Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

The UDP offload conflict is dealt with by simply taking what is
in net-next where we have removed all of the UFO handling code
entirely.

The TCP conflict was a case of local variables in a function
being removed from both net and net-next.

In netvsc we had an assignment right next to where a missing
set of u64 stats sync object inits were added.

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

15 files changed, 183 insertions, 55 deletions

diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 86058a9f3417..1d307f2def2d 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -1785,9 +1785,9 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata)
 
 	xgene_enet_gpiod_get(pdata);
 
-	if (pdata->phy_mode != PHY_INTERFACE_MODE_SGMII) {
-		pdata->clk = devm_clk_get(&pdev->dev, NULL);
-		if (IS_ERR(pdata->clk)) {
+	pdata->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(pdata->clk)) {
+		if (pdata->phy_mode != PHY_INTERFACE_MODE_SGMII) {
 			/* Abort if the clock is defined but couldn't be
 			 * retrived. Always abort if the clock is missing on
 			 * DT system as the driver can't cope with this case.
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index f411936b744c..a1125d10c825 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -2368,6 +2368,7 @@ static int b44_init_one(struct ssb_device *sdev,
 	bp->msg_enable = netif_msg_init(b44_debug, B44_DEF_MSG_ENABLE);
 
 	spin_lock_init(&bp->lock);
+	u64_stats_init(&bp->hw_stats.syncp);
 
 	bp->rx_pending = B44_DEF_RX_RING_PENDING;
 	bp->tx_pending = B44_DEF_TX_RING_PENDING;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 99576ba4187f..32c116652755 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -111,6 +111,7 @@ static void send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8);
 static void send_request_unmap(struct ibmvnic_adapter *, u8);
 static void send_login(struct ibmvnic_adapter *adapter);
 static void send_cap_queries(struct ibmvnic_adapter *adapter);
+static int init_sub_crqs(struct ibmvnic_adapter *);
 static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter);
 static int ibmvnic_init(struct ibmvnic_adapter *);
 static void release_crq_queue(struct ibmvnic_adapter *);
@@ -676,6 +677,7 @@ static int ibmvnic_login(struct net_device *netdev)
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
 	unsigned long timeout = msecs_to_jiffies(30000);
 	struct device *dev = &adapter->vdev->dev;
+	int rc;
 
 	do {
 		if (adapter->renegotiate) {
@@ -689,6 +691,18 @@ static int ibmvnic_login(struct net_device *netdev)
 				dev_err(dev, "Capabilities query timeout\n");
 				return -1;
 			}
+			rc = init_sub_crqs(adapter);
+			if (rc) {
+				dev_err(dev,
+					"Initialization of SCRQ's failed\n");
+				return -1;
+			}
+			rc = init_sub_crq_irqs(adapter);
+			if (rc) {
+				dev_err(dev,
+					"Initialization of SCRQ's irqs failed\n");
+				return -1;
+			}
 		}
 
 		reinit_completion(&adapter->init_done);
@@ -3106,7 +3120,6 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq,
 			 *req_value,
 			 (long int)be64_to_cpu(crq->request_capability_rsp.
 					       number), name);
-		release_sub_crqs(adapter);
 		*req_value = be64_to_cpu(crq->request_capability_rsp.number);
 		ibmvnic_send_req_caps(adapter, 1);
 		return;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index d464fceb300f..8a969d8f0790 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1113,6 +1113,8 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring)
 	if (!tx_ring->tx_bi)
 		goto err;
 
+	u64_stats_init(&tx_ring->syncp);
+
 	/* round up to nearest 4K */
 	tx_ring->size = tx_ring->count * sizeof(struct i40e_tx_desc);
 	/* add u32 for head writeback, align after this takes care of
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 084c53582793..032f8ac06357 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -2988,6 +2988,8 @@ int ixgbevf_setup_tx_resources(struct ixgbevf_ring *tx_ring)
 	if (!tx_ring->tx_buffer_info)
 		goto err;
 
+	u64_stats_init(&tx_ring->syncp);
+
 	/* round up to nearest 4K */
 	tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc);
 	tx_ring->size = ALIGN(tx_ring->size, 4096);
@@ -3046,6 +3048,8 @@ int ixgbevf_setup_rx_resources(struct ixgbevf_ring *rx_ring)
 	if (!rx_ring->rx_buffer_info)
 		goto err;
 
+	u64_stats_init(&rx_ring->syncp);
+
 	/* Round up to nearest 4K */
 	rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc);
 	rx_ring->size = ALIGN(rx_ring->size, 4096);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index c751a1d434ad..3d4e4a5d00d1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -223,6 +223,7 @@ static void mlx4_en_get_wol(struct net_device *netdev,
 			    struct ethtool_wolinfo *wol)
 {
 	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	struct mlx4_caps *caps = &priv->mdev->dev->caps;
 	int err = 0;
 	u64 config = 0;
 	u64 mask;
@@ -235,24 +236,24 @@ static void mlx4_en_get_wol(struct net_device *netdev,
 	mask = (priv->port == 1) ? MLX4_DEV_CAP_FLAG_WOL_PORT1 :
 		MLX4_DEV_CAP_FLAG_WOL_PORT2;
 
-	if (!(priv->mdev->dev->caps.flags & mask)) {
+	if (!(caps->flags & mask)) {
 		wol->supported = 0;
 		wol->wolopts = 0;
 		return;
 	}
 
+	if (caps->wol_port[priv->port])
+		wol->supported = WAKE_MAGIC;
+	else
+		wol->supported = 0;
+
 	err = mlx4_wol_read(priv->mdev->dev, &config, priv->port);
 	if (err) {
 		en_err(priv, "Failed to get WoL information\n");
 		return;
 	}
 
-	if (config & MLX4_EN_WOL_MAGIC)
-		wol->supported = WAKE_MAGIC;
-	else
-		wol->supported = 0;
-
-	if (config & MLX4_EN_WOL_ENABLED)
+	if ((config & MLX4_EN_WOL_ENABLED) && (config & MLX4_EN_WOL_MAGIC))
 		wol->wolopts = WAKE_MAGIC;
 	else
 		wol->wolopts = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 436f7689a032..bf1638044a7a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -574,16 +574,21 @@ static inline __wsum get_fixed_vlan_csum(__wsum hw_checksum,
  * header, the HW adds it. To address that, we are subtracting the pseudo
  * header checksum from the checksum value provided by the HW.
  */
-static void get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb,
-				struct iphdr *iph)
+static int get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb,
+			       struct iphdr *iph)
 {
 	__u16 length_for_csum = 0;
 	__wsum csum_pseudo_header = 0;
+	__u8 ipproto = iph->protocol;
+
+	if (unlikely(ipproto == IPPROTO_SCTP))
+		return -1;
 
 	length_for_csum = (be16_to_cpu(iph->tot_len) - (iph->ihl << 2));
 	csum_pseudo_header = csum_tcpudp_nofold(iph->saddr, iph->daddr,
-						length_for_csum, iph->protocol, 0);
+						length_for_csum, ipproto, 0);
 	skb->csum = csum_sub(hw_checksum, csum_pseudo_header);
+	return 0;
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -594,17 +599,20 @@ static void get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb,
 static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 			       struct ipv6hdr *ipv6h)
 {
+	__u8 nexthdr = ipv6h->nexthdr;
 	__wsum csum_pseudo_hdr = 0;
 
-	if (unlikely(ipv6h->nexthdr == IPPROTO_FRAGMENT ||
-		     ipv6h->nexthdr == IPPROTO_HOPOPTS))
+	if (unlikely(nexthdr == IPPROTO_FRAGMENT ||
+		     nexthdr == IPPROTO_HOPOPTS ||
+		     nexthdr == IPPROTO_SCTP))
 		return -1;
-	hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(ipv6h->nexthdr));
+	hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(nexthdr));
 
 	csum_pseudo_hdr = csum_partial(&ipv6h->saddr,
 				       sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0);
 	csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ipv6h->payload_len);
-	csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ntohs(ipv6h->nexthdr));
+	csum_pseudo_hdr = csum_add(csum_pseudo_hdr,
+				   (__force __wsum)htons(nexthdr));
 
 	skb->csum = csum_sub(hw_checksum, csum_pseudo_hdr);
 	skb->csum = csum_add(skb->csum, csum_partial(ipv6h, sizeof(struct ipv6hdr), 0));
@@ -627,11 +635,10 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 	}
 
 	if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4))
-		get_fixed_ipv4_csum(hw_checksum, skb, hdr);
+		return get_fixed_ipv4_csum(hw_checksum, skb, hdr);
 #if IS_ENABLED(CONFIG_IPV6)
-	else if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6))
-		if (unlikely(get_fixed_ipv6_csum(hw_checksum, skb, hdr)))
-			return -1;
+	if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6))
+		return get_fixed_ipv6_csum(hw_checksum, skb, hdr);
 #endif
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 37e84a59e751..041c0ed65929 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -159,8 +159,9 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[32] = "Loopback source checks support",
 		[33] = "RoCEv2 support",
 		[34] = "DMFS Sniffer support (UC & MC)",
-		[35] = "QinQ VST mode support",
-		[36] = "sl to vl mapping table change event support"
+		[35] = "Diag counters per port",
+		[36] = "QinQ VST mode support",
+		[37] = "sl to vl mapping table change event support",
 	};
 	int i;
 
@@ -764,6 +765,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET	0x3e
 #define QUERY_DEV_CAP_MAX_PKEY_OFFSET		0x3f
 #define QUERY_DEV_CAP_EXT_FLAGS_OFFSET		0x40
+#define QUERY_DEV_CAP_WOL_OFFSET		0x43
 #define QUERY_DEV_CAP_FLAGS_OFFSET		0x44
 #define QUERY_DEV_CAP_RSVD_UAR_OFFSET		0x48
 #define QUERY_DEV_CAP_UAR_SZ_OFFSET		0x49
@@ -920,6 +922,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	MLX4_GET(ext_flags, outbox, QUERY_DEV_CAP_EXT_FLAGS_OFFSET);
 	MLX4_GET(flags, outbox, QUERY_DEV_CAP_FLAGS_OFFSET);
 	dev_cap->flags = flags | (u64)ext_flags << 32;
+	MLX4_GET(field, outbox, QUERY_DEV_CAP_WOL_OFFSET);
+	dev_cap->wol_port[1] = !!(field & 0x20);
+	dev_cap->wol_port[2] = !!(field & 0x40);
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_UAR_OFFSET);
 	dev_cap->reserved_uars = field >> 4;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_UAR_SZ_OFFSET);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 5343a0599253..b52ba01aa486 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -129,6 +129,7 @@ struct mlx4_dev_cap {
 	u32 dmfs_high_rate_qpn_range;
 	struct mlx4_rate_limit_caps rl_caps;
 	struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1];
+	bool wol_port[MLX4_MAX_PORTS + 1];
 };
 
 struct mlx4_func_cap {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index a27c9c13a36e..09b9bc17bce9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -424,6 +424,8 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.stat_rate_support  = dev_cap->stat_rate_support;
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 	dev->caps.max_rss_tbl_sz     = dev_cap->max_rss_tbl_sz;
+	dev->caps.wol_port[1]          = dev_cap->wol_port[1];
+	dev->caps.wol_port[2]          = dev_cap->wol_port[2];
 
 	/* Save uar page shift */
 	if (!mlx4_is_slave(dev)) {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 656b2d3f1bee..5eb1606765c5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -626,8 +626,8 @@ static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp_port->mlxsw_sp->bridge,
 						orig_dev);
-	if (WARN_ON(!bridge_port))
-		return -EINVAL;
+	if (!bridge_port)
+		return 0;
 
 	err = mlxsw_sp_bridge_port_flood_table_set(mlxsw_sp_port, bridge_port,
 						   MLXSW_SP_FLOOD_TYPE_UC,
@@ -711,8 +711,8 @@ static int mlxsw_sp_port_attr_mc_router_set(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp_port->mlxsw_sp->bridge,
 						orig_dev);
-	if (WARN_ON(!bridge_port))
-		return -EINVAL;
+	if (!bridge_port)
+		return 0;
 
 	if (!bridge_port->bridge_device->multicast_enabled)
 		return 0;
@@ -1283,15 +1283,15 @@ static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port,
 		return 0;
 
 	bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev);
-	if (WARN_ON(!bridge_port))
-		return -EINVAL;
+	if (!bridge_port)
+		return 0;
 
 	bridge_device = bridge_port->bridge_device;
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_bridge(mlxsw_sp_port,
 							       bridge_device,
 							       mdb->vid);
-	if (WARN_ON(!mlxsw_sp_port_vlan))
-		return -EINVAL;
+	if (!mlxsw_sp_port_vlan)
+		return 0;
 
 	fid_index = mlxsw_sp_fid_index(mlxsw_sp_port_vlan->fid);
 
@@ -1407,15 +1407,15 @@ static int mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port,
 	int err = 0;
 
 	bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev);
-	if (WARN_ON(!bridge_port))
-		return -EINVAL;
+	if (!bridge_port)
+		return 0;
 
 	bridge_device = bridge_port->bridge_device;
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_bridge(mlxsw_sp_port,
 							       bridge_device,
 							       mdb->vid);
-	if (WARN_ON(!mlxsw_sp_port_vlan))
-		return -EINVAL;
+	if (!mlxsw_sp_port_vlan)
+		return 0;
 
 	fid_index = mlxsw_sp_fid_index(mlxsw_sp_port_vlan->fid);
 
@@ -1974,6 +1974,17 @@ static void mlxsw_sp_fdb_fini(struct mlxsw_sp *mlxsw_sp)
 
 }
 
+static void mlxsw_sp_mids_fini(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_mid *mid, *tmp;
+
+	list_for_each_entry_safe(mid, tmp, &mlxsw_sp->bridge->mids_list, list) {
+		list_del(&mid->list);
+		clear_bit(mid->mid, mlxsw_sp->bridge->mids_bitmap);
+		kfree(mid);
+	}
+}
+
 int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_bridge *bridge;
@@ -1996,7 +2007,7 @@ int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp)
 void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	mlxsw_sp_fdb_fini(mlxsw_sp);
-	WARN_ON(!list_empty(&mlxsw_sp->bridge->mids_list));
+	mlxsw_sp_mids_fini(mlxsw_sp);
 	WARN_ON(!list_empty(&mlxsw_sp->bridge->bridges_list));
 	kfree(mlxsw_sp->bridge);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index ea471604450e..4a990033c4d5 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -513,6 +513,7 @@ nfp_net_tx_ring_init(struct nfp_net_tx_ring *tx_ring,
 	tx_ring->idx = idx;
 	tx_ring->r_vec = r_vec;
 	tx_ring->is_xdp = is_xdp;
+	u64_stats_init(&tx_ring->r_vec->tx_sync);
 
 	tx_ring->qcidx = tx_ring->idx * nn->stride_tx;
 	tx_ring->qcp_q = nn->tx_bar + NFP_QCP_QUEUE_OFF(tx_ring->qcidx);
@@ -532,6 +533,7 @@ nfp_net_rx_ring_init(struct nfp_net_rx_ring *rx_ring,
 
 	rx_ring->idx = idx;
 	rx_ring->r_vec = r_vec;
+	u64_stats_init(&rx_ring->r_vec->rx_sync);
 
 	rx_ring->fl_qcidx = rx_ring->idx * nn->stride_rx;
 	rx_ring->qcp_fl = nn->rx_bar + NFP_QCP_QUEUE_OFF(rx_ring->fl_qcidx);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index c1ecce6b9141..376485d99357 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -253,7 +253,7 @@ int qed_mcp_cmd_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	size = MFW_DRV_MSG_MAX_DWORDS(p_info->mfw_mb_length) * sizeof(u32);
 	p_info->mfw_mb_cur = kzalloc(size, GFP_KERNEL);
 	p_info->mfw_mb_shadow = kzalloc(size, GFP_KERNEL);
-	if (!p_info->mfw_mb_shadow || !p_info->mfw_mb_addr)
+	if (!p_info->mfw_mb_cur || !p_info->mfw_mb_shadow)
 		goto err;
 
 	return 0;
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 32279d21c836..c2121d214f08 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -31,9 +31,18 @@
 
 #include "cpts.h"
 
+#define CPTS_SKB_TX_WORK_TIMEOUT 1 /* jiffies */
+
+struct cpts_skb_cb_data {
+	unsigned long tmo;
+};
+
 #define cpts_read32(c, r)	readl_relaxed(&c->reg->r)
 #define cpts_write32(c, v, r)	writel_relaxed(v, &c->reg->r)
 
+static int cpts_match(struct sk_buff *skb, unsigned int ptp_class,
+		      u16 ts_seqid, u8 ts_msgtype);
+
 static int event_expired(struct cpts_event *event)
 {
 	return time_after(jiffies, event->tmo);
@@ -77,6 +86,47 @@ static int cpts_purge_events(struct cpts *cpts)
 	return removed ? 0 : -1;
 }
 
+static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event)
+{
+	struct sk_buff *skb, *tmp;
+	u16 seqid;
+	u8 mtype;
+	bool found = false;
+
+	mtype = (event->high >> MESSAGE_TYPE_SHIFT) & MESSAGE_TYPE_MASK;
+	seqid = (event->high >> SEQUENCE_ID_SHIFT) & SEQUENCE_ID_MASK;
+
+	/* no need to grab txq.lock as access is always done under cpts->lock */
+	skb_queue_walk_safe(&cpts->txq, skb, tmp) {
+		struct skb_shared_hwtstamps ssh;
+		unsigned int class = ptp_classify_raw(skb);
+		struct cpts_skb_cb_data *skb_cb =
+					(struct cpts_skb_cb_data *)skb->cb;
+
+		if (cpts_match(skb, class, seqid, mtype)) {
+			u64 ns = timecounter_cyc2time(&cpts->tc, event->low);
+
+			memset(&ssh, 0, sizeof(ssh));
+			ssh.hwtstamp = ns_to_ktime(ns);
+			skb_tstamp_tx(skb, &ssh);
+			found = true;
+			__skb_unlink(skb, &cpts->txq);
+			dev_consume_skb_any(skb);
+			dev_dbg(cpts->dev, "match tx timestamp mtype %u seqid %04x\n",
+				mtype, seqid);
+		} else if (time_after(jiffies, skb_cb->tmo)) {
+			/* timeout any expired skbs over 1s */
+			dev_dbg(cpts->dev,
+				"expiring tx timestamp mtype %u seqid %04x\n",
+				mtype, seqid);
+			__skb_unlink(skb, &cpts->txq);
+			dev_consume_skb_any(skb);
+		}
+	}
+
+	return found;
+}
+
 /*
  * Returns zero if matching event type was found.
  */
@@ -101,9 +151,15 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 		event->low = lo;
 		type = event_type(event);
 		switch (type) {
+		case CPTS_EV_TX:
+			if (cpts_match_tx_ts(cpts, event)) {
+				/* if the new event matches an existing skb,
+				 * then don't queue it
+				 */
+				break;
+			}
 		case CPTS_EV_PUSH:
 		case CPTS_EV_RX:
-		case CPTS_EV_TX:
 			list_del_init(&event->list);
 			list_add_tail(&event->list, &cpts->events);
 			break;
@@ -224,6 +280,24 @@ static int cpts_ptp_enable(struct ptp_clock_info *ptp,
 	return -EOPNOTSUPP;
 }
 
+static long cpts_overflow_check(struct ptp_clock_info *ptp)
+{
+	struct cpts *cpts = container_of(ptp, struct cpts, info);
+	unsigned long delay = cpts->ov_check_period;
+	struct timespec64 ts;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cpts->lock, flags);
+	ts = ns_to_timespec64(timecounter_read(&cpts->tc));
+
+	if (!skb_queue_empty(&cpts->txq))
+		delay = CPTS_SKB_TX_WORK_TIMEOUT;
+	spin_unlock_irqrestore(&cpts->lock, flags);
+
+	pr_debug("cpts overflow check at %lld.%09lu\n", ts.tv_sec, ts.tv_nsec);
+	return (long)delay;
+}
+
 static struct ptp_clock_info cpts_info = {
 	.owner		= THIS_MODULE,
 	.name		= "CTPS timer",
@@ -236,18 +310,9 @@ static struct ptp_clock_info cpts_info = {
 	.gettime64	= cpts_ptp_gettime,
 	.settime64	= cpts_ptp_settime,
 	.enable		= cpts_ptp_enable,
+	.do_aux_work	= cpts_overflow_check,
 };
 
-static void cpts_overflow_check(struct work_struct *work)
-{
-	struct timespec64 ts;
-	struct cpts *cpts = container_of(work, struct cpts, overflow_work.work);
-
-	cpts_ptp_gettime(&cpts->info, &ts);
-	pr_debug("cpts overflow check at %lld.%09lu\n", ts.tv_sec, ts.tv_nsec);
-	schedule_delayed_work(&cpts->overflow_work, cpts->ov_check_period);
-}
-
 static int cpts_match(struct sk_buff *skb, unsigned int ptp_class,
 		      u16 ts_seqid, u8 ts_msgtype)
 {
@@ -299,7 +364,7 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type)
 		return 0;
 
 	spin_lock_irqsave(&cpts->lock, flags);
-	cpts_fifo_read(cpts, CPTS_EV_PUSH);
+	cpts_fifo_read(cpts, -1);
 	list_for_each_safe(this, next, &cpts->events) {
 		event = list_entry(this, struct cpts_event, list);
 		if (event_expired(event)) {
@@ -317,6 +382,19 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type)
 			break;
 		}
 	}
+
+	if (ev_type == CPTS_EV_TX && !ns) {
+		struct cpts_skb_cb_data *skb_cb =
+				(struct cpts_skb_cb_data *)skb->cb;
+		/* Not found, add frame to queue for processing later.
+		 * The periodic FIFO check will handle this.
+		 */
+		skb_get(skb);
+		/* get the timestamp for timeouts */
+		skb_cb->tmo = jiffies + msecs_to_jiffies(100);
+		__skb_queue_tail(&cpts->txq, skb);
+		ptp_schedule_worker(cpts->clock, 0);
+	}
 	spin_unlock_irqrestore(&cpts->lock, flags);
 
 	return ns;
@@ -358,6 +436,7 @@ int cpts_register(struct cpts *cpts)
 {
 	int err, i;
 
+	skb_queue_head_init(&cpts->txq);
 	INIT_LIST_HEAD(&cpts->events);
 	INIT_LIST_HEAD(&cpts->pool);
 	for (i = 0; i < CPTS_MAX_EVENTS; i++)
@@ -378,7 +457,7 @@ int cpts_register(struct cpts *cpts)
 	}
 	cpts->phc_index = ptp_clock_index(cpts->clock);
 
-	schedule_delayed_work(&cpts->overflow_work, cpts->ov_check_period);
+	ptp_schedule_worker(cpts->clock, cpts->ov_check_period);
 	return 0;
 
 err_ptp:
@@ -392,14 +471,15 @@ void cpts_unregister(struct cpts *cpts)
 	if (WARN_ON(!cpts->clock))
 		return;
 
-	cancel_delayed_work_sync(&cpts->overflow_work);
-
 	ptp_clock_unregister(cpts->clock);
 	cpts->clock = NULL;
 
 	cpts_write32(cpts, 0, int_enable);
 	cpts_write32(cpts, 0, control);
 
+	/* Drop all packet */
+	skb_queue_purge(&cpts->txq);
+
 	clk_disable(cpts->refclk);
 }
 EXPORT_SYMBOL_GPL(cpts_unregister);
@@ -476,7 +556,6 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs,
 	cpts->dev = dev;
 	cpts->reg = (struct cpsw_cpts __iomem *)regs;
 	spin_lock_init(&cpts->lock);
-	INIT_DELAYED_WORK(&cpts->overflow_work, cpts_overflow_check);
 
 	ret = cpts_of_parse(cpts, node);
 	if (ret)
diff --git a/drivers/net/ethernet/ti/cpts.h b/drivers/net/ethernet/ti/cpts.h
index 01ea82ba9cdc..73d73faf0f38 100644
--- a/drivers/net/ethernet/ti/cpts.h
+++ b/drivers/net/ethernet/ti/cpts.h
@@ -119,13 +119,13 @@ struct cpts {
 	u32 cc_mult; /* for the nominal frequency */
 	struct cyclecounter cc;
 	struct timecounter tc;
-	struct delayed_work overflow_work;
 	int phc_index;
 	struct clk *refclk;
 	struct list_head events;
 	struct list_head pool;
 	struct cpts_event pool_data[CPTS_MAX_EVENTS];
 	unsigned long ov_check_period;
+	struct sk_buff_head txq;
 };
 
 void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb);