I found a bug that stopped IPsec/IPv6 from working.  About
a month ago IPv6 started using rt6i_idev->dev on the cached socket dst
entries.  If the cached socket dst entry is IPsec, then rt6i_idev will
be NULL.

Since we want to look at the rt6i_idev of the original route in this
case, the easiest fix is to store rt6i_idev in the IPsec dst entry just
as we do for a number of other IPv6 route attributes.  Unfortunately
this means that we need some new code to handle the references to
rt6i_idev.  That's why this patch is bigger than it would otherwise be.

I've also done the same thing for IPv4 since it is conceivable that
once these idev attributes start getting used for accounting, we
probably need to dereference them for IPv4 IPsec entries too.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix qlen underrun when doing duplication with netem. If netem is used
as leaf discipline, then the parent needs to be tweaked when packets
are duplicated.
Signed-off-by: NStephen Hemminger <shemminger@osdl.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Netem currently dumps packets into the queue when timer expires. This
patch makes work by self-clocking (more like TBF).  It fixes a bug
when 0 delay is requested (only doing loss or duplication).
Signed-off-by: NStephen Hemminger <shemminger@osdl.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Due to bugs in netem (fixed by later patches), it is possible to get qdisc
qlen to go negative. If this happens the CPU ends up spinning forever
in qdisc_run(). So add a BUG_ON() to trap it.
Signed-off-by: NStephen Hemminger <shemminger@osdl.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Some network drivers call netif_stop_queue() when detecting loss of
carrier. This leads to packets being queued up at the qdisc level for
an unbound period of time. In order to prevent this effect, the core
networking stack will now cease to queue packets for any device, that
is operationally down (i.e. the queue is flushed and disabled).
Signed-off-by: NTommy S. Christensen <tommy.christensen@tpack.net>
Acked-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If we free up a partially processed packet because it's
skb->len dropped to zero, we need to decrement qlen because
we are dropping out of the top-level loop so it will do
the decrement for us.

Spotted by Herbert Xu.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The qlen should continue to decrement, even if we
pop partially processed SKBs back onto the receive queue.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Let's recap the problem.  The current asynchronous netlink kernel
message processing is vulnerable to these attacks:

1) Hit and run: Attacker sends one or more messages and then exits
before they're processed.  This may confuse/disable the next netlink
user that gets the netlink address of the attacker since it may
receive the responses to the attacker's messages.

Proposed solutions:

a) Synchronous processing.
b) Stream mode socket.
c) Restrict/prohibit binding.

2) Starvation: Because various netlink rcv functions were written
to not return until all messages have been processed on a socket,
it is possible for these functions to execute for an arbitrarily
long period of time.  If this is successfully exploited it could
also be used to hold rtnl forever.

Proposed solutions:

a) Synchronous processing.
b) Stream mode socket.

Firstly let's cross off solution c).  It only solves the first
problem and it has user-visible impacts.  In particular, it'll
break user space applications that expect to bind or communicate
with specific netlink addresses (pid's).

So we're left with a choice of synchronous processing versus
SOCK_STREAM for netlink.

For the moment I'm sticking with the synchronous approach as
suggested by Alexey since it's simpler and I'd rather spend
my time working on other things.

However, it does have a number of deficiencies compared to the
stream mode solution:

1) User-space to user-space netlink communication is still vulnerable.

2) Inefficient use of resources.  This is especially true for rtnetlink
since the lock is shared with other users such as networking drivers.
The latter could hold the rtnl while communicating with hardware which
causes the rtnetlink user to wait when it could be doing other things.

3) It is still possible to DoS all netlink users by flooding the kernel
netlink receive queue.  The attacker simply fills the receive socket
with a single netlink message that fills up the entire queue.  The
attacker then continues to call sendmsg with the same message in a loop.

Point 3) can be countered by retransmissions in user-space code, however
it is pretty messy.

In light of these problems (in particular, point 3), we should implement
stream mode netlink at some point.  In the mean time, here is a patch
that implements synchronous processing.  
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Here is a little optimisation for the cb_lock used by netlink_dump.
While fixing that race earlier, I noticed that the reference count
held by cb_lock is completely useless.  The reason is that in order
to obtain the protection of the reference count, you have to take
the cb_lock.  But the only way to take the cb_lock is through
dereferencing the socket.

That is, you must already possess a reference count on the socket
before you can take advantage of the reference count held by cb_lock.
As a corollary, we can remve the reference count held by the cb_lock.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

htb_enqueue(): Free skb and return NET_XMIT_DROP if a packet is
destined for the direct_queue but the direct_queue is full. (Before
this: erroneously returned NET_XMIT_SUCCESS even though the packet was
not enqueued)
Signed-off-by: NAsim Shankar <asimshankar@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

kfree() and vfree() can both deal with NULL pointers. This patch removes 
redundant NULL pointer checks from the ppp code in drivers/net/
Signed-off-by: NJesper Juhl <juhl-lkml@dif.dk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NFolkert van Heusden <folkert@vanheusden.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NFolkert van Heusden <folkert@vanheusden.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is a trivial fix for a typo on Kconfig, where the Generic Random Early 
Detection algorithm is abbreviated as RED instead of GRED.
Signed-off-by: NLucas Correia Villa Real <lucasvr@gobolinux.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

kfree(0) is perfectly valid, checking pointers for NULL before calling 
kfree() on them is redundant. The patch below cleans away a few such 
redundant checks (and while I was around some of those bits I couldn't 
stop myself from making a few tiny whitespace changes as well).
Signed-off-by: NJesper Juhl <juhl-lkml@dif.dk>
Acked-by: NArnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Converts remaining rtnetlink_link tables to use c99 designated
initializers to make greping a little bit easier.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Converts rtm_min and rtm_max arrays to use c99 designated
initializers for easier insertion of new message families.
RTM_GETMULTICAST and RTM_GETANYCAST did not have the minimal
message size specified which means that the netlink message
was parsed for routing attributes starting from the header.
Adds the proper minimal message sizes for these messages
(netlink header + common rtnetlink header) to fix this issue.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

RTM_MAX is currently set to the maximum reserverd message type plus one
thus being the cause of two bugs for new types being assigned a) given the
new family registers only the NEW command in its reserved block the array
size for per family entries is calculated one entry short and b) given the
new family registers all commands RTM_MAX would point to the first entry
of the block following this one and the rtnetlink receive path would accept
a message type for a nonexisting family.

This patch changes RTM_MAX to point to the maximum valid message type
by aligning it to the start of the next block and subtracting one.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Converts xfrm_msg_min and xfrm_dispatch to use c99 designated
initializers to make greping a little bit easier. Also replaces
two hardcoded message type with meaningful names.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Makes the type > XFRM_MSG_MAX check behave correctly to
protect access to xfrm_dispatch.
Signed-off-by: NThomas Graf <tgraf@suug.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch includes net/ipv6.h from addrconf.h since it needs
ipv6_addr_set.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I made a mistake in my last patch to the raw socket checksum code.
I used the value of inet->cork.length as the length of the payload.
While this works with normal packets, it breaks down when IPsec is
present since the cork length includes the extension header length.

So here is a patch to fix the length calculations.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Signed-off-by: NPatrick McHardy <kaber@trash.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

gcc-4.0 generates altivec code implicitly when -mcpu indicates an
altivec capable CPU which is not suitable for the kernel.  However, we
used to set -mcpu=970 when CONFIG_ALTIVEC was set because a gcc-3.x bug
prevented from using -maltivec along with -mcpu=power4, thus prevented
building the RAID6 altivec code.

This patch fixes all of this by testing for the gcc version.  If 4.0 or
later, just normally use -mcpu=power4 and let the RAID6 code add
-maltivec to the few files it needs to be compiled with altivec support.
For 3.x, we still use -mcpu=970 to work around the above problem, which
is fine as 3.x will never implicitly generate altivec code.

The Makefile hackery may not be the most lovely, I welcome anybody more
skilled than me to improve it.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Modify xtSearch so that it returns the next allocated block when the
requested block is unmapped.  This can be used to make sure we don't
create a new extent that overlaps the next one.
Signed-off-by: NDave Kleikamp <shaggy@austin.ibm.com>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

This patch adds jfs_syncpt, which calls lmLogSync to write sync points
to the journal both in jfs_sync_fs and when sync barrier processing
completes.

lmLogSync accomplishes two things:  1) it pushes logged-but-dirty
metadata pages to disk, and 2) it writes a sync record to the journal
so that jfs_fsck doesn't need to replay more transactions than is
necessary.
Signed-off-by: NDave Kleikamp <shaggy@austin.ibm.com>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

jfs has never worked on architecutures where the page size was not 4K.
Signed-off-by: NDave Kleikamp <shaggy@austin.ibm.com>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

JFS code has always assumed a page size of 4K.  This patch fixes the
non-pagecache uses of pages to deal with larger pages.
Signed-off-by: NDave Kleikamp <shaggy@austin.ibm.com>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

JFS was creating a new IAG (inode aggregate group) in one address
space, and afterwards, accessing it from another.  This could lead to
complications when cache pages contain more than one page of jfs
metadata.  This patch causes the IAG to be initialized in the same
address space that it is subsequently accessed with.

This also elimitates an I/O, but IAG's aren't created too often.
Signed-off-by: NDave Kleikamp <shaggy@austin.ibm.com>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

Use an inline pxd list rather than an xad list in the xadlock.
When the number of extents being modified can fit with the xadlock,
a transaction can be committed asynchronously.  Using a list of
pxd's instead of xad's allows us to fit 4 extents, rather than 2.
Signed-off-by: NDave Kleikamp <shaggy@austin.ibm.com>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The cpufreq core patch I sent earlier got only half-applied.  I added a
flag to let the low level driver disable an annoying warning on
suspend/resume that is normal on ppc, but the "resume" part of it wasn't
applied.

This just adds back that missing bit.  The original patch also reworked
the resume() function to avoid nesting too many if () statements along
the way I did the suspend() one, but I didn't include that in the patch
below.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

The clock spreading disable/enable code was called to late/early during
the suspend/resume code on some laptops and would trigger a
might_sleep() warning due to the down() call in the low level i2c code.

This fixes it by calling those functions earlier/later when interrupts
are still enabled.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

As Al Viro noticed, my previous fix missed one instance of "device" in
the driver local debug code. Harmless unless you tweak the #define's in
there but still work fixing.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

A typo in the machine table incorrectly mark the 101 PowerBook as
needing explicit callback from the video driver to enable sleep mode. I
did not implement that mecanism for chipsest older than r128, so we need
to mark this machine as always beeing able to sleep for now.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

My newer iMac mini driver doesn't build with verbose debug enabled.

This fixes it, and removes an erroneous error printk (since it's normal
on some machine to not find some gpios on the "first try").
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

We are experiencing a problem when flushing the CPU caches before sleep
on some laptop models using the 750FX CPU rev 1.X. While I haven't been
able to figure out a proper explanation for what's going on, I do have a
workaround that seem to work reliably and allows those machine to sleep
and wakeup properly again.

I'll re-update that code if/when I ever find exactly what is happening
with those CPU revisions.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>