dpdk.git
5 years agotest/mem: check external memory without IOVA table
Anatoly Burakov [Fri, 21 Dec 2018 11:29:01 +0000 (11:29 +0000)]
test/mem: check external memory without IOVA table

Currently, only scenario with valid IOVA table is tested. Fix this
by also testing without IOVA table - in these cases, EAL should
always return RTE_BAD_IOVA for all memsegs, and contiguous memzone
allocation should fail.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agotest/mem: refactor and rename functions
Anatoly Burakov [Fri, 21 Dec 2018 11:29:00 +0000 (11:29 +0000)]
test/mem: refactor and rename functions

We will be adding a new extmem test that will behave roughly similar
to already existing, so clarify function names to distinguish between
these tests, as well as factor out the common parts.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agomalloc: fix deadlock when reading stats
Anatoly Burakov [Fri, 21 Dec 2018 12:26:05 +0000 (12:26 +0000)]
malloc: fix deadlock when reading stats

Currently, malloc statistics and external heap creation code
use memory hotplug lock as a way to synchronize accesses to
heaps (as in, locking the hotplug lock to prevent list of heaps
from changing under our feet). At the same time, malloc
statistics code will also lock the heap because it needs to
access heap data and does not want any other thread to allocate
anything from that heap.

In such scheme, it is possible to enter a deadlock with the
following sequence of events:

thread 1 thread 2
rte_malloc()
rte_malloc_dump_stats()
take heap lock
take hotplug lock
failed to allocate,
attempt to take
hotplug lock
attempt to take heap lock

Neither thread will be able to continue, as both of them are
waiting for the other one to drop the lock. Adding an
additional lock will require an ABI change, so instead of
that, make malloc statistics calls thread-unsafe with
respect to creating/destroying heaps.

Fixes: 72cf92b31855 ("malloc: index heaps using heap ID rather than NUMA node")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agodevtools: fix return of forbidden addition checks
Arnon Warshavsky [Tue, 18 Dec 2018 15:19:00 +0000 (17:19 +0200)]
devtools: fix return of forbidden addition checks

Explicitly collect the error code of the multiple awk script calls.

Bugzilla ID: 165
Fixes: 4d4c612e6a30 ("devtools: check wrong svg include in guides")
Cc: stable@dpdk.org
Signed-off-by: Arnon Warshavsky <arnon@qwilt.com>
5 years agohash: fix out-of-bound write while freeing key slot
Honnappa Nagarahalli [Thu, 22 Nov 2018 02:51:56 +0000 (20:51 -0600)]
hash: fix out-of-bound write while freeing key slot

Add a debug check for out-of-bound write while freeing the key slot.

Coverity issue: 325733
Fixes: e605a1d36ca7 ("hash: add lock-free r/w concurrency")
Cc: stable@dpdk.org
Signed-off-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Reviewed-by: Steve Capper <steve.capper@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
5 years agohash: fix return of bulk lookup
Jeff Shaw [Sat, 8 Dec 2018 00:01:26 +0000 (16:01 -0800)]
hash: fix return of bulk lookup

The __rte_hash_lookup_bulk() function returns void, and therefore
should not return with an expression. This commit fixes the following
compiler warning when attempting to compile with "-pedantic -std=c11".

  warning: ISO C forbids ‘return’ with expression, in function
           returning void [-Wpedantic]

Fixes: 9eca8bd7a61c ("hash: separate lock-free and r/w lock lookup")
Cc: stable@dpdk.org
Signed-off-by: Jeff Shaw <jeffrey.b.shaw@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
5 years agopower: add p-state driver compatibility
Liang Ma [Thu, 20 Dec 2018 14:43:42 +0000 (14:43 +0000)]
power: add p-state driver compatibility

Previously, in order to use the power library, it was necessary
for the user to disable the intel_pstate driver by adding
“intel_pstate=disable” to the kernel command line for the system,
which causes the acpi_cpufreq driver to be loaded in its place.

This patch adds the ability for the power library use the intel-pstate
driver.

It adds a new suite of functions behind the current power library API,
and will seamlessly set up the user facing API function pointers to
the relevant functions depending on whether the system is running with
acpi_cpufreq kernel driver, intel_pstate kernel driver or in a guest,
using kvm. The library API and ABI is unchanged.

Signed-off-by: Liang Ma <liang.j.ma@intel.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: David Hunt <david.hunt@intel.com>
5 years agoeal: close multi-process socket during cleanup
Qi Zhang [Thu, 20 Dec 2018 12:51:14 +0000 (20:51 +0800)]
eal: close multi-process socket during cleanup

When secondary process quit, the mp_socket* file still exist, that
cause rte_mp_request_sync fail when try to send message on a floating
socket.

The patch fix the issue by introduce a function rte_mp_channel_cleanup.
This function will be called by rte_eal_cleanup and it will close the
mp socket and delete the mp_socket* file.

Fixes: bacaa2754017 ("eal: add channel for multi-process communication")
Cc: stable@dpdk.org
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
5 years agoeal: add 64-bit log2 function
Anatoly Burakov [Thu, 20 Dec 2018 12:09:50 +0000 (12:09 +0000)]
eal: add 64-bit log2 function

Add missing implementation for 64-bit log2 function, and extend
the unit test to test this new function. Also, remove duplicate
reimplementation of this function from testpmd and memalloc.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agoeal: add 64-bit fls function
Anatoly Burakov [Thu, 20 Dec 2018 12:09:49 +0000 (12:09 +0000)]
eal: add 64-bit fls function

Add missing implementation for 64-bit fls function, and extend
unit test to test the new function as well.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agoeal: add 64-bit bsf and 32-bit safe bsf functions
Anatoly Burakov [Thu, 20 Dec 2018 12:09:48 +0000 (12:09 +0000)]
eal: add 64-bit bsf and 32-bit safe bsf functions

Add an rte_bsf64 function that follows the convention of existing
rte_bsf32 function. Also, add missing implementation for safe
version of rte_bsf32, and implement unit tests for all recently
added bsf varieties.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agobitmap: remove deprecated 64-bit bsf function
Anatoly Burakov [Thu, 20 Dec 2018 12:09:47 +0000 (12:09 +0000)]
bitmap: remove deprecated 64-bit bsf function

The function rte_bsf64 was deprecated in a previous release, so
remove the function, and the deprecation notice associated with
it.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agoeal: fix runtime directory cleanup in noshconf mode
Anatoly Burakov [Thu, 20 Dec 2018 11:11:48 +0000 (11:11 +0000)]
eal: fix runtime directory cleanup in noshconf mode

When using --no-shconf or --in-memory modes, there is no runtime
directory to be created, so there is no point in attempting to
clean it.

Fixes: 0a529578f162 ("eal: clean up unused files on initialization")

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agotest/fbarray: add to meson
Anatoly Burakov [Wed, 5 Dec 2018 16:26:00 +0000 (16:26 +0000)]
test/fbarray: add to meson

Currently, fbarray autotest is only built by make, but is
missing from meson build files.

Fixes: 7985860c18af ("test/fbarray: add autotests")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
5 years agotest/mem: add external mem autotest to meson
Anatoly Burakov [Wed, 5 Dec 2018 16:25:48 +0000 (16:25 +0000)]
test/mem: add external mem autotest to meson

The 'external_mem_autotest' was defined in the meson build, but
the actual source file was not being compiled by meson.

Fixes: b270daa43b3d ("test: support external memory")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agodoc: remove note on memory mode limitation in multi-process
Anatoly Burakov [Thu, 6 Dec 2018 09:30:33 +0000 (09:30 +0000)]
doc: remove note on memory mode limitation in multi-process

Memory mode flags are now shared between primary and secondary
processes, so the in documentation about limitations is no longer
necessary.

Fixes: 64cdfc35aaad ("mem: store memory mode flags in shared config")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agotest/mem: check segment fd API
Anatoly Burakov [Thu, 13 Dec 2018 11:43:19 +0000 (11:43 +0000)]
test/mem: check segment fd API

Use memory autotest to also test segment fd API. This will not do
any checks - just see if the relevant API's return success or
indicate that the API is not supported.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Tiwei Bie <tiwei.bie@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
5 years agomem: use memfd for no-huge mode
Anatoly Burakov [Thu, 13 Dec 2018 11:43:18 +0000 (11:43 +0000)]
mem: use memfd for no-huge mode

When running in no-huge mode, we anonymously allocate our memory.
While this works for regular NICs and vdev's, it's not suitable
for memory sharing scenarios such as virtio with vhost_user
backend.

To fix this, allocate no-huge memory using memfd, and register
it with memalloc just like any other memseg fd. This will enable
using rte_memseg_get_fd() API with --no-huge EAL flag.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Tiwei Bie <tiwei.bie@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
5 years agomem: allow setting up segment list fd
Anatoly Burakov [Thu, 13 Dec 2018 11:43:17 +0000 (11:43 +0000)]
mem: allow setting up segment list fd

Currently, only segment fd's for multi-file segments are supported,
while for memfd-backed no-huge memory we need single-file segments
mode. Add support for single-file segments in the internal API.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Tiwei Bie <tiwei.bie@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
5 years agomem: check for memfd support in segment fd API
Anatoly Burakov [Thu, 13 Dec 2018 11:43:16 +0000 (11:43 +0000)]
mem: check for memfd support in segment fd API

If memfd support was not compiled, or hugepage memfd support
is not available at runtime, the API will now return proper
error code, indicating that this API is unsupported. This
changes the API, so document the changes.

Fixes: 41dbdb68723b ("mem: add external API to retrieve page fd")
Fixes: 3a44687139eb ("mem: allow querying offset into segment fd")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Tiwei Bie <tiwei.bie@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
5 years agomem: fix segment fd API error code for external segment
Anatoly Burakov [Thu, 13 Dec 2018 11:43:15 +0000 (11:43 +0000)]
mem: fix segment fd API error code for external segment

Segment fd API does not support getting segment fd's from
externally allocated memory, so return proper error code
on any attempts to do so. This changes API behavior, so
document the change as well.

Fixes: 5282bb1c3695 ("mem: allow memseg lists to be marked as external")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Tiwei Bie <tiwei.bie@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
5 years agomem: allow usage of non-heap external memory in multiprocess
Anatoly Burakov [Thu, 20 Dec 2018 15:32:41 +0000 (15:32 +0000)]
mem: allow usage of non-heap external memory in multiprocess

Add multiprocess support for externally allocated memory areas that
are not added to DPDK heap (and add relevant doc sections).

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
5 years agomem: allow registering external memory areas
Anatoly Burakov [Thu, 20 Dec 2018 15:32:40 +0000 (15:32 +0000)]
mem: allow registering external memory areas

The general use-case of using external memory is well covered by
existing external memory API's. However, certain use cases require
manual management of externally allocated memory areas, so this
memory should not be added to the heap. It should, however, be
added to DPDK's internal structures, so that API's like
``rte_virt2memseg`` would work on such external memory segments.

This commit adds such an API to DPDK. The new functions will allow
to register and unregister externally allocated memory areas, as
well as documentation for them.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
5 years agomalloc: separate destroying memseg list and heap data
Anatoly Burakov [Thu, 20 Dec 2018 15:32:39 +0000 (15:32 +0000)]
malloc: separate destroying memseg list and heap data

Currently, destroying external heap chunk and its memseg list is
part of one process. When we will gain the ability to unregister
external memory from DPDK that doesn't have any heap structures
associated with it, we need to be able to find and destroy
memseg lists as well as heap data separately.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
5 years agomalloc: separate creating memseg list and malloc heap
Anatoly Burakov [Thu, 20 Dec 2018 15:32:38 +0000 (15:32 +0000)]
malloc: separate creating memseg list and malloc heap

Currently, creating external malloc heap involves also creating
a memseg list backing that malloc heap. We need to have them as
separate functions, to allow creating memseg lists without
creating a malloc heap.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
5 years agomalloc: make alignment requirements more stringent
Anatoly Burakov [Fri, 14 Dec 2018 11:54:01 +0000 (11:54 +0000)]
malloc: make alignment requirements more stringent

The external heaps API already implicitly expects start address
of the external memory area to be page-aligned, but it is not
enforced or documented. Fix this by implementing additional
parameter checks at memory add call, and document the page
alignment requirement explicitly.

Fixes: 7d75c31014f7 ("malloc: allow adding memory to named heaps")
Cc: stable@dpdk.org
Suggested-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
5 years agomalloc: fix duplicate mem event notification
Anatoly Burakov [Tue, 11 Dec 2018 16:48:28 +0000 (16:48 +0000)]
malloc: fix duplicate mem event notification

We already trigger a mem event notification inside the walk function,
no need to do it twice.

Fixes: f32c7c9de961 ("malloc: enable event callbacks for external memory")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agomalloc: notify primary process about hotplug in secondary
Seth Howell [Fri, 7 Dec 2018 20:10:42 +0000 (13:10 -0700)]
malloc: notify primary process about hotplug in secondary

When secondary process hotplugs memory, it sends a request
to primary, which then performs the real mmap() and sends
sync requests to all secondary processes. Upon receiving
such sync request, each secondary process will notify the
upper layers of hotplugged memory (and will call all
locally registered event callbacks).

In the end we'll end up with memory event callbacks fired
in all the processes except the primary, which is a bug.

This gets critical if memory is hotplugged while a VFIO
device is attached, as the VFIO memory registration -
which is done from a memory event callback present in the
primary process only - is never called.

After this patch, a primary process fires memory event
callbacks before secondary processes start their
synchronizations - both for hotplug and hotremove.

Fixes: 07dcbfe0101f ("malloc: support multiprocess memory hotplug")
Cc: stable@dpdk.org
Signed-off-by: Seth Howell <seth.howell@intel.com>
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agomalloc: fix finding maximum contiguous IOVA size
Yongseok Koh [Wed, 12 Dec 2018 11:10:54 +0000 (03:10 -0800)]
malloc: fix finding maximum contiguous IOVA size

malloc_elem_find_max_iova_contig() could return invalid size due to a
missing sanity check. The following gdb output shows how 'cur_size' can be
invalid in find_biggest_element().

(gdb) p/x cur_size
$4 = 0xffffffffffe42900
(gdb) p elem
$1 = (struct malloc_elem *) 0x12e842000
(gdb) p *elem
$2 = {heap = 0x7ffff7ff387c, prev = 0x12e831fc0, next =
0x12e842900, free_list = {le_next = 0x109538000, le_prev =
0x7ffff7ff3894}, msl = 0x7ffff7ff107c, state = ELEM_FREE,
pad = 0, size = 2304}
(gdb) p *elem->msl
$5 = {{base_va = 0x100200000, addr_64 = 4297064448}, page_sz =
2097152, socket_id = 0, version = 790, len = 17179869184,
external = 0, memseg_arr = {name = "memseg-2048k-0-0",
'\000' <repeats 47 times>, count = 493, len = 8192, elt_sz
= 48, data = 0x10002e000, rwlock = {cnt = 0}}}

Fixes: 9fe6bceafd51 ("malloc: add finding biggest free IOVA-contiguous element")
Cc: stable@dpdk.org
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agomalloc: add option --match-allocations
Jim Harris [Fri, 14 Dec 2018 17:13:03 +0000 (10:13 -0700)]
malloc: add option --match-allocations

SPDK uses the rte_mem_event_callback_register API to
create RDMA memory regions (MRs) for newly allocated regions
of memory. This is used in both the SPDK NVMe-oF target
and the NVMe-oF host driver.

DPDK creates internal malloc_elem structures for these
allocated regions. As users malloc and free memory, DPDK
will sometimes merge malloc_elems that originated from
different allocations that were notified through the
registered mem_event callback routine. This results
in subsequent allocations that can span across multiple
RDMA MRs. This requires SPDK to check each DPDK buffer to
see if it crosses an MR boundary, and if so, would have to
add considerable logic and complexity to describe that
buffer before it can be accessed by the RNIC. It is somewhat
analagous to rte_malloc returning a buffer that is not
IOVA-contiguous.

As a malloc_elem gets split and some of these elements
get freed, it can also result in DPDK sending an
RTE_MEM_EVENT_FREE notification for a subset of the
original RTE_MEM_EVENT_ALLOC notification. This is also
problematic for RDMA memory regions, since unregistering
the memory region is all-or-nothing. It is not possible
to unregister part of a memory region.

To support these types of applications, this patch adds
a new --match-allocations EAL init flag. When this
flag is specified, malloc elements from different
hugepage allocations will never be merged. Memory will
also only be freed back to the system (with the requisite
memory event callback) exactly as it was originally
allocated.

Since part of this patch is extending the size of struct
malloc_elem, we also fix up the malloc autotests so they
do not assume its size exactly fits in one cacheline.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agomemzone: fix unlock on initialization failure
Gao Feng [Fri, 7 Dec 2018 01:20:08 +0000 (09:20 +0800)]
memzone: fix unlock on initialization failure

The RTE_PROC_PRIMARY error handler lost the unlock statement in the
current codes. Now unlock and return in one place to fix it.

Fixes: 49df3db84883 ("memzone: replace memzone array with fbarray")
Cc: stable@dpdk.org
Signed-off-by: Gao Feng <davidfgao@tencent.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agovfio: support 64KB kernel page size
Tone Zhang [Wed, 12 Dec 2018 11:25:59 +0000 (19:25 +0800)]
vfio: support 64KB kernel page size

With a larger PAGE_SIZE it is possible for the MSI table to very
close to the end of the BAR s.t. when we align the start and end
of the MSI table to the PAGE_SIZE, the end offset of the MSI
table is out of the PCI BAR boundary.

This patch addresses the issue by comparing both the start and the
end offset of the MSI table with the BAR size, and skip the mapping
if it is out of Bar scope.

The patch fixes the debug log as below:
EAL: Skipping BAR0

Signed-off-by: Tone Zhang <tone.zhang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Reviewed-by: Steve Capper <steve.capper@arm.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agoeal: check peer allocation in multi-process request
Gao Feng [Wed, 5 Dec 2018 06:19:24 +0000 (14:19 +0800)]
eal: check peer allocation in multi-process request

Add the check for null peer pointer like the bundle pointer in the mp request
handler. They should follow same style. And add some logs for nomem cases.

Signed-off-by: Gao Feng <davidfgao@tencent.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agoeal: fix leak on multi-process request error
Gao Feng [Wed, 5 Dec 2018 02:50:25 +0000 (10:50 +0800)]
eal: fix leak on multi-process request error

When rte_eal_alarm_set failed, need to free the bundle mem in the
error handler of handle_primary_request and handle_secondary_request.

Fixes: 244d5130719c ("eal: enable hotplug on multi-process")
Fixes: ac9e4a17370f ("eal: support attach/detach shared device from secondary")
Cc: stable@dpdk.org
Signed-off-by: Gao Feng <davidfgao@tencent.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agoeal: fix detection of duplicate option register
Gaetan Rivet [Mon, 17 Dec 2018 09:25:59 +0000 (10:25 +0100)]
eal: fix detection of duplicate option register

Missing brackets around the if means that the loop will end at
its first iteration.

Fixes: 2395332798d0 ("eal: add option register infrastructure")
Cc: stable@dpdk.org
Signed-off-by: Gaetan Rivet <gaetan.rivet@6wind.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
5 years agoeal: fix missing newline in a log
Keith Wiles [Sun, 16 Dec 2018 23:01:03 +0000 (17:01 -0600)]
eal: fix missing newline in a log

Add a missing newline to a RTE_LOG message.

Fixes: 2395332798d0 ("eal: add option register infrastructure")
Cc: stable@dpdk.org
Signed-off-by: Keith Wiles <keith.wiles@intel.com>
5 years agoip_frag: fix IPv6 when MTU sizes not aligned to 8 bytes
Chas Williams [Tue, 27 Nov 2018 04:56:13 +0000 (23:56 -0500)]
ip_frag: fix IPv6 when MTU sizes not aligned to 8 bytes

The same issue was fixed on for the ipv4 version of this routine in
commit 8d4d3a4f7337 ("ip_frag: handle MTU sizes not aligned to 8 bytes").
Briefly, the size of an ipv6 header is always 40 bytes.  With an MTU of
1500, this will never produce a multiple of 8 bytes for the frag_size
and this routine can never succeed. Since RTE_ASSERTS are disabled by
default, this failure is typically ignored.

To fix this, round down to the nearest 8 bytes and use this when
producing the fragments.

Fixes: 0aa31d7a5929 ("ip_frag: add IPv6 fragmentation support")
Cc: stable@dpdk.org
Signed-off-by: Chas Williams <chas3@att.com>
Acked-by: Luca Boccassi <bluca@debian.org>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
5 years agoexamples/ipv4_multicast: remove useless mbuf info copy
Wei Zhao [Wed, 21 Nov 2018 09:49:17 +0000 (17:49 +0800)]
examples/ipv4_multicast: remove useless mbuf info copy

There is no need for these useless information and
it had better be removed in order to not confuse users.

Signed-off-by: Wei Zhao <wei.zhao1@intel.com>
5 years agoexamples/power: increase max cores to 256
David Hunt [Fri, 14 Dec 2018 13:31:37 +0000 (13:31 +0000)]
examples/power: increase max cores to 256

Increase the number of addressable cores from 64 to 256. Also remove the
warning that incresing this number beyond 64 will cause problems (because
of the previous use of uint64_t masks). Now this number can be increased
significantly without causing problems.

Signed-off-by: David Hunt <david.hunt@intel.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agoexamples/power: allow VM to use lcores over 63
David Hunt [Fri, 14 Dec 2018 13:31:36 +0000 (13:31 +0000)]
examples/power: allow VM to use lcores over 63

Extending the functionality to allow vms to power manage cores beyond 63.

Signed-off-by: David Hunt <david.hunt@intel.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agoexamples/power: remove mask functions
David Hunt [Fri, 14 Dec 2018 13:31:35 +0000 (13:31 +0000)]
examples/power: remove mask functions

Since we're moving to allowing greater than 64 cores, the mask functions
that use uint64_t to perform functions on a masked set of cores are no
longer needed, so removing them.

Signed-off-by: David Hunt <david.hunt@intel.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agoexamples/power: change 64-bit masks to arrays
David Hunt [Fri, 14 Dec 2018 13:31:34 +0000 (13:31 +0000)]
examples/power: change 64-bit masks to arrays

vm_power_manager currently makes use of uint64_t masks to keep track of
cores in use, limiting use of the app to only being able to manage the
first 64 cores in a multi-core system. Many modern systems have core
counts greater than 64, so this limitation needs to be removed.

This patch converts the relevant 64-bit masks to character arrays.

Signed-off-by: David Hunt <david.hunt@intel.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agotest/rwlock: add new test-cases
Konstantin Ananyev [Wed, 19 Dec 2018 18:07:17 +0000 (18:07 +0000)]
test/rwlock: add new test-cases

Add few functional and perfomance tests
for rte_rwlock_read_trylock() and rte_rwlock_write_trylock().

Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
5 years agorwlock: introduce try semantics
Konstantin Ananyev [Wed, 19 Dec 2018 18:07:16 +0000 (18:07 +0000)]
rwlock: introduce try semantics

Introduce rte_rwlock_read_trylock() and rte_rwlock_write_trylock().

Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
5 years agotimer: fix race condition
Erik Gabriel Carrillo [Wed, 19 Dec 2018 16:09:34 +0000 (10:09 -0600)]
timer: fix race condition

rte_timer_manage() adds expired timers to a "run list", and walks the
list, transitioning each timer from the PENDING to the RUNNING state.
If another lcore resets or stops the timer at precisely this
moment, the timer state would instead be set to CONFIG by that other
lcore, which would cause timer_manage() to skip over it. This is
expected behavior.

However, if a timer expires quickly enough, there exists the
following race condition that causes the timer_manage() routine to
misinterpret a timer in CONFIG state, resulting in lost timers:

- Thread A:
  - starts a timer with rte_timer_reset()
  - the timer is moved to CONFIG state
  - the spinlock associated with the appropriate skiplist is acquired
  - timer is inserted into the skiplist
  - the spinlock is released
- Thread B:
  - executes rte_timer_manage()
  - find above timer as expired, add it to run list
  - walk run list, see above timer still in CONFIG state, unlink it from
    run list and continue on
- Thread A:
  - move timer to PENDING state
  - return from rte_timer_reset()
  - timer is now in PENDING state, but not actually linked into a
    pending list or a run list and will never get processed further
    by rte_timer_manage()

This commit fixes this race condition by only releasing the spinlock
after the timer state has been transitioned from CONFIG to PENDING,
which prevents rte_timer_manage() from seeing an incorrect state.

Fixes: 9b15ba895b9f ("timer: use a skip list")
Cc: stable@dpdk.org
Signed-off-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
5 years agobbdev: add missing experimental tags and map entries
Amr Mokhtar [Wed, 19 Dec 2018 10:00:27 +0000 (10:00 +0000)]
bbdev: add missing experimental tags and map entries

- add missing APIs to map file
- add experimental tag to all bbdev APIs

Signed-off-by: Amr Mokhtar <amr.mokhtar@intel.com>
5 years agoapp/compress-perf: refactor code
Tomasz Jozwiak [Wed, 12 Dec 2018 12:08:05 +0000 (13:08 +0100)]
app/compress-perf: refactor code

Code refactoring to separate validation from benchmarking part.
Added op's status checking after rte_compressdev_dequeue_burst
function.

Signed-off-by: Tomasz Jozwiak <tomaszx.jozwiak@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Acked-by: Lee Daly <lee.daly@intel.com>
Acked-by: Shally Verma <shally.verma@caviumnetworks.com>
5 years agoapp/compress-perf: add dynamic compression test
Tomasz Jozwiak [Wed, 12 Dec 2018 12:08:04 +0000 (13:08 +0100)]
app/compress-perf: add dynamic compression test

Added dynamic compression feature into compression perf. test.

Signed-off-by: Tomasz Jozwiak <tomaszx.jozwiak@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Acked-by: Lee Daly <lee.daly@intel.com>
Acked-by: Shally Verma <shally.verma@caviumnetworks.com>
5 years agodoc: add details for compress-perf app
Tomasz Jozwiak [Wed, 12 Dec 2018 12:08:03 +0000 (13:08 +0100)]
doc: add details for compress-perf app

Added:
 -  initial version of compression performance test
    description file.
 -  release note in release_18_11.rst

Updated index.rst file

Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Signed-off-by: Tomasz Jozwiak <tomaszx.jozwiak@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Acked-by: Lee Daly <lee.daly@intel.com>
Acked-by: Shally Verma <shally.verma@caviumnetworks.com>
5 years agoapp/compress-perf: add performance measurement
Tomasz Jozwiak [Wed, 12 Dec 2018 12:08:02 +0000 (13:08 +0100)]
app/compress-perf: add performance measurement

Added performance measurement part into compression perf. test.

Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Signed-off-by: Tomasz Jozwiak <tomaszx.jozwiak@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Acked-by: Lee Daly <lee.daly@intel.com>
Acked-by: Shally Verma <shally.verma@caviumnetworks.com>
5 years agoapp/compress-perf: add parser
Tomasz Jozwiak [Wed, 12 Dec 2018 12:08:01 +0000 (13:08 +0100)]
app/compress-perf: add parser

Added parser part into compression perf. test.

Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Signed-off-by: Tomasz Jozwiak <tomaszx.jozwiak@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Acked-by: Lee Daly <lee.daly@intel.com>
Acked-by: Shally Verma <shally.verma@caviumnetworks.com>
5 years agocompress/qat: fix dequeue error counter
Tomasz Jozwiak [Fri, 14 Dec 2018 12:11:47 +0000 (13:11 +0100)]
compress/qat: fix dequeue error counter

This patch increments error counter (stats.dequeue_err_count)
in case of any error detection during qat_comp_process_response
function.

Fixes: 3cc14fc48e35 ("compress/qat: check that correct firmware is in use")
Fixes: 32842f2a6d7d ("compress/qat: create FW request and process response")
Cc: stable@dpdk.org
Signed-off-by: Tomasz Jozwiak <tomaszx.jozwiak@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
5 years agocompress/qat: fix return on building request error
Tomasz Jozwiak [Fri, 14 Dec 2018 11:19:31 +0000 (12:19 +0100)]
compress/qat: fix return on building request error

This patch fixes error status which should be set inside
qat_comp_build_request function in case any errors are detected.
In these cases op.status is set to
RTE_COMP_OP_STATUS_INVALID_ARGS to help application debug.

Fixes: 1947bd18580b ("compress/qat: support scatter-gather buffers")
Cc: stable@dpdk.org
Signed-off-by: Tomasz Jozwiak <tomaszx.jozwiak@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
5 years agocommon/qat: remove check of valid firmware response
Tomasz Jozwiak [Fri, 14 Dec 2018 11:19:30 +0000 (12:19 +0100)]
common/qat: remove check of valid firmware response

This reverts commit d09973f6c4df ("common/qat: fix for invalid
response from firmware") due to incorrectly reporting failures
on some older firmware versions.

Fixes: d09973f6c4df ("common/qat: fix for invalid response from firmware")
Cc: stable@dpdk.org
Signed-off-by: Tomasz Jozwiak <tomaszx.jozwiak@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
5 years agocrypto/qat: fix message for NULL algo setting unused counter
Arek Kusztal [Wed, 12 Dec 2018 19:59:04 +0000 (20:59 +0100)]
crypto/qat: fix message for NULL algo setting unused counter

NULL algo algo does not to set counter flag so it should be zeroed.

Fixes: db0e952a5c01 ("crypto/qat: add NULL capability")
Cc: stable@dpdk.org
Signed-off-by: Arek Kusztal <arkadiuszx.kusztal@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Acked-by: Marko Kovacevic <marko.kovacevic@intel.com>
5 years agocrypto/qat: fix message for CCM when setting unused counter
Arek Kusztal [Wed, 12 Dec 2018 19:59:03 +0000 (20:59 +0100)]
crypto/qat: fix message for CCM when setting unused counter

AES-CCM algo does not to set counter flag so it should be zeroed.

Fixes: ab56c4d9ed9a ("crypto/qat: support AES-CCM")
Cc: stable@dpdk.org
Signed-off-by: Arek Kusztal <arkadiuszx.kusztal@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Acked-by: Marko Kovacevic <marko.kovacevic@intel.com>
5 years agocrypto/qat: fix block size error handling
Arek Kusztal [Wed, 12 Dec 2018 19:59:02 +0000 (20:59 +0100)]
crypto/qat: fix block size error handling

Error code of qat_hash_get_block_size needs to be handle properly.

Fixes: 10b49880e3c5 ("crypto/qat: make the session struct variable in size")
Cc: stable@dpdk.org
Signed-off-by: Arek Kusztal <arkadiuszx.kusztal@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Tested-by: Marko Kovacevic <marko.kovacevic@intel.com>
Acked-by: Marko Kovacevic <marko.kovacevic@intel.com>
5 years agobb/turbo_sw: update for FlexRAN 18.09
Kamil Chalupnik [Wed, 5 Dec 2018 10:40:04 +0000 (11:40 +0100)]
bb/turbo_sw: update for FlexRAN 18.09

Update BBDEV Turbo SW driver and download/build instructions for
FlexRAN 18.09 release

Signed-off-by: Kamil Chalupnik <kamilx.chalupnik@intel.com>
Acked-by: Amr Mokhtar <amr.mokhtar@intel.com>
5 years agobb/turbo_sw: fix dynamic linking
Kamil Chalupnik [Mon, 3 Dec 2018 13:48:11 +0000 (14:48 +0100)]
bb/turbo_sw: fix dynamic linking

Building Turbo Software as shared library for AVX512 failed
due to wrong order of library in the library list (LDLIBS)

Fixes: b8cfe2c9aed2 ("bb/turbo_sw: add software turbo driver")
Cc: stable@dpdk.org
Signed-off-by: Kamil Chalupnik <kamilx.chalupnik@intel.com>
Acked-by: Amr Mokhtar <amr.mokhtar@intel.com>
5 years agoapp/bbdev: enhance interrupt test
Kamil Chalupnik [Fri, 7 Dec 2018 15:15:34 +0000 (16:15 +0100)]
app/bbdev: enhance interrupt test

Improvements added to interrupt test:
- test is run in loop (number of iterations is specified by
TEST_REPETITIONS define) which ensures more accurate results
- mapping cores to thread parameteres was put in order.
Master core is always set at first index. It fixes problem with
running test for only one core

Signed-off-by: Kamil Chalupnik <kamilx.chalupnik@intel.com>
Acked-by: Amr Mokhtar <amr.mokhtar@intel.com>
5 years agobbdev: support bigger transport block
Kamil Chalupnik [Fri, 7 Dec 2018 15:15:33 +0000 (16:15 +0100)]
bbdev: support bigger transport block

Test application and Turbo Software driver were adapted
to support chained-mbuf for bigger TB sizes.

Signed-off-by: Kamil Chalupnik <kamilx.chalupnik@intel.com>
Acked-by: Amr Mokhtar <amr.mokhtar@intel.com>
5 years agobbdev: enhance throughput test
Kamil Chalupnik [Fri, 7 Dec 2018 15:15:32 +0000 (16:15 +0100)]
bbdev: enhance throughput test

Improvements added to throughput test:
- test is run in loop (number of iterations is specified by
TEST_REPETITIONS define) which ensures more accurate results
- length of input data is calculated based on amount of CBs in TB
- maximum number of decoding iterations is gathered from results
- added new functions responsible for printing results
- small fixes for memory management

Signed-off-by: Kamil Chalupnik <kamilx.chalupnik@intel.com>
Acked-by: Amr Mokhtar <amr.mokhtar@intel.com>
5 years agobbdev: enhance offload cost test
Kamil Chalupnik [Fri, 7 Dec 2018 15:15:31 +0000 (16:15 +0100)]
bbdev: enhance offload cost test

Offload cost test was improved in order to collect
more accurate results.

Signed-off-by: Kamil Chalupnik <kamilx.chalupnik@intel.com>
Acked-by: Amr Mokhtar <amr.mokhtar@intel.com>
5 years agocompressdev: fix structure comment
Lee Daly [Tue, 27 Nov 2018 15:10:24 +0000 (15:10 +0000)]
compressdev: fix structure comment

Fixes incorrect comment on compressdev rte_comp_op structure element.
Comment needed to be updated to be compliant with the use of
chained mbufs.

Fixes: f87bdc1ddcf4 ("compressdev: add compression specific data")
Cc: stable@dpdk.org
Signed-off-by: Lee Daly <lee.daly@intel.com>
Acked-by: Fiona Trahe <fiona.trahe@intel.com>
5 years agocrypto/openssl: remove useless check before freeing
Akash Saxena [Fri, 23 Nov 2018 12:10:59 +0000 (12:10 +0000)]
crypto/openssl: remove useless check before freeing

Remove if() condition prior to calling BN_free() as
BN_free(a) does nothing if a is NULL.

Signed-off-by: Akash Saxena <akash.saxena@caviumnetworks.com>
Signed-off-by: Shally Verma <shally.verma@caviumnetworks.com>
Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
5 years agotest/compress: use bulk free operation API
Fiona Trahe [Mon, 19 Nov 2018 22:10:11 +0000 (22:10 +0000)]
test/compress: use bulk free operation API

Use the new rte_comp_op_bulk_free API.
Add trace to catch any mempool elements not freed at test end.

Signed-off-by: Fiona Trahe <fiona.trahe@intel.com>
Acked-by: Shally Verma <shally.verma@caviumnetworks.com>
Acked-by: Lee Daly <lee.daly@intel.com>
5 years agocompressdev: add bulk free operation API
Fiona Trahe [Mon, 19 Nov 2018 22:10:10 +0000 (22:10 +0000)]
compressdev: add bulk free operation API

There's an API to bulk allocate operations,
this adds a corresponding bulk free API.

Signed-off-by: Fiona Trahe <fiona.trahe@intel.com>
Acked-by: Shally Verma <shally.verma@caviumnetworks.com>
Acked-by: Lee Daly <lee.daly@intel.com>
5 years agotest/compress: improve debug trace setup
Lee Daly [Mon, 19 Nov 2018 13:52:53 +0000 (13:52 +0000)]
test/compress: improve debug trace setup

This removes the magic number from the assignment of the engine variable,
which is used in the debug trace.

Signed-off-by: Lee Daly <lee.daly@intel.com>
Acked-by: Tomasz Jozwiak <tomaszx.jozwiak@intel.com>
5 years agoeventdev: fix eth Tx adapter queue count checks
Nikhil Rao [Mon, 17 Dec 2018 04:39:41 +0000 (10:09 +0530)]
eventdev: fix eth Tx adapter queue count checks

rte_event_eth_tx_adapter_queue_add() - add a check
that returns an error if the ethdev has zero Tx queues
configured.

rte_event_eth_tx_adapter_queue_del() - remove the
checks for ethdev queue count, instead check for
queues added to the adapter which maybe different
from the current ethdev queue count.

Fixes: a3bbf2e09756 ("eventdev: add eth Tx adapter implementation")
Cc: stable@dpdk.org
Signed-off-by: Nikhil Rao <nikhil.rao@intel.com>
5 years agoeventdev: fix xstats documentation typo
Gage Eads [Mon, 3 Dec 2018 20:05:04 +0000 (14:05 -0600)]
eventdev: fix xstats documentation typo

The eventdev extended stats documentation referred to two non-existent
functions, rte_eventdev_xstats_get and rte_eventdev_get_xstats_by_name.

Fixes: 3ed7fc039a ("eventdev: add extended stats")
Cc: stable@dpdk.org
Signed-off-by: Gage Eads <gage.eads@intel.com>
5 years agoapp/eventdev: detect deadlock for timer event producer
Erik Gabriel Carrillo [Mon, 3 Dec 2018 17:48:14 +0000 (11:48 -0600)]
app/eventdev: detect deadlock for timer event producer

If timer events get dropped for some reason, the thread that launched
producer and worker cores will never exit, because the deadlock check
doesn't currently apply to the event timer adapter case. This commit
fixes this.

Fixes: d008f20bce23 ("app/eventdev: add event timer adapter as a producer")
Cc: stable@dpdk.org
Signed-off-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
5 years agoeventdev: remove redundant timer adapter function prototypes
Erik Gabriel Carrillo [Thu, 29 Nov 2018 19:45:26 +0000 (13:45 -0600)]
eventdev: remove redundant timer adapter function prototypes

Fixes: 6750b21bd6af ("eventdev: add default software timer adapter")
Cc: stable@dpdk.org
Signed-off-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
5 years agoeventdev: fix error log in eth Rx adapter
Nikhil Rao [Thu, 29 Nov 2018 08:00:17 +0000 (13:30 +0530)]
eventdev: fix error log in eth Rx adapter

strerror() input parameter should be > 0.

Coverity issue: 302864
Fixes: 3810ae435783 ("eventdev: add interrupt driven queues to Rx adapter")
Cc: stable@dpdk.org
Signed-off-by: Nikhil Rao <nikhil.rao@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
5 years agogro: fix overflow of payload length calculation
Jiayu Hu [Mon, 17 Dec 2018 06:05:39 +0000 (14:05 +0800)]
gro: fix overflow of payload length calculation

When the packet length is smaller than the header length,
the calculated payload length will be overflowed and result
in incorrect reassembly behaviors.

Fixes: 1e4cf4d6d4fb ("gro: cleanup")
Fixes: 9e0b9d2ec0f4 ("gro: support VxLAN GRO")
Cc: stable@dpdk.org
Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
5 years agoeal: clean up unused files on initialization
Anatoly Burakov [Tue, 13 Nov 2018 15:54:44 +0000 (15:54 +0000)]
eal: clean up unused files on initialization

When creating process data structures, EAL will create many files
in EAL runtime directory. Because we allow multiple secondary
processes to run, each secondary process gets their own unique
file. With many secondary processes running and exiting on the
system, runtime directory will, over time, create enormous amounts
of sockets, fbarray files and other stuff that just sits there
unused because the process that allocated it has died a long time
ago. This may lead to exhaustion of disk (or RAM) space in the
runtime directory.

Fix this by removing every unlocked file at initialization that
matches either socket or fbarray naming convention. We cannot be
sure of any other files, so we'll leave them alone. Also, remove
similar code from mp socket code.

We do it at the end of init, rather than at the beginning, because
secondary process will use primary process' data structures even
if the primary itself has died, and we don't want to remove those
before we lock them.

Bugzilla ID: 106
Cc: stable@dpdk.org
Reported-by: Vipin Varghese <vipin.varghese@intel.com>
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
5 years agodoc: fix garbage text in generated HTML guides
Luca Boccassi [Wed, 5 Dec 2018 14:25:45 +0000 (14:25 +0000)]
doc: fix garbage text in generated HTML guides

If the user has MAKEFLAGS set in the environment when building the
documentation, the doc/guides/conf.py script which calls "make"
exclusively to get the project version might pick up garbage from
stdout, like:

<title>FAQ &mdash; Data Plane Development Kit make[2]:
Entering directory &#39;/build/1st/dpdk-18.11/doc/guides&#39;
18.11.0
make[2]: Leaving directory &#39;/build/1st/dpdk-18.11&#39;
documentation</title>

Override MAKEFLAGS in the Python subprocess call to avoid this issue.

Fixes: f7aaae2fe6f7 ("doc: add copyright and version")
Cc: stable@dpdk.org
Signed-off-by: Luca Boccassi <bluca@debian.org>
5 years agobus/dpaa: do nothing if bus not present
Stephen Hemminger [Wed, 5 Dec 2018 22:02:30 +0000 (14:02 -0800)]
bus/dpaa: do nothing if bus not present

The DPAA bus support code put out messages like:
dpaax: read_memory_node():  Unable to glob device-tree memory node:
(/proc/device-tree/memory[@0-9]*/reg)(3)
dpaax: PA->VA translation not available;
dpaax: Expect performance impact.

These are unnecessary and likely to confuse the end user.
Fix this by doing nothing if bus is empty.

Fixes: 5a7dbb934d75 ("dpaa: enable dpaax library")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Shreyansh Jain <shreyansh.jain@nxp.com>
5 years agobus/vmbus: debug subchannel setup
Stephen Hemminger [Wed, 5 Dec 2018 22:11:59 +0000 (14:11 -0800)]
bus/vmbus: debug subchannel setup

Add more instrumentation to subchannel setup to help diagnose
startup issues.

Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
5 years agonet/netvsc: disable multi-queue on older servers
Stephen Hemminger [Wed, 5 Dec 2018 22:11:58 +0000 (14:11 -0800)]
net/netvsc: disable multi-queue on older servers

NDIS multi-queue support is only in WS2012 or later. Check the NDIS
version to limit to single queue on older versions. Similar code
exists in Linux driver.

Fixes: 4e9c73e96e83 ("net/netvsc: add Hyper-V network device")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
5 years agonet/netvsc: enable SR-IOV
Stephen Hemminger [Wed, 5 Dec 2018 22:11:57 +0000 (14:11 -0800)]
net/netvsc: enable SR-IOV

Make DPDK enable SRIOV flag in same way as Linux and FreeBSD.

Fixes: dc7680e8597c ("net/netvsc: support integrated VF")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
5 years agobus/vmbus: fix race in subchannel creation
Stephen Hemminger [Wed, 5 Dec 2018 22:11:56 +0000 (14:11 -0800)]
bus/vmbus: fix race in subchannel creation

When using multiple queues, there was a race with the kernel
in setting up the second channel. This regression is due to a kernel change
which does not allow accessing sysfs files for Hyper-V channels that are not opened.

The fix is simple, just move the logic to detect not ready
sub channels earlier in the existing loop.

Fixes: 831dba47bd36 ("bus/vmbus: add Hyper-V virtual bus support")
Cc: stable@dpdk.org
Reported-by: Mohammed Gamal <mgamal@redhat.com>
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
5 years agolog: add missing experimental tag
David Marchand [Tue, 4 Dec 2018 08:28:31 +0000 (09:28 +0100)]
log: add missing experimental tag

When rte_log_register_type_and_pick_level() has been introduced, it has
been correctly added to the EXPERIMENTAL section of the eal map and the
symbol itself has been marked at its definition.

However, the declaration of this symbol in rte_log.h is missing the
__rte_experimental tag.
Because of this, a user can try to call this symbol without being aware
this is an experimental api (neither compilation nor link warning).

Fixes: b22e77c02620 ("eal: register log type and pick level from args")
Cc: stable@dpdk.org
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
5 years agoeal: remove unnecessary dirent.h include
Jeff Shaw [Fri, 14 Dec 2018 16:40:00 +0000 (08:40 -0800)]
eal: remove unnecessary dirent.h include

Prior to this patch, the two affected .c files include <dirent.h>
unnecessarily. This commit removes the include lines.

Signed-off-by: Jeff Shaw <jeffrey.b.shaw@intel.com>
Reviewed-by: Rami Rosen <ramirose@gmail.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
5 years agopdump: remove deprecated APIs
Tiwei Bie [Mon, 3 Dec 2018 02:58:57 +0000 (10:58 +0800)]
pdump: remove deprecated APIs

We already changed to use generic IPC in pdump since below commit:

commit 660098d61f57 ("pdump: use generic multi-process channel")

The `rte_pdump_set_socket_dir()`, the `path` parameter of
`rte_pdump_init()` and the `enum rte_pdump_socktype` have been
deprecated since then. This commit removes these deprecated
APIs and also bumps the pdump ABI.

Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Acked-by: Reshma Pattan <reshma.pattan@intel.com>
5 years agomk: do not install meson.build in usertools
Timothy Redaelli [Tue, 27 Nov 2018 19:35:32 +0000 (20:35 +0100)]
mk: do not install meson.build in usertools

In commit 7dd34c71de2a ("usertools: install with meson") meson.build was
added in usertools directory and so it's copied to $(datadir)/usertools
with "make install".

This patch avoids to copy meson.build when installing usertools with
"make install".

Fixes: 7dd34c71de2a ("usertools: install with meson")
Cc: stable@dpdk.org
Signed-off-by: Timothy Redaelli <tredaelli@redhat.com>
Acked-by: Luca Boccassi <bluca@debian.org>
5 years agoconfig: enable C11 memory model for armv8 with meson
Gavin Hu [Tue, 11 Dec 2018 03:55:50 +0000 (11:55 +0800)]
config: enable C11 memory model for armv8 with meson

This patch makes the configuration based on makefile and the
configuration based on meson to be the same.

Fixes: c6e536e38437 ("build: add more implementers IDs and PNs for ARM")
Cc: stable@dpdk.org
Signed-off-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
5 years agomaintainers: update Cavium email ids
Jerin Jacob [Sun, 16 Dec 2018 15:43:25 +0000 (15:43 +0000)]
maintainers: update Cavium email ids

Following Marvell's acquisition of Cavium, we need to update all the
Cavium maintainer's entries to point to our new e-mail addresses.
Update maintainers as they are no longer working for Cavium.

Thanks to Harish Patil for his support and development of our various
dpdk drivers.

Signed-off-by: Jerin Jacob <jerinj@marvell.com>
5 years agopkg: remove RPM recipe
Thomas Monjalon [Mon, 26 Nov 2018 20:26:59 +0000 (21:26 +0100)]
pkg: remove RPM recipe

This RPM recipe is not well maintained and probably not used a lot.
Each distribution has its own constraints and recipes.
It may not be a good idea to try maintaining packaging recipes in
the project itself.

Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
5 years agonet/i40e: remove redundant reset of queue number
Zhirun Yan [Thu, 13 Dec 2018 12:49:28 +0000 (12:49 +0000)]
net/i40e: remove redundant reset of queue number

Before this patch, there are two functions will call
i40e_dev_free_queues to free queues. For rte_eth_dev_close(), its
redundant because of duplication. For rte_eth_dev_reset() its
redundant because of not necessary, since following dev_configure
is required after dev_reset and it will be updated correctly.

This patch removes redundant code in i40e_dev_free_queues().

Fixes: 6b4537128394 ("i40e: free queue memory when closing")
Cc: stable@dpdk.org
Signed-off-by: Zhirun Yan <zhirun.yan@intel.com>
Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
5 years agonet/i40e: revert fix offload not supported mask
Didier Pallard [Tue, 11 Dec 2018 17:25:01 +0000 (18:25 +0100)]
net/i40e: revert fix offload not supported mask

This reverts
commit 09a62d75691f ("net/i40e: fix offload not supported mask")

Contrary to what is said in above patch commit log,
I40E_TX_OFFLOAD_NOTSUP_MASK is the mask of Tx offload bits that are part
of PKT_TX_OFFLOAD_MASK but not included in I40E_TX_OFFLOAD_MASK.
Above patch erroneously includes all PKT_RX_OFFLOAD_ bits in the
I40E_TX_OFFLOAD_NOTSUP_MASK, this is not what is expected.
Restore the initial xor that gives the expected result.

Fixes: 09a62d75691f ("net/i40e: fix offload not supported mask")
Cc: stable@dpdk.org
Signed-off-by: Didier Pallard <didier.pallard@6wind.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
5 years agoexamples/vhost_crypto: fix bracket
Fan Zhang [Tue, 11 Dec 2018 15:09:51 +0000 (15:09 +0000)]
examples/vhost_crypto: fix bracket

This patch fixes a missed bracket bug in the code.

Fixes: e1d90eaa83ff ("examples/vhost_crypto: fix zero copy")
Cc: stable@dpdk.org
Signed-off-by: Fan Zhang <roy.fan.zhang@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
5 years agovhost: fix double read of descriptor flags
Ilya Maximets [Wed, 5 Dec 2018 15:09:26 +0000 (18:09 +0300)]
vhost: fix double read of descriptor flags

Flags could be updated in a separate process leading to the
inconsistent check.

Additionally, read marked as 'volatile' to highlight the shared
nature of the variable and avoid such issues in the future.

Fixes: d3211c98c456 ("vhost: add helpers for packed virtqueues")
Cc: stable@dpdk.org
Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
5 years agonet/virtio: move bytes accounting to common function
Ilya Maximets [Mon, 3 Dec 2018 16:20:13 +0000 (19:20 +0300)]
net/virtio: move bytes accounting to common function

There is no need to count 'bytes' separately.

Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
5 years agonet/virtio: allocate vrings on device NUMA node
Maxime Coquelin [Tue, 27 Nov 2018 10:54:27 +0000 (11:54 +0100)]
net/virtio: allocate vrings on device NUMA node

When a guest is spanned on multiple NUMA nodes and
multiple Virtio devices are spanned onto these nodes,
we expect that their ring memory is allocated in the
right memory node.

Otherwise, vCPUs from node A may be polling Virtio rings
allocated on node B, which would increase QPI bandwidth
and impact performance.

Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
5 years agovhost: fix crash after mmap failure
Maxime Coquelin [Tue, 27 Nov 2018 09:54:51 +0000 (10:54 +0100)]
vhost: fix crash after mmap failure

If mmap() call fails in vhost_user_set_mem_table, dev->mem
is set to NULL. If later, qva_to_vva() is called, a segfault
occurs.

Fixes: 8f972312b8f4 ("vhost: support vhost-user")
Cc: stable@dpdk.org
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Jens Freimann <jfreimann@redhat.com>
5 years agodrivers/net: fix several Tx prepare functions
Didier Pallard [Tue, 11 Dec 2018 13:00:28 +0000 (14:00 +0100)]
drivers/net: fix several Tx prepare functions

Since below commit, several tx_prep functions are broken, they fail to
pass supported Tx offload features check:
PKT_TX_IPVx must be set when any PKT_TX_L4 checksum is requested,
but these values are not present in the mask of supported Tx offloads
of several drivers that advertise PKT_TX_L4_MASK.
So any packet sent to those drivers with a L4 checksum request and
one of PKT_TX_IPVx bit set is rejected by the tx prepare function.

Fixes: 1037ed842c37 ("mbuf: fix Tx offload mask")
Cc: stable@dpdk.org
Signed-off-by: Didier Pallard <didier.pallard@6wind.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
5 years agonet/nfp: support multiprocess
Alejandro Lucero [Tue, 11 Dec 2018 12:01:59 +0000 (12:01 +0000)]
net/nfp: support multiprocess

This patch introduces changes for supporting multiprocess support.
This is trivial for VFs but comes with some limitations for the PF.

Due to restrictions when using NFP CPP interface, just one secondary
process is supported by now for the PF.

Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
5 years agonet/enic: support multicast filtering
Hyong Youb Kim [Mon, 10 Dec 2018 18:28:55 +0000 (10:28 -0800)]
net/enic: support multicast filtering

The VIC hardware has 64 MAC filters per vNIC, which can be either
unicast or multicast. Use one half for unicast and the other half for
multicast, as the VIC kernel drivers for Linux and Windows do.

Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>
5 years agonet/enic: add handler to return firmware version
Hyong Youb Kim [Mon, 10 Dec 2018 18:28:54 +0000 (10:28 -0800)]
net/enic: add handler to return firmware version

Cisco VIC adapters run firmware. Add the fw_version_get handler to
help diagnostics.

Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>
5 years agonet/enic: release port upon close
Hyong Youb Kim [Mon, 10 Dec 2018 18:28:53 +0000 (10:28 -0800)]
net/enic: release port upon close

Set RTE_ETH_DEV_CLOSE_REMOVE upon probe so rte_eth_dev_close() can
later free port resources including mac_addrs.

Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>