2
0
mirror of https://github.com/openvswitch/ovs synced 2025-10-21 14:49:41 +00:00
Files
openvswitch/datapath/datapath.h

149 lines
4.7 KiB
C
Raw Normal View History

/*
* Copyright (c) 2007-2011 Nicira Networks.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
* 02110-1301, USA
*/
#ifndef DATAPATH_H
#define DATAPATH_H 1
#include <asm/page.h>
#include <linux/kernel.h>
#include <linux/mutex.h>
#include <linux/netdevice.h>
#include <linux/seqlock.h>
#include <linux/skbuff.h>
#include <linux/version.h>
#include "checksum.h"
#include "compat.h"
#include "flow.h"
#include "dp_sysfs.h"
#include "vlan.h"
struct vport;
#define DP_MAX_PORTS 1024
#define SAMPLE_ACTION_DEPTH 3
/**
* struct dp_stats_percpu - per-cpu packet processing statistics for a given
* datapath.
* @n_hit: Number of received packets for which a matching flow was found in
* the flow table.
* @n_miss: Number of received packets that had no matching flow in the flow
* table. The sum of @n_hit and @n_miss is the number of packets that have
* been received by the datapath.
* @n_lost: Number of received packets that had no matching flow in the flow
* table that could not be sent to userspace (normally due to an overflow in
* one of the datapath's queues).
*/
struct dp_stats_percpu {
u64 n_hit;
u64 n_missed;
u64 n_lost;
seqcount_t seqlock;
};
/**
* struct datapath - datapath for flow-based packet switching
* @rcu: RCU callback head for deferred destruction.
* @list_node: Element in global 'dps' list.
* @ifobj: Represents /sys/class/net/<devname>/brif. Protected by RTNL.
* @n_flows: Number of flows currently in flow table.
* @table: Current flow table. Protected by genl_lock and RCU.
* @ports: Map from port number to &struct vport. %OVSP_LOCAL port
* always exists, other ports may be %NULL. Protected by RTNL and RCU.
* @port_list: List of all ports in @ports in arbitrary order. RTNL required
* to iterate or modify.
* @stats_percpu: Per-CPU datapath statistics.
*
* Context: See the comment on locking at the top of datapath.c for additional
* locking information.
*/
struct datapath {
struct rcu_head rcu;
struct list_head list_node;
struct kobject ifobj;
/* Flow table. */
struct flow_table __rcu *table;
/* Switch ports. */
struct vport __rcu *ports[DP_MAX_PORTS];
struct list_head port_list;
/* Stats. */
struct dp_stats_percpu __percpu *stats_percpu;
};
/**
* struct ovs_skb_cb - OVS data in skb CB
* @flow: The flow associated with this packet. May be %NULL if no flow.
* @tun_id: ID of the tunnel that encapsulated this packet. It is 0 if the
* @ip_summed: Consistently stores L4 checksumming status across different
* kernel versions.
* @csum_start: Stores the offset from which to start checksumming independent
* of the transport header on all kernel versions.
* packet was not received on a tunnel.
* @vlan_tci: Provides a substitute for the skb->vlan_tci field on kernels
* before 2.6.27.
*/
struct ovs_skb_cb {
struct sw_flow *flow;
__be64 tun_id;
#ifdef NEED_CSUM_NORMALIZE
enum csum_type ip_summed;
u16 csum_start;
#endif
#ifdef NEED_VLAN_FIELD
u16 vlan_tci;
#endif
};
#define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
datapath: Report kernel's flow key when passing packets up to userspace. One of the goals for Open vSwitch is to decouple kernel and userspace software, so that either one can be upgraded or rolled back independent of the other. To do this in full generality, it must be possible to change the kernel's idea of the flow key separately from the userspace version. This commit takes one step in that direction by making the kernel report its idea of the flow that a packet belongs to whenever it passes a packet up to userspace. This means that userspace can intelligently figure out what to do: - If userspace's notion of the flow for the packet matches the kernel's, then nothing special is necessary. - If the kernel has a more specific notion for the flow than userspace, for example if the kernel decoded IPv6 headers but userspace stopped at the Ethernet type (because it does not understand IPv6), then again nothing special is necessary: userspace can still set up the flow in the usual way. - If userspace has a more specific notion for the flow than the kernel, for example if userspace decoded an IPv6 header but the kernel stopped at the Ethernet type, then userspace can forward the packet manually, without setting up a flow in the kernel. (This case is bad from a performance point of view, but at least it is correct.) This commit does not actually make userspace flexible enough to handle changes in the kernel flow key structure, although userspace does now have enough information to do that intelligently. This will have to wait for later commits. This commit is bigger than it would otherwise be because it is rolled together with changing "struct odp_msg" to a sequence of Netlink attributes. The alternative, to do each of those changes in a separate patch, seemed like overkill because it meant that either we would have to introduce and then kill off Netlink attributes for in_port and tun_id, if Netlink conversion went first, or shove yet another variable-length header into the stuff already after odp_msg, if adding the flow key to odp_msg went first. This commit will slow down performance of checksumming packets sent up to userspace. I'm not entirely pleased with how I did it. I considered a couple of alternatives, but none of them seemed that much better. Suggestions welcome. Not changing anything wasn't an option, unfortunately. At any rate some slowdown will become unavoidable when OVS actually starts using Netlink instead of just Netlink framing. (Actually, I thought of one option where we could avoid that: make userspace do the checksum instead, by passing csum_start and csum_offset as part of what goes to userspace. But that's not perfect either.) Signed-off-by: Ben Pfaff <blp@nicira.com> Acked-by: Jesse Gross <jesse@nicira.com>
2011-01-24 14:59:57 -08:00
/**
* struct dp_upcall - metadata to include with a packet to send to userspace
* @cmd: One of %OVS_PACKET_CMD_*.
* @key: Becomes %OVS_PACKET_ATTR_KEY. Must be nonnull.
* @userdata: If nonnull, its u64 value is extracted and passed to userspace as
* %OVS_PACKET_ATTR_USERDATA.
* @pid: Netlink PID to which packet should be sent. If @pid is 0 then no
* packet is sent and the packet is accounted in the datapath's @n_lost
* counter.
*/
datapath: Report kernel's flow key when passing packets up to userspace. One of the goals for Open vSwitch is to decouple kernel and userspace software, so that either one can be upgraded or rolled back independent of the other. To do this in full generality, it must be possible to change the kernel's idea of the flow key separately from the userspace version. This commit takes one step in that direction by making the kernel report its idea of the flow that a packet belongs to whenever it passes a packet up to userspace. This means that userspace can intelligently figure out what to do: - If userspace's notion of the flow for the packet matches the kernel's, then nothing special is necessary. - If the kernel has a more specific notion for the flow than userspace, for example if the kernel decoded IPv6 headers but userspace stopped at the Ethernet type (because it does not understand IPv6), then again nothing special is necessary: userspace can still set up the flow in the usual way. - If userspace has a more specific notion for the flow than the kernel, for example if userspace decoded an IPv6 header but the kernel stopped at the Ethernet type, then userspace can forward the packet manually, without setting up a flow in the kernel. (This case is bad from a performance point of view, but at least it is correct.) This commit does not actually make userspace flexible enough to handle changes in the kernel flow key structure, although userspace does now have enough information to do that intelligently. This will have to wait for later commits. This commit is bigger than it would otherwise be because it is rolled together with changing "struct odp_msg" to a sequence of Netlink attributes. The alternative, to do each of those changes in a separate patch, seemed like overkill because it meant that either we would have to introduce and then kill off Netlink attributes for in_port and tun_id, if Netlink conversion went first, or shove yet another variable-length header into the stuff already after odp_msg, if adding the flow key to odp_msg went first. This commit will slow down performance of checksumming packets sent up to userspace. I'm not entirely pleased with how I did it. I considered a couple of alternatives, but none of them seemed that much better. Suggestions welcome. Not changing anything wasn't an option, unfortunately. At any rate some slowdown will become unavoidable when OVS actually starts using Netlink instead of just Netlink framing. (Actually, I thought of one option where we could avoid that: make userspace do the checksum instead, by passing csum_start and csum_offset as part of what goes to userspace. But that's not perfect either.) Signed-off-by: Ben Pfaff <blp@nicira.com> Acked-by: Jesse Gross <jesse@nicira.com>
2011-01-24 14:59:57 -08:00
struct dp_upcall_info {
u8 cmd;
datapath: Report kernel's flow key when passing packets up to userspace. One of the goals for Open vSwitch is to decouple kernel and userspace software, so that either one can be upgraded or rolled back independent of the other. To do this in full generality, it must be possible to change the kernel's idea of the flow key separately from the userspace version. This commit takes one step in that direction by making the kernel report its idea of the flow that a packet belongs to whenever it passes a packet up to userspace. This means that userspace can intelligently figure out what to do: - If userspace's notion of the flow for the packet matches the kernel's, then nothing special is necessary. - If the kernel has a more specific notion for the flow than userspace, for example if the kernel decoded IPv6 headers but userspace stopped at the Ethernet type (because it does not understand IPv6), then again nothing special is necessary: userspace can still set up the flow in the usual way. - If userspace has a more specific notion for the flow than the kernel, for example if userspace decoded an IPv6 header but the kernel stopped at the Ethernet type, then userspace can forward the packet manually, without setting up a flow in the kernel. (This case is bad from a performance point of view, but at least it is correct.) This commit does not actually make userspace flexible enough to handle changes in the kernel flow key structure, although userspace does now have enough information to do that intelligently. This will have to wait for later commits. This commit is bigger than it would otherwise be because it is rolled together with changing "struct odp_msg" to a sequence of Netlink attributes. The alternative, to do each of those changes in a separate patch, seemed like overkill because it meant that either we would have to introduce and then kill off Netlink attributes for in_port and tun_id, if Netlink conversion went first, or shove yet another variable-length header into the stuff already after odp_msg, if adding the flow key to odp_msg went first. This commit will slow down performance of checksumming packets sent up to userspace. I'm not entirely pleased with how I did it. I considered a couple of alternatives, but none of them seemed that much better. Suggestions welcome. Not changing anything wasn't an option, unfortunately. At any rate some slowdown will become unavoidable when OVS actually starts using Netlink instead of just Netlink framing. (Actually, I thought of one option where we could avoid that: make userspace do the checksum instead, by passing csum_start and csum_offset as part of what goes to userspace. But that's not perfect either.) Signed-off-by: Ben Pfaff <blp@nicira.com> Acked-by: Jesse Gross <jesse@nicira.com>
2011-01-24 14:59:57 -08:00
const struct sw_flow_key *key;
const struct nlattr *userdata;
u32 pid;
datapath: Report kernel's flow key when passing packets up to userspace. One of the goals for Open vSwitch is to decouple kernel and userspace software, so that either one can be upgraded or rolled back independent of the other. To do this in full generality, it must be possible to change the kernel's idea of the flow key separately from the userspace version. This commit takes one step in that direction by making the kernel report its idea of the flow that a packet belongs to whenever it passes a packet up to userspace. This means that userspace can intelligently figure out what to do: - If userspace's notion of the flow for the packet matches the kernel's, then nothing special is necessary. - If the kernel has a more specific notion for the flow than userspace, for example if the kernel decoded IPv6 headers but userspace stopped at the Ethernet type (because it does not understand IPv6), then again nothing special is necessary: userspace can still set up the flow in the usual way. - If userspace has a more specific notion for the flow than the kernel, for example if userspace decoded an IPv6 header but the kernel stopped at the Ethernet type, then userspace can forward the packet manually, without setting up a flow in the kernel. (This case is bad from a performance point of view, but at least it is correct.) This commit does not actually make userspace flexible enough to handle changes in the kernel flow key structure, although userspace does now have enough information to do that intelligently. This will have to wait for later commits. This commit is bigger than it would otherwise be because it is rolled together with changing "struct odp_msg" to a sequence of Netlink attributes. The alternative, to do each of those changes in a separate patch, seemed like overkill because it meant that either we would have to introduce and then kill off Netlink attributes for in_port and tun_id, if Netlink conversion went first, or shove yet another variable-length header into the stuff already after odp_msg, if adding the flow key to odp_msg went first. This commit will slow down performance of checksumming packets sent up to userspace. I'm not entirely pleased with how I did it. I considered a couple of alternatives, but none of them seemed that much better. Suggestions welcome. Not changing anything wasn't an option, unfortunately. At any rate some slowdown will become unavoidable when OVS actually starts using Netlink instead of just Netlink framing. (Actually, I thought of one option where we could avoid that: make userspace do the checksum instead, by passing csum_start and csum_offset as part of what goes to userspace. But that's not perfect either.) Signed-off-by: Ben Pfaff <blp@nicira.com> Acked-by: Jesse Gross <jesse@nicira.com>
2011-01-24 14:59:57 -08:00
};
extern struct notifier_block dp_device_notifier;
extern struct genl_multicast_group dp_vport_multicast_group;
extern int (*dp_ioctl_hook)(struct net_device *dev, struct ifreq *rq, int cmd);
void dp_process_received_packet(struct vport *, struct sk_buff *);
void dp_detach_port(struct vport *);
int dp_upcall(struct datapath *, struct sk_buff *,
const struct dp_upcall_info *);
const char *dp_name(const struct datapath *dp);
struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
u8 cmd);
int execute_actions(struct datapath *dp, struct sk_buff *skb);
#endif /* datapath.h */