Jerin Jacob [Wed, 22 Apr 2020 19:03:49 +0000 (00:33 +0530)]
doc: add trace library guide
Add programmer's guide for trace library support.
Signed-off-by: Jerin Jacob <jerinj@marvell.com> Signed-off-by: Sunil Kumar Kori <skori@marvell.com> Acked-by: David Marchand <david.marchand@redhat.com>
rte_malloc() and rte_free() has been used in the trace implementation,
in order to avoid tracing implementation specific events, added
an internal no trace version rte_malloc() and rte_free().
Signed-off-by: Jerin Jacob <jerinj@marvell.com> Acked-by: David Marchand <david.marchand@redhat.com>
For example, if an application wishes to emit an int datatype,
it can call rte_eal_trace_generic_int(val) to emit the trace.
Signed-off-by: Jerin Jacob <jerinj@marvell.com> Signed-off-by: Sunil Kumar Kori <skori@marvell.com> Acked-by: David Marchand <david.marchand@redhat.com>
Jerin Jacob [Wed, 22 Apr 2020 19:03:30 +0000 (00:33 +0530)]
trace: implement provider payload
The trace function payloads such as rte_trace_point_emit_* have
dual functions. The first to emit the payload for the registration
function and the second one to act as trace mem emitters a.k.a
provider payload.
When it is used as provider payload, those function copy the trace
field to trace memory based on the tracing mode.
Added payload definitions under ALLOW_EXPERIMENTAL_API define
to allow the existing applications to compile without enabling
experimental APIs.
Signed-off-by: Jerin Jacob <jerinj@marvell.com> Signed-off-by: Sunil Kumar Kori <skori@marvell.com> Acked-by: David Marchand <david.marchand@redhat.com>
Jerin Jacob [Wed, 22 Apr 2020 19:03:29 +0000 (00:33 +0530)]
trace: implement registration payload
The trace function payloads such as rte_trace_point_emit_* have
dual functions. The first to emit the payload for the registration
function and the second one to act as trace memory emitters.
When it is used as registration payload, it will do the following to
fulfill the registration job.
- Find out the size of the event,
- Generate metadata field string using __rte_trace_point_emit_field().
Signed-off-by: Jerin Jacob <jerinj@marvell.com> Signed-off-by: Sunil Kumar Kori <skori@marvell.com> Acked-by: David Marchand <david.marchand@redhat.com>
Jerin Jacob [Wed, 22 Apr 2020 19:03:27 +0000 (00:33 +0530)]
trace: implement debug dump
Implement rte_trace_metadata_dump() and rte_trace_dump()
functions. Former one used to dump the CTF metadata file and
the latter one to dump all the registered events and its status.
Signed-off-by: Jerin Jacob <jerinj@marvell.com> Signed-off-by: Sunil Kumar Kori <skori@marvell.com> Acked-by: David Marchand <david.marchand@redhat.com>
Jerin Jacob [Wed, 22 Apr 2020 19:03:26 +0000 (00:33 +0530)]
trace: implement memory allocation
Trace memory will be allocated per thread to enable lockless trace
events updates to the memory. The allocator will first attempt to
allocate from hugepage, then if not available from hugepage or
finally fallback to malloc memory.
Later in the patches series, this API will be hooked to DPDK fast path
and control plane thread creation API. It is possible for non
DPDK thread to use trace events. In that case, trace memory
will be allocated on the first event emission.
Signed-off-by: Jerin Jacob <jerinj@marvell.com> Acked-by: David Marchand <david.marchand@redhat.com>
Some of the keyword like align, event, "." and "->" etc will be
used in CTF metadata syntax. This patch support for handling
those keywords with DPDK events name.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com> Acked-by: David Marchand <david.marchand@redhat.com>
Jerin Jacob [Wed, 22 Apr 2020 19:03:24 +0000 (00:33 +0530)]
trace: create CTF TDSL metadata in memory
Common trace format(CTF) defines the metadata[1][2] for trace events,
This patch creates the metadata for the DPDK events in memory and
later this will be saved to trace directory on rte_trace_save()
invocation.
Jerin Jacob [Wed, 22 Apr 2020 19:03:22 +0000 (00:33 +0530)]
trace: add internal init and fini interface
Define eal_trace_init() and eal_trace_fini() EAL interface
functions that rte_eal_init() and rte_eal_cleanup() function can
use to initialize and finalize the trace subsystem.
eal_trace_init() function will add the following functionality if
trace is enabled through EAL command line param.
- Test for trace registration failure.
- Test for duplicate trace name registration.
- Generate UUID ver 4.
- Create a trace directory.
Signed-off-by: Jerin Jacob <jerinj@marvell.com> Signed-off-by: Sunil Kumar Kori <skori@marvell.com> Acked-by: David Marchand <david.marchand@redhat.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com> Signed-off-by: Sunil Kumar Kori <skori@marvell.com> Acked-by: David Marchand <david.marchand@redhat.com>
Jerin Jacob [Wed, 22 Apr 2020 19:03:20 +0000 (00:33 +0530)]
trace: implement register API
The consumers of trace API defines the tracepoint and registers
to eal. Internally these tracepoints will be stored in STAILQ
for future use. This patch implements the tracepoint
registration function.
Signed-off-by: Jerin Jacob <jerinj@marvell.com> Acked-by: David Marchand <david.marchand@redhat.com>
Jerin Jacob [Wed, 22 Apr 2020 19:03:19 +0000 (00:33 +0530)]
trace: introduce new subsystem
Define the public API for trace support.
This patch also adds support for the build infrastructure and
update the MAINTAINERS file for the trace subsystem.
The 8 bytes tracepoint object is a global variable, and can be used in
fast path. Created a new __rte_trace_point section to store the
tracepoint objects as,
- It is a mostly read-only data and not to mix with other "write"
global variables.
- Chances that the same subsystem fast path variables come in the same
fast path cache line. i.e, it will enable a more predictable
performance number from build to build.
Signed-off-by: Jerin Jacob <jerinj@marvell.com> Signed-off-by: Sunil Kumar Kori <skori@marvell.com> Acked-by: David Marchand <david.marchand@redhat.com>
Pablo de Lara [Thu, 16 Apr 2020 09:25:32 +0000 (10:25 +0100)]
test/crypto: do not check for PMD
Remove PMD bitmask, which selects the PMD to be tested
for each test case. Instead, all PMDs are eligible
to run all tests, and capability checking discards
the PMDs which do not support each test case.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Adam Dybkowski <adamx.dybkowski@intel.com> Tested-by: Ruifeng Wang <ruifeng.wang@arm.com> Acked-by: Fiona Trahe <fiona.trahe@intel.com> Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
Pablo de Lara [Thu, 16 Apr 2020 17:24:24 +0000 (18:24 +0100)]
test/crypto: do not check for internal PMD information
Now that capabilities are checked to see if an algorithm
is supported by a device, there is no need to check
for a specific version of a library used in a PMD.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Adam Dybkowski <adamx.dybkowski@intel.com> Tested-by: Ruifeng Wang <ruifeng.wang@arm.com> Acked-by: Fiona Trahe <fiona.trahe@intel.com> Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
Pablo de Lara [Thu, 16 Apr 2020 17:24:23 +0000 (18:24 +0100)]
test/crypto: add capability check
Check if test case is supported by the crypto device,
including algorithm and some of its parameter, such as key length,
IV length, etc, using the capabilities API.
If it is not supported, test case is skipped.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Adam Dybkowski <adamx.dybkowski@intel.com> Tested-by: Ruifeng Wang <ruifeng.wang@arm.com> Acked-by: Fiona Trahe <fiona.trahe@intel.com> Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
Adding optional capability to support loopback preloading
and check of the extern HARQ memory.
This function is required to run the HARQ bit exact test successfully.
Signed-off-by: Nicolas Chautru <nicolas.chautru@intel.com> Acked-by: Dave Burley <dave.burley@accelercomm.com> Acked-by: Niall Power <niall.power@intel.com> Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
Nicolas Chautru [Sat, 18 Apr 2020 22:46:40 +0000 (15:46 -0700)]
baseband/fpga_5gnr_fec: add info get function
Add in the "info_get" function to the driver, to allow us to query the
device.
No capability are available yet.
Linking bbdev-test to support the PMD with null capability.
Signed-off-by: Nicolas Chautru <nicolas.chautru@intel.com> Acked-by: Dave Burley <dave.burley@accelercomm.com> Acked-by: Niall Power <niall.power@intel.com> Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
Adam Dybkowski [Fri, 17 Apr 2020 15:44:04 +0000 (17:44 +0200)]
test/compress: check IM buffer too small
This patch adds new tests for verification of the "internal
QAT IM buffer too small" case handling. These unit tests aren't
specific to the QAT PMD only - they pass or skip on other PMDs like
ISAL and ZLIB (depending on particular PMD capabilities).
Signed-off-by: Adam Dybkowski <adamx.dybkowski@intel.com> Acked-by: Fiona Trahe <fiona.trahe@intel.com>
Adam Dybkowski [Fri, 17 Apr 2020 15:44:03 +0000 (17:44 +0200)]
compress/qat: support IM buffer too small operation
This patch implements a special way of buffer handling when internal
QAT IM buffer is too small for Huffman dynamic compression operation.
Instead of falling back to fixed compression, the operation is now
split into multiple smaller dynamic compression requests (possible to
execute on QAT) and their results are then combined and copied into
the output buffer. This is not possible if any checksum calculation
was requested - in such case the code falls back to fixed compression
as before.
Signed-off-by: Adam Dybkowski <adamx.dybkowski@intel.com> Acked-by: Fiona Trahe <fiona.trahe@intel.com>
This patch introduces set of unit tests of librte_security API functions.
Tests are added to dpdk-test application and can be run with
"security_autotest" runtime command.
This is the first patch in the series of patches as adding all test cases
for all API functions in a single patch would make it unreadable.
This patch defines structure of the file and necessary test framework
initialization. It also contains first subset of unit tests for
rte_security_session_create API function.
Structure of the tests file is following:
- macros for making tests more readable;
- mockup structures and functions for rte_security_ops;
- test suite and test cases setup and teardown functions;
- tests functions;
- declaration of testcases.
Fix session counter to be decreased in rte_security_session_destroy
only when session was successfully destroyed.
Formerly session counter was decreased prior session destroying
and returning session object to mempool. It remained decreased even
if session was not destroyed and mempool object released making counter
invalid.
Fixes: c261d1431bd8 ("security: introduce security API and framework") Cc: stable@dpdk.org Signed-off-by: Lukasz Wojciechowski <l.wojciechow@partner.samsung.com> Acked-by: Anoob Joseph <anoobj@marvell.com> Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
This patch adds verification of the parameters to the ret_security API
functions. All required parameters are checked if they are not NULL.
Checks verify full chain of pointers, e.g. in case of verification of
"instance->ops->session_XXX", they check also "instance"
and "instance->ops".
Fixes: c261d1431bd8 ("security: introduce security API and framework") Fixes: 1a08c379b9b5 ("security: support user data retrieval") Cc: stable@dpdk.org Signed-off-by: Lukasz Wojciechowski <l.wojciechow@partner.samsung.com> Acked-by: Anoob Joseph <anoobj@marvell.com> Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
Pablo de Lara [Tue, 14 Apr 2020 17:25:55 +0000 (18:25 +0100)]
crypto/openssl: fix out-of-place encryption
When authenticating after encrypting, if the operation
is out-of-place, the destination buffer is the one
that will get authenticated.
If the cipher offset is higher than the authentication
offset, it means that part of the text to authenticate
will be plaintext, so this needs to get copied to the
destination buffer, or the result will be incorrect.
Fixes: d61f70b4c918 ("crypto/libcrypto: add driver for OpenSSL library") Cc: stable@dpdk.org Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
This patch adds ability to run unit tests in cpu crypto mode
for AESNI MB cryptodev.
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
Support load distribution in security gateway application using
NIC load distribution feature (Flow Director).
Flow Director is used to redirect the specified inbound ipsec flow
to a specified queue. This is achieved by extending the SA rule syntax
to support specification by adding new action_type of <flow-direction>
to a specified <port_id> <queue_id>.
drivers/crypto: fix log type variables for -fno-common
The four crypto drivers: kasumi, mvsam, snow3g and zuc define logtype
variables in their header file. As the header files are included
in more than one compilation unit, it might cause appearance
of multiple instances of the variable and a linker error.
Such situation can occur, when no common section is allowed
by the compiler settings and tentative definitions are placed
in BSS section.
Bruce Richardson [Fri, 10 Apr 2020 17:27:56 +0000 (18:27 +0100)]
drivers: fix log type variables for -fno-common
The zlib compression driver, as well as the aesni-gcm, aesni-mb and openssl
crypto drivers all defined the logtype variable in the header file
directly. This gives errors with gcc 10, due to -fno-common being the
default, so we need to apply the same fix in all cases:
* move the variable definition to a suitable .c file
* mark the forward declaration of the variable in the header as "extern"
The goal of rte_os.h is to mitigate OS differences for EAL users.
In Windows EAL, rte_os.h did excessive things:
1. It included platform SDK headers (windows.h, etc). Those files are
huge, require specific inclusion order, and are generally unused by
the code including rte_os.h. Declarations from platform SDK may
break otherwise platform-independent code, e.g. min, max, ERROR.
2. It included pthread.h, which is clearly not always required.
3. It defined functions private to Windows EAL.
Reorganize Windows EAL includes in the following way:
1. Create rte_windows.h to properly import Windows-specific facilities.
Primary users are bus drivers, tests, and external applications.
2. Remove platform SDK includes from rte_os.h to prevent breaking
otherwise portable code by including rte_os.h on Windows.
Copy necessary definitions to avoid including those headers.
3. Remove pthread.h include from rte_os.h.
4. Move declarations private to Windows EAL into eal_windows.h.
Fixes: 428eb983f5f7 ("eal: add OS specific header file") Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
This fix treats a 0 return value from vfio_open_group_fd
in vfio_get_group_fd as the intended error condition instead
of putting an incorrect 0 file descriptor in the vfio_group table.
Sometimes, the creation of device files in sysfs is not
instantaneously causing vfio_open_groupfd to return 0.
This has been observed when hot removing/adding multiple
NVMe devices (>=4).
Fixes: 340b7bb8d583 ("vfio: extend data structure for multi container") Cc: stable@dpdk.org Signed-off-by: Michael Haeuptle <michael.haeuptle@hpe.com> Acked-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com> Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
When rte_rand_init is invoked, and the kernel running dpdk does not
support *getentropy, at the same time, the cpu does not support rdseed,
then rte_rand_init invoked rte_get_timer_cycles.
If HPET was enabled in the DPDK build (CONFIG_RTE_LIBEAL_USE_HPET=y) and
the system, rte_get_timer_cycles will invoke rte_get_hpet_cycles while
*eal_hpet is not available.
To fix that, use rte_get_tsc_cycles instead of rte_get_timer_cycles.
Fixes: 3f002f069612 ("eal: replace libc-based random generation with LFSR") Cc: stable@dpdk.org Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com> Acked-by: Mattias Rönnblom <mattias.ronnblom@ericsson.com>
Thinh Tran [Wed, 25 Mar 2020 00:13:56 +0000 (20:13 -0400)]
eal/ppc64: use glibc for cpu cycles count
__ppc_get_timebase() reads and returns the current value of the Time
Base Register. It's more efficient as it uses the processor’s time
base facility directly.
DPDK on FreeBSD currently is not supported on Powerpc64, it should
be safe to include the sys/platform/ppc.h.
Signed-off-by: Thinh Tran <thinhtr@linux.vnet.ibm.com> Reviewed-by: David Christensen <drc@linux.vnet.ibm.com>
Due to the fact that the rte_realloc() test depends on the layout of
underlying memory, it can sometimes fail due to fragmentation of the
memory. To address this, make it so that the realloc autotests are run
using a newly created external memory heap instead of main memory.
Bugzilla ID: 424
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com> Tested-by: David Christensen <drc@linux.vnet.ibm.com>
For rings with producer/consumer in RTE_RING_SYNC_ST, RTE_RING_SYNC_MT_HTS
mode, provide an ability to split enqueue/dequeue operation
into two phases:
- enqueue/dequeue start
- enqueue/dequeue finish
That allows user to inspect objects in the ring without removing
them from it (aka MT safe peek).
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Introduce head/tail sync mode for MT ring synchronization.
In that mode enqueue/dequeue operation is fully serialized:
only one thread at a time is allowed to perform given op.
Suppose to reduce stall times in case when ring is used on
overcommitted cpus (multiple active threads on the same cpu).
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Introduce relaxed tail sync (RTS) mode for MT ring synchronization.
Aim to reduce stall times in case when ring is used on
overcommited cpus (multiple active threads on the same cpu).
The main difference from original MP/MC algorithm is that
tail value is increased not by every thread that finished enqueue/dequeue,
but only by the last one.
That allows threads to avoid spinning on ring tail value,
leaving actual tail value change to the last thread in the update queue.
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
To make these preparations two main things are done:
- Change from *single* to *sync_type* to allow different
synchronisation schemes to be applied.
Mark *single* as deprecated in comments.
Add new functions to allow user to query ring sync types.
Replace direct access to *single* with appropriate function call.
- Move actual rte_ring and related structures definitions into a
separate file: <rte_ring_core.h>. It allows to refer contents
of <rte_ring_elem.h> from <rte_ring.h> without introducing a
circular dependency.
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Introduce stress test for ring enqueue/dequeue operations.
Performs the following pattern on each slave worker:
dequeue/read-write data from the dequeued objects/enqueue.
Serves as both functional and performance test of ring
enqueue/dequeue operations under high contention
(for both over committed and non-over committed scenarios).
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
git.droids-corp.org / dpdk.git / log