Commit Graph

380 Commits

Author SHA1 Message Date
David S. Miller 0c1072ae02 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Conflicts:
	drivers/net/ethernet/freescale/fec_main.c
	drivers/net/ethernet/renesas/sh_eth.c
	net/ipv4/gre.c

The GRE conflict is between a bug fix (kfree_skb --> kfree_skb_list)
and the splitting of the gre.c code into seperate files.

The FEC conflict was two sets of changes adding ethtool support code
in an "!CONFIG_M5272" CPP protected block.

Finally the sh_eth.c conflict was between one commit add bits set
in the .eesr_err_check mask whilst another commit removed the
.tx_error_check member and assignments.

Signed-off-by: David S. Miller <davem@davemloft.net>
2013-07-03 14:55:13 -07:00
Julian Anastasov 4d0c875dcc ipvs: add sync_persist_mode flag
Add sync_persist_mode flag to reduce sync traffic
by syncing only persistent templates.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Tested-by: Aleksey Chudov <aleksey.chudov@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-06-26 18:01:46 +09:00
Alexander Frolkin eba3b5a787 ipvs: SH fallback and L4 hashing
By default the SH scheduler rejects connections that are hashed onto a
realserver of weight 0.  This patch adds a flag to make SH choose a
different realserver in this case, instead of rejecting the connection.

The patch also adds a flag to make SH include the source port (TCP, UDP,
SCTP) in the hash as well as the source address.  This basically allows
for deterministic round-robin load balancing (i.e., where any director
in a cluster of directors with identical config will send the same
packet the same way).

The flags are service flags (IP_VS_SVC_F_SCHED*) so that these options
can be set per service.  They are set using a new option to ipvsadm.

Signed-off-by: Alexander Frolkin <avf@eldamar.org.uk>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-06-26 18:01:46 +09:00
Julian Anastasov acaac5d8bb ipvs: drop SCTP connections depending on state
Drop SCTP connections under load (dropentry context) depending
on the protocol state, just like for TCP: INIT conns are
dropped immediately, established are dropped randomly while
connections in progress or shutdown are skipped.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-06-26 18:01:46 +09:00
Julian Anastasov 61e7c420b4 ipvs: replace the SCTP state machine
Convert the SCTP state table, so that it is more readable.
Change the states to be according to the diagram in RFC 2960
and add more states suitable for middle box. Still, such
change in states adds incompatibility if systems in sync
setup include this change and others do not include it.

With this change we also have proper transitions in INPUT-ONLY
mode (DR/TUN) where we see packets only from client. Now
we should not switch to 10-second CLOSED state at a time
when we should stay in ESTABLISHED state.

The short names for states are because we have 16-char space
in ipvsadm and 11-char limit for the connection list format.
It is a sequence of the TCP implementation where the longest
state name is ESTABLISHED.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-06-26 18:01:46 +09:00
Alexander Frolkin c6c96c1883 ipvs: sloppy TCP and SCTP
This adds support for sloppy TCP and SCTP modes to IPVS.

When enabled (sysctls net.ipv4.vs.sloppy_tcp and
net.ipv4.vs.sloppy_sctp), allows IPVS to create connection state on any
packet, not just a TCP SYN (or SCTP INIT).

This allows connections to fail over from one IPVS director to another
mid-flight.

Signed-off-by: Alexander Frolkin <avf@eldamar.org.uk>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-06-26 18:01:46 +09:00
Julian Anastasov bba54de5bd ipvs: provide iph to schedulers
Before now the schedulers needed access only to IP
addresses and it was easy to get them from skb by
using ip_vs_fill_iph_addr_only.

New changes for the SH scheduler will need the protocol
and ports which is difficult to get from skb for the
IPv6 case. As we have all the data in the iph structure,
to avoid the same slow lookups provide the iph to schedulers.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-06-26 18:01:45 +09:00
David S. Miller d98cae64e4 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Conflicts:
	drivers/net/wireless/ath/ath9k/Kconfig
	drivers/net/xen-netback/netback.c
	net/batman-adv/bat_iv_ogm.c
	net/wireless/nl80211.c

The ath9k Kconfig conflict was a change of a Kconfig option name right
next to the deletion of another option.

The xen-netback conflict was overlapping changes involving the
handling of the notify list in xen_netbk_rx_action().

Batman conflict resolution provided by Antonio Quartulli, basically
keep everything in both conflict hunks.

The nl80211 conflict is a little more involved.  In 'net' we added a
dynamic memory allocation to nl80211_dump_wiphy() to fix a race that
Linus reported.  Meanwhile in 'net-next' the handlers were converted
to use pre and post doit handlers which use a flag to determine
whether to hold the RTNL mutex around the operation.

However, the dump handlers to not use this logic.  Instead they have
to explicitly do the locking.  There were apparent bugs in the
conversion of nl80211_dump_wiphy() in that we were not dropping the
RTNL mutex in all the return paths, and it seems we very much should
be doing so.  So I fixed that whilst handling the overlapping changes.

To simplify the initial returns, I take the RTNL mutex after we try
to allocate 'tb'.

Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-19 16:49:39 -07:00
Julian Anastasov 06f3d7f973 ipvs: SCTP ports should be writable in ICMP packets
Make sure that SCTP ports are writable when embedded in ICMP
from client, so that ip_vs_nat_icmp can translate them safely.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-06-19 09:53:52 +09:00
Joe Perches fe2c6338fd net: Convert uses of typedef ctl_table to struct ctl_table
Reduce the uses of this unnecessary typedef.

Done via perl script:

$ git grep --name-only -w ctl_table net | \
  xargs perl -p -i -e '\
	sub trim { my ($local) = @_; $local =~ s/(^\s+|\s+$)//g; return $local; } \
        s/\b(?<!struct\s)ctl_table\b(\s*\*\s*|\s+\w+)/"struct ctl_table " . trim($1)/ge'

Reflow the modified lines that now exceed 80 columns.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-13 02:36:09 -07:00
Dan Carpenter a8241c6351 ipvs: info leak in __ip_vs_get_dest_entries()
The entry struct has a 2 byte hole after ->port and another 4 byte
hole after ->stats.outpkts.  You must have CAP_NET_ADMIN in your
namespace to hit this information leak.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2013-06-10 14:53:00 +02:00
David S. Miller 143554ace8 Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next
Conflicts:
	net/netfilter/nf_log.c

The conflict in nf_log.c is that in 'net' we added CONFIG_PROC_FS
protection around foo_proc_entry() calls to fix a build failure,
whereas in Pablo's tree a guard if() test around a call is
remove_proc_entry() was removed.  Trivially resolved.

Pablo Neira Ayuso says:

====================
The following patchset contains the first batch of
Netfilter/IPVS updates for your net-next tree, they are:

* Three patches with improvements and code refactorization
  for nfnetlink_queue, from Florian Westphal.

* FTP helper now parses replies without brackets, as RFC1123
  recommends, from Jeff Mahoney.

* Rise a warning to tell everyone about ULOG deprecation,
  NFLOG has been already in the kernel tree for long time
  and supersedes the old logging over netlink stub, from
  myself.

* Don't panic if we fail to load netfilter core framework,
  just bail out instead, from myself.

* Add cond_resched_rcu, used by IPVS to allow rescheduling
  while walking over big hashtables, from Simon Horman.

* Change type of IPVS sysctl_sync_qlen_max sysctl to avoid
  possible overflow, from Zhang Yanfei.

* Use strlcpy instead of strncpy to skip zeroing of already
  initialized area to write the extension names in ebtables,
  from Chen Gang.

* Use already existing per-cpu notrack object from xt_CT,
  from Eric Dumazet.

* Save explicit socket lookup in xt_socket now that we have
  early demux, also from Eric Dumazet.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-06 01:03:06 -07:00
David S. Miller 6bc19fb82d Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Merge 'net' bug fixes into 'net-next' as we have patches
that will build on top of them.

This merge commit includes a change from Emil Goode
(emilgoode@gmail.com) that fixes a warning that would
have been introduced by this merge.  Specifically it
fixes the pingv6_ops method ipv6_chk_addr() to add a
"const" to the "struct net_device *dev" argument and
likewise update the dummy_ipv6_chk_addr() declaration.

Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-05 16:37:30 -07:00
Jan Beulich a70b9641e6 ipvs: ip_vs_sh: fix build
kfree_rcu() requires offsetof(..., rcu_head) < 4096, which can
get violated with a sufficiently high CONFIG_IP_VS_SH_TAB_BITS.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2013-05-29 17:50:39 +02:00
Jiri Pirko 351638e7de net: pass info struct via netdevice notifier
So far, only net_device * could be passed along with netdevice notifier
event. This patch provides a possibility to pass custom structure
able to provide info that event listener needs to know.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>

v2->v3: fix typo on simeth
	shortened dev_getter
	shortened notifier_info struct name
v1->v2: fix notifier_call parameter in call_netdevice_notifier()
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-05-28 13:11:01 -07:00
Grzegorz Lyczba dc7b3eb900 ipvs: Fix reuse connection if real server is dead
Expire cached connection for new TCP/SCTP connection if real
server is down. Otherwise, IPVS uses the dead server for the
reused connection, instead of a new working one.

Signed-off-by: Grzegorz Lyczba <grzegorz.lyczba@gmail.com>
Acked-by: Hans Schillstrom <hans@schillstrom.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2013-05-27 13:00:45 +02:00
Zhang Yanfei 0799567424 ipvs: change type of netns_ipvs->sysctl_sync_qlen_max
This member of struct netns_ipvs is calculated from nr_free_buffer_pages
so change its type to unsigned long in case of overflow.  Also, type of
its related proc var sync_qlen_max and the return type of function
sysctl_sync_qlen_max() should be changed to unsigned long, too.

Besides, the type of ipvs_master_sync_state->sync_queue_len should be
changed to unsigned long accordingly.

Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Julian Anastasov <ja@ssi.bg>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-05-26 08:17:33 +09:00
Simon Horman a38e5e230e ipvs: use cond_resched_rcu() helper when walking connections
This avoids the situation where walking of a large number of connections
may prevent scheduling for a long time while also avoiding excessive
calls to rcu_read_unlock() and rcu_read_lock().

Note that in the case of !CONFIG_PREEMPT_RCU this will
add a call to cond_resched().

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2013-05-23 14:23:18 +02:00
David S. Miller 58717686cf Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Conflicts:
	drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
	drivers/net/ethernet/emulex/benet/be.h
	include/net/tcp.h
	net/mac802154/mac802154.h

Most conflicts were minor overlapping stuff.

The be2net driver brought in some fixes that added __vlan_put_tag
calls, which in net-next take an additional argument.

Signed-off-by: David S. Miller <davem@davemloft.net>
2013-04-30 03:55:20 -04:00
Hans Schillstrom f7a1dd6e3a ipvs: ip_vs_sip_fill_param() BUG: bad check of return value
The reason for this patch is crash in kmemdup
caused by returning from get_callid with uniialized
matchoff and matchlen.

Removing Zero check of matchlen since it's done by ct_sip_get_header()

BUG: unable to handle kernel paging request at ffff880457b5763f
IP: [<ffffffff810df7fc>] kmemdup+0x2e/0x35
PGD 27f6067 PUD 0
Oops: 0000 [#1] PREEMPT SMP
Modules linked in: xt_state xt_helper nf_conntrack_ipv6 nf_defrag_ipv6 ip6table_mangle xt_connmark xt_conntrack ip6_tables nf_conntrack_ftp ip_vs_ftp nf_nat xt_tcpudp iptable_mangle xt_mark ip_tables x_tables ip_vs_rr ip_vs_lblcr ip_vs_pe_sip ip_vs nf_conntrack_sip nf_conntrack bonding igb i2c_algo_bit i2c_core
CPU 5
Pid: 0, comm: swapper/5 Not tainted 3.9.0-rc5+ #5                  /S1200KP
RIP: 0010:[<ffffffff810df7fc>]  [<ffffffff810df7fc>] kmemdup+0x2e/0x35
RSP: 0018:ffff8803fea03648  EFLAGS: 00010282
RAX: ffff8803d61063e0 RBX: 0000000000000003 RCX: 0000000000000003
RDX: 0000000000000003 RSI: ffff880457b5763f RDI: ffff8803d61063e0
RBP: ffff8803fea03658 R08: 0000000000000008 R09: 0000000000000011
R10: 0000000000000011 R11: 00ffffffff81a8a3 R12: ffff880457b5763f
R13: ffff8803d67f786a R14: ffff8803fea03730 R15: ffffffffa0098e90
FS:  0000000000000000(0000) GS:ffff8803fea00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffff880457b5763f CR3: 0000000001a0c000 CR4: 00000000001407e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process swapper/5 (pid: 0, threadinfo ffff8803ee18c000, task ffff8803ee18a480)
Stack:
 ffff8803d822a080 000000000000001c ffff8803fea036c8 ffffffffa000937a
 ffffffff81f0d8a0 000000038135fdd5 ffff880300000014 ffff880300110000
 ffffffff150118ac ffff8803d7e8a000 ffff88031e0118ac 0000000000000000
Call Trace:
 <IRQ>

 [<ffffffffa000937a>] ip_vs_sip_fill_param+0x13a/0x187 [ip_vs_pe_sip]
 [<ffffffffa007b209>] ip_vs_sched_persist+0x2c6/0x9c3 [ip_vs]
 [<ffffffff8107dc53>] ? __lock_acquire+0x677/0x1697
 [<ffffffff8100972e>] ? native_sched_clock+0x3c/0x7d
 [<ffffffff8100972e>] ? native_sched_clock+0x3c/0x7d
 [<ffffffff810649bc>] ? sched_clock_cpu+0x43/0xcf
 [<ffffffffa007bb1e>] ip_vs_schedule+0x181/0x4ba [ip_vs]
...

Signed-off-by: Hans Schillstrom <hans@schillstrom.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-04-29 11:35:30 -04:00
Simon Horman 38561437d0 ipvs: Use network byte order for sync message size
struct ip_vs_sync_mesg and ip_vs_sync_mesg_v0 are both sent across the wire
and used internally to store IPVS synchronisation messages.

Up until now the scheme used has been to convert the size field
to network byte order before sending a message on the wire and
convert it to host byte order when sending a message.

This patch changes that scheme to always treat the field
as being network byte order. This seems appropriate as
the structure is sent across the wire. And by consistently
treating the field has network byte order it is now possible
to take advantage of sparse to flag any future miss-use.

Acked-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-23 11:43:06 +09:00
Dan Carpenter 4bfbfbf91f ipvs: off by one in set_sctp_state()
The sctp_events[] come from sch->type in set_sctp_state().  They are
between 0-255 so that means we need 256 elements in the array.

I believe that because of how the code is aligned there is normally a
hole after sctp_events[] so this patch doesn't actually change anything.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-23 11:43:06 +09:00
Simon Horman 9c37510b8f ipvs: Use min3() in ip_vs_dbg_callid()
There are two motivations for this:

1. It improves readability to my eyes
2. Using nested min() calls results in a shadowed _min1 variable,
   which is a bit untidy. Sparse complained about this.

I have also replaced (size_t)64 with a variable of type size_t and value 64.
This also improves readability to my eyes.

Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-23 11:43:06 +09:00
Simon Horman 9fd0fa7ac3 ipvs: Avoid shadowing net variable in ip_vs_leave()
Flagged by sparse.
Compile and sparse tested only.

Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-23 11:43:06 +09:00
Julian Anastasov 0a925864c1 ipvs: fix sparse warnings for some parameters
Some service fields are in network order:

- netmask: used once in network order and also as prefix len for IPv6
- port

Other parameters are in host order:

- struct ip_vs_flags: flags and mask moved between user and kernel only
- sync state: moved between user and kernel only
- syncid: sent over network as single octet

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-23 11:43:05 +09:00
Julian Anastasov f33c8b94fd ipvs: fix sparse warnings in lblc and lblcr
kbuild test robot reports for sparse warnings in
commits c2a4ffb70e ("ipvs: convert lblc scheduler to rcu")
and c5549571f9 ("ipvs: convert lblcr scheduler to rcu").

Fix it by removing extra __rcu annotation.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-23 11:43:05 +09:00
Julian Anastasov 371990eeec ipvs: fix the remaining sparse warnings in ip_vs_ctl.c
- RCU annotations for ip_vs_info_seq_start and _stop
- __percpu for cpustats
- properly dereference svc->pe in ip_vs_genl_fill_service

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-23 11:43:05 +09:00
Julian Anastasov 7cf2eb7bcc ipvs: fix sparse warnings for ip_vs_conn listing
kbuild test robot reports for sparse warnings
in commit 088339a57d ("ipvs: convert connection locking"):

net/netfilter/ipvs/ip_vs_conn.c:962:13: warning: context imbalance
	in 'ip_vs_conn_array' - wrong count at exit
include/linux/rcupdate.h:326:30: warning: context imbalance in
	'ip_vs_conn_seq_next' - unexpected unlock
include/linux/rcupdate.h:326:30: warning: context imbalance in
	'ip_vs_conn_seq_stop' - unexpected unlock

Fix it by running ip_vs_conn_array under RCU lock
to avoid conditional locking and by adding proper RCU
annotations.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-23 11:43:05 +09:00
Julian Anastasov d717bb2a98 ipvs: properly dereference dest_dst in ip_vs_forget_dev
Use rcu_dereference_protected to resolve
sparse warning, found by kbuild test robot:

net/netfilter/ipvs/ip_vs_ctl.c:1464:35: warning: dereference of
noderef expression

Problem from commit 026ace060d
("ipvs: optimize dst usage for real server")

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-23 11:43:05 +09:00
Julian Anastasov ac69269a45 ipvs: do not disable bh for long time
We used a global BH disable in LOCAL_OUT hook.
Add _bh suffix to all places that need it and remove
the disabling from LOCAL_OUT and sync code.

Functions like ip_defrag need protection from
BH, so add it. As for nf_nat_mangle_tcp_packet, it needs
RCU lock.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:58 +02:00
Julian Anastasov ceec4c3816 ipvs: convert services to rcu
This is the final step in RCU conversion.

Things that are removed:

- svc->usecnt: now svc is accessed under RCU read lock
- svc->inc: and some unused code
- ip_vs_bind_pe and ip_vs_unbind_pe: no ability to replace PE
- __ip_vs_svc_lock: replaced with RCU
- IP_VS_WAIT_WHILE: now readers lookup svcs and dests under
	RCU and work in parallel with configuration

Other changes:

- before now, a RCU read-side critical section included the
calling of the schedule method, now it is extended to include
service lookup
- ip_vs_svc_table and ip_vs_svc_fwm_table are now using hlist
- svc->pe and svc->scheduler remain to the end (of grace period),
	the schedulers are prepared for such RCU readers
	even after done_service is called but they need
	to use synchronize_rcu because last ip_vs_scheduler_put
	can happen while RCU read-side critical sections
	use an outdated svc->scheduler pointer
- as planned, update_service is removed
- empty services can be freed immediately after grace period.
	If dests were present, the services are freed from
	the dest trash code

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:58 +02:00
Julian Anastasov 413c2d04e9 ipvs: convert dests to rcu
In previous commits the schedulers started to access
svc->destinations with _rcu list traversal primitives
because the IP_VS_WAIT_WHILE macro still plays the role of
grace period. Now it is time to finish the updating part,
i.e. adding and deleting of dests with _rcu suffix before
removing the IP_VS_WAIT_WHILE in next commit.

We use the same rule for conns as for the
schedulers: dests can be searched in RCU read-side critical
section where ip_vs_dest_hold can be called by ip_vs_bind_dest.

Some things are not perfect, for example, calling
functions like ip_vs_lookup_dest from updating code under
RCU, just because we use some function both from reader
and from updater.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:57 +02:00
Julian Anastasov ba3a3ce14e ipvs: convert sched_lock to spin lock
As all read_locks are gone spin lock is preferred.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:56 +02:00
Julian Anastasov ed3ffc4e48 ipvs: do not expect result from done_service
This method releases the scheduler state,
it can not fail. Such change will help to properly
replace the scheduler in following patch.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:56 +02:00
Julian Anastasov 578bc3ef1e ipvs: reorganize dest trash
All dests will go to trash, no exceptions.
But we have to use new list node t_list for this, due
to RCU changes in following patches. Dests will wait there
initial grace period and later all conns and schedulers to
put their reference. The dests don't get reference for
staying in dest trash as before.

	As result, we do not load ip_vs_dest_put with
extra checks for last refcnt and the schedulers do not
need to play games with atomic_inc_not_zero while
selecting best destination.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:55 +02:00
Julian Anastasov 08cb2d032f ipvs: convert wrr scheduler to rcu
The schedule method now needs _rcu list-traversal
primitive for svc->destinations. As the weight for some
dest can be reduced during dest selection, change the
algorithm to check weights by using minimum weights in the
1 .. max_weight-(di-1) range, with the same step (di). By this
way we ensure that there will be always a weight >= 1 check
before claiming that all destinations are overloaded.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:54 +02:00
Julian Anastasov b310faad3e ipvs: convert wlc scheduler to rcu
The schedule method now needs _rcu list-traversal
primitive for svc->destinations.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:54 +02:00
Julian Anastasov 1acb7f6761 ipvs: convert sh scheduler to rcu
Use the 3 new methods to reassign dests.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:53 +02:00
Julian Anastasov 9be52aba7a ipvs: convert sed scheduler to rcu
The schedule method now needs _rcu list-traversal
primitive for svc->destinations.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:52 +02:00
Julian Anastasov c0d0c0a1c0 ipvs: convert rr scheduler to rcu
The schedule method now needs _rcu list-traversal
primitive for svc->destinations. As the previous entry
could be unlinked, limit the list traversals to 2 when
lookup started from previous entry.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:52 +02:00
Julian Anastasov f92ea8f096 ipvs: convert nq scheduler to rcu
The schedule method now needs _rcu list-traversal
primitive for svc->destinations.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:51 +02:00
Julian Anastasov 4ebd288b69 ipvs: convert lc scheduler to rcu
The schedule method now needs _rcu list-traversal
primitive for svc->destinations.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:50 +02:00
Julian Anastasov c5549571f9 ipvs: convert lblcr scheduler to rcu
The schedule method now needs _rcu list-traversal
primitive for svc->destinations. The read_lock for sched_lock is
removed. The set.lock is removed because now it is used in
rare cases, mostly under sched_lock.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:50 +02:00
Julian Anastasov c2a4ffb70e ipvs: convert lblc scheduler to rcu
The schedule method now needs _rcu list-traversal
primitive for svc->destinations. The read_lock for sched_lock is
removed. Use a dead flag to prevent new entries to be created
while scheduler is reclaimed. Use hlist for the hash table.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:49 +02:00
Julian Anastasov 8f3d0023b9 ipvs: convert dh scheduler to rcu
Use the new add_dest and del_dest methods
to reassign dests.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:49 +02:00
Julian Anastasov fca9c20ae1 ipvs: add ip_vs_dest_hold and ip_vs_dest_put
ip_vs_dest_hold will be used under RCU lock
while ip_vs_dest_put can be called even after dest
is removed from service, as it happens for conns and
some schedulers.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:48 +02:00
Julian Anastasov 6b6df46663 ipvs: preparations for using rcu in schedulers
Allow schedulers to use rcu_dereference when
returning destination on lookup. The RCU read-side critical
section will allow ip_vs_bind_dest to get dest refcnt as
preparation for the step where destinations will be
deleted without an IP_VS_WAIT_WHILE guard that holds the
packet processing during update.

	Add new optional scheduler methods add_dest,
del_dest and upd_dest. For now the methods are called
together with update_service but update_service will be
removed in a following change.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:47 +02:00
Julian Anastasov 71dfa982f1 ipvs: change ip_vs_sched_lock to mutex
The global list with schedulers ip_vs_schedulers
is accessed only from user context - configuration and
scheduler module [un]registration. Use ip_vs_sched_mutex
instead.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:47 +02:00
Julian Anastasov 9a05475ceb ipvs: avoid kmem_cache_zalloc in ip_vs_conn_new
We have many fields to set and few to reset,
use kmem_cache_alloc instead to save some cycles.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:46 +02:00
Julian Anastasov 1845ed0bb2 ipvs: reorder keys in connection structure
__ip_vs_conn_in_get and ip_vs_conn_out_get are
hot places. Optimize them, so that ports are matched first.
By moving net and fwmark below, on 32-bit arch we can fit
caddr in 32-byte cache line and all addresses in 64-byte
cache line.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
2013-04-02 00:23:45 +02:00