There was an error at rte_constant_bswap64 while compiling
with big endian toolchain. so fixing it by adding type cast.
Also, rte_pktmbuf_alloc API should be used to allocate mbuf
instead of rte_pktmbuf_raw_alloc to avoid use of stale mbuf
information.
Fixes: 469c6111a7 ("net/enetc: enable Rx and Tx")
Cc: stable@dpdk.org
Suggested-by: Thomas Monjalon <thomas@monjalon.net>
Signed-off-by: Gagandeep Singh <g.singh@nxp.com>
First configure ring with BDs properly then enable
the ring.
Fixes: 469c6111a7 ("net/enetc: enable Rx and Tx")
Cc: stable@dpdk.org
Signed-off-by: Gagandeep Singh <g.singh@nxp.com>
The RSS validation function was missing the verifcation that
if RSS is requested on inner packet, the flow must have tunnel data.
Fixes: 23c1d42c71 ("net/mlx5: split flow validation to dedicated function")
Cc: stable@dpdk.org
Signed-off-by: Ori Kam <orika@mellanox.com>
Acked-by: Yongseok Koh <yskoh@mellanox.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.
Fixes: 540a211084 ("bnx2x: driver core")
Cc: stable@dpdk.org
Signed-off-by: Rasesh Mody <rmody@marvell.com>
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: 0f6ebeee24 ("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.
Fixes: 540a211084 ("bnx2x: driver core")
Cc: stable@dpdk.org
Signed-off-by: Shahed Shaikh <shshaikh@marvell.com>
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.
Fixes: 540a211084 ("bnx2x: driver core")
Cc: stable@dpdk.org
Signed-off-by: Shahed Shaikh <shshaikh@marvell.com>
We allocate DMA memory but never free after using it.
Add function to free DMA memory.
Fixes: b5bf771922 ("bnx2x: driver support routines")
Cc: stable@dpdk.org
Signed-off-by: Shahed Shaikh <shshaikh@marvell.com>
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.
Coverity issue: 323507
Coverity issue: 325880
Fixes: e7a45f3cc2 ("crypto/caam_jr: add UIO specific operations")
Cc: stable@dpdk.org
Signed-off-by: Gagandeep Singh <g.singh@nxp.com>
Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
CAAM return wrong digest value in AUTH only sg test case
because digest calculated on wrong length of data
Fixes: 71dd6b9d44 ("crypto/caam_jr: add scatter gather")
Cc: stable@dpdk.org
Signed-off-by: Gagandeep Singh <g.singh@nxp.com>
Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
build a shared descriptor accordingly if core and
CAAM endianness is same or different
Fixes: 6ef6beca88 ("crypto/caam_jr: add enqueue/dequeue operations")
Cc: stable@dpdk.org
Signed-off-by: Gagandeep Singh <g.singh@nxp.com>
Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
IPSec Multi-buffer library has recently added API
that sets pointers depending on the architecture, at initiliazation,
in version 0.52.
AESNI MB PMD was updated with these changes, but not
the AESNI GCM PMD, which also uses the same library.
This makes the PMD to be only compatible with version 0.52,
but makes both PMD consistent on version compatibility,
plus adds support for AVX512.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
If MLNX_OFED is installed, there's no .pc file installed for libraries and
dependency() can't find libraries by pkg-config. By adding fallback of
using cc.find_library(), libraries are properly located.
Fixes: e30b4e566f ("build: improve dependency handling")
Cc: stable@dpdk.org
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Acked-by: Luca Boccassi <bluca@debian.org>
Disable octeontx for gcc 4.8.5 as compiler is emitting "internal compiler
error" for aarch64
Fixes: bd77f2d64c ("event/octeontx: build with meson")
Fixes: 4f760550a0 ("mk: disable OcteonTx for buggy compilers")
Fixes: f3af3e44a4 ("mk: disable OcteonTx for buggy compilers only on arm64")
Cc: stable@dpdk.org
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Define variables for "is_linux", "is_freebsd" and "is_windows"
to make the code shorter for comparisons and more readable.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
Acked-by: Luca Boccassi <bluca@debian.org>
This patch stopped LLDP by default to avoid the statistics error.
Signed-off-by: Qiming Yang <qiming.yang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
No need to add additional vlan tag size for max packet size, since
for i40e, the queue's Rx Max Frame Size (rxq->max_pkt_len) already
includes the vlan header size.
Fixes: a3c83a2527 ("net/i40e: enable runtime queue setup")
Fixes: 4861cde461 ("i40e: new poll mode driver")
Fixes: c1715402df ("i40evf: fix jumbo frame support")
Cc: stable@dpdk.org
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
The result of the endian conversion was not being used incorrectly.
Fixes: b11cceb83a ("net/bnxt: support timesync")
Cc: stable@dpdk.org
Reported-by: Thomas Monjalon <thomas@monjalon.net>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
The vlan pattern handler currently assumes the NIC always strips vlan
header from the L2 buffer, regardless of the vlan strip setting. But,
with older VIC models, the vlan header is actually present in the L2
buffer if stripping is disabled. So in this case, the inner ether type
needs to be shifted by that much.
Fixes: 6ced137607 ("net/enic: flow API for NICs with advanced filters enabled")
Cc: stable@dpdk.org
Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>
Currently, the raw item is always preceded by a UDP header, and both
land in the L4 pattern buffer. So consider the UDP header size when
checking if the raw spec fits in the L4 buffer.
Coverity issue: 336796, 336850
Fixes: 477959e6ee ("net/enic: enable limited support for raw flow item")
Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>
UAR (User Access Region) register does not need to be remapped for
primary process but it should be remapped only for secondary process.
UAR register table is in the process private structure in
rte_eth_devices[],
(struct mlx4_proc_priv *)rte_eth_devices[port_id].process_private
The actual UAR table follows the data structure and the table is used
for both Tx and Rx.
For Tx, BlueFlame in UAR is used to ring the doorbell.
MLX4_TX_BFREG(txq) is defined to get a register for the txq. Processes
access its own private data to acquire the register from the UAR table.
For Rx, the doorbell in UAR is required in arming CQ event. However, it
is a known issue that the register isn't remapped for secondary process.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
UAR (User Access Region) register does not need to be remapped for
primary process but it should be remapped only for secondary process.
UAR register table is in the process private structure in
rte_eth_devices[],
(struct mlx5_proc_priv *)rte_eth_devices[port_id].process_private
The actual UAR table follows the data structure and the table is used
for both Tx and Rx.
For Tx, BlueFlame in UAR is used to ring the doorbell.
MLX5_TX_BFREG(txq) is defined to get a register for the txq. Processes
access its own private data to acquire the register from the UAR table.
For Rx, the doorbell in UAR is required in arming CQ event. However, it
is a known issue that the register isn't remapped for secondary process.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Queue index is redundantly stored for both Rx and Tx structures.
E.g. txq_ctrl->idx and txq->stats.idx. Both are consolidated to single
storage - rxq->idx and txq->idx.
Also, rxq and txq are moved to the beginning of its control structure
(rxq_ctrl and txq_ctrl) for cacheline alignment.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
Max frame size setup should consider double VLAN case.
Fixes: ae2bdd0219 ("net/ice: support MTU setting")
Cc: stable@dpdk.org
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
If rdma-core library doesn't support remapping UAR registers, the register
shouldn't be unmapped on device stop.
Fixes: 0203d33a10 ("net/mlx4: support secondary process")
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
In case of cross compilation on aarch64 we must add include for
stdlib in order to use the free function.
Fixes: cbb66daa3c ("net/mlx5: prepare Direct Verbs for Direct Rule")
Signed-off-by: Ori Kam <orika@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
Call to CPP read (nfp_cpp_readl()) can fail, return 0 on fail.
If the call to _nfp6000_cppat_mu_locality fails, the function needs
to return with an error.
If the nfp_cpp_readl() call fails just returns 0.
Coverity issue: 277209, 277215, 277225
Fixes: c7e9729da6 ("net/nfp: support CPP")
Cc: stable@dpdk.org
Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
Although it is rather unlikely getting 0 as the descriptor handle, better
to contemplate that possibility.
Coverity issue: 195018
Fixes: 896c265ef9 ("net/nfp: use new CPP interface")
Cc: stable@dpdk.org
Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
The boolean value was assigned to Tx flag twice, so it could cause bug
whenever Rx checksum will not be supported and Tx will be.
Coverity issue: 336831
Fixes: 117ba4a604 ("net/ena: get device info statically")
Signed-off-by: Michal Krawczyk <mk@semihalf.com>
At the mlx5 device closing the shared IB context was destroyed
before cleanup routines completion. As it was found on some
setups (Netlink fails with old kernel drivers and we have to use
sysfs to retrieve interface index, this requires IB device name,
which is stored in shared context) the mlx5_nl_mac_addr_flush()
requires IB device name, and if shared context is removed it
causes the segmentation fault.
Fixes: 17e19bc4dd ("net/mlx5: add IB shared context alloc/free functions")
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
Retrieving network interface index via Netlink fails in
case of old ib_core kernel driver installed - mlx5_nl_ifindex()
routine fails due to RDMA_NLDEV_ATTR_NDEV_INDEX attribute is not
supported by the old driver.
The patch allowing to retrieve the network interface index and
name via Netlink [1]. So, the problem depends on ib_core module
version - 4.16 supports getting ifindex via Netlink, 4.15 does not.
This error was ignored in previous versions of MLX5 PMD probing
routine. For single device ifindex was retrieved via sysfs
and link control was not lost, so problem just was not noticed.
In order to support MLX5 PMD functioning over old kernel driver
this patch adds ifindex retrieving via sysfs into probing routine.
It is worth to note this method works for master/standalone
device only.
[1] https://www.spinics.net/lists/linux-rdma/msg62948.html
Linux tree: 5b2cc79d (Leon Romanovsky 2018-03-27 20:40:49 +0300 270)
Fixes: ad74bc6195 ("net/mlx5: support multiport IB device during probing")
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
This patch implements the changes proposed in the deprecation
note[1]. Replace multiple color definitions in various places such as
rte_meter.h, rte_tm.h and rte_mtr.h with single rte_color defined
in rte_meter.h.
This is simple search and replace exercise without any implementation
change.
[1] https://mails.dpdk.org/archives/dev/2019-January/123861.html
Signed-off-by: Jasvinder Singh <jasvinder.singh@intel.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Rx refill in one bulk (which is just 8 descriptors) by default is too
aggressive and makes too many MMIO writes (Rx doorbells) if packet rate
is high. Setting default to 1/8 of Rx descriptors number shows good
performance results. Anyway it is a default value which may be
overridden by Rx configuration provided by application.
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Add new protocol type VXLAN-GPE support for UDP tunnel.
inner IP/TCP/UDP checksum and RSS configuration shared
the same implementation of VXLAN.
Signed-off-by: Qiming Yang <qiming.yang@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Currently, if requested MTU is bigger than mbuf size and scattered
receive is not enabled, setting MTU to that value fails.
This patch allows setting this special MTU when device is stopped,
because scattered_rx will be re-configured during next port start
and driver may enable scattered receive according new MTU value.
After this patch, driver may select different receive function
automatically after MTU set, according MTU values selected.
Signed-off-by: David Harton <dharton@cisco.com>
Reviewed-by: Wei Zhao <wei.zhao1@intel.com>
The driver must send its version information to the firmware, so
the firmware knows the driver is up. Otherwise, it will cause unexpected
OS package downloading when multiple driver instances running on the
same device.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
