linux.git/drivers/net/hyperv, branch v4.12-rc2 Linux kernel source tree netvsc: make sure napi enabled before vmbus_open 2017-05-04T15:08:36+00:00 stephen hemminger stephen@networkplumber.org 2017-05-03T23:59:21+00:00 2be0f2644598ee4b8ea0ed6a32913e1ce0212c9c This fixes a race where vmbus callback for new packet arriving could occur before NAPI is initialized. Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
This fixes a race where vmbus callback for new packet arriving
could occur before NAPI is initialized.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2017-04-27T02:39:08+00:00 David S. Miller davem@davemloft.net 2017-04-27T02:39:08+00:00 b1513c35317c106a1588f3ab32f6888f0e2afd71 Signed-off-by: David S. Miller <davem@davemloft.net> 
Signed-off-by: David S. Miller <davem@davemloft.net>
netvsc: fix calculation of available send sections 2017-04-25T15:56:59+00:00 stephen hemminger stephen@networkplumber.org 2017-04-25T01:33:38+00:00 fdfb70d275223b9d69d5d3abe1f88507da579139 My change (introduced in 4.11) to use find_first_clear_bit incorrectly assumed that the size argument was words, not bits. The effect was only a small limited number of the available send sections were being actually used. This can cause performance loss with some workloads. Since map_words is now used only during initialization, it can be on stack instead of in per-device data. Fixes: b58a185801da ("netvsc: simplify get next send section") Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
My change (introduced in 4.11) to use find_first_clear_bit
incorrectly assumed that the size argument was words, not bits.
The effect was only a small limited number of the available send
sections were being actually used. This can cause performance loss
with some workloads.

Since map_words is now used only during initialization, it can
be on stack instead of in per-device data.

Fixes: b58a185801da ("netvsc: simplify get next send section")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
netvsc: fix use after free on module removal 2017-04-21T17:59:57+00:00 stephen hemminger stephen@networkplumber.org 2017-04-19T22:22:02+00:00 76bb5db5c749dfe19d779aac076133e821b859dd The NAPI data structure is embedded in the netvsc_device structure and is freed when device is closed. There is still a reference (in NAPI list) to this which causes a crash in netif_napi_del when device is removed. Fix by managing NAPI instances correctly. Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
The NAPI data structure is embedded in the netvsc_device structure
and is freed when device is closed. There is still a reference
(in NAPI list) to this which causes a crash in netif_napi_del
when device is removed. Fix by managing NAPI instances correctly.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
netvsc: Deal with rescinded channels correctly 2017-04-21T17:47:00+00:00 K. Y. Srinivasan kys@microsoft.com 2017-04-19T20:53:49+00:00 73e64fa4f417b22d8d5521999a631ced8e2d442e We will not be able to send packets over a channel that has been rescinded. Make necessary adjustments so we can properly cleanup even when the channel is rescinded. This issue can be trigerred in the NIC hot-remove path. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
We will not be able to send packets over a channel that has been
rescinded. Make necessary adjustments so we can properly cleanup
even when the channel is rescinded. This issue can be trigerred
in the NIC hot-remove path.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
hv_netvsc: change netvsc device default duplex to FULL 2017-04-17T19:12:33+00:00 Simon Xiao sixiao@microsoft.com 2017-04-14T21:42:58+00:00 f3c9d40ee12926f330a1dfebce0bebadd1406ba6 The netvsc device supports full duplex by default. This warnings in log from bonding device which did not like seeing UNKNOWN duplex. Signed-off-by: Simon Xiao <sixiao@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
The netvsc device supports full duplex by default.
This warnings in log from bonding device which did not like
seeing UNKNOWN duplex.

Signed-off-by: Simon Xiao <sixiao@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
netvsc: fix RCU warning in get_stats 2017-04-17T19:12:33+00:00 stephen hemminger stephen@networkplumber.org 2017-04-14T21:42:57+00:00 776e726bfb3493f71bb11759f7a60f1b0f6dd2d2 The statistics functionis called with RTNL held during probe but with RCU held during access from /proc and elsewhere. This is safe so update the lockdep annotation. Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
The statistics functionis called with RTNL held during probe
but with RCU held during access from /proc and elsewhere.
This is safe so update the lockdep annotation.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
hv_netvsc: Exclude non-TCP port numbers from vRSS hashing 2017-04-17T15:05:19+00:00 Haiyang Zhang haiyangz@microsoft.com 2017-04-12T18:45:18+00:00 f72860afa2e32cdc674cbdd7f354f8fb62e908a6 Azure hosts are not supporting non-TCP port numbers in vRSS hashing for now. For example, UDP packet loss rate will be high if port numbers are also included in vRSS hash. So, we created this patch to use only IP numbers for hashing in non-TCP traffic. Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Reviewed-by: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Azure hosts are not supporting non-TCP port numbers in vRSS hashing for
now. For example, UDP packet loss rate will be high if port numbers are
also included in vRSS hash.

So, we created this patch to use only IP numbers for hashing in non-TCP
traffic.

Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
hv_netvsc: Fix the queue index computation in forwarding case 2017-04-17T15:05:19+00:00 Haiyang Zhang haiyangz@microsoft.com 2017-04-12T18:35:05+00:00 8db91f6a9b2ff2bb5355ad11c668fe63eb8ae0c3 If the outgoing skb has a RX queue mapping available, we use the queue number directly, other than put it through Send Indirection Table. Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Reviewed-by: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
If the outgoing skb has a RX queue mapping available, we use the queue
number directly, other than put it through Send Indirection Table.

Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
netvsc: use napi_consume_skb 2017-04-10T01:14:25+00:00 stephen hemminger stephen@networkplumber.org 2017-04-07T18:41:19+00:00 f9645430ef5f53ddf0ddd481e9f70f6fce7ccff2 This allows using deferred skb freeing and with NAPI. And get buffer recycling. Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
This allows using deferred skb freeing and with NAPI. And get buffer
recycling.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>