Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue

Jeff Kirsher says:

====================
40GbE Intel Wired LAN Driver Updates 2017-03-15

This series contains updates to i40e and i40evf only.

Aaron fixes an issue on x710 devices where simultaneous read accesses
were interfering with each other, so make sure all devices acquire the
NVM lock before reads on all devices.

Shannon adds Wake On LAN support feature for x722 devices and cleaned
up the opcodes so that they are in numerical order.

Mitch adds a client interface to the VF driver, in preparation for the
upcoming RDMA-capable hardware (and client driver).  Cleaned up the
client interface in the PF driver, since it was originally over
engineered to handle multiple clients on multiple netdevs, but that
did not happen and now there will be one client per driver, so apply
the "KISS" (Keep It Simple & Stupid) to the i40e client interface.
Bumped the number of MAC filters an untrusted VF can create.

Jake fixes an issue where a recent refactor of queue pairs accidentally
added all remaining vecotrs to the num_lan_msix which can adversely
affect performance.

Lihong fixes an ethtool issue with x722 devices where "-e" will error
out since its EEPROM has a scope limit at offset 0x5B9FFF, so set the
EEPROM length to the scope limit.  Also fixed an issue where RSS
offloading only worked on PF0.

Filip cleans up and clarifies code comment so there is no confusion
about MAC/VLAN filter initialization routine.

Alex adds support for DMA_ATTR_SKIP_CPU_SYNC and DMA_ATTR_WEAK_ORDERING,
which improves performance on architectures that implement either one.

Harshitha cleans up confusion on flags disabled due to hardware limitation
versus featured disabled by the user, so rename auto_disable_flags to
hw_disabled_flags to avoid the confusion.

v2: Merged patch #1 and #4 in first version to make patch #3 in this
    series based on feedback from David Miller.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/i40e/i40e.h

@@ -348,16 +348,23 @@ struct i40e_pf {
 #define I40E_FLAG_TRUE_PROMISC_SUPPORT		BIT_ULL(51)
 #define I40E_FLAG_HAVE_CRT_RETIMER		BIT_ULL(52)
 #define I40E_FLAG_PTP_L4_CAPABLE		BIT_ULL(53)
-#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE		BIT_ULL(54)
+#define I40E_FLAG_CLIENT_RESET			BIT_ULL(54)
 #define I40E_FLAG_TEMP_LINK_POLLING		BIT_ULL(55)
+#define I40E_FLAG_CLIENT_L2_CHANGE		BIT_ULL(56)
+#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE		BIT_ULL(57)
 
-	/* tracks features that get auto disabled by errors */
-	u64 auto_disable_flags;
+	/* Tracks features that are disabled due to hw limitations.
+	 * If a bit is set here, it means that the corresponding
+	 * bit in the 'flags' field is cleared i.e that feature
+	 * is disabled
+	 */
+	u64 hw_disabled_flags;
 
 #ifdef I40E_FCOE
 	struct i40e_fcoe fcoe;
 
 #endif /* I40E_FCOE */
+	struct i40e_client_instance *cinst;
 	bool stat_offsets_loaded;
 	struct i40e_hw_port_stats stats;
 	struct i40e_hw_port_stats stats_offsets;
@@ -813,8 +820,7 @@ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi);
 void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset);
 void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs);
 void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id);
-int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id,
-			   enum i40e_client_type type);
+int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id);
 /**
  * i40e_irq_dynamic_enable - Enable default interrupt generation settings
  * @vsi: pointer to a vsi

drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h

@@ -132,6 +132,10 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_list_func_capabilities	= 0x000A,
 	i40e_aqc_opc_list_dev_capabilities	= 0x000B,
 
+	/* Proxy commands */
+	i40e_aqc_opc_set_proxy_config		= 0x0104,
+	i40e_aqc_opc_set_ns_proxy_table_entry	= 0x0105,
+
 	/* LAA */
 	i40e_aqc_opc_mac_address_read	= 0x0107,
 	i40e_aqc_opc_mac_address_write	= 0x0108,
@@ -139,6 +143,10 @@ enum i40e_admin_queue_opc {
 	/* PXE */
 	i40e_aqc_opc_clear_pxe_mode	= 0x0110,
 
+	/* WoL commands */
+	i40e_aqc_opc_set_wol_filter	= 0x0120,
+	i40e_aqc_opc_get_wake_reason	= 0x0121,
+
 	/* internal switch commands */
 	i40e_aqc_opc_get_switch_config		= 0x0200,
 	i40e_aqc_opc_add_statistics		= 0x0201,
@@ -177,6 +185,7 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_remove_control_packet_filter	= 0x025B,
 	i40e_aqc_opc_add_cloud_filters		= 0x025C,
 	i40e_aqc_opc_remove_cloud_filters	= 0x025D,
+	i40e_aqc_opc_clear_wol_switch_filters	= 0x025E,
 
 	i40e_aqc_opc_add_mirror_rule	= 0x0260,
 	i40e_aqc_opc_delete_mirror_rule	= 0x0261,
@@ -563,6 +572,56 @@ struct i40e_aqc_clear_pxe {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe);
 
+/* Set WoL Filter (0x0120) */
+
+struct i40e_aqc_set_wol_filter {
+	__le16 filter_index;
+#define I40E_AQC_MAX_NUM_WOL_FILTERS	8
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT	15
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK	(0x1 << \
+		I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT)
+
+#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT		0
+#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK	(0x7 << \
+		I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT)
+	__le16 cmd_flags;
+#define I40E_AQC_SET_WOL_FILTER				0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL		0x4000
+#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR		0
+#define I40E_AQC_SET_WOL_FILTER_ACTION_SET		1
+	__le16 valid_flags;
+#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID		0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID	0x4000
+	u8 reserved[2];
+	__le32	address_high;
+	__le32	address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter);
+
+struct i40e_aqc_set_wol_filter_data {
+	u8 filter[128];
+	u8 mask[16];
+};
+
+I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data);
+
+/* Get Wake Reason (0x0121) */
+
+struct i40e_aqc_get_wake_reason_completion {
+	u8 reserved_1[2];
+	__le16 wake_reason;
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT	0
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \
+		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT)
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT	8
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK	(0xFF << \
+		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT)
+	u8 reserved_2[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion);
+
 /* Switch configuration commands (0x02xx) */
 
 /* Used by many indirect commands that only pass an seid and a buffer in the
@@ -645,6 +704,8 @@ struct i40e_aqc_set_port_parameters {
 #define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS	2 /* must set! */
 #define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA	4
 	__le16	bad_frame_vsi;
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT	0x0
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK	0x3FF
 	__le16	default_seid;        /* reserved for command */
 	u8	reserved[10];
 };
@@ -696,6 +757,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp);
 /* Set Switch Configuration (direct 0x0205) */
 struct i40e_aqc_set_switch_config {
 	__le16	flags;
+/* flags used for both fields below */
 #define I40E_AQ_SET_SWITCH_CFG_PROMISC		0x0001
 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER	0x0002
 	__le16	valid_flags;
@@ -1844,11 +1906,12 @@ struct i40e_aqc_get_link_status {
 #define I40E_AQ_CONFIG_FEC_RS_ENA	0x02
 #define I40E_AQ_CONFIG_CRC_ENA		0x04
 #define I40E_AQ_CONFIG_PACING_MASK	0x78
-	u8	external_power_ability;
+	u8	power_desc;
 #define I40E_AQ_LINK_POWER_CLASS_1	0x00
 #define I40E_AQ_LINK_POWER_CLASS_2	0x01
 #define I40E_AQ_LINK_POWER_CLASS_3	0x02
 #define I40E_AQ_LINK_POWER_CLASS_4	0x03
+#define I40E_AQ_PWR_CLASS_MASK		0x03
 	u8	reserved[4];
 };
 

drivers/net/ethernet/intel/i40e/i40e_client.h

@@ -57,11 +57,6 @@ enum i40e_client_instance_state {
 	__I40E_CLIENT_INSTANCE_OPENED,
 };
 
-enum i40e_client_type {
-	I40E_CLIENT_IWARP,
-	I40E_CLIENT_VMDQ2
-};
-
 struct i40e_ops;
 struct i40e_client;
 
@@ -214,7 +209,8 @@ struct i40e_client {
 	u32 flags;
 #define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE	BIT(0)
 #define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS	BIT(2)
-	enum i40e_client_type type;
+	u8 type;
+#define I40E_CLIENT_IWARP 0
 	const struct i40e_client_ops *ops; /* client ops provided by the client */
 };
 

drivers/net/ethernet/intel/i40e/i40e_ethtool.c

@@ -1165,6 +1165,11 @@ static int i40e_get_eeprom_len(struct net_device *netdev)
 	struct i40e_hw *hw = &np->vsi->back->hw;
 	u32 val;
 
+#define X722_EEPROM_SCOPE_LIMIT 0x5B9FFF
+	if (hw->mac.type == I40E_MAC_X722) {
+		val = X722_EEPROM_SCOPE_LIMIT + 1;
+		return val;
+	}
 	val = (rd32(hw, I40E_GLPCI_LBARCTRL)
 		& I40E_GLPCI_LBARCTRL_FL_SIZE_MASK)
 		>> I40E_GLPCI_LBARCTRL_FL_SIZE_SHIFT;
@@ -2712,7 +2717,7 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 	if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
 		return -EOPNOTSUPP;
 
-	if (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)
+	if (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)
 		return -ENOSPC;
 
 	if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) ||
@@ -3054,7 +3059,7 @@ static u32 i40e_get_priv_flags(struct net_device *dev)
 		I40E_PRIV_FLAGS_FD_ATR : 0;
 	ret_flags |= pf->flags & I40E_FLAG_VEB_STATS_ENABLED ?
 		I40E_PRIV_FLAGS_VEB_STATS : 0;
-	ret_flags |= pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE ?
+	ret_flags |= pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE ?
 		0 : I40E_PRIV_FLAGS_HW_ATR_EVICT;
 	if (pf->hw.pf_id == 0) {
 		ret_flags |= pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT ?
@@ -3094,7 +3099,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 		pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
 	} else {
 		pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
-		pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
+		pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED;
 
 		/* flush current ATR settings */
 		set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
@@ -3139,9 +3144,9 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 
 	if ((flags & I40E_PRIV_FLAGS_HW_ATR_EVICT) &&
 	    (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))
-		pf->auto_disable_flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+		pf->hw_disabled_flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE;
 	else
-		pf->auto_disable_flags |= I40E_FLAG_HW_ATR_EVICT_CAPABLE;
+		pf->hw_disabled_flags |= I40E_FLAG_HW_ATR_EVICT_CAPABLE;
 
 	/* if needed, issue reset to cause things to take effect */
 	if (reset_required)

drivers/net/ethernet/intel/i40e/i40e_nvm.c

@@ -292,14 +292,14 @@ i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset,
 {
 	enum i40e_status_code ret_code = 0;
 
-	if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) {
-		ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
-		if (!ret_code) {
+	ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+	if (!ret_code) {
+		if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) {
 			ret_code = i40e_read_nvm_word_aq(hw, offset, data);
-			i40e_release_nvm(hw);
+		} else {
+			ret_code = i40e_read_nvm_word_srctl(hw, offset, data);
 		}
-	} else {
-		ret_code = i40e_read_nvm_word_srctl(hw, offset, data);
+		i40e_release_nvm(hw);
 	}
 	return ret_code;
 }

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -291,7 +291,7 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
 		    I40E_DEBUG_FD & pf->hw.debug_mask)
 			dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n");
-		pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
+		pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED;
 	} else {
 		pf->fd_tcp_rule = (pf->fd_tcp_rule > 0) ?
 				  (pf->fd_tcp_rule - 1) : 0;
@@ -299,7 +299,7 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 			if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
 			    I40E_DEBUG_FD & pf->hw.debug_mask)
 				dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n");
-			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+			pf->hw_disabled_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
 		}
 	}
 
@@ -484,8 +484,8 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 		pf->fd_atr_cnt = i40e_get_current_atr_cnt(pf);
 
 		if ((rx_desc->wb.qword0.hi_dword.fd_id == 0) &&
-		    (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) {
-			pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED;
+		    (pf->hw_disabled_flags & I40E_FLAG_FD_SB_ENABLED)) {
+			pf->hw_disabled_flags |= I40E_FLAG_FD_ATR_ENABLED;
 			set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
 		}
 
@@ -498,11 +498,11 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 		 */
 		if (fcnt_prog >= (fcnt_avail - I40E_FDIR_BUFFER_FULL_MARGIN)) {
 			if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
-			    !(pf->auto_disable_flags &
+			    !(pf->hw_disabled_flags &
 				     I40E_FLAG_FD_SB_ENABLED)) {
 				if (I40E_DEBUG_FD & pf->hw.debug_mask)
 					dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n");
-				pf->auto_disable_flags |=
+				pf->hw_disabled_flags |=
 							I40E_FLAG_FD_SB_ENABLED;
 			}
 		}
@@ -1010,7 +1010,6 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring)
  **/
 void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 {
-	struct device *dev = rx_ring->dev;
 	unsigned long bi_size;
 	u16 i;
 
@@ -1030,7 +1029,20 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 		if (!rx_bi->page)
 			continue;
 
-		dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE);
+		/* Invalidate cache lines that may have been written to by
+		 * device so that we avoid corrupting memory.
+		 */
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      rx_bi->dma,
+					      rx_bi->page_offset,
+					      I40E_RXBUFFER_2048,
+					      DMA_FROM_DEVICE);
+
+		/* free resources associated with mapping */
+		dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma,
+				     PAGE_SIZE,
+				     DMA_FROM_DEVICE,
+				     I40E_RX_DMA_ATTR);
 		__free_pages(rx_bi->page, 0);
 
 		rx_bi->page = NULL;
@@ -1159,7 +1171,10 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
 	}
 
 	/* map page for use */
-	dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+				 PAGE_SIZE,
+				 DMA_FROM_DEVICE,
+				 I40E_RX_DMA_ATTR);
 
 	/* if mapping failed free memory back to system since
 	 * there isn't much point in holding memory we can't use
@@ -1219,6 +1234,12 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 		if (!i40e_alloc_mapped_page(rx_ring, bi))
 			goto no_buffers;
 
+		/* sync the buffer for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+						 bi->page_offset,
+						 I40E_RXBUFFER_2048,
+						 DMA_FROM_DEVICE);
+
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
@@ -1685,8 +1706,8 @@ struct sk_buff *i40e_fetch_rx_buffer(struct i40e_ring *rx_ring,
 		rx_ring->rx_stats.page_reuse_count++;
 	} else {
 		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
-			       DMA_FROM_DEVICE);
+		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
+				     DMA_FROM_DEVICE, I40E_RX_DMA_ATTR);
 	}
 
 	/* clear contents of buffer_info */
@@ -2079,7 +2100,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	if (!(pf->flags & I40E_FLAG_FD_ATR_ENABLED))
 		return;
 
-	if ((pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
+	if ((pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED))
 		return;
 
 	/* if sampling is disabled do nothing */
@@ -2113,10 +2134,10 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	th = (struct tcphdr *)(hdr.network + hlen);
 
 	/* Due to lack of space, no more new filters can be programmed */
-	if (th->syn && (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED))
+	if (th->syn && (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED))
 		return;
 	if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) &&
-	    (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) {
+	    (!(pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) {
 		/* HW ATR eviction will take care of removing filters on FIN
 		 * and RST packets.
 		 */
@@ -2179,7 +2200,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 			I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
 
 	if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) &&
-	    (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)))
+	    (!(pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)))
 		dtype_cmd |= I40E_TXD_FLTR_QW1_ATR_MASK;
 
 	fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype);

drivers/net/ethernet/intel/i40e/i40e_txrx.h

@@ -133,6 +133,9 @@ enum i40e_dyn_idx_t {
 #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256
 #define i40e_rx_desc i40e_32byte_rx_desc
 
+#define I40E_RX_DMA_ATTR \
+	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
 /**
  * i40e_test_staterr - tests bits in Rx descriptor status and error fields
  * @rx_desc: pointer to receive descriptor (in le64 format)

drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c

@@ -702,10 +702,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 			dev_info(&pf->pdev->dev,
 				 "Could not allocate VF broadcast filter\n");
 		spin_unlock_bh(&vsi->mac_filter_hash_lock);
-		i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id),
-				  (u32)hena);
-		i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id),
-				  (u32)(hena >> 32));
+		wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hena);
+		wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), (u32)(hena >> 32));
 	}
 
 	/* program mac filter */
@@ -1359,7 +1357,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 	if (!vsi->info.pvid)
 		vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_VLAN;
 
-	if (i40e_vf_client_capable(pf, vf->vf_id, I40E_CLIENT_IWARP) &&
+	if (i40e_vf_client_capable(pf, vf->vf_id) &&
 	    (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_IWARP)) {
 		vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_IWARP;
 		set_bit(I40E_VF_STAT_IWARPENA, &vf->vf_states);
@@ -1853,7 +1851,7 @@ static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 }
 
 /* If the VF is not trusted restrict the number of MAC/VLAN it can program */
-#define I40E_VC_MAX_MAC_ADDR_PER_VF 8
+#define I40E_VC_MAX_MAC_ADDR_PER_VF 12
 #define I40E_VC_MAX_VLAN_PER_VF 8
 
 /**

drivers/net/ethernet/intel/i40evf/Makefile

@@ -32,5 +32,5 @@
 obj-$(CONFIG_I40EVF) += i40evf.o
 
 i40evf-objs :=	i40evf_main.o i40evf_ethtool.o i40evf_virtchnl.o \
-		i40e_txrx.o i40e_common.o i40e_adminq.o
+		i40e_txrx.o i40e_common.o i40e_adminq.o i40evf_client.o
 

drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h

@@ -132,6 +132,10 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_list_func_capabilities	= 0x000A,
 	i40e_aqc_opc_list_dev_capabilities	= 0x000B,
 
+	/* Proxy commands */
+	i40e_aqc_opc_set_proxy_config		= 0x0104,
+	i40e_aqc_opc_set_ns_proxy_table_entry	= 0x0105,
+
 	/* LAA */
 	i40e_aqc_opc_mac_address_read	= 0x0107,
 	i40e_aqc_opc_mac_address_write	= 0x0108,
@@ -139,6 +143,10 @@ enum i40e_admin_queue_opc {
 	/* PXE */
 	i40e_aqc_opc_clear_pxe_mode	= 0x0110,
 
+	/* WoL commands */
+	i40e_aqc_opc_set_wol_filter	= 0x0120,
+	i40e_aqc_opc_get_wake_reason	= 0x0121,
+
 	/* internal switch commands */
 	i40e_aqc_opc_get_switch_config		= 0x0200,
 	i40e_aqc_opc_add_statistics		= 0x0201,
@@ -177,6 +185,7 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_remove_control_packet_filter	= 0x025B,
 	i40e_aqc_opc_add_cloud_filters		= 0x025C,
 	i40e_aqc_opc_remove_cloud_filters	= 0x025D,
+	i40e_aqc_opc_clear_wol_switch_filters	= 0x025E,
 
 	i40e_aqc_opc_add_mirror_rule	= 0x0260,
 	i40e_aqc_opc_delete_mirror_rule	= 0x0261,
@@ -558,6 +567,56 @@ struct i40e_aqc_clear_pxe {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe);
 
+/* Set WoL Filter (0x0120) */
+
+struct i40e_aqc_set_wol_filter {
+	__le16 filter_index;
+#define I40E_AQC_MAX_NUM_WOL_FILTERS	8
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT	15
+#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK	(0x1 << \
+		I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT)
+
+#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT		0
+#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK	(0x7 << \
+		I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT)
+	__le16 cmd_flags;
+#define I40E_AQC_SET_WOL_FILTER				0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL		0x4000
+#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR		0
+#define I40E_AQC_SET_WOL_FILTER_ACTION_SET		1
+	__le16 valid_flags;
+#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID		0x8000
+#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID	0x4000
+	u8 reserved[2];
+	__le32	address_high;
+	__le32	address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter);
+
+struct i40e_aqc_set_wol_filter_data {
+	u8 filter[128];
+	u8 mask[16];
+};
+
+I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data);
+
+/* Get Wake Reason (0x0121) */
+
+struct i40e_aqc_get_wake_reason_completion {
+	u8 reserved_1[2];
+	__le16 wake_reason;
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT	0
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \
+		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT)
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT	8
+#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK	(0xFF << \
+		I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT)
+	u8 reserved_2[12];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion);
+
 /* Switch configuration commands (0x02xx) */
 
 /* Used by many indirect commands that only pass an seid and a buffer in the
@@ -640,6 +699,8 @@ struct i40e_aqc_set_port_parameters {
 #define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS	2 /* must set! */
 #define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA	4
 	__le16	bad_frame_vsi;
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT	0x0
+#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK	0x3FF
 	__le16	default_seid;        /* reserved for command */
 	u8	reserved[10];
 };
@@ -691,6 +752,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp);
 /* Set Switch Configuration (direct 0x0205) */
 struct i40e_aqc_set_switch_config {
 	__le16	flags;
+/* flags used for both fields below */
 #define I40E_AQ_SET_SWITCH_CFG_PROMISC		0x0001
 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER	0x0002
 	__le16	valid_flags;
@@ -1839,11 +1901,12 @@ struct i40e_aqc_get_link_status {
 #define I40E_AQ_CONFIG_FEC_RS_ENA	0x02
 #define I40E_AQ_CONFIG_CRC_ENA		0x04
 #define I40E_AQ_CONFIG_PACING_MASK	0x78
-	u8	external_power_ability;
+	u8	power_desc;
 #define I40E_AQ_LINK_POWER_CLASS_1	0x00
 #define I40E_AQ_LINK_POWER_CLASS_2	0x01
 #define I40E_AQ_LINK_POWER_CLASS_3	0x02
 #define I40E_AQ_LINK_POWER_CLASS_4	0x03
+#define I40E_AQ_PWR_CLASS_MASK		0x03
 	u8	reserved[4];
 };
 

drivers/net/ethernet/intel/i40evf/i40e_txrx.c

@@ -493,7 +493,6 @@ int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring)
  **/
 void i40evf_clean_rx_ring(struct i40e_ring *rx_ring)
 {
-	struct device *dev = rx_ring->dev;
 	unsigned long bi_size;
 	u16 i;
 
@@ -513,7 +512,20 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring)
 		if (!rx_bi->page)
 			continue;
 
-		dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE);
+		/* Invalidate cache lines that may have been written to by
+		 * device so that we avoid corrupting memory.
+		 */
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      rx_bi->dma,
+					      rx_bi->page_offset,
+					      I40E_RXBUFFER_2048,
+					      DMA_FROM_DEVICE);
+
+		/* free resources associated with mapping */
+		dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma,
+				     PAGE_SIZE,
+				     DMA_FROM_DEVICE,
+				     I40E_RX_DMA_ATTR);
 		__free_pages(rx_bi->page, 0);
 
 		rx_bi->page = NULL;
@@ -642,7 +654,10 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
 	}
 
 	/* map page for use */
-	dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+				 PAGE_SIZE,
+				 DMA_FROM_DEVICE,
+				 I40E_RX_DMA_ATTR);
 
 	/* if mapping failed free memory back to system since
 	 * there isn't much point in holding memory we can't use
@@ -702,6 +717,12 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 		if (!i40e_alloc_mapped_page(rx_ring, bi))
 			goto no_buffers;
 
+		/* sync the buffer for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+						 bi->page_offset,
+						 I40E_RXBUFFER_2048,
+						 DMA_FROM_DEVICE);
+
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
@@ -1158,8 +1179,8 @@ struct sk_buff *i40evf_fetch_rx_buffer(struct i40e_ring *rx_ring,
 		rx_ring->rx_stats.page_reuse_count++;
 	} else {
 		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
-			       DMA_FROM_DEVICE);
+		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
+				     DMA_FROM_DEVICE, I40E_RX_DMA_ATTR);
 	}
 
 	/* clear contents of buffer_info */

drivers/net/ethernet/intel/i40evf/i40e_txrx.h

@@ -120,6 +120,9 @@ enum i40e_dyn_idx_t {
 #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256
 #define i40e_rx_desc i40e_32byte_rx_desc
 
+#define I40E_RX_DMA_ATTR \
+	(DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
 /**
  * i40e_test_staterr - tests bits in Rx descriptor status and error fields
  * @rx_desc: pointer to receive descriptor (in le64 format)

drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h

@@ -81,7 +81,9 @@ enum i40e_virtchnl_ops {
 	I40E_VIRTCHNL_OP_GET_STATS = 15,
 	I40E_VIRTCHNL_OP_FCOE = 16,
 	I40E_VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */
+	I40E_VIRTCHNL_OP_IWARP = 20,
 	I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP = 21,
+	I40E_VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP = 22,
 	I40E_VIRTCHNL_OP_CONFIG_RSS_KEY = 23,
 	I40E_VIRTCHNL_OP_CONFIG_RSS_LUT = 24,
 	I40E_VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25,
@@ -393,6 +395,37 @@ struct i40e_virtchnl_pf_event {
 	int severity;
 };
 
+/* I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP
+ * VF uses this message to request PF to map IWARP vectors to IWARP queues.
+ * The request for this originates from the VF IWARP driver through
+ * a client interface between VF LAN and VF IWARP driver.
+ * A vector could have an AEQ and CEQ attached to it although
+ * there is a single AEQ per VF IWARP instance in which case
+ * most vectors will have an INVALID_IDX for aeq and valid idx for ceq.
+ * There will never be a case where there will be multiple CEQs attached
+ * to a single vector.
+ * PF configures interrupt mapping and returns status.
+ */
+
+/* HW does not define a type value for AEQ; only for RX/TX and CEQ.
+ * In order for us to keep the interface simple, SW will define a
+ * unique type value for AEQ.
+ */
+#define I40E_QUEUE_TYPE_PE_AEQ  0x80
+#define I40E_QUEUE_INVALID_IDX  0xFFFF
+
+struct i40e_virtchnl_iwarp_qv_info {
+	u32 v_idx; /* msix_vector */
+	u16 ceq_idx;
+	u16 aeq_idx;
+	u8 itr_idx;
+};
+
+struct i40e_virtchnl_iwarp_qvlist_info {
+	u32 num_vectors;
+	struct i40e_virtchnl_iwarp_qv_info qv_info[1];
+};
+
 /* VF reset states - these are written into the RSTAT register:
  * I40E_VFGEN_RSTAT1 on the PF
  * I40E_VFGEN_RSTAT on the VF

drivers/net/ethernet/intel/i40evf/i40evf.h

@@ -60,6 +60,7 @@ struct i40e_vsi {
 	int base_vector;
 	u16 work_limit;
 	u16 qs_handle;
+	void *priv;     /* client driver data reference. */
 };
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
@@ -169,6 +170,7 @@ enum i40evf_state_t {
 
 enum i40evf_critical_section_t {
 	__I40EVF_IN_CRITICAL_TASK,	/* cannot be interrupted */
+	__I40EVF_IN_CLIENT_TASK,
 };
 /* make common code happy */
 #define __I40E_DOWN __I40EVF_DOWN
@@ -178,6 +180,7 @@ struct i40evf_adapter {
 	struct timer_list watchdog_timer;
 	struct work_struct reset_task;
 	struct work_struct adminq_task;
+	struct delayed_work client_task;
 	struct delayed_work init_task;
 	struct i40e_q_vector *q_vectors;
 	struct list_head vlan_filter_list;
@@ -195,7 +198,10 @@ struct i40evf_adapter {
 	u64 hw_csum_rx_error;
 	u32 rx_desc_count;
 	int num_msix_vectors;
+	int num_iwarp_msix;
+	int iwarp_base_vector;
 	u32 client_pending;
+	struct i40e_client_instance *cinst;
 	struct msix_entry *msix_entries;
 
 	u32 flags;
@@ -211,8 +217,11 @@ struct i40evf_adapter {
 #define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE	BIT(12)
 #define I40EVF_FLAG_ADDR_SET_BY_PF		BIT(13)
 #define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED	BIT(14)
-#define I40EVF_FLAG_PROMISC_ON			BIT(15)
-#define I40EVF_FLAG_ALLMULTI_ON			BIT(16)
+#define I40EVF_FLAG_CLIENT_NEEDS_OPEN		BIT(15)
+#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE		BIT(16)
+#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS	BIT(17)
+#define I40EVF_FLAG_PROMISC_ON			BIT(18)
+#define I40EVF_FLAG_ALLMULTI_ON			BIT(19)
 /* duplicates for common code */
 #define I40E_FLAG_FDIR_ATR_ENABLED		0
 #define I40E_FLAG_DCB_ENABLED			0
@@ -258,10 +267,11 @@ struct i40evf_adapter {
 	bool link_up;
 	enum i40e_aq_link_speed link_speed;
 	enum i40e_virtchnl_ops current_op;
-#define CLIENT_ENABLED(_a) ((_a)->vf_res ? \
+#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \
 			    (_a)->vf_res->vf_offload_flags & \
 				I40E_VIRTCHNL_VF_OFFLOAD_IWARP : \
 			    0)
+#define CLIENT_ENABLED(_a) ((_a)->cinst)
 /* RSS by the PF should be preferred over RSS via other methods. */
 #define RSS_PF(_a) ((_a)->vf_res->vf_offload_flags & \
 		    I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF)
@@ -292,6 +302,12 @@ struct i40evf_adapter {
 
 /* Ethtool Private Flags */
 
+/* lan device */
+struct i40e_device {
+	struct list_head list;
+	struct i40evf_adapter *vf;
+};
+
 /* needed by i40evf_ethtool.c */
 extern char i40evf_driver_name[];
 extern const char i40evf_driver_version[];
@@ -337,4 +353,11 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 				enum i40e_virtchnl_ops v_opcode,
 				i40e_status v_retval, u8 *msg, u16 msglen);
 int i40evf_config_rss(struct i40evf_adapter *adapter);
+int i40evf_lan_add_device(struct i40evf_adapter *adapter);
+int i40evf_lan_del_device(struct i40evf_adapter *adapter);
+void i40evf_client_subtask(struct i40evf_adapter *adapter);
+void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len);
+void i40evf_notify_client_l2_params(struct i40e_vsi *vsi);
+void i40evf_notify_client_open(struct i40e_vsi *vsi);
+void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset);
 #endif /* _I40EVF_H_ */

drivers/net/ethernet/intel/i40evf/i40evf_client.h

+#ifndef _I40E_CLIENT_H_
+#define _I40E_CLIENT_H_
+
+#define I40EVF_CLIENT_STR_LENGTH 10
+
+/* Client interface version should be updated anytime there is a change in the
+ * existing APIs or data structures.
+ */
+#define I40EVF_CLIENT_VERSION_MAJOR 0
+#define I40EVF_CLIENT_VERSION_MINOR 01
+#define I40EVF_CLIENT_VERSION_BUILD 00
+#define I40EVF_CLIENT_VERSION_STR     \
+	__stringify(I40EVF_CLIENT_VERSION_MAJOR) "." \
+	__stringify(I40EVF_CLIENT_VERSION_MINOR) "." \
+	__stringify(I40EVF_CLIENT_VERSION_BUILD)
+
+struct i40e_client_version {
+	u8 major;
+	u8 minor;
+	u8 build;
+	u8 rsvd;
+};
+
+enum i40e_client_state {
+	__I40E_CLIENT_NULL,
+	__I40E_CLIENT_REGISTERED
+};
+
+enum i40e_client_instance_state {
+	__I40E_CLIENT_INSTANCE_NONE,
+	__I40E_CLIENT_INSTANCE_OPENED,
+};
+
+struct i40e_ops;
+struct i40e_client;
+
+/* HW does not define a type value for AEQ; only for RX/TX and CEQ.
+ * In order for us to keep the interface simple, SW will define a
+ * unique type value for AEQ.
+ */
+#define I40E_QUEUE_TYPE_PE_AEQ  0x80
+#define I40E_QUEUE_INVALID_IDX	0xFFFF
+
+struct i40e_qv_info {
+	u32 v_idx; /* msix_vector */
+	u16 ceq_idx;
+	u16 aeq_idx;
+	u8 itr_idx;
+};
+
+struct i40e_qvlist_info {
+	u32 num_vectors;
+	struct i40e_qv_info qv_info[1];
+};
+
+#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF
+
+/* set of LAN parameters useful for clients managed by LAN */
+
+/* Struct to hold per priority info */
+struct i40e_prio_qos_params {
+	u16 qs_handle; /* qs handle for prio */
+	u8 tc; /* TC mapped to prio */
+	u8 reserved;
+};
+
+#define I40E_CLIENT_MAX_USER_PRIORITY        8
+/* Struct to hold Client QoS */
+struct i40e_qos_params {
+	struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY];
+};
+
+struct i40e_params {
+	struct i40e_qos_params qos;
+	u16 mtu;
+	u16 link_up; /* boolean */
+};
+
+/* Structure to hold LAN device info for a client device */
+struct i40e_info {
+	struct i40e_client_version version;
+	u8 lanmac[6];
+	struct net_device *netdev;
+	struct pci_dev *pcidev;
+	u8 __iomem *hw_addr;
+	u8 fid;	/* function id, PF id or VF id */
+#define I40E_CLIENT_FTYPE_PF 0
+#define I40E_CLIENT_FTYPE_VF 1
+	u8 ftype; /* function type, PF or VF */
+	void *vf; /* cast to i40evf_adapter */
+
+	/* All L2 params that could change during the life span of the device
+	 * and needs to be communicated to the client when they change
+	 */
+	struct i40e_params params;
+	struct i40e_ops *ops;
+
+	u16 msix_count;	 /* number of msix vectors*/
+	/* Array down below will be dynamically allocated based on msix_count */
+	struct msix_entry *msix_entries;
+	u16 itr_index; /* Which ITR index the PE driver is suppose to use */
+};
+
+struct i40e_ops {
+	/* setup_q_vector_list enables queues with a particular vector */
+	int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client,
+			    struct i40e_qvlist_info *qv_info);
+
+	u32 (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client,
+			     u8 *msg, u16 len);
+
+	/* If the PE Engine is unresponsive, RDMA driver can request a reset.*/
+	void (*request_reset)(struct i40e_info *ldev,
+			      struct i40e_client *client);
+};
+
+struct i40e_client_ops {
+	/* Should be called from register_client() or whenever the driver is
+	 * ready to create a specific client instance.
+	 */
+	int (*open)(struct i40e_info *ldev, struct i40e_client *client);
+
+	/* Should be closed when netdev is unavailable or when unregister
+	 * call comes in. If the close happens due to a reset, set the reset
+	 * bit to true.
+	 */
+	void (*close)(struct i40e_info *ldev, struct i40e_client *client,
+		      bool reset);
+
+	/* called when some l2 managed parameters changes - mss */
+	void (*l2_param_change)(struct i40e_info *ldev,
+				struct i40e_client *client,
+				struct i40e_params *params);
+
+	/* called when a message is received from the PF */
+	int (*virtchnl_receive)(struct i40e_info *ldev,
+				struct i40e_client *client,
+				u8 *msg, u16 len);
+};
+
+/* Client device */
+struct i40e_client_instance {
+	struct list_head list;
+	struct i40e_info lan_info;
+	struct i40e_client *client;
+	unsigned long  state;
+};
+
+struct i40e_client {
+	struct list_head list;		/* list of registered clients */
+	char name[I40EVF_CLIENT_STR_LENGTH];
+	struct i40e_client_version version;
+	unsigned long state;		/* client state */
+	atomic_t ref_cnt;  /* Count of all the client devices of this kind */
+	u32 flags;
+#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE	BIT(0)
+#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS	BIT(2)
+	u8 type;
+#define I40E_CLIENT_IWARP 0
+	struct i40e_client_ops *ops;	/* client ops provided by the client */
+};
+
+/* used by clients */
+int i40evf_register_client(struct i40e_client *client);
+int i40evf_unregister_client(struct i40e_client *client);
+#endif /* _I40E_CLIENT_H_ */

drivers/net/ethernet/intel/i40evf/i40evf_main.c

@@ -26,6 +26,7 @@
 
 #include "i40evf.h"
 #include "i40e_prototype.h"
+#include "i40evf_client.h"
 static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter);
 static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter);
 static int i40evf_close(struct net_device *netdev);
@@ -36,9 +37,9 @@ static const char i40evf_driver_string[] =
 
 #define DRV_KERN "-k"
 
-#define DRV_VERSION_MAJOR 1
-#define DRV_VERSION_MINOR 6
-#define DRV_VERSION_BUILD 27
+#define DRV_VERSION_MAJOR 2
+#define DRV_VERSION_MINOR 1
+#define DRV_VERSION_BUILD 7
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD) \
@@ -1058,6 +1059,8 @@ static void i40evf_up_complete(struct i40evf_adapter *adapter)
 	i40evf_napi_enable_all(adapter);
 
 	adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_QUEUES;
+	if (CLIENT_ENABLED(adapter))
+		adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_OPEN;
 	mod_timer_pending(&adapter->watchdog_timer, jiffies + 1);
 }
 
@@ -1685,6 +1688,7 @@ static void i40evf_watchdog_task(struct work_struct *work)
 		i40evf_set_promiscuous(adapter, 0);
 		goto watchdog_done;
 	}
+	schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5));
 
 	if (adapter->state == __I40EVF_RUNNING)
 		i40evf_request_stats(adapter);
@@ -1773,10 +1777,17 @@ static void i40evf_reset_task(struct work_struct *work)
 	u32 reg_val;
 	int i = 0, err;
 
-	while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK,
+	while (test_and_set_bit(__I40EVF_IN_CLIENT_TASK,
 				&adapter->crit_section))
 		usleep_range(500, 1000);
-
+	if (CLIENT_ENABLED(adapter)) {
+		adapter->flags &= ~(I40EVF_FLAG_CLIENT_NEEDS_OPEN |
+				    I40EVF_FLAG_CLIENT_NEEDS_CLOSE |
+				    I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS |
+				    I40EVF_FLAG_SERVICE_CLIENT_REQUESTED);
+		cancel_delayed_work_sync(&adapter->client_task);
+		i40evf_notify_client_close(&adapter->vsi, true);
+	}
 	i40evf_misc_irq_disable(adapter);
 	if (adapter->flags & I40EVF_FLAG_RESET_NEEDED) {
 		adapter->flags &= ~I40EVF_FLAG_RESET_NEEDED;
@@ -1819,6 +1830,7 @@ static void i40evf_reset_task(struct work_struct *work)
 		dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
 			reg_val);
 		i40evf_disable_vf(adapter);
+		clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
 		return; /* Do not attempt to reinit. It's dead, Jim. */
 	}
 
@@ -1861,9 +1873,8 @@ static void i40evf_reset_task(struct work_struct *work)
 	}
 	adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER;
 	adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER;
-	/* Open RDMA Client again */
-	adapter->aq_required |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
 	clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section);
+	clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
 	i40evf_misc_irq_enable(adapter);
 
 	mod_timer(&adapter->watchdog_timer, jiffies + 2);
@@ -1979,6 +1990,48 @@ static void i40evf_adminq_task(struct work_struct *work)
 	i40evf_misc_irq_enable(adapter);
 }
 
+/**
+ * i40evf_client_task - worker thread to perform client work
+ * @work: pointer to work_struct containing our data
+ *
+ * This task handles client interactions. Because client calls can be
+ * reentrant, we can't handle them in the watchdog.
+ **/
+static void i40evf_client_task(struct work_struct *work)
+{
+	struct i40evf_adapter *adapter =
+		container_of(work, struct i40evf_adapter, client_task.work);
+
+	/* If we can't get the client bit, just give up. We'll be rescheduled
+	 * later.
+	 */
+
+	if (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section))
+		return;
+
+	if (adapter->flags & I40EVF_FLAG_SERVICE_CLIENT_REQUESTED) {
+		i40evf_client_subtask(adapter);
+		adapter->flags &= ~I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+		goto out;
+	}
+	if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_CLOSE) {
+		i40evf_notify_client_close(&adapter->vsi, false);
+		adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_CLOSE;
+		goto out;
+	}
+	if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_OPEN) {
+		i40evf_notify_client_open(&adapter->vsi);
+		adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_OPEN;
+		goto out;
+	}
+	if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS) {
+		i40evf_notify_client_l2_params(&adapter->vsi);
+		adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS;
+	}
+out:
+	clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);
+}
+
 /**
  * i40evf_free_all_tx_resources - Free Tx Resources for All Queues
  * @adapter: board private structure
@@ -2148,6 +2201,8 @@ static int i40evf_close(struct net_device *netdev)
 
 
 	set_bit(__I40E_DOWN, &adapter->vsi.state);
+	if (CLIENT_ENABLED(adapter))
+		adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_CLOSE;
 
 	i40evf_down(adapter);
 	adapter->state = __I40EVF_DOWN_PENDING;
@@ -2188,6 +2243,10 @@ static int i40evf_change_mtu(struct net_device *netdev, int new_mtu)
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 
 	netdev->mtu = new_mtu;
+	if (CLIENT_ENABLED(adapter)) {
+		i40evf_notify_client_l2_params(&adapter->vsi);
+		adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
+	}
 	adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
 	schedule_work(&adapter->reset_task);
 
@@ -2581,6 +2640,12 @@ static void i40evf_init_task(struct work_struct *work)
 	adapter->netdev_registered = true;
 
 	netif_tx_stop_all_queues(netdev);
+	if (CLIENT_ALLOWED(adapter)) {
+		err = i40evf_lan_add_device(adapter);
+		if (err)
+			dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n",
+				 err);
+	}
 
 	dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr);
 	if (netdev->features & NETIF_F_GRO)
@@ -2745,6 +2810,7 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&adapter->reset_task, i40evf_reset_task);
 	INIT_WORK(&adapter->adminq_task, i40evf_adminq_task);
 	INIT_WORK(&adapter->watchdog_task, i40evf_watchdog_task);
+	INIT_DELAYED_WORK(&adapter->client_task, i40evf_client_task);
 	INIT_DELAYED_WORK(&adapter->init_task, i40evf_init_task);
 	schedule_delayed_work(&adapter->init_task,
 			      msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
@@ -2857,14 +2923,21 @@ static void i40evf_remove(struct pci_dev *pdev)
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 	struct i40evf_mac_filter *f, *ftmp;
 	struct i40e_hw *hw = &adapter->hw;
+	int err;
 
 	cancel_delayed_work_sync(&adapter->init_task);
 	cancel_work_sync(&adapter->reset_task);
-
+	cancel_delayed_work_sync(&adapter->client_task);
 	if (adapter->netdev_registered) {
 		unregister_netdev(netdev);
 		adapter->netdev_registered = false;
 	}
+	if (CLIENT_ALLOWED(adapter)) {
+		err = i40evf_lan_del_device(adapter);
+		if (err)
+			dev_warn(&pdev->dev, "Failed to delete client device: %d\n",
+				 err);
+	}
 
 	/* Shut down all the garbage mashers on the detention level */
 	adapter->state = __I40EVF_REMOVE;

drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c

@@ -26,6 +26,7 @@
 
 #include "i40evf.h"
 #include "i40e_prototype.h"
+#include "i40evf_client.h"
 
 /* busy wait delay in msec */
 #define I40EVF_BUSY_WAIT_DELAY 10
@@ -999,6 +1000,16 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 		if (v_opcode != adapter->current_op)
 			return;
 		break;
+	case I40E_VIRTCHNL_OP_IWARP:
+		/* Gobble zero-length replies from the PF. They indicate that
+		 * a previous message was received OK, and the client doesn't
+		 * care about that.
+		 */
+		if (msglen && CLIENT_ENABLED(adapter))
+			i40evf_notify_client_message(&adapter->vsi,
+						     msg, msglen);
+		break;
+
 	case I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP:
 		adapter->client_pending &=
 				~(BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP));
@@ -1014,7 +1025,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 		}
 		break;
 	default:
-		if (v_opcode != adapter->current_op)
+		if (adapter->current_op && (v_opcode != adapter->current_op))
 			dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n",
 				 adapter->current_op, v_opcode);
 		break;