David Marchand [Fri, 25 Oct 2019 13:56:06 +0000 (15:56 +0200)]
log: add log stream accessor
Define an accessor so that users can write their debug message to the
same stream than the rte_log infrastructure.
Use it in the qat infrastructure.
Signed-off-by: David Marchand <david.marchand@redhat.com> Acked-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Kevin Traynor <ktraynor@redhat.com>
David Marchand [Fri, 25 Oct 2019 13:56:04 +0000 (15:56 +0200)]
net/bonding: use non deprecated PCI API
rte_eal_compare_pci_addr has been deprecated since v17.11.
Convert to rte_pci_addr_cmp.
Fixes: c848b518bbc7 ("net/bonding: support bifurcated driver in eal") Cc: stable@dpdk.org Signed-off-by: David Marchand <david.marchand@redhat.com> Acked-by: Thomas Monjalon <thomas@monjalon.net>
Ciara Power [Fri, 25 Oct 2019 09:56:08 +0000 (10:56 +0100)]
examples/load_balancer: remove example
This example can be removed because DPDK now has a range
of libraries, especially rte_eventdev, that did not exist
previously for load balancing, making this less relevant.
Also, modern NIC cards have greater ability to do load balancing,
e.g. using RSS, over a wider range of fields than earlier cards did.
Signed-off-by: Ciara Power <ciara.power@intel.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Ciara Power [Fri, 25 Oct 2019 09:56:06 +0000 (10:56 +0100)]
examples/quota-watermark: remove example
Original DPDK rings code had explicit support for a
single watermark per-ring, but more recent releases of
DPDK had a more general mechanism where each enqueue
or dequeue call could return the remaining elements/free-slots
in the ring.
Therefore, this example is not as relevant as before and can be removed.
Signed-off-by: Ciara Power <ciara.power@intel.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Chunsong Feng [Fri, 25 Oct 2019 12:37:05 +0000 (20:37 +0800)]
net/hns3: fix FLR reset
PF FLR resets the PCIe ECAM space of all VFs under the PF
and does not automatically recover. Therefore, the VF driver
needs to restore the ECAM configuration, including
bus_master_en, msix_enable to avoid FLR reset failure.
Fixes: 2790c6464725 ("net/hns3: support device reset") Signed-off-by: Chunsong Feng <fengchunsong@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Hongbo Zheng [Fri, 25 Oct 2019 12:37:04 +0000 (20:37 +0800)]
net/hns3: fix error code for firmware timeout
Configuration commands are sent to firmware for processing.
When firmware processing timeout, the corresponding error
code is returned. Considering that it is more reasonable to
use error code -ETIME for timeout error, the error code for
processing timeout is changed from -EBADE to -ETIME.
Fixes: 737f30e1c3ab ("net/hns3: support command interface with firmware") Signed-off-by: Hongbo Zheng <zhenghongbo3@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Wei Hu (Xavier) [Fri, 25 Oct 2019 12:37:03 +0000 (20:37 +0800)]
net/hns3: fix offload flag for RSS hash
This patch adds PKT_RX_RSS_HASH flag to rx packet's ol_flags
to repair the bug that hns3 pmd driver doesn't set
PKT_RX_RSS_HASH flag. In hns3 network engine RSS is always
enabled.
Fixes: bba636698316 ("net/hns3: support Rx/Tx and related operations") Signed-off-by: Hao Chen <chenhao164@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Hao Chen [Fri, 25 Oct 2019 12:37:02 +0000 (20:37 +0800)]
net/hns3: fix statistics
This patch fixes the statistics problems for sending and receiving
message as belows:
1.In receiving direction, for FCS error messages, drivers should not
record them in rte_eth_stats.ipackets statistics.
2.In sending direction, for messages of illegal length, too long or
equals 0, drivers should not notify the network card hardware to
send them, should not continue to send the remaining message in burst,
and record them in rte_eth_stats.opackets statistics.
Fixes: 8839c5e202f3 ("net/hns3: support device stats") Signed-off-by: Hao Chen <chenhao164@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Andrew Rybchenko [Thu, 24 Oct 2019 17:46:09 +0000 (18:46 +0100)]
net/virtio: fix Tx checksum offloads
Missing parenthesis around expression before type cast to struct
virtio_net_hdr pointer makes the arithmetic to be in
sizeof(struct virtio_net_hdr) units.
Use rte_pktmbuf_mtod_offset() to fix the problem.
Type of head_size is changed to signed since some compilers bark
on unary minus applied to unsigned.
Fixes: 1ae55ad38e5e ("net/virtio: fix mbuf data and packet length mismatch") Cc: stable@dpdk.org Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Tiwei Bie <tiwei.bie@intel.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Venkat Duvvuru [Thu, 24 Oct 2019 07:44:32 +0000 (13:14 +0530)]
net/bnxt: uninit locks during resource cleanup
Currently, bnxt_uninit_locks is called inside bnxt_dev_uninit. However,
the more appropriate place to call it is inside bnxt_uninit_resources.
This is more logical, as all the resources uninitialization is happening
inside bnxt_uninit_resources.
Kalesh AP [Thu, 24 Oct 2019 07:44:31 +0000 (13:14 +0530)]
net/bnxt: fix memory leak
During hot fw upgrade or error recovery, driver does cleanup and
reallocation of resources. But driver reallocates memory for ring
group info table without freeing the allocated memory during
device init.
Fix this memory leak by moving the freeing of ring group info table
to bnxt_free_mem() in bnxt_uninit_resources().
Kalesh AP [Thu, 24 Oct 2019 07:44:28 +0000 (13:14 +0530)]
net/bnxt: add more checks during firmware reset
Added check for fw reset or fw errors in few more routines.
While processing the events, if it is fw fatal or non-fatal
event, there is no need to process the remaining events as
driver triggers recovery mechanism.
Also added a check for fw reset or fatal error in bnxt_disable_int()
to avoid bar access in case of fatal error.
net/bnxt: fix crash after removing and adding slaves
On removing the slave interface, slave_remove in bonding module calls
_rte_eth_dev_reset which in turn frees both Tx and Rx queues.
1. segfault is seen after removing/adding the slave interface and starting
bond interface.
In this below path, when mtu is set for the slave interface, queues are
not created yet and driver reference to queue[0] causes the segfault.
slave_configure:
rte_eth_dev_set_mtu
rte_eth_dev_configure
rte_eth_rx_queue_setup
2. segfault is seen on starting the port after removing from bond device.
This is a testpmd bug where in, on starting the port, testpmd is supposed
to recreate the queues before starting the port.
Fixed these by adding check for queues created before accessing them.
Kalesh AP [Thu, 24 Oct 2019 07:44:23 +0000 (13:14 +0530)]
net/bnxt: fix race between start and interrupt handler
During port start, driver enables interrupts. At the end of port start
driver schedules the alarm for fw health check. This can cause race
between interrupt handler and schedule fw health check alarm thread
which falsely detects FW error.
Fixes: 9d0cbaecc91a ("net/bnxt: support periodic FW health monitoring") Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com> Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com> Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Venkat Duvvuru [Thu, 24 Oct 2019 07:44:22 +0000 (13:14 +0530)]
net/bnxt: fix default MAC check
bnxt_set_hwrm_vnic_filters programs default mac addr and the
same default mac is added by mac_add_addr_op routine as well.
This redundant mac add is avoided by checking if the default
mac is already added.
However, that check is wrong. The check should consider the
mac index as well to determine the default mac. This patch
fixes it by using mac index to determine the default mac.
net/bnxt: fix RSS configuration for Thor controller
rss_table structure stores receive, completion ring IDs for Thor based
controllers and receive queue id for others. Below commit accidentally
left the old code and hence was always overwriting receive ring id with
queue id for Thor. This causes subsequent VNIC_RSS_CFG command to fail.
Ajit Khaparde [Thu, 24 Oct 2019 07:44:19 +0000 (13:14 +0530)]
net/bnxt: fix writing MTU to FW
We are currently writing the MAX supported MTU size even though
the MTU passed by the application is a different value.
Configure the application specified MTU instead.
Fixes: b7778e8a1c00 ("net/bnxt: refactor to properly allocate resources for PF/VF") Cc: stable@dpdk.org Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com> Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Driver was setting maximum receive unit differently in bnxt_mtu_set_op
and bnxt_hwrm_vnic_alloc. Moreover firmware adds the 4 bytes for FCS.
Fixed it by setting correct maximum receive unit value.
Peng Huang [Thu, 24 Oct 2019 09:37:34 +0000 (09:37 +0000)]
app/testpmd: fix Tx checksum when TSO enabled
This patch fixed the TX checksum value problem when enabled TSO in
tunnel packets, because outer UDP checksum calculation depend on
the TSO configuration.
Fixes: 0f62d63593ed ("app/testpmd: support tunneled TSO in checksum engine") Cc: stable@dpdk.org Signed-off-by: Peng Huang <peng.huang@intel.com> Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Raslan Darawsheh [Wed, 23 Oct 2019 11:31:45 +0000 (11:31 +0000)]
net/mlx: fix debug build with icc
Trying to compile mlx5 pmd in debug mode with icc
will lead to compilation failures due to the fact that
icc doesn't have support for the pragma of pedantic.
Flavio Leitner [Thu, 24 Oct 2019 16:29:19 +0000 (13:29 -0300)]
vhost: fix IPv4 checksum
Currently the IPv4 header checksum is calculated including its
current value, which can be a valid checksum or just garbage.
In any case, if the original value is not zero, then the result
is always wrong.
The IPv4 checksum is defined in RFC791, page 14 says:
Header Checksum: 16 bits
The checksum algorithm is:
The checksum field is the 16 bit one's complement of the one's
complement sum of all 16 bit words in the header. For purposes of
computing the checksum, the value of the checksum field is zero.
Thus force the csum field to always be zero.
Fixes: b08b8cfeb2ae ("vhost: fix IP checksum") Cc: stable@dpdk.org Signed-off-by: Flavio Leitner <fbl@sysclose.org> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Jin Yu [Thu, 24 Oct 2019 10:21:59 +0000 (18:21 +0800)]
examples: delete vhost SCSI example
This example is too old and SPDK will not maintain this example
anymore. Also SPDK has submitted a new vhost example vhost-blk.
We will keep on maintaining vhost-blk and It shows the packed
ring and live recovery support.
Signed-off-by: Jin Yu <jin.yu@intel.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
This driver supports none of DCB, RSS or VMDQ modes, therefore must
check and return error if configured incorrectly.
Virtio can distribute Rx packets across multi-queue, but there is
no controls (algorithm, redirection table, hash function) except
number of Rx queues and ETH_MQ_RX_NONE is the best fit meaning
no method is enforced on how to route packets to MQs.
Fixes: c1f86306a026 ("virtio: add new driver") Cc: stable@dpdk.org Signed-off-by: Dilshod Urazov <dilshod.urazov@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Ilya Maximets [Thu, 17 Oct 2019 15:00:19 +0000 (17:00 +0200)]
vhost: disable host TSO for linear buffers without extbuf
If linear buffers requested and external buffers are not, vhost
will not be able to receive any buffer that doesn't fit in a
single mbuf. Moreover, if such a buffer will appear in a vring
it will never be dequeued and the whole vring will become dead
breaking the network connection.
Disable segmentation offloading from the host side to avoid
having such a big buffers.
Fixes: c3ff0ac70acb ("vhost: improve performance by supporting large buffer") Signed-off-by: Ilya Maximets <i.maximets@ovn.org> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Ilya Maximets [Wed, 16 Oct 2019 14:31:07 +0000 (16:31 +0200)]
vhost: return error message for mbuf allocation failure
mbuf allocation failure is a hard failure that highlights some
significant issues with memory pool size or a mbuf leak.
We still have the message for subsequent chained mbufs, but not
for the first one. It was removed while introducing extbuf
support for large buffers. But it was useful for catching
mempool issues and needs to be returned back.
Marvin Liu [Thu, 24 Oct 2019 16:08:31 +0000 (00:08 +0800)]
vhost: optimize packed ring dequeue
Optimize vhost device packed ring dequeue function by splitting batch
and single functions. No-chained and direct descriptors will be handled
by batch and other will be handled by single as before.
Signed-off-by: Marvin Liu <yong.liu@intel.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Marvin Liu [Thu, 24 Oct 2019 16:08:29 +0000 (00:08 +0800)]
vhost: optimize packed ring enqueue
Optimize vhost device packed ring enqueue function by splitting batch
and single functions. Packets can be filled into one desc will be
handled by batch and others will be handled by single as before.
Signed-off-by: Marvin Liu <yong.liu@intel.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Marvin Liu [Thu, 24 Oct 2019 16:08:28 +0000 (00:08 +0800)]
vhost: update packed ring dequeue
Buffer used ring updates as many as possible in vhost dequeue function
for coordinating with virtio driver. For supporting buffer, shadow used
ring element should contain descriptor's flags. First shadowed ring
index was recorded for calculating buffered number.
Signed-off-by: Marvin Liu <yong.liu@intel.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Marvin Liu [Thu, 24 Oct 2019 16:08:26 +0000 (00:08 +0800)]
vhost: flush enqueue updates by cacheline
Buffer vhost packed ring enqueue updates, flush ring descs if buffered
content filled up one cacheline. Thus virtio can receive packets at a
faster frequency.
Signed-off-by: Marvin Liu <yong.liu@intel.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Marvin Liu [Thu, 24 Oct 2019 16:08:25 +0000 (00:08 +0800)]
vhost: add packed ring batch dequeue
Add batch dequeue function like enqueue function for packed ring, batch
dequeue function will not support chained descriptors, single packet
dequeue function will handle it.
Signed-off-by: Marvin Liu <yong.liu@intel.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Marvin Liu [Thu, 24 Oct 2019 16:08:23 +0000 (00:08 +0800)]
vhost: add packed ring batch enqueue
Batch enqueue function will first check whether descriptors are cache
aligned. It will also check prerequisites in the beginning. Batch
enqueue function do not support chained mbufs, single packet enqueue
function will handle it.
Signed-off-by: Marvin Liu <yong.liu@intel.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Marvin Liu [Thu, 24 Oct 2019 16:08:22 +0000 (00:08 +0800)]
vhost: try to unroll for each loop
Create macro for adding unroll pragma before for each loop. Batch
functions will be contained of several small loops which can be
optimized by compilers' loop unrolling pragma.
Signed-off-by: Marvin Liu <yong.liu@intel.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Alvin Zhang [Tue, 8 Oct 2019 10:52:31 +0000 (18:52 +0800)]
net/i40e: fix exception with multi-driver
If support-multi-driver is enabled, the global registers should not
be configured. But with the current code base, if creating a flow
with rte_flow API, the global register GLQF_FD_MSK may be changed.
Yahui Cao [Thu, 24 Oct 2019 12:56:37 +0000 (20:56 +0800)]
net/ice: fix IPv6 UDP port matching
Reverse the src and dest notion, since the HW expects them to be from Tx
perspective where as the input from user is from Rx filter view.
Fixes: f5cafa961fae ("net/ice: add flow director create and destroy") Signed-off-by: Yahui Cao <yahui.cao@intel.com> Reviewed-by: Xiaolong Ye <xiaolong.ye@intel.com>
Ciara Power [Wed, 23 Oct 2019 12:53:00 +0000 (13:53 +0100)]
ethdev: fix include of ethernet header file
The include for rte_ether.h in each of these files should not use
quotes, as the header file is not in the librte_ethdev directory.
These are now updated to use <> symbols, to search directories
pre-designated by the compiler.
Fixes: 57668ed7bc08 ("net: move ethernet definitions to the net library") Cc: stable@dpdk.org Signed-off-by: Ciara Power <ciara.power@intel.com> Acked-by: Thomas Monjalon <thomas@monjalon.net>
Wisam Jaddo [Thu, 17 Oct 2019 08:13:52 +0000 (08:13 +0000)]
app/testpmd: fix missing GENEVE item in raw encap
Fixes: 0f4203fe9d18 ("app/testpmd: support GENEVE pattern item in flow rules") Cc: stable@dpdk.org Signed-off-by: Wisam Jaddo <wisamm@mellanox.com> Acked-by: Ori Kam <orika@mellanox.com>
Anand Sunkad [Thu, 17 Oct 2019 13:20:50 +0000 (13:20 +0000)]
net/memif: support multiple Tx
When Multiple slave/master Memif's interfaces are created in single
process data transmission over second connection is not successful.
Issue is because of "mq->in_port" is not initialized with
"dev->data->port_id" in memif_tx_queue_setup() function, and while
transmitting packets over second connection in eth_memif_tx function
it refer "mq->in_port" which is always zero, which leads to data
transmission always in 0th port.
To mitigate the issue,"mq->in_port" is initialized with
"dev->data->port_id" in memif_tx_queue_setup() function.
Signed-off-by: Anand Sunkad <anand.sunkad@benisontech.com> Reviewed-by: Jakub Grajciar <jgrajcia@cisco.com>
Jakub Grajciar [Wed, 23 Oct 2019 08:07:32 +0000 (10:07 +0200)]
net/memif: fix Unix domain address length
Define MEMIF_SOCKET_UN_SIZE to size of unix domain socket address.
Report error in case of longer path.
Fixes: b923866c6974 ("net/memif: allow for full key size in socket name") Signed-off-by: Jakub Grajciar <jgrajcia@cisco.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Ting Xu [Tue, 22 Oct 2019 16:26:36 +0000 (16:26 +0000)]
app/testpmd: add GTP parsing and Tx checksum offload
Enable testpmd to forward GTP packet in csum fwd mode.
A GTP header structure (without optional fields and extension header)
is defined in new rte_gtp.h.
A parser function in testpmd is added. GTPU and GTPC packets are both
supported, with respective UDP destination port and GTP message type.
Olivier Matz [Sat, 26 Oct 2019 12:39:01 +0000 (14:39 +0200)]
mbuf: support dynamic fields and flags
Many features require to store data inside the mbuf. As the room in mbuf
structure is limited, it is not possible to have a field for each
feature. Also, changing fields in the mbuf structure can break the API
or ABI.
This commit addresses these issues, by enabling the dynamic registration
of fields or flags:
- a dynamic field is a named area in the rte_mbuf structure, with a
given size (>= 1 byte) and alignment constraint.
- a dynamic flag is a named bit in the rte_mbuf structure.
The typical use case is a PMD that registers space for an offload
feature, when the application requests to enable this feature. As
the space in mbuf is limited, the space should only be reserved if it
is going to be used (i.e when the application explicitly asks for it).
The registration can be done at any moment, but it is not possible
to unregister fields or flags.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com> Acked-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Anatoly Burakov [Thu, 24 Oct 2019 12:36:50 +0000 (13:36 +0100)]
eal: fix memory config allocation for multi-process
Currently, mem config will be mapped without using the virtual
area reservation infrastructure, which means it will be mapped
at an arbitrary location. This may cause failures to map the
shared config in secondary process due to things like PCI
whitelist arguments allocating memory in a space where the
primary has allocated the shared mem config.
Fix this by using virtual area reservation to reserve space for
the mem config, thereby avoiding the problem and reserving the
shared config (hopefully) far away from any normal memory
allocations.
Anatoly Burakov [Thu, 24 Oct 2019 12:36:49 +0000 (13:36 +0100)]
mem: make base address hint OS specific
Not all OS's follow Linux's memory layout, which may lead to
problems following the suggested common address hint absent
of a base-virtaddr flag. Make this address hint OS-specific.
Michal Krawczyk [Thu, 24 Oct 2019 12:10:46 +0000 (14:10 +0200)]
vfio: fix truncated BAR offset for 32-bit
When 32-bit application is built on 64-bit system it is possible that
the offset of the resource is outside of the 32-bit value.
The problem with the unsigned long is, that it is 32-bit and not 64-bit
when using armhf compiler. Although the system is returning u64 value,
we are losing it's value if it's higher than 32-bit in the conversion
process. It can further cause mmap to fail due to offset being 0 or to
map not intended memory region.
To make it more portable, the uint64_t value is now being used for
storing offset instead of unsigned long. The size of being 32-bit seems
to be fine as the 32-bit application won't be able to access bigger
memory and it is further converted to size_t anyway. But for better
readability and to be consistent, it's type was changed to size_t as
well.
Fixes: 0205f873557c ("vfio: fix overflow of BAR region offset and size") Cc: stable@dpdk.org Signed-off-by: Michal Krawczyk <mk@semihalf.com> Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Multiple global variable are defined in multiple unit test files with
same name, but all unit test files are linked into single executable,
which means those variables share same storage which is not the
intention, fixed by making global variables 'static'.
Issue has been detected by '-fno-common' gcc flag.
Fixes: fdeb30fa7102 ("test/bitrate: add unit tests for bitrate library") Fixes: c3eabff124e6 ("distributor: add unit tests") Fixes: 0e925aef2779 ("app/test: add EFD functional and perf tests") Fixes: 359e17bf081f ("app/test: improve hash unit tests") Fixes: c7eb0972e74b ("test/hash: add lock-free r/w concurrency") Fixes: 1e3676a06e4c ("test/latency: add unit tests for latencystats library") Fixes: 0cc67a96e486 ("test/member: add functional and perf tests") Fixes: e6a14121f4ae ("test/rcu: remove arbitrary limit on max core count") Fixes: 104dbec2081a ("test/rcu: increase size of core numbers") Cc: stable@dpdk.org Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
app/testpmd: fix global variable multiple definitions
Some flow config related global variables are defined in a header file
which was causing multiple definitions of the variables, fixed it by
moving them to the .c file.
Issue has been detected by '-fno-common' gcc flag.
Also while being there,
removed duplicated 'ACTION_RAW_ENCAP_MAX_DAT definition,
moved 'vxlan_encap_conf' & 'nvgre_encap_conf' initialization to
'cmdline_flow.c' which is better location than 'testpmd.c'
relocated 'action_raw_encap_data' & 'action_raw_decap_data' struct
definitions slightly within the file
compress/octeontx: fix global variable multiple definitions
'octtx_zip_logtype_driver' global variable is defined in a header file
which was causing multiple definitions of the variable, fixed it by
moving it to the .c file.
Issue has been detected by '-fno-common' gcc flag.
crypto/virtio: fix global variable multiple definitions
'virtio_hw_internal' global variable is defined in both 'crypto/virtio'
and 'net/virtio' PMDs. This means they share same storage when
application linked with static DPDK library, which is not the intention.
Fixing by adding 'crypto_' prefix to the 'crypto/virtio' driver.
Issue has been detected by '-fno-common' gcc flag.
crypto/null: fix global variable multiple definitions
'null_logtype_driver' global variable is defined in a header file which
was causing multiple definitions of the variable, fixed it by moving it
to the .c file.
Issue has been detected by '-fno-common' gcc flag.
Filtering related global variables are defined in a header file which
was causing multiple definitions of the variables, fixed it by moving
them to the .c file.
Issue has been detected by '-fno-common' gcc flag.
bus/fslmc: fix global variable multiple definitions
'qman_version' global variable is defined in a header file which was
causing multiple definitions of the variable, fixed it by moving it to
the .c file.
Issue has been detected by '-fno-common' gcc flag.
Fixes: 293c0ca94c36 ("bus/fslmc: support memory backed portals with QBMAN 5.0") Cc: stable@dpdk.org Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Sachin Saxena <sachin.saxena@nxp.com>
Right now inclusion of rte_mbuf.h header can cause inclusion of
some arch/os specific headers.
That prevents it to be included directly by some
non-DPDK (but related) entities: KNI, BPF programs, etc.
To overcome that problem usually a separate definitions of rte_mbuf
structure is created within these entities.
That aproach has a lot of drawbacks: code duplication, error prone, etc.
This patch moves rte_mbuf structure definition (and some related macros)
into a separate file that can be included by both rte_mbuf.h and
other non-DPDK entities.
Note that it doesn't introduce any change for current DPDK code.
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Michel Machado <michel@digirati.com.br> Acked-by: Olivier Matz <olivier.matz@6wind.com>
Right now RTE_CACHE_ and IOVA definitions are located inside rte_memory.h
That might cause an unwanted inclusions of arch/os specific header files.
See [1] for particular problem example.
Probably the simplest way to deal with such problems -
move these definitions into rte_commmon.h
Note that this move doesn't introduce any change in functionality.
[1] https://bugs.dpdk.org/show_bug.cgi?id=321
Suggested-by: Vipin Varghese <vipin.varghese@intel.com> Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Michel Machado <michel@digirati.com.br>
Jasvinder Singh [Wed, 16 Oct 2019 14:17:28 +0000 (15:17 +0100)]
sched: add 64-bit values
To support high bandwidth network interfaces, all rates (port,
subport level token bucket and traffic class rates, pipe level
token bucket and traffic class rates) and stats counters defined
in public data structures (rte_sched.h) are modified to support
64 bit counters.
git.droids-corp.org / dpdk.git / log