3 files changed, 287 insertions, 61 deletions

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 34aebf00a512..00a5ee487812 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -13,6 +13,7 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/timecounter.h>
 #include <linux/net_tstamp.h>
+#include <linux/bitfield.h>
 
 #include "igc_hw.h"
 
@@ -228,7 +229,10 @@ struct igc_adapter {
 
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_caps;
-	struct work_struct ptp_tx_work;
+	/* Access to ptp_tx_skb and ptp_tx_start are protected by the
+	 * ptp_tx_lock.
+	 */
+	spinlock_t ptp_tx_lock;
 	struct sk_buff *ptp_tx_skb;
 	struct hwtstamp_config tstamp_config;
 	unsigned long ptp_tx_start;
@@ -311,6 +315,33 @@ extern char igc_driver_name[];
 #define IGC_MRQC_RSS_FIELD_IPV4_UDP	0x00400000
 #define IGC_MRQC_RSS_FIELD_IPV6_UDP	0x00800000
 
+/* RX-desc Write-Back format RSS Type's */
+enum igc_rss_type_num {
+	IGC_RSS_TYPE_NO_HASH		= 0,
+	IGC_RSS_TYPE_HASH_TCP_IPV4	= 1,
+	IGC_RSS_TYPE_HASH_IPV4		= 2,
+	IGC_RSS_TYPE_HASH_TCP_IPV6	= 3,
+	IGC_RSS_TYPE_HASH_IPV6_EX	= 4,
+	IGC_RSS_TYPE_HASH_IPV6		= 5,
+	IGC_RSS_TYPE_HASH_TCP_IPV6_EX	= 6,
+	IGC_RSS_TYPE_HASH_UDP_IPV4	= 7,
+	IGC_RSS_TYPE_HASH_UDP_IPV6	= 8,
+	IGC_RSS_TYPE_HASH_UDP_IPV6_EX	= 9,
+	IGC_RSS_TYPE_MAX		= 10,
+};
+#define IGC_RSS_TYPE_MAX_TABLE		16
+#define IGC_RSS_TYPE_MASK		GENMASK(3,0) /* 4-bits (3:0) = mask 0x0F */
+
+/* igc_rss_type - Rx descriptor RSS type field */
+static inline u32 igc_rss_type(const union igc_adv_rx_desc *rx_desc)
+{
+	/* RSS Type 4-bits (3:0) number: 0-9 (above 9 is reserved)
+	 * Accessing the same bits via u16 (wb.lower.lo_dword.hs_rss.pkt_info)
+	 * is slightly slower than via u32 (wb.lower.lo_dword.data)
+	 */
+	return le32_get_bits(rx_desc->wb.lower.lo_dword.data, IGC_RSS_TYPE_MASK);
+}
+
 /* Interrupt defines */
 #define IGC_START_ITR			648 /* ~6000 ints/sec */
 #define IGC_4K_ITR			980
@@ -401,7 +432,6 @@ enum igc_state_t {
 	__IGC_TESTING,
 	__IGC_RESETTING,
 	__IGC_DOWN,
-	__IGC_PTP_TX_IN_PROGRESS,
 };
 
 enum igc_tx_flags {
@@ -471,6 +501,13 @@ struct igc_rx_buffer {
 	};
 };
 
+/* context wrapper around xdp_buff to provide access to descriptor metadata */
+struct igc_xdp_buff {
+	struct xdp_buff xdp;
+	union igc_adv_rx_desc *rx_desc;
+	ktime_t rx_ts; /* data indication bit IGC_RXDADV_STAT_TSIP */
+};
+
 struct igc_q_vector {
 	struct igc_adapter *adapter;    /* backlink */
 	void __iomem *itr_register;
@@ -578,6 +615,7 @@ enum igc_ring_flags_t {
 	IGC_RING_FLAG_TX_CTX_IDX,
 	IGC_RING_FLAG_TX_DETECT_HANG,
 	IGC_RING_FLAG_AF_XDP_ZC,
+	IGC_RING_FLAG_TX_HWTSTAMP,
 };
 
 #define ring_uses_large_buffer(ring) \
@@ -634,6 +672,7 @@ int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
 int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
 void igc_ptp_tx_hang(struct igc_adapter *adapter);
 void igc_ptp_read(struct igc_adapter *adapter, struct timespec64 *ts);
+void igc_ptp_tx_tstamp_event(struct igc_adapter *adapter);
 
 #define igc_rx_pg_size(_ring) (PAGE_SIZE << igc_rx_pg_order(_ring))
 
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 1c4676882082..019ce91c45aa 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -254,6 +254,13 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring)
 	/* reset BQL for queue */
 	netdev_tx_reset_queue(txring_txq(tx_ring));
 
+	/* Zero out the buffer ring */
+	memset(tx_ring->tx_buffer_info, 0,
+	       sizeof(*tx_ring->tx_buffer_info) * tx_ring->count);
+
+	/* Zero out the descriptor ring */
+	memset(tx_ring->desc, 0, tx_ring->size);
+
 	/* reset next_to_use and next_to_clean */
 	tx_ring->next_to_use = 0;
 	tx_ring->next_to_clean = 0;
@@ -267,7 +274,7 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring)
  */
 void igc_free_tx_resources(struct igc_ring *tx_ring)
 {
-	igc_clean_tx_ring(tx_ring);
+	igc_disable_tx_ring(tx_ring);
 
 	vfree(tx_ring->tx_buffer_info);
 	tx_ring->tx_buffer_info = NULL;
@@ -1578,14 +1585,16 @@ done:
 		}
 	}
 
-	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
+	if (unlikely(test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags) &&
+		     skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
 		/* FIXME: add support for retrieving timestamps from
 		 * the other timer registers before skipping the
 		 * timestamping request.
 		 */
-		if (adapter->tstamp_config.tx_type == HWTSTAMP_TX_ON &&
-		    !test_and_set_bit_lock(__IGC_PTP_TX_IN_PROGRESS,
-					   &adapter->state)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&adapter->ptp_tx_lock, flags);
+		if (!adapter->ptp_tx_skb) {
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 			tx_flags |= IGC_TX_FLAGS_TSTAMP;
 
@@ -1594,6 +1603,8 @@ done:
 		} else {
 			adapter->tx_hwtstamp_skipped++;
 		}
+
+		spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags);
 	}
 
 	if (skb_vlan_tag_present(skb)) {
@@ -1690,14 +1701,36 @@ static void igc_rx_checksum(struct igc_ring *ring,
 		   le32_to_cpu(rx_desc->wb.upper.status_error));
 }
 
+/* Mapping HW RSS Type to enum pkt_hash_types */
+static const enum pkt_hash_types igc_rss_type_table[IGC_RSS_TYPE_MAX_TABLE] = {
+	[IGC_RSS_TYPE_NO_HASH]		= PKT_HASH_TYPE_L2,
+	[IGC_RSS_TYPE_HASH_TCP_IPV4]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_IPV4]	= PKT_HASH_TYPE_L3,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_IPV6_EX]	= PKT_HASH_TYPE_L3,
+	[IGC_RSS_TYPE_HASH_IPV6]	= PKT_HASH_TYPE_L3,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6_EX] = PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_UDP_IPV4]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6_EX] = PKT_HASH_TYPE_L4,
+	[10] = PKT_HASH_TYPE_NONE, /* RSS Type above 9 "Reserved" by HW  */
+	[11] = PKT_HASH_TYPE_NONE, /* keep array sized for SW bit-mask   */
+	[12] = PKT_HASH_TYPE_NONE, /* to handle future HW revisons       */
+	[13] = PKT_HASH_TYPE_NONE,
+	[14] = PKT_HASH_TYPE_NONE,
+	[15] = PKT_HASH_TYPE_NONE,
+};
+
 static inline void igc_rx_hash(struct igc_ring *ring,
 			       union igc_adv_rx_desc *rx_desc,
 			       struct sk_buff *skb)
 {
-	if (ring->netdev->features & NETIF_F_RXHASH)
-		skb_set_hash(skb,
-			     le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
-			     PKT_HASH_TYPE_L3);
+	if (ring->netdev->features & NETIF_F_RXHASH) {
+		u32 rss_hash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
+		u32 rss_type = igc_rss_type(rx_desc);
+
+		skb_set_hash(skb, rss_hash, igc_rss_type_table[rss_type]);
+	}
 }
 
 static void igc_rx_vlan(struct igc_ring *rx_ring,
@@ -2214,6 +2247,8 @@ static bool igc_alloc_rx_buffers_zc(struct igc_ring *ring, u16 count)
 	if (!count)
 		return ok;
 
+	XSK_CHECK_PRIV_TYPE(struct igc_xdp_buff);
+
 	desc = IGC_RX_DESC(ring, i);
 	bi = &ring->rx_buffer_info[i];
 	i -= ring->count;
@@ -2387,6 +2422,8 @@ static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp)
 	nq = txring_txq(ring);
 
 	__netif_tx_lock(nq, cpu);
+	/* Avoid transmit queue timeout since we share it with the slow path */
+	txq_trans_cond_update(nq);
 	res = igc_xdp_init_tx_descriptor(ring, xdpf);
 	__netif_tx_unlock(nq);
 	return res;
@@ -2498,8 +2535,8 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 		union igc_adv_rx_desc *rx_desc;
 		struct igc_rx_buffer *rx_buffer;
 		unsigned int size, truesize;
+		struct igc_xdp_buff ctx;
 		ktime_t timestamp = 0;
-		struct xdp_buff xdp;
 		int pkt_offset = 0;
 		void *pktbuf;
 
@@ -2528,18 +2565,20 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 		if (igc_test_staterr(rx_desc, IGC_RXDADV_STAT_TSIP)) {
 			timestamp = igc_ptp_rx_pktstamp(q_vector->adapter,
 							pktbuf);
+			ctx.rx_ts = timestamp;
 			pkt_offset = IGC_TS_HDR_LEN;
 			size -= IGC_TS_HDR_LEN;
 		}
 
 		if (!skb) {
-			xdp_init_buff(&xdp, truesize, &rx_ring->xdp_rxq);
-			xdp_prepare_buff(&xdp, pktbuf - igc_rx_offset(rx_ring),
+			xdp_init_buff(&ctx.xdp, truesize, &rx_ring->xdp_rxq);
+			xdp_prepare_buff(&ctx.xdp, pktbuf - igc_rx_offset(rx_ring),
 					 igc_rx_offset(rx_ring) + pkt_offset,
 					 size, true);
-			xdp_buff_clear_frags_flag(&xdp);
+			xdp_buff_clear_frags_flag(&ctx.xdp);
+			ctx.rx_desc = rx_desc;
 
-			skb = igc_xdp_run_prog(adapter, &xdp);
+			skb = igc_xdp_run_prog(adapter, &ctx.xdp);
 		}
 
 		if (IS_ERR(skb)) {
@@ -2561,9 +2600,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 		} else if (skb)
 			igc_add_rx_frag(rx_ring, rx_buffer, skb, size);
 		else if (ring_uses_build_skb(rx_ring))
-			skb = igc_build_skb(rx_ring, rx_buffer, &xdp);
+			skb = igc_build_skb(rx_ring, rx_buffer, &ctx.xdp);
 		else
-			skb = igc_construct_skb(rx_ring, rx_buffer, &xdp,
+			skb = igc_construct_skb(rx_ring, rx_buffer, &ctx.xdp,
 						timestamp);
 
 		/* exit if we failed to retrieve a buffer */
@@ -2664,6 +2703,15 @@ static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector,
 	napi_gro_receive(&q_vector->napi, skb);
 }
 
+static struct igc_xdp_buff *xsk_buff_to_igc_ctx(struct xdp_buff *xdp)
+{
+	/* xdp_buff pointer used by ZC code path is alloc as xdp_buff_xsk. The
+	 * igc_xdp_buff shares its layout with xdp_buff_xsk and private
+	 * igc_xdp_buff fields fall into xdp_buff_xsk->cb
+	 */
+       return (struct igc_xdp_buff *)xdp;
+}
+
 static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 {
 	struct igc_adapter *adapter = q_vector->adapter;
@@ -2682,6 +2730,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 	while (likely(total_packets < budget)) {
 		union igc_adv_rx_desc *desc;
 		struct igc_rx_buffer *bi;
+		struct igc_xdp_buff *ctx;
 		ktime_t timestamp = 0;
 		unsigned int size;
 		int res;
@@ -2699,9 +2748,13 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 
 		bi = &ring->rx_buffer_info[ntc];
 
+		ctx = xsk_buff_to_igc_ctx(bi->xdp);
+		ctx->rx_desc = desc;
+
 		if (igc_test_staterr(desc, IGC_RXDADV_STAT_TSIP)) {
 			timestamp = igc_ptp_rx_pktstamp(q_vector->adapter,
 							bi->xdp->data);
+			ctx->rx_ts = timestamp;
 
 			bi->xdp->data += IGC_TS_HDR_LEN;
 
@@ -2789,6 +2842,9 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 
 	__netif_tx_lock(nq, cpu);
 
+	/* Avoid transmit queue timeout since we share it with the slow path */
+	txq_trans_cond_update(nq);
+
 	budget = igc_desc_unused(ring);
 
 	while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) {
@@ -5212,7 +5268,7 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter)
 
 	if (tsicr & IGC_TSICR_TXTS) {
 		/* retrieve hardware timestamp */
-		schedule_work(&adapter->ptp_tx_work);
+		igc_ptp_tx_tstamp_event(adapter);
 		ack |= IGC_TSICR_TXTS;
 	}
 
@@ -6068,9 +6124,18 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 	size_t n;
 	int i;
 
-	adapter->qbv_enable = qopt->enable;
+	switch (qopt->cmd) {
+	case TAPRIO_CMD_REPLACE:
+		adapter->qbv_enable = true;
+		break;
+	case TAPRIO_CMD_DESTROY:
+		adapter->qbv_enable = false;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
 
-	if (!qopt->enable)
+	if (!adapter->qbv_enable)
 		return igc_tsn_clear_schedule(adapter);
 
 	if (qopt->base_time < 0)
@@ -6314,6 +6379,9 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 
 	__netif_tx_lock(nq, cpu);
 
+	/* Avoid transmit queue timeout since we share it with the slow path */
+	txq_trans_cond_update(nq);
+
 	drops = 0;
 	for (i = 0; i < num_frames; i++) {
 		int err;
@@ -6454,6 +6522,58 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg)
 	return value;
 }
 
+/* Mapping HW RSS Type to enum xdp_rss_hash_type */
+static enum xdp_rss_hash_type igc_xdp_rss_type[IGC_RSS_TYPE_MAX_TABLE] = {
+	[IGC_RSS_TYPE_NO_HASH]		= XDP_RSS_TYPE_L2,
+	[IGC_RSS_TYPE_HASH_TCP_IPV4]	= XDP_RSS_TYPE_L4_IPV4_TCP,
+	[IGC_RSS_TYPE_HASH_IPV4]	= XDP_RSS_TYPE_L3_IPV4,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6]	= XDP_RSS_TYPE_L4_IPV6_TCP,
+	[IGC_RSS_TYPE_HASH_IPV6_EX]	= XDP_RSS_TYPE_L3_IPV6_EX,
+	[IGC_RSS_TYPE_HASH_IPV6]	= XDP_RSS_TYPE_L3_IPV6,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6_EX] = XDP_RSS_TYPE_L4_IPV6_TCP_EX,
+	[IGC_RSS_TYPE_HASH_UDP_IPV4]	= XDP_RSS_TYPE_L4_IPV4_UDP,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6]	= XDP_RSS_TYPE_L4_IPV6_UDP,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6_EX] = XDP_RSS_TYPE_L4_IPV6_UDP_EX,
+	[10] = XDP_RSS_TYPE_NONE, /* RSS Type above 9 "Reserved" by HW  */
+	[11] = XDP_RSS_TYPE_NONE, /* keep array sized for SW bit-mask   */
+	[12] = XDP_RSS_TYPE_NONE, /* to handle future HW revisons       */
+	[13] = XDP_RSS_TYPE_NONE,
+	[14] = XDP_RSS_TYPE_NONE,
+	[15] = XDP_RSS_TYPE_NONE,
+};
+
+static int igc_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash,
+			   enum xdp_rss_hash_type *rss_type)
+{
+	const struct igc_xdp_buff *ctx = (void *)_ctx;
+
+	if (!(ctx->xdp.rxq->dev->features & NETIF_F_RXHASH))
+		return -ENODATA;
+
+	*hash = le32_to_cpu(ctx->rx_desc->wb.lower.hi_dword.rss);
+	*rss_type = igc_xdp_rss_type[igc_rss_type(ctx->rx_desc)];
+
+	return 0;
+}
+
+static int igc_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp)
+{
+	const struct igc_xdp_buff *ctx = (void *)_ctx;
+
+	if (igc_test_staterr(ctx->rx_desc, IGC_RXDADV_STAT_TSIP)) {
+		*timestamp = ctx->rx_ts;
+
+		return 0;
+	}
+
+	return -ENODATA;
+}
+
+static const struct xdp_metadata_ops igc_xdp_metadata_ops = {
+	.xmo_rx_hash			= igc_xdp_rx_hash,
+	.xmo_rx_timestamp		= igc_xdp_rx_timestamp,
+};
+
 /**
  * igc_probe - Device Initialization Routine
  * @pdev: PCI device information struct
@@ -6527,6 +6647,7 @@ static int igc_probe(struct pci_dev *pdev,
 	hw->hw_addr = adapter->io_addr;
 
 	netdev->netdev_ops = &igc_netdev_ops;
+	netdev->xdp_metadata_ops = &igc_xdp_metadata_ops;
 	igc_ethtool_set_ops(netdev);
 	netdev->watchdog_timeo = 5 * HZ;
 
@@ -6554,6 +6675,7 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->features |= NETIF_F_TSO;
 	netdev->features |= NETIF_F_TSO6;
 	netdev->features |= NETIF_F_TSO_ECN;
+	netdev->features |= NETIF_F_RXHASH;
 	netdev->features |= NETIF_F_RXCSUM;
 	netdev->features |= NETIF_F_HW_CSUM;
 	netdev->features |= NETIF_F_SCTP_CRC;
@@ -6723,6 +6845,9 @@ static void igc_remove(struct pci_dev *pdev)
 
 	igc_ptp_stop(adapter);
 
+	pci_disable_ptm(pdev);
+	pci_clear_master(pdev);
+
 	set_bit(__IGC_DOWN, &adapter->state);
 
 	del_timer_sync(&adapter->watchdog_timer);
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 4e10ced736db..32ef112f8291 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -536,9 +536,34 @@ static void igc_ptp_enable_rx_timestamp(struct igc_adapter *adapter)
 	wr32(IGC_TSYNCRXCTL, val);
 }
 
+static void igc_ptp_clear_tx_tstamp(struct igc_adapter *adapter)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&adapter->ptp_tx_lock, flags);
+
+	dev_kfree_skb_any(adapter->ptp_tx_skb);
+	adapter->ptp_tx_skb = NULL;
+
+	spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags);
+}
+
 static void igc_ptp_disable_tx_timestamp(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
+	int i;
+
+	/* Clear the flags first to avoid new packets to be enqueued
+	 * for TX timestamping.
+	 */
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *tx_ring = adapter->tx_ring[i];
+
+		clear_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags);
+	}
+
+	/* Now we can clean the pending TX timestamp requests. */
+	igc_ptp_clear_tx_tstamp(adapter);
 
 	wr32(IGC_TSYNCTXCTL, 0);
 }
@@ -546,12 +571,23 @@ static void igc_ptp_disable_tx_timestamp(struct igc_adapter *adapter)
 static void igc_ptp_enable_tx_timestamp(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
+	int i;
 
 	wr32(IGC_TSYNCTXCTL, IGC_TSYNCTXCTL_ENABLED | IGC_TSYNCTXCTL_TXSYNSIG);
 
 	/* Read TXSTMP registers to discard any timestamp previously stored. */
 	rd32(IGC_TXSTMPL);
 	rd32(IGC_TXSTMPH);
+
+	/* The hardware is ready to accept TX timestamp requests,
+	 * notify the transmit path.
+	 */
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct igc_ring *tx_ring = adapter->tx_ring[i];
+
+		set_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags);
+	}
+
 }
 
 /**
@@ -603,6 +639,7 @@ static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter,
 	return 0;
 }
 
+/* Requires adapter->ptp_tx_lock held by caller. */
 static void igc_ptp_tx_timeout(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
@@ -610,7 +647,6 @@ static void igc_ptp_tx_timeout(struct igc_adapter *adapter)
 	dev_kfree_skb_any(adapter->ptp_tx_skb);
 	adapter->ptp_tx_skb = NULL;
 	adapter->tx_hwtstamp_timeouts++;
-	clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state);
 	/* Clear the tx valid bit in TSYNCTXCTL register to enable interrupt. */
 	rd32(IGC_TXSTMPH);
 	netdev_warn(adapter->netdev, "Tx timestamp timeout\n");
@@ -618,20 +654,20 @@ static void igc_ptp_tx_timeout(struct igc_adapter *adapter)
 
 void igc_ptp_tx_hang(struct igc_adapter *adapter)
 {
-	bool timeout = time_is_before_jiffies(adapter->ptp_tx_start +
-					      IGC_PTP_TX_TIMEOUT);
+	unsigned long flags;
 
-	if (!test_bit(__IGC_PTP_TX_IN_PROGRESS, &adapter->state))
-		return;
+	spin_lock_irqsave(&adapter->ptp_tx_lock, flags);
 
-	/* If we haven't received a timestamp within the timeout, it is
-	 * reasonable to assume that it will never occur, so we can unlock the
-	 * timestamp bit when this occurs.
-	 */
-	if (timeout) {
-		cancel_work_sync(&adapter->ptp_tx_work);
-		igc_ptp_tx_timeout(adapter);
-	}
+	if (!adapter->ptp_tx_skb)
+		goto unlock;
+
+	if (time_is_after_jiffies(adapter->ptp_tx_start + IGC_PTP_TX_TIMEOUT))
+		goto unlock;
+
+	igc_ptp_tx_timeout(adapter);
+
+unlock:
+	spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags);
 }
 
 /**
@@ -641,20 +677,57 @@ void igc_ptp_tx_hang(struct igc_adapter *adapter)
  * 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.
+ *
+ * Context: Expects adapter->ptp_tx_lock to be held by caller.
  */
 static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter)
 {
 	struct sk_buff *skb = adapter->ptp_tx_skb;
 	struct skb_shared_hwtstamps shhwtstamps;
 	struct igc_hw *hw = &adapter->hw;
+	u32 tsynctxctl;
 	int adjust = 0;
 	u64 regval;
 
 	if (WARN_ON_ONCE(!skb))
 		return;
 
-	regval = rd32(IGC_TXSTMPL);
-	regval |= (u64)rd32(IGC_TXSTMPH) << 32;
+	tsynctxctl = rd32(IGC_TSYNCTXCTL);
+	tsynctxctl &= IGC_TSYNCTXCTL_TXTT_0;
+	if (tsynctxctl) {
+		regval = rd32(IGC_TXSTMPL);
+		regval |= (u64)rd32(IGC_TXSTMPH) << 32;
+	} else {
+		/* There's a bug in the hardware that could cause
+		 * missing interrupts for TX timestamping. The issue
+		 * is that for new interrupts to be triggered, the
+		 * IGC_TXSTMPH_0 register must be read.
+		 *
+		 * To avoid discarding a valid timestamp that just
+		 * happened at the "wrong" time, we need to confirm
+		 * that there was no timestamp captured, we do that by
+		 * assuming that no two timestamps in sequence have
+		 * the same nanosecond value.
+		 *
+		 * So, we read the "low" register, read the "high"
+		 * register (to latch a new timestamp) and read the
+		 * "low" register again, if "old" and "new" versions
+		 * of the "low" register are different, a valid
+		 * timestamp was captured, we can read the "high"
+		 * register again.
+		 */
+		u32 txstmpl_old, txstmpl_new;
+
+		txstmpl_old = rd32(IGC_TXSTMPL);
+		rd32(IGC_TXSTMPH);
+		txstmpl_new = rd32(IGC_TXSTMPL);
+
+		if (txstmpl_old == txstmpl_new)
+			return;
+
+		regval = txstmpl_new;
+		regval |= (u64)rd32(IGC_TXSTMPH) << 32;
+	}
 	if (igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval))
 		return;
 
@@ -676,13 +749,7 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter)
 	shhwtstamps.hwtstamp =
 		ktime_add_ns(shhwtstamps.hwtstamp, adjust);
 
-	/* Clear the lock early before calling skb_tstamp_tx so that
-	 * applications are not woken up before the lock bit is clear. We use
-	 * a copy of the skb pointer to ensure other threads can't change it
-	 * while we're notifying the stack.
-	 */
 	adapter->ptp_tx_skb = NULL;
-	clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state);
 
 	/* Notify the stack and free the skb after we've unlocked */
 	skb_tstamp_tx(skb, &shhwtstamps);
@@ -690,27 +757,25 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter)
 }
 
 /**
- * igc_ptp_tx_work
- * @work: pointer to work struct
+ * igc_ptp_tx_tstamp_event
+ * @adapter: board private structure
  *
- * This work function polls the TSYNCTXCTL valid bit to determine when a
- * timestamp has been taken for the current stored skb.
+ * Called when a TX timestamp interrupt happens to retrieve the
+ * timestamp and send it up to the socket.
  */
-static void igc_ptp_tx_work(struct work_struct *work)
+void igc_ptp_tx_tstamp_event(struct igc_adapter *adapter)
 {
-	struct igc_adapter *adapter = container_of(work, struct igc_adapter,
-						   ptp_tx_work);
-	struct igc_hw *hw = &adapter->hw;
-	u32 tsynctxctl;
+	unsigned long flags;
 
-	if (!test_bit(__IGC_PTP_TX_IN_PROGRESS, &adapter->state))
-		return;
+	spin_lock_irqsave(&adapter->ptp_tx_lock, flags);
 
-	tsynctxctl = rd32(IGC_TSYNCTXCTL);
-	if (WARN_ON_ONCE(!(tsynctxctl & IGC_TSYNCTXCTL_TXTT_0)))
-		return;
+	if (!adapter->ptp_tx_skb)
+		goto unlock;
 
 	igc_ptp_tx_hwtstamp(adapter);
+
+unlock:
+	spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags);
 }
 
 /**
@@ -959,8 +1024,8 @@ void igc_ptp_init(struct igc_adapter *adapter)
 		return;
 	}
 
+	spin_lock_init(&adapter->ptp_tx_lock);
 	spin_lock_init(&adapter->tmreg_lock);
-	INIT_WORK(&adapter->ptp_tx_work, igc_ptp_tx_work);
 
 	adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
 	adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
@@ -1020,10 +1085,7 @@ void igc_ptp_suspend(struct igc_adapter *adapter)
 	if (!(adapter->ptp_flags & IGC_PTP_ENABLED))
 		return;
 
-	cancel_work_sync(&adapter->ptp_tx_work);
-	dev_kfree_skb_any(adapter->ptp_tx_skb);
-	adapter->ptp_tx_skb = NULL;
-	clear_bit_unlock(__IGC_PTP_TX_IN_PROGRESS, &adapter->state);
+	igc_ptp_clear_tx_tstamp(adapter);
 
 	if (pci_device_is_present(adapter->pdev)) {
 		igc_ptp_time_save(adapter);