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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-10-21

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

The main changes are:

1) Implement two new kind of BPF maps, that is, queue and stack
   map along with new peek, push and pop operations, from Mauricio.

2) Add support for MSG_PEEK flag when redirecting into an ingress
   psock sk_msg queue, and add a new helper bpf_msg_push_data() for
   insert data into the message, from John.

3) Allow for BPF programs of type BPF_PROG_TYPE_CGROUP_SKB to use
   direct packet access for __skb_buff, from Song.

4) Use more lightweight barriers for walking perf ring buffer for
   libbpf and perf tool as well. Also, various fixes and improvements
   from verifier side, from Daniel.

5) Add per-symbol visibility for DSO in libbpf and hide by default
   global symbols such as netlink related functions, from Andrey.

6) Two improvements to nfp's BPF offload to check vNIC capabilities
   in case prog is shared with multiple vNICs and to protect against
   mis-initializing atomic counters, from Jakub.

7) Fix for bpftool to use 4 context mode for the nfp disassembler,
   also from Jakub.

8) Fix a return value comparison in test_libbpf.sh and add several
   bpftool improvements in bash completion, documentation of bpf fs
   restrictions and batch mode summary print, from Quentin.

9) Fix a file resource leak in BPF selftest's load_kallsyms()
   helper, from Peng.

10) Fix an unused variable warning in map_lookup_and_delete_elem(),
    from Alexei.

11) Fix bpf_skb_adjust_room() signature in BPF UAPI helper doc,
    from Nicolas.

12) Add missing executables to .gitignore in BPF selftests, from Anders.
====================

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

2 files changed, 181 insertions, 6 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 1a3ac6c46873..35c6933c2622 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2297,6 +2297,137 @@ static const struct bpf_func_proto bpf_msg_pull_data_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
+	   u32, len, u64, flags)
+{
+	struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge;
+	u32 new, i = 0, l, space, copy = 0, offset = 0;
+	u8 *raw, *to, *from;
+	struct page *page;
+
+	if (unlikely(flags))
+		return -EINVAL;
+
+	/* First find the starting scatterlist element */
+	i = msg->sg.start;
+	do {
+		l = sk_msg_elem(msg, i)->length;
+
+		if (start < offset + l)
+			break;
+		offset += l;
+		sk_msg_iter_var_next(i);
+	} while (i != msg->sg.end);
+
+	if (start >= offset + l)
+		return -EINVAL;
+
+	space = MAX_MSG_FRAGS - sk_msg_elem_used(msg);
+
+	/* If no space available will fallback to copy, we need at
+	 * least one scatterlist elem available to push data into
+	 * when start aligns to the beginning of an element or two
+	 * when it falls inside an element. We handle the start equals
+	 * offset case because its the common case for inserting a
+	 * header.
+	 */
+	if (!space || (space == 1 && start != offset))
+		copy = msg->sg.data[i].length;
+
+	page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP,
+			   get_order(copy + len));
+	if (unlikely(!page))
+		return -ENOMEM;
+
+	if (copy) {
+		int front, back;
+
+		raw = page_address(page);
+
+		psge = sk_msg_elem(msg, i);
+		front = start - offset;
+		back = psge->length - front;
+		from = sg_virt(psge);
+
+		if (front)
+			memcpy(raw, from, front);
+
+		if (back) {
+			from += front;
+			to = raw + front + len;
+
+			memcpy(to, from, back);
+		}
+
+		put_page(sg_page(psge));
+	} else if (start - offset) {
+		psge = sk_msg_elem(msg, i);
+		rsge = sk_msg_elem_cpy(msg, i);
+
+		psge->length = start - offset;
+		rsge.length -= psge->length;
+		rsge.offset += start;
+
+		sk_msg_iter_var_next(i);
+		sg_unmark_end(psge);
+		sk_msg_iter_next(msg, end);
+	}
+
+	/* Slot(s) to place newly allocated data */
+	new = i;
+
+	/* Shift one or two slots as needed */
+	if (!copy) {
+		sge = sk_msg_elem_cpy(msg, i);
+
+		sk_msg_iter_var_next(i);
+		sg_unmark_end(&sge);
+		sk_msg_iter_next(msg, end);
+
+		nsge = sk_msg_elem_cpy(msg, i);
+		if (rsge.length) {
+			sk_msg_iter_var_next(i);
+			nnsge = sk_msg_elem_cpy(msg, i);
+		}
+
+		while (i != msg->sg.end) {
+			msg->sg.data[i] = sge;
+			sge = nsge;
+			sk_msg_iter_var_next(i);
+			if (rsge.length) {
+				nsge = nnsge;
+				nnsge = sk_msg_elem_cpy(msg, i);
+			} else {
+				nsge = sk_msg_elem_cpy(msg, i);
+			}
+		}
+	}
+
+	/* Place newly allocated data buffer */
+	sk_mem_charge(msg->sk, len);
+	msg->sg.size += len;
+	msg->sg.copy[new] = false;
+	sg_set_page(&msg->sg.data[new], page, len + copy, 0);
+	if (rsge.length) {
+		get_page(sg_page(&rsge));
+		sk_msg_iter_var_next(new);
+		msg->sg.data[new] = rsge;
+	}
+
+	sk_msg_compute_data_pointers(msg);
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_msg_push_data_proto = {
+	.func		= bpf_msg_push_data,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
 {
 	return task_get_classid(skb);
@@ -4854,6 +4985,7 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_xdp_adjust_head ||
 	    func == bpf_xdp_adjust_meta ||
 	    func == bpf_msg_pull_data ||
+	    func == bpf_msg_push_data ||
 	    func == bpf_xdp_adjust_tail ||
 #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	    func == bpf_lwt_seg6_store_bytes ||
@@ -4876,6 +5008,12 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_map_update_elem_proto;
 	case BPF_FUNC_map_delete_elem:
 		return &bpf_map_delete_elem_proto;
+	case BPF_FUNC_map_push_elem:
+		return &bpf_map_push_elem_proto;
+	case BPF_FUNC_map_pop_elem:
+		return &bpf_map_pop_elem_proto;
+	case BPF_FUNC_map_peek_elem:
+		return &bpf_map_peek_elem_proto;
 	case BPF_FUNC_get_prandom_u32:
 		return &bpf_get_prandom_u32_proto;
 	case BPF_FUNC_get_smp_processor_id:
@@ -5124,6 +5262,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_msg_cork_bytes_proto;
 	case BPF_FUNC_msg_pull_data:
 		return &bpf_msg_pull_data_proto;
+	case BPF_FUNC_msg_push_data:
+		return &bpf_msg_push_data_proto;
 	case BPF_FUNC_get_local_storage:
 		return &bpf_get_local_storage_proto;
 	default:
@@ -5346,6 +5486,40 @@ static bool sk_filter_is_valid_access(int off, int size,
 	return bpf_skb_is_valid_access(off, size, type, prog, info);
 }
 
+static bool cg_skb_is_valid_access(int off, int size,
+				   enum bpf_access_type type,
+				   const struct bpf_prog *prog,
+				   struct bpf_insn_access_aux *info)
+{
+	switch (off) {
+	case bpf_ctx_range(struct __sk_buff, tc_classid):
+	case bpf_ctx_range(struct __sk_buff, data_meta):
+	case bpf_ctx_range(struct __sk_buff, flow_keys):
+		return false;
+	}
+	if (type == BPF_WRITE) {
+		switch (off) {
+		case bpf_ctx_range(struct __sk_buff, mark):
+		case bpf_ctx_range(struct __sk_buff, priority):
+		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
+			break;
+		default:
+			return false;
+		}
+	}
+
+	switch (off) {
+	case bpf_ctx_range(struct __sk_buff, data):
+		info->reg_type = PTR_TO_PACKET;
+		break;
+	case bpf_ctx_range(struct __sk_buff, data_end):
+		info->reg_type = PTR_TO_PACKET_END;
+		break;
+	}
+
+	return bpf_skb_is_valid_access(off, size, type, prog, info);
+}
+
 static bool lwt_is_valid_access(int off, int size,
 				enum bpf_access_type type,
 				const struct bpf_prog *prog,
@@ -7038,7 +7212,7 @@ const struct bpf_prog_ops xdp_prog_ops = {
 
 const struct bpf_verifier_ops cg_skb_verifier_ops = {
 	.get_func_proto		= cg_skb_func_proto,
-	.is_valid_access	= sk_filter_is_valid_access,
+	.is_valid_access	= cg_skb_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
 };
 
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 3c0e44cb811a..be6092ac69f8 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -175,12 +175,13 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 		}
 	}
 
-	psock = sk_psock_get(sk);
+	psock = sk_psock_get_checked(sk);
+	if (IS_ERR(psock)) {
+		ret = PTR_ERR(psock);
+		goto out_progs;
+	}
+
 	if (psock) {
-		if (!sk_has_psock(sk)) {
-			ret = -EBUSY;
-			goto out_progs;
-		}
 		if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) ||
 		    (skb_progs  && READ_ONCE(psock->progs.skb_parser))) {
 			sk_psock_put(sk, psock);