linux/net/dsa/master.c

419 lines
11 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Handling of a master device, switching frames via its switch fabric CPU port
*
* Copyright (c) 2017 Savoir-faire Linux Inc.
* Vivien Didelot <vivien.didelot@savoirfairelinux.com>
*/
#include "dsa_priv.h"
net: dsa: dump CPU port regs through master Merge the CPU port registers dump into the master interface registers dump through ethtool, by nesting the ethtool_drvinfo and ethtool_regs structures of the CPU port into the dump. drvinfo->regdump_len will contain the full data length, while regs->len will contain only the master interface registers dump length. This allows for example to dump the CPU port registers on a ZII Dev C board like this: # ethtool -d eth1 0x004: 0x00000000 0x008: 0x0a8000aa 0x010: 0x01000000 0x014: 0x00000000 0x024: 0xf0000102 0x040: 0x6d82c800 0x044: 0x00000020 0x064: 0x40000000 0x084: RCR (Receive Control Register) 0x47c00104 MAX_FL (Maximum frame length) 1984 FCE (Flow control enable) 0 BC_REJ (Broadcast frame reject) 0 PROM (Promiscuous mode) 0 DRT (Disable receive on transmit) 0 LOOP (Internal loopback) 0 0x0c4: TCR (Transmit Control Register) 0x00000004 RFC_PAUSE (Receive frame control pause) 0 TFC_PAUSE (Transmit frame control pause) 0 FDEN (Full duplex enable) 1 HBC (Heartbeat control) 0 GTS (Graceful transmit stop) 0 0x0e4: 0x76735d6d 0x0e8: 0x7e9e8808 0x0ec: 0x00010000 . . . 88E6352 Switch Port Registers ------------------------------ 00: Port Status 0x4d04 Pause Enabled 0 My Pause 1 802.3 PHY Detected 0 Link Status Up Duplex Full Speed 100 or 200 Mbps EEE Enabled 0 Transmitter Paused 0 Flow Control 0 Config Mode 0x4 01: Physical Control 0x003d RGMII Receive Timing Control Default RGMII Transmit Timing Control Default 200 BASE Mode 100 Flow Control's Forced value 0 Force Flow Control 0 Link's Forced value Up Force Link 1 Duplex's Forced value Full Force Duplex 1 Force Speed 100 or 200 Mbps . . . Signed-off-by: Vivien Didelot <vivien.didelot@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-03 03:34:55 +08:00
static int dsa_master_get_regs_len(struct net_device *dev)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
struct dsa_switch *ds = cpu_dp->ds;
int port = cpu_dp->index;
int ret = 0;
int len;
if (ops->get_regs_len) {
len = ops->get_regs_len(dev);
if (len < 0)
return len;
ret += len;
}
ret += sizeof(struct ethtool_drvinfo);
ret += sizeof(struct ethtool_regs);
if (ds->ops->get_regs_len) {
len = ds->ops->get_regs_len(ds, port);
if (len < 0)
return len;
ret += len;
}
return ret;
}
static void dsa_master_get_regs(struct net_device *dev,
struct ethtool_regs *regs, void *data)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
struct dsa_switch *ds = cpu_dp->ds;
struct ethtool_drvinfo *cpu_info;
struct ethtool_regs *cpu_regs;
int port = cpu_dp->index;
int len;
if (ops->get_regs_len && ops->get_regs) {
len = ops->get_regs_len(dev);
if (len < 0)
return;
regs->len = len;
ops->get_regs(dev, regs, data);
data += regs->len;
}
cpu_info = (struct ethtool_drvinfo *)data;
strlcpy(cpu_info->driver, "dsa", sizeof(cpu_info->driver));
data += sizeof(*cpu_info);
cpu_regs = (struct ethtool_regs *)data;
data += sizeof(*cpu_regs);
if (ds->ops->get_regs_len && ds->ops->get_regs) {
len = ds->ops->get_regs_len(ds, port);
if (len < 0)
return;
cpu_regs->len = len;
ds->ops->get_regs(ds, port, cpu_regs, data);
}
}
static void dsa_master_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats,
uint64_t *data)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
struct dsa_switch *ds = cpu_dp->ds;
int port = cpu_dp->index;
int count = 0;
if (ops->get_sset_count && ops->get_ethtool_stats) {
count = ops->get_sset_count(dev, ETH_SS_STATS);
ops->get_ethtool_stats(dev, stats, data);
}
if (ds->ops->get_ethtool_stats)
ds->ops->get_ethtool_stats(ds, port, data + count);
}
static void dsa_master_get_ethtool_phy_stats(struct net_device *dev,
struct ethtool_stats *stats,
uint64_t *data)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
struct dsa_switch *ds = cpu_dp->ds;
int port = cpu_dp->index;
int count = 0;
if (dev->phydev && !ops->get_ethtool_phy_stats) {
count = phy_ethtool_get_sset_count(dev->phydev);
if (count >= 0)
phy_ethtool_get_stats(dev->phydev, stats, data);
} else if (ops->get_sset_count && ops->get_ethtool_phy_stats) {
count = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
ops->get_ethtool_phy_stats(dev, stats, data);
}
if (count < 0)
count = 0;
if (ds->ops->get_ethtool_phy_stats)
ds->ops->get_ethtool_phy_stats(ds, port, data + count);
}
static int dsa_master_get_sset_count(struct net_device *dev, int sset)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
struct dsa_switch *ds = cpu_dp->ds;
int count = 0;
if (sset == ETH_SS_PHY_STATS && dev->phydev &&
!ops->get_ethtool_phy_stats)
count = phy_ethtool_get_sset_count(dev->phydev);
else if (ops->get_sset_count)
count = ops->get_sset_count(dev, sset);
if (count < 0)
count = 0;
if (ds->ops->get_sset_count)
count += ds->ops->get_sset_count(ds, cpu_dp->index, sset);
return count;
}
static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset,
uint8_t *data)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops;
struct dsa_switch *ds = cpu_dp->ds;
int port = cpu_dp->index;
int len = ETH_GSTRING_LEN;
int mcount = 0, count, i;
uint8_t pfx[4];
uint8_t *ndata;
snprintf(pfx, sizeof(pfx), "p%.2d", port);
/* We do not want to be NULL-terminated, since this is a prefix */
pfx[sizeof(pfx) - 1] = '_';
if (stringset == ETH_SS_PHY_STATS && dev->phydev &&
!ops->get_ethtool_phy_stats) {
mcount = phy_ethtool_get_sset_count(dev->phydev);
if (mcount < 0)
mcount = 0;
else
phy_ethtool_get_strings(dev->phydev, data);
} else if (ops->get_sset_count && ops->get_strings) {
mcount = ops->get_sset_count(dev, stringset);
if (mcount < 0)
mcount = 0;
ops->get_strings(dev, stringset, data);
}
if (ds->ops->get_strings) {
ndata = data + mcount * len;
/* This function copies ETH_GSTRINGS_LEN bytes, we will mangle
* the output after to prepend our CPU port prefix we
* constructed earlier
*/
ds->ops->get_strings(ds, port, stringset, ndata);
count = ds->ops->get_sset_count(ds, port, stringset);
if (count < 0)
return;
for (i = 0; i < count; i++) {
memmove(ndata + (i * len + sizeof(pfx)),
ndata + i * len, len - sizeof(pfx));
memcpy(ndata + i * len, pfx, sizeof(pfx));
}
}
}
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 <olteanv@gmail.com> Acked-by: Richard Cochran <richardcochran@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-12-28 21:30:46 +08:00
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 (dev->netdev_ops->ndo_eth_ioctl)
err = dev->netdev_ops->ndo_eth_ioctl(dev, ifr, cmd);
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 <olteanv@gmail.com> Acked-by: Richard Cochran <richardcochran@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-12-28 21:30:46 +08:00
return err;
}
static const struct dsa_netdevice_ops dsa_netdev_ops = {
.ndo_eth_ioctl = dsa_master_ioctl,
};
static int dsa_master_ethtool_setup(struct net_device *dev)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
struct dsa_switch *ds = cpu_dp->ds;
struct ethtool_ops *ops;
ops = devm_kzalloc(ds->dev, sizeof(*ops), GFP_KERNEL);
if (!ops)
return -ENOMEM;
cpu_dp->orig_ethtool_ops = dev->ethtool_ops;
if (cpu_dp->orig_ethtool_ops)
memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops));
net: dsa: dump CPU port regs through master Merge the CPU port registers dump into the master interface registers dump through ethtool, by nesting the ethtool_drvinfo and ethtool_regs structures of the CPU port into the dump. drvinfo->regdump_len will contain the full data length, while regs->len will contain only the master interface registers dump length. This allows for example to dump the CPU port registers on a ZII Dev C board like this: # ethtool -d eth1 0x004: 0x00000000 0x008: 0x0a8000aa 0x010: 0x01000000 0x014: 0x00000000 0x024: 0xf0000102 0x040: 0x6d82c800 0x044: 0x00000020 0x064: 0x40000000 0x084: RCR (Receive Control Register) 0x47c00104 MAX_FL (Maximum frame length) 1984 FCE (Flow control enable) 0 BC_REJ (Broadcast frame reject) 0 PROM (Promiscuous mode) 0 DRT (Disable receive on transmit) 0 LOOP (Internal loopback) 0 0x0c4: TCR (Transmit Control Register) 0x00000004 RFC_PAUSE (Receive frame control pause) 0 TFC_PAUSE (Transmit frame control pause) 0 FDEN (Full duplex enable) 1 HBC (Heartbeat control) 0 GTS (Graceful transmit stop) 0 0x0e4: 0x76735d6d 0x0e8: 0x7e9e8808 0x0ec: 0x00010000 . . . 88E6352 Switch Port Registers ------------------------------ 00: Port Status 0x4d04 Pause Enabled 0 My Pause 1 802.3 PHY Detected 0 Link Status Up Duplex Full Speed 100 or 200 Mbps EEE Enabled 0 Transmitter Paused 0 Flow Control 0 Config Mode 0x4 01: Physical Control 0x003d RGMII Receive Timing Control Default RGMII Transmit Timing Control Default 200 BASE Mode 100 Flow Control's Forced value 0 Force Flow Control 0 Link's Forced value Up Force Link 1 Duplex's Forced value Full Force Duplex 1 Force Speed 100 or 200 Mbps . . . Signed-off-by: Vivien Didelot <vivien.didelot@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-03 03:34:55 +08:00
ops->get_regs_len = dsa_master_get_regs_len;
ops->get_regs = dsa_master_get_regs;
ops->get_sset_count = dsa_master_get_sset_count;
ops->get_ethtool_stats = dsa_master_get_ethtool_stats;
ops->get_strings = dsa_master_get_strings;
ops->get_ethtool_phy_stats = dsa_master_get_ethtool_phy_stats;
dev->ethtool_ops = ops;
return 0;
}
static void dsa_master_ethtool_teardown(struct net_device *dev)
{
struct dsa_port *cpu_dp = dev->dsa_ptr;
dev->ethtool_ops = cpu_dp->orig_ethtool_ops;
cpu_dp->orig_ethtool_ops = NULL;
}
static void dsa_netdev_ops_set(struct net_device *dev,
const struct dsa_netdevice_ops *ops)
{
dev->dsa_ptr->netdev_ops = ops;
}
static void dsa_master_set_promiscuity(struct net_device *dev, int inc)
{
const struct dsa_device_ops *ops = dev->dsa_ptr->tag_ops;
if (!ops->promisc_on_master)
return;
rtnl_lock();
dev_set_promiscuity(dev, inc);
rtnl_unlock();
}
static ssize_t tagging_show(struct device *d, struct device_attribute *attr,
char *buf)
{
struct net_device *dev = to_net_dev(d);
struct dsa_port *cpu_dp = dev->dsa_ptr;
return sprintf(buf, "%s\n",
dsa_tag_protocol_to_str(cpu_dp->tag_ops));
}
net: dsa: allow changing the tag protocol via the "tagging" device attribute Currently DSA exposes the following sysfs: $ cat /sys/class/net/eno2/dsa/tagging ocelot which is a read-only device attribute, introduced in the kernel as commit 98cdb4807123 ("net: dsa: Expose tagging protocol to user-space"), and used by libpcap since its commit 993db3800d7d ("Add support for DSA link-layer types"). It would be nice if we could extend this device attribute by making it writable: $ echo ocelot-8021q > /sys/class/net/eno2/dsa/tagging This is useful with DSA switches that can make use of more than one tagging protocol. It may be useful in dsa_loop in the future too, to perform offline testing of various taggers, or for changing between dsa and edsa on Marvell switches, if that is desirable. In terms of implementation, drivers can support this feature by implementing .change_tag_protocol, which should always leave the switch in a consistent state: either with the new protocol if things went well, or with the old one if something failed. Teardown of the old protocol, if necessary, must be handled by the driver. Some things remain as before: - The .get_tag_protocol is currently only called at probe time, to load the initial tagging protocol driver. Nonetheless, new drivers should report the tagging protocol in current use now. - The driver should manage by itself the initial setup of tagging protocol, no later than the .setup() method, as well as destroying resources used by the last tagger in use, no earlier than the .teardown() method. For multi-switch DSA trees, error handling is a bit more complicated, since e.g. the 5th out of 7 switches may fail to change the tag protocol. When that happens, a revert to the original tag protocol is attempted, but that may fail too, leaving the tree in an inconsistent state despite each individual switch implementing .change_tag_protocol transactionally. Since the intersection between drivers that implement .change_tag_protocol and drivers that support D in DSA is currently the empty set, the possibility for this error to happen is ignored for now. Testing: $ insmod mscc_felix.ko [ 79.549784] mscc_felix 0000:00:00.5: Adding to iommu group 14 [ 79.565712] mscc_felix 0000:00:00.5: Failed to register DSA switch: -517 $ insmod tag_ocelot.ko $ rmmod mscc_felix.ko $ insmod mscc_felix.ko [ 97.261724] libphy: VSC9959 internal MDIO bus: probed [ 97.267363] mscc_felix 0000:00:00.5: Found PCS at internal MDIO address 0 [ 97.274998] mscc_felix 0000:00:00.5: Found PCS at internal MDIO address 1 [ 97.282561] mscc_felix 0000:00:00.5: Found PCS at internal MDIO address 2 [ 97.289700] mscc_felix 0000:00:00.5: Found PCS at internal MDIO address 3 [ 97.599163] mscc_felix 0000:00:00.5 swp0 (uninitialized): PHY [0000:00:00.3:10] driver [Microsemi GE VSC8514 SyncE] (irq=POLL) [ 97.862034] mscc_felix 0000:00:00.5 swp1 (uninitialized): PHY [0000:00:00.3:11] driver [Microsemi GE VSC8514 SyncE] (irq=POLL) [ 97.950731] mscc_felix 0000:00:00.5 swp0: configuring for inband/qsgmii link mode [ 97.964278] 8021q: adding VLAN 0 to HW filter on device swp0 [ 98.146161] mscc_felix 0000:00:00.5 swp2 (uninitialized): PHY [0000:00:00.3:12] driver [Microsemi GE VSC8514 SyncE] (irq=POLL) [ 98.238649] mscc_felix 0000:00:00.5 swp1: configuring for inband/qsgmii link mode [ 98.251845] 8021q: adding VLAN 0 to HW filter on device swp1 [ 98.433916] mscc_felix 0000:00:00.5 swp3 (uninitialized): PHY [0000:00:00.3:13] driver [Microsemi GE VSC8514 SyncE] (irq=POLL) [ 98.485542] mscc_felix 0000:00:00.5: configuring for fixed/internal link mode [ 98.503584] mscc_felix 0000:00:00.5: Link is Up - 2.5Gbps/Full - flow control rx/tx [ 98.527948] device eno2 entered promiscuous mode [ 98.544755] DSA: tree 0 setup $ ping 10.0.0.1 PING 10.0.0.1 (10.0.0.1): 56 data bytes 64 bytes from 10.0.0.1: seq=0 ttl=64 time=2.337 ms 64 bytes from 10.0.0.1: seq=1 ttl=64 time=0.754 ms ^C - 10.0.0.1 ping statistics - 2 packets transmitted, 2 packets received, 0% packet loss round-trip min/avg/max = 0.754/1.545/2.337 ms $ cat /sys/class/net/eno2/dsa/tagging ocelot $ cat ./test_ocelot_8021q.sh #!/bin/bash ip link set swp0 down ip link set swp1 down ip link set swp2 down ip link set swp3 down ip link set swp5 down ip link set eno2 down echo ocelot-8021q > /sys/class/net/eno2/dsa/tagging ip link set eno2 up ip link set swp0 up ip link set swp1 up ip link set swp2 up ip link set swp3 up ip link set swp5 up $ ./test_ocelot_8021q.sh ./test_ocelot_8021q.sh: line 9: echo: write error: Protocol not available $ rmmod tag_ocelot.ko rmmod: can't unload module 'tag_ocelot': Resource temporarily unavailable $ insmod tag_ocelot_8021q.ko $ ./test_ocelot_8021q.sh $ cat /sys/class/net/eno2/dsa/tagging ocelot-8021q $ rmmod tag_ocelot.ko $ rmmod tag_ocelot_8021q.ko rmmod: can't unload module 'tag_ocelot_8021q': Resource temporarily unavailable $ ping 10.0.0.1 PING 10.0.0.1 (10.0.0.1): 56 data bytes 64 bytes from 10.0.0.1: seq=0 ttl=64 time=0.953 ms 64 bytes from 10.0.0.1: seq=1 ttl=64 time=0.787 ms 64 bytes from 10.0.0.1: seq=2 ttl=64 time=0.771 ms $ rmmod mscc_felix.ko [ 645.544426] mscc_felix 0000:00:00.5: Link is Down [ 645.838608] DSA: tree 0 torn down $ rmmod tag_ocelot_8021q.ko Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-29 09:00:06 +08:00
static ssize_t tagging_store(struct device *d, struct device_attribute *attr,
const char *buf, size_t count)
{
const struct dsa_device_ops *new_tag_ops, *old_tag_ops;
struct net_device *dev = to_net_dev(d);
struct dsa_port *cpu_dp = dev->dsa_ptr;
int err;
old_tag_ops = cpu_dp->tag_ops;
new_tag_ops = dsa_find_tagger_by_name(buf);
/* Bad tagger name, or module is not loaded? */
if (IS_ERR(new_tag_ops))
return PTR_ERR(new_tag_ops);
if (new_tag_ops == old_tag_ops)
/* Drop the temporarily held duplicate reference, since
* the DSA switch tree uses this tagger.
*/
goto out;
err = dsa_tree_change_tag_proto(cpu_dp->ds->dst, dev, new_tag_ops,
old_tag_ops);
if (err) {
/* On failure the old tagger is restored, so we don't need the
* driver for the new one.
*/
dsa_tag_driver_put(new_tag_ops);
return err;
}
/* On success we no longer need the module for the old tagging protocol
*/
out:
dsa_tag_driver_put(old_tag_ops);
return count;
}
static DEVICE_ATTR_RW(tagging);
static struct attribute *dsa_slave_attrs[] = {
&dev_attr_tagging.attr,
NULL
};
static const struct attribute_group dsa_group = {
.name = "dsa",
.attrs = dsa_slave_attrs,
};
static void dsa_master_reset_mtu(struct net_device *dev)
{
int err;
rtnl_lock();
err = dev_set_mtu(dev, ETH_DATA_LEN);
if (err)
netdev_dbg(dev,
"Unable to reset MTU to exclude DSA overheads\n");
rtnl_unlock();
}
static struct lock_class_key dsa_master_addr_list_lock_key;
int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
{
const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops;
net: dsa: unbind all switches from tree when DSA master unbinds Currently the following happens when a DSA master driver unbinds while there are DSA switches attached to it: $ echo 0000:00:00.5 > /sys/bus/pci/drivers/mscc_felix/unbind ------------[ cut here ]------------ WARNING: CPU: 0 PID: 392 at net/core/dev.c:9507 Call trace: rollback_registered_many+0x5fc/0x688 unregister_netdevice_queue+0x98/0x120 dsa_slave_destroy+0x4c/0x88 dsa_port_teardown.part.16+0x78/0xb0 dsa_tree_teardown_switches+0x58/0xc0 dsa_unregister_switch+0x104/0x1b8 felix_pci_remove+0x24/0x48 pci_device_remove+0x48/0xf0 device_release_driver_internal+0x118/0x1e8 device_driver_detach+0x28/0x38 unbind_store+0xd0/0x100 Located at the above location is this WARN_ON: /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev)); Other stacked interfaces, like VLAN, do indeed listen for NETDEV_UNREGISTER on the real_dev and also unregister themselves at that time, which is clearly the behavior that rollback_registered_many expects. But DSA interfaces are not VLAN. They have backing hardware (platform devices, PCI devices, MDIO, SPI etc) which have a life cycle of their own and we can't just trigger an unregister from the DSA framework when we receive a netdev notifier that the master unregisters. Luckily, there is something we can do, and that is to inform the driver core that we have a runtime dependency to the DSA master interface's device, and create a device link where that is the supplier and we are the consumer. Having this device link will make the DSA switch unbind before the DSA master unbinds, which is enough to avoid the WARN_ON from rollback_registered_many. Note that even before the blamed commit, DSA did nothing intelligent when the master interface got unregistered either. See the discussion here: https://lore.kernel.org/netdev/20200505210253.20311-1-f.fainelli@gmail.com/ But this time, at least the WARN_ON is loud enough that the upper_dev_link commit can be blamed. The advantage with this approach vs dev_hold(master) in the attached link is that the latter is not meant for long term reference counting. With dev_hold, the only thing that will happen is that when the user attempts an unbind of the DSA master, netdev_wait_allrefs will keep waiting and waiting, due to DSA keeping the refcount forever. DSA would not access freed memory corresponding to the master interface, but the unbind would still result in a freeze. Whereas with device links, graceful teardown is ensured. It even works with cascaded DSA trees. $ echo 0000:00:00.2 > /sys/bus/pci/drivers/fsl_enetc/unbind [ 1818.797546] device swp0 left promiscuous mode [ 1819.301112] sja1105 spi2.0: Link is Down [ 1819.307981] DSA: tree 1 torn down [ 1819.312408] device eno2 left promiscuous mode [ 1819.656803] mscc_felix 0000:00:00.5: Link is Down [ 1819.667194] DSA: tree 0 torn down [ 1819.711557] fsl_enetc 0000:00:00.2 eno2: Link is Down This approach allows us to keep the DSA framework absolutely unchanged, and the driver core will just know to unbind us first when the master goes away - as opposed to the large (and probably impossible) rework required if attempting to listen for NETDEV_UNREGISTER. As per the documentation at Documentation/driver-api/device_link.rst, specifying the DL_FLAG_AUTOREMOVE_CONSUMER flag causes the device link to be automatically purged when the consumer fails to probe or later unbinds. So we don't need to keep the consumer_link variable in struct dsa_switch. Fixes: 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings") Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Tested-by: Florian Fainelli <f.fainelli@gmail.com> Link: https://lore.kernel.org/r/20210111230943.3701806-1-olteanv@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-12 07:09:43 +08:00
struct dsa_switch *ds = cpu_dp->ds;
struct device_link *consumer_link;
int mtu, ret;
mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops);
net: dsa: unbind all switches from tree when DSA master unbinds Currently the following happens when a DSA master driver unbinds while there are DSA switches attached to it: $ echo 0000:00:00.5 > /sys/bus/pci/drivers/mscc_felix/unbind ------------[ cut here ]------------ WARNING: CPU: 0 PID: 392 at net/core/dev.c:9507 Call trace: rollback_registered_many+0x5fc/0x688 unregister_netdevice_queue+0x98/0x120 dsa_slave_destroy+0x4c/0x88 dsa_port_teardown.part.16+0x78/0xb0 dsa_tree_teardown_switches+0x58/0xc0 dsa_unregister_switch+0x104/0x1b8 felix_pci_remove+0x24/0x48 pci_device_remove+0x48/0xf0 device_release_driver_internal+0x118/0x1e8 device_driver_detach+0x28/0x38 unbind_store+0xd0/0x100 Located at the above location is this WARN_ON: /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev)); Other stacked interfaces, like VLAN, do indeed listen for NETDEV_UNREGISTER on the real_dev and also unregister themselves at that time, which is clearly the behavior that rollback_registered_many expects. But DSA interfaces are not VLAN. They have backing hardware (platform devices, PCI devices, MDIO, SPI etc) which have a life cycle of their own and we can't just trigger an unregister from the DSA framework when we receive a netdev notifier that the master unregisters. Luckily, there is something we can do, and that is to inform the driver core that we have a runtime dependency to the DSA master interface's device, and create a device link where that is the supplier and we are the consumer. Having this device link will make the DSA switch unbind before the DSA master unbinds, which is enough to avoid the WARN_ON from rollback_registered_many. Note that even before the blamed commit, DSA did nothing intelligent when the master interface got unregistered either. See the discussion here: https://lore.kernel.org/netdev/20200505210253.20311-1-f.fainelli@gmail.com/ But this time, at least the WARN_ON is loud enough that the upper_dev_link commit can be blamed. The advantage with this approach vs dev_hold(master) in the attached link is that the latter is not meant for long term reference counting. With dev_hold, the only thing that will happen is that when the user attempts an unbind of the DSA master, netdev_wait_allrefs will keep waiting and waiting, due to DSA keeping the refcount forever. DSA would not access freed memory corresponding to the master interface, but the unbind would still result in a freeze. Whereas with device links, graceful teardown is ensured. It even works with cascaded DSA trees. $ echo 0000:00:00.2 > /sys/bus/pci/drivers/fsl_enetc/unbind [ 1818.797546] device swp0 left promiscuous mode [ 1819.301112] sja1105 spi2.0: Link is Down [ 1819.307981] DSA: tree 1 torn down [ 1819.312408] device eno2 left promiscuous mode [ 1819.656803] mscc_felix 0000:00:00.5: Link is Down [ 1819.667194] DSA: tree 0 torn down [ 1819.711557] fsl_enetc 0000:00:00.2 eno2: Link is Down This approach allows us to keep the DSA framework absolutely unchanged, and the driver core will just know to unbind us first when the master goes away - as opposed to the large (and probably impossible) rework required if attempting to listen for NETDEV_UNREGISTER. As per the documentation at Documentation/driver-api/device_link.rst, specifying the DL_FLAG_AUTOREMOVE_CONSUMER flag causes the device link to be automatically purged when the consumer fails to probe or later unbinds. So we don't need to keep the consumer_link variable in struct dsa_switch. Fixes: 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings") Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Tested-by: Florian Fainelli <f.fainelli@gmail.com> Link: https://lore.kernel.org/r/20210111230943.3701806-1-olteanv@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-12 07:09:43 +08:00
/* The DSA master must use SET_NETDEV_DEV for this to work. */
consumer_link = device_link_add(ds->dev, dev->dev.parent,
DL_FLAG_AUTOREMOVE_CONSUMER);
if (!consumer_link)
netdev_err(dev,
"Failed to create a device link to DSA switch %s\n",
dev_name(ds->dev));
net: dsa: configure the MTU for switch ports It is useful be able to configure port policers on a switch to accept frames of various sizes: - Increase the MTU for better throughput from the default of 1500 if it is known that there is no 10/100 Mbps device in the network. - Decrease the MTU to limit the latency of high-priority frames under congestion, or work around various network segments that add extra headers to packets which can't be fragmented. For DSA slave ports, this is mostly a pass-through callback, called through the regular ndo ops and at probe time (to ensure consistency across all supported switches). The CPU port is called with an MTU equal to the largest configured MTU of the slave ports. The assumption is that the user might want to sustain a bidirectional conversation with a partner over any switch port. The DSA master is configured the same as the CPU port, plus the tagger overhead. Since the MTU is by definition L2 payload (sans Ethernet header), it is up to each individual driver to figure out if it needs to do anything special for its frame tags on the CPU port (it shouldn't except in special cases). So the MTU does not contain the tagger overhead on the CPU port. However the MTU of the DSA master, minus the tagger overhead, is used as a proxy for the MTU of the CPU port, which does not have a net device. This is to avoid uselessly calling the .change_mtu function on the CPU port when nothing should change. So it is safe to assume that the DSA master and the CPU port MTUs are apart by exactly the tagger's overhead in bytes. Some changes were made around dsa_master_set_mtu(), function which was now removed, for 2 reasons: - dev_set_mtu() already calls dev_validate_mtu(), so it's redundant to do the same thing in DSA - __dev_set_mtu() returns 0 if ops->ndo_change_mtu is an absent method That is to say, there's no need for this function in DSA, we can safely call dev_set_mtu() directly, take the rtnl lock when necessary, and just propagate whatever errors get reported (since the user probably wants to be informed). Some inspiration (mainly in the MTU DSA notifier) was taken from a vaguely similar patch from Murali and Florian, who are credited as co-developers down below. Co-developed-by: Murali Krishna Policharla <murali.policharla@broadcom.com> Signed-off-by: Murali Krishna Policharla <murali.policharla@broadcom.com> Co-developed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-28 03:55:42 +08:00
rtnl_lock();
ret = dev_set_mtu(dev, mtu);
net: dsa: configure the MTU for switch ports It is useful be able to configure port policers on a switch to accept frames of various sizes: - Increase the MTU for better throughput from the default of 1500 if it is known that there is no 10/100 Mbps device in the network. - Decrease the MTU to limit the latency of high-priority frames under congestion, or work around various network segments that add extra headers to packets which can't be fragmented. For DSA slave ports, this is mostly a pass-through callback, called through the regular ndo ops and at probe time (to ensure consistency across all supported switches). The CPU port is called with an MTU equal to the largest configured MTU of the slave ports. The assumption is that the user might want to sustain a bidirectional conversation with a partner over any switch port. The DSA master is configured the same as the CPU port, plus the tagger overhead. Since the MTU is by definition L2 payload (sans Ethernet header), it is up to each individual driver to figure out if it needs to do anything special for its frame tags on the CPU port (it shouldn't except in special cases). So the MTU does not contain the tagger overhead on the CPU port. However the MTU of the DSA master, minus the tagger overhead, is used as a proxy for the MTU of the CPU port, which does not have a net device. This is to avoid uselessly calling the .change_mtu function on the CPU port when nothing should change. So it is safe to assume that the DSA master and the CPU port MTUs are apart by exactly the tagger's overhead in bytes. Some changes were made around dsa_master_set_mtu(), function which was now removed, for 2 reasons: - dev_set_mtu() already calls dev_validate_mtu(), so it's redundant to do the same thing in DSA - __dev_set_mtu() returns 0 if ops->ndo_change_mtu is an absent method That is to say, there's no need for this function in DSA, we can safely call dev_set_mtu() directly, take the rtnl lock when necessary, and just propagate whatever errors get reported (since the user probably wants to be informed). Some inspiration (mainly in the MTU DSA notifier) was taken from a vaguely similar patch from Murali and Florian, who are credited as co-developers down below. Co-developed-by: Murali Krishna Policharla <murali.policharla@broadcom.com> Signed-off-by: Murali Krishna Policharla <murali.policharla@broadcom.com> Co-developed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-28 03:55:42 +08:00
rtnl_unlock();
if (ret)
netdev_warn(dev, "error %d setting MTU to %d to include DSA overhead\n",
ret, mtu);
/* If we use a tagging format that doesn't have an ethertype
* field, make sure that all packets from this point on get
* sent to the tag format's receive function.
*/
wmb();
dev->dsa_ptr = cpu_dp;
lockdep_set_class(&dev->addr_list_lock,
&dsa_master_addr_list_lock_key);
dsa_master_set_promiscuity(dev, 1);
ret = dsa_master_ethtool_setup(dev);
if (ret)
goto out_err_reset_promisc;
dsa_netdev_ops_set(dev, &dsa_netdev_ops);
ret = sysfs_create_group(&dev->dev.kobj, &dsa_group);
if (ret)
goto out_err_ndo_teardown;
return ret;
out_err_ndo_teardown:
dsa_netdev_ops_set(dev, NULL);
dsa_master_ethtool_teardown(dev);
out_err_reset_promisc:
dsa_master_set_promiscuity(dev, -1);
return ret;
}
void dsa_master_teardown(struct net_device *dev)
{
sysfs_remove_group(&dev->dev.kobj, &dsa_group);
dsa_netdev_ops_set(dev, NULL);
dsa_master_ethtool_teardown(dev);
dsa_master_reset_mtu(dev);
dsa_master_set_promiscuity(dev, -1);
dev->dsa_ptr = NULL;
/* If we used a tagging format that doesn't have an ethertype
* field, make sure that all packets from this point get sent
* without the tag and go through the regular receive path.
*/
wmb();
}