Compilation fails on 32 bits on Vhost_xen sample app, due to wrong casting:
examples/vhost_xen/vhost_monitor.c: In function ‘new_device’:
examples/vhost_xen/vhost_monitor.c:288:62: error: cast from pointer to integer
of different size [-Werror=pointer-to-int-cast]
Fixes: 47bd46112b ("xen: import xenvirt pmd and vhost_xen")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Compilation fails on 32 bits on Xen driver, due to wrong casting:
drivers/net/xenvirt/virtqueue.h: In function ‘virtqueue_enqueue_xmit’:
drivers/net/xenvirt/virtqueue.h:234:24: error: cast from pointer to integer
of different size [-Werror=pointer-to-int-cast]
start_dp[idx].addr = rte_pktmbuf_mtod(cookie, uint64_t);
^
Fixes: d6b324c00f ("mbuf: get DMA address")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Following discussions with Jan, here is a deprecation notice to prepare for
hotplug and rte_device changes to come in 16.07.
Signed-off-by: David Marchand <david.marchand@6wind.com>
Acked-by: Jan Viktorin <viktorin@rehivetech.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
We currently exposed way too many fields (or even structures) than
necessary. For example, vhost_virtqueue struct should NOT be exposed
to user at all: application just need to tell the right queue id to
locate a specific queue, and that's all. Instead, the structure should
be defined in an internal header file. With that, we could do any changes
to it we want, without worrying about that we may offense the painful
ABI rules.
Similar changes could be done to virtio_net struct as well, just exposing
very few fields that are necessary and moving all others to an internal
structure.
Huawei then suggested a more radical yet much cleaner one: just exposing
a virtio_net handle to application, just like the way kernel exposes an
fd to user for locating a specific file, and exposing some new functions
to access those old fields, such as flags, virt_qp_nb.
With this change, we're likely to be free from ABI violations forever
(well, except when we have to extend the virtio_net_device_ops struct).
For example, following nice cleanup would not be a blocking one then:
http://dpdk.org/ml/archives/dev/2016-February/033528.html
Suggested-by: Huawei Xie <huawei.xie@intel.com>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Acked-by: Panu Matilainen <pmatilai@redhat.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Add a programmer's guide section for cryptodev library.
Signed-off-by: Declan Doherty <declan.doherty@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
Details supported device features and algorithms for each crypto PMD.
Signed-off-by: Declan Doherty <declan.doherty@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
VxLAN & NVGRE are supported by x550. As we know HW can parse
the packet and tell SW the type info. For VxLAN & NVGRE packets
there's some change. HW will not tell SW the info of the outer
header but the inner header instead. But we always take the
info as it's for the outer header. So the packet type info is
not right when x550 receives VxLAN & NVGRE packets.
As x550 only supports IPv4 VxLAN & NVGRE packets, we can tell
the outer header of VxLAN is IPv4 + UDP, and the outer header
of NVGRE is IPv4 only. What we don't know is if there's
optional field in the outer IPv4 header.
This patch implement the support of packet type for VxLAN &
NVGRE. And it fixes the wrong packet type issue either.
BTW:
It doesn't fix any existing commit as although it resolve an
issue it's more like a new feature but not a fix.
Reported-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Performance-thread sample app is only supported for x86_64 targets,
so this commit adds a check to avoid compilation on other targets.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
In icc 14.0, compilation was broken:
examples/ipsec-secgw/sa.c(212): error: a designator for an anonymous
union member can only appear within braces corresponding to that anonymous union
.cipher = { RTE_CRYPTO_CIPHER_OP_ENCRYPT, RTE_CRYPTO_CIPHER_AES_CBC,
^
The member in anonymous union initialization should be inside '{}',
otherwise it will report an error.
Fixes: d299106e8e ("examples/ipsec-secgw: add IPsec sample application")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
error log:
ip_pipeline/pipeline/pipeline_routing_be.c:1537:
integer constant is too large for 'long' type
Fixes: 0ae7275810 ("examples/ip_pipeline: add more functions to routing pipeline")
Signed-off-by: Jasvinder Singh <jasvinder.singh@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
CID 120150:
Wrong size of the allocated memory. Passing argument as size of pointer
(8UL) instead of size of structure app_pipeline_firewall_rule.
Fixes: 67ebdbef0c ("examples/ip_pipeline: add bulk update of firewall rules")
Signed-off-by: Marcin Kerlin <marcinx.kerlin@intel.com>
This patch adds a notice that the API for the xstats
functionality will be modified in the 16.07 release, with
no backwards compatibility planned as it would require
code duplication in each PMD that supports xstats.
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Remy Horton <remy.horton@intel.com>
Acked-by: David Harton <dharton@cisco.com>
Acked-by: Maryam Tahhan <maryam.tahhan@intel.com>
Several new fields will be added to structure rte_port_source_params for
source port enhancement with pcap file reading support.
Signed-off-by: Fan Zhang <roy.fan.zhang@intel.com>
Acked-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Acked-by: Jasvinder Singh <jasvinder.singh@intel.com>
Acked-by: Piotr Azarewicz <piotrx.t.azarewicz@intel.com>
The SNOW3G PMD has a dependency on libsso which can be downloaded
after having passed some Intel validation about export restrictions.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Insert a hook at the end of the config procedure, after having
adapted the configuration to the environment variables and the options
passed to the script.
It allows to better tune the automatic configuration of the build tests
in a function located in the devel config file.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Any build option can be enabled or disabled by appending the end
of its name to the config name.
Examples:
+INTRINSICS to enable CONFIG_RTE_FORCE_INTRINSICS
~RXTX_CALLBACKS to disable CONFIG_RTE_ETHDEV_RXTX_CALLBACKS
These builtin (lowercase) options are also added for convenience:
+debug to enable every debug options
+default to set target machine as default
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
The global variables are reloaded between each build to allow
having different config options based on DPDK_TARGET.
Some checks can now be removed from the script as they can
be done in the devel config file.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
This example is not part of the baseline because of its
experimental state. That's why it must be tested separately.
Fixes: b700090c8c ("examples/performance-thread: mark as experimental")
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Building with "make install T=" is now deprecated.
The script will test only the standard "make" command.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
In order to ease packaging support of changes in DPDK build system,
introduce a decimal integer to compare version numbers.
It does not show the minor numbers as it is not meaningful for packaging.
Usage for DPDK 16.04:
% make showversionum
1604
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
In l3fwd-acl and l3fwd-power not all tx ports was included in tx_port_id
array, used to periodically drain only available ports. This caused that
some packets can remain in buffer when application stops to receiving
packets or when size of burst is small.
Fixes: e2366e74e0 ("examples: use buffered Tx")
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
When parsing crypto device type, the string was being copied
with strcpy(), which could overflow the destination buffer
(which is 32 byte long), so snprintf() should be used instead.
This fixes coverity issue 124575:
/examples/l2fwd-crypto/main.c: 1005 in l2fwd_crypto_parse_args_long_options()
>>> CID 124575: (STRING_OVERFLOW)
>>> You might overrun the 32 byte fixed-size string
"options->string_auth_algo" by copying "optarg" without checking the length.
1005 strcpy(options->string_auth_algo, optarg);
Fixes: 49f79e8648 ("examples/l2fwd-crypto: add missing string initialization")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
DPDK/app/test/test_cryptodev.c:
In function 'test_snow3g_encrypted_authentication.clone.3':
DPDK/x86_64-ivshmem-linuxapp-gcc/include/rte_memcpy.h:796:14: error:
array subscript is above array bounds
In lines like:
rte_memcpy(sym_op->cipher.iv.data, iv, iv_len);
when "iv" is 64 bytes long array, and "iv_len" is "unsigned int",
compiler tries to evaluate also a code for array size larger than 255 bytes
long and reports error "array subscript is above array bounds" in line:
rte_memcpy.h:796
rte_mov128((uint8_t *)dst + 128, (const uint8_t *)src + 128);
caused by evaluation to:
rte_mov128((uint8_t *)sym_op->cipher.iv.data + 128, (const uint8_t *)iv
+ 128);
where "iv" is 64 bytes long buffer and "iv + 128" point out of it, gcc 4.5.
Using uint8_t as a size of copied block prevents to evaluate in rte_memcpy
code for length bigger than 255, causing the problem.
Fixes: 8bdf665fe6 ("app/test: add SNOW 3G")
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
netif_rx() should be used in interrupt context. Replace it with
netif_rx_ni() which is safe to use in process context.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
If the vhost PMD were configured with more queues than the guest, the old
code would segfault in rte_vhost_enable_guest_notification due to a NULL
virtqueue pointer.
Fixes: ee584e9710 ("vhost: add driver on top of the library")
Signed-off-by: Rich Lane <rich.lane@bigswitch.com>
Tested-by: Ciara Loftus <ciara.loftus@intel.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
This patch aligns the logic used to check for the presence of
adjacent segments in has_adjacent_segments() with the logic used
in cleanup_segments() when actually deciding to concatenate or
not a pair of segments. Additionally, adjacent segments are
no longer considered overlapping to avoid generating errors for
segments that can happily coexist together.
This fixes an infinite loop that happened when segments where
adjacent in their physical or virtual addresses but not in their
ioremap addresses: has_adjacent_segments() reported the presence
of adjacent segments while cleanup_segments() was not considering
them for concatenation, resulting in an infinite loop since the
result of has_adjacent_segments() is used in the decision to
continue looping in cleanup_segments().
Signed-off-by: David Verbeiren <david.verbeiren@intel.com>
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
It fix coverity issue:
CID 124557 (#1 of 1): Unchecked return value (CHECKED_RETURN)
check_return: Calling rte_eth_tx_buffer_set_err_callback without
checking return value (as is done elsewhere 6 out of 7 times).
Fixes: d6c99e62c8 ("ethdev: add buffered Tx")
Signed-off-by: Slawomir Mrozowicz <slawomirx.mrozowicz@intel.com>
Enable "other kdrv" because both NICs require kernel support to work.
Unicast and multicast MAC filters are also enabled as both address types can
be filtered on through the MAC add/remove/set callbacks.
Fixes: e86b85ca75 ("doc: fill nics features matrix for mlx")
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Fixes: 83a4a15404 ("doc: fill nics features matrix for e1000/igb and ixgbe")
Reported-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
This patch updates the titles in the multiprocess memory image
to read "Primary Process" and "Secondary Process" instead of
"DPDK Server Process" and "Customer Client Process".
The rest of the image has been converted from PNG to SVG.
Signed-off-by: Harry van Haaren <harry.van.haaren@intel.com>
Explain how to create/initialize virtual crypto PMDs,
through command line and within an application.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
A new process to request the libsso library required by the SNOW3G PMD
has been put in place, through a website, replacing the previous email method.
This commit updates the SNOW3G documentation, to reflect this change.
Since the library does not support newer gcc versions, the documentation
also contains a patch to make the library work with gcc > 5.0.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Declan Doherty <declan.doherty@intel.com>
The cryptodev API was introduced in the DPDK 2.2 release.
Since then it has
- been reviewed and iterated for the DPDK 16.04 release
- had extensive use by the l2fwd-crypto app,
the ipsec-secgw example app,
the test app.
We believe it is now stable and the EXPERIMENTAL label should be removed.
Signed-off-by: Fiona Trahe <fiona.trahe@intel.com>
Acked-by: Thomas Monjalon <thomas.monjalon@6wind.com>
renamed rte_cryptodev_sym_session.type -> dev_type
(as it's not a session type, but a device type)
renamed rte_crypto_sym_op.type -> sess_type
(as it's not an op type, but a session type)
Signed-off-by: Fiona Trahe <fiona.trahe@intel.com>
AES-GCM PMD only supports 128-bit keys, but not 192 and 256,
which the capabilities structure was reporting.
Fixes: 26c2e4ad5a ("cryptodev: add capabilities discovery")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
After some testing, it was found that retrieving numa information
about a vhost device via a call to get_mempolicy is more
accurate when performed during the new_device callback versus
the vring_state_changed callback, in particular upon initial boot
of the VM. Performing this check during new_device is also
potentially more efficient as this callback is only triggered once
during device initialisation, compared with vring_state_changed
which may be called multiple times depending on the number of
queues assigned to the device.
Reorganise the code to perform this check and assign the correct
socket_id to the device during the new_device callback.
Fixes: ee584e9710 ("vhost: add driver on top of the library")
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
The previous code in func_reentrancy autotest was doing in parallel
something close to:
name = "common_name";
do several times {
obj = allocate_an_object(name) // obj = ring, mempool, hash, lpm, ...
if (obj == NULL && lookup(name) == NULL)
return TEST_FAIL;
}
This code is not safe. For instance:
mempool_create() is called on core 0, it creates a ring. At the same
time on core 1, mempool_create() is called too and the creation of the
ring fails (EEXIST). But the mempool lookup can fail on core 1 if
the mempool is not added in the list by core 0.
This commit fixes the func_reentrancy autotest that now works with all
tested class of objects.
Fixes: 104a92bd02 ("app: add reentrancy tests")
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
