igb: Prevent dropped Tx timestamps via work items and interrupts.

In rare circumstances, it's possible a descriptor writeback will occur
before a timestamped Tx packet will go out on the wire, leading to the
driver believing the hardware failed to timestamp the packet. Schedule a
work item for 82576 and use the available time sync interrupt registers
on 82580 and above to account for this.

Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: NMatthew Vick <matthew.vick@intel.com>
Tested-by: NJeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

drivers/net/ethernet/intel/igb/e1000_defines.h

@@ -360,6 +360,7 @@
 #define E1000_ICR_RXDMT0        0x00000010 /* rx desc min. threshold (0) */
 #define E1000_ICR_RXT0          0x00000080 /* rx timer intr (ring 0) */
 #define E1000_ICR_VMMB          0x00000100 /* VM MB event */
+#define E1000_ICR_TS            0x00080000 /* Time Sync Interrupt */
 #define E1000_ICR_DRSTA         0x40000000 /* Device Reset Asserted */
 /* If this bit asserted, the driver should claim the interrupt */
 #define E1000_ICR_INT_ASSERTED  0x80000000
@@ -399,6 +400,7 @@
 #define E1000_IMS_TXDW      E1000_ICR_TXDW      /* Transmit desc written back */
 #define E1000_IMS_LSC       E1000_ICR_LSC       /* Link Status Change */
 #define E1000_IMS_VMMB      E1000_ICR_VMMB      /* Mail box activity */
+#define E1000_IMS_TS        E1000_ICR_TS        /* Time Sync Interrupt */
 #define E1000_IMS_RXSEQ     E1000_ICR_RXSEQ     /* rx sequence error */
 #define E1000_IMS_RXDMT0    E1000_ICR_RXDMT0    /* rx desc min. threshold */
 #define E1000_IMS_RXT0      E1000_ICR_RXT0      /* rx timer intr */
@@ -510,6 +512,9 @@
 
 #define E1000_TIMINCA_16NS_SHIFT 24
 
+#define E1000_TSICR_TXTS 0x00000002
+#define E1000_TSIM_TXTS 0x00000002
+
 #define E1000_MDICNFG_EXT_MDIO    0x80000000      /* MDI ext/int destination */
 #define E1000_MDICNFG_COM_MDIO    0x40000000      /* MDI shared w/ lan 0 */
 #define E1000_MDICNFG_PHY_MASK    0x03E00000

drivers/net/ethernet/intel/igb/e1000_regs.h

@@ -91,6 +91,8 @@
 #define E1000_TIMINCA    0x0B608 /* Increment attributes register - RW */
 #define E1000_TSAUXC     0x0B640 /* Timesync Auxiliary Control register */
 #define E1000_SYSTIMR    0x0B6F8 /* System time register Residue */
+#define E1000_TSICR      0x0B66C /* Interrupt Cause Register */
+#define E1000_TSIM       0x0B674 /* Interrupt Mask Register */
 
 /* Filtering Registers */
 #define E1000_SAQF(_n) (0x5980 + 4 * (_n))

drivers/net/ethernet/intel/igb/igb.h

@@ -381,6 +381,8 @@ struct igb_adapter {
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_caps;
 	struct delayed_work ptp_overflow_work;
+	struct work_struct ptp_tx_work;
+	struct sk_buff *ptp_tx_skb;
 	spinlock_t tmreg_lock;
 	struct cyclecounter cc;
 	struct timecounter tc;
@@ -394,6 +396,7 @@ struct igb_adapter {
 #define IGB_FLAG_QUAD_PORT_A       (1 << 2)
 #define IGB_FLAG_QUEUE_PAIRS       (1 << 3)
 #define IGB_FLAG_DMAC              (1 << 4)
+#define IGB_FLAG_PTP               (1 << 5)
 
 /* DMA Coalescing defines */
 #define IGB_MIN_TXPBSIZE           20408
@@ -440,8 +443,9 @@ extern void igb_set_fw_version(struct igb_adapter *);
 #ifdef CONFIG_IGB_PTP
 extern void igb_ptp_init(struct igb_adapter *adapter);
 extern void igb_ptp_stop(struct igb_adapter *adapter);
-extern void igb_ptp_tx_hwtstamp(struct igb_q_vector *q_vector,
-				struct igb_tx_buffer *buffer_info);
+extern void igb_ptp_reset(struct igb_adapter *adapter);
+extern void igb_ptp_tx_work(struct work_struct *work);
+extern void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter);
 extern void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector,
 				union e1000_adv_rx_desc *rx_desc,
 				struct sk_buff *skb);

drivers/net/ethernet/intel/igb/igb_main.c

@@ -1751,6 +1751,11 @@ void igb_reset(struct igb_adapter *adapter)
 	/* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */
 	wr32(E1000_VET, ETHERNET_IEEE_VLAN_TYPE);
 
+#ifdef CONFIG_IGB_PTP
+	/* Re-enable PTP, where applicable. */
+	igb_ptp_reset(adapter);
+#endif /* CONFIG_IGB_PTP */
+
 	igb_get_phy_info(hw);
 }
 
@@ -4234,7 +4239,7 @@ static __le32 igb_tx_cmd_type(u32 tx_flags)
 
 #ifdef CONFIG_IGB_PTP
 	/* set timestamp bit if present */
-	if (tx_flags & IGB_TX_FLAGS_TSTAMP)
+	if (unlikely(tx_flags & IGB_TX_FLAGS_TSTAMP))
 		cmd_type |= cpu_to_le32(E1000_ADVTXD_MAC_TSTAMP);
 #endif /* CONFIG_IGB_PTP */
 
@@ -4445,6 +4450,9 @@ static inline int igb_maybe_stop_tx(struct igb_ring *tx_ring, const u16 size)
 netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 				struct igb_ring *tx_ring)
 {
+#ifdef CONFIG_IGB_PTP
+	struct igb_adapter *adapter = netdev_priv(tx_ring->netdev);
+#endif /* CONFIG_IGB_PTP */
 	struct igb_tx_buffer *first;
 	int tso;
 	u32 tx_flags = 0;
@@ -4468,9 +4476,14 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	first->gso_segs = 1;
 
 #ifdef CONFIG_IGB_PTP
-	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
+	if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+		     !(adapter->ptp_tx_skb))) {
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		tx_flags |= IGB_TX_FLAGS_TSTAMP;
+
+		adapter->ptp_tx_skb = skb_get(skb);
+		if (adapter->hw.mac.type == e1000_82576)
+			schedule_work(&adapter->ptp_tx_work);
 	}
 #endif /* CONFIG_IGB_PTP */
 
@@ -4859,6 +4872,19 @@ static irqreturn_t igb_msix_other(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+#ifdef CONFIG_IGB_PTP
+	if (icr & E1000_ICR_TS) {
+		u32 tsicr = rd32(E1000_TSICR);
+
+		if (tsicr & E1000_TSICR_TXTS) {
+			/* acknowledge the interrupt */
+			wr32(E1000_TSICR, E1000_TSICR_TXTS);
+			/* retrieve hardware timestamp */
+			schedule_work(&adapter->ptp_tx_work);
+		}
+	}
+#endif /* CONFIG_IGB_PTP */
+
 	wr32(E1000_EIMS, adapter->eims_other);
 
 	return IRQ_HANDLED;
@@ -5650,6 +5676,19 @@ static irqreturn_t igb_intr_msi(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+#ifdef CONFIG_IGB_PTP
+	if (icr & E1000_ICR_TS) {
+		u32 tsicr = rd32(E1000_TSICR);
+
+		if (tsicr & E1000_TSICR_TXTS) {
+			/* acknowledge the interrupt */
+			wr32(E1000_TSICR, E1000_TSICR_TXTS);
+			/* retrieve hardware timestamp */
+			schedule_work(&adapter->ptp_tx_work);
+		}
+	}
+#endif /* CONFIG_IGB_PTP */
+
 	napi_schedule(&q_vector->napi);
 
 	return IRQ_HANDLED;
@@ -5691,6 +5730,19 @@ static irqreturn_t igb_intr(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+#ifdef CONFIG_IGB_PTP
+	if (icr & E1000_ICR_TS) {
+		u32 tsicr = rd32(E1000_TSICR);
+
+		if (tsicr & E1000_TSICR_TXTS) {
+			/* acknowledge the interrupt */
+			wr32(E1000_TSICR, E1000_TSICR_TXTS);
+			/* retrieve hardware timestamp */
+			schedule_work(&adapter->ptp_tx_work);
+		}
+	}
+#endif /* CONFIG_IGB_PTP */
+
 	napi_schedule(&q_vector->napi);
 
 	return IRQ_HANDLED;
@@ -5794,11 +5846,6 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 		total_bytes += tx_buffer->bytecount;
 		total_packets += tx_buffer->gso_segs;
 
-#ifdef CONFIG_IGB_PTP
-		/* retrieve hardware timestamp */
-		igb_ptp_tx_hwtstamp(q_vector, tx_buffer);
-#endif /* CONFIG_IGB_PTP */
-
 		/* free the skb */
 		dev_kfree_skb_any(tx_buffer->skb);
 		tx_buffer->skb = NULL;

drivers/net/ethernet/intel/igb/igb_ptp.c

@@ -289,6 +289,31 @@ static int igb_ptp_enable(struct ptp_clock_info *ptp,
 	return -EOPNOTSUPP;
 }
 
+/**
+ * igb_ptp_tx_work
+ * @work: pointer to work struct
+ *
+ * This work function polls the TSYNCTXCTL valid bit to determine when a
+ * timestamp has been taken for the current stored skb.
+ */
+void igb_ptp_tx_work(struct work_struct *work)
+{
+	struct igb_adapter *adapter = container_of(work, struct igb_adapter,
+						   ptp_tx_work);
+	struct e1000_hw *hw = &adapter->hw;
+	u32 tsynctxctl;
+
+	if (!adapter->ptp_tx_skb)
+		return;
+
+	tsynctxctl = rd32(E1000_TSYNCTXCTL);
+	if (tsynctxctl & E1000_TSYNCTXCTL_VALID)
+		igb_ptp_tx_hwtstamp(adapter);
+	else
+		/* reschedule to check later */
+		schedule_work(&adapter->ptp_tx_work);
+}
+
 static void igb_ptp_overflow_check(struct work_struct *work)
 {
 	struct igb_adapter *igb =
@@ -305,31 +330,25 @@ static void igb_ptp_overflow_check(struct work_struct *work)
 
 /**
  * igb_ptp_tx_hwtstamp - utility function which checks for TX time stamp
- * @q_vector: pointer to q_vector containing needed info
- * @buffer: pointer to igb_tx_buffer structure
+ * @adapter: Board private structure.
  *
  * If we were asked to do hardware stamping and such a time stamp is
  * available, then it must have been for this skb here because we only
  * allow only one such packet into the queue.
  */
-void igb_ptp_tx_hwtstamp(struct igb_q_vector *q_vector,
-			 struct igb_tx_buffer *buffer_info)
+void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
 {
-	struct igb_adapter *adapter = q_vector->adapter;
 	struct e1000_hw *hw = &adapter->hw;
 	struct skb_shared_hwtstamps shhwtstamps;
 	u64 regval;
 
-	/* if skb does not support hw timestamp or TX stamp not valid exit */
-	if (likely(!(buffer_info->tx_flags & IGB_TX_FLAGS_TSTAMP)) ||
-	    !(rd32(E1000_TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID))
-		return;
-
 	regval = rd32(E1000_TXSTMPL);
 	regval |= (u64)rd32(E1000_TXSTMPH) << 32;
 
 	igb_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval);
-	skb_tstamp_tx(buffer_info->skb, &shhwtstamps);
+	skb_tstamp_tx(adapter->ptp_tx_skb, &shhwtstamps);
+	dev_kfree_skb_any(adapter->ptp_tx_skb);
+	adapter->ptp_tx_skb = NULL;
 }
 
 void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector,
@@ -603,16 +622,26 @@ void igb_ptp_init(struct igb_adapter *adapter)
 
 	spin_lock_init(&adapter->tmreg_lock);
 
+	INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work);
+
 	schedule_delayed_work(&adapter->ptp_overflow_work,
 			      IGB_SYSTIM_OVERFLOW_PERIOD);
 
+	/* Initialize the time sync interrupts for devices that support it. */
+	if (hw->mac.type >= e1000_82580) {
+		wr32(E1000_TSIM, E1000_TSIM_TXTS);
+		wr32(E1000_IMS, E1000_IMS_TS);
+	}
+
 	adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps);
 	if (IS_ERR(adapter->ptp_clock)) {
 		adapter->ptp_clock = NULL;
 		dev_err(&adapter->pdev->dev, "ptp_clock_register failed\n");
-	} else
+	} else {
 		dev_info(&adapter->pdev->dev, "added PHC on %s\n",
 			 adapter->netdev->name);
+		adapter->flags |= IGB_FLAG_PTP;
+	}
 }
 
 /**
@@ -624,20 +653,61 @@ void igb_ptp_init(struct igb_adapter *adapter)
 void igb_ptp_stop(struct igb_adapter *adapter)
 {
 	switch (adapter->hw.mac.type) {
-	case e1000_i211:
-	case e1000_i210:
-	case e1000_i350:
-	case e1000_82580:
 	case e1000_82576:
+	case e1000_82580:
+	case e1000_i350:
 		cancel_delayed_work_sync(&adapter->ptp_overflow_work);
 		break;
+	case e1000_i210:
+	case e1000_i211:
+		/* No delayed work to cancel. */
+		break;
 	default:
 		return;
 	}
 
+	cancel_work_sync(&adapter->ptp_tx_work);
+
 	if (adapter->ptp_clock) {
 		ptp_clock_unregister(adapter->ptp_clock);
 		dev_info(&adapter->pdev->dev, "removed PHC on %s\n",
 			 adapter->netdev->name);
+		adapter->flags &= ~IGB_FLAG_PTP;
 	}
 }
+
+/**
+ * igb_ptp_reset - Re-enable the adapter for PTP following a reset.
+ * @adapter: Board private structure.
+ *
+ * This function handles the reset work required to re-enable the PTP device.
+ **/
+void igb_ptp_reset(struct igb_adapter *adapter)
+{
+	struct e1000_hw *hw = &adapter->hw;
+
+	if (!(adapter->flags & IGB_FLAG_PTP))
+		return;
+
+	switch (adapter->hw.mac.type) {
+	case e1000_82576:
+		/* Dial the nominal frequency. */
+		wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576);
+		break;
+	case e1000_82580:
+	case e1000_i350:
+	case e1000_i210:
+	case e1000_i211:
+		/* Enable the timer functions and interrupts. */
+		wr32(E1000_TSAUXC, 0x0);
+		wr32(E1000_TSIM, E1000_TSIM_TXTS);
+		wr32(E1000_IMS, E1000_IMS_TS);
+		break;
+	default:
+		/* No work to do. */
+		return;
+	}
+
+	timecounter_init(&adapter->tc, &adapter->cc,
+			 ktime_to_ns(ktime_get_real()));
+}