mlx4_en: Add PTP hardware clock

This adds a PHC to the mlx4_en driver. We use reader/writer spinlocks to
protect the timecounter since every packet received needs to call
timecounter_cycle2time() when timestamping is enabled.  This can become
a performance bottleneck with RSS and multiple receive queues if normal
spinlocks are used.

This driver has been tested with both Documentation/ptp/testptp and the
linuxptp project (http://linuxptp.sourceforge.net/) on a Mellanox
ConnectX-3 card.

Signed-off-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
Acked-By: Hadar Hen Zion <hadarh@mellanox.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx4/en_clock.c

@@ -103,19 +103,191 @@ void mlx4_en_fill_hwtstamps(struct mlx4_en_dev *mdev,
 			    struct skb_shared_hwtstamps *hwts,
 			    u64 timestamp)
 {
+	unsigned long flags;
 	u64 nsec;
 
+	read_lock_irqsave(&mdev->clock_lock, flags);
 	nsec = timecounter_cyc2time(&mdev->clock, timestamp);
+	read_unlock_irqrestore(&mdev->clock_lock, flags);
 
 	memset(hwts, 0, sizeof(struct skb_shared_hwtstamps));
 	hwts->hwtstamp = ns_to_ktime(nsec);
 }
 
+/**
+ * mlx4_en_remove_timestamp - disable PTP device
+ * @mdev: board private structure
+ *
+ * Stop the PTP support.
+ **/
+void mlx4_en_remove_timestamp(struct mlx4_en_dev *mdev)
+{
+	if (mdev->ptp_clock) {
+		ptp_clock_unregister(mdev->ptp_clock);
+		mdev->ptp_clock = NULL;
+		mlx4_info(mdev, "removed PHC\n");
+	}
+}
+
+void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev)
+{
+	bool timeout = time_is_before_jiffies(mdev->last_overflow_check +
+					      mdev->overflow_period);
+	unsigned long flags;
+
+	if (timeout) {
+		write_lock_irqsave(&mdev->clock_lock, flags);
+		timecounter_read(&mdev->clock);
+		write_unlock_irqrestore(&mdev->clock_lock, flags);
+		mdev->last_overflow_check = jiffies;
+	}
+}
+
+/**
+ * mlx4_en_phc_adjfreq - adjust the frequency of the hardware clock
+ * @ptp: ptp clock structure
+ * @delta: Desired frequency change in parts per billion
+ *
+ * Adjust the frequency of the PHC cycle counter by the indicated delta from
+ * the base frequency.
+ **/
+static int mlx4_en_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta)
+{
+	u64 adj;
+	u32 diff, mult;
+	int neg_adj = 0;
+	unsigned long flags;
+	struct mlx4_en_dev *mdev = container_of(ptp, struct mlx4_en_dev,
+						ptp_clock_info);
+
+	if (delta < 0) {
+		neg_adj = 1;
+		delta = -delta;
+	}
+	mult = mdev->nominal_c_mult;
+	adj = mult;
+	adj *= delta;
+	diff = div_u64(adj, 1000000000ULL);
+
+	write_lock_irqsave(&mdev->clock_lock, flags);
+	timecounter_read(&mdev->clock);
+	mdev->cycles.mult = neg_adj ? mult - diff : mult + diff;
+	write_unlock_irqrestore(&mdev->clock_lock, flags);
+
+	return 0;
+}
+
+/**
+ * mlx4_en_phc_adjtime - Shift the time of the hardware clock
+ * @ptp: ptp clock structure
+ * @delta: Desired change in nanoseconds
+ *
+ * Adjust the timer by resetting the timecounter structure.
+ **/
+static int mlx4_en_phc_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct mlx4_en_dev *mdev = container_of(ptp, struct mlx4_en_dev,
+						ptp_clock_info);
+	unsigned long flags;
+	s64 now;
+
+	write_lock_irqsave(&mdev->clock_lock, flags);
+	now = timecounter_read(&mdev->clock);
+	now += delta;
+	timecounter_init(&mdev->clock, &mdev->cycles, now);
+	write_unlock_irqrestore(&mdev->clock_lock, flags);
+
+	return 0;
+}
+
+/**
+ * mlx4_en_phc_gettime - Reads the current time from the hardware clock
+ * @ptp: ptp clock structure
+ * @ts: timespec structure to hold the current time value
+ *
+ * Read the timecounter and return the correct value in ns after converting
+ * it into a struct timespec.
+ **/
+static int mlx4_en_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
+{
+	struct mlx4_en_dev *mdev = container_of(ptp, struct mlx4_en_dev,
+						ptp_clock_info);
+	unsigned long flags;
+	u32 remainder;
+	u64 ns;
+
+	write_lock_irqsave(&mdev->clock_lock, flags);
+	ns = timecounter_read(&mdev->clock);
+	write_unlock_irqrestore(&mdev->clock_lock, flags);
+
+	ts->tv_sec = div_u64_rem(ns, NSEC_PER_SEC, &remainder);
+	ts->tv_nsec = remainder;
+
+	return 0;
+}
+
+/**
+ * mlx4_en_phc_settime - Set the current time on the hardware clock
+ * @ptp: ptp clock structure
+ * @ts: timespec containing the new time for the cycle counter
+ *
+ * Reset the timecounter to use a new base value instead of the kernel
+ * wall timer value.
+ **/
+static int mlx4_en_phc_settime(struct ptp_clock_info *ptp,
+			       const struct timespec *ts)
+{
+	struct mlx4_en_dev *mdev = container_of(ptp, struct mlx4_en_dev,
+						ptp_clock_info);
+	u64 ns = timespec_to_ns(ts);
+	unsigned long flags;
+
+	/* reset the timecounter */
+	write_lock_irqsave(&mdev->clock_lock, flags);
+	timecounter_init(&mdev->clock, &mdev->cycles, ns);
+	write_unlock_irqrestore(&mdev->clock_lock, flags);
+
+	return 0;
+}
+
+/**
+ * mlx4_en_phc_enable - enable or disable an ancillary feature
+ * @ptp: ptp clock structure
+ * @request: Desired resource to enable or disable
+ * @on: Caller passes one to enable or zero to disable
+ *
+ * Enable (or disable) ancillary features of the PHC subsystem.
+ * Currently, no ancillary features are supported.
+ **/
+static int mlx4_en_phc_enable(struct ptp_clock_info __always_unused *ptp,
+			      struct ptp_clock_request __always_unused *request,
+			      int __always_unused on)
+{
+	return -EOPNOTSUPP;
+}
+
+static const struct ptp_clock_info mlx4_en_ptp_clock_info = {
+	.owner		= THIS_MODULE,
+	.max_adj	= 100000000,
+	.n_alarm	= 0,
+	.n_ext_ts	= 0,
+	.n_per_out	= 0,
+	.pps		= 0,
+	.adjfreq	= mlx4_en_phc_adjfreq,
+	.adjtime	= mlx4_en_phc_adjtime,
+	.gettime	= mlx4_en_phc_gettime,
+	.settime	= mlx4_en_phc_settime,
+	.enable		= mlx4_en_phc_enable,
+};
+
 void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 {
 	struct mlx4_dev *dev = mdev->dev;
+	unsigned long flags;
 	u64 ns;
 
+	rwlock_init(&mdev->clock_lock);
+
 	memset(&mdev->cycles, 0, sizeof(mdev->cycles));
 	mdev->cycles.read = mlx4_en_read_clock;
 	mdev->cycles.mask = CLOCKSOURCE_MASK(48);
@@ -127,9 +299,12 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 	mdev->cycles.shift = 14;
 	mdev->cycles.mult =
 		clocksource_khz2mult(1000 * dev->caps.hca_core_clock, mdev->cycles.shift);
+	mdev->nominal_c_mult = mdev->cycles.mult;
 
+	write_lock_irqsave(&mdev->clock_lock, flags);
 	timecounter_init(&mdev->clock, &mdev->cycles,
 			 ktime_to_ns(ktime_get_real()));
+	write_unlock_irqrestore(&mdev->clock_lock, flags);
 
 	/* Calculate period in seconds to call the overflow watchdog - to make
 	 * sure counter is checked at least once every wrap around.
@@ -137,15 +312,18 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 	ns = cyclecounter_cyc2ns(&mdev->cycles, mdev->cycles.mask);
 	do_div(ns, NSEC_PER_SEC / 2 / HZ);
 	mdev->overflow_period = ns;
-}
 
-void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev)
+	/* Configure the PHC */
-{
+	mdev->ptp_clock_info = mlx4_en_ptp_clock_info;
-	bool timeout = time_is_before_jiffies(mdev->last_overflow_check +
+	snprintf(mdev->ptp_clock_info.name, 16, "mlx4 ptp");
-					      mdev->overflow_period);
 
-	if (timeout) {
+	mdev->ptp_clock = ptp_clock_register(&mdev->ptp_clock_info,
-		timecounter_read(&mdev->clock);
+					     &mdev->pdev->dev);
-		mdev->last_overflow_check = jiffies;
+	if (IS_ERR(mdev->ptp_clock)) {
+		mdev->ptp_clock = NULL;
+		mlx4_err(mdev, "ptp_clock_register failed\n");
+	} else {
+		mlx4_info(mdev, "registered PHC clock\n");
 	}
+
 }

drivers/net/ethernet/mellanox/mlx4/en_ethtool.c

@@ -1193,6 +1193,9 @@ static int mlx4_en_get_ts_info(struct net_device *dev,
 		info->rx_filters =
 			(1 << HWTSTAMP_FILTER_NONE) |
 			(1 << HWTSTAMP_FILTER_ALL);
+
+		if (mdev->ptp_clock)
+			info->phc_index = ptp_clock_index(mdev->ptp_clock);
 	}
 
 	return ret;

drivers/net/ethernet/mellanox/mlx4/en_main.c

@@ -199,6 +199,9 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
 		if (mdev->pndev[i])
 			mlx4_en_destroy_netdev(mdev->pndev[i]);
 
+	if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
+		mlx4_en_remove_timestamp(mdev);
+
 	flush_workqueue(mdev->workqueue);
 	destroy_workqueue(mdev->workqueue);
 	(void) mlx4_mr_free(dev, &mdev->mr);

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -45,6 +45,7 @@
 #include <linux/dcbnl.h>
 #endif
 #include <linux/cpu_rmap.h>
+#include <linux/ptp_clock_kernel.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/qp.h>
@@ -375,10 +376,14 @@ struct mlx4_en_dev {
 	u32                     priv_pdn;
 	spinlock_t              uar_lock;
 	u8			mac_removed[MLX4_MAX_PORTS + 1];
+	rwlock_t		clock_lock;
+	u32			nominal_c_mult;
 	struct cyclecounter	cycles;
 	struct timecounter	clock;
 	unsigned long		last_overflow_check;
 	unsigned long		overflow_period;
+	struct ptp_clock	*ptp_clock;
+	struct ptp_clock_info	ptp_clock_info;
 };
 
 
@@ -791,6 +796,7 @@ void mlx4_en_fill_hwtstamps(struct mlx4_en_dev *mdev,
 			    struct skb_shared_hwtstamps *hwts,
 			    u64 timestamp);
 void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev);
+void mlx4_en_remove_timestamp(struct mlx4_en_dev *mdev);
 int mlx4_en_timestamp_config(struct net_device *dev,
 			     int tx_type,
 			     int rx_filter);