Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:

 1) Don't insert ESP trailer twice in IPSEC code, from Huy Nguyen.

 2) The default crypto algorithm selection in Kconfig for IPSEC is out
    of touch with modern reality, fix this up. From Eric Biggers.

 3) bpftool is missing an entry for BPF_MAP_TYPE_RINGBUF, from Andrii
    Nakryiko.

 4) Missing init of ->frame_sz in xdp_convert_zc_to_xdp_frame(), from
    Hangbin Liu.

 5) Adjust packet alignment handling in ax88179_178a driver to match
    what the hardware actually does. From Jeremy Kerr.

 6) register_netdevice can leak in the case one of the notifiers fail,
    from Yang Yingliang.

 7) Use after free in ip_tunnel_lookup(), from Taehee Yoo.

 8) VLAN checks in sja1105 DSA driver need adjustments, from Vladimir
    Oltean.

 9) tg3 driver can sleep forever when we get enough EEH errors, fix from
    David Christensen.

10) Missing {READ,WRITE}_ONCE() annotations in various Intel ethernet
    drivers, from Ciara Loftus.

11) Fix scanning loop break condition in of_mdiobus_register(), from
    Florian Fainelli.

12) MTU limit is incorrect in ibmveth driver, from Thomas Falcon.

13) Endianness fix in mlxsw, from Ido Schimmel.

14) Use after free in smsc95xx usbnet driver, from Tuomas Tynkkynen.

15) Missing bridge mrp configuration validation, from Horatiu Vultur.

16) Fix circular netns references in wireguard, from Jason A. Donenfeld.

17) PTP initialization on recovery is not done properly in qed driver,
    from Alexander Lobakin.

18) Endian conversion of L4 ports in filters of cxgb4 driver is wrong,
    from Rahul Lakkireddy.

19) Don't clear bound device TX queue of socket prematurely otherwise we
    get problems with ktls hw offloading, from Tariq Toukan.

20) ipset can do atomics on unaligned memory, fix from Russell King.

21) Align ethernet addresses properly in bridging code, from Thomas
    Martitz.

22) Don't advertise ipv4 addresses on SCTP sockets having ipv6only set,
    from Marcelo Ricardo Leitner.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (149 commits)
  rds: transport module should be auto loaded when transport is set
  sch_cake: fix a few style nits
  sch_cake: don't call diffserv parsing code when it is not needed
  sch_cake: don't try to reallocate or unshare skb unconditionally
  ethtool: fix error handling in linkstate_prepare_data()
  wil6210: account for napi_gro_receive never returning GRO_DROP
  hns: do not cast return value of napi_gro_receive to null
  socionext: account for napi_gro_receive never returning GRO_DROP
  wireguard: receive: account for napi_gro_receive never returning GRO_DROP
  vxlan: fix last fdb index during dump of fdb with nhid
  sctp: Don't advertise IPv4 addresses if ipv6only is set on the socket
  tc-testing: avoid action cookies with odd length.
  bpf: tcp: bpf_cubic: fix spurious HYSTART_DELAY exit upon drop in min RTT
  tcp_cubic: fix spurious HYSTART_DELAY exit upon drop in min RTT
  net: dsa: sja1105: fix tc-gate schedule with single element
  net: dsa: sja1105: recalculate gating subschedule after deleting tc-gate rules
  net: dsa: sja1105: unconditionally free old gating config
  net: dsa: sja1105: move sja1105_compose_gating_subschedule at the top
  net: macb: free resources on failure path of at91ether_open()
  net: macb: call pm_runtime_put_sync on failure path
  ...

6 files changed, 127 insertions, 85 deletions

diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c
index 9c628591f452..323ae7f6315d 100644
--- a/net/sched/act_gate.c
+++ b/net/sched/act_gate.c
@@ -32,7 +32,7 @@ static ktime_t gate_get_time(struct tcf_gate *gact)
 	return KTIME_MAX;
 }
 
-static int gate_get_start_time(struct tcf_gate *gact, ktime_t *start)
+static void gate_get_start_time(struct tcf_gate *gact, ktime_t *start)
 {
 	struct tcf_gate_params *param = &gact->param;
 	ktime_t now, base, cycle;
@@ -43,18 +43,13 @@ static int gate_get_start_time(struct tcf_gate *gact, ktime_t *start)
 
 	if (ktime_after(base, now)) {
 		*start = base;
-		return 0;
+		return;
 	}
 
 	cycle = param->tcfg_cycletime;
 
-	/* cycle time should not be zero */
-	if (!cycle)
-		return -EFAULT;
-
 	n = div64_u64(ktime_sub_ns(now, base), cycle);
 	*start = ktime_add_ns(base, (n + 1) * cycle);
-	return 0;
 }
 
 static void gate_start_timer(struct tcf_gate *gact, ktime_t start)
@@ -277,6 +272,27 @@ release_list:
 	return err;
 }
 
+static void gate_setup_timer(struct tcf_gate *gact, u64 basetime,
+			     enum tk_offsets tko, s32 clockid,
+			     bool do_init)
+{
+	if (!do_init) {
+		if (basetime == gact->param.tcfg_basetime &&
+		    tko == gact->tk_offset &&
+		    clockid == gact->param.tcfg_clockid)
+			return;
+
+		spin_unlock_bh(&gact->tcf_lock);
+		hrtimer_cancel(&gact->hitimer);
+		spin_lock_bh(&gact->tcf_lock);
+	}
+	gact->param.tcfg_basetime = basetime;
+	gact->param.tcfg_clockid = clockid;
+	gact->tk_offset = tko;
+	hrtimer_init(&gact->hitimer, clockid, HRTIMER_MODE_ABS_SOFT);
+	gact->hitimer.function = gate_timer_func;
+}
+
 static int tcf_gate_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
 			 int ovr, int bind, bool rtnl_held,
@@ -287,12 +303,12 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 	enum tk_offsets tk_offset = TK_OFFS_TAI;
 	struct nlattr *tb[TCA_GATE_MAX + 1];
 	struct tcf_chain *goto_ch = NULL;
+	u64 cycletime = 0, basetime = 0;
 	struct tcf_gate_params *p;
 	s32 clockid = CLOCK_TAI;
 	struct tcf_gate *gact;
 	struct tc_gate *parm;
 	int ret = 0, err;
-	u64 basetime = 0;
 	u32 gflags = 0;
 	s32 prio = -1;
 	ktime_t start;
@@ -308,6 +324,27 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 	if (!tb[TCA_GATE_PARMS])
 		return -EINVAL;
 
+	if (tb[TCA_GATE_CLOCKID]) {
+		clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]);
+		switch (clockid) {
+		case CLOCK_REALTIME:
+			tk_offset = TK_OFFS_REAL;
+			break;
+		case CLOCK_MONOTONIC:
+			tk_offset = TK_OFFS_MAX;
+			break;
+		case CLOCK_BOOTTIME:
+			tk_offset = TK_OFFS_BOOT;
+			break;
+		case CLOCK_TAI:
+			tk_offset = TK_OFFS_TAI;
+			break;
+		default:
+			NL_SET_ERR_MSG(extack, "Invalid 'clockid'");
+			return -EINVAL;
+		}
+	}
+
 	parm = nla_data(tb[TCA_GATE_PARMS]);
 	index = parm->index;
 
@@ -331,10 +368,6 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 		tcf_idr_release(*a, bind);
 		return -EEXIST;
 	}
-	if (ret == ACT_P_CREATED) {
-		to_gate(*a)->param.tcfg_clockid = -1;
-		INIT_LIST_HEAD(&(to_gate(*a)->param.entries));
-	}
 
 	if (tb[TCA_GATE_PRIORITY])
 		prio = nla_get_s32(tb[TCA_GATE_PRIORITY]);
@@ -345,41 +378,19 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 	if (tb[TCA_GATE_FLAGS])
 		gflags = nla_get_u32(tb[TCA_GATE_FLAGS]);
 
-	if (tb[TCA_GATE_CLOCKID]) {
-		clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]);
-		switch (clockid) {
-		case CLOCK_REALTIME:
-			tk_offset = TK_OFFS_REAL;
-			break;
-		case CLOCK_MONOTONIC:
-			tk_offset = TK_OFFS_MAX;
-			break;
-		case CLOCK_BOOTTIME:
-			tk_offset = TK_OFFS_BOOT;
-			break;
-		case CLOCK_TAI:
-			tk_offset = TK_OFFS_TAI;
-			break;
-		default:
-			NL_SET_ERR_MSG(extack, "Invalid 'clockid'");
-			goto release_idr;
-		}
-	}
+	gact = to_gate(*a);
+	if (ret == ACT_P_CREATED)
+		INIT_LIST_HEAD(&gact->param.entries);
 
 	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
 	if (err < 0)
 		goto release_idr;
 
-	gact = to_gate(*a);
-
 	spin_lock_bh(&gact->tcf_lock);
 	p = &gact->param;
 
-	if (tb[TCA_GATE_CYCLE_TIME]) {
-		p->tcfg_cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]);
-		if (!p->tcfg_cycletime_ext)
-			goto chain_put;
-	}
+	if (tb[TCA_GATE_CYCLE_TIME])
+		cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]);
 
 	if (tb[TCA_GATE_ENTRY_LIST]) {
 		err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack);
@@ -387,35 +398,29 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 			goto chain_put;
 	}
 
-	if (!p->tcfg_cycletime) {
+	if (!cycletime) {
 		struct tcfg_gate_entry *entry;
 		ktime_t cycle = 0;
 
 		list_for_each_entry(entry, &p->entries, list)
 			cycle = ktime_add_ns(cycle, entry->interval);
-		p->tcfg_cycletime = cycle;
+		cycletime = cycle;
+		if (!cycletime) {
+			err = -EINVAL;
+			goto chain_put;
+		}
 	}
+	p->tcfg_cycletime = cycletime;
 
 	if (tb[TCA_GATE_CYCLE_TIME_EXT])
 		p->tcfg_cycletime_ext =
 			nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]);
 
+	gate_setup_timer(gact, basetime, tk_offset, clockid,
+			 ret == ACT_P_CREATED);
 	p->tcfg_priority = prio;
-	p->tcfg_basetime = basetime;
-	p->tcfg_clockid = clockid;
 	p->tcfg_flags = gflags;
-
-	gact->tk_offset = tk_offset;
-	hrtimer_init(&gact->hitimer, clockid, HRTIMER_MODE_ABS_SOFT);
-	gact->hitimer.function = gate_timer_func;
-
-	err = gate_get_start_time(gact, &start);
-	if (err < 0) {
-		NL_SET_ERR_MSG(extack,
-			       "Internal error: failed get start time");
-		release_entry_list(&p->entries);
-		goto chain_put;
-	}
+	gate_get_start_time(gact, &start);
 
 	gact->current_close_time = start;
 	gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING;
@@ -443,6 +448,13 @@ chain_put:
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
 release_idr:
+	/* action is not inserted in any list: it's safe to init hitimer
+	 * without taking tcf_lock.
+	 */
+	if (ret == ACT_P_CREATED)
+		gate_setup_timer(gact, gact->param.tcfg_basetime,
+				 gact->tk_offset, gact->param.tcfg_clockid,
+				 true);
 	tcf_idr_release(*a, bind);
 	return err;
 }
@@ -453,9 +465,7 @@ static void tcf_gate_cleanup(struct tc_action *a)
 	struct tcf_gate_params *p;
 
 	p = &gact->param;
-	if (p->tcfg_clockid != -1)
-		hrtimer_cancel(&gact->hitimer);
-
+	hrtimer_cancel(&gact->hitimer);
 	release_entry_list(&p->entries);
 }
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index a00a203b2ef5..faa78b7dd962 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -652,6 +652,7 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb)
 			       &block->flow_block, tcf_block_shared(block),
 			       &extack);
 	down_write(&block->cb_lock);
+	list_del(&block_cb->driver_list);
 	list_move(&block_cb->list, &bo.cb_list);
 	up_write(&block->cb_lock);
 	rtnl_lock();
@@ -671,25 +672,29 @@ static int tcf_block_offload_cmd(struct tcf_block *block,
 				 struct netlink_ext_ack *extack)
 {
 	struct flow_block_offload bo = {};
-	int err;
 
 	tcf_block_offload_init(&bo, dev, command, ei->binder_type,
 			       &block->flow_block, tcf_block_shared(block),
 			       extack);
 
-	if (dev->netdev_ops->ndo_setup_tc)
+	if (dev->netdev_ops->ndo_setup_tc) {
+		int err;
+
 		err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
-	else
-		err = flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, block,
-						  &bo, tc_block_indr_cleanup);
+		if (err < 0) {
+			if (err != -EOPNOTSUPP)
+				NL_SET_ERR_MSG(extack, "Driver ndo_setup_tc failed");
+			return err;
+		}
 
-	if (err < 0) {
-		if (err != -EOPNOTSUPP)
-			NL_SET_ERR_MSG(extack, "Driver ndo_setup_tc failed");
-		return err;
+		return tcf_block_setup(block, &bo);
 	}
 
-	return tcf_block_setup(block, &bo);
+	flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, block, &bo,
+				    tc_block_indr_cleanup);
+	tcf_block_setup(block, &bo);
+
+	return -EOPNOTSUPP;
 }
 
 static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 60f8ae578819..ca813697728e 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1551,32 +1551,51 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 	return idx + (tin << 16);
 }
 
-static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
+static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash)
 {
-	int wlen = skb_network_offset(skb);
+	const int offset = skb_network_offset(skb);
+	u16 *buf, buf_;
 	u8 dscp;
 
 	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
-		wlen += sizeof(struct iphdr);
-		if (!pskb_may_pull(skb, wlen) ||
-		    skb_try_make_writable(skb, wlen))
+		buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_);
+		if (unlikely(!buf))
 			return 0;
 
-		dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
-		if (wash && dscp)
+		/* ToS is in the second byte of iphdr */
+		dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2;
+
+		if (wash && dscp) {
+			const int wlen = offset + sizeof(struct iphdr);
+
+			if (!pskb_may_pull(skb, wlen) ||
+			    skb_try_make_writable(skb, wlen))
+				return 0;
+
 			ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
+		}
+
 		return dscp;
 
 	case htons(ETH_P_IPV6):
-		wlen += sizeof(struct ipv6hdr);
-		if (!pskb_may_pull(skb, wlen) ||
-		    skb_try_make_writable(skb, wlen))
+		buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_);
+		if (unlikely(!buf))
 			return 0;
 
-		dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
-		if (wash && dscp)
+		/* Traffic class is in the first and second bytes of ipv6hdr */
+		dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2;
+
+		if (wash && dscp) {
+			const int wlen = offset + sizeof(struct ipv6hdr);
+
+			if (!pskb_may_pull(skb, wlen) ||
+			    skb_try_make_writable(skb, wlen))
+				return 0;
+
 			ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
+		}
+
 		return dscp;
 
 	case htons(ETH_P_ARP):
@@ -1593,14 +1612,17 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
 	u32 tin, mark;
+	bool wash;
 	u8 dscp;
 
 	/* Tin selection: Default to diffserv-based selection, allow overriding
-	 * using firewall marks or skb->priority.
+	 * using firewall marks or skb->priority. Call DSCP parsing early if
+	 * wash is enabled, otherwise defer to below to skip unneeded parsing.
 	 */
-	dscp = cake_handle_diffserv(skb,
-				    q->rate_flags & CAKE_FLAG_WASH);
 	mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft;
+	wash = !!(q->rate_flags & CAKE_FLAG_WASH);
+	if (wash)
+		dscp = cake_handle_diffserv(skb, wash);
 
 	if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT)
 		tin = 0;
@@ -1614,6 +1636,8 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
 		tin = q->tin_order[TC_H_MIN(skb->priority) - 1];
 
 	else {
+		if (!wash)
+			dscp = cake_handle_diffserv(skb, wash);
 		tin = q->tin_index[dscp];
 
 		if (unlikely(tin >= q->tin_cnt))
@@ -2691,7 +2715,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt,
 	qdisc_watchdog_init(&q->watchdog, sch);
 
 	if (opt) {
-		int err = cake_change(sch, opt, extack);
+		err = cake_change(sch, opt, extack);
 
 		if (err)
 			return err;
@@ -3008,7 +3032,7 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 			PUT_STAT_S32(BLUE_TIMER_US,
 				     ktime_to_us(
 					     ktime_sub(now,
-						     flow->cvars.blue_timer)));
+						       flow->cvars.blue_timer)));
 		}
 		if (flow->cvars.dropping) {
 			PUT_STAT_S32(DROP_NEXT_US,
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 8f06a808c59a..2fb76fc0cc31 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -1075,3 +1075,4 @@ module_init(fq_module_init)
 module_exit(fq_module_exit)
 MODULE_AUTHOR("Eric Dumazet");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Fair Queue Packet Scheduler");
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 436160be9c18..459a784056c0 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -721,3 +721,4 @@ module_init(fq_codel_module_init)
 module_exit(fq_codel_module_exit)
 MODULE_AUTHOR("Eric Dumazet");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Fair Queue CoDel discipline");
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index be35f03b657b..420ede875322 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -721,3 +721,4 @@ module_exit(hhf_module_exit)
 MODULE_AUTHOR("Terry Lam");
 MODULE_AUTHOR("Nandita Dukkipati");
 MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Heavy-Hitter Filter (HHF)");