The netif_device_detach() conditionally stops all tx queues if the queues
are running. There is no need to call netif_tx_stop_all_queues() again.
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In order to support more coalesce parameters through netlink,
add two new parameter kernel_coal and extack for .set_coalesce
and .get_coalesce, then some extra info can return to user with
the netlink API.
Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
With all vmxnet3 version 6 changes incorporated in the vmxnet3 driver,
the driver can configure emulation to run at vmxnet3 version 6, provided
the emulation advertises support for version 6.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch increases the maximum configurable mtu to 9190
to accommodate jumbo packets of overlay traffic.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As vmxnet3 supports IP/TCP/UDP RSS, this patch sets appropriate
hash type based on the type of RSS performed.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vmxnet3 version 4 added support for ESP RSS. However, only IPv4 was
supported. With vmxnet3 version 6, this patch enables RSS for ESP
IPv6 packets as well.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With version 6, vmxnet3 relaxes the restriction on queues to
be power of two. This is helpful in cases (Edge VM) where
vcpus are less than 8 and device requires more than 4 queues.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, vmxnet3 supports maximum of 8 Tx/Rx queues. With increase
in number of vcpus on a VM, to achieve better performance and utilize
idle vcpus, we need to increase the max number of queues supported.
This patch enhances vmxnet3 to support maximum of 32 Tx/Rx queues.
Increasing the Rx queues also increases the probability of distrubuting
the traffic from different flows to different queues with RSS.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
vmxnet3 is currently at version 4 and this patch initiates the
preparation to accommodate changes for upto version 6. Introduced
utility macros for vmxnet3 version 6 comparison and update Copyright
information.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit dacce2be33 ("vmxnet3: add geneve and vxlan tunnel offload
support") added support for encapsulation offload. However, the inner
offload capability is to be restricted to UDP tunnels with default
Vxlan and Geneve ports.
This patch fixes the issue for tunnels with non-default ports using
features check capability and filtering appropriate features for such
tunnels.
Fixes: dacce2be33 ("vmxnet3: add geneve and vxlan tunnel offload support")
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
So this patch actually does 3 things.
First it removes a stray white space at the start of the variable
declaration in vmxnet3_get_strings.
Second it flips the logic for the string test so that we exit immediately
if we are not looking for the stats strings. Doing this we can avoid
unnecessary indentation and line wrapping.
Then finally it updates the code to use ethtool_sprintf rather than a
memcpy and pointer increment to write the ethtool strings.
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
buf_info structures in RX & TX queues are private driver data that
do not need to be visible to the device. Although there is physical
address and length in the queue descriptor that points to these
structures, their layout is not standardized, and device never looks
at them.
So lets allocate these structures in non-DMA-able memory, and fill
physical address as all-ones and length as zero in the queue
descriptor.
That should alleviate worries brought by Martin Radev in
https://lists.osuosl.org/pipermail/intel-wired-lan/Week-of-Mon-20210104/022829.html
that malicious vmxnet3 device could subvert SVM/TDX guarantees.
Signed-off-by: Petr Vandrovec <petr@vmware.com>
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit dacce2be33 ("vmxnet3: add geneve and vxlan tunnel offload
support") added support for encapsulation offload. However, the inner
offload capability is to be restrictued to UDP tunnels.
This patch fixes the issue for non-udp tunnels by adding features
check capability and filtering appropriate features for non-udp tunnels.
Fixes: dacce2be33 ("vmxnet3: add geneve and vxlan tunnel offload support")
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit dacce2be33 ("vmxnet3: add geneve and vxlan tunnel offload
support") added support for encapsulation offload. However, while
calculating tcp hdr length, it does not take into account if the
packet is encapsulated or not.
This patch fixes this issue by using correct reference for inner
tcp header.
Fixes: dacce2be33 ("vmxnet3: add geneve and vxlan tunnel offload support")
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It makes sense to allow changes to get/set rx flow hash callback only
when rss is enabled. This patch restricts get_rss_hash_opts and
set_rss_hash_opts methods to allow querying and configuring different
Rx flow hash configurations only when rss is enabled
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The value adapter->rss_conf is stored in DMA memory, and it is assigned
to rssConf, so rssConf->indTableSize can be modified at anytime by
malicious hardware. Because rssConf->indTableSize is assigned to n,
buffer overflow may occur when the code "rssConf->indTable[n]" is
executed.
To fix this possible bug, n is checked after being used.
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
'Commit dacce2be33 ("vmxnet3: add geneve and vxlan tunnel offload
support")' added support for encapsulation offload. However, while
preparing inner tso packet, it uses reference to outer ip headers.
This patch fixes this issue by using correct reference for inner
headers.
Fixes: dacce2be33 ("vmxnet3: add geneve and vxlan tunnel offload support")
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With all vmxnet3 version 4 changes incorporated in the vmxnet3 driver,
the driver can configure emulation to run at vmxnet3 version 4, provided
the emulation advertises support for version 4.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vmxnet3 version 3 device supports checksum/TSO offload. Thus, vNIC to
pNIC traffic can leverage hardware checksum/TSO offloads. However,
vmxnet3 does not support checksum/TSO offload for Geneve/VXLAN
encapsulated packets. Thus, for a vNIC configured with an overlay, the
guest stack must first segment the inner packet, compute the inner
checksum for each segment and encapsulate each segment before
transmitting the packet via the vNIC. This results in significant
performance penalty.
This patch will enhance vmxnet3 to support Geneve/VXLAN TSO as well as
checksum offload.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With vmxnet3 version 4, the emulation supports multiqueue(RSS) for
UDP and ESP traffic. A guest can enable/disable RSS for UDP/ESP over
IPv4/IPv6 by issuing commands introduced in this patch. ESP ipv6 is
not yet supported in this patch.
This patch implements get_rss_hash_opts and set_rss_hash_opts
methods to allow querying and configuring different Rx flow hash
configurations.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
vmxnet3 is currently at version 3 and this patch initiates the
preparation to accommodate changes for version 4. Introduced utility
macros for vmxnet3 version 4 comparison and update Copyright
information.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Set ethtool_ops->supported_coalesce_params to let
the core reject unsupported coalescing parameters.
This driver correctly rejects all unsupported parameters.
As a side effect of these changes the error code for
unsupported params changes from EINVAL to EOPNOTSUPP.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use new helper tcp_v6_gso_csum_prep in additional network drivers.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
param->rx_mini_pending is __u32 variable, it will never
be less than zero.
Signed-off-by: yuehaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use accessor functions for skb fragment's page_offset instead
of direct references, in preparation for bvec conversion.
Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In preparation for unifying the skb_frag and bio_vec, use the fine
accessors which already exist and use skb_frag_t instead of
struct skb_frag_struct.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit 518a2f1925
("dma-mapping: zero memory returned from dma_alloc_*"),
dma_alloc_coherent has already zeroed the memory.
So memset is not needed.
Signed-off-by: Fuqian Huang <huangfq.daxian@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, when rx csum is disabled, vmxnet3 driver does not turn
off lro, which can cause performance issues if user does not turn off
lro explicitly. This patch adds fix_features support which is used to
turn off LRO whenever RXCSUM is disabled.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Rishi Mehta <rmehta@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ifa_list is protected by rcu, yet code doesn't reflect this.
Add the __rcu annotations and fix up all places that are now reported by
sparse.
I've done this in the same commit to not add intermediate patches that
result in new warnings.
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
We already need to zero out memory for dma_alloc_coherent(), as such
using dma_zalloc_coherent() is superflous. Phase it out.
This change was generated with the following Coccinelle SmPL patch:
@ replace_dma_zalloc_coherent @
expression dev, size, data, handle, flags;
@@
-dma_zalloc_coherent(dev, size, handle, flags)
+dma_alloc_coherent(dev, size, handle, flags)
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
[hch: re-ran the script on the latest tree]
Signed-off-by: Christoph Hellwig <hch@lst.de>
S390 bpf_jit.S is removed in net-next and had changes in 'net',
since that code isn't used any more take the removal.
TLS data structures split the TX and RX components in 'net-next',
put the new struct members from the bug fix in 'net' into the RX
part.
The 'net-next' tree had some reworking of how the ERSPAN code works in
the GRE tunneling code, overlapping with a one-line headroom
calculation fix in 'net'.
Overlapping changes in __sock_map_ctx_update_elem(), keep the bits
that read the prog members via READ_ONCE() into local variables
before using them.
Signed-off-by: David S. Miller <davem@davemloft.net>
As documented in Documentation/timers/timers-howto.txt,
replace msleep(1) with usleep_range().
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The gen bits must be read first from (resp. written last to) DMA memory.
The proper way to enforce this on Linux is to call dma_rmb() (resp.
dma_wmb()).
Signed-off-by: Regis Duchesne <hpreg@vmware.com>
Acked-by: Ronak Doshi <doshir@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The DMA mask must be set before, not after, the first DMA map operation, or
the first DMA map operation could in theory fail on some systems.
Fixes: b0eb57cb97 ("VMXNET3: Add support for virtual IOMMU")
Signed-off-by: Regis Duchesne <hpreg@vmware.com>
Acked-by: Ronak Doshi <doshir@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
vmxnet3_get_hdr_len() is used to calculate the header length which in
turn is used to calculate the gso_size for skb. When rxvlan offload is
disabled, vlan tag is present in the header and the function references
ip header from sizeof(ethhdr) and leads to incorrect pointer reference.
This patch fixes this issue by taking sizeof(vlan_ethhdr) into account
if vlan tag is present and correctly references the ip hdr.
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Acked-by: Louis Luo <llouis@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
'Commit 45dac1d6ea ("vmxnet3: Changes for vmxnet3 adapter version 2
(fwd)")' introduced a flag "lro" in structure vmxnet3_adapter which is
used to indicate whether LRO is enabled or not. However, the patch
did not set the flag and hence it was never exercised.
So, when LRO is enabled, it resulted in poor TCP performance due to
delayed acks. This issue is seen with packets which are larger than
the mss getting a delayed ack rather than an immediate ack, thus
resulting in high latency.
This patch removes the lro flag and directly uses device features
against NETIF_F_LRO to check if lro is enabled.
Fixes: 45dac1d6ea ("vmxnet3: Changes for vmxnet3 adapter version 2 (fwd)")
Reported-by: Rachel Lunnon <rachel_lunnon@stormagic.com>
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Shrikrishna Khare <skhare@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The field txNumDeferred is used by the driver to keep track of the number
of packets it has pushed to the emulation. The driver increments it on
pushing the packet to the emulation and the emulation resets it to 0 at
the end of the transmit.
There is a possibility of a race either when (a) ESX is under heavy load or
(b) workload inside VM is of low packet rate.
This race results in xmit hangs when network coalescing is disabled. This
change creates a local copy of txNumDeferred and uses it to perform ring
arithmetic.
Reported-by: Noriho Tanaka <ntanaka@vmware.com>
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Shrikrishna Khare <skhare@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pointer rq is being initialized but this value is never read, it
is being updated inside a for-loop. Remove the initialization and
move it into the scope of the for-loop.
Cleans up clang warning:
drivers/net/vmxnet3/vmxnet3_drv.c:2763:27: warning: Value stored
to 'rq' during its initialization is never read
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Shrikrishna Khare <skhare@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
with the introduction of commit
b0eb57cb97, it appears that rq->buf_info
is improperly handled. While it is heap allocated when an rx queue is
setup, and freed when torn down, an old line of code in
vmxnet3_rq_destroy was not properly removed, leading to rq->buf_info[0]
being set to NULL prior to its being freed, causing a memory leak, which
eventually exhausts the system on repeated create/destroy operations
(for example, when the mtu of a vmxnet3 interface is changed
frequently.
Fix is pretty straight forward, just move the NULL set to after the
free.
Tested by myself with successful results
Applies to net, and should likely be queued for stable, please
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Reported-By: boyang@redhat.com
CC: boyang@redhat.com
CC: Shrikrishna Khare <skhare@vmware.com>
CC: "VMware, Inc." <pv-drivers@vmware.com>
CC: David S. Miller <davem@davemloft.net>
Acked-by: Shrikrishna Khare <skhare@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are several reasons for increasing the receive ring sizes:
1. The original ring size of 256 was chosen about 10 years ago when
vmxnet3 was first created. At that time, 10Gbps Ethernet was not prevalent
and servers were dominated by 1Gbps Ethernet. Now 10Gbps is common place,
and higher bandwidth links -- 25Gbps, 40Gbps, 50Gbps -- are starting
to appear. 256 Rx ring entries are simply not enough to keep up with
higher link speed when there is a burst of network frames coming from
these high speed links. Even with full MTU size frames, they are gone
in a short time. It is also more common to have a mix of frame sizes,
and more likely bi-modal distribution of frame sizes so the average frame
size is not close to full MTU. If we consider average frame size of 800B,
1024 frames that come in a burst takes ~0.65 ms to arrive at 10Gbps. With
256 entires, it takes ~0.16 ms to arrive at 10Gbps. At 25Gbps or 40Gbps,
this time is reduced accordingly.
2. On a hypervisor where there are many VMs and CPU is over committed,
i.e. the number of VCPUs is more than the number of VCPUs, each PCPU is
in effect time shared between multiple VMs/VCPUs. The time granularity at
which this multiplexing occurs is typically coarser than between processes
on a guest OS. Trying to time slice more finely is not efficient, for
example, if memory cache is barely warmed up when switching from one VM
to another occurs. This CPU overcommit adds delay to when the driver
in a VM can service incoming packets. Whether CPU is over committed
really depends on customer workloads. For certain situations, it is very
common. For example, workloads of desktop VMs and product testing setups.
Consolidation and sharing is what drives efficiency of a customer setup
for such workloads. In these situations, the raw network bandwidth may
not be very high, but the delays between when a VM is running or not
running can also be relatively long.
Signed-off-by: Shrikrishna Khare <skhare@vmware.com>
Acked-by: Jin Heo <heoj@vmware.com>
Acked-by: Guolin Yang <gyang@vmware.com>
Acked-by: Boon Ang <bang@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
gcc-7 notices that "-event-%d" could be more than 11 characters long
if we had larger 'vector' numbers:
drivers/net/vmxnet3/vmxnet3_drv.c: In function 'vmxnet3_activate_dev':
drivers/net/vmxnet3/vmxnet3_drv.c:2095:40: error: 'sprintf' may write a terminating nul past the end of the destination [-Werror=format-overflow=]
sprintf(intr->event_msi_vector_name, "%s-event-%d",
^~~~~~~~~~~~~
drivers/net/vmxnet3/vmxnet3_drv.c:2095:3: note: 'sprintf' output between 9 and 33 bytes into a destination of size 32
The current code is safe, but making the string a little longer
is harmless and lets gcc see that it's ok.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are several paths in vmxnet3, where settings changes cause the
adapter to be brought down and back up (vmxnet3_set_ringparam among
them). Should part of the reset operation fail, these paths call
vmxnet3_force_close, which enables all napi instances prior to calling
dev_close (with the expectation that vmxnet3_close will then properly
disable them again). However, vmxnet3_force_close neglects to clear
VMXNET3_STATE_BIT_QUIESCED prior to calling dev_close. As a result
vmxnet3_quiesce_dev (called from vmxnet3_close), returns early, and
leaves all the napi instances in a enabled state while the device itself
is closed. If a device in this state is activated again, napi_enable
will be called on already enabled napi_instances, leading to a BUG halt.
The fix is to simply enausre that the QUIESCED bit is cleared in
vmxnet3_force_close to allow quesence to be completed properly on close.
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
CC: Shrikrishna Khare <skhare@vmware.com>
CC: "VMware, Inc." <pv-drivers@vmware.com>
CC: "David S. Miller" <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
The ethtool api {get|set}_settings is deprecated.
We move this driver to new api {get|set}_link_ksettings.
Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
napi_complete_done() allows to opt-in for gro_flush_timeout,
added back in linux-3.19, commit 3b47d30396
("net: gro: add a per device gro flush timer")
This allows for more efficient GRO aggregation without
sacrifying latencies.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The network device operation for reading statistics is only called
in one place, and it ignores the return value. Having a structure
return value is potentially confusing because some future driver could
incorrectly assume that the return value was used.
Fix all drivers with ndo_get_stats64 to have a void function.
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
