fix the error reported by checkpatch:
"ERROR: return is not a function, parentheses are not required"
remove parentheses in return like:
"return (logical expressions)"
remove parentheses in return a function like:
"return (rte_mempool_lookup(...))"
Fixes: 6307b909b8e0 ("lib: remove extra parenthesis after return")
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Currently rte_eal_check_module() detects Linux kernel modules via reading
/proc/modules. Built-in ones aren't listed there and therefore they are not
being found.
Add support for checking built-in modules with parsing the sysfs files
This commit obsoletes the /proc/modules parsing approach.
Signed-off-by: Kamil Rytarowski <kamil.rytarowski@caviumnetworks.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
When configuring RTE_MACHINE to "default", rte_memcpy implementation
is the default one (old AVX).
In this code, clang raises a warning thanks to -Wsometimes-uninitialized:
rte_memcpy.h:838:6: error:
variable 'srcofs' is used uninitialized whenever 'if' condition is false
if (dstofss > 0) {
^~~~~~~~~~~
rte_memcpy.h:849:6: note: uninitialized use occurs here
if (srcofs == 0) {
^~~~~~
It is fixed by moving srcofs initialization out of the condition.
Also dstofss calculation is corrected.
Fixes: 1ae817f9f887 ("eal/x86: tune memcpy for platforms without AVX512")
Reported-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Signed-off-by: Zhihong Wang <zhihong.wang@intel.com>
Normally we could set RTE_PCI_DRV_NEED_MAPPING flag so that eal will
invoke pci_map_device internally for us. From that point view, there
is no need to export pci_map_device.
However, for virtio pmd driver, which is designed to work without
binding UIO (or something similar first), pci_map_device() will fail,
which ends up with virtio pmd driver being skipped. Therefore, we can
not set RTE_PCI_DRV_NEED_MAPPING blindly at virtio pmd driver.
Therefore, this patch exports pci_map_device, and let virtio pmd call
it when necessary.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Tested-by: Santosh Shukla <sshukla@mvista.com>
Tested-by: Qian Xu <qian.q.xu@intel.com>
Reviewed-by: Tetsuya Mukawa <mukawa@igel.co.jp>
Tested-by: Tetsuya Mukawa <mukawa@igel.co.jp>
Acked-by: David Marchand <david.marchand@6wind.com>
Acked-by: Huawei Xie <huawei.xie@intel.com>
Move cpu_feature_table array from arch specific rte_cpuflags.h files to
new arch specific rte_cpuflags.c files.
Main motivation is to escape from static variable declarations in
header files. cpu_feature_table has many copies in final binary, even
exist in some object files that does not use this variable at all.
And this can be a sample to create architecture specific source files
and move some functions which are not performance sensitive from
architecture header files to source files.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
This commit is adding a generic mechanism to support multiple IOMMU
types. For now, it's only type 1 (x86 IOMMU) and no-IOMMU (a special
VFIO mode that doesn't use IOMMU at all), but it's easily extended
by adding necessary definitions to eal_vfio.h, and DMA mapping
functions to eal_pci_vfio.c.
Since type 1 IOMMU module is no longer necessary to have VFIO,
we fix the module check to check for vfio-pci instead. It's not
ideal and triggers VFIO checks more often (and thus produces more
error output, which was the reason behind the module check in the
first place), so we compensate for that by providing more verbose
logging, indicating whether VFIO initialization has succeeded or
failed.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Signed-off-by: Santosh Shukla <sshukla@mvista.com>
Tested-by: Santosh Shukla <sshukla@mvista.com>
In fedora 22 with GCC version 5.3.1, when compile,
will result an error:
include/rte_memcpy.h:309:7: error: "RTE_MACHINE_CPUFLAG_AVX2"
is not defined [-Werror=undef]
#elif RTE_MACHINE_CPUFLAG_AVX2
Fixes: 9484092baad3 ("eal/x86: optimize memcpy for AVX512 platforms")
Signed-off-by: Michael Qiu <michael.qiu@intel.com>
Acked-by: Zhihong Wang <zhihong.wang@intel.com>
For prior platforms, add condition for unalignment handling, to keep this
operation from interrupting the batch copy loop for aligned cases.
Signed-off-by: Zhihong Wang <zhihong.wang@intel.com>
Implement AVX512 memcpy and choose the right implementation based on
predefined macros, to make full utilization of hardware resources and
deliver high performance.
In current DPDK, memcpy holds a large proportion of execution time in
libs like Vhost, especially for large packets, and this patch can bring
considerable benefits for AVX512 platforms.
The implementation is based on the current DPDK memcpy framework, some
background introduction can be found in these threads:
http://dpdk.org/ml/archives/dev/2014-November/008158.htmlhttp://dpdk.org/ml/archives/dev/2015-January/011800.html
Signed-off-by: Zhihong Wang <zhihong.wang@intel.com>
Move these error logs and checks on detach capabilities in a common place.
Signed-off-by: David Marchand <david.marchand@6wind.com>
Reviewed-by: Jan Viktorin <viktorin@rehivetech.com>
We are in static functions and those passed arguments can't be NULL.
Signed-off-by: David Marchand <david.marchand@6wind.com>
Reviewed-by: Jan Viktorin <viktorin@rehivetech.com>
The kernel fills new allocated (huge) pages with zeros.
DPDK just has to populate page tables to trigger the allocation.
Signed-off-by: Zhihong Wang <zhihong.wang@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Changing from 1/2 second to 1/10 doesn't compromise the precision,
and a 4/10 second is worth saving.
Signed-off-by: Zhihong Wang <zhihong.wang@intel.com>
The API has been removed but the symbols were still declared in the map.
Fixes: a421b86a4a02 ("ethdev: remove old flow director API")
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
test_mp_secondary was initially added by mistake.
rte_snprintf has been removed.
Fixes: 9d41beed24b0 ("lib: provide initial versioning")
Fixes: 3185322809c1 ("eal: remove rte_snprintf")
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
In eal_intr_proc_rxtx_intr, negative value may be used as argument to
a function expecting a positive value. If 'read' returns EAGAIN as
example, the bytes_read updates to a negative value which continue
be passed as argument for the next 'read'.
Coverity issue: 107115
Function read(fd, &buf, bytes_read) returns a negative number.
Assigning: signed variable bytes_read = read.
CID 107115 (#1 of 1): Argument cannot be negative
(NEGATIVE_RETURNS) bytes_read is passed to a parameter
that cannot be negative.
bytes_read = read(fd, &buf, bytes_read);
Fixes: c9f3ec1a0f3f ("eal/linux: add Rx interrupt control function")
Signed-off-by: Cunming Liang <cunming.liang@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Cryptodev was marked experimental and mbuf_offload depends on it.
The mbuf_offload library is one of the crypto area which requires
some discussions before having a stable API.
The experimental mark is also added to rte_cryptodev_configure()
to be sure one cannot miss it.
Fixes: 66874e55f550 ("cryptodev: mark experimental state")
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
The current implementation of VFIO will not with the new no-IOMMU mode
in 4.4 kernel. The original code assumed that IOMMU group zero would
never be used. Group numbers are assigned starting at zero, and up
until now the group numbers came from the hardware which is likely
to use group 0 for system devices that are not used with DPDK.
The fix is to allow 0 as a valid group and rearrange code
to split the return value from the group value.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
When guest is booting (or any othertime guest is busy) it is possible
for the small receive ring (256) to get full. If this happens the
vhost library should just return normally. It's current behavior
of logging just creates massive log spew/overflow which could even
act as a DoS attack against host.
Reported-by: Nathan Law <nlaw@brocade.com>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
This patch fixes the compile errors caused by lacking of "size_t"
definition in rte_hash.h.
The compile error exists on IBM POWER and ARM.
The errors are like:
In file included from app/test/test_hash_scaling.c:35:0:
rte_hash.h:70:70: error: unknown type name ‘size_t’
Fixes: 95da2f8e9c61 ("hash: customize compare function")
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
So that we will not break ABI in future extension by adding few more
fields.
Struct vhost_virtqueue is reserved with 16 qwords (the later vhost-live
migration support would at least consume 3 of them), and struct virtio_net
is reserved with a bit more, 64 qwords, as there is only one instance for
a virtio nic instance.
Note that both reservation are not placed at the end of the struct, but
instead before the last field, since both the last field at the two struct
take a lot spaces. Putting the reservation after it would divide those
reserved fields to another cacheline. (we might need fix them in future, btw)
Suggested-by: Panu Matilainen <pmatilai@redhat.com>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
RHEL 7.2 contains additional backports from newer upstream kernels.
Add RHEL_RELEASE_CODE logic for RHEL_RELEASE_VERSION(7,2) to pick up
the changes to kernel functions.
Signed-off-by: Lee Roberts <lee.roberts@hpe.com>
Implement vqtbl1q_u8 intrinsic function, which is not supported in armv7-a.
Signed-off-by: Jianbo Liu <jianbo.liu@linaro.org>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
CONFIG_* from config files can not be used in code.
Fixes: 12f45fa7e29b ("eal/arm: read timer from PMU if enabled")
Signed-off-by: Jianbo Liu <jianbo.liu@linaro.org>
Acked-by: Jan Viktorin <viktorin@rehivetech.com>
This is one of those trivial things git and other tools complain
about.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
The CHANNEL_CMDS_MAX_VM_CHANNELS is duplicated in the channel_commands
header file. This commit removes that duplication.
Fixes: 210c383e247b ("power: packet format for vm power management")
Signed-off-by: Aaron Conole <aconole@redhat.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
The rx_mbuf_alloc_failed counter was only cleared by virtio driver.
Now it is cleared by common rte_eth_stats_reset function for all
drivers at once.
Signed-off-by: Igor Ryzhov <iryzhov@nfware.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Fixes the mbuf allocation not initialized problem. This problem will cause
the mbufs not be able to freed back to mempool by rte_pktmbuf_free().
Fixes: ef3403fb6f9a ("port: source and sink")
Signed-off-by: Fan Zhang <roy.fan.zhang@intel.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Give user a chance to customize the hash key compare function.
The default rte_hash_cmp_eq function is set in the rte_hash_create
function, but these builtin ones may not good enough, so the user
may call this to override the default one.
Signed-off-by: Yu Nemo Wenbin <yuwb_bjy@ctbri.com.cn>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
rte_hash_create function was accidentally duplicated in
DPDK_2.1 in rte_hash_version.map.
Fixes: 473d1beb ("hash: allow to store data in hash table")
Reported-by: Ferruh Yigit <ferruh.yigit@intel.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
RTE_PMD_DEBUG_TRACE was changed also to support pedantic flag,
but not completely.
the macro changed only under the RTE_LIBRTE_ETHDEV_DEBUG define,
but when RTE_LIBRTE_ETHDEV_DEBUG is not defined the old format
was left.
fix the macro to support pedantic flag in any case.
Fixes: b974e4a40cb5 ("ethdev: make error checking macros public")
Signed-off-by: Yaacov Hazan <yaacovh@mellanox.com>
Irrelevant of the target, the preprocessor #ifdef SSE2 for the
grinder_pipe_exists function is inadequate since the __mm_testz_si128
function requires SSE4.1, PTEST instruction described in
https://en.wikipedia.org/wiki/SSE4#SSE4.1 (I do no have better spec
reference). I have bumped the preprocessor #ifdef to require SSE4.
The Atom N2600 does not have SSE4, http://ark.intel.com/products/58916,
and so I had trouble building rte_sched with optimized version of
grinder_pipe_exists, with following:
error: inlining failed in call to always_inline _mm_testz_si128’:
target specific option mismatch
GCC 4.9 correctly identifies my target as not having SSE4, and with
provided patch builds the non-optimized version of grinder_pipe_exists.
Signed-off-by: Mike Sowka <msowka@gmail.com>
The function rte_mempool_obj_iter used in mlx drivers
was not exported. So the driver loading was failing:
EAL: open shared lib librte_pmd_mlx4.so
EAL: x86_64-native-linuxapp-gcc/lib/librte_pmd_mlx4.so:
undefined symbol: rte_mempool_obj_iter
Fixes: 9d41beed24b0 ("lib: provide initial versioning")
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
There is a new function in the EAL API for internal use.
It has neither a proper prefix nor a .map export:
libethdev.so: undefined reference to `is_xen_dom0_supported'
Fixes: 719dbebceb81 ("xen: allow determining DOM0 at runtime")
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
gcc 4.3.4 does not include "immintrin.h", and will post below error:
lib/librte_sched/rte_sched.c:56:23: error:
immintrin.h: No such file or directory
This compiler issue is fixed with rte_vect.h
There is another issue, need SSE2 support
Fixes: 42ec27a0178a ("sched: enable SSE optimizations in config")
Signed-off-by: Michael Qiu <michael.qiu@intel.com>
