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

Pull networking updates from David Miller:

 1) More iov_iter conversion work from Al Viro.

    [ The "crypto: switch af_alg_make_sg() to iov_iter" commit was
      wrong, and this pull actually adds an extra commit on top of the
      branch I'm pulling to fix that up, so that the pre-merge state is
      ok.   - Linus ]

 2) Various optimizations to the ipv4 forwarding information base trie
    lookup implementation.  From Alexander Duyck.

 3) Remove sock_iocb altogether, from CHristoph Hellwig.

 4) Allow congestion control algorithm selection via routing metrics.
    From Daniel Borkmann.

 5) Make ipv4 uncached route list per-cpu, from Eric Dumazet.

 6) Handle rfs hash collisions more gracefully, also from Eric Dumazet.

 7) Add xmit_more support to r8169, e1000, and e1000e drivers.  From
    Florian Westphal.

 8) Transparent Ethernet Bridging support for GRO, from Jesse Gross.

 9) Add BPF packet actions to packet scheduler, from Jiri Pirko.

10) Add support for uniqu flow IDs to openvswitch, from Joe Stringer.

11) New NetCP ethernet driver, from Muralidharan Karicheri and Wingman
    Kwok.

12) More sanely handle out-of-window dupacks, which can result in
    serious ACK storms.  From Neal Cardwell.

13) Various rhashtable bug fixes and enhancements, from Herbert Xu,
    Patrick McHardy, and Thomas Graf.

14) Support xmit_more in be2net, from Sathya Perla.

15) Group Policy extensions for vxlan, from Thomas Graf.

16) Remove Checksum Offload support for vxlan, from Tom Herbert.

17) Like ipv4, support lockless transmit over ipv6 UDP sockets.  From
    Vlad Yasevich.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1494+1 commits)
  crypto: fix af_alg_make_sg() conversion to iov_iter
  ipv4: Namespecify TCP PMTU mechanism
  i40e: Fix for stats init function call in Rx setup
  tcp: don't include Fast Open option in SYN-ACK on pure SYN-data
  openvswitch: Only set TUNNEL_VXLAN_OPT if VXLAN-GBP metadata is set
  ipv6: Make __ipv6_select_ident static
  ipv6: Fix fragment id assignment on LE arches.
  bridge: Fix inability to add non-vlan fdb entry
  net: Mellanox: Delete unnecessary checks before the function call "vunmap"
  cxgb4: Add support in cxgb4 to get expansion rom version via ethtool
  ethtool: rename reserved1 memeber in ethtool_drvinfo for expansion ROM version
  net: dsa: Remove redundant phy_attach()
  IB/mlx4: Reset flow support for IB kernel ULPs
  IB/mlx4: Always use the correct port for mirrored multicast attachments
  net/bonding: Fix potential bad memory access during bonding events
  tipc: remove tipc_snprintf
  tipc: nl compat add noop and remove legacy nl framework
  tipc: convert legacy nl stats show to nl compat
  tipc: convert legacy nl net id get to nl compat
  tipc: convert legacy nl net id set to nl compat
  ...

5 files changed, 123 insertions, 88 deletions

diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 4b082b5cac9e..db3ccb1dd614 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -363,6 +363,14 @@ void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
 }
 EXPORT_SYMBOL(_raw_spin_lock_nested);
 
+void __lockfunc _raw_spin_lock_bh_nested(raw_spinlock_t *lock, int subclass)
+{
+	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
+	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
+}
+EXPORT_SYMBOL(_raw_spin_lock_bh_nested);
+
 unsigned long __lockfunc _raw_spin_lock_irqsave_nested(raw_spinlock_t *lock,
 						   int subclass)
 {
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 670fff88a961..21f82c29c914 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -111,13 +111,8 @@ static int send_reply(struct sk_buff *skb, struct genl_info *info)
 {
 	struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb));
 	void *reply = genlmsg_data(genlhdr);
-	int rc;
 
-	rc = genlmsg_end(skb, reply);
-	if (rc < 0) {
-		nlmsg_free(skb);
-		return rc;
-	}
+	genlmsg_end(skb, reply);
 
 	return genlmsg_reply(skb, info);
 }
@@ -134,11 +129,7 @@ static void send_cpu_listeners(struct sk_buff *skb,
 	void *reply = genlmsg_data(genlhdr);
 	int rc, delcount = 0;
 
-	rc = genlmsg_end(skb, reply);
-	if (rc < 0) {
-		nlmsg_free(skb);
-		return;
-	}
+	genlmsg_end(skb, reply);
 
 	rc = 0;
 	down_read(&listeners->sem);
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index f622cf28628a..c09c07817d7a 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,6 +1,6 @@
 obj-y += time.o timer.o hrtimer.o itimer.o posix-timers.o posix-cpu-timers.o
 obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o
-obj-y += timeconv.o posix-clock.o alarmtimer.o
+obj-y += timeconv.o timecounter.o posix-clock.o alarmtimer.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index b79f39bda7e1..4892352f0e49 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -34,82 +34,6 @@
 #include "tick-internal.h"
 #include "timekeeping_internal.h"
 
-void timecounter_init(struct timecounter *tc,
-		      const struct cyclecounter *cc,
-		      u64 start_tstamp)
-{
-	tc->cc = cc;
-	tc->cycle_last = cc->read(cc);
-	tc->nsec = start_tstamp;
-}
-EXPORT_SYMBOL_GPL(timecounter_init);
-
-/**
- * timecounter_read_delta - get nanoseconds since last call of this function
- * @tc:         Pointer to time counter
- *
- * When the underlying cycle counter runs over, this will be handled
- * correctly as long as it does not run over more than once between
- * calls.
- *
- * The first call to this function for a new time counter initializes
- * the time tracking and returns an undefined result.
- */
-static u64 timecounter_read_delta(struct timecounter *tc)
-{
-	cycle_t cycle_now, cycle_delta;
-	u64 ns_offset;
-
-	/* read cycle counter: */
-	cycle_now = tc->cc->read(tc->cc);
-
-	/* calculate the delta since the last timecounter_read_delta(): */
-	cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask;
-
-	/* convert to nanoseconds: */
-	ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta);
-
-	/* update time stamp of timecounter_read_delta() call: */
-	tc->cycle_last = cycle_now;
-
-	return ns_offset;
-}
-
-u64 timecounter_read(struct timecounter *tc)
-{
-	u64 nsec;
-
-	/* increment time by nanoseconds since last call */
-	nsec = timecounter_read_delta(tc);
-	nsec += tc->nsec;
-	tc->nsec = nsec;
-
-	return nsec;
-}
-EXPORT_SYMBOL_GPL(timecounter_read);
-
-u64 timecounter_cyc2time(struct timecounter *tc,
-			 cycle_t cycle_tstamp)
-{
-	u64 cycle_delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
-	u64 nsec;
-
-	/*
-	 * Instead of always treating cycle_tstamp as more recent
-	 * than tc->cycle_last, detect when it is too far in the
-	 * future and treat it as old time stamp instead.
-	 */
-	if (cycle_delta > tc->cc->mask / 2) {
-		cycle_delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask;
-		nsec = tc->nsec - cyclecounter_cyc2ns(tc->cc, cycle_delta);
-	} else {
-		nsec = cyclecounter_cyc2ns(tc->cc, cycle_delta) + tc->nsec;
-	}
-
-	return nsec;
-}
-EXPORT_SYMBOL_GPL(timecounter_cyc2time);
-
 /**
  * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks
  * @mult:	pointer to mult variable
diff --git a/kernel/time/timecounter.c b/kernel/time/timecounter.c
new file mode 100644
index 000000000000..4687b3104bae
--- /dev/null
+++ b/kernel/time/timecounter.c
@@ -0,0 +1,112 @@
+/*
+ * linux/kernel/time/timecounter.c
+ *
+ * based on code that migrated away from
+ * linux/kernel/time/clocksource.c
+ *
+ * This program is free software; you can redistribute 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/export.h>
+#include <linux/timecounter.h>
+
+void timecounter_init(struct timecounter *tc,
+		      const struct cyclecounter *cc,
+		      u64 start_tstamp)
+{
+	tc->cc = cc;
+	tc->cycle_last = cc->read(cc);
+	tc->nsec = start_tstamp;
+	tc->mask = (1ULL << cc->shift) - 1;
+	tc->frac = 0;
+}
+EXPORT_SYMBOL_GPL(timecounter_init);
+
+/**
+ * timecounter_read_delta - get nanoseconds since last call of this function
+ * @tc:         Pointer to time counter
+ *
+ * When the underlying cycle counter runs over, this will be handled
+ * correctly as long as it does not run over more than once between
+ * calls.
+ *
+ * The first call to this function for a new time counter initializes
+ * the time tracking and returns an undefined result.
+ */
+static u64 timecounter_read_delta(struct timecounter *tc)
+{
+	cycle_t cycle_now, cycle_delta;
+	u64 ns_offset;
+
+	/* read cycle counter: */
+	cycle_now = tc->cc->read(tc->cc);
+
+	/* calculate the delta since the last timecounter_read_delta(): */
+	cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask;
+
+	/* convert to nanoseconds: */
+	ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta,
+					tc->mask, &tc->frac);
+
+	/* update time stamp of timecounter_read_delta() call: */
+	tc->cycle_last = cycle_now;
+
+	return ns_offset;
+}
+
+u64 timecounter_read(struct timecounter *tc)
+{
+	u64 nsec;
+
+	/* increment time by nanoseconds since last call */
+	nsec = timecounter_read_delta(tc);
+	nsec += tc->nsec;
+	tc->nsec = nsec;
+
+	return nsec;
+}
+EXPORT_SYMBOL_GPL(timecounter_read);
+
+/*
+ * This is like cyclecounter_cyc2ns(), but it is used for computing a
+ * time previous to the time stored in the cycle counter.
+ */
+static u64 cc_cyc2ns_backwards(const struct cyclecounter *cc,
+			       cycle_t cycles, u64 mask, u64 frac)
+{
+	u64 ns = (u64) cycles;
+
+	ns = ((ns * cc->mult) - frac) >> cc->shift;
+
+	return ns;
+}
+
+u64 timecounter_cyc2time(struct timecounter *tc,
+			 cycle_t cycle_tstamp)
+{
+	u64 delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
+	u64 nsec = tc->nsec, frac = tc->frac;
+
+	/*
+	 * Instead of always treating cycle_tstamp as more recent
+	 * than tc->cycle_last, detect when it is too far in the
+	 * future and treat it as old time stamp instead.
+	 */
+	if (delta > tc->cc->mask / 2) {
+		delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask;
+		nsec -= cc_cyc2ns_backwards(tc->cc, delta, tc->mask, frac);
+	} else {
+		nsec += cyclecounter_cyc2ns(tc->cc, delta, tc->mask, &frac);
+	}
+
+	return nsec;
+}
+EXPORT_SYMBOL_GPL(timecounter_cyc2time);