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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2019-02-16

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

The main changes are:

1) numerous libbpf API improvements, from Andrii, Andrey, Yonghong.

2) test all bpf progs in alu32 mode, from Jiong.

3) skb->sk access and bpf_sk_fullsock(), bpf_tcp_sock() helpers, from Martin.

4) support for IP encap in lwt bpf progs, from Peter.

5) remove XDP_QUERY_XSK_UMEM dead code, from Jan.
====================

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

71 files changed, 1658 insertions, 182 deletions

diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 27153bb816ac..4f2188845dd8 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -16,7 +16,7 @@ SYNOPSIS
 
 	**bpftool** **version**
 
-	*OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** }
+	*OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** | **feature** }
 
 	*OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** }
 	| { **-j** | **--json** } [{ **-p** | **--pretty** }] }
@@ -34,6 +34,8 @@ SYNOPSIS
 
 	*NET-COMMANDS* := { **show** | **list** | **help** }
 
+	*FEATURE-COMMANDS* := { **probe** | **help** }
+
 DESCRIPTION
 ===========
 	*bpftool* allows for inspection and simple modification of BPF objects
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1777fa0c61e4..bcdd2474eee7 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2016,6 +2016,19 @@ union bpf_attr {
  *			Only works if *skb* contains an IPv6 packet. Insert a
  *			Segment Routing Header (**struct ipv6_sr_hdr**) inside
  *			the IPv6 header.
+ *		**BPF_LWT_ENCAP_IP**
+ *			IP encapsulation (GRE/GUE/IPIP/etc). The outer header
+ *			must be IPv4 or IPv6, followed by zero or more
+ *			additional headers, up to LWT_BPF_MAX_HEADROOM total
+ *			bytes in all prepended headers. Please note that
+ *			if skb_is_gso(skb) is true, no more than two headers
+ *			can be prepended, and the inner header, if present,
+ *			should be either GRE or UDP/GUE.
+ *
+ *		BPF_LWT_ENCAP_SEG6*** types can be called by bpf programs of
+ *		type BPF_PROG_TYPE_LWT_IN; BPF_LWT_ENCAP_IP type can be called
+ *		by bpf programs of types BPF_PROG_TYPE_LWT_IN and
+ *		BPF_PROG_TYPE_LWT_XMIT.
  *
  * 		A call to this helper is susceptible to change the underlaying
  * 		packet buffer. Therefore, at load time, all checks on pointers
@@ -2329,6 +2342,23 @@ union bpf_attr {
  *		"**y**".
  *	Return
  *		0
+ *
+ * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
+ *	Description
+ *		This helper gets a **struct bpf_sock** pointer such
+ *		that all the fields in bpf_sock can be accessed.
+ *	Return
+ *		A **struct bpf_sock** pointer on success, or NULL in
+ *		case of failure.
+ *
+ * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
+ *	Description
+ *		This helper gets a **struct bpf_tcp_sock** pointer from a
+ *		**struct bpf_sock** pointer.
+ *
+ *	Return
+ *		A **struct bpf_tcp_sock** pointer on success, or NULL in
+ *		case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2425,7 +2455,9 @@ union bpf_attr {
 	FN(msg_pop_data),		\
 	FN(rc_pointer_rel),		\
 	FN(spin_lock),			\
-	FN(spin_unlock),
+	FN(spin_unlock),		\
+	FN(sk_fullsock),		\
+	FN(tcp_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2498,7 +2530,8 @@ enum bpf_hdr_start_off {
 /* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */
 enum bpf_lwt_encap_mode {
 	BPF_LWT_ENCAP_SEG6,
-	BPF_LWT_ENCAP_SEG6_INLINE
+	BPF_LWT_ENCAP_SEG6_INLINE,
+	BPF_LWT_ENCAP_IP,
 };
 
 #define __bpf_md_ptr(type, name)	\
@@ -2545,6 +2578,7 @@ struct __sk_buff {
 	__u64 tstamp;
 	__u32 wire_len;
 	__u32 gso_segs;
+	__bpf_md_ptr(struct bpf_sock *, sk);
 };
 
 struct bpf_tunnel_key {
@@ -2586,7 +2620,15 @@ enum bpf_ret_code {
 	BPF_DROP = 2,
 	/* 3-6 reserved */
 	BPF_REDIRECT = 7,
-	/* >127 are reserved for prog type specific return codes */
+	/* >127 are reserved for prog type specific return codes.
+	 *
+	 * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and
+	 *    BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been
+	 *    changed and should be routed based on its new L3 header.
+	 *    (This is an L3 redirect, as opposed to L2 redirect
+	 *    represented by BPF_REDIRECT above).
+	 */
+	BPF_LWT_REROUTE = 128,
 };
 
 struct bpf_sock {
@@ -2596,14 +2638,52 @@ struct bpf_sock {
 	__u32 protocol;
 	__u32 mark;
 	__u32 priority;
-	__u32 src_ip4;		/* Allows 1,2,4-byte read.
-				 * Stored in network byte order.
+	/* IP address also allows 1 and 2 bytes access */
+	__u32 src_ip4;
+	__u32 src_ip6[4];
+	__u32 src_port;		/* host byte order */
+	__u32 dst_port;		/* network byte order */
+	__u32 dst_ip4;
+	__u32 dst_ip6[4];
+	__u32 state;
+};
+
+struct bpf_tcp_sock {
+	__u32 snd_cwnd;		/* Sending congestion window		*/
+	__u32 srtt_us;		/* smoothed round trip time << 3 in usecs */
+	__u32 rtt_min;
+	__u32 snd_ssthresh;	/* Slow start size threshold		*/
+	__u32 rcv_nxt;		/* What we want to receive next		*/
+	__u32 snd_nxt;		/* Next sequence we send		*/
+	__u32 snd_una;		/* First byte we want an ack for	*/
+	__u32 mss_cache;	/* Cached effective mss, not including SACKS */
+	__u32 ecn_flags;	/* ECN status bits.			*/
+	__u32 rate_delivered;	/* saved rate sample: packets delivered */
+	__u32 rate_interval_us;	/* saved rate sample: time elapsed */
+	__u32 packets_out;	/* Packets which are "in flight"	*/
+	__u32 retrans_out;	/* Retransmitted packets out		*/
+	__u32 total_retrans;	/* Total retransmits for entire connection */
+	__u32 segs_in;		/* RFC4898 tcpEStatsPerfSegsIn
+				 * total number of segments in.
 				 */
-	__u32 src_ip6[4];	/* Allows 1,2,4-byte read.
-				 * Stored in network byte order.
+	__u32 data_segs_in;	/* RFC4898 tcpEStatsPerfDataSegsIn
+				 * total number of data segments in.
+				 */
+	__u32 segs_out;		/* RFC4898 tcpEStatsPerfSegsOut
+				 * The total number of segments sent.
+				 */
+	__u32 data_segs_out;	/* RFC4898 tcpEStatsPerfDataSegsOut
+				 * total number of data segments sent.
+				 */
+	__u32 lost_out;		/* Lost packets			*/
+	__u32 sacked_out;	/* SACK'd packets			*/
+	__u64 bytes_received;	/* RFC4898 tcpEStatsAppHCThruOctetsReceived
+				 * sum(delta(rcv_nxt)), or how many bytes
+				 * were acked.
 				 */
-	__u32 src_port;		/* Allows 4-byte read.
-				 * Stored in host byte order
+	__u64 bytes_acked;	/* RFC4898 tcpEStatsAppHCThruOctetsAcked
+				 * sum(delta(snd_una)), or how many bytes
+				 * were acked.
 				 */
 };
 
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index d6533828123a..5b225ff63b48 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -925,6 +925,7 @@ enum {
 enum {
 	LINK_XSTATS_TYPE_UNSPEC,
 	LINK_XSTATS_TYPE_BRIDGE,
+	LINK_XSTATS_TYPE_BOND,
 	__LINK_XSTATS_TYPE_MAX
 };
 #define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1)
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 3defad77dc7a..9cd015574e83 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -22,6 +22,7 @@
  */
 
 #include <stdlib.h>
+#include <string.h>
 #include <memory.h>
 #include <unistd.h>
 #include <asm/unistd.h>
@@ -214,23 +215,35 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 {
 	void *finfo = NULL, *linfo = NULL;
 	union bpf_attr attr;
+	__u32 log_level;
 	__u32 name_len;
 	int fd;
 
-	if (!load_attr)
+	if (!load_attr || !log_buf != !log_buf_sz)
+		return -EINVAL;
+
+	log_level = load_attr->log_level;
+	if (log_level > 2 || (log_level && !log_buf))
 		return -EINVAL;
 
 	name_len = load_attr->name ? strlen(load_attr->name) : 0;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = load_attr->prog_type;
 	attr.expected_attach_type = load_attr->expected_attach_type;
 	attr.insn_cnt = (__u32)load_attr->insns_cnt;
 	attr.insns = ptr_to_u64(load_attr->insns);
 	attr.license = ptr_to_u64(load_attr->license);
-	attr.log_buf = ptr_to_u64(NULL);
-	attr.log_size = 0;
-	attr.log_level = 0;
+
+	attr.log_level = log_level;
+	if (log_level) {
+		attr.log_buf = ptr_to_u64(log_buf);
+		attr.log_size = log_buf_sz;
+	} else {
+		attr.log_buf = ptr_to_u64(NULL);
+		attr.log_size = 0;
+	}
+
 	attr.kern_version = load_attr->kern_version;
 	attr.prog_ifindex = load_attr->prog_ifindex;
 	attr.prog_btf_fd = load_attr->prog_btf_fd;
@@ -286,7 +299,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 			goto done;
 	}
 
-	if (!log_buf || !log_buf_sz)
+	if (log_level || !log_buf)
 		goto done;
 
 	/* Try again with log */
@@ -327,7 +340,7 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = type;
 	attr.insn_cnt = (__u32)insns_cnt;
 	attr.insns = ptr_to_u64(insns);
@@ -347,7 +360,7 @@ int bpf_map_update_elem(int fd, const void *key, const void *value,
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
@@ -360,7 +373,7 @@ int bpf_map_lookup_elem(int fd, const void *key, void *value)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
@@ -372,7 +385,7 @@ int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
@@ -385,7 +398,7 @@ int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
@@ -397,7 +410,7 @@ int bpf_map_delete_elem(int fd, const void *key)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 
@@ -408,7 +421,7 @@ int bpf_map_get_next_key(int fd, const void *key, void *next_key)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.next_key = ptr_to_u64(next_key);
@@ -420,7 +433,7 @@ int bpf_obj_pin(int fd, const char *pathname)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.pathname = ptr_to_u64((void *)pathname);
 	attr.bpf_fd = fd;
 
@@ -431,7 +444,7 @@ int bpf_obj_get(const char *pathname)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.pathname = ptr_to_u64((void *)pathname);
 
 	return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
@@ -442,7 +455,7 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.target_fd	   = target_fd;
 	attr.attach_bpf_fd = prog_fd;
 	attr.attach_type   = type;
@@ -455,7 +468,7 @@ int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.target_fd	 = target_fd;
 	attr.attach_type = type;
 
@@ -466,7 +479,7 @@ int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.target_fd	 = target_fd;
 	attr.attach_bpf_fd = prog_fd;
 	attr.attach_type = type;
@@ -480,7 +493,7 @@ int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
 	union bpf_attr attr;
 	int ret;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.query.target_fd	= target_fd;
 	attr.query.attach_type	= type;
 	attr.query.query_flags	= query_flags;
@@ -501,7 +514,7 @@ int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
 	union bpf_attr attr;
 	int ret;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.test.prog_fd = prog_fd;
 	attr.test.data_in = ptr_to_u64(data);
 	attr.test.data_out = ptr_to_u64(data_out);
@@ -526,7 +539,7 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
 	if (!test_attr->data_out && test_attr->data_size_out > 0)
 		return -EINVAL;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.test.prog_fd = test_attr->prog_fd;
 	attr.test.data_in = ptr_to_u64(test_attr->data_in);
 	attr.test.data_out = ptr_to_u64(test_attr->data_out);
@@ -546,7 +559,7 @@ int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id)
 	union bpf_attr attr;
 	int err;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.start_id = start_id;
 
 	err = sys_bpf(BPF_PROG_GET_NEXT_ID, &attr, sizeof(attr));
@@ -561,7 +574,7 @@ int bpf_map_get_next_id(__u32 start_id, __u32 *next_id)
 	union bpf_attr attr;
 	int err;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.start_id = start_id;
 
 	err = sys_bpf(BPF_MAP_GET_NEXT_ID, &attr, sizeof(attr));
@@ -575,7 +588,7 @@ int bpf_prog_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.prog_id = id;
 
 	return sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
@@ -585,7 +598,7 @@ int bpf_map_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.map_id = id;
 
 	return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
@@ -595,7 +608,7 @@ int bpf_btf_get_fd_by_id(__u32 id)
 {
 	union bpf_attr attr;
 
-	bzero(&attr, sizeof(attr));
+	memset(&attr, 0, sizeof(attr));
 	attr.btf_id = id;
 
 	return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr,