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

Pull networking updates from David Miller:

 1) Add TX fast path in mac80211, from Johannes Berg.

 2) Add TSO/GRO support to ibmveth, from Thomas Falcon

 3) Move away from cached routes in ipv6, just like ipv4, from Martin
    KaFai Lau.

 4) Lots of new rhashtable tests, from Thomas Graf.

 5) Run ingress qdisc lockless, from Alexei Starovoitov.

 6) Allow servers to fetch TCP packet headers for SYN packets of new
    connections, for fingerprinting.  From Eric Dumazet.

 7) Add mode parameter to pktgen, for testing receive.  From Alexei
    Starovoitov.

 8) Cache access optimizations via simplifications of build_skb(), from
    Alexander Duyck.

 9) Move page frag allocator under mm/, also from Alexander.

10) Add xmit_more support to hv_netvsc, from KY Srinivasan.

11) Add a counter guard in case we try to perform endless reclassify
    loops in the packet scheduler.

12) Extern flow dissector to be programmable and use it in new "Flower"
    classifier.  From Jiri Pirko.

13) AF_PACKET fanout rollover fixes, performance improvements, and new
    statistics.  From Willem de Bruijn.

14) Add netdev driver for GENEVE tunnels, from John W Linville.

15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso.

16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet.

17) Add an ECN retry fallback for the initial TCP handshake, from Daniel
    Borkmann.

18) Add tail call support to BPF, from Alexei Starovoitov.

19) Add several pktgen helper scripts, from Jesper Dangaard Brouer.

20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa.

21) Favor even port numbers for allocation to connect() requests, and
    odd port numbers for bind(0), in an effort to help avoid
    ip_local_port_range exhaustion.  From Eric Dumazet.

22) Add Cavium ThunderX driver, from Sunil Goutham.

23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata,
    from Alexei Starovoitov.

24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai.

25) Double TCP Small Queues default to 256K to accomodate situations
    like the XEN driver and wireless aggregation.  From Wei Liu.

26) Add more entropy inputs to flow dissector, from Tom Herbert.

27) Add CDG congestion control algorithm to TCP, from Kenneth Klette
    Jonassen.

28) Convert ipset over to RCU locking, from Jozsef Kadlecsik.

29) Track and act upon link status of ipv4 route nexthops, from Andy
    Gospodarek.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits)
  bridge: vlan: flush the dynamically learned entries on port vlan delete
  bridge: multicast: add a comment to br_port_state_selection about blocking state
  net: inet_diag: export IPV6_V6ONLY sockopt
  stmmac: troubleshoot unexpected bits in des0 & des1
  net: ipv4 sysctl option to ignore routes when nexthop link is down
  net: track link-status of ipv4 nexthops
  net: switchdev: ignore unsupported bridge flags
  net: Cavium: Fix MAC address setting in shutdown state
  drivers: net: xgene: fix for ACPI support without ACPI
  ip: report the original address of ICMP messages
  net/mlx5e: Prefetch skb data on RX
  net/mlx5e: Pop cq outside mlx5e_get_cqe
  net/mlx5e: Remove mlx5e_cq.sqrq back-pointer
  net/mlx5e: Remove extra spaces
  net/mlx5e: Avoid TX CQE generation if more xmit packets expected
  net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion
  net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq()
  net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them
  net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues
  net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device
  ...

23 files changed, 3187 insertions, 653 deletions

diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
index 088921294448..4dd92b7b80f4 100644
--- a/drivers/net/ethernet/sfc/Kconfig
+++ b/drivers/net/ethernet/sfc/Kconfig
@@ -36,3 +36,12 @@ config SFC_SRIOV
 	  This enables support for the SFC9000 I/O Virtualization
 	  features, allowing accelerated network performance in
 	  virtualized environments.
+config SFC_MCDI_LOGGING
+	bool "Solarflare SFC9000/SFC9100-family MCDI logging support"
+	depends on SFC
+	default y
+	---help---
+	  This enables support for tracing of MCDI (Management-Controller-to-
+	  Driver-Interface) commands and responses, allowing debugging of
+	  driver/firmware interaction.  The tracing is actually enabled by
+	  a sysfs file 'mcdi_logging' under the PCI device.
diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index 3a83c0dca8e6..ce8470fe79d5 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -3,6 +3,6 @@ sfc-y			+= efx.o nic.o farch.o falcon.o siena.o ef10.o tx.o \
 			   tenxpress.o txc43128_phy.o falcon_boards.o \
 			   mcdi.o mcdi_port.o mcdi_mon.o ptp.o
 sfc-$(CONFIG_SFC_MTD)	+= mtd.o
-sfc-$(CONFIG_SFC_SRIOV)	+= siena_sriov.o
+sfc-$(CONFIG_SFC_SRIOV)	+= sriov.o siena_sriov.o ef10_sriov.o
 
 obj-$(CONFIG_SFC)	+= sfc.o
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index fbb6cfa0f5f1..847643455468 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -15,6 +15,7 @@
 #include "nic.h"
 #include "workarounds.h"
 #include "selftest.h"
+#include "ef10_sriov.h"
 #include <linux/in.h>
 #include <linux/jhash.h>
 #include <linux/wait.h>
@@ -30,6 +31,9 @@ enum {
 
 /* The reserved RSS context value */
 #define EFX_EF10_RSS_CONTEXT_INVALID	0xffffffff
+/* The maximum size of a shared RSS context */
+/* TODO: this should really be from the mcdi protocol export */
+#define EFX_EF10_MAX_SHARED_RSS_CONTEXT_SIZE 64UL
 
 /* The filter table(s) are managed by firmware and we have write-only
  * access.  When removing filters we must identify them to the
@@ -77,7 +81,6 @@ struct efx_ef10_filter_table {
 /* An arbitrary search limit for the software hash table */
 #define EFX_EF10_FILTER_SEARCH_LIMIT 200
 
-static void efx_ef10_rx_push_rss_config(struct efx_nic *efx);
 static void efx_ef10_rx_free_indir_table(struct efx_nic *efx);
 static void efx_ef10_filter_table_remove(struct efx_nic *efx);
 
@@ -92,8 +95,49 @@ static int efx_ef10_get_warm_boot_count(struct efx_nic *efx)
 
 static unsigned int efx_ef10_mem_map_size(struct efx_nic *efx)
 {
-	return resource_size(&efx->pci_dev->resource[EFX_MEM_BAR]);
+	int bar;
+
+	bar = efx->type->mem_bar;
+	return resource_size(&efx->pci_dev->resource[bar]);
+}
+
+static int efx_ef10_get_pf_index(struct efx_nic *efx)
+{
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_FUNCTION_INFO_OUT_LEN);
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	size_t outlen;
+	int rc;
+
+	rc = efx_mcdi_rpc(efx, MC_CMD_GET_FUNCTION_INFO, NULL, 0, outbuf,
+			  sizeof(outbuf), &outlen);
+	if (rc)
+		return rc;
+	if (outlen < sizeof(outbuf))
+		return -EIO;
+
+	nic_data->pf_index = MCDI_DWORD(outbuf, GET_FUNCTION_INFO_OUT_PF);
+	return 0;
+}
+
+#ifdef CONFIG_SFC_SRIOV
+static int efx_ef10_get_vf_index(struct efx_nic *efx)
+{
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_FUNCTION_INFO_OUT_LEN);
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	size_t outlen;
+	int rc;
+
+	rc = efx_mcdi_rpc(efx, MC_CMD_GET_FUNCTION_INFO, NULL, 0, outbuf,
+			  sizeof(outbuf), &outlen);
+	if (rc)
+		return rc;
+	if (outlen < sizeof(outbuf))
+		return -EIO;
+
+	nic_data->vf_index = MCDI_DWORD(outbuf, GET_FUNCTION_INFO_OUT_VF);
+	return 0;
 }
+#endif
 
 static int efx_ef10_init_datapath_caps(struct efx_nic *efx)
 {
@@ -117,6 +161,13 @@ static int efx_ef10_init_datapath_caps(struct efx_nic *efx)
 	nic_data->datapath_caps =
 		MCDI_DWORD(outbuf, GET_CAPABILITIES_OUT_FLAGS1);
 
+	/* record the DPCPU firmware IDs to determine VEB vswitching support.
+	 */
+	nic_data->rx_dpcpu_fw_id =
+		MCDI_WORD(outbuf, GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID);
+	nic_data->tx_dpcpu_fw_id =
+		MCDI_WORD(outbuf, GET_CAPABILITIES_OUT_TX_DPCPU_FW_ID);
+
 	if (!(nic_data->datapath_caps &
 	      (1 << MC_CMD_GET_CAPABILITIES_OUT_TX_TSO_LBN))) {
 		netif_err(efx, drv, efx->net_dev,
@@ -147,7 +198,7 @@ static int efx_ef10_get_sysclk_freq(struct efx_nic *efx)
 	return rc > 0 ? rc : -ERANGE;
 }
 
-static int efx_ef10_get_mac_address(struct efx_nic *efx, u8 *mac_address)
+static int efx_ef10_get_mac_address_pf(struct efx_nic *efx, u8 *mac_address)
 {
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_MAC_ADDRESSES_OUT_LEN);
 	size_t outlen;
@@ -167,9 +218,66 @@ static int efx_ef10_get_mac_address(struct efx_nic *efx, u8 *mac_address)
 	return 0;
 }
 
+static int efx_ef10_get_mac_address_vf(struct efx_nic *efx, u8 *mac_address)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_GET_MAC_ADDRESSES_IN_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_LENMAX);
+	size_t outlen;
+	int num_addrs, rc;
+
+	MCDI_SET_DWORD(inbuf, VPORT_GET_MAC_ADDRESSES_IN_VPORT_ID,
+		       EVB_PORT_ID_ASSIGNED);
+	rc = efx_mcdi_rpc(efx, MC_CMD_VPORT_GET_MAC_ADDRESSES, inbuf,
+			  sizeof(inbuf), outbuf, sizeof(outbuf), &outlen);
+
+	if (rc)
+		return rc;
+	if (outlen < MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_LENMIN)
+		return -EIO;
+
+	num_addrs = MCDI_DWORD(outbuf,
+			       VPORT_GET_MAC_ADDRESSES_OUT_MACADDR_COUNT);
+
+	WARN_ON(num_addrs != 1);
+
+	ether_addr_copy(mac_address,
+			MCDI_PTR(outbuf, VPORT_GET_MAC_ADDRESSES_OUT_MACADDR));
+
+	return 0;
+}
+
+static ssize_t efx_ef10_show_link_control_flag(struct device *dev,
+					       struct device_attribute *attr,
+					       char *buf)
+{
+	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
+
+	return sprintf(buf, "%d\n",
+		       ((efx->mcdi->fn_flags) &
+			(1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL))
+		       ? 1 : 0);
+}
+
+static ssize_t efx_ef10_show_primary_flag(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
+
+	return sprintf(buf, "%d\n",
+		       ((efx->mcdi->fn_flags) &
+			(1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY))
+		       ? 1 : 0);
+}
+
+static DEVICE_ATTR(link_control_flag, 0444, efx_ef10_show_link_control_flag,
+		   NULL);
+static DEVICE_ATTR(primary_flag, 0444, efx_ef10_show_primary_flag, NULL);
+
 static int efx_ef10_probe(struct efx_nic *efx)
 {
 	struct efx_ef10_nic_data *nic_data;
+	struct net_device *net_dev = efx->net_dev;
 	int i, rc;
 
 	/* We can have one VI for each 8K region.  However, until we
@@ -178,7 +286,7 @@ static int efx_ef10_probe(struct efx_nic *efx)
 	efx->max_channels =
 		min_t(unsigned int,
 		      EFX_MAX_CHANNELS,
-		      resource_size(&efx->pci_dev->resource[EFX_MEM_BAR]) /
+		      efx_ef10_mem_map_size(efx) /
 		      (EFX_VI_PAGE_SIZE * EFX_TXQ_TYPES));
 	if (WARN_ON(efx->max_channels == 0))
 		return -EIO;
@@ -188,6 +296,9 @@ static int efx_ef10_probe(struct efx_nic *efx)
 		return -ENOMEM;
 	efx->nic_data = nic_data;
 
+	/* we assume later that we can copy from this buffer in dwords */
+	BUILD_BUG_ON(MCDI_CTL_SDU_LEN_MAX_V2 % 4);
+
 	rc = efx_nic_alloc_buffer(efx, &nic_data->mcdi_buf,
 				  8 + MCDI_CTL_SDU_LEN_MAX_V2, GFP_KERNEL);
 	if (rc)
@@ -209,6 +320,8 @@ static int efx_ef10_probe(struct efx_nic *efx)
 
 	nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
 
+	nic_data->vport_id = EVB_PORT_ID_ASSIGNED;
+
 	/* In case we're recovering from a crash (kexec), we want to
 	 * cancel any outstanding request by the previous user of this
 	 * function.  We send a special message using the least
@@ -230,45 +343,85 @@ static int efx_ef10_probe(struct efx_nic *efx)
 	if (rc)
 		goto fail3;
 
+	rc = device_create_file(&efx->pci_dev->dev,
+				&dev_attr_link_control_flag);
+	if (rc)
+		goto fail3;
+
+	rc = device_create_file(&efx->pci_dev->dev, &dev_attr_primary_flag);
+	if (rc)
+		goto fail4;
+
+	rc = efx_ef10_get_pf_index(efx);
+	if (rc)
+		goto fail5;
+
 	rc = efx_ef10_init_datapath_caps(efx);
 	if (rc < 0)
-		goto fail3;
+		goto fail5;
 
 	efx->rx_packet_len_offset =
 		ES_DZ_RX_PREFIX_PKTLEN_OFST - ES_DZ_RX_PREFIX_SIZE;
 
 	rc = efx_mcdi_port_get_number(efx);
 	if (rc < 0)
-		goto fail3;
+		goto fail5;
 	efx->port_num = rc;
+	net_dev->dev_port = rc;
 
-	rc = efx_ef10_get_mac_address(efx, efx->net_dev->perm_addr);
+	rc = efx->type->get_mac_address(efx, efx->net_dev->perm_addr);
 	if (rc)
-		goto fail3;
+		goto fail5;
 
 	rc = efx_ef10_get_sysclk_freq(efx);
 	if (rc < 0)
-		goto fail3;
+		goto fail5;
 	efx->timer_quantum_ns = 1536000 / rc; /* 1536 cycles */
 
-	/* Check whether firmware supports bug 35388 workaround */
+	/* Check whether firmware supports bug 35388 workaround.
+	 * First try to enable it, then if we get EPERM, just
+	 * ask if it's already enabled
+	 */
 	rc = efx_mcdi_set_workaround(efx, MC_CMD_WORKAROUND_BUG35388, true);
-	if (rc == 0)
+	if (rc == 0) {
 		nic_data->workaround_35388 = true;
-	else if (rc != -ENOSYS && rc != -ENOENT)
-		goto fail3;
+	} else if (rc == -EPERM) {
+		unsigned int enabled;
+
+		rc = efx_mcdi_get_workarounds(efx, NULL, &enabled);
+		if (rc)
+			goto fail3;
+		nic_data->workaround_35388 = enabled &
+			MC_CMD_GET_WORKAROUNDS_OUT_BUG35388;
+	} else if (rc != -ENOSYS && rc != -ENOENT) {
+		goto fail5;
+	}
 	netif_dbg(efx, probe, efx->net_dev,
 		  "workaround for bug 35388 is %sabled\n",
 		  nic_data->workaround_35388 ? "en" : "dis");
 
 	rc = efx_mcdi_mon_probe(efx);
-	if (rc)
-		goto fail3;
+	if (rc && rc != -EPERM)
+		goto fail5;
 
 	efx_ptp_probe(efx, NULL);
 
+#ifdef CONFIG_SFC_SRIOV
+	if ((efx->pci_dev->physfn) && (!efx->pci_dev->is_physfn)) {
+		struct pci_dev *pci_dev_pf = efx->pci_dev->physfn;
+		struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf);
+
+		efx_pf->type->get_mac_address(efx_pf, nic_data->port_id);
+	} else
+#endif
+		ether_addr_copy(nic_data->port_id, efx->net_dev->perm_addr);
+
 	return 0;
 
+fail5:
+	device_remove_file(&efx->pci_dev->dev, &dev_attr_primary_flag);
+fail4:
+	device_remove_file(&efx->pci_dev->dev, &dev_attr_link_control_flag);
 fail3:
 	efx_mcdi_fini(efx);
 fail2:
@@ -281,7 +434,7 @@ fail1:
 
 static int efx_ef10_free_vis(struct efx_nic *efx)
 {
-	MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, 0);
+	MCDI_DECLARE_BUF_ERR(outbuf);
 	size_t outlen;
 	int rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FREE_VIS, NULL, 0,
 				    outbuf, sizeof(outbuf), &outlen);
@@ -352,9 +505,9 @@ static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
 static int efx_ef10_link_piobufs(struct efx_nic *efx)
 {
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
-	MCDI_DECLARE_BUF(inbuf,
-			 max(MC_CMD_LINK_PIOBUF_IN_LEN,
-			     MC_CMD_UNLINK_PIOBUF_IN_LEN));
+	_MCDI_DECLARE_BUF(inbuf,
+			  max(MC_CMD_LINK_PIOBUF_IN_LEN,
+			      MC_CMD_UNLINK_PIOBUF_IN_LEN));
 	struct efx_channel *channel;
 	struct efx_tx_queue *tx_queue;
 	unsigned int offset, index;
@@ -363,6 +516,8 @@ static int efx_ef10_link_piobufs(struct efx_nic *efx)
 	BUILD_BUG_ON(MC_CMD_LINK_PIOBUF_OUT_LEN != 0);
 	BUILD_BUG_ON(MC_CMD_UNLINK_PIOBUF_OUT_LEN != 0);
 
+	memset(inbuf, 0, sizeof(inbuf));
+
 	/* Link a buffer to each VI in the write-combining mapping */
 	for (index = 0; index < nic_data->n_piobufs; ++index) {
 		MCDI_SET_DWORD(inbuf, LINK_PIOBUF_IN_PIOBUF_HANDLE,
@@ -475,6 +630,25 @@ static void efx_ef10_remove(struct efx_nic *efx)
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	int rc;
 
+#ifdef CONFIG_SFC_SRIOV
+	struct efx_ef10_nic_data *nic_data_pf;
+	struct pci_dev *pci_dev_pf;
+	struct efx_nic *efx_pf;
+	struct ef10_vf *vf;
+
+	if (efx->pci_dev->is_virtfn) {
+		pci_dev_pf = efx->pci_dev->physfn;
+		if (pci_dev_pf) {
+			efx_pf = pci_get_drvdata(pci_dev_pf);
+			nic_data_pf = efx_pf->nic_data;
+			vf = nic_data_pf->vf + nic_data->vf_index;
+			vf->efx = NULL;
+		} else
+			netif_info(efx, drv, efx->net_dev,
+				   "Could not get the PF id from VF\n");
+	}
+#endif
+
 	efx_ptp_remove(efx);
 
 	efx_mcdi_mon_remove(efx);
@@ -490,11 +664,78 @@ static void efx_ef10_remove(struct efx_nic *efx)
 	if (!nic_data->must_restore_piobufs)
 		efx_ef10_free_piobufs(efx);
 
+	device_remove_file(&efx->pci_dev->dev, &dev_attr_primary_flag);
+	device_remove_file(&efx->pci_dev->dev, &dev_attr_link_control_flag);
+
 	efx_mcdi_fini(efx);
 	efx_nic_free_buffer(efx, &nic_data->mcdi_buf);
 	kfree(nic_data);
 }
 
+static int efx_ef10_probe_pf(struct efx_nic *efx)
+{
+	return efx_ef10_probe(efx);
+}
+
+#ifdef CONFIG_SFC_SRIOV
+static int efx_ef10_probe_vf(struct efx_nic *efx)
+{
+	int rc;
+	struct pci_dev *pci_dev_pf;
+
+	/* If the parent PF has no VF data structure, it doesn't know about this
+	 * VF so fail probe.  The VF needs to be re-created.  This can happen
+	 * if the PF driver is unloaded while the VF is assigned to a guest.
+	 */
+	pci_dev_pf = efx->pci_dev->physfn;
+	if (pci_dev_pf) {
+		struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf);
+		struct efx_ef10_nic_data *nic_data_pf = efx_pf->nic_data;
+
+		if (!nic_data_pf->vf) {
+			netif_info(efx, drv, efx->net_dev,
+				   "The VF cannot link to its parent PF; "
+				   "please destroy and re-create the VF\n");
+			return -EBUSY;
+		}
+	}
+
+	rc = efx_ef10_probe(efx);
+	if (rc)
+		return rc;
+
+	rc = efx_ef10_get_vf_index(efx);
+	if (rc)
+		goto fail;
+
+	if (efx->pci_dev->is_virtfn) {
+		if (efx->pci_dev->physfn) {
+			struct efx_nic *efx_pf =
+				pci_get_drvdata(efx->pci_dev->physfn);
+			struct efx_ef10_nic_data *nic_data_p = efx_pf->nic_data;
+			struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+			nic_data_p->vf[nic_data->vf_index].efx = efx;
+			nic_data_p->vf[nic_data->vf_index].pci_dev =
+				efx->pci_dev;
+		} else
+			netif_info(efx, drv, efx->net_dev,
+				   "Could not get the PF id from VF\n");
+	}
+
+	return 0;
+
+fail:
+	efx_ef10_remove(efx);
+	return rc;
+}
+#else
+static int efx_ef10_probe_vf(struct efx_nic *efx __attribute__ ((unused)))
+{
+	return 0;
+}
+#endif
+
 static int efx_ef10_alloc_vis(struct efx_nic *efx,
 			      unsigned int min_vis, unsigned int max_vis)
 {
@@ -687,7 +928,9 @@ static int efx_ef10_init_nic(struct efx_nic *efx)
 		nic_data->must_restore_piobufs = false;
 	}
 
-	efx_ef10_rx_push_rss_config(efx);
+	/* don't fail init if RSS setup doesn't work */
+	efx->type->rx_push_rss_config(efx, false, efx->rx_indir_table);
+
 	return 0;
 }
 
@@ -702,6 +945,14 @@ static void efx_ef10_reset_mc_allocations(struct efx_nic *efx)
 	nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
 }
 
+static enum reset_type efx_ef10_map_reset_reason(enum reset_type reason)
+{
+	if (reason == RESET_TYPE_MC_FAILURE)
+		return RESET_TYPE_DATAPATH;
+
+	return efx_mcdi_map_reset_reason(reason);
+}
+
 static int efx_ef10_map_reset_flags(u32 *flags)
 {
 	enum {
@@ -760,93 +1011,112 @@ static int efx_ef10_reset(struct efx_nic *efx, enum reset_type reset_type)
 	[GENERIC_STAT_ ## ext_name] = { #ext_name, 0, 0 }
 
 static const struct efx_hw_stat_desc efx_ef10_stat_desc[EF10_STAT_COUNT] = {
-	EF10_DMA_STAT(tx_bytes, TX_BYTES),
-	EF10_DMA_STAT(tx_packets, TX_PKTS),
-	EF10_DMA_STAT(tx_pause, TX_PAUSE_PKTS),
-	EF10_DMA_STAT(tx_control, TX_CONTROL_PKTS),
-	EF10_DMA_STAT(tx_unicast, TX_UNICAST_PKTS),
-	EF10_DMA_STAT(tx_multicast, TX_MULTICAST_PKTS),
-	EF10_DMA_STAT(tx_broadcast, TX_BROADCAST_PKTS),
-	EF10_DMA_STAT(tx_lt64, TX_LT64_PKTS),
-	EF10_DMA_STAT(tx_64, TX_64_PKTS),
-	EF10_DMA_STAT(tx_65_to_127, TX_65_TO_127_PKTS),
-	EF10_DMA_STAT(tx_128_to_255, TX_128_TO_255_PKTS),
-	EF10_DMA_STAT(tx_256_to_511, TX_256_TO_511_PKTS),
-	EF10_DMA_STAT(tx_512_to_1023, TX_512_TO_1023_PKTS),
-	EF10_DMA_STAT(tx_1024_to_15xx, TX_1024_TO_15XX_PKTS),
-	EF10_DMA_STAT(tx_15xx_to_jumbo, TX_15XX_TO_JUMBO_PKTS),
-	EF10_DMA_STAT(rx_bytes, RX_BYTES),
-	EF10_DMA_INVIS_STAT(rx_bytes_minus_good_bytes, RX_BAD_BYTES),
-	EF10_OTHER_STAT(rx_good_bytes),
-	EF10_OTHER_STAT(rx_bad_bytes),
-	EF10_DMA_STAT(rx_packets, RX_PKTS),
-	EF10_DMA_STAT(rx_good, RX_GOOD_PKTS),
-	EF10_DMA_STAT(rx_bad, RX_BAD_FCS_PKTS),
-	EF10_DMA_STAT(rx_pause, RX_PAUSE_PKTS),
-	EF10_DMA_STAT(rx_control, RX_CONTROL_PKTS),
-	EF10_DMA_STAT(rx_unicast, RX_UNICAST_PKTS),
-	EF10_DMA_STAT(rx_multicast, RX_MULTICAST_PKTS),
-	EF10_DMA_STAT(rx_broadcast, RX_BROADCAST_PKTS),
-	EF10_DMA_STAT(rx_lt64, RX_UNDERSIZE_PKTS),
-	EF10_DMA_STAT(rx_64, RX_64_PKTS),
-	EF10_DMA_STAT(rx_65_to_127, RX_65_TO_127_PKTS),
-	EF10_DMA_STAT(rx_128_to_255, RX_128_TO_255_PKTS),
-	EF10_DMA_STAT(rx_256_to_511, RX_256_TO_511_PKTS),
-	EF10_DMA_STAT(rx_512_to_1023, RX_512_TO_1023_PKTS),
-	EF10_DMA_STAT(rx_1024_to_15xx, RX_1024_TO_15XX_PKTS),
-	EF10_DMA_STAT(rx_15xx_to_jumbo, RX_15XX_TO_JUMBO_PKTS),
-	EF10_DMA_STAT(rx_gtjumbo, RX_GTJUMBO_PKTS),
-	EF10_DMA_STAT(rx_bad_gtjumbo, RX_JABBER_PKTS),
-	EF10_DMA_STAT(rx_overflow, RX_OVERFLOW_PKTS),
-	EF10_DMA_STAT(rx_align_error, RX_ALIGN_ERROR_PKTS),
-	EF10_DMA_STAT(rx_length_error, RX_LENGTH_ERROR_PKTS),
-	EF10_DMA_STAT(rx_nodesc_drops, RX_NODESC_DROPS),
+	EF10_DMA_STAT(port_tx_bytes, TX_BYTES),
+	EF10_DMA_STAT(port_tx_packets, TX_PKTS),
+	EF10_DMA_STAT(port_tx_pause, TX_PAUSE_PKTS),
+	EF10_DMA_STAT(port_tx_control, TX_CONTROL_PKTS),
+	EF10_DMA_STAT(port_tx_unicast, TX_UNICAST_PKTS),
+	EF10_DMA_STAT(port_tx_multicast, TX_MULTICAST_PKTS),
+	EF10_DMA_STAT(port_tx_broadcast, TX_BROADCAST_PKTS),
+	EF10_DMA_STAT(port_tx_lt64, TX_LT64_PKTS),
+	EF10_DMA_STAT(port_tx_64, TX_64_PKTS),
+	EF10_DMA_STAT(port_tx_65_to_127, TX_65_TO_127_PKTS),
+	EF10_DMA_STAT(port_tx_128_to_255, TX_128_TO_255_PKTS),
+	EF10_DMA_STAT(port_tx_256_to_511, TX_256_TO_511_PKTS),
+	EF10_DMA_STAT(port_tx_512_to_1023, TX_512_TO_1023_PKTS),
+	EF10_DMA_STAT(port_tx_1024_to_15xx, TX_1024_TO_15XX_PKTS),
+	EF10_DMA_STAT(port_tx_15xx_to_jumbo, TX_15XX_TO_JUMBO_PKTS),
+	EF10_DMA_STAT(port_rx_bytes, RX_BYTES),
+	EF10_DMA_INVIS_STAT(port_rx_bytes_minus_good_bytes, RX_BAD_BYTES),
+	EF10_OTHER_STAT(port_rx_good_bytes),
+	EF10_OTHER_STAT(port_rx_bad_bytes),
+	EF10_DMA_STAT(port_rx_packets, RX_PKTS),
+	EF10_DMA_STAT(port_rx_good, RX_GOOD_PKTS),
+	EF10_DMA_STAT(port_rx_bad, RX_BAD_FCS_PKTS),
+	EF10_DMA_STAT(port_rx_pause, RX_PAUSE_PKTS),
+	EF10_DMA_STAT(port_rx_control, RX_CONTROL_PKTS),
+	EF10_DMA_STAT(port_rx_unicast, RX_UNICAST_PKTS),
+	EF10_DMA_STAT(port_rx_multicast, RX_MULTICAST_PKTS),
+	EF10_DMA_STAT(port_rx_broadcast, RX_BROADCAST_PKTS),
+	EF10_DMA_STAT(port_rx_lt64, RX_UNDERSIZE_PKTS),
+	EF10_DMA_STAT(port_rx_64, RX_64_PKTS),
+	EF10_DMA_STAT(port_rx_65_to_127, RX_65_TO_127_PKTS),
+	EF10_DMA_STAT(port_rx_128_to_255, RX_128_TO_255_PKTS),
+	EF10_DMA_STAT(port_rx_256_to_511, RX_256_TO_511_PKTS),
+	EF10_DMA_STAT(port_rx_512_to_1023, RX_512_TO_1023_PKTS),
+	EF10_DMA_STAT(port_rx_1024_to_15xx, RX_1024_TO_15XX_PKTS),
+	EF10_DMA_STAT(port_rx_15xx_to_jumbo, RX_15XX_TO_JUMBO_PKTS),
+	EF10_DMA_STAT(port_rx_gtjumbo, RX_GTJUMBO_PKTS),
+	EF10_DMA_STAT(port_rx_bad_gtjumbo, RX_JABBER_PKTS),
+	EF10_DMA_STAT(port_rx_overflow, RX_OVERFLOW_PKTS),
+	EF10_DMA_STAT(port_rx_align_error, RX_ALIGN_ERROR_PKTS),
+	EF10_DMA_STAT(port_rx_length_error, RX_LENGTH_ERROR_PKTS),
+	EF10_DMA_STAT(port_rx_nodesc_drops, RX_NODESC_DROPS),
 	GENERIC_SW_STAT(rx_nodesc_trunc),
 	GENERIC_SW_STAT(rx_noskb_drops),
-	EF10_DMA_STAT(rx_pm_trunc_bb_overflow, PM_TRUNC_BB_OVERFLOW),
-	EF10_DMA_STAT(rx_pm_discard_bb_overflow, PM_DISCARD_BB_OVERFLOW),
-	EF10_DMA_STAT(rx_pm_trunc_vfifo_full, PM_TRUNC_VFIFO_FULL),
-	EF10_DMA_STAT(rx_pm_discard_vfifo_full, PM_DISCARD_VFIFO_FULL),
-	EF10_DMA_STAT(rx_pm_trunc_qbb, PM_TRUNC_QBB),
-	EF10_DMA_STAT(rx_pm_discard_qbb, PM_DISCARD_QBB),
-	EF10_DMA_STAT(rx_pm_discard_mapping, PM_DISCARD_MAPPING),
-	EF10_DMA_STAT(rx_dp_q_disabled_packets, RXDP_Q_DISABLED_PKTS),
-	EF10_DMA_STAT(rx_dp_di_dropped_packets, RXDP_DI_DROPPED_PKTS),
-	EF10_DMA_STAT(rx_dp_streaming_packets, RXDP_STREAMING_PKTS),
-	EF10_DMA_STAT(rx_dp_hlb_fetch, RXDP_EMERGENCY_FETCH_CONDITIONS),
-	EF10_DMA_STAT(rx_dp_hlb_wait, RXDP_EMERGENCY_WAIT_CONDITIONS),
+	EF10_DMA_STAT(port_rx_pm_trunc_bb_overflow, PM_TRUNC_BB_OVERFLOW),
+	EF10_DMA_STAT(port_rx_pm_discard_bb_overflow, PM_DISCARD_BB_OVERFLOW),
+	EF10_DMA_STAT(port_rx_pm_trunc_vfifo_full, PM_TRUNC_VFIFO_FULL),
+	EF10_DMA_STAT(port_rx_pm_discard_vfifo_full, PM_DISCARD_VFIFO_FULL),
+	EF10_DMA_STAT(port_rx_pm_trunc_qbb, PM_TRUNC_QBB),
+	EF10_DMA_STAT(port_rx_pm_discard_qbb, PM_DISCARD_QBB),
+	EF10_DMA_STAT(port_rx_pm_discard_mapping, PM_DISCARD_MAPPING),
+	EF10_DMA_STAT(port_rx_dp_q_disabled_packets, RXDP_Q_DISABLED_PKTS),
+	EF10_DMA_STAT(port_rx_dp_di_dropped_packets, RXDP_DI_DROPPED_PKTS),
+	EF10_DMA_STAT(port_rx_dp_streaming_packets, RXDP_STREAMING_PKTS),
+	EF10_DMA_STAT(port_rx_dp_hlb_fetch, RXDP_HLB_FETCH_CONDITIONS),
+	EF10_DMA_STAT(port_rx_dp_hlb_wait, RXDP_HLB_WAIT_CONDITIONS),
+	EF10_DMA_STAT(rx_unicast, VADAPTER_RX_UNICAST_PACKETS),
+	EF10_DMA_STAT(rx_unicast_bytes, VADAPTER_RX_UNICAST_BYTES),
+	EF10_DMA_STAT(rx_multicast, VADAPTER_RX_MULTICAST_PACKETS),
+	EF10_DMA_STAT(rx_multicast_bytes, VADAPTER_RX_MULTICAST_BYTES),
+	EF10_DMA_STAT(rx_broadcast, VADAPTER_RX_BROADCAST_PACKETS),
+	EF10_DMA_STAT(rx_broadcast_bytes, VADAPTER_RX_BROADCAST_BYTES),
+	EF10_DMA_STAT(rx_bad, VADAPTER_RX_BAD_PACKETS),
+	EF10_DMA_STAT(rx_bad_bytes, VADAPTER_RX_BAD_BYTES),
+	EF10_DMA_STAT(rx_overflow, VADAPTER_RX_OVERFLOW),
+	EF10_DMA_STAT(tx_unicast, VADAPTER_TX_UNICAST_PACKETS),
+	EF10_DMA_STAT(tx_unicast_bytes, VADAPTER_TX_UNICAST_BYTES),
+	EF10_DMA_STAT(tx_multicast, VADAPTER_TX_MULTICAST_PACKETS),
+	EF10_DMA_STAT(tx_multicast_bytes, VADAPTER_TX_MULTICAST_BYTES),
+	EF10_DMA_STAT(tx_broadcast, VADAPTER_TX_BROADCAST_PACKETS),
+	EF10_DMA_STAT(tx_broadcast_bytes, VADAPTER_TX_BROADCAST_BYTES),
+	EF10_DMA_STAT(tx_bad, VADAPTER_TX_BAD_PACKETS),
+	EF10_DMA_STAT(tx_bad_bytes, VADAPTER_TX_BAD_BYTES),
+	EF10_DMA_STAT(tx_overflow, VADAPTER_TX_OVERFLOW),
 };
 
-#define HUNT_COMMON_STAT_MASK ((1ULL << EF10_STAT_tx_bytes) |		\
-			       (1ULL << EF10_STAT_tx_packets) |		\
-			       (1ULL << EF10_STAT_tx_pause) |		\
-			       (1ULL << EF10_STAT_tx_unicast) |		\
-			       (1ULL << EF10_STAT_tx_multicast) |	\
-			       (1ULL << EF10_STAT_tx_broadcast) |	\
-			       (1ULL << EF10_STAT_rx_bytes) |		\
-			       (1ULL << EF10_STAT_rx_bytes_minus_good_bytes) | \
-			       (1ULL << EF10_STAT_rx_good_bytes) |	\
-			       (1ULL << EF10_STAT_rx_bad_bytes) |	\
-			       (1ULL << EF10_STAT_rx_packets) |		\
-			       (1ULL << EF10_STAT_rx_good) |		\
-			       (1ULL << EF10_STAT_rx_bad) |		\
-			       (1ULL << EF10_STAT_rx_pause) |		\
-			       (1ULL << EF10_STAT_rx_control) |		\
-			       (1ULL << EF10_STAT_rx_unicast) |		\
-			       (1ULL << EF10_STAT_rx_multicast) |	\
-			       (1ULL << EF10_STAT_rx_broadcast) |	\
-			       (1ULL << EF10_STAT_rx_lt64) |		\
-			       (1ULL << EF10_STAT_rx_64) |		\
-			       (1ULL << EF10_STAT_rx_65_to_127) |	\
-			       (1ULL << EF10_STAT_rx_128_to_255) |	\
-			       (1ULL << EF10_STAT_rx_256_to_511) |	\
-			       (1ULL << EF10_STAT_rx_512_to_1023) |	\
-			       (1ULL << EF10_STAT_rx_1024_to_15xx) |	\
-			       (1ULL << EF10_STAT_rx_15xx_to_jumbo) |	\
-			       (1ULL << EF10_STAT_rx_gtjumbo) |		\
-			       (1ULL << EF10_STAT_rx_bad_gtjumbo) |	\
-			       (1ULL << EF10_STAT_rx_overflow) |	\
-			       (1ULL << EF10_STAT_rx_nodesc_drops) |	\
+#define HUNT_COMMON_STAT_MASK ((1ULL << EF10_STAT_port_tx_bytes) |	\
+			       (1ULL << EF10_STAT_port_tx_packets) |	\
+			       (1ULL << EF10_STAT_port_tx_pause) |	\
+			       (1ULL << EF10_STAT_port_tx_unicast) |	\
+			       (1ULL << EF10_STAT_port_tx_multicast) |	\
+			       (1ULL << EF10_STAT_port_tx_broadcast) |	\
+			       (1ULL << EF10_STAT_port_rx_bytes) |	\
+			       (1ULL <<                                 \
+				EF10_STAT_port_rx_bytes_minus_good_bytes) | \
+			       (1ULL << EF10_STAT_port_rx_good_bytes) |	\
+			       (1ULL << EF10_STAT_port_rx_bad_bytes) |	\
+			       (1ULL << EF10_STAT_port_rx_packets) |	\
+			       (1ULL << EF10_STAT_port_rx_good) |	\
+			       (1ULL << EF10_STAT_port_rx_bad) |	\
+			       (1ULL << EF10_STAT_port_rx_pause) |	\
+			       (1ULL << EF10_STAT_port_rx_control) |	\
+			       (1ULL << EF10_STAT_port_rx_unicast) |	\
+			       (1ULL << EF10_STAT_port_rx_multicast) |	\
+			       (1ULL << EF10_STAT_port_rx_broadcast) |	\
+			       (1ULL << EF10_STAT_port_rx_lt64) |	\
+			       (1ULL << EF10_STAT_port_rx_64) |		\
+			       (1ULL << EF10_STAT_port_rx_65_to_127) |	\
+			       (1ULL << EF10_STAT_port_rx_128_to_255) |	\
+			       (1ULL << EF10_STAT_port_rx_256_to_511) |	\
+			       (1ULL << EF10_STAT_port_rx_512_to_1023) |\
+			       (1ULL << EF10_STAT_port_rx_1024_to_15xx) |\
+			       (1ULL << EF10_STAT_port_rx_15xx_to_jumbo) |\
+			       (1ULL << EF10_STAT_port_rx_gtjumbo) |	\
+			       (1ULL << EF10_STAT_port_rx_bad_gtjumbo) |\
+			       (1ULL << EF10_STAT_port_rx_overflow) |	\
+			       (1ULL << EF10_STAT_port_rx_nodesc_drops) |\
 			       (1ULL << GENERIC_STAT_rx_nodesc_trunc) |	\
 			       (1ULL << GENERIC_STAT_rx_noskb_drops))
 
@@ -854,39 +1124,39 @@ static const struct efx_hw_stat_desc efx_ef10_stat_desc[EF10_STAT_COUNT] = {
  * switchable port we do not expose these because they might not
  * include all the packets they should.
  */
-#define HUNT_10G_ONLY_STAT_MASK ((1ULL << EF10_STAT_tx_control) |	\
-				 (1ULL << EF10_STAT_tx_lt64) |		\
-				 (1ULL << EF10_STAT_tx_64) |		\
-				 (1ULL << EF10_STAT_tx_65_to_127) |	\
-				 (1ULL << EF10_STAT_tx_128_to_255) |	\
-				 (1ULL << EF10_STAT_tx_256_to_511) |	\
-				 (1ULL << EF10_STAT_tx_512_to_1023) |	\
-				 (1ULL << EF10_STAT_tx_1024_to_15xx) |	\
-				 (1ULL << EF10_STAT_tx_15xx_to_jumbo))
+#define HUNT_10G_ONLY_STAT_MASK ((1ULL << EF10_STAT_port_tx_control) |	\
+				 (1ULL << EF10_STAT_port_tx_lt64) |	\
+				 (1ULL << EF10_STAT_port_tx_64) |	\
+				 (1ULL << EF10_STAT_port_tx_65_to_127) |\
+				 (1ULL << EF10_STAT_port_tx_128_to_255) |\
+				 (1ULL << EF10_STAT_port_tx_256_to_511) |\
+				 (1ULL << EF10_STAT_port_tx_512_to_1023) |\
+				 (1ULL << EF10_STAT_port_tx_1024_to_15xx) |\
+				 (1ULL << EF10_STAT_port_tx_15xx_to_jumbo))
 
 /* These statistics are only provided by the 40G MAC.  For a 10G/40G
  * switchable port we do expose these because the errors will otherwise
  * be silent.
  */
-#define HUNT_40G_EXTRA_STAT_MASK ((1ULL << EF10_STAT_rx_align_error) |	\
-				  (1ULL << EF10_STAT_rx_length_error))
+#define HUNT_40G_EXTRA_STAT_MASK ((1ULL << EF10_STAT_port_rx_align_error) |\
+				  (1ULL << EF10_STAT_port_rx_length_error))
 
 /* These statistics are only provided if the firmware supports the
  * capability PM_AND_RXDP_COUNTERS.
  */
 #define HUNT_PM_AND_RXDP_STAT_MASK (					\
-	(1ULL << EF10_STAT_rx_pm_trunc_bb_overflow) |			\
-	(1ULL << EF10_STAT_rx_pm_discard_bb_overflow) |			\
-	(1ULL << EF10_STAT_rx_pm_trunc_vfifo_full) |			\
-	(1ULL << EF10_STAT_rx_pm_discard_vfifo_full) |			\
-	(1ULL << EF10_STAT_rx_pm_trunc_qbb) |				\
-	(1ULL << EF10_STAT_rx_pm_discard_qbb) |				\
-	(1ULL << EF10_STAT_rx_pm_discard_mapping) |			\
-	(1ULL << EF10_STAT_rx_dp_q_disabled_packets) |			\
-	(1ULL << EF10_STAT_rx_dp_di_dropped_packets) |			\
-	(1ULL << EF10_STAT_rx_dp_streaming_packets) |			\
-	(1ULL << EF10_STAT_rx_dp_hlb_fetch) |				\
-	(1ULL << EF10_STAT_rx_dp_hlb_wait))
+	(1ULL << EF10_STAT_port_rx_pm_trunc_bb_overflow) |		\
+	(1ULL << EF10_STAT_port_rx_pm_discard_bb_overflow) |		\
+	(1ULL << EF10_STAT_port_rx_pm_trunc_vfifo_full) |		\
+	(1ULL << EF10_STAT_port_rx_pm_discard_vfifo_full) |		\
+	(1ULL << EF10_STAT_port_rx_pm_trunc_qbb) |			\
+	(1ULL << EF10_STAT_port_rx_pm_discard_qbb) |			\
+	(1ULL << EF10_STAT_port_rx_pm