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

Pull networking changes from David Miller:

 1) Get rid of the error prone NLA_PUT*() macros that used an embedded
    goto.

 2) Kill off the token-ring and MCA networking drivers, from Paul
    Gortmaker.

 3) Reduce high-order allocations made by datagram AF_UNIX sockets, from
    Eric Dumazet.

 4) Add PTP hardware clock support to IGB and IXGBE, from Richard
    Cochran and Jacob Keller.

 5) Allow users to query timestamping capabilities of a card via
    ethtool, from Richard Cochran.

 6) Add loadbalance mode to the teaming driver, from Jiri Pirko.  Part
    of this is that we can now have BPF filters not attached to sockets,
    and the loadbalancing function is calculated using one.

 7) Francois Romieu went through the network drivers removing gratuitous
    uses of netdev->base_addr, perhaps some day we can remove it
    completely but it's used for ISA probing still.

 8) Add a BPF JIT for sparc.  I know, who cares, right? :-)

 9) Move networking sysctl registry away from using the compatability
    mode interfaces in the sysctl code.  From Eric W Biederman.

10) Pavel Emelyanov added a way to save and restore TCP socket state via
    TCP_REPAIR, TCP_REPAIR_QUEUE, and TCP_QUEUE_SEQ socket options as
    well as a way to forcefully bind a socket to a port via the
    sk->sk_reuse value SK_FORCE_REUSE.  There is also a
    TCP_REPAIR_OPTIONS which allows to reinstante the TCP options
    enabled on the connection.

11) Several enhancements from Eric Dumazet that, in particular, can
    enhance splice performance on TCP sockets significantly.

     a) Reset the offset of the per-socket sendmsg page when we know
        we're the only use of the page in linear_to_page().

     b) Add facilities such that skb->data can be backed a page rather
        than SLAB kmalloc'd memory.  In particular devices which were
        receiving into linear RX buffers can now end up providing paged
        data.

    The big result is that code like splice and GRO do not have to copy
    any more.

12) Allow a pure sender to more gracefully handle ACK backlogs in TCP.
    What can happen at high rates is that the sender hasn't grown his
    receive buffer limits at all (he's not receiving data so really
    doesn't need to), but the non-data ACKs consume receive buffer
    space.

    sk_add_backlog() is too aggressive in dropping frames in this case,
    so relax it's requirements by using the receive buffer plus the send
    buffer limit as the backlog limit instead of just the former.

    Also from Eric Dumazet.

13) Add ipv6 support to L2TP, from Benjamin LaHaise, James Chapman, and
    Chris Elston.

14) Implement TCP early retransmit (RFC 5827), from Yuchung Cheng.
    Basically, we can start fast retransmit before hiting the dupack
    threshold under certain conditions.

15) New CODEL active queue management packet scheduler, from Eric
    Dumazet based upon initial work by Dave Taht.

    Basically, the big feature is that packets are dropped (or ECN bits
    are set) based upon how long packets live in the queue, rather than
    the queue length (which is what RED uses).

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1341 commits)
  drivers/net/stmmac: seq_file fix memory leak
  ipv6/exthdrs: strict Pad1 and PadN check
  USB: qmi_wwan: Add ZTE (Vodafone) K3520-Z
  USB: qmi_wwan: Add ZTE (Vodafone) K3765-Z
  USB: qmi_wwan: Make forced int 4 whitelist generic
  net/ipv4: replace simple_strtoul with kstrtoul
  net/ipv4/ipconfig: neaten __setup placement
  net: qmi_wwan: Add Vodafone/Huawei K5005 support
  net: cdc_ether: Add ZTE WWAN matches before generic Ethernet
  ipv6: use skb coalescing in reassembly
  ipv4: use skb coalescing in defragmentation
  net: introduce skb_try_coalesce()
  net:ipv6:fixed space issues relating to operators.
  net:ipv6:fixed a trailing white space issue.
  ipv6: disable GSO on sockets hitting dst_allfrag
  tg3: use netdev_alloc_frag() API
  net: napi_frags_skb() is static
  ppp: avoid false drop_monitor false positives
  ipv6: bool/const conversions phase2
  ipx: Remove spurious NULL checking in ipx_ioctl().
  ...

1 files changed, 316 insertions, 0 deletions

diff --git a/net/mac80211/mesh_sync.c b/net/mac80211/mesh_sync.c
new file mode 100644
index 000000000000..38d30e8ce6dc
--- /dev/null
+++ b/net/mac80211/mesh_sync.c
@@ -0,0 +1,316 @@
+/*
+ * Copyright 2011-2012, Pavel Zubarev <pavel.zubarev@gmail.com>
+ * Copyright 2011-2012, Marco Porsch <marco.porsch@s2005.tu-chemnitz.de>
+ * Copyright 2011-2012, cozybit Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "ieee80211_i.h"
+#include "mesh.h"
+#include "driver-ops.h"
+
+#ifdef CONFIG_MAC80211_VERBOSE_MESH_SYNC_DEBUG
+#define msync_dbg(fmt, args...) \
+	printk(KERN_DEBUG "Mesh sync (%s): " fmt "\n", sdata->name, ##args)
+#else
+#define msync_dbg(fmt, args...)   do { (void)(0); } while (0)
+#endif
+
+/* This is not in the standard.  It represents a tolerable tbtt drift below
+ * which we do no TSF adjustment.
+ */
+#define TOFFSET_MINIMUM_ADJUSTMENT 10
+
+/* This is not in the standard. It is a margin added to the
+ * Toffset setpoint to mitigate TSF overcorrection
+ * introduced by TSF adjustment latency.
+ */
+#define TOFFSET_SET_MARGIN 20
+
+/* This is not in the standard.  It represents the maximum Toffset jump above
+ * which we'll invalidate the Toffset setpoint and choose a new setpoint.  This
+ * could be, for instance, in case a neighbor is restarted and its TSF counter
+ * reset.
+ */
+#define TOFFSET_MAXIMUM_ADJUSTMENT 30000		/* 30 ms */
+
+struct sync_method {
+	u8 method;
+	struct ieee80211_mesh_sync_ops ops;
+};
+
+/**
+ * mesh_peer_tbtt_adjusting - check if an mp is currently adjusting its TBTT
+ *
+ * @ie: information elements of a management frame from the mesh peer
+ */
+static bool mesh_peer_tbtt_adjusting(struct ieee802_11_elems *ie)
+{
+	return (ie->mesh_config->meshconf_cap &
+	    MESHCONF_CAPAB_TBTT_ADJUSTING) != 0;
+}
+
+void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
+	/* sdata->vif.bss_conf.beacon_int in 1024us units, 0.04% */
+	u64 beacon_int_fraction = sdata->vif.bss_conf.beacon_int * 1024 / 2500;
+	u64 tsf;
+	u64 tsfdelta;
+
+	spin_lock_bh(&ifmsh->sync_offset_lock);
+
+	if (ifmsh->sync_offset_clockdrift_max < beacon_int_fraction) {
+		msync_dbg("TBTT : max clockdrift=%lld; adjusting",
+			(long long) ifmsh->sync_offset_clockdrift_max);
+		tsfdelta = -ifmsh->sync_offset_clockdrift_max;
+		ifmsh->sync_offset_clockdrift_max = 0;
+	} else {
+		msync_dbg("TBTT : max clockdrift=%lld; adjusting by %llu",
+			(long long) ifmsh->sync_offset_clockdrift_max,
+			(unsigned long long) beacon_int_fraction);
+		tsfdelta = -beacon_int_fraction;
+		ifmsh->sync_offset_clockdrift_max -= beacon_int_fraction;
+	}
+
+	tsf = drv_get_tsf(local, sdata);
+	if (tsf != -1ULL)
+		drv_set_tsf(local, sdata, tsf + tsfdelta);
+	spin_unlock_bh(&ifmsh->sync_offset_lock);
+}
+
+static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata,
+				   u16 stype,
+				   struct ieee80211_mgmt *mgmt,
+				   struct ieee802_11_elems *elems,
+				   struct ieee80211_rx_status *rx_status)
+{
+	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
+	struct ieee80211_local *local = sdata->local;
+	struct sta_info *sta;
+	u64 t_t, t_r;
+
+	WARN_ON(ifmsh->mesh_sp_id != IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET);
+
+	/* standard mentions only beacons */
+	if (stype != IEEE80211_STYPE_BEACON)
+		return;
+
+	/* The current tsf is a first approximation for the timestamp
+	 * for the received beacon.  Further down we try to get a
+	 * better value from the rx_status->mactime field if
+	 * available. Also we have to call drv_get_tsf() before
+	 * entering the rcu-read section.*/
+	t_r = drv_get_tsf(local, sdata);
+
+	rcu_read_lock();
+	sta = sta_info_get(sdata, mgmt->sa);
+	if (!sta)
+		goto no_sync;
+
+	/* check offset sync conditions (13.13.2.2.1)
+	 *
+	 * TODO also sync to
+	 * dot11MeshNbrOffsetMaxNeighbor non-peer non-MBSS neighbors
+	 */
+
+	if (elems->mesh_config && mesh_peer_tbtt_adjusting(elems)) {
+		clear_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN);
+		msync_dbg("STA %pM : is adjusting TBTT", sta->sta.addr);
+		goto no_sync;
+	}
+
+	if (rx_status->flag & RX_FLAG_MACTIME_MPDU && rx_status->mactime) {
+		/*
+		 * The mactime is defined as the time the first data symbol
+		 * of the frame hits the PHY, and the timestamp of the beacon
+		 * is defined as "the time that the data symbol containing the
+		 * first bit of the timestamp is transmitted to the PHY plus
+		 * the transmitting STA's delays through its local PHY from the
+		 * MAC-PHY interface to its interface with the WM" (802.11
+		 * 11.1.2)
+		 *
+		 * T_r, in 13.13.2.2.2, is just defined as "the frame reception
+		 * time" but we unless we interpret that time to be the same
+		 * time of the beacon timestamp, the offset calculation will be
+		 * off.  Below we adjust t_r to be "the time at which the first
+		 * symbol of the timestamp element in the beacon is received".
+		 * This correction depends on the rate.
+		 *
+		 * Based on similar code in ibss.c
+		 */
+		int rate;
+
+		if (rx_status->flag & RX_FLAG_HT) {
+			/* TODO:
+			 * In principle there could be HT-beacons (Dual Beacon
+			 * HT Operation options), but for now ignore them and
+			 * just use the primary (i.e. non-HT) beacons for
+			 * synchronization.
+			 * */
+			goto no_sync;
+		} else
+			rate = local->hw.wiphy->bands[rx_status->band]->
+				bitrates[rx_status->rate_idx].bitrate;
+
+		/* 24 bytes of header * 8 bits/byte *
+		 * 10*(100 Kbps)/Mbps / rate (100 Kbps)*/
+		t_r = rx_status->mactime + (24 * 8 * 10 / rate);
+	}
+
+	/* Timing offset calculation (see 13.13.2.2.2) */
+	t_t = le64_to_cpu(mgmt->u.beacon.timestamp);
+	sta->t_offset = t_t - t_r;
+
+	if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) {
+		s64 t_clockdrift = sta->t_offset_setpoint
+				   - sta->t_offset;
+		msync_dbg("STA %pM : sta->t_offset=%lld, sta->t_offset_setpoint=%lld, t_clockdrift=%lld",
+			  sta->sta.addr,
+			  (long long) sta->t_offset,
+			  (long long)
+			  sta->t_offset_setpoint,
+			  (long long) t_clockdrift);
+
+		if (t_clockdrift > TOFFSET_MAXIMUM_ADJUSTMENT ||
+			t_clockdrift < -TOFFSET_MAXIMUM_ADJUSTMENT) {
+			msync_dbg("STA %pM : t_clockdrift=%lld too large, setpoint reset",
+				  sta->sta.addr,
+				  (long long) t_clockdrift);
+			clear_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN);
+			goto no_sync;
+		}
+
+		rcu_read_unlock();
+
+		spin_lock_bh(&ifmsh->sync_offset_lock);
+		if (t_clockdrift >
+		    ifmsh->sync_offset_clockdrift_max)
+			ifmsh->sync_offset_clockdrift_max
+				= t_clockdrift;
+		spin_unlock_bh(&ifmsh->sync_offset_lock);
+
+	} else {
+		sta->t_offset_setpoint = sta->t_offset - TOFFSET_SET_MARGIN;
+		set_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN);
+		msync_dbg("STA %pM : offset was invalid, "
+			  " sta->t_offset=%lld",
+			  sta->sta.addr,
+			  (long long) sta->t_offset);
+		rcu_read_unlock();
+	}
+	return;
+
+no_sync:
+	rcu_read_unlock();
+}
+
+static void mesh_sync_offset_adjust_tbtt(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
+
+	WARN_ON(ifmsh->mesh_sp_id
+		!= IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET);
+	BUG_ON(!rcu_read_lock_held());
+
+	spin_lock_bh(&ifmsh->sync_offset_lock);
+
+	if (ifmsh->sync_offset_clockdrift_max >
+		TOFFSET_MINIMUM_ADJUSTMENT) {
+		/* Since ajusting the tsf here would
+		 * require a possibly blocking call
+		 * to the driver tsf setter, we punt
+		 * the tsf adjustment to the mesh tasklet
+		 */
+		msync_dbg("TBTT : kicking off TBTT "
+			  "adjustment with "
+			  "clockdrift_max=%lld",
+		  ifmsh->sync_offset_clockdrift_max);
+		set_bit(MESH_WORK_DRIFT_ADJUST,
+			&ifmsh->wrkq_flags);
+	} else {
+		msync_dbg("TBTT : max clockdrift=%lld; "
+			  "too small to adjust",
+			  (long long)
+		       ifmsh->sync_offset_clockdrift_max);
+		ifmsh->sync_offset_clockdrift_max = 0;
+	}
+	spin_unlock_bh(&ifmsh->sync_offset_lock);
+}
+
+static const u8 *mesh_get_vendor_oui(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
+	u8 offset;
+
+	if (!ifmsh->ie || !ifmsh->ie_len)
+		return NULL;
+
+	offset = ieee80211_ie_split_vendor(ifmsh->ie,
+					ifmsh->ie_len, 0);
+
+	if (!offset)
+		return NULL;
+
+	return ifmsh->ie + offset + 2;
+}
+
+static void mesh_sync_vendor_rx_bcn_presp(struct ieee80211_sub_if_data *sdata,
+				   u16 stype,
+				   struct ieee80211_mgmt *mgmt,
+				   struct ieee802_11_elems *elems,
+				   struct ieee80211_rx_status *rx_status)
+{
+	const u8 *oui;
+
+	WARN_ON(sdata->u.mesh.mesh_sp_id != IEEE80211_SYNC_METHOD_VENDOR);
+	msync_dbg("called mesh_sync_vendor_rx_bcn_presp");
+	oui = mesh_get_vendor_oui(sdata);
+	/*  here you would implement the vendor offset tracking for this oui */
+}
+
+static void mesh_sync_vendor_adjust_tbtt(struct ieee80211_sub_if_data *sdata)
+{
+	const u8 *oui;
+
+	WARN_ON(sdata->u.mesh.mesh_sp_id != IEEE80211_SYNC_METHOD_VENDOR);
+	msync_dbg("called mesh_sync_vendor_adjust_tbtt");
+	oui = mesh_get_vendor_oui(sdata);
+	/*  here you would implement the vendor tsf adjustment for this oui */
+}
+
+/* global variable */
+static struct sync_method sync_methods[] = {
+	{
+		.method = IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET,
+		.ops = {
+			.rx_bcn_presp = &mesh_sync_offset_rx_bcn_presp,
+			.adjust_tbtt = &mesh_sync_offset_adjust_tbtt,
+		}
+	},
+	{
+		.method = IEEE80211_SYNC_METHOD_VENDOR,
+		.ops = {
+			.rx_bcn_presp = &mesh_sync_vendor_rx_bcn_presp,
+			.adjust_tbtt = &mesh_sync_vendor_adjust_tbtt,
+		}
+	},
+};
+
+struct ieee80211_mesh_sync_ops *ieee80211_mesh_sync_ops_get(u8 method)
+{
+	struct ieee80211_mesh_sync_ops *ops = NULL;
+	u8 i;
+
+	for (i = 0 ; i < ARRAY_SIZE(sync_methods); ++i) {
+		if (sync_methods[i].method == method) {
+			ops = &sync_methods[i].ops;
+			break;
+		}
+	}
+	return ops;
+}