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

Daniel Borkmann says:

====================
pull-request: bpf-next 2019-03-04

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

The main changes are:

1) Add AF_XDP support to libbpf. Rationale is to facilitate writing
   AF_XDP applications by offering higher-level APIs that hide many
   of the details of the AF_XDP uapi. Sample programs are converted
   over to this new interface as well, from Magnus.

2) Introduce a new cant_sleep() macro for annotation of functions
   that cannot sleep and use it in BPF_PROG_RUN() to assert that
   BPF programs run under preemption disabled context, from Peter.

3) Introduce per BPF prog stats in order to monitor the usage
   of BPF; this is controlled by kernel.bpf_stats_enabled sysctl
   knob where monitoring tools can make use of this to efficiently
   determine the average cost of programs, from Alexei.

4) Split up BPF selftest's test_progs similarly as we already
   did with test_verifier. This allows to further reduce merge
   conflicts in future and to get more structure into our
   quickly growing BPF selftest suite, from Stanislav.

5) Fix a bug in BTF's dedup algorithm which can cause an infinite
   loop in some circumstances; also various BPF doc fixes and
   improvements, from Andrii.

6) Various BPF sample cleanups and migration to libbpf in order
   to further isolate the old sample loader code (so we can get
   rid of it at some point), from Jakub.

7) Add a new BPF helper for BPF cgroup skb progs that allows
   to set ECN CE code point and a Host Bandwidth Manager (HBM)
   sample program for limiting the bandwidth used by v2 cgroups,
   from Lawrence.

8) Enable write access to skb->queue_mapping from tc BPF egress
   programs in order to let BPF pick TX queue, from Jesper.

9) Fix a bug in BPF spinlock handling for map-in-map which did
   not propagate spin_lock_off to the meta map, from Yonghong.

10) Fix a bug in the new per-CPU BPF prog counters to properly
    initialize stats for each CPU, from Eric.

11) Add various BPF helper prototypes to selftest's bpf_helpers.h,
    from Willem.

12) Fix various BPF samples bugs in XDP and tracing progs,
    from Toke, Daniel and Yonghong.

13) Silence preemption splat in test_bpf after BPF_PROG_RUN()
    enforces it now everywhere, from Anders.

14) Fix a signedness bug in libbpf's btf_dedup_ref_type() to
    get error handling working, from Dan.

15) Fix bpftool documentation and auto-completion with regards
    to stream_{verdict,parser} attach types, from Alban.
====================

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

2 files changed, 61 insertions, 9 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 7f62d168411d..da7051d62727 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -296,31 +296,45 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	if (!repeat)
 		repeat = 1;
 
+	rcu_read_lock();
+	preempt_disable();
 	time_start = ktime_get_ns();
 	for (i = 0; i < repeat; i++) {
-		preempt_disable();
-		rcu_read_lock();
 		retval = __skb_flow_bpf_dissect(prog, skb,
 						&flow_keys_dissector,
 						&flow_keys);
-		rcu_read_unlock();
-		preempt_enable();
+
+		if (signal_pending(current)) {
+			preempt_enable();
+			rcu_read_unlock();
+
+			ret = -EINTR;
+			goto out;
+		}
 
 		if (need_resched()) {
-			if (signal_pending(current))
-				break;
 			time_spent += ktime_get_ns() - time_start;
+			preempt_enable();
+			rcu_read_unlock();
+
 			cond_resched();
+
+			rcu_read_lock();
+			preempt_disable();
 			time_start = ktime_get_ns();
 		}
 	}
 	time_spent += ktime_get_ns() - time_start;
+	preempt_enable();
+	rcu_read_unlock();
+
 	do_div(time_spent, repeat);
 	duration = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;
 
 	ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys),
 			      retval, duration);
 
+out:
 	kfree_skb(skb);
 	kfree(sk);
 	return ret;
diff --git a/net/core/filter.c b/net/core/filter.c
index 5132c054c981..5ceba98069d4 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5422,6 +5422,32 @@ static const struct bpf_func_proto bpf_tcp_sock_proto = {
 	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
 };
 
+BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb)
+{
+	unsigned int iphdr_len;
+
+	if (skb->protocol == cpu_to_be16(ETH_P_IP))
+		iphdr_len = sizeof(struct iphdr);
+	else if (skb->protocol == cpu_to_be16(ETH_P_IPV6))
+		iphdr_len = sizeof(struct ipv6hdr);
+	else
+		return 0;
+
+	if (skb_headlen(skb) < iphdr_len)
+		return 0;
+
+	if (skb_cloned(skb) && !skb_clone_writable(skb, iphdr_len))
+		return 0;
+
+	return INET_ECN_set_ce(skb);
+}
+
+static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = {
+	.func           = bpf_skb_ecn_set_ce,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+};
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
@@ -5581,6 +5607,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #ifdef CONFIG_INET
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
+	case BPF_FUNC_skb_ecn_set_ce:
+		return &bpf_skb_ecn_set_ce_proto;
 #endif
 	default:
 		return sk_filter_func_proto(func_id, prog);
@@ -6275,6 +6303,7 @@ static bool tc_cls_act_is_valid_access(int off, int size,
 		case bpf_ctx_range(struct __sk_buff, tc_classid):
 		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
 		case bpf_ctx_range(struct __sk_buff, tstamp):
+		case bpf_ctx_range(struct __sk_buff, queue_mapping):
 			break;
 		default:
 			return false;
@@ -6679,9 +6708,18 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 		break;
 
 	case offsetof(struct __sk_buff, queue_mapping):
-		*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg,
-				      bpf_target_off(struct sk_buff, queue_mapping, 2,
-						     target_size));
+		if (type == BPF_WRITE) {
+			*insn++ = BPF_JMP_IMM(BPF_JGE, si->src_reg, NO_QUEUE_MAPPING, 1);
+			*insn++ = BPF_STX_MEM(BPF_H, si->dst_reg, si->src_reg,
+					      bpf_target_off(struct sk_buff,
+							     queue_mapping,
+							     2, target_size));
+		} else {
+			*insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg,
+					      bpf_target_off(struct sk_buff,
+							     queue_mapping,
+							     2, target_size));
+		}
 		break;
 
 	case offsetof(struct __sk_buff, vlan_present):