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

Pull networking fixes from David Miller:

 1) Fix RCU warnings in ipv6 multicast router code, from Madhuparna
    Bhowmik.

 2) Nexthop attributes aren't being checked properly because of
    mis-initialized iterator, from David Ahern.

 3) Revert iop_idents_reserve() change as it caused performance
    regressions and was just working around what is really a UBSAN bug
    in the compiler. From Yuqi Jin.

 4) Read MAC address properly from ROM in bmac driver (double iteration
    proceeds past end of address array), from Jeremy Kerr.

 5) Add Microsoft Surface device IDs to r8152, from Marc Payne.

 6) Prevent reference to freed SKB in __netif_receive_skb_core(), from
    Boris Sukholitko.

 7) Fix ACK discard behavior in rxrpc, from David Howells.

 8) Preserve flow hash across packet scrubbing in wireguard, from Jason
    A. Donenfeld.

 9) Cap option length properly for SO_BINDTODEVICE in AX25, from Eric
    Dumazet.

10) Fix encryption error checking in kTLS code, from Vadim Fedorenko.

11) Missing BPF prog ref release in flow dissector, from Jakub Sitnicki.

12) dst_cache must be used with BH disabled in tipc, from Eric Dumazet.

13) Fix use after free in mlxsw driver, from Jiri Pirko.

14) Order kTLS key destruction properly in mlx5 driver, from Tariq
    Toukan.

15) Check devm_platform_ioremap_resource() return value properly in
    several drivers, from Tiezhu Yang.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (71 commits)
  net: smsc911x: Fix runtime PM imbalance on error
  net/mlx4_core: fix a memory leak bug.
  net: ethernet: ti: cpsw: fix ASSERT_RTNL() warning during suspend
  net: phy: mscc: fix initialization of the MACsec protocol mode
  net: stmmac: don't attach interface until resume finishes
  net: Fix return value about devm_platform_ioremap_resource()
  net/mlx5: Fix error flow in case of function_setup failure
  net/mlx5e: CT: Correctly get flow rule
  net/mlx5e: Update netdev txq on completions during closure
  net/mlx5: Annotate mutex destroy for root ns
  net/mlx5: Don't maintain a case of del_sw_func being null
  net/mlx5: Fix cleaning unmanaged flow tables
  net/mlx5: Fix memory leak in mlx5_events_init
  net/mlx5e: Fix inner tirs handling
  net/mlx5e: kTLS, Destroy key object after destroying the TIS
  net/mlx5e: Fix allowed tc redirect merged eswitch offload cases
  net/mlx5: Avoid processing commands before cmdif is ready
  net/mlx5: Fix a race when moving command interface to events mode
  net/mlx5: Add command entry handling completion
  rxrpc: Fix a memory leak in rxkad_verify_response()
  ...

1 files changed, 195 insertions, 0 deletions

diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c
new file mode 100644
index 000000000000..928d8b34a3ee
--- /dev/null
+++ b/net/rxrpc/rtt.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/* RTT/RTO calculation.
+ *
+ * Adapted from TCP for AF_RXRPC by David Howells (dhowells@redhat.com)
+ *
+ * https://tools.ietf.org/html/rfc6298
+ * https://tools.ietf.org/html/rfc1122#section-4.2.3.1
+ * http://ccr.sigcomm.org/archive/1995/jan95/ccr-9501-partridge87.pdf
+ */
+
+#include <linux/net.h>
+#include "ar-internal.h"
+
+#define RXRPC_RTO_MAX	((unsigned)(120 * HZ))
+#define RXRPC_TIMEOUT_INIT ((unsigned)(1*HZ))	/* RFC6298 2.1 initial RTO value	*/
+#define rxrpc_jiffies32 ((u32)jiffies)		/* As rxrpc_jiffies32 */
+#define rxrpc_min_rtt_wlen 300			/* As sysctl_tcp_min_rtt_wlen */
+
+static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer)
+{
+	return 200;
+}
+
+static u32 __rxrpc_set_rto(const struct rxrpc_peer *peer)
+{
+	return _usecs_to_jiffies((peer->srtt_us >> 3) + peer->rttvar_us);
+}
+
+static u32 rxrpc_bound_rto(u32 rto)
+{
+	return min(rto, RXRPC_RTO_MAX);
+}
+
+/*
+ * Called to compute a smoothed rtt estimate. The data fed to this
+ * routine either comes from timestamps, or from segments that were
+ * known _not_ to have been retransmitted [see Karn/Partridge
+ * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88
+ * piece by Van Jacobson.
+ * NOTE: the next three routines used to be one big routine.
+ * To save cycles in the RFC 1323 implementation it was better to break
+ * it up into three procedures. -- erics
+ */
+static void rxrpc_rtt_estimator(struct rxrpc_peer *peer, long sample_rtt_us)
+{
+	long m = sample_rtt_us; /* RTT */
+	u32 srtt = peer->srtt_us;
+
+	/*	The following amusing code comes from Jacobson's
+	 *	article in SIGCOMM '88.  Note that rtt and mdev
+	 *	are scaled versions of rtt and mean deviation.
+	 *	This is designed to be as fast as possible
+	 *	m stands for "measurement".
+	 *
+	 *	On a 1990 paper the rto value is changed to:
+	 *	RTO = rtt + 4 * mdev
+	 *
+	 * Funny. This algorithm seems to be very broken.
+	 * These formulae increase RTO, when it should be decreased, increase
+	 * too slowly, when it should be increased quickly, decrease too quickly
+	 * etc. I guess in BSD RTO takes ONE value, so that it is absolutely
+	 * does not matter how to _calculate_ it. Seems, it was trap
+	 * that VJ failed to avoid. 8)
+	 */
+	if (srtt != 0) {
+		m -= (srtt >> 3);	/* m is now error in rtt est */
+		srtt += m;		/* rtt = 7/8 rtt + 1/8 new */
+		if (m < 0) {
+			m = -m;		/* m is now abs(error) */
+			m -= (peer->mdev_us >> 2);   /* similar update on mdev */
+			/* This is similar to one of Eifel findings.
+			 * Eifel blocks mdev updates when rtt decreases.
+			 * This solution is a bit different: we use finer gain
+			 * for mdev in this case (alpha*beta).
+			 * Like Eifel it also prevents growth of rto,
+			 * but also it limits too fast rto decreases,
+			 * happening in pure Eifel.
+			 */
+			if (m > 0)
+				m >>= 3;
+		} else {
+			m -= (peer->mdev_us >> 2);   /* similar update on mdev */
+		}
+
+		peer->mdev_us += m;		/* mdev = 3/4 mdev + 1/4 new */
+		if (peer->mdev_us > peer->mdev_max_us) {
+			peer->mdev_max_us = peer->mdev_us;
+			if (peer->mdev_max_us > peer->rttvar_us)
+				peer->rttvar_us = peer->mdev_max_us;
+		}
+	} else {
+		/* no previous measure. */
+		srtt = m << 3;		/* take the measured time to be rtt */
+		peer->mdev_us = m << 1;	/* make sure rto = 3*rtt */
+		peer->rttvar_us = max(peer->mdev_us, rxrpc_rto_min_us(peer));
+		peer->mdev_max_us = peer->rttvar_us;
+	}
+
+	peer->srtt_us = max(1U, srtt);
+}
+
+/*
+ * Calculate rto without backoff.  This is the second half of Van Jacobson's
+ * routine referred to above.
+ */
+static void rxrpc_set_rto(struct rxrpc_peer *peer)
+{
+	u32 rto;
+
+	/* 1. If rtt variance happened to be less 50msec, it is hallucination.
+	 *    It cannot be less due to utterly erratic ACK generation made
+	 *    at least by solaris and freebsd. "Erratic ACKs" has _nothing_
+	 *    to do with delayed acks, because at cwnd>2 true delack timeout
+	 *    is invisible. Actually, Linux-2.4 also generates erratic
+	 *    ACKs in some circumstances.
+	 */
+	rto = __rxrpc_set_rto(peer);
+
+	/* 2. Fixups made earlier cannot be right.
+	 *    If we do not estimate RTO correctly without them,
+	 *    all the algo is pure shit and should be replaced
+	 *    with correct one. It is exactly, which we pretend to do.
+	 */
+
+	/* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo
+	 * guarantees that rto is higher.
+	 */
+	peer->rto_j = rxrpc_bound_rto(rto);
+}
+
+static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us)
+{
+	if (rtt_us < 0)
+		return;
+
+	//rxrpc_update_rtt_min(peer, rtt_us);
+	rxrpc_rtt_estimator(peer, rtt_us);
+	rxrpc_set_rto(peer);
+
+	/* RFC6298: only reset backoff on valid RTT measurement. */
+	peer->backoff = 0;
+}
+
+/*
+ * Add RTT information to cache.  This is called in softirq mode and has
+ * exclusive access to the peer RTT data.
+ */
+void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
+			rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
+			ktime_t send_time, ktime_t resp_time)
+{
+	struct rxrpc_peer *peer = call->peer;
+	s64 rtt_us;
+
+	rtt_us = ktime_to_us(ktime_sub(resp_time, send_time));
+	if (rtt_us < 0)
+		return;
+
+	spin_lock(&peer->rtt_input_lock);
+	rxrpc_ack_update_rtt(peer, rtt_us);
+	if (peer->rtt_count < 3)
+		peer->rtt_count++;
+	spin_unlock(&peer->rtt_input_lock);
+
+	trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial,
+			   peer->srtt_us >> 3, peer->rto_j);
+}
+
+/*
+ * Get the retransmission timeout to set in jiffies, backing it off each time
+ * we retransmit.
+ */
+unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans)
+{
+	u64 timo_j;
+	u8 backoff = READ_ONCE(peer->backoff);
+
+	timo_j = peer->rto_j;
+	timo_j <<= backoff;
+	if (retrans && timo_j * 2 <= RXRPC_RTO_MAX)
+		WRITE_ONCE(peer->backoff, backoff + 1);
+
+	if (timo_j < 1)
+		timo_j = 1;
+
+	return timo_j;
+}
+
+void rxrpc_peer_init_rtt(struct rxrpc_peer *peer)
+{
+	peer->rto_j	= RXRPC_TIMEOUT_INIT;
+	peer->mdev_us	= jiffies_to_usecs(RXRPC_TIMEOUT_INIT);
+	peer->backoff	= 0;
+	//minmax_reset(&peer->rtt_min, rxrpc_jiffies32, ~0U);
+}