Merge branch 'for-davem' of git://git.kernel.org/pub/scm/linux/kernel/git/bwh/sfc-next

Ben Hutchings says:

====================
1. Change PTP clock name to 'sfc'.
2. Complete support for hardware timestamping and PTP clock on the
SFC9100 family.
3. Various cleanups for the PTP code.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/ethernet/sfc/ef10.c

@@ -264,6 +264,8 @@ static int efx_ef10_probe(struct efx_nic *efx)
 	if (rc)
 		goto fail3;
 
+	efx_ptp_probe(efx, NULL);
+
 	return 0;
 
 fail3:
@@ -472,9 +474,10 @@ static void efx_ef10_remove(struct efx_nic *efx)
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	int rc;
 
+	efx_ptp_remove(efx);
+
 	efx_mcdi_mon_remove(efx);
 
-	/* This needs to be after efx_ptp_remove_channel() with no filters */
 	efx_ef10_rx_free_indir_table(efx);
 
 	if (nic_data->wc_membase)
@@ -1469,8 +1472,9 @@ static void efx_ef10_rx_init(struct efx_rx_queue *rx_queue)
 	MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_LABEL, efx_rx_queue_index(rx_queue));
 	MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_INSTANCE,
 		       efx_rx_queue_index(rx_queue));
-	MCDI_POPULATE_DWORD_1(inbuf, INIT_RXQ_IN_FLAGS,
-			      INIT_RXQ_IN_FLAG_PREFIX, 1);
+	MCDI_POPULATE_DWORD_2(inbuf, INIT_RXQ_IN_FLAGS,
+			      INIT_RXQ_IN_FLAG_PREFIX, 1,
+			      INIT_RXQ_IN_FLAG_TIMESTAMP, 1);
 	MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_OWNER_ID, 0);
 	MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_PORT_ID, EVB_PORT_ID_ASSIGNED);
 
@@ -3406,6 +3410,119 @@ static void efx_ef10_ptp_write_host_time(struct efx_nic *efx, u32 host_time)
 	_efx_writed(efx, cpu_to_le32(host_time), ER_DZ_MC_DB_LWRD);
 }
 
+static int efx_ef10_rx_enable_timestamping(struct efx_channel *channel,
+					   bool temp)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_LEN);
+	int rc;
+
+	if (channel->sync_events_state == SYNC_EVENTS_REQUESTED ||
+	    channel->sync_events_state == SYNC_EVENTS_VALID ||
+	    (temp && channel->sync_events_state == SYNC_EVENTS_DISABLED))
+		return 0;
+	channel->sync_events_state = SYNC_EVENTS_REQUESTED;
+
+	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_TIME_EVENT_SUBSCRIBE);
+	MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
+	MCDI_SET_DWORD(inbuf, PTP_IN_TIME_EVENT_SUBSCRIBE_QUEUE,
+		       channel->channel);
+
+	rc = efx_mcdi_rpc(channel->efx, MC_CMD_PTP,
+			  inbuf, sizeof(inbuf), NULL, 0, NULL);
+
+	if (rc != 0)
+		channel->sync_events_state = temp ? SYNC_EVENTS_QUIESCENT :
+						    SYNC_EVENTS_DISABLED;
+
+	return rc;
+}
+
+static int efx_ef10_rx_disable_timestamping(struct efx_channel *channel,
+					    bool temp)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_LEN);
+	int rc;
+
+	if (channel->sync_events_state == SYNC_EVENTS_DISABLED ||
+	    (temp && channel->sync_events_state == SYNC_EVENTS_QUIESCENT))
+		return 0;
+	if (channel->sync_events_state == SYNC_EVENTS_QUIESCENT) {
+		channel->sync_events_state = SYNC_EVENTS_DISABLED;
+		return 0;
+	}
+	channel->sync_events_state = temp ? SYNC_EVENTS_QUIESCENT :
+					    SYNC_EVENTS_DISABLED;
+
+	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_TIME_EVENT_UNSUBSCRIBE);
+	MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
+	MCDI_SET_DWORD(inbuf, PTP_IN_TIME_EVENT_UNSUBSCRIBE_CONTROL,
+		       MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_SINGLE);
+	MCDI_SET_DWORD(inbuf, PTP_IN_TIME_EVENT_UNSUBSCRIBE_QUEUE,
+		       channel->channel);
+
+	rc = efx_mcdi_rpc(channel->efx, MC_CMD_PTP,
+			  inbuf, sizeof(inbuf), NULL, 0, NULL);
+
+	return rc;
+}
+
+static int efx_ef10_ptp_set_ts_sync_events(struct efx_nic *efx, bool en,
+					   bool temp)
+{
+	int (*set)(struct efx_channel *channel, bool temp);
+	struct efx_channel *channel;
+
+	set = en ?
+	      efx_ef10_rx_enable_timestamping :
+	      efx_ef10_rx_disable_timestamping;
+
+	efx_for_each_channel(channel, efx) {
+		int rc = set(channel, temp);
+		if (en && rc != 0) {
+			efx_ef10_ptp_set_ts_sync_events(efx, false, temp);
+			return rc;
+		}
+	}
+
+	return 0;
+}
+
+static int efx_ef10_ptp_set_ts_config(struct efx_nic *efx,
+				      struct hwtstamp_config *init)
+{
+	int rc;
+
+	switch (init->rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		efx_ef10_ptp_set_ts_sync_events(efx, false, false);
+		/* if TX timestamping is still requested then leave PTP on */
+		return efx_ptp_change_mode(efx,
+					   init->tx_type != HWTSTAMP_TX_OFF, 0);
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+		init->rx_filter = HWTSTAMP_FILTER_ALL;
+		rc = efx_ptp_change_mode(efx, true, 0);
+		if (!rc)
+			rc = efx_ef10_ptp_set_ts_sync_events(efx, true, false);
+		if (rc)
+			efx_ptp_change_mode(efx, false, 0);
+		return rc;
+	default:
+		return -ERANGE;
+	}
+}
+
 const struct efx_nic_type efx_hunt_a0_nic_type = {
 	.mem_map_size = efx_ef10_mem_map_size,
 	.probe = efx_ef10_probe,
@@ -3484,11 +3601,14 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 	.mtd_sync = efx_mcdi_mtd_sync,
 #endif
 	.ptp_write_host_time = efx_ef10_ptp_write_host_time,
+	.ptp_set_ts_sync_events = efx_ef10_ptp_set_ts_sync_events,
+	.ptp_set_ts_config = efx_ef10_ptp_set_ts_config,
 
 	.revision = EFX_REV_HUNT_A0,
 	.max_dma_mask = DMA_BIT_MASK(ESF_DZ_TX_KER_BUF_ADDR_WIDTH),
 	.rx_prefix_size = ES_DZ_RX_PREFIX_SIZE,
 	.rx_hash_offset = ES_DZ_RX_PREFIX_HASH_OFST,
+	.rx_ts_offset = ES_DZ_RX_PREFIX_TSTAMP_OFST,
 	.can_rx_scatter = true,
 	.always_rx_scatter = true,
 	.max_interrupt_mode = EFX_INT_MODE_MSIX,
@@ -3497,4 +3617,6 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 			     NETIF_F_RXHASH | NETIF_F_NTUPLE),
 	.mcdi_max_ver = 2,
 	.max_rx_ip_filters = HUNT_FILTER_TBL_ROWS,
+	.hwtstamp_filters = 1 << HWTSTAMP_FILTER_NONE |
+			    1 << HWTSTAMP_FILTER_ALL,
 };

drivers/net/ethernet/sfc/efx.c

@@ -1117,6 +1117,77 @@ static void efx_remove_port(struct efx_nic *efx)
  *
  **************************************************************************/
 
+static LIST_HEAD(efx_primary_list);
+static LIST_HEAD(efx_unassociated_list);
+
+static bool efx_same_controller(struct efx_nic *left, struct efx_nic *right)
+{
+	return left->type == right->type &&
+		left->vpd_sn && right->vpd_sn &&
+		!strcmp(left->vpd_sn, right->vpd_sn);
+}
+
+static void efx_associate(struct efx_nic *efx)
+{
+	struct efx_nic *other, *next;
+
+	if (efx->primary == efx) {
+		/* Adding primary function; look for secondaries */
+
+		netif_dbg(efx, probe, efx->net_dev, "adding to primary list\n");
+		list_add_tail(&efx->node, &efx_primary_list);
+
+		list_for_each_entry_safe(other, next, &efx_unassociated_list,
+					 node) {
+			if (efx_same_controller(efx, other)) {
+				list_del(&other->node);
+				netif_dbg(other, probe, other->net_dev,
+					  "moving to secondary list of %s %s\n",
+					  pci_name(efx->pci_dev),
+					  efx->net_dev->name);
+				list_add_tail(&other->node,
+					      &efx->secondary_list);
+				other->primary = efx;
+			}
+		}
+	} else {
+		/* Adding secondary function; look for primary */
+
+		list_for_each_entry(other, &efx_primary_list, node) {
+			if (efx_same_controller(efx, other)) {
+				netif_dbg(efx, probe, efx->net_dev,
+					  "adding to secondary list of %s %s\n",
+					  pci_name(other->pci_dev),
+					  other->net_dev->name);
+				list_add_tail(&efx->node,
+					      &other->secondary_list);
+				efx->primary = other;
+				return;
+			}
+		}
+
+		netif_dbg(efx, probe, efx->net_dev,
+			  "adding to unassociated list\n");
+		list_add_tail(&efx->node, &efx_unassociated_list);
+	}
+}
+
+static void efx_dissociate(struct efx_nic *efx)
+{
+	struct efx_nic *other, *next;
+
+	list_del(&efx->node);
+	efx->primary = NULL;
+
+	list_for_each_entry_safe(other, next, &efx->secondary_list, node) {
+		list_del(&other->node);
+		netif_dbg(other, probe, other->net_dev,
+			  "moving to unassociated list\n");
+		list_add_tail(&other->node, &efx_unassociated_list);
+		other->primary = NULL;
+	}
+}
+
 /* This configures the PCI device to enable I/O and DMA. */
 static int efx_init_io(struct efx_nic *efx)
 {
@@ -2214,6 +2285,8 @@ static int efx_register_netdev(struct efx_nic *efx)
 			efx_init_tx_queue_core_txq(tx_queue);
 	}
 
+	efx_associate(efx);
+
 	rtnl_unlock();
 
 	rc = device_create_file(&efx->pci_dev->dev, &dev_attr_phy_type);
@@ -2227,6 +2300,7 @@ static int efx_register_netdev(struct efx_nic *efx)
 
 fail_registered:
 	rtnl_lock();
+	efx_dissociate(efx);
 	unregister_netdevice(net_dev);
 fail_locked:
 	efx->state = STATE_UNINIT;
@@ -2568,6 +2642,8 @@ static int efx_init_struct(struct efx_nic *efx,
 	int i;
 
 	/* Initialise common structures */
+	INIT_LIST_HEAD(&efx->node);
+	INIT_LIST_HEAD(&efx->secondary_list);
 	spin_lock_init(&efx->biu_lock);
 #ifdef CONFIG_SFC_MTD
 	INIT_LIST_HEAD(&efx->mtd_list);
@@ -2586,6 +2662,8 @@ static int efx_init_struct(struct efx_nic *efx,
 		NET_IP_ALIGN ? (efx->rx_prefix_size + NET_IP_ALIGN) % 4 : 0;
 	efx->rx_packet_hash_offset =
 		efx->type->rx_hash_offset - efx->type->rx_prefix_size;
+	efx->rx_packet_ts_offset =
+		efx->type->rx_ts_offset - efx->type->rx_prefix_size;
 	spin_lock_init(&efx->stats_lock);
 	mutex_init(&efx->mac_lock);
 	efx->phy_op = &efx_dummy_phy_operations;
@@ -2626,6 +2704,8 @@ static void efx_fini_struct(struct efx_nic *efx)
 	for (i = 0; i < EFX_MAX_CHANNELS; i++)
 		kfree(efx->channel[i]);
 
+	kfree(efx->vpd_sn);
+
 	if (efx->workqueue) {
 		destroy_workqueue(efx->workqueue);
 		efx->workqueue = NULL;
@@ -2670,6 +2750,7 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
 
 	/* Mark the NIC as fini, then stop the interface */
 	rtnl_lock();
+	efx_dissociate(efx);
 	dev_close(efx->net_dev);
 	efx_disable_interrupts(efx);
 	rtnl_unlock();
@@ -2696,12 +2777,12 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
  * always appear within the first 512 bytes.
  */
 #define SFC_VPD_LEN 512
-static void efx_print_product_vpd(struct efx_nic *efx)
+static void efx_probe_vpd_strings(struct efx_nic *efx)
 {
 	struct pci_dev *dev = efx->pci_dev;
 	char vpd_data[SFC_VPD_LEN];
 	ssize_t vpd_size;
-	int i, j;
+	int ro_start, ro_size, i, j;
 
 	/* Get the vpd data from the device */
 	vpd_size = pci_read_vpd(dev, 0, sizeof(vpd_data), vpd_data);
@@ -2711,14 +2792,15 @@ static void efx_print_product_vpd(struct efx_nic *efx)
 	}
 
 	/* Get the Read only section */
-	i = pci_vpd_find_tag(vpd_data, 0, vpd_size, PCI_VPD_LRDT_RO_DATA);
-	if (i < 0) {
+	ro_start = pci_vpd_find_tag(vpd_data, 0, vpd_size, PCI_VPD_LRDT_RO_DATA);
+	if (ro_start < 0) {
 		netif_err(efx, drv, efx->net_dev, "VPD Read-only not found\n");
 		return;
 	}
 
-	j = pci_vpd_lrdt_size(&vpd_data[i]);
-	i += PCI_VPD_LRDT_TAG_SIZE;
+	ro_size = pci_vpd_lrdt_size(&vpd_data[ro_start]);
+	j = ro_size;
+	i = ro_start + PCI_VPD_LRDT_TAG_SIZE;
 	if (i + j > vpd_size)
 		j = vpd_size - i;
 
@@ -2738,6 +2820,27 @@ static void efx_print_product_vpd(struct efx_nic *efx)
 
 	netif_info(efx, drv, efx->net_dev,
 		   "Part Number : %.*s\n", j, &vpd_data[i]);
+
+	i = ro_start + PCI_VPD_LRDT_TAG_SIZE;
+	j = ro_size;
+	i = pci_vpd_find_info_keyword(vpd_data, i, j, "SN");
+	if (i < 0) {
+		netif_err(efx, drv, efx->net_dev, "Serial number not found\n");
+		return;
+	}
+
+	j = pci_vpd_info_field_size(&vpd_data[i]);
+	i += PCI_VPD_INFO_FLD_HDR_SIZE;
+	if (i + j > vpd_size) {
+		netif_err(efx, drv, efx->net_dev, "Incomplete serial number\n");
+		return;
+	}
+
+	efx->vpd_sn = kmalloc(j + 1, GFP_KERNEL);
+	if (!efx->vpd_sn)
+		return;
+
+	snprintf(efx->vpd_sn, j + 1, "%s", &vpd_data[i]);
 }
 
 
@@ -2834,7 +2937,7 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 	netif_info(efx, probe, efx->net_dev,
 		   "Solarflare NIC detected\n");
 
-	efx_print_product_vpd(efx);
+	efx_probe_vpd_strings(efx);
 
 	/* Set up basic I/O (BAR mappings etc) */
 	rc = efx_init_io(efx);

drivers/net/ethernet/sfc/falcon.c

@@ -2247,6 +2247,8 @@ static int falcon_probe_nic(struct efx_nic *efx)
 	struct falcon_board *board;
 	int rc;
 
+	efx->primary = efx; /* only one usable function per controller */
+
 	/* Allocate storage for hardware specific data */
 	nic_data = kzalloc(sizeof(*nic_data), GFP_KERNEL);
 	if (!nic_data)

drivers/net/ethernet/sfc/mcdi.c

@@ -102,6 +102,10 @@ int efx_mcdi_init(struct efx_nic *efx)
 		netif_err(efx, probe, efx->net_dev,
 			  "Host already registered with MCPU\n");
 
+	if (efx->mcdi->fn_flags &
+	    (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY))
+		efx->primary = efx;
+
 	return 0;
 }
 
@@ -1018,6 +1022,9 @@ void efx_mcdi_process_event(struct efx_channel *channel,
 	case MCDI_EVENT_CODE_PTP_PPS:
 		efx_ptp_event(efx, event);
 		break;
+	case MCDI_EVENT_CODE_PTP_TIME:
+		efx_time_sync_event(channel, event);
+		break;
 	case MCDI_EVENT_CODE_TX_FLUSH:
 	case MCDI_EVENT_CODE_RX_FLUSH:
 		/* Two flush events will be sent: one to the same event
@@ -1132,13 +1139,27 @@ static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
 		goto fail;
 	}
 
+	if (driver_operating) {
+		if (outlen >= MC_CMD_DRV_ATTACH_EXT_OUT_LEN) {
+			efx->mcdi->fn_flags =
+				MCDI_DWORD(outbuf,
+					   DRV_ATTACH_EXT_OUT_FUNC_FLAGS);
+		} else {
+			/* Synthesise flags for Siena */
+			efx->mcdi->fn_flags =
+				1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL |
+				1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED |
+				(efx_port_num(efx) == 0) <<
+				MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY;
+		}
+	}
+
 	/* We currently assume we have control of the external link
 	 * and are completely trusted by firmware.  Abort probing
 	 * if that's not true for this function.
 	 */
 	if (driver_operating &&
-	    outlen >= MC_CMD_DRV_ATTACH_EXT_OUT_LEN &&
-	    (MCDI_DWORD(outbuf, DRV_ATTACH_EXT_OUT_FUNC_FLAGS) &
+	    (efx->mcdi->fn_flags &
 	     (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL |
 	      1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED)) !=
 	    (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL |

drivers/net/ethernet/sfc/mcdi.h

@@ -94,12 +94,14 @@ struct efx_mcdi_mtd_partition {
  * struct efx_mcdi_data - extra state for NICs that implement MCDI
  * @iface: Interface/protocol state
  * @hwmon: Hardware monitor state
+ * @fn_flags: Flags for this function, as returned by %MC_CMD_DRV_ATTACH.
  */
 struct efx_mcdi_data {
 	struct efx_mcdi_iface iface;
 #ifdef CONFIG_SFC_MCDI_MON
 	struct efx_mcdi_mon hwmon;
 #endif
+	u32 fn_flags;
 };
 
 #ifdef CONFIG_SFC_MCDI_MON

drivers/net/ethernet/sfc/net_driver.h

@@ -91,6 +91,7 @@
 
 /* Forward declare Precision Time Protocol (PTP) support structure. */
 struct efx_ptp_data;
+struct hwtstamp_config;
 
 struct efx_self_tests;
 
@@ -368,6 +369,13 @@ enum efx_rx_alloc_method {
 	RX_ALLOC_METHOD_PAGE = 2,
 };
 
+enum efx_sync_events_state {
+	SYNC_EVENTS_DISABLED = 0,
+	SYNC_EVENTS_QUIESCENT,
+	SYNC_EVENTS_REQUESTED,
+	SYNC_EVENTS_VALID,
+};
+
 /**
  * struct efx_channel - An Efx channel
  *
@@ -407,6 +415,9 @@ enum efx_rx_alloc_method {
  *	by __efx_rx_packet(), if @rx_pkt_n_frags != 0
  * @rx_queue: RX queue for this channel
  * @tx_queue: TX queues for this channel
+ * @sync_events_state: Current state of sync events on this channel
+ * @sync_timestamp_major: Major part of the last ptp sync event
+ * @sync_timestamp_minor: Minor part of the last ptp sync event
  */
 struct efx_channel {
 	struct efx_nic *efx;
@@ -445,6 +456,10 @@ struct efx_channel {
 
 	struct efx_rx_queue rx_queue;
 	struct efx_tx_queue tx_queue[EFX_TXQ_TYPES];
+
+	enum efx_sync_events_state sync_events_state;
+	u32 sync_timestamp_major;
+	u32 sync_timestamp_minor;
 };
 
 /**
@@ -520,15 +535,6 @@ enum nic_state {
 	STATE_RECOVERY = 3,	/* device recovering from PCI error */
 };
 
-/*
- * Alignment of the skb->head which wraps a page-allocated RX buffer
- *
- * The skb allocated to wrap an rx_buffer can have this alignment. Since
- * the data is memcpy'd from the rx_buf, it does not need to be equal to
- * NET_IP_ALIGN.
- */
-#define EFX_PAGE_SKB_ALIGN 2
-
 /* Forward declaration */
 struct efx_nic;
 
@@ -651,6 +657,13 @@ struct vfdi_status;
  * struct efx_nic - an Efx NIC
  * @name: Device name (net device name or bus id before net device registered)
  * @pci_dev: The PCI device
+ * @node: List node for maintaning primary/secondary function lists
+ * @primary: &struct efx_nic instance for the primary function of this
+ *	controller.  May be the same structure, and may be %NULL if no
+ *	primary function is bound.  Serialised by rtnl_lock.
+ * @secondary_list: List of &struct efx_nic instances for the secondary PCI
+ *	functions of the controller, if this is for the primary function.
+ *	Serialised by rtnl_lock.
  * @type: Controller type attributes
  * @legacy_irq: IRQ number
  * @workqueue: Workqueue for port reconfigures and the HW monitor.
@@ -694,6 +707,8 @@ struct vfdi_status;
  *	(valid only if @rx_prefix_size != 0; always negative)
  * @rx_packet_len_offset: Offset of RX packet length from start of packet data
  *	(valid only for NICs that set %EFX_RX_PKT_PREFIX_LEN; always negative)
+ * @rx_packet_ts_offset: Offset of timestamp from start of packet data
+ *	(valid only if channel->sync_timestamps_enabled; always negative)
  * @rx_hash_key: Toeplitz hash key for RSS
  * @rx_indir_table: Indirection table for RSS
  * @rx_scatter: Scatter mode enabled for receives
@@ -763,6 +778,7 @@ struct vfdi_status;
  * @local_lock: Mutex protecting %local_addr_list and %local_page_list.
  * @peer_work: Work item to broadcast peer addresses to VMs.
  * @ptp_data: PTP state data
+ * @vpd_sn: Serial number read from VPD
  * @monitor_work: Hardware monitor workitem
  * @biu_lock: BIU (bus interface unit) lock
  * @last_irq_cpu: Last CPU to handle a possible test interrupt.  This
@@ -777,6 +793,9 @@ struct efx_nic {
 	/* The following fields should be written very rarely */
 
 	char name[IFNAMSIZ];
+	struct list_head node;
+	struct efx_nic *primary;
+	struct list_head secondary_list;
 	struct pci_dev *pci_dev;
 	unsigned int port_num;
 	const struct efx_nic_type *type;
@@ -828,6 +847,7 @@ struct efx_nic {
 	unsigned int rx_prefix_size;
 	int rx_packet_hash_offset;
 	int rx_packet_len_offset;
+	int rx_packet_ts_offset;
 	u8 rx_hash_key[40];
 	u32 rx_indir_table[128];
 	bool rx_scatter;
@@ -911,6 +931,8 @@ struct efx_nic {
 
 	struct efx_ptp_data *ptp_data;
 
+	char *vpd_sn;
+
 	/* The following fields may be written more often */
 
 	struct delayed_work monitor_work ____cacheline_aligned_in_smp;
@@ -1042,6 +1064,12 @@ struct efx_mtd_partition {
  * @mtd_sync: Wait for write-back to complete on MTD partition.  This
  *	also notifies the driver that a writer has finished using this
  *	partition.
+ * @ptp_write_host_time: Send host time to MC as part of sync protocol
+ * @ptp_set_ts_sync_events: Enable or disable sync events for inline RX
+ *	timestamping, possibly only temporarily for the purposes of a reset.
+ * @ptp_set_ts_config: Set hardware timestamp configuration.  The flags
+ *	and tx_type will already have been validated but this operation
+ *	must validate and update rx_filter.
  * @revision: Hardware architecture revision
  * @txd_ptr_tbl_base: TX descriptor ring base address
  * @rxd_ptr_tbl_base: RX descriptor ring base address
@@ -1051,6 +1079,7 @@ struct efx_mtd_partition {
  * @max_dma_mask: Maximum possible DMA mask
  * @rx_prefix_size: Size of RX prefix before packet data
  * @rx_hash_offset: Offset of RX flow hash within prefix
+ * @rx_ts_offset: Offset of timestamp within prefix
  * @rx_buffer_padding: Size of padding at end of RX packet
  * @can_rx_scatter: NIC is able to scatter packets to multiple buffers
  * @always_rx_scatter: NIC will always scatter packets to multiple buffers
@@ -1060,6 +1089,7 @@ struct efx_mtd_partition {
  * @offload_features: net_device feature flags for protocol offload
  *	features implemented in hardware
  * @mcdi_max_ver: Maximum MCDI version supported
+ * @hwtstamp_filters: Mask of hardware timestamp filter types supported
  */
 struct efx_nic_type {
 	unsigned int (*mem_map_size)(struct efx_nic *efx);
@@ -1161,6 +1191,9 @@ struct efx_nic_type {
 	int (*mtd_sync)(struct mtd_info *mtd);
 #endif
 	void (*ptp_write_host_time)(struct efx_nic *efx, u32 host_time);
+	int (*ptp_set_ts_sync_events)(struct efx_nic *efx, bool en, bool temp);
+	int (*ptp_set_ts_config)(struct efx_nic *efx,
+				 struct hwtstamp_config *init);
 
 	int revision;
 	unsigned int txd_ptr_tbl_base;
@@ -1171,6 +1204,7 @@ struct efx_nic_type {
 	u64 max_dma_mask;
 	unsigned int rx_prefix_size;
 	unsigned int rx_hash_offset;
+	unsigned int rx_ts_offset;
 	unsigned int rx_buffer_padding;
 	bool can_rx_scatter;
 	bool always_rx_scatter;
@@ -1179,6 +1213,7 @@ struct efx_nic_type {
 	netdev_features_t offload_features;
 	int mcdi_max_ver;
 	unsigned int max_rx_ip_filters;
+	u32 hwtstamp_filters;
 };
 
 /**************************************************************************

drivers/net/ethernet/sfc/nic.h

@@ -561,8 +561,20 @@ int efx_ptp_set_ts_config(struct efx_nic *efx, struct ifreq *ifr);
 int efx_ptp_get_ts_config(struct efx_nic *efx, struct ifreq *ifr);
 void efx_ptp_get_ts_info(struct efx_nic *efx, struct ethtool_ts_info *ts_info);
 bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
+int efx_ptp_get_mode(struct efx_nic *efx);
+int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted,
+			unsigned int new_mode);
 int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
 void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev);
+void efx_time_sync_event(struct efx_channel *channel, efx_qword_t *ev);
+void __efx_rx_skb_attach_timestamp(struct efx_channel *channel,
+				   struct sk_buff *skb);
+static inline void efx_rx_skb_attach_timestamp(struct efx_channel *channel,
+					       struct sk_buff *skb)
+{
+	if (channel->sync_events_state == SYNC_EVENTS_VALID)
+		__efx_rx_skb_attach_timestamp(channel, skb);
+}
 void efx_ptp_start_datapath(struct efx_nic *efx);
 void efx_ptp_stop_datapath(struct efx_nic *efx);
 

drivers/net/ethernet/sfc/rx.c

@@ -476,14 +476,18 @@ static struct sk_buff *efx_rx_mk_skb(struct efx_channel *channel,
 	struct sk_buff *skb;
 
 	/* Allocate an SKB to store the headers */
-	skb = netdev_alloc_skb(efx->net_dev, hdr_len + EFX_PAGE_SKB_ALIGN);
+	skb = netdev_alloc_skb(efx->net_dev,
+			       efx->rx_ip_align + efx->rx_prefix_size +
+			       hdr_len);
 	if (unlikely(skb == NULL))
 		return NULL;
 
 	EFX_BUG_ON_PARANOID(rx_buf->len < hdr_len);
 
-	skb_reserve(skb, EFX_PAGE_SKB_ALIGN);
-	memcpy(__skb_put(skb, hdr_len), eh, hdr_len);
+	memcpy(skb->data + efx->rx_ip_align, eh - efx->rx_prefix_size,
+	       efx->rx_prefix_size + hdr_len);
+	skb_reserve(skb, efx->rx_ip_align + efx->rx_prefix_size);
+	__skb_put(skb, hdr_len);
 
 	/* Append the remaining page(s) onto the frag list */
 	if (rx_buf->len > hdr_len) {
@@ -620,6 +624,8 @@ static void efx_rx_deliver(struct efx_channel *channel, u8 *eh,
 	if (likely(rx_buf->flags & EFX_RX_PKT_CSUMMED))
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
+	efx_rx_skb_attach_timestamp(channel, skb);
+
 	if (channel->type->receive_skb)
 		if (channel->type->receive_skb(channel, skb))
 			return;

drivers/net/ethernet/sfc/siena.c

@@ -116,6 +116,54 @@ static int siena_test_chip(struct efx_nic *efx, struct efx_self_tests *tests)
 	return rc ? rc : rc2;
 }
 
+/**************************************************************************
+ *
+ * PTP
+ *
+ **************************************************************************
+ */
+
+static void siena_ptp_write_host_time(struct efx_nic *efx, u32 host_time)
+{
+	_efx_writed(efx, cpu_to_le32(host_time),
+		    FR_CZ_MC_TREG_SMEM + MC_SMEM_P0_PTP_TIME_OFST);
+}
+
+static int siena_ptp_set_ts_config(struct efx_nic *efx,
+				   struct hwtstamp_config *init)
+{
+	int rc;
+
+	switch (init->rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		/* if TX timestamping is still requested then leave PTP on */
+		return efx_ptp_change_mode(efx,
+					   init->tx_type != HWTSTAMP_TX_OFF,
+					   efx_ptp_get_mode(efx));
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+		init->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		return efx_ptp_change_mode(efx, true, MC_CMD_PTP_MODE_V1);
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+		init->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
+		rc = efx_ptp_change_mode(efx, true,
+					 MC_CMD_PTP_MODE_V2_ENHANCED);
+		/* bug 33070 - old versions of the firmware do not support the
+		 * improved UUID filtering option. Similarly old versions of the
+		 * application do not expect it to be enabled. If the firmware
+		 * does not accept the enhanced mode, fall back to the standard
+		 * PTP v2 UUID filtering. */
+		if (rc != 0)
+			rc = efx_ptp_change_mode(efx, true, MC_CMD_PTP_MODE_V2);
+		return rc;
+	default:
+		return -ERANGE;
+	}
+}
+
 /**************************************************************************
  *
  * Device reset
@@ -837,19 +885,6 @@ static int siena_mtd_probe(struct efx_nic *efx)
 
 #endif /* CONFIG_SFC_MTD */
 
-/**************************************************************************
- *
- * PTP
- *
- **************************************************************************
- */
-
-static void siena_ptp_write_host_time(struct efx_nic *efx, u32 host_time)
-{
-	_efx_writed(efx, cpu_to_le32(host_time),
-		    FR_CZ_MC_TREG_SMEM + MC_SMEM_P0_PTP_TIME_OFST);
-}
-
 /**************************************************************************
  *
  * Revision-dependent attributes used by efx.c and nic.c
@@ -942,6 +977,7 @@ const struct efx_nic_type siena_a0_nic_type = {
 	.mtd_sync = efx_mcdi_mtd_sync,
 #endif
 	.ptp_write_host_time = siena_ptp_write_host_time,
+	.ptp_set_ts_config = siena_ptp_set_ts_config,
 
 	.revision = EFX_REV_SIENA_A0,
 	.txd_ptr_tbl_base = FR_BZ_TX_DESC_PTR_TBL,
@@ -960,4 +996,11 @@ const struct efx_nic_type siena_a0_nic_type = {
 			     NETIF_F_RXHASH | NETIF_F_NTUPLE),
 	.mcdi_max_ver = 1,
 	.max_rx_ip_filters = FR_BZ_RX_FILTER_TBL0_ROWS,
+	.hwtstamp_filters = (1 << HWTSTAMP_FILTER_NONE |
+			     1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT |
+			     1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC |
+			     1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ |
+			     1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT |
+			     1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC |
+			     1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ),
 };