This patch implements receive flow steering (RFS). RFS steers
received packets for layer 3 and 4 processing to the CPU where
the application for the corresponding flow is running. RFS is an
extension of Receive Packet Steering (RPS).
The basic idea of RFS is that when an application calls recvmsg
(or sendmsg) the application's running CPU is stored in a hash
table that is indexed by the connection's rxhash which is stored in
the socket structure. The rxhash is passed in skb's received on
the connection from netif_receive_skb. For each received packet,
the associated rxhash is used to look up the CPU in the hash table,
if a valid CPU is set then the packet is steered to that CPU using
the RPS mechanisms.
The convolution of the simple approach is that it would potentially
allow OOO packets. If threads are thrashing around CPUs or multiple
threads are trying to read from the same sockets, a quickly changing
CPU value in the hash table could cause rampant OOO packets--
we consider this a non-starter.
To avoid OOO packets, this solution implements two types of hash
tables: rps_sock_flow_table and rps_dev_flow_table.
rps_sock_table is a global hash table. Each entry is just a CPU
number and it is populated in recvmsg and sendmsg as described above.
This table contains the "desired" CPUs for flows.
rps_dev_flow_table is specific to each device queue. Each entry
contains a CPU and a tail queue counter. The CPU is the "current"
CPU for a matching flow. The tail queue counter holds the value
of a tail queue counter for the associated CPU's backlog queue at
the time of last enqueue for a flow matching the entry.
Each backlog queue has a queue head counter which is incremented
on dequeue, and so a queue tail counter is computed as queue head
count + queue length. When a packet is enqueued on a backlog queue,
the current value of the queue tail counter is saved in the hash
entry of the rps_dev_flow_table.
And now the trick: when selecting the CPU for RPS (get_rps_cpu)
the rps_sock_flow table and the rps_dev_flow table for the RX queue
are consulted. When the desired CPU for the flow (found in the
rps_sock_flow table) does not match the current CPU (found in the
rps_dev_flow table), the current CPU is changed to the desired CPU
if one of the following is true:
- The current CPU is unset (equal to RPS_NO_CPU)
- Current CPU is offline
- The current CPU's queue head counter >= queue tail counter in the
rps_dev_flow table. This checks if the queue tail has advanced
beyond the last packet that was enqueued using this table entry.
This guarantees that all packets queued using this entry have been
dequeued, thus preserving in order delivery.
Making each queue have its own rps_dev_flow table has two advantages:
1) the tail queue counters will be written on each receive, so
keeping the table local to interrupting CPU s good for locality. 2)
this allows lockless access to the table-- the CPU number and queue
tail counter need to be accessed together under mutual exclusion
from netif_receive_skb, we assume that this is only called from
device napi_poll which is non-reentrant.
This patch implements RFS for TCP and connected UDP sockets.
It should be usable for other flow oriented protocols.
There are two configuration parameters for RFS. The
"rps_flow_entries" kernel init parameter sets the number of
entries in the rps_sock_flow_table, the per rxqueue sysfs entry
"rps_flow_cnt" contains the number of entries in the rps_dev_flow
table for the rxqueue. Both are rounded to power of two.
The obvious benefit of RFS (over just RPS) is that it achieves
CPU locality between the receive processing for a flow and the
applications processing; this can result in increased performance
(higher pps, lower latency).
The benefits of RFS are dependent on cache hierarchy, application
load, and other factors. On simple benchmarks, we don't necessarily
see improvement and sometimes see degradation. However, for more
complex benchmarks and for applications where cache pressure is
much higher this technique seems to perform very well.
Below are some benchmark results which show the potential benfit of
this patch. The netperf test has 500 instances of netperf TCP_RR
test with 1 byte req. and resp. The RPC test is an request/response
test similar in structure to netperf RR test ith 100 threads on
each host, but does more work in userspace that netperf.
e1000e on 8 core Intel
No RFS or RPS 104K tps at 30% CPU
No RFS (best RPS config): 290K tps at 63% CPU
RFS 303K tps at 61% CPU
RPC test tps CPU% 50/90/99% usec latency Latency StdDev
No RFS/RPS 103K 48% 757/900/3185 4472.35
RPS only: 174K 73% 415/993/2468 491.66
RFS 223K 73% 379/651/1382 315.61
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The af_packet protocol is used by Perl to do ioctls as reported by
Stephane Riviere:
"Net::RawIP relies on SIOCGIFADDR et SIOCGIFHWADDR to get the IP and MAC
addresses of the network interface."
But in a new network namespace these ioctl fail because it is disabled for
a namespace different from the init_net_ns.
These two lines should not be there as af_inet and af_packet are
namespace aware since a long time now. I suppose we forget to remove these
lines because we sent the af_packet first, before af_inet was supported.
Signed-off-by: Daniel Lezcano <daniel.lezcano@free.fr>
Reported-by: Stephane Riviere <stephane.riviere@regis-dgac.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
In a scenario, where a cfg80211 driver (station mode) does not send assoc request
and assoc response IEs in cfg80211_connect_result after a successful association
to an AP, cfg80211 sends IWEVASSOCREQIE and IWEVASSOCRESPIE to the user space
application with NULL data. This can cause an issue at the event recipient.
An example of this is when cfg80211 sends IWEVASSOCREQIE and IWEVASSOCRESPIE
events with NULL event body to wpa_supplicant. The wpa_supplicant overwrites
the assoc request and assoc response IEs for this station with NULL data.
If the association is WPA/WPA2, the wpa_supplicant is not able to generate
EAPOL handshake messages, since the IEs are NULL.
With the patch, req_ie and resp_ie will be NULL by avoiding the
assignment if the driver has not sent the IEs to cfg80211. The event sending
code sends the events only if resp_ie and req_ie are not NULL. This
will ensure that the events are not sent with NULL event body.
Signed-off-by: Nishant Sarmukadam <nishants@marvell.com>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
As Herbert Xu said: we should be able to simply replace ipfragok
with skb->local_df. commit f88037(sctp: Drop ipfargok in sctp_xmit function)
has droped ipfragok and set local_df value properly.
The patch kills the ipfragok parameter of .queue_xmit().
Signed-off-by: Shan Wei <shanwei@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
commit f88037(sctp: Drop ipfargok in sctp_xmit function)
has droped ipfragok and set local_df value properly.
So the change of commit 77e2f1(ipv6: Fix ip6_xmit to
send fragments if ipfragok is true) is not needed.
So the patch remove them.
Signed-off-by: Shan Wei <shanwei@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Paris got following trace with a linux-next kernel
[ 14.203970] BUG: using smp_processor_id() in preemptible [00000000]
code: avahi-daemon/2093
[ 14.204025] caller is netif_rx+0xfa/0x110
[ 14.204035] Call Trace:
[ 14.204064] [<ffffffff81278fe5>] debug_smp_processor_id+0x105/0x110
[ 14.204070] [<ffffffff8142163a>] netif_rx+0xfa/0x110
[ 14.204090] [<ffffffff8145b631>] ip_dev_loopback_xmit+0x71/0xa0
[ 14.204095] [<ffffffff8145b892>] ip_mc_output+0x192/0x2c0
[ 14.204099] [<ffffffff8145d610>] ip_local_out+0x20/0x30
[ 14.204105] [<ffffffff8145d8ad>] ip_push_pending_frames+0x28d/0x3d0
[ 14.204119] [<ffffffff8147f1cc>] udp_push_pending_frames+0x14c/0x400
[ 14.204125] [<ffffffff814803fc>] udp_sendmsg+0x39c/0x790
[ 14.204137] [<ffffffff814891d5>] inet_sendmsg+0x45/0x80
[ 14.204149] [<ffffffff8140af91>] sock_sendmsg+0xf1/0x110
[ 14.204189] [<ffffffff8140dc6c>] sys_sendmsg+0x20c/0x380
[ 14.204233] [<ffffffff8100ad82>] system_call_fastpath+0x16/0x1b
While current linux-2.6 kernel doesnt emit this warning, bug is latent
and might cause unexpected failures.
ip_dev_loopback_xmit() runs in process context, preemption enabled, so
must call netif_rx_ni() instead of netif_rx(), to make sure that we
process pending software interrupt.
Same change for ip6_dev_loopback_xmit()
Reported-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix an oversight in ipmr_destroy_unres() - the net pointer is
unconditionally initialized to NULL, resulting in a NULL pointer
dereference later on.
Fix by adding a net pointer to struct mr_table and using it in
ipmr_destroy_unres().
Signed-off-by: Patrick McHardy <kaber@trash.net>
The patch to convert struct mfc_cache to list_heads (ipv4: ipmr: convert
struct mfc_cache to struct list_head) introduced a bug when adding new
cache entries that don't match any unresolved entries.
The unres queue is searched for a matching entry, which is then resolved.
When no matching entry is present, the iterator points to the head of the
list, but is treated as a matching entry. Use a seperate variable to
indicate that a matching entry was found.
Signed-off-by: Patrick McHardy <kaber@trash.net>
When dev_pick_tx() caches tx queue_index on a socket, we must check
socket dst_entry matches skb one, or risk a crash later, as reported by
Denys Fedorysychenko, if old packets are in flight during a route
change, involving devices with different number of queues.
Bug introduced by commit a4ee3ce3
(net: Use sk_tx_queue_mapping for connected sockets)
Reported-by: Denys Fedorysychenko <nuclearcat@nuclearcat.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Paris reported netif_rx() is calling smp_processor_id() from
preemptible context, in particular when caller is
ip_dev_loopback_xmit().
RPS commit added this smp_processor_id() call, this patch makes sure
preemption is disabled. rps_get_cpus() wants rcu_read_lock() anyway, we
can dot it a bit earlier.
Reported-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Followup of commit 634a4b20
Allow tnode_get_child_rcu() to be called either under rcu_read_lock()
protection or with RTNL held.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for multiple independant multicast routing instances,
named "tables".
Userspace multicast routing daemons can bind to a specific table instance by
issuing a setsockopt call using a new option MRT_TABLE. The table number is
stored in the raw socket data and affects all following ipmr setsockopt(),
getsockopt() and ioctl() calls. By default, a single table (RT_TABLE_DEFAULT)
is created with a default routing rule pointing to it. Newly created pimreg
devices have the table number appended ("pimregX"), with the exception of
devices created in the default table, which are named just "pimreg" for
compatibility reasons.
Packets are directed to a specific table instance using routing rules,
similar to how regular routing rules work. Currently iif, oif and mark
are supported as keys, source and destination addresses could be supported
additionally.
Example usage:
- bind pimd/xorp/... to a specific table:
uint32_t table = 123;
setsockopt(fd, IPPROTO_IP, MRT_TABLE, &table, sizeof(table));
- create routing rules directing packets to the new table:
# ip mrule add iif eth0 lookup 123
# ip mrule add oif eth0 lookup 123
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now that cache entries in unres_queue don't need to be distinguished by their
network namespace pointer anymore, we can remove it from struct mfc_cache
add pass the namespace as function argument to the functions that need it.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The unres_queue is currently shared between all namespaces. Following patches
will additionally allow to create multiple multicast routing tables in each
namespace. Having a single shared queue for all these users seems to excessive,
move the queue and the cleanup timer to the per-namespace data to unshare it.
As a side-effect, this fixes a bug in the seq file iteration functions: the
first entry returned is always from the current namespace, entries returned
after that may belong to any namespace.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Decouple the address family values used for fib_rules from the real
address families in socket.h. This allows to use fib_rules for
code that is not a real address family without increasing AF_MAX/NPROTO.
Values up to 127 are reserved for real address families and map directly
to the corresponding AF value, values starting from 128 are for other
uses. rtnetlink is changed to invoke the AF_UNSPEC dumpit/doit handlers
for these families.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
All fib_rules implementations need to set the family in their ->fill()
functions. Since the value is available to the generic fib_nl_fill_rule()
function, set it there.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Both functions are equivalent, consolidate them since a following patch
needs a third implementation for multicast routing.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (25 commits)
smc91c92_cs: define multicast_table as unsigned char
can: avoids a false warning
e1000e: stop cleaning when we reach tx_ring->next_to_use
igb: restrict WoL for 82576 ET2 Quad Port Server Adapter
virtio_net: missing sg_init_table
Revert "tcp: Set CHECKSUM_UNNECESSARY in tcp_init_nondata_skb"
iwlwifi: need check for valid qos packet before free
tcp: Set CHECKSUM_UNNECESSARY in tcp_init_nondata_skb
udp: fix for unicast RX path optimization
myri10ge: fix rx_pause in myri10ge_set_pauseparam
net: corrected documentation for hardware time stamping
stmmac: use resource_size()
x.25 attempts to negotiate invalid throughput
x25: Patch to fix bug 15678 - x25 accesses fields beyond end of packet.
bridge: Fix IGMP3 report parsing
cnic: Fix crash during bnx2x MTU change.
qlcnic: fix set mac addr
r6040: fix r6040_multicast_list
vhost-net: fix vq_memory_access_ok error checking
ath9k: fix double calls to ath_radio_enable
...
The function dst_ifdown is called only two places but in a non-
performance critical code path, there is no reason to inline it.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
skb_bond_should_drop() is too big to be inlined.
This patch reduces kernel text size, and its compilation time as well
(shrinking include/linux/netdevice.h)
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
At this point optlen == sizeof(sfilter) but some compilers are dumb.
Reported-by: Németh Márton <nm127@freemail.h
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Oliver Hartkopp <oliver@hartkopp.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The notifier for address down should only be called if address is completely
gone, not just being marked as tentative on link transistion. The code
in net-next would case bonding/sctp/s390 to see address disappear on link
down, but they would never see it reappear on link up.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since an address in hash list has to already have a ref count,
no additional ref count is needed.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When link goes down, want address to be preserved but in a tentative
state, therefore it has to stay in hash list.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Recent changes preserve IPv6 address when link goes down (good).
But would cause address to point to dead dst entry (bad).
The simplest fix is to just not delete route if address is
being held for later use.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With latest CONFIG_PROVE_RCU stuff, I felt more comfortable to make this
work.
sk->sk_dst_cache is currently protected by a rwlock (sk_dst_lock)
This rwlock is readlocked for a very small amount of time, and dst
entries are already freed after RCU grace period. This calls for RCU
again :)
This patch converts sk_dst_lock to a spinlock, and use RCU for readers.
__sk_dst_get() is supposed to be called with rcu_read_lock() or if
socket locked by user, so use appropriate rcu_dereference_check()
condition (rcu_read_lock_held() || sock_owned_by_user(sk))
This patch avoids two atomic ops per tx packet on UDP connected sockets,
for example, and permits sk_dst_lock to be much less dirtied.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Dont use netdev_warn() in dev_cap_txqueue() and get_rps_cpu() so that we
can catch following warnings without crash.
bond0.2240 received packet on queue 6, but number of RX queues is 1
bond0.2240 received packet on queue 11, but number of RX queues is 1
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Enable the SO_TIMESTAMPING socket infrastructure for raw packet sockets.
We introduce PACKET_TX_TIMESTAMP for the control message cmsg_type.
Similar support for UDP and CAN sockets was added in commit
51f31cabe3
Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Signed-off-by: David S. Miller <davem@davemloft.net>
Back in commit 04a0551c87
("loopback: Drop obsolete ip_summed setting") we stopped
setting CHECKSUM_UNNECESSARY in the loopback xmit.
This is because such a setting was a lie since it implies that the
checksum field of the packet is properly filled in.
Instead what happens normally is that CHECKSUM_PARTIAL is set and
skb->csum is calculated as needed.
But this was only happening for TCP data packets (via the
skb->ip_summed assignment done in tcp_sendmsg()). It doesn't
happen for non-data packets like ACKs etc.
Fix this by setting skb->ip_summed in the common non-data packet
constructor. It already is setting skb->csum to zero.
But this reminds us that we still have things like ip_output.c's
ip_dev_loopback_xmit() which sets skb->ip_summed to the value
CHECKSUM_UNNECESSARY, which Herbert's patch teaches us is not
valid. So we'll have to address that at some point too.
Signed-off-by: David S. Miller <davem@davemloft.net>
inet: Remove unused send_check length argument
This patch removes the unused length argument from the send_check
function in struct inet_connection_sock_af_ops.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Yinghai <yinghai.lu@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp: Handle CHECKSUM_PARTIAL for SYNACK packets for IPv6
This patch moves the common code between tcp_v6_send_check and
tcp_v6_gso_send_check into a new function __tcp_v6_send_check.
It then uses the new function in tcp_v6_send_synack as well as
tcp_v6_send_response so that they handle CHECKSUM_PARTIAL properly.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Yinghai <yinghai.lu@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp: Handle CHECKSUM_PARTIAL for SYNACK packets for IPv4
This patch moves the common code between tcp_v4_send_check and
tcp_v4_gso_send_check into a new function __tcp_v4_send_check.
It then uses the new function in tcp_v4_send_synack so that it
handles CHECKSUM_PARTIAL properly.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Yinghai <yinghai.lu@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This reverts commit 2626419ad5.
It causes regressions for people with IGB cards. Connection
requests don't complete etc. The true cause of the issue is
still not known, but we should sort this out in net-next-2.6
not net-2.6
Signed-off-by: David S. Miller <davem@davemloft.net>
As scan_work is queued from work_work it needs to be checked if scan
has been started during execution of work_work. Otherwise, when hw
scan is used, the stack gets error about hw being busy with ongoing
scan. This causes the stack to abort scan without notifying the driver
about it. This leads to a situation where the hw is scanning and the stack
thinks it's not. Then when the scan finishes, the stack will complain by
warnings.
Signed-off-by: Teemu Paasikivi <ext-teemu.3.paasikivi@nokia.com>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
We delay the skb linearising in ieee80211_rx_h_decrypt so that
frames do not require software decryption are not linearized. We
are safe to do this because ieee80211_get_mmie_keyidx() only
requires to touch nonlinear data for management frames, which are
already linearized before getting here.
Cc: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Zhu Yi <yi.zhu@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Enhance tracing by adding tracing for a variety of
callbacks that the drivers call, and also for
internal calls (currently limited to queue status).
This can aid debugging what is going on in mac80211
in interaction with drivers, since we can now see
what drivers call and not just what mac80211 calls
in the driver.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Grouped mesh action codes together with the other action codes in
ieee80211.h.
Signed-off-by: Javier Cardona <javier@cozybit.com>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Back in commit 04a0551c87
("loopback: Drop obsolete ip_summed setting") we stopped
setting CHECKSUM_UNNECESSARY in the loopback xmit.
This is because such a setting was a lie since it implies that the
checksum field of the packet is properly filled in.
Instead what happens normally is that CHECKSUM_PARTIAL is set and
skb->csum is calculated as needed.
But this was only happening for TCP data packets (via the
skb->ip_summed assignment done in tcp_sendmsg()). It doesn't
happen for non-data packets like ACKs etc.
Fix this by setting skb->ip_summed in the common non-data packet
constructor. It already is setting skb->csum to zero.
But this reminds us that we still have things like ip_output.c's
ip_dev_loopback_xmit() which sets skb->ip_summed to the value
CHECKSUM_UNNECESSARY, which Herbert's patch teaches us is not
valid. So we'll have to address that at some point too.
Signed-off-by: David S. Miller <davem@davemloft.net>
Commits 5051ebd275 and
5051ebd275 ("ipv[46]: udp: optimize unicast RX
path") broke some programs.
After upgrading a L2TP server to 2.6.33 it started to fail, tunnels going up an
down, after the 10th tunnel came up. My modified rp-l2tp uses a global
unconnected socket bound to (INADDR_ANY, 1701) and one connected socket per
tunnel after parameter negotiation.
After ten sockets were open and due to mixed parameters to
udp[46]_lib_lookup2() kernel started to drop packets.
Signed-off-by: Jorge Boncompte [DTI2] <jorge@dti2.net>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix coding style errors and warnings output while running checkpatch.pl
on the files net/core/ethtool.c and include/linux/ethtool.h
Signed-off-by: chavey <chavey@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The current X.25 code has some bugs in throughput negotiation:
1. It does negotiation in all cases, usually there is no need
2. It incorrectly attempts to negotiate the throughput class in one
direction only. There are separate throughput classes for input
and output and if either is negotiated both mist be negotiates.
This is bug https://bugzilla.kernel.org/show_bug.cgi?id=15681
This bug was first reported by Daniel Ferenci to the linux-x25 mailing
list on 6/8/2004, but is still present.
The current (2.6.34) x.25 code doesn't seem to know that the X.25
throughput facility includes two values, one for the required
throughput outbound, one for inbound.
This causes it to attempt to negotiate throughput 0x0A, which is
throughput 9600 inbound and the illegal value "0" for inbound
throughput.
Because of this some X.25 devices (e.g. Cisco 1600) refuse to connect
to Linux X.25.
The following patch fixes this behaviour. Unless the user specifies a
required throughput it does not attempt to negotiate. If the user
does not specify a throughput it accepts the suggestion of the remote
X.25 system. If the user requests a throughput then it validates both
the input and output throughputs and correctly negotiates them with
the remote end.
Signed-off-by: John Hughes <john@calva.com>
Tested-by: Andrew Hendry <andrew.hendry@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Here is a patch to stop X.25 examining fields beyond the end of the packet.
For example, when a simple CALL ACCEPTED was received:
10 10 0f
x25_parse_facilities was attempting to decode the FACILITIES field, but this
packet contains no facilities field.
Signed-off-by: John Hughes <john@calva.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The IGMP3 report parsing is looking at the wrong address for
group records. This patch fixes it.
Reported-by: Banyeer <banyeer@yahoo.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
As pointed by Randy Dunlap, we must include linux/proc_fs.h in
net/core/dev_addr_lists.c, regardless of CONFIG_PROC_FS
Reported-by: Randy Dunlap <randy.dunlap@oracle.com>,
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
WEP crypto was broken, but upon finding the problem
it is evident that other things were broken by the
paged RX patch as well.
To fix it, for now move the linearising in front.
This means that we linearise all frames, which is
not at all what we want, but at least it fixes the
problem for now.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Acked-by: Zhu Yi <yi.zhu@intel.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
A few places in mac80211 do not currently acquire
the sta lock for RX aggregation, but they should.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
The aggregation code has a number of quirks, like
inventing an unneeded WLAN_BACK_TIMER value and
leaking memory under certain circumstances during
station destruction. Fix these issues by using
the regular aggregation session teardown code and
blocking new aggregation sessions, all before the
station is really destructed.
As a side effect, this gets rid of the long code
block to destroy aggregation safely.
Additionally, rename tid_state_rx which can only
have the values IDLE and OPERATIONAL to
tid_active_rx to make it easier to understand
that there is no bitwise stuff going on on the
RX side -- the TX side remains because it needs
to keep track of the driver and peer states.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
I want to use it during station destruction as well
so rename it to WLAN_STA_BLOCK_BA which is also the
only use of it now.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
All callers of ieee80211_sta_stop_rx_ba_session can
just call __ieee80211_stop_rx_ba_session instead
because they already have the station struct, so do
that and remove ieee80211_sta_stop_rx_ba_session.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
All other places except one in the TX path, which
has BHs disabled, and it also cannot be locked from
interrupts so disabling IRQs is not necessary.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
When a station w/o a key is destroyed, or when
a driver submits work for a station and thereby
references it again, it seems like potentially
we could reference the station structure while
it is being destroyed.
Wait for an RCU grace period to elapse before
finishing destroying the station after we have
removed the station from the driver and from
the hash table etc., even in the case where no
key is associated with the station.
Also, there's no point in deleting the plink
timer here since it'll be properly deleted just
a bit later.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
cfg80211 is quite strict on allowing authentication and association
commands only in certain states. In order to meet these requirements,
user space applications may need to clear authentication or
association state in some cases. Currently, this can be done with
deauth/disassoc command, but that ends up sending out Deauthentication
or Disassociation frame unnecessarily. Add a new nl80211 attribute to
allow this sending of the frame be skipped, but with all other
deauth/disassoc operations being completed.
Similar state change is also needed for IEEE 802.11r FT protocol in
the FT-over-DS case which does not use Authentication frame exchange
in a transition to another BSS. For this to work with cfg80211, an
authentication entry needs to be created for the target BSS without
sending out an Authentication frame. The nl80211 authentication
command can be used for this purpose, too, with the new attribute to
indicate that the command is only for changing local state. This
enables wpa_supplicant to complete FT-over-DS transition successfully.
Signed-off-by: Jouni Malinen <j@w1.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Speed up lookups by freeing flow cache entries later. After
virtualizing flow cache entry operations, the flow cache may now
end up calling policy or bundle destructor which can be slowish.
As gc_list is more effective with double linked list, the flow cache
is converted to use common hlist and list macroes where appropriate.
Signed-off-by: Timo Teras <timo.teras@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
Policies are now properly reference counted and destroyed from
all code paths. The delayed gc is just an overhead now and can
be removed.
Signed-off-by: Timo Teras <timo.teras@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
__xfrm_lookup() is called for each packet transmitted out of
system. The xfrm_find_bundle() does a linear search which can
kill system performance depending on how many bundles are
required per policy.
This modifies __xfrm_lookup() to store bundles directly in
the flow cache. If we did not get a hit, we just create a new
bundle instead of doing slow search. This means that we can now
get multiple xfrm_dst's for same flow (on per-cpu basis).
Signed-off-by: Timo Teras <timo.teras@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
This allows to validate the cached object before returning it.
It also allows to destruct object properly, if the last reference
was held in flow cache. This is also a prepartion for caching
bundles in the flow cache.
In return for virtualizing the methods, we save on:
- not having to regenerate the whole flow cache on policy removal:
each flow matching a killed policy gets refreshed as the getter
function notices it smartly.
- we do not have to call flow_cache_flush from policy gc, since the
flow cache now properly deletes the object if it had any references
Signed-off-by: Timo Teras <timo.teras@iki.fi>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
struct timespec ts was alreay defined. Reuse the previously
defined one and reduce the memory footprint on the stack by
16 bytes.
Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch makes it explicit in the API that all fields in subscriptions and events exchanged with the Topology Server must be in
network byte order.
It also ensures that all fields of a subscription are compared when cancelling a subscription, in order to avoid inadvertent
cancelling of the wrong subscription.
Finally, the tipc module version is updated to 2.0.0, to reflect the API change.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit e34e09401ee9888dd662b2fca5d607794a56daf2 incorrectly removed
use of ieee80211_has_protected() from the management frame case and in
practice, made this validation drop all Action frames when MFP is
enabled. This should have only been done for frames with Protected
field set to zero.
Signed-off-by: Jouni Malinen <j@w1.fi>
Cc: stable@kernel.org
Signed-off-by: John W. Linville <linville@tuxdriver.com>
The new RCU lockdep support warns about these
in some contexts -- make it aware of the locks
used to protect all this. Different locks are
used in different contexts which unfortunately
means we can't get perfect checking.
Also remove rcu_dereference() from two places
that don't actually dereference the pointers.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
This fixes the problem introduced in commit
8404080568 which broke mesh peer link establishment.
changes:
v2 Added missing break (Johannes)
v3 Broke original patch into two (Johannes)
Signed-off-by: Javier Cardona <javier@cozybit.com>
Cc: stable@kernel.org
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (37 commits)
smc91c92_cs: fix the problem of "Unable to find hardware address"
r8169: clean up my printk uglyness
net: Hook up cxgb4 to Kconfig and Makefile
cxgb4: Add main driver file and driver Makefile
cxgb4: Add remaining driver headers and L2T management
cxgb4: Add packet queues and packet DMA code
cxgb4: Add HW and FW support code
cxgb4: Add register, message, and FW definitions
netlabel: Fix several rcu_dereference() calls used without RCU read locks
bonding: fix potential deadlock in bond_uninit()
net: check the length of the socket address passed to connect(2)
stmmac: add documentation for the driver.
stmmac: fix kconfig for crc32 build error
be2net: fix bug in vlan rx path for big endian architecture
be2net: fix flashing on big endian architectures
be2net: fix a bug in flashing the redboot section
bonding: bond_xmit_roundrobin() fix
drivers/net: Add missing unlock
net: gianfar - align BD ring size console messages
net: gianfar - initialize per-queue statistics
...
Fix kernel panic by NULL pointer dereference in the context of
ieee80211_ops->prepare_multicast().
This bug was introduced by commit 22bedad3c.. ("net: convert
multicast list to list_head").
Call __hw_addr_init() in ieee80211_alloc_hw() to initialize
list_head of private device multicast list, like we do in
bond_init().
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Reviewed-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As noticed by Changli Gao, we must call local_irq_enable() after
rps_unlock()
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix spin_unlock_irq which needs to be rps_unlock.
Signed-off-by: Tom Herbert <therbert@google.com>
Acked-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/ericvh/v9fs:
9p: saving negative to unsigned char
9p: return on mutex_lock_interruptible()
9p: Creating files with names too long should fail with ENAMETOOLONG.
9p: Make sure we are able to clunk the cached fid on umount
9p: drop nlink remove
fs/9p: Clunk the fid resulting from partial walk of the name
9p: documentation update
9p: Fix setting of protocol flags in v9fs_session_info structure.
Saving -EINVAL as unsigned char truncates the high bits and changes it
into 234 instead of -22. This breaks the test for "if (ret == -EINVAL)"
in parse_opts().
Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
RPC6 requires that it be possible to create endpoints that listen
exclusively for IPv4 or IPv6 connection requests. This is not currently
supported by the RDMA API.
This fixes a server RDMA regression introduced by 37498292a "NFSD:
Create PF_INET6 listener in write_ports".
Signed-off-by: Tom Tucker<tom@opengridcomputing.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
dcache prune happen on umount. So we cannot mark the client
satus disconnect. That will prevent a 9p call to the server
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
Followup to commit 789a4a2c
(l2tp: Add support for static unmanaged L2TPv3 tunnels)
One missing init in l2tp_tunnel_sock_create() could access random kernel
memory, and a bit field should be unsigned.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When ip_append() fails because of socket limit or memory shortage,
increment ICMP_MIB_OUTERRORS counter, so that "netstat -s" can report
these errors.
LANG=C netstat -s | grep "ICMP messages failed"
0 ICMP messages failed
For IPV6, implement ICMP6_MIB_OUTERRORS counter as well.
# grep Icmp6OutErrors /proc/net/dev_snmp6/*
/proc/net/dev_snmp6/eth0:Icmp6OutErrors 0
/proc/net/dev_snmp6/lo:Icmp6OutErrors 0
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for static (unmanaged) L2TPv3 tunnels, where
the tunnel socket is created by the kernel rather than being created
by userspace. This means L2TP tunnels and sessions can be created
manually, without needing an L2TP control protocol implemented in
userspace. This might be useful where the user wants a simple ethernet
over IP tunnel.
A patch to iproute2 adds a new command set under "ip l2tp" to make use
of this feature. This will be submitted separately.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The existing pppol2tp driver exports debug info to
/proc/net/pppol2tp. Rather than adding info to that file for the new
functionality added in this patch series, we add new files in debugfs,
leaving the old /proc file for backwards compatibility (L2TPv2 only).
Currently only one file is provided: l2tp/tunnels, which lists
internal debug info for all l2tp tunnels and sessions. More files may
be added later. The info is for debug and problem analysis only -
userspace apps should use netlink to obtain status about l2tp tunnels
and sessions.
Although debugfs does not support net namespaces, the tunnels and
sessions dumped in l2tp/tunnels are only those in the net namespace of
the process reading the file.
Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This driver presents a regular net_device for each L2TP ethernet
pseudowire instance. These interfaces are named l2tpethN by default,
though userspace can specify an alternative name when the L2TP
session is created, if preferred. When the pseudowire is established,
regular Linux networking utilities may be used to configure the
interface, i.e. give it IP address info or add it to a bridge. Any
data passed over the interface is carried over an L2TP tunnel.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reader/write locks are discouraged because they are slower than spin
locks. So this patch converts the rwlocks used in the per_net structs
to rcu.
Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In L2TPv3, we need to create/delete/modify/query L2TP tunnel and
session contexts. The number of parameters is significant. So let's
use netlink. Userspace uses this API to control L2TP tunnel/session
contexts in the kernel.
The previous pppol2tp driver was managed using [gs]etsockopt(). This
API is retained for backwards compatibility. Unlike L2TPv2 which
carries only PPP frames, L2TPv3 can carry raw ethernet frames or other
frame types and these do not always have an associated socket
family. Therefore, we need a way to use L2TP sessions that doesn't
require a socket type for each supported frame type. Hence netlink is
used.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This lets kernel modules which use genl netlink APIs serialize netlink
processing.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds a new L2TPIP socket family and modifies the core to
handle the case where there is no UDP header in the L2TP
packet. L2TP/IP uses IP protocol 115. Since L2TP/UDP and L2TP/IP
packets differ in layout, the datapath packet handling code needs
changes too. Userspace uses an L2TPIP socket instead of a UDP socket
when IP encapsulation is required.
We can't use raw sockets for this because the semantics of raw sockets
don't lend themselves to the socket-per-tunnel model - we need to
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch makes changes to the L2TP PPP code for L2TPv3.
The existing code has some assumptions about the L2TP header which are
broken by L2TPv3. Also the sockaddr_pppol2tp structure of the original
code is too small to support the increased size of the L2TPv3 tunnel
and session id, so a new sockaddr_pppol2tpv3 structure is needed. In
the socket calls, the size of this structure is used to tell if the
operation is for L2TPv2 or L2TPv3.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The L2TPv3 protocol changes the layout of the L2TP packet
header. Tunnel and session ids change from 16-bit to 32-bit values,
data sequence numbers change from 16-bit to 24-bit values and PPP-specific
fields are moved into protocol-specific subheaders.
Although this patch introduces L2TPv3 protocol support, there are no
userspace interfaces to create L2TPv3 sessions yet.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When dumping L2TP PPP sessions using /proc/net/pppol2tp, get the
assigned PPP device name from PPP using ppp_dev_name().
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch splits the pppol2tp driver into separate L2TP and PPP parts
to prepare for L2TPv3 support. In L2TPv3, protocols other than PPP can
be carried, so this split creates a common L2TP core that will handle
the common L2TP bits which protocol support modules such as PPP will
use.
Note that the existing pppol2tp module is split into l2tp_core and
l2tp_ppp by this change.
There are no feature changes here. Internally, however, there are
significant changes, mostly to handle the separation of PPP-specific
data from the L2TP session and to provide hooks in the core for
modules like PPP to access.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch moves the existing pppol2tp driver from drivers/net into a
new net/l2tp directory, which is where the upcoming L2TPv3 code will
live. The existing CONFIG_PPPOL2TP config option is left in its
current place to avoid "make oldconfig" issues when an existing
pppol2tp user takes this change. (This is the same approach used for
the pppoatm driver, which moved to net/atm.)
There are no code changes. The existing drivers/net/pppol2tp.c is
simply moved to net/l2tp.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Converts the list and the core manipulating with it to be the same as uc_list.
+uses two functions for adding/removing mc address (normal and "global"
variant) instead of a function parameter.
+removes dev_mcast.c completely.
+exposes netdev_hw_addr_list_* macros along with __hw_addr_* functions for
manipulation with lists on a sandbox (used in bonding and 80211 drivers)
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
+little renaming of unicast functions to be smooth with multicast ones
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Followup to commit 5acbbd428d
(net: change illegal_highdma to use dma_mask)
If dev->dev.parent is NULL, we should not try to dereference it.
Dont force inline illegal_highdma() as its pretty big now.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Robert Hancock pointed out two problems about NETIF_F_HIGHDMA:
-Many drivers only set the flag when they detect they can use 64-bit DMA,
since otherwise they could receive DMA addresses that they can't handle
(which on platforms without IOMMU/SWIOTLB support is fatal). This means that if
64-bit support isn't available, even buffers located below 4GB will get copied
unnecessarily.
-Some drivers set the flag even though they can't actually handle 64-bit DMA,
which would mean that on platforms without IOMMU/SWIOTLB they would get a DMA
mapping error if the memory they received happened to be located above 4GB.
http://lkml.org/lkml/2010/3/3/530
We can use the dma_mask if we need bouncing or not here. Then we can
safely fix drivers that misuse NETIF_F_HIGHDMA.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
Group all per-cpu data to one structure instead of having many
globals. Also prepare the internals so that we can have multiple
instances of the flow cache if needed.
Only the kmem_cache is left as a global as all flow caches share
the same element size, and benefit from using a common cache.
Signed-off-by: Timo Teras <timo.teras@iki.fi>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
All of the code considers ->dead as a hint that the cached policy
needs to get refreshed. The read side can just drop the read lock
without any side effects.
The write side needs to make sure that it's written only exactly
once. Only possible race is at xfrm_policy_kill(). This is fixed
by checking result of __xfrm_policy_unlink() when needed. It will
always succeed if the policy object is looked up from the hash
list (so some checks are removed), but it needs to be checked if
we are trying to unlink policy via a reference (appropriate
checks added).
Since policy->walk.dead is written exactly once, it no longer
needs to be protected with a write lock.
Signed-off-by: Timo Teras <timo.teras@iki.fi>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add missing check for policy direction verification. This is
especially important since without this xfrm_user may end up
deleting per-socket policy which is not allowed.
Signed-off-by: Timo Teras <timo.teras@iki.fi>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
The xfrm state genid only needs to be matched against the copy
saved in xfrm_dst. So we don't need a global genid at all. In
fact, we don't even need to initialise it.
Based on observation by Timo Teräs.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
keep the old behavior on SMP without rps
RPS introduces a lock operation to per cpu variable input_pkt_queue on
SMP whenever rps is enabled or not. On SMP without RPS, this lock isn't
needed at all.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
----
net/core/dev.c | 42 ++++++++++++++++++++++++++++--------------
1 file changed, 28 insertions(+), 14 deletions(-)
Signed-off-by: David S. Miller <davem@davemloft.net>
One of my test machine got a deadlock during "tc" sessions,
adding/deleting classes & filters, using traffic estimators.
After some analysis, I believe we have a potential use after free case
in est_timer() :
spin_lock(e->stats_lock); << HERE >>
read_lock(&est_lock);
if (e->bstats == NULL) << TEST >>
goto skip;
Test is done a bit late, because after estimator is killed, and before
rcu grace period elapsed, we might already have freed/reuse memory where
e->stats_locks points to (some qdisc->q.lock)
A possible fix is to respect a rcu grace period at Qdisc dismantle time.
On 64bit, sizeof(struct Qdisc) is exactly 192 bytes. Adding 16 bytes to
it (for struct rcu_head) is a problem because it might change
performance, given QDISC_ALIGNTO is 32 bytes.
This is why I also change QDISC_ALIGNTO to 64 bytes, to satisfy most
current alignment requirements.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The check if error signaling is wanted (inet->recverr != 0) is done by
the caller: raw.c:raw_err() and udp.c:__udp4_lib_err(), so there is no
need to check this condition again.
Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The recent changes to add RCU lock verification to rcu_dereference() calls
caught out a problem with netlbl_unlhsh_hash(), see below.
===================================================
[ INFO: suspicious rcu_dereference_check() usage. ]
---------------------------------------------------
net/netlabel/netlabel_unlabeled.c:246 invoked rcu_dereference_check()
without protection!
This patch fixes this problem as well as others like it in the NetLabel
code. Also included in this patch is the identification of future work
to eliminate the RCU read lock in netlbl_domhsh_add(), but in the interest
of getting this patch out quickly that work will happen in another patch
to be finished later.
Thanks to Eric Dumazet and Paul McKenney for their help in understanding
the recent RCU changes.
Signed-off-by: Paul Moore <paul.moore@hp.com>
Reported-by: David Howells <dhowells@redhat.com>
CC: Eric Dumazet <eric.dumazet@gmail.com>
CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
check the length of the socket address passed to connect(2).
Check the length of the socket address passed to connect(2). If the
length is invalid, -EINVAL will be returned.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
----
net/bluetooth/l2cap.c | 3 ++-
net/bluetooth/rfcomm/sock.c | 3 ++-
net/bluetooth/sco.c | 3 ++-
net/can/bcm.c | 3 +++
net/ieee802154/af_ieee802154.c | 3 +++
net/ipv4/af_inet.c | 5 +++++
net/netlink/af_netlink.c | 3 +++
7 files changed, 20 insertions(+), 3 deletions(-)
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit bef5d1c70d split
ieee80211_drop_unencrypted() into separate functions that are used for
Data and Management frames. However, it did not handle the
RX_FLAG_DECRYPTED correctly for Management frames:
ieee80211_drop_unencrypted() can only return 0 for Management frames,
so there is no point in calling it here. Instead, just check the
status->flag directly.
Signed-off-by: Jouni Malinen <j@w1.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
iw dev <devname> station del <MAC address> is quiet useful in mesh mode and should be possible.
Signed-off-by: Marco Porsch <marco.porsch@siemens.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
When selecting the RX key for group-addressed robust management
frames, we do not actually select any BIP key if the frame is
unprotected (since we cannot find the key index from MMIE). This
results in the drop_unencrypted check in failing to drop the frame. It
is enough to verify that we have a STA entry for the transmitter and
that MFP is enabled for that STA; we do not need to check rx->key
here. This fixes BIP processing for unprotected, group-addressed,
robust management frames.
Signed-off-by: Jouni Malinen <j@w1.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
BIP (part of IEEE 802.11w) is only supposed to be used with
group-addressed frames. We ended up picking it as a default mechanism
for every management whenever we did not have a STA entry for the
destination (e.g., for Probe Response to a STA that is not
associated). While the extra MMIE in the end of management frames
should not break frames completed in most cases, there is no point in
doing this. Fix key selection to pick the default management key only
if the frame is sent to multicast/broadcast address and the frame is a
robust management frame.
Signed-off-by: Jouni Malinen <j@w1.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
When management frame protection (IEEE 802.11w) is used, the
deauthentication and disassociation frames must be protected whenever
the encryption keys are configured. We were removing the STA entry and
with it, the keys, just before actually sending out these frames which
meant that the frames went out unprotected. The AP will drop them in
such a case. Fix this by reordering the operations a bit so that
sta_info_destroy_addr() gets called only after
ieee80211_send_deauth_disassoc().
Signed-off-by: Jouni Malinen <j@w1.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Calculate a running average of the signal strength reported for Beacon
frames and indicate cqm events if the average value moves below or
above the configured threshold value (and filter out repetitive events
with by using the configured hysteresis).
Signed-off-by: Jouni Malinen <j@w1.fi>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Enable QoS explicitly, when user space AP program will setup a QoS
queues. Currently this is not needed as iwlwifi not work in AP mode
and no other driver implement enable/disable QoS.
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Add interface to disable/enable QoS (aka WMM or WME). Currently drivers
enable it explicitly when ->conf_tx method is called, and newer disable.
Disabling is needed for some APs, which do not support QoS, such
we should send QoS frames to them.
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Mac80211 drivers can now pass paged SKBs to mac80211 via
ieee80211_rx{_irqsafe}. The implementation currently use
skb_linearize() in a few places i.e. management frame
handling, software decryption, defragmentation and A-MSDU
process. We will optimize them one by one later.
Signed-off-by: Zhu Yi <yi.zhu@intel.com>
Cc: Kalle Valo <kalle.valo@iki.fi>
Cc: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Remove duplicate declaration of symbol: struct hlist_node *node was
already declared, the seconds declaration shadows the first one.
CC: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
struct _zone *tipc_zones has local scope level and
should defined with the correct scoping.
CC: Per Liden <per.liden@nospam.ericsson.com>
Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix coding style errors and warnings output while running checkpatch.pl
on the file net/core/dst.c.
Signed-off-by: chavey <chavey@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds ethtool and device feature flag to allow control
of receive hashing offload.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Acked-by: Jeff Garzik <jgarzik@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
addr_bit_test() is used in various places in IPv6 routing table
subsystem. It checks if the given fn_bit is set,
where fn_bit counts bits from MSB in words in network-order.
fn_bit : 0 .... 31 32 .... 64 65 .... 95 96 ....127
fn_bit >> 5 gives offset of word, and (~fn_bit & 0x1f) gives
count from LSB in the network-endian word in question.
fn_bit >> 5 : 0 1 2 3
~fn_bit & 0x1f: 31 .... 0 31 .... 0 31 .... 0 31 .... 0
Thus, the mask was generated as htonl(1 << (~fn_bit & 0x1f)).
This can be optimized by "sweezle" (See include/asm-generic/bitops/le.h).
In little-endian,
htonl(1 << bit) = 1 << (bit ^ BITOP_BE32_SWIZZLE)
where
BITOP_BE32_SWIZZLE is (0x1f & ~7)
So,
htonl(1 << (~fn_bit & 0x1f)) = 1 << ((~fn_bit & 0x1f) ^ (0x1f & ~7))
= 1 << ((~fn_bit ^ ~7) & 0x1f)
= 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)
In big-endian, BITOP_BE32_SWIZZLE is equal to 0.
1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)
= 1 << ((~fn_bit) & 0x1f)
= htonl(1 << (~fn_bit & 0x1f))
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
These changes were suggested by Alexey Dobriyan <adobriyan@gmail.com>:
- psched_show() does not use any private data so just pass NULL to
psched_open()
- remove unnecessary return statement
Signed-off-by: Tom Goff <thomas.goff@boeing.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Kconfig and Makefiles with options for:
CAIF: Including caif
CAIF_DEBUG: CAIF Debug
CAIF_NETDEV: CAIF Network Device for GPRS Contexts
Signed-off-by: Sjur Braendeland <sjur.brandeland@stericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Adding GPRS Net Device for PDP Contexts.
The device can be managed by RTNL as defined in if_caif.h.
Signed-off-by: Sjur Braendeland <sjur.brandeland@stericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Implementation of CAIF sockets for protocol and address family
PF_CAIF and AF_CAIF.
CAIF socket is connection oriented implementing SOCK_SEQPACKET
and SOCK_STREAM interface with supporting blocking and non-blocking mode.
Signed-off-by: Sjur Braendeland <sjur.brandeland@stericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Registration and deregistration of CAIF Link Layer.
Signed-off-by: Sjur Braendeland <sjur.brandeland@stericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Support functions for the caif protocol stack:
cfcnfg.c - CAIF Configuration Module used for
adding and removing drivers and connection
cfpkt_skbuff.c - CAIF Packet layer (SKB helper functions)
Signed-off-by: Sjur Braendeland <sjur.brandeland@stericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
CAIF generic protocol implementation. This layer is
somewhat generic in order to be able to use and test it outside
the Linux Kernel.
cfctrl.c - CAIF control protocol layer
cfdbgl.c - CAIF debug protocol layer
cfdgml.c - CAIF datagram protocol layer
cffrml.c - CAIF framing protocol layer
cfmuxl.c - CAIF mux protocol layer
cfrfml.c - CAIF remote file manager protocol layer
cfserl.c - CAIF serial (fragmentation) protocol layer
cfsrvl.c - CAIF generic service layer functions
cfutill.c - CAIF utility protocol layer
cfveil.c - CAIF AT protocol layer
cfvidl.c - CAIF video protocol layer
Signed-off-by: Sjur Braendeland <sjur.brandeland@stericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp_read_sock() can have a eat skbs without immediately advancing copied_seq.
This can cause a panic in tcp_collapse() if it is called as a result
of the recv_actor dropping the socket lock.
A userspace program that splices data from a socket to either another
socket or to a file can trigger this bug.
Signed-off-by: Steven J. Magnani <steve@digidescorp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
"mac80211: fix skb buffering issue" still left a race
between enabling the hardware queues and the virtual
interface queues. In hindsight it's totally obvious
that enabling the netdev queues for a hardware queue
when the hardware queue is enabled is wrong, because
it could well possible that we can fill the hw queue
with packets we already have pending. Thus, we must
only enable the netdev queues once all the pending
packets have been processed and sent off to the device.
In testing, I haven't been able to trigger this race
condition, but it's clearly there, possibly only when
aggregation is being enabled.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Cc: stable@kernel.org
Signed-off-by: John W. Linville <linville@tuxdriver.com>
1st) a PREQ should only be processed, if it has the same SN and better
metric (instead of better or equal).
2nd) next_hop[ETH_ALEN] now actually used to buffer
mpath->next_hop->sta.addr for use out of lock.
Signed-off-by: Marco Porsch <marco.porsch@siemens.com>
Acked-by: Javier Cardona <javier@cozybit.com>
Cc: stable@kernel.org
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Stanse discovered that kmalloc is being called with GFP_KERNEL while
holding this spinlock. The spinlock can be a mutex instead, which also
enables the removal of the unlock/lock around the lock/unlock of
cfg80211_mutex and the call to set_regdom.
Reported-by: Jiri Slaby <jirislaby@gmail.com>
Cc: stable@kernel.org
Signed-off-by: John W. Linville <linville@tuxdriver.com>
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (33 commits)
r8169: offical fix for CVE-2009-4537 (overlength frame DMAs)
ipv6: Don't drop cache route entry unless timer actually expired.
tulip: Add missing parens.
r8169: fix broken register writes
pcnet_cs: add new id
bonding: fix broken multicast with round-robin mode
drivers/net: Fix continuation lines
e1000: do not modify tx_queue_len on link speed change
net: ipmr/ip6mr: prevent out-of-bounds vif_table access
ixgbe: Do not run all Diagnostic offline tests when VFs are active
igb: use correct bits to identify if managability is enabled
benet: Fix compile warnnings in drivers/net/benet/be_ethtool.c
net: Add MSG_WAITFORONE flag to recvmmsg
e1000e: do not modify tx_queue_len on link speed change
igbvf: do not modify tx_queue_len on link speed change
ipv4: Restart rt_intern_hash after emergency rebuild (v2)
ipv4: Cleanup struct net dereference in rt_intern_hash
net: fix netlink address dumping in IPv4/IPv6
tulip: Fix null dereference in uli526x_rx_packet()
gianfar: fix undo of reserve()
...
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is ipv6 variant of the commit 5e016cbf6.. ("ipv4: Don't drop
redirected route cache entry unless PTMU actually expired")
by Guenter Roeck <guenter.roeck@ericsson.com>.
Remove cache route entry in ipv6_negative_advice() only if
the timer is expired.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
When more data is stuffed into an nlmsg than initially projected, an
extra allocation needs to be done. Reserve enough for IFLA_STATS64 so
that this does not to needlessy happen.
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tony Luck observes that the original IFLA_STATS64 submission causes
unaligned accesses. This is because nla_data() returns a pointer to a
memory region that is only aligned to 32 bits. Do some memcpying to
workaround this.
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
When cache is unresolved, c->mf[6]c_parent is set to 65535 and
minvif, maxvif are not initialized, hence we must avoid to
parse IIF and OIF.
A second problem can happen when the user dumps a cache entry
where a VIF, that was referenced at creation time, has been
removed.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add new flag MSG_WAITFORONE for the recvmmsg() syscall.
When this flag is specified for a blocking socket, recvmmsg()
will only block until at least 1 packet is available. The
default behavior is to block until all vlen packets are
available. This flag has no effect on non-blocking sockets
or when used in combination with MSG_DONTWAIT.
Signed-off-by: Brandon L Black <blblack@gmail.com>
Acked-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The the rebuild changes the genid which in turn is used at
the hash calculation. Thus if we don't restart and go on with
inserting the rt will happen in wrong chain.
(Fixed Neil's comment about the index passed into the rt_intern_hash)
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Reviewed-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There's no need in getting it 3 times and gcc isn't smart enough
to understand this himself.
This is just a cleanup before the fix (next patch).
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a dump is interrupted at the last device in a hash chain and
then continued, "idx" won't get incremented past s_idx, so s_ip_idx
is not reset when moving on to the next device. This means of all
following devices only the last n - s_ip_idx addresses are dumped.
Tested-by: Pawel Staszewski <pstaszewski@itcare.pl>
Signed-off-by: Patrick McHardy <kaber@trash.net>
This was included in OpenVZ kernels but wasn't integrated upstream.
>From git://git.openvz.org/pub/linux-2.6.24-openvz:
commit 5c69402f18adf7276352e051ece2cf31feefab02
Author: Alexey Dobriyan <adobriyan@openvz.org>
Date: Mon Dec 24 14:37:45 2007 +0300
netlink: fixup ->tgid to work in multiple PID namespaces
Signed-off-by: Tom Goff <thomas.goff@boeing.com>
Acked-by: Alexey Dobriyan <adobriyan@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use list_add_tail() to get the behavior we had before
the list_head conversion for ipv6 address lists.
Signed-off-by: David S. Miller <davem@davemloft.net>
RPS currently depends on SMP and SYSFS
Adding a CONFIG_RPS makes sense in case this requirement changes in the
future. This patch saves about 1500 bytes of kernel text in case SMP is
on but SYSFS is off.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A missing break statement in hashlimit_ipv6_mask(), and masks
between /64 and /95 are not working at all...
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
The order of the IPv6 raw table is currently reversed, that makes impossible
to use the NOTRACK target in IPv6: for example if someone enters
ip6tables -t raw -A PREROUTING -p tcp --dport 80 -j NOTRACK
and if we receive fragmented packets then the first fragment will be
untracked and thus skip nf_ct_frag6_gather (and conntrack), while all
subsequent fragments enter nf_ct_frag6_gather and reassembly will never
successfully be finished.
Singed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Patrick McHardy <kaber@trash.net>
If dl_seq_start() memory allocation fails, we crash later in
dl_seq_stop(), trying to kfree(ERR_PTR(-ENOMEM))
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
* 'bugfixes' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6:
NFS: don't try to decode GETATTR if DELEGRETURN returned error
sunrpc: handle allocation errors from __rpc_lookup_create()
SUNRPC: Fix the return value of rpc_run_bc_task()
SUNRPC: Fix a use after free bug with the NFSv4.1 backchannel
SUNRPC: Fix a potential memory leak in auth_gss
NFS: Prevent another deadlock in nfs_release_page()
Signed-off-by: Frans Pop <elendil@planet.nl>
Cc: Per Liden <per.liden@ericsson.com>
Cc: Jon Maloy <jon.maloy@ericsson.com>
Cc: Allan Stephens <allan.stephens@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We don't need "dev" any more after:
a5a04819c5
[LLC]: station source mac address
Signed-off-by: Dan Carpenter <error27@gmail.com>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The original code saved the error value but just returned 0 in the end.
Signed-off-by: Dan Carpenter <error27@gmail.com>
Acked-by: Jamal Hadi Salim <hadi@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We don't need "sdata" any more after:
d84f323477
mac80211: remove dev_hold/put calls
Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Add support for the set_cqm_config op. This op function configures the
requested connection quality monitor rssi threshold and rssi hysteresis
values to the hardware if the hardware supports
IEEE80211_HW_SUPPORTS_CQM.
For unsupported hardware, currently -EOPNOTSUPP is returned, so the mac80211
is currently not doing connection quality monitoring on the host. This could be
added later, if needed.
Signed-off-by: Juuso Oikarinen <juuso.oikarinen@nokia.com>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Add support for basic configuration of a connection quality monitoring to the
nl80211 interface, and basic support for notifying about triggered monitoring
events.
Via this interface a user-space connection manager may configure and receive
pre-warning events of deteriorating WLAN connection quality, and start
preparing for roaming in advance, before the connection is already lost.
An example usage of such a trigger is starting scanning for nearby AP's in
an attempt to find one with better connection quality, and associate to it
before the connection characteristics of the existing connection become too bad
or the association is even lost, leading in a prolonged delay in connectivity.
The interface currently supports only RSSI, but it could be later extended
to include other parameters, such as signal-to-noise ratio, if need for that
arises.
Signed-off-by: Juuso Oikarinen <juuso.oikarinen@nokia.com>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Updates real_num_tx_queues in case underlying real device
has changed real_num_tx_queues.
-v2
As per Eric Dumazet<eric.dumazet@gmail.com> comment:-
-- adds BUG_ON to catch case of real_num_tx_queues exceeding num_tx_queues.
-- created this self contained patch to just update real_num_tx_queues.
Signed-off-by: Vasu Dev <vasu.dev@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is required to correctly select vlan tx queue for a driver
supporting multi tx queue with ndo_select_queue implemented since
currently selected vlan tx queue is unaligned to selected queue by
real net_devce ndo_select_queue.
Unaligned vlan tx queue selection causes thrash with higher vlan
tx lock contention for least fcoe traffic and wrong socket tx
queue_mapping for ixgbe having ndo_select_queue implemented.
-v2
As per Eric Dumazet<eric.dumazet@gmail.com> comments, mirrored
vlan net_device_ops to have them with and without vlan_dev_select_queue
and then select according to real dev ndo_select_queue present or not
for a vlan net_device. This is to completely skip vlan_dev_select_queue
calling for real net_device not supporting ndo_select_queue.
Signed-off-by: Vasu Dev <vasu.dev@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Need to take spinlocks when dequeuing from input_pkt_queue in flush_backlog.
Also, flush_backlog can now be called directly from netdev_run_todo.
Signed-off-by: Tom Herbert <therbert@google.com>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is based on a RFC patch by Kalle Valo.
The wl1271 has a feature which handles the connection monitor logic
in hardware, basically sending periodically nullfunc frames and reporting
to the host if AP is lost, after attempting to recover by sending
probe-requests to the AP.
Add support to mac80211 by adding a new flag IEEE80211_HW_CONNECTION_MONITOR
which prevents conn_mon_timer from triggering during idle periods, and
prevents sending probe-requests to the AP if beacon-loss is indicated by the
hardware.
Cc: Kalle Valo <kalle.valo@nokia.com>
Signed-off-by: Juuso Oikarinen <juuso.oikarinen@nokia.com>
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
There's a wireless.h macro for this, might as well use it.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
There's a wireless.h macro for this, might as well use it.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Allows the net_cls cgroup subsystem to be compiled as a module
This patch modifies net/sched/cls_cgroup.c to allow the net_cls subsystem
to be optionally compiled as a module instead of builtin. The
cgroup_subsys struct is moved around a bit to allow the subsys_id to be
either declared as a compile-time constant by the cgroup_subsys.h include
in cgroup.h, or, if it's a module, initialized within the struct by
cgroup_load_subsys.
Signed-off-by: Ben Blum <bblum@andrew.cmu.edu>
Acked-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Paul Menage <menage@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Mostly minor changes to add a net argument to various functions and
remove initial network namespace checks.
Make /proc/net/psched per network namespace.
Signed-off-by: Tom Goff <thomas.goff@boeing.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
v2: update according to Frans' comments.
Currently, if we leave spaces before dst port,
netconsole will silently accept it as 0. Warn about this.
Also, when spaces appear in other places, make them
visible in error messages.
Signed-off-by: WANG Cong <amwang@redhat.com>
Cc: David Miller <davem@davemloft.net>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 8ccb92ad (netfilter: xt_recent: fix false match) fixed supposedly
false matches in rules using a zero hit_count. As it turns out there is
nothing false about these matches and people are actually using entries
with a hit_count of zero to make rules dependant on addresses inserted
manually through /proc.
Since this slipped past the eyes of three reviewers, instead of
reverting the commit in question, this patch explicitly checks
for a hit_count of zero to make the intentions more clear.
Reported-by: Thomas Jarosch <thomas.jarosch@intra2net.com>
Tested-by: Thomas Jarosch <thomas.jarosch@intra2net.com>
Cc: stable@kernel.org
Signed-off-by: Patrick McHardy <kaber@trash.net>
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (38 commits)
ip_gre: include route header_len in max_headroom calculation
if_tunnel.h: add missing ams/byteorder.h include
ipv4: Don't drop redirected route cache entry unless PTMU actually expired
net: suppress lockdep-RCU false positive in FIB trie.
Bluetooth: Fix kernel crash on L2CAP stress tests
Bluetooth: Convert debug files to actually use debugfs instead of sysfs
Bluetooth: Fix potential bad memory access with sysfs files
netfilter: ctnetlink: fix reliable event delivery if message building fails
netlink: fix NETLINK_RECV_NO_ENOBUFS in netlink_set_err()
NET_DMA: free skbs periodically
netlink: fix unaligned access in nla_get_be64()
tcp: Fix tcp_mark_head_lost() with packets == 0
net: ipmr/ip6mr: fix potential out-of-bounds vif_table access
KS8695: update ksp->next_rx_desc_read at the end of rx loop
igb: Add support for 82576 ET2 Quad Port Server Adapter
ixgbevf: Message formatting cleanups
ixgbevf: Shorten up delay timer for watchdog task
ixgbevf: Fix VF Stats accounting after reset
ixgbe: Set IXGBE_RSC_CB(skb)->DMA field to zero after unmapping the address
ixgbe: fix for real_num_tx_queues update issue
...
Currently rpc_run_bc_task() will return NULL if the task allocation failed.
However the only caller is bc_send, which assumes that the return value
will be an ERR_PTR.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
The ->release_request() callback was designed to allow the transport layer
to do housekeeping after the RPC call is done. It cannot be used to free
the request itself, and doing so leads to a use-after-free bug in
xprt_release().
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Taking route's header_len into account, and updating gre device
needed_headroom will give better hints on upper bound of required
headroom. This is useful if the gre traffic is xfrm'ed.
Signed-off-by: Timo Teras <timo.teras@iki.fi>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
We never actually use iph again so this assignment can be removed.
Signed-off-by: Dan Carpenter <error27@gmail.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
TCP sessions over IPv4 can get stuck if routers between endpoints
do not fragment packets but implement PMTU instead, and we are using
those routers because of an ICMP redirect.
Setup is as follows
MTU1 MTU2 MTU1
A--------B------C------D
with MTU1 > MTU2. A and D are endpoints, B and C are routers. B and C
implement PMTU and drop packets larger than MTU2 (for example because
DF is set on all packets). TCP sessions are initiated between A and D.
There is packet loss between A and D, causing frequent TCP
retransmits.
After the number of retransmits on a TCP session reaches tcp_retries1,
tcp calls dst_negative_advice() prior to each retransmit. This results
in route cache entries for the peer to be deleted in
ipv4_negative_advice() if the Path MTU is set.
If the outstanding data on an affected TCP session is larger than
MTU2, packets sent from the endpoints will be dropped by B or C, and
ICMP NEEDFRAG will be returned. A and D receive NEEDFRAG messages and
update PMTU.
Before the next retransmit, tcp will again call dst_negative_advice(),
causing the route cache entry (with correct PMTU) to be deleted. The
retransmitted packet will be larger than MTU2, causing it to be
dropped again.
This sequence repeats until the TCP session aborts or is terminated.
Problem is fixed by removing redirected route cache entries in
ipv4_negative_advice() only if the PMTU is expired.
Signed-off-by: Guenter Roeck <guenter.roeck@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Here is patch to manipulate packet node allocation and implicitly
how packets are DMA'd etc.
The flag NODE_ALLOC enables the function and numa_node_id();
when enabled it can also be explicitly controlled via a new
node parameter
Tested this with 10 Intel 82599 ports w. TYAN S7025 E5520 CPU's.
Was able to TX/DMA ~80 Gbit/s to Ethernet wires.
Signed-off-by: Robert Olsson <robert.olsson@its.uu.se>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use RCU to avoid RTNL use in dev_getfirstbyhwtype()
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is no point to align or pad mibs to cache lines, they are per cpu
allocated with a 8 bytes alignment anyway.
This wastes space for no gain. This patch removes __SNMP_MIB_ALIGN__
Since SNMP mibs contain "unsigned long" fields only, we can relax the
allocation alignment from "unsigned long long" to "unsigned long"
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We currently force a synchronize_net() in netdev_set_master()
This seems necessary only when a slave had a master and we dismantle it.
In the other case ("ifenslave bond0 ethO"), we dont need this long
delay.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Its currently hard to diagnose when ACK frames are dropped because an
application set TCP_DEFER_ACCEPT on its listening socket.
See http://bugzilla.kernel.org/show_bug.cgi?id=15507
This patch adds a SNMP value, named TCPDeferAcceptDrop
netstat -s | grep TCPDeferAcceptDrop
TCPDeferAcceptDrop: 0
This counter is incremented every time we drop a pure ACK frame received
by a socket in SYN_RECV state because its SYNACK retrans count is lower
than defer_accept value.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After the type change, addresses in unicast and multicast lists wouldn't make
sense, not to mention possible different lenghts. So flush both lists here.
Note "dev_addr_discard" will be very soon replaced by "dev_mc_flush" (once
mc_list conversion will be done).
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Ignore the new NETDEV_PRE_TYPE_CHANGE event in rtnetlink_event() since
there have been no changes userspace needs to be notified of.
Also add a comment to the netdev notifier event definitions to remind
people to update the exclusion list when adding new event types.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow fib_find_node() to be called either under rcu_read_lock()
protection or with RTNL held.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The function alloc_enc_pages() currently fails to release the pointer
rqstp->rq_enc_pages in the error path.
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Acked-by: J. Bruce Fields <bfields@citi.umich.edu>
Cc: stable@kernel.org
Some of the debug files ended up wrongly in sysfs, because at that point
of time, debugfs didn't exist. Convert these files to use debugfs and
also seq_file. This patch converts all of these files at once and then
removes the exported symbol for the Bluetooth sysfs class.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
When creating a high number of Bluetooth sockets (L2CAP, SCO
and RFCOMM) it is possible to scribble repeatedly on arbitrary
pages of memory. Ensure that the content of these sysfs files is
always less than one page. Even if this means truncating. The
files in question are scheduled to be moved over to debugfs in
the future anyway.
Based on initial patches from Neil Brown and Linus Torvalds
Reported-by: Neil Brown <neilb@suse.de>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
hlist_for_each_entry(p...) will not necessarily initialize 'p'
to anything if the hlist is empty. GCC notices this and emits
a warning.
Just return true explicitly when we hit a match, and return
false is we fall out of the loop without one.
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch reduces timer events while keeping accuracy by rounding
our timer and/or batching several address validations in addrconf_verify().
addrconf_verify() is called at earliest timeout among interface addresses'
timeouts, but at maximum ADDR_CHECK_FREQUENCY (120 secs).
In most cases, all of timeouts of interface addresses are long enough
(e.g. several hours or days vs 2 minutes), this timer is usually called
every ADDR_CHECK_FREQUENCY, and it is okay to be lazy.
(Note this timer could be eliminated if all code paths which modifies
variables related to timeouts call us manually, but it is another story.)
However, in other least but important cases, we try keeping accuracy.
When the real interface address timeout is coming, and the timeout
is just before the rounded timeout, we accept some error.
When a timeout has been reached, we also try batching other several
events in very near future.
Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The variable regen_advance is only used in the privacy case.
Move it to simplify code and eliminate ifdef's
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some minor stuff, reformat comments and add whitespace for clarity
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Convert to list macro's for the list of addresses per interface
in IPv6.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The existing hash function has a couple of issues:
* it is hardwired to 16 for IN6_ADDR_HSIZE
* limited to 256 and callers using int
* use jhash2 rather than some old BSD algorithm
No need for random seed since this is local only (based on assigned
addresses) table.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Convert from reader/writer lock to RCU and spinlock for addrconf
hash list.
Adds an additional helper macro for hlist_for_each_entry_continue_rcu
to handle the continue case.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Using hash list macros, simplifies code and helps later RCU.
This patch includes some initialization that is not strictly necessary,
since an empty hlist node/list is all zero; and list is in BSS
and node is allocated with kzalloc.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use list macros instead of open coded linked list.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch fixes a bug that allows to lose events when reliable
event delivery mode is used, ie. if NETLINK_BROADCAST_SEND_ERROR
and NETLINK_RECV_NO_ENOBUFS socket options are set.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, ENOBUFS errors are reported to the socket via
netlink_set_err() even if NETLINK_RECV_NO_ENOBUFS is set. However,
that should not happen. This fixes this problem and it changes the
prototype of netlink_set_err() to return the number of sockets that
have set the NETLINK_RECV_NO_ENOBUFS socket option. This return
value is used in the next patch in these bugfix series.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Under NET_DMA, data transfer can grind to a halt when userland issues a
large read on a socket with a high RCVLOWAT (i.e., 512 KB for both).
This appears to be because the NET_DMA design queues up lots of memcpy
operations, but doesn't issue or wait for them (and thus free the
associated skbs) until it is time for tcp_recvmesg() to return.
The socket hangs when its TCP window goes to zero before enough data is
available to satisfy the read.
Periodically issue asynchronous memcpy operations, and free skbs for ones
that have completed, to prevent sockets from going into zero-window mode.
Signed-off-by: Steven J. Magnani <steve@digidescorp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A packet is marked as lost in case packets == 0, although nothing should be done.
This results in a too early retransmitted packet during recovery in some cases.
This small patch fixes this issue by returning immediately.
Signed-off-by: Lennart Schulte <lennart.schulte@nets.rwth-aachen.de>
Signed-off-by: Arnd Hannemann <hannemann@nets.rwth-aachen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
mfc_parent of cache entries is used to index into the vif_table and is
initialised from mfcctl->mfcc_parent. This can take values of to 2^16-1,
while the vif_table has only MAXVIFS (32) entries. The same problem
affects ip6mr.
Refuse invalid values to fix a potential out-of-bounds access. Unlike
the other validity checks, this is checked in ipmr_mfc_add() instead of
the setsockopt handler since its unused in the delete path and might be
uninitialized.
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds RFC5082 checks for TTL on received ICMP packets.
It adds some security against spoofed ICMP packets
disrupting GTSM protected sessions.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As the only path leading to ip6_dst_check makes an indirect call
through dst->ops, dst cannot be NULL in ip6_dst_check.
This patch removes this check in case it misleads people who
come across this code.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Xfrm_dst keeps a reference to ipv4 rtable entries on each
cached bundle. The only way to renew xfrm_dst when the underlying
route has changed, is to implement dst_check for this. This is
what ipv6 side does too.
The problems started after 87c1e12b5e
("ipsec: Fix bogus bundle flowi") which fixed a bug causing xfrm_dst
to not get reused, until that all lookups always generated new
xfrm_dst with new route reference and path mtu worked. But after the
fix, the old routes started to get reused even after they were expired
causing pmtu to break (well it would occationally work if the rtable
gc had run recently and marked the route obsolete causing dst_check to
get called).
Signed-off-by: Timo Teras <timo.teras@iki.fi>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch renames the (never officially released) sysfs-knobs
"blocked_hw" and "blocked_sw" to "hard" and "soft", as the hardware vs
software conotation is misleading.
It also gets rid of not needed locks around u32-read-access.
Signed-off-by: Florian Mickler <florian@mickler.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
When doing "ifenslave -d bond0 eth0", there is chance to get NULL
dereference in netif_receive_skb(), because dev->master suddenly becomes
NULL after we tested it.
We should use ACCESS_ONCE() to avoid this (or rcu_dereference())
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It's not desired for underlaying devices to change type. At the time,
there is for example possible to have bond with changed type from
Ethernet to Infiniband as a port of a bridge. This patch fixes this.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: Jay Vosburgh <fubar@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds the possibility to refuse the bonding type change for
other subsystems (such as for example bridge, vlan, etc.)
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since generally there could be more netdevices changing type other
than bonding, making this event type name "bonding-unrelated"
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
* 'bugfixes' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6:
NFS: ensure bdi_unregister is called on mount failure.
NFS: Avoid a deadlock in nfs_release_page
NFSv4: Don't ignore the NFS_INO_REVAL_FORCED flag in nfs_revalidate_inode()
nfs4: Make the v4 callback service hidden
nfs: fix unlikely memory leak
rpc client can not deal with ENOSOCK, so translate it into ENOCONN
In mlx4, using char * to store mc address in private structure instead.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Forward port commit
fc477e160af086f6e30c3d4fdf5f5c000d29beb5
from git://tipc.cslab.ericsson.net/pub/git/people/allan/tipc.git
Origional commit message:
Allow retransmission of cloned buffers
This patch fixes an issue with TIPC's message retransmission logic
that prevented retransmission of clone sk_buffs. Originally intended
as a means of avoiding wasted work in retransmitting messages that
were still on the driver's outbound queue, it also prevented TIPC
from retransmitting messages through other means -- such as the
secondary bearer of the broadcast link, or another interface in a
set of bonded interfaces. This fix removes existing checks for
cloned sk_buffs that prevented such retransmission.
Origionally-Signed-off-by: Allan Stephens <allan.stephens@windriver.com>
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Forward port commit 29eb572941501c40ac6e62dbc5043bf9ee76ee56
from git://tipc.cslab.ericsson.net/pub/git/people/allan/tipc.git
Origional commit message:
Increase frequency of load distribution over broadcast link
This patch enhances the behavior of TIPC's broadcast link so that it
alternates between redundant bearers (if available) after every
message sent, rather than after every 10 messages. This change helps
to speed up delivery of retransmitted messages by ensuring that
they are not sent repeatedly over a bearer that is no longer working,
but not yet recognized as failed.
Tested by myself in the latest net-2.6 tree using the tipc sanity test suite
Origionally-signed-off-by: Allan Stephens <allan.stephens@windriver.com>
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
bcast.c | 35 ++++++++++++++---------------------
1 file changed, 14 insertions(+), 21 deletions(-)
Signed-off-by: David S. Miller <davem@davemloft.net>
`ip -s link` shows interface counters truncated to 32 bit. This is
because interface statistics are transported only in 32-bit quantity
to userspace. This commit adds a new IFLA_STATS64 attribute that
exports them in full 64 bit.
References: http://lkml.indiana.edu/hypermail/linux/kernel/0307.3/0215.html
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
We hold RTNL at this point and dont use RCU variants of list traversals,
we dont need rcu_read_lock()/rcu_read_unlock()
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The shared packet statistics are a potential source of slow down
on bridged traffic. Convert to per-cpu array, but only keep those
statistics which change per-packet.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch implements software receive side packet steering (RPS). RPS
distributes the load of received packet processing across multiple CPUs.
Problem statement: Protocol processing done in the NAPI context for received
packets is serialized per device queue and becomes a bottleneck under high
packet load. This substantially limits pps that can be achieved on a single
queue NIC and provides no scaling with multiple cores.
This solution queues packets early on in the receive path on the backlog queues
of other CPUs. This allows protocol processing (e.g. IP and TCP) to be
performed on packets in parallel. For each device (or each receive queue in
a multi-queue device) a mask of CPUs is set to indicate the CPUs that can
process packets. A CPU is selected on a per packet basis by hashing contents
of the packet header (e.g. the TCP or UDP 4-tuple) and using the result to index
into the CPU mask. The IPI mechanism is used to raise networking receive
softirqs between CPUs. This effectively emulates in software what a multi-queue
NIC can provide, but is generic requiring no device support.
Many devices now provide a hash over the 4-tuple on a per packet basis
(e.g. the Toeplitz hash). This patch allow drivers to set the HW reported hash
in an skb field, and that value in turn is used to index into the RPS maps.
Using the HW generated hash can avoid cache misses on the packet when
steering it to a remote CPU.
The CPU mask is set on a per device and per queue basis in the sysfs variable
/sys/class/net/<device>/queues/rx-<n>/rps_cpus. This is a set of canonical
bit maps for receive queues in the device (numbered by <n>). If a device
does not support multi-queue, a single variable is used for the device (rx-0).
Generally, we have found this technique increases pps capabilities of a single
queue device with good CPU utilization. Optimal settings for the CPU mask
seem to depend on architectures and cache hierarcy. Below are some results
running 500 instances of netperf TCP_RR test with 1 byte req. and resp.
Results show cumulative transaction rate and system CPU utilization.
e1000e on 8 core Intel
Without RPS: 108K tps at 33% CPU
With RPS: 311K tps at 64% CPU
forcedeth on 16 core AMD
Without RPS: 156K tps at 15% CPU
With RPS: 404K tps at 49% CPU
bnx2x on 16 core AMD
Without RPS 567K tps at 61% CPU (4 HW RX queues)
Without RPS 738K tps at 96% CPU (8 HW RX queues)
With RPS: 854K tps at 76% CPU (4 HW RX queues)
Caveats:
- The benefits of this patch are dependent on architecture and cache hierarchy.
Tuning the masks to get best performance is probably necessary.
- This patch adds overhead in the path for processing a single packet. In
a lightly loaded server this overhead may eliminate the advantages of
increased parallelism, and possibly cause some relative performance degradation.
We have found that masks that are cache aware (share same caches with
the interrupting CPU) mitigate much of this.
- The RPS masks can be changed dynamically, however whenever the mask is changed
this introduces the possibility of generating out of order packets. It's
probably best not change the masks too frequently.
Signed-off-by: Tom Herbert <therbert@google.com>
include/linux/netdevice.h | 32 ++++-
include/linux/skbuff.h | 3 +
net/core/dev.c | 335 +++++++++++++++++++++++++++++++++++++--------
net/core/net-sysfs.c | 225 ++++++++++++++++++++++++++++++-
net/core/skbuff.c | 2 +
5 files changed, 538 insertions(+), 59 deletions(-)
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Create per-cpu workqueue threads instead of a single
krdsd thread. This is a step towards better scalability.
Signed-off-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
set_page_dirty() unconditionally re-enables interrupts, so
if we call it with irqs off, they will be on after the call,
and that's bad. This patch moves the call after we've re-enabled
interrupts in send_drop_to(), so it's safe.
Also, add BUG_ONs to let us know if we ever do call set_page_dirty
with interrupts off.
Signed-off-by: Andy Grover <andy.grover@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
