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

Pull networking changes from David S Miller:

 1) Remove the ipv4 routing cache.  Now lookups go directly into the FIB
    trie and use prebuilt routes cached there.

    No more garbage collection, no more rDOS attacks on the routing
    cache.  Instead we now get predictable and consistent performance,
    no matter what the pattern of traffic we service.

    This has been almost 2 years in the making.  Special thanks to
    Julian Anastasov, Eric Dumazet, Steffen Klassert, and others who
    have helped along the way.

    I'm sure that with a change of this magnitude there will be some
    kind of fallout, but such things ought the be simple to fix at this
    point.  Luckily I'm not European so I'll be around all of August to
    fix things :-)

    The major stages of this work here are each fronted by a forced
    merge commit whose commit message contains a top-level description
    of the motivations and implementation issues.

 2) Pre-demux of established ipv4 TCP sockets, saves a route demux on
    input.

 3) TCP SYN/ACK performance tweaks from Eric Dumazet.

 4) Add namespace support for netfilter L4 conntrack helpers, from Gao
    Feng.

 5) Add config mechanism for Energy Efficient Ethernet to ethtool, from
    Yuval Mintz.

 6) Remove quadratic behavior from /proc/net/unix, from Eric Dumazet.

 7) Support for connection tracker helpers in userspace, from Pablo
    Neira Ayuso.

 8) Allow userspace driven TX load balancing functions in TEAM driver,
    from Jiri Pirko.

 9) Kill off NLMSG_PUT and RTA_PUT macros, more gross stuff with
    embedded gotos.

10) TCP Small Queues, essentially minimize the amount of TCP data queued
    up in the packet scheduler layer.  Whereas the existing BQL (Byte
    Queue Limits) limits the pkt_sched --> netdevice queuing levels,
    this controls the TCP --> pkt_sched queueing levels.

    From Eric Dumazet.

11) Reduce the number of get_page/put_page ops done on SKB fragments,
    from Alexander Duyck.

12) Implement protection against blind resets in TCP (RFC 5961), from
    Eric Dumazet.

13) Support the client side of TCP Fast Open, basically the ability to
    send data in the SYN exchange, from Yuchung Cheng.

    Basically, the sender queues up data with a sendmsg() call using
    MSG_FASTOPEN, then they do the connect() which emits the queued up
    fastopen data.

14) Avoid all the problems we get into in TCP when timers or PMTU events
    hit a locked socket.  The TCP Small Queues changes added a
    tcp_release_cb() that allows us to queue work up to the
    release_sock() caller, and that's what we use here too.  From Eric
    Dumazet.

15) Zero copy on TX support for TUN driver, from Michael S. Tsirkin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1870 commits)
  genetlink: define lockdep_genl_is_held() when CONFIG_LOCKDEP
  r8169: revert "add byte queue limit support".
  ipv4: Change rt->rt_iif encoding.
  net: Make skb->skb_iif always track skb->dev
  ipv4: Prepare for change of rt->rt_iif encoding.
  ipv4: Remove all RTCF_DIRECTSRC handliing.
  ipv4: Really ignore ICMP address requests/replies.
  decnet: Don't set RTCF_DIRECTSRC.
  net/ipv4/ip_vti.c: Fix __rcu warnings detected by sparse.
  ipv4: Remove redundant assignment
  rds: set correct msg_namelen
  openvswitch: potential NULL deref in sample()
  tcp: dont drop MTU reduction indications
  bnx2x: Add new 57840 device IDs
  tcp: avoid oops in tcp_metrics and reset tcpm_stamp
  niu: Change niu_rbr_fill() to use unlikely() to check niu_rbr_add_page() return value
  niu: Fix to check for dma mapping errors.
  net: Fix references to out-of-scope variables in put_cmsg_compat()
  net: ethernet: davinci_emac: add pm_runtime support
  net: ethernet: davinci_emac: Remove unnecessary #include
  ...

1 files changed, 240 insertions, 0 deletions

diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c
new file mode 100644
index 000000000000..bfd34e4c1afc
--- /dev/null
+++ b/net/sched/em_canid.c
@@ -0,0 +1,240 @@
+/*
+ * em_canid.c  Ematch rule to match CAN frames according to their CAN IDs
+ *
+ *              This program is free software; you can distribute it and/or
+ *              modify it under the terms of the GNU General Public License
+ *              as published by the Free Software Foundation; either version
+ *              2 of the License, or (at your option) any later version.
+ *
+ * Idea:       Oliver Hartkopp <oliver.hartkopp@volkswagen.de>
+ * Copyright:  (c) 2011 Czech Technical University in Prague
+ *             (c) 2011 Volkswagen Group Research
+ * Authors:    Michal Sojka <sojkam1@fel.cvut.cz>
+ *             Pavel Pisa <pisa@cmp.felk.cvut.cz>
+ *             Rostislav Lisovy <lisovy@gmail.cz>
+ * Funded by:  Volkswagen Group Research
+ */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/skbuff.h>
+#include <net/pkt_cls.h>
+#include <linux/can.h>
+
+#define EM_CAN_RULES_MAX 500
+
+struct canid_match {
+	/* For each SFF CAN ID (11 bit) there is one record in this bitfield */
+	DECLARE_BITMAP(match_sff, (1 << CAN_SFF_ID_BITS));
+
+	int rules_count;
+	int sff_rules_count;
+	int eff_rules_count;
+
+	/*
+	 * Raw rules copied from netlink message; Used for sending
+	 * information to userspace (when 'tc filter show' is invoked)
+	 * AND when matching EFF frames
+	 */
+	struct can_filter rules_raw[];
+};
+
+/**
+ * em_canid_get_id() - Extracts Can ID out of the sk_buff structure.
+ */
+static canid_t em_canid_get_id(struct sk_buff *skb)
+{
+	/* CAN ID is stored within the data field */
+	struct can_frame *cf = (struct can_frame *)skb->data;
+
+	return cf->can_id;
+}
+
+static void em_canid_sff_match_add(struct canid_match *cm, u32 can_id,
+					u32 can_mask)
+{
+	int i;
+
+	/*
+	 * Limit can_mask and can_id to SFF range to
+	 * protect against write after end of array
+	 */
+	can_mask &= CAN_SFF_MASK;
+	can_id &= can_mask;
+
+	/* Single frame */
+	if (can_mask == CAN_SFF_MASK) {
+		set_bit(can_id, cm->match_sff);
+		return;
+	}
+
+	/* All frames */
+	if (can_mask == 0) {
+		bitmap_fill(cm->match_sff, (1 << CAN_SFF_ID_BITS));
+		return;
+	}
+
+	/*
+	 * Individual frame filter.
+	 * Add record (set bit to 1) for each ID that
+	 * conforms particular rule
+	 */
+	for (i = 0; i < (1 << CAN_SFF_ID_BITS); i++) {
+		if ((i & can_mask) == can_id)
+			set_bit(i, cm->match_sff);
+	}
+}
+
+static inline struct canid_match *em_canid_priv(struct tcf_ematch *m)
+{
+	return (struct canid_match *)m->data;
+}
+
+static int em_canid_match(struct sk_buff *skb, struct tcf_ematch *m,
+			 struct tcf_pkt_info *info)
+{
+	struct canid_match *cm = em_canid_priv(m);
+	canid_t can_id;
+	int match = 0;
+	int i;
+	const struct can_filter *lp;
+
+	can_id = em_canid_get_id(skb);
+
+	if (can_id & CAN_EFF_FLAG) {
+		for (i = 0, lp = cm->rules_raw;
+		     i < cm->eff_rules_count; i++, lp++) {
+			if (!(((lp->can_id ^ can_id) & lp->can_mask))) {
+				match = 1;
+				break;
+			}
+		}
+	} else { /* SFF */
+		can_id &= CAN_SFF_MASK;
+		match = (test_bit(can_id, cm->match_sff) ? 1 : 0);
+	}
+
+	return match;
+}
+
+static int em_canid_change(struct tcf_proto *tp, void *data, int len,
+			  struct tcf_ematch *m)
+{
+	struct can_filter *conf = data; /* Array with rules */
+	struct canid_match *cm;
+	struct canid_match *cm_old = (struct canid_match *)m->data;
+	int i;
+
+	if (!len)
+		return -EINVAL;
+
+	if (len % sizeof(struct can_filter))
+		return -EINVAL;
+
+	if (len > sizeof(struct can_filter) * EM_CAN_RULES_MAX)
+		return -EINVAL;
+
+	cm = kzalloc(sizeof(struct canid_match) + len, GFP_KERNEL);
+	if (!cm)
+		return -ENOMEM;
+
+	cm->rules_count = len / sizeof(struct can_filter);
+
+	/*
+	 * We need two for() loops for copying rules into two contiguous
+	 * areas in rules_raw to process all eff rules with a simple loop.
+	 * NB: The configuration interface supports sff and eff rules.
+	 * We do not support filters here that match for the same can_id
+	 * provided in a SFF and EFF frame (e.g. 0x123 / 0x80000123).
+	 * For this (unusual case) two filters have to be specified. The
+	 * SFF/EFF separation is done with the CAN_EFF_FLAG in the can_id.
+	 */
+
+	/* Fill rules_raw with EFF rules first */
+	for (i = 0; i < cm->rules_count; i++) {
+		if (conf[i].can_id & CAN_EFF_FLAG) {
+			memcpy(cm->rules_raw + cm->eff_rules_count,
+				&conf[i],
+				sizeof(struct can_filter));
+
+			cm->eff_rules_count++;
+		}
+	}
+
+	/* append SFF frame rules */
+	for (i = 0; i < cm->rules_count; i++) {
+		if (!(conf[i].can_id & CAN_EFF_FLAG)) {
+			memcpy(cm->rules_raw
+				+ cm->eff_rules_count
+				+ cm->sff_rules_count,
+				&conf[i], sizeof(struct can_filter));
+
+			cm->sff_rules_count++;
+
+			em_canid_sff_match_add(cm,
+				conf[i].can_id, conf[i].can_mask);
+		}
+	}
+
+	m->datalen = sizeof(struct canid_match) + len;
+	m->data = (unsigned long)cm;
+
+	if (cm_old != NULL) {
+		pr_err("canid: Configuring an existing ematch!\n");
+		kfree(cm_old);
+	}
+
+	return 0;
+}
+
+static void em_canid_destroy(struct tcf_proto *tp, struct tcf_ematch *m)
+{
+	struct canid_match *cm = em_canid_priv(m);
+
+	kfree(cm);
+}
+
+static int em_canid_dump(struct sk_buff *skb, struct tcf_ematch *m)
+{
+	struct canid_match *cm = em_canid_priv(m);
+
+	/*
+	 * When configuring this ematch 'rules_count' is set not to exceed
+	 * 'rules_raw' array size
+	 */
+	if (nla_put_nohdr(skb, sizeof(struct can_filter) * cm->rules_count,
+	    &cm->rules_raw) < 0)
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static struct tcf_ematch_ops em_canid_ops = {
+	.kind	  = TCF_EM_CANID,
+	.change	  = em_canid_change,
+	.match	  = em_canid_match,
+	.destroy  = em_canid_destroy,
+	.dump	  = em_canid_dump,
+	.owner	  = THIS_MODULE,
+	.link	  = LIST_HEAD_INIT(em_canid_ops.link)
+};
+
+static int __init init_em_canid(void)
+{
+	return tcf_em_register(&em_canid_ops);
+}
+
+static void __exit exit_em_canid(void)
+{
+	tcf_em_unregister(&em_canid_ops);
+}
+
+MODULE_LICENSE("GPL");
+
+module_init(init_em_canid);
+module_exit(exit_em_canid);
+
+MODULE_ALIAS_TCF_EMATCH(TCF_EM_CANID);