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

Ben Hutchings says:

====================
1. Extension to PPS/PTP to allow for PHC devices where pulses are
   subject to a variable but measurable delay.
2. PPS/PTP/PHC support for Solarflare boards with a timestamping
   peripheral.
3. MTD support for updating the timestamping peripheral on those boards.
4. Fix for potential over-length requests to firmware.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

17 files changed, 1671 insertions, 34 deletions

diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
index fb3cbc27063c..25906c1d1b15 100644
--- a/drivers/net/ethernet/sfc/Kconfig
+++ b/drivers/net/ethernet/sfc/Kconfig
@@ -34,3 +34,10 @@ config SFC_SRIOV
 	  This enables support for the SFC9000 I/O Virtualization
 	  features, allowing accelerated network performance in
 	  virtualized environments.
+config SFC_PTP
+	bool "Solarflare SFC9000-family PTP support"
+	depends on SFC && PTP_1588_CLOCK && !(SFC=y && PTP_1588_CLOCK=m)
+	default y
+	---help---
+	  This enables support for the Precision Time Protocol (PTP)
+	  on SFC9000-family NICs
diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index ea1f8db57318..e11f2ecf69d9 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -5,5 +5,6 @@ sfc-y			+= efx.o nic.o falcon.o siena.o tx.o rx.o filter.o \
 			   mcdi.o mcdi_phy.o mcdi_mon.o
 sfc-$(CONFIG_SFC_MTD)	+= mtd.o
 sfc-$(CONFIG_SFC_SRIOV)	+= siena_sriov.o
+sfc-$(CONFIG_SFC_PTP)	+= ptp.o
 
 obj-$(CONFIG_SFC)	+= sfc.o
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index a606db43c5ba..96bd980e828d 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -734,6 +734,7 @@ static void efx_remove_channel(struct efx_channel *channel)
 	efx_for_each_possible_channel_tx_queue(tx_queue, channel)
 		efx_remove_tx_queue(tx_queue);
 	efx_remove_eventq(channel);
+	channel->type->post_remove(channel);
 }
 
 static void efx_remove_channels(struct efx_nic *efx)
@@ -852,6 +853,7 @@ void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue)
 
 static const struct efx_channel_type efx_default_channel_type = {
 	.pre_probe		= efx_channel_dummy_op_int,
+	.post_remove		= efx_channel_dummy_op_void,
 	.get_name		= efx_get_channel_name,
 	.copy			= efx_copy_channel,
 	.keep_eventq		= false,
@@ -862,6 +864,10 @@ int efx_channel_dummy_op_int(struct efx_channel *channel)
 	return 0;
 }
 
+void efx_channel_dummy_op_void(struct efx_channel *channel)
+{
+}
+
 /**************************************************************************
  *
  * Port handling
@@ -1451,10 +1457,16 @@ static void efx_set_channels(struct efx_nic *efx)
 	efx->tx_channel_offset =
 		separate_tx_channels ? efx->n_channels - efx->n_tx_channels : 0;
 
-	/* We need to adjust the TX queue numbers if we have separate
+	/* We need to mark which channels really have RX and TX
+	 * queues, and adjust the TX queue numbers if we have separate
 	 * RX-only and TX-only channels.
 	 */
 	efx_for_each_channel(channel, efx) {
+		if (channel->channel < efx->n_rx_channels)
+			channel->rx_queue.core_index = channel->channel;
+		else
+			channel->rx_queue.core_index = -1;
+
 		efx_for_each_channel_tx_queue(tx_queue, channel)
 			tx_queue->queue -= (efx->tx_channel_offset *
 					    EFX_TXQ_TYPES);
@@ -1767,6 +1779,9 @@ static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
 	struct efx_nic *efx = netdev_priv(net_dev);
 	struct mii_ioctl_data *data = if_mii(ifr);
 
+	if (cmd == SIOCSHWTSTAMP)
+		return efx_ptp_ioctl(efx, ifr, cmd);
+
 	/* Convert phy_id from older PRTAD/DEVAD format */
 	if ((cmd == SIOCGMIIREG || cmd == SIOCSMIIREG) &&
 	    (data->phy_id & 0xfc00) == 0x0400)
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index 70755c97251a..f11170bc48bf 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -102,6 +102,7 @@ static inline void efx_filter_rfs_expire(struct efx_channel *channel) {}
 
 /* Channels */
 extern int efx_channel_dummy_op_int(struct efx_channel *channel);
+extern void efx_channel_dummy_op_void(struct efx_channel *channel);
 extern void efx_process_channel_now(struct efx_channel *channel);
 extern int
 efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries);
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index f8e7e204981f..9df556c01b8e 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -1174,6 +1174,7 @@ const struct ethtool_ops efx_ethtool_ops = {
 	.get_rxfh_indir_size	= efx_ethtool_get_rxfh_indir_size,
 	.get_rxfh_indir		= efx_ethtool_get_rxfh_indir,
 	.set_rxfh_indir		= efx_ethtool_set_rxfh_indir,
+	.get_ts_info		= efx_ptp_get_ts_info,
 	.get_module_info	= efx_ethtool_get_module_info,
 	.get_module_eeprom	= efx_ethtool_get_module_eeprom,
 };
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index fc5e7bbcbc9e..aea43cbd0520 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -320,14 +320,20 @@ static void efx_mcdi_ev_cpl(struct efx_nic *efx, unsigned int seqno,
 		efx_mcdi_complete(mcdi);
 }
 
-/* Issue the given command by writing the data into the shared memory PDU,
- * ring the doorbell and wait for completion. Copyout the result. */
 int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd,
 		 const u8 *inbuf, size_t inlen, u8 *outbuf, size_t outlen,
 		 size_t *outlen_actual)
 {
+	efx_mcdi_rpc_start(efx, cmd, inbuf, inlen);
+	return efx_mcdi_rpc_finish(efx, cmd, inlen,
+				   outbuf, outlen, outlen_actual);
+}
+
+void efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd, const u8 *inbuf,
+			size_t inlen)
+{
 	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
-	int rc;
+
 	BUG_ON(efx_nic_rev(efx) < EFX_REV_SIENA_A0);
 
 	efx_mcdi_acquire(mcdi);
@@ -338,6 +344,15 @@ int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd,
 	spin_unlock_bh(&mcdi->iface_lock);
 
 	efx_mcdi_copyin(efx, cmd, inbuf, inlen);
+}
+
+int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen,
+			u8 *outbuf, size_t outlen, size_t *outlen_actual)
+{
+	struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+	int rc;
+
+	BUG_ON(efx_nic_rev(efx) < EFX_REV_SIENA_A0);
 
 	if (mcdi->mode == MCDI_MODE_POLL)
 		rc = efx_mcdi_poll(efx);
@@ -563,6 +578,11 @@ void efx_mcdi_process_event(struct efx_channel *channel,
 	case MCDI_EVENT_CODE_FLR:
 		efx_sriov_flr(efx, MCDI_EVENT_FIELD(*event, FLR_VF));
 		break;
+	case MCDI_EVENT_CODE_PTP_RX:
+	case MCDI_EVENT_CODE_PTP_FAULT:
+	case MCDI_EVENT_CODE_PTP_PPS:
+		efx_ptp_event(efx, event);
+		break;
 
 	default:
 		netif_err(efx, hw, efx->net_dev, "Unknown MCDI event 0x%x\n",
@@ -641,9 +661,8 @@ int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address,
 			   u16 *fw_subtype_list, u32 *capabilities)
 {
 	uint8_t outbuf[MC_CMD_GET_BOARD_CFG_OUT_LENMIN];
-	size_t outlen;
+	size_t outlen, offset, i;
 	int port_num = efx_port_num(efx);
-	int offset;
 	int rc;
 
 	BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_IN_LEN != 0);
@@ -663,11 +682,18 @@ int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address,
 		: MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_OFST;
 	if (mac_address)
 		memcpy(mac_address, outbuf + offset, ETH_ALEN);
-	if (fw_subtype_list)
-		memcpy(fw_subtype_list,
-		       outbuf + MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_OFST,
-		       MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MINNUM *
-		       sizeof(fw_subtype_list[0]));
+	if (fw_subtype_list) {
+		/* Byte-swap and truncate or zero-pad as necessary */
+		offset = MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_OFST;
+		for (i = 0;
+		     i < MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MAXNUM;
+		     i++) {
+			fw_subtype_list[i] =
+				(offset + 2 <= outlen) ?
+				le16_to_cpup((__le16 *)(outbuf + offset)) : 0;
+			offset += 2;
+		}
+	}
 	if (capabilities) {
 		if (port_num)
 			*capabilities = MCDI_DWORD(outbuf,
@@ -1169,6 +1195,9 @@ int efx_mcdi_flush_rxqs(struct efx_nic *efx)
 	__le32 *qid;
 	int rc, count;
 
+	BUILD_BUG_ON(EFX_MAX_CHANNELS >
+		     MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM);
+
 	qid = kmalloc(EFX_MAX_CHANNELS * sizeof(*qid), GFP_KERNEL);
 	if (qid == NULL)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index 0bdf3e331832..dc25caaa3983 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -71,6 +71,12 @@ extern int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, const u8 *inbuf,
 			size_t inlen, u8 *outbuf, size_t outlen,
 			size_t *outlen_actual);
 
+extern void efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd,
+			       const u8 *inbuf, size_t inlen);
+extern int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen,
+			       u8 *outbuf, size_t outlen,
+			       size_t *outlen_actual);
+
 extern int efx_mcdi_poll_reboot(struct efx_nic *efx);
 extern void efx_mcdi_mode_poll(struct efx_nic *efx);
 extern void efx_mcdi_mode_event(struct efx_nic *efx);
diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h
index db4beed97669..9d426d0457bd 100644
--- a/drivers/net/ethernet/sfc/mcdi_pcol.h
+++ b/drivers/net/ethernet/sfc/mcdi_pcol.h
@@ -289,6 +289,7 @@
 #define          MCDI_EVENT_CODE_TX_FLUSH  0xc /* enum */
 #define          MCDI_EVENT_CODE_PTP_RX  0xd /* enum */
 #define          MCDI_EVENT_CODE_PTP_FAULT  0xe /* enum */
+#define          MCDI_EVENT_CODE_PTP_PPS  0xf /* enum */
 #define       MCDI_EVENT_CMDDONE_DATA_OFST 0
 #define       MCDI_EVENT_CMDDONE_DATA_LBN 0
 #define       MCDI_EVENT_CMDDONE_DATA_WIDTH 32
@@ -491,12 +492,12 @@
 
 /* MC_CMD_GET_FPGAREG_OUT msgresponse */
 #define    MC_CMD_GET_FPGAREG_OUT_LENMIN 1
-#define    MC_CMD_GET_FPGAREG_OUT_LENMAX 255
+#define    MC_CMD_GET_FPGAREG_OUT_LENMAX 252
 #define    MC_CMD_GET_FPGAREG_OUT_LEN(num) (0+1*(num))
 #define       MC_CMD_GET_FPGAREG_OUT_BUFFER_OFST 0
 #define       MC_CMD_GET_FPGAREG_OUT_BUFFER_LEN 1
 #define       MC_CMD_GET_FPGAREG_OUT_BUFFER_MINNUM 1
-#define       MC_CMD_GET_FPGAREG_OUT_BUFFER_MAXNUM 255
+#define       MC_CMD_GET_FPGAREG_OUT_BUFFER_MAXNUM 252
 
 
 /***********************************/
@@ -507,13 +508,13 @@
 
 /* MC_CMD_PUT_FPGAREG_IN msgrequest */
 #define    MC_CMD_PUT_FPGAREG_IN_LENMIN 5
-#define    MC_CMD_PUT_FPGAREG_IN_LENMAX 255
+#define    MC_CMD_PUT_FPGAREG_IN_LENMAX 252
 #define    MC_CMD_PUT_FPGAREG_IN_LEN(num) (4+1*(num))
 #define       MC_CMD_PUT_FPGAREG_IN_ADDR_OFST 0
 #define       MC_CMD_PUT_FPGAREG_IN_BUFFER_OFST 4
 #define       MC_CMD_PUT_FPGAREG_IN_BUFFER_LEN 1
 #define       MC_CMD_PUT_FPGAREG_IN_BUFFER_MINNUM 1
-#define       MC_CMD_PUT_FPGAREG_IN_BUFFER_MAXNUM 251
+#define       MC_CMD_PUT_FPGAREG_IN_BUFFER_MAXNUM 248
 
 /* MC_CMD_PUT_FPGAREG_OUT msgresponse */
 #define    MC_CMD_PUT_FPGAREG_OUT_LEN 0
@@ -560,7 +561,7 @@
 
 /* MC_CMD_PTP_IN_TRANSMIT msgrequest */
 #define    MC_CMD_PTP_IN_TRANSMIT_LENMIN 13
-#define    MC_CMD_PTP_IN_TRANSMIT_LENMAX 255
+#define    MC_CMD_PTP_IN_TRANSMIT_LENMAX 252
 #define    MC_CMD_PTP_IN_TRANSMIT_LEN(num) (12+1*(num))
 /*            MC_CMD_PTP_IN_CMD_OFST 0 */
 /*            MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
@@ -568,7 +569,7 @@
 #define       MC_CMD_PTP_IN_TRANSMIT_PACKET_OFST 12
 #define       MC_CMD_PTP_IN_TRANSMIT_PACKET_LEN 1
 #define       MC_CMD_PTP_IN_TRANSMIT_PACKET_MINNUM 1
-#define       MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM 243
+#define       MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM 240
 
 /* MC_CMD_PTP_IN_READ_NIC_TIME msgrequest */
 #define    MC_CMD_PTP_IN_READ_NIC_TIME_LEN 8
@@ -1145,7 +1146,7 @@
 
 /* MC_CMD_PUTS_IN msgrequest */
 #define    MC_CMD_PUTS_IN_LENMIN 13
-#define    MC_CMD_PUTS_IN_LENMAX 255
+#define    MC_CMD_PUTS_IN_LENMAX 252
 #define    MC_CMD_PUTS_IN_LEN(num) (12+1*(num))
 #define       MC_CMD_PUTS_IN_DEST_OFST 0
 #define        MC_CMD_PUTS_IN_UART_LBN 0
@@ -1157,7 +1158,7 @@
 #define       MC_CMD_PUTS_IN_STRING_OFST 12
 #define       MC_CMD_PUTS_IN_STRING_LEN 1
 #define       MC_CMD_PUTS_IN_STRING_MINNUM 1
-#define       MC_CMD_PUTS_IN_STRING_MAXNUM 243
+#define       MC_CMD_PUTS_IN_STRING_MAXNUM 240
 
 /* MC_CMD_PUTS_OUT msgresponse */
 #define    MC_CMD_PUTS_OUT_LEN 0
@@ -1947,12 +1948,12 @@
 
 /* MC_CMD_NVRAM_READ_OUT msgresponse */
 #define    MC_CMD_NVRAM_READ_OUT_LENMIN 1
-#define    MC_CMD_NVRAM_READ_OUT_LENMAX 255
+#define    MC_CMD_NVRAM_READ_OUT_LENMAX 252
 #define    MC_CMD_NVRAM_READ_OUT_LEN(num) (0+1*(num))
 #define       MC_CMD_NVRAM_READ_OUT_READ_BUFFER_OFST 0
 #define       MC_CMD_NVRAM_READ_OUT_READ_BUFFER_LEN 1
 #define       MC_CMD_NVRAM_READ_OUT_READ_BUFFER_MINNUM 1
-#define       MC_CMD_NVRAM_READ_OUT_READ_BUFFER_MAXNUM 255
+#define       MC_CMD_NVRAM_READ_OUT_READ_BUFFER_MAXNUM 252
 
 
 /***********************************/
@@ -1963,7 +1964,7 @@
 
 /* MC_CMD_NVRAM_WRITE_IN msgrequest */
 #define    MC_CMD_NVRAM_WRITE_IN_LENMIN 13
-#define    MC_CMD_NVRAM_WRITE_IN_LENMAX 255
+#define    MC_CMD_NVRAM_WRITE_IN_LENMAX 252
 #define    MC_CMD_NVRAM_WRITE_IN_LEN(num) (12+1*(num))
 #define       MC_CMD_NVRAM_WRITE_IN_TYPE_OFST 0
 /*            Enum values, see field(s): */
@@ -1973,7 +1974,7 @@
 #define       MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_OFST 12
 #define       MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_LEN 1
 #define       MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MINNUM 1
-#define       MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MAXNUM 243
+#define       MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MAXNUM 240
 
 /* MC_CMD_NVRAM_WRITE_OUT msgresponse */
 #define    MC_CMD_NVRAM_WRITE_OUT_LEN 0
@@ -2305,13 +2306,13 @@
 
 /* MC_CMD_GET_PHY_MEDIA_INFO_OUT msgresponse */
 #define    MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMIN 5
-#define    MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMAX 255
+#define    MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMAX 252
 #define    MC_CMD_GET_PHY_MEDIA_INFO_OUT_LEN(num) (4+1*(num))
 #define       MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATALEN_OFST 0
 #define       MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_OFST 4
 #define       MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_LEN 1
 #define       MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_MINNUM 1
-#define       MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_MAXNUM 251
+#define       MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_MAXNUM 248
 
 
 /***********************************/
diff --git a/drivers/net/ethernet/sfc/mtd.c b/drivers/net/ethernet/sfc/mtd.c
index 758148379b0e..08f825b71ac8 100644
--- a/drivers/net/ethernet/sfc/mtd.c
+++ b/drivers/net/ethernet/sfc/mtd.c
@@ -585,6 +585,7 @@ static const struct siena_nvram_type_info siena_nvram_types[] = {
 	[MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT1]	= { 1, "sfc_exp_rom_cfg" },
 	[MC_CMD_NVRAM_TYPE_PHY_PORT0]		= { 0, "sfc_phy_fw" },
 	[MC_CMD_NVRAM_TYPE_PHY_PORT1]		= { 1, "sfc_phy_fw" },
+	[MC_CMD_NVRAM_TYPE_FPGA]		= { 0, "sfc_fpga" },
 };
 
 static int siena_mtd_probe_partition(struct efx_nic *efx,
@@ -598,7 +599,8 @@ static int siena_mtd_probe_partition(struct efx_nic *efx,
 	bool protected;
 	int rc;
 
-	if (type >= ARRAY_SIZE(siena_nvram_types))
+	if (type >= ARRAY_SIZE(siena_nvram_types) ||
+	    siena_nvram_types[type].name == NULL)
 		return -ENODEV;
 
 	info = &siena_nvram_types[type];
@@ -627,7 +629,8 @@ static int siena_mtd_get_fw_subtypes(struct efx_nic *efx,
 				     struct efx_mtd *efx_mtd)
 {
 	struct efx_mtd_partition *part;
-	uint16_t fw_subtype_list[MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MINNUM];
+	uint16_t fw_subtype_list[
+		MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MAXNUM];
 	int rc;
 
 	rc = efx_mcdi_get_board_cfg(efx, NULL, fw_subtype_list, NULL);
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 7ab1232494ef..c1a010cda89b 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -37,7 +37,7 @@
  *
  **************************************************************************/
 
-#define EFX_DRIVER_VERSION	"3.1"
+#define EFX_DRIVER_VERSION	"3.2"
 
 #ifdef DEBUG
 #define EFX_BUG_ON_PARANOID(x) BUG_ON(x)
@@ -56,7 +56,8 @@
 #define EFX_MAX_CHANNELS 32U
 #define EFX_MAX_RX_QUEUES EFX_MAX_CHANNELS
 #define EFX_EXTRA_CHANNEL_IOV	0
-#define EFX_MAX_EXTRA_CHANNELS	1U
+#define EFX_EXTRA_CHANNEL_PTP	1
+#define EFX_MAX_EXTRA_CHANNELS	2U
 
 /* Checksum generation is a per-queue option in hardware, so each
  * queue visible to the networking core is backed by two hardware TX
@@ -68,6 +69,9 @@
 #define EFX_TXQ_TYPES		4
 #define EFX_MAX_TX_QUEUES	(EFX_TXQ_TYPES * EFX_MAX_CHANNELS)
 
+/* Forward declare Precision Time Protocol (PTP) support structure. */
+struct efx_ptp_data;
+
 struct efx_self_tests;
 
 /**
@@ -242,6 +246,8 @@ struct efx_rx_page_state {
 /**
  * struct efx_rx_queue - An Efx RX queue
  * @efx: The associated Efx NIC
+ * @core_index:  Index of network core RX queue.  Will be >= 0 iff this
+ *	is associated with a real RX queue.
  * @buffer: The software buffer ring
  * @rxd: The hardware descriptor ring
  * @ptr_mask: The size of the ring minus 1.
@@ -263,6 +269,7 @@ struct efx_rx_page_state {
  */
 struct efx_rx_queue {
 	struct efx_nic *efx;
+	int core_index;
 	struct efx_rx_buffer *buffer;
 	struct efx_special_buffer rxd;
 	unsigned int ptr_mask;
@@ -390,14 +397,17 @@ struct efx_channel {
  * @get_name: Generate the channel's name (used for its IRQ handler)
  * @copy: Copy the channel state prior to reallocation.  May be %NULL if
  *	reallocation is not supported.
+ * @receive_skb: Handle an skb ready to be passed to netif_receive_skb()
  * @keep_eventq: Flag for whether event queue should be kept initialised
  *	while the device is stopped
  */
 struct efx_channel_type {
 	void (*handle_no_channel)(struct efx_nic *);
 	int (*pre_probe)(struct efx_channel *);
+	void (*post_remove)(struct efx_channel *);
 	void (*get_name)(struct efx_channel *, char *buf, size_t len);
 	struct efx_channel *(*copy)(const struct efx_channel *);
+	void (*receive_skb)(struct efx_channel *, struct sk_buff *);
 	bool keep_eventq;
 };
 
@@ -730,6 +740,7 @@ struct vfdi_status;
  *	%local_addr_list. Protected by %local_lock.
  * @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
  * @monitor_work: Hardware monitor workitem
  * @biu_lock: BIU (bus interface unit) lock
  * @last_irq_cpu: Last CPU to handle a possible test interrupt.  This
@@ -857,6 +868,10 @@ struct efx_nic {
 	struct work_struct peer_work;
 #endif
 
+#ifdef CONFIG_SFC_PTP
+	struct efx_ptp_data *ptp_data;
+#endif
+
 	/* The following fields may be written more often */
 
 	struct delayed_work monitor_work ____cacheline_aligned_in_smp;
@@ -1047,7 +1062,7 @@ static inline bool efx_tx_queue_used(struct efx_tx_queue *tx_queue)
 
 static inline bool efx_channel_has_rx_queue(struct efx_channel *channel)
 {
-	return channel->channel < channel->efx->n_rx_channels;
+	return channel->rx_queue.core_index >= 0;
 }
 
 static inline struct efx_rx_queue *
@@ -1119,5 +1134,13 @@ static inline void clear_bit_le(unsigned nr, unsigned char *addr)
 #define EFX_MAX_FRAME_LEN(mtu) \
 	((((mtu) + ETH_HLEN + VLAN_HLEN + 4/* FCS */ + 7) & ~7) + 16)
 
+static inline bool efx_xmit_with_hwtstamp(struct sk_buff *skb)
+{
+	return skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP;
+}
+static inline void efx_xmit_hwtstamp_pending(struct sk_buff *skb)
+{
+	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+}
 
 #endif /* EFX_NET_DRIVER_H */
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index bab5cd9f5740..438cef11f727 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -11,6 +11,7 @@
 #ifndef EFX_NIC_H
 #define EFX_NIC_H
 
+#include <linux/net_tstamp.h>
 #include <linux/i2c-algo-bit.h>
 #include "net_driver.h"
 #include "efx.h"
@@ -250,6 +251,41 @@ extern int efx_sriov_get_vf_config(struct net_device *dev, int vf,
 extern int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf,
 				     bool spoofchk);
 
+struct ethtool_ts_info;
+#ifdef CONFIG_SFC_PTP
+extern void efx_ptp_probe(struct efx_nic *efx);
+extern int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd);
+extern int efx_ptp_get_ts_info(struct net_device *net_dev,
+			       struct ethtool_ts_info *ts_info);
+extern bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
+extern int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
+extern void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev);
+#else
+static inline void efx_ptp_probe(struct efx_nic *efx) {}
+static inline int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd)
+{
+	return -EOPNOTSUPP;
+}
+static inline int efx_ptp_get_ts_info(struct net_device *net_dev,
+				      struct ethtool_ts_info *ts_info)
+{
+	ts_info->so_timestamping = (SOF_TIMESTAMPING_SOFTWARE |
+				    SOF_TIMESTAMPING_RX_SOFTWARE);
+	ts_info->phc_index = -1;
+
+	return 0;
+}
+static inline bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
+{
+	return false;
+}
+static inline int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
+{
+	return NETDEV_TX_OK;
+}
+static inline void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev) {}
+#endif
+
 extern const struct efx_nic_type falcon_a1_nic_type;
 extern const struct efx_nic_type falcon_b0_nic_type;
 extern const struct efx_nic_type siena_a0_nic_type;
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
new file mode 100644
index 000000000000..2b07a4eae07e
--- /dev/null
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -0,0 +1,1483 @@
+/****************************************************************************
+ * Driver for Solarflare Solarstorm network controllers and boards
+ * Copyright 2011 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+/* Theory of operation:
+ *
+ * PTP support is assisted by firmware running on the MC, which provides
+ * the hardware timestamping capabilities.  Both transmitted and received
+ * PTP event packets are queued onto internal queues for subsequent processing;
+ * this is because the MC operations are relatively long and would block
+ * block NAPI/interrupt operation.
+ *
+ * Receive event processing:
+ *	The event contains the packet's UUID and sequence number, together
+ *	with the hardware timestamp.  The PTP receive packet queue is searched
+ *	for this UUID/sequence number and, if found, put on a pending queue.
+ *	Packets not matching are delivered without timestamps (MCDI events will
+ *	always arrive after the actual packet).
+ *	It is important for the operation of the PTP protocol that the ordering
+ *	of packets between the event and general port is maintained.
+ *
+ * Work queue processing:
+ *	If work waiting, synchronise host/hardware time
+ *
+ *	Transmit: send packet through MC, which returns the transmission time
+ *	that is converted to an appropriate timestamp.
+ *
+ *	Receive: the packet's reception time is converted to an appropriate
+ *	timestamp.
+ */
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/time.h>
+#include <linux/ktime.h>
+#include <linux/module.h>
+#include <linux/net_tstamp.h>
+#include <linux/pps_kernel.h>
+#include <linux/ptp_clock_kernel.h>
+#include "net_driver.h"
+#include "efx.h"
+#include "mcdi.h"
+#include "mcdi_pcol.h"
+#include "io.h"
+#include "regs.h"
+#include "nic.h"
+
+/* Maximum number of events expected to make up a PTP event */
+#define	MAX_EVENT_FRAGS			3
+
+/* Maximum delay, ms, to begin synchronisation */
+#define	MAX_SYNCHRONISE_WAIT_MS		2
+
+/* How long, at most, to spend synchronising */
+#define	SYNCHRONISE_PERIOD_NS		250000
+
+/* How often to update the shared memory time */
+#define	SYNCHRONISATION_GRANULARITY_NS	200
+
+/* Minimum permitted length of a (corrected) synchronisation time */
+#define	MIN_SYNCHRONISATION_NS		120
+
+/* Maximum permitted length of a (corrected) synchronisation time */
+#define	MAX_SYNCHRONISATION_NS		1000
+
+/* How many (MC) receive events that can be queued */
+#define	MAX_RECEIVE_EVENTS		8
+
+/* Length of (modified) moving average. */
+#define	AVERAGE_LENGTH			16
+
+/* How long an unmatched event or packet can be held */
+#define PKT_EVENT_LIFETIME_MS		10
+
+/* Offsets into PTP packet for identification.  These offsets are from the
+ * start of the IP header, not the MAC header.  Note that neither PTP V1 nor
+ * PTP V2 permit the use of IPV4 options.
+ */
+#define PTP_DPORT_OFFSET	22
+
+#define PTP_V1_VERSION_LENGTH	2
+#define PTP_V1_VERSION_OFFSET	28
+
+#define PTP_V1_UUID_LENGTH	6
+#define PTP_V1_UUID_OFFSET	50
+
+#define PTP_V1_SEQUENCE_LENGTH	2
+#define PTP_V1_SEQUENCE_OFFSET	58
+
+/* The minimum length of a PTP V1 packet for offsets, etc. to be valid:
+ * includes IP header.
+ */
+#define	PTP_V1_MIN_LENGTH	64
+
+#define PTP_V2_VERSION_LENGTH	1
+#define PTP_V2_VERSION_OFFSET	29
+
+/* Although PTP V2 UUIDs are comprised a ClockIdentity (8) and PortNumber (2),
+ * the MC only captures the last six bytes of the clock identity. These values
+ * reflect those, not the ones used in the standard.  The standard permits
+ * mapping of V1 UUIDs to V2 UUIDs with these same values.
+ */
+#define PTP_V2_MC_UUID_LENGTH	6
+#define PTP_V2_MC_UUID_OFFSET	50
+
+#define PTP_V2_SEQUENCE_LENGTH	2
+#define PTP_V2_SEQUENCE_OFFSET	58
+
+/* The minimum length of a PTP V2 packet for offsets, etc. to be valid:
+ * includes IP header.
+ */
+#define	PTP_V2_MIN_LENGTH	63
+
+#define	PTP_MIN_LENGTH		63
+
+#define PTP_ADDRESS		0xe0000181	/* 224.0.1.129 */
+#define PTP_EVENT_PORT		319
+#define PTP_GENERAL_PORT	320
+
+/* Annoyingly the format of the version numbers are different between
+ * versions 1 and 2 so it isn't possible to simply look for 1 or 2.
+ */
+#define	PTP_VERSION_V1		1
+
+#define	PTP_VERSION_V2		2
+#define	PTP_VERSION_V2_MASK	0x0f
+
+enum ptp_packet_state {
+	PTP_PACKET_STATE_UNMATCHED = 0,
+	PTP_PACKET_STATE_MATCHED,
+	PTP_PACKET_STATE_TIMED_OUT,
+	PTP_PACKET_STATE_MATCH_UNWANTED
+};
+
+/* NIC synchronised with single word of time only comprising
+ * partial seconds and full nanoseconds: 10^9 ~ 2^30 so 2 bits for seconds.
+ */
+#define	MC_NANOSECOND_BITS	30
+#define	MC_NANOSECOND_MASK	((1 << MC_NANOSECOND_BITS) - 1)
+#define	MC_SECOND_MASK		((1 << (32 - MC_NANOSECOND_BITS)) - 1)
+
+/* Maximum parts-per-billion adjustment that is acceptable */
+#define MAX_PPB			1000000
+
+/* Number of bits required to hold the above */
+#define	MAX_PPB_BITS		20
+
+/* Number of extra bits allowed when calculating fractional ns.
+ * EXTRA_BITS + MC_CMD_PTP_IN_ADJUST_BITS + MAX_PPB_BITS should
+ * be less than 63.
+ */
+#define	PPB_EXTRA_BITS		2
+
+/* Precalculate scale word to avoid long long division at runtime */
+#define	PPB_SCALE_WORD	((1LL << (PPB_EXTRA_BITS + MC_CMD_PTP_IN_ADJUST_BITS +\
+			MAX_PPB_BITS)) / 1000000000LL)
+
+#define PTP_SYNC_ATTEMPTS	4
+
+/**
+ * struct efx_ptp_match - Matching structure, stored in sk_buff's cb area.
+ * @words: UUID and (partial) sequence number
+ * @expiry: Time after which the packet should be delivered irrespective of
+ *            event arrival.
+ * @state: The state of the packet - whether it is ready for processing or
+ *         whether that is of no interest.
+ */
+struct efx_ptp_match {
+	u32 words[DIV_ROUND_UP(PTP_V1_UUID_LENGTH, 4)];
+	unsigned long expiry;
+	enum ptp_packet_state state;
+};
+
+/**
+ * struct efx_ptp_event_rx - A PTP receive event (from MC)
+ * @seq0: First part of (PTP) UUID
+ * @seq1: Second part of (PTP) UUID and sequence number
+ * @hwtimestamp: Event timestamp
+ */
+struct efx_ptp_event_rx {
+	struct list_head link;
+	u32 seq0;
+	u32 seq1;
+	ktime_t hwtimestamp;
+	unsigned long expiry;
+};
+
+/**
+ * struct efx_ptp_timeset - Synchronisation between host and MC
+ * @host_start: Host time immediately before hardware timestamp taken
+ * @seconds: Hardware timestamp, seconds
+ * @nanoseconds: Hardware timestamp, nanoseconds
+ * @host_end: Host time immediately after hardware timestamp taken
+ * @waitns: Number of nanoseconds between hardware timestamp being read and
+ *          host end time being seen
+ * @window: Difference of host_end and host_start
+ * @valid: Whether this timeset is valid
+ */
+struct efx_ptp_timeset {
+	u32 host_start;
+	u32 seconds;
+	u32 nanoseconds;
+	u32 host_end;
+	u32 waitns;
+	u32 window;	/* Derived: end - start, allowing for wrap */
+};
+
+/**
+ * struct efx_ptp_data - Precision Time Protocol (PTP) state
+ * @channel: The PTP channel
+ * @rxq: Receive queue (awaiting timestamps)
+ * @txq: Transmit queue
+ * @evt_list: List of MC receive events awaiting packets
+ * @evt_free_list: List of free events
+ * @evt_lock: Lock for manipulating evt_list and evt_free_list
+ * @rx_evts: Instantiated events (on evt_list and evt_free_list)
+ * @workwq: Work queue for processing pending PTP operations
+ * @work: Work task
+ * @reset_required: A serious error has occurred and the PTP task needs to be
+ *                  reset (disable, enable).
+ * @rxfilter_event: Receive filter when operating
+ * @rxfilter_general: Receive filter when operating
+ * @config: Current timestamp configuration
+ * @enabled: PTP operation enabled
+ * @mode: Mode in which PTP operating (PTP version)
+ * @evt_frags: Partly assembled PTP events
+ * @evt_frag_idx: Current fragment number
+ * @evt_code: Last event code
+ * @start: Address at which MC indicates ready for synchronisation
+ * @host_time_pps: Host time at last PPS
+ * @last_sync_ns: Last number of nanoseconds between readings when synchronising
+ * @base_sync_ns: Number of nanoseconds for last synchronisation.
+ * @base_sync_valid: Whether base_sync_time is valid.
+ * @current_adjfreq: Current ppb adjustment.
+ * @phc_clock: Pointer to registered phc device
+ * @phc_clock_info: Registration structure for phc device
+ * @pps_work: pps work task for handling pps events
+ * @pps_workwq: pps work queue
+ * @nic_ts_enabled: Flag indicating if NIC generated TS events are handled
+ * @txbuf: Buffer for use when transmitting (PTP) packets to MC (avoids
+ *         allocations in main data path).
+ * @debug_ptp_dir: PTP debugfs directory
+ * @missed_rx_sync: Number of packets received without syncrhonisation.
+ * @good_syncs: Number of successful synchronisations.
+ * @no_time_syncs: Number of synchronisations with no good times.
+ * @bad_sync_durations: Number of synchronisations with bad durations.
+ * @bad_syncs: Number of failed synchronisations.
+ * @last_sync_time: Number of nanoseconds for last synchronisation.
+ * @sync_timeouts: Number of synchronisation timeouts
+ * @fast_syncs: Number of synchronisations requiring short delay
+ * @min_sync_delta: Minimum time between event and synchronisation
+ * @max_sync_delta: Maximum time between event and synchronisation
+ * @average_sync_delta: Average time between event and synchronisation.
+ *                      Modified moving average.
+ * @last_sync_delta: Last time between event and synchronisation
+ * @mc_stats: Context value for MC statistics
+ * @timeset: Last set of synchronisation statistics.
+ */
+struct efx_ptp_data {
+	struct efx_channel *channel;
+	struct sk_buff_head rxq;
+	struct sk_buff_head txq;
+	struct list_head evt_list;
+	struct list_head evt_free_list;
+	spinlock_t evt_lock;
+	struct efx_ptp_event_rx rx_evts[MAX_RECEIVE_EVENTS];
+	struct workqueue_struct *workwq;
+	struct work_struct work;
+	bool reset_required;
+	u32 rxfilter_event;
+	u32 rxfilter_general;
+	bool rxfilter_installed;
+	struct hwtstamp_config config;
+	bool enabled;
+	unsigned int mode;
+	efx_qword_t evt_frags[MAX_EVENT_FRAGS];
+	int evt_frag_idx;
+	int evt_code;
+	struct efx_buffer start;
+	struct pps_event_time host_time_pps;
+	unsigned last_sync_ns;