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

Pull networking fixes from David Miller:

 1) Fix NAPI poll list corruption in enic driver, from Christian
    Lamparter.

 2) Fix route use after free, from Eric Dumazet.

 3) Fix regression in reuseaddr handling, from Josef Bacik.

 4) Assert the size of control messages in compat handling since we copy
    it in from userspace twice. From Meng Xu.

 5) SMC layer bug fixes (missing RCU locking, bad refcounting, etc.)
    from Ursula Braun.

 6) Fix races in AF_PACKET fanout handling, from Willem de Bruijn.

 7) Don't use ARRAY_SIZE on spinlock array which might have zero
    entries, from Geert Uytterhoeven.

 8) Fix miscomputation of checksum in ipv6 udp code, from Subash Abhinov
    Kasiviswanathan.

 9) Push the ipv6 header properly in ipv6 GRE tunnel driver, from Xin
    Long.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (75 commits)
  inet: fix improper empty comparison
  net: use inet6_rcv_saddr to compare sockets
  net: set tb->fast_sk_family
  net: orphan frags on stand-alone ptype in dev_queue_xmit_nit
  MAINTAINERS: update git tree locations for ieee802154 subsystem
  net: prevent dst uses after free
  net: phy: Fix truncation of large IRQ numbers in phy_attached_print()
  net/smc: no close wait in case of process shut down
  net/smc: introduce a delay
  net/smc: terminate link group if out-of-sync is received
  net/smc: longer delay for client link group removal
  net/smc: adapt send request completion notification
  net/smc: adjust net_device refcount
  net/smc: take RCU read lock for routing cache lookup
  net/smc: add receive timeout check
  net/smc: add missing dev_put
  net: stmmac: Cocci spatch "of_table"
  lan78xx: Use default values loaded from EEPROM/OTP after reset
  lan78xx: Allow EEPROM write for less than MAX_EEPROM_SIZE
  lan78xx: Fix for eeprom read/write when device auto suspend
  ...

1 files changed, 22 insertions, 0 deletions

diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
index bcd4708b3745..0ea3ca09c689 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
@@ -551,6 +551,28 @@ static void emac_mac_start(struct emac_adapter *adpt)
 	mac &= ~(HUGEN | VLAN_STRIP | TPAUSE | SIMR | HUGE | MULTI_ALL |
 		 DEBUG_MODE | SINGLE_PAUSE_MODE);
 
+	/* Enable single-pause-frame mode if requested.
+	 *
+	 * If enabled, the EMAC will send a single pause frame when the RX
+	 * queue is full.  This normally leads to packet loss because
+	 * the pause frame disables the remote MAC only for 33ms (the quanta),
+	 * and then the remote MAC continues sending packets even though
+	 * the RX queue is still full.
+	 *
+	 * If disabled, the EMAC sends a pause frame every 31ms until the RX
+	 * queue is no longer full.  Normally, this is the preferred
+	 * method of operation.  However, when the system is hung (e.g.
+	 * cores are halted), the EMAC interrupt handler is never called
+	 * and so the RX queue fills up quickly and stays full.  The resuling
+	 * non-stop "flood" of pause frames sometimes has the effect of
+	 * disabling nearby switches.  In some cases, other nearby switches
+	 * are also affected, shutting down the entire network.
+	 *
+	 * The user can enable or disable single-pause-frame mode
+	 * via ethtool.
+	 */
+	mac |= adpt->single_pause_mode ? SINGLE_PAUSE_MODE : 0;
+
 	writel_relaxed(csr1, adpt->csr + EMAC_EMAC_WRAPPER_CSR1);
 
 	writel_relaxed(mac, adpt->base + EMAC_MAC_CTRL);