Patrick McHardy [Tue, 21 Mar 2006 06:40:54 +0000 (22:40 -0800)]
[XFRM]: Fix aevent related crash
When xfrm_user isn't loaded xfrm_nl is NULL, which makes IPsec crash because
xfrm_aevent_is_on passes the NULL pointer to netlink_has_listeners as socket.
A second problem is that the xfrm_nl pointer is not cleared when the socket
is releases at module unload time.
Protect references of xfrm_nl from outside of xfrm_user by RCU, check
that the socket is present in xfrm_aevent_is_on and set it to NULL
when unloading xfrm_user.
Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
Rick Jones [Tue, 21 Mar 2006 06:40:29 +0000 (22:40 -0800)]
[TCP]: sysctl to allow TCP window > 32767 sans wscale
Back in the dark ages, we had to be conservative and only allow 15-bit
window fields if the window scale option was not negotiated. Some
ancient stacks used a signed 16-bit quantity for the window field of
the TCP header and would get confused.
Those days are long gone, so we can use the full 16-bits by default
now.
There is a sysctl added so that we can still interact with such old
stacks
Signed-off-by: Rick Jones <rick.jones2@hp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Neil Horman [Tue, 21 Mar 2006 06:40:03 +0000 (22:40 -0800)]
[IPV4] ARP: Documentation for new arp_accept sysctl variable.
As John pointed out, I had not added documentation to describe the
arp_accpet sysctl that I posted in my last patch. This patch adds
that documentation.
Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jeff Mahoney [Tue, 21 Mar 2006 06:39:21 +0000 (22:39 -0800)]
[TG3]: netif_carrier_off runs too early; could still be queued when init fails
Move the netif_carrier_off() call from tg3_init_one()->
tg3_init_link_config() to tg3_open() as is the convention for most other
network drivers.
I was getting a panic after a tg3 device failed to initialize due to DMA
failure. The oops pointed to the link watch queue with spinlock debugging
enabled. Without spinlock debugging, the Oops didn't occur.
I suspect that the link event was getting queued but not executed until
after the DMA test had failed and the device was freed. The link event was
then operating on freed memory, which could contain anything. With this
patch applied, the Oops no longer occurs.
[ Based upon feedback from Michael Chan, we move netif_carrier_off()
to the end of tg3_init_one() instead of moving it to tg3_open() -DaveM ]
Signed-off-by: Jeff Mahoney <jeffm@suse.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Per Liden [Tue, 21 Mar 2006 06:38:14 +0000 (22:38 -0800)]
[TIPC]: Reduce stack usage
The node_map struct can be quite large (516 bytes) and allocating two of
them on the stack is not a good idea since we might only have a 4K stack
to start with.
Signed-off-by: Per Liden <per.liden@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Adrian Bunk [Tue, 21 Mar 2006 06:37:52 +0000 (22:37 -0800)]
[TIPC]: Cleanups
This patch contains the following possible cleanups:
- make needlessly global code static
- #if 0 the following unused global functions:
- name_table.c: tipc_nametbl_print()
- name_table.c: tipc_nametbl_dump()
- net.c: tipc_net_next_node()
Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Per Liden <per.liden@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Sam Ravnborg [Tue, 21 Mar 2006 06:37:04 +0000 (22:37 -0800)]
[TIPC]: Remove inlines from *.c
With reference to latest discussions on linux-kernel with respect to
inline here is a patch for tipc to remove all inlines as used in
the .c files. See also chapter 14 in Documentation/CodingStyle.
Before:
text data bss dec hex filename
102990 5292 1752 110034 1add2 tipc.o
Now:
text data bss dec hex filename
101190 5292 1752 108234 1a6ca tipc.o
This is a nice text size reduction which will improve icache usage.
In some cases bigger (> 4 lines) functions where declared inline
and used in many places, they are most probarly no longer inlined by gcc
resulting in the size reduction.
There are several one liners that no longer are declared inline, but gcc
should inline these just fine without the inline hint.
With this patch applied one warning is added about an unused static
function - that was hidded by utilising inline before.
The function in question were kept so this patch is solely a
inline removal patch.
Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Per Liden <per.liden@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Sam Ravnborg [Tue, 21 Mar 2006 06:36:47 +0000 (22:36 -0800)]
[TIPC]: Fix simple sparse warnings
Tried to run the new tipc stack through sparse.
Following patch fixes all cases where 0 was used
as replacement of NULL.
Use NULL to document this is a pointer and to silence sparse.
This brough sparse warning count down with 127 to 24 warnings.
Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Per Liden <per.liden@ericsson.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Tue, 21 Mar 2006 06:36:21 +0000 (22:36 -0800)]
[NETFILTER]: Fix warnings in ip_nat_snmp_basic.c
net/ipv4/netfilter/ip_nat_snmp_basic.c: In function 'asn1_header_decode':
net/ipv4/netfilter/ip_nat_snmp_basic.c:248: warning: 'len' may be used uninitialized in this function
net/ipv4/netfilter/ip_nat_snmp_basic.c:248: warning: 'def' may be used uninitialized in this function
net/ipv4/netfilter/ip_nat_snmp_basic.c: In function 'snmp_translate':
net/ipv4/netfilter/ip_nat_snmp_basic.c:672: warning: 'l' may be used uninitialized in this function
net/ipv4/netfilter/ip_nat_snmp_basic.c:668: warning: 'type' may be used uninitialized in this function
Signed-off-by: David S. Miller <davem@davemloft.net>
Sam Ravnborg [Tue, 21 Mar 2006 06:34:52 +0000 (22:34 -0800)]
[WAN]: fix section mismatch warning in sbni
In latest -mm sbni gives following warning: WARNING:
drivers/net/wan/sbni.o - Section mismatch: reference to \ .init.data:
from .text between 'init_module' (at offset 0x14ef) and \
'cleanup_module'
The warning is caused by init_module() calling a function declared
__init. Declare init_module() __init too to fix warning.
Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Arjan van de Ven [Tue, 21 Mar 2006 06:33:17 +0000 (22:33 -0800)]
[NET] sem2mutex: net/
Semaphore to mutex conversion.
The conversion was generated via scripts, and the result was validated
automatically via a script as well.
Signed-off-by: Arjan van de Ven <arjan@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Arjan van de Ven [Tue, 21 Mar 2006 06:32:53 +0000 (22:32 -0800)]
[IRDA] sem2mutex: drivers/net/irda
Semaphore to mutex conversion.
The conversion was generated via scripts, and the result was validated
automatically via a script as well.
Signed-off-by: Arjan van de Ven <arjan@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Get rid of the old __dev_put macro that is just a hold over from pre 2.6
kernel. And turn dev_hold into an inline instead of a macro.
Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
[DCCP]: Use sk->sk_prot->max_header consistently for non-data packets
Using this also provides opportunities for introducing
inet_csk_alloc_skb that would call alloc_skb, account it to the sock
and skb_reserve(max_header), but I'll leave this for later, for now
using sk_prot->max_header consistently is enough.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Michael Chan [Tue, 21 Mar 2006 06:28:41 +0000 (22:28 -0800)]
[TG3]: Add new one-shot MSI handler
Support one-shot MSI on 5787.
This one-shot MSI idea is credited to David Miller. In this mode, MSI
disables itself automatically after it is generated, saving the driver
a register access to disable it for NAPI.
Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Michael Chan [Tue, 21 Mar 2006 06:28:05 +0000 (22:28 -0800)]
[TG3]: Add new hard_start_xmit
Support 5787 hardware TSO using a new flag TG3_FLG2_HW_TSO_2.
Since the TSO interface is slightly different and these chips have
finally fixed the 4GB DMA problem and do not have the 40-bit DMA
problem, a new hard_start_xmit is used for these chips. All previous
chips will use the old hard_start_xmit that is now renamed
tg3_start_xmit_dma_bug().
Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Benjamin LaHaise [Tue, 21 Mar 2006 06:27:12 +0000 (22:27 -0800)]
[NET]: use fget_light() in net/socket.c
Here's an updated copy of the patch to use fget_light in net/socket.c.
Rerunning the tests show a drop of ~80Mbit/s on average, which looks
bad until you see the drop in cpu usage from ~89% to ~82%. That will
get fixed in another patch...
Alpt [Tue, 21 Mar 2006 06:26:17 +0000 (22:26 -0800)]
[NET] rtnetlink: Add RTPROT entry for Netsukuku.
The Netsukuku daemon is using the same number to mark its routes, you
can see it here:
http://hinezumilabs.org/cgi-bin/viewcvs.cgi/netsukuku/src/krnl_route.h?rev=HEAD&content-type=text/vnd.viewcvs-markup
Signed-off-by: David S. Miller <davem@davemloft.net>
[NET]: Move destructor from neigh->ops to neigh_params
struct neigh_ops currently has a destructor field, which no in-kernel
drivers outside of infiniband use. The infiniband/ulp/ipoib in-tree
driver stashes some info in the neighbour structure (the results of
the second-stage lookup from ARP results to real link-level path), and
it uses neigh->ops->destructor to get a callback so it can clean up
this extra info when a neighbour is freed. We've run into problems
with this: since the destructor is in an ops field that is shared
between neighbours that may belong to different net devices, there's
no way to set/clear it safely.
The following patch moves this field to neigh_parms where it can be
safely set, together with its twin neigh_setup. Two additional
patches in the patch series update ipoib to use this new interface.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Baruch Even [Tue, 21 Mar 2006 06:22:47 +0000 (22:22 -0800)]
[TCP] H-TCP: Account for delayed-ACKs
Account for delayed-ACKs in H-TCP.
Delayed-ACKs cause H-TCP to be less aggressive than its design calls
for. It is especially true when the receiver is a Linux machine where
the average delayed ack is over 3 packets with values of 7 not unheard
of.
Signed-off-By: Baruch Even <baruch@ev-en.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Baruch Even [Tue, 21 Mar 2006 06:22:20 +0000 (22:22 -0800)]
[TCP] H-TCP: Use msecs_to_jiffies
Use functions to calculate jiffies from milliseconds and not the old,
crude method of dividing HZ by a value. Ensures more accurate values
even in the face of strange HZ values.
Signed-off-By: Baruch Even <baruch@ev-en.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Evgeniy Polyakov [Tue, 21 Mar 2006 06:21:40 +0000 (22:21 -0800)]
[CONNECTOR]: Use netlink_has_listeners() to avoind unnecessary allocations.
Return -ESRCH from cn_netlink_send() when there are not listeners,
just as it could be done by netlink_broadcast(). Propagate
netlink_broadcast() error back to the caller.
Signed-off-by: Evgeniy Polyakov <johnpol@2ka.mipt.ru> Signed-off-by: David S. Miller <davem@davemloft.net>
David Basden [Tue, 21 Mar 2006 06:21:10 +0000 (22:21 -0800)]
[IRDA]: TOIM3232 dongle support
Here goes a patch for supporting TOIM3232 based serial IrDA dongles.
The code is based on the tekram dongle code.
It's been tested with a TOIM3232 based IRWave 320S dongle. It may work
for TOIM4232 dongles, although it's not been tested.
Signed-off-by: David Basden <davidb-irda@rcpt.to> Signed-off-by: Samuel Ortiz <samuel.ortiz@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Luiz Capitulino [Tue, 21 Mar 2006 06:17:55 +0000 (22:17 -0800)]
[PKTGEN]: Fix Initialization fail leak.
Even if pktgen's thread initialization fails for all CPUs, the module
will be successfully loaded.
This patch changes that behaivor, by returning an error on module load time,
and also freeing all the resources allocated. It also prints a warning if a
thread initialization has failed.
Signed-off-by: Luiz Capitulino <lcapitulino@mandriva.com.br> Signed-off-by: David S. Miller <davem@davemloft.net>
Luiz Capitulino [Tue, 21 Mar 2006 06:16:40 +0000 (22:16 -0800)]
[PKTGEN]: Ports thread list to Kernel list implementation.
The final result is a simpler and smaller code.
Note that I'm adding a new member in the struct pktgen_thread called
'removed'. The reason is that I didn't find a better wait condition to
be used in the place of the replaced one.
Signed-off-by: Luiz Capitulino <lcapitulino@mandriva.com.br> Signed-off-by: David S. Miller <davem@davemloft.net>
[DCCP] options: Fix some aspects of mandatory option processing
According to dccp draft (draft-ietf-dccp-spec-13.txt) section 5.8.2
(Mandatory Option) the following patch correct the handling of the
following cases:
1) "... and any Mandatory options received on DCCP-Data packets MUST be
ignored."
2) "The connection is in error and should be reset with Reset Code 5, ...
if option O is absent (Mandatory was the last byte of the option list), or
if option O equals Mandatory."
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com> Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: David S. Miller <davem@davemloft.net>
Ditched IP_DCCP_UNLOAD_HACK, as now we would have to do it for both
IPv6 and IPv4, so I'll come up with another way for freeing the
control sockets in upcoming changesets.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Adrian Bunk [Tue, 21 Mar 2006 05:58:29 +0000 (21:58 -0800)]
[DCCP] ipv4: make struct dccp_v4_prot static
There's no reason for struct dccp_v4_prot being global.
Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Michael Chan [Tue, 21 Mar 2006 05:33:26 +0000 (21:33 -0800)]
[TG3]: Add some missing netif_running() checks
Add missing netif_running() checks in tg3's dev->set_multicast_list()
and dev->set_mac_address(). If not netif_running(), these 2 calls can
simply return 0 after storing the new settings if required.
Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Benjamin LaHaise [Tue, 21 Mar 2006 05:31:51 +0000 (21:31 -0800)]
[AF_UNIX]: scm: better initialization
Instead of doing a memset then initialization of the fields of the scm
structure, just initialize all the members explicitly. Prevent reloading
of current on x86 and x86-64 by storing the value in a local variable for
subsequent dereferences. This is worth a ~7KB/s increase in af_unix
bandwidth. Note that we avoid the issues surrounding potentially
uninitialized members of the ucred structure by constructing a struct
ucred instead of assigning the members individually, which forces the
compiler to zero any padding.
[ I modified the patch not to use the aggregate assignment since
gcc-3.4.x and earlier cannot optimize that properly at all even
though gcc-4.0.x and later can -DaveM ]
Signed-off-by: Benjamin LaHaise <benjamin.c.lahaise@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Benjamin LaHaise [Tue, 21 Mar 2006 05:29:05 +0000 (21:29 -0800)]
[AF_UNIX]: use shift instead of integer division
The patch below replaces a divide by 2 with a shift -- sk_sndbuf is an
integer, so gcc emits an idiv, which takes 10x longer than a shift by 1.
This improves af_unix bandwidth by ~6-10K/s. Also, tidy up the comment
to fit in 80 columns while we're at it.
Signed-off-by: Benjamin LaHaise <benjamin.c.lahaise@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Arthur Kepner [Tue, 21 Mar 2006 05:26:56 +0000 (21:26 -0800)]
[NET] pktgen: Fix races between control/worker threads.
There's a race in pktgen which can lead to a double
free of a pktgen_dev's skb. If a worker thread is in
the midst of doing fill_packet(), and the controlling
thread gets a "stop" message, the already freed skb
can be freed once again in pktgen_stop_device(). This
patch gives all responsibility for cleaning up a
pktgen_dev's skb to the associated worker thread.
Signed-off-by: Arthur Kepner <akepner@sgi.com> Acked-by: Robert Olsson <Robert.Olsson@data.slu.se> Signed-off-by: David S. Miller <davem@davemloft.net>
[DCCP]: Move the IPv4 specific bits from proto.c to ipv4.c
With this patch in place we can break down the complexity by better
compartmentalizing the code that is common to ipv6 and ipv4.
Now we have these modules:
Module Size Used by
dccp_diag 1344 0
inet_diag 9448 1 dccp_diag
dccp_ccid3 15856 0
dccp_tfrc_lib 12320 1 dccp_ccid3
dccp_ccid2 5764 0
dccp_ipv4 16996 2
dccp 48208 4 dccp_diag,dccp_ccid3,dccp_ccid2,dccp_ipv4
dccp_ipv6 still requires dccp_ipv4 due to dccp_ipv6_mapped, that is
the next target to work on the "hey, ipv4 is legacy, I only want ipv6
dude!" direction.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com> Signed-off-by: David S. Miller <davem@davemloft.net>
[DCCP]: Dont use dccp_v4_checksum in dccp_make_response
dccp_make_response is shared by ipv4/6 and the ipv6 code was
recalculating the checksum, not good, so move the dccp_v4_checksum
call to dccp_v4_send_response.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Of course we also need the setsockopt for each app to tell its preferences, but
for testing or defining something other than CCID2 as the default for apps that
don't explicitely set their preference the sysctl interface is handy.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com> Signed-off-by: David S. Miller <davem@davemloft.net>
As per the draft. This fixes the build when netfilter dccp components
are built and dccp isn't. Thanks to Reuben Farrelly for reporting
this.
The following changesets will introduce /proc/sys/net/dccp/defaults/
to give more flexibility to DCCP developers and testers while apps
doesn't use setsockopt to specify the desired CCID, etc.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Andrea Bittau [Tue, 21 Mar 2006 03:23:32 +0000 (19:23 -0800)]
[DCCP]: sparse endianness annotations
This also fixes the layout of dccp_hdr short sequence numbers, problem
was not fatal now as we only support long (48 bits) sequence numbers.
Signed-off-by: Andrea Bittau <a.bittau@cs.ucl.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
Patrick McHardy [Tue, 21 Mar 2006 03:23:05 +0000 (19:23 -0800)]
[NETFILTER]: Fix skb->nf_bridge lifetime issues
The bridge netfilter code simulates the NF_IP_PRE_ROUTING hook and skips
the real hook by registering with high priority and returning NF_STOP if
skb->nf_bridge is present and the BRNF_NF_BRIDGE_PREROUTING flag is not
set. The flag is only set during the simulated hook.
Because skb->nf_bridge is only freed when the packet is destroyed, the
packet will not only skip the first invocation of NF_IP_PRE_ROUTING, but
in the case of tunnel devices on top of the bridge also all further ones.
Forwarded packets from a bridge encapsulated by a tunnel device and sent
as locally outgoing packet will also still have the incorrect bridge
information from the input path attached.
We already have nf_reset calls on all RX/TX paths of tunnel devices,
so simply reset the nf_bridge field there too. As an added bonus,
the bridge information for locally delivered packets is now also freed
when the packet is queued to a socket.
Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
Andrea Bittau [Tue, 21 Mar 2006 03:22:37 +0000 (19:22 -0800)]
[DCCP] feat: Actually change the CCID upon negotiation
Change the CCID upon successful feature negotiation.
Commiter note: patch mostly rewritten to use the new ccid API.
Signed-off-by: Andrea Bittau <a.bittau@cs.ucl.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com> Signed-off-by: David S. Miller <davem@davemloft.net>
1. No need for ->ccid_init nor ->ccid_exit, this is what module_{init,exit}
does and anynways neither ccid2 nor ccid3 were using it.
2. Rename struct ccid to struct ccid_operations and introduce struct ccid
with a pointer to ccid_operations and rigth after it the rx or tx
private state.
3. Remove the pointer to the state of the half connections from struct
dccp_sock, now its derived thru ccid_priv() from the ccid pointer.
Now we also can implement the setsockopt for changing the CCID easily as
no ccid init routines can affect struct dccp_sock in any way that prevents
other CCIDs from working if a CCID switch operation is asked by apps.
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Patrick McHardy [Tue, 21 Mar 2006 03:20:44 +0000 (19:20 -0800)]
[PKT_SCHED]: Convert sch_red to a classful qdisc
Convert sch_red to a classful qdisc. All qdiscs that maintain accurate
backlog counters are eligible as child qdiscs. When a queue limit larger
than zero is given, a bfifo qdisc is used for backwards compatibility.
Current versions of tc enforce a limit larger than zero, other users
can avoid creating the default qdisc by using zero.
Signed-off-by: Patrick McHardy <kaber@trash.net> Acked-by: Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
Jamal Hadi Salim [Tue, 21 Mar 2006 03:17:03 +0000 (19:17 -0800)]
[IPSEC]: Sync series - SA expires
This patch allows a user to insert SA expires. This is useful to
do on an HA backup for the case of byte counts but may not be very
useful for the case of time based expiry.
Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
projects / linux-2.6 / log