fdb dumps spanning multiple skb's currently restart from the first
interface again for every skb. This results in unnecessary
iterations on the already visited interfaces and their fdb
entries. In large scale setups, we have seen this to slow
down fdb dumps considerably. On a system with 30k macs we
see fdb dumps spanning across more than 300 skbs.

To fix the problem, this patch replaces the existing single fdb
marker with three markers: netdev hash entries, netdevs and fdb
index to continue where we left off instead of restarting from the
first netdev. This is consistent with link dumps.

In the process of fixing the performance issue, this patch also
re-implements fix done by
commit 472681d5 ("net: ndo_fdb_dump should report -EMSGSIZE to rtnl_fdb_dump")
(with an internal fix from Wilson Kok) in the following ways:
- change ndo_fdb_dump handlers to return error code instead
of the last fdb index
- use cb->args strictly for dump frag markers and not error codes.
This is consistent with other dump functions.

Below results were taken on a system with 1000 netdevs
and 35085 fdb entries:
before patch:
$time bridge fdb show | wc -l
15065

real    1m11.791s
user    0m0.070s
sys 1m8.395s

(existing code does not return all macs)

after patch:
$time bridge fdb show | wc -l
35085

real    0m2.017s
user    0m0.113s
sys 0m1.942s
Signed-off-by: NRoopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: NWilson Kok <wkok@cumulusnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

switchdev_port_fwd_mark_set() is used to set the 'offload_fwd_mark' of
port netdevs so that packets being flooded by the device won't be
flooded twice.

It works by assigning a unique identifier (the ifindex of the first
bridge port) to bridge ports sharing the same parent ID. This prevents
packets from being flooded twice by the same switch, but will flood
packets through bridge ports belonging to a different switch.

This method is problematic when stacked devices are taken into account,
such as VLANs. In such cases, a physical port netdev can have upper
devices being members in two different bridges, thus requiring two
different 'offload_fwd_mark's to be configured on the port netdev, which
is impossible.

The main problem is that packet and netdev marking is performed at the
physical netdev level, whereas flooding occurs between bridge ports,
which are not necessarily port netdevs.

Instead, packet and netdev marking should really be done in the bridge
driver with the switch driver only telling it which packets it already
forwarded. The bridge driver will mark such packets using the mark
assigned to the ingress bridge port and will prevent the packet from
being forwarded through any bridge port sharing the same mark (i.e.
having the same parent ID).

Remove the current switchdev 'offload_fwd_mark' implementation and
instead implement the proposed method. In addition, make rocker - the
sole user of the mark - use the proposed method.
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The idea for type_check in dev_get_nest_level() was to count the number
of nested devices of the same type (currently, only macvlan or vlan
devices).
This prevented the false positive lockdep warning on configurations such
as:

eth0 <--- macvlan0 <--- vlan0 <--- macvlan1

However, this doesn't prevent a warning on a configuration such as:

eth0 <--- macvlan0 <--- vlan0
eth1 <--- vlan1 <--- macvlan1

In this case, all the locks end up with a nesting subclass of 1, so
lockdep thinks that there is still a deadlock:

- in the first case we have (macvlan_netdev_addr_lock_key, 1) and then
  take (vlan_netdev_xmit_lock_key, 1)
- in the second case, we have (vlan_netdev_xmit_lock_key, 1) and then
  take (macvlan_netdev_addr_lock_key, 1)

By removing the linktype check in dev_get_nest_level() and always
incrementing the nesting depth, lockdep considers this configuration
valid.
Signed-off-by: NSabrina Dubroca <sd@queasysnail.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Convert the per-device linked list into a hashtable. The primary
motivation for this change is that currently, we're not tracking all the
qdiscs in hierarchy (e.g. excluding default qdiscs), as the lookup
performed over the linked list by qdisc_match_from_root() is rather
expensive.

The ultimate goal is to get rid of hidden qdiscs completely, which will
bring much more determinism in user experience.
Reviewed-by: NCong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NJiri Kosina <jkosina@suse.cz>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Following the work that have been done on offloading classifiers like u32
and flower, now the match-all classifier hw offloading is possible. if
the interface supports tc offloading.

To control the offloading, two tc flags have been introduced: skip_sw and
skip_hw. Typical usage:

tc filter add dev eth25 parent ffff: 	\
	matchall skip_sw		\
	action mirred egress mirror	\
	dev eth27
Signed-off-by: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add one new netdev op for drivers implementing the BPF_PROG_TYPE_XDP
filter. The single op is used for both setup/query of the xdp program,
modelled after ndo_setup_tc.
Signed-off-by: NBrenden Blanco <bblanco@plumgrid.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

macsec can't cope with mtu frames which need vlan tag insertion, and
vlan device set the default mtu equal to the underlying dev's one.
By default vlan over macsec devices use invalid mtu, dropping
all the large packets.
This patch adds a netif helper to check if an upper vlan device
needs mtu reduction. The helper is used during vlan devices
initialization to set a valid default and during mtu updating to
forbid invalid, too bit, mtu values.
The helper currently only check if the lower dev is a macsec device,
if we get more users, we need to update only the helper (possibly
reserving an additional IFF bit).
Signed-off-by: NPaolo Abeni <pabeni@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

L2 upper device needs to propagate neigh_construct/destroy calls down to
lower devices. Do this by defining default ndo functions and use them in
team, bond, bridge and vlan.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As the following patch will allow upper devices to follow the call down
lower devices, we need to add dev here and not rely on n->dev.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add functions that iterate over lower devices and find port device.
As a dependency add netdev_for_each_all_lower_dev and
netdev_for_each_all_lower_dev_rcu macro with
netdev_all_lower_get_next and netdev_all_lower_get_next_rcu shelpers.

Also, add functions to return mlxsw struct according to lower device
found and mlxsw_port struct with a reference to lower device.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NIdo Schimmel <idosch@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch introduces a new event - NETDEV_CHANGE_TX_QUEUE_LEN, this
will be triggered when tx_queue_len. It could be used by net device
who want to do some processing at that time. An example is tun who may
want to resize tx array when tx_queue_len is changed.

Cc: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Acked-by: NJohn Fastabend <john.r.fastabend@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that we have all the drivers using udp_tunnel_get_rx_ports,
ndo_add_udp_enc_rx_port, and ndo_del_udp_enc_rx_port we can drop the
function calls that were specific to VXLAN and GENEVE.
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Acked-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch merges the notifiers for VXLAN and GENEVE into a single UDP
tunnel notifier.  The idea is that we will want to only have to make one
notifier call to receive the list of ports for VXLAN and GENEVE tunnels
that need to be offloaded.

In addition we add a new set of ndo functions named ndo_udp_tunnel_add and
ndo_udp_tunnel_del that are meant to allow us to track the tunnel meta-data
such as port and address family as tunnels are added and removed.  The
tunnel meta-data is now transported in a structure named udp_tunnel_info
which for now carries the type, address family, and port number.  In the
future this could be updated so that we can include a tuple of values
including things such as the destination IP address and other fields.

I also ended up going with a naming scheme that consisted of using the
prefix udp_tunnel on function names.  I applied this to the notifier and
ndo ops as well so that it hopefully points to the fact that these are
primarily used in the udp_tunnel functions.
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Acked-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch introduces neighbour discovery ops callback structure. The
idea is to separate the handling for 6LoWPAN into the 6lowpan module.

These callback offers 6lowpan different handling, such as 802.15.4 short
address handling or RFC6775 (Neighbor Discovery Optimization for IPv6
over 6LoWPANs).

Cc: David S. Miller <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: James Morris <jmorris@namei.org>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Patrick McHardy <kaber@trash.net>
Acked-by: NYOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: NAlexander Aring <aar@pengutronix.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch will introduce a 6lowpan neighbour private data. Like the
interface private data we handle private data for generic 6lowpan and
for link-layer specific 6lowpan.

The current first use case if to save the short address for a 802.15.4
6lowpan neighbour.

Cc: David S. Miller <davem@davemloft.net>
Reviewed-by: NStefan Schmidt <stefan@osg.samsung.com>
Acked-by: NYOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: NAlexander Aring <aar@pengutronix.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

sch_atm returns this when TC_ACT_SHOT classification occurs.

But all other schedulers that use tc_classify
(htb, hfsc, drr, fq_codel ...) return NET_XMIT_SUCCESS | __BYPASS
in this case so just do that in atm.

BATMAN uses it as an intermediate return value to signal
forwarding vs. buffering, but it did not return POLICED to
callers outside of BATMAN.
Reviewed-by: NSven Eckelmann <sven@narfation.org>
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Respect the stack's xmit_recursion limit for calls into dev_queue_xmit().
Currently, they are not handeled by the limiter when attached to clsact's
egress parent, for example, and a buggy program redirecting it to the
same device again could run into stack overflow eventually. It would be
good if we could notify an admin to give him a chance to react. We reuse
xmit_recursion instead of having one private to eBPF, so that the stack's
current recursion depth will be taken into account as well. Follow-up to
commit 3896d655 ("bpf: introduce bpf_clone_redirect() helper") and
27b29f63 ("bpf: add bpf_redirect() helper").
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NAlexei Starovoitov <ast@kernel.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It is time to add netdev_lockdep_set_classes() helper
so that lockdep annotations per device type are easier to manage.

This removes a lot of copies and missing annotations.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

"make htmldocs" complains otherwise:

.//net/core/gen_stats.c:168: warning: No description found for parameter 'running'
.//include/linux/netdevice.h:1867: warning: No description found for parameter 'qdisc_running_key'

Fixes: f9eb8aea ("net_sched: transform qdisc running bit into a seqcount")
Fixes: edb09eb1 ("net: sched: do not acquire qdisc spinlock in qdisc/class stats dump")
Signed-off-by: NEric Dumazet <edumazet@google.com>
Reported-by: Nkbuild test robot <fengguang.wu@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Instead of using a single bit (__QDISC___STATE_RUNNING)
in sch->__state, use a seqcount.

This adds lockdep support, but more importantly it will allow us
to sample qdisc/class statistics without having to grab qdisc root lock.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

SCTP has this pecualiarity that its packets cannot be just segmented to
(P)MTU. Its chunks must be contained in IP segments, padding respected.
So we can't just generate a big skb, set gso_size to the fragmentation
point and deliver it to IP layer.

This patch takes a different approach. SCTP will now build a skb as it
would be if it was received using GRO. That is, there will be a cover
skb with protocol headers and children ones containing the actual
segments, already segmented to a way that respects SCTP RFCs.

With that, we can tell skb_segment() to just split based on frag_list,
trusting its sizes are already in accordance.

This way SCTP can benefit from GSO and instead of passing several
packets through the stack, it can pass a single large packet.

v2:
- Added support for receiving GSO frames, as requested by Dave Miller.
- Clear skb->cb if packet is GSO (otherwise it's not used by SCTP)
- Added heuristics similar to what we have in TCP for not generating
  single GSO packets that fills cwnd.
v3:
- consider sctphdr size in skb_gso_transport_seglen()
- rebased due to 5c7cdf33 ("gso: Remove arbitrary checks for
  unsupported GSO")
Signed-off-by: NMarcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Tested-by: NXin Long <lucien.xin@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch defines two new GSO definitions SKB_GSO_IPXIP4 and
SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and
NETIF_F_GSO_IPXIP6. These are used to described IP in IP
tunnel and what the outer protocol is. The inner protocol
can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and
SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT
are removed (these are both instances of SKB_GSO_IPXIP4).
SKB_GSO_IPXIP6 will be used when support for GSO with IP
encapsulation over IPv6 is added.
Signed-off-by: NTom Herbert <tom@herbertland.com>
Acked-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Move the bpf_jit_enable declaration to the filter.h file where
most other core code is declared, also since we're going to add
a second knob there.
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Acked-by: NAlexei Starovoitov <ast@kernel.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently the VRF driver uses the rx_handler to switch the skb device
to the VRF device. Switching the dev prior to the ip / ipv6 layer
means the VRF driver has to duplicate IP/IPv6 processing which adds
overhead and makes features such as retaining the ingress device index
more complicated than necessary.

This patch moves the hook to the L3 layer just after the first NF_HOOK
for PRE_ROUTING. This location makes exposing the original ingress device
trivial (next patch) and allows adding other NF_HOOKs to the VRF driver
in the future.

dev_queue_xmit_nit is exported so that the VRF driver can cycle the skb
with the switched device through the packet taps to maintain current
behavior (tcpdump can be used on either the vrf device or the enslaved
devices).
Signed-off-by: NDavid Ahern <dsa@cumulusnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

UDP tunnel segmentation code relies on the inner offsets being set for
an UDP tunnel GSO packet, but the inner *_complete() functions will
set the inner offsets only if 'encapsulation' is set before calling
them.  Currently, udp_gro_complete() sets 'encapsulation' only after
the inner *_complete() functions are done.  This causes the inner
offsets having invalid values after udp_gro_complete() returns, which
in turn will make it impossible to properly segment the packet in case
it needs to be forwarded, which would be visible to the user either as
invalid packets being sent or as packet loss.

This patch fixes this by setting skb's 'encapsulation' in
udp_gro_complete() before calling into the inner complete functions,
and by making each possible UDP tunnel gro_complete() callback set the
inner_mac_header to the beginning of the tunnel payload.
Signed-off-by: NJarno Rajahalme <jarno@ovn.org>
Reviewed-by: NAlexander Duyck <aduyck@mirantis.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

previous patches removed all direct accesses to dev->trans_start,
so change the netif_trans_update helper to update trans_start of
netdev queue 0 instead and then remove trans_start from struct net_device.

AFAICS a lot of the netif_trans_update() invocations are now useless
because they occur in ndo_start_xmit and driver doesn't set LLTX
(i.e. stack already took care of the update).

As I can't test any of them it seems better to just leave them alone.
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

trans_start exists twice:
- as member of net_device (legacy)
- as member of netdev_queue

In order to get rid of the legacy case, add a helper for the
dev->trans_update (this patch), then convert spots that do

dev->trans_start = jiffies

to use this helper (next patch).

This would then allow us to change the helper so that it updates the
trans_stamp of netdev queue 0 instead.
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

- trans_timeout is incremented when tx queue timed out (tx watchdog).
- tx_maxrate is set via sysfs

Moving tx_maxrate to read-mostly part shrinks the struct by 64 bytes.
While at it, also move trans_timeout (it is out-of-place in the
'write-mostly' part).
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

is_skb_forwardable is not supposed to change anything so constify its
arguments
Signed-off-by: NNikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix casting in net_gso_ok. Otherwise the shift on
gso_type << NETIF_F_GSO_SHIFT may hit the 32th bit and make it look like
a INT_MIN, which is then promoted from signed to uint64 which is
0xffffffff80000000, resulting in wrong behavior when it is and'ed with
the feature itself, as in:

This test app:
#include <stdio.h>
#include <stdint.h>

int main(int argc, char **argv)
{
	uint64_t feature1;
	uint64_t feature2;
	int gso_type = 1 << 15;

	feature1 = gso_type << 16;
	feature2 = (uint64_t)gso_type << 16;
	printf("%lx %lx\n", feature1, feature2);

	return 0;
}

Gives:
ffffffff80000000 80000000

So that this:
   return (features & feature) == feature;
Actually works on more bits than expected and invalid ones.

Fix is to promote it earlier.

Issue noted while rebasing SCTP GSO patch but posting separetely as
someone else may experience this meanwhile.
Signed-off-by: NMarcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

sd->input_queue_head is incremented for each processed packet
in process_backlog(), and read from other cpus performing
Out Of Order avoidance in get_rps_cpu()

Moving this field in a separate cache line keeps it mostly
hot for the cpu in process_backlog(), as other cpus will
only read it.

In a stress test, process_backlog() was consuming 6.80 % of cpu cycles,
and the patch reduced the cost to 0.65 %
Signed-off-by: NEric Dumazet <edumazet@google.com>
Acked-by: NTom Herbert <tom@herbertland.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

No more users in the tree, remove NETDEV_TX_LOCKED support.
Adds another hole in softnet_stats struct, but better than keeping
the unused collision counter around.
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Equivalent to "vxlan: break dependency with netdev drivers", don't
autoload geneve module in case the driver is loaded. Instead make the
coupling weaker by using netdevice notifiers as proxy.

Cc: Jesse Gross <jesse@kernel.org>
Signed-off-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently all drivers depend and autoload the vxlan module because how
vxlan_get_rx_port is linked into them. Remove this dependency:

By using a new event type in the netdevice notifier call chain we proxy
the request from the drivers to flush and resetup the vxlan ports not
directly via function call but by the already existing netdevice
notifier call chain.

I added a separate new event type, NETDEV_OFFLOAD_PUSH_VXLAN, to do so.
We don't need to save those ids, as the event type field is an unsigned
long and using specialized event types for this purpose seemed to be a
more elegant way. This also comes in beneficial if in future we want to
add offloading knobs for vxlan.

Cc: Jesse Gross <jesse@kernel.org>
Signed-off-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds support for something I am referring to as GSO partial.
The basic idea is that we can support a broader range of devices for
segmentation if we use fixed outer headers and have the hardware only
really deal with segmenting the inner header.  The idea behind the naming
is due to the fact that everything before csum_start will be fixed headers,
and everything after will be the region that is handled by hardware.

With the current implementation it allows us to add support for the
following GSO types with an inner TSO_MANGLEID or TSO6 offload:
NETIF_F_GSO_GRE
NETIF_F_GSO_GRE_CSUM
NETIF_F_GSO_IPIP
NETIF_F_GSO_SIT
NETIF_F_UDP_TUNNEL
NETIF_F_UDP_TUNNEL_CSUM

In the case of hardware that already supports tunneling we may be able to
extend this further to support TSO_TCPV4 without TSO_MANGLEID if the
hardware can support updating inner IPv4 headers.
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch does two things.

First it allows TCP to aggregate TCP frames with a fixed IPv4 ID field.  As
a result we should now be able to aggregate flows that were converted from
IPv6 to IPv4.  In addition this allows us more flexibility for future
implementations of segmentation as we may be able to use a fixed IP ID when
segmenting the flow.

The second thing this does is that it places limitations on the outer IPv4
ID header in the case of tunneled frames.  Specifically it forces the IP ID
to be incrementing by 1 unless the DF bit is set in the outer IPv4 header.
This way we can avoid creating overlapping series of IP IDs that could
possibly be fragmented if the frame goes through GRO and is then
resegmented via GSO.
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds support for TSO using IPv4 headers with a fixed IP ID
field.  This is meant to allow us to do a lossless GRO in the case of TCP
flows that use a fixed IP ID such as those that convert IPv6 header to IPv4
headers.

In addition I am adding a feature that for now I am referring to TSO with
IP ID mangling.  Basically when this flag is enabled the device has the
option to either output the flow with incrementing IP IDs or with a fixed
IP ID regardless of what the original IP ID ordering was.  This is useful
in cases where the DF bit is set and we do not care if the original IP ID
value is maintained.
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After introduction of ndo_features_check(), we believe that very
specific checks for rare features should not be done in core
networking stack.

No driver uses gso_min_segs yet, so we revert this feature and save
few instructions per tx packet in fast path.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Sometimes gcc mysteriously doesn't inline
very small functions we expect to be inlined. See
    https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122
Arguably, gcc should do better, but gcc people aren't willing
to invest time into it, asking to use __always_inline instead.

With this .config:
http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os,
the following functions get deinlined many times.

netif_tx_stop_queue: 207 copies, 590 calls:
	55                      push   %rbp
	48 89 e5                mov    %rsp,%rbp
	f0 80 8f e0 01 00 00 01 lock orb $0x1,0x1e0(%rdi)
	5d                      pop    %rbp
	c3                      retq

netif_tx_start_queue: 47 copies, 111 calls
	55                      push   %rbp
	48 89 e5                mov    %rsp,%rbp
	f0 80 a7 e0 01 00 00 fe lock andb $0xfe,0x1e0(%rdi)
	5d                      pop    %rbp
	c3                      retq

sock_hold: 39 copies, 124 calls
	55                      push   %rbp
	48 89 e5                mov    %rsp,%rbp
	f0 ff 87 80 00 00 00    lock incl 0x80(%rdi)
	5d                      pop    %rbp
	c3                      retq

__sock_put: 6 copies, 13 calls
	55                      push   %rbp
	48 89 e5                mov    %rsp,%rbp
	f0 ff 8f 80 00 00 00    lock decl 0x80(%rdi)
	5d                      pop    %rbp
	c3                      retq

This patch fixes this via s/inline/__always_inline/.

Code size decrease after the patch is ~2.5k:

    text      data      bss       dec     hex filename
56719876  56364551 36196352 149280779 8e5d80b vmlinux_before
56717440  56364551 36196352 149278343 8e5ce87 vmlinux
Signed-off-by: NDenys Vlasenko <dvlasenk@redhat.com>
CC: David S. Miller <davem@davemloft.net>
CC: linux-kernel@vger.kernel.org
CC: netdev@vger.kernel.org
CC: netfilter-devel@vger.kernel.org
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch fixes an issue I found in which we were dropping frames if we
had enabled checksums on GRE headers that were encapsulated by either FOU
or GUE.  Without this patch I was barely able to get 1 Gb/s of throughput.
With this patch applied I am now at least getting around 6 Gb/s.

The issue is due to the fact that with FOU or GUE applied we do not provide
a transport offset pointing to the GRE header, nor do we offload it in
software as the GRE header is completely skipped by GSO and treated like a
VXLAN or GENEVE type header.  As such we need to prevent the stack from
generating it and also prevent GRE from generating it via any interface we
create.

Fixes: c3483384 ("gro: Allow tunnel stacking in the case of FOU/GUE")
Signed-off-by: NAlexander Duyck <aduyck@mirantis.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>