If we're sending more than one page via kernel_sendpage(), then set
MSG_SENDPAGE_NOTLAST between the pages so that we don't send suboptimal
frames (see commit 2f53384424 and commit 35f9c09fe9).
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
When the controller is unconfigured (for example it does not have a
valid Bluetooth address), then the basic debugfs entries for dut_mode
and vendor_diag are not creates. Ensure they are created in __hci_init
and also __hci_unconf_init functions. One of them is called during setup
stage of a new controller.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Stream protocols such as TCP can often build up a backlog of data to be
read due to ordering. Combine this with the fact that some workloads such
as NFS read()-intensive workloads need to receive a lot of data per RPC
call, and it turns out that receiving the data from inside a softirq
context can cause starvation.
The following patch moves the TCP data receive into a workqueue context.
We still end up calling tcp_read_sock(), but we do so from a process
context, meaning that softirqs are enabled for most of the time.
With this patch, I see a doubling of read bandwidth when running a
multi-threaded iozone workload between a virtual client and server setup.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Move the TCP data receive loop out of xs_tcp_data_ready(). Doing so
will allow us to move the data receive out of the softirq context in
a set of followup patches.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
While recently arguing on a seccomp discussion that raw prandom_u32()
access shouldn't be exposed to unpriviledged user space, I forgot the
fact that SKF_AD_RANDOM extension actually already does it for some time
in cBPF via commit 4cd3675ebf ("filter: added BPF random opcode").
Since prandom_u32() is being used in a lot of critical networking code,
lets be more conservative and split their states. Furthermore, consolidate
eBPF and cBPF prandom handlers to use the new internal PRNG. For eBPF,
bpf_get_prandom_u32() was only accessible for priviledged users, but
should that change one day, we also don't want to leak raw sequences
through things like eBPF maps.
One thought was also to have own per bpf_prog states, but due to ABI
reasons this is not easily possible, i.e. the program code currently
cannot access bpf_prog itself, and copying the rnd_state to/from the
stack scratch space whenever a program uses the prng seems not really
worth the trouble and seems too hacky. If needed, taus113 could in such
cases be implemented within eBPF using a map entry to keep the state
space, or get_random_bytes() could become a second helper in cases where
performance would not be critical.
Both sides can trigger a one-time late init via prandom_init_once() on
the shared state. Performance-wise, there should even be a tiny gain
as bpf_user_rnd_u32() saves one function call. The PRNG needs to live
inside the BPF core since kernels could have a NET-less config as well.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Chema Gonzalez <chema@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There's no good reason why users outside of networking should not
be using this facility, f.e. for initializing their seeds.
Therefore, make it accessible from there as get_random_once().
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch moves values for all lowpan interface to the shared
implementation of 6lowpan. This patch also quietly fixes the forgotten
IFF_NO_QUEUE flag for the bluetooth 6LoWPAN interface. An identically
commit is 4afbc0d ("net: 6lowpan: convert to using IFF_NO_QUEUE") which
wasn't changed for bluetooth 6lowpan.
All 6lowpan interfaces should be virtual with IFF_NO_QUEUE, using EUI64
address length, the mtu size is 1280 (IPV6_MIN_MTU) and the netdev type
is ARPHRD_6LOWPAN.
Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Acked-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Commit deaa0a6a93 ("net: Lookup actual route when oif is VRF device")
exposed a bug in __ip_route_output_key_hash for VRF devices: on FIB lookup
failure if the oif is specified the current logic drops to make_route on
the assumption that the route tables are wrong. For VRF/L3 master devices
this leads to wrong dst entries and route lookups. For example:
$ ip route ls table vrf-red
unreachable default
broadcast 10.2.1.0 dev eth1 proto kernel scope link src 10.2.1.2
10.2.1.0/24 dev eth1 proto kernel scope link src 10.2.1.2
local 10.2.1.2 dev eth1 proto kernel scope host src 10.2.1.2
broadcast 10.2.1.255 dev eth1 proto kernel scope link src 10.2.1.2
$ ip route get oif vrf-red 1.1.1.1
1.1.1.1 dev vrf-red src 10.0.0.2
cache
With this patch:
$ ip route get oif vrf-red 1.1.1.1
RTNETLINK answers: No route to host
which is the correct response based on the default route
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Similar to commit c29390c6df ("xps: must clear sender_cpu before
forwarding"), we also need to clear the skb->sender_cpu when moving
from RX to TX via skb_do_redirect() due to the shared location of
napi_id (used on RX) and sender_cpu (used on TX).
Fixes: 27b29f6305 ("bpf: add bpf_redirect() helper")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Similar to commit c29390c6df ("xps: must clear sender_cpu before forwarding")
the skb->sender_cpu needs to be cleared before xmit.
Fixes: 3896d655f4 ("bpf: introduce bpf_clone_redirect() helper")
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Santosh Shilimkar says:
====================
RDS: connection scalability and performance improvements
[v4]
Re-sending the same patches from v3 again since my repost of
patch 05/14 from v3 was whitespace damaged.
[v3]
Updated patch "[PATCH v2 05/14] RDS: defer the over_batch work to
send worker" as per David Miller's comment [4] to avoid the magic
value usage. Patch now makes use of already available but unused
send_batch_count module parameter. Rest of the patches are same as
earlier version v2 [3]
[v2]:
Dropped "[PATCH 05/15] RDS: increase size of hash-table to 8K" from
earlier version [1]. I plan to address the hash table scalability using
re-sizable hash tables as suggested by David Laight and David Miller [2]
This series addresses RDS connection bottlenecks on massive workloads and
improve the RDMA performance almost by 3X. RDS TCP also gets a small gain
of about 12%.
RDS is being used in massive systems with high scalability where several
hundred thousand end points and tens of thousands of local processes
are operating in tens of thousand sockets. Being RC(reliable connection),
socket bind and release happens very often and any inefficiencies in
bind hash look ups hurts the overall system performance. RDS bin hash-table
uses global spin-lock which is the biggest bottleneck. To make matter worst,
it uses rcu inside global lock for hash buckets.
This is being addressed by simply using per bucket rw lock which makes the
locking simple and very efficient. The hash table size is still an issue and
I plan to address it by using re-sizable hash tables as suggested on the list.
For RDS RDMA improvement, the completion handling is revamped so that we
can do batch completions. Both send and receive completion handlers are
split logically to achieve the same. RDS 8K messages being one of the
key usecase, mr pool is adapted to have the 8K mrs along with default 1M
mrs. And while doing this, few fixes and couple of bottlenecks seen with
rds_sendmsg() are addressed.
Series applies against 4.3-rc1 as well net-next. Its tested on Oracle
hardware with IB fabric for both bcopy as well as RDMA mode. RDS TCP is
tested with iXGB NIC. Like last time, iWARP transport is untested with
these changes. The patchset is also available at below git repo:
git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux.git net/rds/4.3-v3
As a side note, the IB HCA driver I used for testing misses at least 3
important patches in upstream to see the full blown IB performance and
am hoping to get that in mainline with help of them.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The network namespace is already passed into dst_output pass it into
dst->output lwt->output and friends.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Compute net and store it in a variable in the functions
ip_build_and_send_pkt and ip_queue_xmit so that it does not need to be
recomputed next time it is needed.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Store net in a variable in ip_tunnel_xmit so it does not need
to be recomputed when it is used again.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Stop hidding the sk parameter with an inline helper function and make
all of the callers pass it, so that it is clear what the function is
doing.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Only __ip6_local_out_sk has callers so rename __ip6_local_out_sk
__ip6_local_out and remove the previous __ip6_local_out.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It is confusing and silly hiding a parameter so modify all of
the callers to pass in the appropriate socket or skb->sk if
no socket is known.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
For consistency with the other similar methods in the kernel pass a
struct sock into the dst_ops .local_out method.
Simplifying the socket passing case is needed a prequel to passing a
struct net reference into .local_out.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After a packet has been encapsulated by a tunnel we should use the
tunnel sockets local multicast loopback flag to control if the
encapsulated packet should be locally loopback back.
Pass sk into ip_local_out_sk so that in the rare case we are dealing
with a tunneled packet whose tunnel destination address is a multicast
address the kernel properly decides to loopback this packet.
In practice I don't think this matters as ip_queue_xmit is used by
tcp, l2tp and sctp none of which I am aware of uses ip level
multicasting as they are all point to point communications protocols.
Let's fix this before someone uses ip_queue_xmit for a tunnel protocol
that does use multicast.
Fixes: aad88724c9 ("ipv4: add a sock pointer to dst->output() path.")
Fixes: b0270e9101 ("ipv4: add a sock pointer to ip_queue_xmit()")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the rare case where sk != skb->sk ip_local_out_sk arranges
to call dst->output differently if the skb is queued or not.
This is a bug.
Fix this bug by passing the sk parameter of ip_local_out_sk through
from ip_local_out_sk to __ip_local_out_sk (skipping __ip_local_out).
Fixes: 7026b1ddb6 ("netfilter: Pass socket pointer down through okfn().")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch split up struct ib_send_wr so that all non-trivial verbs
use their own structure which embedds struct ib_send_wr. This dramaticly
shrinks the size of a WR for most common operations:
sizeof(struct ib_send_wr) (old): 96
sizeof(struct ib_send_wr): 48
sizeof(struct ib_rdma_wr): 64
sizeof(struct ib_atomic_wr): 96
sizeof(struct ib_ud_wr): 88
sizeof(struct ib_fast_reg_wr): 88
sizeof(struct ib_bind_mw_wr): 96
sizeof(struct ib_sig_handover_wr): 80
And with Sagi's pending MR rework the fast registration WR will also be
down to a reasonable size:
sizeof(struct ib_fastreg_wr): 64
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> [srp, srpt]
Reviewed-by: Chuck Lever <chuck.lever@oracle.com> [sunrpc]
Tested-by: Haggai Eran <haggaie@mellanox.com>
Tested-by: Sagi Grimberg <sagig@mellanox.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
The chan_get() function just adds unnecessary indirection to calling
the chan_create() call. The only added value it gives is the chan->ops
assignment, but that can equally well be done in the calling code.
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
The typical convention when having both a child and a parent channel
variable is to call the former 'chan' and the latter 'pchan'. When
there's only one variable it's called chan. Rename the 'pchan'
variables in the 6lowpan code to follow this convention.
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
The L2CAP core code makes sure of setting the channel state to
BT_CONNECTED, so there's no need for the implementation code (6lowpan
in this case) to do it.
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
The L2CAP core code already sets the local MPS to a sane value. The
remote MPS value otoh comes from the remote side so there's no point
in trying to hard-code it to any value.
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
The omtu value is determined by the remote peer so there's no point in
trying to hard-code it to any value. The IPSP specification otoh gives
a more reasonable value for the imtu, i.e. 1280.
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
When calling the hci_recv_frame driver function check for valid packet
types that the core should process. This should catch issues with
drivers trying to feed vendor packet types through this interface.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
When the controller requires the HCI Reset command to be send when
closing the transport, the HCI_AUTO_OFF needs to be accounted for. The
current code tries to actually do that, but the flag gets cleared to
early. So store its value and use it that stored value instead of
checking for a flag that is always cleared.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
This adds a new debugfs entry for enabling and disabling the vendor
diagnostic mode. It is only exposed for drivers that provide the
set_diag driver callback and actually have an option for vendor
specific diagnostic information.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Introduce hci_recv_diag function for HCI drivers to allow sending vendor
specific diagnostic messages into the Bluetooth core stack. The messages
are not processed, but they are forwarded to the monitor channel and can
be retrieved by user space diagnostic tools.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
The Bluetooth public device address might change during controller setup
and it makes it a lot simpler for monitoring tools if they just get told
what the new address is. In addition include the manufacturer / company
information of the controller. That allows for easy vendor specific HCI
command and event handling.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Some applications use a listen() backlog of 1.
Prior kernels were silently enforcing a qlen_log of 4, so that we were
sending up to /proc/sys/net/ipv4/tcp_synack_retries SYNACK messages.
Fixes: ef547f2ac1 ("tcp: remove max_qlen_log")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Previously, the CT_ATTR_FLAGS attribute, when nested under the
OVS_ACTION_ATTR_CT, encoded a 32-bit bitmask of flags that modify the
semantics of the ct action. It's more extensible to just represent each
flag as a nested attribute, and this requires no additional error
checking to reject flags that aren't currently supported.
Suggested-by: Ben Pfaff <blp@nicira.com>
Signed-off-by: Joe Stringer <joestringer@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ct_state field was initially added as an 8-bit field, however six of
the bits are already being used and use cases are already starting to
appear that may push the limits of this field. This patch extends the
field to 32 bits while retaining the internal representation of 8 bits.
This should cover forward compatibility of the ABI for the foreseeable
future.
This patch also reorders the OVS_CS_F_* bits to be sequential.
Suggested-by: Jarno Rajahalme <jrajahalme@nicira.com>
Signed-off-by: Joe Stringer <joestringer@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Previously, if userspace specified ct_state bits in the flow key which
are currently undefined (and therefore unsupported), then they would be
ignored. This could cause unexpected behaviour in future if userspace is
extended to support additional bits but attempts to communicate with the
current version of the kernel. This patch rectifies the situation by
rejecting such ct_state bits.
Fixes: 7f8a436eaa "openvswitch: Add conntrack action"
Signed-off-by: Joe Stringer <joestringer@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ct action uses parts of the flow key, so we need to ensure that it
is valid before executing that action.
Fixes: 7f8a436eaa "openvswitch: Add conntrack action"
Signed-off-by: Joe Stringer <joestringer@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If ovs_fragment() was unable to fragment the skb due to an L2 header
that exceeds the supported length, skbs would be leaked. Fix the bug.
Fixes: 7f8a436eaa "openvswitch: Add conntrack action"
Signed-off-by: Joe Stringer <joestringer@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If no switch were found in dsa_setup_dst, return -ENODEV and
exit the dsa_probe cleanly.
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now the kfree calls exists in the the remove functions, remove them in all
places except the of_probe functions and replace allocation calls
with their devm_ counterparts.
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
