sync with latest bpf-next (#6)

The following two new files are added: README.rst bpf_prog_linfo.c Signed-off-by: Yonghong Song <yhs@fb.com>
2026-03-20 16:29:07 +08:00 · 2019-01-03 12:44:33 -08:00
parent 556e0a0def
commit 07a48dcda2
12 changed files with 1018 additions and 314 deletions
--- a/include/uapi/linux/bpf.h
+++ b/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,
@@ -232,6 +240,20 @@ enum bpf_attach_type {
 */
 #define BPF_F_STRICT_ALIGNMENT	(1U << 0)

+/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROF_LOAD command, the
+ * verifier will allow any alignment whatsoever.  On platforms
+ * with strict alignment requirements for loads ands stores (such
+ * as sparc and mips) the verifier validates that all loads and
+ * stores provably follow this requirement.  This flag turns that
+ * checking and enforcement off.
+ *
+ * It is mostly used for testing when we want to validate the
+ * context and memory access aspects of the verifier, but because
+ * of an unaligned access the alignment check would trigger before
+ * the one we are interested in.
+ */
+#define BPF_F_ANY_ALIGNMENT	(1U << 1)
+
 /* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
 #define BPF_PSEUDO_MAP_FD	1

@@ -329,7 +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 */
@@ -342,6 +364,9 @@ union bpf_attr {
 		__u32		func_info_rec_size;	/* userspace bpf_func_info size */
 		__aligned_u64	func_info;	/* func info */
 		__u32		func_info_cnt;	/* number of bpf_func_info records */
+		__u32		line_info_rec_size;	/* userspace bpf_line_info size */
+		__aligned_u64	line_info;	/* line info */
+		__u32		line_info_cnt;	/* number of bpf_line_info records */
 	};

 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -360,8 +385,11 @@ union bpf_attr {
 	struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */
 		__u32		prog_fd;
 		__u32		retval;
-		__u32		data_size_in;
-		__u32		data_size_out;
+		__u32		data_size_in;	/* input: len of data_in */
+		__u32		data_size_out;	/* input/output: len of data_out
+						 *   returns ENOSPC if data_out
+						 *   is too small.
+						 */
 		__aligned_u64	data_in;
 		__aligned_u64	data_out;
 		__u32		repeat;
@@ -482,18 +510,6 @@ union bpf_attr {
 * 	Return
 * 		0 on success, or a negative error in case of failure.
 *
- * int bpf_map_pop_elem(struct bpf_map *map, void *value)
- * 	Description
- * 		Pop an element from *map*.
- * Return
- * 		0 on success, or a negative error in case of failure.
- *
- * int bpf_map_peek_elem(struct bpf_map *map, void *value)
- * 	Description
- * 		Get an element from *map* without removing it.
- * Return
- * 		0 on success, or a negative error in case of failure.
- *
 * int bpf_probe_read(void *dst, u32 size, const void *src)
 * 	Description
 * 		For tracing programs, safely attempt to read *size* bytes from
@@ -1917,9 +1933,9 @@ union bpf_attr {
 *		is set to metric from route (IPv4/IPv6 only), and ifindex
 *		is set to the device index of the nexthop from the FIB lookup.
 *
- *             *plen* argument is the size of the passed in struct.
- *             *flags* argument can be a combination of one or more of the
- *             following values:
+ *		*plen* argument is the size of the passed in struct.
+ *		*flags* argument can be a combination of one or more of the
+ *		following values:
 *
 *		**BPF_FIB_LOOKUP_DIRECT**
 *			Do a direct table lookup vs full lookup using FIB
@@ -1928,9 +1944,9 @@ union bpf_attr {
 *			Perform lookup from an egress perspective (default is
 *			ingress).
 *
- *             *ctx* is either **struct xdp_md** for XDP programs or
- *             **struct sk_buff** tc cls_act programs.
- *     Return
+ *		*ctx* is either **struct xdp_md** for XDP programs or
+ *		**struct sk_buff** tc cls_act programs.
+ *	Return
 *		* < 0 if any input argument is invalid
 *		*   0 on success (packet is forwarded, nexthop neighbor exists)
 *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
@@ -2075,8 +2091,8 @@ union bpf_attr {
 *		translated to a keycode using the rc keymap, and reported as
 *		an input key down event. After a period a key up event is
 *		generated. This period can be extended by calling either
- *		**bpf_rc_keydown** () again with the same values, or calling
- *		**bpf_rc_repeat** ().
+ *		**bpf_rc_keydown**\ () again with the same values, or calling
+ *		**bpf_rc_repeat**\ ().
 *
 *		Some protocols include a toggle bit, in case the button	was
 *		released and pressed again between consecutive scancodes.
@@ -2159,29 +2175,30 @@ union bpf_attr {
 *		The *flags* meaning is specific for each map type,
 *		and has to be 0 for cgroup local storage.
 *
- *		Depending on the bpf program type, a local storage area
- *		can be shared between multiple instances of the bpf program,
+ *		Depending on the BPF program type, a local storage area
+ *		can be shared between multiple instances of the BPF program,
 *		running simultaneously.
 *
 *		A user should care about the synchronization by himself.
- *		For example, by using the BPF_STX_XADD instruction to alter
+ *		For example, by using the **BPF_STX_XADD** instruction to alter
 *		the shared data.
 *	Return
- *		Pointer to the local storage area.
+ *		A pointer to the local storage area.
 *
 * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
 *	Description
- *		Select a SO_REUSEPORT sk from a	BPF_MAP_TYPE_REUSEPORT_ARRAY map
- *		It checks the selected sk is matching the incoming
- *		request in the skb.
+ *		Select a **SO_REUSEPORT** socket from a
+ *		**BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*.
+ *		It checks the selected socket is matching the incoming
+ *		request in the socket buffer.
 *	Return
 *		0 on success, or a negative error in case of failure.
 *
- * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
 *	Description
 *		Look for TCP socket matching *tuple*, optionally in a child
 *		network namespace *netns*. The return value must be checked,
- *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *		and if non-**NULL**, released via **bpf_sk_release**\ ().
 *
 *		The *ctx* should point to the context of the program, such as
 *		the skb or socket (depending on the hook in use). This is used
@@ -2194,12 +2211,14 @@ union bpf_attr {
 *		**sizeof**\ (*tuple*\ **->ipv6**)
 *			Look for an IPv6 socket.
 *
- *		If the *netns* is zero, then the socket lookup table in the
- *		netns associated with the *ctx* will be used. For the TC hooks,
- *		this in the netns of the device in the skb. For socket hooks,
- *		this in the netns of the socket. If *netns* is non-zero, then
- *		it specifies the ID of the netns relative to the netns
- *		associated with the *ctx*.
+ *		If the *netns* is a negative signed 32-bit integer, then the
+ *		socket lookup table in the netns associated with the *ctx* will
+ *		will be used. For the TC hooks, this is the netns of the device
+ *		in the skb. For socket hooks, this is the netns of the socket.
+ *		If *netns* is any other signed 32-bit value greater than or
+ *		equal to zero then it specifies the ID of the netns relative to
+ *		the netns associated with the *ctx*. *netns* values beyond the
+ *		range of 32-bit integers are reserved for future use.
 *
 *		All values for *flags* are reserved for future usage, and must
 *		be left at zero.
@@ -2207,15 +2226,15 @@ union bpf_attr {
 *		This helper is available only if the kernel was compiled with
 *		**CONFIG_NET** configuration option.
 *	Return
- *		Pointer to *struct bpf_sock*, or NULL in case of failure.
- *		For sockets with reuseport option, *struct bpf_sock*
- *		return is from reuse->socks[] using hash of the packet.
+ *		Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ *		For sockets with reuseport option, the **struct bpf_sock**
+ *		result is from **reuse->socks**\ [] using the hash of the tuple.
 *
- * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
+ * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
 *	Description
 *		Look for UDP socket matching *tuple*, optionally in a child
 *		network namespace *netns*. The return value must be checked,
- *		and if non-NULL, released via **bpf_sk_release**\ ().
+ *		and if non-**NULL**, released via **bpf_sk_release**\ ().
 *
 *		The *ctx* should point to the context of the program, such as
 *		the skb or socket (depending on the hook in use). This is used
@@ -2228,12 +2247,14 @@ union bpf_attr {
 *		**sizeof**\ (*tuple*\ **->ipv6**)
 *			Look for an IPv6 socket.
 *
- *		If the *netns* is zero, then the socket lookup table in the
- *		netns associated with the *ctx* will be used. For the TC hooks,
- *		this in the netns of the device in the skb. For socket hooks,
- *		this in the netns of the socket. If *netns* is non-zero, then
- *		it specifies the ID of the netns relative to the netns
- *		associated with the *ctx*.
+ *		If the *netns* is a negative signed 32-bit integer, then the
+ *		socket lookup table in the netns associated with the *ctx* will
+ *		will be used. For the TC hooks, this is the netns of the device
+ *		in the skb. For socket hooks, this is the netns of the socket.
+ *		If *netns* is any other signed 32-bit value greater than or
+ *		equal to zero then it specifies the ID of the netns relative to
+ *		the netns associated with the *ctx*. *netns* values beyond the
+ *		range of 32-bit integers are reserved for future use.
 *
 *		All values for *flags* are reserved for future usage, and must
 *		be left at zero.
@@ -2241,33 +2262,71 @@ union bpf_attr {
 *		This helper is available only if the kernel was compiled with
 *		**CONFIG_NET** configuration option.
 *	Return
- *		Pointer to *struct bpf_sock*, or NULL in case of failure.
- *		For sockets with reuseport option, *struct bpf_sock*
- *		return is from reuse->socks[] using hash of the packet.
+ *		Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ *		For sockets with reuseport option, the **struct bpf_sock**
+ *		result is from **reuse->socks**\ [] using the hash of the tuple.
 *
- * int bpf_sk_release(struct bpf_sock *sk)
+ * int bpf_sk_release(struct bpf_sock *sock)
 *	Description
- *		Release the reference held by *sock*. *sock* must be a non-NULL
- *		pointer that was returned from bpf_sk_lookup_xxx\ ().
+ *		Release the reference held by *sock*. *sock* must be a
+ *		non-**NULL** pointer that was returned from
+ *		**bpf_sk_lookup_xxx**\ ().
 *	Return
 *		0 on success, or a negative error in case of failure.
 *
+ * int bpf_map_pop_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Pop an element from *map*.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_peek_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Get an element from *map* without removing it.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
 * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags)
 *	Description
- *		For socket policies, insert *len* bytes into msg at offset
+ *		For socket policies, insert *len* bytes into *msg* at offset
 *		*start*.
 *
 *		If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
- *		*msg* it may want to insert metadata or options into the msg.
+ *		*msg* it may want to insert metadata or options into the *msg*.
 *		This can later be read and used by any of the lower layer BPF
 *		hooks.
 *
 *		This helper may fail if under memory pressure (a malloc
 *		fails) in these cases BPF programs will get an appropriate
 *		error and BPF programs will need to handle them.
- *
 *	Return
 *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 pop, u64 flags)
+ *	Description
+ *		Will remove *pop* bytes from a *msg* starting at byte *start*.
+ *		This may result in **ENOMEM** errors under certain situations if
+ *		an allocation and copy are required due to a full ring buffer.
+ *		However, the helper will try to avoid doing the allocation
+ *		if possible. Other errors can occur if input parameters are
+ *		invalid either due to *start* byte not being valid part of *msg*
+ *		payload and/or *pop* value being to large.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y)
+ *	Description
+ *		This helper is used in programs implementing IR decoding, to
+ *		report a successfully decoded pointer movement.
+ *
+ *		The *ctx* should point to the lirc sample as passed into
+ *		the program.
+ *
+ *		This helper is only available is the kernel was compiled with
+ *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ *		"**y**".
+ *	Return
+ *		0
 */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2360,7 +2419,9 @@ union bpf_attr {
 	FN(map_push_elem),		\
 	FN(map_pop_elem),		\
 	FN(map_peek_elem),		\
-	FN(msg_push_data),
+	FN(msg_push_data),		\
+	FN(msg_pop_data),		\
+	FN(rc_pointer_rel),

 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
 * function eBPF program intends to call
@@ -2416,6 +2477,9 @@ enum bpf_func_id {
 /* BPF_FUNC_perf_event_output for sk_buff input context. */
 #define BPF_F_CTXLEN_MASK		(0xfffffULL << 32)

+/* Current network namespace */
+#define BPF_F_CURRENT_NETNS		(-1L)
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
@@ -2433,6 +2497,12 @@ enum bpf_lwt_encap_mode {
 	BPF_LWT_ENCAP_SEG6_INLINE
 };

+#define __bpf_md_ptr(type, name)	\
+union {					\
+	type name;			\
+	__u64 :64;			\
+} __attribute__((aligned(8)))
+
 /* user accessible mirror of in-kernel sk_buff.
 * new fields can only be added to the end of this structure
 */
@@ -2467,8 +2537,9 @@ struct __sk_buff {
 	/* ... here. */

 	__u32 data_meta;
-	struct bpf_flow_keys *flow_keys;
+	__bpf_md_ptr(struct bpf_flow_keys *, flow_keys);
 	__u64 tstamp;
+	__u32 wire_len;
 };

 struct bpf_tunnel_key {
@@ -2584,8 +2655,8 @@ enum sk_action {
 * be added to the end of this structure
 */
 struct sk_msg_md {
-	void *data;
-	void *data_end;
+	__bpf_md_ptr(void *, data);
+	__bpf_md_ptr(void *, data_end);

 	__u32 family;
 	__u32 remote_ip4;	/* Stored in network byte order */
@@ -2594,6 +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 {
@@ -2601,8 +2673,9 @@ struct sk_reuseport_md {
 	 * Start of directly accessible data. It begins from
 	 * the tcp/udp header.
 	 */
-	void *data;
-	void *data_end;		/* End of directly accessible data */
+	__bpf_md_ptr(void *, data);
+	/* End of directly accessible data */
+	__bpf_md_ptr(void *, data_end);
 	/*
 	 * Total length of packet (starting from the tcp/udp header).
 	 * Note that the directly accessible bytes (data_end - data)
@@ -2646,7 +2719,15 @@ struct bpf_prog_info {
 	__u32 btf_id;
 	__u32 func_info_rec_size;
 	__aligned_u64 func_info;
-	__u32 func_info_cnt;
+	__u32 nr_func_info;
+	__u32 nr_line_info;
+	__aligned_u64 line_info;
+	__aligned_u64 jited_line_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 {
@@ -2959,8 +3040,18 @@ struct bpf_flow_keys {
 };

 struct bpf_func_info {
-	__u32	insn_offset;
+	__u32	insn_off;
 	__u32	type_id;
 };

+#define BPF_LINE_INFO_LINE_NUM(line_col)	((line_col) >> 10)
+#define BPF_LINE_INFO_LINE_COL(line_col)	((line_col) & 0x3ff)
+
+struct bpf_line_info {
+	__u32	insn_off;
+	__u32	file_name_off;
+	__u32	line_off;
+	__u32	line_col;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
--- a/include/uapi/linux/btf.h
+++ b/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").
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -155,7 +155,7 @@ enum nlmsgerr_attrs {
 #define NETLINK_LIST_MEMBERSHIPS	9
 #define NETLINK_CAP_ACK			10
 #define NETLINK_EXT_ACK			11
-#define NETLINK_DUMP_STRICT_CHK		12
+#define NETLINK_GET_STRICT_CHK		12

 struct nl_pktinfo {
 	__u32	group;