Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 21 1月, 2015 1 次提交
  3. 23 12月, 2014 1 次提交
    • H
      virtio_net: Fix napi poll list corruption · 8acdf999
      由 Herbert Xu 提交于 
      The commit d75b1ade (net: less
interrupt masking in NAPI) breaks virtio_net in an insidious way.

It is now required that if the entire budget is consumed when poll
returns, the napi poll_list must remain empty.  However, like some
other drivers virtio_net tries to do a last-ditch check and if
there is more work it will call napi_schedule and then immediately
process some of this new work.  Should the entire budget be consumed
while processing such new work then we will violate the new caller
contract.

This patch fixes this by not touching any work when we reschedule
in virtio_net.

The worst part of this bug is that the list corruption causes other
napi users to be moved off-list.  In my case I was chasing a stall
in IPsec (IPsec uses netif_rx) and I only belatedly realised that it
was virtio_net which caused the stall even though the virtio_net
poll was still functioning perfectly after IPsec stalled.
Signed-off-by: NHerbert Xu <herbert@gondor.apana.org.au>
Acked-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      8acdf999
  5. 09 12月, 2014 8 次提交
  7. 21 11月, 2014 1 次提交
  9. 31 10月, 2014 1 次提交
    • B
      drivers/net: Disable UFO through virtio · 3d0ad094
      由 Ben Hutchings 提交于 
      IPv6 does not allow fragmentation by routers, so there is no
fragmentation ID in the fixed header.  UFO for IPv6 requires the ID to
be passed separately, but there is no provision for this in the virtio
net protocol.

Until recently our software implementation of UFO/IPv6 generated a new
ID, but this was a bug.  Now we will use ID=0 for any UFO/IPv6 packet
passed through a tap, which is even worse.

Unfortunately there is no distinction between UFO/IPv4 and v6
features, so disable UFO on taps and virtio_net completely until we
have a proper solution.

We cannot depend on VM managers respecting the tap feature flags, so
keep accepting UFO packets but log a warning the first time we do
this.
Signed-off-by: NBen Hutchings <ben@decadent.org.uk>
Fixes: 916e4cf4 ("ipv6: reuse ip6_frag_id from ip6_ufo_append_data")
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      3d0ad094
  11. 16 10月, 2014 1 次提交
  13. 15 10月, 2014 6 次提交
  15. 14 9月, 2014 1 次提交
    • R
      virtio_net: pass well-formed sgs to virtqueue_add_*() · a5835440
      由 Rusty Russell 提交于 
      This is the only driver which doesn't hand virtqueue_add_inbuf and
virtqueue_add_outbuf a well-formed, well-terminated sg.  Fix it,
so we can make virtio_add_* simpler.

pktgen results:
	modprobe pktgen
	echo 'add_device eth0' > /proc/net/pktgen/kpktgend_0
	echo nowait 1 > /proc/net/pktgen/eth0
	echo count 1000000 > /proc/net/pktgen/eth0
	echo clone_skb 100000 > /proc/net/pktgen/eth0
	echo dst_mac 4e:14:25:a9:30:ac > /proc/net/pktgen/eth0
	echo dst 192.168.1.2 > /proc/net/pktgen/eth0
	for i in `seq 20`; do echo start > /proc/net/pktgen/pgctrl; tail -n1 /proc/net/pktgen/eth0; done

Before:
  746547-793084(786421+/-9.6e+03)pps 346-367(364.4+/-4.4)Mb/sec (346397808-367990976(3.649e+08+/-4.5e+06)bps) errors: 0

After:
  767390-792966(785159+/-6.5e+03)pps 356-367(363.75+/-2.9)Mb/sec (356068960-367936224(3.64314e+08+/-3e+06)bps) errors: 0
Signed-off-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      a5835440
  17. 28 8月, 2014 1 次提交
  19. 26 8月, 2014 1 次提交
    • D
      net: Remove ndo_xmit_flush netdev operation, use signalling instead. · 0b725a2c
      由 David S. Miller 提交于 
      As reported by Jesper Dangaard Brouer, for high packet rates the
overhead of having another indirect call in the TX path is
non-trivial.

There is the indirect call itself, and then there is all of the
reloading of the state to refetch the tail pointer value and
then write the device register.

Move to a more passive scheme, which requires very light modifications
to the device drivers.

The signal is a new skb->xmit_more value, if it is non-zero it means
that more SKBs are pending to be transmitted on the same queue as the
current SKB.  And therefore, the driver may elide the tail pointer
update.

Right now skb->xmit_more is always zero.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      0b725a2c
  21. 25 8月, 2014 1 次提交
  23. 24 7月, 2014 2 次提交
    • J
      virtio-net: rx busy polling support · 91815639
      由 Jason Wang 提交于 
      Add basic support for rx busy polling. Instead of introducing new
states and spinlock to synchronize between NAPI and polling method,
this patch just reuse NAPI state to avoid extra overhead for fast path
and simplified the codes.

Test was done between a kvm guest and an external host. Two hosts were
connected through 40gb mlx4 cards. With both busy_poll and busy_read
are set to 50 in guest, 1 byte netperf tcp_rr shows 127% improvement:
transaction rate was increased from 8353.33 to 18966.87.

Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Vlad Yasevich <vyasevic@redhat.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      91815639
    • J
      virtio-net: introduce virtnet_receive() · 2ffa7598
      由 Jason Wang 提交于 
      Move common receive logic to a new helper virtnet_receive(). It will
also be used by rx busy polling method.

Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Vlad Yasevich <vyasevic@redhat.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      2ffa7598
  25. 14 5月, 2014 1 次提交
  27. 01 5月, 2014 1 次提交
    • Z
      virtio-net: Set needed_headroom for virtio-net when VIRTIO_F_ANY_LAYOUT is true · 6ebbc1a6
      由 Zhangjie \(HZ\) 提交于 
      This is a small supplement for commit e7428e95
("virtio-net: put virtio-net header inline with data"). TCP packages have
enough room to put virtio-net header in, but UDP packages do not. By
setting dev->needed_headroom for virtio-net device, UDP packages could have
enough room.

For UDP packages, sk_buff is alloced in fun __ip_append_data. The size is
"alloclen + hh_len + 15", and "hh_len = LL_RESERVED_SPACE(rt-dst.dev);".
The Macro is defined as follows:
#define LL_RESERVED_SPACE(dev) \
     ((((dev)->hard_header_len+(dev)->needed_headroom)\
     &~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
By default, for UDP packages, after skb is allocated, only 16 bytes
reserved. And 2 bytes remained after mac header is set. That is not enough
to put virtio-net header in. If we set dev->needed_headroom to 12 or 10
(according to mergeable_rx_bufs is on or off ), more room can be reserved.
Then there is enough room for UDP packages to put the header in.

test result list as below:
guest and host: suse11sp3, netperf, intel 2.4GHz
+-------+---------+---------+---------+---------+
|       |   old             |   new             |
+-------+---------+---------+---------+---------+
| UDP   |  Gbit/s | pps     |  Gbit/s | pps     |
| 64    |  0.57   | 692232  |  0.61   | 742420  |
| 256   |  1.60   | 686860  |  1.71   | 733331  |
| 512   |  2.92   | 674576  |  3.07   | 710446  |
| 1024  |  4.99   | 598977  |  5.17   | 620821  |
| 1460  |  5.68   | 483757  |  7.16   | 610519  |
| 4096  |  6.98   | 637468  |  7.21   | 658471  |
+-------+---------+---------+---------+---------+
Signed-off-by: NZhang Jie <zhangjie14@huawei.com>
Acked-by: NRusty Russell <rusty@rustcorp.com.au>
Acked-by: NJason Wang <jasowang@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      6ebbc1a6
  29. 23 4月, 2014 1 次提交
  31. 28 3月, 2014 1 次提交
    • J
      virtio-net: correct error handling of virtqueue_kick() · 681daee2
      由 Jason Wang 提交于 
      Current error handling of virtqueue_kick() was wrong in two places:
- The skb were freed immediately when virtqueue_kick() fail during
  xmit. This may lead double free since the skb was not detached from
  the virtqueue.
- try_fill_recv() returns false when virtqueue_kick() fail. This will
  lead unnecessary rescheduling of refill work.

Actually, it's safe to just ignore the kick failure in those two
places. So this patch fixes this by partially revert commit
67975901.

Fixes 67975901
(virtio_net: verify if virtqueue_kick() succeeded).

Cc: Heinz Graalfs <graalfs@linux.vnet.ibm.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      681daee2
  33. 25 3月, 2014 1 次提交
  35. 15 3月, 2014 1 次提交
  37. 13 3月, 2014 1 次提交
  39. 25 2月, 2014 1 次提交
  41. 17 1月, 2014 4 次提交
    • M
      virtio-net: initial rx sysfs support, export mergeable rx buffer size · fbf28d78
      由 Michael Dalton 提交于 
      Add initial support for per-rx queue sysfs attributes to virtio-net. If
mergeable packet buffers are enabled, adds a read-only mergeable packet
buffer size sysfs attribute for each RX queue.
Suggested-by: NMichael S. Tsirkin <mst@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael Dalton <mwdalton@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      fbf28d78
    • M
      virtio-net: auto-tune mergeable rx buffer size for improved performance · ab7db917
      由 Michael Dalton 提交于 
      Commit 2613af0e ("virtio_net: migrate mergeable rx buffers to page frag
allocators") changed the mergeable receive buffer size from PAGE_SIZE to
MTU-size, introducing a single-stream regression for benchmarks with large
average packet size. There is no single optimal buffer size for all
workloads.  For workloads with packet size <= MTU bytes, MTU + virtio-net
header-sized buffers are preferred as larger buffers reduce the TCP window
due to SKB truesize. However, single-stream workloads with large average
packet sizes have higher throughput if larger (e.g., PAGE_SIZE) buffers
are used.

This commit auto-tunes the mergeable receiver buffer packet size by
choosing the packet buffer size based on an EWMA of the recent packet
sizes for the receive queue. Packet buffer sizes range from MTU_SIZE +
virtio-net header len to PAGE_SIZE. This improves throughput for
large packet workloads, as any workload with average packet size >=
PAGE_SIZE will use PAGE_SIZE buffers.

These optimizations interact positively with recent commit
ba275241 ("virtio-net: coalesce rx frags when possible during rx"),
which coalesces adjacent RX SKB fragments in virtio_net. The coalescing
optimizations benefit buffers of any size.

Benchmarks taken from an average of 5 netperf 30-second TCP_STREAM runs
between two QEMU VMs on a single physical machine. Each VM has two VCPUs
with all offloads & vhost enabled. All VMs and vhost threads run in a
single 4 CPU cgroup cpuset, using cgroups to ensure that other processes
in the system will not be scheduled on the benchmark CPUs. Trunk includes
SKB rx frag coalescing.

net-next w/ virtio_net before 2613af0e (PAGE_SIZE bufs): 14642.85Gb/s
net-next (MTU-size bufs):  13170.01Gb/s
net-next + auto-tune: 14555.94Gb/s

Jason Wang also reported a throughput increase on mlx4 from 22Gb/s
using MTU-sized buffers to about 26Gb/s using auto-tuning.
Signed-off-by: NMichael Dalton <mwdalton@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      ab7db917
    • M
      virtio-net: use per-receive queue page frag alloc for mergeable bufs · fb51879d
      由 Michael Dalton 提交于 
      The virtio-net driver currently uses netdev_alloc_frag() for GFP_ATOMIC
mergeable rx buffer allocations. This commit migrates virtio-net to use
per-receive queue page frags for GFP_ATOMIC allocation. This change unifies
mergeable rx buffer memory allocation, which now will use skb_refill_frag()
for both atomic and GFP-WAIT buffer allocations.

To address fragmentation concerns, if after buffer allocation there
is too little space left in the page frag to allocate a subsequent
buffer, the remaining space is added to the current allocated buffer
so that the remaining space can be used to store packet data.
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael Dalton <mwdalton@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      fb51879d
    • J
      virtio-net: drop rq->max and rq->num · be121f46
      由 Jason Wang 提交于 
      It looks like there's no need for those two fields:

- Unless there's a failure for the first refill try, rq->max should be always
  equal to the vring size.
- rq->num is only used to determine the condition that we need to do the refill,
  we could check vq->num_free instead.
- rq->num was required to be increased or decreased explicitly after each
  get/put which results a bad API.

So this patch removes them both to make the code simpler.

Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Acked-by: NRusty Russell <rusty@rustcorp.com.au>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      be121f46
  43. 03 1月, 2014 1 次提交
    • J
      virtio-net: fix refill races during restore · 6cd4ce00
      由 Jason Wang 提交于 
      During restoring, try_fill_recv() was called with neither napi lock nor napi
disabled. This can lead two try_fill_recv() was called in the same time. Fix
this by refilling before trying to enable napi.

Fixes 0741bcb5
(virtio: net: Add freeze, restore handlers to support S4).

Cc: Amit Shah <amit.shah@redhat.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NJason Wang <jasowang@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      6cd4ce00
  45. 11 12月, 2013 2 次提交