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

Pull networking changes from David Miller:

1) Allow to dump, monitor, and change the bridge multicast database
   using netlink.  From Cong Wang.

2) RFC 5961 TCP blind data injection attack mitigation, from Eric
   Dumazet.

3) Networking user namespace support from Eric W. Biederman.

4) tuntap/virtio-net multiqueue support by Jason Wang.

5) Support for checksum offload of encapsulated packets (basically,
   tunneled traffic can still be checksummed by HW).  From Joseph
   Gasparakis.

6) Allow BPF filter access to VLAN tags, from Eric Dumazet and
   Daniel Borkmann.

7) Bridge port parameters over netlink and BPDU blocking support
   from Stephen Hemminger.

8) Improve data access patterns during inet socket demux by rearranging
   socket layout, from Eric Dumazet.

9) TIPC protocol updates and cleanups from Ying Xue, Paul Gortmaker, and
   Jon Maloy.

10) Update TCP socket hash sizing to be more in line with current day
    realities.  The existing heurstics were choosen a decade ago.
    From Eric Dumazet.

11) Fix races, queue bloat, and excessive wakeups in ATM and
    associated drivers, from Krzysztof Mazur and David Woodhouse.

12) Support DOVE (Distributed Overlay Virtual Ethernet) extensions
    in VXLAN driver, from David Stevens.

13) Add "oops_only" mode to netconsole, from Amerigo Wang.

14) Support set and query of VEB/VEPA bridge mode via PF_BRIDGE, also
    allow DCB netlink to work on namespaces other than the initial
    namespace.  From John Fastabend.

15) Support PTP in the Tigon3 driver, from Matt Carlson.

16) tun/vhost zero copy fixes and improvements, plus turn it on
    by default, from Michael S. Tsirkin.

17) Support per-association statistics in SCTP, from Michele
    Baldessari.

And many, many, driver updates, cleanups, and improvements.  Too
numerous to mention individually.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
  net/mlx4_en: Add support for destination MAC in steering rules
  net/mlx4_en: Use generic etherdevice.h functions.
  net: ethtool: Add destination MAC address to flow steering API
  bridge: add support of adding and deleting mdb entries
  bridge: notify mdb changes via netlink
  ndisc: Unexport ndisc_{build,send}_skb().
  uapi: add missing netconf.h to export list
  pkt_sched: avoid requeues if possible
  solos-pci: fix double-free of TX skb in DMA mode
  bnx2: Fix accidental reversions.
  bna: Driver Version Updated to 3.1.2.1
  bna: Firmware update
  bna: Add RX State
  bna: Rx Page Based Allocation
  bna: TX Intr Coalescing Fix
  bna: Tx and Rx Optimizations
  bna: Code Cleanup and Enhancements
  ath9k: check pdata variable before dereferencing it
  ath5k: RX timestamp is reported at end of frame
  ath9k_htc: RX timestamp is reported at end of frame
  ...

15 files changed, 161 insertions, 123 deletions

diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
index 25906c1d1b15..435b4f1e3488 100644
--- a/drivers/net/ethernet/sfc/Kconfig
+++ b/drivers/net/ethernet/sfc/Kconfig
@@ -1,10 +1,11 @@
 config SFC
 	tristate "Solarflare SFC4000/SFC9000-family support"
-	depends on PCI && INET
+	depends on PCI
 	select MDIO
 	select CRC32
 	select I2C
 	select I2C_ALGOBIT
+	select PTP_1588_CLOCK
 	---help---
 	  This driver supports 10-gigabit Ethernet cards based on
 	  the Solarflare SFC4000 and SFC9000-family controllers.
@@ -34,10 +35,3 @@ config SFC_SRIOV
 	  This enables support for the SFC9000 I/O Virtualization
 	  features, allowing accelerated network performance in
 	  virtualized environments.
-config SFC_PTP
-	bool "Solarflare SFC9000-family PTP support"
-	depends on SFC && PTP_1588_CLOCK && !(SFC=y && PTP_1588_CLOCK=m)
-	default y
-	---help---
-	  This enables support for the Precision Time Protocol (PTP)
-	  on SFC9000-family NICs
diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index e11f2ecf69d9..945bf06e69ef 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -2,9 +2,8 @@ sfc-y			+= efx.o nic.o falcon.o siena.o tx.o rx.o filter.o \
 			   falcon_xmac.o mcdi_mac.o \
 			   selftest.o ethtool.o qt202x_phy.o mdio_10g.o \
 			   tenxpress.o txc43128_phy.o falcon_boards.o \
-			   mcdi.o mcdi_phy.o mcdi_mon.o
+			   mcdi.o mcdi_phy.o mcdi_mon.o ptp.o
 sfc-$(CONFIG_SFC_MTD)	+= mtd.o
 sfc-$(CONFIG_SFC_SRIOV)	+= siena_sriov.o
-sfc-$(CONFIG_SFC_PTP)	+= ptp.o
 
 obj-$(CONFIG_SFC)	+= sfc.o
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 4f86d0cd516a..bf57b3cb16ab 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -106,8 +106,8 @@ static struct workqueue_struct *reset_workqueue;
  *
  * This is only used in MSI-X interrupt mode
  */
-static unsigned int separate_tx_channels;
-module_param(separate_tx_channels, uint, 0444);
+static bool separate_tx_channels;
+module_param(separate_tx_channels, bool, 0444);
 MODULE_PARM_DESC(separate_tx_channels,
 		 "Use separate channels for TX and RX");
 
@@ -160,8 +160,8 @@ static unsigned int rss_cpus;
 module_param(rss_cpus, uint, 0444);
 MODULE_PARM_DESC(rss_cpus, "Number of CPUs to use for Receive-Side Scaling");
 
-static int phy_flash_cfg;
-module_param(phy_flash_cfg, int, 0644);
+static bool phy_flash_cfg;
+module_param(phy_flash_cfg, bool, 0644);
 MODULE_PARM_DESC(phy_flash_cfg, "Set PHYs into reflash mode initially");
 
 static unsigned irq_adapt_low_thresh = 8000;
@@ -2279,7 +2279,7 @@ int efx_reset(struct efx_nic *efx, enum reset_type method)
 	netif_info(efx, drv, efx->net_dev, "resetting (%s)\n",
 		   RESET_TYPE(method));
 
-	netif_device_detach(efx->net_dev);
+	efx_device_detach_sync(efx);
 	efx_reset_down(efx, method);
 
 	rc = efx->type->reset(efx, method);
@@ -2669,8 +2669,8 @@ static int efx_pci_probe_main(struct efx_nic *efx)
  * transmission; this is left to the first time one of the network
  * interfaces is brought up (i.e. efx_net_open).
  */
-static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
-				   const struct pci_device_id *entry)
+static int efx_pci_probe(struct pci_dev *pci_dev,
+			 const struct pci_device_id *entry)
 {
 	struct net_device *net_dev;
 	struct efx_nic *efx;
@@ -2758,7 +2758,7 @@ static int efx_pm_freeze(struct device *dev)
 	if (efx->state != STATE_DISABLED) {
 		efx->state = STATE_UNINIT;
 
-		netif_device_detach(efx->net_dev);
+		efx_device_detach_sync(efx);
 
 		efx_stop_all(efx);
 		efx_stop_interrupts(efx, false);
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index f11170bc48bf..50247dfe8f57 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -163,4 +163,17 @@ extern void efx_link_status_changed(struct efx_nic *efx);
 extern void efx_link_set_advertising(struct efx_nic *efx, u32);
 extern void efx_link_set_wanted_fc(struct efx_nic *efx, u8);
 
+static inline void efx_device_detach_sync(struct efx_nic *efx)
+{
+	struct net_device *dev = efx->net_dev;
+
+	/* Lock/freeze all TX queues so that we can be sure the
+	 * TX scheduler is stopped when we're done and before
+	 * netif_device_present() becomes false.
+	 */
+	netif_tx_lock(dev);
+	netif_device_detach(dev);
+	netif_tx_unlock(dev);
+}
+
 #endif /* EFX_EFX_H */
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 90f078eff8e6..8e61cd06f66a 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -816,6 +816,9 @@ static int efx_ethtool_reset(struct net_device *net_dev, u32 *flags)
 /* MAC address mask including only MC flag */
 static const u8 mac_addr_mc_mask[ETH_ALEN] = { 0x01, 0, 0, 0, 0, 0 };
 
+#define IP4_ADDR_FULL_MASK	((__force __be32)~0)
+#define PORT_FULL_MASK		((__force __be16)~0)
+
 static int efx_ethtool_get_class_rule(struct efx_nic *efx,
 				      struct ethtool_rx_flow_spec *rule)
 {
@@ -865,12 +868,12 @@ static int efx_ethtool_get_class_rule(struct efx_nic *efx,
 			&spec, &proto, &ip_entry->ip4dst, &ip_entry->pdst,
 			&ip_entry->ip4src, &ip_entry->psrc);
 		EFX_WARN_ON_PARANOID(rc);
-		ip_mask->ip4src = ~0;
-		ip_mask->psrc = ~0;
+		ip_mask->ip4src = IP4_ADDR_FULL_MASK;
+		ip_mask->psrc = PORT_FULL_MASK;
 	}
 	rule->flow_type = (proto == IPPROTO_TCP) ? TCP_V4_FLOW : UDP_V4_FLOW;
-	ip_mask->ip4dst = ~0;
-	ip_mask->pdst = ~0;
+	ip_mask->ip4dst = IP4_ADDR_FULL_MASK;
+	ip_mask->pdst = PORT_FULL_MASK;
 	return rc;
 }
 
@@ -971,7 +974,7 @@ static int efx_ethtool_set_class_rule(struct efx_nic *efx,
 
 	/* Check for unsupported extensions */
 	if ((rule->flow_type & FLOW_EXT) &&
-	    (rule->m_ext.vlan_etype | rule->m_ext.data[0] |
+	    (rule->m_ext.vlan_etype || rule->m_ext.data[0] ||
 	     rule->m_ext.data[1]))
 		return -EINVAL;
 
@@ -986,16 +989,16 @@ static int efx_ethtool_set_class_rule(struct efx_nic *efx,
 			    IPPROTO_TCP : IPPROTO_UDP);
 
 		/* Must match all of destination, */
-		if ((__force u32)~ip_mask->ip4dst |
-		    (__force u16)~ip_mask->pdst)
+		if (!(ip_mask->ip4dst == IP4_ADDR_FULL_MASK &&
+		      ip_mask->pdst == PORT_FULL_MASK))
 			return -EINVAL;
 		/* all or none of source, */
-		if ((ip_mask->ip4src | ip_mask->psrc) &&
-		    ((__force u32)~ip_mask->ip4src |
-		     (__force u16)~ip_mask->psrc))
+		if ((ip_mask->ip4src || ip_mask->psrc) &&
+		    !(ip_mask->ip4src == IP4_ADDR_FULL_MASK &&
+		      ip_mask->psrc == PORT_FULL_MASK))
 			return -EINVAL;
 		/* and nothing else */
-		if (ip_mask->tos | rule->m_ext.vlan_tci)
+		if (ip_mask->tos || rule->m_ext.vlan_tci)
 			return -EINVAL;
 
 		if (ip_mask->ip4src)
diff --git a/drivers/net/ethernet/sfc/falcon.c b/drivers/net/ethernet/sfc/falcon.c
index 12b573a8e82b..49bcd196e10d 100644
--- a/drivers/net/ethernet/sfc/falcon.c
+++ b/drivers/net/ethernet/sfc/falcon.c
@@ -1792,6 +1792,7 @@ const struct efx_nic_type falcon_a1_nic_type = {
 	.remove_port = falcon_remove_port,
 	.handle_global_event = falcon_handle_global_event,
 	.prepare_flush = falcon_prepare_flush,
+	.finish_flush = efx_port_dummy_op_void,
 	.update_stats = falcon_update_nic_stats,
 	.start_stats = falcon_start_nic_stats,
 	.stop_stats = falcon_stop_nic_stats,
@@ -1834,6 +1835,7 @@ const struct efx_nic_type falcon_b0_nic_type = {
 	.remove_port = falcon_remove_port,
 	.handle_global_event = falcon_handle_global_event,
 	.prepare_flush = falcon_prepare_flush,
+	.finish_flush = efx_port_dummy_op_void,
 	.update_stats = falcon_update_nic_stats,
 	.start_stats = falcon_start_nic_stats,
 	.stop_stats = falcon_stop_nic_stats,
diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h
index 751d1ec112cc..96759aee1c6c 100644
--- a/drivers/net/ethernet/sfc/io.h
+++ b/drivers/net/ethernet/sfc/io.h
@@ -22,22 +22,21 @@
  *
  * Notes on locking strategy:
  *
- * Most CSRs are 128-bit (oword) and therefore cannot be read or
- * written atomically.  Access from the host is buffered by the Bus
- * Interface Unit (BIU).  Whenever the host reads from the lowest
- * address of such a register, or from the address of a different such
- * register, the BIU latches the register's value.  Subsequent reads
- * from higher addresses of the same register will read the latched
- * value.  Whenever the host writes part of such a register, the BIU
- * collects the written value and does not write to the underlying
- * register until all 4 dwords have been written.  A similar buffering
- * scheme applies to host access to the NIC's 64-bit SRAM.
+ * Many CSRs are very wide and cannot be read or written atomically.
+ * Writes from the host are buffered by the Bus Interface Unit (BIU)
+ * up to 128 bits.  Whenever the host writes part of such a register,
+ * the BIU collects the written value and does not write to the
+ * underlying register until all 4 dwords have been written.  A
+ * similar buffering scheme applies to host access to the NIC's 64-bit
+ * SRAM.
  *
- * Access to different CSRs and 64-bit SRAM words must be serialised,
- * since interleaved access can result in lost writes or lost
- * information from read-to-clear fields.  We use efx_nic::biu_lock
- * for this.  (We could use separate locks for read and write, but
- * this is not normally a performance bottleneck.)
+ * Writes to different CSRs and 64-bit SRAM words must be serialised,
+ * since interleaved access can result in lost writes.  We use
+ * efx_nic::biu_lock for this.
+ *
+ * We also serialise reads from 128-bit CSRs and SRAM with the same
+ * spinlock.  This may not be necessary, but it doesn't really matter
+ * as there are no such reads on the fast path.
  *
  * The DMA descriptor pointers (RX_DESC_UPD and TX_DESC_UPD) are
  * 128-bit but are special-cased in the BIU to avoid the need for
@@ -204,20 +203,6 @@ static inline void efx_reado_table(struct efx_nic *efx, efx_oword_t *value,
 	efx_reado(efx, value, reg + index * sizeof(efx_oword_t));
 }
 
-/* Write a 32-bit CSR forming part of a table, or 32-bit SRAM */
-static inline void efx_writed_table(struct efx_nic *efx, efx_dword_t *value,
-				       unsigned int reg, unsigned int index)
-{
-	efx_writed(efx, value, reg + index * sizeof(efx_oword_t));
-}
-
-/* Read a 32-bit CSR forming part of a table, or 32-bit SRAM */
-static inline void efx_readd_table(struct efx_nic *efx, efx_dword_t *value,
-				   unsigned int reg, unsigned int index)
-{
-	efx_readd(efx, value, reg + index * sizeof(efx_dword_t));
-}
-
 /* Page-mapped register block size */
 #define EFX_PAGE_BLOCK_SIZE 0x2000
 
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index aea43cbd0520..0095ce95150b 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -22,7 +22,7 @@
  **************************************************************************
  */
 
-#define MCDI_RPC_TIMEOUT       10 /*seconds */
+#define MCDI_RPC_TIMEOUT       (10 * HZ)
 
 #define MCDI_PDU(efx)							\
 	(efx_port_num(efx) ? MC_SMEM_P1_PDU_OFST : MC_SMEM_P0_PDU_OFST)
@@ -120,7 +120,7 @@ static void efx_mcdi_copyout(struct efx_nic *efx, u8 *outbuf, size_t outlen)
 static int efx_mcdi_poll(struct efx_nic *efx)
 {
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
-	unsigned int time, finish;
+	unsigned long time, finish;
 	unsigned int respseq, respcmd, error;
 	unsigned int pdu = FR_CZ_MC_TREG_SMEM + MCDI_PDU(efx);
 	unsigned int rc, spins;
@@ -136,7 +136,7 @@ static int efx_mcdi_poll(struct efx_nic *efx)
 	 * and poll once a jiffy (approximately)
 	 */
 	spins = TICK_USEC;
-	finish = get_seconds() + MCDI_RPC_TIMEOUT;
+	finish = jiffies + MCDI_RPC_TIMEOUT;
 
 	while (1) {
 		if (spins != 0) {
@@ -146,7 +146,7 @@ static int efx_mcdi_poll(struct efx_nic *efx)
 			schedule_timeout_uninterruptible(1);
 		}
 
-		time = get_seconds();
+		time = jiffies;
 
 		rmb();
 		efx_readd(efx, &reg, pdu);
@@ -158,7 +158,7 @@ static int efx_mcdi_poll(struct efx_nic *efx)
 		    EFX_DWORD_FIELD(reg, MCDI_HEADER_RESPONSE))
 			break;
 
-		if (time >= finish)
+		if (time_after(time, finish))
 			return -ETIMEDOUT;
 	}
 
@@ -207,7 +207,9 @@ out:
 	return 0;
 }
 
-/* Test and clear MC-rebooted flag for this port/function */
+/* Test and clear MC-rebooted flag for this port/function; reset
+ * software state as necessary.
+ */
 int efx_mcdi_poll_reboot(struct efx_nic *efx)
 {
 	unsigned int addr = FR_CZ_MC_TREG_SMEM + MCDI_STATUS(efx);
@@ -223,6 +225,11 @@ int efx_mcdi_poll_reboot(struct efx_nic *efx)
 	if (value == 0)
 		return 0;
 
+	/* MAC statistics have been cleared on the NIC; clear our copy
+	 * so that efx_update_diff_stat() can continue to work.
+	 */
+	memset(&efx->mac_stats, 0, sizeof(efx->mac_stats));
+
 	EFX_ZERO_DWORD(reg);
 	efx_writed(efx, &reg, addr);
 
@@ -250,7 +257,7 @@ static int efx_mcdi_await_completion(struct efx_nic *efx)
 	if (wait_event_timeout(
 		    mcdi->wq,
 		    atomic_read(&mcdi->state) == MCDI_STATE_COMPLETED,
-		    msecs_to_jiffies(MCDI_RPC_TIMEOUT * 1000)) == 0)
+		    MCDI_RPC_TIMEOUT) == 0)
 		return -ETIMEDOUT;
 
 	/* Check if efx_mcdi_set_mode() switched us back to polled completions.
@@ -1216,7 +1223,7 @@ int efx_mcdi_flush_rxqs(struct efx_nic *efx)
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_FLUSH_RX_QUEUES, (u8 *)qid,
 			  count * sizeof(*qid), NULL, 0, NULL);
-	WARN_ON(rc > 0);
+	WARN_ON(rc < 0);
 
 	kfree(qid);
 
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 576a31091165..2d756c1d7142 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -200,6 +200,7 @@ struct efx_tx_queue {
 	/* Members shared between paths and sometimes updated */
 	unsigned int empty_read_count ____cacheline_aligned_in_smp;
 #define EFX_EMPTY_COUNT_VALID 0x80000000
+	atomic_t flush_outstanding;
 };
 
 /**
@@ -868,9 +869,7 @@ struct efx_nic {
 	struct work_struct peer_work;
 #endif
 
-#ifdef CONFIG_SFC_PTP
 	struct efx_ptp_data *ptp_data;
-#endif
 
 	/* The following fields may be written more often */
 
@@ -909,6 +908,7 @@ static inline unsigned int efx_port_num(struct efx_nic *efx)
  * @remove_port: Free resources allocated by probe_port()
  * @handle_global_event: Handle a "global" event (may be %NULL)
  * @prepare_flush: Prepare the hardware for flushing the DMA queues
+ * @finish_flush: Clean up after flushing the DMA queues
  * @update_stats: Update statistics not provided by event handling
  * @start_stats: Start the regular fetching of statistics
  * @stop_stats: Stop the regular fetching of statistics
@@ -956,6 +956,7 @@ struct efx_nic_type {
 	void (*remove_port)(struct efx_nic *efx);
 	bool (*handle_global_event)(struct efx_channel *channel, efx_qword_t *);
 	void (*prepare_flush)(struct efx_nic *efx);
+	void (*finish_flush)(struct efx_nic *efx);
 	void (*update_stats)(struct efx_nic *efx);
 	void (*start_stats)(struct efx_nic *efx);
 	void (*stop_stats)(struct efx_nic *efx);
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index aab7cacb2e34..0ad790cc473c 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -73,6 +73,8 @@
 	_EFX_CHANNEL_MAGIC(_EFX_CHANNEL_MAGIC_TX_DRAIN,			\
 			   (_tx_queue)->queue)
 
+static void efx_magic_event(struct efx_channel *channel, u32 magic);
+
 /**************************************************************************
  *
  * Solarstorm hardware access
@@ -255,9 +257,6 @@ static int efx_alloc_special_buffer(struct efx_nic *efx,
 	buffer->entries = len / EFX_BUF_SIZE;
 	BUG_ON(buffer->dma_addr & (EFX_BUF_SIZE - 1));
 
-	/* All zeros is a potentially valid event so memset to 0xff */
-	memset(buffer->addr, 0xff, len);
-
 	/* Select new buffer ID */
 	buffer->index = efx->next_buffer_table;
 	efx->next_buffer_table += buffer->entries;
@@ -494,6 +493,9 @@ static void efx_flush_tx_queue(struct efx_tx_queue *tx_queue)
 	struct efx_nic *efx = tx_queue->efx;
 	efx_oword_t tx_flush_descq;
 
+	WARN_ON(atomic_read(&tx_queue->flush_outstanding));
+	atomic_set(&tx_queue->flush_outstanding, 1);
+
 	EFX_POPULATE_OWORD_2(tx_flush_descq,
 			     FRF_AZ_TX_FLUSH_DESCQ_CMD, 1,
 			     FRF_AZ_TX_FLUSH_DESCQ, tx_queue->queue);
@@ -669,6 +671,47 @@ static bool efx_flush_wake(struct efx_nic *efx)
 		 && atomic_read(&efx->rxq_flush_pending) > 0));
 }
 
+static bool efx_check_tx_flush_complete(struct efx_nic *efx)
+{
+	bool i = true;
+	efx_oword_t txd_ptr_tbl;
+	struct efx_channel *channel;
+	struct efx_tx_queue *tx_queue;
+
+	efx_for_each_channel(channel, efx) {
+		efx_for_each_channel_tx_queue(tx_queue, channel) {
+			efx_reado_table(efx, &txd_ptr_tbl,
+					FR_BZ_TX_DESC_PTR_TBL, tx_queue->queue);
+			if (EFX_OWORD_FIELD(txd_ptr_tbl,
+					    FRF_AZ_TX_DESCQ_FLUSH) ||
+			    EFX_OWORD_FIELD(txd_ptr_tbl,
+					    FRF_AZ_TX_DESCQ_EN)) {
+				netif_dbg(efx, hw, efx->net_dev,
+					  "flush did not complete on TXQ %d\n",
+					  tx_queue->queue);
+				i = false;
+			} else if (atomic_cmpxchg(&tx_queue->flush_outstanding,
+						  1, 0)) {
+				/* The flush is complete, but we didn't
+				 * receive a flush completion event
+				 */
+				netif_dbg(efx, hw, efx->net_dev,
+					  "flush complete on TXQ %d, so drain "
+					  "the queue\n", tx_queue->queue);
+				/* Don't need to increment drain_pending as it
+				 * has already been incremented for the queues
+				 * which did not drain
+				 */
+				efx_magic_event(channel,
+						EFX_CHANNEL_MAGIC_TX_DRAIN(
+							tx_queue));
+			}
+		}
+	}
+
+	return i;
+}
+
 /* Flush all the transmit queues, and continue flushing receive queues until
  * they're all flushed. Wait for the DRAIN events to be recieved so that there
  * are no more RX and TX events left on any channel. */
@@ -680,7 +723,6 @@ int efx_nic_flush_queues(struct efx_nic *efx)
 	struct efx_tx_queue *tx_queue;
 	int rc = 0;
 
-	efx->fc_disable++;
 	efx->type->prepare_flush(efx);
 
 	efx_for_each_channel(channel, efx) {
@@ -730,7 +772,8 @@ int efx_nic_flush_queues(struct efx_nic *efx)
 					     timeout);
 	}
 
-	if (atomic_read(&efx->drain_pending)) {
+	if (atomic_read(&efx->drain_pending) &&
+	    !efx_check_tx_flush_complete(efx)) {
 		netif_err(efx, hw, efx->net_dev, "failed to flush %d queues "
 			  "(rx %d+%d)\n", atomic_read(&efx->drain_pending),
 			  atomic_read(&efx->rxq_flush_outstanding),
@@ -742,7 +785,7 @@ int efx_nic_flush_queues(struct efx_nic *efx)
 		atomic_set(&efx->rxq_flush_outstanding, 0);
 	}
 
-	efx->fc_disable--;
+	efx->type->finish_flush(efx);
 
 	return rc;
 }
@@ -766,8 +809,13 @@ void efx_nic_eventq_read_ack(struct efx_channel *channel)
 
 	EFX_POPULATE_DWORD_1(reg, FRF_AZ_EVQ_RPTR,
 			     channel->eventq_read_ptr & channel->eventq_mask);
-	efx_writed_table(efx, &reg, efx->type->evq_rptr_tbl_base,
-			 channel->channel);
+
+	/* For Falcon A1, EVQ_RPTR_KER is documented as having a step size
+	 * of 4 bytes, but it is really 16 bytes just like later revisions.
+	 */
+	efx_writed(efx, &reg,
+		   efx->type->evq_rptr_tbl_base +
+		   FR_BZ_EVQ_RPTR_STEP * channel->channel);
 }
 
 /* Use HW to insert a SW defined event */
@@ -1017,9 +1065,10 @@ efx_handle_tx_flush_done(struct efx_nic *efx, efx_qword_t *event)
 	if (qid < EFX_TXQ_TYPES * efx->n_tx_channels) {
 		tx_queue = efx_get_tx_queue(efx, qid / EFX_TXQ_TYPES,
 					    qid % EFX_TXQ_TYPES);
-
-		efx_magic_event(tx_queue->channel,
-				EFX_CHANNEL_MAGIC_TX_DRAIN(tx_queue));
+		if (atomic_cmpxchg(&tx_queue->flush_outstanding, 1, 0)) {
+			efx_magic_event(tx_queue->channel,
+					EFX_CHANNEL_MAGIC_TX_DRAIN(tx_queue));
+		}
 	}
 }
 
@@ -1565,7 +1614,9 @@ void efx_nic_push_rx_indir_table(struct efx_nic *efx)
 	for (i = 0; i < FR_BZ_RX_INDIRECTION_TBL_ROWS; i++) {
 		EFX_POPULATE_DWORD_1(dword, FRF_BZ_IT_QUEUE,
 				     efx->rx_indir_table[i]);
-		efx_writed_table(efx, &dword, FR_BZ_RX_INDIRECTION_TBL, i);
+		efx_writed(efx, &dword,
+			   FR_BZ_RX_INDIRECTION_TBL +
+			   FR_BZ_RX_INDIRECTION_TBL_STEP * i);
 	}
 }
 
@@ -2029,15 +2080,15 @@ void efx_nic_get_regs(struct efx_nic *efx, void *buf)
 
 		for (i = 0; i < table->rows; i++) {
 			switch (table->step) {
-			case 4: /* 32-bit register or SRAM */
-				efx_readd_table(efx, buf, table->offset, i);
+			case 4: /* 32-bit SRAM */
+				efx_readd(efx, buf, table->offset + 4 * i);
 				break;
 			case 8: /* 64-bit SRAM */
 				efx_sram_readq(efx,
 					       efx->membase + table->offset,
 					       buf, i);
 				break;
-			case 16: /* 128-bit register */
+			case 16: /* 128-bit-readable register */
 				efx_reado_table(efx, buf, table->offset, i);
 				break;
 			case 32: /* 128-bit register, interleaved */
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 438cef11f727..1b0003323498 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -252,7 +252,6 @@ extern int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf,
 				     bool spoofchk);
 
 struct ethtool_ts_info;
-#ifdef CONFIG_SFC_PTP
 extern void efx_ptp_probe(struct efx_nic *efx);
 extern int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd);
 extern int efx_ptp_get_ts_info(struct net_device *net_dev,
@@ -260,31 +259,6 @@ extern int efx_ptp_get_ts_info(struct net_device *net_dev,
 extern bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
 extern int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
 extern void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev);
-#else
-static inline void efx_ptp_probe(struct efx_nic *efx) {}
-static inline int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd)
-{
-	return -EOPNOTSUPP;
-}
-static inline int efx_ptp_get_ts_info(struct net_device *net_dev,
-				      struct ethtool_ts_info *ts_info)
-{
-	ts_info->so_timestamping = (SOF_TIMESTAMPING_SOFTWARE |
-				    SOF_TIMESTAMPING_RX_SOFTWARE);
-	ts_info->phc_index = -1;
-
-	return 0;
-}
-static inline bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
-{
-	return false;
-}
-static inline int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
-{
-	return NETDEV_TX_OK;
-}
-static inline void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev) {}
-#endif
 
 extern const struct efx_nic_type falcon_a1_nic_type;
 extern const struct efx_nic_type falcon_b0_nic_type;
@@ -370,6 +344,8 @@ static inline int efx_nic_irq_test_irq_cpu(struct efx_nic *efx)
 
 /* Global Resources */
 extern int efx_nic_flush_queues(struct efx_nic *efx);
+extern void siena_prepare_flush(struct efx_nic *efx);
+extern void siena_finish_flush(struct efx_nic *efx);
 extern void falcon_start_nic_stats(struct efx_nic *efx);
 extern void falcon_stop_nic_stats(struct efx_nic *efx);
 extern void falcon_setup_xaui(struct efx_nic *efx);
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 9e0ad1b75c33..d780a0d096b4 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -187,7 +187,6 @@ static int efx_init_rx_buffers_page(struct efx_rx_queue *rx_queue)
 	struct efx_nic *efx = rx_queue->efx;
 	struct efx_rx_buffer *rx_buf;
 	struct page *page;
-	void *page_addr;
 	struct efx_rx_page_state *state;
 	dma_addr_t dma_addr;
 	unsigned index, count;
@@ -207,12 +206,10 @@ static int efx_init_rx_buffers_page(struct efx_rx_queue *rx_queue)
 			__free_pages(page, efx->rx_buffer_order);
 			return -EIO;
 		}
-		page_addr = page_address(page);
-		state = page_addr;
+		state = page_address(page);
 		state->refcnt = 0;
 		state->dma_addr = dma_addr;
 
-		page_addr += sizeof(struct efx_rx_page_state);
 		dma_addr += sizeof(struct efx_rx_page_state);
 
 	split:
@@ -230,7 +227,6 @@ static int efx_init_rx_buffers_page(struct efx_rx_queue *rx_queue)
 			/* Use the second half of the page */
 			get_page(page);
 			dma_addr += (PAGE_SIZE >> 1);
-			page_addr += (PAGE_SIZE >> 1);
 			++count;
 			goto split;
 		}
diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c
index ce72ae4f399f..2069f51b2aa9 100644
--- a/drivers/net/ethernet/sfc/selftest.c
+++ b/drivers/net/ethernet/sfc/selftest.c
@@ -373,7 +373,7 @@ static void efx_iterate_state(struct efx_nic *efx)
 	/* saddr set later and used as incrementing count */
 	payload->ip.daddr = htonl(INADDR_LOOPBACK);
 	payload->ip.ihl = 5;
-	payload->ip.check = htons(0xdead);
+	payload->ip.check = (__force __sum16) htons(0xdead);
 	payload->ip.tot_len = htons(sizeof(*payload) - sizeof(struct ethhdr));
 	payload->ip.version = IPVERSION;
 	payload->ip.protocol = IPPROTO_UDP;
@@ -722,7 +722,7 @@ int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests,
 	/* Detach the device so the kernel doesn't transmit during the
 	 * loopback test and the watchdog timeout doesn't fire.
 	 */
-	netif_device_detach(efx->net_dev);
+	efx_device_detach_sync(efx);
 
 	if (efx->type->test_chip) {
 		rc_reset = efx->type->test_chip(efx, tests);
diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c
index 84b41bf08a38..ba40f67e4f05 100644
--- a/drivers/net/ethernet/sfc/siena.c
+++ b/drivers/net/ethernet/sfc/siena.c
@@ -127,6 +127,18 @@ static void siena_remove_port(struct efx_nic *efx)
 	efx_nic_free_buffer(efx, &efx->stats_buffer);
 }
 
+void siena_prepare_flush(struct efx_nic *efx)
+{
+	if (efx->fc_disable++ == 0)
+		efx_mcdi_set_mac(efx);
+}
+
+void siena_finish_flush(struct efx_nic *efx)
+{
+	if (--efx->fc_disable == 0)
+		efx_mcdi_set_mac(efx);
+}
+
 static const struct efx_nic_register_test siena_register_tests[] = {
 	{ FR_AZ_ADR_REGION,
 	  EFX_OWORD32(0x0003FFFF, 0x0003FFFF, 0x0003FFFF, 0x0003FFFF) },
@@ -158,7 +170,7 @@ static const struct efx_nic_register_test siena_register_tests[] = {
 
 static int siena_test_chip(struct efx_nic *efx, struct efx_self_tests *tests)
 {
-	enum reset_type reset_method = reset_method;
+	enum reset_type reset_method = RESET_TYPE_ALL;
 	int rc, rc2;
 
 	efx_reset_down(efx, reset_method);
@@ -659,7 +671,8 @@ const struct efx_nic_type siena_a0_nic_type = {
 	.reset = siena_reset_hw,
 	.probe_port = siena_probe_port,
 	.remove_port = siena_remove_port,
-	.prepare_flush = efx_port_dummy_op_void,
+	.prepare_flush = siena_prepare_flush,
+	.finish_flush = siena_finish_flush,
 	.update_stats = siena_update_nic_stats,
 	.start_stats = siena_start_nic_stats,
 	.stop_stats = siena_stop_nic_stats,
diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c
index d49b53dc2a50..90f8d1604f5f 100644
--- a/drivers/net/ethernet/sfc/siena_sriov.c
+++ b/drivers/net/ethernet/sfc/siena_sriov.c
@@ -695,8 +695,7 @@ static int efx_vfdi_fini_all_queues(struct efx_vf *vf)
 		return VFDI_RC_ENOMEM;
 
 	rtnl_lock();
-	if (efx->fc_disable++ == 0)
-		efx_mcdi_set_mac(efx);
+	siena_prepare_flush(efx);
 	rtnl_unlock();
 
 	/* Flush all the initialized queues */
@@ -733,8 +732,7 @@ static int efx_vfdi_fini_all_queues(struct efx_vf *vf)
 	}
 
 	rtnl_lock();
-	if (--efx->fc_disable == 0)
-		efx_mcdi_set_mac(efx);
+	siena_finish_flush(efx);
 	rtnl_unlock();
 
 	/* Irrespective of success/failure, fini the queues */
@@ -995,7 +993,7 @@ static void efx_sriov_reset_vf(struct efx_vf *vf, struct efx_buffer *buffer)
 			     FRF_AZ_EVQ_BUF_BASE_ID, buftbl);
 	efx_writeo_table(efx, &reg, FR_BZ_EVQ_PTR_TBL, abs_evq);
 	EFX_POPULATE_DWORD_1(ptr, FRF_AZ_EVQ_RPTR, 0);
-	efx_writed_table(efx, &ptr, FR_BZ_EVQ_RPTR, abs_evq);
+	efx_writed(efx, &ptr, FR_BZ_EVQ_RPTR + FR_BZ_EVQ_RPTR_STEP * abs_evq);
 
 	mutex_unlock(&vf->status_lock);
 }