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

Pull networking updates from David Miller:

Changes of note:

 1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.

 2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
    David Ahern.

 3) Allow the user to ask for the statistics to be filtered out of
    ipv4/ipv6 address netlink dumps.  From Sowmini Varadhan.

 4) More work to pass the network namespace context around deep into
    various packet path APIs, starting with the netfilter hooks.  From
    Eric W Biederman.

 5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
    Richter.

 6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.

 7) Support Very High Throughput in wireless MESH code, from Bob
    Copeland.

 8) Allow setting the ageing_time in switchdev/rocker.  From Scott
    Feldman.

 9) Properly autoload L2TP type modules, from Stephen Hemminger.

10) Fix and enable offload features by default in 8139cp driver, from
    David Woodhouse.

11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
    Jiri Benc.

12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
    Opstad.

13) Fix IPSEC flowcache overflows on large systems, from Steffen
    Klassert.

14) Convert bridging to track VLANs using rhashtable entries rather than
    a bitmap.  From Nikolay Aleksandrov.

15) Make TCP listener handling completely lockless, this is a major
    accomplishment.  Incoming request sockets now live in the
    established hash table just like any other socket too.

    From Eric Dumazet.

15) Provide more bridging attributes to netlink, from Nikolay
    Aleksandrov.

16) Use hash based algorithm for ipv4 multipath routing, this was very
    long overdue.  From Peter Nørlund.

17) Several y2038 cures, mostly avoiding timespec.  From Arnd Bergmann.

18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.

19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet.  This
    influences the port binding selection logic used by SO_REUSEPORT.

20) Add ipv6 support to VRF, from David Ahern.

21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.

22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.

23) Implement RACK loss recovery in TCP, from Yuchung Cheng.

24) Support multipath routes in MPLS, from Roopa Prabhu.

25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
    Dumazet.

26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
    Sudarsana Kalluru.

27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
    Sowa.

28) Support ipv6 geneve tunnels, from John W Linville.

29) Add flood control support to switchdev layer, from Ido Schimmel.

30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
    Hannes Frederic Sowa.

31) Support persistent maps and progs in bpf, from Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
  sh_eth: use DMA barriers
  switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
  net: sched: kill dead code in sch_choke.c
  irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
  net: dsa: mv88e6xxx: include DSA ports in VLANs
  net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
  net/core: fix for_each_netdev_feature
  vlan: Invoke driver vlan hooks only if device is present
  arcnet/com20020: add LEDS_CLASS dependency
  bpf, verifier: annotate verbose printer with __printf
  dp83640: Only wait for timestamps for packets with timestamping enabled.
  ptp: Change ptp_class to a proper bitmask
  dp83640: Prune rx timestamp list before reading from it
  dp83640: Delay scheduled work.
  dp83640: Include hash in timestamp/packet matching
  ipv6: fix tunnel error handling
  net/mlx5e: Fix LSO vlan insertion
  net/mlx5e: Re-eanble client vlan TX acceleration
  net/mlx5e: Return error in case mlx5e_set_features() fails
  net/mlx5e: Don't allow more than max supported channels
  ...

1 files changed, 33 insertions, 30 deletions

diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index c4d45fd8c551..f357f34d02d2 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -35,14 +35,20 @@
 
 #define NO_DEFAULT_INDEX	(1 << 16)
 
+struct mask_value {
+	u8			mask;
+	u8			value;
+};
+
 struct dsmark_qdisc_data {
 	struct Qdisc		*q;
 	struct tcf_proto __rcu	*filter_list;
-	u8			*mask;	/* "owns" the array */
-	u8			*value;
+	struct mask_value	*mv;
 	u16			indices;
+	u8			set_tc_index;
 	u32			default_index;	/* index range is 0...0xffff */
-	int			set_tc_index;
+#define DSMARK_EMBEDDED_SZ	16
+	struct mask_value	embedded[DSMARK_EMBEDDED_SZ];
 };
 
 static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index)
@@ -116,7 +122,6 @@ static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent,
 	struct nlattr *opt = tca[TCA_OPTIONS];
 	struct nlattr *tb[TCA_DSMARK_MAX + 1];
 	int err = -EINVAL;
-	u8 mask = 0;
 
 	pr_debug("%s(sch %p,[qdisc %p],classid %x,parent %x), arg 0x%lx\n",
 		 __func__, sch, p, classid, parent, *arg);
@@ -133,14 +138,11 @@ static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent,
 	if (err < 0)
 		goto errout;
 
-	if (tb[TCA_DSMARK_MASK])
-		mask = nla_get_u8(tb[TCA_DSMARK_MASK]);
-
 	if (tb[TCA_DSMARK_VALUE])
-		p->value[*arg - 1] = nla_get_u8(tb[TCA_DSMARK_VALUE]);
+		p->mv[*arg - 1].value = nla_get_u8(tb[TCA_DSMARK_VALUE]);
 
 	if (tb[TCA_DSMARK_MASK])
-		p->mask[*arg - 1] = mask;
+		p->mv[*arg - 1].mask = nla_get_u8(tb[TCA_DSMARK_MASK]);
 
 	err = 0;
 
@@ -155,8 +157,8 @@ static int dsmark_delete(struct Qdisc *sch, unsigned long arg)
 	if (!dsmark_valid_index(p, arg))
 		return -EINVAL;
 
-	p->mask[arg - 1] = 0xff;
-	p->value[arg - 1] = 0;
+	p->mv[arg - 1].mask = 0xff;
+	p->mv[arg - 1].value = 0;
 
 	return 0;
 }
@@ -173,7 +175,7 @@ static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker)
 		return;
 
 	for (i = 0; i < p->indices; i++) {
-		if (p->mask[i] == 0xff && !p->value[i])
+		if (p->mv[i].mask == 0xff && !p->mv[i].value)
 			goto ignore;
 		if (walker->count >= walker->skip) {
 			if (walker->fn(sch, i + 1, walker) < 0) {
@@ -291,12 +293,12 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 
 	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
-		ipv4_change_dsfield(ip_hdr(skb), p->mask[index],
-				    p->value[index]);
+		ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask,
+				    p->mv[index].value);
 			break;
 	case htons(ETH_P_IPV6):
-		ipv6_change_dsfield(ipv6_hdr(skb), p->mask[index],
-				    p->value[index]);
+		ipv6_change_dsfield(ipv6_hdr(skb), p->mv[index].mask,
+				    p->mv[index].value);
 			break;
 	default:
 		/*
@@ -304,7 +306,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		 * This way, we can send non-IP traffic through dsmark
 		 * and don't need yet another qdisc as a bypass.
 		 */
-		if (p->mask[index] != 0xff || p->value[index])
+		if (p->mv[index].mask != 0xff || p->mv[index].value)
 			pr_warn("%s: unsupported protocol %d\n",
 				__func__, ntohs(tc_skb_protocol(skb)));
 		break;
@@ -346,7 +348,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt)
 	int err = -EINVAL;
 	u32 default_index = NO_DEFAULT_INDEX;
 	u16 indices;
-	u8 *mask;
+	int i;
 
 	pr_debug("%s(sch %p,[qdisc %p],opt %p)\n", __func__, sch, p, opt);
 
@@ -366,18 +368,18 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt)
 	if (tb[TCA_DSMARK_DEFAULT_INDEX])
 		default_index = nla_get_u16(tb[TCA_DSMARK_DEFAULT_INDEX]);
 
-	mask = kmalloc(indices * 2, GFP_KERNEL);
-	if (mask == NULL) {
+	if (indices <= DSMARK_EMBEDDED_SZ)
+		p->mv = p->embedded;
+	else
+		p->mv = kmalloc_array(indices, sizeof(*p->mv), GFP_KERNEL);
+	if (!p->mv) {
 		err = -ENOMEM;
 		goto errout;
 	}
-
-	p->mask = mask;
-	memset(p->mask, 0xff, indices);
-
-	p->value = p->mask + indices;
-	memset(p->value, 0, indices);
-
+	for (i = 0; i < indices; i++) {
+		p->mv[i].mask = 0xff;
+		p->mv[i].value = 0;
+	}
 	p->indices = indices;
 	p->default_index = default_index;
 	p->set_tc_index = nla_get_flag(tb[TCA_DSMARK_SET_TC_INDEX]);
@@ -410,7 +412,8 @@ static void dsmark_destroy(struct Qdisc *sch)
 
 	tcf_destroy_chain(&p->filter_list);
 	qdisc_destroy(p->q);
-	kfree(p->mask);
+	if (p->mv != p->embedded)
+		kfree(p->mv);
 }
 
 static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl,
@@ -430,8 +433,8 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl,
 	opts = nla_nest_start(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
-	if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mask[cl - 1]) ||
-	    nla_put_u8(skb, TCA_DSMARK_VALUE, p->value[cl - 1]))
+	if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mv[cl - 1].mask) ||
+	    nla_put_u8(skb, TCA_DSMARK_VALUE, p->mv[cl - 1].value))
 		goto nla_put_failure;
 
 	return nla_nest_end(skb, opts);