[ Upstream commit 52acf73b6e ]
Recently people reported the NIC stops working after
"ifdown eth0; ifup eth0". It turns out in this case the TX queues are not
enabled, after the refactoring of the common detach logic: when the NIC
has sub-channels, usually we enable all the TX queues after all
sub-channels are set up: see rndis_set_subchannel() ->
netif_device_attach(), but in the case of "ifdown eth0; ifup eth0" where
the number of channels doesn't change, we also must make sure the TX queues
are enabled. The patch fixes the regression.
Fixes: 7b2ee50c0c ("hv_netvsc: common detach logic")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit f03dbb06dc ]
My recent change to netvsc drive in how receive flags are handled
broke multicast. The Hyper-v/Azure virtual interface there is not a
multicast filter list, filtering is only all or none. The driver must
enable all multicast if any multicast address is present.
Fixes: 009f766ca2 ("hv_netvsc: filter multicast/broadcast")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 35a57b7fef ]
The rx_mode operation handler is different than other callbacks
in that is not always called with rtnl held. Therefore use
RCU to ensure that references are valid.
Fixes: bee9d41b37 ("hv_netvsc: propagate rx filters to VF")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit bee9d41b37 ]
The netvsc device should propagate filters to the SR-IOV VF
device (if present). The flags also need to be propagated to the
VF device as well. This only really matters on local Hyper-V
since Azure does not support multiple addresses.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit 55be9f25be upstream. ]
On older windows hosts the net_device instance is returned to
the caller of rndis_filter_device_add() without having the presence
bit set first. This would cause any subsequent calls to network device
operations (e.g. MTU change, channel change) to fail after the device
is detached once, returning -ENODEV.
Instead of returning the device instabce, we take the exit path where
we call netif_device_attach()
Fixes: 7b2ee50c0c ("hv_netvsc: common detach logic")
Signed-off-by: Mohammed Gamal <mgamal@redhat.com>
Reviewed-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit a56d99d714 upstream. ]
Prior to commit 0cf737808a ("hv_netvsc: netvsc_teardown_gpadl() split")
the call sequence in netvsc_device_remove() was as follows (as
implemented in netvsc_destroy_buf()):
1- Send NVSP_MSG1_TYPE_REVOKE_RECV_BUF message
2- Teardown receive buffer GPADL
3- Send NVSP_MSG1_TYPE_REVOKE_SEND_BUF message
4- Teardown send buffer GPADL
5- Close vmbus
This didn't work for WS2016 hosts. Commit 0cf737808a
("hv_netvsc: netvsc_teardown_gpadl() split") rearranged the
teardown sequence as follows:
1- Send NVSP_MSG1_TYPE_REVOKE_RECV_BUF message
2- Send NVSP_MSG1_TYPE_REVOKE_SEND_BUF message
3- Close vmbus
4- Teardown receive buffer GPADL
5- Teardown send buffer GPADL
That worked well for WS2016 hosts, but it prevented guests on older hosts from
shutting down after changing network settings. Commit 0ef58b0a05
("hv_netvsc: change GPAD teardown order on older versions") ensured the
following message sequence for older hosts
1- Send NVSP_MSG1_TYPE_REVOKE_RECV_BUF message
2- Send NVSP_MSG1_TYPE_REVOKE_SEND_BUF message
3- Teardown receive buffer GPADL
4- Teardown send buffer GPADL
5- Close vmbus
However, with this sequence calling `ip link set eth0 mtu 1000` hangs and the
process becomes uninterruptible. On futher analysis it turns out that on tearing
down the receive buffer GPADL the kernel is waiting indefinitely
in vmbus_teardown_gpadl() for a completion to be signaled.
Here is a snippet of where this occurs:
int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
{
struct vmbus_channel_gpadl_teardown *msg;
struct vmbus_channel_msginfo *info;
unsigned long flags;
int ret;
info = kmalloc(sizeof(*info) +
sizeof(struct vmbus_channel_gpadl_teardown), GFP_KERNEL);
if (!info)
return -ENOMEM;
init_completion(&info->waitevent);
info->waiting_channel = channel;
[....]
ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_gpadl_teardown),
true);
if (ret)
goto post_msg_err;
wait_for_completion(&info->waitevent);
[....]
}
The completion is signaled from vmbus_ongpadl_torndown(), which gets called when
the corresponding message is received from the host, which apparently never happens
in that case.
This patch works around the issue by restoring the first mentioned message sequence
for older hosts
Fixes: 0ef58b0a05 ("hv_netvsc: change GPAD teardown order on older versions")
Signed-off-by: Mohammed Gamal <mgamal@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit 7992894c30 upstream. ]
Split each of the functions into two for each of send/recv buffers.
This will be needed in order to implement a fine-grained messaging
sequence to the host so that we accommodate the requirements of
different Windows versions
Fixes: 0ef58b0a05 ("hv_netvsc: change GPAD teardown order on older versions")
Signed-off-by: Mohammed Gamal <mgamal@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 2afc5d61a7197de25a61f54ea4ecfb4cb62b1d42A upstram
When changing network interface settings, Windows guests
older than WS2016 can no longer shutdown. This was addressed
by commit 0ef58b0a05 ("hv_netvsc: change GPAD teardown order
on older versions"), however the issue also occurs on WS2012
guests that share NVSP protocol versions with WS2016 guests.
Hence we use Windows version directly to differentiate them.
Fixes: 0ef58b0a05 ("hv_netvsc: change GPAD teardown order on older versions")
Signed-off-by: Mohammed Gamal <mgamal@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit 7b2ee50c0c upstream. ]
Make common function for detaching internals of device
during changes to MTU and RSS. Make sure no more packets
are transmitted and all packets have been received before
doing device teardown.
Change the wait logic to be common and use usleep_range().
Changes transmit enabling logic so that transmit queues are disabled
during the period when lower device is being changed. And enabled
only after sub channels are setup. This avoids issue where it could
be that a packet was being sent while subchannel was not initialized.
Fixes: 8195b1396e ("hv_netvsc: fix deadlock on hotplug")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit 0ef58b0a05 upstream. ]
On older versions of Windows, the host ignores messages after
vmbus channel is closed.
Workaround this by doing what Windows does and send the teardown
before close on older versions of NVSP protocol.
Reported-by: Mohammed Gamal <mgamal@redhat.com>
Fixes: 0cf737808a ("hv_netvsc: netvsc_teardown_gpadl() split")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit 02400fcee2 upstream. ]
The receive processing may continue to happen while the
internal network device state is in RCU grace period.
The internal RNDIS structure is associated with the
internal netvsc_device structure; both have the same
RCU lifetime.
Defer freeing all associated parts until after grace
period.
Fixes: 0cf737808a ("hv_netvsc: netvsc_teardown_gpadl() split")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit 8348e0460a upstream. ]
This makes sure that no CPU is still process packets when
the channel is closed.
Fixes: 76bb5db5c7 ("netvsc: fix use after free on module removal")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit b3bf5666a5 upstream. ]
When VF is used for accelerated networking it will likely have
more queues (and different policy) than the synthetic NIC.
This patch defers the queue policy to the VF so that all the
queues can be used. This impacts workloads like local generate UDP.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit d64e38ae69 upstream. ]
There is a race between napi_reschedule and re-enabling interrupts
which could lead to missed host interrrupts. This occurs when
interrupts are re-enabled (hv_end_read) and vmbus irq callback
(netvsc_channel_cb) has already scheduled NAPI.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit 12f69661a4 upstream. ]
Change the initialization order so that the device is ready to transmit
(ie connect vsp is completed) before setting the internal reference
to the device with RCU.
This avoids any races on initialization and prevents retry issues
on shutdown.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit 25a39f7f97 upstream. ]
Since we no longer localize channel/CPU affiliation within one NUMA
node, num_online_cpus() is used as the number of channel cap, instead of
the number of processors in a NUMA node.
This patch allows a bigger range for tuning the number of channels.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit cfd8afd986 upstream. ]
If the transmit queue is known full, then don't keep aggregating
data. And the cp_partial flag which indicates that the current
aggregation buffer is full can be folded in to avoid more
conditionals.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit aefd80e874 upstream. ]
rndis_filter_device_add() is called both from netvsc_probe() when we
initially create the device and from set channels/mtu/ringparam
routines where we basically remove the device and add it back.
hw_features is reset in rndis_filter_device_add() and filled with
host data. However, we lose all additional flags which are set outside
of the driver, e.g. register_netdevice() adds NETIF_F_SOFT_FEATURES and
many others.
Unfortunately, calls to rndis_{query_hwcaps(), _set_offload_params()}
calls cannot be avoided on every RNDIS reset: host expects us to set
required features explicitly. Moreover, in theory hardware capabilities
can change and we need to reflect the change in hw_features.
Reset net->hw_features bits according to host data in
rndis_netdev_set_hwcaps(), clear corresponding feature bits
from net->features in case some features went missing (will never happen
in real life I guess but let's be consistent).
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit 0cf737808a upstream. ]
It was found that in some cases host refuses to teardown GPADL for send/
receive buffers (probably when some work with these buffere is scheduled or
ongoing). Change the teardown logic to be:
1) Send NVSP_MSG1_TYPE_REVOKE_* messages
2) Close the channel
3) Teardown GPADLs.
This seems to work reliably.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit a6fb6aa3cf upstream. ]
In some cases, like internal vSwitch, the host doesn't provide
send indirection table updates. This patch sets the table to be
equal weight after subchannels are all open. Otherwise, all workload
will be on one TX channel.
As tested, this patch has largely increased the throughput over
internal vSwitch.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit 6b0cbe3158 upstream. ]
tx_table is part of the private data of kernel net_device. It is only
zero-ed out when allocating net_device.
We may recreate netvsc_device w/o recreating net_device, so the private
netdev data, including tx_table, are not zeroed. It may contain channel
numbers for the older netvsc_device.
This patch adds initialization of tx_table each time we recreate
netvsc_device.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Commit 6450f8f269 upstream. ]
For older hosts without multi-channel (vRSS) support, and some error
cases, we still need to set the real number of queues to one.
This patch adds this missing setting.
Fixes: 8195b1396e ("hv_netvsc: fix deadlock on hotplug")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 97f3efb643 ]
The hyper-v transparent bonding should have used master_dev_link.
The netvsc device should look like a master bond device not
like the upper side of a tunnel.
This makes the semantics the same so that userspace applications
looking at network devices see the correct master relationshipship.
Fixes: 0c195567a8 ("netvsc: transparent VF management")
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 41f61db2cd ]
The values were not computed correctly. There are no significant
visible impact, though.
The intended size of RX buffer is 16 MB, and the default slot size is 1728.
So, NETVSC_DEFAULT_RX should be 16*1024*1024 / 1728 = 9709.
The intended size of TX buffer is 1 MB, and the slot size is 6144.
So, NETVSC_DEFAULT_TX should be 1024*1024 / 6144 = 170.
The patch puts the formula directly into the macro, and moves them to
hyperv_net.h, together with related macros.
Fixes: 5023a6db73 ("netvsc: increase default receive buffer size")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 11b2b65310 ]
The max should be 31 MB on host with NVSP version > 2.
On legacy hosts (NVSP version <=2) only 15 MB receive buffer is allowed,
otherwise the buffer request will be rejected by the host, resulting
vNIC not coming up.
The NVSP version is only available after negotiation. So, we add the
limit checking for legacy hosts in netvsc_init_buf().
Fixes: 5023a6db73 ("netvsc: increase default receive buffer size")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
If MTU is changed the host would reject the send buffer change.
This problem is result of recent change to allow changing send
buffer size.
Every time we change the MTU, we store the previous net_device section
count before destroying the buffer, but we don’t store the previous
section size. When we reinitialize the buffer, its size is calculated
by multiplying the previous count and previous size. Since we
continuously increase the MTU, the host returns us a decreasing count
value while the section size is reinitialized to 1728 bytes every
time.
This eventually leads to a condition where the calculated buf_size is
so small that the host rejects it.
Fixes: 8b5327975a ("netvsc: allow controlling send/recv buffer size")
Signed-off-by: Alex Ng <alexng@microsoft.com>
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The default receive buffer size was reduced by recent change
to a value which was appropriate for 10G and Windows Server 2016.
But the value is too small for full performance with 40G on Azure.
Increase the default back to maximum supported by host.
Fixes: 8b5327975a ("netvsc: allow controlling send/recv buffer size")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Only need to wakeup the initiator after all sub-channels
are opened.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a virtual device is added dynamically (via host console), then
the vmbus sends an offer message for the primary channel. The processing
of this message for networking causes the network device to then
initialize the sub channels.
The problem is that setting up the sub channels needs to wait until
the subsequent subchannel offers have been processed. These offers
come in on the same ring buffer and work queue as where the primary
offer is being processed; leading to a deadlock.
This did not happen in older kernels, because the sub channel waiting
logic was broken (it wasn't really waiting).
The solution is to do the sub channel setup in its own work queue
context that is scheduled by the primary channel setup; and then
happens later.
Fixes: 732e49850c ("netvsc: fix race on sub channel creation")
Reported-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The limit of setting receive indirection table value should be
the current number of channels, not the VRSS_CHANNEL_MAX.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Because of the following code, net->num_tx_queues equals to
VRSS_CHANNEL_MAX, and max_chn is less than or equals to VRSS_CHANNEL_MAX.
netvsc_drv.c:
alloc_etherdev_mq(sizeof(struct net_device_context),
VRSS_CHANNEL_MAX);
rndis_filter.c:
net_device->max_chn = min_t(u32, VRSS_CHANNEL_MAX, num_possible_rss_qs);
So this patch removes the unnecessary limit check before comparing
with "max_chn".
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The minus one and assignment to a local variable is not necessary.
This patch simplifies it.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch removes the parameter, num_queue in
rndis_filter_set_rss_param(), which is no longer in use.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If VF is attached then can still allow netvsc driver module to
be removed. Just have to make sure and do the cleanup.
Also, avoid extra rtnl round trip when calling unregister.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use one routine for datapath up/down. Don't need to reopen
the rndis layer.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There is a deadlock possible when canceling the link status
delayed work queue. The removal process is run with RTNL held,
and the link status callback is acquring RTNL.
Resolve the issue by using trylock and rescheduling.
If cancel is in process, that block it from happening.
Fixes: 122a5f6410 ("staging: hv: use delayed_work for netvsc_send_garp()")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We now remove rndis filter before unregister_netdev(), which calls
device close. It involves closing rndis filter already removed.
This patch fixes this error.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The patch add the functions to switch UDP hash level between
L3 and L4 by ethtool command. UDP over IPv4 and v6 can be set
differently. The default hash level is L4. We currently only
allow switching TX hash level from within the guests.
On Azure, fragmented UDP packets have high loss rate with L4
hashing. Using L3 hashing is recommended in this case.
For example, for UDP over IPv4 on eth0:
To include UDP port numbers in hasing:
ethtool -N eth0 rx-flow-hash udp4 sdfn
To exclude UDP port numbers in hasing:
ethtool -N eth0 rx-flow-hash udp4 sd
To show UDP hash level:
ethtool -n eth0 rx-flow-hash udp4
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
