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

Pull networking merge from David Miller:
 "1) Move ixgbe driver over to purely page based buffering on receive.
     From Alexander Duyck.

  2) Add receive packet steering support to e1000e, from Bruce Allan.

  3) Convert TCP MD5 support over to RCU, from Eric Dumazet.

  4) Reduce cpu usage in handling out-of-order TCP packets on modern
     systems, also from Eric Dumazet.

  5) Support the IP{,V6}_UNICAST_IF socket options, making the wine
     folks happy, from Erich Hoover.

  6) Support VLAN trunking from guests in hyperv driver, from Haiyang
     Zhang.

  7) Support byte-queue-limtis in r8169, from Igor Maravic.

  8) Outline code intended for IP_RECVTOS in IP_PKTOPTIONS existed but
     was never properly implemented, Jiri Benc fixed that.

  9) 64-bit statistics support in r8169 and 8139too, from Junchang Wang.

  10) Support kernel side dump filtering by ctmark in netfilter
      ctnetlink, from Pablo Neira Ayuso.

  11) Support byte-queue-limits in gianfar driver, from Paul Gortmaker.

  12) Add new peek socket options to assist with socket migration, from
      Pavel Emelyanov.

  13) Add sch_plug packet scheduler whose queue is controlled by
      userland daemons using explicit freeze and release commands.  From
      Shriram Rajagopalan.

  14) Fix FCOE checksum offload handling on transmit, from Yi Zou."

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1846 commits)
  Fix pppol2tp getsockname()
  Remove printk from rds_sendmsg
  ipv6: fix incorrent ipv6 ipsec packet fragment
  cpsw: Hook up default ndo_change_mtu.
  net: qmi_wwan: fix build error due to cdc-wdm dependecy
  netdev: driver: ethernet: Add TI CPSW driver
  netdev: driver: ethernet: add cpsw address lookup engine support
  phy: add am79c874 PHY support
  mlx4_core: fix race on comm channel
  bonding: send igmp report for its master
  fs_enet: Add MPC5125 FEC support and PHY interface selection
  net: bpf_jit: fix BPF_S_LDX_B_MSH compilation
  net: update the usage of CHECKSUM_UNNECESSARY
  fcoe: use CHECKSUM_UNNECESSARY instead of CHECKSUM_PARTIAL on tx
  net: do not do gso for CHECKSUM_UNNECESSARY in netif_needs_gso
  ixgbe: Fix issues with SR-IOV loopback when flow control is disabled
  net/hyperv: Fix the code handling tx busy
  ixgbe: fix namespace issues when FCoE/DCB is not enabled
  rtlwifi: Remove unused ETH_ADDR_LEN defines
  igbvf: Use ETH_ALEN
  ...

Fix up fairly trivial conflicts in drivers/isdn/gigaset/interface.c and
drivers/net/usb/{Kconfig,qmi_wwan.c} as per David.

1 files changed, 535 insertions, 396 deletions

diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index e43702f33b62..3cbfbffe3f00 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -25,6 +25,7 @@
 #include "net_driver.h"
 #include "efx.h"
 #include "nic.h"
+#include "selftest.h"
 
 #include "mcdi.h"
 #include "workarounds.h"
@@ -38,15 +39,15 @@
 
 /* Loopback mode names (see LOOPBACK_MODE()) */
 const unsigned int efx_loopback_mode_max = LOOPBACK_MAX;
-const char *efx_loopback_mode_names[] = {
+const char *const efx_loopback_mode_names[] = {
 	[LOOPBACK_NONE]		= "NONE",
 	[LOOPBACK_DATA]		= "DATAPATH",
 	[LOOPBACK_GMAC]		= "GMAC",
 	[LOOPBACK_XGMII]	= "XGMII",
 	[LOOPBACK_XGXS]		= "XGXS",
-	[LOOPBACK_XAUI]  	= "XAUI",
-	[LOOPBACK_GMII] 	= "GMII",
-	[LOOPBACK_SGMII] 	= "SGMII",
+	[LOOPBACK_XAUI]		= "XAUI",
+	[LOOPBACK_GMII]		= "GMII",
+	[LOOPBACK_SGMII]	= "SGMII",
 	[LOOPBACK_XGBR]		= "XGBR",
 	[LOOPBACK_XFI]		= "XFI",
 	[LOOPBACK_XAUI_FAR]	= "XAUI_FAR",
@@ -55,21 +56,21 @@ const char *efx_loopback_mode_names[] = {
 	[LOOPBACK_XFI_FAR]	= "XFI_FAR",
 	[LOOPBACK_GPHY]		= "GPHY",
 	[LOOPBACK_PHYXS]	= "PHYXS",
-	[LOOPBACK_PCS]	 	= "PCS",
-	[LOOPBACK_PMAPMD] 	= "PMA/PMD",
+	[LOOPBACK_PCS]		= "PCS",
+	[LOOPBACK_PMAPMD]	= "PMA/PMD",
 	[LOOPBACK_XPORT]	= "XPORT",
 	[LOOPBACK_XGMII_WS]	= "XGMII_WS",
-	[LOOPBACK_XAUI_WS]  	= "XAUI_WS",
+	[LOOPBACK_XAUI_WS]	= "XAUI_WS",
 	[LOOPBACK_XAUI_WS_FAR]  = "XAUI_WS_FAR",
 	[LOOPBACK_XAUI_WS_NEAR] = "XAUI_WS_NEAR",
-	[LOOPBACK_GMII_WS] 	= "GMII_WS",
+	[LOOPBACK_GMII_WS]	= "GMII_WS",
 	[LOOPBACK_XFI_WS]	= "XFI_WS",
 	[LOOPBACK_XFI_WS_FAR]	= "XFI_WS_FAR",
-	[LOOPBACK_PHYXS_WS]  	= "PHYXS_WS",
+	[LOOPBACK_PHYXS_WS]	= "PHYXS_WS",
 };
 
 const unsigned int efx_reset_type_max = RESET_TYPE_MAX;
-const char *efx_reset_type_names[] = {
+const char *const efx_reset_type_names[] = {
 	[RESET_TYPE_INVISIBLE]     = "INVISIBLE",
 	[RESET_TYPE_ALL]           = "ALL",
 	[RESET_TYPE_WORLD]         = "WORLD",
@@ -122,15 +123,6 @@ static int napi_weight = 64;
  */
 static unsigned int efx_monitor_interval = 1 * HZ;
 
-/* This controls whether or not the driver will initialise devices
- * with invalid MAC addresses stored in the EEPROM or flash.  If true,
- * such devices will be initialised with a random locally-generated
- * MAC address.  This allows for loading the sfc_mtd driver to
- * reprogram the flash, even if the flash contents (including the MAC
- * address) have previously been erased.
- */
-static unsigned int allow_bad_hwaddr;
-
 /* Initial interrupt moderation settings.  They can be modified after
  * module load with ethtool.
  *
@@ -162,7 +154,7 @@ static unsigned int interrupt_mode;
  * interrupt handling.
  *
  * Cards without MSI-X will only target one CPU via legacy or MSI interrupt.
- * The default (0) means to assign an interrupt to each package (level II cache)
+ * The default (0) means to assign an interrupt to each core.
  */
 static unsigned int rss_cpus;
 module_param(rss_cpus, uint, 0444);
@@ -172,12 +164,12 @@ static int phy_flash_cfg;
 module_param(phy_flash_cfg, int, 0644);
 MODULE_PARM_DESC(phy_flash_cfg, "Set PHYs into reflash mode initially");
 
-static unsigned irq_adapt_low_thresh = 10000;
+static unsigned irq_adapt_low_thresh = 8000;
 module_param(irq_adapt_low_thresh, uint, 0644);
 MODULE_PARM_DESC(irq_adapt_low_thresh,
 		 "Threshold score for reducing IRQ moderation");
 
-static unsigned irq_adapt_high_thresh = 20000;
+static unsigned irq_adapt_high_thresh = 16000;
 module_param(irq_adapt_high_thresh, uint, 0644);
 MODULE_PARM_DESC(irq_adapt_high_thresh,
 		 "Threshold score for increasing IRQ moderation");
@@ -195,9 +187,13 @@ MODULE_PARM_DESC(debug, "Bitmapped debugging message enable value");
  *
  *************************************************************************/
 
+static void efx_start_interrupts(struct efx_nic *efx, bool may_keep_eventq);
+static void efx_stop_interrupts(struct efx_nic *efx, bool may_keep_eventq);
+static void efx_remove_channel(struct efx_channel *channel);
 static void efx_remove_channels(struct efx_nic *efx);
+static const struct efx_channel_type efx_default_channel_type;
 static void efx_remove_port(struct efx_nic *efx);
-static void efx_init_napi(struct efx_nic *efx);
+static void efx_init_napi_channel(struct efx_channel *channel);
 static void efx_fini_napi(struct efx_nic *efx);
 static void efx_fini_napi_channel(struct efx_channel *channel);
 static void efx_fini_struct(struct efx_nic *efx);
@@ -226,27 +222,27 @@ static void efx_stop_all(struct efx_nic *efx);
  */
 static int efx_process_channel(struct efx_channel *channel, int budget)
 {
-	struct efx_nic *efx = channel->efx;
 	int spent;
 
-	if (unlikely(efx->reset_pending || !channel->enabled))
+	if (unlikely(!channel->enabled))
 		return 0;
 
 	spent = efx_nic_process_eventq(channel, budget);
-	if (spent == 0)
-		return 0;
-
-	/* Deliver last RX packet. */
-	if (channel->rx_pkt) {
-		__efx_rx_packet(channel, channel->rx_pkt,
-				channel->rx_pkt_csummed);
-		channel->rx_pkt = NULL;
+	if (spent && efx_channel_has_rx_queue(channel)) {
+		struct efx_rx_queue *rx_queue =
+			efx_channel_get_rx_queue(channel);
+
+		/* Deliver last RX packet. */
+		if (channel->rx_pkt) {
+			__efx_rx_packet(channel, channel->rx_pkt);
+			channel->rx_pkt = NULL;
+		}
+		if (rx_queue->enabled) {
+			efx_rx_strategy(channel);
+			efx_fast_push_rx_descriptors(rx_queue);
+		}
 	}
 
-	efx_rx_strategy(channel);
-
-	efx_fast_push_rx_descriptors(efx_channel_get_rx_queue(channel));
-
 	return spent;
 }
 
@@ -286,7 +282,7 @@ static int efx_poll(struct napi_struct *napi, int budget)
 	spent = efx_process_channel(channel, budget);
 
 	if (spent < budget) {
-		if (channel->channel < efx->n_rx_channels &&
+		if (efx_channel_has_rx_queue(channel) &&
 		    efx->irq_rx_adaptive &&
 		    unlikely(++channel->irq_count == 1000)) {
 			if (unlikely(channel->irq_mod_score <
@@ -373,7 +369,7 @@ static int efx_probe_eventq(struct efx_channel *channel)
 	struct efx_nic *efx = channel->efx;
 	unsigned long entries;
 
-	netif_dbg(channel->efx, probe, channel->efx->net_dev,
+	netif_dbg(efx, probe, efx->net_dev,
 		  "chan %d create event queue\n", channel->channel);
 
 	/* Build an event queue with room for one event per tx and rx buffer,
@@ -396,6 +392,34 @@ static void efx_init_eventq(struct efx_channel *channel)
 	efx_nic_init_eventq(channel);
 }
 
+/* Enable event queue processing and NAPI */
+static void efx_start_eventq(struct efx_channel *channel)
+{
+	netif_dbg(channel->efx, ifup, channel->efx->net_dev,
+		  "chan %d start event queue\n", channel->channel);
+
+	/* The interrupt handler for this channel may set work_pending
+	 * as soon as we enable it.  Make sure it's cleared before
+	 * then.  Similarly, make sure it sees the enabled flag set.
+	 */
+	channel->work_pending = false;
+	channel->enabled = true;
+	smp_wmb();
+
+	napi_enable(&channel->napi_str);
+	efx_nic_eventq_read_ack(channel);
+}
+
+/* Disable event queue processing and NAPI */
+static void efx_stop_eventq(struct efx_channel *channel)
+{
+	if (!channel->enabled)
+		return;
+
+	napi_disable(&channel->napi_str);
+	channel->enabled = false;
+}
+
 static void efx_fini_eventq(struct efx_channel *channel)
 {
 	netif_dbg(channel->efx, drv, channel->efx->net_dev,
@@ -418,8 +442,7 @@ static void efx_remove_eventq(struct efx_channel *channel)
  *
  *************************************************************************/
 
-/* Allocate and initialise a channel structure, optionally copying
- * parameters (but not resources) from an old channel structure. */
+/* Allocate and initialise a channel structure. */
 static struct efx_channel *
 efx_alloc_channel(struct efx_nic *efx, int i, struct efx_channel *old_channel)
 {
@@ -428,45 +451,60 @@ efx_alloc_channel(struct efx_nic *efx, int i, struct efx_channel *old_channel)
 	struct efx_tx_queue *tx_queue;
 	int j;
 
-	if (old_channel) {
-		channel = kmalloc(sizeof(*channel), GFP_KERNEL);
-		if (!channel)
-			return NULL;
+	channel = kzalloc(sizeof(*channel), GFP_KERNEL);
+	if (!channel)
+		return NULL;
 
-		*channel = *old_channel;
+	channel->efx = efx;
+	channel->channel = i;
+	channel->type = &efx_default_channel_type;
 
-		channel->napi_dev = NULL;
-		memset(&channel->eventq, 0, sizeof(channel->eventq));
+	for (j = 0; j < EFX_TXQ_TYPES; j++) {
+		tx_queue = &channel->tx_queue[j];
+		tx_queue->efx = efx;
+		tx_queue->queue = i * EFX_TXQ_TYPES + j;
+		tx_queue->channel = channel;
+	}
 
-		rx_queue = &channel->rx_queue;
-		rx_queue->buffer = NULL;
-		memset(&rx_queue->rxd, 0, sizeof(rx_queue->rxd));
+	rx_queue = &channel->rx_queue;
+	rx_queue->efx = efx;
+	setup_timer(&rx_queue->slow_fill, efx_rx_slow_fill,
+		    (unsigned long)rx_queue);
 
-		for (j = 0; j < EFX_TXQ_TYPES; j++) {
-			tx_queue = &channel->tx_queue[j];
-			if (tx_queue->channel)
-				tx_queue->channel = channel;
-			tx_queue->buffer = NULL;
-			memset(&tx_queue->txd, 0, sizeof(tx_queue->txd));
-		}
-	} else {
-		channel = kzalloc(sizeof(*channel), GFP_KERNEL);
-		if (!channel)
-			return NULL;
+	return channel;
+}
 
-		channel->efx = efx;
-		channel->channel = i;
+/* Allocate and initialise a channel structure, copying parameters
+ * (but not resources) from an old channel structure.
+ */
+static struct efx_channel *
+efx_copy_channel(const struct efx_channel *old_channel)
+{
+	struct efx_channel *channel;
+	struct efx_rx_queue *rx_queue;
+	struct efx_tx_queue *tx_queue;
+	int j;
+
+	channel = kmalloc(sizeof(*channel), GFP_KERNEL);
+	if (!channel)
+		return NULL;
 
-		for (j = 0; j < EFX_TXQ_TYPES; j++) {
-			tx_queue = &channel->tx_queue[j];
-			tx_queue->efx = efx;
-			tx_queue->queue = i * EFX_TXQ_TYPES + j;
+	*channel = *old_channel;
+
+	channel->napi_dev = NULL;
+	memset(&channel->eventq, 0, sizeof(channel->eventq));
+
+	for (j = 0; j < EFX_TXQ_TYPES; j++) {
+		tx_queue = &channel->tx_queue[j];
+		if (tx_queue->channel)
 			tx_queue->channel = channel;
-		}
+		tx_queue->buffer = NULL;
+		memset(&tx_queue->txd, 0, sizeof(tx_queue->txd));
 	}
 
 	rx_queue = &channel->rx_queue;
-	rx_queue->efx = efx;
+	rx_queue->buffer = NULL;
+	memset(&rx_queue->rxd, 0, sizeof(rx_queue->rxd));
 	setup_timer(&rx_queue->slow_fill, efx_rx_slow_fill,
 		    (unsigned long)rx_queue);
 
@@ -482,57 +520,62 @@ static int efx_probe_channel(struct efx_channel *channel)
 	netif_dbg(channel->efx, probe, channel->efx->net_dev,
 		  "creating channel %d\n", channel->channel);
 
+	rc = channel->type->pre_probe(channel);
+	if (rc)
+		goto fail;
+
 	rc = efx_probe_eventq(channel);
 	if (rc)
-		goto fail1;
+		goto fail;
 
 	efx_for_each_channel_tx_queue(tx_queue, channel) {
 		rc = efx_probe_tx_queue(tx_queue);
 		if (rc)
-			goto fail2;
+			goto fail;
 	}
 
 	efx_for_each_channel_rx_queue(rx_queue, channel) {
 		rc = efx_probe_rx_queue(rx_queue);
 		if (rc)
-			goto fail3;
+			goto fail;
 	}
 
 	channel->n_rx_frm_trunc = 0;
 
 	return 0;
 
- fail3:
-	efx_for_each_channel_rx_queue(rx_queue, channel)
-		efx_remove_rx_queue(rx_queue);
- fail2:
-	efx_for_each_channel_tx_queue(tx_queue, channel)
-		efx_remove_tx_queue(tx_queue);
- fail1:
+fail:
+	efx_remove_channel(channel);
 	return rc;
 }
 
+static void
+efx_get_channel_name(struct efx_channel *channel, char *buf, size_t len)
+{
+	struct efx_nic *efx = channel->efx;
+	const char *type;
+	int number;
+
+	number = channel->channel;
+	if (efx->tx_channel_offset == 0) {
+		type = "";
+	} else if (channel->channel < efx->tx_channel_offset) {
+		type = "-rx";
+	} else {
+		type = "-tx";
+		number -= efx->tx_channel_offset;
+	}
+	snprintf(buf, len, "%s%s-%d", efx->name, type, number);
+}
 
 static void efx_set_channel_names(struct efx_nic *efx)
 {
 	struct efx_channel *channel;
-	const char *type = "";
-	int number;
 
-	efx_for_each_channel(channel, efx) {
-		number = channel->channel;
-		if (efx->n_channels > efx->n_rx_channels) {
-			if (channel->channel < efx->n_rx_channels) {
-				type = "-rx";
-			} else {
-				type = "-tx";
-				number -= efx->n_rx_channels;
-			}
-		}
-		snprintf(efx->channel_name[channel->channel],
-			 sizeof(efx->channel_name[0]),
-			 "%s%s-%d", efx->name, type, number);
-	}
+	efx_for_each_channel(channel, efx)
+		channel->type->get_name(channel,
+					efx->channel_name[channel->channel],
+					sizeof(efx->channel_name[0]));
 }
 
 static int efx_probe_channels(struct efx_nic *efx)
@@ -543,7 +586,12 @@ static int efx_probe_channels(struct efx_nic *efx)
 	/* Restart special buffer allocation */
 	efx->next_buffer_table = 0;
 
-	efx_for_each_channel(channel, efx) {
+	/* Probe channels in reverse, so that any 'extra' channels
+	 * use the start of the buffer table. This allows the traffic
+	 * channels to be resized without moving them or wasting the
+	 * entries before them.
+	 */
+	efx_for_each_channel_rev(channel, efx) {
 		rc = efx_probe_channel(channel);
 		if (rc) {
 			netif_err(efx, probe, efx->net_dev,
@@ -565,7 +613,7 @@ fail:
  * to propagate configuration changes (mtu, checksum offload), or
  * to clear hardware error conditions
  */
-static void efx_init_channels(struct efx_nic *efx)
+static void efx_start_datapath(struct efx_nic *efx)
 {
 	struct efx_tx_queue *tx_queue;
 	struct efx_rx_queue *rx_queue;
@@ -584,68 +632,26 @@ static void efx_init_channels(struct efx_nic *efx)
 
 	/* Initialise the channels */
 	efx_for_each_channel(channel, efx) {
-		netif_dbg(channel->efx, drv, channel->efx->net_dev,
-			  "init chan %d\n", channel->channel);
-
-		efx_init_eventq(channel);
-
 		efx_for_each_channel_tx_queue(tx_queue, channel)
 			efx_init_tx_queue(tx_queue);
 
 		/* The rx buffer allocation strategy is MTU dependent */
 		efx_rx_strategy(channel);
 
-		efx_for_each_channel_rx_queue(rx_queue, channel)
+		efx_for_each_channel_rx_queue(rx_queue, channel) {
 			efx_init_rx_queue(rx_queue);
+			efx_nic_generate_fill_event(rx_queue);
+		}
 
 		WARN_ON(channel->rx_pkt != NULL);
 		efx_rx_strategy(channel);
 	}
-}
-
-/* This enables event queue processing and packet transmission.
- *
- * Note that this function is not allowed to fail, since that would
- * introduce too much complexity into the suspend/resume path.
- */
-static void efx_start_channel(struct efx_channel *channel)
-{
-	struct efx_rx_queue *rx_queue;
-
-	netif_dbg(channel->efx, ifup, channel->efx->net_dev,
-		  "starting chan %d\n", channel->channel);
-
-	/* The interrupt handler for this channel may set work_pending
-	 * as soon as we enable it.  Make sure it's cleared before
-	 * then.  Similarly, make sure it sees the enabled flag set. */
-	channel->work_pending = false;
-	channel->enabled = true;
-	smp_wmb();
 
-	/* Fill the queues before enabling NAPI */
-	efx_for_each_channel_rx_queue(rx_queue, channel)
-		efx_fast_push_rx_descriptors(rx_queue);
-
-	napi_enable(&channel->napi_str);
-}
-
-/* This disables event queue processing and packet transmission.
- * This function does not guarantee that all queue processing
- * (e.g. RX refill) is complete.
- */
-static void efx_stop_channel(struct efx_channel *channel)
-{
-	if (!channel->enabled)
-		return;
-
-	netif_dbg(channel->efx, ifdown, channel->efx->net_dev,
-		  "stop chan %d\n", channel->channel);
-
-	channel->enabled = false;
-	napi_disable(&channel->napi_str);
+	if (netif_device_present(efx->net_dev))
+		netif_tx_wake_all_queues(efx->net_dev);
 }
 
-static void efx_fini_channels(struct efx_nic *efx)
+static void efx_stop_datapath(struct efx_nic *efx)
 {
 	struct efx_channel *channel;
 	struct efx_tx_queue *tx_queue;
@@ -672,14 +678,21 @@ static void efx_fini_channels(struct efx_nic *efx)
 	}
 
 	efx_for_each_channel(channel, efx) {
-		netif_dbg(channel->efx, drv, channel->efx->net_dev,
-			  "shut down chan %d\n", channel->channel);
+		/* RX packet processing is pipelined, so wait for the
+		 * NAPI handler to complete.  At least event queue 0
+		 * might be kept active by non-data events, so don't
+		 * use napi_synchronize() but actually disable NAPI
+		 * temporarily.
+		 */
+		if (efx_channel_has_rx_queue(channel)) {
+			efx_stop_eventq(channel);
+			efx_start_eventq(channel);
+		}
 
 		efx_for_each_channel_rx_queue(rx_queue, channel)
 			efx_fini_rx_queue(rx_queue);
 		efx_for_each_possible_channel_tx_queue(tx_queue, channel)
 			efx_fini_tx_queue(tx_queue);
-		efx_fini_eventq(channel);
 	}
 }
 
@@ -711,16 +724,40 @@ efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
 {
 	struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel;
 	u32 old_rxq_entries, old_txq_entries;
-	unsigned i;
-	int rc;
+	unsigned i, next_buffer_table = 0;
+	int rc = 0;
+
+	/* Not all channels should be reallocated. We must avoid
+	 * reallocating their buffer table entries.
+	 */
+	efx_for_each_channel(channel, efx) {
+		struct efx_rx_queue *rx_queue;
+		struct efx_tx_queue *tx_queue;
+
+		if (channel->type->copy)
+			continue;
+		next_buffer_table = max(next_buffer_table,
+					channel->eventq.index +
+					channel->eventq.entries);
+		efx_for_each_channel_rx_queue(rx_queue, channel)
+			next_buffer_table = max(next_buffer_table,
+						rx_queue->rxd.index +
+						rx_queue->rxd.entries);
+		efx_for_each_channel_tx_queue(tx_queue, channel)
+			next_buffer_table = max(next_buffer_table,
+						tx_queue->txd.index +
+						tx_queue->txd.entries);
+	}
 
 	efx_stop_all(efx);
-	efx_fini_channels(efx);
+	efx_stop_interrupts(efx, true);
 
-	/* Clone channels */
+	/* Clone channels (where possible) */
 	memset(other_channel, 0, sizeof(other_channel));
 	for (i = 0; i < efx->n_channels; i++) {
-		channel = efx_alloc_channel(efx, i, efx->channel[i]);
+		channel = efx->channel[i];
+		if (channel->type->copy)
+			channel = channel->type->copy(channel);
 		if (!channel) {
 			rc = -ENOMEM;
 			goto out;
@@ -739,23 +776,31 @@ efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
 		other_channel[i] = channel;
 	}
 
-	rc = efx_probe_channels(efx);
-	if (rc)
-		goto rollback;
-
-	efx_init_napi(efx);
+	/* Restart buffer table allocation */
+	efx->next_buffer_table = next_buffer_table;
 
-	/* Destroy old channels */
 	for (i = 0; i < efx->n_channels; i++) {
-		efx_fini_napi_channel(other_channel[i]);
-		efx_remove_channel(other_channel[i]);
+		channel = efx->channel[i];
+		if (!channel->type->copy)
+			continue;
+		rc = efx_probe_channel(channel);
+		if (rc)
+			goto rollback;
+		efx_init_napi_channel(efx->channel[i]);
 	}
+
 out:
-	/* Free unused channel structures */
-	for (i = 0; i < efx->n_channels; i++)
-		kfree(other_channel[i]);
+	/* Destroy unused channel structures */
+	for (i = 0; i < efx->n_channels; i++) {
+		channel = other_channel[i];
+		if (channel && channel->type->copy) {
+			efx_fini_napi_channel(channel);
+			efx_remove_channel(channel);
+			kfree(channel);
+		}
+	}
 
-	efx_init_channels(efx);
+	efx_start_interrupts(efx, true);
 	efx_start_all(efx);
 	return rc;
 
@@ -776,6 +821,18 @@ void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue)
 	mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(100));
 }
 
+static const struct efx_channel_type efx_default_channel_type = {
+	.pre_probe		= efx_channel_dummy_op_int,
+	.get_name		= efx_get_channel_name,
+	.copy			= efx_copy_channel,
+	.keep_eventq		= false,
+};
+
+int efx_channel_dummy_op_int(struct efx_channel *channel)
+{
+	return 0;
+}
+
 /**************************************************************************
  *
  * Port handling
@@ -807,16 +864,14 @@ void efx_link_status_changed(struct efx_nic *efx)
 	}
 
 	/* Status message for kernel log */
-	if (link_state->up) {
+	if (link_state->up)
 		netif_info(efx, link, efx->net_dev,
 			   "link up at %uMbps %s-duplex (MTU %d)%s\n",
 			   link_state->speed, link_state->fd ? "full" : "half",
 			   efx->net_dev->mtu,
 			   (efx->promiscuous ? " [PROMISC]" : ""));
-	} else {
+	else
 		netif_info(efx, link, efx->net_dev, "link down\n");
-	}
-
 }
 
 void efx_link_set_advertising(struct efx_nic *efx, u32 advertising)
@@ -863,11 +918,9 @@ int __efx_reconfigure_port(struct efx_nic *efx)
 
 	WARN_ON(!mutex_is_locked(&efx->mac_lock));
 
-	/* Serialise the promiscuous flag with efx_set_multicast_list. */
-	if (efx_dev_registered(efx)) {
-		netif_addr_lock_bh(efx->net_dev);
-		netif_addr_unlock_bh(efx->net_dev);
-	}
+	/* Serialise the promiscuous flag with efx_set_rx_mode. */
+	netif_addr_lock_bh(efx->net_dev);
+	netif_addr_unlock_bh(efx->net_dev);
 
 	/* Disable PHY transmit in mac level loopbacks */
 	phy_mode = efx->phy_mode;
@@ -907,16 +960,13 @@ static void efx_mac_work(struct work_struct *data)
 	struct efx_nic *efx = container_of(data, struct efx_nic, mac_work);
 
 	mutex_lock(&efx->mac_lock);
-	if (efx->port_enabled) {
-		efx->type->push_multicast_hash(efx);
-		efx->mac_op->reconfigure(efx);
-	}
+	if (efx->port_enabled)
+		efx->type->reconfigure_mac(efx);
 	mutex_unlock(&efx->mac_lock);
 }
 
 static int efx_probe_port(struct efx_nic *efx)
 {
-	unsigned char *perm_addr;
 	int rc;
 
 	netif_dbg(efx, probe, efx->net_dev, "create port\n");
@@ -929,28 +979,10 @@ static int efx_probe_port(struct efx_nic *efx)
 	if (rc)
 		return rc;
 
-	/* Sanity check MAC address */
-	perm_addr = efx->net_dev->perm_addr;
-	if (is_valid_ether_addr(perm_addr)) {
-		memcpy(efx->net_dev->dev_addr, perm_addr, ETH_ALEN);
-	} else {
-		netif_err(efx, probe, efx->net_dev, "invalid MAC address %pM\n",
-			  perm_addr);
-		if (!allow_bad_hwaddr) {
-			rc = -EINVAL;
-			goto err;
-		}
-		random_ether_addr(efx->net_dev->dev_addr);
-		netif_info(efx, probe, efx->net_dev,
-			   "using locally-generated MAC %pM\n",
-			   efx->net_dev->dev_addr);
-	}
+	/* Initialise MAC address to permanent address */
+	memcpy(efx->net_dev->dev_addr, efx->net_dev->perm_addr, ETH_ALEN);
 
 	return 0;
-
- err:
-	efx->type->remove_port(efx);
-	return rc;
 }
 
 static int efx_init_port(struct efx_nic *efx)
@@ -969,7 +1001,7 @@ static int efx_init_port(struct efx_nic *efx)
 
 	/* Reconfigure the MAC before creating dma queues (required for
 	 * Falcon/A1 where RX_INGR_EN/TX_DRAIN_EN isn't supported) */
-	efx->mac_op->reconfigure(efx);
+	efx->type->reconfigure_mac(efx);
 
 	/* Ensure the PHY advertises the correct flow control settings */
 	rc = efx->phy_op->reconfigure(efx);
@@ -996,8 +1028,7 @@ static void efx_start_port(struct efx_nic *efx)
 
 	/* efx_mac_work() might have been scheduled after efx_stop_port(),
 	 * and then cancelled by efx_flush_all() */
-	efx->type->push_multicast_hash(efx);
-	efx->mac_op->reconfigure(efx);
+	efx->type->reconfigure_mac(efx);
 
 	mutex_unlock(&efx->mac_lock);
 }
@@ -1012,10 +1043,8 @@ static void efx_stop_port(struct efx_nic *efx)
 	mutex_unlock(&efx->mac_lock);
 
 	/* Serialise against efx_set_multicast_list() */
-	if (efx_dev_registered(efx)) {
-		netif_addr_lock_bh(efx->net_dev);
-		netif_addr_unlock_bh(efx->net_dev);
-	}
+	netif_addr_lock_bh(efx->net_dev);
+	netif_addr_unlock_bh(efx->net_dev);
 }
 
 static void efx_fini_port(struct efx_nic *efx)
@@ -1069,9 +1098,11 @@ static int efx_init_io(struct efx_nic *efx)
 	 * masks event though they reject 46 bit masks.
 	 */
 	while (dma_mask > 0x7fffffffUL) {
-		if (pci_dma_supported(pci_dev, dma_mask) &&
-		    ((rc = pci_set_dma_mask(pci_dev, dma_mask)) == 0))
-			break;
+		if (pci_dma_supported(pci_dev, dma_mask)) {
+			rc = pci_set_dma_mask(pci_dev, dma_mask);
+			if (rc == 0)
+				break;
+		}
 		dma_mask >>= 1;
 	}
 	if (rc) {
@@ -1144,33 +1175,46 @@ static void efx_fini_io(struct efx_nic *efx)
 	pci_disable_device(efx->pci_dev);
 }
 
-/* Get number of channels wanted.  Each channel will have its own IRQ,
- * 1 RX queue and/or 2 TX queues. */
-static int efx_wanted_channels(void)
+static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
 {
-	cpumask_var_t core_mask;
-	int count;
+	cpumask_var_t thread_mask;
+	unsigned int count;
 	int cpu;
 
-	if (rss_cpus)
-		return rss_cpus;
+	if (rss_cpus) {
+		count = rss_cpus;
+	} else {
+		if (unlikely(!zalloc_cpumask_var(&thread_mask, GFP_KERNEL))) {
+			netif_warn(efx, probe, efx->net_dev,
+				   "RSS disabled due to allocation failure\n");
+			return 1;
+		}
+
+		count = 0;
+		for_each_online_cpu(cpu) {
+			if (!cpumask_test_cpu(cpu, thread_mask)) {
+				++count;
+				cpumask_or(thread_mask, thread_mask,
+					   topology_thread_cpumask(cpu));
+			}
+		}
 
-	if (unlikely(!zalloc_cpumask_var(&core_mask, GFP_KERNEL))) {
-		printk(KERN_WARNING
-		       "sfc: RSS disabled due to allocation failure\n");
-		return 1;
+		free_cpumask_var(thread_mask);
 	}
 
-	count = 0;
-	for_each_online_cpu(cpu) {
-		if (!cpumask_test_cpu(cpu, core_mask)) {
-			++count;
-			cpumask_or(core_mask, core_mask,
-				   topology_core_cpumask(cpu));
-		}
+	/* If RSS is requested for the PF *and* VFs then we can't write RSS
+	 * table entries that are inaccessible to VFs
+	 */
+	if (efx_sriov_wanted(efx) && efx_vf_size(efx) > 1 &&
+	    count > efx_vf_size(efx)) {
+		netif_warn(efx, probe, efx->net_dev,
+			   "Reducing number of RSS channels from %u to %u for "
+			   "VF support. Increase vf-msix-limit to use more "
+			   "channels on the PF.\n",
+			   count, efx_vf_size(efx));
+		count = efx_vf_size(efx);
 	}
 
-	free_cpumask_var(core_mask);
 	return count;
 }
 
@@ -1178,7 +1222,8 @@ static int
 efx_init_rx_cpu_rmap(struct efx_nic *efx, struct msix_entry *xentries)
 {
 #ifdef CONFIG_RFS_ACCEL
-	int i, rc;
+	unsigned int i;
+	int rc;
 
 	efx->net_dev->rx_cpu_rmap = alloc_irq_cpu_rmap(efx->n_rx_channels);
 	if (!efx->net_dev->rx_cpu_rmap)
@@ -1201,17 +1246,24 @@ efx_init_rx_cpu_rmap(struct efx_nic *efx, struct msix_entry *xentries)
  */
 static int efx_probe_interrupts(struct efx_nic *efx)
 {
-	int max_channels =
-		min_t(int, efx->type->phys_addr_channels, EFX_MAX_CHANNELS);
-	int rc, i;
+	unsigned int max_channels =
+		min(efx->type->phys_addr_channels, EFX_MAX_CHANNELS);
+	unsigned int extra_channels = 0;
+	unsigned int i, j;
+	int rc;
+
+	for (i = 0; i < EFX_MAX_EXTRA_CHANNELS; i++)
+		if (efx->extra_channel_type[i])
+			++extra_channels;
 
 	if (efx->interrupt_mode == EFX_INT_MODE_MSIX) {
 		struct msix_entry xentries[EFX_MAX_CHANNELS];
-		int n_channels;
+		unsigned int n_channels;
 
-		n_channels = efx_wanted_channels();
+		n_channels = efx_wanted_parallelism(efx);
 		if (separate_tx_channels)
 			n_channels *= 2;
+		n_channels += extra_channels;
 		n_channels = min(n_channels, max_channels);
 
 		for (i = 0; i < n_channels; i++)
@@ -1220,7 +1272,7 @@ static int efx_probe_interrupts(struct efx_nic *efx)
 		if (rc > 0) {
 			netif_err(efx, drv, efx->net_dev,
 				  "WARNING: Insufficient MSI-X vectors"
-				  " available (%d < %d).\n", rc, n_channels);
+				  " available (%d < %u).\n", rc, n_channels);
 			netif_err(efx, drv, efx->net_dev,
 				  "WARNING: Performance may be reduced.\n");
 			EFX_BUG_ON_PARANOID(rc >= n_channels);
@@ -1231,22 +1283,23 @@ static int efx_probe_interrupts(struct efx_nic *efx)
 
 		if (rc == 0) {
 			efx->n_channels = n_channels;
+			if (n_channels > extra_channels)
+				n_channels -= extra_channels;
 			if (separate_tx_channels) {
-				efx->n_tx_channels =
-					max(efx->n_channels / 2, 1U);
-				efx->n_rx_channels =
-					max(efx->n_channels -
-					    efx->n_tx_channels, 1U);
+				efx->n_tx_channels = max(n_channels / 2, 1U);
+				efx->n_rx_channels = max(n_channels -
+							 efx->n_tx_channels,
+							 1U);
 			} else {
-				efx->n_tx_channels = efx->n_channels;
-				efx->n_rx_channels = efx->n_channels;
+				efx->n_tx_channels = n_channels;
+				efx->n_rx_channels = n_channels;
 			}
 			rc = efx_init_rx_cpu_rmap(efx, xentries);
 			if (rc) {
 				pci_disable_msix(efx->pci_dev);
 				return rc;
 			}
-			for (i = 0; i < n_channels; i++)
+			for (i = 0; i < efx->n_channels; i++)
 				efx_get_channel(efx, i)->irq =
 					xentries[i].vector;
 		} else {
@@ -1280,9 +1333,68 @@ static int efx_probe_interrupts(struct efx_nic *efx)
 		efx->legacy_irq = efx->pci_dev->irq;
 	}
 
+	/* Assign extra channels if possible */
+	j = efx->n_channels;
+	for (i = 0; i < EFX_MAX_EXTRA_CHANNELS; i++) {
+		if (!efx->extra_channel_type[i])
+			continue;
+		if (efx->interrupt_mode != EFX_INT_MODE_MSIX ||
+		    efx->n_channels <= extra_channels) {
+			efx->extra_channel_type[i]->handle_no_channel(efx);
+		} else {
+			--j;
+			efx_get_channel(efx, j)->type =
+				efx->extra_channel_type[i];
+		}
+	}
+
+	/* RSS might be usable on VFs even if it is disabled on the PF */
+	efx->rss_spread = (efx->n_rx_channels > 1 ?
+			   efx->n_rx_channels : efx_vf_size(efx));
+
 	return 0;
 }
 
+/* Enable interrupts, then probe and start the event queues */
+static void efx_start_interrupts(struct efx_nic *efx, bool may_keep_eventq)
+{
+	struct efx_channel *channel;
+
+	if (efx->legacy_irq)
+		efx->legacy_irq_enabled = true;
+	efx_nic_enable_interrupts(efx);
+
+	efx_for_each_channel(channel, efx) {
+		if (!channel->type->keep_eventq || !may_keep_eventq)
+			efx_init_eventq(channel);
+		efx_start_eventq(channel);
+	}
+
+	efx_mcdi_mode_event(efx);
+}
+
+static void efx_stop_interrupts(struct efx_nic *efx, bool may_keep_eventq)
+{
+	struct efx_channel *channel;
+
+	efx_mcdi_mode_poll(efx);
+
+	efx_nic_disable_interrupts(efx);
+	if (efx->legacy_irq) {
+		synchronize_irq(efx->legacy_irq);
+		efx->legacy_irq_enabled = false;
+	}
+
+	efx_for_each_channel(channel, efx) {
+		if (channel->irq)
+			synchronize_irq(channel->irq);
+
+		efx_stop_eventq(channel);
+		if (!channel->type->keep_eventq || !may_keep_eventq)
+			efx_fini_eventq(channel);
+	}
+}
+
 static void efx_remove_interrupts(struct efx_nic *efx)
 {
 	struct efx_channel *channel;
@@ -1333,11 +1445,13 @@ static int efx_probe_nic(struct efx_nic *efx)
 	if (rc)
 		goto fail;
 
+	efx->type->dimension_resources(efx);
+
 	if (efx->n_channels > 1)
 		get_random_bytes(&efx->rx_hash_key, sizeof(efx->rx_hash_key));
 	for (i = 0; i < ARRAY_SIZE(efx->rx_indir_table); i++)
 		efx->rx_indir_table[i] =
-			ethtool_rxfh_indir_default(i, efx->n_rx_channels);
+			ethtool_rxfh_indir_default(i, efx->rss_spread);
 
 	efx_set_channels(efx);
 	netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
@@ -1385,21 +1499,22 @@ static int efx_probe_all(struct efx_nic *efx)
 	}
 
 	efx->rxq_entries = efx->txq_entries = EFX_DEFAULT_DMAQ_SIZE;
-	rc = efx_probe_channels(efx);
-	if (rc)
-		goto fail3;
 
 	rc = efx_probe_filters(efx);
 	if (rc) {
 		netif_err(efx, probe, efx->net_dev,
 			  "failed to create filter tables\n");
-		goto fail4;
+		goto fail3;
 	}
 
+	rc = efx_probe_channels(efx);
+	if (rc)
+		goto fail4;
+
 	return 0;
 
  fail4:
-	efx_remove_channels(efx);
+	efx_remove_filters(efx);
  fail3:
 	efx_remove_port(efx);
  fail2:
@@ -1408,15 +1523,13 @@ static int efx_probe_all(struct efx_nic *efx)
 	return rc;
 }
 
-/* Called after previous invocation(s) of efx_stop_all, restarts the
- * port, kernel transmit queue, NAPI processing and hardware interrupts,
- * and ensures that the port is scheduled to be reconfigured.
- * This function is safe to call multiple times when the NIC is in any
- * state. */
+/* Called after previous invocation(s) of efx_stop_all, restarts the port,
+ * kernel transmit queues and NAPI processing, and ensures that the port is
+ * scheduled to be reconfigured. This function is safe to call multiple
+ * times when the NIC is in any state.
+ */
 static void efx_start_all(struct efx_nic *efx)
 {
-	struct efx_channel *channel;
-
 	EFX_ASSERT_RESET_SERIALISED(efx);
 
 	/* Check that it is appropriate to restart the interface. All
@@ -1425,31 +1538,11 @@ static void efx_start_all(struct efx_nic *efx)
 		return;
 	if ((efx->state != STATE_RUNNING) && (efx->state != STATE_INIT))
 		return;
-	if (efx_dev_registered(efx) && !netif_running(efx->net_dev))
+	if (!netif_running(efx->net_dev))
 		return;
 
-	/* Mark the port as enabled so port reconfigurations can start, then
-	 * restart the transmit interface early so the watchdog timer stops */
 	efx_start_port(efx);
-
-	if (efx_dev_registered(efx) && netif_device_present(efx->net_dev))
-		netif_tx_wake_all_queues(efx->net_dev);
-
-	efx_for_each_channel(channel, efx)
-		efx_start_channel(channel);
-
-	if (efx->legacy_irq)
-		efx->legacy_irq_enabled = true;
-	efx_nic_enable_interrupts(efx);
-
-	/* Switch to event based MCDI completions after enabling interrupts.
-	 * If a reset has been scheduled, then we need to stay in polled mode.
-	 * Rather than serialising efx_mcdi_mode_event() [which sleeps] and
-	 * reset_pending [modified from an atomic context], we instead guarantee
-	 * that efx_mcdi_mode_poll() isn't reverted erroneously */
-	efx_mcdi_mode_event(efx);
-	if (efx->reset_pending)
-		efx_mcdi_mode_poll(efx);
+	efx_start_datapath(efx);
 
 	/* Start the hardware monitor if there is one. Otherwise (we're link
 	 * event driven), we have to poll the PHY because after an event queue
@@ -1472,8 +1565,9 @@ static void efx_start_all(struct efx_nic *efx)
  * since we're holding the rtnl_lock at this point. */
 static void efx_flush_all(struct efx_nic *efx)
 {
-	/* Make sure the hardware monitor is stopped */
+	/* Make sure the hardware monitor and event self-test are stopped */
 	cancel_delayed_work_sync(&efx->monitor_work);
+	efx_selftest_async_cancel(efx);
 	/* Stop scheduled port reconfigurations */
 	cancel_work_sync(&efx->mac_work);
 }
@@ -1485,8 +1579,6 @@ static void efx_flush_all(struct efx_nic *efx)
  * taking locks. */
 static void efx_stop_all(struct efx_nic *efx)
 {
-	struct efx_channel *channel;
-
 	EFX_ASSERT_RESET_SERIALISED(efx);
 
 	/* port_enabled can be read safely under the rtnl lock */
@@ -1494,28 +1586,6 @@ static void efx_stop_all(struct efx_nic *efx)
 		return;
 
 	efx->type->stop_stats(efx);
-
-	/* Switch to MCDI polling on Siena before disabling interrupts */
-	efx_mcdi_mode_poll(efx);
-
-	/* Disable interrupts and wait for ISR to complete */
-	efx_nic_disable_interrupts(efx);
-	if (efx->legacy_irq) {
-		synchronize_irq(efx->legacy_irq);
-		efx->legacy_irq_enabled = false;
-	}
-	efx_for_each_channel(channel, efx) {
-		if (channel->irq)
-			synchronize_irq(channel->irq);
-	}
-
-	/* Stop all NAPI processing and synchronous rx refills */
-	efx_for_each_channel(channel, efx)
-		efx_stop_channel(channel);
-
-	/* Stop all asynchronous port reconfigurations. Since all
-	 * event processing has already been stopped, there is no
-	 * window to loose phy events */
 	efx_stop_port(efx);
 
 	/* Flush efx_mac_work(), refill_workqueue, monitor_work */
@@ -1523,17 +1593,15 @@ static void efx_stop_all(struct efx_nic *efx)
 
 	/* Stop the kernel transmit interface late, so the watchdog
 	 * timer isn't ticking over the flush */
-	if (efx_dev_registered(efx)) {
-		netif_tx_stop_all_queues(efx->net_dev);
-		netif_tx_lock_bh(efx->net_dev);
-		netif_tx_unlock_bh(efx->net_dev);
-	}
+	netif_tx_disable(efx->net_dev);
+
+	efx_stop_datapath(efx);
 }
 
 static void efx_remove_all(struct efx_nic *efx)
 {
-	efx_remove_filters(efx);
 	efx_remove_channels(efx);
+	efx_remove_filters(efx);
 	efx_remove_port(efx);
 	efx_remove_nic(efx);
 }
@@ -1544,13 +1612,13 @@ static void efx_remove_all(struct efx_nic *efx)
  *
  **************************************************************************/
 
-static unsigned int irq_mod_ticks(unsigned int usecs, unsigned int resolution)
+static unsigned int irq_mod_ticks(unsigned int usecs, unsigned int quantum_ns)
 {
 	if (usecs == 0)
 		return 0;
-	if (usecs < resolution)
+	if (usecs * 1000 < quantum_ns)
 		return 1; /* never round down to 0 */
-	return usecs / resolution;
+	return usecs * 1000 / quantum_ns;
 }
 
 /* Set interrupt moderation parameters */
@@ -1559,14 +1627,20 @@ int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs,
 			    bool rx_may_override_tx)
 {
 	struct efx_channel *channel;
-	unsigned tx_ticks = irq_mod_ticks(tx_usecs, EFX_IRQ_MOD_RESOLUTION);
-	unsigned rx_ticks = irq_mod_ticks(rx_usecs, EFX_IRQ_MOD_RESOLUTION);
+	unsigned int irq_mod_max = DIV_ROUND_UP(efx->type->timer_period_max *
+						efx->timer_quantum_ns,
+						1000);
+	unsigned int tx_ticks;
+	unsigned int rx_ticks;
 
 	EFX_ASSERT_RESET_SERIALISED(efx);
 
-	if (tx_ticks > EFX_IRQ_MOD_MAX || rx_ticks > EFX_IRQ_MOD_MAX)
+	if (tx_usecs > irq_mod_max || rx_usecs > irq_mod_max)
 		return -EINVAL;
 
+	tx_ticks = irq_mod_ticks(tx_usecs, efx->timer_quantum_ns);
+	rx_ticks = irq_mod_ticks(rx_usecs, efx->timer_quantum_ns);
+
 	if (tx_ticks != rx_ticks && efx->tx_channel_offset == 0 &&
 	    !rx_may_override_tx) {
 		netif_err(efx, drv, efx->net_dev, "Channels are shared. "
@@ -1589,8 +1663,14 @@ int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs,
 void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs,
 			    unsigned int *rx_usecs, bool *rx_adaptive)
 {
+	/* We must round up when converting ticks to microseconds
+	 * because we round down when converting the other way.
+	 */
+
 	*rx_adaptive = efx->irq_rx_adaptive;
-	*rx_usecs = efx->irq_rx_moderation * EFX_IRQ_MOD_RESOLUTION;
+	*rx_usecs = DIV_ROUND_UP(efx->irq_rx_moderation *
+				 efx->timer_quantum_ns,
+				 1000);
 
 	/* If channels are shared between RX and TX, so is IRQ
 	 * moderation.  Otherwise, IRQ moderation is the same for all
@@ -1599,9 +1679,10 @@ void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs,
 	if (efx->tx_channel_offset == 0)
 		*tx_usecs = *rx_usecs;
 	else
-		*tx_usecs =
+		*tx_usecs = DIV_ROUND_UP(
 			efx->channel[efx->tx_channel_offset]->irq_moderation *
-			EFX_IRQ_MOD_RESOLUTION;
+			efx->timer_quantum_ns,
+			1000);
 }
 
 /**************************************************************************
@@ -1664,15 +1745,21 @@ static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
  *
  **************************************************************************/
 
+static void efx_init_napi_channel(struct efx_channel *channel)
+{
+	struct efx_nic *efx = channel->efx;
+
+	channel->napi_dev = efx->net_dev;
+	netif_napi_add(channel->napi_dev, &channel->napi_str,
+		       efx_poll, napi_weight);
+}
+
 static void efx_init_napi(struct efx_nic *efx)
 {
 	struct efx_channel *channel;
 
-	efx_for_each_channel(channel, efx) {
-		channel->napi_dev = efx->net_dev;
-		netif_napi_add(channel->napi_dev, &channel->napi_str,
-			       efx_poll, napi_weight);
-	}
+	efx_for_each_channel(channel, efx)
+		efx_init_napi_channel(channel);
 }
 
 static void efx_fini_napi_channel(struct efx_channel *channel)
@@ -1740,6 +1827,7 @@ static int efx_net_open(struct net_device *net_dev)
 	efx_link_status_changed(efx);
 
 	efx_start_all(efx);
+	efx_selftest_async_start(efx);
 	return 0;
 }
 
@@ -1757,22 +1845,21 @@ static int efx_net_stop(struct net_device *net_dev)
 	if (efx->state != STATE_DISABLED) {
 		/* Stop the device and flush all the channels */
 		efx_stop_all(efx);
-		efx_fini_channels(efx);
-		efx_init_channels(efx);
 	}
 
 	return 0;
 }
 
 /* Context: process, dev_base_lock or RTNL held, non-blocking. */
-static struct rtnl_link_stats64 *efx_net_stats(struct net_device *net_dev, struct rtnl_link_stats64 *stats)
+static struct rtnl_link_stats64 *efx_net_stats(struct net_device *net_dev,
+					       struct rtnl_link_stats64 *stats)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 	struct efx_mac_stats *mac_stats = &efx->mac_stats;
 
 	spin_lock_bh(&efx->stats_lock);
+
 	efx->type->update_stats(efx);
-	spin_unlock_bh(&efx->stats_lock);
 
 	stats->rx_packets = mac_stats->rx_packets;
 	stats->tx_packets = mac_stats->tx_packets;
@@ -1796,6 +1883,8 @@ static struct rtnl_link_stats64 *efx_net_stats(struct net_device *net_dev, struc
 	stats->tx_errors = (stats->tx_window_errors +
 			    mac_stats->tx_bad);
 
+	spin_unlock_bh(&efx->stats_lock);
+
 	return stats;
 }
 
@@ -1816,7 +1905,6 @@ static void efx_watchdog(struct net_device *net_dev)
 static int efx_change_mtu(struct net_device *net_dev, int new_mtu)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
-	int rc = 0;
 
 	EFX_ASSERT_RESET_SERIALISED(efx);
 
@@ -1827,19 +1915,15 @@ static int efx_change_mtu(struct net_device *net_dev, int new_mtu)
 
 	netif_dbg(efx, drv, efx->net_dev, "changing MTU to %d\n", new_mtu);
 
-	efx_fini_channels(efx);
-
 	mutex_lock(&efx->mac_lock);
 	/* Reconfigure the MAC before enabling the dma queues so that
 	 * the RX buffers don't overflow */
 	net_dev->mtu = new_mtu;
-	efx->mac_op->reconfigure(efx);
+	efx->type->reconfigure_mac(efx);
 	mutex_unlock(&efx->mac_lock);
 
-	efx_init_channels(efx);
-
 	efx_start_all(efx);
-	return rc;
+	return 0;
 }
 
 static int efx_set_mac_address(struct net_device *net_dev, void *data)
@@ -1854,21 +1938,22 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data)
 		netif_err(efx, drv, efx->net_dev,
 			  "invalid ethernet MAC address requested: %pM\n",
 			  new_addr);
-		return -EINVAL;
+		return -EADDRNOTAVAIL;
 	}
 
 	memcpy(net_dev->dev_addr, new_addr, net_dev->addr_len);
+	efx_sriov_mac_address_changed(efx);
 
 	/* Reconfigure the MAC */
 	mutex_lock(&efx->mac_lock);
-	efx->mac_op->reconfigure(efx);
+	efx->type->reconfigure_mac(efx);
 	mutex_unlock(&efx->mac_lock);
 
 	return 0;
 }
 
 /* Context: netif_addr_lock held, BHs disabled. */
-static void efx_set_multicast_list(struct net_device *net_dev)
+static void efx_set_rx_mode(struct net_device *net_dev)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 	struct netdev_hw_addr *ha;
@@ -1922,8 +2007,14 @@ static const struct net_device_ops efx_netdev_ops = {
 	.ndo_do_ioctl		= efx_ioctl,
 	.ndo_change_mtu		= efx_change_mtu,
 	.ndo_set_mac_address	= efx_set_mac_address,
-	.ndo_set_rx_mode	= efx_set_multicast_list,
+	.ndo_set_rx_mode	= efx_set_rx_mode,
 	.ndo_set_features	= efx_set_features,
+#ifdef CONFIG_SFC_SRIOV
+	.ndo_set_vf_mac		= efx_sriov_set_vf_mac,
+	.ndo_set_vf_vlan	= efx_sriov_set_vf_vlan,
+	.ndo_set_vf_spoofchk	= efx_sriov_set_vf_spoofchk,
+	.ndo_get_vf_config	= efx_sriov_get_vf_config,
+#endif
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = efx_netpoll,
 #endif
@@ -1975,10 +2066,6 @@ static int efx_register_netdev(struct efx_nic *efx)
 	net_dev->netdev_ops = &efx_netdev_ops;
 	SET_ETHTOOL_OPS(net_dev, &efx_ethtool_ops);
 
-	/* Clear MAC statistics */
-	efx->mac_op->update_stats(efx);
-	memset(&efx->mac_stats, 0, sizeof(efx->mac_stats));
-
 	rtnl_lock();
 
 	rc = dev_alloc_name(net_dev, net_dev->name);
@@ -1997,7 +2084,7 @@ static int efx_register_netdev(struct efx_nic *efx)
 	}
 
 	/* Always start with carrier off; PHY events will detect the link */
-	netif_carrier_off(efx->net_dev);
+	netif_carrier_off(net_dev);
 
 	rtnl_unlock();
 
@@ -2038,11 +2125,9 @@ static void efx_unregister_netdev(struct efx_nic *efx)
 			efx_release_tx_buffers(tx_queue);
 	}
 
-	if (efx_dev_registered(efx)) {
-		strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name));
-		device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
-		unregister_netdev(efx->net_dev);
-	}
+	strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name));
+	device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
+	unregister_netdev(efx->net_dev);
 }
 
 /**************************************************************************
@@ -2060,7 +2145,7 @@ void efx_reset_down(struct efx_nic *efx, enum reset_type method)
 	efx_stop_all(efx);
 	mutex_lock(&efx->mac_lock);
 
-	efx_fini_channels(efx);
+	efx_stop_interrupts(efx, false);
 	if (efx->port_initialized && method != RESET_TYPE_INVISIBLE)
 		efx->phy_op->fini(efx);
 	efx->type->fini(efx);
@@ -2095,10 +2180,11 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
 				  "could not restore PHY settings\n");
 	}
 
-	efx->mac_op->reconfigure(efx);
+	efx->type->reconfigure_mac(efx);
 
-	efx_init_channels(efx);
+	efx_start_interrupts(efx, false);
 	efx_restore_filters(efx);
+	efx_sriov_reset(efx);
 
 	mutex_unlock(&efx->mac_lock);
 
@@ -2292,6 +2378,7 @@ static int efx_init_struct(struct efx_nic *efx, const struct efx_nic_type *type,
 #endif
 	INIT_WORK(&efx->reset_work, efx_reset_work);
 	INIT_DELAYED_WORK(&efx->monitor_work, efx_monitor);
+	INIT_DELAYED_WORK(&efx->selftest_work, efx_selftest_async_work);
 	efx->pci_dev = pci_dev;
 	efx->msg_enable = debug;
 	efx->state = STATE_INIT;
@@ -2300,10 +2387,10 @@ static int efx_init_struct(struct efx_nic *efx, const struct efx_nic_type *type,
 	efx->net_dev = net_dev;
 	spin_lock_init(&efx->stats_lock);
 	mutex_init(&efx->mac_lock);
-	efx->mac_op = type->default_mac_ops;
 	efx->phy_op = &efx_dummy_phy_operations;
 	efx->mdio.dev = net_dev;
 	INIT_WORK(&efx->mac_work, efx_mac_work);
+	init_waitqueue_head(&efx->flush_wq);
 
 	for (i = 0; i < EFX_MAX_CHANNELS; i++) {
 		efx->channel[i] = efx_alloc_channel(efx, i, NULL);
@@ -2361,8 +2448,8 @@ static void efx_pci_remove_main(struct efx_nic *efx)
 	free_irq_cpu_rmap(efx->net_dev->rx_cpu_rmap);
 	efx->net_dev->rx_cpu_rmap = NULL;
 #endif
+	efx_stop_interrupts(efx, false);
 	efx_nic_fini_interrupt(efx);
-	efx_fini_channels(efx);
 	efx_fini_port(efx);
 	efx->type->fini(efx);
 	efx_fini_napi(efx);
@@ -2388,6 +2475,8 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
 	/* Allow any queued efx_resets() to complete */
 	rtnl_unlock();
 
+	efx_stop_interrupts(efx, false);
+	efx_sriov_fini(efx);
 	efx_unregister_netdev(efx);
 
 	efx_mtd_remove(efx);
@@ -2408,6 +2497,57 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
 	free_netdev(efx->net_dev);
 };
 
+/* NIC VPD information
+ * Called during probe to display the part number of the
+ * installed NIC.  VPD is potentially very large but this should
+ * always appear within the first 512 bytes.
+ */
+#define SFC_VPD_LEN 512
+static void efx_print_product_vpd(struct efx_nic *efx)
+{
+	struct pci_dev *dev = efx->pci_dev;
+	char vpd_data[SFC_VPD_LEN];
+	ssize_t vpd_size;
+	int i, j;
+
+	/* Get the vpd data from the device */
+	vpd_size = pci_read_vpd(dev, 0, sizeof(vpd_data), vpd_data);
+	if (vpd_size <= 0) {
+		netif_err(efx, drv, efx->net_dev, "Unable to read VPD\n");
+		return;
+	}
+
+	/* Get the Read only section */
+	i = pci_vpd_find_tag(vpd_data, 0, vpd_size, PCI_VPD_LRDT_RO_DATA);
+	if (i < 0) {
+		netif_err(efx, drv, efx->net_dev, "VPD Read-only not found\n");
+		return;
+	}
+
+	j = pci_vpd_lrdt_size(&vpd_data[i]);
+	i += PCI_VPD_LRDT_TAG_SIZE;
+	if (i + j > vpd_size)
+		j = vpd_size - i;
+
+	/* Get the Part number */
+	i = pci_vpd_find_info_keyword(vpd_data, i, j, "PN");
+	if (i < 0) {
+		netif_err(efx, drv, efx->net_dev, "Part number not found\n");
+		return;
+	}
+
+	j = pci_vpd_info_field_size(&vpd_data[i]);
+	i += PCI_VPD_INFO_FLD_HDR_SIZE;
+	if (i + j > vpd_size) {
+		netif_err(efx, drv, efx->net_dev, "Incomplete part number\n");
+		return;
+	}
+
+	netif_info(efx, drv, efx->net_dev,
+		   "Part Number : %.*s\n", j, &vpd_data[i]);
+}
+
+
 /* Main body of NIC initialisation
  * This is called at module load (or hotplug insertion, theoretically).
  */
@@ -2436,16 +2576,14 @@ static int efx_pci_probe_main(struct efx_nic *efx)
 		goto fail4;
 	}
 
-	efx_init_channels(efx);
-
 	rc = efx_nic_init_interrupt(efx);
 	if (rc)
 		goto fail5;
+	efx_start_interrupts(efx, false);
 
 	return 0;
 
  fail5:
-	efx_fini_channels(efx);
 	efx_fini_port(efx);
  fail4:
 	efx->type->fini(efx);
@@ -2459,7 +2597,7 @@ static int efx_pci_probe_main(struct efx_nic *efx)
 /* NIC initialisation
  *
  * This is called at module load (or hotplug insertion,
- * theoretically).  It sets up PCI mappings, tests and resets the NIC,
+ * theoretically).  It sets up PCI mappings, resets the NIC,
  * sets up and registers the network devices with the kernel and hooks
  * the interrupt service routine.  It does not prepare the device for
  * transmission; this is left to the first time one of the network
@@ -2471,7 +2609,7 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
 	const struct efx_nic_type *type = (const struct efx_nic_type *) entry->driver_data;
 	struct net_device *net_dev;
 	struct efx_nic *efx;
-	int i, rc;
+	int rc;
 
 	/* Allocate and initialise a struct net_device and struct efx_nic */
 	net_dev = alloc_etherdev_mqs(sizeof(*efx), EFX_MAX_CORE_TX_QUEUES,
@@ -2499,44 +2637,29 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
 	netif_info(efx, probe, efx->net_dev,
 		   "Solarflare NIC detected\n");
 
+	efx_print_product_vpd(efx);
+
 	/* Set up basic I/O (BAR mappings etc) */
 	rc = efx_init_io(efx);
 	if (rc)
 		goto fail2;
 
-	/* No serialisation is required with the reset path because
-	 * we're in STATE_INIT. */
-	for (i = 0; i < 5; i++) {
-		rc = efx_pci_probe_main(efx);
-
-		/* Serialise against efx_reset(). No more resets will be
-		 * scheduled since efx_stop_all() has been called, and we
-		 * have not and never have been registered with either
-		 * the rtnetlink or driverlink layers. */
-		cancel_work_sync(&efx->reset_work);
-
-		if (rc == 0) {
-			if (efx->reset_pending) {
-				/* If there was a scheduled reset during
-				 * probe, the NIC is probably hosed anyway */
-				efx_pci_remove_main(efx);
-				rc = -EIO;
-			} else {
-				break;
-			}
-		}
+	rc = efx_pci_probe_main(efx);
 
-		/* Retry if a recoverably reset event has been scheduled */
-		if (efx->reset_pending &
-		    ~(1 << RESET_TYPE_INVISIBLE | 1 << RESET_TYPE_ALL) ||
-		    !efx->reset_pending)
-			goto fail3;
+	/* Serialise against efx_reset(). No more resets will be
+	 * scheduled since efx_stop_all() has been called, and we have
+	 * not and never have been registered.
+	 */
+	cancel_work_sync(&efx->reset_work);
 
-		efx->reset_pending = 0;
-	}
+	if (rc)
+		goto fail3;
 
-	if (rc) {
-		netif_err(efx, probe, efx->net_dev, "Could not reset NIC\n");
+	/* If there was a scheduled reset during probe, the NIC is
+	 * probably hosed anyway.
+	 */
+	if (efx->reset_pending) {
+		rc = -EIO;
 		goto fail4;
 	}
 
@@ -2546,18 +2669,27 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
 
 	rc = efx_register_netdev(efx);
 	if (rc)
-		goto fail5;
+		goto fail4;
+
+	rc = efx_sriov_init(efx);
+	if (rc)
+		netif_err(efx, probe, efx->net_dev,
+			  "SR-IOV can't be enabled rc %d\n", rc);
 
 	netif_dbg(efx, probe, efx->net_dev, "initialisation successful\n");
 
+	/* Try to create MTDs, but allow this to fail */
 	rtnl_lock();
-	efx_mtd_probe(efx); /* allowed to fail */
+	rc = efx_mtd_probe(efx);
 	rtnl_unlock();
+	if (rc)
+		netif_warn(efx, probe, efx->net_dev,
+			   "failed to create MTDs (%d)\n", rc);
+
 	return 0;
 
- fail5:
-	efx_pci_remove_main(efx);
  fail4:
+	efx_pci_remove_main(efx);
  fail3:
 	efx_fini_io(efx);
  fail2:
@@ -2578,7 +2710,7 @@ static int efx_pm_freeze(struct device *dev)
 	netif_device_detach(efx->net_dev);
 
 	efx_stop_all(efx);
-	efx_fini_channels(efx);
+	efx_stop_interrupts(efx, false);
 
 	return 0;
 }
@@ -2589,7 +2721,7 @@ static int efx_pm_thaw(struct device *dev)
 
 	efx->state = STATE_INIT;
 
-	efx_init_channels(efx);
+	efx_start_interrupts(efx, false);
 
 	mutex_lock(&efx->mac_lock);
 	efx->phy_op->reconfigure(efx);
@@ -2658,7 +2790,7 @@ static int efx_pm_suspend(struct device *dev)
 	return rc;
 }
 
-static struct dev_pm_ops efx_pm_ops = {
+static const struct dev_pm_ops efx_pm_ops = {
 	.suspend	= efx_pm_suspend,
 	.resume		= efx_pm_resume,
 	.freeze		= efx_pm_freeze,
@@ -2695,6 +2827,10 @@ static int __init efx_init_module(void)
 	if (rc)
 		goto err_notifier;
 
+	rc = efx_init_sriov();
+	if (rc)
+		goto err_sriov;
+
 	reset_workqueue = create_singlethread_workqueue("sfc_reset");
 	if (!reset_workqueue) {
 		rc = -ENOMEM;
@@ -2710,6 +2846,8 @@ static int __init efx_init_module(void)
  err_pci:
 	destroy_workqueue(reset_workqueue);
  err_reset:
+	efx_fini_sriov();
+ err_sriov:
 	unregister_netdevice_notifier(&efx_netdev_notifier);
  err_notifier:
 	return rc;
@@ -2721,6 +2859,7 @@ static void __exit efx_exit_module(void)
 
 	pci_unregister_driver(&efx_pci_driver);
 	destroy_workqueue(reset_workqueue);
+	efx_fini_sriov();
 	unregister_netdevice_notifier(&efx_netdev_notifier);
 
 }