dpdk.git
22 months agovdpa/mlx5: use common interrupt management
Spike Du [Tue, 5 Jul 2022 13:44:51 +0000 (16:44 +0300)]
vdpa/mlx5: use common interrupt management

Replace vDPA interrupt handle creation logic
with mlx5-common interrupt management function.

Signed-off-by: Spike Du <spiked@nvidia.com>
22 months agonet/mlx5: reject negative integrity item configuration
Raja Zidane [Mon, 4 Jul 2022 10:11:39 +0000 (13:11 +0300)]
net/mlx5: reject negative integrity item configuration

Negative integrity item refers to condition when the item value mask
is set, but value spec is cleared:
    ... integrity value mask l4_ok value spec 0 ...

ethdev library defines integrity bits `l3_ok` and `l4_ok` as accumulators
for all hardware L3 and L4 integrity verifications respectfully.
Hardware `l3_ok` and `l4_ok` integrity bits refer to L3 and L4
network headers only.
Integrity bits `l3_ok` and `l4_ok` are not compatible between
ethdev library and hardware.

PMD translations for ethdev `l3_ok` are:
 IPv4: `l3_ok` and `l3_csum_ok`
 IPv6: `l3_ok`
ethdev `l4_ok` is translated into PMD `l4_ok` and `l4_csum_ok` bits.

Positive IPv4 `l3_ok` flow item configuration is translated into
a single matcher that AND corresponding hardware bits.
Negative IPv4 `l3_ok` is translated into 2 hardware conditions where
each condition probes a single integrity bit:
  ethdev::l3_ok is 0 => MLX5::l3_ok is 0 OR MLX5:l3_csum_ok is 0
MLX5 hardware does not do OR condition in flow rule item.
Negative IPv4 `l3_ok` must be translated into 2 flow rules.
Similarly negative ethdev `l4_ok` condition is also translated into 2
hardware rules.

Current PMD roadmap does not allow implicit flow rule split.

Bugzilla ID: 948
Cc: stable@dpdk.org
Suggested-by: Raja Zidane <rzidane@nvidia.com>
Signed-off-by: Gregory Etelson <getelson@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
22 months agocommon/mlx5: fix non-expandable global MR cache
Dmitry Kozlyuk [Wed, 29 Jun 2022 22:08:00 +0000 (01:08 +0300)]
common/mlx5: fix non-expandable global MR cache

The number of memory regions (MR) that MLX5 PMD can use
was limited by 512 per IB device, the size of the global MR cache
that was fixed at compile time.
The cache allows to search MR LKey by address efficiently,
therefore it is the last place searched on data path
(skipped is the global MR database which would be slow).
If the application logic caused the PMD to create more than 512 MRs,
which can be the case with external memory,
those MRs would never be found on data path
and later cause a HW failure.

The cache size was fixed because at the time of overflow
the EAL memory hotplug lock may be held,
prohibiting to allocate a larger cache
(it must reside in DPDK memory for multi-process support).
This patch adds logic to release the necessary locks,
extend the cache, and repeat the attempt to insert new entries.

`mlx5_mr_btree` structure had `overflow` field
that was set when a cache (not only the global one)
could not accept new entries.
However, it was only checked for the global cache,
because caches of upper layers were dynamically expandable.
With the global cache size limitation removed, this field is not needed.
Cache size was previously limited by 16-bit indices.
Use the space in the structure previously field by `overflow` field
to extend indices to 32 bits.
With this patch, it is the HW and RAM that limit the number of MRs.

Fixes: 974f1e7ef146 ("net/mlx5: add new memory region support")
Cc: stable@dpdk.org
Signed-off-by: Dmitry Kozlyuk <dkozlyuk@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
22 months agonet/mlx5: add test for external Rx queue
Michael Baum [Tue, 28 Jun 2022 14:58:41 +0000 (17:58 +0300)]
net/mlx5: add test for external Rx queue

Add mlx5 internal test for map and unmap external RxQs.
This patch adds to testpmd app a runtime function to test the mapping
API.

  testpmd> mlx5 port (port_id) ext_rxq map (sw_queue_id) (hw_queue_id)
  testpmd> mlx5 port (port_id) ext_rxq unmap (sw_queue_id)

Signed-off-by: Michael Baum <michaelba@nvidia.com>
Reviewed-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Matan Azrad <matan@nvidia.com>
22 months agonet/mlx5: add test for remote PD and CTX
Michael Baum [Tue, 28 Jun 2022 14:58:40 +0000 (17:58 +0300)]
net/mlx5: add test for remote PD and CTX

Add mlx5 internal option in testpmd similar to run-time function
"port attach" which adds another parameter named "socket" for attaching
port and add 2 devargs before.

The arguments are "cmd_fd" and "pd_handle" using to import device
created out of PMD. Testpmd application import it using IPC, and updates
the devargs list before attaching.

These arguments were added in
the commit 9d936f4f1a5e ("common/mlx5: support remote PD and CTX")

The syntax is:

  testpmd> mlx5 port attach (identifier) socket=(path)

Where "path" is the IPC socket path agreed on the remote process.

Signed-off-by: Michael Baum <michaelba@nvidia.com>
Reviewed-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Matan Azrad <matan@nvidia.com>
22 months agocommon/cnxk: allow changing PTP mode on CN10K
Tomasz Duszynski [Fri, 1 Jul 2022 11:54:48 +0000 (13:54 +0200)]
common/cnxk: allow changing PTP mode on CN10K

Since firmware has added support for toggling PTP mode on 10k platforms
userspace code should allow doing that as well.

Cc: stable@dpdk.org
Signed-off-by: Tomasz Duszynski <tduszynski@marvell.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
22 months agogro: fix identifying fragmented packets
Kumara Parameshwaran [Mon, 27 Jun 2022 10:31:14 +0000 (16:01 +0530)]
gro: fix identifying fragmented packets

A packet with RTE_PTYPE_L4_FRAG(0x300) contains both RTE_PTYPE_L4_TCP
(0x100) & RTE_PTYPE_L4_UDP (0x200). A fragmented packet as defined in
rte_mbuf_ptype.h cannot be recognized as other L4 types and hence the
GRO layer should not use IS_IPV4_TCP_PKT or IS_IPV4_UDP_PKT for
RTE_PTYPE_L4_FRAG. Hence, if the packet type is RTE_PTYPE_L4_FRAG the
IP header should be parsed to recognize the appropriate IP type and
invoke the respective gro handler.

Fixes: 1ca5e6740852 ("gro: support UDP/IPv4")
Cc: stable@dpdk.org
Signed-off-by: Kumara Parameshwaran <kumaraparamesh92@gmail.com>
Reviewed-by: Jiayu Hu <jiayu.hu@intel.com>
22 months agoservice: fix lingering active status
Harry van Haaren [Tue, 5 Jul 2022 13:32:07 +0000 (13:32 +0000)]
service: fix lingering active status

This commit fixes an issue where calling rte_service_lcore_stop()
would result in a service's "active on lcore" status becoming stale.

The stale status would result in rte_service_may_be_active() always
returning "1", indicating that the service is not certainly stopped.

This is fixed by ensuring the "active on lcore" status of each service
is set to 0 when an lcore is stopped.

Fixes: e30dd31847d2 ("service: add mechanism for quiescing")
Fixes: 8929de043eb4 ("service: retrieve lcore active state")

Reported-by: Naga Harish K S V <s.v.naga.harish.k@intel.com>
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com>
22 months agonet/igc: support multi-process
Zhichao Zeng [Thu, 30 Jun 2022 11:03:30 +0000 (19:03 +0800)]
net/igc: support multi-process

The Rx function was not specified in the secondary process, causing the
secondary process to segfault in a multi-process environment.

This patch specify RX/TX functions in "dev_init" to support secondary
processes.

Fixes: 66fde1b943eb ("net/igc: add skeleton")
Cc: stable@dpdk.org
Signed-off-by: Zhichao Zeng <zhichaox.zeng@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
22 months agonet/i40e: fix QinQ enablement
Kevin Liu [Wed, 29 Jun 2022 15:39:50 +0000 (15:39 +0000)]
net/i40e: fix QinQ enablement

Enable double VLAN by default after firmware v8.3
and disable double VLAN is not allowed in subsequent
operations.

Fixes: 38e9762be16a ("net/i40e: add outer VLAN processing")

Signed-off-by: Kevin Liu <kevinx.liu@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
22 months agonet/iavf: fix VF reset
Yiding Zhou [Mon, 27 Jun 2022 07:22:32 +0000 (15:22 +0800)]
net/iavf: fix VF reset

When the VF is in closed state, the vf_reset flag can not be reverted
if the VF is reset asynchronously. This prevents all virtchnl commands
from executing, causing subsequent calls to iavf_dev_reset() to fail.

So the vf_reset flag needs to be reverted even when VF is in closed state.

Fixes: 676d986b4b86 ("net/iavf: fix crash after VF reset failure")
Cc: stable@dpdk.org
Signed-off-by: Yiding Zhou <yidingx.zhou@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
22 months agonet/ice: fix memory allocation insufficiency
Yuying Zhang [Tue, 28 Jun 2022 04:06:51 +0000 (04:06 +0000)]
net/ice: fix memory allocation insufficiency

Current code doesn't allocate memory of lookup element to add packet
flag. This patch adds one lookup item in the list to fix this memory
issue.

Fixes: 8b95092b7f69 ("net/ice/base: fix direction of flow that matches any")
Cc: stable@dpdk.org
Signed-off-by: Yuying Zhang <yuying.zhang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
22 months agonet/cnxk: fix extended statistics
Rakesh Kudurumalla [Fri, 1 Jul 2022 12:51:10 +0000 (18:21 +0530)]
net/cnxk: fix extended statistics

This fix replaces the usage of roc_nix_num_xstats_get() which is compile
time RoC API with runtime RoC  roc_nix_xstats_names_get() API resolving
xstat count difference for cn9k and cn10k while displaying xstats
for ethdev ports

Fixes: 825bd1d9d8e6 ("common/cnxk: update extra stats for inline device")
Cc: stable@dpdk.org
Signed-off-by: Rakesh Kudurumalla <rkudurumalla@marvell.com>
22 months agodoc: add environment variables in cnxk guide
Nithin Dabilpuram [Fri, 24 Jun 2022 11:32:15 +0000 (17:02 +0530)]
doc: add environment variables in cnxk guide

Add list of environment variables used by cnxk drivers.

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
22 months agocommon/cnxk: fix GRE tunnel parsing
Satheesh Paul [Thu, 23 Jun 2022 03:42:04 +0000 (09:12 +0530)]
common/cnxk: fix GRE tunnel parsing

After parsing GRE tunnel, parse subsequent protocols
(for example, TCP or UDP) as tunneled versions.

Fixes: c34ea71b878 ("common/cnxk: add NPC parsing API")
Cc: stable@dpdk.org
Signed-off-by: Satheesh Paul <psatheesh@marvell.com>
Reviewed-by: Kiran Kumar K <kirankumark@marvell.com>
22 months agonet/virtio-user: fix Rx interrupts with multi-queue
Yuan Wang [Mon, 4 Jul 2022 07:04:28 +0000 (15:04 +0800)]
net/virtio-user: fix Rx interrupts with multi-queue

The callfds[] array stores eventfds sequentially for Rx and Tx vq.

Fixes: d61138d4f0e2 ("drivers: remove direct access to interrupt handle")
Cc: stable@dpdk.org
Signed-off-by: Yuan Wang <yuanx.wang@intel.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
23 months agoexamples/vhost: update usage message
Herakliusz Lipiec [Tue, 21 Jun 2022 15:20:33 +0000 (16:20 +0100)]
examples/vhost: update usage message

updating vhost usage message to be aligned with the documentation.

Signed-off-by: Herakliusz Lipiec <herakliusz.lipiec@intel.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
23 months agodoc: update vhost application guide
Herakliusz Lipiec [Tue, 21 Jun 2022 15:20:32 +0000 (16:20 +0100)]
doc: update vhost application guide

Vhost sample app documentation describes parameters that are not in the
code and omits parameters that exist.
Also switching the order of sections on running vhost and VM,
since the --client parameter in the sample line
requires a socket to be created by VM.
Removing uio references and updating with vfio-pci.

Signed-off-by: Herakliusz Lipiec <herakliusz.lipiec@intel.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
23 months agoexamples/vhost: update makefile to match Meson build
Herakliusz Lipiec [Tue, 21 Jun 2022 15:20:31 +0000 (16:20 +0100)]
examples/vhost: update makefile to match Meson build

Meson build system creates a vhost binary but Makefile
and docs reference same as vhost-switch. Updating makefile
to match meson and the docs accordingly.

Signed-off-by: Herakliusz Lipiec <herakliusz.lipiec@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
23 months agovhost: prefix logs with context
David Marchand [Fri, 1 Jul 2022 13:20:56 +0000 (15:20 +0200)]
vhost: prefix logs with context

We recently improved the log messages in the vhost library, adding some
context that helps filtering for a given vhost-user device.
However, some parts of the code were missed, and some later code changes
broke this new convention (fixes were sent previous to this patch).

Change the VHOST_LOG_CONFIG/DATA helpers and always ask for a string
used as context. This should help limit regressions on this topic.

Most of the time, the context is the vhost-user device socket path.
For the rest when a vhost-user device can not be related, generic
names were chosen:
- "dma", for vhost-user async DMA operations,
- "device", for vhost-user device creation and lookup,
- "thread", for threads management,

Signed-off-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
23 months agovhost: improve some datapath log messages
David Marchand [Fri, 1 Jul 2022 07:55:10 +0000 (09:55 +0200)]
vhost: improve some datapath log messages

Those messages were missed when adding socket context.
Fix this.

Signed-off-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
23 months agovhost: restore device information in log messages
David Marchand [Fri, 1 Jul 2022 07:55:09 +0000 (09:55 +0200)]
vhost: restore device information in log messages

device information in the log messages was dropped.

Fixes: 52ade97e3641 ("vhost: fix physical address mapping")
Cc: stable@dpdk.org
Signed-off-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
23 months agovhost: add some trailing newline in log messages
David Marchand [Fri, 1 Jul 2022 07:55:08 +0000 (09:55 +0200)]
vhost: add some trailing newline in log messages

VHOST_LOG_* macros don't append a newline.
Add missing ones.

Fixes: e623e0c6d8a5 ("vhost: add reconnect ability")
Fixes: af1475918124 ("vhost: introduce API to start a specific driver")
Fixes: 2dfeebe26546 ("vhost: check return of mutex initialization")
Cc: stable@dpdk.org
Signed-off-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
23 months agovhost: check DMA info return
Jiayu Hu [Wed, 29 Jun 2022 09:07:06 +0000 (05:07 -0400)]
vhost: check DMA info return

This patch checks the return value of rte_dma_info_get()
called in rte_vhost_async_dma_configure().

Coverity issue: 379066
Fixes: 53d3f4778c1d ("vhost: integrate dmadev in asynchronous data-path")
Cc: stable@dpdk.org
Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
23 months agovdpa/sfc: fix sync between QEMU and vhost-user
Abhimanyu Saini [Tue, 28 Jun 2022 05:29:26 +0000 (10:59 +0530)]
vdpa/sfc: fix sync between QEMU and vhost-user

When DPDK app is running in the VF, it sometimes rings the doorbell
before dev_config has had a chance to complete and hence it misses
the event. As workaround, ring the doorbell when vDPA reports the
notify_area to QEMU.

Fixes: 630be406dcbf ("vdpa/sfc: get queue notify area info")
Cc: stable@dpdk.org
Signed-off-by: Vijay Kumar Srivastava <vsrivast@xilinx.com>
Signed-off-by: Abhimanyu Saini <absaini@amd.com>
Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
23 months agonet/vhost: fix deadlock on vring state change
Yuan Wang [Mon, 27 Jun 2022 05:51:25 +0000 (13:51 +0800)]
net/vhost: fix deadlock on vring state change

If vring state changes after pmd starts working, the locked vring
notifies pmd, thus calling update_queuing_status(), the latter
will wait for pmd to finish accessing vring, while pmd is also
waiting for vring to be unlocked, thus causing deadlock.

Actually, update_queuing_status() only needs to wait while
destroy/stopping the device, but not in other cases.

This patch adds a flag for whether or not to wait to fix this issue.

Fixes: 1ce3c7fe149f ("net/vhost: emulate device start/stop behavior")
Cc: stable@dpdk.org
Signed-off-by: Yuan Wang <yuanx.wang@intel.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
23 months agovhost: fix sync dequeue offload
Xuan Ding [Fri, 24 Jun 2022 05:38:24 +0000 (05:38 +0000)]
vhost: fix sync dequeue offload

This patch fixes the missing virtio net header copy in sync
dequeue path caused by refactoring, which affects dequeue
offloading.

Fixes: 6d823bb302c7 ("vhost: prepare sync for descriptor to mbuf refactoring")

Signed-off-by: Xuan Ding <xuan.ding@intel.com>
Tested-by: Wei Ling <weix.ling@intel.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
23 months agodoc: fix readability in vhost guide
Herakliusz Lipiec [Thu, 23 Jun 2022 13:57:21 +0000 (14:57 +0100)]
doc: fix readability in vhost guide

fix grammar issues and readbility in vhost library programmer guide

Fixes: 768274ebbd5e ("vhost: avoid populate guest memory")
Cc: stable@dpdk.org
Signed-off-by: Herakliusz Lipiec <herakliusz.lipiec@intel.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
23 months agovdpa/mlx5: add ConnectX-6 LX device ID
Wisam Jaddo [Thu, 23 Jun 2022 09:00:04 +0000 (12:00 +0300)]
vdpa/mlx5: add ConnectX-6 LX device ID

This adds ConnectX-6 LX to the list of supported
Mellanox devices that run the MLX5 vdpa PMD.

Signed-off-by: Wisam Jaddo <wisamm@nvidia.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
23 months agoexamples/vhost: fix retry logic on Rx path
Yuan Wang [Wed, 22 Jun 2022 09:25:55 +0000 (17:25 +0800)]
examples/vhost: fix retry logic on Rx path

drain_eth_rx() uses rte_vhost_avail_entries() to calculate
the available entries to determine if a retry is required.
However, this function only works with split rings, and
calculating packed rings will return the wrong value and cause
unnecessary retries resulting in a significant performance penalty.

This patch fix that by using the difference between tx/rx burst
as the retry condition.

Fixes: be800696c26e ("examples/vhost: use burst enqueue and dequeue from lib")
Cc: stable@dpdk.org
Signed-off-by: Yuan Wang <yuanx.wang@intel.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
Tested-by: Wei Ling <weix.ling@intel.com>
23 months agovhost: fix virtio block vDPA live migration IO drop
Andy Pei [Wed, 22 Jun 2022 07:47:08 +0000 (15:47 +0800)]
vhost: fix virtio block vDPA live migration IO drop

In the virtio blk vDPA live migration use case, before the live
migration process, QEMU will set call fd to vDPA back-end. QEMU
and vDPA back-end stand by until live migration starts.
During live migration process, QEMU sets kick fd and a new call
fd. However, after the kick fd is set to the vDPA back-end, the
vDPA back-end configures device and data path starts. The new
call fd will cause some kind of "re-configuration", this kind
of "re-configuration" cause IO drop.
After this patch, vDPA back-end configures device after kick fd
and call fd are well set and make sure no IO drops.
This patch only impact virtio blk vDPA device and does not impact
net device.

Fixes: 7015b6577178 ("vdpa/ifc: add block device SW live-migration")

Signed-off-by: Andy Pei <andy.pei@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
23 months agodoc: clean vhost async note
Xuan Ding [Wed, 22 Jun 2022 01:45:56 +0000 (01:45 +0000)]
doc: clean vhost async note

This patch moves the 'Recommended IOVA mode in async datapath'
section under 'Vhost asynchronous data path' as a sub-section,
which makes the doc cleaner.

Signed-off-by: Xuan Ding <xuan.ding@intel.com>
Reviewed-by: Jiayu Hu <jiayu.hu@intel.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
23 months agovdpa/ifc: fix vhost message size check
Andy Pei [Tue, 21 Jun 2022 13:46:31 +0000 (21:46 +0800)]
vdpa/ifc: fix vhost message size check

For vhost message VHOST_USER_GET_CONFIG, we do not check
payload size in vhost lib, we check payload size in driver
specific ops.
For ifc vdpa driver, we just need to make sure payload size
is not smaller than sizeof(struct virtio_blk_config).

Fixes: 856d03bcdc54 ("vdpa/ifc: add block operations")

Signed-off-by: Andy Pei <andy.pei@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
23 months agodoc: add vhost async enqueue API usage
Xuan Ding [Tue, 21 Jun 2022 07:21:31 +0000 (07:21 +0000)]
doc: add vhost async enqueue API usage

This patch updates the correct usage for async enqueue APIs.
The rte_vhost_poll_enqueue_completed() needs to be
called in time to notify the guest of completed packets and
avoid packet loss.

Signed-off-by: Xuan Ding <xuan.ding@intel.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
23 months agonet/virtio-user: fix socket non-blocking mode
Yuan Wang [Fri, 17 Jun 2022 02:42:29 +0000 (10:42 +0800)]
net/virtio-user: fix socket non-blocking mode

The virtio-user initialization requires unix socket to receive backend
messages in block mode. However, vhost_user_update_link_state() sets
the same socket to nonblocking via fcntl, which affects all threads.
Enabling the rxq interrupt can causes both of these behaviors to occur
concurrently, with the result that the initialization may fail
because no messages are received in nonblocking socket.

Thread 1:
virtio_init_device()
--> virtio_user_start_device()
--> vhost_user_set_memory_table()
--> vhost_user_check_reply_ack()

Thread 2:
virtio_interrupt_handler()
--> vhost_user_update_link_state()

Fix that by replacing O_NONBLOCK with the recv per-call option
MSG_DONTWAIT.

Fixes: ef53b6030039 ("net/virtio-user: support LSC")
Cc: stable@dpdk.org
Signed-off-by: Yuan Wang <yuanx.wang@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
23 months agonet/netvsc: fix vmbus device reference in multi-process
Long Li [Wed, 29 Jun 2022 23:29:44 +0000 (16:29 -0700)]
net/netvsc: fix vmbus device reference in multi-process

The vmbus device is allocated via "calloc" before the EAL memory is
initialized. The secondary process can't reference the vmbus device as
it is not mapped correctly in the shared memory region.

Replace all references to the vmbus device (and its contents) with the
pointers/contents set by the primary process.

Fixes: 4e9c73e96e ("net/netvsc: add Hyper-V network device")
Cc: stable@dpdk.org
Signed-off-by: Long Li <longli@microsoft.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
23 months agonet/ngbe: fix customized device probing
Jiawen Wu [Wed, 29 Jun 2022 03:34:17 +0000 (11:34 +0800)]
net/ngbe: fix customized device probing

The devices with OEM subsystem vendor ID failed to be initialized,
because flash was read before memory address was set.

Fixes: 240422edbf84 ("net/ngbe: support OEM subsystem vendor ID")

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
23 months agonet/txgbe: fix customized device probing
Jiawen Wu [Wed, 29 Jun 2022 03:34:16 +0000 (11:34 +0800)]
net/txgbe: fix customized device probing

The devices with OEM subsystem vendor ID failed to be initialized,
because flash was read before memory address was set.

Fixes: 138d869e41c0 ("net/txgbe: support OEM subsystem vendor ID")

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
23 months agoapp/testpmd: remove duplicated flow type name table
Ferruh Yigit [Wed, 29 Jun 2022 08:34:51 +0000 (16:34 +0800)]
app/testpmd: remove duplicated flow type name table

Flow type table has two instance, one is used for flow type to string
conversion, and other is used for string to flow type conversion.
And tables are diverged by time.

Unifying tables to prevent maintaining two different tables.

Note: made 'flowtype_to_str()' and 'str_to_flowtype()' non-static to
prevent build error for the case PMDs using it disables. Making the two
functions generic, not for some PMDs.

Signed-off-by: Ferruh Yigit <ferruh.yigit@xilinx.com>
Signed-off-by: Huisong Li <lihuisong@huawei.com>
23 months agoapp/testpmd: reorder RSS type table
Huisong Li [Wed, 29 Jun 2022 08:34:50 +0000 (16:34 +0800)]
app/testpmd: reorder RSS type table

There are group and individual types in rss_type_table[]. However, group
types are very scattered, and individual types are not arranged based on
the bit number order in 'RTE_ETH_RSS_xxx'. For a clear distribution of
types and better maintenance, this patch reorders this table.

Signed-off-by: Huisong Li <lihuisong@huawei.com>
Acked-by: Ferruh Yigit <ferruh.yigit@xilinx.com>
23 months agoapp/testpmd: compact RSS types output
Ferruh Yigit [Wed, 29 Jun 2022 08:34:49 +0000 (16:34 +0800)]
app/testpmd: compact RSS types output

In port info command output, 'show port info all', supported RSS offload
types printed one type per line, and although this information is not
most important part of the command it takes big part of the command
output.

In port RSS hash and flow RSS command output, 'show port 0 rss-hash',
and 'flow query 0 0 rss', all enabled RSS types are printed on one line.
If there are many types, the print will be very long.

Compacting these RSS offloads and types output by fixing the length of
the character string printed on each line, instead of one per line or
one line.
Output becomes as following:

Supported RSS offload flow types:
  ipv4-frag  ipv4-tcp  ipv4-udp  ipv4-sctp  ipv4-other
  ipv6-frag  ipv6-tcp  ipv6-udp  ipv6-sctp  ipv6-other
  l4-dst-only  l4-src-only  l3-dst-only  l3-src-only

Signed-off-by: Ferruh Yigit <ferruh.yigit@xilinx.com>
Signed-off-by: Huisong Li <lihuisong@huawei.com>
23 months agoapp/testpmd: unify RSS types display
Huisong Li [Wed, 29 Jun 2022 08:34:48 +0000 (16:34 +0800)]
app/testpmd: unify RSS types display

The 'rss_type_table[]' maintains the name and value of RSS types. This
patch unifies a common interface to display RSS types.

Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Ferruh Yigit <ferruh.yigit@xilinx.com>
23 months agoapp/testpmd: refactor config all RSS command
Huisong Li [Wed, 29 Jun 2022 08:34:47 +0000 (16:34 +0800)]
app/testpmd: refactor config all RSS command

The "port config <port_id> rss-hash-key" and "show port <port_id>
rss-hash key" commands both use the 'rss_type_table[]' to get
'rss_types' or the RSS type name. So this patch uses the
'rss_type_table[]' to get the RSS types.  In this way, this command
naturally supports more individual types.

Suggested-by: Ferruh Yigit <ferruh.yigit@xilinx.com>
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Acked-by: Ferruh Yigit <ferruh.yigit@xilinx.com>
23 months agoapp/testpmd: unify name of L2 payload offload
Huisong Li [Wed, 29 Jun 2022 08:34:45 +0000 (16:34 +0800)]
app/testpmd: unify name of L2 payload offload

Currently, the "port config all rss xx" command uses 'ether' name to match
and to set 'RTE_ETH_RSS_L2_PAYLOAD' offload. However, others RSS command,
such as, "port config <port_id> rss-hash-key" and "show port <port_id>
rss-hash key", use 'l2-payload' to represent this offload. So this patch
unifies the name of 'RTE_ETH_RSS_L2_PAYLOAD' offload.

Signed-off-by: Huisong Li <lihuisong@huawei.com>
Acked-by: Ferruh Yigit <ferruh.yigit@xilinx.com>
23 months agoapp/testpmd: fix supported RSS offload display
Huisong Li [Wed, 29 Jun 2022 08:34:44 +0000 (16:34 +0800)]
app/testpmd: fix supported RSS offload display

The rte_eth_dev_info.flow_type_rss_offloads is populated in terms of
RTE_ETH_RSS_* bits. If PMD sets RTE_ETH_RSS_L3_SRC_ONLY to
dev_info->flow_type_rss_offloads. testpmd will display "user defined 63"
when run 'show port info 0'. Because testpmd use flowtype_to_str()
to display the supported RSS offload of PMD. In fact, the function is
used to display flow type in FDIR commands for i40e or ixgbe. This patch
uses the RTE_ETH_RSS_* bits to display supported RSS offload of PMD.

Fixes: b12964f621dc ("ethdev: unification of RSS offload types")
Cc: stable@dpdk.org
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Ferruh Yigit <ferruh.yigit@xilinx.com>
22 months agodoc: update DLB2 guide
Timothy McDaniel [Sat, 2 Jul 2022 19:35:00 +0000 (14:35 -0500)]
doc: update DLB2 guide

Updated DLB2 guide to document following features.
1) CQ Weight
2) Port COS
3) Maximum CQ depth
4) Maximum enqueue depth

Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
22 months agoevent/dlb2: fix port COS initialization
Timothy McDaniel [Sat, 2 Jul 2022 16:22:39 +0000 (11:22 -0500)]
event/dlb2: fix port COS initialization

Fix cos initialization, handling the default case too.

Substitute the semicolon for the comma
that was expected in the cos_bw command line override.
Commas are not allowed within a multi field option.
The new format is cos_bw=%d:%d:%d:%d, where the sum of
the 4 decimal values must be less than or equal to 100.

Corrected probe-time initialization order.

Fixes: bec8901bfe9f ("event/dlb2: support ldb port specific COS")
Cc: stable@dpdk.org
Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
22 months agoevent/dlb2: fix CQ depth override credit deadlock
Timothy McDaniel [Sat, 2 Jul 2022 16:22:38 +0000 (11:22 -0500)]
event/dlb2: fix CQ depth override credit deadlock

This commit fixes a bug, where we could encounter a credit
deadlock due to changing the CQ depth. To remedy this situation,
the commit reduces the maximum CQ depth from 1024 to 128,
and also allows configuring the maximum enqueue depth. Maximum
enqueue depth must be tuned to the CQ depth, if the CQ depth
is increased.

Fixes: 86fe66d45667 ("event/dlb2: allow CQ depths up to 1024")
Cc: stable@dpdk.org
Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
22 months agoevent/dlb2: fix CQ depth override
Timothy McDaniel [Sat, 2 Jul 2022 16:22:37 +0000 (11:22 -0500)]
event/dlb2: fix CQ depth override

This commit fixes a bug, where we could assign a CQ depth
of zero, leading to a subsequent divide-by-zero fault.
It also fixes an issue where the original default CQ depth
was returned on a query, instead of the overridden value.

Fixes: 86fe66d45667 ("event/dlb2: allow CQ depths up to 1024")
Cc: stable@dpdk.org
Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
22 months agoevent/dlb2: fix initialization of COS bandwidth args
Timothy McDaniel [Sat, 2 Jul 2022 16:22:36 +0000 (11:22 -0500)]
event/dlb2: fix initialization of COS bandwidth args

This commit fixes a typo and resultant bug that triggered a
coverity warning.

Coverity issue: 4607286
Fixes: bec8901bfe9f ("event/dlb2: support ldb port specific COS")
Cc: stable@dpdk.org
Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
22 months agoevent/dlb2: fix array overflow
Timothy McDaniel [Sat, 2 Jul 2022 16:22:35 +0000 (11:22 -0500)]
event/dlb2: fix array overflow

This commit fixes a segfault that resulted from reading
beyond the end of the port_cos array. The root cause was using
the DLB num ports define instead of the eventdev num ports define.

Fixes: bec8901bfe9f ("event/dlb2: support ldb port specific COS")
Cc: stable@dpdk.org
Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
22 months agoeventdev/eth_tx: fix queue delete
Naga Harish K S V [Thu, 23 Jun 2022 10:05:11 +0000 (15:35 +0530)]
eventdev/eth_tx: fix queue delete

Add spinlock protection in queue delete function.
This protects the data path while the queue delete operation
is in progress.

Fixes: a3bbf2e09756 ("eventdev: add eth Tx adapter implementation")
Cc: stable@dpdk.org
Signed-off-by: Naga Harish K S V <s.v.naga.harish.k@intel.com>
Acked-by: Jay Jayatheerthan <jay.jayatheerthan@intel.com>
22 months agoexamples/fips_validation: fix print for zero length payload
Archana Muniganti [Thu, 30 Jun 2022 11:21:23 +0000 (16:51 +0530)]
examples/fips_validation: fix print for zero length payload

NIST GCM decrypt result vectors expects to have following print
for zero length payload instead of having no print.
"pt" = ""

Fixes: b09aac2d6e2b ("examples/fips_validation: add JSON to GCM test")

Signed-off-by: Archana Muniganti <marchana@marvell.com>
22 months agoexamples/ipsec-secgw: fix fallback session create
Radu Nicolau [Thu, 30 Jun 2022 11:45:27 +0000 (12:45 +0100)]
examples/ipsec-secgw: fix fallback session create

Fix fallback session create for inline sessions.

Fixes: a8ade12123c3 ("examples/ipsec-secgw: create lookaside sessions at init")

Signed-off-by: Radu Nicolau <radu.nicolau@intel.com>
Acked-by: Akhil Goyal <gakhil@marvell.com>
Tested-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
22 months agodoc: update QAT driver location
Rebecca Troy [Fri, 1 Jul 2022 18:08:07 +0000 (18:08 +0000)]
doc: update QAT driver location

This commit removes any references to the old QAT
driver location 01.org in the documentation and
replaces them with the updated location IDZ (Intel
Development Zone).

This commit also adds a note to the docs to alert
users of a possible error when building the new QAT
driver and provides the patch needed to resolve this
error.

Signed-off-by: Rebecca Troy <rebecca.troy@intel.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
22 months agodoc: fix grammar and parameters in l2fwd-crypto guide
Jakub Poczatek [Wed, 1 Jun 2022 09:35:52 +0000 (09:35 +0000)]
doc: fix grammar and parameters in l2fwd-crypto guide

Doc was updated with fixed grammar in most cases. These
include adding periods to ends of sentences and capitalizing
some words. Some instances of "a" were changed to "an". The
option "-n 4" has also been removed from the example of
running the application.

Fixes: ba7b86b1419 ("doc: add l2fwd-crypto sample app guide")
Fixes: 2661f4fbe93 ("examples/l2fwd-crypto: add AEAD parameters")
Fixes: 4790f99d2d3 ("examples/l2fwd-crypto: use cryptodev algorithm parser")
Fixes: 5949e30dae6 ("doc: fix typo in l2fwd-crypto usage")
Fixes: acf8616901b ("cryptodev: add auth IV")
Fixes: b79e4c00af0 ("cryptodev: use AES-GCM/CCM as AEAD algorithms")
Fixes: d2797f51cc6 ("examples/l2fwd-crypto: add cryptodev mask option")
Fixes: e2a94f9ad3e ("doc: remove references to make from apps guide")
Fixes: 10b9d471a6f ("doc: update minimum requirement of l2fwd-crypto")
Fixes: 3cc28001a33 ("doc: fix typo in l2fwd-crypto guide")
Cc: stable@dpdk.org
Signed-off-by: Jakub Poczatek <jakub.poczatek@intel.com>
Acked-by: Akhil Goyal <gakhil@marvell.com>
22 months agodoc: fix grammar and formatting in compressdev guide
Ciara Power [Mon, 30 May 2022 16:03:42 +0000 (16:03 +0000)]
doc: fix grammar and formatting in compressdev guide

Small improvements made to the compressdev programmer's guide.
This includes rephrasing some sentences, fixing grammar,
and aligning formatting.

Fixes: a584d3bea902 ("doc: add compressdev library guide")
Fixes: f7095d41bba6 ("doc: clarify data plane error handling in compressdev")
Cc: stable@dpdk.org
Signed-off-by: Ciara Power <ciara.power@intel.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
22 months agocrypto/qat: fix DOCSIS crash
Rebecca Troy [Wed, 29 Jun 2022 16:10:36 +0000 (16:10 +0000)]
crypto/qat: fix DOCSIS crash

Currently if AES or DES algorithms fail for DOCSIS test suite,
a segmentation fault occurs when cryptodev_qat_autotest is ran.

This is due to a duplicate call of EVP_CIPHER_CTX_free for the
session context. Ctx is freed firstly in the bpi_cipher_ctx_init
function and then again at the end of qat_sym_session_configure_cipher
function.

This commit fixes this bug by removing the first instance
of EVP_CIPHER_CTX_free, leaving just the dedicated function in
the upper level to free the ctx.

Fixes: 98f060891615 ("crypto/qat: add symmetric session file")
Cc: stable@dpdk.org
Signed-off-by: Rebecca Troy <rebecca.troy@intel.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
22 months agoexamples/fips_validation: add parsing for SHA
Gowrishankar Muthukrishnan [Wed, 29 Jun 2022 12:35:06 +0000 (18:05 +0530)]
examples/fips_validation: add parsing for SHA

Added function to parse algorithm for SHA test.

Signed-off-by: Gowrishankar Muthukrishnan <gmuthukrishn@marvell.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
23 months agoexamples/fips_validation: add parsing for AES-XTS
Gowrishankar Muthukrishnan [Wed, 29 Jun 2022 12:35:05 +0000 (18:05 +0530)]
examples/fips_validation: add parsing for AES-XTS

Added function to parse algorithm for AES XTS test.

Signed-off-by: Gowrishankar Muthukrishnan <gmuthukrishn@marvell.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
23 months agoexamples/fips_validation: add AES-CBC in the enum
Gowrishankar Muthukrishnan [Wed, 29 Jun 2022 12:35:04 +0000 (18:05 +0530)]
examples/fips_validation: add AES-CBC in the enum

Add algorithm enum specifically for AES_CBC instead of relying on
AES as such.

Fixes: 8b8546aaedf ("examples/fips_validation: add parsing for AES-CBC")

Signed-off-by: Gowrishankar Muthukrishnan <gmuthukrishn@marvell.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
23 months agoexamples/fips_validation: handle empty payload
Gowrishankar Muthukrishnan [Tue, 28 Jun 2022 13:11:09 +0000 (18:41 +0530)]
examples/fips_validation: handle empty payload

Allocate at least onebyte to handle empty payload in a test vector
when defined.

Fixes: 3d0fad56b74 ("examples/fips_validation: add crypto FIPS application")
Cc: stable@dpdk.org
Signed-off-by: Gowrishankar Muthukrishnan <gmuthukrishn@marvell.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
23 months agocrypto/cnxk: decrement ESN to be used in session
Anoob Joseph [Mon, 27 Jun 2022 08:12:33 +0000 (13:42 +0530)]
crypto/cnxk: decrement ESN to be used in session

ESN provided in the session would be the next sequence number to be
used. Hence predecrement the value, so that in datapath, incremented
value will be as expected.

Signed-off-by: Anoob Joseph <anoobj@marvell.com>
23 months agotest/crypto: add additional stream cipher cases
Tejasree Kondoj [Thu, 23 Jun 2022 18:19:47 +0000 (23:49 +0530)]
test/crypto: add additional stream cipher cases

Added ZUC, SNOW3G and AES-CTR-CMAC auth-cipher
test vectors with same auth and cipher offsets
and total digest data encrypted.
Existing tests have different cipher and
auth offsets and partial or no digest encrypted.

Signed-off-by: Tejasree Kondoj <ktejasree@marvell.com>
Acked-by: Ciara Power <ciara.power@intel.com>
23 months agobaseband/acc100: remove prefix of internal file
Nicolas Chautru [Fri, 24 Jun 2022 23:32:42 +0000 (16:32 -0700)]
baseband/acc100: remove prefix of internal file

File renamed to avoid the rte_ file prefix since rte_acc100_pmd.h
is actually internal only.

Signed-off-by: Nicolas Chautru <nicolas.chautru@intel.com>
Acked-by: Akhil Goyal <gakhil@marvell.com>
23 months agotest/crypto: fix SNOW3G vector IV format
Ciara Power [Thu, 23 Jun 2022 14:42:50 +0000 (14:42 +0000)]
test/crypto: fix SNOW3G vector IV format

Some of the cipher and authentication IVs did not follow the spec for
SNOW3G algorithm [1].

Cipher IVs must have the last 3 bytes of each 8 byte block as 0x0.
IV[4] and IV[12] must have the last 2 bits set to 0.
Each 8 byte block is repeated.

Auth IVs must also have a repeated 8 byte block.
IV[8] and IV[14] may have a flipped bit based on direction.

[1] https://www.gsma.com/aboutus/wp-content/uploads/2014/12/uea2uia2d1v21.pdf

Fixes: 8bdf665fe6c0 ("app/test: add SNOW 3G")
Fixes: 24342ade2c9d ("test/crypto: check SNOW3G when digest is encrypted")
Fixes: 02ed7b3871d6 ("test/crypto: add SNOW3G test cases for auth-cipher")
Fixes: 11c5485bb276 ("test/crypto: add scatter-gather tests for IP and OOP")
Cc: stable@dpdk.org
Signed-off-by: Ciara Power <ciara.power@intel.com>
Acked-by: Tejasree Kondoj <ktejasree@marvell.com>
23 months agotest/crypto: fix ZUC vector IV format
Ciara Power [Thu, 23 Jun 2022 14:42:49 +0000 (14:42 +0000)]
test/crypto: fix ZUC vector IV format

Some authentication and cipher IV formats were not following the spec [1].

For ZUC128 cipher IV, an 8 byte block is repeated,
with the last 3 bytes of each being 0x0.
IV[4] and IV[12] must have the last 2 bits set to 0.

Auth IVs must also have repeated bytes with the last 3 bytes
containing 0x0 in each 8 byte block.
IV[4] and IV[12] must have the last 3 bits set to 0.
IV[8] and IV[14] may have a flipped bit based on direction.

[1] https://www.gsma.com/security/wp-content/uploads/2019/05/EEA3_EIA3_specification_v1_8.pdf

Fixes: a81a81850fb1 ("test/crypto: add ZUC test cases for QAT")
Fixes: b1c1df46878d ("test/crypto: add ZUC test cases for auth-cipher")
Cc: stable@dpdk.org
Signed-off-by: Ciara Power <ciara.power@intel.com>
Acked-by: Tejasree Kondoj <ktejasree@marvell.com>
23 months agotest/crypto: fix authentication IV for ZUC SGL
Ciara Power [Thu, 23 Jun 2022 14:31:42 +0000 (14:31 +0000)]
test/crypto: fix authentication IV for ZUC SGL

The wireless operation for ZUC SGL tests was being passed NULL instead
of a pointer to the test data authentication IV, and IV length 0.
This is now corrected to use the IV from the test data.

Fixes: 11c5485bb276 ("test/crypto: add scatter-gather tests for IP and OOP")
Cc: stable@dpdk.org
Signed-off-by: Ciara Power <ciara.power@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
23 months agoexamples/ipsec-secgw: support poll mode NEON LPM lookup
Rahul Bhansali [Thu, 23 Jun 2022 09:38:16 +0000 (15:08 +0530)]
examples/ipsec-secgw: support poll mode NEON LPM lookup

This adds the support of NEON based LPM lookup along with
multi packet processing for burst send in packets routing.

Performance impact:
On cn10k, with poll mode inline protocol, outbound performance
increased by ~8% and inbound performance increased by ~6%.

Signed-off-by: Rahul Bhansali <rbhansali@marvell.com>
Acked-by: Akhil Goyal <gakhil@marvell.com>
23 months agoexamples/l3fwd: move packet group function in common
Rahul Bhansali [Thu, 23 Jun 2022 09:38:15 +0000 (15:08 +0530)]
examples/l3fwd: move packet group function in common

This will make the packet grouping function common, so
that other examples can utilize as per need.

For each architecture sse/neon/altivec, port group
headers will be created under examples/common/<arch>.

Signed-off-by: Rahul Bhansali <rbhansali@marvell.com>
Tested-by: Konstantin Ananyev <konstantin.v.ananyev@yandex.ru>
Acked-by: Konstantin Ananyev <konstantin.v.ananyev@yandex.ru>
23 months agoexamples/ipsec-secgw: fix Tx checksum offload flag
Radu Nicolau [Wed, 29 Jun 2022 16:46:07 +0000 (17:46 +0100)]
examples/ipsec-secgw: fix Tx checksum offload flag

For the inline crypto path set the Tx checksum offload flag
only if the device supports it.

Fixes: d24471e5786b ("examples/ipsec-secgw: disable Tx checksum for inline")

Signed-off-by: Radu Nicolau <radu.nicolau@intel.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
Acked-by: Akhil Goyal <gakhil@marvell.com>
23 months agotest/security: add event inline IPsec cases
Volodymyr Fialko [Wed, 22 Jun 2022 11:33:20 +0000 (13:33 +0200)]
test/security: add event inline IPsec cases

Enable ability to run inline security tests using event
API(rte_event_eth_tx_adapter_enqueue/rte_event_dequeue_burst).
New test command - event_inline_ipsec_autotest will run same list of
test cases as inline_ipsec_autotest, but packets will go through eventdev.

Signed-off-by: Volodymyr Fialko <vfialko@marvell.com>
Acked-by: Anoob Joseph <anoobj@marvell.com>
Acked-by: Akhil Goyal <gakhil@marvell.com>
23 months agoexamples/ipsec-secgw: support more flow patterns and actions
Satheesh Paul [Wed, 22 Jun 2022 01:22:23 +0000 (06:52 +0530)]
examples/ipsec-secgw: support more flow patterns and actions

Added support to create flow rules with count, mark and
security actions and mark pattern.

Signed-off-by: Satheesh Paul <psatheesh@marvell.com>
Acked-by: Fan Zhang <roy.fan.zhang@intel.com>
Acked-by: Akhil Goyal <gakhil@marvell.com>
23 months agoversion: 22.07-rc2
Thomas Monjalon [Mon, 27 Jun 2022 02:03:44 +0000 (04:03 +0200)]
version: 22.07-rc2

Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
23 months agonet/bnxt: fix check for autoneg enablement in the PHY FW
Somnath Kotur [Wed, 15 Jun 2022 14:57:03 +0000 (20:27 +0530)]
net/bnxt: fix check for autoneg enablement in the PHY FW

The current combination of checks to determine whether autoneg is
enabled in the card is a bit convoluted and may become incorrect
as well in the future as one of the fields being used - auto_link_speed
might become deprecated.
Switch to using the 'auto_mode' field obtained from the response of
HWRM_PHY_QCFG cmd as that is always deterministically set by the PHY
FW.
Fixed a bug in the 40G check to only look for the bit setting and
not the actual value.
Also, check the forced speeds first before trying to enforce the
auto speeds

Allow the user to set autoneg speed in all cases except for PAM4 200G
as PAM4 200G will come up only in forced mode.

Fixes: c23f9ded0391 ("net/bnxt: support 200G PAM4 link")
Cc: stable@dpdk.org
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
23 months agonet/bnxt: cleanup MTU setting
Damodharam Ammepalli [Wed, 15 Jun 2022 14:57:02 +0000 (20:27 +0530)]
net/bnxt: cleanup MTU setting

Minor cleanup in bnxt_mtu_set_op() to move pre-mature
setting of jumbo flag post mtu check and remove
a redundant mtu set operation from rxq vnic configs.

Fixes: daef48efe5e5 ("net/bnxt: support set MTU")
Cc: stable@dpdk.org
Signed-off-by: Damodharam Ammepalli <damodharam.ammepalli@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
23 months agonet/bnxt: disallow MTU change when device is started
Damodharam Ammepalli [Wed, 15 Jun 2022 14:57:01 +0000 (20:27 +0530)]
net/bnxt: disallow MTU change when device is started

With this patch, bnxt_mtu_set_op() will return an error code if the
device has already started. The user application will have to take
care to bring down device before invoking the mtu_set()

Fixes: daef48efe5e5 ("net/bnxt: support set MTU")
Cc: stable@dpdk.org
Signed-off-by: Damodharam Ammepalli <damodharam.ammepalli@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
23 months agonet/bnxt: fix setting forced speed
Kalesh AP [Wed, 15 Jun 2022 14:57:00 +0000 (20:27 +0530)]
net/bnxt: fix setting forced speed

The "active_fec_signal_mode" in HWRM_PORT_PHY_QCFG response
does not return correct value till the link is up. Driver cannot
rely on active_fec_signal_mode while setting forced speed.

While setting forced speed of 50G/100G/200G, check if PAM4 speeds
are supported for the port first and then populate the HWRM request
accordingly.

Also, If PAM4 speed is supported, use PAM4 supported speed while
reporting speed capabilities.

Fixes: c23f9ded0391 ("net/bnxt: support 200G PAM4 link")
Cc: stable@dpdk.org
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
23 months agonet/bnxt: allow Tx only or Rx only
Damodharam Ammepalli [Wed, 15 Jun 2022 14:56:59 +0000 (20:26 +0530)]
net/bnxt: allow Tx only or Rx only

Currently, we fail the init/probe of PMD if eth_dev->data->nb_tx_queues
or eth_dev->data->nb_rx_queues is 0. We are removing this check.

Fixes: daef48efe5e5 ("net/bnxt: support set MTU")
Cc: stable@dpdk.org
Signed-off-by: Damodharam Ammepalli <damodharam.ammepalli@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
23 months agonet/bnxt: reduce level of an Rx setup log
Kalesh AP [Wed, 15 Jun 2022 14:56:58 +0000 (20:26 +0530)]
net/bnxt: reduce level of an Rx setup log

Broadcom HW drops packets when there are no descriptors available.
It does not matter what flag the application specifies in "rx_drop_en"
when configuring the Rx ring.

Reduce the verbosity of the log to print the status of the "rx_drop_en"
when configuring the Rx ring.

Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
23 months agonet/bnxt: fix switch domain allocation
Ajit Khaparde [Wed, 15 Jun 2022 14:56:57 +0000 (20:26 +0530)]
net/bnxt: fix switch domain allocation

Allocate switch domain after the trusted VF capability is queried
from the FW. Currently we are calling the function earlier.
Since the switch domain is allocated only for PFs or trusted VF,
the current location of code fails to allocate the domain during init.
But during cleanup we try to free the domain incorrectly.
Fix the behavior by changing the sequence of function calls.

Fixes: 3127f99274b67 ("net/bnxt: refactor init/uninit")
Cc: stable@dpdk.org
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
23 months agonet/bnxt: remove assert for zero data length in Tx
Somnath Kotur [Wed, 15 Jun 2022 14:56:56 +0000 (20:26 +0530)]
net/bnxt: remove assert for zero data length in Tx

Currently the PMD tries to detect a potential 0 byte DMA by
using RTE_VERIFY.
But since RTE_VERIFY internally calls rte_panic() it is fatal to
the application and some applications want to avoid that.
So return an error from the bnxt xmit handler if such a bad pkt is
encountered by logging an error message, dumping the pkt header and
dump the current stack as well

Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
23 months agonet/bnxt: reduce barriers in NEON vector Rx
Ruifeng Wang [Mon, 13 Jun 2022 06:22:25 +0000 (14:22 +0800)]
net/bnxt: reduce barriers in NEON vector Rx

To read descriptors in expected order, barriers are inserted after each
descriptor read. The excessive use of barriers is unnecessary and could
cause performance drop.

Removed barriers between descriptor reads. And changed counting of valid
packets so as to handle discontinuous valid packets. Because out of
order read could lead to valid descriptors that fetched being
discontinuous.

In VPP L3 routing test, 6% performance gain was observed. The test was
done on a platform with ThunderX2 CPU and Broadcom PS225 NIC.

Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
23 months agodoc: add note about running as non-root in virtio guide
Dmitry Kozlyuk [Fri, 24 Jun 2022 13:19:56 +0000 (16:19 +0300)]
doc: add note about running as non-root in virtio guide

The requirement of SYS_ADMIN capability in legacy virtio mode
was missing. Add it to the driver-specific page.

Signed-off-by: Dmitry Kozlyuk <dkozlyuk@nvidia.com>
23 months agodoc: update running as non-root in mlx5 guide
Dmitry Kozlyuk [Fri, 24 Jun 2022 13:19:55 +0000 (16:19 +0300)]
doc: update running as non-root in mlx5 guide

Reference the common guide for generic setup.
Remove excessive capabilities from the recommended list.

Cc: stable@dpdk.org
Signed-off-by: Dmitry Kozlyuk <dkozlyuk@nvidia.com>
23 months agodoc: add more instructions for running as non-root
Dmitry Kozlyuk [Fri, 24 Jun 2022 13:19:54 +0000 (16:19 +0300)]
doc: add more instructions for running as non-root

The guide to run DPDK applications as non-root in Linux
did not provide specific instructions to configure the required access
and did not explain why each bit is needed.
The latter is important because running as non-root
is one of the ways to tighten security and grant minimal permissions.

Cc: stable@dpdk.org
Signed-off-by: Dmitry Kozlyuk <dkozlyuk@nvidia.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
23 months agousertools: add options for hugetlbfs mount point owner
Dmitry Kozlyuk [Fri, 24 Jun 2022 13:19:53 +0000 (16:19 +0300)]
usertools: add options for hugetlbfs mount point owner

Per mount(8), the previous owner and mode of the mount point
become invisible as long as this filesystem remains mounted.
Because dpdk-hugepages.py must be run as root,
the new owner would be root.
This is undesirable if the hugepage directory is being set up
by the administrator for an unprivileged user.
HugeTLB filesystem has options to set the mount point owner.
Add --user/-U and --group/-G options to apply this when mounting.
The benefit of performing this in dpdk-hugepages.py
is that the user does not need to care about this detail
of mount command operation.

Signed-off-by: Dmitry Kozlyuk <dkozlyuk@nvidia.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
23 months agousertools: add option for hugetlbfs directory
Dmitry Kozlyuk [Fri, 24 Jun 2022 13:19:52 +0000 (16:19 +0300)]
usertools: add option for hugetlbfs directory

dpdk-hugepages.py had /dev/hugepages hardcoded as the mount point.
It may be desirable to setup hugepage directory at another path,
for example, when using hugepages of multiple sizes in different
directories or when granting different permissions to mount points.
Add --directory/-d option to the script.

Signed-off-by: Dmitry Kozlyuk <dkozlyuk@nvidia.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
23 months agodoc: make doc roadmap common for Linux and BSD guides
Bruce Richardson [Wed, 16 Mar 2022 16:05:46 +0000 (16:05 +0000)]
doc: make doc roadmap common for Linux and BSD guides

Both the Linux and FreeBSD GSG docs had a "Documentation Roadmap"
section as part of the introduction page, and this contained the same
information, with only the reference to the GSGs themselves being
different. This text can be consolidated into a single text file which
is included by both GSG intro sections - using relative links for the
self reference.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
23 months agoexamples/distributor: fix distributor on Rx core
Abdullah Ömer Yamaç [Mon, 20 Jun 2022 16:31:46 +0000 (19:31 +0300)]
examples/distributor: fix distributor on Rx core

This patch fixes the syntax error when using the single-core
for both Rx and distributor functions.

Fixes: 4a7f40c0ff9a ("examples/distributor: add dedicated core")
Cc: stable@dpdk.org
Signed-off-by: Abdullah Ömer Yamaç <omer.yamac@ceng.metu.edu.tr>
Acked-by: Ferruh Yigit <ferruh.yigit@xilinx.com>
Tested-by: David Hunt <david.hunt@intel.com>
23 months agoapp/testpmd: support different input color method
Sunil Kumar Kori [Thu, 23 Jun 2022 12:57:01 +0000 (18:27 +0530)]
app/testpmd: support different input color method

To enable input coloring, based on VLAN or DSCP, patch adds
command line interface to configure the following:

 - configuring input coloring using VLAN or DSCP while creating
   meter i.e. during rte_mtr_create()

 - Update VLAN input coloring table at runtime.

 - configures protocol priorities.

 - retrieve protocol and priority information

Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
23 months agonet/hns3: delete unused code
Dongdong Liu [Fri, 24 Jun 2022 08:59:51 +0000 (16:59 +0800)]
net/hns3: delete unused code

The RTE_HNS3_ONLY_1630_FPGA macro is not in use, so delete the code.

Fixes: 2192c428f9a6 ("net/hns3: fix firmware compatibility configuration")
Fixes: bdaf190f8235 ("net/hns3: support link speed autoneg for PF")
Cc: stable@dpdk.org
Signed-off-by: Dongdong Liu <liudongdong3@huawei.com>
23 months agonet/hns3: clean some functions
Dongdong Liu [Fri, 24 Jun 2022 08:59:50 +0000 (16:59 +0800)]
net/hns3: clean some functions

Delete unnecessary code and adjust code to make code more clean.

Signed-off-by: Dongdong Liu <liudongdong3@huawei.com>
23 months agonet/hns3: fix descriptors check with SVE
Chengwen Feng [Fri, 24 Jun 2022 08:59:49 +0000 (16:59 +0800)]
net/hns3: fix descriptors check with SVE

The SVE algorithm and NEON algorithm have the same requirements for
nb-desc, but the nb-desc is verified only when using NEON.

Fixes: fa29fe45a7b4 ("net/hns3: support queue start and stop")
Cc: stable@dpdk.org
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
Signed-off-by: Dongdong Liu <liudongdong3@huawei.com>
23 months agonet/hns3: fix statistics locking
Huisong Li [Fri, 24 Jun 2022 08:59:48 +0000 (16:59 +0800)]
net/hns3: fix statistics locking

The stats_lock is used to protect statistics update in stats APIs and
periodic task, but current code only protect queue related statistics.

Fixes: a65342d9d5d2 ("net/hns3: fix MAC and queues HW statistics overflow")
Cc: stable@dpdk.org
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Dongdong Liu <liudongdong3@huawei.com>
23 months agonet/hns3: fix PTP interrupt logging
Huisong Li [Fri, 24 Jun 2022 08:59:47 +0000 (16:59 +0800)]
net/hns3: fix PTP interrupt logging

PMD driver will receive a PTP interrupt when receive a PTP packet.
But driver doesn't distinguish it. As a result, many unknown events
are printed when many PTP packets are received on the link. The PTP
interrupt is normal, so this patch doesn't log and ignores it.

Fixes: 38b539d96eb6 ("net/hns3: support IEEE 1588 PTP")
Cc: stable@dpdk.org
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Dongdong Liu <liudongdong3@huawei.com>
23 months agonet/hns3: cancel heartbeat alarm when VF reset
Huisong Li [Fri, 24 Jun 2022 08:59:46 +0000 (16:59 +0800)]
net/hns3: cancel heartbeat alarm when VF reset

The purpose of the heartbeat alarm is to keep alive for VF. The mailbox
channel is disabled when VF is reset, and the heartbeat mailbox message
will fail to send. If the reset is not complete, the error information
about the heartbeat sending failure will be printed continuously.
In fact, VF does set alive when VF restore its configuration. So the
heartbeat alarm can be canceled to prepare to start reset and start the
alarm when start service.

Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Dongdong Liu <liudongdong3@huawei.com>
23 months agonet/hns3: support backplane media type
Chengwen Feng [Wed, 22 Jun 2022 03:09:57 +0000 (11:09 +0800)]
net/hns3: support backplane media type

The 802.11 physical PMA sub-layer defines three media: copper, fiber and
backplane. For PMD, the backplane is similar to the fiber, the main
differences are that backplane doesn't have optical module.

Because the interface of firmware fiber is also applicable to the
backplane, this patch supports the backplane only through simple
extension.

Cc: stable@dpdk.org
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
Signed-off-by: Dongdong Liu <liudongdong3@huawei.com>
23 months agonet/hns3: fix link status capability query from VF
Huisong Li [Sat, 11 Jun 2022 07:42:26 +0000 (15:42 +0800)]
net/hns3: fix link status capability query from VF

Currently, the VF LSC capability is obtained from PF driver in
the interrupt mailbox interrupt thread, it is asynchronous.
The VF driver waits for 500ms to get this capability in probe
process.

The primary process will receive a message and do probe in the
interrupt thread context when attach a device in the secondary
process. At this case, VF driver never obtains this capability
from PF.

The root cause is that 'vf->pf_push_lsc_cap' is not updated by
the handling mailbox thread until finishing probe. The reason
this update wouldn't be done is that the handling mailbox interrupt
thread and the probe alarm thread are both in epool thread, and
the probe alarm thread is before the mailbox interrupt thread.

Fixes: 9bc2289fe5ea ("net/hns3: refactor VF LSC event report")
Cc: stable@dpdk.org
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Dongdong Liu <liudongdong3@huawei.com>
23 months agomaintainers: update for hns3
Dongdong Liu [Wed, 22 Jun 2022 10:49:11 +0000 (18:49 +0800)]
maintainers: update for hns3

Lijun Ou and Min Hu currently do not work for the hns3 PMD.
I will do the work, so update the hns3 maintainers.

Signed-off-by: Dongdong Liu <liudongdong3@huawei.com>
Acked-by: Yisen Zhuang <yisen.zhuang@huawei.com>