We burn a lot of useless cycles, cpu store buffer traffic, and
memory operations memset()'ing the on-stack flow used to perform
output route lookups in __ip_route_output_key().
Only the first half of the flow object members even matter for
output route lookups in this context, specifically:
FIB rules matching cares about:
dst, src, tos, iif, oif, mark
FIB trie lookup cares about:
dst
FIB semantic match cares about:
tos, scope, oif
Therefore only initialize these specific members and elide the
memset entirely.
On Niagara2 this kills about ~300 cycles from the output route
lookup path.
Likely, we can take things further, since all callers of output
route lookups essentially throw away the on-stack flow they use.
So they don't care if we use it as a scratch-pad to compute the
final flow key.
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
David noticed :
------------------
Eric, I was profiling the non-routing-cache case and something that
stuck out is the case of calling inet_getpeer() with create==0.
If an entry is not found, we have to redo the lookup under a spinlock
to make certain that a concurrent writer rebalancing the tree does
not "hide" an existing entry from us.
This makes the case of a create==0 lookup for a not-present entry
really expensive. It is on the order of 600 cpu cycles on my
Niagara2.
I added a hack to not do the relookup under the lock when create==0
and it now costs less than 300 cycles.
This is now a pretty common operation with the way we handle COW'd
metrics, so I think it's definitely worth optimizing.
-----------------
One solution is to use a seqlock instead of a spinlock to protect struct
inet_peer_base.
After a failed avl tree lookup, we can easily detect if a writer did
some changes during our lookup. Taking the lock and redo the lookup is
only necessary in this case.
Note: Add one private rcu_deref_locked() macro to place in one spot the
access to spinlock included in seqlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6:
DNS: Fix a NULL pointer deref when trying to read an error key [CVE-2011-1076]
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (42 commits)
MAINTAINERS: Add Andy Gospodarek as co-maintainer.
r8169: disable ASPM
RxRPC: Fix v1 keys
AF_RXRPC: Handle receiving ACKALL packets
cnic: Fix lost interrupt on bnx2x
cnic: Prevent status block race conditions with hardware
net: dcbnl: check correct ops in dcbnl_ieee_set()
e1000e: disable broken PHY wakeup for ICH10 LOMs, use MAC wakeup instead
igb: fix sparse warning
e1000: fix sparse warning
netfilter: nf_log: avoid oops in (un)bind with invalid nfproto values
dccp: fix oops on Reset after close
ipvs: fix dst_lock locking on dest update
davinci_emac: Add Carrier Link OK check in Davinci RX Handler
bnx2x: update driver version to 1.62.00-6
bnx2x: properly calculate lro_mss
bnx2x: perform statistics "action" before state transition.
bnx2x: properly configure coefficients for MinBW algorithm (NPAR mode).
bnx2x: Fix ethtool -t link test for MF (non-pmf) devices.
bnx2x: Fix nvram test for single port devices.
...
When a DNS resolver key is instantiated with an error indication, attempts to
read that key will result in an oops because user_read() is expecting there to
be a payload - and there isn't one [CVE-2011-1076].
Give the DNS resolver key its own read handler that returns the error cached in
key->type_data.x[0] as an error rather than crashing.
Also make the kenter() at the beginning of dns_resolver_instantiate() limit the
amount of data it prints, since the data is not necessarily NUL-terminated.
The buggy code was added in:
commit 4a2d789267
Author: Wang Lei <wang840925@gmail.com>
Date: Wed Aug 11 09:37:58 2010 +0100
Subject: DNS: If the DNS server returns an error, allow that to be cached [ver #2]
This can trivially be reproduced by any user with the following program
compiled with -lkeyutils:
#include <stdlib.h>
#include <keyutils.h>
#include <err.h>
static char payload[] = "#dnserror=6";
int main()
{
key_serial_t key;
key = add_key("dns_resolver", "a", payload, sizeof(payload),
KEY_SPEC_SESSION_KEYRING);
if (key == -1)
err(1, "add_key");
if (keyctl_read(key, NULL, 0) == -1)
err(1, "read_key");
return 0;
}
What should happen is that keyctl_read() reports error 6 (ENXIO) to the user:
dns-break: read_key: No such device or address
but instead the kernel oopses.
This cannot be reproduced with the 'keyutils add' or 'keyutils padd' commands
as both of those cut the data down below the NUL termination that must be
included in the data. Without this dns_resolver_instantiate() will return
-EINVAL and the key will not be instantiated such that it can be read.
The oops looks like:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000010
IP: [<ffffffff811b99f7>] user_read+0x4f/0x8f
PGD 3bdf8067 PUD 385b9067 PMD 0
Oops: 0000 [#1] SMP
last sysfs file: /sys/devices/pci0000:00/0000:00:19.0/irq
CPU 0
Modules linked in:
Pid: 2150, comm: dns-break Not tainted 2.6.38-rc7-cachefs+ #468 /DG965RY
RIP: 0010:[<ffffffff811b99f7>] [<ffffffff811b99f7>] user_read+0x4f/0x8f
RSP: 0018:ffff88003bf47f08 EFLAGS: 00010246
RAX: 0000000000000001 RBX: ffff88003b5ea378 RCX: ffffffff81972368
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88003b5ea378
RBP: ffff88003bf47f28 R08: ffff88003be56620 R09: 0000000000000000
R10: 0000000000000395 R11: 0000000000000002 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: ffffffffffffffa1
FS: 00007feab5751700(0000) GS:ffff88003e000000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000010 CR3: 000000003de40000 CR4: 00000000000006f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process dns-break (pid: 2150, threadinfo ffff88003bf46000, task ffff88003be56090)
Stack:
ffff88003b5ea378 ffff88003b5ea3a0 0000000000000000 0000000000000000
ffff88003bf47f68 ffffffff811b708e ffff88003c442bc8 0000000000000000
00000000004005a0 00007fffba368060 0000000000000000 0000000000000000
Call Trace:
[<ffffffff811b708e>] keyctl_read_key+0xac/0xcf
[<ffffffff811b7c07>] sys_keyctl+0x75/0xb6
[<ffffffff81001f7b>] system_call_fastpath+0x16/0x1b
Code: 75 1f 48 83 7b 28 00 75 18 c6 05 58 2b fb 00 01 be bb 00 00 00 48 c7 c7 76 1c 75 81 e8 13 c2 e9 ff 4c 8b b3 e0 00 00 00 4d 85 ed <41> 0f b7 5e 10 74 2d 4d 85 e4 74 28 e8 98 79 ee ff 49 39 dd 48
RIP [<ffffffff811b99f7>] user_read+0x4f/0x8f
RSP <ffff88003bf47f08>
CR2: 0000000000000010
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
cc: Wang Lei <wang840925@gmail.com>
Signed-off-by: James Morris <jmorris@namei.org>
Netlink message processing in the kernel is synchronous these days,
capabilities can be checked directly in security_netlink_recv() from
the current process.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Reviewed-by: James Morris <jmorris@namei.org>
[chrisw: update to include pohmelfs and uvesafb]
Signed-off-by: Chris Wright <chrisw@sous-sol.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Because of various alignements [SLUB / qdisc], we use 512 bytes of
memory for one {p|b}fifo qdisc, instead of 256 bytes on 64bit arches and
192 bytes on 32bit ones.
Move the "u32 limit" inside "struct Qdisc" (no impact on other qdiscs)
Change qdisc_alloc(), first trying a regular allocation before an
oversized one.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Netlink message processing in the kernel is synchronous these days, the
session information can be collected when needed.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
As reported by Eric:
[11483.697233] IP: [<c12b0638>] dst_release+0x18/0x60
...
[11483.697741] Call Trace:
[11483.697764] [<c12fc9d2>] udp_sendmsg+0x282/0x6e0
[11483.697790] [<c12a1c01>] ? memcpy_toiovec+0x51/0x70
[11483.697818] [<c12dbd90>] ? ip_generic_getfrag+0x0/0xb0
The pointer passed to dst_release() is -EINVAL, that's because
we leave an error pointer in the local variable "rt" by accident.
NULL it out to fix the bug.
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The OpenAFS server is now sending ACKALL packets, so we need to handle them.
Otherwise we report a protocol error and abort.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds the support for retrieving the remote or peer DCBX
configuration via dcbnl for embedded DCBX stacks supporting the CEE DCBX
standard.
Signed-off-by: Shmulik Ravid <shmulikr@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
These 2 patches add the support for retrieving the remote or peer DCBX
configuration via dcbnl for embedded DCBX stacks. The peer configuration
is part of the DCBX MIB and is useful for debugging and diagnostics of
the overall DCB configuration. The first patch add this support for IEEE
802.1Qaz standard the second patch add the same support for the older
CEE standard. Diff for v2 - the peer-app-info is CEE specific.
Signed-off-by: Shmulik Ravid <shmulikr@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The incorrect ops routine was being tested for in
DCB_ATTR_IEEE_PFC attributes. This patch corrects
it.
Currently, every driver implementing ieee_setets also
implements ieee_setpfc so this bug is not actualized
yet.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Like many other places, we have to check that the array index is
within allowed limits, or otherwise, a kernel oops and other nastiness
can ensue when we access memory beyond the end of the array.
[ 5954.115381] BUG: unable to handle kernel paging request at 0000004000000000
[ 5954.120014] IP: __find_logger+0x6f/0xa0
[ 5954.123979] nf_log_bind_pf+0x2b/0x70
[ 5954.123979] nfulnl_recv_config+0xc0/0x4a0 [nfnetlink_log]
[ 5954.123979] nfnetlink_rcv_msg+0x12c/0x1b0 [nfnetlink]
...
The problem goes back to v2.6.30-rc1~1372~1342~31 where nf_log_bind
was decoupled from nf_log_register.
Reported-by: Miguel Di Ciurcio Filho <miguel.filho@gmail.com>,
via irc.freenode.net/#netfilter
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
This fixes a bug in the order of dccp_rcv_state_process() that still permitted
reception even after closing the socket. A Reset after close thus causes a NULL
pointer dereference by not preventing operations on an already torn-down socket.
dccp_v4_do_rcv()
|
| state other than OPEN
v
dccp_rcv_state_process()
|
| DCCP_PKT_RESET
v
dccp_rcv_reset()
|
v
dccp_time_wait()
WARNING: at net/ipv4/inet_timewait_sock.c:141 __inet_twsk_hashdance+0x48/0x128()
Modules linked in: arc4 ecb carl9170 rt2870sta(C) mac80211 r8712u(C) crc_ccitt ah
[<c0038850>] (unwind_backtrace+0x0/0xec) from [<c0055364>] (warn_slowpath_common)
[<c0055364>] (warn_slowpath_common+0x4c/0x64) from [<c0055398>] (warn_slowpath_n)
[<c0055398>] (warn_slowpath_null+0x1c/0x24) from [<c02b72d0>] (__inet_twsk_hashd)
[<c02b72d0>] (__inet_twsk_hashdance+0x48/0x128) from [<c031caa0>] (dccp_time_wai)
[<c031caa0>] (dccp_time_wait+0x40/0xc8) from [<c031c15c>] (dccp_rcv_state_proces)
[<c031c15c>] (dccp_rcv_state_process+0x120/0x538) from [<c032609c>] (dccp_v4_do_)
[<c032609c>] (dccp_v4_do_rcv+0x11c/0x14c) from [<c0286594>] (release_sock+0xac/0)
[<c0286594>] (release_sock+0xac/0x110) from [<c031fd34>] (dccp_close+0x28c/0x380)
[<c031fd34>] (dccp_close+0x28c/0x380) from [<c02d9a78>] (inet_release+0x64/0x70)
The fix is by testing the socket state first. Receiving a packet in Closed state
now also produces the required "No connection" Reset reply of RFC 4340, 8.3.1.
Reported-and-tested-by: Johan Hovold <jhovold@gmail.com>
Cc: stable@kernel.org
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
The patch to replace inet->cork with cork left out two spots in
__ip_append_data that can result in bogus packet construction.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
If CONFIG_NET_KEY_MIGRATE is not defined the arguments of
pfkey_migrate stub do not match causing warning.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The route lookup code in icmpv6_send() is slightly tricky as a result of
having to handle all of the requirements of RFC 4301 host relookups.
Pull the route resolution into a seperate function, so that the error
handling and route reference counting is hopefully easier to see and
contained wholly within this new routine.
Signed-off-by: David S. Miller <davem@davemloft.net>
The route lookup code in icmp_send() is slightly tricky as a result of
having to handle all of the requirements of RFC 4301 host relookups.
Pull the route resolution into a seperate function, so that the error
handling and route reference counting is hopefully easier to see and
contained wholly within this new routine.
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix dst_lock usage in __ip_vs_update_dest. We need
_bh locking because destination is updated in user context.
Can cause lockups on frequent destination updates.
Problem reported by Simon Kirby. Bug was introduced
in 2.6.37 from the "ipvs: changes for local real server"
change.
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>
Return a dst pointer which is potentitally error encoded.
Don't pass original dst pointer by reference, pass a struct net
instead of a socket, and elide the flow argument since it is
unnecessary.
Signed-off-by: David S. Miller <davem@davemloft.net>
Route lookups follow a general pattern in the ipv6 code wherein
we first find the non-IPSEC route, potentially override the
flow destination address due to ipv6 options settings, and then
finally make an IPSEC search using either xfrm_lookup() or
__xfrm_lookup().
__xfrm_lookup() is used when we want to generate a blackhole route
if the key manager needs to resolve the IPSEC rules (in this case
-EREMOTE is returned and the original 'dst' is left unchanged).
Otherwise plain xfrm_lookup() is used and when asynchronous IPSEC
resolution is necessary, we simply fail the lookup completely.
All of these cases are encapsulated into two routines,
ip6_dst_lookup_flow and ip6_sk_dst_lookup_flow. The latter of which
handles unconnected UDP datagram sockets.
Signed-off-by: David S. Miller <davem@davemloft.net>
The UDP transmit path has been running under the socket lock
for a long time because of the corking feature. This means that
transmitting to the same socket in multiple threads does not
scale at all.
However, as most users don't actually use corking, the locking
can be removed in the common case.
This patch creates a lockless fast path where corking is not used.
Please note that this does create a slight inaccuracy in the
enforcement of socket send buffer limits. In particular, we
may exceed the socket limit by up to (number of CPUs) * (packet
size) because of the way the limit is computed.
As the primary purpose of socket buffers is to indicate congestion,
this should not be a great problem for now.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch converts UDP to use the new ip_finish_skb API. This
would then allows us to more easily use ip_make_skb which allows
UDP to run without a socket lock.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds the helper ip_make_skb which is like ip_append_data
and ip_push_pending_frames all rolled into one, except that it does
not send the skb produced. The sending part is carried out by
ip_send_skb, which the transport protocol can call after it has
tweaked the skb.
It is meant to be called in cases where corking is not used should
have a one-to-one correspondence to sendmsg.
This patch also adds the helper ip_finish_skb which is meant to
be replace ip_push_pending_frames when corking is required.
Previously the protocol stack would peek at the socket write
queue and add its header to the first packet. With ip_finish_skb,
the protocol stack can directly operate on the final skb instead,
just like the non-corking case with ip_make_skb.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to allow simultaneous calls to ip_append_data on the same
socket, it must not modify any shared state in sk or inet (other
than those that are designed to allow that such as atomic counters).
This patch abstracts out write references to sk and inet_sk in
ip_append_data and its friends so that we may use the underlying
code in parallel.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
UFO doesn't really use the sk_sndmsg_* parameters so touching
them is pointless. It can't use them anyway since the whole
point of UFO is to use the original pages without copying.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
... Otherwise it is displayed when mac80211 isn't
even turned on, which is completely pointless.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Also fix a typo in the STATION_INFO_TX_BITRATE description
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Enabling TX timestamps (SO_TIMESTAMPING) for IPv6 UDP packets, in
the same fashion as for IPv4. Necessary in order for NICs such as
Intel 82580 to timestamp IPv6 packets.
Signed-off-by: Anders Berggren <anders@halon.se>
Signed-off-by: David S. Miller <davem@davemloft.net>
netlink_dump() may failed, but nobody handle its error.
It generates output data, when a previous portion has been returned to
user space. This mechanism works when all data isn't go in skb. If we
enter in netlink_recvmsg() and skb is absent in the recv queue, the
netlink_dump() will not been executed. So if netlink_dump() is failed
one time, the new data never appear and the reader will sleep forever.
netlink_dump() is called from two places:
1. from netlink_sendmsg->...->netlink_dump_start().
In this place we can report error directly and it will be returned
by sendmsg().
2. from netlink_recvmsg
There we can't report error directly, because we have a portion of
valid output data and call netlink_dump() for prepare the next portion.
If netlink_dump() is failed, the socket will be mark as error and the
next recvmsg will be failed.
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller