GSO isn't the only offload feature with restrictions that
potentially can't be expressed with the current features mechanism.
Checksum is another although it's a general issue that could in
theory apply to anything. Even if it may be possible to
implement these restrictions in other ways, it can result in
duplicate code or inefficient per-packet behavior.
This generalizes ndo_gso_check so that drivers can remove any
features that don't make sense for a given packet, similar to
netif_skb_features(). It also converts existing driver
restrictions to the new format, completing the work that was
done to support tunnel protocols since the issues apply to
checksums as well.
By actually removing features from the set that are used to do
offloading, it solves another problem with the existing
interface. In these cases, GSO would run with the original set
of features and not do anything because it appears that
segmentation is not required.
CC: Tom Herbert <therbert@google.com>
CC: Joe Stringer <joestringer@nicira.com>
CC: Eric Dumazet <edumazet@google.com>
CC: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
Acked-by: Tom Herbert <therbert@google.com>
Fixes: 04ffcb255f ("net: Add ndo_gso_check")
Tested-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When using VXLAN tunnels and a sky2 device, I have experienced
checksum failures of the following type:
[ 4297.761899] eth0: hw csum failure
[...]
[ 4297.765223] Call Trace:
[ 4297.765224] <IRQ> [<ffffffff8172f026>] dump_stack+0x46/0x58
[ 4297.765235] [<ffffffff8162ba52>] netdev_rx_csum_fault+0x42/0x50
[ 4297.765238] [<ffffffff8161c1a0>] ? skb_push+0x40/0x40
[ 4297.765240] [<ffffffff8162325c>] __skb_checksum_complete+0xbc/0xd0
[ 4297.765243] [<ffffffff8168c602>] tcp_v4_rcv+0x2e2/0x950
[ 4297.765246] [<ffffffff81666ca0>] ? ip_rcv_finish+0x360/0x360
These are reliably reproduced in a network topology of:
container:eth0 == host(OVS VXLAN on VLAN) == bond0 == eth0 (sky2) -> switch
When VXLAN encapsulated traffic is received from a similarly
configured peer, the above warning is generated in the receive
processing of the encapsulated packet. Note that the warning is
associated with the container eth0.
The skbs from sky2 have ip_summed set to CHECKSUM_COMPLETE, and
because the packet is an encapsulated Ethernet frame, the checksum
generated by the hardware includes the inner protocol and Ethernet
headers.
The receive code is careful to update the skb->csum, except in
__dev_forward_skb, as called by dev_forward_skb. __dev_forward_skb
calls eth_type_trans, which in turn calls skb_pull_inline(skb, ETH_HLEN)
to skip over the Ethernet header, but does not update skb->csum when
doing so.
This patch resolves the problem by adding a call to
skb_postpull_rcsum to update the skb->csum after the call to
eth_type_trans.
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When vlan tags are stacked, it is very likely that the outer tag is stored
in skb->vlan_tci and skb->protocol shows the inner tag's vlan_proto.
Currently netif_skb_features() first looks at skb->protocol even if there
is the outer tag in vlan_tci, thus it incorrectly retrieves the protocol
encapsulated by the inner vlan instead of the inner vlan protocol.
This allows GSO packets to be passed to HW and they end up being
corrupted.
Fixes: 58e998c6d2 ("offloading: Force software GSO for multiple vlan tags.")
Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fixes MPLS GSO for case when mpls is compiled as kernel module.
Fixes: 0d89d2035f ("MPLS: Add limited GSO support").
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch rearranges the loop in net_rx_action to reduce the
amount of jumping back and forth when reading the code.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
We should only perform the softnet_break check after we have polled
at least one device in net_rx_action. Otherwise a zero or negative
setting of netdev_budget can lock up the whole system.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
The commit d75b1ade56 (net: less
interrupt masking in NAPI) required drivers to leave poll_list
empty if the entire budget is consumed.
We have already had two broken drivers so let's add a check for
this.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch creates a new function napi_poll and moves the napi
polling code from net_rx_action into it.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit cecda693a9 ("net: keep original skb
which only needs header checking during software GSO") keeps the original
skb for packets that only needs header check, but it doesn't drop the
packet if software segmentation or header check were failed.
Fixes cecda693a9 ("net: keep original skb which only needs header checking during software GSO")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull networking updates from David Miller:
1) New offloading infrastructure and example 'rocker' driver for
offloading of switching and routing to hardware.
This work was done by a large group of dedicated individuals, not
limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend,
Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu
2) Start making the networking operate on IOV iterators instead of
modifying iov objects in-situ during transfers. Thanks to Al Viro
and Herbert Xu.
3) A set of new netlink interfaces for the TIPC stack, from Richard
Alpe.
4) Remove unnecessary looping during ipv6 routing lookups, from Martin
KaFai Lau.
5) Add PAUSE frame generation support to gianfar driver, from Matei
Pavaluca.
6) Allow for larger reordering levels in TCP, which are easily
achievable in the real world right now, from Eric Dumazet.
7) Add a variable of napi_schedule that doesn't need to disable cpu
interrupts, from Eric Dumazet.
8) Use a doubly linked list to optimize neigh_parms_release(), from
Nicolas Dichtel.
9) Various enhancements to the kernel BPF verifier, and allow eBPF
programs to actually be attached to sockets. From Alexei
Starovoitov.
10) Support TSO/LSO in sunvnet driver, from David L Stevens.
11) Allow controlling ECN usage via routing metrics, from Florian
Westphal.
12) Remote checksum offload, from Tom Herbert.
13) Add split-header receive, BQL, and xmit_more support to amd-xgbe
driver, from Thomas Lendacky.
14) Add MPLS support to openvswitch, from Simon Horman.
15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen
Klassert.
16) Do gro flushes on a per-device basis using a timer, from Eric
Dumazet. This tries to resolve the conflicting goals between the
desired handling of bulk vs. RPC-like traffic.
17) Allow userspace to ask for the CPU upon what a packet was
received/steered, via SO_INCOMING_CPU. From Eric Dumazet.
18) Limit GSO packets to half the current congestion window, from Eric
Dumazet.
19) Add a generic helper so that all drivers set their RSS keys in a
consistent way, from Eric Dumazet.
20) Add xmit_more support to enic driver, from Govindarajulu
Varadarajan.
21) Add VLAN packet scheduler action, from Jiri Pirko.
22) Support configurable RSS hash functions via ethtool, from Eyal
Perry.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits)
Fix race condition between vxlan_sock_add and vxlan_sock_release
net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header
net/mlx4: Add support for A0 steering
net/mlx4: Refactor QUERY_PORT
net/mlx4_core: Add explicit error message when rule doesn't meet configuration
net/mlx4: Add A0 hybrid steering
net/mlx4: Add mlx4_bitmap zone allocator
net/mlx4: Add a check if there are too many reserved QPs
net/mlx4: Change QP allocation scheme
net/mlx4_core: Use tasklet for user-space CQ completion events
net/mlx4_core: Mask out host side virtualization features for guests
net/mlx4_en: Set csum level for encapsulated packets
be2net: Export tunnel offloads only when a VxLAN tunnel is created
gianfar: Fix dma check map error when DMA_API_DEBUG is enabled
cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call
net: fec: only enable mdio interrupt before phy device link up
net: fec: clear all interrupt events to support i.MX6SX
net: fec: reset fep link status in suspend function
net: sock: fix access via invalid file descriptor
net: introduce helper macro for_each_cmsghdr
...
This change pulls the core functionality out of __netdev_alloc_skb and
places them in a new function named __alloc_rx_skb. The reason for doing
this is to make these bits accessible to a new function __napi_alloc_skb.
In addition __alloc_rx_skb now has a new flags value that is used to
determine which page frag pool to allocate from. If the SKB_ALLOC_NAPI
flag is set then the NAPI pool is used. The advantage of this is that we
do not have to use local_irq_save/restore when accessing the NAPI pool from
NAPI context.
In my test setup I saw at least 11ns of savings using the napi_alloc_skb
function versus the netdev_alloc_skb function, most of this being due to
the fact that we didn't have to call local_irq_save/restore.
The main use case for napi_alloc_skb would be for things such as copybreak
or page fragment based receive paths where an skb is allocated after the
data has been received instead of before.
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The commit 56bfa7ee7c ("unregister_netdevice : move RTM_DELLINK to
until after ndo_uninit") tried to do this ealier but while doing so
it created a problem. Unfortunately the delayed rtmsg_ifinfo() also
delayed call to fill_info(). So this translated into asking driver
to remove private state and then query it's private state. This
could have catastropic consequences.
This change breaks the rtmsg_ifinfo() into two parts - one takes the
precise snapshot of the device by called fill_info() before calling
the ndo_uninit() and the second part sends the notification using
collected snapshot.
It was brought to notice when last link is deleted from an ipvlan device
when it has free-ed the port and the subsequent .fill_info() call is
trying to get the info from the port.
kernel: [ 255.139429] ------------[ cut here ]------------
kernel: [ 255.139439] WARNING: CPU: 12 PID: 11173 at net/core/rtnetlink.c:2238 rtmsg_ifinfo+0x100/0x110()
kernel: [ 255.139493] Modules linked in: ipvlan bonding w1_therm ds2482 wire cdc_acm ehci_pci ehci_hcd i2c_dev i2c_i801 i2c_core msr cpuid bnx2x ptp pps_core mdio libcrc32c
kernel: [ 255.139513] CPU: 12 PID: 11173 Comm: ip Not tainted 3.18.0-smp-DEV #167
kernel: [ 255.139514] Hardware name: Intel RML,PCH/Ibis_QC_18, BIOS 1.0.10 05/15/2012
kernel: [ 255.139515] 0000000000000009 ffff880851b6b828 ffffffff815d87f4 00000000000000e0
kernel: [ 255.139516] 0000000000000000 ffff880851b6b868 ffffffff8109c29c 0000000000000000
kernel: [ 255.139518] 00000000ffffffa6 00000000000000d0 ffffffff81aaf580 0000000000000011
kernel: [ 255.139520] Call Trace:
kernel: [ 255.139527] [<ffffffff815d87f4>] dump_stack+0x46/0x58
kernel: [ 255.139531] [<ffffffff8109c29c>] warn_slowpath_common+0x8c/0xc0
kernel: [ 255.139540] [<ffffffff8109c2ea>] warn_slowpath_null+0x1a/0x20
kernel: [ 255.139544] [<ffffffff8150d570>] rtmsg_ifinfo+0x100/0x110
kernel: [ 255.139547] [<ffffffff814f78b5>] rollback_registered_many+0x1d5/0x2d0
kernel: [ 255.139549] [<ffffffff814f79cf>] unregister_netdevice_many+0x1f/0xb0
kernel: [ 255.139551] [<ffffffff8150acab>] rtnl_dellink+0xbb/0x110
kernel: [ 255.139553] [<ffffffff8150da90>] rtnetlink_rcv_msg+0xa0/0x240
kernel: [ 255.139557] [<ffffffff81329283>] ? rhashtable_lookup_compare+0x43/0x80
kernel: [ 255.139558] [<ffffffff8150d9f0>] ? __rtnl_unlock+0x20/0x20
kernel: [ 255.139562] [<ffffffff8152cb11>] netlink_rcv_skb+0xb1/0xc0
kernel: [ 255.139563] [<ffffffff8150a495>] rtnetlink_rcv+0x25/0x40
kernel: [ 255.139565] [<ffffffff8152c398>] netlink_unicast+0x178/0x230
kernel: [ 255.139567] [<ffffffff8152c75f>] netlink_sendmsg+0x30f/0x420
kernel: [ 255.139571] [<ffffffff814e0b0c>] sock_sendmsg+0x9c/0xd0
kernel: [ 255.139575] [<ffffffff811d1d7f>] ? rw_copy_check_uvector+0x6f/0x130
kernel: [ 255.139577] [<ffffffff814e11c9>] ? copy_msghdr_from_user+0x139/0x1b0
kernel: [ 255.139578] [<ffffffff814e1774>] ___sys_sendmsg+0x304/0x310
kernel: [ 255.139581] [<ffffffff81198723>] ? handle_mm_fault+0xca3/0xde0
kernel: [ 255.139585] [<ffffffff811ebc4c>] ? destroy_inode+0x3c/0x70
kernel: [ 255.139589] [<ffffffff8108e6ec>] ? __do_page_fault+0x20c/0x500
kernel: [ 255.139597] [<ffffffff811e8336>] ? dput+0xb6/0x190
kernel: [ 255.139606] [<ffffffff811f05f6>] ? mntput+0x26/0x40
kernel: [ 255.139611] [<ffffffff811d2b94>] ? __fput+0x174/0x1e0
kernel: [ 255.139613] [<ffffffff814e2129>] __sys_sendmsg+0x49/0x90
kernel: [ 255.139615] [<ffffffff814e2182>] SyS_sendmsg+0x12/0x20
kernel: [ 255.139617] [<ffffffff815df092>] system_call_fastpath+0x12/0x17
kernel: [ 255.139619] ---[ end trace 5e6703e87d984f6b ]---
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Reported-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: David S. Miller <davem@davemloft.net>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use them to push skb->vlan_tci into the payload and avoid code
duplication.
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Name fits better. Plus there's going to be introduced
__vlan_insert_tag later on.
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Large receive offloading is known to cause problems if received packets
are passed to other host. Therefore the kernel disables it by calling
dev_disable_lro() whenever a network device is enslaved in a bridge or
forwarding is enabled for it (or globally). For virtual devices we need
to disable LRO on the underlying physical device (which is actually
receiving the packets).
Current dev_disable_lro() code handles this propagation for a vlan
(including 802.1ad nested vlan), macvlan or a vlan on top of a macvlan.
It doesn't handle other stacked devices and their combinations, in
particular propagation from a bond to its slaves which often causes
problems in virtualization setups.
As we now have generic data structures describing the upper-lower device
relationship, dev_disable_lro() can be generalized to disable LRO also
for all lower devices (if any) once it is disabled for the device
itself.
For bonding and teaming devices, it is necessary to disable LRO not only
on current slaves at the moment when dev_disable_lro() is called but
also on any slave (port) added later.
v2: use lower device links for all devices (including vlan and macvlan)
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Acked-by: Veaceslav Falico <vfalico@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tuning coalescing parameters on NIC can be really hard.
Servers can handle both bulk and RPC like traffic, with conflicting
goals : bulk flows want as big GRO packets as possible, RPC want minimal
latencies.
To reach big GRO packets on 10Gbe NIC, one can use :
ethtool -C eth0 rx-usecs 4 rx-frames 44
But this penalizes rpc sessions, with an increase of latencies, up to
50% in some cases, as NICs generally do not force an interrupt when
a packet with TCP Push flag is received.
Some NICs do not have an absolute timer, only a timer rearmed for every
incoming packet.
This patch uses a different strategy : Let GRO stack decides what do do,
based on traffic pattern.
Packets with Push flag wont be delayed.
Packets without Push flag might be held in GRO engine, if we keep
receiving data.
This new mechanism is off by default, and shall be enabled by setting
/sys/class/net/ethX/gro_flush_timeout to a value in nanosecond.
To fully enable this mechanism, drivers should use napi_complete_done()
instead of napi_complete().
Tested:
Ran 200 netperf TCP_STREAM from A to B (10Gbe mlx4 link, 8 RX queues)
Without this feature, we send back about 305,000 ACK per second.
GRO aggregation ratio is low (811/305 = 2.65 segments per GRO packet)
Setting a timer of 2000 nsec is enough to increase GRO packet sizes
and reduce number of ACK packets. (811/19.2 = 42)
Receiver performs less calls to upper stacks, less wakes up.
This also reduces cpu usage on the sender, as it receives less ACK
packets.
Note that reducing number of wakes up increases cpu efficiency, but can
decrease QPS, as applications wont have the chance to warmup cpu caches
doing a partial read of RPC requests/answers if they fit in one skb.
B:~# sar -n DEV 1 10 | grep eth0 | tail -1
Average: eth0 811269.80 305732.30 1199462.57 19705.72 0.00
0.00 0.50
B:~# echo 2000 >/sys/class/net/eth0/gro_flush_timeout
B:~# sar -n DEV 1 10 | grep eth0 | tail -1
Average: eth0 811577.30 19230.80 1199916.51 1239.80 0.00
0.00 0.50
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Allow datapath to recognize and extract MPLS labels into flow keys
and execute actions which push, pop, and set labels on packets.
Based heavily on work by Leo Alterman, Ravi K, Isaku Yamahata and Joe Stringer.
Cc: Ravi K <rkerur@gmail.com>
Cc: Leo Alterman <lalterman@nicira.com>
Cc: Isaku Yamahata <yamahata@valinux.co.jp>
Cc: Joe Stringer <joe@wand.net.nz>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
net_rx_action() can mask irqs a single time to transfert sd->poll_list
into a private list, for a very short duration.
Then, napi_complete() can avoid masking irqs again,
and net_rx_action() only needs to mask irq again in slow path.
This patch removes 2 couples of irq mask/unmask per typical NAPI run,
more if multiple napi were triggered.
Note this also allows to give control back to caller (do_softirq())
more often, so that other softirq handlers can be called a bit earlier,
or ksoftirqd can be wakeup earlier under pressure.
This was developed while testing an alternative to RX interrupt
mitigation to reduce latencies while keeping or improving GRO
aggregation on fast NIC.
Idea is to test napi->gro_list at the end of a napi->poll() and
reschedule one NAPI poll, but after servicing a full round of
softirqs (timers, TX, rcu, ...). This will be allowed only if softirq
is currently serviced by idle task or ksoftirqd, and resched not needed.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
napi_schedule() can be called from any context and has to mask hard
irqs.
Add a variant that can only be called from hard interrupts handlers
or when irqs are already masked.
Many NIC drivers can use it from their hard IRQ handler instead of
generic variant.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Do not reuse skb if it was pfmemalloc tainted, otherwise
future frame might be dropped anyway.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Roman Gushchin <klamm@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
