Several DV-based structs of type 'struct mlx5dv_devx_XXX' are replaced
with 'void *' to enable compilation under non-Linux operating systems.
New getter functions were added to retrieve the specific fields that
were previously accessed directly.
Replaced structs:
'struct mlx5dv_pp *'
'struct mlx5dv_devx_event_channel *'
'struct mlx5dv_devx_umem *'
'struct mlx5dv_devx_uar *'
Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Flow metering is supported only in direct rules (DR). Currently the APIs
of meter actions create and modify are under #ifdef
HAVE_MLX5_DR_CREATE_ACTION_FLOW_METER, while detaching the meter action
is executed unconditionally. This commit adds the same ifdef to API
mlx5_flow_meter_detach().
This commit avoids compilation failure of non-Linux operating systems
which do not support DR.
Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Remove utility macros INFO, WARN, ERROR. They are not in use and
conflict with identical definitions when compiled under Windows.
Fixes: 80f2d0ed7f ("net/mlx5: add hardware flow debug dump")
Cc: stable@dpdk.org
Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
This commit adds Linux implementation of routine mlx5_os_mac_addr_flush
as wrapper to Netlink API to avoid direct calls under non-Linux
operating systems.
Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
mlx5_get_ifname() prototype includes 'IF_NAMESIZE' definition from Linux
file net/if.h. Since this API is only used under Linux and to enable
compilation under non-Linux OS - move this prototype from shared file
mlx5.h to file linux/mlx5_os.h.
Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Enumerated variable REG_NONE (defined in mlx5_prm.h) is in conflict with
Windows definition (winnt.h): #define REG_NONE ( 0ul ) // No value type
To enable mlx5 PMD Windows compilation - rename REG_NONE as REG_NON.
Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
strsep() is a non-standardized API (by C or POSIX) and thus it is
non-portable between different operating systems. Replace it with
strtok_r() which is standardized by the C standard, and hence also by
POSIX.
The replacement occurs in the code that extracts individual PCI class
names (e.g. class=net:vdpa:foo:bar).
Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
SIGIO maybe used by application, instead choose another rt-signal.
Linux allows any signal to be used for signal based IO.
Search for an unused signal in the available rt-signal range.
Add more error checking for fcntl and signal handling.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Morten Brørup <mb@smartsharesystems.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
* rte_is_broadcast_ether_addr():
Use binary logic instead of comparisons and boolean logic, thus reducing
the number of branches.
It now resembles rte_is_zero_ether_addr().
* rte_ether_addr_copy():
The source code modifications were discussed on the mailing list:
http://mails.dpdk.org/archives/dev/2020-June/171584.html
Remove obsolete ICC-specific code and related comment.
Restrict pointer aliasing (suggested by Jerin Jacob).
Remove superfluous "Fast" from function description headline; all DPDK
data plane functions are supposed to be fast.
Signed-off-by: Morten Brørup <mb@smartsharesystems.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Negative array index read using variable 'i' as an index to array
'filter_info->pkt_filters'. Fixed by add return value check.
Coverity issue: 350364
Fixes: f4ca3fd54c ("net/hinic: create and destroy flow director filter")
Cc: stable@dpdk.org
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
This patch adds checking whether the related Tx or Rx queue has been
setup in the rte_eth_rx_queue_info_get and rte_eth_tx_queue_info_get
API function to avoid illegal address access.
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
This patch adds support for querying Rx/Tx queue information.
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Currently, if there are not available Rx buffer descriptors in receiving
direction based on hns3 network engine, incoming packets will always be
dropped by hardware. This patch reports the '.rx_drop_en' information to
DPDK framework in the '.dev_infos_get', '.rxq_info_get' and
'.rx_queue_setup' ops implementation function.
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
To manage header modify actions mlx5 PMD used the single linked list and
lookup and insertion operations took too long times if there were
millions of objects and this impacted the flow insertion/deletion rate.
In order to optimize the performance the hashed list is engaged. The
list implementation is updated to support non-unique keys with few
collisions.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
The mlx5 PMD hashed list was designed in approach to contain the items
with unique keys only. Now there is the need to store the objects with
possible key collisions. It is not expected to have many collisions
(very likely to have a few ones), but keys become not unique.
This commit adds the hash list extended functions in order to support
insertion and lookup for the lists with non-unique keys.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
The data from the host is trusted but checked by the driver.
One check that is missing is that the packet offset and length
might cause wraparound.
Cc: stable@dpdk.org
Reported-by: Nan Chen <whutchennan@gmail.com>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Long Li <longli@microsoft.com>
chim_index could potentially be used in other hn_txdesc when re-allocated.
Mark it as invalid to prevent stale value being used.
Fixes: cc02518132 ("net/netvsc: split send buffers from Tx descriptors")
Cc: stable@dpdk.org
Signed-off-by: Long Li <longli@microsoft.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
netvsc is a high speed VMBus device that uses monitor bit to signal the
host. It's not necessary to send interrupts via INT bit.
Signed-off-by: Long Li <longli@microsoft.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
netvsc uses rxbuf_info buffer to track received packets attached via
rte_pktmbuf_attach_extbuf() and ack the host based on usage count. It
uses the transaction_id in the VMBus packet to locate where to use
memory in the rxbuf_info.
This is not correct in multiple channel setup, as different channels may
return identical transaction_ids at a time, and may corrupt the
rxbuf_info buffer.
Fix this by defining rxbuf_info for each queue.
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>
This patch adds a missing LLQ-related check in the
ena_com_is_doorbell_needed() routine, which is relevant for the feature
supported by the next generation HW of the ENA.
Fixes: b2b02edeb0 ("net/ena/base: upgrade HAL for new HW features")
CC: stable@dpdk.org
Signed-off-by: Michal Krawczyk <mk@semihalf.com>
Signed-off-by: Artur Rojek <ar@semihalf.com>
This commit fixes a potential race condition in the tests
where the lcore running a service would increment a counter
that was already reset by the test-suite thread. The resulting
race-condition incremented value could cause CI failures, as
indicated by DPDK's CI.
This patch fixes the race-condition by making use of the
added rte_service_lcore_active() API, which indicates when
a service-core is no longer in the service-core polling loop.
The unit test makes use of the above function to detect when
all statistics increments are done in the service-core thread,
and then the unit test continues finalizing and checking state.
Fixes: f28f3594de ("service: add attribute API")
Reported-by: David Marchand <david.marchand@redhat.com>
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
This commit adds a new experimental API which allows the user
to retrieve the active state of an lcore. Knowing when the service
lcore is completed its polling loop can be useful to applications
to avoid race conditions when e.g. finalizing statistics.
The service thread itself now has a variable to indicate if its
thread is active. When zero the service thread has completed its
service, and has returned from the service_runner_func() function.
Suggested-by: Lukasz Wojciechowski <l.wojciechow@partner.samsung.com>
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
This declaration is the same as the one a few lines before.
Fixes: 6844d146ff ("eal: add bus pointer in device structure")
Cc: stable@dpdk.org
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
This structure is not used in the public API.
Fixes: a753e53d51 ("eal: add device event monitor framework")
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Jeff Guo <jia.guo@intel.com>
Acked-by: Ray Kinsella <mdr@ashroe.eu>
Now that the pci_map_resource API is private to the PCI bus, we can drop
the compatibility workaround we had implemented in 20.08.
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
As reported during 20.08 work for Windows, the pci_map_resource API was
built with the assumption that its flags would be passed to mmap().
This introduced a regression when adding the rte_mem_map API as reported
in the workaround commit 9d2b245937 ("pci: keep API compatibility with
mmap values").
This API was only used in the PCI bus code, so move it there.
There is no code change happening during the move.
The only change is in the pci_map_resource description where the
additional flags are now documented as rte_mem_map API flags:
- * The additional flags for the mapping range.
+ * The additional rte_mem_map() flags for the mapping range.
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Ray Kinsella <mdr@ashroe.eu>
The rte_kernel_driver enum actually only pointed at PCI drivers and is
only used in the PCI subsystem.
Remove it from the generic device API and use a private enum in the PCI
code.
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
This field was not generic as it was filled with PCI kernel drivers only.
It has no known in-tree user (and I could not find opensource projects
using it).
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Remove the deprecated buf_physaddr union field from rte_mbuf.
It is replaced with buf_iova which is at the same offset.
The single field buf_physaddr in rte_kni_mbuf is also renamed.
This concludes a 3-year process of semantic change.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Ray Kinsella <mdr@ashroe.eu>
Remove the deprecated functions
- rte_mbuf_data_dma_addr
- rte_mbuf_data_dma_addr_default
which aliased the more recent functions
- rte_mbuf_data_iova
- rte_mbuf_data_iova_default
Remove the deprecated macros
- rte_pktmbuf_mtophys
- rte_pktmbuf_mtophys_offset
which aliased the more recent macros
- rte_pktmbuf_iova
- rte_pktmbuf_iova_offset
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: Ray Kinsella <mdr@ashroe.eu>
Remove the deprecated unioned fields physaddr and phys_addr
from the structures rte_mempool_objhdr and rte_mempool_memhdr.
They are replaced with the fields iova which are at the same offsets.
Remove the deprecated macro MEMPOOL_F_NO_PHYS_CONTIG
which is an alias of the more recent MEMPOOL_F_NO_IOVA_CONTIG.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Ray Kinsella <mdr@ashroe.eu>
Remove the deprecated unioned fields phys_addr
from the structures rte_memseg and rte_memzone.
They are replaced with the fields iova which are at the same offsets.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: Ray Kinsella <mdr@ashroe.eu>
trace_mem is declared as 'void *' which triggers following error:
'...invalid conversion from ‘void*’ to ‘__rte_trace_header*’
[-fpermissive]...'
Fix this by adding proper typecast to 'struct __rte_trace_header *'.
Fixes: ebaee64097 ("trace: simplify trace point headers")
Cc: stable@dpdk.org
Signed-off-by: Pawel Wodkowski <pawelwod@gmail.com>
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Nicolas Chautru <nicolas.chautru@intel.com>
The BPF lib was introduced in 18.05.
There were no changes in its public API since 19.11.
It should be mature enough to remove its 'experimental' tag.
RTE_BPF_XTYPE_NUM is also being dropped from rte_bpf_xtype to
avoid possible ABI problems in the future.
Signed-off-by: Conor Walsh <conor.walsh@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
As announced in earlier releases, rte_logs can now be made
internal to EAL.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
Applications will need to use this API now to get internal
state of rte_log.
Suggested-by: David Marchand <david.marchand@redhat.com>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David Marchand <david.marchand@redhat.com>
The debug message was poorly worded and did not include the
part that would be useful. I.e it never said what was being ignored.
Change it to print the message so that if udev changes format or
other subsystems need to be added then the necessary information
will be in the debug log.
Fixes: 0d0f478d04 ("eal/linux: add uevent parse and process")
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Jeff Guo <jia.guo@intel.com>
The checks for libfdt try dependency() first which would only work if
a pkg-config would be present but libfdt has none.
Then it probes for the lib path itself via cc.find_library.
But later it adds the result of either probe to ext_deps which ends up
in build and also the resulting pkg-config to contain toolchain versioned
paths in Libs.private like:
/usr/lib/gcc/x86_64-linux-gnu/9/../../../x86_64-linux-gnu/libfdt.so
which obviously breaks on toolchain updates.
In general libs used multiple times - ipn3ke + ifpga in this case - are
checked centrally in config/meson.build so move it there and fix the
adding of dependencies to not use the full file path.
The result is libfdt in pkg-config now showing up as:
Libs.private: -pthread -lm -ldl -lnuma -lfdt -lpcap
Fixes: e1defba4cf ("raw/ifpga/base: support device tree")
Cc: stable@dpdk.org
Signed-off-by: Christian Ehrhardt <christian.ehrhardt@canonical.com>
Reviewed-by: Luca Boccassi <bluca@debian.org>
Reviewed-by: Bruce Richardson <bruce.richardson@intel.com>
Remove the deprecated refcnt_atomic union fields in
rte_mbuf and rte_mbuf_ext_shared_info structures.
Signed-off-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Since all changes covered by the deprecation notice have been applied, the
notice can be removed.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Nipun Gupta <nipun.gupta@nxp.com>
Not all rawdevs will require a device start/stop function, so rather than
requiring such drivers to provide dummy functions, just set the
started/stopped rawdev flag from the rawdev layer and return success.
Signed-off-by: Kevin Laatz <kevin.laatz@intel.com>
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Nipun Gupta <nipun.gupta@nxp.com>
The driver APIs for returning the queue default config can fail if the
parameters are invalid, or other reasons, so allow them to return error
codes to the rawdev layer and from hence to the app.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Nipun Gupta <nipun.gupta@nxp.com>
The queue setup and queue defaults query functions take a void * parameter
as configuration data, preventing any compile-time checking of the
parameters and limiting runtime checks. Adding in the length of the
expected structure provides a measure of typechecking, and can also be used
for ABI compatibility in future, since ABI changes involving structs almost
always involve a change in size.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Nipun Gupta <nipun.gupta@nxp.com>
Currently with the rawdev API there is no way to check that the structure
passed in via the dev_private pointer in the structure passed to configure
API is of the correct type - it's just checked that it is non-NULL. Adding
in the length of the expected structure provides a measure of typechecking,
and can also be used for ABI compatibility in future, since ABI changes
involving structs almost always involve a change in size.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Rosen Xu <rosen.xu@intel.com>
Acked-by: Nipun Gupta <nipun.gupta@nxp.com>
Since we now allow some parameter checking inside the driver info_get()
functions, it makes sense to allow error return from those functions to the
caller. Therefore we change the driver callback return type from void to
int.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Rosen Xu <rosen.xu@intel.com>
Acked-by: Nipun Gupta <nipun.gupta@nxp.com>
Currently with the rawdev API there is no way to check that the structure
passed in via the dev_private pointer in the dev_info structure is of the
correct type - it's just checked that it is non-NULL. Adding in the length
of the expected structure provides a measure of typechecking, and can also
be used for ABI compatibility in future, since ABI changes involving
structs almost always involve a change in size.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Rosen Xu <rosen.xu@intel.com>
Acked-by: Rosen Xu <rosen.xu@intel.com>
Acked-by: Nipun Gupta <nipun.gupta@nxp.com>
