sfc: Add support for IEEE-1588 PTP

Add PTP IEEE-1588 support and make accesible via the PHC subsystem.

This work is based on prior code by Andrew Jackson

Signed-off-by: Stuart Hodgson <smhodgson@solarflare.com>
[bwh:
 - Add byte order conversion in efx_ptp_send_times()
 - Simplify conversion of PPS event times
 - Add the built-in vs module check to CONFIG_SFC_PTP dependencies]
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

11 files changed, 1562 insertions, 1 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 8b79a6413fe4..96bd980e828d 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1779,6 +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/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 2707e86def9e..294df4bca4a6 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -578,6 +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",
diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h
index 50389326bec8..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
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 0f0926e68963..797dbed25d94 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -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;
 
 /**
@@ -736,6 +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
@@ -863,6 +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;
@@ -1125,5 +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;
+	unsigned base_sync_ns;
+	bool base_sync_valid;
+	s64 current_adjfreq;
+	struct ptp_clock *phc_clock;
+	struct ptp_clock_info phc_clock_info;
+	struct work_struct pps_work;
+	struct workqueue_struct *pps_workwq;
+	bool nic_ts_enabled;
+	u8 txbuf[ALIGN(MC_CMD_PTP_IN_TRANSMIT_LEN(
+			       MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM), 4)];
+	struct efx_ptp_timeset
+	timeset[MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_MAXNUM];
+};
+
+static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta);
+static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta);
+static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts);
+static int efx_phc_settime(struct ptp_clock_info *ptp,
+			   const struct timespec *e_ts);
+static int efx_phc_enable(struct ptp_clock_info *ptp,
+			  struct ptp_clock_request *request, int on);
+
+/* Enable MCDI PTP support. */
+static int efx_ptp_enable(struct efx_nic *efx)
+{
+	u8 inbuf[MC_CMD_PTP_IN_ENABLE_LEN];
+
+	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_ENABLE);
+	MCDI_SET_DWORD(inbuf, PTP_IN_ENABLE_QUEUE,
+		       efx->ptp_data->channel->channel);
+	MCDI_SET_DWORD(inbuf, PTP_IN_ENABLE_MODE, efx->ptp_data->mode);
+
+	return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL);
+}
+
+/* Disable MCDI PTP support.
+ *
+ * Note that this function should never rely on the presence of ptp_data -
+ * may be called before that exists.
+ */
+static int efx_ptp_disable(struct efx_nic *efx)
+{
+	u8 inbuf[MC_CMD_PTP_IN_DISABLE_LEN];
+
+	MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_DISABLE);
+	return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL);
+}
+
+static void efx_ptp_deliver_rx_queue(struct sk_buff_head *q)
+{
+	struct sk_buff *skb;
+
+	while ((skb = skb_dequeue(q))) {
+		local_bh_disable();
+		netif_receive_skb(skb);
+		local_bh_enable();
+	}
+}
+
+static void efx_ptp_handle_no_channel(struct efx_nic *efx)
+{
+	netif_err(efx, drv, efx->net_dev,
+		  "ERROR: PTP requires MSI-X and 1 additional interrupt"
+		  "vector. PTP disabled\n");
+}
+
+/* Repeatedly send the host time to the MC which will capture the hardware
+ * time.
+ */
+static void efx_ptp_send_times(struct efx_nic *efx,
+			       struct pps_event_time *last_time)
+{
+	struct pps_event_time now;
+	struct timespec limit;
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	struct timespec start;
+	int *mc_running = ptp->start.addr;
+
+	pps_get_ts(&now);
+	start = now.ts_real;
+	limit = now.ts_real;
+	timespec_add_ns(&limit, SYNCHRONISE_PERIOD_NS);
+
+	/* Write host time for specified period or until MC is done */
+	while ((timespec_compare(&now.ts_real, &limit) < 0) &&
+	       ACCESS_ONCE(*mc_running)) {
+		struct timespec update_time;
+		unsigned int host_time;
+
+		/* Don't update continuously to avoid saturating the PCIe bus */
+		update_time = now.ts_real;
+		timespec_add_ns(&update_time, SYNCHRONISATION_GRANULARITY_NS);
+		do {
+			pps_get_ts(&now);
+		} while ((timespec_compare(&now.ts_real, &update_time) < 0) &&
+			 ACCESS_ONCE(*mc_running));
+
+		/* Synchronise NIC with single word of time only */
+		host_time = (now.ts_real.tv_sec << MC_NANOSECOND_BITS |
+			     now.ts_real.tv_nsec);
+		/* Update host time in NIC memory */
+		_efx_writed(efx, cpu_to_le32(host_time),
+			    FR_CZ_MC_TREG_SMEM + MC_SMEM_P0_PTP_TIME_OFST);
+	}
+	*last_time = now;
+}
+
+/* Read a timeset from the MC's results and partial process. */
+static void efx_ptp_read_timeset(u8 *data, struct efx_ptp_timeset *timeset)
+{
+	unsigned start_ns, end_ns;
+
+	timeset->host_start = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTSTART);
+	timeset->seconds = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_SECONDS);
+	timeset->nanoseconds = MCDI_DWORD(data,
+					 PTP_OUT_SYNCHRONIZE_NANOSECONDS);
+	timeset->host_end = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTEND),
+	timeset->waitns = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_WAITNS);
+
+	/* Ignore seconds */
+	start_ns = timeset->host_start & MC_NANOSECOND_MASK;
+	end_ns = timeset->host_end & MC_NANOSECOND_MASK;
+	/* Allow for rollover */
+	if (end_ns < start_ns)
+		end_ns += NSEC_PER_SEC;
+	/* Determine duration of operation */
+	timeset->window = end_ns - start_ns;
+}
+
+/* Process times received from MC.
+ *
+ * Extract times from returned results, and establish the minimum value
+ * seen.  The minimum value represents the "best" possible time and events
+ * too much greater than this are rejected - the machine is, perhaps, too
+ * busy. A number of readings are taken so that, hopefully, at least one good
+ * synchronisation will be seen in the results.
+ */
+static int efx_ptp_process_times(struct efx_nic *efx, u8 *synch_buf,
+				 size_t response_length,
+				 const struct pps_event_time *last_time)
+{
+	unsigned number_readings = (response_length /
+			       MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_LEN);
+	unsigned i;
+	unsigned min;
+	unsigned min_set = 0;
+	unsigned total;
+	unsigned ngood = 0;
+	unsigned last_good = 0;
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	bool min_valid = false;
+	u32 last_sec;
+	u32 start_sec;
+	struct timespec delta;
+
+	if (number_readings == 0)
+		return -EAGAIN;
+
+	/* Find minimum value in this set of results, discarding clearly
+	 * erroneous results.
+	 */
+	for (i = 0; i < number_readings; i++) {
+		efx_ptp_read_timeset(synch_buf, &ptp->timeset[i]);
+		synch_buf += MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_LEN;
+		if (ptp->timeset[i].window > SYNCHRONISATION_GRANULARITY_NS) {
+			if (min_valid) {
+				if (ptp->timeset[i].window < min_set)
+					min_set = ptp->timeset[i].window;
+			} else {
+				min_valid = true;
+				min_set = ptp->timeset[i].window;
+			}
+		}
+	}
+
+	if (min_valid) {
+		if (ptp->base_sync_valid && (min_set > ptp->base_sync_ns))
+			min = ptp->base_sync_ns;
+		else
+			min = min_set;
+	} else {
+		min = SYNCHRONISATION_GRANULARITY_NS;
+	}
+
+	/* Discard excessively long synchronise durations.  The MC times
+	 * when it finishes reading the host time so the corrected window
+	 * time should be fairly constant for a given platform.
+	 */
+	total = 0;
+	for (i = 0; i < number_readings; i++)
+		if (ptp->timeset[i].window > ptp->timeset[i].waitns) {
+			unsigned win;
+
+			win = ptp->timeset[i].window - ptp->timeset[i].waitns;
+			if (win >= MIN_SYNCHRONISATION_NS &&
+			    win < MAX_SYNCHRONISATION_NS) {
+				total += ptp->timeset[i].window;
+				ngood++;
+				last_good = i;
+			}
+		}
+
+	if (ngood == 0) {
+		netif_warn(efx, drv, efx->net_dev,
+			   "PTP no suitable synchronisations %dns %dns\n",
+			   ptp->base_sync_ns, min_set);
+		return -EAGAIN;
+	}
+
+	/* Average minimum this synchronisation */
+	ptp->last_sync_ns = DIV_ROUND_UP(total, ngood);
+	if (!ptp->base_sync_valid || (ptp->last_sync_ns < ptp->base_sync_ns)) {
+		ptp->base_sync_valid = true;
+		ptp->base_sync_ns = ptp->last_sync_ns;
+	}
+
+	/* Calculate delay from actual PPS to last_time */
+	delta.tv_nsec =
+		ptp->timeset[last_good].nanoseconds +
+		last_time->ts_real.tv_nsec -
+		(ptp->timeset[last_good].host_start & MC_NANOSECOND_MASK);
+
+	/* It is possible that the seconds rolled over between taking
+	 * the start reading and the last value written by the host.  The
+	 * timescales are such that a gap of more than one second is never
+	 * expected.
+	 */
+	start_sec = ptp->timeset[last_good].host_start >> MC_NANOSECOND_BITS;
+	last_sec = last_time->ts_real.tv_sec & MC_SECOND_MASK;
+	if (start_sec != last_sec) {
+		if (((start_sec + 1) & MC_SECOND_MASK) != last_sec) {
+			netif_warn(efx, hw, efx->net_dev,
+				   "PTP bad synchronisation seconds\n");
+			return -EAGAIN;
+		} else {
+			delta.tv_sec = 1;
+		}
+	} else {
+		delta.tv_sec = 0;
+	}
+
+	ptp->host_time_pps = *last_time;
+	pps_sub_ts(&ptp->host_time_pps, delta);
+
+	return 0;
+}
+
+/* Synchronize times between the host and the MC */
+static int efx_ptp_synchronize(struct efx_nic *efx, unsigned int num_readings)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	u8 synch_buf[MC_CMD_PTP_OUT_SYNCHRONIZE_LENMAX];
+	size_t response_length;
+	int rc;
+	unsigned long timeout;
+	struct pps_event_time last_time = {};
+	unsigned int loops = 0;
+	int *start = ptp->start.addr;
+
+	MCDI_SET_DWORD(synch_buf, PTP_IN_OP, MC_CMD_PTP_OP_SYNCHRONIZE);
+	MCDI_SET_DWORD(synch_buf, PTP_IN_SYNCHRONIZE_NUMTIMESETS,
+		       num_readings);
+	MCDI_SET_DWORD(synch_buf, PTP_IN_SYNCHRONIZE_START_ADDR_LO,
+		       (u32)ptp->start.dma_addr);
+	MCDI_SET_DWORD(synch_buf, PTP_IN_SYNCHRONIZE_START_ADDR_HI,
+		       (u32)((u64)ptp->start.dma_addr >> 32));
+
+	/* Clear flag that signals MC ready */
+	ACCESS_ONCE(*start) = 0;
+	efx_mcdi_rpc_start(efx, MC_CMD_PTP, synch_buf,
+			   MC_CMD_PTP_IN_SYNCHRONIZE_LEN);
+
+	/* Wait for start from MCDI (or timeout) */
+	timeout = jiffies + msecs_to_jiffies(MAX_SYNCHRONISE_WAIT_MS);
+	while (!ACCESS_ONCE(*start) && (time_before(jiffies, timeout))) {
+		udelay(20);	/* Usually start MCDI execution quickly */
+		loops++;
+	}
+
+	if (ACCESS_ONCE(*start))
+		efx_ptp_send_times(efx, &last_time);
+
+	/* Collect results */
+	rc = efx_mcdi_rpc_finish(efx, MC_CMD_PTP,
+				 MC_CMD_PTP_IN_SYNCHRONIZE_LEN,
+				 synch_buf, sizeof(synch_buf),
+				 &response_length);
+	if (rc == 0)
+		rc = efx_ptp_process_times(efx, synch_buf, response_length,
+					   &last_time);
+
+	return rc;
+}
+
+/* Transmit a PTP packet, via the MCDI interface, to the wire. */
+static int efx_ptp_xmit_skb(struct efx_nic *efx, struct sk_buff *skb)
+{
+	u8 *txbuf = efx->ptp_data->txbuf;
+	struct skb_shared_hwtstamps timestamps;
+	int rc = -EIO;
+	/* MCDI driver requires word aligned lengths */
+	size_t len = ALIGN(MC_CMD_PTP_IN_TRANSMIT_LEN(skb->len), 4);
+	u8 txtime[MC_CMD_PTP_OUT_TRANSMIT_LEN];
+
+	MCDI_SET_DWORD(txbuf, PTP_IN_OP, MC_CMD_PTP_OP_TRANSMIT);
+	MCDI_SET_DWORD(txbuf, PTP_IN_TRANSMIT_LENGTH, skb->len);
+	if (skb_shinfo(skb)->nr_frags != 0) {
+		rc = skb_linearize(skb);
+		if (rc != 0)
+			goto fail;
+	}
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		rc = skb_checksum_help(skb);
+		if (rc != 0)
+			goto fail;
+	}
+	skb_copy_from_linear_data(skb,
+				  &txbuf[MC_CMD_PTP_IN_TRANSMIT_PACKET_OFST],
+				  len);
+	rc = efx_mcdi_rpc(efx, MC_CMD_PTP, txbuf, len, txtime,
+			  sizeof(txtime), &len);
+	if (rc != 0)
+		goto fail;
+
+	memset(&timestamps, 0, sizeof(timestamps));
+	timestamps.hwtstamp = ktime_set(
+		MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_SECONDS),
+		MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_NANOSECONDS));
+
+	skb_tstamp_tx(skb, &timestamps);
+
+	rc = 0;
+
+fail:
+	dev_kfree_skb(skb);
+
+	return rc;
+}
+
+static void efx_ptp_drop_time_expired_events(struct efx_nic *efx)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	struct list_head *cursor;
+	struct list_head *next;
+
+	/* Drop time-expired events */
+	spin_lock_bh(&ptp->evt_lock);
+	if (!list_empty(&ptp->evt_list)) {
+		list_for_each_safe(cursor, next, &ptp->evt_list) {
+			struct efx_ptp_event_rx *evt;
+
+			evt = list_entry(cursor, struct efx_ptp_event_rx,
+					 link);
+			if (time_after(jiffies, evt->expiry)) {
+				list_del(&evt->link);
+				list_add(&evt->link, &ptp->evt_free_list);
+				netif_warn(efx, hw, efx->net_dev,
+					   "PTP rx event dropped\n");
+			}
+		}
+	}
+	spin_unlock_bh(&ptp->evt_lock);
+}
+
+static enum ptp_packet_state efx_ptp_match_rx(struct efx_nic *efx,
+					      struct sk_buff *skb)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	bool evts_waiting;
+	struct list_head *cursor;
+	struct list_head *next;
+	struct efx_ptp_match *match;
+	enum ptp_packet_state rc = PTP_PACKET_STATE_UNMATCHED;
+
+	spin_lock_bh(&ptp->evt_lock);
+	evts_waiting = !list_empty(&ptp->evt_list);
+	spin_unlock_bh(&ptp->evt_lock);
+
+	if (!evts_waiting)
+		return PTP_PACKET_STATE_UNMATCHED;
+
+	match = (struct efx_ptp_match *)skb->cb;
+	/* Look for a matching timestamp in the event queue */
+	spin_lock_bh(&ptp->evt_lock);
+	list_for_each_safe(cursor, next, &ptp->evt_list) {
+		struct efx_ptp_event_rx *evt;
+
+		evt = list_entry(cursor, struct efx_ptp_event_rx, link);
+		if ((evt->seq0 == match->words[0]) &&
+		    (evt->seq1 == match->words[1])) {
+			struct skb_shared_hwtstamps *timestamps;
+
+			/* Match - add in hardware timestamp */
+			timestamps = skb_hwtstamps(skb);
+			timestamps->hwtstamp = evt->hwtimestamp;
+
+			match->state = PTP_PACKET_STATE_MATCHED;
+			rc = PTP_PACKET_STATE_MATCHED;
+			list_del(&evt->link);
+			list_add(&evt->link, &ptp->evt_free_list);
+			break;
+		}
+	}
+	spin_unlock_bh(&ptp->evt_lock);
+
+	return rc;
+}
+
+/* Process any queued receive events and corresponding packets
+ *
+ * q is returned with all the packets that are ready for delivery.
+ * true is returned if at least one of those packets requires
+ * synchronisation.
+ */
+static bool efx_ptp_process_events(struct efx_nic *efx, struct sk_buff_head *q)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	bool rc = false;
+	struct sk_buff *skb;
+
+	while ((skb = skb_dequeue(&ptp->rxq))) {
+		struct efx_ptp_match *match;
+
+		match = (struct efx_ptp_match *)skb->cb;
+		if (match->state == PTP_PACKET_STATE_MATCH_UNWANTED) {
+			__skb_queue_tail(q, skb);
+		} else if (efx_ptp_match_rx(efx, skb) ==
+			   PTP_PACKET_STATE_MATCHED) {
+			rc = true;
+			__skb_queue_tail(q, skb);
+		} else if (time_after(jiffies, match->expiry)) {
+			match->state = PTP_PACKET_STATE_TIMED_OUT;
+			netif_warn(efx, rx_err, efx->net_dev,
+				   "PTP packet - no timestamp seen\n");
+			__skb_queue_tail(q, skb);
+		} else {
+			/* Replace unprocessed entry and stop */
+			skb_queue_head(&ptp->rxq, skb);
+			break;
+		}
+	}
+
+	return rc;
+}
+
+/* Complete processing of a received packet */
+static inline void efx_ptp_process_rx(struct efx_nic *efx, struct sk_buff *skb)
+{
+	local_bh_disable();
+	netif_receive_skb(skb);
+	local_bh_enable();
+}
+
+static int efx_ptp_start(struct efx_nic *efx)
+{
+	struct efx_ptp_data *ptp = efx->ptp_data;
+	struct efx_filter_spec rxfilter;
+	int rc;
+
+	ptp->reset_required = false;
+
+	/* Must filter on both event and general ports to ensure
+	 * that there is no packet re-ordering.
+	 */
+	efx_filter_init_rx(&rxfilter, EFX_FILTER_PRI_REQUIRED, 0,