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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-12-21

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

There is a merge conflict in test_verifier.c. Result looks as follows:

        [...]
        },
        {
                "calls: cross frame pruning",
                .insns = {
                [...]
                .prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
                .errstr_unpriv = "function calls to other bpf functions are allowed for root only",
                .result_unpriv = REJECT,
                .errstr = "!read_ok",
                .result = REJECT,
	},
        {
                "jset: functional",
                .insns = {
        [...]
        {
                "jset: unknown const compare not taken",
                .insns = {
                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
                                     BPF_FUNC_get_prandom_u32),
                        BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
                        BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
                        BPF_EXIT_INSN(),
                },
                .prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
                .errstr_unpriv = "!read_ok",
                .result_unpriv = REJECT,
                .errstr = "!read_ok",
                .result = REJECT,
        },
        [...]
        {
                "jset: range",
                .insns = {
                [...]
                },
                .prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
                .result_unpriv = ACCEPT,
                .result = ACCEPT,
        },

The main changes are:

1) Various BTF related improvements in order to get line info
   working. Meaning, verifier will now annotate the corresponding
   BPF C code to the error log, from Martin and Yonghong.

2) Implement support for raw BPF tracepoints in modules, from Matt.

3) Add several improvements to verifier state logic, namely speeding
   up stacksafe check, optimizations for stack state equivalence
   test and safety checks for liveness analysis, from Alexei.

4) Teach verifier to make use of BPF_JSET instruction, add several
   test cases to kselftests and remove nfp specific JSET optimization
   now that verifier has awareness, from Jakub.

5) Improve BPF verifier's slot_type marking logic in order to
   allow more stack slot sharing, from Jiong.

6) Add sk_msg->size member for context access and add set of fixes
   and improvements to make sock_map with kTLS usable with openssl
   based applications, from John.

7) Several cleanups and documentation updates in bpftool as well as
   auto-mount of tracefs for "bpftool prog tracelog" command,
   from Quentin.

8) Include sub-program tags from now on in bpf_prog_info in order to
   have a reliable way for user space to get all tags of the program
   e.g. needed for kallsyms correlation, from Song.

9) Add BTF annotations for cgroup_local_storage BPF maps and
   implement bpf fs pretty print support, from Roman.

10) Fix bpftool in order to allow for cross-compilation, from Ivan.

11) Update of bpftool license to GPLv2-only + BSD-2-Clause in order
    to be compatible with libbfd and allow for Debian packaging,
    from Jakub.

12) Remove an obsolete prog->aux sanitation in dump and get rid of
    version check for prog load, from Daniel.

13) Fix a memory leak in libbpf's line info handling, from Prashant.

14) Fix cpumap's frame alignment for build_skb() so that skb_shared_info
    does not get unaligned, from Jesper.

15) Fix test_progs kselftest to work with older compilers which are less
    smart in optimizing (and thus throwing build error), from Stanislav.

16) Cleanup and simplify AF_XDP socket teardown, from Björn.

17) Fix sk lookup in BPF kselftest's test_sock_addr with regards
    to netns_id argument, from Andrey.
====================

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

arch/arm64/net/bpf_jit_comp.c

@@ -932,6 +932,7 @@ skip_init_ctx:
 	prog->jited_len = image_size;
 
 	if (!prog->is_func || extra_pass) {
+		bpf_prog_fill_jited_linfo(prog, ctx.offset);
 out_off:
 		kfree(ctx.offset);
 		kfree(jit_data);

arch/sparc/net/bpf_jit_comp_64.c

@@ -1575,6 +1575,7 @@ skip_init_ctx:
 	prog->jited_len = image_size;
 
 	if (!prog->is_func || extra_pass) {
+		bpf_prog_fill_jited_linfo(prog, ctx.offset);
 out_off:
 		kfree(ctx.offset);
 		kfree(jit_data);

drivers/net/ethernet/netronome/nfp/bpf/jit.c

@@ -3052,26 +3052,19 @@ static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
 	u64 imm = insn->imm; /* sign extend */
+	u8 dst_gpr = insn->dst_reg * 2;
 	swreg tmp_reg;
 
-	if (!imm) {
+	tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
-		meta->skip = true;
+	emit_alu(nfp_prog, imm_b(nfp_prog),
-		return 0;
+		 reg_a(dst_gpr), ALU_OP_AND, tmp_reg);
-	}
+	/* Upper word of the mask can only be 0 or ~0 from sign extension,
-
+	 * so either ignore it or OR the whole thing in.
-	if (imm & ~0U) {
+	 */
-		tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
+	if (imm >> 32)
 		emit_alu(nfp_prog, reg_none(),
-			 reg_a(insn->dst_reg * 2), ALU_OP_AND, tmp_reg);
+			 reg_a(dst_gpr + 1), ALU_OP_OR, imm_b(nfp_prog));
-		emit_br(nfp_prog, BR_BNE, insn->off, 0);
+	emit_br(nfp_prog, BR_BNE, insn->off, 0);
-	}
-
-	if (imm >> 32) {
-		tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
-		emit_alu(nfp_prog, reg_none(),
-			 reg_a(insn->dst_reg * 2 + 1), ALU_OP_AND, tmp_reg);
-		emit_br(nfp_prog, BR_BNE, insn->off, 0);
-	}
 
 	return 0;
 }

include/linux/bpf.h

@@ -23,6 +23,7 @@ struct bpf_prog;
 struct bpf_map;
 struct sock;
 struct seq_file;
+struct btf;
 struct btf_type;
 
 /* map is generic key/value storage optionally accesible by eBPF programs */
@@ -52,6 +53,7 @@ struct bpf_map_ops {
 	void (*map_seq_show_elem)(struct bpf_map *map, void *key,
 				  struct seq_file *m);
 	int (*map_check_btf)(const struct bpf_map *map,
+			     const struct btf *btf,
 			     const struct btf_type *key_type,
 			     const struct btf_type *value_type);
 };
@@ -126,6 +128,7 @@ static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
 }
 
 int map_check_no_btf(const struct bpf_map *map,
+		     const struct btf *btf,
 		     const struct btf_type *key_type,
 		     const struct btf_type *value_type);
 

include/linux/bpf_verifier.h

@@ -38,6 +38,7 @@ enum bpf_reg_liveness {
 	REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */
 	REG_LIVE_READ, /* reg was read, so we're sensitive to initial value */
 	REG_LIVE_WRITTEN, /* reg was written first, screening off later reads */
+	REG_LIVE_DONE = 4, /* liveness won't be updating this register anymore */
 };
 
 struct bpf_reg_state {
@@ -224,6 +225,7 @@ struct bpf_verifier_env {
 	bool allow_ptr_leaks;
 	bool seen_direct_write;
 	struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
+	const struct bpf_line_info *prev_linfo;
 	struct bpf_verifier_log log;
 	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
 	u32 subprog_cnt;

include/linux/btf.h

@@ -7,6 +7,7 @@
 #include <linux/types.h>
 
 struct btf;
+struct btf_member;
 struct btf_type;
 union bpf_attr;
 
@@ -46,7 +47,9 @@ void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
 		       struct seq_file *m);
 int btf_get_fd_by_id(u32 id);
 u32 btf_id(const struct btf *btf);
-bool btf_name_offset_valid(const struct btf *btf, u32 offset);
+bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
+			   const struct btf_member *m,
+			   u32 expected_offset, u32 expected_size);
 
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);

include/linux/module.h

@@ -432,6 +432,10 @@ struct module {
 	unsigned int num_tracepoints;
 	tracepoint_ptr_t *tracepoints_ptrs;
 #endif
+#ifdef CONFIG_BPF_EVENTS
+	unsigned int num_bpf_raw_events;
+	struct bpf_raw_event_map *bpf_raw_events;
+#endif
 #ifdef HAVE_JUMP_LABEL
 	struct jump_entry *jump_entries;
 	unsigned int num_jump_entries;

include/linux/skmsg.h

@@ -36,6 +36,7 @@ struct sk_msg_sg {
 	struct scatterlist		data[MAX_MSG_FRAGS + 1];
 };
 
+/* UAPI in filter.c depends on struct sk_msg_sg being first element. */
 struct sk_msg {
 	struct sk_msg_sg		sg;
 	void				*data;
@@ -416,6 +417,14 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock)
 		sk_psock_drop(sk, psock);
 }
 
+static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock)
+{
+	if (psock->parser.enabled)
+		psock->parser.saved_data_ready(sk);
+	else
+		sk->sk_data_ready(sk);
+}
+
 static inline void psock_set_prog(struct bpf_prog **pprog,
 				  struct bpf_prog *prog)
 {

include/linux/socket.h

@@ -286,6 +286,7 @@ struct ucred {
 #define MSG_NOSIGNAL	0x4000	/* Do not generate SIGPIPE */
 #define MSG_MORE	0x8000	/* Sender will send more */
 #define MSG_WAITFORONE	0x10000	/* recvmmsg(): block until 1+ packets avail */
+#define MSG_SENDPAGE_NOPOLICY 0x10000 /* sendpage() internal : do no apply policy */
 #define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */
 #define MSG_BATCH	0x40000 /* sendmmsg(): more messages coming */
 #define MSG_EOF         MSG_FIN

include/linux/trace_events.h

@@ -471,7 +471,8 @@ void perf_event_detach_bpf_prog(struct perf_event *event);
 int perf_event_query_prog_array(struct perf_event *event, void __user *info);
 int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
 int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog);
-struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name);
+struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name);
+void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp);
 int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 			    u32 *fd_type, const char **buf,
 			    u64 *probe_offset, u64 *probe_addr);
@@ -502,10 +503,13 @@ static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf
 {
 	return -EOPNOTSUPP;
 }
-static inline struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
+static inline struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name)
 {
 	return NULL;
 }
+static inline void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp)
+{
+}
 static inline int bpf_get_perf_event_info(const struct perf_event *event,
 					  u32 *prog_id, u32 *fd_type,
 					  const char **buf, u64 *probe_offset,

include/net/tls.h

@@ -460,6 +460,15 @@ tls_offload_ctx_tx(const struct tls_context *tls_ctx)
 	return (struct tls_offload_context_tx *)tls_ctx->priv_ctx_tx;
 }
 
+static inline bool tls_sw_has_ctx_tx(const struct sock *sk)
+{
+	struct tls_context *ctx = tls_get_ctx(sk);
+
+	if (!ctx)
+		return false;
+	return !!tls_sw_ctx_tx(ctx);
+}
+
 static inline struct tls_offload_context_rx *
 tls_offload_ctx_rx(const struct tls_context *tls_ctx)
 {

include/uapi/linux/bpf.h

@@ -133,6 +133,14 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_STACK,
 };
 
+/* Note that tracing related programs such as
+ * BPF_PROG_TYPE_{KPROBE,TRACEPOINT,PERF_EVENT,RAW_TRACEPOINT}
+ * are not subject to a stable API since kernel internal data
+ * structures can change from release to release and may
+ * therefore break existing tracing BPF programs. Tracing BPF
+ * programs correspond to /a/ specific kernel which is to be
+ * analyzed, and not /a/ specific kernel /and/ all future ones.
+ */
 enum bpf_prog_type {
 	BPF_PROG_TYPE_UNSPEC,
 	BPF_PROG_TYPE_SOCKET_FILTER,
@@ -343,7 +351,7 @@ union bpf_attr {
 		__u32		log_level;	/* verbosity level of verifier */
 		__u32		log_size;	/* size of user buffer */
 		__aligned_u64	log_buf;	/* user supplied buffer */
-		__u32		kern_version;	/* checked when prog_type=kprobe */
+		__u32		kern_version;	/* not used */
 		__u32		prog_flags;
 		char		prog_name[BPF_OBJ_NAME_LEN];
 		__u32		prog_ifindex;	/* ifindex of netdev to prep for */
@@ -2657,6 +2665,7 @@ struct sk_msg_md {
 	__u32 local_ip6[4];	/* Stored in network byte order */
 	__u32 remote_port;	/* Stored in network byte order */
 	__u32 local_port;	/* stored in host byte order */
+	__u32 size;		/* Total size of sk_msg */
 };
 
 struct sk_reuseport_md {
@@ -2717,6 +2726,8 @@ struct bpf_prog_info {
 	__u32 nr_jited_line_info;
 	__u32 line_info_rec_size;
 	__u32 jited_line_info_rec_size;
+	__u32 nr_prog_tags;
+	__aligned_u64 prog_tags;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {

include/uapi/linux/btf.h

@@ -34,7 +34,9 @@ struct btf_type {
 	 * bits  0-15: vlen (e.g. # of struct's members)
 	 * bits 16-23: unused
 	 * bits 24-27: kind (e.g. int, ptr, array...etc)
-	 * bits 28-31: unused
+	 * bits 28-30: unused
+	 * bit     31: kind_flag, currently used by
+	 *             struct, union and fwd
 	 */
 	__u32 info;
 	/* "size" is used by INT, ENUM, STRUCT and UNION.
@@ -52,6 +54,7 @@ struct btf_type {
 
 #define BTF_INFO_KIND(info)	(((info) >> 24) & 0x0f)
 #define BTF_INFO_VLEN(info)	((info) & 0xffff)
+#define BTF_INFO_KFLAG(info)	((info) >> 31)
 
 #define BTF_KIND_UNKN		0	/* Unknown	*/
 #define BTF_KIND_INT		1	/* Integer	*/
@@ -110,9 +113,22 @@ struct btf_array {
 struct btf_member {
 	__u32	name_off;
 	__u32	type;
-	__u32	offset;	/* offset in bits */
+	/* If the type info kind_flag is set, the btf_member offset
+	 * contains both member bitfield size and bit offset. The
+	 * bitfield size is set for bitfield members. If the type
+	 * info kind_flag is not set, the offset contains only bit
+	 * offset.
+	 */
+	__u32	offset;
 };
 
+/* If the struct/union type info kind_flag is set, the
+ * following two macros are used to access bitfield_size
+ * and bit_offset from btf_member.offset.
+ */
+#define BTF_MEMBER_BITFIELD_SIZE(val)	((val) >> 24)
+#define BTF_MEMBER_BIT_OFFSET(val)	((val) & 0xffffff)
+
 /* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param".
  * The exact number of btf_param is stored in the vlen (of the
  * info in "struct btf_type").

kernel/bpf/arraymap.c

@@ -382,6 +382,7 @@ static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key,
 }
 
 static int array_map_check_btf(const struct bpf_map *map,
+			       const struct btf *btf,
 			       const struct btf_type *key_type,
 			       const struct btf_type *value_type)
 {

kernel/bpf/btf.c

@@ -164,7 +164,7 @@
 #define BITS_ROUNDUP_BYTES(bits) \
 	(BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits))
 
-#define BTF_INFO_MASK 0x0f00ffff
+#define BTF_INFO_MASK 0x8f00ffff
 #define BTF_INT_MASK 0x0fffffff
 #define BTF_TYPE_ID_VALID(type_id) ((type_id) <= BTF_MAX_TYPE)
 #define BTF_STR_OFFSET_VALID(name_off) ((name_off) <= BTF_MAX_NAME_OFFSET)
@@ -274,6 +274,10 @@ struct btf_kind_operations {
 			    const struct btf_type *struct_type,
 			    const struct btf_member *member,
 			    const struct btf_type *member_type);
+	int (*check_kflag_member)(struct btf_verifier_env *env,
+				  const struct btf_type *struct_type,
+				  const struct btf_member *member,
+				  const struct btf_type *member_type);
 	void (*log_details)(struct btf_verifier_env *env,
 			    const struct btf_type *t);
 	void (*seq_show)(const struct btf *btf, const struct btf_type *t,
@@ -419,6 +423,25 @@ static u16 btf_type_vlen(const struct btf_type *t)
 	return BTF_INFO_VLEN(t->info);
 }
 
+static bool btf_type_kflag(const struct btf_type *t)
+{
+	return BTF_INFO_KFLAG(t->info);
+}
+
+static u32 btf_member_bit_offset(const struct btf_type *struct_type,
+			     const struct btf_member *member)
+{
+	return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset)
+					   : member->offset;
+}
+
+static u32 btf_member_bitfield_size(const struct btf_type *struct_type,
+				    const struct btf_member *member)
+{
+	return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset)
+					   : 0;
+}
+
 static u32 btf_type_int(const struct btf_type *t)
 {
 	return *(u32 *)(t + 1);
@@ -474,7 +497,7 @@ static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
 	return !*src;
 }
 
-const char *btf_name_by_offset(const struct btf *btf, u32 offset)
+static const char *__btf_name_by_offset(const struct btf *btf, u32 offset)
 {
 	if (!offset)
 		return "(anon)";
@@ -484,6 +507,14 @@ const char *btf_name_by_offset(const struct btf *btf, u32 offset)
 		return "(invalid-name-offset)";
 }
 
+const char *btf_name_by_offset(const struct btf *btf, u32 offset)
+{
+	if (offset < btf->hdr.str_len)
+		return &btf->strings[offset];
+
+	return NULL;
+}
+
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
 {
 	if (type_id > btf->nr_types)
@@ -514,6 +545,47 @@ static bool btf_type_int_is_regular(const struct btf_type *t)
 	return true;
 }
 
+/*
+ * Check that given struct member is a regular int with expected
+ * offset and size.
+ */
+bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
+			   const struct btf_member *m,
+			   u32 expected_offset, u32 expected_size)
+{
+	const struct btf_type *t;
+	u32 id, int_data;
+	u8 nr_bits;
+
+	id = m->type;
+	t = btf_type_id_size(btf, &id, NULL);
+	if (!t || !btf_type_is_int(t))
+		return false;
+
+	int_data = btf_type_int(t);
+	nr_bits = BTF_INT_BITS(int_data);
+	if (btf_type_kflag(s)) {
+		u32 bitfield_size = BTF_MEMBER_BITFIELD_SIZE(m->offset);
+		u32 bit_offset = BTF_MEMBER_BIT_OFFSET(m->offset);
+
+		/* if kflag set, int should be a regular int and
+		 * bit offset should be at byte boundary.
+		 */
+		return !bitfield_size &&
+		       BITS_ROUNDUP_BYTES(bit_offset) == expected_offset &&
+		       BITS_ROUNDUP_BYTES(nr_bits) == expected_size;
+	}
+
+	if (BTF_INT_OFFSET(int_data) ||
+	    BITS_PER_BYTE_MASKED(m->offset) ||
+	    BITS_ROUNDUP_BYTES(m->offset) != expected_offset ||
+	    BITS_PER_BYTE_MASKED(nr_bits) ||
+	    BITS_ROUNDUP_BYTES(nr_bits) != expected_size)
+		return false;
+
+	return true;
+}
+
 __printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log,
 					      const char *fmt, ...)
 {
@@ -554,7 +626,7 @@ __printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env,
 	__btf_verifier_log(log, "[%u] %s %s%s",
 			   env->log_type_id,
 			   btf_kind_str[kind],
-			   btf_name_by_offset(btf, t->name_off),
+			   __btf_name_by_offset(btf, t->name_off),
 			   log_details ? " " : "");
 
 	if (log_details)
@@ -597,9 +669,17 @@ static void btf_verifier_log_member(struct btf_verifier_env *env,
 	if (env->phase != CHECK_META)
 		btf_verifier_log_type(env, struct_type, NULL);
 
-	__btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u",
+	if (btf_type_kflag(struct_type))
-			   btf_name_by_offset(btf, member->name_off),
+		__btf_verifier_log(log,
-			   member->type, member->offset);
+				   "\t%s type_id=%u bitfield_size=%u bits_offset=%u",
+				   __btf_name_by_offset(btf, member->name_off),
+				   member->type,
+				   BTF_MEMBER_BITFIELD_SIZE(member->offset),
+				   BTF_MEMBER_BIT_OFFSET(member->offset));
+	else
+		__btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u",
+				   __btf_name_by_offset(btf, member->name_off),
+				   member->type, member->offset);
 
 	if (fmt && *fmt) {
 		__btf_verifier_log(log, " ");
@@ -915,6 +995,38 @@ static int btf_df_check_member(struct btf_verifier_env *env,
 	return -EINVAL;
 }
 
+static int btf_df_check_kflag_member(struct btf_verifier_env *env,
+				     const struct btf_type *struct_type,
+				     const struct btf_member *member,
+				     const struct btf_type *member_type)
+{
+	btf_verifier_log_basic(env, struct_type,
+			       "Unsupported check_kflag_member");
+	return -EINVAL;
+}
+
+/* Used for ptr, array and struct/union type members.
+ * int, enum and modifier types have their specific callback functions.
+ */
+static int btf_generic_check_kflag_member(struct btf_verifier_env *env,
+					  const struct btf_type *struct_type,
+					  const struct btf_member *member,
+					  const struct btf_type *member_type)
+{
+	if (BTF_MEMBER_BITFIELD_SIZE(member->offset)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Invalid member bitfield_size");
+		return -EINVAL;
+	}
+
+	/* bitfield size is 0, so member->offset represents bit offset only.
+	 * It is safe to call non kflag check_member variants.
+	 */
+	return btf_type_ops(member_type)->check_member(env, struct_type,
+						       member,
+						       member_type);
+}
+
 static int btf_df_resolve(struct btf_verifier_env *env,
 			  const struct resolve_vertex *v)
 {
@@ -967,6 +1079,62 @@ static int btf_int_check_member(struct btf_verifier_env *env,
 	return 0;
 }
 
+static int btf_int_check_kflag_member(struct btf_verifier_env *env,
+				      const struct btf_type *struct_type,
+				      const struct btf_member *member,
+				      const struct btf_type *member_type)
+{
+	u32 struct_bits_off, nr_bits, nr_int_data_bits, bytes_offset;
+	u32 int_data = btf_type_int(member_type);
+	u32 struct_size = struct_type->size;
+	u32 nr_copy_bits;
+
+	/* a regular int type is required for the kflag int member */
+	if (!btf_type_int_is_regular(member_type)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Invalid member base type");
+		return -EINVAL;
+	}
+
+	/* check sanity of bitfield size */
+	nr_bits = BTF_MEMBER_BITFIELD_SIZE(member->offset);
+	struct_bits_off = BTF_MEMBER_BIT_OFFSET(member->offset);
+	nr_int_data_bits = BTF_INT_BITS(int_data);
+	if (!nr_bits) {
+		/* Not a bitfield member, member offset must be at byte
+		 * boundary.
+		 */
+		if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+			btf_verifier_log_member(env, struct_type, member,
+						"Invalid member offset");
+			return -EINVAL;
+		}
+
+		nr_bits = nr_int_data_bits;
+	} else if (nr_bits > nr_int_data_bits) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Invalid member bitfield_size");
+		return -EINVAL;
+	}
+
+	bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off);
+	nr_copy_bits = nr_bits + BITS_PER_BYTE_MASKED(struct_bits_off);
+	if (nr_copy_bits > BITS_PER_U64) {
+		btf_verifier_log_member(env, struct_type, member,
+					"nr_copy_bits exceeds 64");
+		return -EINVAL;
+	}
+
+	if (struct_size < bytes_offset ||
+	    struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Member exceeds struct_size");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static s32 btf_int_check_meta(struct btf_verifier_env *env,
 			      const struct btf_type *t,
 			      u32 meta_left)
@@ -986,6 +1154,11 @@ static s32 btf_int_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
 	int_data = btf_type_int(t);
 	if (int_data & ~BTF_INT_MASK) {
 		btf_verifier_log_basic(env, t, "Invalid int_data:%x",
@@ -1038,26 +1211,16 @@ static void btf_int_log(struct btf_verifier_env *env,
 			 btf_int_encoding_str(BTF_INT_ENCODING(int_data)));
 }
 
-static void btf_int_bits_seq_show(const struct btf *btf,
+static void btf_bitfield_seq_show(void *data, u8 bits_offset,
-				  const struct btf_type *t,
+				  u8 nr_bits, struct seq_file *m)
-				  void *data, u8 bits_offset,
-				  struct seq_file *m)
 {
 	u16 left_shift_bits, right_shift_bits;
-	u32 int_data = btf_type_int(t);
-	u8 nr_bits = BTF_INT_BITS(int_data);
-	u8 total_bits_offset;
 	u8 nr_copy_bytes;
 	u8 nr_copy_bits;
 	u64 print_num;
 
-	/*
+	data += BITS_ROUNDDOWN_BYTES(bits_offset);
-	 * bits_offset is at most 7.
+	bits_offset = BITS_PER_BYTE_MASKED(bits_offset);
-	 * BTF_INT_OFFSET() cannot exceed 64 bits.
-	 */
-	total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
-	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
-	bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
 	nr_copy_bits = nr_bits + bits_offset;
 	nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
 
@@ -1077,6 +1240,24 @@ static void btf_int_bits_seq_show(const struct btf *btf,
 	seq_printf(m, "0x%llx", print_num);
 }
 
+
+static void btf_int_bits_seq_show(const struct btf *btf,
+				  const struct btf_type *t,
+				  void *data, u8 bits_offset,
+				  struct seq_file *m)
+{
+	u32 int_data = btf_type_int(t);
+	u8 nr_bits = BTF_INT_BITS(int_data);
+	u8 total_bits_offset;
+
+	/*
+	 * bits_offset is at most 7.
+	 * BTF_INT_OFFSET() cannot exceed 64 bits.
+	 */
+	total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
+	btf_bitfield_seq_show(data, total_bits_offset, nr_bits, m);
+}
+
 static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
 			     u32 type_id, void *data, u8 bits_offset,
 			     struct seq_file *m)
@@ -1126,6 +1307,7 @@ static const struct btf_kind_operations int_ops = {
 	.check_meta = btf_int_check_meta,
 	.resolve = btf_df_resolve,
 	.check_member = btf_int_check_member,
+	.check_kflag_member = btf_int_check_kflag_member,
 	.log_details = btf_int_log,
 	.seq_show = btf_int_seq_show,
 };
@@ -1155,6 +1337,31 @@ static int btf_modifier_check_member(struct btf_verifier_env *env,
 							 resolved_type);
 }
 
+static int btf_modifier_check_kflag_member(struct btf_verifier_env *env,
+					   const struct btf_type *struct_type,
+					   const struct btf_member *member,
+					   const struct btf_type *member_type)
+{
+	const struct btf_type *resolved_type;
+	u32 resolved_type_id = member->type;
+	struct btf_member resolved_member;
+	struct btf *btf = env->btf;
+
+	resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL);
+	if (!resolved_type) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Invalid member");
+		return -EINVAL;
+	}
+
+	resolved_member = *member;
+	resolved_member.type = resolved_type_id;
+
+	return btf_type_ops(resolved_type)->check_kflag_member(env, struct_type,
+							       &resolved_member,
+							       resolved_type);
+}
+
 static int btf_ptr_check_member(struct btf_verifier_env *env,
 				const struct btf_type *struct_type,
 				const struct btf_member *member,
@@ -1190,6 +1397,11 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
 	if (!BTF_TYPE_ID_VALID(t->type)) {
 		btf_verifier_log_type(env, t, "Invalid type_id");
 		return -EINVAL;
@@ -1343,6 +1555,7 @@ static struct btf_kind_operations modifier_ops = {
 	.check_meta = btf_ref_type_check_meta,
 	.resolve = btf_modifier_resolve,
 	.check_member = btf_modifier_check_member,
+	.check_kflag_member = btf_modifier_check_kflag_member,
 	.log_details = btf_ref_type_log,
 	.seq_show = btf_modifier_seq_show,
 };
@@ -1351,6 +1564,7 @@ static struct btf_kind_operations ptr_ops = {
 	.check_meta = btf_ref_type_check_meta,
 	.resolve = btf_ptr_resolve,
 	.check_member = btf_ptr_check_member,
+	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_ref_type_log,
 	.seq_show = btf_ptr_seq_show,
 };
@@ -1381,11 +1595,18 @@ static s32 btf_fwd_check_meta(struct btf_verifier_env *env,
 	return 0;
 }
 
+static void btf_fwd_type_log(struct btf_verifier_env *env,
+			     const struct btf_type *t)
+{
+	btf_verifier_log(env, "%s", btf_type_kflag(t) ? "union" : "struct");
+}
+
 static struct btf_kind_operations fwd_ops = {
 	.check_meta = btf_fwd_check_meta,
 	.resolve = btf_df_resolve,
 	.check_member = btf_df_check_member,
-	.log_details = btf_ref_type_log,
+	.check_kflag_member = btf_df_check_kflag_member,
+	.log_details = btf_fwd_type_log,
 	.seq_show = btf_df_seq_show,
 };
 
@@ -1443,6 +1664,11 @@ static s32 btf_array_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
 	if (t->size) {
 		btf_verifier_log_type(env, t, "size != 0");
 		return -EINVAL;
@@ -1566,6 +1792,7 @@ static struct btf_kind_operations array_ops = {
 	.check_meta = btf_array_check_meta,
 	.resolve = btf_array_resolve,
 	.check_member = btf_array_check_member,
+	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_array_log,
 	.seq_show = btf_array_seq_show,
 };
@@ -1604,6 +1831,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 	u32 meta_needed, last_offset;
 	struct btf *btf = env->btf;
 	u32 struct_size = t->size;
+	u32 offset;
 	u16 i;
 
 	meta_needed = btf_type_vlen(t) * sizeof(*member);
@@ -1645,7 +1873,8 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 			return -EINVAL;
 		}
 
-		if (is_union && member->offset) {
+		offset = btf_member_bit_offset(t, member);
+		if (is_union && offset) {
 			btf_verifier_log_member(env, t, member,
 						"Invalid member bits_offset");
 			return -EINVAL;
@@ -1655,20 +1884,20 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
 		 * ">" instead of ">=" because the last member could be
 		 * "char a[0];"
 		 */
-		if (last_offset > member->offset) {
+		if (last_offset > offset) {
 			btf_verifier_log_member(env, t, member,
 						"Invalid member bits_offset");
 			return -EINVAL;
 		}
 
-		if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
+		if (BITS_ROUNDUP_BYTES(offset) > struct_size) {
 			btf_verifier_log_member(env, t, member,
 						"Member bits_offset exceeds its struct size");
 			return -EINVAL;
 		}
 
 		btf_verifier_log_member(env, t, member, NULL);
-		last_offset = member->offset;
+		last_offset = offset;
 	}
 
 	return meta_needed;
@@ -1698,9 +1927,14 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
 
 		last_member_type = btf_type_by_id(env->btf,
 						  last_member_type_id);
-		err = btf_type_ops(last_member_type)->check_member(env, v->t,
+		if (btf_type_kflag(v->t))
-							last_member,
+			err = btf_type_ops(last_member_type)->check_kflag_member(env, v->t,
-							last_member_type);
+								last_member,
+								last_member_type);
+		else
+			err = btf_type_ops(last_member_type)->check_member(env, v->t,
+								last_member,
+								last_member_type);
 		if (err)
 			return err;
 	}
@@ -1722,9 +1956,14 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
 			return env_stack_push(env, member_type, member_type_id);
 		}
 
-		err = btf_type_ops(member_type)->check_member(env, v->t,
+		if (btf_type_kflag(v->t))
-							      member,
+			err = btf_type_ops(member_type)->check_kflag_member(env, v->t,
-							      member_type);
+									    member,
+									    member_type);
+		else
+			err = btf_type_ops(member_type)->check_member(env, v->t,
+								      member,
+								      member_type);
 		if (err)
 			return err;
 	}
@@ -1752,17 +1991,26 @@ static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t,
 	for_each_member(i, t, member) {
 		const struct btf_type *member_type = btf_type_by_id(btf,
 								member->type);
-		u32 member_offset = member->offset;
-		u32 bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
-		u8 bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
 		const struct btf_kind_operations *ops;
+		u32 member_offset, bitfield_size;
+		u32 bytes_offset;
+		u8 bits8_offset;
 
 		if (i)
 			seq_puts(m, seq);
 
-		ops = btf_type_ops(member_type);
+		member_offset = btf_member_bit_offset(t, member);
-		ops->seq_show(btf, member_type, member->type,
+		bitfield_size = btf_member_bitfield_size(t, member);
-			      data + bytes_offset, bits8_offset, m);
+		if (bitfield_size) {
+			btf_bitfield_seq_show(data, member_offset,
+					      bitfield_size, m);
+		} else {
+			bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset);
+			bits8_offset = BITS_PER_BYTE_MASKED(member_offset);
+			ops = btf_type_ops(member_type);
+			ops->seq_show(btf, member_type, member->type,
+				      data + bytes_offset, bits8_offset, m);
+		}
 	}
 	seq_puts(m, "}");
 }
@@ -1771,6 +2019,7 @@ static struct btf_kind_operations struct_ops = {
 	.check_meta = btf_struct_check_meta,
 	.resolve = btf_struct_resolve,
 	.check_member = btf_struct_check_member,
+	.check_kflag_member = btf_generic_check_kflag_member,
 	.log_details = btf_struct_log,
 	.seq_show = btf_struct_seq_show,
 };
@@ -1800,6 +2049,41 @@ static int btf_enum_check_member(struct btf_verifier_env *env,
 	return 0;
 }
 
+static int btf_enum_check_kflag_member(struct btf_verifier_env *env,
+				       const struct btf_type *struct_type,
+				       const struct btf_member *member,
+				       const struct btf_type *member_type)
+{
+	u32 struct_bits_off, nr_bits, bytes_end, struct_size;
+	u32 int_bitsize = sizeof(int) * BITS_PER_BYTE;
+
+	struct_bits_off = BTF_MEMBER_BIT_OFFSET(member->offset);
+	nr_bits = BTF_MEMBER_BITFIELD_SIZE(member->offset);
+	if (!nr_bits) {
+		if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
+			btf_verifier_log_member(env, struct_type, member,
+						"Member is not byte aligned");
+				return -EINVAL;
+		}
+
+		nr_bits = int_bitsize;
+	} else if (nr_bits > int_bitsize) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Invalid member bitfield_size");
+		return -EINVAL;
+	}
+
+	struct_size = struct_type->size;
+	bytes_end = BITS_ROUNDUP_BYTES(struct_bits_off + nr_bits);
+	if (struct_size < bytes_end) {
+		btf_verifier_log_member(env, struct_type, member,
+					"Member exceeds struct_size");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static s32 btf_enum_check_meta(struct btf_verifier_env *env,
 			       const struct btf_type *t,
 			       u32 meta_left)
@@ -1819,6 +2103,11 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
 	if (t->size != sizeof(int)) {
 		btf_verifier_log_type(env, t, "Expected size:%zu",
 				      sizeof(int));
@@ -1850,7 +2139,7 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
 
 
 		btf_verifier_log(env, "\t%s val=%d\n",
-				 btf_name_by_offset(btf, enums[i].name_off),
+				 __btf_name_by_offset(btf, enums[i].name_off),
 				 enums[i].val);
 	}
 
@@ -1874,7 +2163,8 @@ static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t,
 	for (i = 0; i < nr_enums; i++) {
 		if (v == enums[i].val) {
 			seq_printf(m, "%s",
-				   btf_name_by_offset(btf, enums[i].name_off));
+				   __btf_name_by_offset(btf,
+							enums[i].name_off));
 			return;
 		}
 	}
@@ -1886,6 +2176,7 @@ static struct btf_kind_operations enum_ops = {
 	.check_meta = btf_enum_check_meta,
 	.resolve = btf_df_resolve,
 	.check_member = btf_enum_check_member,
+	.check_kflag_member = btf_enum_check_kflag_member,
 	.log_details = btf_enum_log,
 	.seq_show = btf_enum_seq_show,
 };
@@ -1908,6 +2199,11 @@ static s32 btf_func_proto_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
 	btf_verifier_log_type(env, t, NULL);
 
 	return meta_needed;
@@ -1932,20 +2228,20 @@ static void btf_func_proto_log(struct btf_verifier_env *env,
 	}
 
 	btf_verifier_log(env, "%u %s", args[0].type,
-			 btf_name_by_offset(env->btf,
+			 __btf_name_by_offset(env->btf,
-					    args[0].name_off));
+					      args[0].name_off));
 	for (i = 1; i < nr_args - 1; i++)
 		btf_verifier_log(env, ", %u %s", args[i].type,
-				 btf_name_by_offset(env->btf,
+				 __btf_name_by_offset(env->btf,
-						    args[i].name_off));
+						      args[i].name_off));
 
 	if (nr_args > 1) {
 		const struct btf_param *last_arg = &args[nr_args - 1];
 
 		if (last_arg->type)
 			btf_verifier_log(env, ", %u %s", last_arg->type,
-					 btf_name_by_offset(env->btf,
+					 __btf_name_by_offset(env->btf,
-							    last_arg->name_off));
+							      last_arg->name_off));
 		else
 			btf_verifier_log(env, ", vararg");
 	}
@@ -1967,6 +2263,7 @@ static struct btf_kind_operations func_proto_ops = {
 	 * Hence, there is no btf_func_check_member().
 	 */
 	.check_member = btf_df_check_member,
+	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_func_proto_log,
 	.seq_show = btf_df_seq_show,
 };
@@ -1986,6 +2283,11 @@ static s32 btf_func_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
 	btf_verifier_log_type(env, t, NULL);
 
 	return 0;
@@ -1995,6 +2297,7 @@ static struct btf_kind_operations func_ops = {
 	.check_meta = btf_func_check_meta,
 	.resolve = btf_df_resolve,
 	.check_member = btf_df_check_member,
+	.check_kflag_member = btf_df_check_kflag_member,
 	.log_details = btf_ref_type_log,
 	.seq_show = btf_df_seq_show,
 };

kernel/bpf/cpumap.c

@@ -183,7 +183,7 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
 	 * is not at a fixed memory location, with mixed length
 	 * packets, which is bad for cache-line hotness.
 	 */
-	frame_size = SKB_DATA_ALIGN(xdpf->len) + xdpf->headroom +
+	frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) +
 		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	pkt_data_start = xdpf->data - xdpf->headroom;

kernel/bpf/local_storage.c

@@ -1,11 +1,13 @@
 //SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf-cgroup.h>
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/bug.h>
 #include <linux/filter.h>
 #include <linux/mm.h>
 #include <linux/rbtree.h>
 #include <linux/slab.h>
+#include <uapi/linux/btf.h>
 
 DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
 
@@ -308,6 +310,85 @@ static int cgroup_storage_delete_elem(struct bpf_map *map, void *key)
 	return -EINVAL;
 }
 
+static int cgroup_storage_check_btf(const struct bpf_map *map,
+				    const struct btf *btf,
+				    const struct btf_type *key_type,
+				    const struct btf_type *value_type)
+{
+	struct btf_member *m;
+	u32 offset, size;
+
+	/* Key is expected to be of struct bpf_cgroup_storage_key type,
+	 * which is:
+	 * struct bpf_cgroup_storage_key {
+	 *	__u64	cgroup_inode_id;
+	 *	__u32	attach_type;
+	 * };
+	 */
+
+	/*
+	 * Key_type must be a structure with two fields.
+	 */
+	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ||
+	    BTF_INFO_VLEN(key_type->info) != 2)
+		return -EINVAL;
+
+	/*
+	 * The first field must be a 64 bit integer at 0 offset.
+	 */
+	m = (struct btf_member *)(key_type + 1);
+	size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, cgroup_inode_id);
+	if (!btf_member_is_reg_int(btf, key_type, m, 0, size))
+		return -EINVAL;
+
+	/*
+	 * The second field must be a 32 bit integer at 64 bit offset.
+	 */
+	m++;
+	offset = offsetof(struct bpf_cgroup_storage_key, attach_type);
+	size = FIELD_SIZEOF(struct bpf_cgroup_storage_key, attach_type);
+	if (!btf_member_is_reg_int(btf, key_type, m, offset, size))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *_key,
+					 struct seq_file *m)
+{
+	enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
+	struct bpf_cgroup_storage_key *key = _key;
+	struct bpf_cgroup_storage *storage;
+	int cpu;
+
+	rcu_read_lock();
+	storage = cgroup_storage_lookup(map_to_storage(map), key, false);
+	if (!storage) {
+		rcu_read_unlock();
+		return;
+	}
+
+	btf_type_seq_show(map->btf, map->btf_key_type_id, key, m);
+	stype = cgroup_storage_type(map);
+	if (stype == BPF_CGROUP_STORAGE_SHARED) {
+		seq_puts(m, ": ");
+		btf_type_seq_show(map->btf, map->btf_value_type_id,
+				  &READ_ONCE(storage->buf)->data[0], m);
+		seq_puts(m, "\n");
+	} else {
+		seq_puts(m, ": {\n");
+		for_each_possible_cpu(cpu) {
+			seq_printf(m, "\tcpu%d: ", cpu);
+			btf_type_seq_show(map->btf, map->btf_value_type_id,
+					  per_cpu_ptr(storage->percpu_buf, cpu),
+					  m);
+			seq_puts(m, "\n");
+		}
+		seq_puts(m, "}\n");
+	}
+	rcu_read_unlock();
+}
+
 const struct bpf_map_ops cgroup_storage_map_ops = {
 	.map_alloc = cgroup_storage_map_alloc,
 	.map_free = cgroup_storage_map_free,
@@ -315,7 +396,8 @@ const struct bpf_map_ops cgroup_storage_map_ops = {
 	.map_lookup_elem = cgroup_storage_lookup_elem,
 	.map_update_elem = cgroup_storage_update_elem,
 	.map_delete_elem = cgroup_storage_delete_elem,
-	.map_check_btf = map_check_no_btf,
+	.map_check_btf = cgroup_storage_check_btf,
+	.map_seq_show_elem = cgroup_storage_seq_show_elem,
 };
 
 int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)

kernel/bpf/lpm_trie.c

@@ -728,6 +728,7 @@ free_stack:
 }
 
 static int trie_check_btf(const struct bpf_map *map,
+			  const struct btf *btf,
 			  const struct btf_type *key_type,
 			  const struct btf_type *value_type)
 {

kernel/bpf/syscall.c

@@ -456,6 +456,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
 }
 
 int map_check_no_btf(const struct bpf_map *map,
+		     const struct btf *btf,
 		     const struct btf_type *key_type,
 		     const struct btf_type *value_type)
 {
@@ -478,7 +479,7 @@ static int map_check_btf(const struct bpf_map *map, const struct btf *btf,
 		return -EINVAL;
 
 	if (map->ops->map_check_btf)
-		ret = map->ops->map_check_btf(map, key_type, value_type);
+		ret = map->ops->map_check_btf(map, btf, key_type, value_type);
 
 	return ret;
 }
@@ -1472,11 +1473,6 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 
 	if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS)
 		return -E2BIG;
-
-	if (type == BPF_PROG_TYPE_KPROBE &&
-	    attr->kern_version != LINUX_VERSION_CODE)
-		return -EINVAL;
-
 	if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
 	    type != BPF_PROG_TYPE_CGROUP_SKB &&
 	    !capable(CAP_SYS_ADMIN))
@@ -1608,6 +1604,7 @@ static int bpf_raw_tracepoint_release(struct inode *inode, struct file *filp)
 		bpf_probe_unregister(raw_tp->btp, raw_tp->prog);
 		bpf_prog_put(raw_tp->prog);
 	}
+	bpf_put_raw_tracepoint(raw_tp->btp);
 	kfree(raw_tp);
 	return 0;
 }
@@ -1633,13 +1630,15 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 		return -EFAULT;
 	tp_name[sizeof(tp_name) - 1] = 0;
 
-	btp = bpf_find_raw_tracepoint(tp_name);
+	btp = bpf_get_raw_tracepoint(tp_name);
 	if (!btp)
 		return -ENOENT;
 
 	raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER);
-	if (!raw_tp)
+	if (!raw_tp) {
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto out_put_btp;
+	}
 	raw_tp->btp = btp;
 
 	prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd,
@@ -1667,6 +1666,8 @@ out_put_prog:
 	bpf_prog_put(prog);
 out_free_tp:
 	kfree(raw_tp);
+out_put_btp:
+	bpf_put_raw_tracepoint(btp);
 	return err;
 }
 
@@ -2031,13 +2032,6 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
 			insns[i + 1].imm = 0;
 			continue;
 		}
-
-		if (!bpf_dump_raw_ok() &&
-		    imm == (unsigned long)prog->aux) {
-			insns[i].imm = 0;
-			insns[i + 1].imm = 0;
-			continue;
-		}
 	}
 
 	return insns;
@@ -2271,33 +2265,25 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	ulen = info.nr_func_info;
 	info.nr_func_info = prog->aux->func_info_cnt;
 	if (info.nr_func_info && ulen) {
-		if (bpf_dump_raw_ok()) {
+		char __user *user_finfo;
-			char __user *user_finfo;
 
-			user_finfo = u64_to_user_ptr(info.func_info);
+		user_finfo = u64_to_user_ptr(info.func_info);
-			ulen = min_t(u32, info.nr_func_info, ulen);
+		ulen = min_t(u32, info.nr_func_info, ulen);
-			if (copy_to_user(user_finfo, prog->aux->func_info,
+		if (copy_to_user(user_finfo, prog->aux->func_info,
-					 info.func_info_rec_size * ulen))
+				 info.func_info_rec_size * ulen))
-				return -EFAULT;
+			return -EFAULT;
-		} else {
-			info.func_info = 0;
-		}
 	}
 
 	ulen = info.nr_line_info;
 	info.nr_line_info = prog->aux->nr_linfo;
 	if (info.nr_line_info && ulen) {
-		if (bpf_dump_raw_ok()) {
+		__u8 __user *user_linfo;
-			__u8 __user *user_linfo;
 
-			user_linfo = u64_to_user_ptr(info.line_info);
+		user_linfo = u64_to_user_ptr(info.line_info);
-			ulen = min_t(u32, info.nr_line_info, ulen);
+		ulen = min_t(u32, info.nr_line_info, ulen);
-			if (copy_to_user(user_linfo, prog->aux->linfo,
+		if (copy_to_user(user_linfo, prog->aux->linfo,
-					 info.line_info_rec_size * ulen))
+				 info.line_info_rec_size * ulen))
-				return -EFAULT;
+			return -EFAULT;
-		} else {
-			info.line_info = 0;
-		}
 	}
 
 	ulen = info.nr_jited_line_info;
@@ -2322,6 +2308,28 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		}
 	}
 
+	ulen = info.nr_prog_tags;
+	info.nr_prog_tags = prog->aux->func_cnt ? : 1;
+	if (ulen) {
+		__u8 __user (*user_prog_tags)[BPF_TAG_SIZE];
+		u32 i;
+
+		user_prog_tags = u64_to_user_ptr(info.prog_tags);
+		ulen = min_t(u32, info.nr_prog_tags, ulen);
+		if (prog->aux->func_cnt) {
+			for (i = 0; i < ulen; i++) {
+				if (copy_to_user(user_prog_tags[i],
+						 prog->aux->func[i]->tag,
+						 BPF_TAG_SIZE))
+					return -EFAULT;
+			}
+		} else {
+			if (copy_to_user(user_prog_tags[0],
+					 prog->tag, BPF_TAG_SIZE))
+				return -EFAULT;
+		}
+	}
+
 done:
 	if (copy_to_user(uinfo, &info, info_len) ||
 	    put_user(info_len, &uattr->info.info_len))

kernel/bpf/verifier.c

@@ -26,6 +26,7 @@
 #include <linux/bsearch.h>
 #include <linux/sort.h>
 #include <linux/perf_event.h>
+#include <linux/ctype.h>
 
 #include "disasm.h"
 
@@ -216,6 +217,27 @@ struct bpf_call_arg_meta {
 
 static DEFINE_MUTEX(bpf_verifier_lock);
 
+static const struct bpf_line_info *
+find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
+{
+	const struct bpf_line_info *linfo;
+	const struct bpf_prog *prog;
+	u32 i, nr_linfo;
+
+	prog = env->prog;
+	nr_linfo = prog->aux->nr_linfo;
+
+	if (!nr_linfo || insn_off >= prog->len)
+		return NULL;
+
+	linfo = prog->aux->linfo;
+	for (i = 1; i < nr_linfo; i++)
+		if (insn_off < linfo[i].insn_off)
+			break;
+
+	return &linfo[i - 1];
+}
+
 void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
 		       va_list args)
 {
@@ -266,6 +288,42 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
 	va_end(args);
 }
 
+static const char *ltrim(const char *s)
+{
+	while (isspace(*s))
+		s++;
+
+	return s;
+}
+
+__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env,
+					 u32 insn_off,
+					 const char *prefix_fmt, ...)
+{
+	const struct bpf_line_info *linfo;
+
+	if (!bpf_verifier_log_needed(&env->log))
+		return;
+
+	linfo = find_linfo(env, insn_off);
+	if (!linfo || linfo == env->prev_linfo)
+		return;
+
+	if (prefix_fmt) {
+		va_list args;
+
+		va_start(args, prefix_fmt);
+		bpf_verifier_vlog(&env->log, prefix_fmt, args);
+		va_end(args);
+	}
+
+	verbose(env, "%s\n",
+		ltrim(btf_name_by_offset(env->prog->aux->btf,
+					 linfo->line_off)));
+
+	env->prev_linfo = linfo;
+}
+
 static bool type_is_pkt_pointer(enum bpf_reg_type type)
 {
 	return type == PTR_TO_PACKET ||
@@ -339,12 +397,14 @@ static char slot_type_char[] = {
 static void print_liveness(struct bpf_verifier_env *env,
 			   enum bpf_reg_liveness live)
 {
-	if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN))
+	if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE))
 	    verbose(env, "_");
 	if (live & REG_LIVE_READ)
 		verbose(env, "r");
 	if (live & REG_LIVE_WRITTEN)
 		verbose(env, "w");
+	if (live & REG_LIVE_DONE)
+		verbose(env, "D");
 }
 
 static struct bpf_func_state *func(struct bpf_verifier_env *env,
@@ -1074,6 +1134,12 @@ static int mark_reg_read(struct bpf_verifier_env *env,
 		/* if read wasn't screened by an earlier write ... */
 		if (writes && state->live & REG_LIVE_WRITTEN)
 			break;
+		if (parent->live & REG_LIVE_DONE) {
+			verbose(env, "verifier BUG type %s var_off %lld off %d\n",
+				reg_type_str[parent->type],
+				parent->var_off.value, parent->off);
+			return -EFAULT;
+		}
 		/* ... then we depend on parent's value */
 		parent->live |= REG_LIVE_READ;
 		state = parent;
@@ -1220,6 +1286,10 @@ static int check_stack_write(struct bpf_verifier_env *env,
 
 		/* regular write of data into stack destroys any spilled ptr */
 		state->stack[spi].spilled_ptr.type = NOT_INIT;
+		/* Mark slots as STACK_MISC if they belonged to spilled ptr. */
+		if (state->stack[spi].slot_type[0] == STACK_SPILL)
+			for (i = 0; i < BPF_REG_SIZE; i++)
+				state->stack[spi].slot_type[i] = STACK_MISC;
 
 		/* only mark the slot as written if all 8 bytes were written
 		 * otherwise read propagation may incorrectly stop too soon
@@ -1237,6 +1307,7 @@ static int check_stack_write(struct bpf_verifier_env *env,
 		    register_is_null(&cur->regs[value_regno]))
 			type = STACK_ZERO;
 
+		/* Mark slots affected by this stack write. */
 		for (i = 0; i < size; i++)
 			state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
 				type;
@@ -3788,6 +3859,12 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
 		if (tnum_is_const(reg->var_off))
 			return !tnum_equals_const(reg->var_off, val);
 		break;
+	case BPF_JSET:
+		if ((~reg->var_off.mask & reg->var_off.value) & val)
+			return 1;
+		if (!((reg->var_off.mask | reg->var_off.value) & val))
+			return 0;
+		break;
 	case BPF_JGT:
 		if (reg->umin_value > val)
 			return 1;
@@ -3872,6 +3949,13 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
 		 */
 		__mark_reg_known(false_reg, val);
 		break;
+	case BPF_JSET:
+		false_reg->var_off = tnum_and(false_reg->var_off,
+					      tnum_const(~val));
+		if (is_power_of_2(val))
+			true_reg->var_off = tnum_or(true_reg->var_off,
+						    tnum_const(val));
+		break;
 	case BPF_JGT:
 		false_reg->umax_value = min(false_reg->umax_value, val);
 		true_reg->umin_value = max(true_reg->umin_value, val + 1);
@@ -3944,6 +4028,13 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
 		 */
 		__mark_reg_known(false_reg, val);
 		break;
+	case BPF_JSET:
+		false_reg->var_off = tnum_and(false_reg->var_off,
+					      tnum_const(~val));
+		if (is_power_of_2(val))
+			true_reg->var_off = tnum_or(true_reg->var_off,
+						    tnum_const(val));
+		break;
 	case BPF_JGT:
 		true_reg->umax_value = min(true_reg->umax_value, val - 1);
 		false_reg->umin_value = max(false_reg->umin_value, val);
@@ -4561,6 +4652,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
 		return 0;
 
 	if (w < 0 || w >= env->prog->len) {
+		verbose_linfo(env, t, "%d: ", t);
 		verbose(env, "jump out of range from insn %d to %d\n", t, w);
 		return -EINVAL;
 	}
@@ -4578,6 +4670,8 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
 		insn_stack[cur_stack++] = w;
 		return 1;
 	} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
+		verbose_linfo(env, t, "%d: ", t);
+		verbose_linfo(env, w, "%d: ", w);
 		verbose(env, "back-edge from insn %d to %d\n", t, w);
 		return -EINVAL;
 	} else if (insn_state[w] == EXPLORED) {
@@ -4600,10 +4694,6 @@ static int check_cfg(struct bpf_verifier_env *env)
 	int ret = 0;
 	int i, t;
 
-	ret = check_subprogs(env);
-	if (ret < 0)
-		return ret;
-
 	insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
 	if (!insn_state)
 		return -ENOMEM;
@@ -4910,8 +5000,16 @@ static int check_btf_line(struct bpf_verifier_env *env,
 			goto err_free;
 		}
 
-		if (!btf_name_offset_valid(btf, linfo[i].line_off) ||
+		if (!prog->insnsi[linfo[i].insn_off].code) {
-		    !btf_name_offset_valid(btf, linfo[i].file_name_off)) {
+			verbose(env,
+				"Invalid insn code at line_info[%u].insn_off\n",
+				i);
+			err = -EINVAL;
+			goto err_free;
+		}
+
+		if (!btf_name_by_offset(btf, linfo[i].line_off) ||
+		    !btf_name_by_offset(btf, linfo[i].file_name_off)) {
 			verbose(env, "Invalid line_info[%u].line_off or .file_name_off\n", i);
 			err = -EINVAL;
 			goto err_free;
@@ -5021,6 +5119,102 @@ static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap)
 	return false;
 }
 
+static void clean_func_state(struct bpf_verifier_env *env,
+			     struct bpf_func_state *st)
+{
+	enum bpf_reg_liveness live;
+	int i, j;
+
+	for (i = 0; i < BPF_REG_FP; i++) {
+		live = st->regs[i].live;
+		/* liveness must not touch this register anymore */
+		st->regs[i].live |= REG_LIVE_DONE;
+		if (!(live & REG_LIVE_READ))
+			/* since the register is unused, clear its state
+			 * to make further comparison simpler
+			 */
+			__mark_reg_not_init(&st->regs[i]);
+	}
+
+	for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) {
+		live = st->stack[i].spilled_ptr.live;
+		/* liveness must not touch this stack slot anymore */
+		st->stack[i].spilled_ptr.live |= REG_LIVE_DONE;
+		if (!(live & REG_LIVE_READ)) {
+			__mark_reg_not_init(&st->stack[i].spilled_ptr);
+			for (j = 0; j < BPF_REG_SIZE; j++)
+				st->stack[i].slot_type[j] = STACK_INVALID;
+		}
+	}
+}
+
+static void clean_verifier_state(struct bpf_verifier_env *env,
+				 struct bpf_verifier_state *st)
+{
+	int i;
+
+	if (st->frame[0]->regs[0].live & REG_LIVE_DONE)
+		/* all regs in this state in all frames were already marked */
+		return;
+
+	for (i = 0; i <= st->curframe; i++)
+		clean_func_state(env, st->frame[i]);
+}
+
+/* the parentage chains form a tree.
+ * the verifier states are added to state lists at given insn and
+ * pushed into state stack for future exploration.
+ * when the verifier reaches bpf_exit insn some of the verifer states
+ * stored in the state lists have their final liveness state already,
+ * but a lot of states will get revised from liveness point of view when
+ * the verifier explores other branches.
+ * Example:
+ * 1: r0 = 1
+ * 2: if r1 == 100 goto pc+1
+ * 3: r0 = 2
+ * 4: exit
+ * when the verifier reaches exit insn the register r0 in the state list of
+ * insn 2 will be seen as !REG_LIVE_READ. Then the verifier pops the other_branch
+ * of insn 2 and goes exploring further. At the insn 4 it will walk the
+ * parentage chain from insn 4 into insn 2 and will mark r0 as REG_LIVE_READ.
+ *
+ * Since the verifier pushes the branch states as it sees them while exploring
+ * the program the condition of walking the branch instruction for the second
+ * time means that all states below this branch were already explored and
+ * their final liveness markes are already propagated.
+ * Hence when the verifier completes the search of state list in is_state_visited()
+ * we can call this clean_live_states() function to mark all liveness states
+ * as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state'
+ * will not be used.
+ * This function also clears the registers and stack for states that !READ
+ * to simplify state merging.
+ *
+ * Important note here that walking the same branch instruction in the callee
+ * doesn't meant that the states are DONE. The verifier has to compare
+ * the callsites
+ */
+static void clean_live_states(struct bpf_verifier_env *env, int insn,
+			      struct bpf_verifier_state *cur)
+{
+	struct bpf_verifier_state_list *sl;
+	int i;
+
+	sl = env->explored_states[insn];
+	if (!sl)
+		return;
+
+	while (sl != STATE_LIST_MARK) {
+		if (sl->state.curframe != cur->curframe)
+			goto next;
+		for (i = 0; i <= cur->curframe; i++)
+			if (sl->state.frame[i]->callsite != cur->frame[i]->callsite)
+				goto next;
+		clean_verifier_state(env, &sl->state);
+next:
+		sl = sl->next;
+	}
+}
+
 /* Returns true if (rold safe implies rcur safe) */
 static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
 		    struct idpair *idmap)
@@ -5134,12 +5328,6 @@ static bool stacksafe(struct bpf_func_state *old,
 {
 	int i, spi;
 
-	/* if explored stack has more populated slots than current stack
-	 * such stacks are not equivalent
-	 */
-	if (old->allocated_stack > cur->allocated_stack)
-		return false;
-
 	/* walk slots of the explored stack and ignore any additional
 	 * slots in the current stack, since explored(safe) state
 	 * didn't use them
@@ -5147,12 +5335,21 @@ static bool stacksafe(struct bpf_func_state *old,
 	for (i = 0; i < old->allocated_stack; i++) {
 		spi = i / BPF_REG_SIZE;
 
-		if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ))
+		if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) {
+			i += BPF_REG_SIZE - 1;
 			/* explored state didn't use this */
 			continue;
+		}
 
 		if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
 			continue;
+
+		/* explored stack has more populated slots than current stack
+		 * and these slots were used
+		 */
+		if (i >= cur->allocated_stack)
+			return false;
+
 		/* if old state was safe with misc data in the stack
 		 * it will be safe with zero-initialized stack.
 		 * The opposite is not true
@@ -5336,6 +5533,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 		 */
 		return 0;
 
+	clean_live_states(env, insn_idx, cur);
+
 	while (sl != STATE_LIST_MARK) {
 		if (states_equal(env, &sl->state, cur)) {
 			/* reached equivalent register/stack state,
@@ -5455,6 +5654,8 @@ static int do_check(struct bpf_verifier_env *env)
 	int insn_processed = 0;
 	bool do_print_state = false;
 
+	env->prev_linfo = NULL;
+
 	state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
 	if (!state)
 		return -ENOMEM;
@@ -5528,6 +5729,7 @@ static int do_check(struct bpf_verifier_env *env)
 				.private_data	= env,
 			};
 
+			verbose_linfo(env, insn_idx, "; ");
 			verbose(env, "%d: ", insn_idx);
 			print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
 		}
@@ -6762,7 +6964,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 
 	env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
 
-	ret = check_cfg(env);
+	ret = check_subprogs(env);
 	if (ret < 0)
 		goto skip_full_check;
 
@@ -6770,6 +6972,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	if (ret < 0)
 		goto skip_full_check;
 
+	ret = check_cfg(env);
+	if (ret < 0)
+		goto skip_full_check;
+
 	ret = do_check(env);
 	if (env->cur_state) {
 		free_verifier_state(env->cur_state, true);
@@ -6783,12 +6989,13 @@ skip_full_check:
 	while (!pop_stack(env, NULL, NULL));
 	free_states(env);
 
-	if (ret == 0)
-		sanitize_dead_code(env);
-
 	if (ret == 0)
 		ret = check_max_stack_depth(env);
 
+	/* instruction rewrites happen after this point */
+	if (ret == 0)
+		sanitize_dead_code(env);
+
 	if (ret == 0)
 		/* program is valid, convert *(u32*)(ctx + off) accesses */
 		ret = convert_ctx_accesses(env);

kernel/module.c

@@ -3093,6 +3093,11 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 					     sizeof(*mod->tracepoints_ptrs),
 					     &mod->num_tracepoints);
 #endif
+#ifdef CONFIG_BPF_EVENTS
+	mod->bpf_raw_events = section_objs(info, "__bpf_raw_tp_map",
+					   sizeof(*mod->bpf_raw_events),
+					   &mod->num_bpf_raw_events);
+#endif
 #ifdef HAVE_JUMP_LABEL
 	mod->jump_entries = section_objs(info, "__jump_table",
 					sizeof(*mod->jump_entries),

kernel/trace/bpf_trace.c

@@ -17,6 +17,43 @@
 #include "trace_probe.h"
 #include "trace.h"
 
+#ifdef CONFIG_MODULES
+struct bpf_trace_module {
+	struct module *module;
+	struct list_head list;
+};
+
+static LIST_HEAD(bpf_trace_modules);
+static DEFINE_MUTEX(bpf_module_mutex);
+
+static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name)
+{
+	struct bpf_raw_event_map *btp, *ret = NULL;
+	struct bpf_trace_module *btm;
+	unsigned int i;
+
+	mutex_lock(&bpf_module_mutex);
+	list_for_each_entry(btm, &bpf_trace_modules, list) {
+		for (i = 0; i < btm->module->num_bpf_raw_events; ++i) {
+			btp = &btm->module->bpf_raw_events[i];
+			if (!strcmp(btp->tp->name, name)) {
+				if (try_module_get(btm->module))
+					ret = btp;
+				goto out;
+			}
+		}
+	}
+out:
+	mutex_unlock(&bpf_module_mutex);
+	return ret;
+}
+#else
+static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name)
+{
+	return NULL;
+}
+#endif /* CONFIG_MODULES */
+
 u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 
@@ -1076,7 +1113,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
 extern struct bpf_raw_event_map __start__bpf_raw_tp[];
 extern struct bpf_raw_event_map __stop__bpf_raw_tp[];
 
-struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
+struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name)
 {
 	struct bpf_raw_event_map *btp = __start__bpf_raw_tp;
 
@@ -1084,7 +1121,16 @@ struct bpf_raw_event_map *bpf_find_raw_tracepoint(const char *name)
 		if (!strcmp(btp->tp->name, name))
 			return btp;
 	}
-	return NULL;
+
+	return bpf_get_raw_tracepoint_module(name);
+}
+
+void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp)
+{
+	struct module *mod = __module_address((unsigned long)btp);
+
+	if (mod)
+		module_put(mod);
 }
 
 static __always_inline
@@ -1222,3 +1268,52 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 
 	return err;
 }
+
+#ifdef CONFIG_MODULES
+int bpf_event_notify(struct notifier_block *nb, unsigned long op, void *module)
+{
+	struct bpf_trace_module *btm, *tmp;
+	struct module *mod = module;
+
+	if (mod->num_bpf_raw_events == 0 ||
+	    (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING))
+		return 0;
+
+	mutex_lock(&bpf_module_mutex);
+
+	switch (op) {
+	case MODULE_STATE_COMING:
+		btm = kzalloc(sizeof(*btm), GFP_KERNEL);
+		if (btm) {
+			btm->module = module;
+			list_add(&btm->list, &bpf_trace_modules);
+		}
+		break;
+	case MODULE_STATE_GOING:
+		list_for_each_entry_safe(btm, tmp, &bpf_trace_modules, list) {
+			if (btm->module == module) {
+				list_del(&btm->list);
+				kfree(btm);
+				break;
+			}
+		}
+		break;
+	}
+
+	mutex_unlock(&bpf_module_mutex);
+
+	return 0;
+}
+
+static struct notifier_block bpf_module_nb = {
+	.notifier_call = bpf_event_notify,
+};
+
+int __init bpf_event_init(void)
+{
+	register_module_notifier(&bpf_module_nb);
+	return 0;
+}
+
+fs_initcall(bpf_event_init);
+#endif /* CONFIG_MODULES */

net/core/filter.c

@@ -6313,6 +6313,9 @@ static bool sk_msg_is_valid_access(int off, int size,
 	if (type == BPF_WRITE)
 		return false;
 
+	if (off % size != 0)
+		return false;
+
 	switch (off) {
 	case offsetof(struct sk_msg_md, data):
 		info->reg_type = PTR_TO_PACKET;
@@ -6324,16 +6327,20 @@ static bool sk_msg_is_valid_access(int off, int size,
 		if (size != sizeof(__u64))
 			return false;
 		break;
-	default:
+	case bpf_ctx_range(struct sk_msg_md, family):
+	case bpf_ctx_range(struct sk_msg_md, remote_ip4):
+	case bpf_ctx_range(struct sk_msg_md, local_ip4):
+	case bpf_ctx_range_till(struct sk_msg_md, remote_ip6[0], remote_ip6[3]):
+	case bpf_ctx_range_till(struct sk_msg_md, local_ip6[0], local_ip6[3]):
+	case bpf_ctx_range(struct sk_msg_md, remote_port):
+	case bpf_ctx_range(struct sk_msg_md, local_port):
+	case bpf_ctx_range(struct sk_msg_md, size):
 		if (size != sizeof(__u32))
 			return false;
+		break;
+	default:
+		return false;
 	}
-
-	if (off < 0 || off >= sizeof(struct sk_msg_md))
-		return false;
-	if (off % size != 0)
-		return false;
-
 	return true;
 }
 
@@ -7418,6 +7425,9 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type,
 	int off;
 #endif
 
+	/* convert ctx uses the fact sg element is first in struct */
+	BUILD_BUG_ON(offsetof(struct sk_msg, sg) != 0);
+
 	switch (si->off) {
 	case offsetof(struct sk_msg_md, data):
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data),
@@ -7530,6 +7540,12 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type,
 		*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg,
 				      offsetof(struct sock_common, skc_num));
 		break;
+
+	case offsetof(struct sk_msg_md, size):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_sg, size),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct sk_msg_sg, size));
+		break;
 	}
 
 	return insn - insn_buf;

net/core/skmsg.c

@@ -403,7 +403,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
 	msg->skb = skb;
 
 	sk_psock_queue_msg(psock, msg);
-	sk->sk_data_ready(sk);
+	sk_psock_data_ready(sk, psock);
 	return copied;
 }
 
@@ -572,6 +572,7 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 {
 	rcu_assign_sk_user_data(sk, NULL);
 	sk_psock_cork_free(psock);
+	sk_psock_zap_ingress(psock);
 	sk_psock_restore_proto(sk, psock);
 
 	write_lock_bh(&sk->sk_callback_lock);
@@ -669,6 +670,22 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
 	bool ingress;
 
 	switch (verdict) {
+	case __SK_PASS:
+		sk_other = psock->sk;
+		if (sock_flag(sk_other, SOCK_DEAD) ||
+		    !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
+			goto out_free;
+		}
+		if (atomic_read(&sk_other->sk_rmem_alloc) <=
+		    sk_other->sk_rcvbuf) {
+			struct tcp_skb_cb *tcp = TCP_SKB_CB(skb);
+
+			tcp->bpf.flags |= BPF_F_INGRESS;
+			skb_queue_tail(&psock->ingress_skb, skb);
+			schedule_work(&psock->work);
+			break;
+		}
+		goto out_free;
 	case __SK_REDIRECT:
 		sk_other = tcp_skb_bpf_redirect_fetch(skb);
 		if (unlikely(!sk_other))
@@ -735,7 +752,7 @@ static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb)
 }
 
 /* Called with socket lock held. */
-static void sk_psock_data_ready(struct sock *sk)
+static void sk_psock_strp_data_ready(struct sock *sk)
 {
 	struct sk_psock *psock;
 
@@ -783,7 +800,7 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
 		return;
 
 	parser->saved_data_ready = sk->sk_data_ready;
-	sk->sk_data_ready = sk_psock_data_ready;
+	sk->sk_data_ready = sk_psock_strp_data_ready;
 	sk->sk_write_space = sk_psock_write_space;
 	parser->enabled = true;
 }

net/ipv4/tcp_bpf.c

@@ -8,6 +8,7 @@
 #include <linux/wait.h>
 
 #include <net/inet_common.h>
+#include <net/tls.h>
 
 static bool tcp_bpf_stream_read(const struct sock *sk)
 {
@@ -198,7 +199,7 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
 		msg->sg.start = i;
 		msg->sg.size -= apply_bytes;
 		sk_psock_queue_msg(psock, tmp);
-		sk->sk_data_ready(sk);
+		sk_psock_data_ready(sk, psock);
 	} else {
 		sk_msg_free(sk, tmp);
 		kfree(tmp);
@@ -218,6 +219,8 @@ static int tcp_bpf_push(struct sock *sk, struct sk_msg *msg, u32 apply_bytes,
 	u32 off;
 
 	while (1) {
+		bool has_tx_ulp;
+
 		sge = sk_msg_elem(msg, msg->sg.start);
 		size = (apply && apply_bytes < sge->length) ?
 			apply_bytes : sge->length;
@@ -226,7 +229,15 @@ static int tcp_bpf_push(struct sock *sk, struct sk_msg *msg, u32 apply_bytes,
 
 		tcp_rate_check_app_limited(sk);
 retry:
-		ret = do_tcp_sendpages(sk, page, off, size, flags);
+		has_tx_ulp = tls_sw_has_ctx_tx(sk);
+		if (has_tx_ulp) {
+			flags |= MSG_SENDPAGE_NOPOLICY;
+			ret = kernel_sendpage_locked(sk,
+						     page, off, size, flags);
+		} else {
+			ret = do_tcp_sendpages(sk, page, off, size, flags);
+		}
+
 		if (ret <= 0)
 			return ret;
 		if (apply)

net/tls/tls_main.c

@@ -55,6 +55,8 @@ enum {
 
 static struct proto *saved_tcpv6_prot;
 static DEFINE_MUTEX(tcpv6_prot_mutex);
+static struct proto *saved_tcpv4_prot;
+static DEFINE_MUTEX(tcpv4_prot_mutex);
 static LIST_HEAD(device_list);
 static DEFINE_SPINLOCK(device_spinlock);
 static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG];
@@ -700,6 +702,16 @@ static int tls_init(struct sock *sk)
 		mutex_unlock(&tcpv6_prot_mutex);
 	}
 
+	if (ip_ver == TLSV4 &&
+	    unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv4_prot))) {
+		mutex_lock(&tcpv4_prot_mutex);
+		if (likely(sk->sk_prot != saved_tcpv4_prot)) {
+			build_protos(tls_prots[TLSV4], sk->sk_prot);
+			smp_store_release(&saved_tcpv4_prot, sk->sk_prot);
+		}
+		mutex_unlock(&tcpv4_prot_mutex);
+	}
+
 	ctx->tx_conf = TLS_BASE;
 	ctx->rx_conf = TLS_BASE;
 	update_sk_prot(sk, ctx);
@@ -731,8 +743,6 @@ static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = {
 
 static int __init tls_register(void)
 {
-	build_protos(tls_prots[TLSV4], &tcp_prot);
-
 	tls_sw_proto_ops = inet_stream_ops;
 	tls_sw_proto_ops.splice_read = tls_sw_splice_read;
 

net/tls/tls_sw.c

@@ -686,12 +686,13 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
 	struct sk_psock *psock;
 	struct sock *sk_redir;
 	struct tls_rec *rec;
+	bool enospc, policy;
 	int err = 0, send;
 	u32 delta = 0;
-	bool enospc;
 
+	policy = !(flags & MSG_SENDPAGE_NOPOLICY);
 	psock = sk_psock_get(sk);
-	if (!psock)
+	if (!psock || !policy)
 		return tls_push_record(sk, flags, record_type);
 more_data:
 	enospc = sk_msg_full(msg);
@@ -1017,8 +1018,8 @@ send_end:
 	return copied ? copied : ret;
 }
 
-int tls_sw_sendpage(struct sock *sk, struct page *page,
+int tls_sw_do_sendpage(struct sock *sk, struct page *page,
-		    int offset, size_t size, int flags)
+		       int offset, size_t size, int flags)
 {
 	long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
@@ -1033,15 +1034,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 	int ret = 0;
 	bool eor;
 
-	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
-		      MSG_SENDPAGE_NOTLAST))
-		return -ENOTSUPP;
-
-	/* No MSG_EOR from splice, only look at MSG_MORE */
 	eor = !(flags & (MSG_MORE | MSG_SENDPAGE_NOTLAST));
-
-	lock_sock(sk);
-
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	/* Wait till there is any pending write on socket */
@@ -1145,10 +1138,34 @@ wait_for_memory:
 	}
 sendpage_end:
 	ret = sk_stream_error(sk, flags, ret);
-	release_sock(sk);
 	return copied ? copied : ret;
 }
 
+int tls_sw_sendpage_locked(struct sock *sk, struct page *page,
+			   int offset, size_t size, int flags)
+{
+	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
+		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
+		return -ENOTSUPP;
+
+	return tls_sw_do_sendpage(sk, page, offset, size, flags);
+}
+
+int tls_sw_sendpage(struct sock *sk, struct page *page,
+		    int offset, size_t size, int flags)
+{
+	int ret;
+
+	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
+		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
+		return -ENOTSUPP;
+
+	lock_sock(sk);
+	ret = tls_sw_do_sendpage(sk, page, offset, size, flags);
+	release_sock(sk);
+	return ret;
+}
+
 static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock,
 				     int flags, long timeo, int *err)
 {

net/xdp/xsk.c

@@ -366,6 +366,7 @@ static int xsk_release(struct socket *sock)
 
 	xskq_destroy(xs->rx);
 	xskq_destroy(xs->tx);
+	xdp_put_umem(xs->umem);
 
 	sock_orphan(sk);
 	sock->sk = NULL;
@@ -713,18 +714,6 @@ static const struct proto_ops xsk_proto_ops = {
 	.sendpage	= sock_no_sendpage,
 };
 
-static void xsk_destruct(struct sock *sk)
-{
-	struct xdp_sock *xs = xdp_sk(sk);
-
-	if (!sock_flag(sk, SOCK_DEAD))
-		return;
-
-	xdp_put_umem(xs->umem);
-
-	sk_refcnt_debug_dec(sk);
-}
-
 static int xsk_create(struct net *net, struct socket *sock, int protocol,
 		      int kern)
 {
@@ -751,9 +740,6 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 
 	sk->sk_family = PF_XDP;
 
-	sk->sk_destruct = xsk_destruct;
-	sk_refcnt_debug_inc(sk);
-
 	sock_set_flag(sk, SOCK_RCU_FREE);
 
 	xs = xdp_sk(sk);

tools/bpf/bpftool/Documentation/bpftool-map.rst

@@ -128,6 +128,10 @@ OPTIONS
 	-f, --bpffs
 		  Show file names of pinned maps.
 
+	-n, --nomount
+		  Do not automatically attempt to mount any virtual file system
+		  (such as tracefs or BPF virtual file system) when necessary.
+
 EXAMPLES
 ========
 **# bpftool map show**
@@ -170,6 +174,61 @@ The following three commands are equivalent:
 | **# bpftool map pin id 10 /sys/fs/bpf/map**
 | **# bpftool map del pinned /sys/fs/bpf/map key 13 00 07 00**
 
+Note that map update can also be used in order to change the program references
+hold by a program array map. This can be used, for example, to change the
+programs used for tail-call jumps at runtime, without having to reload the
+entry-point program. Below is an example for this use case: we load a program
+defining a prog array map, and with a main function that contains a tail call
+to other programs that can be used either to "process" packets or to "debug"
+processing. Note that the prog array map MUST be pinned into the BPF virtual
+file system for the map update to work successfully, as kernel flushes prog
+array maps when they have no more references from user space (and the update
+would be lost as soon as bpftool exits).
+
+|
+| **# bpftool prog loadall tail_calls.o /sys/fs/bpf/foo type xdp**
+| **# bpftool prog --bpffs**
+
+::
+
+  545: xdp  name main_func  tag 674b4b5597193dc3  gpl
+          loaded_at 2018-12-12T15:02:58+0000  uid 0
+          xlated 240B  jited 257B  memlock 4096B  map_ids 294
+          pinned /sys/fs/bpf/foo/xdp
+  546: xdp  name bpf_func_process  tag e369a529024751fc  gpl
+          loaded_at 2018-12-12T15:02:58+0000  uid 0
+          xlated 200B  jited 164B  memlock 4096B
+          pinned /sys/fs/bpf/foo/process
+  547: xdp  name bpf_func_debug  tag 0b597868bc7f0976  gpl
+          loaded_at 2018-12-12T15:02:58+0000  uid 0
+          xlated 200B  jited 164B  memlock 4096B
+          pinned /sys/fs/bpf/foo/debug
+
+**# bpftool map**
+
+::
+
+  294: prog_array  name jmp_table  flags 0x0
+          key 4B  value 4B  max_entries 1  memlock 4096B
+          owner_prog_type xdp  owner jited
+
+|
+| **# bpftool map pin id 294 /sys/fs/bpf/bar**
+| **# bpftool map dump pinned /sys/fs/bpf/bar**
+
+::
+
+  Found 0 elements
+
+|
+| **# bpftool map update pinned /sys/fs/bpf/bar key 0 0 0 0 value pinned /sys/fs/bpf/foo/debug**
+| **# bpftool map dump pinned /sys/fs/bpf/bar**
+
+::
+
+  key: 00 00 00 00  value: 22 02 00 00
+  Found 1 element
+
 SEE ALSO
 ========
 	**bpf**\ (2),

tools/bpf/bpftool/Documentation/bpftool-prog.rst

@@ -158,83 +158,98 @@ OPTIONS
 		  When showing BPF programs, show file names of pinned
 		  programs.
 
+	-m, --mapcompat
+		  Allow loading maps with unknown map definitions.
+
+	-n, --nomount
+		  Do not automatically attempt to mount any virtual file system
+		  (such as tracefs or BPF virtual file system) when necessary.
+
 EXAMPLES
 ========
 **# bpftool prog show**
+
 ::
 
-  10: xdp  name some_prog  tag 005a3d2123620c8b  gpl
+    10: xdp  name some_prog  tag 005a3d2123620c8b  gpl
-	loaded_at Sep 29/20:11  uid 0
+            loaded_at 2017-09-29T20:11:00+0000  uid 0
-	xlated 528B  jited 370B  memlock 4096B  map_ids 10
+            xlated 528B  jited 370B  memlock 4096B  map_ids 10
 
 **# bpftool --json --pretty prog show**
 
 ::
 
-    {
+    [{
-        "programs": [{
+            "id": 10,
-                "id": 10,
+            "type": "xdp",
-                "type": "xdp",
+            "tag": "005a3d2123620c8b",
-                "tag": "005a3d2123620c8b",
+            "gpl_compatible": true,
-                "gpl_compatible": true,
+            "loaded_at": 1506715860,
-                "loaded_at": "Sep 29/20:11",
+            "uid": 0,
-                "uid": 0,
+            "bytes_xlated": 528,
-                "bytes_xlated": 528,
+            "jited": true,
-                "jited": true,
+            "bytes_jited": 370,
-                "bytes_jited": 370,
+            "bytes_memlock": 4096,
-                "bytes_memlock": 4096,
+            "map_ids": [10
-                "map_ids": [10
+            ]
-                ]
+        }
-            }
+    ]
-        ]
-    }
 
 |
 | **# bpftool prog dump xlated id 10 file /tmp/t**
 | **# ls -l /tmp/t**
-|   -rw------- 1 root root 560 Jul 22 01:42 /tmp/t
-
-**# bpftool prog dum jited tag 005a3d2123620c8b**
 
 ::
 
-    push   %rbp
+    -rw------- 1 root root 560 Jul 22 01:42 /tmp/t
-    mov    %rsp,%rbp
+
-    sub    $0x228,%rsp
+**# bpftool prog dump jited tag 005a3d2123620c8b**
-    sub    $0x28,%rbp
+
-    mov    %rbx,0x0(%rbp)
+::
+
+    0:   push   %rbp
+    1:   mov    %rsp,%rbp
+    2:   sub    $0x228,%rsp
+    3:   sub    $0x28,%rbp
+    4:   mov    %rbx,0x0(%rbp)
 
 |
 | **# mount -t bpf none /sys/fs/bpf/**
 | **# bpftool prog pin id 10 /sys/fs/bpf/prog**
 | **# bpftool prog load ./my_prog.o /sys/fs/bpf/prog2**
 | **# ls -l /sys/fs/bpf/**
-|   -rw------- 1 root root 0 Jul 22 01:43 prog
-|   -rw------- 1 root root 0 Jul 22 01:44 prog2
-
-**# bpftool prog dum jited pinned /sys/fs/bpf/prog opcodes**
 
 ::
 
-    push   %rbp
+    -rw------- 1 root root 0 Jul 22 01:43 prog
-    55
+    -rw------- 1 root root 0 Jul 22 01:44 prog2
-    mov    %rsp,%rbp
+
-    48 89 e5
+**# bpftool prog dump jited pinned /sys/fs/bpf/prog opcodes**
-    sub    $0x228,%rsp
+
-    48 81 ec 28 02 00 00
+::
-    sub    $0x28,%rbp
+
-    48 83 ed 28
+   0:   push   %rbp
-    mov    %rbx,0x0(%rbp)
+        55
-    48 89 5d 00
+   1:   mov    %rsp,%rbp
+        48 89 e5
+   4:   sub    $0x228,%rsp
+        48 81 ec 28 02 00 00
+   b:   sub    $0x28,%rbp
+        48 83 ed 28
+   f:   mov    %rbx,0x0(%rbp)
+        48 89 5d 00
 
 |
 | **# bpftool prog load xdp1_kern.o /sys/fs/bpf/xdp1 type xdp map name rxcnt id 7**
 | **# bpftool prog show pinned /sys/fs/bpf/xdp1**
-|   9: xdp  name xdp_prog1  tag 539ec6ce11b52f98  gpl
+
-|	loaded_at 2018-06-25T16:17:31-0700  uid 0
+::
-|	xlated 488B  jited 336B  memlock 4096B  map_ids 7
+
-| **# rm /sys/fs/bpf/xdp1**
+    9: xdp  name xdp_prog1  tag 539ec6ce11b52f98  gpl
-|
+            loaded_at 2018-06-25T16:17:31-0700  uid 0
+            xlated 488B  jited 336B  memlock 4096B  map_ids 7
+
+**# rm /sys/fs/bpf/xdp1**
 
 SEE ALSO
 ========

tools/bpf/bpftool/Documentation/bpftool.rst

@@ -60,6 +60,10 @@ OPTIONS
 	-m, --mapcompat
 		  Allow loading maps with unknown map definitions.
 
+	-n, --nomount
+		  Do not automatically attempt to mount any virtual file system
+		  (such as tracefs or BPF virtual file system) when necessary.
+
 
 SEE ALSO
 ========

tools/bpf/bpftool/Makefile

@@ -35,8 +35,6 @@ $(LIBBPF)-clean:
 prefix ?= /usr/local
 bash_compdir ?= /usr/share/bash-completion/completions
 
-CC = gcc
-
 CFLAGS += -O2
 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow -Wno-missing-field-initializers
 CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \

tools/bpf/bpftool/bash-completion/bpftool

@@ -1,37 +1,8 @@
 # bpftool(8) bash completion                               -*- shell-script -*-
 #
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 # Copyright (C) 2017-2018 Netronome Systems, Inc.
 #
-# This software is dual licensed under the GNU General License
-# Version 2, June 1991 as shown in the file COPYING in the top-level
-# directory of this source tree or the BSD 2-Clause License provided
-# below.  You have the option to license this software under the
-# complete terms of either license.
-#
-# The BSD 2-Clause License:
-#
-#     Redistribution and use in source and binary forms, with or
-#     without modification, are permitted provided that the following
-#     conditions are met:
-#
-#      1. Redistributions of source code must retain the above
-#         copyright notice, this list of conditions and the following
-#         disclaimer.
-#
-#      2. Redistributions in binary form must reproduce the above
-#         copyright notice, this list of conditions and the following
-#         disclaimer in the documentation and/or other materials
-#         provided with the distribution.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-#
 # Author: Quentin Monnet <quentin.monnet@netronome.com>
 
 # Takes a list of words in argument; each one of them is added to COMPREPLY if

tools/bpf/bpftool/btf_dumper.c

@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (c) 2018 Facebook */
 
 #include <ctype.h>
@@ -73,20 +73,17 @@ static int btf_dumper_array(const struct btf_dumper *d, __u32 type_id,
 	return ret;
 }
 
-static void btf_dumper_int_bits(__u32 int_type, __u8 bit_offset,
+static void btf_dumper_bitfield(__u32 nr_bits, __u8 bit_offset,
 				const void *data, json_writer_t *jw,
 				bool is_plain_text)
 {
 	int left_shift_bits, right_shift_bits;
-	int nr_bits = BTF_INT_BITS(int_type);
-	int total_bits_offset;
 	int bytes_to_copy;
 	int bits_to_copy;
 	__u64 print_num;
 
-	total_bits_offset = bit_offset + BTF_INT_OFFSET(int_type);
+	data += BITS_ROUNDDOWN_BYTES(bit_offset);
-	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
+	bit_offset = BITS_PER_BYTE_MASKED(bit_offset);
-	bit_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
 	bits_to_copy = bit_offset + nr_bits;
 	bytes_to_copy = BITS_ROUNDUP_BYTES(bits_to_copy);
 
@@ -109,6 +106,22 @@ static void btf_dumper_int_bits(__u32 int_type, __u8 bit_offset,
 		jsonw_printf(jw, "%llu", print_num);
 }
 
+
+static void btf_dumper_int_bits(__u32 int_type, __u8 bit_offset,
+				const void *data, json_writer_t *jw,
+				bool is_plain_text)
+{
+	int nr_bits = BTF_INT_BITS(int_type);
+	int total_bits_offset;
+
+	/* bits_offset is at most 7.
+	 * BTF_INT_OFFSET() cannot exceed 64 bits.
+	 */
+	total_bits_offset = bit_offset + BTF_INT_OFFSET(int_type);
+	btf_dumper_bitfield(nr_bits, total_bits_offset, data, jw,
+			    is_plain_text);
+}
+
 static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset,
 			  const void *data, json_writer_t *jw,
 			  bool is_plain_text)
@@ -180,6 +193,7 @@ static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id,
 	const struct btf_type *t;
 	struct btf_member *m;
 	const void *data_off;
+	int kind_flag;
 	int ret = 0;
 	int i, vlen;
 
@@ -187,18 +201,32 @@ static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id,
 	if (!t)
 		return -EINVAL;
 
+	kind_flag = BTF_INFO_KFLAG(t->info);
 	vlen = BTF_INFO_VLEN(t->info);
 	jsonw_start_object(d->jw);
 	m = (struct btf_member *)(t + 1);
 
 	for (i = 0; i < vlen; i++) {
-		data_off = data + BITS_ROUNDDOWN_BYTES(m[i].offset);
+		__u32 bit_offset = m[i].offset;
+		__u32 bitfield_size = 0;
+
+		if (kind_flag) {
+			bitfield_size = BTF_MEMBER_BITFIELD_SIZE(bit_offset);
+			bit_offset = BTF_MEMBER_BIT_OFFSET(bit_offset);
+		}
+
 		jsonw_name(d->jw, btf__name_by_offset(d->btf, m[i].name_off));
-		ret = btf_dumper_do_type(d, m[i].type,
+		if (bitfield_size) {
-					 BITS_PER_BYTE_MASKED(m[i].offset),
+			btf_dumper_bitfield(bitfield_size, bit_offset,
-					 data_off);
+					    data, d->jw, d->is_plain_text);
-		if (ret)
+		} else {
-			break;
+			data_off = data + BITS_ROUNDDOWN_BYTES(bit_offset);
+			ret = btf_dumper_do_type(d, m[i].type,
+						 BITS_PER_BYTE_MASKED(bit_offset),
+						 data_off);
+			if (ret)
+				break;
+		}
 	}
 
 	jsonw_end_object(d->jw);
@@ -285,6 +313,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id,
 
 	switch (BTF_INFO_KIND(t->info)) {
 	case BTF_KIND_INT:
+	case BTF_KIND_TYPEDEF:
 		BTF_PRINT_ARG("%s ", btf__name_by_offset(btf, t->name_off));
 		break;
 	case BTF_KIND_STRUCT:
@@ -308,10 +337,11 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id,
 		BTF_PRINT_TYPE(t->type);
 		BTF_PRINT_ARG("* ");
 		break;
-	case BTF_KIND_UNKN:
 	case BTF_KIND_FWD:
-	case BTF_KIND_TYPEDEF:
+		BTF_PRINT_ARG("%s %s ",
-		return -1;
+			      BTF_INFO_KFLAG(t->info) ? "union" : "struct",
+			      btf__name_by_offset(btf, t->name_off));
+		break;
 	case BTF_KIND_VOLATILE:
 		BTF_PRINT_ARG("volatile ");
 		BTF_PRINT_TYPE(t->type);
@@ -335,6 +365,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id,
 		if (pos == -1)
 			return -1;
 		break;
+	case BTF_KIND_UNKN:
 	default:
 		return -1;
 	}

tools/bpf/bpftool/cfg.c

@@ -1,39 +1,5 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-/*
+/* Copyright (C) 2018 Netronome Systems, Inc. */
- * Copyright (C) 2018 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
 
 #include <linux/list.h>
 #include <stdlib.h>

tools/bpf/bpftool/cfg.h

@@ -1,39 +1,5 @@
-// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
-/*
+/* Copyright (C) 2018 Netronome Systems, Inc. */
- * Copyright (C) 2018 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
 
 #ifndef __BPF_TOOL_CFG_H
 #define __BPF_TOOL_CFG_H

tools/bpf/bpftool/cgroup.c

@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (C) 2017 Facebook
 // Author: Roman Gushchin <guro@fb.com>
 

tools/bpf/bpftool/common.c

@@ -1,35 +1,5 @@
-/*
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
- * Copyright (C) 2017-2018 Netronome Systems, Inc.
+/* Copyright (C) 2017-2018 Netronome Systems, Inc. */
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
 
 #include <ctype.h>
 #include <errno.h>
@@ -58,7 +28,7 @@
 #define BPF_FS_MAGIC		0xcafe4a11
 #endif
 
-void p_err(const char *fmt, ...)
+void __printf(1, 2) p_err(const char *fmt, ...)
 {
 	va_list ap;
 
@@ -76,7 +46,7 @@ void p_err(const char *fmt, ...)
 	va_end(ap);
 }
 
-void p_info(const char *fmt, ...)
+void __printf(1, 2) p_info(const char *fmt, ...)
 {
 	va_list ap;
 
@@ -106,7 +76,8 @@ void set_max_rlimit(void)
 	setrlimit(RLIMIT_MEMLOCK, &rinf);
 }
 
-static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
+static int
+mnt_fs(const char *target, const char *type, char *buff, size_t bufflen)
 {
 	bool bind_done = false;
 
@@ -128,15 +99,29 @@ static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
 		bind_done = true;
 	}
 
-	if (mount("bpf", target, "bpf", 0, "mode=0700")) {
+	if (mount(type, target, type, 0, "mode=0700")) {
-		snprintf(buff, bufflen, "mount -t bpf bpf %s failed: %s",
+		snprintf(buff, bufflen, "mount -t %s %s %s failed: %s",
-			 target, strerror(errno));
+			 type, type, target, strerror(errno));
 		return -1;
 	}
 
 	return 0;
 }
 
+int mount_tracefs(const char *target)
+{
+	char err_str[ERR_MAX_LEN];
+	int err;
+
+	err = mnt_fs(target, "tracefs", err_str, ERR_MAX_LEN);
+	if (err) {
+		err_str[ERR_MAX_LEN - 1] = '\0';
+		p_err("can't mount tracefs: %s", err_str);
+	}
+
+	return err;
+}
+
 int open_obj_pinned(char *path, bool quiet)
 {
 	int fd;
@@ -192,7 +177,13 @@ int mount_bpffs_for_pin(const char *name)
 		/* nothing to do if already mounted */
 		goto out_free;
 
-	err = mnt_bpffs(dir, err_str, ERR_MAX_LEN);
+	if (block_mount) {
+		p_err("no BPF file system found, not mounting it due to --nomount option");
+		err = -1;
+		goto out_free;
+	}
+
+	err = mnt_fs(dir, "bpf", err_str, ERR_MAX_LEN);
 	if (err) {
 		err_str[ERR_MAX_LEN - 1] = '\0';
 		p_err("can't mount BPF file system to pin the object (%s): %s",

tools/bpf/bpftool/jit_disasm.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /*
  * Based on:
  *

tools/bpf/bpftool/json_writer.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /*
  * Simple streaming JSON writer
  *
@@ -19,6 +20,7 @@
 #include <malloc.h>
 #include <inttypes.h>
 #include <stdint.h>
+#include <linux/compiler.h>
 
 #include "json_writer.h"
 
@@ -156,7 +158,8 @@ void jsonw_name(json_writer_t *self, const char *name)
 		putc(' ', self->out);
 }
 
-void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap)
+void __printf(2, 0)
+jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap)
 {
 	jsonw_eor(self);
 	putc('"', self->out);
@@ -164,7 +167,7 @@ void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap)
 	putc('"', self->out);
 }
 
-void jsonw_printf(json_writer_t *self, const char *fmt, ...)
+void __printf(2, 3) jsonw_printf(json_writer_t *self, const char *fmt, ...)
 {
 	va_list ap;
 

tools/bpf/bpftool/json_writer.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
 /*
  * Simple streaming JSON writer
  *

tools/bpf/bpftool/main.c

@@ -1,35 +1,5 @@
-/*
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
- * Copyright (C) 2017-2018 Netronome Systems, Inc.
+/* Copyright (C) 2017-2018 Netronome Systems, Inc. */
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
 
 #include <ctype.h>
 #include <errno.h>
@@ -54,6 +24,7 @@ json_writer_t *json_wtr;
 bool pretty_output;
 bool json_output;
 bool show_pinned;
+bool block_mount;
 int bpf_flags;
 struct pinned_obj_table prog_table;
 struct pinned_obj_table map_table;
@@ -343,6 +314,7 @@ int main(int argc, char **argv)
 		{ "version",	no_argument,	NULL,	'V' },
 		{ "bpffs",	no_argument,	NULL,	'f' },
 		{ "mapcompat",	no_argument,	NULL,	'm' },
+		{ "nomount",	no_argument,	NULL,	'n' },
 		{ 0 }
 	};
 	int opt, ret;
@@ -351,13 +323,14 @@ int main(int argc, char **argv)
 	pretty_output = false;
 	json_output = false;
 	show_pinned = false;
+	block_mount = false;
 	bin_name = argv[0];
 
 	hash_init(prog_table.table);
 	hash_init(map_table.table);
 
 	opterr = 0;
-	while ((opt = getopt_long(argc, argv, "Vhpjfm",
+	while ((opt = getopt_long(argc, argv, "Vhpjfmn",
 				  options, NULL)) >= 0) {
 		switch (opt) {
 		case 'V':
@@ -384,6 +357,9 @@ int main(int argc, char **argv)
 		case 'm':
 			bpf_flags = MAPS_RELAX_COMPAT;
 			break;
+		case 'n':
+			block_mount = true;
+			break;
 		default:
 			p_err("unrecognized option '%s'", argv[optind - 1]);
 			if (json_output)

tools/bpf/bpftool/main.h

@@ -1,35 +1,5 @@
-/*
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
- * Copyright (C) 2017-2018 Netronome Systems, Inc.
+/* Copyright (C) 2017-2018 Netronome Systems, Inc. */
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
 
 #ifndef __BPF_TOOL_H
 #define __BPF_TOOL_H
@@ -74,7 +44,8 @@
 #define HELP_SPEC_PROGRAM						\
 	"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
 #define HELP_SPEC_OPTIONS						\
-	"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} | {-m|--mapcompat}"
+	"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} |\n"	\
+	"\t            {-m|--mapcompat} | {-n|--nomount} }"
 #define HELP_SPEC_MAP							\
 	"MAP := { id MAP_ID | pinned FILE }"
 
@@ -115,6 +86,7 @@ extern const char *bin_name;
 extern json_writer_t *json_wtr;
 extern bool json_output;
 extern bool show_pinned;
+extern bool block_mount;
 extern int bpf_flags;
 extern struct pinned_obj_table prog_table;
 extern struct pinned_obj_table map_table;
@@ -128,6 +100,8 @@ void usage(void) __noreturn;
 
 void set_max_rlimit(void);
 
+int mount_tracefs(const char *target);
+
 struct pinned_obj_table {
 	DECLARE_HASHTABLE(table, 16);
 };
@@ -177,8 +151,8 @@ int prog_parse_fd(int *argc, char ***argv);
 int map_parse_fd(int *argc, char ***argv);
 int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
 
-#ifdef HAVE_LIBBFD_SUPPORT
 struct bpf_prog_linfo;
+#ifdef HAVE_LIBBFD_SUPPORT
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 		       const char *arch, const char *disassembler_options,
 		       const struct btf *btf,

tools/bpf/bpftool/map.c

@@ -1,35 +1,5 @@
-/*
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
- * Copyright (C) 2017-2018 Netronome Systems, Inc.
+/* Copyright (C) 2017-2018 Netronome Systems, Inc. */
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
 
 #include <assert.h>
 #include <errno.h>

tools/bpf/bpftool/map_perf_ring.c

@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0-only
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (C) 2018 Netronome Systems, Inc. */
 /* This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public

tools/bpf/bpftool/net.c

@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (C) 2018 Facebook
 
 #define _GNU_SOURCE

tools/bpf/bpftool/netlink_dumper.c

@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (C) 2018 Facebook
 
 #include <stdlib.h>

tools/bpf/bpftool/netlink_dumper.h

@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
 // Copyright (C) 2018 Facebook
 
 #ifndef _NETLINK_DUMPER_H_

tools/bpf/bpftool/perf.c

@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (C) 2018 Facebook
 // Author: Yonghong Song <yhs@fb.com>
 

tools/bpf/bpftool/prog.c

@@ -1,35 +1,5 @@
-/*
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
- * Copyright (C) 2017-2018 Netronome Systems, Inc.
+/* Copyright (C) 2017-2018 Netronome Systems, Inc. */
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
 
 #define _GNU_SOURCE
 #include <errno.h>
@@ -62,7 +32,7 @@ static const char * const attach_type_strings[] = {
 	[__MAX_BPF_ATTACH_TYPE] = NULL,
 };
 
-enum bpf_attach_type parse_attach_type(const char *str)
+static enum bpf_attach_type parse_attach_type(const char *str)
 {
 	enum bpf_attach_type type;
 
@@ -626,13 +596,6 @@ static int do_dump(int argc, char **argv)
 		goto err_free;
 	}
 
-	if (func_info && !info.func_info) {
-		/* kernel.kptr_restrict is set.  No func_info available. */
-		free(func_info);
-		func_info = NULL;
-		nr_finfo = 0;
-	}
-
 	if (linfo && info.nr_line_info != nr_linfo) {
 		p_err("incorrect nr_line_info %u vs. expected %u",
 		      info.nr_line_info, nr_linfo);
@@ -835,7 +798,7 @@ struct map_replace {
 	char *name;
 };
 
-int map_replace_compar(const void *p1, const void *p2)
+static int map_replace_compar(const void *p1, const void *p2)
 {
 	const struct map_replace *a = p1, *b = p2;
 

tools/bpf/bpftool/tracelog.c

@@ -54,7 +54,7 @@ find_tracefs_mnt_single(unsigned long magic, char *mnt, const char *mntpt)
 	return true;
 }
 
-static bool find_tracefs_pipe(char *mnt)
+static bool get_tracefs_pipe(char *mnt)
 {
 	static const char * const known_mnts[] = {
 		"/sys/kernel/debug/tracing",
@@ -88,7 +88,20 @@ static bool find_tracefs_pipe(char *mnt)
 	fclose(fp);
 
 	/* The string from fscanf() might be truncated, check mnt is valid */
-	if (!found || validate_tracefs_mnt(mnt, TRACEFS_MAGIC))
+	if (found && validate_tracefs_mnt(mnt, TRACEFS_MAGIC))
+		goto exit_found;
+
+	if (block_mount)
+		return false;
+
+	p_info("could not find tracefs, attempting to mount it now");
+	/* Most of the time, tracefs is automatically mounted by debugfs at
+	 * /sys/kernel/debug/tracing when we try to access it. If we could not
+	 * find it, it is likely that debugfs is not mounted. Let's give one
+	 * attempt at mounting just tracefs at /sys/kernel/tracing.
+	 */
+	strcpy(mnt, known_mnts[1]);
+	if (mount_tracefs(mnt))
 		return false;
 
 exit_found:
@@ -115,17 +128,13 @@ int do_tracelog(int argc, char **argv)
 		.sa_handler = exit_tracelog
 	};
 	char trace_pipe[PATH_MAX];
-	bool found_trace_pipe;
 	size_t buff_len = 0;
 
 	if (json_output)
 		jsonw_start_array(json_wtr);
 
-	found_trace_pipe = find_tracefs_pipe(trace_pipe);
+	if (!get_tracefs_pipe(trace_pipe))
-	if (!found_trace_pipe) {
-		p_err("could not find trace pipe, tracefs not mounted?");
 		return -1;
-	}
 
 	trace_pipe_fd = fopen(trace_pipe, "r");
 	if (!trace_pipe_fd) {

tools/bpf/bpftool/xlated_dumper.c

@@ -1,39 +1,5 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-/*
+/* Copyright (C) 2018 Netronome Systems, Inc. */
- * Copyright (C) 2018 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
 
 #define _GNU_SOURCE
 #include <stdarg.h>
@@ -115,7 +81,7 @@ struct kernel_sym *kernel_syms_search(struct dump_data *dd,
 		       sizeof(*dd->sym_mapping), kernel_syms_cmp) : NULL;
 }
 
-static void print_insn(void *private_data, const char *fmt, ...)
+static void __printf(2, 3) print_insn(void *private_data, const char *fmt, ...)
 {
 	va_list args;
 
@@ -124,7 +90,7 @@ static void print_insn(void *private_data, const char *fmt, ...)
 	va_end(args);
 }
 
-static void
+static void __printf(2, 3)
 print_insn_for_graph(void *private_data, const char *fmt, ...)
 {
 	char buf[64], *p;
@@ -155,7 +121,8 @@ print_insn_for_graph(void *private_data, const char *fmt, ...)
 	printf("%s", buf);
 }
 
-static void print_insn_json(void *private_data, const char *fmt, ...)
+static void __printf(2, 3)
+print_insn_json(void *private_data, const char *fmt, ...)
 {
 	unsigned int l = strlen(fmt);
 	char chomped_fmt[l];

tools/bpf/bpftool/xlated_dumper.h

@@ -1,39 +1,5 @@
-// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
-/*
+/* Copyright (C) 2018 Netronome Systems, Inc. */
- * Copyright (C) 2018 Netronome Systems, Inc.
- *
- * This software is dual licensed under the GNU General License Version 2,
- * June 1991 as shown in the file COPYING in the top-level directory of this
- * source tree or the BSD 2-Clause License provided below.  You have the
- * option to license this software under the complete terms of either license.
- *
- * The BSD 2-Clause License:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      1. Redistributions of source code must retain the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer.
- *
- *      2. Redistributions in binary form must reproduce the above
- *         copyright notice, this list of conditions and the following
- *         disclaimer in the documentation and/or other materials
- *         provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
 
 #ifndef __BPF_TOOL_XLATED_DUMPER_H
 #define __BPF_TOOL_XLATED_DUMPER_H

tools/include/uapi/linux/bpf.h

@@ -133,6 +133,14 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_STACK,
 };
 
+/* Note that tracing related programs such as
+ * BPF_PROG_TYPE_{KPROBE,TRACEPOINT,PERF_EVENT,RAW_TRACEPOINT}
+ * are not subject to a stable API since kernel internal data
+ * structures can change from release to release and may
+ * therefore break existing tracing BPF programs. Tracing BPF
+ * programs correspond to /a/ specific kernel which is to be
+ * analyzed, and not /a/ specific kernel /and/ all future ones.
+ */
 enum bpf_prog_type {
 	BPF_PROG_TYPE_UNSPEC,
 	BPF_PROG_TYPE_SOCKET_FILTER,
@@ -343,7 +351,7 @@ union bpf_attr {
 		__u32		log_level;	/* verbosity level of verifier */
 		__u32		log_size;	/* size of user buffer */
 		__aligned_u64	log_buf;	/* user supplied buffer */
-		__u32		kern_version;	/* checked when prog_type=kprobe */
+		__u32		kern_version;	/* not used */
 		__u32		prog_flags;
 		char		prog_name[BPF_OBJ_NAME_LEN];
 		__u32		prog_ifindex;	/* ifindex of netdev to prep for */
@@ -2657,6 +2665,7 @@ struct sk_msg_md {
 	__u32 local_ip6[4];	/* Stored in network byte order */
 	__u32 remote_port;	/* Stored in network byte order */
 	__u32 local_port;	/* stored in host byte order */
+	__u32 size;		/* Total size of sk_msg */
 };
 
 struct sk_reuseport_md {
@@ -2717,6 +2726,8 @@ struct bpf_prog_info {
 	__u32 nr_jited_line_info;
 	__u32 line_info_rec_size;
 	__u32 jited_line_info_rec_size;
+	__u32 nr_prog_tags;
+	__aligned_u64 prog_tags;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {

tools/include/uapi/linux/btf.h

@@ -34,7 +34,9 @@ struct btf_type {
 	 * bits  0-15: vlen (e.g. # of struct's members)
 	 * bits 16-23: unused
 	 * bits 24-27: kind (e.g. int, ptr, array...etc)
-	 * bits 28-31: unused
+	 * bits 28-30: unused
+	 * bit     31: kind_flag, currently used by
+	 *             struct, union and fwd
 	 */
 	__u32 info;
 	/* "size" is used by INT, ENUM, STRUCT and UNION.
@@ -52,6 +54,7 @@ struct btf_type {
 
 #define BTF_INFO_KIND(info)	(((info) >> 24) & 0x0f)
 #define BTF_INFO_VLEN(info)	((info) & 0xffff)
+#define BTF_INFO_KFLAG(info)	((info) >> 31)
 
 #define BTF_KIND_UNKN		0	/* Unknown	*/
 #define BTF_KIND_INT		1	/* Integer	*/
@@ -110,9 +113,22 @@ struct btf_array {
 struct btf_member {
 	__u32	name_off;
 	__u32	type;
-	__u32	offset;	/* offset in bits */
+	/* If the type info kind_flag is set, the btf_member offset
+	 * contains both member bitfield size and bit offset. The
+	 * bitfield size is set for bitfield members. If the type
+	 * info kind_flag is not set, the offset contains only bit
+	 * offset.
+	 */
+	__u32	offset;
 };
 
+/* If the struct/union type info kind_flag is set, the
+ * following two macros are used to access bitfield_size
+ * and bit_offset from btf_member.offset.
+ */
+#define BTF_MEMBER_BITFIELD_SIZE(val)	((val) >> 24)
+#define BTF_MEMBER_BIT_OFFSET(val)	((val) & 0xffffff)
+
 /* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param".
  * The exact number of btf_param is stored in the vlen (of the
  * info in "struct btf_type").

tools/lib/bpf/bpf_prog_linfo.c

@@ -107,11 +107,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info)
 
 	nr_linfo = info->nr_line_info;
 
-	/*
+	if (!nr_linfo)
-	 * Test !info->line_info because the kernel may NULL
-	 * the ptr if kernel.kptr_restrict is set.
-	 */
-	if (!nr_linfo || !info->line_info)
 		return NULL;
 
 	/*

tools/lib/bpf/libbpf.c

@@ -266,6 +266,7 @@ void bpf_program__unload(struct bpf_program *prog)
 
 	zclose(prog->btf_fd);
 	zfree(&prog->func_info);
+	zfree(&prog->line_info);
 }
 
 static void bpf_program__exit(struct bpf_program *prog)

tools/testing/selftests/bpf/.gitignore

@@ -27,3 +27,4 @@ test_flow_dissector
 flow_dissector_load
 test_netcnt
 test_section_names
+test_tcpnotify_user

tools/testing/selftests/bpf/connect4_prog.c

@@ -35,9 +35,11 @@ int connect_v4_prog(struct bpf_sock_addr *ctx)
 	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
 		return 0;
 	else if (ctx->type == SOCK_STREAM)
-		sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv4), 0, 0);
+		sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv4),
+				       BPF_F_CURRENT_NETNS, 0);
 	else
-		sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv4), 0, 0);
+		sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv4),
+				       BPF_F_CURRENT_NETNS, 0);
 
 	if (!sk)
 		return 0;

tools/testing/selftests/bpf/connect6_prog.c

@@ -47,9 +47,11 @@ int connect_v6_prog(struct bpf_sock_addr *ctx)
 	if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
 		return 0;
 	else if (ctx->type == SOCK_STREAM)
-		sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv6), 0, 0);
+		sk = bpf_sk_lookup_tcp(ctx, &tuple, sizeof(tuple.ipv6),
+				       BPF_F_CURRENT_NETNS, 0);
 	else
-		sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv6), 0, 0);
+		sk = bpf_sk_lookup_udp(ctx, &tuple, sizeof(tuple.ipv6),
+				       BPF_F_CURRENT_NETNS, 0);
 
 	if (!sk)
 		return 0;

tools/testing/selftests/bpf/netcnt_prog.c

@@ -16,12 +16,18 @@ struct bpf_map_def SEC("maps") percpu_netcnt = {
 	.value_size = sizeof(struct percpu_net_cnt),
 };
 
+BPF_ANNOTATE_KV_PAIR(percpu_netcnt, struct bpf_cgroup_storage_key,
+		     struct percpu_net_cnt);
+
 struct bpf_map_def SEC("maps") netcnt = {
 	.type = BPF_MAP_TYPE_CGROUP_STORAGE,
 	.key_size = sizeof(struct bpf_cgroup_storage_key),
 	.value_size = sizeof(struct net_cnt),
 };
 
+BPF_ANNOTATE_KV_PAIR(netcnt, struct bpf_cgroup_storage_key,
+		     struct net_cnt);
+
 SEC("cgroup/skb")
 int bpf_nextcnt(struct __sk_buff *skb)
 {

tools/testing/selftests/bpf/test_btf.c

@@ -65,8 +65,8 @@ static int __base_pr(const char *format, ...)
 	return err;
 }
 
-#define BTF_INFO_ENC(kind, root, vlen)			\
+#define BTF_INFO_ENC(kind, kind_flag, vlen)			\
-	((!!(root) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
+	((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
 
 #define BTF_TYPE_ENC(name, info, size_or_type)	\
 	(name), (info), (size_or_type)
@@ -86,6 +86,8 @@ static int __base_pr(const char *format, ...)
 #define BTF_MEMBER_ENC(name, type, bits_offset)	\
 	(name), (type), (bits_offset)
 #define BTF_ENUM_ENC(name, val) (name), (val)
+#define BTF_MEMBER_OFFSET(bitfield_size, bits_offset) \
+	((bitfield_size) << 24 | (bits_offset))
 
 #define BTF_TYPEDEF_ENC(name, type) \
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type)
@@ -2215,6 +2217,496 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid type_id",
 },
 
+{
+	.descr = "invalid int kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_INT, 1, 0), 4),	/* [2] */
+		BTF_INT_ENC(0, 0, 32),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "int_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid ptr kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 1, 0), 1),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "ptr_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid array kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 1, 0), 0),	/* [2] */
+		BTF_ARRAY_ENC(1, 1, 1),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "array_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid enum kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 1, 1), 4),	/* [2] */
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "enum_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "valid fwd kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(NAME_TBD,
+			     BTF_INFO_ENC(BTF_KIND_FWD, 1, 0), 0),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "fwd_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "invalid typedef kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(NAME_TBD,
+			     BTF_INFO_ENC(BTF_KIND_TYPEDEF, 1, 0), 1),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "typedef_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid volatile kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 1, 0), 1),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "volatile_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid const kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 1, 0), 1),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "const_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid restrict kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_RESTRICT, 1, 0), 1),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "restrict_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid func kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 0), 0),	/* [2] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_FUNC, 1, 0), 2),	/* [3] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "invalid func_proto kind_flag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 1, 0), 0),	/* [2] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC(""),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "func_proto_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+
+{
+	.descr = "valid struct, kind_flag, bitfield_size = 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 8),	/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(0, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(0, 32)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "valid struct, kind_flag, int member, bitfield_size != 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),	/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(4, 4)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "valid union, kind_flag, int member, bitfield_size != 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 1, 2), 4),	/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "union_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "valid struct, kind_flag, enum member, bitfield_size != 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),	/* [2] */
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(4, 4)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B\0C"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "valid union, kind_flag, enum member, bitfield_size != 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),	/* [2] */
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 1, 2), 4),	/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B\0C"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "union_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "valid struct, kind_flag, typedef member, bitfield_size != 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),	/* [2] */
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 4, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 5, BTF_MEMBER_OFFSET(4, 4)),
+		BTF_TYPEDEF_ENC(NAME_TBD, 1),				/* [4] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 2),				/* [5] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B\0C\0D\0E"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "valid union, kind_flag, typedef member, bitfield_size != 0",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),	/* [2] */
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 1, 2), 4),	/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 4, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 5, BTF_MEMBER_OFFSET(4, 0)),
+		BTF_TYPEDEF_ENC(NAME_TBD, 1),				/* [4] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 2),				/* [5] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B\0C\0D\0E"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "union_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+},
+
+{
+	.descr = "invalid struct, kind_flag, bitfield_size greater than struct size",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),	/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(20, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(20, 20)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Member exceeds struct_size",
+},
+
+{
+	.descr = "invalid struct, kind_flag, bitfield base_type int not regular",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 20, 4),			/* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),	/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(20, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(20, 20)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid member base type",
+},
+
+{
+	.descr = "invalid struct, kind_flag, base_type int not regular",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 12, 4),			/* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 4),	/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(8, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(8, 8)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid member base type",
+},
+
+{
+	.descr = "invalid union, kind_flag, bitfield_size greater than struct size",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),		/* [1] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 1, 2), 2),	/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(8, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 1, BTF_MEMBER_OFFSET(20, 0)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "union_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Member exceeds struct_size",
+},
+
+{
+	.descr = "invalid struct, kind_flag, int member, bitfield_size = 0, wrong byte alignment",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 12),	/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(0, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(0, 36)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid member offset",
+},
+
+{
+	.descr = "invalid struct, kind_flag, enum member, bitfield_size = 0, wrong byte alignment",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),	/* [2] */
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 2), 12),	/* [3] */
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(0, 0)),
+		BTF_MEMBER_ENC(NAME_TBD, 2, BTF_MEMBER_OFFSET(0, 36)),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0A\0B\0C"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 4,
+	.btf_load_err = true,
+	.err_str = "Invalid member offset",
+},
+
 }; /* struct btf_raw_test raw_tests[] */
 
 static const char *get_next_str(const char *start, const char *end)
@@ -2916,7 +3408,7 @@ static int do_test_file(unsigned int test_num)
 		goto done;
 	}
 	rec_size = info.func_info_rec_size;
-	if (CHECK(rec_size < 4,
+	if (CHECK(rec_size != sizeof(struct bpf_func_info),
 		  "incorrect info.func_info_rec_size (1st) %d\n", rec_size)) {
 		err = -1;
 		goto done;
@@ -3036,7 +3528,8 @@ struct pprint_mapv {
 	} aenum;
 };
 
-static struct btf_raw_test pprint_test_template = {
+static struct btf_raw_test pprint_test_template[] = {
+{
 	.raw_types = {
 		/* unsighed char */			/* [1] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
@@ -3086,13 +3579,140 @@ static struct btf_raw_test pprint_test_template = {
 		BTF_MEMBER_ENC(NAME_TBD, 15, 192),	/* aenum */
 		BTF_END_RAW,
 	},
-	.str_sec = "\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum",
+	BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"),
-	.str_sec_size = sizeof("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"),
 	.key_size = sizeof(unsigned int),
 	.value_size = sizeof(struct pprint_mapv),
 	.key_type_id = 3,	/* unsigned int */
 	.value_type_id = 16,	/* struct pprint_mapv */
 	.max_entries = 128 * 1024,
+},
+
+{
+	/* this type will have the same type as the
+	 * first .raw_types definition, but struct type will
+	 * be encoded with kind_flag set.
+	 */
+	.raw_types = {
+		/* unsighed char */			/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
+		/* unsigned short */			/* [2] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
+		/* unsigned int */			/* [3] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),
+		/* int */				/* [4] */
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+		/* unsigned long long */		/* [5] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8),
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),	/* [6] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),	/* [7] */
+		/* uint8_t[8] */			/* [8] */
+		BTF_TYPE_ARRAY_ENC(9, 1, 8),
+		/* typedef unsigned char uint8_t */	/* [9] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 1),
+		/* typedef unsigned short uint16_t */	/* [10] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 2),
+		/* typedef unsigned int uint32_t */	/* [11] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 3),
+		/* typedef int int32_t */		/* [12] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 4),
+		/* typedef unsigned long long uint64_t *//* [13] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 5),
+		/* union (anon) */			/* [14] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 0, 2), 8),
+		BTF_MEMBER_ENC(NAME_TBD, 13, 0),/* uint64_t ui64; */
+		BTF_MEMBER_ENC(NAME_TBD, 8, 0),	/* uint8_t ui8a[8]; */
+		/* enum (anon) */			/* [15] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 4), 4),
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_ENUM_ENC(NAME_TBD, 1),
+		BTF_ENUM_ENC(NAME_TBD, 2),
+		BTF_ENUM_ENC(NAME_TBD, 3),
+		/* struct pprint_mapv */		/* [16] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 8), 32),
+		BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 0)),	/* uint32_t ui32 */
+		BTF_MEMBER_ENC(NAME_TBD, 10, BTF_MEMBER_OFFSET(0, 32)),	/* uint16_t ui16 */
+		BTF_MEMBER_ENC(NAME_TBD, 12, BTF_MEMBER_OFFSET(0, 64)),	/* int32_t si32 */
+		BTF_MEMBER_ENC(NAME_TBD, 6, BTF_MEMBER_OFFSET(2, 96)),	/* unused_bits2a */
+		BTF_MEMBER_ENC(NAME_TBD, 7, BTF_MEMBER_OFFSET(28, 98)),	/* bits28 */
+		BTF_MEMBER_ENC(NAME_TBD, 6, BTF_MEMBER_OFFSET(2, 126)),	/* unused_bits2b */
+		BTF_MEMBER_ENC(0, 14, BTF_MEMBER_OFFSET(0, 128)),	/* union (anon) */
+		BTF_MEMBER_ENC(NAME_TBD, 15, BTF_MEMBER_OFFSET(0, 192)),	/* aenum */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"),
+	.key_size = sizeof(unsigned int),
+	.value_size = sizeof(struct pprint_mapv),
+	.key_type_id = 3,	/* unsigned int */
+	.value_type_id = 16,	/* struct pprint_mapv */
+	.max_entries = 128 * 1024,
+},
+
+{
+	/* this type will have the same layout as the
+	 * first .raw_types definition. The struct type will
+	 * be encoded with kind_flag set, bitfield members
+	 * are added typedef/const/volatile, and bitfield members
+	 * will have both int and enum types.
+	 */
+	.raw_types = {
+		/* unsighed char */			/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
+		/* unsigned short */			/* [2] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
+		/* unsigned int */			/* [3] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),
+		/* int */				/* [4] */
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+		/* unsigned long long */		/* [5] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8),
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),	/* [6] */
+		BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),	/* [7] */
+		/* uint8_t[8] */			/* [8] */
+		BTF_TYPE_ARRAY_ENC(9, 1, 8),
+		/* typedef unsigned char uint8_t */	/* [9] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 1),
+		/* typedef unsigned short uint16_t */	/* [10] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 2),
+		/* typedef unsigned int uint32_t */	/* [11] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 3),
+		/* typedef int int32_t */		/* [12] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 4),
+		/* typedef unsigned long long uint64_t *//* [13] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 5),
+		/* union (anon) */			/* [14] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 0, 2), 8),
+		BTF_MEMBER_ENC(NAME_TBD, 13, 0),/* uint64_t ui64; */
+		BTF_MEMBER_ENC(NAME_TBD, 8, 0),	/* uint8_t ui8a[8]; */
+		/* enum (anon) */			/* [15] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 4), 4),
+		BTF_ENUM_ENC(NAME_TBD, 0),
+		BTF_ENUM_ENC(NAME_TBD, 1),
+		BTF_ENUM_ENC(NAME_TBD, 2),
+		BTF_ENUM_ENC(NAME_TBD, 3),
+		/* struct pprint_mapv */		/* [16] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 8), 32),
+		BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 0)),	/* uint32_t ui32 */
+		BTF_MEMBER_ENC(NAME_TBD, 10, BTF_MEMBER_OFFSET(0, 32)),	/* uint16_t ui16 */
+		BTF_MEMBER_ENC(NAME_TBD, 12, BTF_MEMBER_OFFSET(0, 64)),	/* int32_t si32 */
+		BTF_MEMBER_ENC(NAME_TBD, 17, BTF_MEMBER_OFFSET(2, 96)),	/* unused_bits2a */
+		BTF_MEMBER_ENC(NAME_TBD, 7, BTF_MEMBER_OFFSET(28, 98)),	/* bits28 */
+		BTF_MEMBER_ENC(NAME_TBD, 19, BTF_MEMBER_OFFSET(2, 126)),/* unused_bits2b */
+		BTF_MEMBER_ENC(0, 14, BTF_MEMBER_OFFSET(0, 128)),	/* union (anon) */
+		BTF_MEMBER_ENC(NAME_TBD, 15, BTF_MEMBER_OFFSET(0, 192)),	/* aenum */
+		/* typedef unsigned int ___int */	/* [17] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 18),
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), 6),	/* [18] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 15),	/* [19] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0___int"),
+	.key_size = sizeof(unsigned int),
+	.value_size = sizeof(struct pprint_mapv),
+	.key_type_id = 3,	/* unsigned int */
+	.value_type_id = 16,	/* struct pprint_mapv */
+	.max_entries = 128 * 1024,
+},
+
 };
 
 static struct btf_pprint_test_meta {
@@ -3195,9 +3815,9 @@ static int check_line(const char *expected_line, int nexpected_line,
 }
 
 
-static int do_test_pprint(void)
+static int do_test_pprint(int test_num)
 {
-	const struct btf_raw_test *test = &pprint_test_template;
+	const struct btf_raw_test *test = &pprint_test_template[test_num];
 	struct bpf_create_map_attr create_attr = {};
 	bool ordered_map, lossless_map, percpu_map;
 	int err, ret, num_cpus, rounded_value_size;
@@ -3213,7 +3833,7 @@ static int do_test_pprint(void)
 	uint8_t *raw_btf;
 	ssize_t nread;
 
-	fprintf(stderr, "%s......", test->descr);
+	fprintf(stderr, "%s(#%d)......", test->descr, test_num);
 	raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
 				 test->str_sec, test->str_sec_size,
 				 &raw_btf_size, NULL);
@@ -3406,15 +4026,27 @@ static int test_pprint(void)
 	unsigned int i;
 	int err = 0;
 
+	/* test various maps with the first test template */
 	for (i = 0; i < ARRAY_SIZE(pprint_tests_meta); i++) {
-		pprint_test_template.descr = pprint_tests_meta[i].descr;
+		pprint_test_template[0].descr = pprint_tests_meta[i].descr;
-		pprint_test_template.map_type = pprint_tests_meta[i].map_type;
+		pprint_test_template[0].map_type = pprint_tests_meta[i].map_type;
-		pprint_test_template.map_name = pprint_tests_meta[i].map_name;
+		pprint_test_template[0].map_name = pprint_tests_meta[i].map_name;
-		pprint_test_template.ordered_map = pprint_tests_meta[i].ordered_map;
+		pprint_test_template[0].ordered_map = pprint_tests_meta[i].ordered_map;
-		pprint_test_template.lossless_map = pprint_tests_meta[i].lossless_map;
+		pprint_test_template[0].lossless_map = pprint_tests_meta[i].lossless_map;
-		pprint_test_template.percpu_map = pprint_tests_meta[i].percpu_map;
+		pprint_test_template[0].percpu_map = pprint_tests_meta[i].percpu_map;
 
-		err |= count_result(do_test_pprint());
+		err |= count_result(do_test_pprint(0));
+	}
+
+	/* test rest test templates with the first map */
+	for (i = 1; i < ARRAY_SIZE(pprint_test_template); i++) {
+		pprint_test_template[i].descr = pprint_tests_meta[0].descr;
+		pprint_test_template[i].map_type = pprint_tests_meta[0].map_type;
+		pprint_test_template[i].map_name = pprint_tests_meta[0].map_name;
+		pprint_test_template[i].ordered_map = pprint_tests_meta[0].ordered_map;
+		pprint_test_template[i].lossless_map = pprint_tests_meta[0].lossless_map;
+		pprint_test_template[i].percpu_map = pprint_tests_meta[0].percpu_map;
+		err |= count_result(do_test_pprint(i));
 	}
 
 	return err;
@@ -3621,6 +4253,33 @@ static struct prog_info_raw_test {
 	.expected_prog_load_failure = true,
 },
 
+{
+	.descr = "line_info (Zero bpf insn code)",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8),	/* [2] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 2),			/* [3] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0int\0unsigned long\0u64\0u64 a=1;\0return a;"),
+	.insns = {
+		BPF_LD_IMM64(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.func_info_cnt = 0,
+	.line_info = {
+		BPF_LINE_INFO_ENC(0, 0, NAME_TBD, 1, 10),
+		BPF_LINE_INFO_ENC(1, 0, 0, 2, 9),
+		BPF_LINE_INFO_ENC(2, 0, NAME_TBD, 3, 8),
+		BTF_END_RAW,
+	},
+	.line_info_rec_size = sizeof(struct bpf_line_info),
+	.nr_jited_ksyms = 1,
+	.err_str = "Invalid insn code at line_info[1]",
+	.expected_prog_load_failure = true,
+},
+
 {
 	.descr = "line_info (No subprog. zero tailing line_info",
 	.raw_types = {
@@ -3912,7 +4571,7 @@ static int test_get_finfo(const struct prog_info_raw_test *test,
 	}
 
 	rec_size = info.func_info_rec_size;
-	if (CHECK(rec_size < 8,
+	if (CHECK(rec_size != sizeof(struct bpf_func_info),
 		  "incorrect info.func_info_rec_size (1st) %d", rec_size)) {
 		return -1;
 	}
@@ -3941,19 +4600,13 @@ static int test_get_finfo(const struct prog_info_raw_test *test,
 		err = -1;
 		goto done;
 	}
-	if (CHECK(info.func_info_rec_size < 8,
+	if (CHECK(info.func_info_rec_size != rec_size,
 		  "incorrect info.func_info_rec_size (2nd) %d",
 		  info.func_info_rec_size)) {
 		err = -1;
 		goto done;
 	}
 
-	if (CHECK(!info.func_info,
-		  "info.func_info == 0. kernel.kptr_restrict is set?")) {
-		err = -1;
-		goto done;
-	}
-
 	finfo = func_info;
 	for (i = 0; i < test->func_info_cnt; i++) {
 		if (CHECK(finfo->type_id != test->func_info[i][1],
@@ -4023,8 +4676,8 @@ static int test_get_linfo(const struct prog_info_raw_test *test,
 		goto done;
 	}
 
-	if (CHECK(info.line_info_rec_size < 16 ||
+	if (CHECK(info.line_info_rec_size != sizeof(struct bpf_line_info) ||
-		  info.jited_line_info_rec_size < 8,
+		  info.jited_line_info_rec_size != sizeof(__u64),
 		  "info: line_info_rec_size:%u(userspace expected:%u) jited_line_info_rec_size:%u(userspace expected:%u)",
 		  info.line_info_rec_size, rec_size,
 		  info.jited_line_info_rec_size, jited_rec_size)) {
@@ -4077,7 +4730,6 @@ static int test_get_linfo(const struct prog_info_raw_test *test,
 	 * Other fields are not the concern of this test.
 	 */
 	if (CHECK(err == -1 ||
-		  !info.line_info ||
 		  info.nr_line_info != cnt ||
 		  (jited_cnt && !info.jited_line_info) ||
 		  info.nr_jited_line_info != jited_cnt ||

tools/testing/selftests/bpf/test_progs.c

@@ -51,10 +51,10 @@ static struct {
 	struct iphdr iph;
 	struct tcphdr tcp;
 } __packed pkt_v4 = {
-	.eth.h_proto = bpf_htons(ETH_P_IP),
+	.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
 	.iph.ihl = 5,
 	.iph.protocol = 6,
-	.iph.tot_len = bpf_htons(MAGIC_BYTES),
+	.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
 	.tcp.urg_ptr = 123,
 };
 
@@ -64,9 +64,9 @@ static struct {
 	struct ipv6hdr iph;
 	struct tcphdr tcp;
 } __packed pkt_v6 = {
-	.eth.h_proto = bpf_htons(ETH_P_IPV6),
+	.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
 	.iph.nexthdr = 6,
-	.iph.payload_len = bpf_htons(MAGIC_BYTES),
+	.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
 	.tcp.urg_ptr = 123,
 };
 

tools/testing/selftests/bpf/test_verifier.c

@@ -49,6 +49,7 @@
 #define MAX_INSNS	BPF_MAXINSNS
 #define MAX_FIXUPS	8
 #define MAX_NR_MAPS	13
+#define MAX_TEST_RUNS	8
 #define POINTER_VALUE	0xcafe4all
 #define TEST_DATA_LEN	64
 
@@ -76,7 +77,7 @@ struct bpf_test {
 	int fixup_percpu_cgroup_storage[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
-	uint32_t retval, retval_unpriv;
+	uint32_t retval, retval_unpriv, insn_processed;
 	enum {
 		UNDEF,
 		ACCEPT,
@@ -86,6 +87,14 @@ struct bpf_test {
 	uint8_t flags;
 	__u8 data[TEST_DATA_LEN];
 	void (*fill_helper)(struct bpf_test *self);
+	uint8_t runs;
+	struct {
+		uint32_t retval, retval_unpriv;
+		union {
+			__u8 data[TEST_DATA_LEN];
+			__u64 data64[TEST_DATA_LEN / 8];
+		};
+	} retvals[MAX_TEST_RUNS];
 };
 
 /* Note we want this to be 64 bit aligned so that the end of our array is
@@ -1001,13 +1010,43 @@ static struct bpf_test tests[] = {
 			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
 			/* mess up with R1 pointer on stack */
 			BPF_ST_MEM(BPF_B, BPF_REG_10, -7, 0x23),
-			/* fill back into R0 should fail */
+			/* fill back into R0 is fine for priv.
+			 * R0 now becomes SCALAR_VALUE.
+			 */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+			/* Load from R0 should fail. */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8),
+			BPF_EXIT_INSN(),
+		},
+		.errstr_unpriv = "attempt to corrupt spilled",
+		.errstr = "R0 invalid mem access 'inv",
+		.result = REJECT,
+	},
+	{
+		"check corrupted spill/fill, LSB",
+		.insns = {
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+			BPF_ST_MEM(BPF_H, BPF_REG_10, -8, 0xcafe),
 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
 			BPF_EXIT_INSN(),
 		},
 		.errstr_unpriv = "attempt to corrupt spilled",
-		.errstr = "corrupted spill",
+		.result_unpriv = REJECT,
-		.result = REJECT,
+		.result = ACCEPT,
+		.retval = POINTER_VALUE,
+	},
+	{
+		"check corrupted spill/fill, MSB",
+		.insns = {
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+			BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0x12345678),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+			BPF_EXIT_INSN(),
+		},
+		.errstr_unpriv = "attempt to corrupt spilled",
+		.result_unpriv = REJECT,
+		.result = ACCEPT,
+		.retval = POINTER_VALUE,
 	},
 	{
 		"invalid src register in STX",
@@ -1813,10 +1852,20 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SK_SKB,
 	},
 	{
-		"invalid 64B read of family in SK_MSG",
+		"valid access size in SK_MSG",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct sk_msg_md, size)),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SK_MSG,
+	},
+	{
+		"invalid 64B read of size in SK_MSG",
 		.insns = {
 			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1,
-				    offsetof(struct sk_msg_md, family)),
+				    offsetof(struct sk_msg_md, size)),
 			BPF_EXIT_INSN(),
 		},
 		.errstr = "invalid bpf_context access",
@@ -1827,10 +1876,10 @@ static struct bpf_test tests[] = {
 		"invalid read past end of SK_MSG",
 		.insns = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-				    offsetof(struct sk_msg_md, local_port) + 4),
+				    offsetof(struct sk_msg_md, size) + 4),
 			BPF_EXIT_INSN(),
 		},
-		.errstr = "R0 !read_ok",
+		.errstr = "invalid bpf_context access",
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_SK_MSG,
 	},
@@ -13647,6 +13696,28 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = ACCEPT,
 	},
+	{
+		"allocated_stack",
+		.insns = {
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+			BPF_ALU64_REG(BPF_MOV, BPF_REG_7, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, -8),
+			BPF_STX_MEM(BPF_B, BPF_REG_10, BPF_REG_7, -9),
+			BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_10, -9),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.result_unpriv = ACCEPT,
+		.insn_processed = 15,
+	},
 	{
 		"reference tracking in call: free reference in subprog and outside",
 		.insns = {
@@ -14099,6 +14170,7 @@ static struct bpf_test tests[] = {
 		.errstr_unpriv = "R1 leaks addr",
 		.result = REJECT,
 	},
+	{
 		"calls: cross frame pruning",
 		.insns = {
 			/* r8 = !!random();
@@ -14122,10 +14194,199 @@ static struct bpf_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
 		.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+                .result = REJECT,
+	},
+	{
+		"jset: functional",
+		.insns = {
+			/* r0 = 0 */
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			/* prep for direct packet access via r2 */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_4, BPF_REG_3, 1),
+			BPF_EXIT_INSN(),
+
+			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_2, 0),
+
+			/* reg, bit 63 or bit 0 set, taken */
+			BPF_LD_IMM64(BPF_REG_8, 0x8000000000000001),
+			BPF_JMP_REG(BPF_JSET, BPF_REG_7, BPF_REG_8, 1),
+			BPF_EXIT_INSN(),
+
+			/* reg, bit 62, not taken */
+			BPF_LD_IMM64(BPF_REG_8, 0x4000000000000000),
+			BPF_JMP_REG(BPF_JSET, BPF_REG_7, BPF_REG_8, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_EXIT_INSN(),
+
+			/* imm, any bit set, taken */
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_7, -1, 1),
+			BPF_EXIT_INSN(),
+
+			/* imm, bit 31 set, taken */
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_7, 0x80000000, 1),
+			BPF_EXIT_INSN(),
+
+			/* all good - return r0 == 2 */
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.runs = 7,
+		.retvals = {
+			{ .retval = 2,
+			  .data64 = { (1ULL << 63) | (1U << 31) | (1U << 0), }
+			},
+			{ .retval = 2,
+			  .data64 = { (1ULL << 63) | (1U << 31), }
+			},
+			{ .retval = 2,
+			  .data64 = { (1ULL << 31) | (1U << 0), }
+			},
+			{ .retval = 2,
+			  .data64 = { (__u32)-1, }
+			},
+			{ .retval = 2,
+			  .data64 = { ~0x4000000000000000ULL, }
+			},
+			{ .retval = 0,
+			  .data64 = { 0, }
+			},
+			{ .retval = 0,
+			  .data64 = { ~0ULL, }
+			},
+		},
+	},
+	{
+		"jset: sign-extend",
+		.insns = {
+			/* r0 = 0 */
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			/* prep for direct packet access via r2 */
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_4, BPF_REG_3, 1),
+			BPF_EXIT_INSN(),
+
+			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_2, 0),
+
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_7, 0x80000000, 1),
+			BPF_EXIT_INSN(),
+
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+		.retval = 2,
+		.data = { 1, 0, 0, 0, 0, 0, 0, 1, },
+	},
+	{
+		"jset: known const compare",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.retval_unpriv = 1,
+		.result_unpriv = ACCEPT,
+		.retval = 1,
+		.result = ACCEPT,
+	},
+	{
+		"jset: known const compare bad",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.errstr_unpriv = "!read_ok",
 		.result_unpriv = REJECT,
 		.errstr = "!read_ok",
 		.result = REJECT,
 	},
+	{
+		"jset: unknown const compare taken",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_prandom_u32),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.errstr_unpriv = "!read_ok",
+		.result_unpriv = REJECT,
+		.errstr = "!read_ok",
+		.result = REJECT,
+	},
+	{
+		"jset: unknown const compare not taken",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_prandom_u32),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.errstr_unpriv = "!read_ok",
+		.result_unpriv = REJECT,
+		.errstr = "!read_ok",
+		.result = REJECT,
+	},
+	{
+		"jset: half-known const compare",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_prandom_u32),
+			BPF_ALU64_IMM(BPF_OR, BPF_REG_0, 2),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.result_unpriv = ACCEPT,
+		.result = ACCEPT,
+	},
+	{
+		"jset: range",
+		.insns = {
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_prandom_u32),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xff),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0xf0, 3),
+			BPF_JMP_IMM(BPF_JLT, BPF_REG_1, 0x10, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_EXIT_INSN(),
+			BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0x10, 1),
+			BPF_EXIT_INSN(),
+			BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0x10, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.result_unpriv = ACCEPT,
+		.result = ACCEPT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
@@ -14408,16 +14669,42 @@ out:
 	return ret;
 }
 
+static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val,
+			    void *data, size_t size_data)
+{
+	__u8 tmp[TEST_DATA_LEN << 2];
+	__u32 size_tmp = sizeof(tmp);
+	uint32_t retval;
+	int err;
+
+	if (unpriv)
+		set_admin(true);
+	err = bpf_prog_test_run(fd_prog, 1, data, size_data,
+				tmp, &size_tmp, &retval, NULL);
+	if (unpriv)
+		set_admin(false);
+	if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
+		printf("Unexpected bpf_prog_test_run error ");
+		return err;
+	}
+	if (!err && retval != expected_val &&
+	    expected_val != POINTER_VALUE) {
+		printf("FAIL retval %d != %d ", retval, expected_val);
+		return 1;
+	}
+
+	return 0;
+}
+
 static void do_test_single(struct bpf_test *test, bool unpriv,
 			   int *passes, int *errors)
 {
 	int fd_prog, expected_ret, alignment_prevented_execution;
 	int prog_len, prog_type = test->prog_type;
 	struct bpf_insn *prog = test->insns;
+	int run_errs, run_successes;
 	int map_fds[MAX_NR_MAPS];
 	const char *expected_err;
-	uint32_t expected_val;
-	uint32_t retval;
 	__u32 pflags;
 	int i, err;
 
@@ -14441,8 +14728,6 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		       test->result_unpriv : test->result;
 	expected_err = unpriv && test->errstr_unpriv ?
 		       test->errstr_unpriv : test->errstr;
-	expected_val = unpriv && test->retval_unpriv ?
-		       test->retval_unpriv : test->retval;
 
 	alignment_prevented_execution = 0;
 
@@ -14454,10 +14739,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		}
 #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 		if (fd_prog >= 0 &&
-		    (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)) {
+		    (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS))
 			alignment_prevented_execution = 1;
-			goto test_ok;
-		}
 #endif
 	} else {
 		if (fd_prog >= 0) {
@@ -14471,33 +14754,67 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		}
 	}
 
-	if (fd_prog >= 0) {
+	if (test->insn_processed) {
-		__u8 tmp[TEST_DATA_LEN << 2];
+		uint32_t insn_processed;
-		__u32 size_tmp = sizeof(tmp);
+		char *proc;
 
-		if (unpriv)
+		proc = strstr(bpf_vlog, "processed ");
-			set_admin(true);
+		insn_processed = atoi(proc + 10);
-		err = bpf_prog_test_run(fd_prog, 1, test->data,
+		if (test->insn_processed != insn_processed) {
-					sizeof(test->data), tmp, &size_tmp,
+			printf("FAIL\nUnexpected insn_processed %u vs %u\n",
-					&retval, NULL);
+			       insn_processed, test->insn_processed);
-		if (unpriv)
-			set_admin(false);
-		if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
-			printf("Unexpected bpf_prog_test_run error\n");
-			goto fail_log;
-		}
-		if (!err && retval != expected_val &&
-		    expected_val != POINTER_VALUE) {
-			printf("FAIL retval %d != %d\n", retval, expected_val);
 			goto fail_log;
 		}
 	}
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+
-test_ok:
+	run_errs = 0;
-#endif
+	run_successes = 0;
-	(*passes)++;
+	if (!alignment_prevented_execution && fd_prog >= 0) {
-	printf("OK%s\n", alignment_prevented_execution ?
+		uint32_t expected_val;
-	       " (NOTE: not executed due to unknown alignment)" : "");
+		int i;
+
+		if (!test->runs) {
+			expected_val = unpriv && test->retval_unpriv ?
+				test->retval_unpriv : test->retval;
+
+			err = do_prog_test_run(fd_prog, unpriv, expected_val,
+					       test->data, sizeof(test->data));
+			if (err)
+				run_errs++;
+			else
+				run_successes++;
+		}
+
+		for (i = 0; i < test->runs; i++) {
+			if (unpriv && test->retvals[i].retval_unpriv)
+				expected_val = test->retvals[i].retval_unpriv;
+			else
+				expected_val = test->retvals[i].retval;
+
+			err = do_prog_test_run(fd_prog, unpriv, expected_val,
+					       test->retvals[i].data,
+					       sizeof(test->retvals[i].data));
+			if (err) {
+				printf("(run %d/%d) ", i + 1, test->runs);
+				run_errs++;
+			} else {
+				run_successes++;
+			}
+		}
+	}
+
+	if (!run_errs) {
+		(*passes)++;
+		if (run_successes > 1)
+			printf("%d cases ", run_successes);
+		printf("OK");
+		if (alignment_prevented_execution)
+			printf(" (NOTE: not executed due to unknown alignment)");
+		printf("\n");
+	} else {
+		printf("\n");
+		goto fail_log;
+	}
 close_fds:
 	close(fd_prog);
 	for (i = 0; i < MAX_NR_MAPS; i++)