| Age | Commit message (Collapse) | Author |
|---|
|
git://git.kernel.org/pub/scm/linux/kernel/git/jesse/openvswitch
Jesse Gross says:
====================
A set of OVS changes for net-next/3.16.
The major change here is a switch from per-CPU to per-NUMA flow
statistics. This improves scalability by reducing kernel overhead
in flow setup and maintenance.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
There exist configurations where the administrator or another management
entity has the foreknowledge of all the mac addresses of end systems
that are being bridged together.
In these environments, the administrator can statically configure known
addresses in the bridge FDB and disable flooding and learning on ports.
This makes it possible to turn off promiscuous mode on the interfaces
connected to the bridge.
Here is why disabling flooding and learning allows us to control
promiscuity:
Consider port X. All traffic coming into this port from outside the
bridge (ingress) will be either forwarded through other ports of the
bridge (egress) or dropped. Forwarding (egress) is defined by FDB
entries and by flooding in the event that no FDB entry exists.
In the event that flooding is disabled, only FDB entries define
the egress. Once learning is disabled, only static FDB entries
provided by a management entity define the egress. If we provide
information from these static FDBs to the ingress port X, then we'll
be able to accept all traffic that can be successfully forwarded and
drop all the other traffic sooner without spending CPU cycles to
process it.
Another way to define the above is as following equations:
ingress = egress + drop
expanding egress
ingress = static FDB + learned FDB + flooding + drop
disabling flooding and learning we a left with
ingress = static FDB + drop
By adding addresses from the static FDB entries to the MAC address
filter of an ingress port X, we fully define what the bridge can
process without dropping and can thus turn off promiscuous mode,
thus dropping packets sooner.
There have been suggestions that we may want to allow learning
and update the filters with learned addresses as well. This
would require mac-level authentication similar to 802.1x to
prevent attacks against the hw filters as they are limited
resource.
Additionally, if the user places the bridge device in promiscuous mode,
all ports are placed in promiscuous mode regardless of the changes
to flooding and learning.
Since the above functionality depends on full static configuration,
we have also require that vlan filtering be enabled to take
advantage of this. The reason is that the bridge has to be
able to receive and process VLAN-tagged frames and the there
are only 2 ways to accomplish this right now: promiscuous mode
or vlan filtering.
Suggested-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When a static fdb entry is created, add the mac address
from this fdb entry to any ports that are currently running
in non-promiscuous mode. These ports need this data so that
they can receive traffic destined to these addresses.
By default ports start in promiscuous mode, so this feature
is disabled.
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Introduce a BR_PROMISC per-port flag that will help us track if the
current port is supposed to be in promiscuous mode or not. For now,
always start in promiscuous mode.
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Add code that allows static fdb entires to be synced to the
hw list for a specified port. This will be used later to
program ports that can function in non-promiscuous mode.
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
By default, ports on the bridge are capable of automatic
discovery of nodes located behind the port. This is accomplished
via flooding of unknown traffic (BR_FLOOD) and learning the
mac addresses from these packets (BR_LEARNING).
If the above functionality is disabled by turning off these
flags, the port requires static configuration in the form
of static FDB entries to function properly.
This patch adds functionality to keep track of all ports
capable of automatic discovery. This will later be used
to control promiscuity settings.
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Turn the flag change macro into a function to allow
easier updates and to reduce space.
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The connected check fails to check for ip_gre nbma mode tunnels
properly. ip_gre creates temporary tnl_params with daddr specified
to pass-in the actual target on per-packet basis from neighbor
layer. Detect these tunnels by inspecting the actual tunnel
configuration.
Minimal test case:
ip route add 192.168.1.1/32 via 10.0.0.1
ip route add 192.168.1.2/32 via 10.0.0.2
ip tunnel add nbma0 mode gre key 1 tos c0
ip addr add 172.17.0.0/16 dev nbma0
ip link set nbma0 up
ip neigh add 172.17.0.1 lladdr 192.168.1.1 dev nbma0
ip neigh add 172.17.0.2 lladdr 192.168.1.2 dev nbma0
ping 172.17.0.1
ping 172.17.0.2
The second ping should be going to 192.168.1.2 and head 10.0.0.2;
but cached gre tunnel level route is used and it's actually going
to 192.168.1.1 via 10.0.0.1.
The lladdr's need to go to separate dst for the bug to trigger.
Test case uses separate route entries, but this can also happen
when the route entry is same: if there is a nexthop exception or
the GRE tunnel is IPsec'ed in which case the dst points to xfrm
bundle unique to the gre lladdr.
Fixes: 7d442fab0a67 ("ipv4: Cache dst in tunnels")
Signed-off-by: Timo Teräs <timo.teras@iki.fi>
Cc: Tom Herbert <therbert@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When using command "ip tunnel add" to add a tunnel, the tunnel will be added twice,
through ip_tunnel_create() and ip_tunnel_update().
Because the second is unnecessary, so we can just break after adding tunnel
through ip_tunnel_create().
Signed-off-by: Duan Jiong <duanj.fnst@cn.fujitsu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Adding more than one chip on device-tree currently causes the probing
routine to always use the first chips data pointer.
Signed-off-by: Fabian Godehardt <fg@emlix.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Currently, "ip -6 route get mark xyz" ignores the mark passed in
by userspace. Make it honour the mark, just like IPv4 does.
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch replaces rcu_assign_pointer(x, NULL) with RCU_INIT_POINTER(x, NULL)
The rcu_assign_pointer() ensures that the initialization of a structure
is carried out before storing a pointer to that structure.
And in the case of the NULL pointer, there is no structure to initialize.
So, rcu_assign_pointer(p, NULL) can be safely converted to RCU_INIT_POINTER(p, NULL)
Signed-off-by: Monam Agarwal <monamagarwal123@gmail.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
|
|
We already extract the TCP flags for the key, might as well use that
for stats.
Signed-off-by: Jarno Rajahalme <jrajahalme@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
|
|
The 'output' argument of the ovs_nla_put_flow() is the one from which
the bits are written to the netlink attributes. For SCTP we
accidentally used the bits from the 'swkey' instead. This caused the
mask attributes to include the bits from the actual flow key instead
of the mask.
Signed-off-by: Jarno Rajahalme <jrajahalme@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
|
|
Keep kernel flow stats for each NUMA node rather than each (logical)
CPU. This avoids using the per-CPU allocator and removes most of the
kernel-side OVS locking overhead otherwise on the top of perf reports
and allows OVS to scale better with higher number of threads.
With 9 handlers and 4 revalidators netperf TCP_CRR test flow setup
rate doubles on a server with two hyper-threaded physical CPUs (16
logical cores each) compared to the current OVS master. Tested with
non-trivial flow table with a TCP port match rule forcing all new
connections with unique port numbers to OVS userspace. The IP
addresses are still wildcarded, so the kernel flows are not considered
as exact match 5-tuple flows. This type of flows can be expected to
appear in large numbers as the result of more effective wildcarding
made possible by improvements in OVS userspace flow classifier.
Perf results for this test (master):
Events: 305K cycles
+ 8.43% ovs-vswitchd [kernel.kallsyms] [k] mutex_spin_on_owner
+ 5.64% ovs-vswitchd [kernel.kallsyms] [k] __ticket_spin_lock
+ 4.75% ovs-vswitchd ovs-vswitchd [.] find_match_wc
+ 3.32% ovs-vswitchd libpthread-2.15.so [.] pthread_mutex_lock
+ 2.61% ovs-vswitchd [kernel.kallsyms] [k] pcpu_alloc_area
+ 2.19% ovs-vswitchd ovs-vswitchd [.] flow_hash_in_minimask_range
+ 2.03% swapper [kernel.kallsyms] [k] intel_idle
+ 1.84% ovs-vswitchd libpthread-2.15.so [.] pthread_mutex_unlock
+ 1.64% ovs-vswitchd ovs-vswitchd [.] classifier_lookup
+ 1.58% ovs-vswitchd libc-2.15.so [.] 0x7f4e6
+ 1.07% ovs-vswitchd [kernel.kallsyms] [k] memset
+ 1.03% netperf [kernel.kallsyms] [k] __ticket_spin_lock
+ 0.92% swapper [kernel.kallsyms] [k] __ticket_spin_lock
...
And after this patch:
Events: 356K cycles
+ 6.85% ovs-vswitchd ovs-vswitchd [.] find_match_wc
+ 4.63% ovs-vswitchd libpthread-2.15.so [.] pthread_mutex_lock
+ 3.06% ovs-vswitchd [kernel.kallsyms] [k] __ticket_spin_lock
+ 2.81% ovs-vswitchd ovs-vswitchd [.] flow_hash_in_minimask_range
+ 2.51% ovs-vswitchd libpthread-2.15.so [.] pthread_mutex_unlock
+ 2.27% ovs-vswitchd ovs-vswitchd [.] classifier_lookup
+ 1.84% ovs-vswitchd libc-2.15.so [.] 0x15d30f
+ 1.74% ovs-vswitchd [kernel.kallsyms] [k] mutex_spin_on_owner
+ 1.47% swapper [kernel.kallsyms] [k] intel_idle
+ 1.34% ovs-vswitchd ovs-vswitchd [.] flow_hash_in_minimask
+ 1.33% ovs-vswitchd ovs-vswitchd [.] rule_actions_unref
+ 1.16% ovs-vswitchd ovs-vswitchd [.] hindex_node_with_hash
+ 1.16% ovs-vswitchd ovs-vswitchd [.] do_xlate_actions
+ 1.09% ovs-vswitchd ovs-vswitchd [.] ofproto_rule_ref
+ 1.01% netperf [kernel.kallsyms] [k] __ticket_spin_lock
...
There is a small increase in kernel spinlock overhead due to the same
spinlock being shared between multiple cores of the same physical CPU,
but that is barely visible in the netperf TCP_CRR test performance
(maybe ~1% performance drop, hard to tell exactly due to variance in
the test results), when testing for kernel module throughput (with no
userspace activity, handful of kernel flows).
On flow setup, a single stats instance is allocated (for the NUMA node
0). As CPUs from multiple NUMA nodes start updating stats, new
NUMA-node specific stats instances are allocated. This allocation on
the packet processing code path is made to never block or look for
emergency memory pools, minimizing the allocation latency. If the
allocation fails, the existing preallocated stats instance is used.
Also, if only CPUs from one NUMA-node are updating the preallocated
stats instance, no additional stats instances are allocated. This
eliminates the need to pre-allocate stats instances that will not be
used, also relieving the stats reader from the burden of reading stats
that are never used.
Signed-off-by: Jarno Rajahalme <jrajahalme@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
|
|
The 5-tuple optimization becomes unnecessary with a later per-NUMA
node stats patch. Remove it first to make the changes easier to
grasp.
Signed-off-by: Jarno Rajahalme <jrajahalme@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
|
|
It's slightly smaller/faster for some architectures.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
|
|
Add "openvswitch: " prefix to OVS_NLERR output
to match the other OVS_NLERR output of datapath.c
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
|
|
Each use of pr_<level>_once has a per-site flag.
Some of the OVS_NLERR messages look as if seeing them
multiple times could be useful, so use net_ratelimit()
instead of pr_info_once.
Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
|
|
This is necessary, since u64 is not unsigned long long
in all architectures: u64 could be also uint64_t.
Signed-off-by: Daniele Di Proietto <daniele.di.proietto@gmail.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
|
|
This function must cast a const value to a non const value.
By adding an uintptr_t cast the warning is suppressed.
To avoid the cast (proper solution) several function signatures
must be changed.
Signed-off-by: Daniele Di Proietto <daniele.di.proietto@gmail.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
|
|
This change, firstly, avoids declaring the formal parameter const,
since it is treated as non const. (to avoid -Wcast-qual)
Secondly, it cast the pointer from void* to u8*, since it is used
in arithmetic (to avoid -Wpointer-arith)
Signed-off-by: Daniele Di Proietto <daniele.di.proietto@gmail.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
|
|
In few functions, const formal parameters are assigned or cast to
non-const.
These changes suppress warnings if compiled with -Wcast-qual.
Signed-off-by: Daniele Di Proietto <daniele.di.proietto@gmail.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
|
|
Include changes:
- fix NULL dereference in batadv_orig_hardif_seq_print_text()
- fix reference counting imbalance when using fragmentation
- avoid access to orig_node objects after they have been free'd
- fix local TT check for outgoing arp requests in DAT
|
|
Using whole of allocated pages reduces requested skb->data size.
This is just a little more thriftily allocation.
netperf does not show difference with the current performance.
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless
John W. Linville says:
====================
pull request: wireless 2014-05-15
Please pull this batch of fixes for the 3.15 stream...
For the mac80211 bits, Johannes says:
"One fix is to get better VHT performance and the other fixes tracing
garbage or other potential issues with the interface name tracing."
And...
"This has a fix from Emmanuel for a problem I failed to fix - when
association is in progress then it needs to be cancelled while
suspending (I had fixed the same for authentication). Also included a
fix from myself for a userspace API problem that hit the iw tool and a
fix to the remain-on-channel framework."
For the iwlwifi bits, Emmanuel says:
"Alex fixes the scan by disabling the fragmented scan. David prevents
scan offload while associated, the firmware seems not to like it. I
fix a stupid bug I made in BT Coex, and fix a bad #ifdef clause in rate
scaling. Along with that there is a fix for a NULL pointer exception
that can happen if we load the driver and our ISR gets called because
the interrupt line is shared. The fix has been tested by the reporter."
And...
"We have here a fix from David Spinadel that makes a previous fix more
complete, and an off-by-one issue fixed by Eliad in the same area.
I fix the monitor that broke on the way."
Beyond that...
Daniel Kim's one-liner fixes a brcmfmac regression caused by a typo
in an earlier commit..
Rajkumar Manoharan fixes an ath9k oops reported by David Herrmann.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
There may be padding on the ticket contained in the key payload, so just ensure
that the claimed token length is large enough, rather than exactly the right
size.
Signed-off-by: Nathaniel Wesley Filardo <nwf@cs.jhu.edu>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Commit e2b149cc4ba0 ("crush: add chooseleaf_vary_r tunable") added the
crush_map::chooseleaf_vary_r field but missed the decode part. This
lead to misdirected requests caused by incorrect raw crush mapping
sets.
Fixes: http://tracker.ceph.com/issues/8226
Reported-and-Tested-by: Dmitry Smirnov <onlyjob@member.fsf.org>
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
|
|
It has been reported that using ZFSonLinux on rbd will result in memory
corruption. The bug report can be found here:
https://github.com/zfsonlinux/spl/issues/241
http://tracker.ceph.com/issues/7790
The reason is that ZFS will send pages with page_count 0 into rbd, which in
turns send them to tcp_sendpage. However, tcp_sendpage cannot deal with
page_count 0, as it will do get_page and put_page, and erroneously free the
page.
This type of issue has been noted before, and handled in iscsi, drbd,
etc. So, rbd should also handle this. This fix address this issue by fall back
to slower sendmsg when page_count 0 detected.
Cc: Sage Weil <sage@inktank.com>
Cc: Yehuda Sadeh <yehuda@inktank.com>
Cc: stable@vger.kernel.org
Signed-off-by: Chunwei Chen <tuxoko@gmail.com>
Reviewed-by: Ilya Dryomov <ilya.dryomov@inktank.com>
|
|
cgroup in general is moving towards using cgroup_subsys_state as the
fundamental structural component and css_parent() was introduced to
convert from using cgroup->parent to css->parent. It was quite some
time ago and we're moving forward with making css more prominent.
This patch drops the trivial wrapper css_parent() and let the users
dereference css->parent. While at it, explicitly mark fields of css
which are public and immutable.
v2: New usage from device_cgroup.c converted.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: "David S. Miller" <davem@davemloft.net>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Johannes Weiner <hannes@cmpxchg.org>
|
|
conn_info_age value is calculated in ms, so need to be converted to
jiffies.
Signed-off-by: Andrzej Kaczmarek <andrzej.kaczmarek@tieto.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
|
|
This patch adds support for max_tx_power in Get Connection Information
request. Value is read only once for given connection and then always
returned in response as parameter.
Signed-off-by: Andrzej Kaczmarek <andrzej.kaczmarek@tieto.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
|
|
This patch adds support to store local maximum TX power level for
connection when reply for HCI_Read_Transmit_Power_Level is received.
Signed-off-by: Andrzej Kaczmarek <andrzej.kaczmarek@tieto.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
|
|
TX power for LE links is immutable thus we do not need to query for it
if already have value.
Signed-off-by: Andrzej Kaczmarek <andrzej.kaczmarek@tieto.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
|
|
This patch adds support for Get Connection Information mgmt command
which can be used to query for information about connection, i.e. RSSI
and local TX power level.
In general values cached in hci_conn are returned as long as they are
considered valid, i.e. do not exceed age limit set in hdev. This limit
is calculated as random value between min/max values to avoid client
trying to guess when to poll for updated information.
Signed-off-by: Andrzej Kaczmarek <andrzej.kaczmarek@tieto.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
|
|
This patch adds conn_info_min_age and conn_info_max_age parameters to
debugfs which determine lifetime of connection information. Actual
lifetime will be random value between min and max age.
Default values for min and max age are 1000ms and 3000ms respectively.
Signed-off-by: Andrzej Kaczmarek <andrzej.kaczmarek@tieto.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
|
|
RFC 4861 states in 7.2.5:
The IsRouter flag in the cache entry MUST be set based on the
Router flag in the received advertisement. In those cases
where the IsRouter flag changes from TRUE to FALSE as a result
of this update, the node MUST remove that router from the
Default Router List and update the Destination Cache entries
for all destinations using that neighbor as a router as
specified in Section 7.3.3. This is needed to detect when a
node that is used as a router stops forwarding packets due to
being configured as a host.
Currently, when dealing with NA Message which IsRouter flag changes from
TRUE to FALSE, the kernel only removes router from the Default Router List,
and don't update the Destination Cache entries.
Now in order to update those Destination Cache entries, i introduce
function rt6_clean_tohost().
Signed-off-by: Duan Jiong <duanj.fnst@cn.fujitsu.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec
Conflicts:
net/ipv4/ip_vti.c
Steffen Klassert says:
====================
pull request (net): ipsec 2014-05-15
This pull request has a merge conflict in net/ipv4/ip_vti.c
between commit 8d89dcdf80d8 ("vti: don't allow to add the same
tunnel twice") and commit a32452366b72 ("vti4:Don't count header
length twice"). It can be solved like it is done in linux-next.
1) Fix a ipv6 xfrm output crash when a packet is rerouted
by netfilter to not use IPsec.
2) vti4 counts some header lengths twice leading to an incorrect
device mtu. Fix this by counting these headers only once.
3) We don't catch the case if an unsupported protocol is submitted
to the xfrm protocol handlers, this can lead to NULL pointer
dereferences. Fix this by adding the appropriate checks.
4) vti6 may unregister pernet ops twice on init errors.
Fix this by removing one of the calls to do it only once.
From Mathias Krause.
5) Set the vti tunnel mark before doing a lookup in the error
handlers. Otherwise we don't find the correct xfrm state.
====================
The conflict in ip_vti.c was simple, 'net' had a commit
removing a line from vti_tunnel_init() and this tree
being merged had a commit adding a line to the same
location.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Netdev_priv is an accessor function, and has no purpose if its result is
not used.
A simplified version of the semantic match that fixes this problem is as
follows: (http://coccinelle.lip6.fr/)
// <smpl>
@@ local idexpression x; @@
-x = netdev_priv(...);
... when != x
// </smpl>
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Netdev_priv is an accessor function, and has no purpose if its result is
not used.
A simplified version of the semantic match that fixes this problem is as
follows: (http://coccinelle.lip6.fr/)
// <smpl>
@@ local idexpression x; @@
-x = netdev_priv(...);
... when != x
// </smpl>
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Maps all internal BPF instructions into x86_64 instructions.
This patch replaces original BPF x64 JIT with internal BPF x64 JIT.
sysctl net.core.bpf_jit_enable is reused as on/off switch.
Performance:
1. old BPF JIT and internal BPF JIT generate equivalent x86_64 code.
No performance difference is observed for filters that were JIT-able before
Example assembler code for BPF filter "tcpdump port 22"
original BPF -> old JIT: original BPF -> internal BPF -> new JIT:
0: push %rbp 0: push %rbp
1: mov %rsp,%rbp 1: mov %rsp,%rbp
4: sub $0x60,%rsp 4: sub $0x228,%rsp
8: mov %rbx,-0x8(%rbp) b: mov %rbx,-0x228(%rbp) // prologue
12: mov %r13,-0x220(%rbp)
19: mov %r14,-0x218(%rbp)
20: mov %r15,-0x210(%rbp)
27: xor %eax,%eax // clear A
c: xor %ebx,%ebx 29: xor %r13,%r13 // clear X
e: mov 0x68(%rdi),%r9d 2c: mov 0x68(%rdi),%r9d
12: sub 0x6c(%rdi),%r9d 30: sub 0x6c(%rdi),%r9d
16: mov 0xd8(%rdi),%r8 34: mov 0xd8(%rdi),%r10
3b: mov %rdi,%rbx
1d: mov $0xc,%esi 3e: mov $0xc,%esi
22: callq 0xffffffffe1021e15 43: callq 0xffffffffe102bd75
27: cmp $0x86dd,%eax 48: cmp $0x86dd,%rax
2c: jne 0x0000000000000069 4f: jne 0x000000000000009a
2e: mov $0x14,%esi 51: mov $0x14,%esi
33: callq 0xffffffffe1021e31 56: callq 0xffffffffe102bd91
38: cmp $0x84,%eax 5b: cmp $0x84,%rax
3d: je 0x0000000000000049 62: je 0x0000000000000074
3f: cmp $0x6,%eax 64: cmp $0x6,%rax
42: je 0x0000000000000049 68: je 0x0000000000000074
44: cmp $0x11,%eax 6a: cmp $0x11,%rax
47: jne 0x00000000000000c6 6e: jne 0x0000000000000117
49: mov $0x36,%esi 74: mov $0x36,%esi
4e: callq 0xffffffffe1021e15 79: callq 0xffffffffe102bd75
53: cmp $0x16,%eax 7e: cmp $0x16,%rax
56: je 0x00000000000000bf 82: je 0x0000000000000110
58: mov $0x38,%esi 88: mov $0x38,%esi
5d: callq 0xffffffffe1021e15 8d: callq 0xffffffffe102bd75
62: cmp $0x16,%eax 92: cmp $0x16,%rax
65: je 0x00000000000000bf 96: je 0x0000000000000110
67: jmp 0x00000000000000c6 98: jmp 0x0000000000000117
69: cmp $0x800,%eax 9a: cmp $0x800,%rax
6e: jne 0x00000000000000c6 a1: jne 0x0000000000000117
70: mov $0x17,%esi a3: mov $0x17,%esi
75: callq 0xffffffffe1021e31 a8: callq 0xffffffffe102bd91
7a: cmp $0x84,%eax ad: cmp $0x84,%rax
7f: je 0x000000000000008b b4: je 0x00000000000000c2
81: cmp $0x6,%eax b6: cmp $0x6,%rax
84: je 0x000000000000008b ba: je 0x00000000000000c2
86: cmp $0x11,%eax bc: cmp $0x11,%rax
89: jne 0x00000000000000c6 c0: jne 0x0000000000000117
8b: mov $0x14,%esi c2: mov $0x14,%esi
90: callq 0xffffffffe1021e15 c7: callq 0xffffffffe102bd75
95: test $0x1fff,%ax cc: test $0x1fff,%rax
99: jne 0x00000000000000c6 d3: jne 0x0000000000000117
d5: mov %rax,%r14
9b: mov $0xe,%esi d8: mov $0xe,%esi
a0: callq 0xffffffffe1021e44 dd: callq 0xffffffffe102bd91 // MSH
e2: and $0xf,%eax
e5: shl $0x2,%eax
e8: mov %rax,%r13
eb: mov %r14,%rax
ee: mov %r13,%rsi
a5: lea 0xe(%rbx),%esi f1: add $0xe,%esi
a8: callq 0xffffffffe1021e0d f4: callq 0xffffffffe102bd6d
ad: cmp $0x16,%eax f9: cmp $0x16,%rax
b0: je 0x00000000000000bf fd: je 0x0000000000000110
ff: mov %r13,%rsi
b2: lea 0x10(%rbx),%esi 102: add $0x10,%esi
b5: callq 0xffffffffe1021e0d 105: callq 0xffffffffe102bd6d
ba: cmp $0x16,%eax 10a: cmp $0x16,%rax
bd: jne 0x00000000000000c6 10e: jne 0x0000000000000117
bf: mov $0xffff,%eax 110: mov $0xffff,%eax
c4: jmp 0x00000000000000c8 115: jmp 0x000000000000011c
c6: xor %eax,%eax 117: mov $0x0,%eax
c8: mov -0x8(%rbp),%rbx 11c: mov -0x228(%rbp),%rbx // epilogue
cc: leaveq 123: mov -0x220(%rbp),%r13
cd: retq 12a: mov -0x218(%rbp),%r14
131: mov -0x210(%rbp),%r15
138: leaveq
139: retq
On fully cached SKBs both JITed functions take 12 nsec to execute.
BPF interpreter executes the program in 30 nsec.
The difference in generated assembler is due to the following:
Old BPF imlements LDX_MSH instruction via sk_load_byte_msh() helper function
inside bpf_jit.S.
New JIT removes the helper and does it explicitly, so ldx_msh cost
is the same for both JITs, but generated code looks longer.
New JIT has 4 registers to save, so prologue/epilogue are larger,
but the cost is within noise on x64.
Old JIT checks whether first insn clears A and if not emits 'xor %eax,%eax'.
New JIT clears %rax unconditionally.
2. old BPF JIT doesn't support ANC_NLATTR, ANC_PAY_OFFSET, ANC_RANDOM
extensions. New JIT supports all BPF extensions.
Performance of such filters improves 2-4 times depending on a filter.
The longer the filter the higher performance gain.
Synthetic benchmarks with many ancillary loads see 20x speedup
which seems to be the maximum gain from JIT
Notes:
. net.core.bpf_jit_enable=2 + tools/net/bpf_jit_disasm is still functional
and can be used to see generated assembler
. there are two jit_compile() functions and code flow for classic filters is:
sk_attach_filter() - load classic BPF
bpf_jit_compile() - try to JIT from classic BPF
sk_convert_filter() - convert classic to internal
bpf_int_jit_compile() - JIT from internal BPF
seccomp and tracing filters will just call bpf_int_jit_compile()
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This function is only used within the same translation unit, so mark it
static.
Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
802.15.4 datagram sockets do not currently have a compliant sendmsg().
The destination address supplied is always ignored, and in unconnected
mode, packets are broadcast instead of dropped with -EDESTADDRREQ. This
patch fixes 802.15.4 dgram sockets to be compliant, i.e.
!conn && !msg_name => -EDESTADDRREQ
!conn && msg_name => send to msg_name
conn && !msg_name => send to connected
conn && msg_name => -EISCONN
Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Currently, 6lowpan creates one 802.15.4 MAC header for the original
packet the device was given by upper layers and reuses this header for
all fragments, if fragmentation is required. This also reuses frame
sequence numbers, which must not happen. 6lowpan also has issues with
fragmentation in the presence of security headers, since those may imply
the presence of trailing fields that are not accounted for by the
fragmentation code right now.
Fix both of these issues by properly allocating fragment skbs with
headromm and tailroom as specified by the underlying device, create one
header for each skb instead of reusing the original header, let the
underlying device do the rest.
Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The current mac_cb handling of ieee802154 is rather awkward and limited.
Decompose the single flags field into multiple fields with the meanings
of each subfield of the flags field to make future extensions (for
example, link-layer security) easier. Also don't set the frame sequence
number in upper layers, since that's a thing the MAC is supposed to set
on frame transmit - we set it on header creation, but assuming that
upper layers do not blindly duplicate our headers, this is fine.
Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The current WPAN header creation code checks for EMSGSIZE conditions,
but does not account for the MIC field that link layer security may add
at the end of the frame. Now that we can accurately calculate the
maximum payload size of packets, use that to check for EMSGSIZE
conditions.
Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When dealing with 802.15.4, one often has to know the maximum payload
size for a given packet. This depends on many factors, one of which is
whether or not a security header is present in the frame. These
definitions and functions provide an easy way for any upper layer to
calculate the maximum payload size for a packet. The first obvious user
for this is 6lowpan, which duplicates this calculation and gets it
partially wrong because it ignores security headers.
Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
From: Cong Wang <cwang@twopensource.com>
commit 50624c934db18ab90 (net: Delay default_device_exit_batch until no
devices are unregistering) introduced rtnl_lock_unregistering() for
default_device_exit_batch(). Same race could happen we when rmmod a driver
which calls rtnl_link_unregister() as we call dev->destructor without rtnl
lock.
For long term, I think we should clean up the mess of netdev_run_todo()
and net namespce exit code.
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Change introduced by 88e48d7b3340ef07b108eb8a8b3813dd093cc7f7
("batman-adv: make DAT drop ARP requests targeting local clients")
implements a check that prevents DAT from using the caching
mechanism when the client that is supposed to provide a reply
to an arp request is local.
However change brought by be1db4f6615b5e6156c807ea8985171c215c2d57
("batman-adv: make the Distributed ARP Table vlan aware")
has not converted the above check into its vlan aware version
thus making it useless when the local client is behind a vlan.
Fix the behaviour by properly specifying the vlan when
checking for a client being local or not.
Reported-by: Simon Wunderlich <simon@open-mesh.com>
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
|
|
A pointer to the orig_node representing a bat-gateway is
stored in the gw_node->orig_node member, but the refcount
for such orig_node is never increased.
This leads to memory faults when gw_node->orig_node is accessed
and the originator has already been freed.
Fix this by increasing the refcount on gw_node creation
and decreasing it on gw_node free.
Signed-off-by: Antonio Quartulli <antonio@open-mesh.com>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
|
