Added new path to do lpm4 lookup by using scalable vector extension.
The SVE path will be selected if compiler has flag SVE set.
Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>
Acked-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
rte_lpm_lookupx4 could return wrong next hop when more than 256 tbl8
groups are created. This is caused by incorrect type casting of tbl8
group index that been stored in tbl24 entry. The casting caused group
index truncation and hence wrong tbl8 group been searched.
Issue fixed by applying proper mask to tbl24 entry to get tbl8 group index.
Fixes: dc81ebbaca ("lpm: extend IPv4 next hop field")
Fixes: cbc2f1dccf ("lpm/arm: support NEON")
Fixes: d2cc795934 ("lpm: add AltiVec for ppc64")
Cc: stable@dpdk.org
Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>
Tested-by: David Christensen <drc@linux.vnet.ibm.com>
Acked-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
Improved performance for AVX512 FIB6 lookup by doubling the number
of flows being processed
Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Ray Kinsella <mdr@ashroe.eu>
When scanning a buffer it is possible that the scan will abort
due to some internal resource limit.
This commit adds such response flag, so application can handle such cases.
Signed-off-by: Francis Kelly <fkelly@nvidia.com>
Signed-off-by: Ori Kam <orika@nvidia.com>
Add support for TLS functionality in EAL.
The following functions are added:
rte_thread_tls_key_create - create a TLS data key.
rte_thread_tls_key_delete - delete a TLS data key.
rte_thread_tls_value_set - set value bound to the TLS key
rte_thread_tls_value_get - get value bound to the TLS key
TLS key is defined by the new type rte_tls_key.
The API allocates the thread local storage (TLS) key.
Any thread of the process can subsequently use this key
to store and retrieve values that are local to the thread.
Those functions are added in addition to TLS capability
in rte_per_lcore.h to allow abstraction of the pthread
layer for all operating systems.
Windows implementation is under librte_eal/windows and
implemented using WIN32 API for Windows only.
Unix implementation is under librte_eal/unix and
implemented using pthread for UNIX compilation.
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Move the definition of the functions
rte_thread_set_affinity and rte_thread_get_affinity
to new file, rte_thread.h
The file will implement generic threading functionality
and will only host threading functions which do not reference
pthread API.
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
This patch moves memory region mmaping and related
preparation in a dedicated function in order to simplify
VHOST_USER_SET_MEM_TABLE request handling function.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
This patch moves the registration of postcopy to a
dedicated function, with the goal of simplifying
VHOST_USER_SET_MEM_TABLE request handling function.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
This patch moves the registration of memory regions to
userfaultfd to a dedicated function, with the goal of
simplifying VHOST_USER_SET_MEM_TABLE request handling
function.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
Simply replace the smp barriers with atomic thread fence for vhost control
path, if there are no synchronization points.
Signed-off-by: Joyce Kong <joyce.kong@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Simply replace smp barriers with atomic thread fence for
virtio packed vring.
Signed-off-by: Joyce Kong <joyce.kong@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Used idx can be synchronized by one-way barrier instead of full
write barrier for split vring.
Signed-off-by: Joyce Kong <joyce.kong@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Relax the full read barrier to one-way barrier for desc flags in
packed vring.
Signed-off-by: Joyce Kong <joyce.kong@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
The ordering between avail index and desc reads has been enforced
by load-acquire for split vring, so smp_rmb barrier is not needed
behind it.
Signed-off-by: Joyce Kong <joyce.kong@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
As function desc_is_avail performs a load-acquire barrier to
enforce the ordering between desc flags and desc content, it is
unnecessary to add a rte_smp_rmb barrier around the trace which
follows desc_is_avail.
Signed-off-by: Joyce Kong <joyce.kong@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Use rte_atomic_thread_fence wrapper which has been provided for
__atomic_thread_fence builtins to support optimized code for
__ATOMIC_SEQ_CST memory order on x86 platforms.
Signed-off-by: Joyce Kong <joyce.kong@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
The header was missing the extern "C" directive which causes name
mangling of functions by C++ compilers, leading to linker errors
complaining of undefined references to these functions.
Fixes: 4958ca3a44 ("mbuf: support dynamic fields and flags")
Cc: stable@dpdk.org
Signed-off-by: Ashish Sadanandan <ashish.sadanandan@gmail.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
The "rev->epdata.event" assigned to "events.epdata.event" directly, which
was wrong in case of epoll events. It should be set to the "evs.events".
Fixes: 9efe9c6cdc ("eal/linux: add epoll wrappers")
Cc: stable@dpdk.org
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Acked-by: Harman Kalra <hkalra@marvell.com>
According to GCC documentation for __builtin_clz:
Returns the number of leading 0-bits in x,
starting at the most significant bit position.
If x is 0, the result is undefined.
__builtin_clz will be called with 0 if the existing
prefix address matches the one we want to insert.
Fixes: 5a5793a5ff ("rib: add RIB library")
Cc: stable@dpdk.org
Reported-by: David Marchand <david.marchand@redhat.com>
Signed-off-by: Vladimir Medvedkin <vladimir.medvedkin@intel.com>
When building with clang (11.0,--buildtype=debug), eal_lcore.c
produces a -Wformat-nonliteral warning from the vfprintf call
in log_early.
Add __rte_format_printf annotation.
Fixes: b8a36b0866 ("eal/windows: improve CPU and NUMA node detection")
Cc: stable@dpdk.org
Suggested-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Signed-off-by: Nick Connolly <nick.connolly@mayadata.io>
Acked-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Acked-by: Pallavi Kadam <pallavi.kadam@intel.com>
Compiling with MinGW in --buildtype=debug produces a redefinition
error for strncasecmp.
The root cause is that rte_os.h shouldn't be injecting POSIX definitions
into the environment. It is the applications responsibility to decide
how to handle missing functionality.
Resolving this properly will require further work, but in the meantime
wrap all such definitions with #ifndef/#endif. This resolves the specific
issue with strncasecmp and handles similar issues that applications may
encounter.
Fixes: e8428a9d89 ("eal/windows: add some basic functions and macros")
Cc: stable@dpdk.org
Reported-by: David Marchand <david.marchand@redhat.com>
Signed-off-by: Nick Connolly <nick.connolly@mayadata.io>
MinGW-w64 above 8.0.0 exposes VirtualAlloc2() API in headers, but lacks
it in import libraries. Hence, availability of this API at compile-time
can't be used to choose between locating VirtualAlloc2() manually or
relying on the dynamic linker.
Fix redefinition compile-time errors.
Always link VirtualAlloc2() when using GCC.
Fixes: 2a5d547a4a ("eal/windows: implement basic memory management")
Cc: stable@dpdk.org
Reported-by: Thomas Monjalon <thomas@monjalon.net>
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Tested-by: Thomas Monjalon <thomas@monjalon.net>
A new generic shared actions API may be used to create shared
counter. There is no point to keep duplicate COUNT action specific
capability to create shared counters.
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Acked-by: Ori Kam <orika@nvidia.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
GCC build with '-O0' on platforms with RTE_ARM_FEATURE_ATOMICS set
failed for:
../lib/librte_efd/rte_efd.c
Assembler messages:
3866: Error: selected processor does not support `crc32cb w0,w0,w1'
3890: Error: selected processor does not support `crc32ch w0,w0,w1'
3914: Error: selected processor does not support `crc32cw w0,w0,w1'
3938: Error: selected processor does not support `crc32cx w0,w0,x1'
This was caused by an architecture specifier added for Clang.
Unlike Clang, GCC considers each inline assembly block to be dependent
and therefore, the architecture specifier impacts assemble of some
blocks require certain extension support.
Removed the architecture for GCC to fix the issue.
Fixes: 8fce34cd0a ("eal/arm: fix clang build of native target")
Cc: stable@dpdk.org
Reported-by: Feifei Wang <feifei.wang2@arm.com>
Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Commit 49b536fc30 ("eal: load only shared libs from driver plugin directories")
introduced a check that any shared library must ends with .so, but it can't
work, at least, on Fedora/CentOS/RHEL since .so symlinks are not installed
when you install dpdk package, but only when you install dpdk-devel package.
This commit adds also a check for .so.ABI_VERSION to check for shared lib.
See Fedora Packaging Guidelines for more information:
https://docs.fedoraproject.org/en-US/packaging-guidelines/#_devel_packages
Fixes: 49b536fc30 ("eal: load only shared libs from driver plugin directories")
Cc: stable@dpdk.org
Signed-off-by: Timothy Redaelli <tredaelli@redhat.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: David Marchand <david.marchand@redhat.com>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Tested-by: Ferruh Yigit <ferruh.yigit@intel.com>
Tested-by: Ali Alnubani <alialnu@nvidia.com>
Commit 06c7871dde ("eal: restrict default plugin path to shared lib mode")
introduced a check that enabled shared lib mode when librte_eal.so can
be loaded, but it can't work, at least, on Fedora/CentOS/RHEL since .so
symlinks are not installed when you install dpdk package, but only when
you install dpdk-devel package.
This commit uses librte_eal.so.ABI_VERSION to check for shared lib,
since it exists on any linux distributions.
See Fedora Packaging Guidelines for more information:
https://docs.fedoraproject.org/en-US/packaging-guidelines/#_devel_packages
Fixes: 06c7871dde ("eal: restrict default plugin path to shared lib mode")
Cc: stable@dpdk.org
Signed-off-by: Timothy Redaelli <tredaelli@redhat.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: David Marchand <david.marchand@redhat.com>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Tested-by: Ali Alnubani <alialnu@nvidia.com>
The initialization me->locked=1 in lock() must happen before
next->locked=0 in unlock(), otherwise a thread may hang forever,
waiting me->locked become 0. On weak memory systems (such as ARMv8),
the current implementation allows me->locked=1 to be reordered with
announcing the node (pred->next=me) and, consequently, to be
reordered with next->locked=0 in unlock().
This fix adds a release barrier to pred->next=me, forcing
me->locked=1 to happen before this operation.
Fixes: 2173f3333b ("mcslock: add MCS queued lock implementation")
Cc: stable@dpdk.org
Signed-off-by: Diogo Behrens <diogo.behrens@huawei.com>
Acked-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Linking with the 'pci' driver when building with MinGW on
Windows fails with undefined symbol 'GUID_DEVCLASS_NET'.
This occurs because devguid.h is included in rte_windows.h
before INITGUID is defined.
Move the include of devguid.h after the definition of INITGUID.
Fixes: b762221ac2 ("bus/pci: support Windows with bifurcated drivers")
Cc: stable@dpdk.org
Signed-off-by: Nick Connolly <nick.connolly@mayadata.io>
Reviewed-by: Tal Shnaiderman <talshn@nvidia.com>
Cleanup code style issue reported by kernel checkpatch. As follows:
* ERROR:CODE_INDENT: code indent should use tabs where possible
* ERROR:SPACING: spaces required around that '?' (ctx:VxE)
* WARNING:INDENTED_LABEL: labels should not be indented
Fixes: b0489e7bca ("malloc: fix linear complexity")
Cc: stable@dpdk.org
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
In the experimental function rte_flow_shared_action_destroy()
introduced in DPDK 20.11, the errno ETOOMANYREFS was used.
This errno is not always available on Windows,
so it is preferred using EBUSY instead.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Reviewed-by: Tal Shnaiderman <talshn@nvidia.com>
Tested-by: Tal Shnaiderman <talshn@nvidia.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
This patch defines new RSS offload types for eCPRI. For eCPRI with
Message Type 0, the hash field is physical channel ID.
Signed-off-by: Simei Su <simei.su@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Reasons for building not supported generally start with lowercase
because printed as the second part of a line.
Other changes:
- "linux" should be "Linux" with a capital letter.
- ARCH_X86_64 may be simply x86_64.
- aarch64 is preferred over arm64.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: David Marchand <david.marchand@redhat.com>
The definition of ETOOMANYREFS is reverted as it breaks build of
external applications already defining it.
Fixes: c917b54b0c ("eal/windows: add definition of ETOOMANYREFS")
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Reviewed-by: Nick Connolly <nick.connolly@mayadata.io>
Acked-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
The ETOOMANYREFS errno was missing from the Windows build.
It is used in initialization of flow error structures.
It is defined with the same error code used by WSAETOOMANYREFS.
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Replace -w / --pci-whitelist with -a / --allow options
and --pci-blacklist with --block.
The -b short option remains unchanged.
Allow the old options for now, but print a nag
warning since old options are deprecated.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Luca Boccassi <bluca@debian.org>
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Rename the enum values in the EAL include files.
As a backward compatible temporary migration tool, define
a replacement mapping for old values.
The old names relating to blacklist and whitelist are replaced
by block list and allow list, but applications may be using the
older compatibility macros, marked as deprecated.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Luca Boccassi <bluca@debian.org>
Acked-by: Gaetan Rivet <grive@u256.net>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Fix the detection of instruction pattern with multiple emits followed
by TX. Once detected, this is one of the instruction patterns that is
internally replaced with a single optimized instruction, as long as
none of the instructions to be replaced is referenced by a jump
instruction. The fix enforces this check for the TX instruction of
the pattern.
Fixes: 31035e87b2 ("pipeline: add SWX instruction optimizer")
Signed-off-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
This patch fixes a file descriptor leak which happens
in the error path of vhost_user_set_vring_kick().
Fixes: 4796ad63ba ("examples/vhost: import userspace vhost application")
Cc: stable@dpdk.org
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
Reviewed-by: Xueming Li <xuemingl@nvidia.com>
This patch fixes a file descriptor leak which happens
in the error path of vhost_user_set_log_base().
Fixes: 4796ad63ba ("examples/vhost: import userspace vhost application")
Cc: stable@dpdk.org
Reported-by: Xuan Ding <xuan.ding@intel.com>
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
Reviewed-by: Xueming Li <xuemingl@nvidia.com>
If an error is encountered before the memory regions are
parsed, the file descriptors for these shared buffers are
leaked.
This patch fixes this by closing the message file descriptors
on error, taking care of avoiding double closing of the file
descriptors. guest_pages is also freed, even though it was not
leaked as its pointer was not overridden on subsequent function
calls.
Fixes: 8f972312b8 ("vhost: support vhost-user")
Cc: stable@dpdk.org
Reported-by: Xuan Ding <xuan.ding@intel.com>
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
Reviewed-by: Xueming Li <xuemingl@nvidia.com>
This patches fixes virtqueue initialization issue causing
segfault or file descriptor being closed unexpectedly.
The wrong index was passed to init_vring_queue() by
alloc_vring_queue() when a hole in the virtqueue array was
met.
Fixes: 8acd7c2133 ("vhost: fix virtqueues metadata allocation")
Cc: stable@dpdk.org
Reported-by: Yu Jiang <yux.jiang@intel.com>
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
Tested-by: Yu Jiang <yux.jiang@intel.com>
Async inflight packet counter should take failed packets into account.
Failed packets will be deducted in the error handling logic.
Fixes: 6b3c81db8b ("vhost: simplify async copy completion")
Fixes: cd6760da10 ("vhost: introduce async enqueue for split ring")
Cc: stable@dpdk.org
Signed-off-by: Patrick Fu <patrick.fu@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
For VxLAN packets, GRO will mistakenly reassemble them
if inner L3 is IPv6, inner L4 is TCP or UDP, and outer L3
is IPv4 because the value of IS_IPV4_VXLAN_TCP4/UDP4_PKT
is true for them.
This fix makes sure IS_IPV4_TCP_PKT, IS_IPV4_UDP_PKT,
IS_IPV4_VXLAN_TCP4_PKT and IS_IPV4_VXLAN_UDP4_PKT can make
decision precisely.
Fixes: e2d8110636 ("gro: support VXLAN UDP/IPv4")
Fixes: 1ca5e67408 ("gro: support UDP/IPv4")
Fixes: 9e0b9d2ec0 ("gro: support VxLAN GRO")
Fixes: 0d2cbe59b7 ("lib/gro: support TCP/IPv4")
Cc: stable@dpdk.org
Signed-off-by: Yi Yang <yangyi01@inspur.com>
Acked-by: Jiayu Hu <jiayu.hu@intel.com>
Meson versions >= 0.54.0 include support for handling /implib
with msvc link. Specifying it explicitly causes failures when
linking against the dll. Tested using Link 14.27.29112.0 and
Clang 11.0.0.
There were a number of changes to the way that import libraries
are handled between 0.47.1 and 0.54.0. Only make the change
for >= 0.54.0, leaving the behaviour unchanged for earlier
versions.
Fixes: 77cca7ccec ("build: fix drivers library path on Windows")
Cc: stable@dpdk.org
Signed-off-by: Nick Connolly <nick.connolly@mayadata.io>
Tested-by: Ranjit Menon <ranjit.menon@intel.com>
Acked-by: Ranjit Menon <ranjit.menon@intel.com>
Acked-by: Khoa To <khot@microsoft.com>
When doing Clang build with '-mcpu=native' on N1 platform, build failed
with:
../lib/librte_eal/arm/include/rte_atomic_64.h:76:39:
error: instruction requires: lse
__ATOMIC128_CAS_OP(__cas_128_release, "caspl")
This is because native detection for Neoverse N1 was added in Clang-11.
Prior version of Clang's assembler doesn't know LSE support on hardware.
Fixed this for Clang earlier than version 11 by specifying architecture
for assembler.
Referred to [1] for this fix.
Fixes: 7e2c3e17fe ("eal/arm64: add 128-bit atomic compare exchange")
Cc: stable@dpdk.org
[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=e0d5896bd356cd577f9710a02d7a474cdf58426b
Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
The SPAPR IOMMU requires that a DMA window size be defined before memory
can be mapped for DMA. Current code dynamically modifies the DMA window
size in response to every new memory allocation which is potentially
dangerous because all existing mappings need to be unmapped/remapped in
order to resize the DMA window, leaving hardware holding IOVA addresses
that are temporarily unmapped. The new SPAPR code statically assigns
the DMA window size on first use, using the largest physical memory
memory address when IOVA=PA and the highest existing memseg virtual
address when IOVA=VA.
Signed-off-by: David Christensen <drc@linux.vnet.ibm.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
