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. 26 2月, 2021 2 次提交
  3. 25 2月, 2021 2 次提交
  5. 24 2月, 2021 2 次提交
  7. 23 2月, 2021 10 次提交
  9. 22 2月, 2021 1 次提交
  11. 20 2月, 2021 2 次提交
  13. 19 2月, 2021 6 次提交
  15. 18 2月, 2021 10 次提交
  17. 17 2月, 2021 5 次提交
    • J
      net: re-solve some conflicts after net -> net-next merge · b646acd5
      由 Jakub Kicinski 提交于 
      Signed-off-by: NJakub Kicinski <kuba@kernel.org>
      b646acd5
    • S
      lan743x: sync only the received area of an rx ring buffer · 966df6de
      由 Sven Van Asbroeck 提交于 
      On cpu architectures w/o dma cache snooping, dma_unmap() is a
is a very expensive operation, because its resulting sync
needs to invalidate cpu caches.

Increase efficiency/performance by syncing only those sections
of the lan743x's rx ring buffers that are actually in use.
Signed-off-by: NSven Van Asbroeck <thesven73@gmail.com>
Reviewed-by: NBryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      966df6de
    • S
      lan743x: boost performance on cpu archs w/o dma cache snooping · a8db76d4
      由 Sven Van Asbroeck 提交于 
      The buffers in the lan743x driver's receive ring are always 9K,
even when the largest packet that can be received (the mtu) is
much smaller. This performs particularly badly on cpu archs
without dma cache snooping (such as ARM): each received packet
results in a 9K dma_{map|unmap} operation, which is very expensive
because cpu caches need to be invalidated.

Careful measurement of the driver rx path on armv7 reveals that
the cpu spends the majority of its time waiting for cache
invalidation.

Optimize by keeping the rx ring buffer size as close as possible
to the mtu. This limits the amount of cache that requires
invalidation.

This optimization would normally force us to re-allocate all
ring buffers when the mtu is changed - a disruptive event,
because it can only happen when the network interface is down.

Remove the need to re-allocate all ring buffers by adding support
for multi-buffer frames. Now any combination of mtu and ring
buffer size will work. When the mtu changes from mtu1 to mtu2,
consumed buffers of size mtu1 are lazily replaced by newly
allocated buffers of size mtu2.

These optimizations double the rx performance on armv7.
Third parties report 3x rx speedup on armv8.

Tested with iperf3 on a freescale imx6qp + lan7430, both sides
set to mtu 1500 bytes, measure rx performance:

Before:
[ ID] Interval           Transfer     Bandwidth       Retr
[  4]   0.00-20.00  sec   550 MBytes   231 Mbits/sec    0
After:
[ ID] Interval           Transfer     Bandwidth       Retr
[  4]   0.00-20.00  sec  1.33 GBytes   570 Mbits/sec    0
Signed-off-by: NSven Van Asbroeck <thesven73@gmail.com>
Reviewed-by: NBryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      a8db76d4
    • V
      net: enetc: fix destroyed phylink dereference during unbind · 3af409ca
      由 Vladimir Oltean 提交于 
      The following call path suggests that calling unregister_netdev on an
interface that is up will first bring it down.

enetc_pf_remove
-> unregister_netdev
   -> unregister_netdevice_queue
      -> unregister_netdevice_many
         -> dev_close_many
            -> __dev_close_many
               -> enetc_close
                  -> enetc_stop
                     -> phylink_stop

However, enetc first destroys the phylink instance, then calls
unregister_netdev. This is already dissimilar to the setup (and error
path teardown path) from enetc_pf_probe, but more than that, it is buggy
because it is invalid to call phylink_stop after phylink_destroy.

So let's first unregister the netdev (and let the .ndo_stop events
consume themselves), then destroy the phylink instance, then free the
netdev.

Fixes: 71b77a7a ("enetc: Migrate to PHYLINK and PCS_LYNX")
Signed-off-by: NVladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      3af409ca
    • M
      net: mvneta: Implement mqprio support · 4906887a
      由 Maxime Chevallier 提交于 
      Implement a basic MQPrio support, inserting rules in RX that translate
the TC to prio mapping into vlan prio to queues.

The TX logic stays the same as when we don't offload the qdisc.
Signed-off-by: NMaxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      4906887a