From c26a2c2ddc0115eb088873f5c309cf46b982f522 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 28 Dec 2019 15:30:45 +0200 Subject: gianfar: Fix TX timestamping with a stacked DSA driver The driver wrongly assumes that it is the only entity that can set the SKBTX_IN_PROGRESS bit of the current skb. Therefore, in the gfar_clean_tx_ring function, where the TX timestamp is collected if necessary, the aforementioned bit is used to discriminate whether or not the TX timestamp should be delivered to the socket's error queue. But a stacked driver such as a DSA switch can also set the SKBTX_IN_PROGRESS bit, which is actually exactly what it should do in order to denote that the hardware timestamping process is undergoing. Therefore, gianfar would misinterpret the "in progress" bit as being its own, and deliver a second skb clone in the socket's error queue, completely throwing off a PTP process which is not expecting to receive it, _even though_ TX timestamping is not enabled for gianfar. There have been discussions [0] as to whether non-MAC drivers need or not to set SKBTX_IN_PROGRESS at all (whose purpose is to avoid sending 2 timestamps, a sw and a hw one, to applications which only expect one). But as of this patch, there are at least 2 PTP drivers that would break in conjunction with gianfar: the sja1105 DSA switch and the felix switch, by way of its ocelot core driver. So regardless of that conclusion, fix the gianfar driver to not do stuff based on flags set by others and not intended for it. [0]: https://www.spinics.net/lists/netdev/msg619699.html Fixes: f0ee7acfcdd4 ("gianfar: Add hardware TX timestamping support") Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/gianfar.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index b636d83a7ee9..f7e5cafe89a9 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -2205,13 +2205,17 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) skb_dirtytx = tx_queue->skb_dirtytx; while ((skb = tx_queue->tx_skbuff[skb_dirtytx])) { + bool do_tstamp; + + do_tstamp = (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + priv->hwts_tx_en; frags = skb_shinfo(skb)->nr_frags; /* When time stamping, one additional TxBD must be freed. * Also, we need to dma_unmap_single() the TxPAL. */ - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) + if (unlikely(do_tstamp)) nr_txbds = frags + 2; else nr_txbds = frags + 1; @@ -2225,7 +2229,7 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) (lstatus & BD_LENGTH_MASK)) break; - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) { + if (unlikely(do_tstamp)) { next = next_txbd(bdp, base, tx_ring_size); buflen = be16_to_cpu(next->length) + GMAC_FCB_LEN + GMAC_TXPAL_LEN; @@ -2235,7 +2239,7 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) dma_unmap_single(priv->dev, be32_to_cpu(bdp->bufPtr), buflen, DMA_TO_DEVICE); - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) { + if (unlikely(do_tstamp)) { struct skb_shared_hwtstamps shhwtstamps; u64 *ns = (u64 *)(((uintptr_t)skb->data + 0x10) & ~0x7UL); -- cgit v1.2.3-59-g8ed1b From f685e609a301f171b62ee52a69acc3a74c2c04aa Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 28 Dec 2019 15:30:46 +0200 Subject: net: dsa: Deny PTP on master if switch supports it It is possible to kill PTP on a DSA switch completely and absolutely, until a reboot, with a simple command: tcpdump -i eth2 -j adapter_unsynced where eth2 is the switch's DSA master. Why? Well, in short, the PTP API in place today is a bit rudimentary and relies on applications to retrieve the TX timestamps by polling the error queue and looking at the cmsg structure. But there is no timestamp identification of any sorts (except whether it's HW or SW), you don't know how many more timestamps are there to come, which one is this one, from whom it is, etc. In other words, the SO_TIMESTAMPING API is fundamentally limited in that you can get a single HW timestamp from the stack. And the "-j adapter_unsynced" flag of tcpdump enables hardware timestamping. So let's imagine what happens when the DSA master decides it wants to deliver TX timestamps to the skb's socket too: - The timestamp that the user space sees is taken by the DSA master. Whereas the RX timestamp will eventually be overwritten by the DSA switch. So the RX and TX timestamps will be in different time bases (aka garbage). - The user space applications have no way to deal with the second (real) TX timestamp finally delivered by the DSA switch, or even to know to wait for it. Take ptp4l from the linuxptp project, for example. This is its behavior after running tcpdump, before the patch: ptp4l[172]: [6469.594] Unexpected data on socket err queue: ptp4l[172]: [6469.693] rms 8 max 16 freq -21257 +/- 11 delay 748 +/- 0 ptp4l[172]: [6469.711] Unexpected data on socket err queue: ptp4l[172]: 0020 00 00 00 1f 7b ff fe 63 02 48 00 03 aa 05 00 fd ptp4l[172]: 0030 00 00 00 00 00 00 00 00 00 00 ptp4l[172]: [6469.721] Unexpected data on socket err queue: ptp4l[172]: 0000 01 80 c2 00 00 0e 00 1f 7b 63 02 48 88 f7 10 02 ptp4l[172]: 0010 00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 ptp4l[172]: 0020 00 00 00 1f 7b ff fe 63 02 48 00 01 c6 b1 00 fd ptp4l[172]: 0030 00 00 00 00 00 00 00 00 00 00 ptp4l[172]: [6469.838] Unexpected data on socket err queue: ptp4l[172]: 0000 01 80 c2 00 00 0e 00 1f 7b 63 02 48 88 f7 10 02 ptp4l[172]: 0010 00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 ptp4l[172]: 0020 00 00 00 1f 7b ff fe 63 02 48 00 03 aa 06 00 fd ptp4l[172]: 0030 00 00 00 00 00 00 00 00 00 00 ptp4l[172]: [6469.848] Unexpected data on socket err queue: ptp4l[172]: 0000 01 80 c2 00 00 0e 00 1f 7b 63 02 48 88 f7 13 02 ptp4l[172]: 0010 00 36 00 00 02 00 00 00 00 00 00 00 00 00 00 00 ptp4l[172]: 0020 00 00 00 1f 7b ff fe 63 02 48 00 04 1a 45 05 7f ptp4l[172]: 0030 00 00 5e 05 41 32 27 c2 1a 68 00 04 9f ff fe 05 ptp4l[172]: 0040 de 06 00 01 ptp4l[172]: [6469.855] Unexpected data on socket err queue: ptp4l[172]: 0000 01 80 c2 00 00 0e 00 1f 7b 63 02 48 88 f7 10 02 ptp4l[172]: 0010 00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 ptp4l[172]: 0020 00 00 00 1f 7b ff fe 63 02 48 00 01 c6 b2 00 fd ptp4l[172]: 0030 00 00 00 00 00 00 00 00 00 00 ptp4l[172]: [6469.974] Unexpected data on socket err queue: ptp4l[172]: 0000 01 80 c2 00 00 0e 00 1f 7b 63 02 48 88 f7 10 02 ptp4l[172]: 0010 00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 ptp4l[172]: 0020 00 00 00 1f 7b ff fe 63 02 48 00 03 aa 07 00 fd ptp4l[172]: 0030 00 00 00 00 00 00 00 00 00 00 The ptp4l program itself is heavily patched to show this (more details here [0]). Otherwise, by default it just hangs. On the other hand, with the DSA patch to disallow HW timestamping applied: tcpdump -i eth2 -j adapter_unsynced tcpdump: SIOCSHWTSTAMP failed: Device or resource busy So it is a fact of life that PTP timestamping on the DSA master is incompatible with timestamping on the switch MAC, at least with the current API. And if the switch supports PTP, taking the timestamps from the switch MAC is highly preferable anyway, due to the fact that those don't contain the queuing latencies of the switch. So just disallow PTP on the DSA master if there is any PTP-capable switch attached. [0]: https://sourceforge.net/p/linuxptp/mailman/message/36880648/ Fixes: 0336369d3a4d ("net: dsa: forward hardware timestamping ioctls to switch driver") Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: David S. Miller --- net/dsa/master.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/net/dsa/master.c b/net/dsa/master.c index 3255dfc97f86..bd44bde272f4 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -197,6 +197,35 @@ static int dsa_master_get_phys_port_name(struct net_device *dev, return 0; } +static int dsa_master_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch *ds = cpu_dp->ds; + struct dsa_switch_tree *dst; + int err = -EOPNOTSUPP; + struct dsa_port *dp; + + dst = ds->dst; + + switch (cmd) { + case SIOCGHWTSTAMP: + case SIOCSHWTSTAMP: + /* Deny PTP operations on master if there is at least one + * switch in the tree that is PTP capable. + */ + list_for_each_entry(dp, &dst->ports, list) + if (dp->ds->ops->port_hwtstamp_get || + dp->ds->ops->port_hwtstamp_set) + return -EBUSY; + break; + } + + if (cpu_dp->orig_ndo_ops && cpu_dp->orig_ndo_ops->ndo_do_ioctl) + err = cpu_dp->orig_ndo_ops->ndo_do_ioctl(dev, ifr, cmd); + + return err; +} + static int dsa_master_ethtool_setup(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; @@ -249,6 +278,7 @@ static int dsa_master_ndo_setup(struct net_device *dev) memcpy(ops, cpu_dp->orig_ndo_ops, sizeof(*ops)); ops->ndo_get_phys_port_name = dsa_master_get_phys_port_name; + ops->ndo_do_ioctl = dsa_master_ioctl; dev->netdev_ops = ops; -- cgit v1.2.3-59-g8ed1b