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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-04-21

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

The main changes are:

1) Initial work on BPF Type Format (BTF) is added, which is a meta
   data format which describes the data types of BPF programs / maps.
   BTF has its roots from CTF (Compact C-Type format) with a number
   of changes to it. First use case is to provide a generic pretty
   print capability for BPF maps inspection, later work will also
   add BTF to bpftool. pahole support to convert dwarf to BTF will
   be upstreamed as well (https://github.com/iamkafai/pahole/tree/btf),
   from Martin.

2) Add a new xdp_bpf_adjust_tail() BPF helper for XDP that allows
   for changing the data_end pointer. Only shrinking is currently
   supported which helps for crafting ICMP control messages. Minor
   changes in drivers have been added where needed so they recalc
   the packet's length also when data_end was adjusted, from Nikita.

3) Improve bpftool to make it easier to feed hex bytes via cmdline
   for map operations, from Quentin.

4) Add support for various missing BPF prog types and attach types
   that have been added to kernel recently but neither to bpftool
   nor libbpf yet. Doc and bash completion updates have been added
   as well for bpftool, from Andrey.

5) Proper fix for avoiding to leak info stored in frame data on page
   reuse for the two bpf_xdp_adjust_{head,meta} helpers by disallowing
   to move the pointers into struct xdp_frame area, from Jesper.

6) Follow-up compile fix from BTF in order to include stdbool.h in
   libbpf, from Björn.

7) Few fixes in BPF sample code, that is, a typo on the netdevice
   in a comment and fixup proper dump of XDP action code in the
   tracepoint exception, from Wang and Jesper.
====================

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

Author: davem330

drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c

@@ -113,10 +113,10 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 	if (tx_avail != bp->tx_ring_size)
 		*event &= ~BNXT_RX_EVENT;
 
+	*len = xdp.data_end - xdp.data;
 	if (orig_data != xdp.data) {
 		offset = xdp.data - xdp.data_hard_start;
 		*data_ptr = xdp.data_hard_start + offset;
-		*len = xdp.data_end - xdp.data;
 	}
 	switch (act) {
 	case XDP_PASS:

drivers/net/ethernet/cavium/thunder/nicvf_main.c

@@ -538,9 +538,9 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog,
 	action = bpf_prog_run_xdp(prog, &xdp);
 	rcu_read_unlock();
 
+	len = xdp.data_end - xdp.data;
 	/* Check if XDP program has changed headers */
 	if (orig_data != xdp.data) {
-		len = xdp.data_end - xdp.data;
 		offset = orig_data - xdp.data;
 		dma_addr -= offset;
 	}

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -775,8 +775,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 
 			act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
+			length = xdp.data_end - xdp.data;
 			if (xdp.data != orig_data) {
-				length = xdp.data_end - xdp.data;
 				frags[0].page_offset = xdp.data -
 					xdp.data_hard_start;
 				va = xdp.data;

drivers/net/ethernet/netronome/nfp/nfp_net_common.c

@@ -1722,7 +1722,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 
 			act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
-			pkt_len -= xdp.data - orig_data;
+			pkt_len = xdp.data_end - xdp.data;
 			pkt_off += xdp.data - orig_data;
 
 			switch (act) {

drivers/net/tun.c

@@ -1690,6 +1690,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 			return NULL;
 		case XDP_PASS:
 			delta = orig_data - xdp.data;
+			len = xdp.data_end - xdp.data;
 			break;
 		default:
 			bpf_warn_invalid_xdp_action(act);
@@ -1710,7 +1711,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	}
 
 	skb_reserve(skb, pad - delta);
-	skb_put(skb, len + delta);
+	skb_put(skb, len);
 	get_page(alloc_frag->page);
 	alloc_frag->offset += buflen;
 

drivers/net/virtio_net.c

@@ -606,6 +606,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 		case XDP_PASS:
 			/* Recalculate length in case bpf program changed it */
 			delta = orig_data - xdp.data;
+			len = xdp.data_end - xdp.data;
 			break;
 		case XDP_TX:
 			xdpf = convert_to_xdp_frame(&xdp);
@@ -642,7 +643,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 		goto err;
 	}
 	skb_reserve(skb, headroom - delta);
-	skb_put(skb, len + delta);
+	skb_put(skb, len);
 	if (!delta) {
 		buf += header_offset;
 		memcpy(skb_vnet_hdr(skb), buf, vi->hdr_len);
@@ -757,6 +758,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			offset = xdp.data -
 					page_address(xdp_page) - vi->hdr_len;
 
+			/* recalculate len if xdp.data or xdp.data_end were
+			 * adjusted
+			 */
+			len = xdp.data_end - xdp.data;
 			/* We can only create skb based on xdp_page. */
 			if (unlikely(xdp_page != page)) {
 				rcu_read_unlock();

include/linux/bpf.h

@@ -22,6 +22,8 @@ struct perf_event;
 struct bpf_prog;
 struct bpf_map;
 struct sock;
+struct seq_file;
+struct btf;
 
 /* map is generic key/value storage optionally accesible by eBPF programs */
 struct bpf_map_ops {
@@ -43,10 +45,14 @@ struct bpf_map_ops {
 	void (*map_fd_put_ptr)(void *ptr);
 	u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
 	u32 (*map_fd_sys_lookup_elem)(void *ptr);
+	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,
+			     u32 key_type_id, u32 value_type_id);
 };
 
 struct bpf_map {
-	/* 1st cacheline with read-mostly members of which some
+	/* The first two cachelines with read-mostly members of which some
 	 * are also accessed in fast-path (e.g. ops, max_entries).
 	 */
 	const struct bpf_map_ops *ops ____cacheline_aligned;
@@ -62,10 +68,13 @@ struct bpf_map {
 	u32 pages;
 	u32 id;
 	int numa_node;
+	u32 btf_key_id;
+	u32 btf_value_id;
+	struct btf *btf;
 	bool unpriv_array;
-	/* 7 bytes hole */
+	/* 55 bytes hole */
 
-	/* 2nd cacheline with misc members to avoid false sharing
+	/* The 3rd and 4th cacheline with misc members to avoid false sharing
 	 * particularly with refcounting.
 	 */
 	struct user_struct *user ____cacheline_aligned;
@@ -100,6 +109,11 @@ static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map)
 	return container_of(map, struct bpf_offloaded_map, map);
 }
 
+static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
+{
+	return map->ops->map_seq_show_elem && map->ops->map_check_btf;
+}
+
 extern const struct bpf_map_ops bpf_map_offload_ops;
 
 /* function argument constraints */

include/linux/btf.h

@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+
+#ifndef _LINUX_BTF_H
+#define _LINUX_BTF_H 1
+
+#include <linux/types.h>
+
+struct btf;
+struct btf_type;
+union bpf_attr;
+
+extern const struct file_operations btf_fops;
+
+void btf_put(struct btf *btf);
+int btf_new_fd(const union bpf_attr *attr);
+struct btf *btf_get_by_fd(int fd);
+int btf_get_info_by_fd(const struct btf *btf,
+		       const union bpf_attr *attr,
+		       union bpf_attr __user *uattr);
+/* Figure out the size of a type_id.  If type_id is a modifier
+ * (e.g. const), it will be resolved to find out the type with size.
+ *
+ * For example:
+ * In describing "const void *",  type_id is "const" and "const"
+ * refers to "void *".  The return type will be "void *".
+ *
+ * If type_id is a simple "int", then return type will be "int".
+ *
+ * @btf: struct btf object
+ * @type_id: Find out the size of type_id. The type_id of the return
+ *           type is set to *type_id.
+ * @ret_size: It can be NULL.  If not NULL, the size of the return
+ *            type is set to *ret_size.
+ * Return: The btf_type (resolved to another type with size info if needed).
+ *         NULL is returned if type_id itself does not have size info
+ *         (e.g. void) or it cannot be resolved to another type that
+ *         has size info.
+ *         *type_id and *ret_size will not be changed in the
+ *         NULL return case.
+ */
+const struct btf_type *btf_type_id_size(const struct btf *btf,
+					u32 *type_id,
+					u32 *ret_size);
+void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
+		       struct seq_file *m);
+
+#endif

include/uapi/linux/bpf.h

@@ -95,6 +95,7 @@ enum bpf_cmd {
 	BPF_OBJ_GET_INFO_BY_FD,
 	BPF_PROG_QUERY,
 	BPF_RAW_TRACEPOINT_OPEN,
+	BPF_BTF_LOAD,
 };
 
 enum bpf_map_type {
@@ -279,6 +280,9 @@ union bpf_attr {
 					 */
 		char	map_name[BPF_OBJ_NAME_LEN];
 		__u32	map_ifindex;	/* ifindex of netdev to create on */
+		__u32	btf_fd;		/* fd pointing to a BTF type data */
+		__u32	btf_key_id;	/* BTF type_id of the key */
+		__u32	btf_value_id;	/* BTF type_id of the value */
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -363,6 +367,14 @@ union bpf_attr {
 		__u64 name;
 		__u32 prog_fd;
 	} raw_tracepoint;
+
+	struct { /* anonymous struct for BPF_BTF_LOAD */
+		__aligned_u64	btf;
+		__aligned_u64	btf_log_buf;
+		__u32		btf_size;
+		__u32		btf_log_size;
+		__u32		btf_log_level;
+	};
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:
@@ -755,6 +767,13 @@ union bpf_attr {
  *     @addr: pointer to struct sockaddr to bind socket to
  *     @addr_len: length of sockaddr structure
  *     Return: 0 on success or negative error code
+ *
+ * int bpf_xdp_adjust_tail(xdp_md, delta)
+ *     Adjust the xdp_md.data_end by delta. Only shrinking of packet's
+ *     size is supported.
+ *     @xdp_md: pointer to xdp_md
+ *     @delta: A negative integer to be added to xdp_md.data_end
+ *     Return: 0 on success or negative on error
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -821,7 +840,8 @@ union bpf_attr {
 	FN(msg_apply_bytes),		\
 	FN(msg_cork_bytes),		\
 	FN(msg_pull_data),		\
-	FN(bind),
+	FN(bind),			\
+	FN(xdp_adjust_tail),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

include/uapi/linux/btf.h

@@ -0,0 +1,130 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (c) 2018 Facebook */
+#ifndef _UAPI__LINUX_BTF_H__
+#define _UAPI__LINUX_BTF_H__
+
+#include <linux/types.h>
+
+#define BTF_MAGIC	0xeB9F
+#define BTF_MAGIC_SWAP	0x9FeB
+#define BTF_VERSION	1
+#define BTF_FLAGS_COMPR	0x01
+
+struct btf_header {
+	__u16	magic;
+	__u8	version;
+	__u8	flags;
+
+	__u32	parent_label;
+	__u32	parent_name;
+
+	/* All offsets are in bytes relative to the end of this header */
+	__u32	label_off;	/* offset of label section	*/
+	__u32	object_off;	/* offset of data object section*/
+	__u32	func_off;	/* offset of function section	*/
+	__u32	type_off;	/* offset of type section	*/
+	__u32	str_off;	/* offset of string section	*/
+	__u32	str_len;	/* length of string section	*/
+};
+
+/* Max # of type identifier */
+#define BTF_MAX_TYPE	0x7fffffff
+/* Max offset into the string section */
+#define BTF_MAX_NAME_OFFSET	0x7fffffff
+/* Max # of struct/union/enum members or func args */
+#define BTF_MAX_VLEN	0xffff
+
+/* The type id is referring to a parent BTF */
+#define BTF_TYPE_PARENT(id)	(((id) >> 31) & 0x1)
+#define BTF_TYPE_ID(id)		((id) & BTF_MAX_TYPE)
+
+/* String is in the ELF string section */
+#define BTF_STR_TBL_ELF_ID(ref)	(((ref) >> 31) & 0x1)
+#define BTF_STR_OFFSET(ref)	((ref) & BTF_MAX_NAME_OFFSET)
+
+struct btf_type {
+	__u32 name;
+	/* "info" bits arrangement
+	 * bits  0-15: vlen (e.g. # of struct's members)
+	 * bits 16-23: unused
+	 * bits 24-28: kind (e.g. int, ptr, array...etc)
+	 * bits 29-30: unused
+	 * bits    31: root
+	 */
+	__u32 info;
+	/* "size" is used by INT, ENUM, STRUCT and UNION.
+	 * "size" tells the size of the type it is describing.
+	 *
+	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT.
+	 * "type" is a type_id referring to another type.
+	 */
+	union {
+		__u32 size;
+		__u32 type;
+	};
+};
+
+#define BTF_INFO_KIND(info)	(((info) >> 24) & 0x1f)
+#define BTF_INFO_ISROOT(info)	(!!(((info) >> 24) & 0x80))
+#define BTF_INFO_VLEN(info)	((info) & 0xffff)
+
+#define BTF_KIND_UNKN		0	/* Unknown	*/
+#define BTF_KIND_INT		1	/* Integer	*/
+#define BTF_KIND_PTR		2	/* Pointer	*/
+#define BTF_KIND_ARRAY		3	/* Array	*/
+#define BTF_KIND_STRUCT		4	/* Struct	*/
+#define BTF_KIND_UNION		5	/* Union	*/
+#define BTF_KIND_ENUM		6	/* Enumeration	*/
+#define BTF_KIND_FWD		7	/* Forward	*/
+#define BTF_KIND_TYPEDEF	8	/* Typedef	*/
+#define BTF_KIND_VOLATILE	9	/* Volatile	*/
+#define BTF_KIND_CONST		10	/* Const	*/
+#define BTF_KIND_RESTRICT	11	/* Restrict	*/
+#define BTF_KIND_MAX		11
+#define NR_BTF_KINDS		12
+
+/* For some specific BTF_KIND, "struct btf_type" is immediately
+ * followed by extra data.
+ */
+
+/* BTF_KIND_INT is followed by a u32 and the following
+ * is the 32 bits arrangement:
+ */
+#define BTF_INT_ENCODING(VAL)	(((VAL) & 0xff000000) >> 24)
+#define BTF_INT_OFFSET(VAL)	(((VAL  & 0x00ff0000)) >> 16)
+#define BTF_INT_BITS(VAL)	((VAL)  & 0x0000ffff)
+
+/* Attributes stored in the BTF_INT_ENCODING */
+#define BTF_INT_SIGNED	0x1
+#define BTF_INT_CHAR	0x2
+#define BTF_INT_BOOL	0x4
+#define BTF_INT_VARARGS	0x8
+
+/* BTF_KIND_ENUM is followed by multiple "struct btf_enum".
+ * The exact number of btf_enum is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_enum {
+	__u32	name;
+	__s32	val;
+};
+
+/* BTF_KIND_ARRAY is followed by one "struct btf_array" */
+struct btf_array {
+	__u32	type;
+	__u32	index_type;
+	__u32	nelems;
+};
+
+/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed
+ * by multiple "struct btf_member".  The exact number
+ * of btf_member is stored in the vlen (of the info in
+ * "struct btf_type").
+ */
+struct btf_member {
+	__u32	name;
+	__u32	type;
+	__u32	offset;	/* offset in bits */
+};
+
+#endif /* _UAPI__LINUX_BTF_H__ */

kernel/bpf/Makefile

@@ -4,6 +4,7 @@ obj-y := core.o
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
+obj-$(CONFIG_BPF_SYSCALL) += btf.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
 obj-$(CONFIG_BPF_SYSCALL) += cpumap.o