linux/net/dsa/master.c

350 lines
8.8 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;
unsigned int 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);
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_do_ioctl)
err = dev->netdev_ops->ndo_do_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_do_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 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));
}
static DEVICE_ATTR_RO(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)
{
int ret;
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, ETH_DATA_LEN + cpu_dp->tag_ops->overhead);
rtnl_unlock();
if (ret)
netdev_warn(dev, "error %d setting MTU to include DSA overhead\n",
ret);
/* 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);
ret = dsa_master_ethtool_setup(dev);
if (ret)
return ret;
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);
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);
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();
}