Merge tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - bpf:
        - allow bpf programs calling kernel functions (initially to
          reuse TCP congestion control implementations)
        - enable task local storage for tracing programs - remove the
          need to store per-task state in hash maps, and allow tracing
          programs access to task local storage previously added for
          BPF_LSM
        - add bpf_for_each_map_elem() helper, allowing programs to walk
          all map elements in a more robust and easier to verify fashion
        - sockmap: support UDP and cross-protocol BPF_SK_SKB_VERDICT
          redirection
        - lpm: add support for batched ops in LPM trie
        - add BTF_KIND_FLOAT support - mostly to allow use of BTF on
          s390 which has floats in its headers files
        - improve BPF syscall documentation and extend the use of kdoc
          parsing scripts we already employ for bpf-helpers
        - libbpf, bpftool: support static linking of BPF ELF files
        - improve support for encapsulation of L2 packets

   - xdp: restructure redirect actions to avoid a runtime lookup,
     improving performance by 4-8% in microbenchmarks

   - xsk: build skb by page (aka generic zerocopy xmit) - improve
     performance of software AF_XDP path by 33% for devices which don't
     need headers in the linear skb part (e.g. virtio)

   - nexthop: resilient next-hop groups - improve path stability on
     next-hops group changes (incl. offload for mlxsw)

   - ipv6: segment routing: add support for IPv4 decapsulation

   - icmp: add support for RFC 8335 extended PROBE messages

   - inet: use bigger hash table for IP ID generation

   - tcp: deal better with delayed TX completions - make sure we don't
     give up on fast TCP retransmissions only because driver is slow in
     reporting that it completed transmitting the original

   - tcp: reorder tcp_congestion_ops for better cache locality

   - mptcp:
        - add sockopt support for common TCP options
        - add support for common TCP msg flags
        - include multiple address ids in RM_ADDR
        - add reset option support for resetting one subflow

   - udp: GRO L4 improvements - improve 'forward' / 'frag_list'
     co-existence with UDP tunnel GRO, allowing the first to take place
     correctly even for encapsulated UDP traffic

   - micro-optimize dev_gro_receive() and flow dissection, avoid
     retpoline overhead on VLAN and TEB GRO

   - use less memory for sysctls, add a new sysctl type, to allow using
     u8 instead of "int" and "long" and shrink networking sysctls

   - veth: allow GRO without XDP - this allows aggregating UDP packets
     before handing them off to routing, bridge, OvS, etc.

   - allow specifing ifindex when device is moved to another namespace

   - netfilter:
        - nft_socket: add support for cgroupsv2
        - nftables: add catch-all set element - special element used to
          define a default action in case normal lookup missed
        - use net_generic infra in many modules to avoid allocating
          per-ns memory unnecessarily

   - xps: improve the xps handling to avoid potential out-of-bound
     accesses and use-after-free when XPS change race with other
     re-configuration under traffic

   - add a config knob to turn off per-cpu netdev refcnt to catch
     underflows in testing

  Device APIs:

   - add WWAN subsystem to organize the WWAN interfaces better and
     hopefully start driving towards more unified and vendor-
     independent APIs

   - ethtool:
        - add interface for reading IEEE MIB stats (incl. mlx5 and bnxt
          support)
        - allow network drivers to dump arbitrary SFP EEPROM data,
          current offset+length API was a poor fit for modern SFP which
          define EEPROM in terms of pages (incl. mlx5 support)

   - act_police, flow_offload: add support for packet-per-second
     policing (incl. offload for nfp)

   - psample: add additional metadata attributes like transit delay for
     packets sampled from switch HW (and corresponding egress and
     policy-based sampling in the mlxsw driver)

   - dsa: improve support for sandwiched LAGs with bridge and DSA

   - netfilter:
        - flowtable: use direct xmit in topologies with IP forwarding,
          bridging, vlans etc.
        - nftables: counter hardware offload support

   - Bluetooth:
        - improvements for firmware download w/ Intel devices
        - add support for reading AOSP vendor capabilities
        - add support for virtio transport driver

   - mac80211:
        - allow concurrent monitor iface and ethernet rx decap
        - set priority and queue mapping for injected frames

   - phy: add support for Clause-45 PHY Loopback

   - pci/iov: add sysfs MSI-X vector assignment interface to distribute
     MSI-X resources to VFs (incl. mlx5 support)

  New hardware/drivers:

   - dsa: mv88e6xxx: add support for Marvell mv88e6393x - 11-port
     Ethernet switch with 8x 1-Gigabit Ethernet and 3x 10-Gigabit
     interfaces.

   - dsa: support for legacy Broadcom tags used on BCM5325, BCM5365 and
     BCM63xx switches

   - Microchip KSZ8863 and KSZ8873; 3x 10/100Mbps Ethernet switches

   - ath11k: support for QCN9074 a 802.11ax device

   - Bluetooth: Broadcom BCM4330 and BMC4334

   - phy: Marvell 88X2222 transceiver support

   - mdio: add BCM6368 MDIO mux bus controller

   - r8152: support RTL8153 and RTL8156 (USB Ethernet) chips

   - mana: driver for Microsoft Azure Network Adapter (MANA)

   - Actions Semi Owl Ethernet MAC

   - can: driver for ETAS ES58X CAN/USB interfaces

  Pure driver changes:

   - add XDP support to: enetc, igc, stmmac

   - add AF_XDP support to: stmmac

   - virtio:
        - page_to_skb() use build_skb when there's sufficient tailroom
          (21% improvement for 1000B UDP frames)
        - support XDP even without dedicated Tx queues - share the Tx
          queues with the stack when necessary

   - mlx5:
        - flow rules: add support for mirroring with conntrack, matching
          on ICMP, GTP, flex filters and more
        - support packet sampling with flow offloads
        - persist uplink representor netdev across eswitch mode changes
        - allow coexistence of CQE compression and HW time-stamping
        - add ethtool extended link error state reporting

   - ice, iavf: support flow filters, UDP Segmentation Offload

   - dpaa2-switch:
        - move the driver out of staging
        - add spanning tree (STP) support
        - add rx copybreak support
        - add tc flower hardware offload on ingress traffic

   - ionic:
        - implement Rx page reuse
        - support HW PTP time-stamping

   - octeon: support TC hardware offloads - flower matching on ingress
     and egress ratelimitting.

   - stmmac:
        - add RX frame steering based on VLAN priority in tc flower
        - support frame preemption (FPE)
        - intel: add cross time-stamping freq difference adjustment

   - ocelot:
        - support forwarding of MRP frames in HW
        - support multiple bridges
        - support PTP Sync one-step timestamping

   - dsa: mv88e6xxx, dpaa2-switch: offload bridge port flags like
     learning, flooding etc.

   - ipa: add IPA v4.5, v4.9 and v4.11 support (Qualcomm SDX55, SM8350,
     SC7280 SoCs)

   - mt7601u: enable TDLS support

   - mt76:
        - add support for 802.3 rx frames (mt7915/mt7615)
        - mt7915 flash pre-calibration support
        - mt7921/mt7663 runtime power management fixes"

* tag 'net-next-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2451 commits)
  net: selftest: fix build issue if INET is disabled
  net: netrom: nr_in: Remove redundant assignment to ns
  net: tun: Remove redundant assignment to ret
  net: phy: marvell: add downshift support for M88E1240
  net: dsa: ksz: Make reg_mib_cnt a u8 as it never exceeds 255
  net/sched: act_ct: Remove redundant ct get and check
  icmp: standardize naming of RFC 8335 PROBE constants
  bpf, selftests: Update array map tests for per-cpu batched ops
  bpf: Add batched ops support for percpu array
  bpf: Implement formatted output helpers with bstr_printf
  seq_file: Add a seq_bprintf function
  sfc: adjust efx->xdp_tx_queue_count with the real number of initialized queues
  net:nfc:digital: Fix a double free in digital_tg_recv_dep_req
  net: fix a concurrency bug in l2tp_tunnel_register()
  net/smc: Remove redundant assignment to rc
  mpls: Remove redundant assignment to err
  llc2: Remove redundant assignment to rc
  net/tls: Remove redundant initialization of record
  rds: Remove redundant assignment to nr_sig
  dt-bindings: net: mdio-gpio: add compatible for microchip,mdio-smi0
  ...

1 files changed, 214 insertions, 62 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 58bcb8c849d5..a5d72c48fb66 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2017 Facebook
  */
 #include <linux/bpf.h>
+#include <linux/btf_ids.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/etherdevice.h>
@@ -10,20 +11,86 @@
 #include <net/bpf_sk_storage.h>
 #include <net/sock.h>
 #include <net/tcp.h>
+#include <net/net_namespace.h>
 #include <linux/error-injection.h>
 #include <linux/smp.h>
+#include <linux/sock_diag.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/bpf_test_run.h>
 
+struct bpf_test_timer {
+	enum { NO_PREEMPT, NO_MIGRATE } mode;
+	u32 i;
+	u64 time_start, time_spent;
+};
+
+static void bpf_test_timer_enter(struct bpf_test_timer *t)
+	__acquires(rcu)
+{
+	rcu_read_lock();
+	if (t->mode == NO_PREEMPT)
+		preempt_disable();
+	else
+		migrate_disable();
+
+	t->time_start = ktime_get_ns();
+}
+
+static void bpf_test_timer_leave(struct bpf_test_timer *t)
+	__releases(rcu)
+{
+	t->time_start = 0;
+
+	if (t->mode == NO_PREEMPT)
+		preempt_enable();
+	else
+		migrate_enable();
+	rcu_read_unlock();
+}
+
+static bool bpf_test_timer_continue(struct bpf_test_timer *t, u32 repeat, int *err, u32 *duration)
+	__must_hold(rcu)
+{
+	t->i++;
+	if (t->i >= repeat) {
+		/* We're done. */
+		t->time_spent += ktime_get_ns() - t->time_start;
+		do_div(t->time_spent, t->i);
+		*duration = t->time_spent > U32_MAX ? U32_MAX : (u32)t->time_spent;
+		*err = 0;
+		goto reset;
+	}
+
+	if (signal_pending(current)) {
+		/* During iteration: we've been cancelled, abort. */
+		*err = -EINTR;
+		goto reset;
+	}
+
+	if (need_resched()) {
+		/* During iteration: we need to reschedule between runs. */
+		t->time_spent += ktime_get_ns() - t->time_start;
+		bpf_test_timer_leave(t);
+		cond_resched();
+		bpf_test_timer_enter(t);
+	}
+
+	/* Do another round. */
+	return true;
+
+reset:
+	t->i = 0;
+	return false;
+}
+
 static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
 			u32 *retval, u32 *time, bool xdp)
 {
 	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { NULL };
+	struct bpf_test_timer t = { NO_MIGRATE };
 	enum bpf_cgroup_storage_type stype;
-	u64 time_start, time_spent = 0;
-	int ret = 0;
-	u32 i;
+	int ret;
 
 	for_each_cgroup_storage_type(stype) {
 		storage[stype] = bpf_cgroup_storage_alloc(prog, stype);
@@ -38,40 +105,20 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
 	if (!repeat)
 		repeat = 1;
 
-	rcu_read_lock();
-	migrate_disable();
-	time_start = ktime_get_ns();
-	for (i = 0; i < repeat; i++) {
-		bpf_cgroup_storage_set(storage);
+	bpf_test_timer_enter(&t);
+	do {
+		ret = bpf_cgroup_storage_set(storage);
+		if (ret)
+			break;
 
 		if (xdp)
 			*retval = bpf_prog_run_xdp(prog, ctx);
 		else
 			*retval = BPF_PROG_RUN(prog, ctx);
 
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			break;
-		}
-
-		if (need_resched()) {
-			time_spent += ktime_get_ns() - time_start;
-			migrate_enable();
-			rcu_read_unlock();
-
-			cond_resched();
-
-			rcu_read_lock();
-			migrate_disable();
-			time_start = ktime_get_ns();
-		}
-	}
-	time_spent += ktime_get_ns() - time_start;
-	migrate_enable();
-	rcu_read_unlock();
-
-	do_div(time_spent, repeat);
-	*time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;
+		bpf_cgroup_storage_unset();
+	} while (bpf_test_timer_continue(&t, repeat, &ret, time));
+	bpf_test_timer_leave(&t);
 
 	for_each_cgroup_storage_type(stype)
 		bpf_cgroup_storage_free(storage[stype]);
@@ -167,10 +214,37 @@ int noinline bpf_modify_return_test(int a, int *b)
 	*b += 1;
 	return a + *b;
 }
+
+u64 noinline bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d)
+{
+	return a + b + c + d;
+}
+
+int noinline bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b)
+{
+	return a + b;
+}
+
+struct sock * noinline bpf_kfunc_call_test3(struct sock *sk)
+{
+	return sk;
+}
+
 __diag_pop();
 
 ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO);
 
+BTF_SET_START(test_sk_kfunc_ids)
+BTF_ID(func, bpf_kfunc_call_test1)
+BTF_ID(func, bpf_kfunc_call_test2)
+BTF_ID(func, bpf_kfunc_call_test3)
+BTF_SET_END(test_sk_kfunc_ids)
+
+bool bpf_prog_test_check_kfunc_call(u32 kfunc_id)
+{
+	return btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id);
+}
+
 static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
 			   u32 headroom, u32 tailroom)
 {
@@ -674,18 +748,17 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 				     const union bpf_attr *kattr,
 				     union bpf_attr __user *uattr)
 {
+	struct bpf_test_timer t = { NO_PREEMPT };
 	u32 size = kattr->test.data_size_in;
 	struct bpf_flow_dissector ctx = {};
 	u32 repeat = kattr->test.repeat;
 	struct bpf_flow_keys *user_ctx;
 	struct bpf_flow_keys flow_keys;
-	u64 time_start, time_spent = 0;
 	const struct ethhdr *eth;
 	unsigned int flags = 0;
 	u32 retval, duration;
 	void *data;
 	int ret;
-	u32 i;
 
 	if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR)
 		return -EINVAL;
@@ -721,48 +794,127 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	ctx.data = data;
 	ctx.data_end = (__u8 *)data + size;
 
-	rcu_read_lock();
-	preempt_disable();
-	time_start = ktime_get_ns();
-	for (i = 0; i < repeat; i++) {
+	bpf_test_timer_enter(&t);
+	do {
 		retval = bpf_flow_dissect(prog, &ctx, eth->h_proto, ETH_HLEN,
 					  size, flags);
+	} while (bpf_test_timer_continue(&t, repeat, &ret, &duration));
+	bpf_test_timer_leave(&t);
 
-		if (signal_pending(current)) {
-			preempt_enable();
-			rcu_read_unlock();
+	if (ret < 0)
+		goto out;
 
-			ret = -EINTR;
-			goto out;
-		}
+	ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys),
+			      retval, duration);
+	if (!ret)
+		ret = bpf_ctx_finish(kattr, uattr, user_ctx,
+				     sizeof(struct bpf_flow_keys));
 
-		if (need_resched()) {
-			time_spent += ktime_get_ns() - time_start;
-			preempt_enable();
-			rcu_read_unlock();
+out:
+	kfree(user_ctx);
+	kfree(data);
+	return ret;
+}
 
-			cond_resched();
+int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr,
+				union bpf_attr __user *uattr)
+{
+	struct bpf_test_timer t = { NO_PREEMPT };
+	struct bpf_prog_array *progs = NULL;
+	struct bpf_sk_lookup_kern ctx = {};
+	u32 repeat = kattr->test.repeat;
+	struct bpf_sk_lookup *user_ctx;
+	u32 retval, duration;
+	int ret = -EINVAL;
 
-			rcu_read_lock();
-			preempt_disable();
-			time_start = ktime_get_ns();
-		}
+	if (prog->type != BPF_PROG_TYPE_SK_LOOKUP)
+		return -EINVAL;
+
+	if (kattr->test.flags || kattr->test.cpu)
+		return -EINVAL;
+
+	if (kattr->test.data_in || kattr->test.data_size_in || kattr->test.data_out ||
+	    kattr->test.data_size_out)
+		return -EINVAL;
+
+	if (!repeat)
+		repeat = 1;
+
+	user_ctx = bpf_ctx_init(kattr, sizeof(*user_ctx));
+	if (IS_ERR(user_ctx))
+		return PTR_ERR(user_ctx);
+
+	if (!user_ctx)
+		return -EINVAL;
+
+	if (user_ctx->sk)
+		goto out;
+
+	if (!range_is_zero(user_ctx, offsetofend(typeof(*user_ctx), local_port), sizeof(*user_ctx)))
+		goto out;
+
+	if (user_ctx->local_port > U16_MAX || user_ctx->remote_port > U16_MAX) {
+		ret = -ERANGE;
+		goto out;
 	}
-	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;
+	ctx.family = (u16)user_ctx->family;
+	ctx.protocol = (u16)user_ctx->protocol;
+	ctx.dport = (u16)user_ctx->local_port;
+	ctx.sport = (__force __be16)user_ctx->remote_port;
 
-	ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys),
-			      retval, duration);
+	switch (ctx.family) {
+	case AF_INET:
+		ctx.v4.daddr = (__force __be32)user_ctx->local_ip4;
+		ctx.v4.saddr = (__force __be32)user_ctx->remote_ip4;
+		break;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		ctx.v6.daddr = (struct in6_addr *)user_ctx->local_ip6;
+		ctx.v6.saddr = (struct in6_addr *)user_ctx->remote_ip6;
+		break;
+#endif
+
+	default:
+		ret = -EAFNOSUPPORT;
+		goto out;
+	}
+
+	progs = bpf_prog_array_alloc(1, GFP_KERNEL);
+	if (!progs) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	progs->items[0].prog = prog;
+
+	bpf_test_timer_enter(&t);
+	do {
+		ctx.selected_sk = NULL;
+		retval = BPF_PROG_SK_LOOKUP_RUN_ARRAY(progs, ctx, BPF_PROG_RUN);
+	} while (bpf_test_timer_continue(&t, repeat, &ret, &duration));
+	bpf_test_timer_leave(&t);
+
+	if (ret < 0)
+		goto out;
+
+	user_ctx->cookie = 0;
+	if (ctx.selected_sk) {
+		if (ctx.selected_sk->sk_reuseport && !ctx.no_reuseport) {
+			ret = -EOPNOTSUPP;
+			goto out;
+		}
+
+		user_ctx->cookie = sock_gen_cookie(ctx.selected_sk);
+	}
+
+	ret = bpf_test_finish(kattr, uattr, NULL, 0, retval, duration);
 	if (!ret)
-		ret = bpf_ctx_finish(kattr, uattr, user_ctx,
-				     sizeof(struct bpf_flow_keys));
+		ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(*user_ctx));
 
 out:
+	bpf_prog_array_free(progs);
 	kfree(user_ctx);
-	kfree(data);
 	return ret;
 }