From b8210a9e4bea6354eccc5d8a50ecc21ea7486dc9 Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Fri, 19 May 2017 17:52:35 +0200 Subject: [PATCH 1/7] net: define receive timestamp filter for NTP Add HWTSTAMP_FILTER_NTP_ALL to the hwtstamp_rx_filters enum for timestamping of NTP packets. There is currently only one driver (phyter) that could support it directly. CC: Richard Cochran CC: Willem de Bruijn Signed-off-by: Miroslav Lichvar Signed-off-by: David S. Miller --- include/uapi/linux/net_tstamp.h | 3 +++ net/core/dev_ioctl.c | 2 ++ 2 files changed, 5 insertions(+) diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 464dcca5ed68..0749fb13e517 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -125,6 +125,9 @@ 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, }; #endif /* _NET_TIMESTAMPING_H */ diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index b94b1d293506..8f036a76b92e 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -227,6 +227,8 @@ static int net_hwtstamp_validate(struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: rx_filter_valid = 1; break; + case HWTSTAMP_FILTER_NTP_ALL: + break; } if (!tx_type_valid || !rx_filter_valid) From e3412575488ac2408f737a14296cce34c9d8b4f8 Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Fri, 19 May 2017 17:52:36 +0200 Subject: [PATCH 2/7] net: ethernet: update drivers to handle HWTSTAMP_FILTER_NTP_ALL Include HWTSTAMP_FILTER_NTP_ALL in net_hwtstamp_validate() as a valid filter and update drivers which can timestamp all packets, or which explicitly list unsupported filters instead of using a default case, to handle the filter. CC: Richard Cochran CC: Willem de Bruijn Signed-off-by: Miroslav Lichvar Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 1 + drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 1 + drivers/net/ethernet/cavium/liquidio/lio_main.c | 1 + drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 1 + drivers/net/ethernet/cavium/octeon/octeon_mgmt.c | 1 + drivers/net/ethernet/intel/e1000e/netdev.c | 1 + drivers/net/ethernet/intel/i40e/i40e_ptp.c | 1 + drivers/net/ethernet/intel/igb/igb_ptp.c | 1 + drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_clock.c | 1 + drivers/net/ethernet/neterion/vxge/vxge-main.c | 1 + drivers/net/ethernet/qlogic/qede/qede_ptp.c | 1 + drivers/net/ethernet/sfc/ef10.c | 1 + drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 + drivers/net/ethernet/ti/cpsw.c | 1 + drivers/net/ethernet/tile/tilegx.c | 1 + net/core/dev_ioctl.c | 3 +-- 18 files changed, 18 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index c772420fa41c..89b21d7c537b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/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); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 7414ffd70c90..14c236e5bdb1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/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: diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 649f2aaf0afb..ba012427edd6 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/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: diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index d51c8d8d9a35..31d737c22648 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/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: diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index a2138686c605..2887bcaf6af5 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/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) { diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index b3679728caac..0ff9295ed449 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/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; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 18c1cc08da97..0efff18ee336 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/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; diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 7a3fd4d74592..d333d6d80194 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/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 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index ef0635e0918c..d44c728fdc0b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/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. diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 94fab20ef146..82436742ad75 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/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: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c index e706a87fc8b2..e29494464cae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c +++ b/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); diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 6a4310af5d97..50ea69d88480 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/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; diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index 24f06e2ef43e..9b2280badaf7 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/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; diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 78efb2822b86..ad9c4ded2b90 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/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) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a74c481401c4..cce862b81f3e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/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; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index f4d7aec50479..37fc16521143 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/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: diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index 7c634bc75615..aec95382ea5c 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/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: diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 8f036a76b92e..77f04e71100f 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -225,9 +225,8 @@ 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: - rx_filter_valid = 1; - break; case HWTSTAMP_FILTER_NTP_ALL: + rx_filter_valid = 1; break; } From 90b602f80397657429373ca009f98aec4dd3c553 Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Fri, 19 May 2017 17:52:37 +0200 Subject: [PATCH 3/7] net: add function to retrieve original skb device using NAPI ID Since commit b68581778cd0 ("net: Make skb->skb_iif always track skb->dev") skbs don't have the original index of the interface which received the packet. This information is now needed for a new control message related to hardware timestamping. Instead of adding a new field to skb, we can find the device by the NAPI ID if it is available, i.e. CONFIG_NET_RX_BUSY_POLL is enabled and the driver is using NAPI. Add dev_get_by_napi_id() and also skb_napi_id() to hide the CONFIG_NET_RX_BUSY_POLL ifdef. CC: Richard Cochran Suggested-by: Willem de Bruijn Acked-by: Willem de Bruijn Signed-off-by: Miroslav Lichvar Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + include/linux/skbuff.h | 9 +++++++++ net/core/dev.c | 26 ++++++++++++++++++++++++++ 3 files changed, 36 insertions(+) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f8f7cd52a0a0..c50c9218e31e 100644 --- a/include/linux/netdevice.h +++ b/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); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1713e4b7ea9f..8acce7143f6a 100644 --- a/include/linux/skbuff.h +++ b/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); diff --git a/net/core/dev.c b/net/core/dev.c index bb136f726890..3d98fbf4cbb0 100644 --- a/net/core/dev.c +++ b/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 From aad9c8c470f2a8321a99eb053630ce0e199558d6 Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Fri, 19 May 2017 17:52:38 +0200 Subject: [PATCH 4/7] net: add new control message for incoming HW-timestamped packets Add SOF_TIMESTAMPING_OPT_PKTINFO option to request a new control message for incoming packets with hardware timestamps. It contains the index of the real interface which received the packet and the length of the packet at layer 2. The index is useful with bonding, bridges and other interfaces, where IP_PKTINFO doesn't allow applications to determine which PHC made the timestamp. With the L2 length (and link speed) it is possible to transpose preamble timestamps to trailer timestamps, which are used in the NTP protocol. While this information could be provided by two new socket options independently from timestamping, it doesn't look like they would be very useful. With this option any performance impact is limited to hardware timestamping. Use dev_get_by_napi_id() to get the device and its index. On kernels with disabled CONFIG_NET_RX_BUSY_POLL or drivers not using NAPI, a zero index will be returned in the control message. CC: Richard Cochran Acked-by: Willem de Bruijn Signed-off-by: Miroslav Lichvar Signed-off-by: David S. Miller --- Documentation/networking/timestamping.txt | 10 +++++++++ include/uapi/asm-generic/socket.h | 2 ++ include/uapi/linux/net_tstamp.h | 11 ++++++++- net/socket.c | 27 ++++++++++++++++++++++- 4 files changed, 48 insertions(+), 2 deletions(-) diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index 96f50694a748..ce11e3a08c0d 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -193,6 +193,16 @@ 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. + 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. diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 2b488565599d..a5f6e819fafd 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -100,4 +100,6 @@ #define SO_COOKIE 57 +#define SCM_TIMESTAMPING_PKTINFO 58 + #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 0749fb13e517..dee74d39da94 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -9,6 +9,7 @@ #ifndef _NET_TIMESTAMPING_H #define _NET_TIMESTAMPING_H +#include #include /* for SO_TIMESTAMPING */ /* SO_TIMESTAMPING gets an integer bit field comprised of these values */ @@ -26,8 +27,9 @@ 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_LAST = SOF_TIMESTAMPING_OPT_STATS, + SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_PKTINFO, SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) | SOF_TIMESTAMPING_LAST }; @@ -130,4 +132,11 @@ enum hwtstamp_rx_filters { 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 */ diff --git a/net/socket.c b/net/socket.c index c2564eb25c6b..67db7d8a3b81 100644 --- a/net/socket.c +++ b/net/socket.c @@ -662,6 +662,27 @@ static bool skb_is_err_queue(const struct sk_buff *skb) return skb->pkt_type == PACKET_OUTGOING; } +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) */ @@ -699,8 +720,12 @@ 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)) + 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); From 67953d47bb24e63d209705f745a0de411a4c6578 Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Fri, 19 May 2017 17:52:39 +0200 Subject: [PATCH 5/7] net: fix documentation of struct scm_timestamping The scm_timestamping struct may return multiple non-zero fields, e.g. when both software and hardware RX timestamping is enabled, or when the SO_TIMESTAMP(NS) option is combined with SCM_TIMESTAMPING and a false software timestamp is generated in the recvmsg() call in order to always return a SCM_TIMESTAMP(NS) message. CC: Richard Cochran CC: Willem de Bruijn Signed-off-by: Miroslav Lichvar Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- Documentation/networking/timestamping.txt | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index ce11e3a08c0d..50eb0e554778 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -322,7 +322,7 @@ 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. @@ -331,6 +331,12 @@ 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 From b50a5c70ffa4fd6b6da324ab54c84adf48fb17d9 Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Fri, 19 May 2017 17:52:40 +0200 Subject: [PATCH 6/7] net: allow simultaneous SW and HW transmit timestamping Add SOF_TIMESTAMPING_OPT_TX_SWHW option to allow an outgoing packet to be looped to the socket's error queue with a software timestamp even when a hardware transmit timestamp is expected to be provided by the driver. Applications using this option will receive two separate messages from the error queue, one with a software timestamp and the other with a hardware timestamp. As the hardware timestamp is saved to the shared skb info, which may happen before the first message with software timestamp is received by the application, the hardware timestamp is copied to the SCM_TIMESTAMPING control message only when the skb has no software timestamp or it is an incoming packet. While changing sw_tx_timestamp(), inline it in skb_tx_timestamp() as there are no other users. CC: Richard Cochran CC: Willem de Bruijn Signed-off-by: Miroslav Lichvar Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- Documentation/networking/timestamping.txt | 8 ++++++++ include/linux/skbuff.h | 10 ++-------- include/uapi/linux/net_tstamp.h | 3 ++- net/core/skbuff.c | 4 ++++ net/socket.c | 20 ++++++++++++++++++-- 5 files changed, 34 insertions(+), 11 deletions(-) diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index 50eb0e554778..196ba17cc344 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -203,6 +203,14 @@ SOF_TIMESTAMPING_OPT_PKTINFO: 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. diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8acce7143f6a..45a59c1e0cc7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3259,13 +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 * @@ -3281,7 +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); } /** diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index dee74d39da94..3d421d912193 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -28,8 +28,9 @@ enum { 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_PKTINFO, + SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_TX_SWHW, SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) | SOF_TIMESTAMPING_LAST }; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d5c98117cbce..780b7c1563d0 100644 --- a/net/core/skbuff.c +++ b/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; diff --git a/net/socket.c b/net/socket.c index 67db7d8a3b81..cb355a7ef135 100644 --- a/net/socket.c +++ b/net/socket.c @@ -662,6 +662,19 @@ 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; @@ -691,14 +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)) { @@ -720,6 +735,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, empty = 0; if (shhwtstamps && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && + !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) && From 74abc9b18f446d1a9e0602a71a22e5ffe8a2cd23 Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Fri, 19 May 2017 17:52:41 +0200 Subject: [PATCH 7/7] net: ethernet: update drivers to make both SW and HW TX timestamps Some drivers were calling the skb_tx_timestamp() function only when a hardware timestamp was not requested. Now that applications can use the SOF_TIMESTAMPING_OPT_TX_SWHW option to request both software and hardware timestamps, the drivers need to be modified to unconditionally call skb_tx_timestamp(). CC: Richard Cochran CC: Willem de Bruijn Signed-off-by: Miroslav Lichvar Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 3 +-- drivers/net/ethernet/intel/e1000e/netdev.c | 4 ++-- drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c | 3 +-- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 ++---- 4 files changed, 6 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 89b21d7c537b..5a2ad9c5faab 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1391,8 +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) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 0ff9295ed449..6ed3bc419b96 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5868,10 +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. */ diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index 1e594351a60f..89831adb8eb7 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/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); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index cce862b81f3e..27c12e732a8a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2880,8 +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)) { @@ -3084,8 +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