

Documentation/bpf/index.rst

@@ -36,6 +36,12 @@ Two sets of Questions and Answers (Q&A) are maintained.
    bpf_devel_QA
 
 
+Helper functions
+================
+
+* `bpf-helpers(7)`_ maintains a list of helpers available to eBPF programs.
+
+
 Program types
 =============
 
@@ -79,4 +85,5 @@ Other
 .. _networking-filter: ../networking/filter.rst
 .. _man-pages: https://www.kernel.org/doc/man-pages/
 .. _bpf(2): https://man7.org/linux/man-pages/man2/bpf.2.html
+.. _bpf-helpers(7): https://man7.org/linux/man-pages/man7/bpf-helpers.7.html
 .. _BPF and XDP Reference Guide: https://docs.cilium.io/en/latest/bpf/

kernel/bpf/stackmap.c

@@ -213,11 +213,13 @@ static int stack_map_get_build_id_32(void *page_addr,
 
 	phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr));
 
-	for (i = 0; i < ehdr->e_phnum; ++i)
-		if (phdr[i].p_type == PT_NOTE)
-			return stack_map_parse_build_id(page_addr, build_id,
-					page_addr + phdr[i].p_offset,
-					phdr[i].p_filesz);
+	for (i = 0; i < ehdr->e_phnum; ++i) {
+		if (phdr[i].p_type == PT_NOTE &&
+		    !stack_map_parse_build_id(page_addr, build_id,
+					      page_addr + phdr[i].p_offset,
+					      phdr[i].p_filesz))
+			return 0;
+	}
 	return -EINVAL;
 }
 
@@ -236,11 +238,13 @@ static int stack_map_get_build_id_64(void *page_addr,
 
 	phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr));
 
-	for (i = 0; i < ehdr->e_phnum; ++i)
-		if (phdr[i].p_type == PT_NOTE)
-			return stack_map_parse_build_id(page_addr, build_id,
-					page_addr + phdr[i].p_offset,
-					phdr[i].p_filesz);
+	for (i = 0; i < ehdr->e_phnum; ++i) {
+		if (phdr[i].p_type == PT_NOTE &&
+		    !stack_map_parse_build_id(page_addr, build_id,
+					      page_addr + phdr[i].p_offset,
+					      phdr[i].p_filesz))
+			return 0;
+	}
 	return -EINVAL;
 }
 

net/core/dev.c

@@ -8913,10 +8913,6 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 		NL_SET_ERR_MSG(extack, "Active program does not match expected");
 		return -EEXIST;
 	}
-	if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) {
-		NL_SET_ERR_MSG(extack, "XDP program already attached");
-		return -EBUSY;
-	}
 
 	/* put effective new program into new_prog */
 	if (link)
@@ -8927,6 +8923,10 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 		enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB
 					       ? XDP_MODE_DRV : XDP_MODE_SKB;
 
+		if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) {
+			NL_SET_ERR_MSG(extack, "XDP program already attached");
+			return -EBUSY;
+		}
 		if (!offload && dev_xdp_prog(dev, other_mode)) {
 			NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time");
 			return -EEXIST;

net/core/filter.c

@@ -8317,15 +8317,31 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 /* Helper macro for adding read access to tcp_sock or sock fields. */
 #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ)			      \
 	do {								      \
+		int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 2;     \
 		BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) >		      \
 			     sizeof_field(struct bpf_sock_ops, BPF_FIELD));   \
+		if (si->dst_reg == reg || si->src_reg == reg)		      \
+			reg--;						      \
+		if (si->dst_reg == reg || si->src_reg == reg)		      \
+			reg--;						      \
+		if (si->dst_reg == si->src_reg) {			      \
+			*insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg,	      \
+					  offsetof(struct bpf_sock_ops_kern,  \
+					  temp));			      \
+			fullsock_reg = reg;				      \
+			jmp += 2;					      \
+		}							      \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
 						struct bpf_sock_ops_kern,     \
 						is_fullsock),		      \
-				      si->dst_reg, si->src_reg,		      \
+				      fullsock_reg, si->src_reg,	      \
 				      offsetof(struct bpf_sock_ops_kern,      \
 					       is_fullsock));		      \
-		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 2);	      \
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp);	      \
+		if (si->dst_reg == si->src_reg)				      \
+			*insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg,	      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+				      temp));				      \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
 						struct bpf_sock_ops_kern, sk),\
 				      si->dst_reg, si->src_reg,		      \
@@ -8334,6 +8350,49 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 						       OBJ_FIELD),	      \
 				      si->dst_reg, si->dst_reg,		      \
 				      offsetof(OBJ, OBJ_FIELD));	      \
+		if (si->dst_reg == si->src_reg)	{			      \
+			*insn++ = BPF_JMP_A(1);				      \
+			*insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg,	      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+				      temp));				      \
+		}							      \
+	} while (0)
+
+#define SOCK_OPS_GET_SK()							      \
+	do {								      \
+		int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 1;     \
+		if (si->dst_reg == reg || si->src_reg == reg)		      \
+			reg--;						      \
+		if (si->dst_reg == reg || si->src_reg == reg)		      \
+			reg--;						      \
+		if (si->dst_reg == si->src_reg) {			      \
+			*insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg,	      \
+					  offsetof(struct bpf_sock_ops_kern,  \
+					  temp));			      \
+			fullsock_reg = reg;				      \
+			jmp += 2;					      \
+		}							      \
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
+						struct bpf_sock_ops_kern,     \
+						is_fullsock),		      \
+				      fullsock_reg, si->src_reg,	      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+					       is_fullsock));		      \
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp);	      \
+		if (si->dst_reg == si->src_reg)				      \
+			*insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg,	      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+				      temp));				      \
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
+						struct bpf_sock_ops_kern, sk),\
+				      si->dst_reg, si->src_reg,		      \
+				      offsetof(struct bpf_sock_ops_kern, sk));\
+		if (si->dst_reg == si->src_reg)	{			      \
+			*insn++ = BPF_JMP_A(1);				      \
+			*insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg,	      \
+				      offsetof(struct bpf_sock_ops_kern,      \
+				      temp));				      \
+		}							      \
 	} while (0)
 
 #define SOCK_OPS_GET_TCP_SOCK_FIELD(FIELD) \
@@ -8620,17 +8679,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 		SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked);
 		break;
 	case offsetof(struct bpf_sock_ops, sk):
-		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
-						struct bpf_sock_ops_kern,
-						is_fullsock),
-				      si->dst_reg, si->src_reg,
-				      offsetof(struct bpf_sock_ops_kern,
-					       is_fullsock));
-		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
-		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(
-						struct bpf_sock_ops_kern, sk),
-				      si->dst_reg, si->src_reg,
-				      offsetof(struct bpf_sock_ops_kern, sk));
+		SOCK_OPS_GET_SK();
 		break;
 	}
 	return insn - insn_buf;

tools/bpf/bpftool/btf_dumper.c

@@ -67,7 +67,7 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d,
 	if (!info->btf_id || !info->nr_func_info ||
 	    btf__get_from_id(info->btf_id, &prog_btf))
 		goto print;
-	finfo = (struct bpf_func_info *)info->func_info;
+	finfo = u64_to_ptr(info->func_info);
 	func_type = btf__type_by_id(prog_btf, finfo->type_id);
 	if (!func_type || !btf_is_func(func_type))
 		goto print;

tools/bpf/bpftool/gen.c

@@ -143,6 +143,20 @@ static int codegen_datasec_def(struct bpf_object *obj,
 			      var_name, align);
 			return -EINVAL;
 		}
+		/* Assume 32-bit architectures when generating data section
+		 * struct memory layout. Given bpftool can't know which target
+		 * host architecture it's emitting skeleton for, we need to be
+		 * conservative and assume 32-bit one to ensure enough padding
+		 * bytes are generated for pointer and long types. This will
+		 * still work correctly for 64-bit architectures, because in
+		 * the worst case we'll generate unnecessary padding field,
+		 * which on 64-bit architectures is not strictly necessary and
+		 * would be handled by natural 8-byte alignment. But it still
+		 * will be a correct memory layout, based on recorded offsets
+		 * in BTF.
+		 */
+		if (align > 4)
+			align = 4;
 
 		align_off = (off + align - 1) / align * align;
 		if (align_off != need_off) {
@@ -397,7 +411,7 @@ static int do_skeleton(int argc, char **argv)
 		{							    \n\
 			struct %1$s *obj;				    \n\
 									    \n\
-			obj = (typeof(obj))calloc(1, sizeof(*obj));	    \n\
+			obj = (struct %1$s *)calloc(1, sizeof(*obj));	    \n\
 			if (!obj)					    \n\
 				return NULL;				    \n\
 			if (%1$s__create_skeleton(obj))			    \n\
@@ -461,7 +475,7 @@ static int do_skeleton(int argc, char **argv)
 		{							    \n\
 			struct bpf_object_skeleton *s;			    \n\
 									    \n\
-			s = (typeof(s))calloc(1, sizeof(*s));		    \n\
+			s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\
 			if (!s)						    \n\
 				return -1;				    \n\
 			obj->skeleton = s;				    \n\
@@ -479,7 +493,7 @@ static int do_skeleton(int argc, char **argv)
 				/* maps */				    \n\
 				s->map_cnt = %zu;			    \n\
 				s->map_skel_sz = sizeof(*s->maps);	    \n\
-				s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz);\n\
+				s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\
 				if (!s->maps)				    \n\
 					goto err;			    \n\
 			",
@@ -515,7 +529,7 @@ static int do_skeleton(int argc, char **argv)
 				/* programs */				    \n\
 				s->prog_cnt = %zu;			    \n\
 				s->prog_skel_sz = sizeof(*s->progs);	    \n\
-				s->progs = (typeof(s->progs))calloc(s->prog_cnt, s->prog_skel_sz);\n\
+				s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\
 				if (!s->progs)				    \n\
 					goto err;			    \n\
 			",

tools/bpf/bpftool/link.c

@@ -106,7 +106,7 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 	switch (info->type) {
 	case BPF_LINK_TYPE_RAW_TRACEPOINT:
 		jsonw_string_field(json_wtr, "tp_name",
-				   (const char *)info->raw_tracepoint.tp_name);
+				   u64_to_ptr(info->raw_tracepoint.tp_name));
 		break;
 	case BPF_LINK_TYPE_TRACING:
 		err = get_prog_info(info->prog_id, &prog_info);
@@ -185,7 +185,7 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 	switch (info->type) {
 	case BPF_LINK_TYPE_RAW_TRACEPOINT:
 		printf("\n\ttp '%s'  ",
-		       (const char *)info->raw_tracepoint.tp_name);
+		       (const char *)u64_to_ptr(info->raw_tracepoint.tp_name));
 		break;
 	case BPF_LINK_TYPE_TRACING:
 		err = get_prog_info(info->prog_id, &prog_info);

tools/bpf/bpftool/main.h

@@ -21,7 +21,15 @@
 /* Make sure we do not use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
 
-#define ptr_to_u64(ptr)	((__u64)(unsigned long)(ptr))
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64)(unsigned long)ptr;
+}
+
+static inline void *u64_to_ptr(__u64 ptr)
+{
+	return (void *)(unsigned long)ptr;
+}
 
 #define NEXT_ARG()	({ argc--; argv++; if (argc < 0) usage(); })
 #define NEXT_ARGP()	({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })

tools/bpf/bpftool/prog.c

@@ -428,14 +428,14 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 			p_info("no instructions returned");
 			return -1;
 		}
-		buf = (unsigned char *)(info->jited_prog_insns);
+		buf = u64_to_ptr(info->jited_prog_insns);
 		member_len = info->jited_prog_len;
 	} else {	/* DUMP_XLATED */
 		if (info->xlated_prog_len == 0 || !info->xlated_prog_insns) {
 			p_err("error retrieving insn dump: kernel.kptr_restrict set?");
 			return -1;
 		}
-		buf = (unsigned char *)info->xlated_prog_insns;
+		buf = u64_to_ptr(info->xlated_prog_insns);
 		member_len = info->xlated_prog_len;
 	}
 
@@ -444,7 +444,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 		return -1;
 	}
 
-	func_info = (void *)info->func_info;
+	func_info = u64_to_ptr(info->func_info);
 
 	if (info->nr_line_info) {
 		prog_linfo = bpf_prog_linfo__new(info);
@@ -462,7 +462,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 
 		n = write(fd, buf, member_len);
 		close(fd);
-		if (n != member_len) {
+		if (n != (ssize_t)member_len) {
 			p_err("error writing output file: %s",
 			      n < 0 ? strerror(errno) : "short write");
 			return -1;
@@ -492,13 +492,13 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 			__u32 i;
 			if (info->nr_jited_ksyms) {
 				kernel_syms_load(&dd);
-				ksyms = (__u64 *) info->jited_ksyms;
+				ksyms = u64_to_ptr(info->jited_ksyms);
 			}
 
 			if (json_output)
 				jsonw_start_array(json_wtr);
 
-			lens = (__u32 *) info->jited_func_lens;
+			lens = u64_to_ptr(info->jited_func_lens);
 			for (i = 0; i < info->nr_jited_func_lens; i++) {
 				if (ksyms) {
 					sym = kernel_syms_search(&dd, ksyms[i]);
@@ -559,7 +559,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
 	} else {
 		kernel_syms_load(&dd);
 		dd.nr_jited_ksyms = info->nr_jited_ksyms;
-		dd.jited_ksyms = (__u64 *) info->jited_ksyms;
+		dd.jited_ksyms = u64_to_ptr(info->jited_ksyms);
 		dd.btf = btf;
 		dd.func_info = func_info;
 		dd.finfo_rec_size = info->func_info_rec_size;
@@ -1681,7 +1681,7 @@ static char *profile_target_name(int tgt_fd)
 		goto out;
 	}
 
-	func_info = (struct bpf_func_info *)(info_linear->info.func_info);
+	func_info = u64_to_ptr(info_linear->info.func_info);
 	t = btf__type_by_id(btf, func_info[0].type_id);
 	if (!t) {
 		p_err("btf %d doesn't have type %d",

tools/lib/bpf/bpf_helpers.h

@@ -40,7 +40,7 @@
  * Helper macro to manipulate data structures
  */
 #ifndef offsetof
-#define offsetof(TYPE, MEMBER)  __builtin_offsetof(TYPE, MEMBER)
+#define offsetof(TYPE, MEMBER)	((unsigned long)&((TYPE *)0)->MEMBER)
 #endif
 #ifndef container_of
 #define container_of(ptr, type, member)				\