WSL2-Linux-Kernel/include/net/dst_metadata.h

273 строки
6.3 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 */
#ifndef __NET_DST_METADATA_H
#define __NET_DST_METADATA_H 1
#include <linux/skbuff.h>
#include <net/ip_tunnels.h>
#include <net/macsec.h>
#include <net/dst.h>
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-23 23:11:58 +03:00
enum metadata_type {
METADATA_IP_TUNNEL,
METADATA_HW_PORT_MUX,
METADATA_MACSEC,
net: allow storing xfrm interface metadata in metadata_dst XFRM interfaces provide the association of various XFRM transformations to a netdevice using an 'if_id' identifier common to both the XFRM data structures (polcies, states) and the interface. The if_id is configured by the controlling entity (usually the IKE daemon) and can be used by the administrator to define logical relations between different connections. For example, different connections can share the if_id identifier so that they pass through the same interface, . However, currently it is not possible for connections using a different if_id to use the same interface while retaining the logical separation between them, without using additional criteria such as skb marks or different traffic selectors. When having a large number of connections, it is useful to have a the logical separation offered by the if_id identifier but use a single network interface. Similar to the way collect_md mode is used in IP tunnels. This patch attempts to enable different configuration mechanisms - such as ebpf programs, LWT encapsulations, and TC - to attach metadata to skbs which would carry the if_id. This way a single xfrm interface in collect_md mode can demux traffic based on this configuration on tx and provide this metadata on rx. The XFRM metadata is somewhat similar to ip tunnel metadata in that it has an "id", and shares similar configuration entities (bpf, tc, ...), however, it does not necessarily represent an IP tunnel or use other ip tunnel information, and also has an optional "link" property which can be used for affecting underlying routing decisions. Additional xfrm related criteria may also be added in the future. Therefore, a new metadata type is introduced, to be used in subsequent patches in the xfrm interface and configuration entities. Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org> Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: Eyal Birger <eyal.birger@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2022-08-26 14:46:58 +03:00
METADATA_XFRM,
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-23 23:11:58 +03:00
};
struct hw_port_info {
struct net_device *lower_dev;
u32 port_id;
};
struct macsec_info {
sci_t sci;
};
net: allow storing xfrm interface metadata in metadata_dst XFRM interfaces provide the association of various XFRM transformations to a netdevice using an 'if_id' identifier common to both the XFRM data structures (polcies, states) and the interface. The if_id is configured by the controlling entity (usually the IKE daemon) and can be used by the administrator to define logical relations between different connections. For example, different connections can share the if_id identifier so that they pass through the same interface, . However, currently it is not possible for connections using a different if_id to use the same interface while retaining the logical separation between them, without using additional criteria such as skb marks or different traffic selectors. When having a large number of connections, it is useful to have a the logical separation offered by the if_id identifier but use a single network interface. Similar to the way collect_md mode is used in IP tunnels. This patch attempts to enable different configuration mechanisms - such as ebpf programs, LWT encapsulations, and TC - to attach metadata to skbs which would carry the if_id. This way a single xfrm interface in collect_md mode can demux traffic based on this configuration on tx and provide this metadata on rx. The XFRM metadata is somewhat similar to ip tunnel metadata in that it has an "id", and shares similar configuration entities (bpf, tc, ...), however, it does not necessarily represent an IP tunnel or use other ip tunnel information, and also has an optional "link" property which can be used for affecting underlying routing decisions. Additional xfrm related criteria may also be added in the future. Therefore, a new metadata type is introduced, to be used in subsequent patches in the xfrm interface and configuration entities. Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org> Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: Eyal Birger <eyal.birger@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2022-08-26 14:46:58 +03:00
struct xfrm_md_info {
u32 if_id;
int link;
};
struct metadata_dst {
struct dst_entry dst;
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-23 23:11:58 +03:00
enum metadata_type type;
vxlan: Flow based tunneling Allows putting a VXLAN device into a new flow-based mode in which skbs with a ip_tunnel_info dst metadata attached will be encapsulated according to the instructions stored in there with the VXLAN device defaults taken into consideration. Similar on the receive side, if the VXLAN_F_COLLECT_METADATA flag is set, the packet processing will populate a ip_tunnel_info struct for each packet received and attach it to the skb using the new metadata dst. The metadata structure will contain the outer header and tunnel header fields which have been stripped off. Layers further up in the stack such as routing, tc or netfitler can later match on these fields and perform forwarding. It is the responsibility of upper layers to ensure that the flag is set if the metadata is needed. The flag limits the additional cost of metadata collecting based on demand. This prepares the VXLAN device to be steered by the routing and other subsystems which allows to support encapsulation for a large number of tunnel endpoints and tunnel ids through a single net_device which improves the scalability. It also allows for OVS to leverage this mode which in turn allows for the removal of the OVS specific VXLAN code. Because the skb is currently scrubed in vxlan_rcv(), the attachment of the new dst metadata is postponed until after scrubing which requires the temporary addition of a new member to vxlan_metadata. This member is removed again in a later commit after the indirect VXLAN receive API has been removed. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-21 11:43:58 +03:00
union {
struct ip_tunnel_info tun_info;
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-23 23:11:58 +03:00
struct hw_port_info port_info;
struct macsec_info macsec_info;
net: allow storing xfrm interface metadata in metadata_dst XFRM interfaces provide the association of various XFRM transformations to a netdevice using an 'if_id' identifier common to both the XFRM data structures (polcies, states) and the interface. The if_id is configured by the controlling entity (usually the IKE daemon) and can be used by the administrator to define logical relations between different connections. For example, different connections can share the if_id identifier so that they pass through the same interface, . However, currently it is not possible for connections using a different if_id to use the same interface while retaining the logical separation between them, without using additional criteria such as skb marks or different traffic selectors. When having a large number of connections, it is useful to have a the logical separation offered by the if_id identifier but use a single network interface. Similar to the way collect_md mode is used in IP tunnels. This patch attempts to enable different configuration mechanisms - such as ebpf programs, LWT encapsulations, and TC - to attach metadata to skbs which would carry the if_id. This way a single xfrm interface in collect_md mode can demux traffic based on this configuration on tx and provide this metadata on rx. The XFRM metadata is somewhat similar to ip tunnel metadata in that it has an "id", and shares similar configuration entities (bpf, tc, ...), however, it does not necessarily represent an IP tunnel or use other ip tunnel information, and also has an optional "link" property which can be used for affecting underlying routing decisions. Additional xfrm related criteria may also be added in the future. Therefore, a new metadata type is introduced, to be used in subsequent patches in the xfrm interface and configuration entities. Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org> Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: Eyal Birger <eyal.birger@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2022-08-26 14:46:58 +03:00
struct xfrm_md_info xfrm_info;
vxlan: Flow based tunneling Allows putting a VXLAN device into a new flow-based mode in which skbs with a ip_tunnel_info dst metadata attached will be encapsulated according to the instructions stored in there with the VXLAN device defaults taken into consideration. Similar on the receive side, if the VXLAN_F_COLLECT_METADATA flag is set, the packet processing will populate a ip_tunnel_info struct for each packet received and attach it to the skb using the new metadata dst. The metadata structure will contain the outer header and tunnel header fields which have been stripped off. Layers further up in the stack such as routing, tc or netfitler can later match on these fields and perform forwarding. It is the responsibility of upper layers to ensure that the flag is set if the metadata is needed. The flag limits the additional cost of metadata collecting based on demand. This prepares the VXLAN device to be steered by the routing and other subsystems which allows to support encapsulation for a large number of tunnel endpoints and tunnel ids through a single net_device which improves the scalability. It also allows for OVS to leverage this mode which in turn allows for the removal of the OVS specific VXLAN code. Because the skb is currently scrubed in vxlan_rcv(), the attachment of the new dst metadata is postponed until after scrubing which requires the temporary addition of a new member to vxlan_metadata. This member is removed again in a later commit after the indirect VXLAN receive API has been removed. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-21 11:43:58 +03:00
} u;
};
static inline struct metadata_dst *skb_metadata_dst(const struct sk_buff *skb)
{
struct metadata_dst *md_dst = (struct metadata_dst *) skb_dst(skb);
if (md_dst && md_dst->dst.flags & DST_METADATA)
return md_dst;
return NULL;
}
static inline struct ip_tunnel_info *
skb_tunnel_info(const struct sk_buff *skb)
vxlan: Flow based tunneling Allows putting a VXLAN device into a new flow-based mode in which skbs with a ip_tunnel_info dst metadata attached will be encapsulated according to the instructions stored in there with the VXLAN device defaults taken into consideration. Similar on the receive side, if the VXLAN_F_COLLECT_METADATA flag is set, the packet processing will populate a ip_tunnel_info struct for each packet received and attach it to the skb using the new metadata dst. The metadata structure will contain the outer header and tunnel header fields which have been stripped off. Layers further up in the stack such as routing, tc or netfitler can later match on these fields and perform forwarding. It is the responsibility of upper layers to ensure that the flag is set if the metadata is needed. The flag limits the additional cost of metadata collecting based on demand. This prepares the VXLAN device to be steered by the routing and other subsystems which allows to support encapsulation for a large number of tunnel endpoints and tunnel ids through a single net_device which improves the scalability. It also allows for OVS to leverage this mode which in turn allows for the removal of the OVS specific VXLAN code. Because the skb is currently scrubed in vxlan_rcv(), the attachment of the new dst metadata is postponed until after scrubing which requires the temporary addition of a new member to vxlan_metadata. This member is removed again in a later commit after the indirect VXLAN receive API has been removed. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-21 11:43:58 +03:00
{
struct metadata_dst *md_dst = skb_metadata_dst(skb);
struct dst_entry *dst;
vxlan: Flow based tunneling Allows putting a VXLAN device into a new flow-based mode in which skbs with a ip_tunnel_info dst metadata attached will be encapsulated according to the instructions stored in there with the VXLAN device defaults taken into consideration. Similar on the receive side, if the VXLAN_F_COLLECT_METADATA flag is set, the packet processing will populate a ip_tunnel_info struct for each packet received and attach it to the skb using the new metadata dst. The metadata structure will contain the outer header and tunnel header fields which have been stripped off. Layers further up in the stack such as routing, tc or netfitler can later match on these fields and perform forwarding. It is the responsibility of upper layers to ensure that the flag is set if the metadata is needed. The flag limits the additional cost of metadata collecting based on demand. This prepares the VXLAN device to be steered by the routing and other subsystems which allows to support encapsulation for a large number of tunnel endpoints and tunnel ids through a single net_device which improves the scalability. It also allows for OVS to leverage this mode which in turn allows for the removal of the OVS specific VXLAN code. Because the skb is currently scrubed in vxlan_rcv(), the attachment of the new dst metadata is postponed until after scrubing which requires the temporary addition of a new member to vxlan_metadata. This member is removed again in a later commit after the indirect VXLAN receive API has been removed. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-21 11:43:58 +03:00
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-23 23:11:58 +03:00
if (md_dst && md_dst->type == METADATA_IP_TUNNEL)
vxlan: Flow based tunneling Allows putting a VXLAN device into a new flow-based mode in which skbs with a ip_tunnel_info dst metadata attached will be encapsulated according to the instructions stored in there with the VXLAN device defaults taken into consideration. Similar on the receive side, if the VXLAN_F_COLLECT_METADATA flag is set, the packet processing will populate a ip_tunnel_info struct for each packet received and attach it to the skb using the new metadata dst. The metadata structure will contain the outer header and tunnel header fields which have been stripped off. Layers further up in the stack such as routing, tc or netfitler can later match on these fields and perform forwarding. It is the responsibility of upper layers to ensure that the flag is set if the metadata is needed. The flag limits the additional cost of metadata collecting based on demand. This prepares the VXLAN device to be steered by the routing and other subsystems which allows to support encapsulation for a large number of tunnel endpoints and tunnel ids through a single net_device which improves the scalability. It also allows for OVS to leverage this mode which in turn allows for the removal of the OVS specific VXLAN code. Because the skb is currently scrubed in vxlan_rcv(), the attachment of the new dst metadata is postponed until after scrubing which requires the temporary addition of a new member to vxlan_metadata. This member is removed again in a later commit after the indirect VXLAN receive API has been removed. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-21 11:43:58 +03:00
return &md_dst->u.tun_info;
dst = skb_dst(skb);
if (dst && dst->lwtstate &&
(dst->lwtstate->type == LWTUNNEL_ENCAP_IP ||
dst->lwtstate->type == LWTUNNEL_ENCAP_IP6))
return lwt_tun_info(dst->lwtstate);
vxlan: Flow based tunneling Allows putting a VXLAN device into a new flow-based mode in which skbs with a ip_tunnel_info dst metadata attached will be encapsulated according to the instructions stored in there with the VXLAN device defaults taken into consideration. Similar on the receive side, if the VXLAN_F_COLLECT_METADATA flag is set, the packet processing will populate a ip_tunnel_info struct for each packet received and attach it to the skb using the new metadata dst. The metadata structure will contain the outer header and tunnel header fields which have been stripped off. Layers further up in the stack such as routing, tc or netfitler can later match on these fields and perform forwarding. It is the responsibility of upper layers to ensure that the flag is set if the metadata is needed. The flag limits the additional cost of metadata collecting based on demand. This prepares the VXLAN device to be steered by the routing and other subsystems which allows to support encapsulation for a large number of tunnel endpoints and tunnel ids through a single net_device which improves the scalability. It also allows for OVS to leverage this mode which in turn allows for the removal of the OVS specific VXLAN code. Because the skb is currently scrubed in vxlan_rcv(), the attachment of the new dst metadata is postponed until after scrubing which requires the temporary addition of a new member to vxlan_metadata. This member is removed again in a later commit after the indirect VXLAN receive API has been removed. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-21 11:43:58 +03:00
return NULL;
}
static inline struct xfrm_md_info *lwt_xfrm_info(struct lwtunnel_state *lwt)
{
return (struct xfrm_md_info *)lwt->data;
}
net: allow storing xfrm interface metadata in metadata_dst XFRM interfaces provide the association of various XFRM transformations to a netdevice using an 'if_id' identifier common to both the XFRM data structures (polcies, states) and the interface. The if_id is configured by the controlling entity (usually the IKE daemon) and can be used by the administrator to define logical relations between different connections. For example, different connections can share the if_id identifier so that they pass through the same interface, . However, currently it is not possible for connections using a different if_id to use the same interface while retaining the logical separation between them, without using additional criteria such as skb marks or different traffic selectors. When having a large number of connections, it is useful to have a the logical separation offered by the if_id identifier but use a single network interface. Similar to the way collect_md mode is used in IP tunnels. This patch attempts to enable different configuration mechanisms - such as ebpf programs, LWT encapsulations, and TC - to attach metadata to skbs which would carry the if_id. This way a single xfrm interface in collect_md mode can demux traffic based on this configuration on tx and provide this metadata on rx. The XFRM metadata is somewhat similar to ip tunnel metadata in that it has an "id", and shares similar configuration entities (bpf, tc, ...), however, it does not necessarily represent an IP tunnel or use other ip tunnel information, and also has an optional "link" property which can be used for affecting underlying routing decisions. Additional xfrm related criteria may also be added in the future. Therefore, a new metadata type is introduced, to be used in subsequent patches in the xfrm interface and configuration entities. Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org> Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: Eyal Birger <eyal.birger@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2022-08-26 14:46:58 +03:00
static inline struct xfrm_md_info *skb_xfrm_md_info(const struct sk_buff *skb)
{
struct metadata_dst *md_dst = skb_metadata_dst(skb);
struct dst_entry *dst;
net: allow storing xfrm interface metadata in metadata_dst XFRM interfaces provide the association of various XFRM transformations to a netdevice using an 'if_id' identifier common to both the XFRM data structures (polcies, states) and the interface. The if_id is configured by the controlling entity (usually the IKE daemon) and can be used by the administrator to define logical relations between different connections. For example, different connections can share the if_id identifier so that they pass through the same interface, . However, currently it is not possible for connections using a different if_id to use the same interface while retaining the logical separation between them, without using additional criteria such as skb marks or different traffic selectors. When having a large number of connections, it is useful to have a the logical separation offered by the if_id identifier but use a single network interface. Similar to the way collect_md mode is used in IP tunnels. This patch attempts to enable different configuration mechanisms - such as ebpf programs, LWT encapsulations, and TC - to attach metadata to skbs which would carry the if_id. This way a single xfrm interface in collect_md mode can demux traffic based on this configuration on tx and provide this metadata on rx. The XFRM metadata is somewhat similar to ip tunnel metadata in that it has an "id", and shares similar configuration entities (bpf, tc, ...), however, it does not necessarily represent an IP tunnel or use other ip tunnel information, and also has an optional "link" property which can be used for affecting underlying routing decisions. Additional xfrm related criteria may also be added in the future. Therefore, a new metadata type is introduced, to be used in subsequent patches in the xfrm interface and configuration entities. Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org> Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: Eyal Birger <eyal.birger@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2022-08-26 14:46:58 +03:00
if (md_dst && md_dst->type == METADATA_XFRM)
return &md_dst->u.xfrm_info;
dst = skb_dst(skb);
if (dst && dst->lwtstate &&
dst->lwtstate->type == LWTUNNEL_ENCAP_XFRM)
return lwt_xfrm_info(dst->lwtstate);
net: allow storing xfrm interface metadata in metadata_dst XFRM interfaces provide the association of various XFRM transformations to a netdevice using an 'if_id' identifier common to both the XFRM data structures (polcies, states) and the interface. The if_id is configured by the controlling entity (usually the IKE daemon) and can be used by the administrator to define logical relations between different connections. For example, different connections can share the if_id identifier so that they pass through the same interface, . However, currently it is not possible for connections using a different if_id to use the same interface while retaining the logical separation between them, without using additional criteria such as skb marks or different traffic selectors. When having a large number of connections, it is useful to have a the logical separation offered by the if_id identifier but use a single network interface. Similar to the way collect_md mode is used in IP tunnels. This patch attempts to enable different configuration mechanisms - such as ebpf programs, LWT encapsulations, and TC - to attach metadata to skbs which would carry the if_id. This way a single xfrm interface in collect_md mode can demux traffic based on this configuration on tx and provide this metadata on rx. The XFRM metadata is somewhat similar to ip tunnel metadata in that it has an "id", and shares similar configuration entities (bpf, tc, ...), however, it does not necessarily represent an IP tunnel or use other ip tunnel information, and also has an optional "link" property which can be used for affecting underlying routing decisions. Additional xfrm related criteria may also be added in the future. Therefore, a new metadata type is introduced, to be used in subsequent patches in the xfrm interface and configuration entities. Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org> Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: Eyal Birger <eyal.birger@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2022-08-26 14:46:58 +03:00
return NULL;
}
static inline bool skb_valid_dst(const struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
return dst && !(dst->flags & DST_METADATA);
}
static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a,
const struct sk_buff *skb_b)
{
const struct metadata_dst *a, *b;
if (!(skb_a->_skb_refdst | skb_b->_skb_refdst))
return 0;
a = (const struct metadata_dst *) skb_dst(skb_a);
b = (const struct metadata_dst *) skb_dst(skb_b);
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-23 23:11:58 +03:00
if (!a != !b || a->type != b->type)
return 1;
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-23 23:11:58 +03:00
switch (a->type) {
case METADATA_HW_PORT_MUX:
return memcmp(&a->u.port_info, &b->u.port_info,
sizeof(a->u.port_info));
case METADATA_IP_TUNNEL:
return memcmp(&a->u.tun_info, &b->u.tun_info,
sizeof(a->u.tun_info) +
a->u.tun_info.options_len);
case METADATA_MACSEC:
return memcmp(&a->u.macsec_info, &b->u.macsec_info,
sizeof(a->u.macsec_info));
net: allow storing xfrm interface metadata in metadata_dst XFRM interfaces provide the association of various XFRM transformations to a netdevice using an 'if_id' identifier common to both the XFRM data structures (polcies, states) and the interface. The if_id is configured by the controlling entity (usually the IKE daemon) and can be used by the administrator to define logical relations between different connections. For example, different connections can share the if_id identifier so that they pass through the same interface, . However, currently it is not possible for connections using a different if_id to use the same interface while retaining the logical separation between them, without using additional criteria such as skb marks or different traffic selectors. When having a large number of connections, it is useful to have a the logical separation offered by the if_id identifier but use a single network interface. Similar to the way collect_md mode is used in IP tunnels. This patch attempts to enable different configuration mechanisms - such as ebpf programs, LWT encapsulations, and TC - to attach metadata to skbs which would carry the if_id. This way a single xfrm interface in collect_md mode can demux traffic based on this configuration on tx and provide this metadata on rx. The XFRM metadata is somewhat similar to ip tunnel metadata in that it has an "id", and shares similar configuration entities (bpf, tc, ...), however, it does not necessarily represent an IP tunnel or use other ip tunnel information, and also has an optional "link" property which can be used for affecting underlying routing decisions. Additional xfrm related criteria may also be added in the future. Therefore, a new metadata type is introduced, to be used in subsequent patches in the xfrm interface and configuration entities. Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org> Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Signed-off-by: Eyal Birger <eyal.birger@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2022-08-26 14:46:58 +03:00
case METADATA_XFRM:
return memcmp(&a->u.xfrm_info, &b->u.xfrm_info,
sizeof(a->u.xfrm_info));
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-23 23:11:58 +03:00
default:
return 1;
}
}
void metadata_dst_free(struct metadata_dst *);
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-23 23:11:58 +03:00
struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type,
gfp_t flags);
void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst);
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-23 23:11:58 +03:00
struct metadata_dst __percpu *
metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags);
static inline struct metadata_dst *tun_rx_dst(int md_size)
{
struct metadata_dst *tun_dst;
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-23 23:11:58 +03:00
tun_dst = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC);
if (!tun_dst)
return NULL;
tun_dst->u.tun_info.options_len = 0;
tun_dst->u.tun_info.mode = 0;
return tun_dst;
}
static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb)
{
struct metadata_dst *md_dst = skb_metadata_dst(skb);
int md_size;
struct metadata_dst *new_md;
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-23 23:11:58 +03:00
if (!md_dst || md_dst->type != METADATA_IP_TUNNEL)
return ERR_PTR(-EINVAL);
md_size = md_dst->u.tun_info.options_len;
net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com> Signed-off-by: Simon Horman <horms@verge.net.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-06-23 23:11:58 +03:00
new_md = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC);
if (!new_md)
return ERR_PTR(-ENOMEM);
memcpy(&new_md->u.tun_info, &md_dst->u.tun_info,
sizeof(struct ip_tunnel_info) + md_size);
#ifdef CONFIG_DST_CACHE
/* Unclone the dst cache if there is one */
if (new_md->u.tun_info.dst_cache.cache) {
int ret;
ret = dst_cache_init(&new_md->u.tun_info.dst_cache, GFP_ATOMIC);
if (ret) {
metadata_dst_free(new_md);
return ERR_PTR(ret);
}
}
#endif
skb_dst_drop(skb);
skb_dst_set(skb, &new_md->dst);
return new_md;
}
static inline struct ip_tunnel_info *skb_tunnel_info_unclone(struct sk_buff *skb)
{
struct metadata_dst *dst;
dst = tun_dst_unclone(skb);
if (IS_ERR(dst))
return NULL;
return &dst->u.tun_info;
}
static inline struct metadata_dst *__ip_tun_set_dst(__be32 saddr,
__be32 daddr,
__u8 tos, __u8 ttl,
__be16 tp_dst,
__be16 flags,
__be64 tunnel_id,
int md_size)
{
struct metadata_dst *tun_dst;
tun_dst = tun_rx_dst(md_size);
if (!tun_dst)
return NULL;
ip_tunnel_key_init(&tun_dst->u.tun_info.key,
saddr, daddr, tos, ttl,
0, 0, tp_dst, tunnel_id, flags);
return tun_dst;
}
static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb,
__be16 flags,
__be64 tunnel_id,
int md_size)
{
const struct iphdr *iph = ip_hdr(skb);
return __ip_tun_set_dst(iph->saddr, iph->daddr, iph->tos, iph->ttl,
0, flags, tunnel_id, md_size);
}
static inline struct metadata_dst *__ipv6_tun_set_dst(const struct in6_addr *saddr,
const struct in6_addr *daddr,
__u8 tos, __u8 ttl,
__be16 tp_dst,
__be32 label,
__be16 flags,
__be64 tunnel_id,
int md_size)
{
struct metadata_dst *tun_dst;
struct ip_tunnel_info *info;
tun_dst = tun_rx_dst(md_size);
if (!tun_dst)
return NULL;
info = &tun_dst->u.tun_info;
info->mode = IP_TUNNEL_INFO_IPV6;
info->key.tun_flags = flags;
info->key.tun_id = tunnel_id;
info->key.tp_src = 0;
info->key.tp_dst = tp_dst;
info->key.u.ipv6.src = *saddr;
info->key.u.ipv6.dst = *daddr;
info->key.tos = tos;
info->key.ttl = ttl;
info->key.label = label;
return tun_dst;
}
static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb,
__be16 flags,
__be64 tunnel_id,
int md_size)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
return __ipv6_tun_set_dst(&ip6h->saddr, &ip6h->daddr,
ipv6_get_dsfield(ip6h), ip6h->hop_limit,
0, ip6_flowlabel(ip6h), flags, tunnel_id,
md_size);
}
#endif /* __NET_DST_METADATA_H */