WSL2-Linux-Kernel/net/core/dev_ioctl.c

637 строки
14 KiB
C
Исходник Обычный вид История

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 17:07:57 +03:00
// SPDX-License-Identifier: GPL-2.0
#include <linux/kmod.h>
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
#include <linux/rtnetlink.h>
#include <linux/net_tstamp.h>
#include <linux/wireless.h>
#include <linux/if_bridge.h>
net: dsa: replace NETDEV_PRE_CHANGE_HWTSTAMP notifier with a stub There was a sort of rush surrounding commit 88c0a6b503b7 ("net: create a netdev notifier for DSA to reject PTP on DSA master"), due to a desire to convert DSA's attempt to deny TX timestamping on a DSA master to something that doesn't block the kernel-wide API conversion from ndo_eth_ioctl() to ndo_hwtstamp_set(). What was required was a mechanism that did not depend on ndo_eth_ioctl(), and what was provided was a mechanism that did not depend on ndo_eth_ioctl(), while at the same time introducing something that wasn't absolutely necessary - a new netdev notifier. There have been objections from Jakub Kicinski that using notifiers in general when they are not absolutely necessary creates complications to the control flow and difficulties to maintainers who look at the code. So there is a desire to not use notifiers. In addition to that, the notifier chain gets called even if there is no DSA in the system and no one is interested in applying any restriction. Take the model of udp_tunnel_nic_ops and introduce a stub mechanism, through which net/core/dev_ioctl.c can call into DSA even when CONFIG_NET_DSA=m. Compared to the code that existed prior to the notifier conversion, aka what was added in commits: - 4cfab3566710 ("net: dsa: Add wrappers for overloaded ndo_ops") - 3369afba1e46 ("net: Call into DSA netdevice_ops wrappers") this is different because we are not overloading any struct net_device_ops of the DSA master anymore, but rather, we are exposing a rather specific functionality which is orthogonal to which API is used to enable it - ndo_eth_ioctl() or ndo_hwtstamp_set(). Also, what is similar is that both approaches use function pointers to get from built-in code to DSA. There is no point in replicating the function pointers towards __dsa_master_hwtstamp_validate() once for every CPU port (dev->dsa_ptr). Instead, it is sufficient to introduce a singleton struct dsa_stubs, built into the kernel, which contains a single function pointer to __dsa_master_hwtstamp_validate(). I find this approach preferable to what we had originally, because dev->dsa_ptr->netdev_ops->ndo_do_ioctl() used to require going through struct dsa_port (dev->dsa_ptr), and so, this was incompatible with any attempts to add any data encapsulation and hide DSA data structures from the outside world. Link: https://lore.kernel.org/netdev/20230403083019.120b72fd@kernel.org/ Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-04-06 14:42:46 +03:00
#include <net/dsa_stubs.h>
#include <net/wext.h>
#include "dev.h"
/*
* Map an interface index to its name (SIOCGIFNAME)
*/
/*
* We need this ioctl for efficient implementation of the
* if_indextoname() function required by the IPv6 API. Without
* it, we would have to search all the interfaces to find a
* match. --pb
*/
static int dev_ifname(struct net *net, struct ifreq *ifr)
{
ifr->ifr_name[IFNAMSIZ-1] = 0;
return netdev_get_name(net, ifr->ifr_name, ifr->ifr_ifindex);
}
/*
* Perform a SIOCGIFCONF call. This structure will change
* size eventually, and there is nothing I can do about it.
* Thus we will need a 'compatibility mode'.
*/
int dev_ifconf(struct net *net, struct ifconf __user *uifc)
{
struct net_device *dev;
void __user *pos;
size_t size;
int len, total = 0, done;
/* both the ifconf and the ifreq structures are slightly different */
if (in_compat_syscall()) {
struct compat_ifconf ifc32;
if (copy_from_user(&ifc32, uifc, sizeof(struct compat_ifconf)))
return -EFAULT;
pos = compat_ptr(ifc32.ifcbuf);
len = ifc32.ifc_len;
size = sizeof(struct compat_ifreq);
} else {
struct ifconf ifc;
if (copy_from_user(&ifc, uifc, sizeof(struct ifconf)))
return -EFAULT;
pos = ifc.ifc_buf;
len = ifc.ifc_len;
size = sizeof(struct ifreq);
}
/* Loop over the interfaces, and write an info block for each. */
rtnl_lock();
for_each_netdev(net, dev) {
if (!pos)
done = inet_gifconf(dev, NULL, 0, size);
else
done = inet_gifconf(dev, pos + total,
len - total, size);
if (done < 0) {
rtnl_unlock();
return -EFAULT;
}
total += done;
}
rtnl_unlock();
return put_user(total, &uifc->ifc_len);
}
static int dev_getifmap(struct net_device *dev, struct ifreq *ifr)
{
struct ifmap *ifmap = &ifr->ifr_map;
if (in_compat_syscall()) {
struct compat_ifmap *cifmap = (struct compat_ifmap *)ifmap;
cifmap->mem_start = dev->mem_start;
cifmap->mem_end = dev->mem_end;
cifmap->base_addr = dev->base_addr;
cifmap->irq = dev->irq;
cifmap->dma = dev->dma;
cifmap->port = dev->if_port;
return 0;
}
ifmap->mem_start = dev->mem_start;
ifmap->mem_end = dev->mem_end;
ifmap->base_addr = dev->base_addr;
ifmap->irq = dev->irq;
ifmap->dma = dev->dma;
ifmap->port = dev->if_port;
return 0;
}
static int dev_setifmap(struct net_device *dev, struct ifreq *ifr)
{
struct compat_ifmap *cifmap = (struct compat_ifmap *)&ifr->ifr_map;
if (!dev->netdev_ops->ndo_set_config)
return -EOPNOTSUPP;
if (in_compat_syscall()) {
struct ifmap ifmap = {
.mem_start = cifmap->mem_start,
.mem_end = cifmap->mem_end,
.base_addr = cifmap->base_addr,
.irq = cifmap->irq,
.dma = cifmap->dma,
.port = cifmap->port,
};
return dev->netdev_ops->ndo_set_config(dev, &ifmap);
}
return dev->netdev_ops->ndo_set_config(dev, &ifr->ifr_map);
}
/*
* Perform the SIOCxIFxxx calls, inside rcu_read_lock()
*/
static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd)
{
int err;
struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name);
if (!dev)
return -ENODEV;
switch (cmd) {
case SIOCGIFFLAGS: /* Get interface flags */
ifr->ifr_flags = (short) dev_get_flags(dev);
return 0;
case SIOCGIFMETRIC: /* Get the metric on the interface
(currently unused) */
ifr->ifr_metric = 0;
return 0;
case SIOCGIFMTU: /* Get the MTU of a device */
ifr->ifr_mtu = dev->mtu;
return 0;
case SIOCGIFSLAVE:
err = -EINVAL;
break;
case SIOCGIFMAP:
return dev_getifmap(dev, ifr);
case SIOCGIFINDEX:
ifr->ifr_ifindex = dev->ifindex;
return 0;
case SIOCGIFTXQLEN:
ifr->ifr_qlen = dev->tx_queue_len;
return 0;
default:
/* dev_ioctl() should ensure this case
* is never reached
*/
WARN_ON(1);
err = -ENOTTY;
break;
}
return err;
}
static int net_hwtstamp_validate(const struct kernel_hwtstamp_config *cfg)
{
enum hwtstamp_tx_types tx_type;
enum hwtstamp_rx_filters rx_filter;
int tx_type_valid = 0;
int rx_filter_valid = 0;
if (cfg->flags & ~HWTSTAMP_FLAG_MASK)
return -EINVAL;
tx_type = cfg->tx_type;
rx_filter = cfg->rx_filter;
switch (tx_type) {
case HWTSTAMP_TX_OFF:
case HWTSTAMP_TX_ON:
case HWTSTAMP_TX_ONESTEP_SYNC:
case HWTSTAMP_TX_ONESTEP_P2P:
tx_type_valid = 1;
break;
case __HWTSTAMP_TX_CNT:
/* not a real value */
break;
}
switch (rx_filter) {
case HWTSTAMP_FILTER_NONE:
case HWTSTAMP_FILTER_ALL:
case HWTSTAMP_FILTER_SOME:
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_PTP_V2_L4_EVENT:
case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
case HWTSTAMP_FILTER_PTP_V2_EVENT:
case HWTSTAMP_FILTER_PTP_V2_SYNC:
case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
case HWTSTAMP_FILTER_NTP_ALL:
rx_filter_valid = 1;
break;
case __HWTSTAMP_FILTER_CNT:
/* not a real value */
break;
}
if (!tx_type_valid || !rx_filter_valid)
return -ERANGE;
return 0;
}
static int dev_eth_ioctl(struct net_device *dev,
struct ifreq *ifr, unsigned int cmd)
{
const struct net_device_ops *ops = dev->netdev_ops;
if (!ops->ndo_eth_ioctl)
return -EOPNOTSUPP;
if (!netif_device_present(dev))
return -ENODEV;
return ops->ndo_eth_ioctl(dev, ifr, cmd);
}
static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
{
return dev_eth_ioctl(dev, ifr, SIOCGHWTSTAMP);
}
static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr)
{
struct kernel_hwtstamp_config kernel_cfg;
net: create a netdev notifier for DSA to reject PTP on DSA master The fact that PTP 2-step TX timestamping is broken on DSA switches if the master also timestamps the same packets is documented by commit f685e609a301 ("net: dsa: Deny PTP on master if switch supports it"). We attempt to help the users avoid shooting themselves in the foot by making DSA reject the timestamping ioctls on an interface that is a DSA master, and the switch tree beneath it contains switches which are aware of PTP. The only problem is that there isn't an established way of intercepting ndo_eth_ioctl calls, so DSA creates avoidable burden upon the network stack by creating a struct dsa_netdevice_ops with overlaid function pointers that are manually checked from the relevant call sites. There used to be 2 such dsa_netdevice_ops, but now, ndo_eth_ioctl is the only one left. There is an ongoing effort to migrate driver-visible hardware timestamping control from the ndo_eth_ioctl() based API to a new ndo_hwtstamp_set() model, but DSA actively prevents that migration, since dsa_master_ioctl() is currently coded to manually call the master's legacy ndo_eth_ioctl(), and so, whenever a network device driver would be converted to the new API, DSA's restrictions would be circumvented, because any device could be used as a DSA master. The established way for unrelated modules to react on a net device event is via netdevice notifiers. So we create a new notifier which gets called whenever there is an attempt to change hardware timestamping settings on a device. Finally, there is another reason why a netdev notifier will be a good idea, besides strictly DSA, and this has to do with PHY timestamping. With ndo_eth_ioctl(), all MAC drivers must manually call phy_has_hwtstamp() before deciding whether to act upon SIOCSHWTSTAMP, otherwise they must pass this ioctl to the PHY driver via phy_mii_ioctl(). With the new ndo_hwtstamp_set() API, it will be desirable to simply not make any calls into the MAC device driver when timestamping should be performed at the PHY level. But there exist drivers, such as the lan966x switch, which need to install packet traps for PTP regardless of whether they are the layer that provides the hardware timestamps, or the PHY is. That would be impossible to support with the new API. The proposal there, too, is to introduce a netdev notifier which acts as a better cue for switching drivers to add or remove PTP packet traps, than ndo_hwtstamp_set(). The one introduced here "almost" works there as well, except for the fact that packet traps should only be installed if the PHY driver succeeded to enable hardware timestamping, whereas here, we need to deny hardware timestamping on the DSA master before it actually gets enabled. This is why this notifier is called "PRE_", and the notifier that would get used for PHY timestamping and packet traps would be called NETDEV_CHANGE_HWTSTAMP. This isn't a new concept, for example NETDEV_CHANGEUPPER and NETDEV_PRECHANGEUPPER do the same thing. In expectation of future netlink UAPI, we also pass a non-NULL extack pointer to the netdev notifier, and we make DSA populate it with an informative reason for the rejection. To avoid making it go to waste, we make the ioctl-based dev_set_hwtstamp() create a fake extack and print the message to the kernel log. Link: https://lore.kernel.org/netdev/20230401191215.tvveoi3lkawgg6g4@skbuf/ Link: https://lore.kernel.org/netdev/20230310164451.ls7bbs6pdzs4m6pw@skbuf/ Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-04-02 15:37:55 +03:00
struct netlink_ext_ack extack = {};
struct hwtstamp_config cfg;
int err;
if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
return -EFAULT;
hwtstamp_config_to_kernel(&kernel_cfg, &cfg);
err = net_hwtstamp_validate(&kernel_cfg);
if (err)
return err;
net: dsa: replace NETDEV_PRE_CHANGE_HWTSTAMP notifier with a stub There was a sort of rush surrounding commit 88c0a6b503b7 ("net: create a netdev notifier for DSA to reject PTP on DSA master"), due to a desire to convert DSA's attempt to deny TX timestamping on a DSA master to something that doesn't block the kernel-wide API conversion from ndo_eth_ioctl() to ndo_hwtstamp_set(). What was required was a mechanism that did not depend on ndo_eth_ioctl(), and what was provided was a mechanism that did not depend on ndo_eth_ioctl(), while at the same time introducing something that wasn't absolutely necessary - a new netdev notifier. There have been objections from Jakub Kicinski that using notifiers in general when they are not absolutely necessary creates complications to the control flow and difficulties to maintainers who look at the code. So there is a desire to not use notifiers. In addition to that, the notifier chain gets called even if there is no DSA in the system and no one is interested in applying any restriction. Take the model of udp_tunnel_nic_ops and introduce a stub mechanism, through which net/core/dev_ioctl.c can call into DSA even when CONFIG_NET_DSA=m. Compared to the code that existed prior to the notifier conversion, aka what was added in commits: - 4cfab3566710 ("net: dsa: Add wrappers for overloaded ndo_ops") - 3369afba1e46 ("net: Call into DSA netdevice_ops wrappers") this is different because we are not overloading any struct net_device_ops of the DSA master anymore, but rather, we are exposing a rather specific functionality which is orthogonal to which API is used to enable it - ndo_eth_ioctl() or ndo_hwtstamp_set(). Also, what is similar is that both approaches use function pointers to get from built-in code to DSA. There is no point in replicating the function pointers towards __dsa_master_hwtstamp_validate() once for every CPU port (dev->dsa_ptr). Instead, it is sufficient to introduce a singleton struct dsa_stubs, built into the kernel, which contains a single function pointer to __dsa_master_hwtstamp_validate(). I find this approach preferable to what we had originally, because dev->dsa_ptr->netdev_ops->ndo_do_ioctl() used to require going through struct dsa_port (dev->dsa_ptr), and so, this was incompatible with any attempts to add any data encapsulation and hide DSA data structures from the outside world. Link: https://lore.kernel.org/netdev/20230403083019.120b72fd@kernel.org/ Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-04-06 14:42:46 +03:00
err = dsa_master_hwtstamp_validate(dev, &kernel_cfg, &extack);
net: create a netdev notifier for DSA to reject PTP on DSA master The fact that PTP 2-step TX timestamping is broken on DSA switches if the master also timestamps the same packets is documented by commit f685e609a301 ("net: dsa: Deny PTP on master if switch supports it"). We attempt to help the users avoid shooting themselves in the foot by making DSA reject the timestamping ioctls on an interface that is a DSA master, and the switch tree beneath it contains switches which are aware of PTP. The only problem is that there isn't an established way of intercepting ndo_eth_ioctl calls, so DSA creates avoidable burden upon the network stack by creating a struct dsa_netdevice_ops with overlaid function pointers that are manually checked from the relevant call sites. There used to be 2 such dsa_netdevice_ops, but now, ndo_eth_ioctl is the only one left. There is an ongoing effort to migrate driver-visible hardware timestamping control from the ndo_eth_ioctl() based API to a new ndo_hwtstamp_set() model, but DSA actively prevents that migration, since dsa_master_ioctl() is currently coded to manually call the master's legacy ndo_eth_ioctl(), and so, whenever a network device driver would be converted to the new API, DSA's restrictions would be circumvented, because any device could be used as a DSA master. The established way for unrelated modules to react on a net device event is via netdevice notifiers. So we create a new notifier which gets called whenever there is an attempt to change hardware timestamping settings on a device. Finally, there is another reason why a netdev notifier will be a good idea, besides strictly DSA, and this has to do with PHY timestamping. With ndo_eth_ioctl(), all MAC drivers must manually call phy_has_hwtstamp() before deciding whether to act upon SIOCSHWTSTAMP, otherwise they must pass this ioctl to the PHY driver via phy_mii_ioctl(). With the new ndo_hwtstamp_set() API, it will be desirable to simply not make any calls into the MAC device driver when timestamping should be performed at the PHY level. But there exist drivers, such as the lan966x switch, which need to install packet traps for PTP regardless of whether they are the layer that provides the hardware timestamps, or the PHY is. That would be impossible to support with the new API. The proposal there, too, is to introduce a netdev notifier which acts as a better cue for switching drivers to add or remove PTP packet traps, than ndo_hwtstamp_set(). The one introduced here "almost" works there as well, except for the fact that packet traps should only be installed if the PHY driver succeeded to enable hardware timestamping, whereas here, we need to deny hardware timestamping on the DSA master before it actually gets enabled. This is why this notifier is called "PRE_", and the notifier that would get used for PHY timestamping and packet traps would be called NETDEV_CHANGE_HWTSTAMP. This isn't a new concept, for example NETDEV_CHANGEUPPER and NETDEV_PRECHANGEUPPER do the same thing. In expectation of future netlink UAPI, we also pass a non-NULL extack pointer to the netdev notifier, and we make DSA populate it with an informative reason for the rejection. To avoid making it go to waste, we make the ioctl-based dev_set_hwtstamp() create a fake extack and print the message to the kernel log. Link: https://lore.kernel.org/netdev/20230401191215.tvveoi3lkawgg6g4@skbuf/ Link: https://lore.kernel.org/netdev/20230310164451.ls7bbs6pdzs4m6pw@skbuf/ Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-04-02 15:37:55 +03:00
if (err) {
if (extack._msg)
netdev_err(dev, "%s\n", extack._msg);
return err;
net: create a netdev notifier for DSA to reject PTP on DSA master The fact that PTP 2-step TX timestamping is broken on DSA switches if the master also timestamps the same packets is documented by commit f685e609a301 ("net: dsa: Deny PTP on master if switch supports it"). We attempt to help the users avoid shooting themselves in the foot by making DSA reject the timestamping ioctls on an interface that is a DSA master, and the switch tree beneath it contains switches which are aware of PTP. The only problem is that there isn't an established way of intercepting ndo_eth_ioctl calls, so DSA creates avoidable burden upon the network stack by creating a struct dsa_netdevice_ops with overlaid function pointers that are manually checked from the relevant call sites. There used to be 2 such dsa_netdevice_ops, but now, ndo_eth_ioctl is the only one left. There is an ongoing effort to migrate driver-visible hardware timestamping control from the ndo_eth_ioctl() based API to a new ndo_hwtstamp_set() model, but DSA actively prevents that migration, since dsa_master_ioctl() is currently coded to manually call the master's legacy ndo_eth_ioctl(), and so, whenever a network device driver would be converted to the new API, DSA's restrictions would be circumvented, because any device could be used as a DSA master. The established way for unrelated modules to react on a net device event is via netdevice notifiers. So we create a new notifier which gets called whenever there is an attempt to change hardware timestamping settings on a device. Finally, there is another reason why a netdev notifier will be a good idea, besides strictly DSA, and this has to do with PHY timestamping. With ndo_eth_ioctl(), all MAC drivers must manually call phy_has_hwtstamp() before deciding whether to act upon SIOCSHWTSTAMP, otherwise they must pass this ioctl to the PHY driver via phy_mii_ioctl(). With the new ndo_hwtstamp_set() API, it will be desirable to simply not make any calls into the MAC device driver when timestamping should be performed at the PHY level. But there exist drivers, such as the lan966x switch, which need to install packet traps for PTP regardless of whether they are the layer that provides the hardware timestamps, or the PHY is. That would be impossible to support with the new API. The proposal there, too, is to introduce a netdev notifier which acts as a better cue for switching drivers to add or remove PTP packet traps, than ndo_hwtstamp_set(). The one introduced here "almost" works there as well, except for the fact that packet traps should only be installed if the PHY driver succeeded to enable hardware timestamping, whereas here, we need to deny hardware timestamping on the DSA master before it actually gets enabled. This is why this notifier is called "PRE_", and the notifier that would get used for PHY timestamping and packet traps would be called NETDEV_CHANGE_HWTSTAMP. This isn't a new concept, for example NETDEV_CHANGEUPPER and NETDEV_PRECHANGEUPPER do the same thing. In expectation of future netlink UAPI, we also pass a non-NULL extack pointer to the netdev notifier, and we make DSA populate it with an informative reason for the rejection. To avoid making it go to waste, we make the ioctl-based dev_set_hwtstamp() create a fake extack and print the message to the kernel log. Link: https://lore.kernel.org/netdev/20230401191215.tvveoi3lkawgg6g4@skbuf/ Link: https://lore.kernel.org/netdev/20230310164451.ls7bbs6pdzs4m6pw@skbuf/ Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-04-02 15:37:55 +03:00
}
return dev_eth_ioctl(dev, ifr, SIOCSHWTSTAMP);
}
static int dev_siocbond(struct net_device *dev,
struct ifreq *ifr, unsigned int cmd)
{
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_siocbond) {
if (netif_device_present(dev))
return ops->ndo_siocbond(dev, ifr, cmd);
else
return -ENODEV;
}
return -EOPNOTSUPP;
}
static int dev_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
void __user *data, unsigned int cmd)
{
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_siocdevprivate) {
if (netif_device_present(dev))
return ops->ndo_siocdevprivate(dev, ifr, data, cmd);
else
return -ENODEV;
}
return -EOPNOTSUPP;
}
static int dev_siocwandev(struct net_device *dev, struct if_settings *ifs)
{
const struct net_device_ops *ops = dev->netdev_ops;
if (ops->ndo_siocwandev) {
if (netif_device_present(dev))
return ops->ndo_siocwandev(dev, ifs);
else
return -ENODEV;
}
return -EOPNOTSUPP;
}
/*
* Perform the SIOCxIFxxx calls, inside rtnl_lock()
*/
static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data,
unsigned int cmd)
{
int err;
struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
const struct net_device_ops *ops;
netdevice_tracker dev_tracker;
if (!dev)
return -ENODEV;
ops = dev->netdev_ops;
switch (cmd) {
case SIOCSIFFLAGS: /* Set interface flags */
return dev_change_flags(dev, ifr->ifr_flags, NULL);
case SIOCSIFMETRIC: /* Set the metric on the interface
(currently unused) */
return -EOPNOTSUPP;
case SIOCSIFMTU: /* Set the MTU of a device */
return dev_set_mtu(dev, ifr->ifr_mtu);
case SIOCSIFHWADDR:
if (dev->addr_len > sizeof(struct sockaddr))
return -EINVAL;
return dev_set_mac_address_user(dev, &ifr->ifr_hwaddr, NULL);
case SIOCSIFHWBROADCAST:
if (ifr->ifr_hwaddr.sa_family != dev->type)
return -EINVAL;
memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
net: dev: Convert sa_data to flexible array in struct sockaddr One of the worst offenders of "fake flexible arrays" is struct sockaddr, as it is the classic example of why GCC and Clang have been traditionally forced to treat all trailing arrays as fake flexible arrays: in the distant misty past, sa_data became too small, and code started just treating it as a flexible array, even though it was fixed-size. The special case by the compiler is specifically that sizeof(sa->sa_data) and FORTIFY_SOURCE (which uses __builtin_object_size(sa->sa_data, 1)) do not agree (14 and -1 respectively), which makes FORTIFY_SOURCE treat it as a flexible array. However, the coming -fstrict-flex-arrays compiler flag will remove these special cases so that FORTIFY_SOURCE can gain coverage over all the trailing arrays in the kernel that are _not_ supposed to be treated as a flexible array. To deal with this change, convert sa_data to a true flexible array. To keep the structure size the same, move sa_data into a union with a newly introduced sa_data_min with the original size. The result is that FORTIFY_SOURCE can continue to have no idea how large sa_data may actually be, but anything using sizeof(sa->sa_data) must switch to sizeof(sa->sa_data_min). Cc: Jens Axboe <axboe@kernel.dk> Cc: Pavel Begunkov <asml.silence@gmail.com> Cc: David Ahern <dsahern@kernel.org> Cc: Dylan Yudaken <dylany@fb.com> Cc: Yajun Deng <yajun.deng@linux.dev> Cc: Petr Machata <petrm@nvidia.com> Cc: Hangbin Liu <liuhangbin@gmail.com> Cc: Leon Romanovsky <leon@kernel.org> Cc: syzbot <syzkaller@googlegroups.com> Cc: Willem de Bruijn <willemb@google.com> Cc: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20221018095503.never.671-kees@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-10-18 12:56:03 +03:00
min(sizeof(ifr->ifr_hwaddr.sa_data_min),
(size_t)dev->addr_len));
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
return 0;
case SIOCSIFMAP:
return dev_setifmap(dev, ifr);
case SIOCADDMULTI:
if (!ops->ndo_set_rx_mode ||
ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
return -EINVAL;
if (!netif_device_present(dev))
return -ENODEV;
return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data);
case SIOCDELMULTI:
if (!ops->ndo_set_rx_mode ||
ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
return -EINVAL;
if (!netif_device_present(dev))
return -ENODEV;
return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data);
case SIOCSIFTXQLEN:
if (ifr->ifr_qlen < 0)
return -EINVAL;
return dev_change_tx_queue_len(dev, ifr->ifr_qlen);
case SIOCSIFNAME:
ifr->ifr_newname[IFNAMSIZ-1] = '\0';
return dev_change_name(dev, ifr->ifr_newname);
case SIOCWANDEV:
return dev_siocwandev(dev, &ifr->ifr_settings);
case SIOCBRADDIF:
case SIOCBRDELIF:
if (!netif_device_present(dev))
return -ENODEV;
net: core: don't call SIOCBRADD/DELIF for non-bridge devices Commit ad2f99aedf8f ("net: bridge: move bridge ioctls out of .ndo_do_ioctl") changed SIOCBRADD/DELIF to use bridge's ioctl hook (br_ioctl_hook) without checking if the target netdevice is actually a bridge which can cause crashes and generally interpreting other devices' private pointers as net_bridge pointers. Crash example (lo - loopback): $ brctl addif lo ens16 BUG: kernel NULL pointer dereference, address: 000000000000059898 #PF: supervisor read access in kernel modede #PF: error_code(0x0000) - not-present pagege PGD 0 P4D 0 ^Ac Oops: 0000 [#1] SMP NOPTI CPU: 2 PID: 1376 Comm: brctl Kdump: loaded Tainted: G W 5.14.0-rc3+ #405 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-4.fc34 04/01/2014 RIP: 0010:add_del_if+0x1f/0x7c [bridge] Code: 80 bf 1b a0 41 5c e9 c0 3c 03 e1 0f 1f 44 00 00 41 55 41 54 41 89 f4 be 0c 00 00 00 55 48 89 fd 53 48 8b 87 88 00 00 00 89 d3 <4c> 8b a8 98 05 00 00 49 8b bd d0 00 00 00 e8 17 d7 f3 e0 84 c0 74 RSP: 0018:ffff888109d97cb0 EFLAGS: 00010202^Ac RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 000000000000000c RDI: ffff888101239bc0 RBP: ffff888101239bc0 R08: 0000000000000001 R09: 0000000000000000 R10: ffff888109d97cd8 R11: 00000000000000a3 R12: 0000000000000012 R13: 0000000000000000 R14: ffff888101239bc0 R15: ffff888109d97e10 FS: 00007fc1e365b540(0000) GS:ffff88822be80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000598 CR3: 0000000106506000 CR4: 00000000000006e0 Call Trace: br_ioctl_stub+0x7c/0x441 [bridge] br_ioctl_call+0x6d/0x8a dev_ifsioc+0x325/0x4e8 dev_ioctl+0x46b/0x4e1 sock_do_ioctl+0x7b/0xad sock_ioctl+0x2de/0x2f2 vfs_ioctl+0x1e/0x2b __do_sys_ioctl+0x63/0x86 do_syscall_64+0xcb/0xf2 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7fc1e3589427 Code: 00 00 90 48 8b 05 69 aa 0c 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 39 aa 0c 00 f7 d8 64 89 01 48 RSP: 002b:00007ffc8d501d38 EFLAGS: 00000202 ORIG_RAX: 000000000000001010 RAX: ffffffffffffffda RBX: 0000000000000012 RCX: 00007fc1e3589427 RDX: 00007ffc8d501d60 RSI: 00000000000089a3 RDI: 0000000000000003 RBP: 00007ffc8d501d60 R08: 0000000000000000 R09: fefefeff77686d74 R10: fffffffffffff8f9 R11: 0000000000000202 R12: 00007ffc8d502e06 R13: 00007ffc8d502e06 R14: 0000000000000000 R15: 0000000000000000 Modules linked in: bridge stp llc bonding ipv6 virtio_net [last unloaded: llc]^Ac CR2: 0000000000000598 Reported-by: syzbot+79f4a8692e267bdb7227@syzkaller.appspotmail.com Fixes: ad2f99aedf8f ("net: bridge: move bridge ioctls out of .ndo_do_ioctl") Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-05 11:29:03 +03:00
if (!netif_is_bridge_master(dev))
return -EOPNOTSUPP;
netdev_hold(dev, &dev_tracker, GFP_KERNEL);
rtnl_unlock();
err = br_ioctl_call(net, netdev_priv(dev), cmd, ifr, NULL);
netdev_put(dev, &dev_tracker);
rtnl_lock();
return err;
case SIOCDEVPRIVATE ... SIOCDEVPRIVATE + 15:
return dev_siocdevprivate(dev, ifr, data, cmd);
case SIOCSHWTSTAMP:
return dev_set_hwtstamp(dev, ifr);
case SIOCGHWTSTAMP:
return dev_get_hwtstamp(dev, ifr);
case SIOCGMIIPHY:
case SIOCGMIIREG:
case SIOCSMIIREG:
return dev_eth_ioctl(dev, ifr, cmd);
case SIOCBONDENSLAVE:
case SIOCBONDRELEASE:
case SIOCBONDSETHWADDR:
case SIOCBONDSLAVEINFOQUERY:
case SIOCBONDINFOQUERY:
case SIOCBONDCHANGEACTIVE:
return dev_siocbond(dev, ifr, cmd);
/* Unknown ioctl */
default:
err = -EINVAL;
}
return err;
}
/**
* dev_load - load a network module
* @net: the applicable net namespace
* @name: name of interface
*
* If a network interface is not present and the process has suitable
* privileges this function loads the module. If module loading is not
* available in this kernel then it becomes a nop.
*/
void dev_load(struct net *net, const char *name)
{
struct net_device *dev;
int no_module;
rcu_read_lock();
dev = dev_get_by_name_rcu(net, name);
rcu_read_unlock();
no_module = !dev;
if (no_module && capable(CAP_NET_ADMIN))
no_module = request_module("netdev-%s", name);
dev_ioctl: remove dev_load() CAP_SYS_MODULE message Marcel reported to see the following message when autoloading is being triggered when adding nlmon device: Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-nlmon instead. This false-positive happens despite with having correct capabilities set, e.g. through issuing `ip link del dev nlmon` more than once on a valid device with name nlmon, but Marcel has also seen it on creation time when no nlmon module is previously compiled-in or loaded as module and the device name equals a link type name (e.g. nlmon, vxlan, team). Stephen says: The netdev module alias is a hold over from the past. For normal devices, people used to create a alias eth0 to and point it to the type of network device used, that was back in the bad old ISA days before real discovery. Also, the tunnels create module alias for the control device and ip used to use this to autoload the tunnel device. The message is bogus and should just be removed, I also see it in a couple of other cases where tap devices are renamed for other usese. As mentioned in 8909c9ad8ff0 ("net: don't allow CAP_NET_ADMIN to load non-netdev kernel modules"), we nevertheless still might want to leave the old autoloading behaviour in place as it could break old scripts, so for now, lets just remove the log message as Stephen suggests. Reference: http://thread.gmane.org/gmane.linux.kernel/1105168 Reported-by: Marcel Holtmann <marcel@holtmann.org> Suggested-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Cc: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-03 01:30:05 +04:00
if (no_module && capable(CAP_SYS_MODULE))
request_module("%s", name);
}
EXPORT_SYMBOL(dev_load);
/*
* This function handles all "interface"-type I/O control requests. The actual
* 'doing' part of this is dev_ifsioc above.
*/
/**
* dev_ioctl - network device ioctl
* @net: the applicable net namespace
* @cmd: command to issue
* @ifr: pointer to a struct ifreq in user space
* @data: data exchanged with userspace
* @need_copyout: whether or not copy_to_user() should be called
*
* Issue ioctl functions to devices. This is normally called by the
* user space syscall interfaces but can sometimes be useful for
* other purposes. The return value is the return from the syscall if
* positive or a negative errno code on error.
*/
int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr,
void __user *data, bool *need_copyout)
{
int ret;
char *colon;
if (need_copyout)
*need_copyout = true;
if (cmd == SIOCGIFNAME)
return dev_ifname(net, ifr);
ifr->ifr_name[IFNAMSIZ-1] = 0;
colon = strchr(ifr->ifr_name, ':');
if (colon)
*colon = 0;
/*
* See which interface the caller is talking about.
*/
switch (cmd) {
case SIOCGIFHWADDR:
dev_load(net, ifr->ifr_name);
ret = dev_get_mac_address(&ifr->ifr_hwaddr, net, ifr->ifr_name);
if (colon)
*colon = ':';
return ret;
/*
* These ioctl calls:
* - can be done by all.
* - atomic and do not require locking.
* - return a value
*/
case SIOCGIFFLAGS:
case SIOCGIFMETRIC:
case SIOCGIFMTU:
case SIOCGIFSLAVE:
case SIOCGIFMAP:
case SIOCGIFINDEX:
case SIOCGIFTXQLEN:
dev_load(net, ifr->ifr_name);
rcu_read_lock();
ret = dev_ifsioc_locked(net, ifr, cmd);
rcu_read_unlock();
if (colon)
*colon = ':';
return ret;
case SIOCETHTOOL:
dev_load(net, ifr->ifr_name);
ret = dev_ethtool(net, ifr, data);
if (colon)
*colon = ':';
return ret;
/*
* These ioctl calls:
* - require superuser power.
* - require strict serialization.
* - return a value
*/
case SIOCGMIIPHY:
case SIOCGMIIREG:
case SIOCSIFNAME:
dev_load(net, ifr->ifr_name);
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
rtnl_lock();
ret = dev_ifsioc(net, ifr, data, cmd);
rtnl_unlock();
if (colon)
*colon = ':';
return ret;
/*
* These ioctl calls:
* - require superuser power.
* - require strict serialization.
* - do not return a value
*/
case SIOCSIFMAP:
case SIOCSIFTXQLEN:
if (!capable(CAP_NET_ADMIN))
return -EPERM;
fallthrough;
/*
* These ioctl calls:
* - require local superuser power.
* - require strict serialization.
* - do not return a value
*/
case SIOCSIFFLAGS:
case SIOCSIFMETRIC:
case SIOCSIFMTU:
case SIOCSIFHWADDR:
case SIOCSIFSLAVE:
case SIOCADDMULTI:
case SIOCDELMULTI:
case SIOCSIFHWBROADCAST:
case SIOCSMIIREG:
case SIOCBONDENSLAVE:
case SIOCBONDRELEASE:
case SIOCBONDSETHWADDR:
case SIOCBONDCHANGEACTIVE:
case SIOCBRADDIF:
case SIOCBRDELIF:
case SIOCSHWTSTAMP:
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
fallthrough;
case SIOCBONDSLAVEINFOQUERY:
case SIOCBONDINFOQUERY:
dev_load(net, ifr->ifr_name);
rtnl_lock();
ret = dev_ifsioc(net, ifr, data, cmd);
rtnl_unlock();
if (need_copyout)
*need_copyout = false;
return ret;
case SIOCGIFMEM:
/* Get the per device memory space. We can add this but
* currently do not support it */
case SIOCSIFMEM:
/* Set the per device memory buffer space.
* Not applicable in our case */
case SIOCSIFLINK:
return -ENOTTY;
/*
* Unknown or private ioctl.
*/
default:
if (cmd == SIOCWANDEV ||
cmd == SIOCGHWTSTAMP ||
(cmd >= SIOCDEVPRIVATE &&
cmd <= SIOCDEVPRIVATE + 15)) {
dev_load(net, ifr->ifr_name);
rtnl_lock();
ret = dev_ifsioc(net, ifr, data, cmd);
rtnl_unlock();
return ret;
}
return -ENOTTY;
}
}