Alexey Dobriyan [Wed, 26 Nov 2008 01:16:11 +0000 (17:16 -0800)]
netns xfrm: per-netns xfrm_state_all list
This is done to get
a) simple "something leaked" check
b) cover possible DoSes when other netns puts many, many xfrm_states
onto a list.
c) not miss "alien xfrm_state" check in some of list iterators in future.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Ingo Molnar [Wed, 26 Nov 2008 01:00:05 +0000 (17:00 -0800)]
atlx: fix warning in drivers/net/atlx/atl2.c
fix this warning:
drivers/net/atlx/atl2.c: In function ‘atl2_request_irq’:
drivers/net/atlx/atl2.c:644: warning: unused variable ‘err’
'err' is unused in the !CONFIG_PCI_MSI case.
Instead of further increasing the #ifdeffery in this function,
restructure the code a bit and get rid of the #ifdef. This
relies on the fact that pci_enable_msi() will always fail in
the !CONFIG_PCI_MSI case.
There should be no change in driver behavior.
Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: David S. Miller <davem@davemloft.net>
Ingo Molnar [Wed, 26 Nov 2008 00:59:21 +0000 (16:59 -0800)]
bluetooth: fix warning in net/bluetooth/rfcomm/sock.c
fix this warning:
net/bluetooth/rfcomm/sock.c: In function ‘rfcomm_sock_ioctl’:
net/bluetooth/rfcomm/sock.c:795: warning: unused variable ‘sk’
perhaps BT_DEBUG() should be improved to do printf format checking
instead of the #ifdef, but that looks quite intrusive: each bluetooth
.c file undefines the macro.
Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: David S. Miller <davem@davemloft.net>
Ingo Molnar [Wed, 26 Nov 2008 00:58:19 +0000 (16:58 -0800)]
ax25: fix warning in net/ax25/sysctl_net_ax25.c
fix this warning:
net/ax25/sysctl_net_ax25.c:27: warning: ‘min_ds_timeout’ defined but not used
net/ax25/sysctl_net_ax25.c:27: warning: ‘max_ds_timeout’ defined but not used
These are only used in the CONFIG_AX25_DAMA_SLAVE case.
Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: David S. Miller <davem@davemloft.net>
Ingo Molnar [Wed, 26 Nov 2008 00:57:30 +0000 (16:57 -0800)]
dccp: fix warning in net/dccp/options.c
this warning:
net/dccp/options.c: In function ‘dccp_parse_options’:
net/dccp/options.c:67: warning: ‘value’ may be used uninitialized in this function
is a bogus GCC warning. The compiler does not recognize the relation
between "value" and "mandatory" variables: the code flow can ever reach
the "out_invalid_option:" label if 'mandatory' is set to 1, and when
'mandatory' is non-zero, we'll always have 'value' initialized.
Help out the compiler by annotating the variable.
Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: David S. Miller <davem@davemloft.net>
Ingo Molnar [Wed, 26 Nov 2008 00:53:32 +0000 (16:53 -0800)]
mlx4: fix error path in drivers/net/mlx4/en_rx.c
this warning:
drivers/net/mlx4/en_rx.c: In function ‘mlx4_en_activate_rx_rings’:
drivers/net/mlx4/en_rx.c:412: warning: ‘err’ may be used uninitialized in this function
Triggers because 'err' is uninitialized in the following input
conditions: priv->rx_ring_num is zero and mlx4_en_fill_rx_buffers()
fails.
But even if ->rx_ring_num is nonzero, 'err' will be zero if
mlx4_en_fill_rx_buffers() fails and mlx4_en_activate_rx_rings() returns
success - incorrectly.
So it's best to keep the error code uptodate on mlx4_en_fill_rx_buffers()
calls as well.
Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: David S. Miller <davem@davemloft.net>
Ingo Molnar [Wed, 26 Nov 2008 00:49:37 +0000 (16:49 -0800)]
sunrpc: fix warning in net/sunrpc/xprtrdma/svc_rdma_transport.c
this warning:
net/sunrpc/xprtrdma/svc_rdma_transport.c: In function ‘svc_rdma_accept’:
net/sunrpc/xprtrdma/svc_rdma_transport.c:830: warning: ‘dma_mr_acc’ may be used uninitialized in this function
triggers because GCC does not recognize the (correct) flow connection
between need_dma_mr and dma_mr_acc.
Annotate it.
Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: David S. Miller <davem@davemloft.net>
Ingo Molnar [Wed, 26 Nov 2008 00:48:12 +0000 (16:48 -0800)]
niu: fix warnings in drivers/net/niu.c
these warnings:
drivers/net/niu.c: In function ‘serdes_init_niu_1g_serdes’:
drivers/net/niu.c:451: warning: ‘sig’ may be used uninitialized in this function
drivers/net/niu.c: In function ‘serdes_init_niu_10g_serdes’:
drivers/net/niu.c:550: warning: ‘sig’ may be used uninitialized in this function
triggers because GCC does not recognize that the max_retry loop
always initializes 'sig', due to max_retry != 0.
Annotate them.
Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: David S. Miller <davem@davemloft.net>
Daniel Lezcano [Wed, 26 Nov 2008 00:46:37 +0000 (16:46 -0800)]
netns: filter out uevent not belonging to init_net
This patch will filter out the uevent not related to the init_net.
Without this patch if a network device is created in a network
namespace with the same name as one network device belonging to the
initial network namespace (eg. eth0), when the network namespace
will die and the network device will be destroyed, an event will
be sent and catched by the udevd daemon. That will result to have
the real network device to be shutdown because the udevd/uevent are
not namespace aware.
Signed-off-by: Daniel Lezcano <dlezcano@fr.ibm.com> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Robert Olsson [Wed, 26 Nov 2008 00:43:52 +0000 (16:43 -0800)]
ixgbe: Naming interrupt vectors
Signed-off-by: Robert Olsson <robert.olsson@its.uu.se> Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Robert Olsson [Wed, 26 Nov 2008 00:41:57 +0000 (16:41 -0800)]
niu: Naming interrupt vectors.
A patch to put names on the niu interrupt vectors according the syntax below.
This is needed to assign correct affinity.
> So on a multiqueue card with 2 RX queues and 2 TX queues we'd
> have names like:
>
> eth0-rx-0
> eth0-rx-1
> eth0-tx-0
> eth0-tx-1
Signed-off-by: Robert Olsson <robert.olsson@its.uu.se> Tested-by: Jesper Dangaard Brouer <jdb@comx.dk> Signed-off-by: David S. Miller <davem@davemloft.net>
Jarek Poplawski [Tue, 25 Nov 2008 21:56:06 +0000 (13:56 -0800)]
pkt_sched: sch_api: Remove qdisc_list_lock
After implementing qdisc->ops->peek() there is no more calling
qdisc_tree_decrease_qlen() without rtnl_lock(), so qdisc_list_lock
added by commit: f6e0b239a2657ea8cb67f0d83d0bfdbfd19a481b "pkt_sched:
Fix qdisc list locking" can be removed.
Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Tue, 25 Nov 2008 09:04:03 +0000 (01:04 -0800)]
igb: loopback bits not correctly cleared from RCTL register
This change forces the bits to 0 by using an &= operation with an inverted
mask of all options instead of using an |= with a value of 0.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck [Tue, 25 Nov 2008 09:03:26 +0000 (01:03 -0800)]
igb: remove unneeded bit refrence when enabling jumbo frames
There is a reference to a Buffer Size extention bit that is unneded by
82575/82576 hardware. Since it is not needed it should be removed from the
code.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jeff Kirsher [Tue, 25 Nov 2008 09:02:08 +0000 (01:02 -0800)]
DCB: fix kconfig option
Since the netlink option for DCB is necessary to actually be useful,
simplified the Kconfig option. In addition, added useful help text for the
Kconfig option.
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Made usb_drivers reset_resume function point to hso_resume this
fixes problems a usb reset is done when the network interface
is left idle for a few minutes. Possibly reset_resume should
initialise hardware more but this works in the common case.
Signed-off-by: Denis Joseph Barrow <D.Barow@option.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Makes TIOCM ioctls for Data Carrier Detect & related functions
work like /drivers/serial/serial-core.c potentially needed
for pppd & similar user programs.
Signed-off-by: Denis Joseph Barrow <D.Barow@option.com> Signed-off-by: David S. Miller <davem@davemloft.net>
A new structure hso_mutex_table had to be declared statically
& used as as hso_device mutex_lock(&serial->parent->mutex) etc
is freed in hso_serial_open & hso_serial_close by kref_put while
the mutex is still in use.
This is a substantial change but should make the driver much stabler.
Signed-off-by: Denis Joseph Barrow <D.Barow@option.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Added check for IFF_UP in hso_resume, this should eliminate -EINVAL (-22)
errors caused from urb's being submitted twice, once by hso_resume
& once in hso_net_open, if suspend/resume USB power saving mode is enabled
Signed-off-by: Denis Joseph Barrow <D.Barow@option.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Moved serial_open_count in hso_serial_open to
prevent crashes owing to the serial structure being made NULL
when hso_serial_close is called even though hso_serial_open
returned -ENODEV, Alan Cox pointed out this happens,
also put in sanity check in hso_serial_close
to check for a valid serial structure which should prevent
the most reproducable crash in the driver when the hso device
is disconnected while in use.
Signed-off-by: Denis Joseph Barrow <D.Barow@option.com> Signed-off-by: David S. Miller <davem@davemloft.net>
As a concession to vendors who have to deal with one source for different
kernel versions, add a HAVE_NET_DEVICE_OPS so they don't end up hard
coding ifdef against kernel version.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Ilpo Järvinen [Tue, 25 Nov 2008 05:30:21 +0000 (21:30 -0800)]
tcp: handle shift/merge of cloned skbs too
This caused me to get repeatably:
tcpdump: pcap_loop: recvfrom: Bad address
Happens occassionally when I tcpdump my for-looped test xfers:
while [ : ]; do echo -n "$(date '+%s.%N') "; ./sendfile; sleep 20; done
Rest of the relevant commands:
ethtool -K eth0 tso off
tc qdisc add dev eth0 root netem drop 4%
tcpdump -n -s0 -i eth0 -w sacklog.all
Running net-next under kvm, connection goes to the same host
(basically just out of kvm). The connection itself works ok
and data gets sent without corruption even with a large
number of tests while tcpdump fails usually within less than
5 tests.
Whether it only happens because of this change or not, I
don't know for sure but it's the only thing with which
I've seen that error. The non-cloned variant works w/o it
for much longer time. I'm yet to debug where the error
actually comes from.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
Ilpo Järvinen [Tue, 25 Nov 2008 05:26:56 +0000 (21:26 -0800)]
tcp: Make shifting not clear the hints
The earlier version was just very basic one which is "playing
safe" by always clearing the hints. However, clearing of a hint
is extremely costly operation with large windows, so it must be
avoided at all cost whenever possible, there is a way with
shifting too achieve not-clearing.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
Ilpo Järvinen [Tue, 25 Nov 2008 05:20:15 +0000 (21:20 -0800)]
tcp: Try to restore large SKBs while SACK processing
During SACK processing, most of the benefits of TSO are eaten by
the SACK blocks that one-by-one fragment SKBs to MSS sized chunks.
Then we're in problems when cleanup work for them has to be done
when a large cumulative ACK comes. Try to return back to pre-split
state already while more and more SACK info gets discovered by
combining newly discovered SACK areas with the previous skb if
that's SACKed as well.
This approach has a number of benefits:
1) The processing overhead is spread more equally over the RTT
2) Write queue has less skbs to process (affect everything
which has to walk in the queue past the sacked areas)
3) Write queue is consistent whole the time, so no other parts
of TCP has to be aware of this (this was not the case with
some other approach that was, well, quite intrusive all
around).
4) Clean_rtx_queue can release most of the pages using single
put_page instead of previous PAGE_SIZE/mss+1 calls
In case a hole is fully filled by the new SACK block, we attempt
to combine the next skb too which allows construction of skbs
that are even larger than what tso split them to and it handles
hole per on every nth patterns that often occur during slow start
overshoot pretty nicely. Though this to be really useful also
a retransmission would have to get lost since cumulative ACKs
advance one hole at a time in the most typical case.
TODO: handle upwards only merging. That should be rather easy
when segment is fully sacked but I'm leaving that as future
work item (it won't make very large difference anyway since
this current approach already covers quite a lot of normal
cases).
I was earlier thinking of some sophisticated way of tracking
timestamps of the first and the last segment but later on
realized that it won't be that necessary at all to store the
timestamp of the last segment. The cases that can occur are
basically either:
1) ambiguous => no sensible measurement can be taken anyway
2) non-ambiguous is due to reordering => having the timestamp
of the last segment there is just skewing things more off
than does some good since the ack got triggered by one of
the holes (besides some substle issues that would make
determining right hole/skb even harder problem). Anyway,
it has nothing to do with this change then.
I choose to route some abnormal looking cases with goto noop,
some could be handled differently (eg., by stopping the
walking at that skb but again). In general, they either
shouldn't happen at all or are rare enough to make no difference
in practice.
In theory this change (as whole) could cause some macroscale
regression (global) because of cache misses that are taken over
the round-trip time but it gets very likely better because of much
less (local) cache misses per other write queue walkers and the
big recovery clearing cumulative ack.
Worth to note that these benefits would be very easy to get also
without TSO/GSO being on as long as the data is in pages so that
we can merge them. Currently I won't let that happen because
DSACK splitting at fragment that would mess up pcounts due to
sk_can_gso in tcp_set_skb_tso_segs. Once DSACKs fragments gets
avoided, we have some conditions that can be made less strict.
TODO: I will probably have to convert the excessive pointer
passing to struct sacktag_state... :-)
My testing revealed that considerable amount of skbs couldn't
be shifted because they were cloned (most likely still awaiting
tx reclaim)...
[The rest is considering future work instead since I got
repeatably EFAULT to tcpdump's recvfrom when I added
pskb_expand_head to deal with clones, so I separated that
into another, later patch]
...To counter that, I gave up on the fifth advantage:
5) When growing previous SACK block, less allocs for new skbs
are done, basically a new alloc is needed only when new hole
is detected and when the previous skb runs out of frags space
...which now only happens of if reclaim is fast enough to dispose
the clone before the SACK block comes in (the window is RTT long),
otherwise we'll have to alloc some.
With clones being handled I got these numbers (will be somewhat
worse without that), taken with fine-grained mibs:
Ilpo Järvinen [Tue, 25 Nov 2008 05:14:43 +0000 (21:14 -0800)]
tcp: make tcp_sacktag_one able to handle partial skb too
This is preparatory work for SACK combiner patch which may
have to count TCP state changes for only a part of the skb
because it will intentionally avoids splitting skb to SACKed
and not sacked parts.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
Ilpo Järvinen [Tue, 25 Nov 2008 05:12:28 +0000 (21:12 -0800)]
tcp: more aggressive skipping
I knew already when rewriting the sacktag that this condition
was too conservative, change it now since it prevent lot of
useless work (especially in the sack shifter decision code
that is being added by a later patch). This shouldn't change
anything really, just save some processing regardless of the
shifter.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
Ilpo Järvinen [Tue, 25 Nov 2008 05:03:43 +0000 (21:03 -0800)]
tcp: collapse more than two on retransmission
I always had thought that collapsing up to two at a time was
intentional decision to avoid excessive processing if 1 byte
sized skbs are to be combined for a full mtu, and consecutive
retransmissions would make the size of the retransmittee
double each round anyway, but some recent discussion made me
to understand that was not the case. Thus make collapse work
more and wait less.
It would be possible to take advantage of the shifting
machinery (added in the later patch) in the case of paged
data but that can be implemented on top of this change.
tcp_skb_is_last check is now provided by the loop.
I tested a bit (ss-after-idle-off, fill 4096x4096B xfer,
10s sleep + 4096 x 1byte writes while dropping them for
some a while with netem):
Eric Dumazet [Tue, 25 Nov 2008 00:07:50 +0000 (16:07 -0800)]
net: avoid a pair of dst_hold()/dst_release() in ip_push_pending_frames()
We can reduce pressure on dst entry refcount that slowdown UDP transmit
path on SMP machines. This pressure is visible on RTP servers when
delivering content to mediagateways, especially big ones, handling
thousand of streams. Several cpus send UDP frames to the same
destination, hence use the same dst entry.
This patch makes ip_push_pending_frames() steal the refcount its
callers had to take when filling inet->cork.dst.
This doesnt avoid all refcounting, but still gives speedups on SMP,
on UDP/RAW transmit path.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Mon, 24 Nov 2008 23:52:46 +0000 (15:52 -0800)]
net: avoid a pair of dst_hold()/dst_release() in ip_append_data()
We can reduce pressure on dst entry refcount that slowdown UDP transmit
path on SMP machines. This pressure is visible on RTP servers when
delivering content to mediagateways, especially big ones, handling
thousand of streams. Several cpus send UDP frames to the same
destination, hence use the same dst entry.
This patch makes ip_append_data() eventually steal the refcount its
callers had to take on the dst entry.
This doesnt avoid all refcounting, but still gives speedups on SMP,
on UDP/RAW transmit path
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
gen_kill_estimator() linear lists lookups are very slow, and e.g. while
deleting a large number of HTB classes soft lockups were reported. Here
is another try to fix this problem: this time internally, with rbtree,
so similarly to Jamal's hashing idea IIRC. (Looking for next hits could
be still optimized, but it's really fast as it is.)
Reported-by: Badalian Vyacheslav <slavon@bigtelecom.ru> Reported-by: Denys Fedoryshchenko <denys@visp.net.lb> Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Acked-by: Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
Patrick McHardy [Mon, 24 Nov 2008 23:46:08 +0000 (15:46 -0800)]
pkt_sched: sch_drr: fix drr_dequeue loop()
Jarek Poplawski points out:
If all child qdiscs of sch_drr are non-work-conserving (e.g. sch_tbf)
drr_dequeue() will busy-loop waiting for skbs instead of leaving the
job for a watchdog. Checking for list_empty() in each loop isn't
necessary either, because this can never be true except the first time.
Using non-work-conserving qdiscs as children of DRR makes no sense,
simply bail out in that case.
Reported-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Mon, 24 Nov 2008 08:09:29 +0000 (00:09 -0800)]
net: Make sure BHs are disabled in sock_prot_inuse_add()
The rule of calling sock_prot_inuse_add() is that BHs must
be disabled. Some new calls were added where this was not
true and this tiggers warnings as reported by Ilpo.
Fix this by adding explicit BH disabling around those call sites,
or moving sock_prot_inuse_add() call inside an existing BH disabled
section.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Mon, 24 Nov 2008 07:24:32 +0000 (23:24 -0800)]
eth: Declare an optimized compare_ether_addr_64bits() function
Linus mentioned we could try to perform long word operations, even
on potentially unaligned addresses, on x86 at least. David mentioned
the HAVE_EFFICIENT_UNALIGNED_ACCESS test to handle this on all
arches that have efficient unailgned accesses.
I tried this idea and got nice assembly on 32 bits:
And very nice assembly on 64 bits of course (one xor, one shl)
Nice oprofile improvement in eth_type_trans(), 0.17 % instead of 0.41 %,
expected since we remove 8 instructions on a fast path.
This patch implements a compare_ether_addr_64bits() function, that
uses the CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS ifdef to efficiently
perform the 6 bytes comparison on all capable arches.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 24 Nov 2008 04:01:59 +0000 (20:01 -0800)]
axnet_cs: Fix build after net device ops ne2k conversion.
Commit 4e4fd4e485ad63a9074ff09a9b53ffc7a5c594ec ("ne2k: convert to
net_device_ops") exported some ei_* symbols from the 8390 library,
but the axnet_cs driver defines local static versions of the same
functions.
Rename them to avoid the namespace conflict.
Reported by Stephen Rothwell.
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Mon, 24 Nov 2008 01:34:03 +0000 (17:34 -0800)]
net: Make sure BHs are disabled in sock_prot_inuse_add()
The rule of calling sock_prot_inuse_add() is that BHs must
be disabled. Some new calls were added where this was not
true and this tiggers warnings as reported by Ilpo.
Fix this by adding explicit BH disabling around those call sites.
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexey Dobriyan [Mon, 24 Nov 2008 01:26:26 +0000 (17:26 -0800)]
net: fix tunnels in netns after ndo_ changes
dev_net_set() should be the very first thing after alloc_netdev().
"ndo_" changes turned simple assignment (which is OK to do before netns
assignment) into quite non-trivial operation (which is not OK, init_net was
used). This leads to incomplete initialisation of tunnel device in netns.
BUG: unable to handle kernel NULL pointer dereference at 00000004
IP: [<c02efdb5>] ip6_tnl_exit_net+0x37/0x4f
*pde = 00000000
Oops: 0000 [#1] PREEMPT DEBUG_PAGEALLOC
last sysfs file: /sys/class/net/lo/operstate
Eric Dumazet [Mon, 24 Nov 2008 01:22:55 +0000 (17:22 -0800)]
net: Convert TCP/DCCP listening hash tables to use RCU
This is the last step to be able to perform full RCU lookups
in __inet_lookup() : After established/timewait tables, we
add RCU lookups to listening hash table.
The only trick here is that a socket of a given type (TCP ipv4,
TCP ipv6, ...) can now flight between two different tables
(established and listening) during a RCU grace period, so we
must use different 'nulls' end-of-chain values for two tables.
We define a large value :
#define LISTENING_NULLS_BASE (1U << 29)
So that slots in listening table are guaranteed to have different
end-of-chain values than slots in established table. A reader can
still detect it finished its lookup in the right chain.
Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
projects / linux-beck.git / log