Merge branch 'net-extend-socket-timestamping-API'

Miroslav Lichvar says:

====================
Extend socket timestamping API

Changes v5->v6:
- fixed skb_is_swtx_tstamp() when OPT_TX_SWHW is disabled and improved
  its description
- improved OPT_PKTINFO documentation
- improved scm_timestamping documentation

Changes v4->v5:
- fixed initialization of reserved fields in struct scm_ts_pktinfo

Changes v3->v4:
- added reserved fields to struct scm_ts_pktinfo
- replaced patch fixing false SW timestamps with a documentation fix
- updated OPT_TX_SWHW patch to handle false SW timestamps

Changes v2->v3:
- modified struct scm_ts_pktinfo to use fixed-width integer types
- added WARN_ON_ONCE for missing RCU lock in dev_get_by_napi_id()
- modified dev_get_by_napi_id() to not return dev in unexpected branch
- modified recv to return SCM_TIMESTAMPING_PKTINFO even if the interface
  index is unknown

Changes v1->v2:
- added separate patch for new NAPI functions
- split code from __sock_recv_timestamp() for better readability
- fixed RCU locking
- fixed compiler warning (missing case in switch in first patch)
- inline sw_tx_timestamp() in its only user

Changes RFC->v1:
- reworked SOF_TIMESTAMPING_OPT_PKTINFO patch to not add new fields to
  skb shared info (net device is now looked up by napi_id), not require
  any changes in drivers, and restrict the cmsg to incoming packets
- renamed SOF_TIMESTAMPING_OPT_MULTIMSG to SOF_TIMESTAMPING_OPT_TX_SWHW
  and fixed its description
- moved struct scm_ts_pktinfo from errqueue.h to net_tstamp.h as it
  can't be received from the error queue anymore
- improved commit descriptions and removed incorrect comment

This patchset adds new options to the timestamping API that will be
useful for NTP implementations and possibly other applications.

The first patch specifies a timestamp filter for NTP packets. The second
patch updates drivers that can timestamp all packets, or need to list
the filter as unsupported. There is no attempt to add the support to the
phyter driver.

The third patch adds two helper functions working with NAPI ID, which is
needed by the next patch. The fourth patch adds a new option to get a
new control message with the L2 length and interface index for incoming
packets with hardware timestamps.

The fifth patch fixes documentation on number of non-zero fields in
scm_timestamping and warns about false software timestamps when
SO_TIMESTAMP(NS) is combined with SCM_TIMESTAMPING.

The sixth patch adds a new option to request both software and hardware
timestamps for outgoing packets. The seventh patch updates drivers that
assumed software timestamping cannot be used together with hardware
timestamping.

The patches have been tested on x86_64 machines with igb and e1000e
drivers.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Documentation/networking/timestamping.txt

@@ -193,6 +193,24 @@ SOF_TIMESTAMPING_OPT_STATS:
   the transmit timestamps, such as how long a certain block of
   data was limited by peer's receiver window.
 
+SOF_TIMESTAMPING_OPT_PKTINFO:
+
+  Enable the SCM_TIMESTAMPING_PKTINFO control message for incoming
+  packets with hardware timestamps. The message contains struct
+  scm_ts_pktinfo, which supplies the index of the real interface which
+  received the packet and its length at layer 2. A valid (non-zero)
+  interface index will be returned only if CONFIG_NET_RX_BUSY_POLL is
+  enabled and the driver is using NAPI. The struct contains also two
+  other fields, but they are reserved and undefined.
+
+SOF_TIMESTAMPING_OPT_TX_SWHW:
+
+  Request both hardware and software timestamps for outgoing packets
+  when SOF_TIMESTAMPING_TX_HARDWARE and SOF_TIMESTAMPING_TX_SOFTWARE
+  are enabled at the same time. If both timestamps are generated,
+  two separate messages will be looped to the socket's error queue,
+  each containing just one timestamp.
+
 New applications are encouraged to pass SOF_TIMESTAMPING_OPT_ID to
 disambiguate timestamps and SOF_TIMESTAMPING_OPT_TSONLY to operate
 regardless of the setting of sysctl net.core.tstamp_allow_data.
@@ -312,7 +330,7 @@ struct scm_timestamping {
 };
 
 The structure can return up to three timestamps. This is a legacy
-feature. Only one field is non-zero at any time. Most timestamps
+feature. At least one field is non-zero at any time. Most timestamps
 are passed in ts[0]. Hardware timestamps are passed in ts[2].
 
 ts[1] used to hold hardware timestamps converted to system time.
@@ -321,6 +339,12 @@ a HW PTP clock source, to allow time conversion in userspace and
 optionally synchronize system time with a userspace PTP stack such
 as linuxptp. For the PTP clock API, see Documentation/ptp/ptp.txt.
 
+Note that if the SO_TIMESTAMP or SO_TIMESTAMPNS option is enabled
+together with SO_TIMESTAMPING using SOF_TIMESTAMPING_SOFTWARE, a false
+software timestamp will be generated in the recvmsg() call and passed
+in ts[0] when a real software timestamp is missing. This happens also
+on hardware transmit timestamps.
+
 2.1.1 Transmit timestamps with MSG_ERRQUEUE
 
 For transmit timestamps the outgoing packet is looped back to the

drivers/net/ethernet/amd/xgbe/xgbe-drv.c

@@ -1268,6 +1268,7 @@ static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata,
 	case HWTSTAMP_FILTER_NONE:
 		break;
 
+	case HWTSTAMP_FILTER_NTP_ALL:
 	case HWTSTAMP_FILTER_ALL:
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENALL, 1);
 		XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1);
@@ -1390,8 +1391,7 @@ static void xgbe_prep_tx_tstamp(struct xgbe_prv_data *pdata,
 		spin_unlock_irqrestore(&pdata->tstamp_lock, flags);
 	}
 
-	if (!XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES, PTP))
-		skb_tx_timestamp(skb);
+	skb_tx_timestamp(skb);
 }
 
 static void xgbe_prep_vlan(struct sk_buff *skb, struct xgbe_packet_data *packet)

drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c

@@ -15351,6 +15351,7 @@ int bnx2x_configure_ptp_filters(struct bnx2x *bp)
 		break;
 	case HWTSTAMP_FILTER_ALL:
 	case HWTSTAMP_FILTER_SOME:
+	case HWTSTAMP_FILTER_NTP_ALL:
 		bp->rx_filter = HWTSTAMP_FILTER_NONE;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:

drivers/net/ethernet/cavium/liquidio/lio_main.c

@@ -3024,6 +3024,7 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
 		conf.rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:

drivers/net/ethernet/cavium/liquidio/lio_vf_main.c

@@ -2085,6 +2085,7 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
 		conf.rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:

drivers/net/ethernet/cavium/octeon/octeon_mgmt.c

@@ -755,6 +755,7 @@ static int octeon_mgmt_ioctl_hwtstamp(struct net_device *netdev,
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
 		p->has_rx_tstamp = have_hw_timestamps;
 		config.rx_filter = HWTSTAMP_FILTER_ALL;
 		if (p->has_rx_tstamp) {

drivers/net/ethernet/intel/e1000e/netdev.c

@@ -3680,6 +3680,7 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter,
 		 * Delay Request messages but not both so fall-through to
 		 * time stamp all packets.
 		 */
+	case HWTSTAMP_FILTER_NTP_ALL:
 	case HWTSTAMP_FILTER_ALL:
 		is_l2 = true;
 		is_l4 = true;
@@ -5867,10 +5868,10 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 			adapter->tx_hwtstamp_skb = skb_get(skb);
 			adapter->tx_hwtstamp_start = jiffies;
 			schedule_work(&adapter->tx_hwtstamp_work);
-		} else {
-			skb_tx_timestamp(skb);
 		}
 
+		skb_tx_timestamp(skb);
+
 		netdev_sent_queue(netdev, skb->len);
 		e1000_tx_queue(tx_ring, tx_flags, count);
 		/* Make sure there is space in the ring for the next send. */

drivers/net/ethernet/intel/i40e/i40e_ptp.c

@@ -562,6 +562,7 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf,
 			config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 		}
 		break;
+	case HWTSTAMP_FILTER_NTP_ALL:
 	case HWTSTAMP_FILTER_ALL:
 	default:
 		return -ERANGE;

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

@@ -941,6 +941,7 @@ static int igb_ptp_set_timestamp_mode(struct igb_adapter *adapter,
 		is_l4 = true;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_NTP_ALL:
 	case HWTSTAMP_FILTER_ALL:
 		/* 82576 cannot timestamp all packets, which it needs to do to
 		 * support both V1 Sync and Delay_Req messages

drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c

@@ -883,6 +883,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
 				   IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_NTP_ALL:
 	case HWTSTAMP_FILTER_ALL:
 		/* The X550 controller is capable of timestamping all packets,
 		 * which allows it to accept any filter.

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

@@ -2375,6 +2375,7 @@ static int mlx4_en_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
 		config.rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:

drivers/net/ethernet/mellanox/mlx5/core/en_clock.c

@@ -128,6 +128,7 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
 		/* Disable CQE compression */
 		netdev_warn(dev, "Disabling cqe compression");
 		err = mlx5e_modify_rx_cqe_compression_locked(priv, false);

drivers/net/ethernet/neterion/vxge/vxge-main.c

@@ -3218,6 +3218,7 @@ static int vxge_hwtstamp_set(struct vxgedev *vdev, void __user *data)
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
 		if (vdev->devh->config.hwts_en != VXGE_HW_HWTS_ENABLE)
 			return -EFAULT;
 

drivers/net/ethernet/qlogic/qede/qede_ptp.c

@@ -244,6 +244,7 @@ static int qede_ptp_cfg_filters(struct qede_dev *edev)
 		break;
 	case HWTSTAMP_FILTER_ALL:
 	case HWTSTAMP_FILTER_SOME:
+	case HWTSTAMP_FILTER_NTP_ALL:
 		ptp->rx_filter = HWTSTAMP_FILTER_NONE;
 		rx_filter = QED_PTP_FILTER_ALL;
 		break;

drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c

@@ -1418,8 +1418,7 @@ static netdev_tx_t sxgbe_xmit(struct sk_buff *skb, struct net_device *dev)
 		priv->hw->desc->tx_enable_tstamp(first_desc);
 	}
 
-	if (!tqueue->hwts_tx_en)
-		skb_tx_timestamp(skb);
+	skb_tx_timestamp(skb);
 
 	priv->hw->dma->enable_dma_transmission(priv->ioaddr, txq_index);
 

drivers/net/ethernet/sfc/ef10.c

@@ -6068,6 +6068,7 @@ static int efx_ef10_ptp_set_ts_config(struct efx_nic *efx,
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
 		init->rx_filter = HWTSTAMP_FILTER_ALL;
 		rc = efx_ptp_change_mode(efx, true, 0);
 		if (!rc)

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c

@@ -644,6 +644,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 			ptp_over_ethernet = PTP_TCR_TSIPENA;
 			break;
 
+		case HWTSTAMP_FILTER_NTP_ALL:
 		case HWTSTAMP_FILTER_ALL:
 			/* time stamp any incoming packet */
 			config.rx_filter = HWTSTAMP_FILTER_ALL;
@@ -2879,8 +2880,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 		priv->xstats.tx_set_ic_bit++;
 	}
 
-	if (!priv->hwts_tx_en)
-		skb_tx_timestamp(skb);
+	skb_tx_timestamp(skb);
 
 	if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
 		     priv->hwts_tx_en)) {
@@ -3083,8 +3083,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		priv->xstats.tx_set_ic_bit++;
 	}
 
-	if (!priv->hwts_tx_en)
-		skb_tx_timestamp(skb);
+	skb_tx_timestamp(skb);
 
 	/* Ready to fill the first descriptor and set the OWN bit w/o any
 	 * problems because all the descriptors are actually ready to be

drivers/net/ethernet/ti/cpsw.c

@@ -1734,6 +1734,7 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
 		return -ERANGE;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:

drivers/net/ethernet/tile/tilegx.c

@@ -512,6 +512,7 @@ static int tile_hwtstamp_set(struct net_device *dev, struct ifreq *rq)
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
 		config.rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
 	default:

include/linux/netdevice.h

@@ -2456,6 +2456,7 @@ static inline int dev_recursion_level(void)
 struct net_device *dev_get_by_index(struct net *net, int ifindex);
 struct net_device *__dev_get_by_index(struct net *net, int ifindex);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
+struct net_device *dev_get_by_napi_id(unsigned int napi_id);
 int netdev_get_name(struct net *net, char *name, int ifindex);
 int dev_restart(struct net_device *dev);
 int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb);

include/linux/skbuff.h

@@ -858,6 +858,15 @@ static inline bool skb_pkt_type_ok(u32 ptype)
 	return ptype <= PACKET_OTHERHOST;
 }
 
+static inline unsigned int skb_napi_id(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	return skb->napi_id;
+#else
+	return 0;
+#endif
+}
+
 void kfree_skb(struct sk_buff *skb);
 void kfree_skb_list(struct sk_buff *segs);
 void skb_tx_error(struct sk_buff *skb);
@@ -3250,13 +3259,6 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 void skb_tstamp_tx(struct sk_buff *orig_skb,
 		   struct skb_shared_hwtstamps *hwtstamps);
 
-static inline void sw_tx_timestamp(struct sk_buff *skb)
-{
-	if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP &&
-	    !(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS))
-		skb_tstamp_tx(skb, NULL);
-}
-
 /**
  * skb_tx_timestamp() - Driver hook for transmit timestamping
  *
@@ -3272,7 +3274,8 @@ static inline void sw_tx_timestamp(struct sk_buff *skb)
 static inline void skb_tx_timestamp(struct sk_buff *skb)
 {
 	skb_clone_tx_timestamp(skb);
-	sw_tx_timestamp(skb);
+	if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP)
+		skb_tstamp_tx(skb, NULL);
 }
 
 /**

include/uapi/asm-generic/socket.h

@@ -100,4 +100,6 @@
 
 #define SO_COOKIE		57
 
+#define SCM_TIMESTAMPING_PKTINFO	58
+
 #endif /* __ASM_GENERIC_SOCKET_H */

include/uapi/linux/net_tstamp.h

@@ -9,6 +9,7 @@
 #ifndef _NET_TIMESTAMPING_H
 #define _NET_TIMESTAMPING_H
 
+#include <linux/types.h>
 #include <linux/socket.h>   /* for SO_TIMESTAMPING */
 
 /* SO_TIMESTAMPING gets an integer bit field comprised of these values */
@@ -26,8 +27,10 @@ enum {
 	SOF_TIMESTAMPING_OPT_CMSG = (1<<10),
 	SOF_TIMESTAMPING_OPT_TSONLY = (1<<11),
 	SOF_TIMESTAMPING_OPT_STATS = (1<<12),
+	SOF_TIMESTAMPING_OPT_PKTINFO = (1<<13),
+	SOF_TIMESTAMPING_OPT_TX_SWHW = (1<<14),
 
-	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_STATS,
+	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_TX_SWHW,
 	SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) |
 				 SOF_TIMESTAMPING_LAST
 };
@@ -125,6 +128,16 @@ enum hwtstamp_rx_filters {
 	HWTSTAMP_FILTER_PTP_V2_SYNC,
 	/* PTP v2/802.AS1, any layer, Delay_req packet */
 	HWTSTAMP_FILTER_PTP_V2_DELAY_REQ,
+
+	/* NTP, UDP, all versions and packet modes */
+	HWTSTAMP_FILTER_NTP_ALL,
+};
+
+/* SCM_TIMESTAMPING_PKTINFO control message */
+struct scm_ts_pktinfo {
+	__u32 if_index;
+	__u32 pkt_length;
+	__u32 reserved[2];
 };
 
 #endif /* _NET_TIMESTAMPING_H */

net/core/dev.c

@@ -163,6 +163,7 @@ static int netif_rx_internal(struct sk_buff *skb);
 static int call_netdevice_notifiers_info(unsigned long val,
 					 struct net_device *dev,
 					 struct netdev_notifier_info *info);
+static struct napi_struct *napi_by_id(unsigned int napi_id);
 
 /*
  * The @dev_base_head list is protected by @dev_base_lock and the rtnl
@@ -866,6 +867,31 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex)
 }
 EXPORT_SYMBOL(dev_get_by_index);
 
+/**
+ *	dev_get_by_napi_id - find a device by napi_id
+ *	@napi_id: ID of the NAPI struct
+ *
+ *	Search for an interface by NAPI ID. Returns %NULL if the device
+ *	is not found or a pointer to the device. The device has not had
+ *	its reference counter increased so the caller must be careful
+ *	about locking. The caller must hold RCU lock.
+ */
+
+struct net_device *dev_get_by_napi_id(unsigned int napi_id)
+{
+	struct napi_struct *napi;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	if (napi_id < MIN_NAPI_ID)
+		return NULL;
+
+	napi = napi_by_id(napi_id);
+
+	return napi ? napi->dev : NULL;
+}
+EXPORT_SYMBOL(dev_get_by_napi_id);
+
 /**
  *	netdev_get_name - get a netdevice name, knowing its ifindex.
  *	@net: network namespace

net/core/dev_ioctl.c

@@ -225,6 +225,7 @@ static int net_hwtstamp_validate(struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_NTP_ALL:
 		rx_filter_valid = 1;
 		break;
 	}

net/core/skbuff.c

@@ -3901,6 +3901,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 	if (!sk)
 		return;
 
+	if (!hwtstamps && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
+	    skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS)
+		return;
+
 	tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
 	if (!skb_may_tx_timestamp(sk, tsonly))
 		return;

net/socket.c

@@ -662,6 +662,40 @@ static bool skb_is_err_queue(const struct sk_buff *skb)
 	return skb->pkt_type == PACKET_OUTGOING;
 }
 
+/* On transmit, software and hardware timestamps are returned independently.
+ * As the two skb clones share the hardware timestamp, which may be updated
+ * before the software timestamp is received, a hardware TX timestamp may be
+ * returned only if there is no software TX timestamp. Ignore false software
+ * timestamps, which may be made in the __sock_recv_timestamp() call when the
+ * option SO_TIMESTAMP(NS) is enabled on the socket, even when the skb has a
+ * hardware timestamp.
+ */
+static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp)
+{
+	return skb->tstamp && !false_tstamp && skb_is_err_queue(skb);
+}
+
+static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb)
+{
+	struct scm_ts_pktinfo ts_pktinfo;
+	struct net_device *orig_dev;
+
+	if (!skb_mac_header_was_set(skb))
+		return;
+
+	memset(&ts_pktinfo, 0, sizeof(ts_pktinfo));
+
+	rcu_read_lock();
+	orig_dev = dev_get_by_napi_id(skb_napi_id(skb));
+	if (orig_dev)
+		ts_pktinfo.if_index = orig_dev->ifindex;
+	rcu_read_unlock();
+
+	ts_pktinfo.pkt_length = skb->len - skb_mac_offset(skb);
+	put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_PKTINFO,
+		 sizeof(ts_pktinfo), &ts_pktinfo);
+}
+
 /*
  * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP)
  */
@@ -670,14 +704,16 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 {
 	int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP);
 	struct scm_timestamping tss;
-	int empty = 1;
+	int empty = 1, false_tstamp = 0;
 	struct skb_shared_hwtstamps *shhwtstamps =
 		skb_hwtstamps(skb);
 
 	/* Race occurred between timestamp enabling and packet
 	   receiving.  Fill in the current time for now. */
-	if (need_software_tstamp && skb->tstamp == 0)
+	if (need_software_tstamp && skb->tstamp == 0) {
 		__net_timestamp(skb);
+		false_tstamp = 1;
+	}
 
 	if (need_software_tstamp) {
 		if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) {
@@ -699,8 +735,13 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 		empty = 0;
 	if (shhwtstamps &&
 	    (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
-	    ktime_to_timespec_cond(shhwtstamps->hwtstamp, tss.ts + 2))
+	    !skb_is_swtx_tstamp(skb, false_tstamp) &&
+	    ktime_to_timespec_cond(shhwtstamps->hwtstamp, tss.ts + 2)) {
 		empty = 0;
+		if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
+		    !skb_is_err_queue(skb))
+			put_ts_pktinfo(msg, skb);
+	}
 	if (!empty) {
 		put_cmsg(msg, SOL_SOCKET,
 			 SCM_TIMESTAMPING, sizeof(tss), &tss);