Add a sanity check for number of tx descriptors requested during tx
queue setup. Return -EINVAL if the number requested does not meet
the tx descriptor requirements of the device.
Fixes: 80a1deb4c77a ("ethdev: add API to retrieve queue information")
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
It prevents some drivers to load:
undefined symbol: rte_eth_dma_zone_reserve
Fixes: 719dbebceb81 ("xen: allow determining DOM0 at runtime")
Signed-off-by: Panu Matilainen <pmatilai@redhat.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Not all filesystems supply struct dirent d_type field, in which case
everything in the specified directory would go ignored. One such
filesystem being XFS which RHEL 7 defaults to... stat() the entries
instead.
Fixes: 9f8eb1d9ca0f ("eal: support driver loading from directory")
Signed-off-by: Panu Matilainen <pmatilai@redhat.com>
The added error checking on plugin initialization in
commit 9f8eb1d9ca0f56d6292db5858c52e6873d0abe51 broke the ability of
loading plugins by their basename from default linker locations.
Only use stat() for directory discovery and leave error handling
to dlopen() to restore former behavior.
Fixes: 9f8eb1d9ca0f ("eal: support driver loading from directory")
Signed-off-by: Panu Matilainen <pmatilai@redhat.com>
No need for those forward declarations (which breaks build when asking for
C++11 or adding pedantic flag).
Signed-off-by: David Marchand <david.marchand@6wind.com>
It does not build with every C++ compilers.
Reverts the _UNDERLYING_TYPE workarounds to prepare
for another fix in the next patch.
Fixes: 621389bbbe08 ("eal: fix C++ app build")
Signed-off-by: David Marchand <david.marchand@6wind.com>
CLOCK_MONOTONIC_RAW added in glibc 2.12, using this define in older
glibc versions cause compile error:
'error: identifier "CLOCK_MONOTONIC_RAW" is undefined'
This patch replaces "CLOCK_MONOTONIC_RAW" with "CLOCK_MONOTONIC" for
older glibc versions, versions that support "CLOCK_MONOTONIC_RAW"
will keep using this clock type.
Fixes: d08d304508a8 ("eal/linux: make alarm not affected by system time jump")
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
On HSW box with icc 16.0.0 build for x86_64-native-linuxapp-icc fails with:
icc: command line warning #10120: overriding '-march=native' with '-msse4.1'
...
dpdk.org/x86_64-native-linuxapp-icc/include/rte_memcpy.h(96): error: identifier "__m256i" is undefined
The reason is that icc treats "-march=native ... -msse4.1"
in a different way, then gcc and clang.
For icc it means override all flags enabled with
'-march=native' with '-msse4.1'.
Even when '-march=native' is a superset for '-msse4.1'.
To overcome the problem add a check is SSE4.1 compilation flag already enabled.
If yes, then no need to add '-msse4.1'
Similar change for avx2 compilation option.
Fixes: 074f54ad03ee ("acl: fix build and runtime for default target")
Reported-by: Declan Doherty <declan.doherty@intel.com>
Reported-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
Adds functions for detecting and reporting the live-ness of LCores,
the primary requirement of which is minimal overheads for the
core(s) being checked. Core failures are notified via an application
defined callback.
Signed-off-by: Remy Horton <remy.horton@intel.com>
It fixes the compile issue on kernel version 2.6.32 or old ones.
Error logs:
lib/librte_eal/linuxapp/kni/kni_misc.c:121: error: unknown field id specified in initializer
lib/librte_eal/linuxapp/kni/kni_misc.c:121: error: excess elements in struct initializer
lib/librte_eal/linuxapp/kni/kni_misc.c:121: error: (near initialization for kni_net_ops)
lib/librte_eal/linuxapp/kni/kni_misc.c:122: error: unknown field size specified in initializer
lib/librte_eal/linuxapp/kni/kni_misc.c:122: error: excess elements in struct initializer
lib/librte_eal/linuxapp/kni/kni_misc.c:122: error: (near initialization for kni_net_ops)
Fixes: 72a7a2b2469e ("kni: allow per-net instances")
Signed-off-by: Helin Zhang <helin.zhang@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
/proc/version_signature is the version for the host machine, but in
e.g., chroots, this does not necessarily match that DPDK is built
for. DPDK will then build for the wrong kernel version - that of the
server, and not that installed in the (build) chroot.
The patch uses utsrelease.h from the kernel sources instead and fakes
the upload version.
Tested on a server with Ubuntu 12.04, building in a chroot for Ubuntu
14.04.
Signed-off-by: Simon Kagstrom <simon.kagstrom@netinsight.net>
Signed-off-by: Johan Faltstrom <johan.faltstrom@netinsight.net>
Acked-by: Helin Zhang <helin.zhang@intel.com>
This commit introduce rte_smp_mb(), rte_smp_wmb() and rte_smp_rmb(), in
order to enable memory barriers between lcores.
The patch does not provide any functional change for IA, the goal is to
have infrastructure for weakly ordered machines like ARM to work on DPDK.
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
The implementation uses NEON gcc intrinsic.
Verified with testacl and acl_autotest applications on arm64 architecture.
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
cntcvt_el0 ticks are not based on cpu clk unlike rdtsc in x86.
Its a fixed clock running based at constant speed.
Though its a armv8-a implementer choice, typically it runs at 50 or 100 MHz
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Based on the patch by David Hunt and Armuta Zende:
lib: added support for armv7 architecture
Signed-off-by: Jan Viktorin <viktorin@rehivetech.com>
Signed-off-by: Amruta Zende <amruta.zende@intel.com>
Signed-off-by: David Hunt <david.hunt@intel.com>
Acked-by: David Marchand <david.marchand@6wind.com>
This implementation is based on IBM POWER version of
rte_cpuflags. We use software emulation of HW capability
registers, because those are usually not directly accessible
from userspace on ARM.
Signed-off-by: Vlastimil Kosar <kosar@rehivetech.com>
Signed-off-by: Jan Viktorin <viktorin@rehivetech.com>
Acked-by: David Marchand <david.marchand@6wind.com>
The GCC can be configured to avoid using NEON extensions.
For that purpose, we provide just the memcpy implementation
of the rte_memcpy.
Based on the patch by David Hunt and Armuta Zende:
lib: added support for armv7 architecture
Signed-off-by: Jan Viktorin <viktorin@rehivetech.com>
Signed-off-by: Amruta Zende <amruta.zende@intel.com>
Signed-off-by: David Hunt <david.hunt@intel.com>
Acked-by: David Marchand <david.marchand@6wind.com>
This patch adds spinlock operations for ARM architecture.
We do not support HTM in spinlocks on ARM. Setting of the
RTE_FORCE_INTRINSICS=y is required.
Signed-off-by: Vlastimil Kosar <kosar@rehivetech.com>
Signed-off-by: Jan Viktorin <viktorin@rehivetech.com>
Acked-by: David Marchand <david.marchand@6wind.com>
This patch adds architecture specific atomic operation file
for ARM architecture. The RTE_FORCE_INTRINSICS=y is required.
Signed-off-by: Vlastimil Kosar <kosar@rehivetech.com>
Signed-off-by: Jan Viktorin <viktorin@rehivetech.com>
Acked-by: David Marchand <david.marchand@6wind.com>
This patch adds architecture specific prefetch operations
for ARM architecture. It utilizes the pld instruction that
starts filling the appropriate cache line without blocking.
Signed-off-by: Vlastimil Kosar <kosar@rehivetech.com>
Signed-off-by: Jan Viktorin <viktorin@rehivetech.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Enable to choose a preferred way to read timer based on the
configuration entry CONFIG_RTE_ARM_EAL_RDTSC_USE_PMU.
It requires a kernel module that is not included to work.
Based on the patch by David Hunt and Armuta Zende:
lib: added support for armv7 architecture
Signed-off-by: Jan Viktorin <viktorin@rehivetech.com>
Signed-off-by: Amruta Zende <amruta.zende@intel.com>
Signed-off-by: David Hunt <david.hunt@intel.com>
Acked-by: David Marchand <david.marchand@6wind.com>
ARM architecture doesn't have a suitable source of CPU cycles. This
patch uses clock_gettime instead. The implementation should be improved
in the future.
Signed-off-by: Vlastimil Kosar <kosar@rehivetech.com>
Signed-off-by: Jan Viktorin <viktorin@rehivetech.com>
Acked-by: David Marchand <david.marchand@6wind.com>
This patch adds architecture specific byte order operations
for ARM. The architecture supports both big and little endian.
It requires RTE_FORCE_INTRINSICS=y.
Signed-off-by: Vlastimil Kosar <kosar@rehivetech.com>
Signed-off-by: Jan Viktorin <viktorin@rehivetech.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Add common functions and structures to handle time, and cycle counts
which will be used for PTP processing.
Signed-off-by: Daniel Mrzyglod <danielx.t.mrzyglod@intel.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Reviewed-by: John McNamara <john.mcnamara@intel.com>
Add additional functions to support the existing IEEE1588
functionality.
* rte_eth_timesync_write_time(): set the device clock time.
* rte_eth_timesync_read_time(): get the device clock time.
* rte_eth_timesync_adjust_time(): adjust the device clock time.
Signed-off-by: Daniel Mrzyglod <danielx.t.mrzyglod@intel.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Reviewed-by: John McNamara <john.mcnamara@intel.com>
Use deprecated attribute to highlight any use of fields that
are marked as going away in the rte_ether device statistics.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
This patch refactors the generic queue stats to be exposed
by rte_ethdev_xstats_get().
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com>
Acked-by: Maryam Tahhan <maryam.tahhan@intel.com>
Add support for directories as arguments to -d for loading all drivers
from a given directory. Additionally a default driver directory can be
set in build-time configuration, in which case it will be always be used
when EAL is initialized.
This simplifies usage in shared library configuration significantly over
manually loading individual drivers with -d, and allows distros to
establish a drop-in driver directory for seamless integration
with 3rd party drivers etc.
Suggested-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Suggested-by: David Marchand <david.marchand@6wind.com>
Signed-off-by: Panu Matilainen <pmatilai@redhat.com>
Acked-by: David Marchand <david.marchand@6wind.com>
There's no good reason to limit plugins to Linux, make it available
on FreeBSD too. Refactor the plugin code from Linux EAL to common
helper functions, also check for and fail on errors during initialization.
Signed-off-by: Panu Matilainen <pmatilai@redhat.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Currently, we reset all fields of a device to zero when reset
happens, which is wrong, since for some fields like device_fh,
ifname, and virt_qp_nb, they should be same and be kept after
reset until the device is removed. And this is what's the new
helper function reset_device() for.
And use rte_zmalloc() instead of rte_malloc, so that we could
avoid init_device(), which basically dose zero reset only so far.
Hence, init_device() is dropped in this patch.
This patch also removes a hack of using the offset a specific
field (which is virtqueue now) inside of `virtio_net' structure
to do reset, which could be broken easily if someone changed the
field order without caution.
Cc: Tetsuya Mukawa <mukawa@igel.co.jp>
Cc: Huawei Xie <huawei.xie@intel.com>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Acked-by: Rich Lane <rich.lane@bigswitch.com>
QEMU sends VHOST_RESET_OWNER first when shutting down.
There was previously no way for the dataplane to know that the
virtio_net instance had become unusable and it would segfault
when trying to do RX/TX.
Signed-off-by: Rich Lane <rich.lane@bigswitch.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Fix to take this change into account: https://lkml.org/lkml/2015/7/9/101
Has been applied to Kernel 4.3.0-rc6
Linux: 4a7cc831 ("genirq/MSI: Move msi_list from struct pci_dev to struct device")
Signed-off-by: David Hunt <david.hunt@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Someone may need to call rte_eal_init() with a fake argc/argv array
in the middle of using getopt() to parse its own unrelated argc/argv
parameters. So getopt lib shouldn't be reset by rte_eal_init().
Now eal will always save optind, optarg and optopt (and optreset on
FreeBSD) at the beginning, initialize optind (and optreset on FreeBSD)
to 1 before calling getopt_long(), then restore all values after.
Suggested-by: Don Provan <dprovan@bivio.net>
Suggested-by: Bruce Richardson <bruce.richardson@intel.com>
Signed-off-by: Tiwei Bie <btw@mail.ustc.edu.cn>
Reviewed-by: Don Provan <dprovan@bivio.net>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Calling the Ethernet driver's link_update function from
rte_eth_dev_start can result in a race condition if the NIC raises
the link interrupt at the same time.
Depending on the interrupt handler implementation, the race can cause
the it to think that it received two consecutive link up interrupts,
and it exits without calling the user callback. Appears to impact
E1000/IGB and virtio drivers only.
Signed-off-by: Tim Shearer <tim.shearer@overturenetworks.com>
The tx_rate unit is Mbps.
Gleaned from the ixgbe implementation, the 82599 datasheet and the use
in test-pmd.
Signed-off-by: Simon Kagstrom <simon.kagstrom@netinsight.net>
Add support for RTE_ETH_FDIR_PASSTHRU flow director behavior so
output queue is assigned by other filters.
Signed-off-by: Andrey Chilikin <andrey.chilikin@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
The i40e driver was using a #define value for the max number of rxtx interrupts
supported. This value was defined only for linux, giving an error when compiling
on FreeBSD.
CC i40e_ethdev.o
/usr/home/bruce/dpdk.org/drivers/net/i40e/i40e_ethdev.c:3885:9: fatal error: use of undeclared
identifier 'RTE_MAX_RXTX_INTR_VEC_ID'
Copying the necessary #define into the FreeBSD EAL header fixes the compile
error.
Fixes: d37641029ada ("eal/linux: add interrupt vectors")
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Following the same approach taken with dev_started field
in rte_eth_dev_data structure, this patch adds two new fields
in it, rx_queue_state and tx_queue_state arrays, which track
which queues have been started and which not.
This is important to avoid trying to start/stop twice a queue,
which will result in undefined behaviour
(which may cause RX/TX disruption).
Mind that only the PMDs which have queue_start/stop functions
have been changed to update this field, as the functions will
check the queue state before switching it.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
VFIO allows multiple MSI-X vector, others doesn't, but maybe will
allow it in the future.
Device drivers need to be aware of the capability.
It's better to avoid condition check on interrupt type (VFIO) everywhere,
instead a capability api is more flexible for the condition change.
Signed-off-by: Cunming Liang <cunming.liang@intel.com>
Acked-by: David Marchand <david.marchand@6wind.com>
