This patch deals with local client processing.
Prefer LOCAL_OUT hook for scheduling connections from
local clients. LOCAL_IN is still supported if the packets are
not marked as processed in LOCAL_OUT. The idea to process
requests in LOCAL_OUT is to alter conntrack reply before
it is confirmed at POST_ROUTING. If the local requests are
processed in LOCAL_IN the conntrack can not be updated
and matching by state is impossible.
Add the following handlers:
- ip_vs_reply[46] at LOCAL_IN:99 to process replies from
remote real servers to local clients. Now when both
replies from remote real servers (ip_vs_reply*) and
local real servers (ip_vs_local_reply*) are handled
it is safe to remove the conn_out_get call from ip_vs_in
because it does not support related ICMP packets.
- ip_vs_local_request[46] at LOCAL_OUT:-98 to process
requests from local client
Handling in LOCAL_OUT causes some changes:
- as skb->dev, skb->protocol and skb->pkt_type are not defined
in LOCAL_OUT make sure we set skb->dev before calling icmpv6_send,
prefer skb_dst(skb) for struct net and remove the skb->protocol
checks from TUN transmitters.
[ horms@verge.net.au: removed trailing whitespace ]
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
This patch deals with local real servers:
- Add support for DNAT to local address (different real server port).
It needs ip_vs_out hook in LOCAL_OUT for both families because
skb->protocol is not set for locally generated packets and can not
be used to set 'af'.
- Skip packets in ip_vs_in marked with skb->ipvs_property because
ip_vs_out processing can be executed in LOCAL_OUT but we still
have the conn_out_get check in ip_vs_in.
- Ignore packets with inet->nodefrag from local stack
- Require skb_dst(skb) != NULL because we use it to get struct net
- Add support for changing the route to local IPv4 stack after DNAT
depending on the source address type. Local client sets output
route and the remote client sets input route. It looks like
IPv6 does not need such rerouting because the replies use
addresses from initial incoming header, not from skb route.
- All transmitters now have strict checks for the destination
address type: redirect from non-local address to local real
server requires NAT method, local address can not be used as
source address when talking to remote real server.
- Now LOCALNODE is not set explicitly as forwarding
method in real server to allow the connections to provide
correct forwarding method to the backup server. Not sure if
this breaks tools that expect to see 'Local' real server type.
If needed, this can be supported with new flag IP_VS_DEST_F_LOCAL.
Now it should be possible connections in backup that lost
their fwmark information during sync to be forwarded properly
to their daddr, even if it is local address in the backup server.
By this way backup could be used as real server for DR or TUN,
for NAT there are some restrictions because tuple collisions
in conntracks can create problems for the traffic.
- Call ip_vs_dst_reset when destination is updated in case
some real server IP type is changed between local and remote.
[ horms@verge.net.au: removed trailing whitespace ]
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Currently, ip_route_me_harder after ip_vs_out_icmp
is called even if packet is not related to IPVS connection.
Move it into handle_response_icmp. Also, force rerouting
if sending to local client because IPv4 stack uses addresses
from the route.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Create new function ip_vs_defrag_user to return correct
IP_DEFRAG_xxx user depending on the hooknum. It will be needed
when we add handlers in LOCAL_OUT.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
The recent change in IP_VS_XMIT_TUNNEL to set
CHECKSUM_NONE is not correct. After adding IPIP header
skb->csum becomes invalid but the CHECKSUM_PARTIAL
case must be supported. So, use skb_forward_csum() which is
most suitable for us to allow local clients to send IPIP
to remote real server.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Delivering locally ICMP from FORWARD hook is not supported.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
This patch is needed to avoid scheduling of
packets from local real server when we add ip_vs_in
in LOCAL_OUT hook to support local client.
Currently, when ip_vs_in can not find existing
connection it tries to create new one by calling ip_vs_schedule.
The default indication from ip_vs_schedule was if
connection was scheduled to real server. If real server is
not available we try to use the bypass forwarding method
or to send ICMP error. But in some cases we do not want to use
the bypass feature. So, add flag 'ignored' to indicate if
the scheduler ignores this packet.
Make sure we do not create new connections from replies.
We can hit this problem for persistent services and local real
server when ip_vs_in is added to LOCAL_OUT hook to handle
local clients.
Also, make sure ip_vs_schedule ignores SYN packets
for Active FTP DATA from local real server. The FTP DATA
connection should be created on SYN+ACK from client to assign
correct connection daddr.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Change skb->ipvs_property semantic. This is preparation
to support ip_vs_out processing in LOCAL_OUT. ipvs_property=1
will be used to avoid expensive lookups for traffic sent by
transmitters. Now when conntrack support is not used we call
ip_vs_notrack method to avoid problems in OUTPUT and
POST_ROUTING hooks instead of exiting POST_ROUTING as before.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Avoid full checksum calculation for apps that can provide
info whether csum was broken after payload mangling. For now only
ip_vs_ftp mangles payload and it updates the csum, so the full
recalculation is avoided for all packets.
Add CHECKSUM_UNNECESSARY for snat_handler (TCP and UDP).
It is needed to support SNAT from local address for the case
when csum is fully recalculated.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Fix CHECKSUM_PARTIAL handling. Tested for IPv4 TCP,
UDP not tested because it needs network card with HW CSUM support.
May be fixes problem where IPVS can not be used in virtual boxes.
Problem appears with DNAT to local address when the local stack
sends reply in CHECKSUM_PARTIAL mode.
Fix tcp_dnat_handler and udp_dnat_handler to provide
vaddr and daddr in right order (old and new IP) when calling
tcp_partial_csum_update/udp_partial_csum_update (CHECKSUM_PARTIAL).
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
If some of the underlying devices support it, enable vlan offload on
transmit for bridge devices. This allows senders to take advantage of the
hardware support, similar to other forms of acceleration.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that vlan acceleration is handled consistently regardless of usage,
it is possible to enable and disable it at will. This adds support for
Ethtool operations that change the offloading status for debugging
purposes, similar to other forms of hardware acceleration.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently each driver that is capable of vlan hardware acceleration
must be aware of the vlan groups that are configured and then pass
the stripped tag to a specialized receive function. This is
different from other types of hardware offload in that it places a
significant amount of knowledge in the driver itself rather keeping
it in the networking core.
This makes vlan offloading function more similarly to other forms
of offloading (such as checksum offloading or TSO) by doing the
following:
* On receive, stripped vlans are passed directly to the network
core, without attempting to check for vlan groups or reconstructing
the header if no group
* vlans are made less special by folding the logic into the main
receive routines
* On transmit, the device layer will add the vlan header in software
if the hardware doesn't support it, instead of spreading that logic
out in upper layers, such as bonding.
There are a number of advantages to this:
* Fixes all bugs with drivers incorrectly dropping vlan headers at once.
* Avoids having to disable VLAN acceleration when in promiscuous mode
(good for bridging since it always puts devices in promiscuous mode).
* Keeps VLAN tag separate until given to ultimate consumer, which
avoids needing to do header reconstruction as in tg3 unless absolutely
necessary.
* Consolidates common code in core networking.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A struct net_device always maps to zero or one vlan groups and we
always know the device when we are looking up a group. We currently
do a hash table lookup on the device to find the group but it is
much simpler to just store a pointer.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently users of hardware vlan accleration need to know whether
the device supports it before generating packets. However, vlan
acceleration will soon be available in a more flexible manner so
knowing ahead of time becomes much more difficult. This adds
a software fallback path for vlan packets on devices without the
necessary offloading support, similar to other types of hardware
accleration.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
VLAN_GROUP_ARRAY_LEN is simply the number of possible vlan VIDs.
Since vlan groups will soon be more of an implementation detail
for vlan devices, rename the constant to be descriptive of its
actual purpose.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
An upcoming commit will allow packets with hardware vlan acceleration
information to be passed though more parts of the network stack, including
packets trunked through the bridge. This adds support for matching and
filtering those packets through ebtables.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When CONFIG_NF_CONNTRACK_SECMARK is not set we accidentally attempt to use
the secmark fielf of struct nf_conn. Problem is when that config isn't set
the field doesn't exist. whoops. Wrap the incorrect usage in the config.
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: James Morris <jmorris@namei.org>
The current secmark code exports a secmark= field which just indicates if
there is special labeling on a packet or not. We drop this field as it
isn't particularly useful and instead export a new field secctx= which is
the actual human readable text label.
Signed-off-by: Eric Paris <eparis@redhat.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: James Morris <jmorris@namei.org>
The conntrack code can export the internal secid to userspace. These are
dynamic, can change on lsm changes, and have no meaning in userspace. We
should instead be sending lsm contexts to userspace instead. This patch sends
the secctx (rather than secid) to userspace over the netlink socket. We use a
new field CTA_SECCTX and stop using the the old CTA_SECMARK field since it did
not send particularly useful information.
Signed-off-by: Eric Paris <eparis@redhat.com>
Reviewed-by: Paul Moore <paul.moore@hp.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: James Morris <jmorris@namei.org>
Right now secmark has lots of direct selinux calls. Use all LSM calls and
remove all SELinux specific knowledge. The only SELinux specific knowledge
we leave is the mode. The only point is to make sure that other LSMs at
least test this generic code before they assume it works. (They may also
have to make changes if they do not represent labels as strings)
Signed-off-by: Eric Paris <eparis@redhat.com>
Acked-by: Paul Moore <paul.moore@hp.com>
Acked-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: James Morris <jmorris@namei.org>
Commit 4a5a5c73 attempted to pass decent error messages back to userspace for
netfilter errors. In xt_SECMARK.c however the patch screwed up and returned
on 0 (aka no error) early and didn't finish setting up secmark. This results
in a kernel BUG if you use SECMARK.
Signed-off-by: Eric Paris <eparis@redhat.com>
Acked-by: Paul Moore <paul.moore@hp.com>
Signed-off-by: James Morris <jmorris@namei.org>
This only happened when parse_extra_token was not passed
to ceph_parse_option() (hence, only happened in rbd).
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
These facilitate preallocation of pages so that we can encode into the pagelist
in an atomic context.
Signed-off-by: Greg Farnum <gregf@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
The rados block device (rbd), based on osdblk, creates a block device
that is backed by objects stored in the Ceph distributed object storage
cluster. Each device consists of a single metadata object and data
striped over many data objects.
The rbd driver supports read-only snapshots.
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
This factors out protocol and low-level storage parts of ceph into a
separate libceph module living in net/ceph and include/linux/ceph. This
is mostly a matter of moving files around. However, a few key pieces
of the interface change as well:
- ceph_client becomes ceph_fs_client and ceph_client, where the latter
captures the mon and osd clients, and the fs_client gets the mds client
and file system specific pieces.
- Mount option parsing and debugfs setup is correspondingly broken into
two pieces.
- The mon client gets a generic handler callback for otherwise unknown
messages (mds map, in this case).
- The basic supported/required feature bits can be expanded (and are by
ceph_fs_client).
No functional change, aside from some subtle error handling cases that got
cleaned up in the refactoring process.
Signed-off-by: Sage Weil <sage@newdream.net>
There is no point using RCU for dst we allocate for a very short time
(used once).
Change dst_release() to take DST_NOCACHE into account, but also change
skb_dst_set_noref() to force a refcount increment for such dst.
This is a _huge_ gain, because we dont waste memory to store xx thousand
of dsts. Instead of queueing them to RCU, we can free them instantly.
CPU caches can stay hot, re-using same memory blocks to hold temporary
dsts.
Note : remove unneeded smp_mb__before_atomic_dec(); in dst_release(),
since atomic_dec_return() implies a full memory barrier.
Stress test, 160.000.000 udp frames sent, IP route cache disabled
(DDOS).
Before:
real 0m38.091s
user 0m13.189s
sys 7m53.018s
After:
real 0m29.946s
user 0m12.157s
sys 7m40.605s
For reference, if IP route cache was enabled :
real 0m32.030s
user 0m10.521s
sys 8m15.243s
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces netif_alloc_netdev_queues which is called from
register_device instead of alloc_netdev_mq. This makes TX queue
allocation symmetric with RX allocation. Also, queue locks allocation
is done in netdev_init_one_queue. Change set_real_num_tx_queues to
fail if requested number < 1 or greater than number of allocated
queues.
Signed-off-by: Tom Herbert <therbert@google.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Clean up in RX queue allocation. In netif_set_real_num_rx_queues
return error on attempt to set zero queues, or requested number is
greater than number of allocated queues. In netif_alloc_rx_queues,
do BUG_ON if queue_count is zero.
Signed-off-by: Tom Herbert <therbert@google.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In alloc_netdev_mq fail if requested queue_count < 1.
Signed-off-by: Tom Herbert <therbert@google.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In an erlier patch I modified napi_poll so that devices with IFF_MASTER polled
the per_cpu list instead of the device list for napi. I did this because the
bonding driver has no napi instances to poll, it instead expects to check the
slave devices napi instances, which napi_poll was unaware of. Looking at this
more closely however, I now see this isn't strictly needed. As the bond driver
poll_controller calls the slaves poll_controller via netpoll_poll_dev, which
recursively calls poll_napi on each slave, allowing those napi instances to get
serviced. The earlier patch isn't at all harmfull, its just not needed, so lets
revert it to make the code cleaner. Sorry for the noise,
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reviewed-by: WANG Cong <amwang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Lists were initialized after the module was registered. Multiple ipvsadm
processes at module load triggered a race condition that resulted in a null
pointer dereference in do_ip_vs_get_ctl(). As a result, __ip_vs_mutex
was left locked preventing all further ipvsadm commands.
Signed-off-by: Eduardo J. Blanco <ejblanco@google.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
Convert inetdev_by_index() to not increment in_dev refcount.
Callers hold RCU or RTNL, and should not decrement in_dev refcount.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We hold RTNL in ip_mc_find_dev(), no need to touch device refcount.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The sunrpc cache_ioctl function does not need the big kernel lock
because it uses its own queue_lock already.
rpc_pipe_ioctl apparently should be using i_lock like the other
operations on the pipe file descriptor do.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
IPv6 encapsulation uses a bad source address for the tunnel.
i.e. VIP will be used as local-addr and encap. dst addr.
Decapsulation will not accept this.
Example
LVS (eth1 2003::2:0:1/96, VIP 2003::2:0:100)
(eth0 2003::1:0:1/96)
RS (ethX 2003::1:0:5/96)
tcpdump
2003::2:0:100 > 2003::1:0:5: IP6 (hlim 63, next-header TCP (6) payload length: 40) 2003::3:0:10.50991 > 2003::2:0:100.http: Flags [S], cksum 0x7312 (correct), seq 3006460279, win 5760, options [mss 1440,sackOK,TS val 1904932 ecr 0,nop,wscale 3], length 0
In Linux IPv6 impl. you can't have a tunnel with an any cast address
receiving packets (I have not tried to interpret RFC 2473)
To have receive capabilities the tunnel must have:
- Local address set as multicast addr or an unicast addr
- Remote address set as an unicast addr.
- Loop back addres or Link local address are not allowed.
This causes us to setup a tunnel in the Real Server with the
LVS as the remote address, here you can't use the VIP address since it's
used inside the tunnel.
Solution
Use outgoing interface IPv6 address (match against the destination).
i.e. use ip6_route_output() to look up the route cache and
then use ipv6_dev_get_saddr(...) to set the source address of the
encapsulated packet.
Additionally, cache the results in new destination
fields: dst_cookie and dst_saddr and properly check the
returned dst from ip6_route_output. We now add xfrm_lookup
call only for the tunneling method where the source address
is a local one.
Signed-off-by:Hans Schillstrom <hans.schillstrom@ericsson.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
This patch allows to listen to events that inform about
expectations destroyed.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Peter Zijlstra found a bug in the way softirq time is accounted in
VIRT_CPU_ACCOUNTING on this thread:
http://lkml.indiana.edu/hypermail//linux/kernel/1009.2/01366.html
The problem is, softirq processing uses local_bh_disable internally. There
is no way, later in the flow, to differentiate between whether softirq is
being processed or is it just that bh has been disabled. So, a hardirq when bh
is disabled results in time being wrongly accounted as softirq.
Looking at the code a bit more, the problem exists in !VIRT_CPU_ACCOUNTING
as well. As account_system_time() in normal tick based accouting also uses
softirq_count, which will be set even when not in softirq with bh disabled.
Peter also suggested solution of using 2*SOFTIRQ_OFFSET as irq count
for local_bh_{disable,enable} and using just SOFTIRQ_OFFSET while softirq
processing. The patch below does that and adds API in_serving_softirq() which
returns whether we are currently processing softirq or not.
Also changes one of the usages of softirq_count in net/sched/cls_cgroup.c
to in_serving_softirq.
Looks like many usages of in_softirq really want in_serving_softirq. Those
changes can be made individually on a case by case basis.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-2-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Usually the netpoll path, when preforming a napi poll can get away with just
polling all the napi instances of the configured device. Thats not the case for
the bonding driver however, as the napi instances which may wind up getting
flagged as needing polling after the poll_controller call don't belong to the
bonded device, but rather to the slave devices. Fix this by checking the device
in question for the IFF_MASTER flag, if set, we know we need to check the full
poll list for this cpu, rather than just the devices napi instance list.
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The bonding driver currently modifies the netpoll structure in its xmit path
while sending frames from netpoll. This is racy, as other cpus can access the
netpoll structure in parallel. Since the bonding driver points np->dev to a
slave device, other cpus can inadvertently attempt to send data directly to
slave devices, leading to improper locking with the bonding master, lost frames,
and deadlocks. This patch fixes that up.
This patch also removes the real_dev pointer from the netpoll structure as that
data is really only used by bonding in the poll_controller, and we can emulate
its behavior by check each slave for IS_UP.
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Change a few checks against the hardcoded broadcast address,
0xffffffff, to ipv4_is_lbcast(). Remove some existing checks
using ipv4_is_lbcast() that are now obviously superfluous.
Signed-off-by: Andy Walls <awalls@md.metrocast.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The patch below updates broken web addresses in the kernel
Signed-off-by: Justin P. Mattock <justinmattock@gmail.com>
Cc: Maciej W. Rozycki <macro@linux-mips.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Finn Thain <fthain@telegraphics.com.au>
Cc: Randy Dunlap <rdunlap@xenotime.net>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Dimitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Mike Frysinger <vapier.adi@gmail.com>
Acked-by: Ben Pfaff <blp@cs.stanford.edu>
Acked-by: Hans J. Koch <hjk@linutronix.de>
Reviewed-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Optimize processing in TIPC's bearer shutdown code, including:
1. Remove an unnecessary check to see if TIPC bearer's can exist.
2. Don't release spinlocks before calling a media-specific disabling
routine, since the routine can't sleep.
3. Make bearer_disable() operate directly on a struct bearer, instead
of needlessly taking a name and then mapping that to the struct.
Signed-off-by: Allan Stephens <allan.stephens@windriver.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Reviewed-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It's completely unused and exporting a static symbol
makes no sense and breaks the build.
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
In error cases when the ACL is insecure or we fail to allocate a new
struct sock, we jump to the "response" label. If so, "sk" will be
null and the kernel crashes.
Signed-off-by: Nathan Holstein <nathan.holstein@gmail.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
