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

Pull networking changes from David S Miller:

 1) Remove the ipv4 routing cache.  Now lookups go directly into the FIB
    trie and use prebuilt routes cached there.

    No more garbage collection, no more rDOS attacks on the routing
    cache.  Instead we now get predictable and consistent performance,
    no matter what the pattern of traffic we service.

    This has been almost 2 years in the making.  Special thanks to
    Julian Anastasov, Eric Dumazet, Steffen Klassert, and others who
    have helped along the way.

    I'm sure that with a change of this magnitude there will be some
    kind of fallout, but such things ought the be simple to fix at this
    point.  Luckily I'm not European so I'll be around all of August to
    fix things :-)

    The major stages of this work here are each fronted by a forced
    merge commit whose commit message contains a top-level description
    of the motivations and implementation issues.

 2) Pre-demux of established ipv4 TCP sockets, saves a route demux on
    input.

 3) TCP SYN/ACK performance tweaks from Eric Dumazet.

 4) Add namespace support for netfilter L4 conntrack helpers, from Gao
    Feng.

 5) Add config mechanism for Energy Efficient Ethernet to ethtool, from
    Yuval Mintz.

 6) Remove quadratic behavior from /proc/net/unix, from Eric Dumazet.

 7) Support for connection tracker helpers in userspace, from Pablo
    Neira Ayuso.

 8) Allow userspace driven TX load balancing functions in TEAM driver,
    from Jiri Pirko.

 9) Kill off NLMSG_PUT and RTA_PUT macros, more gross stuff with
    embedded gotos.

10) TCP Small Queues, essentially minimize the amount of TCP data queued
    up in the packet scheduler layer.  Whereas the existing BQL (Byte
    Queue Limits) limits the pkt_sched --> netdevice queuing levels,
    this controls the TCP --> pkt_sched queueing levels.

    From Eric Dumazet.

11) Reduce the number of get_page/put_page ops done on SKB fragments,
    from Alexander Duyck.

12) Implement protection against blind resets in TCP (RFC 5961), from
    Eric Dumazet.

13) Support the client side of TCP Fast Open, basically the ability to
    send data in the SYN exchange, from Yuchung Cheng.

    Basically, the sender queues up data with a sendmsg() call using
    MSG_FASTOPEN, then they do the connect() which emits the queued up
    fastopen data.

14) Avoid all the problems we get into in TCP when timers or PMTU events
    hit a locked socket.  The TCP Small Queues changes added a
    tcp_release_cb() that allows us to queue work up to the
    release_sock() caller, and that's what we use here too.  From Eric
    Dumazet.

15) Zero copy on TX support for TUN driver, from Michael S. Tsirkin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1870 commits)
  genetlink: define lockdep_genl_is_held() when CONFIG_LOCKDEP
  r8169: revert "add byte queue limit support".
  ipv4: Change rt->rt_iif encoding.
  net: Make skb->skb_iif always track skb->dev
  ipv4: Prepare for change of rt->rt_iif encoding.
  ipv4: Remove all RTCF_DIRECTSRC handliing.
  ipv4: Really ignore ICMP address requests/replies.
  decnet: Don't set RTCF_DIRECTSRC.
  net/ipv4/ip_vti.c: Fix __rcu warnings detected by sparse.
  ipv4: Remove redundant assignment
  rds: set correct msg_namelen
  openvswitch: potential NULL deref in sample()
  tcp: dont drop MTU reduction indications
  bnx2x: Add new 57840 device IDs
  tcp: avoid oops in tcp_metrics and reset tcpm_stamp
  niu: Change niu_rbr_fill() to use unlikely() to check niu_rbr_add_page() return value
  niu: Fix to check for dma mapping errors.
  net: Fix references to out-of-scope variables in put_cmsg_compat()
  net: ethernet: davinci_emac: add pm_runtime support
  net: ethernet: davinci_emac: Remove unnecessary #include
  ...

16 files changed, 185 insertions, 156 deletions

diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index b95f2e1b33f0..70554a1b2b02 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1103,8 +1103,8 @@ 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);
+		if (dma_supported(&pci_dev->dev, dma_mask)) {
+			rc = dma_set_mask(&pci_dev->dev, dma_mask);
 			if (rc == 0)
 				break;
 		}
@@ -1117,10 +1117,10 @@ static int efx_init_io(struct efx_nic *efx)
 	}
 	netif_dbg(efx, probe, efx->net_dev,
 		  "using DMA mask %llx\n", (unsigned long long) dma_mask);
-	rc = pci_set_consistent_dma_mask(pci_dev, dma_mask);
+	rc = dma_set_coherent_mask(&pci_dev->dev, dma_mask);
 	if (rc) {
-		/* pci_set_consistent_dma_mask() is not *allowed* to
-		 * fail with a mask that pci_set_dma_mask() accepted,
+		/* dma_set_coherent_mask() is not *allowed* to
+		 * fail with a mask that dma_set_mask() accepted,
 		 * but just in case...
 		 */
 		netif_err(efx, probe, efx->net_dev,
diff --git a/drivers/net/ethernet/sfc/enum.h b/drivers/net/ethernet/sfc/enum.h
index d725a8fbe1a6..182dbe2cc6e4 100644
--- a/drivers/net/ethernet/sfc/enum.h
+++ b/drivers/net/ethernet/sfc/enum.h
@@ -136,10 +136,10 @@ enum efx_loopback_mode {
  *
  * Reset methods are numbered in order of increasing scope.
  *
- * @RESET_TYPE_INVISIBLE: don't reset the PHYs or interrupts
- * @RESET_TYPE_ALL: reset everything but PCI core blocks
- * @RESET_TYPE_WORLD: reset everything, save & restore PCI config
- * @RESET_TYPE_DISABLE: disable NIC
+ * @RESET_TYPE_INVISIBLE: Reset datapath and MAC (Falcon only)
+ * @RESET_TYPE_ALL: Reset datapath, MAC and PHY
+ * @RESET_TYPE_WORLD: Reset as much as possible
+ * @RESET_TYPE_DISABLE: Reset datapath, MAC and PHY; leave NIC disabled
  * @RESET_TYPE_TX_WATCHDOG: reset due to TX watchdog
  * @RESET_TYPE_INT_ERROR: reset due to internal error
  * @RESET_TYPE_RX_RECOVERY: reset to recover from RX datapath errors
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 03ded364c8da..10536f93b561 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -453,7 +453,7 @@ static void efx_ethtool_get_strings(struct net_device *net_dev,
 	switch (string_set) {
 	case ETH_SS_STATS:
 		for (i = 0; i < EFX_ETHTOOL_NUM_STATS; i++)
-			strncpy(ethtool_strings[i].name,
+			strlcpy(ethtool_strings[i].name,
 				efx_ethtool_stats[i].name,
 				sizeof(ethtool_strings[i].name));
 		break;
diff --git a/drivers/net/ethernet/sfc/falcon.c b/drivers/net/ethernet/sfc/falcon.c
index 3a1ca2bd1548..12b573a8e82b 100644
--- a/drivers/net/ethernet/sfc/falcon.c
+++ b/drivers/net/ethernet/sfc/falcon.c
@@ -25,9 +25,12 @@
 #include "io.h"
 #include "phy.h"
 #include "workarounds.h"
+#include "selftest.h"
 
 /* Hardware control for SFC4000 (aka Falcon). */
 
+static int falcon_reset_hw(struct efx_nic *efx, enum reset_type method);
+
 static const unsigned int
 /* "Large" EEPROM device: Atmel AT25640 or similar
  * 8 KB, 16-bit address, 32 B write block */
@@ -1034,10 +1037,34 @@ static const struct efx_nic_register_test falcon_b0_register_tests[] = {
 	  EFX_OWORD32(0x0003FF0F, 0x00000000, 0x00000000, 0x00000000) },
 };
 
-static int falcon_b0_test_registers(struct efx_nic *efx)
+static int
+falcon_b0_test_chip(struct efx_nic *efx, struct efx_self_tests *tests)
 {
-	return efx_nic_test_registers(efx, falcon_b0_register_tests,
-				      ARRAY_SIZE(falcon_b0_register_tests));
+	enum reset_type reset_method = RESET_TYPE_INVISIBLE;
+	int rc, rc2;
+
+	mutex_lock(&efx->mac_lock);
+	if (efx->loopback_modes) {
+		/* We need the 312 clock from the PHY to test the XMAC
+		 * registers, so move into XGMII loopback if available */
+		if (efx->loopback_modes & (1 << LOOPBACK_XGMII))
+			efx->loopback_mode = LOOPBACK_XGMII;
+		else
+			efx->loopback_mode = __ffs(efx->loopback_modes);
+	}
+	__efx_reconfigure_port(efx);
+	mutex_unlock(&efx->mac_lock);
+
+	efx_reset_down(efx, reset_method);
+
+	tests->registers =
+		efx_nic_test_registers(efx, falcon_b0_register_tests,
+				       ARRAY_SIZE(falcon_b0_register_tests))
+		? -1 : 1;
+
+	rc = falcon_reset_hw(efx, reset_method);
+	rc2 = efx_reset_up(efx, reset_method, rc == 0);
+	return rc ? rc : rc2;
 }
 
 /**************************************************************************
@@ -1818,7 +1845,7 @@ const struct efx_nic_type falcon_b0_nic_type = {
 	.get_wol = falcon_get_wol,
 	.set_wol = falcon_set_wol,
 	.resume_wol = efx_port_dummy_op_void,
-	.test_registers = falcon_b0_test_registers,
+	.test_chip = falcon_b0_test_chip,
 	.test_nvram = falcon_test_nvram,
 
 	.revision = EFX_REV_FALCON_B0,
diff --git a/drivers/net/ethernet/sfc/falcon_xmac.c b/drivers/net/ethernet/sfc/falcon_xmac.c
index 6106ef15dee3..8333865d4c95 100644
--- a/drivers/net/ethernet/sfc/falcon_xmac.c
+++ b/drivers/net/ethernet/sfc/falcon_xmac.c
@@ -341,12 +341,12 @@ void falcon_update_stats_xmac(struct efx_nic *efx)
 	FALCON_STAT(efx, XgTxIpSrcErrPkt, tx_ip_src_error);
 
 	/* Update derived statistics */
-	mac_stats->tx_good_bytes =
-		(mac_stats->tx_bytes - mac_stats->tx_bad_bytes -
-		 mac_stats->tx_control * 64);
-	mac_stats->rx_bad_bytes =
-		(mac_stats->rx_bytes - mac_stats->rx_good_bytes -
-		 mac_stats->rx_control * 64);
+	efx_update_diff_stat(&mac_stats->tx_good_bytes,
+			     mac_stats->tx_bytes - mac_stats->tx_bad_bytes -
+			     mac_stats->tx_control * 64);
+	efx_update_diff_stat(&mac_stats->rx_bad_bytes,
+			     mac_stats->rx_bytes - mac_stats->rx_good_bytes -
+			     mac_stats->rx_control * 64);
 }
 
 void falcon_poll_xmac(struct efx_nic *efx)
diff --git a/drivers/net/ethernet/sfc/filter.c b/drivers/net/ethernet/sfc/filter.c
index fea7f7300675..c3fd61f0a95c 100644
--- a/drivers/net/ethernet/sfc/filter.c
+++ b/drivers/net/ethernet/sfc/filter.c
@@ -662,7 +662,7 @@ s32 efx_filter_insert_filter(struct efx_nic *efx, struct efx_filter_spec *spec,
 	struct efx_filter_table *table = efx_filter_spec_table(state, spec);
 	struct efx_filter_spec *saved_spec;
 	efx_oword_t filter;
-	unsigned int filter_idx, depth;
+	unsigned int filter_idx, depth = 0;
 	u32 key;
 	int rc;
 
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index 17b6463e459c..fc5e7bbcbc9e 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -1001,12 +1001,17 @@ static void efx_mcdi_exit_assertion(struct efx_nic *efx)
 {
 	u8 inbuf[MC_CMD_REBOOT_IN_LEN];
 
-	/* Atomically reboot the mcfw out of the assertion handler */
+	/* If the MC is running debug firmware, it might now be
+	 * waiting for a debugger to attach, but we just want it to
+	 * reboot.  We set a flag that makes the command a no-op if it
+	 * has already done so.  We don't know what return code to
+	 * expect (0 or -EIO), so ignore it.
+	 */
 	BUILD_BUG_ON(MC_CMD_REBOOT_OUT_LEN != 0);
 	MCDI_SET_DWORD(inbuf, REBOOT_IN_FLAGS,
 		       MC_CMD_REBOOT_FLAGS_AFTER_ASSERTION);
-	efx_mcdi_rpc(efx, MC_CMD_REBOOT, inbuf, MC_CMD_REBOOT_IN_LEN,
-		     NULL, 0, NULL);
+	(void) efx_mcdi_rpc(efx, MC_CMD_REBOOT, inbuf, MC_CMD_REBOOT_IN_LEN,
+			    NULL, 0, NULL);
 }
 
 int efx_mcdi_handle_assertion(struct efx_nic *efx)
diff --git a/drivers/net/ethernet/sfc/mcdi_mon.c b/drivers/net/ethernet/sfc/mcdi_mon.c
index fb7f65b59eb8..1d552f0664d7 100644
--- a/drivers/net/ethernet/sfc/mcdi_mon.c
+++ b/drivers/net/ethernet/sfc/mcdi_mon.c
@@ -222,6 +222,7 @@ efx_mcdi_mon_add_attr(struct efx_nic *efx, const char *name,
 	attr->index = index;
 	attr->type = type;
 	attr->limit_value = limit_value;
+	sysfs_attr_init(&attr->dev_attr.attr);
 	attr->dev_attr.attr.name = attr->name;
 	attr->dev_attr.attr.mode = S_IRUGO;
 	attr->dev_attr.show = reader;
diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h
index 0310b9f08c9b..db4beed97669 100644
--- a/drivers/net/ethernet/sfc/mcdi_pcol.h
+++ b/drivers/net/ethernet/sfc/mcdi_pcol.h
@@ -48,8 +48,7 @@
 
 /* Unused commands: 0x23, 0x27, 0x30, 0x31 */
 
-/**
- * MCDI version 1
+/* MCDI version 1
  *
  * Each MCDI request starts with an MCDI_HEADER, which is a 32byte
  * structure, filled in by the client.
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 0e575359af17..cd9c0a989692 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -68,6 +68,8 @@
 #define EFX_TXQ_TYPES		4
 #define EFX_MAX_TX_QUEUES	(EFX_TXQ_TYPES * EFX_MAX_CHANNELS)
 
+struct efx_self_tests;
+
 /**
  * struct efx_special_buffer - An Efx special buffer
  * @addr: CPU base address of the buffer
@@ -100,7 +102,7 @@ struct efx_special_buffer {
  * @len: Length of this fragment.
  *	This field is zero when the queue slot is empty.
  * @continuation: True if this fragment is not the end of a packet.
- * @unmap_single: True if pci_unmap_single should be used.
+ * @unmap_single: True if dma_unmap_single should be used.
  * @unmap_len: Length of this fragment to unmap
  */
 struct efx_tx_buffer {
@@ -527,7 +529,7 @@ struct efx_phy_operations {
 };
 
 /**
- * @enum efx_phy_mode - PHY operating mode flags
+ * enum efx_phy_mode - PHY operating mode flags
  * @PHY_MODE_NORMAL: on and should pass traffic
  * @PHY_MODE_TX_DISABLED: on with TX disabled
  * @PHY_MODE_LOW_POWER: set to low power through MDIO
@@ -901,7 +903,8 @@ static inline unsigned int efx_port_num(struct efx_nic *efx)
  * @get_wol: Get WoL configuration from driver state
  * @set_wol: Push WoL configuration to the NIC
  * @resume_wol: Synchronise WoL state between driver and MC (e.g. after resume)
- * @test_registers: Test read/write functionality of control registers
+ * @test_chip: Test registers.  Should use efx_nic_test_registers(), and is
+ *	expected to reset the NIC.
  * @test_nvram: Test validity of NVRAM contents
  * @revision: Hardware architecture revision
  * @mem_map_size: Memory BAR mapped size
@@ -946,7 +949,7 @@ struct efx_nic_type {
 	void (*get_wol)(struct efx_nic *efx, struct ethtool_wolinfo *wol);
 	int (*set_wol)(struct efx_nic *efx, u32 type);
 	void (*resume_wol)(struct efx_nic *efx);
-	int (*test_registers)(struct efx_nic *efx);
+	int (*test_chip)(struct efx_nic *efx, struct efx_self_tests *tests);
 	int (*test_nvram)(struct efx_nic *efx);
 
 	int revision;
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index 4a9a5beec8fc..326d799762d6 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -124,9 +124,6 @@ int efx_nic_test_registers(struct efx_nic *efx,
 	unsigned address = 0, i, j;
 	efx_oword_t mask, imask, original, reg, buf;
 
-	/* Falcon should be in loopback to isolate the XMAC from the PHY */
-	WARN_ON(!LOOPBACK_INTERNAL(efx));
-
 	for (i = 0; i < n_regs; ++i) {
 		address = regs[i].address;
 		mask = imask = regs[i].mask;
@@ -308,8 +305,8 @@ efx_free_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer)
 int efx_nic_alloc_buffer(struct efx_nic *efx, struct efx_buffer *buffer,
 			 unsigned int len)
 {
-	buffer->addr = pci_alloc_consistent(efx->pci_dev, len,
-					    &buffer->dma_addr);
+	buffer->addr = dma_alloc_coherent(&efx->pci_dev->dev, len,
+					  &buffer->dma_addr, GFP_ATOMIC);
 	if (!buffer->addr)
 		return -ENOMEM;
 	buffer->len = len;
@@ -320,8 +317,8 @@ int efx_nic_alloc_buffer(struct efx_nic *efx, struct efx_buffer *buffer,
 void efx_nic_free_buffer(struct efx_nic *efx, struct efx_buffer *buffer)
 {
 	if (buffer->addr) {
-		pci_free_consistent(efx->pci_dev, buffer->len,
-				    buffer->addr, buffer->dma_addr);
+		dma_free_coherent(&efx->pci_dev->dev, buffer->len,
+				  buffer->addr, buffer->dma_addr);
 		buffer->addr = NULL;
 	}
 }
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index f48ccf6bb3b9..bab5cd9f5740 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -294,6 +294,24 @@ extern bool falcon_xmac_check_fault(struct efx_nic *efx);
 extern int falcon_reconfigure_xmac(struct efx_nic *efx);
 extern void falcon_update_stats_xmac(struct efx_nic *efx);
 
+/* Some statistics are computed as A - B where A and B each increase
+ * linearly with some hardware counter(s) and the counters are read
+ * asynchronously.  If the counters contributing to B are always read
+ * after those contributing to A, the computed value may be lower than
+ * the true value by some variable amount, and may decrease between
+ * subsequent computations.
+ *
+ * We should never allow statistics to decrease or to exceed the true
+ * value.  Since the computed value will never be greater than the
+ * true value, we can achieve this by only storing the computed value
+ * when it increases.
+ */
+static inline void efx_update_diff_stat(u64 *stat, u64 diff)
+{
+	if ((s64)(diff - *stat) > 0)
+		*stat = diff;
+}
+
 /* Interrupts and test events */
 extern int efx_nic_init_interrupt(struct efx_nic *efx);
 extern void efx_nic_enable_interrupts(struct efx_nic *efx);
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 243e91f3dff9..719319b89d7a 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -155,11 +155,11 @@ static int efx_init_rx_buffers_skb(struct efx_rx_queue *rx_queue)
 		rx_buf->len = skb_len - NET_IP_ALIGN;
 		rx_buf->flags = 0;
 
-		rx_buf->dma_addr = pci_map_single(efx->pci_dev,
+		rx_buf->dma_addr = dma_map_single(&efx->pci_dev->dev,
 						  skb->data, rx_buf->len,
-						  PCI_DMA_FROMDEVICE);
-		if (unlikely(pci_dma_mapping_error(efx->pci_dev,
-						   rx_buf->dma_addr))) {
+						  DMA_FROM_DEVICE);
+		if (unlikely(dma_mapping_error(&efx->pci_dev->dev,
+					       rx_buf->dma_addr))) {
 			dev_kfree_skb_any(skb);
 			rx_buf->u.skb = NULL;
 			return -EIO;
@@ -200,10 +200,10 @@ static int efx_init_rx_buffers_page(struct efx_rx_queue *rx_queue)
 				   efx->rx_buffer_order);
 		if (unlikely(page == NULL))
 			return -ENOMEM;
-		dma_addr = pci_map_page(efx->pci_dev, page, 0,
+		dma_addr = dma_map_page(&efx->pci_dev->dev, page, 0,
 					efx_rx_buf_size(efx),
-					PCI_DMA_FROMDEVICE);
-		if (unlikely(pci_dma_mapping_error(efx->pci_dev, dma_addr))) {
+					DMA_FROM_DEVICE);
+		if (unlikely(dma_mapping_error(&efx->pci_dev->dev, dma_addr))) {
 			__free_pages(page, efx->rx_buffer_order);
 			return -EIO;
 		}
@@ -247,14 +247,14 @@ static void efx_unmap_rx_buffer(struct efx_nic *efx,
 
 		state = page_address(rx_buf->u.page);
 		if (--state->refcnt == 0) {
-			pci_unmap_page(efx->pci_dev,
+			dma_unmap_page(&efx->pci_dev->dev,
 				       state->dma_addr,
 				       efx_rx_buf_size(efx),
-				       PCI_DMA_FROMDEVICE);
+				       DMA_FROM_DEVICE);
 		}
 	} else if (!(rx_buf->flags & EFX_RX_BUF_PAGE) && rx_buf->u.skb) {
-		pci_unmap_single(efx->pci_dev, rx_buf->dma_addr,
-				 rx_buf->len, PCI_DMA_FROMDEVICE);
+		dma_unmap_single(&efx->pci_dev->dev, rx_buf->dma_addr,
+				 rx_buf->len, DMA_FROM_DEVICE);
 	}
 }
 
@@ -336,6 +336,7 @@ static void efx_recycle_rx_buffer(struct efx_channel *channel,
 /**
  * efx_fast_push_rx_descriptors - push new RX descriptors quickly
  * @rx_queue:		RX descriptor queue
+ *
  * This will aim to fill the RX descriptor queue up to
  * @rx_queue->@max_fill. If there is insufficient atomic
  * memory to do so, a slow fill will be scheduled.
diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c
index de4c0069f5b2..96068d15b601 100644
--- a/drivers/net/ethernet/sfc/selftest.c
+++ b/drivers/net/ethernet/sfc/selftest.c
@@ -120,19 +120,6 @@ static int efx_test_nvram(struct efx_nic *efx, struct efx_self_tests *tests)
 	return rc;
 }
 
-static int efx_test_chip(struct efx_nic *efx, struct efx_self_tests *tests)
-{
-	int rc = 0;
-
-	/* Test register access */
-	if (efx->type->test_registers) {
-		rc = efx->type->test_registers(efx);
-		tests->registers = rc ? -1 : 1;
-	}
-
-	return rc;
-}
-
 /**************************************************************************
  *
  * Interrupt and event queue testing
@@ -488,7 +475,7 @@ static int efx_end_loopback(struct efx_tx_queue *tx_queue,
 		skb = state->skbs[i];
 		if (skb && !skb_shared(skb))
 			++tx_done;
-		dev_kfree_skb_any(skb);
+		dev_kfree_skb(skb);
 	}
 
 	netif_tx_unlock_bh(efx->net_dev);
@@ -699,8 +686,7 @@ int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests,
 {
 	enum efx_loopback_mode loopback_mode = efx->loopback_mode;
 	int phy_mode = efx->phy_mode;
-	enum reset_type reset_method = RESET_TYPE_INVISIBLE;
-	int rc_test = 0, rc_reset = 0, rc;
+	int rc_test = 0, rc_reset, rc;
 
 	efx_selftest_async_cancel(efx);
 
@@ -737,44 +723,26 @@ int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests,
 	 */
 	netif_device_detach(efx->net_dev);
 
-	mutex_lock(&efx->mac_lock);
-	if (efx->loopback_modes) {
-		/* We need the 312 clock from the PHY to test the XMAC
-		 * registers, so move into XGMII loopback if available */
-		if (efx->loopback_modes & (1 << LOOPBACK_XGMII))
-			efx->loopback_mode = LOOPBACK_XGMII;
-		else
-			efx->loopback_mode = __ffs(efx->loopback_modes);
-	}
-
-	__efx_reconfigure_port(efx);
-	mutex_unlock(&efx->mac_lock);
-
-	/* free up all consumers of SRAM (including all the queues) */
-	efx_reset_down(efx, reset_method);
-
-	rc = efx_test_chip(efx, tests);
-	if (rc && !rc_test)
-		rc_test = rc;
+	if (efx->type->test_chip) {
+		rc_reset = efx->type->test_chip(efx, tests);
+		if (rc_reset) {
+			netif_err(efx, hw, efx->net_dev,
+				  "Unable to recover from chip test\n");
+			efx_schedule_reset(efx, RESET_TYPE_DISABLE);
+			return rc_reset;
+		}
 
-	/* reset the chip to recover from the register test */
-	rc_reset = efx->type->reset(efx, reset_method);
+		if ((tests->registers < 0) && !rc_test)
+			rc_test = -EIO;
+	}
 
 	/* Ensure that the phy is powered and out of loopback
 	 * for the bist and loopback tests */
+	mutex_lock(&efx->mac_lock);
 	efx->phy_mode &= ~PHY_MODE_LOW_POWER;
 	efx->loopback_mode = LOOPBACK_NONE;
-
-	rc = efx_reset_up(efx, reset_method, rc_reset == 0);
-	if (rc && !rc_reset)
-		rc_reset = rc;
-
-	if (rc_reset) {
-		netif_err(efx, drv, efx->net_dev,
-			  "Unable to recover from chip test\n");
-		efx_schedule_reset(efx, RESET_TYPE_DISABLE);
-		return rc_reset;
-	}
+	__efx_reconfigure_port(efx);
+	mutex_unlock(&efx->mac_lock);
 
 	rc = efx_test_phy(efx, tests, flags);
 	if (rc && !rc_test)
diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c
index 9f8d7cea3967..6bafd216e55e 100644
--- a/drivers/net/ethernet/sfc/siena.c
+++ b/drivers/net/ethernet/sfc/siena.c
@@ -25,10 +25,12 @@
 #include "workarounds.h"
 #include "mcdi.h"
 #include "mcdi_pcol.h"
+#include "selftest.h"
 
 /* Hardware control for SFC9000 family including SFL9021 (aka Siena). */
 
 static void siena_init_wol(struct efx_nic *efx);
+static int siena_reset_hw(struct efx_nic *efx, enum reset_type method);
 
 
 static void siena_push_irq_moderation(struct efx_channel *channel)
@@ -154,10 +156,29 @@ static const struct efx_nic_register_test siena_register_tests[] = {
 	  EFX_OWORD32(0xFFFFFFFF, 0xFFFFFFFF, 0x00000007, 0x00000000) },
 };
 
-static int siena_test_registers(struct efx_nic *efx)
+static int siena_test_chip(struct efx_nic *efx, struct efx_self_tests *tests)
 {
-	return efx_nic_test_registers(efx, siena_register_tests,
-				      ARRAY_SIZE(siena_register_tests));
+	enum reset_type reset_method = reset_method;
+	int rc, rc2;
+
+	efx_reset_down(efx, reset_method);
+
+	/* Reset the chip immediately so that it is completely
+	 * quiescent regardless of what any VF driver does.
+	 */
+	rc = siena_reset_hw(efx, reset_method);
+	if (rc)
+		goto out;
+
+	tests->registers =
+		efx_nic_test_registers(efx, siena_register_tests,
+				       ARRAY_SIZE(siena_register_tests))
+		? -1 : 1;
+
+	rc = siena_reset_hw(efx, reset_method);
+out:
+	rc2 = efx_reset_up(efx, reset_method, rc == 0);
+	return rc ? rc : rc2;
 }
 
 /**************************************************************************
@@ -437,8 +458,8 @@ static int siena_try_update_nic_stats(struct efx_nic *efx)
 
 	MAC_STAT(tx_bytes, TX_BYTES);
 	MAC_STAT(tx_bad_bytes, TX_BAD_BYTES);
-	mac_stats->tx_good_bytes = (mac_stats->tx_bytes -
-				    mac_stats->tx_bad_bytes);
+	efx_update_diff_stat(&mac_stats->tx_good_bytes,
+			     mac_stats->tx_bytes - mac_stats->tx_bad_bytes);
 	MAC_STAT(tx_packets, TX_PKTS);
 	MAC_STAT(tx_bad, TX_BAD_FCS_PKTS);
 	MAC_STAT(tx_pause, TX_PAUSE_PKTS);
@@ -471,8 +492,8 @@ static int siena_try_update_nic_stats(struct efx_nic *efx)
 	MAC_STAT(tx_ip_src_error, TX_IP_SRC_ERR_PKTS);
 	MAC_STAT(rx_bytes, RX_BYTES);
 	MAC_STAT(rx_bad_bytes, RX_BAD_BYTES);
-	mac_stats->rx_good_bytes = (mac_stats->rx_bytes -
-				    mac_stats->rx_bad_bytes);
+	efx_update_diff_stat(&mac_stats->rx_good_bytes,
+			     mac_stats->rx_bytes - mac_stats->rx_bad_bytes);
 	MAC_STAT(rx_packets, RX_PKTS);
 	MAC_STAT(rx_good, RX_GOOD_PKTS);
 	MAC_STAT(rx_bad, RX_BAD_FCS_PKTS);
@@ -649,7 +670,7 @@ const struct efx_nic_type siena_a0_nic_type = {
 	.get_wol = siena_get_wol,
 	.set_wol = siena_set_wol,
 	.resume_wol = siena_init_wol,
-	.test_registers = siena_test_registers,
+	.test_chip = siena_test_chip,
 	.test_nvram = efx_mcdi_nvram_test_all,
 
 	.revision = EFX_REV_SIENA_A0,
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 94d0365b31cd..9b225a7769f7 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -36,15 +36,15 @@ static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
 			       unsigned int *bytes_compl)
 {
 	if (buffer->unmap_len) {
-		struct pci_dev *pci_dev = tx_queue->efx->pci_dev;
+		struct device *dma_dev = &tx_queue->efx->pci_dev->dev;
 		dma_addr_t unmap_addr = (buffer->dma_addr + buffer->len -
 					 buffer->unmap_len);
 		if (buffer->unmap_single)
-			pci_unmap_single(pci_dev, unmap_addr, buffer->unmap_len,
-					 PCI_DMA_TODEVICE);
+			dma_unmap_single(dma_dev, unmap_addr, buffer->unmap_len,
+					 DMA_TO_DEVICE);
 		else
-			pci_unmap_page(pci_dev, unmap_addr, buffer->unmap_len,
-				       PCI_DMA_TODEVICE);
+			dma_unmap_page(dma_dev, unmap_addr, buffer->unmap_len,
+				       DMA_TO_DEVICE);
 		buffer->unmap_len = 0;
 		buffer->unmap_single = false;
 	}
@@ -138,7 +138,7 @@ efx_max_tx_len(struct efx_nic *efx, dma_addr_t dma_addr)
 netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 {
 	struct efx_nic *efx = tx_queue->efx;
-	struct pci_dev *pci_dev = efx->pci_dev;
+	struct device *dma_dev = &efx->pci_dev->dev;
 	struct efx_tx_buffer *buffer;
 	skb_frag_t *fragment;
 	unsigned int len, unmap_len = 0, fill_level, insert_ptr;
@@ -167,17 +167,17 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 	fill_level = tx_queue->insert_count - tx_queue->old_read_count;
 	q_space = efx->txq_entries - 1 - fill_level;
 
-	/* Map for DMA.  Use pci_map_single rather than pci_map_page
+	/* Map for DMA.  Use dma_map_single rather than dma_map_page
 	 * since this is more efficient on machines with sparse
 	 * memory.
 	 */
 	unmap_single = true;
-	dma_addr = pci_map_single(pci_dev, skb->data, len, PCI_DMA_TODEVICE);
+	dma_addr = dma_map_single(dma_dev, skb->data, len, PCI_DMA_TODEVICE);
 
 	/* Process all fragments */
 	while (1) {
-		if (unlikely(pci_dma_mapping_error(pci_dev, dma_addr)))
-			goto pci_err;
+		if (unlikely(dma_mapping_error(dma_dev, dma_addr)))
+			goto dma_err;
 
 		/* Store fields for marking in the per-fragment final
 		 * descriptor */
@@ -246,7 +246,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 		i++;
 		/* Map for DMA */
 		unmap_single = false;
-		dma_addr = skb_frag_dma_map(&pci_dev->dev, fragment, 0, len,
+		dma_addr = skb_frag_dma_map(dma_dev, fragment, 0, len,
 					    DMA_TO_DEVICE);
 	}
 
@@ -261,7 +261,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 
 	return NETDEV_TX_OK;
 
- pci_err:
+ dma_err:
 	netif_err(efx, tx_err, efx->net_dev,
 		  " TX queue %d could not map skb with %d bytes %d "
 		  "fragments for DMA\n", tx_queue->queue, skb->len,
@@ -284,11 +284,11 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 	/* Free the fragment we were mid-way through pushing */
 	if (unmap_len) {
 		if (unmap_single)
-			pci_unmap_single(pci_dev, unmap_addr, unmap_len,
-					 PCI_DMA_TODEVICE);
+			dma_unmap_single(dma_dev, unmap_addr, unmap_len,
+					 DMA_TO_DEVICE);
 		else
-			pci_unmap_page(pci_dev, unmap_addr, unmap_len,
-				       PCI_DMA_TODEVICE);
+			dma_unmap_page(dma_dev, unmap_addr, unmap_len,
+				       DMA_TO_DEVICE);
 	}
 
 	return rc;
@@ -651,17 +651,8 @@ static __be16 efx_tso_check_protocol(struct sk_buff *skb)
 	EFX_BUG_ON_PARANOID(((struct ethhdr *)skb->data)->h_proto !=
 			    protocol);
 	if (protocol == htons(ETH_P_8021Q)) {
-		/* Find the encapsulated protocol; reset network header
-		 * and transport header based on that. */
 		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
 		protocol = veh->h_vlan_encapsulated_proto;
-		skb_set_network_header(skb, sizeof(*veh));
-		if (protocol == htons(ETH_P_IP))
-			skb_set_transport_header(skb, sizeof(*veh) +
-						 4 * ip_hdr(skb)->ihl);
-		else if (protocol == htons(ETH_P_IPV6))
-			skb_set_transport_header(skb, sizeof(*veh) +
-						 sizeof(struct ipv6hdr));
 	}
 
 	if (protocol == htons(ETH_P_IP)) {
@@ -684,20 +675,19 @@ static __be16 efx_tso_check_protocol(struct sk_buff *skb)
  */
 static int efx_tsoh_block_alloc(struct efx_tx_queue *tx_queue)
 {
-
-	struct pci_dev *pci_dev = tx_queue->efx->pci_dev;
+	struct device *dma_dev = &tx_queue->efx->pci_dev->dev;
 	struct efx_tso_header *tsoh;
 	dma_addr_t dma_addr;
 	u8 *base_kva, *kva;
 
-	base_kva = pci_alloc_consistent(pci_dev, PAGE_SIZE, &dma_addr);
+	base_kva = dma_alloc_coherent(dma_dev, PAGE_SIZE, &dma_addr, GFP_ATOMIC);
 	if (base_kva == NULL) {
 		netif_err(tx_queue->efx, tx_err, tx_queue->efx->net_dev,
 			  "Unable to allocate page for TSO headers\n");
 		return -ENOMEM;
 	}
 
-	/* pci_alloc_consistent() allocates pages. */
+	/* dma_alloc_coherent() allocates pages. */
 	EFX_BUG_ON_PARANOID(dma_addr & (PAGE_SIZE - 1u));
 
 	for (kva = base_kva; kva < base_kva + PAGE_SIZE; kva += TSOH_STD_SIZE) {
@@ -714,7 +704,7 @@ static int efx_tsoh_block_alloc(struct efx_tx_queue *tx_queue)
 /* Free up a TSO header, and all others in the same page. */
 static void efx_tsoh_block_free(struct efx_tx_queue *tx_queue,
 				struct efx_tso_header *tsoh,
-				struct pci_dev *pci_dev)
+				struct device *dma_dev)
 {
 	struct efx_tso_header **p;
 	unsigned long base_kva;
@@ -731,7 +721,7 @@ static void efx_tsoh_block_free(struct efx_tx_queue *tx_queue,
 			p = &(*p)->next;
 	}
 
-	pci_free_consistent(pci_dev, PAGE_SIZE, (void *)base_kva, base_dma);
+	dma_free_coherent(dma_dev, PAGE_SIZE, (void *)base_kva, base_dma);
 }
 
 static struct efx_tso_header *
@@ -743,11 +733,11 @@ efx_tsoh_heap_alloc(struct efx_tx_queue *tx_queue, size_t header_len)
 	if (unlikely(!tsoh))
 		return NULL;
 
-	tsoh->dma_addr = pci_map_single(tx_queue->efx->pci_dev,
+	tsoh->dma_addr = dma_map_single(&tx_queue->efx->pci_dev->dev,
 					TSOH_BUFFER(tsoh), header_len,
-					PCI_DMA_TODEVICE);
-	if (unlikely(pci_dma_mapping_error(tx_queue->efx->pci_dev,
-					   tsoh->dma_addr))) {
+					DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(&tx_queue->efx->pci_dev->dev,
+				       tsoh->dma_addr))) {
 		kfree(tsoh);
 		return NULL;
 	}
@@ -759,9 +749,9 @@ efx_tsoh_heap_alloc(struct efx_tx_queue *tx_queue, size_t header_len)
 static void
 efx_tsoh_heap_free(struct efx_tx_queue *tx_queue, struct efx_tso_header *tsoh)
 {
-	pci_unmap_single(tx_queue->efx->pci_dev,
+	dma_unmap_single(&tx_queue->efx->pci_dev->dev,
 			 tsoh->dma_addr, tsoh->unmap_len,
-			 PCI_DMA_TODEVICE);
+			 DMA_TO_DEVICE);
 	kfree(tsoh);
 }
 
@@ -892,13 +882,13 @@ static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue)
 			unmap_addr = (buffer->dma_addr + buffer->len -
 				      buffer->unmap_len);
 			if (buffer->unmap_single)
-				pci_unmap_single(tx_queue->efx->pci_dev,
+				dma_unmap_single(&tx_queue->efx->pci_dev->dev,
 						 unmap_addr, buffer->unmap_len,
-						 PCI_DMA_TODEVICE);
+						 DMA_TO_DEVICE);
 			else
-				pci_unmap_page(tx_queue->efx->pci_dev,
+				dma_unmap_page(&tx_queue->efx->pci_dev->dev,
 					       unmap_addr, buffer->unmap_len,
-					       PCI_DMA_TODEVICE);
+					       DMA_TO_DEVICE);
 			buffer->unmap_len = 0;
 		}
 		buffer->len = 0;
@@ -927,7 +917,6 @@ static void tso_start(struct tso_state *st, const struct sk_buff *skb)
 	EFX_BUG_ON_PARANOID(tcp_hdr(skb)->syn);
 	EFX_BUG_ON_PARANOID(tcp_hdr(skb)->rst);
 
-	st->packet_space = st->full_packet_size;
 	st->out_len = skb->len - st->header_len;
 	st->unmap_len = 0;
 	st->unmap_single = false;
@@ -954,9 +943,9 @@ static int tso_get_head_fragment(struct tso_state *st, struct efx_nic *efx,
 	int hl = st->header_len;
 	int len = skb_headlen(skb) - hl;
 
-	st->unmap_addr = pci_map_single(efx->pci_dev, skb->data + hl,
-					len, PCI_DMA_TODEVICE);
-	if (likely(!pci_dma_mapping_error(efx->pci_dev, st->unmap_addr))) {
+	st->unmap_addr = dma_map_single(&efx->pci_dev->dev, skb->data + hl,
+					len, DMA_TO_DEVICE);
+	if (likely(!dma_mapping_error(&efx->pci_dev->dev, st->unmap_addr))) {
 		st->unmap_single = true;
 		st->unmap_len = len;
 		st->in_len = len;
@@ -1008,7 +997,7 @@ static int tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue,
 		buffer->continuation = !end_of_packet;
 
 		if (st->in_len == 0) {
-			/* Transfer ownership of the pci mapping */
+			/* Transfer ownership of the DMA mapping */
 			buffer->unmap_len = st->unmap_len;
 			buffer->unmap_single = st->unmap_single;
 			st->unmap_len = 0;
@@ -1181,18 +1170,18 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 
  mem_err:
 	netif_err(efx, tx_err, efx->net_dev,
-		  "Out of memory for TSO headers, or PCI mapping error\n");
+		  "Out of memory for TSO headers, or DMA mapping error\n");
 	dev_kfree_skb_any(skb);
 
  unwind:
 	/* Free the DMA mapping we were in the process of writing out */
 	if (state.unmap_len) {
 		if (state.unmap_single)
-			pci_unmap_single(efx->pci_dev, state.unmap_addr,
-					 state.unmap_len, PCI_DMA_TODEVICE);
+			dma_unmap_single(&efx->pci_dev->dev, state.unmap_addr,
+					 state.unmap_len, DMA_TO_DEVICE);
 		else
-			pci_unmap_page(efx->pci_dev, state.unmap_addr,
-				       state.unmap_len, PCI_DMA_TODEVICE);
+			dma_unmap_page(&efx->pci_dev->dev, state.unmap_addr,
+				       state.unmap_len, DMA_TO_DEVICE);
 	}
 
 	efx_enqueue_unwind(tx_queue);
@@ -1216,5 +1205,5 @@ static void efx_fini_tso(struct efx_tx_queue *tx_queue)
 
 	while (tx_queue->tso_headers_free != NULL)
 		efx_tsoh_block_free(tx_queue, tx_queue->tso_headers_free,
-				    tx_queue->efx->pci_dev);
+				    &tx_queue->efx->pci_dev->dev);
 }