This patch creates a new type of interfaceless lightweight tunnel (SEG6),
enabling the encapsulation and injection of SRH within locally emitted
packets and forwarded packets.
>From a configuration viewpoint, a seg6 tunnel would be configured as follows:
ip -6 ro ad fc00::1/128 encap seg6 mode encap segs fc42::1,fc42::2,fc42::3 dev eth0
Any packet whose destination address is fc00::1 would thus be encapsulated
within an outer IPv6 header containing the SRH with three segments, and would
actually be routed to the first segment of the list. If `mode inline' was
specified instead of `mode encap', then the SRH would be directly inserted
after the IPv6 header without outer encapsulation.
The inline mode is only available if CONFIG_IPV6_SEG6_INLINE is enabled. This
feature was made configurable because direct header insertion may break
several mechanisms such as PMTUD or IPSec AH.
Signed-off-by: David Lebrun <david.lebrun@uclouvain.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
Receiving a GSO packet in dev_gro_receive() is not uncommon
in stacked devices, or devices partially implementing LRO/GRO
like bnx2x. GRO is implementing the aggregation the device
was not able to do itself.
Current code causes reorders, like in following case :
For a given flow where sender sent 3 packets P1,P2,P3,P4
Receiver might receive P1 as a single packet, stored in GRO engine.
Then P2-P4 are received as a single GSO packet, immediately given to
upper stack, while P1 is held in GRO engine.
This patch will make sure P1 is given to upper stack, then P2-P4
immediately after.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Without this check, it is not possible to create two rules that
are identical except for their UID ranges. For example:
root@net-test:/# ip rule add prio 1000 lookup 300
root@net-test:/# ip rule add prio 1000 uidrange 100-200 lookup 300
RTNETLINK answers: File exists
root@net-test:/# ip rule add prio 1000 uidrange 100-199 lookup 100
root@net-test:/# ip rule add prio 1000 uidrange 200-299 lookup 200
root@net-test:/# ip rule add prio 1000 uidrange 300-399 lookup 100
RTNETLINK answers: File exists
Tested: https://android-review.googlesource.com/#/c/299980/
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Acked-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Do not set sk_err when dequeuing errors from the error queue.
Doing so results in:
a) Bugs: By overwriting existing sk_err values, it possibly
hides legitimate errors. It is also incorrect when local
errors are queued with ip_local_error. That happens in the
context of a system call, which already returns the error
code.
b) Inconsistent behavior: When there are pending errors on
the error queue, sk_err is sometimes 0 (e.g., for
the first timestamp on the error queue) and sometimes
set to an error code (after dequeuing the first
timestamp).
c) Suboptimality: Setting sk_err to ENOMSG on simple
TX timestamps can abort parallel reads and writes.
Removing this line doesn't break userspace. This is because
userspace code cannot rely on sk_err for detecting whether
there is something on the error queue. Except for ICMP messages
received for UDP and RAW, sk_err is not set at enqueue time,
and as a result sk_err can be 0 while there are plenty of
errors on the error queue.
For ICMP packets in UDP and RAW, sk_err is set when they are
enqueued on the error queue, but that does not result in aborting
reads and writes. For such cases, sk_err is only readable via
getsockopt(SO_ERROR) which will reset the value of sk_err on
its own. More importantly, prior to this patch,
recvmsg(MSG_ERRQUEUE) has a race on setting sk_err (i.e.,
sk_err is set by sock_dequeue_err_skb without atomic ops or
locks) which can store 0 in sk_err even when we have ICMP
messages pending. Removing this line from sock_dequeue_err_skb
eliminates that race.
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The flag IFF_NO_QUEUE marks virtual device drivers that doesn't need a
default qdisc attached, given they will be backed by physical device,
that already have a qdisc attached for pushback.
It is still supported to attach a qdisc to a IFF_NO_QUEUE device, as
this can be useful for difference policy reasons (e.g. bandwidth
limiting containers). For this to work, the tx_queue_len need to have
a sane value, because some qdiscs inherit/copy the tx_queue_len
(namely, pfifo, bfifo, gred, htb, plug and sfb).
Commit a813104d92 ("IFF_NO_QUEUE: Fix for drivers not calling
ether_setup()") caught situations where some drivers didn't initialize
tx_queue_len. The problem with the commit was choosing 1 as the
fallback value.
A qdisc queue length of 1 causes more harm than good, because it
creates hard to debug situations for userspace. It gives userspace a
false sense of a working config after attaching a qdisc. As low
volume traffic (that doesn't activate the qdisc policy) works,
like ping, while traffic that e.g. needs shaping cannot reach the
configured policy levels, given the queue length is too small.
This patch change the value to DEFAULT_TX_QUEUE_LEN, given other
IFF_NO_QUEUE devices (that call ether_setup()) also use this value.
Fixes: a813104d92 ("IFF_NO_QUEUE: Fix for drivers not calling ether_setup()")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A new argument is added to __skb_recv_datagram to provide
an explicit skb destructor, invoked under the receive queue
lock.
The UDP protocol uses such argument to perform memory
reclaiming on dequeue, so that the UDP protocol does not
set anymore skb->desctructor.
Instead explicit memory reclaiming is performed at close() time and
when skbs are removed from the receive queue.
The in kernel UDP protocol users now need to call a
skb_recv_udp() variant instead of skb_recv_datagram() to
properly perform memory accounting on dequeue.
Overall, this allows acquiring only once the receive queue
lock on dequeue.
Tested using pktgen with random src port, 64 bytes packet,
wire-speed on a 10G link as sender and udp_sink as the receiver,
using an l4 tuple rxhash to stress the contention, and one or more
udp_sink instances with reuseport.
nr sinks vanilla patched
1 440 560
3 2150 2300
6 3650 3800
9 4450 4600
12 6250 6450
v1 -> v2:
- do rmem and allocated memory scheduling under the receive lock
- do bulk scheduling in first_packet_length() and in udp_destruct_sock()
- avoid the typdef for the dequeue callback
Suggested-by: Eric Dumazet <edumazet@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
- Define a new FIB rule attributes, FRA_UID_RANGE, to describe a
range of UIDs.
- Define a RTA_UID attribute for per-UID route lookups and dumps.
- Support passing these attributes to and from userspace via
rtnetlink. The value INVALID_UID indicates no UID was
specified.
- Add a UID field to the flow structures.
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Protocol sockets (struct sock) don't have UIDs, but most of the
time, they map 1:1 to userspace sockets (struct socket) which do.
Various operations such as the iptables xt_owner match need
access to the "UID of a socket", and do so by following the
backpointer to the struct socket. This involves taking
sk_callback_lock and doesn't work when there is no socket
because userspace has already called close().
Simplify this by adding a sk_uid field to struct sock whose value
matches the UID of the corresponding struct socket. The semantics
are as follows:
1. Whenever sk_socket is non-null: sk_uid is the same as the UID
in sk_socket, i.e., matches the return value of sock_i_uid.
Specifically, the UID is set when userspace calls socket(),
fchown(), or accept().
2. When sk_socket is NULL, sk_uid is defined as follows:
- For a socket that no longer has a sk_socket because
userspace has called close(): the previous UID.
- For a cloned socket (e.g., an incoming connection that is
established but on which userspace has not yet called
accept): the UID of the socket it was cloned from.
- For a socket that has never had an sk_socket: UID 0 inside
the user namespace corresponding to the network namespace
the socket belongs to.
Kernel sockets created by sock_create_kern are a special case
of #1 and sk_uid is the user that created them. For kernel
sockets created at network namespace creation time, such as the
per-processor ICMP and TCP sockets, this is the user that created
the network namespace.
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds support for setting and using XPS when QoS via traffic
classes is enabled. With this change we will factor in the priority and
traffic class mapping of the packet and use that information to correctly
select the queue.
This allows us to define a set of queues for a given traffic class via
mqprio and then configure the XPS mapping for those queues so that the
traffic flows can avoid head-of-line blocking between the individual CPUs
if so desired.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch updates the code for removing queues from the XPS map and makes
it so that we can apply the code any time we change either the number of
traffic classes or the mapping of a given block of queues. This way we
avoid having queues pulling traffic from a foreign traffic class.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a sysfs attribute for a Tx queue that allows us to determine the
traffic class for a given queue. This will allow us to more easily
determine this in the future. It is needed as XPS will take the traffic
class for a group of queues into account in order to avoid pulling traffic
from one traffic class into another.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The functions for configuring the traffic class to queue mappings have
other effects that need to be addressed. Instead of trying to export a
bunch of new functions just relocate the functions so that we can
instrument them directly with the functionality they will need.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Mostly simple overlapping changes.
For example, David Ahern's adjacency list revamp in 'net-next'
conflicted with an adjacency list traversal bug fix in 'net'.
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking fixes from David Miller:
"Lots of fixes, mostly drivers as is usually the case.
1) Don't treat zero DMA address as invalid in vmxnet3, from Alexey
Khoroshilov.
2) Fix element timeouts in netfilter's nft_dynset, from Anders K.
Pedersen.
3) Don't put aead_req crypto struct on the stack in mac80211, from
Ard Biesheuvel.
4) Several uninitialized variable warning fixes from Arnd Bergmann.
5) Fix memory leak in cxgb4, from Colin Ian King.
6) Fix bpf handling of VLAN header push/pop, from Daniel Borkmann.
7) Several VRF semantic fixes from David Ahern.
8) Set skb->protocol properly in ip6_tnl_xmit(), from Eli Cooper.
9) Socket needs to be locked in udp_disconnect(), from Eric Dumazet.
10) Div-by-zero on 32-bit fix in mlx4 driver, from Eugenia Emantayev.
11) Fix stale link state during failover in NCSCI driver, from Gavin
Shan.
12) Fix netdev lower adjacency list traversal, from Ido Schimmel.
13) Propvide proper handle when emitting notifications of filter
deletes, from Jamal Hadi Salim.
14) Memory leaks and big-endian issues in rtl8xxxu, from Jes Sorensen.
15) Fix DESYNC_FACTOR handling in ipv6, from Jiri Bohac.
16) Several routing offload fixes in mlxsw driver, from Jiri Pirko.
17) Fix broadcast sync problem in TIPC, from Jon Paul Maloy.
18) Validate chunk len before using it in SCTP, from Marcelo Ricardo
Leitner.
19) Revert a netns locking change that causes regressions, from Paul
Moore.
20) Add recursion limit to GRO handling, from Sabrina Dubroca.
21) GFP_KERNEL in irq context fix in ibmvnic, from Thomas Falcon.
22) Avoid accessing stale vxlan/geneve socket in data path, from
Pravin Shelar"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (189 commits)
geneve: avoid using stale geneve socket.
vxlan: avoid using stale vxlan socket.
qede: Fix out-of-bound fastpath memory access
net: phy: dp83848: add dp83822 PHY support
enic: fix rq disable
tipc: fix broadcast link synchronization problem
ibmvnic: Fix missing brackets in init_sub_crq_irqs
ibmvnic: Fix releasing of sub-CRQ IRQs in interrupt context
Revert "ibmvnic: Fix releasing of sub-CRQ IRQs in interrupt context"
arch/powerpc: Update parameters for csum_tcpudp_magic & csum_tcpudp_nofold
net/mlx4_en: Save slave ethtool stats command
net/mlx4_en: Fix potential deadlock in port statistics flow
net/mlx4: Fix firmware command timeout during interrupt test
net/mlx4_core: Do not access comm channel if it has not yet been initialized
net/mlx4_en: Fix panic during reboot
net/mlx4_en: Process all completions in RX rings after port goes up
net/mlx4_en: Resolve dividing by zero in 32-bit system
net/mlx4_core: Change the default value of enable_qos
net/mlx4_core: Avoid setting ports to auto when only one port type is supported
net/mlx4_core: Fix the resource-type enum in res tracker to conform to FW spec
...
netdev_walk_all_lower_dev is not properly walking the lower device
list. Commit 1a3f060c1a made netdev_walk_all_lower_dev similar
to netdev_walk_all_upper_dev_rcu and netdev_walk_all_lower_dev_rcu
but failed to update its netdev_next_lower_dev iterator. This patch
fixes that.
Fixes: 1a3f060c1a ("net: Introduce new api for walking upper and
lower devices")
Reported-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Tested-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When transmitting on a packet socket with PACKET_VNET_HDR and
PACKET_QDISC_BYPASS, validate device support for features requested
in vnet_hdr.
Drop TSO packets sent to devices that do not support TSO or have the
feature disabled. Note that the latter currently do process those
packets correctly, regardless of not advertising the feature.
Because of SKB_GSO_DODGY, it is not sufficient to test device features
with netif_needs_gso. Full validate_xmit_skb is needed.
Switch to software checksum for non-TSO packets that request checksum
offload if that device feature is unsupported or disabled. Note that
similar to the TSO case, device drivers may perform checksum offload
correctly even when not advertising it.
When switching to software checksum, packets hit skb_checksum_help,
which has two BUG_ON checksum not in linear segment. Packet sockets
always allocate at least up to csum_start + csum_off + 2 as linear.
Tested by running github.com/wdebruij/kerneltools/psock_txring_vnet.c
ethtool -K eth0 tso off tx on
psock_txring_vnet -d $dst -s $src -i eth0 -l 2000 -n 1 -q -v
psock_txring_vnet -d $dst -s $src -i eth0 -l 2000 -n 1 -q -v -N
ethtool -K eth0 tx off
psock_txring_vnet -d $dst -s $src -i eth0 -l 1000 -n 1 -q -v -G
psock_txring_vnet -d $dst -s $src -i eth0 -l 1000 -n 1 -q -v -G -N
v2:
- add EXPORT_SYMBOL_GPL(validate_xmit_skb_list)
Fixes: d346a3fae3 ("packet: introduce PACKET_QDISC_BYPASS socket option")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
No one can see these events, because a network namespace can not be
destroyed, if it has sockets.
Unlike other devices, uevent-s for network devices are generated
only inside their network namespaces. They are filtered in
kobj_bcast_filter()
My experiments shows that net namespaces are destroyed more 30% faster
with this optimization.
Here is a perf output for destroying network namespaces without this
patch.
- 94.76% 0.02% kworker/u48:1 [kernel.kallsyms] [k] cleanup_net
- 94.74% cleanup_net
- 94.64% ops_exit_list.isra.4
- 41.61% default_device_exit_batch
- 41.47% unregister_netdevice_many
- rollback_registered_many
- 40.36% netdev_unregister_kobject
- 14.55% device_del
+ 13.71% kobject_uevent
- 13.04% netdev_queue_update_kobjects
+ 12.96% kobject_put
- 12.72% net_rx_queue_update_kobjects
kobject_put
- kobject_release
+ 12.69% kobject_uevent
+ 0.80% call_netdevice_notifiers_info
+ 19.57% nfsd_exit_net
+ 11.15% tcp_net_metrics_exit
+ 8.25% rpcsec_gss_exit_net
It's very critical to optimize the exit path for network namespaces,
because they are destroyed under net_mutex and many namespaces can be
destroyed for one iteration.
v2: use dev_set_uevent_suppress()
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Andrei Vagin <avagin@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
gcc warns about an uninitialized pointer dereference in the vlan
priority handling:
net/core/flow_dissector.c: In function '__skb_flow_dissect':
net/core/flow_dissector.c:281:61: error: 'vlan' may be used uninitialized in this function [-Werror=maybe-uninitialized]
As pointed out by Jiri Pirko, the variable is never actually used
without being initialized first as the only way it end up uninitialized
is with skb_vlan_tag_present(skb)==true, and that means it does not
get accessed.
However, the warning hints at some related issues that I'm addressing
here:
- the second check for the vlan tag is different from the first one
that tests the skb for being NULL first, causing both the warning
and a possible NULL pointer dereference that was not entirely fixed.
- The same patch that introduced the NULL pointer check dropped an
earlier optimization that skipped the repeated check of the
protocol type
- The local '_vlan' variable is referenced through the 'vlan' pointer
but the variable has gone out of scope by the time that it is
accessed, causing undefined behavior
Caching the result of the 'skb && skb_vlan_tag_present(skb)' check
in a local variable allows the compiler to further optimize the
later check. With those changes, the warning also disappears.
Fixes: 3805a938a6 ("flow_dissector: Check skb for VLAN only if skb specified.")
Fixes: d5709f7ab7 ("flow_dissector: For stripped vlan, get vlan info from skb->vlan_tci")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Eric Garver <e@erig.me>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now genl_register_family() is the only thing (other than the
users themselves, perhaps, but I didn't find any doing that)
writing to the family struct.
In all families that I found, genl_register_family() is only
called from __init functions (some indirectly, in which case
I've add __init annotations to clarifly things), so all can
actually be marked __ro_after_init.
This protects the data structure from accidental corruption.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of providing macros/inline functions to initialize
the families, make all users initialize them statically and
get rid of the macros.
This reduces the kernel code size by about 1.6k on x86-64
(with allyesconfig).
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Static family IDs have never really been used, the only
use case was the workaround I introduced for those users
that assumed their family ID was also their multicast
group ID.
Additionally, because static family IDs would never be
reserved by the generic netlink code, using a relatively
low ID would only work for built-in families that can be
registered immediately after generic netlink is started,
which is basically only the control family (apart from
the workaround code, which I also had to add code for so
it would reserve those IDs)
Thus, anything other than GENL_ID_GENERATE is flawed and
luckily not used except in the cases I mentioned. Move
those workarounds into a few lines of code, and then get
rid of GENL_ID_GENERATE entirely, making it more robust.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a port_type_set() is been called and the new port type set is the same
as the old one, just return success.
Signed-off-by: Elad Raz <eladr@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net_mutex can be locked for a long time. It may be because many
namespaces are being destroyed or many processes decide to create
a network namespace.
Both these operations are heavy, so it is better to have an ability to
kill a process which is waiting net_mutex.
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Andrei Vagin <avagin@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use case is mainly for soreuseport to select sockets for the local
numa node, but since generic, lets also add this for other networking
and tracing program types.
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
David Lebrun
Eric Dumazet
Lorenzo Colitti
Soheil Hassas Yeganeh
Jesper Dangaard Brouer
Paolo Abeni
Alexander Duyck
David S. Miller
Linus Torvalds
David Ahern
Florian Westphal
Willem de Bruijn
Andrey Vagin
Arnd Bergmann
Johannes Berg
Elad Raz
Daniel Borkmann