linux/net/openvswitch/actions.c

1546 lines
38 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2007-2017 Nicira, Inc.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/skbuff.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/openvswitch.h>
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
#include <linux/netfilter_ipv6.h>
#include <linux/sctp.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/in6.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
#include <net/dst.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/checksum.h>
#include <net/dsfield.h>
#include <net/mpls.h>
#include <net/sctp/checksum.h>
#include "datapath.h"
#include "flow.h"
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
#include "conntrack.h"
#include "vport.h"
openvswitch: enable NSH support v16->17 - Fixed disputed check code: keep them in nsh_push and nsh_pop but also add them in __ovs_nla_copy_actions v15->v16 - Add csum recalculation for nsh_push, nsh_pop and set_nsh pointed out by Pravin - Move nsh key into the union with ipv4 and ipv6 and add check for nsh key in match_validate pointed out by Pravin - Add nsh check in validate_set and __ovs_nla_copy_actions v14->v15 - Check size in nsh_hdr_from_nlattr - Fixed four small issues pointed out By Jiri and Eric v13->v14 - Rename skb_push_nsh to nsh_push per Dave's comment - Rename skb_pop_nsh to nsh_pop per Dave's comment v12->v13 - Fix NSH header length check in set_nsh v11->v12 - Fix missing changes old comments pointed out - Fix new comments for v11 v10->v11 - Fix the left three disputable comments for v9 but not fixed in v10. v9->v10 - Change struct ovs_key_nsh to struct ovs_nsh_key_base base; __be32 context[NSH_MD1_CONTEXT_SIZE]; - Fix new comments for v9 v8->v9 - Fix build error reported by daily intel build because nsh module isn't selected by openvswitch v7->v8 - Rework nested value and mask for OVS_KEY_ATTR_NSH - Change pop_nsh to adapt to nsh kernel module - Fix many issues per comments from Jiri Benc v6->v7 - Remove NSH GSO patches in v6 because Jiri Benc reworked it as another patch series and they have been merged. - Change it to adapt to nsh kernel module added by NSH GSO patch series v5->v6 - Fix the rest comments for v4. - Add NSH GSO support for VxLAN-gpe + NSH and Eth + NSH. v4->v5 - Fix many comments by Jiri Benc and Eric Garver for v4. v3->v4 - Add new NSH match field ttl - Update NSH header to the latest format which will be final format and won't change per its author's confirmation. - Fix comments for v3. v2->v3 - Change OVS_KEY_ATTR_NSH to nested key to handle length-fixed attributes and length-variable attriubte more flexibly. - Remove struct ovs_action_push_nsh completely - Add code to handle nested attribute for SET_MASKED - Change PUSH_NSH to use the nested OVS_KEY_ATTR_NSH to transfer NSH header data. - Fix comments and coding style issues by Jiri and Eric v1->v2 - Change encap_nsh and decap_nsh to push_nsh and pop_nsh - Dynamically allocate struct ovs_action_push_nsh for length-variable metadata. OVS master and 2.8 branch has merged NSH userspace patch series, this patch is to enable NSH support in kernel data path in order that OVS can support NSH in compat mode by porting this. Signed-off-by: Yi Yang <yi.y.yang@intel.com> Acked-by: Jiri Benc <jbenc@redhat.com> Acked-by: Eric Garver <e@erig.me> Acked-by: Pravin Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-07 21:07:02 +08:00
#include "flow_netlink.h"
struct deferred_action {
struct sk_buff *skb;
const struct nlattr *actions;
int actions_len;
/* Store pkt_key clone when creating deferred action. */
struct sw_flow_key pkt_key;
};
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
#define MAX_L2_LEN (VLAN_ETH_HLEN + 3 * MPLS_HLEN)
struct ovs_frag_data {
unsigned long dst;
struct vport *vport;
struct ovs_skb_cb cb;
__be16 inner_protocol;
u16 network_offset; /* valid only for MPLS */
u16 vlan_tci;
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
__be16 vlan_proto;
unsigned int l2_len;
u8 mac_proto;
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
u8 l2_data[MAX_L2_LEN];
};
static DEFINE_PER_CPU(struct ovs_frag_data, ovs_frag_data_storage);
#define DEFERRED_ACTION_FIFO_SIZE 10
#define OVS_RECURSION_LIMIT 5
#define OVS_DEFERRED_ACTION_THRESHOLD (OVS_RECURSION_LIMIT - 2)
struct action_fifo {
int head;
int tail;
/* Deferred action fifo queue storage. */
struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
};
struct action_flow_keys {
struct sw_flow_key key[OVS_DEFERRED_ACTION_THRESHOLD];
};
static struct action_fifo __percpu *action_fifos;
static struct action_flow_keys __percpu *flow_keys;
static DEFINE_PER_CPU(int, exec_actions_level);
/* Make a clone of the 'key', using the pre-allocated percpu 'flow_keys'
* space. Return NULL if out of key spaces.
*/
static struct sw_flow_key *clone_key(const struct sw_flow_key *key_)
{
struct action_flow_keys *keys = this_cpu_ptr(flow_keys);
int level = this_cpu_read(exec_actions_level);
struct sw_flow_key *key = NULL;
if (level <= OVS_DEFERRED_ACTION_THRESHOLD) {
key = &keys->key[level - 1];
*key = *key_;
}
return key;
}
static void action_fifo_init(struct action_fifo *fifo)
{
fifo->head = 0;
fifo->tail = 0;
}
static bool action_fifo_is_empty(const struct action_fifo *fifo)
{
return (fifo->head == fifo->tail);
}
static struct deferred_action *action_fifo_get(struct action_fifo *fifo)
{
if (action_fifo_is_empty(fifo))
return NULL;
return &fifo->fifo[fifo->tail++];
}
static struct deferred_action *action_fifo_put(struct action_fifo *fifo)
{
if (fifo->head >= DEFERRED_ACTION_FIFO_SIZE - 1)
return NULL;
return &fifo->fifo[fifo->head++];
}
/* Return true if fifo is not full */
static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
const struct sw_flow_key *key,
const struct nlattr *actions,
const int actions_len)
{
struct action_fifo *fifo;
struct deferred_action *da;
fifo = this_cpu_ptr(action_fifos);
da = action_fifo_put(fifo);
if (da) {
da->skb = skb;
da->actions = actions;
da->actions_len = actions_len;
da->pkt_key = *key;
}
return da;
}
static void invalidate_flow_key(struct sw_flow_key *key)
{
key->mac_proto |= SW_FLOW_KEY_INVALID;
}
static bool is_flow_key_valid(const struct sw_flow_key *key)
{
return !(key->mac_proto & SW_FLOW_KEY_INVALID);
}
static int clone_execute(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key,
u32 recirc_id,
const struct nlattr *actions, int len,
bool last, bool clone_flow_key);
net: openvswitch: Add a new action check_pkt_len This patch adds a new action - 'check_pkt_len' which checks the packet length and executes a set of actions if the packet length is greater than the specified length or executes another set of actions if the packet length is lesser or equal to. This action takes below nlattrs * OVS_CHECK_PKT_LEN_ATTR_PKT_LEN - 'pkt_len' to check for * OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER - Nested actions to apply if the packet length is greater than the specified 'pkt_len' * OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL - Nested actions to apply if the packet length is lesser or equal to the specified 'pkt_len'. The main use case for adding this action is to solve the packet drops because of MTU mismatch in OVN virtual networking solution. When a VM (which belongs to a logical switch of OVN) sends a packet destined to go via the gateway router and if the nic which provides external connectivity, has a lesser MTU, OVS drops the packet if the packet length is greater than this MTU. With the help of this action, OVN will check the packet length and if it is greater than the MTU size, it will generate an ICMP packet (type 3, code 4) and includes the next hop mtu in it so that the sender can fragment the packets. Reported-at: https://mail.openvswitch.org/pipermail/ovs-discuss/2018-July/047039.html Suggested-by: Ben Pfaff <blp@ovn.org> Signed-off-by: Numan Siddique <nusiddiq@redhat.com> CC: Gregory Rose <gvrose8192@gmail.com> CC: Pravin B Shelar <pshelar@ovn.org> Acked-by: Pravin B Shelar <pshelar@ovn.org> Tested-by: Greg Rose <gvrose8192@gmail.com> Reviewed-by: Greg Rose <gvrose8192@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-26 08:43:46 +08:00
static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key,
const struct nlattr *attr, int len);
static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
__be16 ethertype)
{
if (skb->ip_summed == CHECKSUM_COMPLETE) {
__be16 diff[] = { ~(hdr->h_proto), ethertype };
net: openvswitch: fix csum updates for MPLS actions Skbs may have their checksum value populated by HW. If this is a checksum calculated over the entire packet then the CHECKSUM_COMPLETE field is marked. Changes to the data pointer on the skb throughout the network stack still try to maintain this complete csum value if it is required through functions such as skb_postpush_rcsum. The MPLS actions in Open vSwitch modify a CHECKSUM_COMPLETE value when changes are made to packet data without a push or a pull. This occurs when the ethertype of the MAC header is changed or when MPLS lse fields are modified. The modification is carried out using the csum_partial function to get the csum of a buffer and add it into the larger checksum. The buffer is an inversion of the data to be removed followed by the new data. Because the csum is calculated over 16 bits and these values align with 16 bits, the effect is the removal of the old value from the CHECKSUM_COMPLETE and addition of the new value. However, the csum fed into the function and the outcome of the calculation are also inverted. This would only make sense if it was the new value rather than the old that was inverted in the input buffer. Fix the issue by removing the bit inverts in the csum_partial calculation. The bug was verified and the fix tested by comparing the folded value of the updated CHECKSUM_COMPLETE value with the folded value of a full software checksum calculation (reset skb->csum to 0 and run skb_checksum_complete(skb)). Prior to the fix the outcomes differed but after they produce the same result. Fixes: 25cd9ba0abc0 ("openvswitch: Add basic MPLS support to kernel") Fixes: bc7cc5999fd3 ("openvswitch: update checksum in {push,pop}_mpls") Signed-off-by: John Hurley <john.hurley@netronome.com> Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com> Reviewed-by: Simon Horman <simon.horman@netronome.com> Acked-by: Pravin B Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-27 21:37:30 +08:00
skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
}
hdr->h_proto = ethertype;
}
static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
const struct ovs_action_push_mpls *mpls)
{
int err;
err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype);
if (err)
return err;
invalidate_flow_key(key);
return 0;
}
static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
const __be16 ethertype)
{
int err;
err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
skb->mac_len);
__skb_pull(skb, MPLS_HLEN);
skb_reset_mac_header(skb);
net: mpls: Fixups for GSO As reported by Lennert the MPLS GSO code is failing to properly segment large packets. There are a couple of problems: 1. the inner protocol is not set so the gso segment functions for inner protocol layers are not getting run, and 2 MPLS labels for packets that use the "native" (non-OVS) MPLS code are not properly accounted for in mpls_gso_segment. The MPLS GSO code was added for OVS. It is re-using skb_mac_gso_segment to call the gso segment functions for the higher layer protocols. That means skb_mac_gso_segment is called twice -- once with the network protocol set to MPLS and again with the network protocol set to the inner protocol. This patch sets the inner skb protocol addressing item 1 above and sets the network_header and inner_network_header to mark where the MPLS labels start and end. The MPLS code in OVS is also updated to set the two network markers. >From there the MPLS GSO code uses the difference between the network header and the inner network header to know the size of the MPLS header that was pushed. It then pulls the MPLS header, resets the mac_len and protocol for the inner protocol and then calls skb_mac_gso_segment to segment the skb. Afterward the inner protocol segmentation is done the skb protocol is set to mpls for each segment and the network and mac headers restored. Reported-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-25 11:10:44 +08:00
skb_set_network_header(skb, skb->mac_len);
if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET) {
struct ethhdr *hdr;
/* mpls_hdr() is used to locate the ethertype field correctly in the
* presence of VLAN tags.
*/
hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
update_ethertype(skb, hdr, ethertype);
}
if (eth_p_mpls(skb->protocol))
skb->protocol = ethertype;
invalidate_flow_key(key);
return 0;
}
static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
const __be32 *mpls_lse, const __be32 *mask)
{
struct mpls_shim_hdr *stack;
__be32 lse;
int err;
err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
if (unlikely(err))
return err;
stack = mpls_hdr(skb);
lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask);
if (skb->ip_summed == CHECKSUM_COMPLETE) {
__be32 diff[] = { ~(stack->label_stack_entry), lse };
net: openvswitch: fix csum updates for MPLS actions Skbs may have their checksum value populated by HW. If this is a checksum calculated over the entire packet then the CHECKSUM_COMPLETE field is marked. Changes to the data pointer on the skb throughout the network stack still try to maintain this complete csum value if it is required through functions such as skb_postpush_rcsum. The MPLS actions in Open vSwitch modify a CHECKSUM_COMPLETE value when changes are made to packet data without a push or a pull. This occurs when the ethertype of the MAC header is changed or when MPLS lse fields are modified. The modification is carried out using the csum_partial function to get the csum of a buffer and add it into the larger checksum. The buffer is an inversion of the data to be removed followed by the new data. Because the csum is calculated over 16 bits and these values align with 16 bits, the effect is the removal of the old value from the CHECKSUM_COMPLETE and addition of the new value. However, the csum fed into the function and the outcome of the calculation are also inverted. This would only make sense if it was the new value rather than the old that was inverted in the input buffer. Fix the issue by removing the bit inverts in the csum_partial calculation. The bug was verified and the fix tested by comparing the folded value of the updated CHECKSUM_COMPLETE value with the folded value of a full software checksum calculation (reset skb->csum to 0 and run skb_checksum_complete(skb)). Prior to the fix the outcomes differed but after they produce the same result. Fixes: 25cd9ba0abc0 ("openvswitch: Add basic MPLS support to kernel") Fixes: bc7cc5999fd3 ("openvswitch: update checksum in {push,pop}_mpls") Signed-off-by: John Hurley <john.hurley@netronome.com> Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com> Reviewed-by: Simon Horman <simon.horman@netronome.com> Acked-by: Pravin B Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-27 21:37:30 +08:00
skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
}
stack->label_stack_entry = lse;
flow_key->mpls.top_lse = lse;
return 0;
}
static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key)
{
int err;
err = skb_vlan_pop(skb);
if (skb_vlan_tag_present(skb)) {
invalidate_flow_key(key);
} else {
key->eth.vlan.tci = 0;
key->eth.vlan.tpid = 0;
}
return err;
}
static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
const struct ovs_action_push_vlan *vlan)
{
if (skb_vlan_tag_present(skb)) {
invalidate_flow_key(key);
} else {
key->eth.vlan.tci = vlan->vlan_tci;
key->eth.vlan.tpid = vlan->vlan_tpid;
}
return skb_vlan_push(skb, vlan->vlan_tpid,
ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK);
}
/* 'src' is already properly masked. */
static void ether_addr_copy_masked(u8 *dst_, const u8 *src_, const u8 *mask_)
{
u16 *dst = (u16 *)dst_;
const u16 *src = (const u16 *)src_;
const u16 *mask = (const u16 *)mask_;
OVS_SET_MASKED(dst[0], src[0], mask[0]);
OVS_SET_MASKED(dst[1], src[1], mask[1]);
OVS_SET_MASKED(dst[2], src[2], mask[2]);
}
static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_ethernet *key,
const struct ovs_key_ethernet *mask)
{
int err;
err = skb_ensure_writable(skb, ETH_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
ether_addr_copy_masked(eth_hdr(skb)->h_source, key->eth_src,
mask->eth_src);
ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst,
mask->eth_dst);
skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
ether_addr_copy(flow_key->eth.src, eth_hdr(skb)->h_source);
ether_addr_copy(flow_key->eth.dst, eth_hdr(skb)->h_dest);
return 0;
}
/* pop_eth does not support VLAN packets as this action is never called
* for them.
*/
static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
{
skb_pull_rcsum(skb, ETH_HLEN);
skb_reset_mac_header(skb);
skb_reset_mac_len(skb);
/* safe right before invalidate_flow_key */
key->mac_proto = MAC_PROTO_NONE;
invalidate_flow_key(key);
return 0;
}
static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
const struct ovs_action_push_eth *ethh)
{
struct ethhdr *hdr;
/* Add the new Ethernet header */
if (skb_cow_head(skb, ETH_HLEN) < 0)
return -ENOMEM;
skb_push(skb, ETH_HLEN);
skb_reset_mac_header(skb);
skb_reset_mac_len(skb);
hdr = eth_hdr(skb);
ether_addr_copy(hdr->h_source, ethh->addresses.eth_src);
ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst);
hdr->h_proto = skb->protocol;
skb_postpush_rcsum(skb, hdr, ETH_HLEN);
/* safe right before invalidate_flow_key */
key->mac_proto = MAC_PROTO_ETHERNET;
invalidate_flow_key(key);
return 0;
}
openvswitch: enable NSH support v16->17 - Fixed disputed check code: keep them in nsh_push and nsh_pop but also add them in __ovs_nla_copy_actions v15->v16 - Add csum recalculation for nsh_push, nsh_pop and set_nsh pointed out by Pravin - Move nsh key into the union with ipv4 and ipv6 and add check for nsh key in match_validate pointed out by Pravin - Add nsh check in validate_set and __ovs_nla_copy_actions v14->v15 - Check size in nsh_hdr_from_nlattr - Fixed four small issues pointed out By Jiri and Eric v13->v14 - Rename skb_push_nsh to nsh_push per Dave's comment - Rename skb_pop_nsh to nsh_pop per Dave's comment v12->v13 - Fix NSH header length check in set_nsh v11->v12 - Fix missing changes old comments pointed out - Fix new comments for v11 v10->v11 - Fix the left three disputable comments for v9 but not fixed in v10. v9->v10 - Change struct ovs_key_nsh to struct ovs_nsh_key_base base; __be32 context[NSH_MD1_CONTEXT_SIZE]; - Fix new comments for v9 v8->v9 - Fix build error reported by daily intel build because nsh module isn't selected by openvswitch v7->v8 - Rework nested value and mask for OVS_KEY_ATTR_NSH - Change pop_nsh to adapt to nsh kernel module - Fix many issues per comments from Jiri Benc v6->v7 - Remove NSH GSO patches in v6 because Jiri Benc reworked it as another patch series and they have been merged. - Change it to adapt to nsh kernel module added by NSH GSO patch series v5->v6 - Fix the rest comments for v4. - Add NSH GSO support for VxLAN-gpe + NSH and Eth + NSH. v4->v5 - Fix many comments by Jiri Benc and Eric Garver for v4. v3->v4 - Add new NSH match field ttl - Update NSH header to the latest format which will be final format and won't change per its author's confirmation. - Fix comments for v3. v2->v3 - Change OVS_KEY_ATTR_NSH to nested key to handle length-fixed attributes and length-variable attriubte more flexibly. - Remove struct ovs_action_push_nsh completely - Add code to handle nested attribute for SET_MASKED - Change PUSH_NSH to use the nested OVS_KEY_ATTR_NSH to transfer NSH header data. - Fix comments and coding style issues by Jiri and Eric v1->v2 - Change encap_nsh and decap_nsh to push_nsh and pop_nsh - Dynamically allocate struct ovs_action_push_nsh for length-variable metadata. OVS master and 2.8 branch has merged NSH userspace patch series, this patch is to enable NSH support in kernel data path in order that OVS can support NSH in compat mode by porting this. Signed-off-by: Yi Yang <yi.y.yang@intel.com> Acked-by: Jiri Benc <jbenc@redhat.com> Acked-by: Eric Garver <e@erig.me> Acked-by: Pravin Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-07 21:07:02 +08:00
static int push_nsh(struct sk_buff *skb, struct sw_flow_key *key,
const struct nshhdr *nh)
{
int err;
err = nsh_push(skb, nh);
if (err)
return err;
/* safe right before invalidate_flow_key */
key->mac_proto = MAC_PROTO_NONE;
invalidate_flow_key(key);
return 0;
}
static int pop_nsh(struct sk_buff *skb, struct sw_flow_key *key)
{
int err;
err = nsh_pop(skb);
if (err)
return err;
/* safe right before invalidate_flow_key */
if (skb->protocol == htons(ETH_P_TEB))
key->mac_proto = MAC_PROTO_ETHERNET;
else
key->mac_proto = MAC_PROTO_NONE;
invalidate_flow_key(key);
return 0;
}
static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh,
__be32 addr, __be32 new_addr)
{
int transport_len = skb->len - skb_transport_offset(skb);
if (nh->frag_off & htons(IP_OFFSET))
return;
if (nh->protocol == IPPROTO_TCP) {
if (likely(transport_len >= sizeof(struct tcphdr)))
inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,
addr, new_addr, true);
} else if (nh->protocol == IPPROTO_UDP) {
if (likely(transport_len >= sizeof(struct udphdr))) {
struct udphdr *uh = udp_hdr(skb);
if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
inet_proto_csum_replace4(&uh->check, skb,
addr, new_addr, true);
if (!uh->check)
uh->check = CSUM_MANGLED_0;
}
}
}
}
static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
__be32 *addr, __be32 new_addr)
{
update_ip_l4_checksum(skb, nh, *addr, new_addr);
csum_replace4(&nh->check, *addr, new_addr);
skb_clear_hash(skb);
*addr = new_addr;
}
static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto,
__be32 addr[4], const __be32 new_addr[4])
{
int transport_len = skb->len - skb_transport_offset(skb);
if (l4_proto == NEXTHDR_TCP) {
if (likely(transport_len >= sizeof(struct tcphdr)))
inet_proto_csum_replace16(&tcp_hdr(skb)->check, skb,
addr, new_addr, true);
} else if (l4_proto == NEXTHDR_UDP) {
if (likely(transport_len >= sizeof(struct udphdr))) {
struct udphdr *uh = udp_hdr(skb);
if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
inet_proto_csum_replace16(&uh->check, skb,
addr, new_addr, true);
if (!uh->check)
uh->check = CSUM_MANGLED_0;
}
}
} else if (l4_proto == NEXTHDR_ICMP) {
if (likely(transport_len >= sizeof(struct icmp6hdr)))
inet_proto_csum_replace16(&icmp6_hdr(skb)->icmp6_cksum,
skb, addr, new_addr, true);
}
}
static void mask_ipv6_addr(const __be32 old[4], const __be32 addr[4],
const __be32 mask[4], __be32 masked[4])
{
masked[0] = OVS_MASKED(old[0], addr[0], mask[0]);
masked[1] = OVS_MASKED(old[1], addr[1], mask[1]);
masked[2] = OVS_MASKED(old[2], addr[2], mask[2]);
masked[3] = OVS_MASKED(old[3], addr[3], mask[3]);
}
static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
__be32 addr[4], const __be32 new_addr[4],
bool recalculate_csum)
{
if (recalculate_csum)
update_ipv6_checksum(skb, l4_proto, addr, new_addr);
skb_clear_hash(skb);
memcpy(addr, new_addr, sizeof(__be32[4]));
}
static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask)
{
/* Bits 21-24 are always unmasked, so this retains their values. */
OVS_SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16));
OVS_SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8));
OVS_SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask);
}
static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl,
u8 mask)
{
new_ttl = OVS_MASKED(nh->ttl, new_ttl, mask);
csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8));
nh->ttl = new_ttl;
}
static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_ipv4 *key,
const struct ovs_key_ipv4 *mask)
{
struct iphdr *nh;
__be32 new_addr;
int err;
err = skb_ensure_writable(skb, skb_network_offset(skb) +
sizeof(struct iphdr));
if (unlikely(err))
return err;
nh = ip_hdr(skb);
/* Setting an IP addresses is typically only a side effect of
* matching on them in the current userspace implementation, so it
* makes sense to check if the value actually changed.
*/
if (mask->ipv4_src) {
new_addr = OVS_MASKED(nh->saddr, key->ipv4_src, mask->ipv4_src);
if (unlikely(new_addr != nh->saddr)) {
set_ip_addr(skb, nh, &nh->saddr, new_addr);
flow_key->ipv4.addr.src = new_addr;
}
}
if (mask->ipv4_dst) {
new_addr = OVS_MASKED(nh->daddr, key->ipv4_dst, mask->ipv4_dst);
if (unlikely(new_addr != nh->daddr)) {
set_ip_addr(skb, nh, &nh->daddr, new_addr);
flow_key->ipv4.addr.dst = new_addr;
}
}
if (mask->ipv4_tos) {
ipv4_change_dsfield(nh, ~mask->ipv4_tos, key->ipv4_tos);
flow_key->ip.tos = nh->tos;
}
if (mask->ipv4_ttl) {
set_ip_ttl(skb, nh, key->ipv4_ttl, mask->ipv4_ttl);
flow_key->ip.ttl = nh->ttl;
}
return 0;
}
static bool is_ipv6_mask_nonzero(const __be32 addr[4])
{
return !!(addr[0] | addr[1] | addr[2] | addr[3]);
}
static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_ipv6 *key,
const struct ovs_key_ipv6 *mask)
{
struct ipv6hdr *nh;
int err;
err = skb_ensure_writable(skb, skb_network_offset(skb) +
sizeof(struct ipv6hdr));
if (unlikely(err))
return err;
nh = ipv6_hdr(skb);
/* Setting an IP addresses is typically only a side effect of
* matching on them in the current userspace implementation, so it
* makes sense to check if the value actually changed.
*/
if (is_ipv6_mask_nonzero(mask->ipv6_src)) {
__be32 *saddr = (__be32 *)&nh->saddr;
__be32 masked[4];
mask_ipv6_addr(saddr, key->ipv6_src, mask->ipv6_src, masked);
if (unlikely(memcmp(saddr, masked, sizeof(masked)))) {
set_ipv6_addr(skb, flow_key->ip.proto, saddr, masked,
true);
memcpy(&flow_key->ipv6.addr.src, masked,
sizeof(flow_key->ipv6.addr.src));
}
}
if (is_ipv6_mask_nonzero(mask->ipv6_dst)) {
unsigned int offset = 0;
int flags = IP6_FH_F_SKIP_RH;
bool recalc_csum = true;
__be32 *daddr = (__be32 *)&nh->daddr;
__be32 masked[4];
mask_ipv6_addr(daddr, key->ipv6_dst, mask->ipv6_dst, masked);
if (unlikely(memcmp(daddr, masked, sizeof(masked)))) {
if (ipv6_ext_hdr(nh->nexthdr))
recalc_csum = (ipv6_find_hdr(skb, &offset,
NEXTHDR_ROUTING,
NULL, &flags)
!= NEXTHDR_ROUTING);
set_ipv6_addr(skb, flow_key->ip.proto, daddr, masked,
recalc_csum);
memcpy(&flow_key->ipv6.addr.dst, masked,
sizeof(flow_key->ipv6.addr.dst));
}
}
if (mask->ipv6_tclass) {
ipv6_change_dsfield(nh, ~mask->ipv6_tclass, key->ipv6_tclass);
flow_key->ip.tos = ipv6_get_dsfield(nh);
}
if (mask->ipv6_label) {
set_ipv6_fl(nh, ntohl(key->ipv6_label),
ntohl(mask->ipv6_label));
flow_key->ipv6.label =
*(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
}
if (mask->ipv6_hlimit) {
OVS_SET_MASKED(nh->hop_limit, key->ipv6_hlimit,
mask->ipv6_hlimit);
flow_key->ip.ttl = nh->hop_limit;
}
return 0;
}
openvswitch: enable NSH support v16->17 - Fixed disputed check code: keep them in nsh_push and nsh_pop but also add them in __ovs_nla_copy_actions v15->v16 - Add csum recalculation for nsh_push, nsh_pop and set_nsh pointed out by Pravin - Move nsh key into the union with ipv4 and ipv6 and add check for nsh key in match_validate pointed out by Pravin - Add nsh check in validate_set and __ovs_nla_copy_actions v14->v15 - Check size in nsh_hdr_from_nlattr - Fixed four small issues pointed out By Jiri and Eric v13->v14 - Rename skb_push_nsh to nsh_push per Dave's comment - Rename skb_pop_nsh to nsh_pop per Dave's comment v12->v13 - Fix NSH header length check in set_nsh v11->v12 - Fix missing changes old comments pointed out - Fix new comments for v11 v10->v11 - Fix the left three disputable comments for v9 but not fixed in v10. v9->v10 - Change struct ovs_key_nsh to struct ovs_nsh_key_base base; __be32 context[NSH_MD1_CONTEXT_SIZE]; - Fix new comments for v9 v8->v9 - Fix build error reported by daily intel build because nsh module isn't selected by openvswitch v7->v8 - Rework nested value and mask for OVS_KEY_ATTR_NSH - Change pop_nsh to adapt to nsh kernel module - Fix many issues per comments from Jiri Benc v6->v7 - Remove NSH GSO patches in v6 because Jiri Benc reworked it as another patch series and they have been merged. - Change it to adapt to nsh kernel module added by NSH GSO patch series v5->v6 - Fix the rest comments for v4. - Add NSH GSO support for VxLAN-gpe + NSH and Eth + NSH. v4->v5 - Fix many comments by Jiri Benc and Eric Garver for v4. v3->v4 - Add new NSH match field ttl - Update NSH header to the latest format which will be final format and won't change per its author's confirmation. - Fix comments for v3. v2->v3 - Change OVS_KEY_ATTR_NSH to nested key to handle length-fixed attributes and length-variable attriubte more flexibly. - Remove struct ovs_action_push_nsh completely - Add code to handle nested attribute for SET_MASKED - Change PUSH_NSH to use the nested OVS_KEY_ATTR_NSH to transfer NSH header data. - Fix comments and coding style issues by Jiri and Eric v1->v2 - Change encap_nsh and decap_nsh to push_nsh and pop_nsh - Dynamically allocate struct ovs_action_push_nsh for length-variable metadata. OVS master and 2.8 branch has merged NSH userspace patch series, this patch is to enable NSH support in kernel data path in order that OVS can support NSH in compat mode by porting this. Signed-off-by: Yi Yang <yi.y.yang@intel.com> Acked-by: Jiri Benc <jbenc@redhat.com> Acked-by: Eric Garver <e@erig.me> Acked-by: Pravin Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-07 21:07:02 +08:00
static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct nlattr *a)
{
struct nshhdr *nh;
size_t length;
int err;
u8 flags;
u8 ttl;
int i;
struct ovs_key_nsh key;
struct ovs_key_nsh mask;
err = nsh_key_from_nlattr(a, &key, &mask);
if (err)
return err;
/* Make sure the NSH base header is there */
if (!pskb_may_pull(skb, skb_network_offset(skb) + NSH_BASE_HDR_LEN))
return -ENOMEM;
nh = nsh_hdr(skb);
length = nsh_hdr_len(nh);
/* Make sure the whole NSH header is there */
err = skb_ensure_writable(skb, skb_network_offset(skb) +
length);
if (unlikely(err))
return err;
nh = nsh_hdr(skb);
skb_postpull_rcsum(skb, nh, length);
flags = nsh_get_flags(nh);
flags = OVS_MASKED(flags, key.base.flags, mask.base.flags);
flow_key->nsh.base.flags = flags;
ttl = nsh_get_ttl(nh);
ttl = OVS_MASKED(ttl, key.base.ttl, mask.base.ttl);
flow_key->nsh.base.ttl = ttl;
nsh_set_flags_and_ttl(nh, flags, ttl);
nh->path_hdr = OVS_MASKED(nh->path_hdr, key.base.path_hdr,
mask.base.path_hdr);
flow_key->nsh.base.path_hdr = nh->path_hdr;
switch (nh->mdtype) {
case NSH_M_TYPE1:
for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) {
nh->md1.context[i] =
OVS_MASKED(nh->md1.context[i], key.context[i],
mask.context[i]);
}
memcpy(flow_key->nsh.context, nh->md1.context,
sizeof(nh->md1.context));
break;
case NSH_M_TYPE2:
memset(flow_key->nsh.context, 0,
sizeof(flow_key->nsh.context));
break;
default:
return -EINVAL;
}
skb_postpush_rcsum(skb, nh, length);
return 0;
}
/* Must follow skb_ensure_writable() since that can move the skb data. */
static void set_tp_port(struct sk_buff *skb, __be16 *port,
__be16 new_port, __sum16 *check)
{
inet_proto_csum_replace2(check, skb, *port, new_port, false);
*port = new_port;
}
static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_udp *key,
const struct ovs_key_udp *mask)
{
struct udphdr *uh;
__be16 src, dst;
int err;
err = skb_ensure_writable(skb, skb_transport_offset(skb) +
sizeof(struct udphdr));
if (unlikely(err))
return err;
uh = udp_hdr(skb);
/* Either of the masks is non-zero, so do not bother checking them. */
src = OVS_MASKED(uh->source, key->udp_src, mask->udp_src);
dst = OVS_MASKED(uh->dest, key->udp_dst, mask->udp_dst);
if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) {
if (likely(src != uh->source)) {
set_tp_port(skb, &uh->source, src, &uh->check);
flow_key->tp.src = src;
}
if (likely(dst != uh->dest)) {
set_tp_port(skb, &uh->dest, dst, &uh->check);
flow_key->tp.dst = dst;
}
if (unlikely(!uh->check))
uh->check = CSUM_MANGLED_0;
} else {
uh->source = src;
uh->dest = dst;
flow_key->tp.src = src;
flow_key->tp.dst = dst;
}
skb_clear_hash(skb);
return 0;
}
static int set_tcp(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_tcp *key,
const struct ovs_key_tcp *mask)
{
struct tcphdr *th;
__be16 src, dst;
int err;
err = skb_ensure_writable(skb, skb_transport_offset(skb) +
sizeof(struct tcphdr));
if (unlikely(err))
return err;
th = tcp_hdr(skb);
src = OVS_MASKED(th->source, key->tcp_src, mask->tcp_src);
if (likely(src != th->source)) {
set_tp_port(skb, &th->source, src, &th->check);
flow_key->tp.src = src;
}
dst = OVS_MASKED(th->dest, key->tcp_dst, mask->tcp_dst);
if (likely(dst != th->dest)) {
set_tp_port(skb, &th->dest, dst, &th->check);
flow_key->tp.dst = dst;
}
skb_clear_hash(skb);
return 0;
}
static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
const struct ovs_key_sctp *key,
const struct ovs_key_sctp *mask)
{
unsigned int sctphoff = skb_transport_offset(skb);
struct sctphdr *sh;
__le32 old_correct_csum, new_csum, old_csum;
int err;
err = skb_ensure_writable(skb, sctphoff + sizeof(struct sctphdr));
if (unlikely(err))
return err;
sh = sctp_hdr(skb);
old_csum = sh->checksum;
old_correct_csum = sctp_compute_cksum(skb, sctphoff);
sh->source = OVS_MASKED(sh->source, key->sctp_src, mask->sctp_src);
sh->dest = OVS_MASKED(sh->dest, key->sctp_dst, mask->sctp_dst);
new_csum = sctp_compute_cksum(skb, sctphoff);
/* Carry any checksum errors through. */
sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
skb_clear_hash(skb);
flow_key->tp.src = sh->source;
flow_key->tp.dst = sh->dest;
return 0;
}
static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *skb)
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
{
struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage);
struct vport *vport = data->vport;
if (skb_cow_head(skb, data->l2_len) < 0) {
kfree_skb(skb);
return -ENOMEM;
}
__skb_dst_copy(skb, data->dst);
*OVS_CB(skb) = data->cb;
skb->inner_protocol = data->inner_protocol;
if (data->vlan_tci & VLAN_CFI_MASK)
__vlan_hwaccel_put_tag(skb, data->vlan_proto, data->vlan_tci & ~VLAN_CFI_MASK);
else
__vlan_hwaccel_clear_tag(skb);
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
/* Reconstruct the MAC header. */
skb_push(skb, data->l2_len);
memcpy(skb->data, &data->l2_data, data->l2_len);
skb_postpush_rcsum(skb, skb->data, data->l2_len);
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
skb_reset_mac_header(skb);
if (eth_p_mpls(skb->protocol)) {
skb->inner_network_header = skb->network_header;
skb_set_network_header(skb, data->network_offset);
skb_reset_mac_len(skb);
}
ovs_vport_send(vport, skb, data->mac_proto);
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
return 0;
}
static unsigned int
ovs_dst_get_mtu(const struct dst_entry *dst)
{
return dst->dev->mtu;
}
static struct dst_ops ovs_dst_ops = {
.family = AF_UNSPEC,
.mtu = ovs_dst_get_mtu,
};
/* prepare_frag() is called once per (larger-than-MTU) frame; its inverse is
* ovs_vport_output(), which is called once per fragmented packet.
*/
static void prepare_frag(struct vport *vport, struct sk_buff *skb,
u16 orig_network_offset, u8 mac_proto)
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
{
unsigned int hlen = skb_network_offset(skb);
struct ovs_frag_data *data;
data = this_cpu_ptr(&ovs_frag_data_storage);
data->dst = skb->_skb_refdst;
data->vport = vport;
data->cb = *OVS_CB(skb);
data->inner_protocol = skb->inner_protocol;
data->network_offset = orig_network_offset;
if (skb_vlan_tag_present(skb))
data->vlan_tci = skb_vlan_tag_get(skb) | VLAN_CFI_MASK;
else
data->vlan_tci = 0;
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
data->vlan_proto = skb->vlan_proto;
data->mac_proto = mac_proto;
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
data->l2_len = hlen;
memcpy(&data->l2_data, skb->data, hlen);
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
skb_pull(skb, hlen);
}
static void ovs_fragment(struct net *net, struct vport *vport,
struct sk_buff *skb, u16 mru,
struct sw_flow_key *key)
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
{
u16 orig_network_offset = 0;
if (eth_p_mpls(skb->protocol)) {
orig_network_offset = skb_network_offset(skb);
skb->network_header = skb->inner_network_header;
}
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
if (skb_network_offset(skb) > MAX_L2_LEN) {
OVS_NLERR(1, "L2 header too long to fragment");
goto err;
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
}
if (key->eth.type == htons(ETH_P_IP)) {
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
struct dst_entry ovs_dst;
unsigned long orig_dst;
prepare_frag(vport, skb, orig_network_offset,
ovs_key_mac_proto(key));
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
dst_init(&ovs_dst, &ovs_dst_ops, NULL, 1,
DST_OBSOLETE_NONE, DST_NOCOUNT);
ovs_dst.dev = vport->dev;
orig_dst = skb->_skb_refdst;
skb_dst_set_noref(skb, &ovs_dst);
IPCB(skb)->frag_max_size = mru;
ip_do_fragment(net, skb->sk, skb, ovs_vport_output);
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
refdst_drop(orig_dst);
} else if (key->eth.type == htons(ETH_P_IPV6)) {
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
unsigned long orig_dst;
struct rt6_info ovs_rt;
if (!v6ops)
goto err;
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
prepare_frag(vport, skb, orig_network_offset,
ovs_key_mac_proto(key));
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
memset(&ovs_rt, 0, sizeof(ovs_rt));
dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1,
DST_OBSOLETE_NONE, DST_NOCOUNT);
ovs_rt.dst.dev = vport->dev;
orig_dst = skb->_skb_refdst;
skb_dst_set_noref(skb, &ovs_rt.dst);
IP6CB(skb)->frag_max_size = mru;
v6ops->fragment(net, skb->sk, skb, ovs_vport_output);
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
refdst_drop(orig_dst);
} else {
WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
ovs_vport_name(vport), ntohs(key->eth.type), mru,
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
vport->dev->mtu);
goto err;
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
}
return;
err:
kfree_skb(skb);
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
}
static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
struct sw_flow_key *key)
{
struct vport *vport = ovs_vport_rcu(dp, out_port);
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
if (likely(vport)) {
u16 mru = OVS_CB(skb)->mru;
u32 cutlen = OVS_CB(skb)->cutlen;
if (unlikely(cutlen > 0)) {
if (skb->len - cutlen > ovs_mac_header_len(key))
pskb_trim(skb, skb->len - cutlen);
else
pskb_trim(skb, ovs_mac_header_len(key));
}
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
if (likely(!mru ||
(skb->len <= mru + vport->dev->hard_header_len))) {
ovs_vport_send(vport, skb, ovs_key_mac_proto(key));
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
} else if (mru <= vport->dev->mtu) {
struct net *net = read_pnet(&dp->net);
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
ovs_fragment(net, vport, skb, mru, key);
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
} else {
kfree_skb(skb);
}
} else {
kfree_skb(skb);
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
}
}
static int output_userspace(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key, const struct nlattr *attr,
const struct nlattr *actions, int actions_len,
uint32_t cutlen)
{
struct dp_upcall_info upcall;
const struct nlattr *a;
int rem;
memset(&upcall, 0, sizeof(upcall));
upcall.cmd = OVS_PACKET_CMD_ACTION;
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
upcall.mru = OVS_CB(skb)->mru;
for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
a = nla_next(a, &rem)) {
switch (nla_type(a)) {
case OVS_USERSPACE_ATTR_USERDATA:
upcall.userdata = a;
break;
case OVS_USERSPACE_ATTR_PID:
upcall.portid = nla_get_u32(a);
break;
case OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: {
/* Get out tunnel info. */
struct vport *vport;
vport = ovs_vport_rcu(dp, nla_get_u32(a));
if (vport) {
int err;
err = dev_fill_metadata_dst(vport->dev, skb);
if (!err)
upcall.egress_tun_info = skb_tunnel_info(skb);
}
break;
}
case OVS_USERSPACE_ATTR_ACTIONS: {
/* Include actions. */
upcall.actions = actions;
upcall.actions_len = actions_len;
break;
}
} /* End of switch. */
}
return ovs_dp_upcall(dp, skb, key, &upcall, cutlen);
}
openvswitch: Optimize sample action for the clone use cases With the introduction of open flow 'clone' action, the OVS user space can now translate the 'clone' action into kernel datapath 'sample' action, with 100% probability, to ensure that the clone semantics, which is that the packet seen by the clone action is the same as the packet seen by the action after clone, is faithfully carried out in the datapath. While the sample action in the datpath has the matching semantics, its implementation is only optimized for its original use. Specifically, there are two limitation: First, there is a 3 level of nesting restriction, enforced at the flow downloading time. This limit turns out to be too restrictive for the 'clone' use case. Second, the implementation avoid recursive call only if the sample action list has a single userspace action. The main optimization implemented in this series removes the static nesting limit check, instead, implement the run time recursion limit check, and recursion avoidance similar to that of the 'recirc' action. This optimization solve both #1 and #2 issues above. One related optimization attempts to avoid copying flow key as long as the actions enclosed does not change the flow key. The detection is performed only once at the flow downloading time. Another related optimization is to rewrite the action list at flow downloading time in order to save the fast path from parsing the sample action list in its original form repeatedly. Signed-off-by: Andy Zhou <azhou@ovn.org> Acked-by: Pravin B Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-21 07:32:29 +08:00
/* When 'last' is true, sample() should always consume the 'skb'.
* Otherwise, sample() should keep 'skb' intact regardless what
* actions are executed within sample().
*/
static int sample(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key, const struct nlattr *attr,
openvswitch: Optimize sample action for the clone use cases With the introduction of open flow 'clone' action, the OVS user space can now translate the 'clone' action into kernel datapath 'sample' action, with 100% probability, to ensure that the clone semantics, which is that the packet seen by the clone action is the same as the packet seen by the action after clone, is faithfully carried out in the datapath. While the sample action in the datpath has the matching semantics, its implementation is only optimized for its original use. Specifically, there are two limitation: First, there is a 3 level of nesting restriction, enforced at the flow downloading time. This limit turns out to be too restrictive for the 'clone' use case. Second, the implementation avoid recursive call only if the sample action list has a single userspace action. The main optimization implemented in this series removes the static nesting limit check, instead, implement the run time recursion limit check, and recursion avoidance similar to that of the 'recirc' action. This optimization solve both #1 and #2 issues above. One related optimization attempts to avoid copying flow key as long as the actions enclosed does not change the flow key. The detection is performed only once at the flow downloading time. Another related optimization is to rewrite the action list at flow downloading time in order to save the fast path from parsing the sample action list in its original form repeatedly. Signed-off-by: Andy Zhou <azhou@ovn.org> Acked-by: Pravin B Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-21 07:32:29 +08:00
bool last)
{
openvswitch: Optimize sample action for the clone use cases With the introduction of open flow 'clone' action, the OVS user space can now translate the 'clone' action into kernel datapath 'sample' action, with 100% probability, to ensure that the clone semantics, which is that the packet seen by the clone action is the same as the packet seen by the action after clone, is faithfully carried out in the datapath. While the sample action in the datpath has the matching semantics, its implementation is only optimized for its original use. Specifically, there are two limitation: First, there is a 3 level of nesting restriction, enforced at the flow downloading time. This limit turns out to be too restrictive for the 'clone' use case. Second, the implementation avoid recursive call only if the sample action list has a single userspace action. The main optimization implemented in this series removes the static nesting limit check, instead, implement the run time recursion limit check, and recursion avoidance similar to that of the 'recirc' action. This optimization solve both #1 and #2 issues above. One related optimization attempts to avoid copying flow key as long as the actions enclosed does not change the flow key. The detection is performed only once at the flow downloading time. Another related optimization is to rewrite the action list at flow downloading time in order to save the fast path from parsing the sample action list in its original form repeatedly. Signed-off-by: Andy Zhou <azhou@ovn.org> Acked-by: Pravin B Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-21 07:32:29 +08:00
struct nlattr *actions;
struct nlattr *sample_arg;
int rem = nla_len(attr);
const struct sample_arg *arg;
bool clone_flow_key;
openvswitch: Optimize sample action for the clone use cases With the introduction of open flow 'clone' action, the OVS user space can now translate the 'clone' action into kernel datapath 'sample' action, with 100% probability, to ensure that the clone semantics, which is that the packet seen by the clone action is the same as the packet seen by the action after clone, is faithfully carried out in the datapath. While the sample action in the datpath has the matching semantics, its implementation is only optimized for its original use. Specifically, there are two limitation: First, there is a 3 level of nesting restriction, enforced at the flow downloading time. This limit turns out to be too restrictive for the 'clone' use case. Second, the implementation avoid recursive call only if the sample action list has a single userspace action. The main optimization implemented in this series removes the static nesting limit check, instead, implement the run time recursion limit check, and recursion avoidance similar to that of the 'recirc' action. This optimization solve both #1 and #2 issues above. One related optimization attempts to avoid copying flow key as long as the actions enclosed does not change the flow key. The detection is performed only once at the flow downloading time. Another related optimization is to rewrite the action list at flow downloading time in order to save the fast path from parsing the sample action list in its original form repeatedly. Signed-off-by: Andy Zhou <azhou@ovn.org> Acked-by: Pravin B Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-21 07:32:29 +08:00
/* The first action is always 'OVS_SAMPLE_ATTR_ARG'. */
sample_arg = nla_data(attr);
arg = nla_data(sample_arg);
actions = nla_next(sample_arg, &rem);
openvswitch: Optimize sample action for the clone use cases With the introduction of open flow 'clone' action, the OVS user space can now translate the 'clone' action into kernel datapath 'sample' action, with 100% probability, to ensure that the clone semantics, which is that the packet seen by the clone action is the same as the packet seen by the action after clone, is faithfully carried out in the datapath. While the sample action in the datpath has the matching semantics, its implementation is only optimized for its original use. Specifically, there are two limitation: First, there is a 3 level of nesting restriction, enforced at the flow downloading time. This limit turns out to be too restrictive for the 'clone' use case. Second, the implementation avoid recursive call only if the sample action list has a single userspace action. The main optimization implemented in this series removes the static nesting limit check, instead, implement the run time recursion limit check, and recursion avoidance similar to that of the 'recirc' action. This optimization solve both #1 and #2 issues above. One related optimization attempts to avoid copying flow key as long as the actions enclosed does not change the flow key. The detection is performed only once at the flow downloading time. Another related optimization is to rewrite the action list at flow downloading time in order to save the fast path from parsing the sample action list in its original form repeatedly. Signed-off-by: Andy Zhou <azhou@ovn.org> Acked-by: Pravin B Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-21 07:32:29 +08:00
if ((arg->probability != U32_MAX) &&
(!arg->probability || prandom_u32() > arg->probability)) {
if (last)
consume_skb(skb);
return 0;
}
clone_flow_key = !arg->exec;
return clone_execute(dp, skb, key, 0, actions, rem, last,
clone_flow_key);
}
/* When 'last' is true, clone() should always consume the 'skb'.
* Otherwise, clone() should keep 'skb' intact regardless what
* actions are executed within clone().
*/
static int clone(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key, const struct nlattr *attr,
bool last)
{
struct nlattr *actions;
struct nlattr *clone_arg;
int rem = nla_len(attr);
bool dont_clone_flow_key;
/* The first action is always 'OVS_CLONE_ATTR_ARG'. */
clone_arg = nla_data(attr);
dont_clone_flow_key = nla_get_u32(clone_arg);
actions = nla_next(clone_arg, &rem);
return clone_execute(dp, skb, key, 0, actions, rem, last,
!dont_clone_flow_key);
}
static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
const struct nlattr *attr)
{
struct ovs_action_hash *hash_act = nla_data(attr);
u32 hash = 0;
/* OVS_HASH_ALG_L4 is the only possible hash algorithm. */
hash = skb_get_hash(skb);
hash = jhash_1word(hash, hash_act->hash_basis);
if (!hash)
hash = 0x1;
key->ovs_flow_hash = hash;
}
static int execute_set_action(struct sk_buff *skb,
struct sw_flow_key *flow_key,
const struct nlattr *a)
{
/* Only tunnel set execution is supported without a mask. */
if (nla_type(a) == OVS_KEY_ATTR_TUNNEL_INFO) {
struct ovs_tunnel_info *tun = nla_data(a);
skb_dst_drop(skb);
dst_hold((struct dst_entry *)tun->tun_dst);
skb_dst_set(skb, (struct dst_entry *)tun->tun_dst);
return 0;
}
return -EINVAL;
}
/* Mask is at the midpoint of the data. */
#define get_mask(a, type) ((const type)nla_data(a) + 1)
static int execute_masked_set_action(struct sk_buff *skb,
struct sw_flow_key *flow_key,
const struct nlattr *a)
{
int err = 0;
switch (nla_type(a)) {
case OVS_KEY_ATTR_PRIORITY:
OVS_SET_MASKED(skb->priority, nla_get_u32(a),
*get_mask(a, u32 *));
flow_key->phy.priority = skb->priority;
break;
case OVS_KEY_ATTR_SKB_MARK:
OVS_SET_MASKED(skb->mark, nla_get_u32(a), *get_mask(a, u32 *));
flow_key->phy.skb_mark = skb->mark;
break;
case OVS_KEY_ATTR_TUNNEL_INFO:
/* Masked data not supported for tunnel. */
err = -EINVAL;
break;
case OVS_KEY_ATTR_ETHERNET:
err = set_eth_addr(skb, flow_key, nla_data(a),
get_mask(a, struct ovs_key_ethernet *));
break;
openvswitch: enable NSH support v16->17 - Fixed disputed check code: keep them in nsh_push and nsh_pop but also add them in __ovs_nla_copy_actions v15->v16 - Add csum recalculation for nsh_push, nsh_pop and set_nsh pointed out by Pravin - Move nsh key into the union with ipv4 and ipv6 and add check for nsh key in match_validate pointed out by Pravin - Add nsh check in validate_set and __ovs_nla_copy_actions v14->v15 - Check size in nsh_hdr_from_nlattr - Fixed four small issues pointed out By Jiri and Eric v13->v14 - Rename skb_push_nsh to nsh_push per Dave's comment - Rename skb_pop_nsh to nsh_pop per Dave's comment v12->v13 - Fix NSH header length check in set_nsh v11->v12 - Fix missing changes old comments pointed out - Fix new comments for v11 v10->v11 - Fix the left three disputable comments for v9 but not fixed in v10. v9->v10 - Change struct ovs_key_nsh to struct ovs_nsh_key_base base; __be32 context[NSH_MD1_CONTEXT_SIZE]; - Fix new comments for v9 v8->v9 - Fix build error reported by daily intel build because nsh module isn't selected by openvswitch v7->v8 - Rework nested value and mask for OVS_KEY_ATTR_NSH - Change pop_nsh to adapt to nsh kernel module - Fix many issues per comments from Jiri Benc v6->v7 - Remove NSH GSO patches in v6 because Jiri Benc reworked it as another patch series and they have been merged. - Change it to adapt to nsh kernel module added by NSH GSO patch series v5->v6 - Fix the rest comments for v4. - Add NSH GSO support for VxLAN-gpe + NSH and Eth + NSH. v4->v5 - Fix many comments by Jiri Benc and Eric Garver for v4. v3->v4 - Add new NSH match field ttl - Update NSH header to the latest format which will be final format and won't change per its author's confirmation. - Fix comments for v3. v2->v3 - Change OVS_KEY_ATTR_NSH to nested key to handle length-fixed attributes and length-variable attriubte more flexibly. - Remove struct ovs_action_push_nsh completely - Add code to handle nested attribute for SET_MASKED - Change PUSH_NSH to use the nested OVS_KEY_ATTR_NSH to transfer NSH header data. - Fix comments and coding style issues by Jiri and Eric v1->v2 - Change encap_nsh and decap_nsh to push_nsh and pop_nsh - Dynamically allocate struct ovs_action_push_nsh for length-variable metadata. OVS master and 2.8 branch has merged NSH userspace patch series, this patch is to enable NSH support in kernel data path in order that OVS can support NSH in compat mode by porting this. Signed-off-by: Yi Yang <yi.y.yang@intel.com> Acked-by: Jiri Benc <jbenc@redhat.com> Acked-by: Eric Garver <e@erig.me> Acked-by: Pravin Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-07 21:07:02 +08:00
case OVS_KEY_ATTR_NSH:
err = set_nsh(skb, flow_key, a);
break;
case OVS_KEY_ATTR_IPV4:
err = set_ipv4(skb, flow_key, nla_data(a),
get_mask(a, struct ovs_key_ipv4 *));
break;
case OVS_KEY_ATTR_IPV6:
err = set_ipv6(skb, flow_key, nla_data(a),
get_mask(a, struct ovs_key_ipv6 *));
break;
case OVS_KEY_ATTR_TCP:
err = set_tcp(skb, flow_key, nla_data(a),
get_mask(a, struct ovs_key_tcp *));
break;
case OVS_KEY_ATTR_UDP:
err = set_udp(skb, flow_key, nla_data(a),
get_mask(a, struct ovs_key_udp *));
break;
case OVS_KEY_ATTR_SCTP:
err = set_sctp(skb, flow_key, nla_data(a),
get_mask(a, struct ovs_key_sctp *));
break;
case OVS_KEY_ATTR_MPLS:
err = set_mpls(skb, flow_key, nla_data(a), get_mask(a,
__be32 *));
break;
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
case OVS_KEY_ATTR_CT_STATE:
case OVS_KEY_ATTR_CT_ZONE:
case OVS_KEY_ATTR_CT_MARK:
case OVS_KEY_ATTR_CT_LABELS:
openvswitch: Add original direction conntrack tuple to sw_flow_key. Add the fields of the conntrack original direction 5-tuple to struct sw_flow_key. The new fields are initially marked as non-existent, and are populated whenever a conntrack action is executed and either finds or generates a conntrack entry. This means that these fields exist for all packets that were not rejected by conntrack as untrackable. The original tuple fields in the sw_flow_key are filled from the original direction tuple of the conntrack entry relating to the current packet, or from the original direction tuple of the master conntrack entry, if the current conntrack entry has a master. Generally, expected connections of connections having an assigned helper (e.g., FTP), have a master conntrack entry. The main purpose of the new conntrack original tuple fields is to allow matching on them for policy decision purposes, with the premise that the admissibility of tracked connections reply packets (as well as original direction packets), and both direction packets of any related connections may be based on ACL rules applying to the master connection's original direction 5-tuple. This also makes it easier to make policy decisions when the actual packet headers might have been transformed by NAT, as the original direction 5-tuple represents the packet headers before any such transformation. When using the original direction 5-tuple the admissibility of return and/or related packets need not be based on the mere existence of a conntrack entry, allowing separation of admission policy from the established conntrack state. While existence of a conntrack entry is required for admission of the return or related packets, policy changes can render connections that were initially admitted to be rejected or dropped afterwards. If the admission of the return and related packets was based on mere conntrack state (e.g., connection being in an established state), a policy change that would make the connection rejected or dropped would need to find and delete all conntrack entries affected by such a change. When using the original direction 5-tuple matching the affected conntrack entries can be allowed to time out instead, as the established state of the connection would not need to be the basis for packet admission any more. It should be noted that the directionality of related connections may be the same or different than that of the master connection, and neither the original direction 5-tuple nor the conntrack state bits carry this information. If needed, the directionality of the master connection can be stored in master's conntrack mark or labels, which are automatically inherited by the expected related connections. The fact that neither ARP nor ND packets are trackable by conntrack allows mutual exclusion between ARP/ND and the new conntrack original tuple fields. Hence, the IP addresses are overlaid in union with ARP and ND fields. This allows the sw_flow_key to not grow much due to this patch, but it also means that we must be careful to never use the new key fields with ARP or ND packets. ARP is easy to distinguish and keep mutually exclusive based on the ethernet type, but ND being an ICMPv6 protocol requires a bit more attention. Signed-off-by: Jarno Rajahalme <jarno@ovn.org> Acked-by: Joe Stringer <joe@ovn.org> Acked-by: Pravin B Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-10 03:21:59 +08:00
case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4:
case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6:
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
err = -EINVAL;
break;
}
return err;
}
static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key,
const struct nlattr *a, bool last)
{
u32 recirc_id;
if (!is_flow_key_valid(key)) {
int err;
err = ovs_flow_key_update(skb, key);
if (err)
return err;
}
BUG_ON(!is_flow_key_valid(key));
recirc_id = nla_get_u32(a);
return clone_execute(dp, skb, key, recirc_id, NULL, 0, last, true);
}
net: openvswitch: Add a new action check_pkt_len This patch adds a new action - 'check_pkt_len' which checks the packet length and executes a set of actions if the packet length is greater than the specified length or executes another set of actions if the packet length is lesser or equal to. This action takes below nlattrs * OVS_CHECK_PKT_LEN_ATTR_PKT_LEN - 'pkt_len' to check for * OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER - Nested actions to apply if the packet length is greater than the specified 'pkt_len' * OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL - Nested actions to apply if the packet length is lesser or equal to the specified 'pkt_len'. The main use case for adding this action is to solve the packet drops because of MTU mismatch in OVN virtual networking solution. When a VM (which belongs to a logical switch of OVN) sends a packet destined to go via the gateway router and if the nic which provides external connectivity, has a lesser MTU, OVS drops the packet if the packet length is greater than this MTU. With the help of this action, OVN will check the packet length and if it is greater than the MTU size, it will generate an ICMP packet (type 3, code 4) and includes the next hop mtu in it so that the sender can fragment the packets. Reported-at: https://mail.openvswitch.org/pipermail/ovs-discuss/2018-July/047039.html Suggested-by: Ben Pfaff <blp@ovn.org> Signed-off-by: Numan Siddique <nusiddiq@redhat.com> CC: Gregory Rose <gvrose8192@gmail.com> CC: Pravin B Shelar <pshelar@ovn.org> Acked-by: Pravin B Shelar <pshelar@ovn.org> Tested-by: Greg Rose <gvrose8192@gmail.com> Reviewed-by: Greg Rose <gvrose8192@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-26 08:43:46 +08:00
static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key,
const struct nlattr *attr, bool last)
{
const struct nlattr *actions, *cpl_arg;
const struct check_pkt_len_arg *arg;
int rem = nla_len(attr);
bool clone_flow_key;
/* The first netlink attribute in 'attr' is always
* 'OVS_CHECK_PKT_LEN_ATTR_ARG'.
*/
cpl_arg = nla_data(attr);
arg = nla_data(cpl_arg);
if (skb->len <= arg->pkt_len) {
/* Second netlink attribute in 'attr' is always
* 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'.
*/
actions = nla_next(cpl_arg, &rem);
clone_flow_key = !arg->exec_for_lesser_equal;
} else {
/* Third netlink attribute in 'attr' is always
* 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER'.
*/
actions = nla_next(cpl_arg, &rem);
actions = nla_next(actions, &rem);
clone_flow_key = !arg->exec_for_greater;
}
return clone_execute(dp, skb, key, 0, nla_data(actions),
nla_len(actions), last, clone_flow_key);
}
/* Execute a list of actions against 'skb'. */
static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key,
2014-07-22 06:12:34 +08:00
const struct nlattr *attr, int len)
{
const struct nlattr *a;
int rem;
for (a = attr, rem = len; rem > 0;
a = nla_next(a, &rem)) {
int err = 0;
switch (nla_type(a)) {
case OVS_ACTION_ATTR_OUTPUT: {
int port = nla_get_u32(a);
struct sk_buff *clone;
/* Every output action needs a separate clone
* of 'skb', In case the output action is the
* last action, cloning can be avoided.
*/
if (nla_is_last(a, rem)) {
do_output(dp, skb, port, key);
/* 'skb' has been used for output.
*/
return 0;
}
clone = skb_clone(skb, GFP_ATOMIC);
if (clone)
do_output(dp, clone, port, key);
OVS_CB(skb)->cutlen = 0;
break;
}
case OVS_ACTION_ATTR_TRUNC: {
struct ovs_action_trunc *trunc = nla_data(a);
if (skb->len > trunc->max_len)
OVS_CB(skb)->cutlen = skb->len - trunc->max_len;
break;
}
case OVS_ACTION_ATTR_USERSPACE:
output_userspace(dp, skb, key, a, attr,
len, OVS_CB(skb)->cutlen);
OVS_CB(skb)->cutlen = 0;
break;
case OVS_ACTION_ATTR_HASH:
execute_hash(skb, key, a);
break;
case OVS_ACTION_ATTR_PUSH_MPLS:
err = push_mpls(skb, key, nla_data(a));
break;
case OVS_ACTION_ATTR_POP_MPLS:
err = pop_mpls(skb, key, nla_get_be16(a));
break;
case OVS_ACTION_ATTR_PUSH_VLAN:
err = push_vlan(skb, key, nla_data(a));
break;
case OVS_ACTION_ATTR_POP_VLAN:
err = pop_vlan(skb, key);
break;
case OVS_ACTION_ATTR_RECIRC: {
bool last = nla_is_last(a, rem);
err = execute_recirc(dp, skb, key, a, last);
if (last) {
/* If this is the last action, the skb has
* been consumed or freed.
* Return immediately.
*/
return err;
}
break;
}
case OVS_ACTION_ATTR_SET:
err = execute_set_action(skb, key, nla_data(a));
break;
case OVS_ACTION_ATTR_SET_MASKED:
case OVS_ACTION_ATTR_SET_TO_MASKED:
err = execute_masked_set_action(skb, key, nla_data(a));
break;
openvswitch: Optimize sample action for the clone use cases With the introduction of open flow 'clone' action, the OVS user space can now translate the 'clone' action into kernel datapath 'sample' action, with 100% probability, to ensure that the clone semantics, which is that the packet seen by the clone action is the same as the packet seen by the action after clone, is faithfully carried out in the datapath. While the sample action in the datpath has the matching semantics, its implementation is only optimized for its original use. Specifically, there are two limitation: First, there is a 3 level of nesting restriction, enforced at the flow downloading time. This limit turns out to be too restrictive for the 'clone' use case. Second, the implementation avoid recursive call only if the sample action list has a single userspace action. The main optimization implemented in this series removes the static nesting limit check, instead, implement the run time recursion limit check, and recursion avoidance similar to that of the 'recirc' action. This optimization solve both #1 and #2 issues above. One related optimization attempts to avoid copying flow key as long as the actions enclosed does not change the flow key. The detection is performed only once at the flow downloading time. Another related optimization is to rewrite the action list at flow downloading time in order to save the fast path from parsing the sample action list in its original form repeatedly. Signed-off-by: Andy Zhou <azhou@ovn.org> Acked-by: Pravin B Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-21 07:32:29 +08:00
case OVS_ACTION_ATTR_SAMPLE: {
bool last = nla_is_last(a, rem);
err = sample(dp, skb, key, a, last);
if (last)
return err;
break;
openvswitch: Optimize sample action for the clone use cases With the introduction of open flow 'clone' action, the OVS user space can now translate the 'clone' action into kernel datapath 'sample' action, with 100% probability, to ensure that the clone semantics, which is that the packet seen by the clone action is the same as the packet seen by the action after clone, is faithfully carried out in the datapath. While the sample action in the datpath has the matching semantics, its implementation is only optimized for its original use. Specifically, there are two limitation: First, there is a 3 level of nesting restriction, enforced at the flow downloading time. This limit turns out to be too restrictive for the 'clone' use case. Second, the implementation avoid recursive call only if the sample action list has a single userspace action. The main optimization implemented in this series removes the static nesting limit check, instead, implement the run time recursion limit check, and recursion avoidance similar to that of the 'recirc' action. This optimization solve both #1 and #2 issues above. One related optimization attempts to avoid copying flow key as long as the actions enclosed does not change the flow key. The detection is performed only once at the flow downloading time. Another related optimization is to rewrite the action list at flow downloading time in order to save the fast path from parsing the sample action list in its original form repeatedly. Signed-off-by: Andy Zhou <azhou@ovn.org> Acked-by: Pravin B Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-21 07:32:29 +08:00
}
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
case OVS_ACTION_ATTR_CT:
if (!is_flow_key_valid(key)) {
err = ovs_flow_key_update(skb, key);
if (err)
return err;
}
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
err = ovs_ct_execute(ovs_dp_get_net(dp), skb, key,
nla_data(a));
/* Hide stolen IP fragments from user space. */
if (err)
return err == -EINPROGRESS ? 0 : err;
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
break;
case OVS_ACTION_ATTR_CT_CLEAR:
err = ovs_ct_clear(skb, key);
break;
case OVS_ACTION_ATTR_PUSH_ETH:
err = push_eth(skb, key, nla_data(a));
break;
case OVS_ACTION_ATTR_POP_ETH:
err = pop_eth(skb, key);
break;
openvswitch: enable NSH support v16->17 - Fixed disputed check code: keep them in nsh_push and nsh_pop but also add them in __ovs_nla_copy_actions v15->v16 - Add csum recalculation for nsh_push, nsh_pop and set_nsh pointed out by Pravin - Move nsh key into the union with ipv4 and ipv6 and add check for nsh key in match_validate pointed out by Pravin - Add nsh check in validate_set and __ovs_nla_copy_actions v14->v15 - Check size in nsh_hdr_from_nlattr - Fixed four small issues pointed out By Jiri and Eric v13->v14 - Rename skb_push_nsh to nsh_push per Dave's comment - Rename skb_pop_nsh to nsh_pop per Dave's comment v12->v13 - Fix NSH header length check in set_nsh v11->v12 - Fix missing changes old comments pointed out - Fix new comments for v11 v10->v11 - Fix the left three disputable comments for v9 but not fixed in v10. v9->v10 - Change struct ovs_key_nsh to struct ovs_nsh_key_base base; __be32 context[NSH_MD1_CONTEXT_SIZE]; - Fix new comments for v9 v8->v9 - Fix build error reported by daily intel build because nsh module isn't selected by openvswitch v7->v8 - Rework nested value and mask for OVS_KEY_ATTR_NSH - Change pop_nsh to adapt to nsh kernel module - Fix many issues per comments from Jiri Benc v6->v7 - Remove NSH GSO patches in v6 because Jiri Benc reworked it as another patch series and they have been merged. - Change it to adapt to nsh kernel module added by NSH GSO patch series v5->v6 - Fix the rest comments for v4. - Add NSH GSO support for VxLAN-gpe + NSH and Eth + NSH. v4->v5 - Fix many comments by Jiri Benc and Eric Garver for v4. v3->v4 - Add new NSH match field ttl - Update NSH header to the latest format which will be final format and won't change per its author's confirmation. - Fix comments for v3. v2->v3 - Change OVS_KEY_ATTR_NSH to nested key to handle length-fixed attributes and length-variable attriubte more flexibly. - Remove struct ovs_action_push_nsh completely - Add code to handle nested attribute for SET_MASKED - Change PUSH_NSH to use the nested OVS_KEY_ATTR_NSH to transfer NSH header data. - Fix comments and coding style issues by Jiri and Eric v1->v2 - Change encap_nsh and decap_nsh to push_nsh and pop_nsh - Dynamically allocate struct ovs_action_push_nsh for length-variable metadata. OVS master and 2.8 branch has merged NSH userspace patch series, this patch is to enable NSH support in kernel data path in order that OVS can support NSH in compat mode by porting this. Signed-off-by: Yi Yang <yi.y.yang@intel.com> Acked-by: Jiri Benc <jbenc@redhat.com> Acked-by: Eric Garver <e@erig.me> Acked-by: Pravin Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-07 21:07:02 +08:00
case OVS_ACTION_ATTR_PUSH_NSH: {
u8 buffer[NSH_HDR_MAX_LEN];
struct nshhdr *nh = (struct nshhdr *)buffer;
err = nsh_hdr_from_nlattr(nla_data(a), nh,
NSH_HDR_MAX_LEN);
if (unlikely(err))
break;
err = push_nsh(skb, key, nh);
break;
}
case OVS_ACTION_ATTR_POP_NSH:
err = pop_nsh(skb, key);
break;
case OVS_ACTION_ATTR_METER:
if (ovs_meter_execute(dp, skb, key, nla_get_u32(a))) {
consume_skb(skb);
return 0;
}
break;
case OVS_ACTION_ATTR_CLONE: {
bool last = nla_is_last(a, rem);
err = clone(dp, skb, key, a, last);
if (last)
return err;
break;
}
net: openvswitch: Add a new action check_pkt_len This patch adds a new action - 'check_pkt_len' which checks the packet length and executes a set of actions if the packet length is greater than the specified length or executes another set of actions if the packet length is lesser or equal to. This action takes below nlattrs * OVS_CHECK_PKT_LEN_ATTR_PKT_LEN - 'pkt_len' to check for * OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER - Nested actions to apply if the packet length is greater than the specified 'pkt_len' * OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL - Nested actions to apply if the packet length is lesser or equal to the specified 'pkt_len'. The main use case for adding this action is to solve the packet drops because of MTU mismatch in OVN virtual networking solution. When a VM (which belongs to a logical switch of OVN) sends a packet destined to go via the gateway router and if the nic which provides external connectivity, has a lesser MTU, OVS drops the packet if the packet length is greater than this MTU. With the help of this action, OVN will check the packet length and if it is greater than the MTU size, it will generate an ICMP packet (type 3, code 4) and includes the next hop mtu in it so that the sender can fragment the packets. Reported-at: https://mail.openvswitch.org/pipermail/ovs-discuss/2018-July/047039.html Suggested-by: Ben Pfaff <blp@ovn.org> Signed-off-by: Numan Siddique <nusiddiq@redhat.com> CC: Gregory Rose <gvrose8192@gmail.com> CC: Pravin B Shelar <pshelar@ovn.org> Acked-by: Pravin B Shelar <pshelar@ovn.org> Tested-by: Greg Rose <gvrose8192@gmail.com> Reviewed-by: Greg Rose <gvrose8192@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-26 08:43:46 +08:00
case OVS_ACTION_ATTR_CHECK_PKT_LEN: {
bool last = nla_is_last(a, rem);
err = execute_check_pkt_len(dp, skb, key, a, last);
if (last)
return err;
break;
}
}
if (unlikely(err)) {
kfree_skb(skb);
return err;
}
}
consume_skb(skb);
return 0;
}
/* Execute the actions on the clone of the packet. The effect of the
* execution does not affect the original 'skb' nor the original 'key'.
*
* The execution may be deferred in case the actions can not be executed
* immediately.
*/
static int clone_execute(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key, u32 recirc_id,
const struct nlattr *actions, int len,
bool last, bool clone_flow_key)
{
struct deferred_action *da;
struct sw_flow_key *clone;
skb = last ? skb : skb_clone(skb, GFP_ATOMIC);
if (!skb) {
/* Out of memory, skip this action.
*/
return 0;
}
/* When clone_flow_key is false, the 'key' will not be change
* by the actions, then the 'key' can be used directly.
* Otherwise, try to clone key from the next recursion level of
* 'flow_keys'. If clone is successful, execute the actions
* without deferring.
*/
clone = clone_flow_key ? clone_key(key) : key;
if (clone) {
int err = 0;
if (actions) { /* Sample action */
if (clone_flow_key)
__this_cpu_inc(exec_actions_level);
err = do_execute_actions(dp, skb, clone,
actions, len);
if (clone_flow_key)
__this_cpu_dec(exec_actions_level);
} else { /* Recirc action */
clone->recirc_id = recirc_id;
ovs_dp_process_packet(skb, clone);
}
return err;
}
/* Out of 'flow_keys' space. Defer actions */
da = add_deferred_actions(skb, key, actions, len);
if (da) {
if (!actions) { /* Recirc action */
key = &da->pkt_key;
key->recirc_id = recirc_id;
}
} else {
/* Out of per CPU action FIFO space. Drop the 'skb' and
* log an error.
*/
kfree_skb(skb);
if (net_ratelimit()) {
if (actions) { /* Sample action */
pr_warn("%s: deferred action limit reached, drop sample action\n",
ovs_dp_name(dp));
} else { /* Recirc action */
pr_warn("%s: deferred action limit reached, drop recirc action\n",
ovs_dp_name(dp));
}
}
}
return 0;
}
static void process_deferred_actions(struct datapath *dp)
{
struct action_fifo *fifo = this_cpu_ptr(action_fifos);
/* Do not touch the FIFO in case there is no deferred actions. */
if (action_fifo_is_empty(fifo))
return;
/* Finishing executing all deferred actions. */
do {
struct deferred_action *da = action_fifo_get(fifo);
struct sk_buff *skb = da->skb;
struct sw_flow_key *key = &da->pkt_key;
const struct nlattr *actions = da->actions;
int actions_len = da->actions_len;
if (actions)
do_execute_actions(dp, skb, key, actions, actions_len);
else
ovs_dp_process_packet(skb, key);
} while (!action_fifo_is_empty(fifo));
/* Reset FIFO for the next packet. */
action_fifo_init(fifo);
}
/* Execute a list of actions against 'skb'. */
int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
const struct sw_flow_actions *acts,
struct sw_flow_key *key)
{
int err, level;
level = __this_cpu_inc_return(exec_actions_level);
if (unlikely(level > OVS_RECURSION_LIMIT)) {
net_crit_ratelimited("ovs: recursion limit reached on datapath %s, probable configuration error\n",
ovs_dp_name(dp));
kfree_skb(skb);
err = -ENETDOWN;
goto out;
}
openvswitch: fix skb_panic due to the incorrect actions attrlen For sw_flow_actions, the actions_len only represents the kernel part's size, and when we dump the actions to the userspace, we will do the convertions, so it's true size may become bigger than the actions_len. But unfortunately, for OVS_PACKET_ATTR_ACTIONS, we use the actions_len to alloc the skbuff, so the user_skb's size may become insufficient and oops will happen like this: skbuff: skb_over_panic: text:ffffffff8148fabf len:1749 put:157 head: ffff881300f39000 data:ffff881300f39000 tail:0x6d5 end:0x6c0 dev:<NULL> ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:129! [...] Call Trace: <IRQ> [<ffffffff8148be82>] skb_put+0x43/0x44 [<ffffffff8148fabf>] skb_zerocopy+0x6c/0x1f4 [<ffffffffa0290d36>] queue_userspace_packet+0x3a3/0x448 [openvswitch] [<ffffffffa0292023>] ovs_dp_upcall+0x30/0x5c [openvswitch] [<ffffffffa028d435>] output_userspace+0x132/0x158 [openvswitch] [<ffffffffa01e6890>] ? ip6_rcv_finish+0x74/0x77 [ipv6] [<ffffffffa028e277>] do_execute_actions+0xcc1/0xdc8 [openvswitch] [<ffffffffa028e3f2>] ovs_execute_actions+0x74/0x106 [openvswitch] [<ffffffffa0292130>] ovs_dp_process_packet+0xe1/0xfd [openvswitch] [<ffffffffa0292b77>] ? key_extract+0x63c/0x8d5 [openvswitch] [<ffffffffa029848b>] ovs_vport_receive+0xa1/0xc3 [openvswitch] [...] Also we can find that the actions_len is much little than the orig_len: crash> struct sw_flow_actions 0xffff8812f539d000 struct sw_flow_actions { rcu = { next = 0xffff8812f5398800, func = 0xffffe3b00035db32 }, orig_len = 1384, actions_len = 592, actions = 0xffff8812f539d01c } So as a quick fix, use the orig_len instead of the actions_len to alloc the user_skb. Last, this oops happened on our system running a relative old kernel, but the same risk still exists on the mainline, since we use the wrong actions_len from the beginning. Fixes: ccea74457bbd ("openvswitch: include datapath actions with sampled-packet upcall to userspace") Cc: Neil McKee <neil.mckee@inmon.com> Signed-off-by: Liping Zhang <zlpnobody@gmail.com> Acked-by: Pravin B Shelar <pshelar@ovn.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 13:30:07 +08:00
OVS_CB(skb)->acts_origlen = acts->orig_len;
err = do_execute_actions(dp, skb, key,
acts->actions, acts->actions_len);
if (level == 1)
process_deferred_actions(dp);
out:
__this_cpu_dec(exec_actions_level);
return err;
}
int action_fifos_init(void)
{
action_fifos = alloc_percpu(struct action_fifo);
if (!action_fifos)
return -ENOMEM;
flow_keys = alloc_percpu(struct action_flow_keys);
if (!flow_keys) {
free_percpu(action_fifos);
return -ENOMEM;
}
return 0;
}
void action_fifos_exit(void)
{
free_percpu(action_fifos);
free_percpu(flow_keys);
}