Ori Kam [Thu, 18 Apr 2019 13:16:01 +0000 (13:16 +0000)]
net/mlx5: support Direct Rules E-Switch
This commit checks the for DR E-Switch support.
The support is based on both Device and Kernel.
This commit also enables the user to manually disable this this feature.
Signed-off-by: Ori Kam <orika@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
Ori Kam [Thu, 18 Apr 2019 13:15:59 +0000 (13:15 +0000)]
net/mlx5: fix translate vport function name
Modify the translate vport function to match other translate items
naming conventions.
Fixes: 0fe3f18f78d8 ("net/mlx5: add source vport match to the ingress rules") Signed-off-by: Ori Kam <orika@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
Ori Kam [Wed, 17 Apr 2019 20:01:45 +0000 (20:01 +0000)]
net/mlx5: fix modify header action position
According to RTE flow the action order should be the order that the
actions were given.
In the case of modify actions the position of the action was always
last.
This commit solves this issue by saving the position of the first modify
action, and then adds to this position the pointer to the modify action.
Fixes: 4bb14c83df95 ("net/mlx5: support modify header using Direct Verbs") Cc: stable@dpdk.org Signed-off-by: Ori Kam <orika@mellanox.com> Acked-by: Shahaf Shuler <shahafs@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
Ori Kam [Sun, 14 Apr 2019 20:17:11 +0000 (20:17 +0000)]
net/mlx5: fix release of jump to queue action
Currently the allocation of the jump to QP is done in flow apply,
this results in memory leak.
This patch fixes this issue by moving the allocation and release of the
jump to QP action to the responsibility of the hrxq.
Fixes: cbb66daa3c85 ("net/mlx5: prepare Direct Verbs for Direct Rule") Cc: stable@dpdk.org Signed-off-by: Ori Kam <orika@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
On BlueField platform we have the new entity - PF representor.
This one represents the PCI PF attached to external host on the
side of ARM. The traffic sent by the external host to the NIC
via PF will be seem by ARM on this PF representor.
This patch refactors port recognizing capability on the base of
physical port name. We have two groups of name formats. Legacy
name formats are supported by kernels before ver 5.0 (being
more precise - before the patch [1]) or before Mellanox OFED 4.6,
and new naming formats added by the patch [1].
Legacy naming formats are supported:
- missing physical port name (no sysfs/netlink key) at all,
master is assumed
- decimal digits (for example "12"), representor is assumed,
the value is the index of attached VF
New naming formats are supported:
- "p" followed by decimal digits, for example "p2", master
is assumed
- "pf" followed by PF index concatenated with "vf" followed by
VF index, for example "pf0vf1", representor is assumed.
If index of VF is "-1" it is a special case of host PF
representor, this representor must be indexed in devargs
as 65535, for example representor=[0-3,65535] will
allow representors for VF0, VF1, VF2, VF3 and for host PF.
Note: do not specify representor=[0-65535], it causes devargs
processing error, because number of ports (rte_eth_dev) is
limited.
Applications should distinguish representors and master devices
exclusively by device flag RTE_ETH_DEV_REPRESENTOR and do not
rely on switch port_id (mlx5 PMD deduces ones from representor_id)
values returned by dev_infos_get() API.
[1] https://www.spinics.net/lists/netdev/msg547007.html
Linux-tree: c12ecc23 (Or Gerlitz 2018-04-25 17:32 +0300)
"net/mlx5e: Move to use common phys port names for vport representors"
mlx4 driver has a global list of Memory Regions created by
device, and there is a ml4_mr_release() routine which makes
a memory cleanup at device closing. The head of device MR list
was fetched outside the rwlock protected section. Also some
noticed typos are fixed.
Fixes: 9797bfcce1c9 ("net/mlx4: add new memory region support") Cc: stable@dpdk.org Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
mlx5 driver has a global list of Memory Regions created by
device, and there is a ml5_mr_release() routine which makes
a memory cleanup at device closing. The head of device MR list
was fetched outside the rwlock protected section. Also some
noticed typos are fixed.
Fixes: 974f1e7ef146 ("net/mlx5: add new memory region support") Cc: stable@dpdk.org Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
When passed to the application, Rx packets retain the port ID value
originally set by slave devices. Unfortunately these IDs have no
meaning to applications, which are typically unaware of their existence.
This confuses those caring about the source port field in mbufs
(m->port) which experience issues ranging from traffic drop to crashes.
Thomas Monjalon [Wed, 17 Apr 2019 22:59:27 +0000 (00:59 +0200)]
ethdev: avoid explicit check of valid port state
Some port iterations are manually checking against RTE_ETH_DEV_UNUSED
instead of using the iterators based on rte_eth_find_next().
A new macro RTE_ETH_FOREACH_VALID_DEV() is introduced, but kept private
because there should be no need of iterating over all devices in the
API. The public iterators have additional filters for ownership, parent
device or sibling ports.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Thomas Monjalon [Wed, 17 Apr 2019 00:36:27 +0000 (02:36 +0200)]
ethdev: deprecate legacy filter API
As stated in the deprecation notice from December 2016,
"the legacy filter API, including rte_eth_dev_filter_supported(),
rte_eth_dev_filter_ctrl() as well as filter types MACVLAN, ETHERTYPE,
FLEXIBLE, SYN, NTUPLE, TUNNEL, FDIR, HASH and L2_TUNNEL, is superseded
by the generic flow API (rte_flow)".
After a long wait of more than two years, the legacy filter API
is marked as deprecated, while still tested with testpmd and
the tep_termination example.
The next step will be to announce a deadline for complete removal.
As preparation of the removal of rte_eth_ctrl.h,
RTE_ETH_FLOW_*, RTE_TUNNEL_TYPE_* and RTE_ETH_HASH_FUNCTION_* definitions
are moved to rte_ethdev.h and rte_flow.h.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Shahaf Shuler <shahafs@mellanox.com> Acked-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Pavel Belous [Thu, 18 Apr 2019 11:39:57 +0000 (11:39 +0000)]
net/atlantic: configure MACsec from interrupt handler
MACSEC should be configured only after link up event, thus we use
link interrupt to file an alarm for configuration.
FW also uses link interrupt line to indicate incoming events from
MACSEC. These may include key expiration, packet counter wrap, etc.
We pass these events to the upper layers.
Signed-off-by: Pavel Belous <pavel.belous@aquantia.com> Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Pavel Belous [Thu, 18 Apr 2019 11:39:55 +0000 (11:39 +0000)]
net/atlantic: implement MACsec firmware interface
Implementation of firmware interface for MACsec configuration.
Structure with config data is written into FW memory, then we trigger
FW to execute the request and wait for result.
Signed-off-by: Pavel Belous <pavel.belous@aquantia.com> Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Pavel Belous [Thu, 18 Apr 2019 11:39:51 +0000 (11:39 +0000)]
net/atlantic: enable MACsec configuration
These are driver MACsec configuration routines.
They fill in config structures and prepare these
to be send to FW. Actual configuration will happen in
link interrupt handler.
We declare MACsec offload bits in DPDK offload capabilities
and provide external experimental MACsec API wrappers.
Also update documentation with feature matrix for the
enabled feature.
Signed-off-by: Pavel Belous <pavel.belous@aquantia.com> Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Pavel Belous [Thu, 18 Apr 2019 11:39:48 +0000 (11:39 +0000)]
net/atlantic: declare MACsec hardware structures
Here we define hardware and software configuration structures
for MACsec interface. MACSEC itself is implemented in Phy module,
but its configuration is done via firmware interface
Signed-off-by: Pavel Belous <pavel.belous@aquantia.com> Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
When launch testpmd with VF and quit testpmd, there'll
be lots of messages "i40evf_handle_aq_msg(): Request 0
is not supported yet", which are triggered during VF
reset and VF needn't do anything. So cancel alarm handler
before VF reset to ignore the admin queue messages.
Fixes: e0e6a7f2154e ("net/i40e: cancel alarm handler at the end of closure") Cc: stable@dpdk.org Signed-off-by: Beilei Xing <beilei.xing@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Enable CLEARPBA bit is required by ice NIC of A0/A1 version to
enable Tx and Rx queue interrupt.
Also enable CLEARPBA bit does no impact on IAVF behaviour when be
hosted by other devices, so we can make it as default.
Xiaolong Ye [Wed, 17 Apr 2019 13:49:45 +0000 (21:49 +0800)]
net/af_xdp: make reserve/submit peek/release consistent
As David pointed out, if we reserve N slots for Tx, but only submit n
slots, we would end up with an incorrect opinion of the number of available
slots later, we also would get wrong idx when we call
xsk_ring_prod__reserve next time. It also applies to
xsk_ring_cons__peek()/xsk_ring_cons__release().
This patch ensures that both reserve/submit and peek/release are
consistent.
Fixes: f1debd77efaf ("net/af_xdp: introduce AF_XDP PMD") Suggested-by: David Marchand <david.marchand@redhat.com> Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com> Reviewed-by: David Marchand <david.marchand@redhat.com>
Xiaolong Ye [Wed, 17 Apr 2019 13:49:44 +0000 (21:49 +0800)]
net/af_xdp: specify minimal and maximal MTU
Properly report mtu capability in port device info.
Reported-by: David Marchand <david.marchand@redhat.com> Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com> Reviewed-by: David Marchand <david.marchand@redhat.com>
vhost: fix silent queue enabling with legacy guests
vhost should notify the application in case of all vring state changes.
In general, application should not care about negotiation of
VHOST_USER_F_PROTOCOL_FEATURES. Protocol details like this should
be hidden by the vhost library.
With this patch applications like OVS will be able to assume that
all vrings disabled by default and only process 'vring_state_changed'
events.
Fixes: 321203a54ba7 ("vhost: enable rings at the right time") Cc: stable@dpdk.org Signed-off-by: Ilya Maximets <i.maximets@samsung.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
vhost: fix passing destroyed device to destroy callback
Application should be able to obtain information like 'ifname' from
the 'vid' passed to 'destroy_connection' callback. Currently, all the
API calls with passed 'vid' fails with 'device not found'.
Fixes: efba12a78ddf ("vhost: add user callbacks for socket open/close") Cc: stable@dpdk.org Signed-off-by: Ilya Maximets <i.maximets@samsung.com> Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
The function rte_vlan_insert may allocate a new buffer for the
vlan header and return a different mbuf than originally passed.
In this case, the stored mbuf in txm[] array could point to wrong
buffer.
Fixes: dd856dfcb9e7 ("virtio: use any layout on Tx") Cc: stable@dpdk.org Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Reviewed-by: Jens Freimann <jfreimann@redhat.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Ying A Wang [Wed, 17 Apr 2019 01:47:52 +0000 (09:47 +0800)]
net/ice: fix promiscuous mode
When device promiscuous mode has already been enabled,
should not return error if user re-enable it.
Fixes: c945e4bf9063 ("net/ice: support promiscuous mode") Cc: stable@dpdk.org Signed-off-by: Ying A Wang <ying.a.wang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
Ying A Wang [Wed, 17 Apr 2019 01:47:51 +0000 (09:47 +0800)]
net/ice: fix variable storage type
Variable "status" should be defined as "enum ice_status"
instead of "uint16_t". This patch fixes the issue.
Fixes: c945e4bf9063 ("net/ice: support promiscuous mode") Cc: stable@dpdk.org Signed-off-by: Ying A Wang <ying.a.wang@intel.com> Acked-by: Qiming Yang <qiming.yang@intel.com>
At port detach routine after calling the rte_dev_remove()
testpmd performs some cleanup, checking the statuses of
remaining ports and closes the appropriate ones. The port
scanning is based on the new sibling iterator which uses the
invalid (already closed) port for reference. This patch
replaces the foreach iterator and uses the device object for
reference. It is worth to note this cleanup is not needed
for some drivers (at least for mlx5 and probably for others)
and is preserved due to possible compatibility issues.
Fixes: 13302cd5bd63 ("app/testpmd: use port sibling iterator in device cleanup") Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com> Acked-by: Thomas Monjalon <thomas@monjalon.net>
Xiao Wang [Mon, 15 Apr 2019 07:56:25 +0000 (15:56 +0800)]
net/ifc: fix used ring update
The vring relay thread is created after HW datapath start and is
canceled before HW datapath stop, so we need to take care of the
ring update when the relay thread is not on duty.
Fixes: 4bb531e152d3 ("net/ifc: support SW assisted VDPA live migration") Cc: stable@dpdk.org Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
Xiao Wang [Mon, 15 Apr 2019 07:56:23 +0000 (15:56 +0800)]
net/ifc: do not relay for Tx queue
Relay for Tx queue doesn't provide any benefit, since the packet buffer
in Tx queue is read-only, there's no dirty page logging for Tx buffer.
This change further reduces CPU usage and improves throughput.
Andrew Rybchenko [Fri, 12 Apr 2019 13:12:33 +0000 (14:12 +0100)]
app/testpmd: set fixed flag for exact link speed
Setting exact link speed makes sense if auto-negotiation is
disabled. Fixed flag is required to disable auto-negotiation.
Fixes: 88fbedcd5e5a ("app/testpmd: move speed and duplex parsing in a function") Cc: stable@dpdk.org Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
There is two eth group devices in PAC N3000 card,
each eth group include PHY device and MAC device. Exposing
APIs for DPDK PMD driver to access those devices.
1. Add Altera I2C master device driver
2. Add at24 eeprom driver which is i2c slave device
3. Introducing a new ops for opae_manager: opae_manager_networking_ops.
This ops will include some networking operation by FPGA, like vBNG
operation, MAC ROM operation and so on.
raw/ifpga/base: store private features in FME and port
Get private features attribute like size, id, address after
enumeration, and insert into FEM or Port dedicate list.
when initial the private feature driver, we just compare the
private feature id between the list and feature drivers array
to match the proper drivers.
This patch avoid the hardcore in feature_info array in previous
implementation. and the same time we can use one driver for mulitple
devices which the id is the same.
AFU can be implemented into many different acceleration
devices, these devices need shared data to store private
information when they are handled by users.
Signed-off-by: Rosen Xu <rosen.xu@intel.com> Signed-off-by: Andy Pei <andy.pei@intel.com>
Enable the optic module vendor and part number verification from driver
by setting appropriate flags. Link handling module in conjunction with
FW performs optic module verification.
Without this fix the SFP is powered down and the link doesn't come up,
if module verification is enforced in nvram setting.
The periodic callout function and the interrupt handler both modify the
periodic flags. There is a possible race condition when an application
is going through dev_stop()/dev_start() and an interrupt handler is
invoked. We also need to ensure that periodic polling is not invoked in
interrupt context.
This patch handles such case by using separate variable to check for
interrupt context. Also, atomically load and store the periodic flag
value.
Fixes: 0f6ebeee2402 ("net/bnx2x: fix call to link handling periodic function") Cc: stable@dpdk.org Signed-off-by: Rasesh Mody <rmody@marvell.com>
In some cases, DPDK application may send packets
while PMD is going through load or unload flow.
This causes firmware to access invalid/unallocated
memory to process transmit buffer. Which results in
error on PCI bus and chip further blocks access to host,
causing a DMAE timeout.
Fix this issue by installing dummy empty transmit and receive
handlers at the beginning of unload path (rte_eth_dev_stop())
and install actual transmit and receive handlers after successful
load of the PMD port (rte_eth_dev_start()). This way, application
won't be able to send packets while device is going through
load/unload flow.
There is a race condition while processing RAMROD
completion in fast path queue through interrupt handler
and polling method.
Interrupt handler invoked from actual interrupt event
and from RAMROD processing polling flow may create a
situation where one flow will read and clear a fastpath
interrupt without actually processing the RAMROD completion.
Thus, causing a RAMROD timeout even though HW sent an
completion event.
Fix this by introducing an atomic variable which will be
set only when interrupt handler needs to process RAMROD
completion.
Bruce Richardson [Fri, 19 Apr 2019 12:04:49 +0000 (13:04 +0100)]
devtools: fix meson build test for plain bourne shell
The pipefail option is not supported in /bin/sh, just in bash/ksh and
similar shells - which means it's there by default on most Linux distros
but not on e.g. FreeBSD. Therefore we check for it's presence before
setting the option, and if it's missing, we upgrade verbosity level if
needed to ensure we never hide any build failures.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
app/test/test_compressdev.c:1949:11: note:
previous definition of 'i' was here
app/test/test_compressdev.c:1992:2: error:
'for' loop initial declarations are only allowed in C99 mode
app/test/test_compressdev.c:1992:2: note:
use option -std=c99 or -std=gnu99 to compile your code
app/test/test_compressdev.c:1996:19: warning:
assignment from incompatible pointer type [enabled by default]
Fixes: 355b02eedc65 ("test/compress: add max mbuf size test case") Signed-off-by: Tomasz Jozwiak <tomaszx.jozwiak@intel.com> Signed-off-by: Fiona Trahe <fiona.trahe@intel.com>
Build error seen with Linux kernel 5.1 and
when CONFIG_RTE_KNI_KMOD_ETHTOOL is enabled.
Build error:
kernel/linux/kni/igb_main.c:2352:18:
error: initialization of ... from incompatible pointer type ...
[-Werror=incompatible-pointer-types]
.ndo_fdb_add = igb_ndo_fdb_add,
^~~~~~~~~~~~~~~
ndo_fdb_add() is changed in Linux kernel version 5.1 and now requires
a new parameter, 'struct netlink_ext_ack *extack':
Linux Commit 87b0984ebfab ("net: Add extack argument to ndo_fdb_add()")
ndo_fdb_add() parameter updated with compile time Linux kernel version
check.
Added crypto_dequeue_burst() function to call
rte_crypto_dequeue_burst() in a loop with a
delay to ensure that all the packets are
dequeued from the crypto device.
Fixes: 59d7353b0df0 ("test/ipsec: fix test suite setup") Cc: stable@dpdk.org Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com> Acked-by: Fiona Trahe <fiona.trahe@intel.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
The socket_id is used as an array index so should be within the range
of zero to max numa nodes. Add a range check to ensure we don't get
excessive values.
Coverity issue: 336812
Coverity issue: 336829 Fixes: 2c59bd32b70d ("cryptodev: do not create session mempool internally") CC: stable@dpdk.org Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Fan Zhang <roy.fan.zhang@intel.com> Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
crypto/caam_jr: fix memory leak and illegal access
Opendir() returns allocated storage which must be freed at the
end of function or in case any return on error. so freeing the
allocation using closedir in an error case.
Marko Kovacevic [Mon, 15 Apr 2019 15:04:48 +0000 (16:04 +0100)]
examples/fips_validation: fix CMAC test
As a result of the cmac test running the test where
PT len is 65536 it should give a result back to the
user USER1: Error -1: Prepare op USER1: PT len 65536
as this MSG len is not supported. Issue was
that the application was not freeing the op properly after
a while causing the app to fail.
CRYPTODEV: rte_cryptodev_sym_session_create() line 1340:
couldn't get object from session mempool
USER1: Error -12: test block
USER1: Error -12: Failed test CMAC/req/CMAC.req
Fixes: cd255ccf5764 ("examples/fips_validation: support AES parsing") Cc: stable@dpdk.org Signed-off-by: Marko Kovacevic <marko.kovacevic@intel.com>
Marko Kovacevic [Mon, 15 Apr 2019 15:04:47 +0000 (16:04 +0100)]
examples/fips_validation: fix HMAC test
Application was failing as the HMAC and
Plain SHA fips request files are similar in a
way that they both have SHA- in the top section to
determine the hash algo and hash sizes. And HMAC having the
algo in the second line but the Plain SHA in the third
meant that when the HMAC files was used once it parsed the third
line Plain SHA was set as the algo and not HMAC.
USER1: Failed to get capability for cdev 0
USER1: Error -22: test block
[L=20 SHAAlg=SHA_2]
USER1: Error -22: Failed test /root/FIPS/HMAC/req/HMAC.req
Fixes: f4797bae0050 ("examples/fips_validation: support plain SHA") Signed-off-by: Marko Kovacevic <marko.kovacevic@intel.com>
Current default cache line size for armv8 CPUs having Implementor ID of
0x41 is 128 bytes, changing it to 64 bytes. Also, the max number of lcores
is changed to 16 from 256.
git.droids-corp.org / dpdk.git / log