When adding items to a hash table with multiple threads,
there is an spinlock used to prevent data corruption
(unless Transactional Memory is supported).
If there is a failure, the spinlock should be released,
but there were cases where that was not happening.
Fixes: be856325cb ("hash: add scalable multi-writer insertion with Intel TSX")
Cc: stable@dpdk.org
Signed-off-by: Mike Stolarchuk <mike.stolarchuk@bigswitch.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Replace the incorrect reference to "Cavium Networks", "Cavium Ltd"
company name with correct the "Cavium, Inc" company name in
copyright headers.
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Since SSE4 is now part of the minimum requirements for DPDK, we don't need
a fallback case to handle selection of algorithm when SSE4 is unavailable.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Remove rte_pause() definition from rte_common.h and
switchover to architecture specific rte_pause.h
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Compile the armv8a CRC32 support only if the machine
has the CRC extensions i.e if RTE_MACHINE_CPUFLAG_CRC32
is defined.
Removed the .arch assembly directives as these are no
more necessary.
Signed-off-by: Ashwin Sekhar T K <ashwin.sekhar@caviumnetworks.com>
Reviewed-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Verified the changes with thash_autotest unit test case
Signed-off-by: Ashwin Sekhar T K <ashwin.sekhar@caviumnetworks.com>
Acked-by: Jianbo Liu <jianbo.liu@linaro.org>
Fixing typos across dpdk source code using codespell utility.
Skipped the ethdev driver's base code fixes to keep the base
code intact.
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Acked-by: John McNamara <john.mcnamara@intel.com>
build error with icc version 17.0.4 (gcc version 7.0.0 compatibility):
In file included from .../dpdk/lib/librte_hash/rte_fbk_hash.h(59),
from .../dpdk/lib/librte_hash/rte_fbk_hash.c(54):
.../dpdk/x86_64-native-linuxapp-icc/include/rte_hash_crc.h(480):
error #1292: unknown attribute "fallthrough"
__attribute__ ((fallthrough));
^
In file included from .../dpdk/lib/librte_hash/rte_fbk_hash.h(59),
from .../dpdk/lib/librte_hash/rte_fbk_hash.c(54):
.../dpdk/x86_64-native-linuxapp-icc/include/rte_hash_crc.h(486):
error #1292: unknown attribute "fallthrough"
__attribute__ ((fallthrough));
^
This code patch hit when gcc > 7 installed and ICC doesn't recognize
fallthrough attribute.
Fixed by disabling code when compiled with ICC.
Fixes: 3dfb9facb0 ("lib: add switch fall-through comments")
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
This fixes compiler warnings with GCC 7 for arm64 build.
Fixes: da8dcc27f6 ("hash: use armv8-a CRC32 instructions")
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
With GCC 7 we need to explicitly document when we are falling through from
one switch case to another.
Fixes: af75078fec ("first public release")
Fixes: 8bae1da2af ("hash: fallback to software CRC32 implementation")
Fixes: 9ec201f5d6 ("mbuf: provide bulk allocation")
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Add an extra parameter to the ring dequeue burst/bulk functions so that
those functions can optionally return the amount of remaining objs in the
ring. This information can be used by applications in a number of ways,
for instance, with single-consumer queues, it provides a max
dequeue size which is guaranteed to work.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Add an extra parameter to the ring enqueue burst/bulk functions so that
those functions can optionally return the amount of free space in the
ring. This information can be used by applications in a number of ways,
for instance, with single-producer queues, it provides a max
enqueue size which is guaranteed to work. It can also be used to
implement watermark functionality in apps, replacing the older
functionality with a more flexible version, which enables apps to
implement multiple watermark thresholds, rather than just one.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Before this patch, the management of dependencies between directories
had several issues:
- the generation of .depdirs, done at configuration is slow: it can take
more than one minute on some slow targets (usually ~10s on a standard
PC without -j).
- for instance, it is possible to express a dependency like:
- app/foo depends on lib/librte_foo
- and lib/librte_foo depends on app/bar
But this won't work because the directories are traversed with a
depth-first algorithm, so we have to choose between doing 'app' before
or after 'lib'.
- the script depdirs-rule.sh is too complex.
- we cannot use "make -d" for debug, because the output of make is used for
the generation of .depdirs.
This patch moves the DEPDIRS-* variables in the upper Makefile, making
the dependencies much easier to calculate. A DEPDIRS variable is still
used to process library dependencies in LDLIBS.
After this commit, "make config" is almost immediate.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Tested-by: Robin Jarry <robin.jarry@6wind.com>
Tested-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Multiwriter insert function was using a fixed value for
the bucket size, instead of using the
RTE_HASH_BUCKET_ENTRIES macro, which value was changed
recently (making it inconsistent in this case).
Fixes: be856325cb ("hash: add scalable multi-writer insertion with Intel TSX")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
When trying to insert a new entry, if its target bucket is full,
the alternative location (bucket) of one of the entries is checked,
to try to find an empty slot, with make_space_bucket.
This function is called every time a new bucket is checked, recursively.
To avoid having a very long insert operation (and to avoid filling up
the stack), a limit in the number of pushes is introduced.
Fixes: 48a3991196 ("hash: replace with cuckoo hash implementation")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
This patch replaces the pipelined rte_hash lookup mechanism with a
loop-and-jump model, which performs significantly better,
especially for smaller table sizes and smaller table occupancies.
Signed-off-by: Byron Marohn <byron.marohn@intel.com>
Signed-off-by: Saikrishna Edupuganti <saikrishna.edupuganti@intel.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Sameh Gobriel <sameh.gobriel@intel.com>
In lookup bulk function, the signatures of all entries
are compared against the signature of the key that is being looked up.
Now that all the signatures are together, they can be compared
with vector instructions (SSE, AVX2), achieving higher lookup performance.
Also, entries per bucket are increased to 8 when using processors
with AVX2, as 256 bits can be compared at once, which is the size of
8x32-bit signatures.
Signed-off-by: Byron Marohn <byron.marohn@intel.com>
Signed-off-by: Saikrishna Edupuganti <saikrishna.edupuganti@intel.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Sameh Gobriel <sameh.gobriel@intel.com>
Move current signatures of all entries together in the bucket
and same with all alternative signatures, instead of having
current and alternative signatures together per entry in the bucket.
This will be benefitial in the next commits, where a vectorized
comparison will be performed, achieving better performance.
The alternative signatures have been moved away from
the current signatures, to make the key indices be consecutive
to the current signatures, as these two fields are used by lookup,
so they are in the same cache line.
Signed-off-by: Byron Marohn <byron.marohn@intel.com>
Signed-off-by: Saikrishna Edupuganti <saikrishna.edupuganti@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Sameh Gobriel <sameh.gobriel@intel.com>
In order to optimize lookup performance, hash structure
is reordered, so all fields used for lookup will be
in the first cache line.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Sameh Gobriel <sameh.gobriel@intel.com>
In function rte_hash_cuckoo_insert_mw_tm, while looking for
an empty slot, only the first entry in the bucket was being checked,
as key_idx array was not being iterated.
Fixes: 5fc74c2e14 ("hash: check if slot is empty with key index")
Reported-by: Bruce Richardson <bruce.richardson@intel.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Instead of checking if the current and alternative signatures are 0,
it is faster to check if the key index associated to an entry
is 0, meaning that the slot is empty.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Saikrishna Edupuganti <saikrishna.edupuganti@intel.com>
This commit fixes a corner case scenario. When a key is deleted,
its signature in the hash table gets clear, which should prevent
a lookup of that same key, unless the signature of the key is all zeroes.
In that case, there will be a match, and key would be compared against
the key that is in the table (which does not get cleared,
as the performance penalty would be high), resulting in a wrong hit.
To prevent this from happening, the key index associated to that entry
should be set to zero when deleting it, so in case that same key
is looked up just after a deletion, it will point to the dummy key slot,
which guarantees a miss.
Fixes: 48a3991196 ("hash: replace with cuckoo hash implementation")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Saikrishna Edupuganti <saikrishna.edupuganti@intel.com>
Ring stores the free slots available to be used in the key table.
The ring size was being increased by 1, because of the dummy slot,
used for key misses, but this is not actually stored in the ring,
so there is no need to increase it.
Fixes: 5915699153 ("hash: fix scaling by reducing contention")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Saikrishna Edupuganti <saikrishna.edupuganti@intel.com>
Set cmp_jump_table_idx to KEY_CUSTOM in rte_hash_cmp_eq so that the custom
function we are setting in rte_hash_set_cmp_func properly works. The custom
function is only called by rte_hash_cmp_eq if cmp_jump_table_idx is set to
KEY_CUSTOM.
Fixes: 95da2f8e9c ("hash: customize compare function")
Signed-off-by: Masoud Hasanifard <masoudhasanifard@gmail.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Exported header files used by applications should allow the strictest
compiler flags. Language extensions used in many places must be explicitly
marked to avoid warnings and compilation failures.
Unnamed structs/unions are allowed since C11, however many compiler
versions do not use this mode by default.
This commit prevents the following errors:
error: ISO C99 doesn't support unnamed structs/unions
error: struct has no named members
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Exported header files used by applications should allow the strictest
compiler flags. Language extensions used in many places must be explicitly
marked or removed to avoid warnings and compilation failures.
The extension keyword is used whenever the C99 syntax cannot do it.
This commit prevents the following errors:
error: ISO C forbids zero-size array `[...]'
Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
The function rte_hash_get_key_with_position is added in this patch.
As the position returned when adding a key is frequently used as an
offset into an array of user data, this function performs the operation
of retrieving a key given this offset.
A possible use case would be to delete a key from the hash table when
its entry in the array of data has certain value. For instance, the key
could be a flow 5-tuple, and the value stored in the array a time
stamp.
Signed-off-by: Juan Antonio Montesinos <juan.antonio.montesinos.delgado@ericsson.com>
Signed-off-by: Yari Adan Petralanda <yari.adan.petralanda@ericsson.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
This patch introduced scalable multi-writer Cuckoo Hash insertion
based on a split Cuckoo Search and Move operation using Intel
TSX. It can do scalable hash insertion with 22 cores with little
performance loss and negligible TSX abortion rate.
* Added an extra rte_hash flag definition to switch default single writer
Cuckoo Hash behavior to multiwriter.
- If HTM is available, it would use hardware feature for concurrency.
- If HTM is not available, it would fall back to spinlock.
* Created a rte_cuckoo_hash_x86.h file to hold all x86-arch related
cuckoo_hash functions. And rte_cuckoo_hash.c uses compile time flag to
select x86 file or other platform-specific implementations. While HTM check
is still done at runtime (same idea with
RTE_HASH_EXTRA_FLAGS_TRANS_MEM_SUPPORT)
* Moved rte_hash private struct definitions to rte_cuckoo_hash.h, to allow
rte_cuckoo_hash_x86.h or future platform dependent functions to include.
* Following new functions are created for consistent names when new platform
TM support are added.
- rte_hash_cuckoo_move_insert_mw_tm: do insertion with bucket movement.
- rte_hash_cuckoo_insert_mw_tm: do insertion without bucket movement.
* One extra multi-writer test case is added.
Signed-off-by: Wei Shen <wei1.shen@intel.com>
Signed-off-by: Sameh Gobriel <sameh.gobriel@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
The function rte_hash_lookup_multi() was renamed rte_hash_lookup_bulk()
in DPDK 1.4 and was kept as an undocumented alias.
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
To avoid a race condition while creating a new hash object, the
list has to be locked before the lookup, and released only once the
new object is added in the list.
As the lock is held by the rte_ring_create(), move its creation at the
beginning of the function and only take the lock after the ring is
created to avoid a deadlock.
Fixes: 48a3991196 ("hash: replace with cuckoo hash implementation")
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Change rte_hash*_create() functions to return NULL and set rte_errno to
EEXIST when the object name already exists. This is the behavior
described in the API documentation in the header file.
These functions were returning a pointer to the existing object in that
case, but it is a problem as the caller did not know if the object had
to be freed or not.
Doing this change also makes the hash API more consistent with the other
APIs (mempool, rings, ...).
Fixes: 916e4f4f4e ("memory: fix for multi process support")
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Hash library used a function pointer to choose a different
key compare function, depending on the key size.
As a result, multiple processes could not use the same hash table,
as the function addresses vary from one process to another.
Instead, a jump table is used, so each process has its own
function addresses, accessing this table with an index stored
in the hash table (note that using a custom key compare function
is not supported in multi-process mode).
Fixes: 48a3991196 ("hash: replace with cuckoo hash implementation")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Instead of using RTE_ARCH_X86_64, RTE_ARCH_X86_32
and RTE_ARCH_I686, use directly RTTE_ARCH_X86
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
rte_hash_set_cmp_func() had an incorrect Doxygen comment
for one of its parameters.
Fixes: 95da2f8e9c ("hash: customize compare function")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Fix crc32c hash functions to return a valid crc32c value for
data lengths not multiple of 4 bytes.
ARM code is not tested.
Fixes: af75078fec ("first public release")
Signed-off-by: Didier Pallard <didier.pallard@6wind.com>
Acked-by: David Marchand <david.marchand@6wind.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
When built in a C++ application, the jhash include fails:
rte_jhash.h:123:22: error:
invalid conversion from ‘const void*’ to ‘const uint32_t*’ [-fpermissive]
const uint32_t *k = key;
^
The cast must be explicit for C++.
Fixes: 8718219a87 ("hash: add new jhash functions")
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
fix the error reported by checkpatch:
"ERROR: return is not a function, parentheses are not required"
remove parentheses in return like:
"return (logical expressions)"
remove parentheses in return a function like:
"return (rte_mempool_lookup(...))"
Fixes: 6307b909b8 ("lib: remove extra parenthesis after return")
Signed-off-by: Huawei Xie <huawei.xie@intel.com>
This patch fixes the compile errors caused by lacking of "size_t"
definition in rte_hash.h.
The compile error exists on IBM POWER and ARM.
The errors are like:
In file included from app/test/test_hash_scaling.c:35:0:
rte_hash.h:70:70: error: unknown type name ‘size_t’
Fixes: 95da2f8e9c ("hash: customize compare function")
Signed-off-by: Chao Zhu <chaozhu@linux.vnet.ibm.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Give user a chance to customize the hash key compare function.
The default rte_hash_cmp_eq function is set in the rte_hash_create
function, but these builtin ones may not good enough, so the user
may call this to override the default one.
Signed-off-by: Yu Nemo Wenbin <yuwb_bjy@ctbri.com.cn>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
rte_hash_create function was accidentally duplicated in
DPDK_2.1 in rte_hash_version.map.
Fixes: 473d1beb ("hash: allow to store data in hash table")
Reported-by: Ferruh Yigit <ferruh.yigit@intel.com>
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
select hash function for cuckoo, fbk as rte_hash_crc_4byte
if arm64-CRC extension available
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
armv8-a has optional CRC32 extension, march=armv8-a+crc enables code
generation for the ARMv8-A architecture together with
the optional CRC32 extensions.
added RTE_MACHINE_CPUFLAG_CRC32 to detect the availability of
CRC32 extension in compile time. At run-time, The RTE_CPUFLAG_CRC32
can be used to find the availability.
armv8-a+crc target support added in GCC 4.9,
Used inline assembly and emulated __ARM_FEATURE_CRC32 to work
with tool-chain < 4.9
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
The following measurements shows improvement over the default
libc memcmp function
Length(B) by X% over libc memcmp
16 149.57%
32 122.7%
48 104.96%
64 98.21%
80 93.75%
96 90.55%
112 110.48%
128 137.24%
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
If user has not added an all zero key in the hash table,
and tries to look it up, it results in an incorrect hit,
as dummy slot in the key table has all zero as well.
Fixes: 48a3991196 ("hash: replace with cuckoo hash implementation")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
If using multiple cores on a system with hardware transactional
memory support, thread scaling does not work, as there was a single
point in the hash library which is a bottleneck for all threads,
which is the "free_slots" ring, which stores all the indices of
the free slots in the table.
This patch fixes the problem, by creating a local cache per logical core,
which stores locally indices of free slots,
so most times, writer threads will not interfere each other.
Fixes: 48a3991196 ("hash: replace with cuckoo hash implementation")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Since freeing a ring is now possible, then when freeing
a hash table, its internal ring can be freed as well.
Therefore when a new table, with the same name as a previously
freed table, is created, there is no need to look up
the already allocated ring.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
When calculating the size for the table which allocates
the keys, size was calculated wrongly from multiplying
two 32-bit variables, resulting on a 32-bit number,
before casting to 64-bit, so maximum size was 4G.
Fixes: 48a3991196 ("hash: replace with cuckoo hash implementation")
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
The function rte_jhash2() was renamed rte_jhash_32b and
macros RTE_HASH_KEY_LENGTH_MAX and RTE_HASH_BUCKET_ENTRIES_MAX
were tagged as deprecated, so they can be removed in 2.2.
RTE_HASH_KEY_LENGTH is replaced in unit tests by an internal macro
for the memory allocation of all keys used.
The library version number is incremented.
Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
Signed-off-by: Thomas Monjalon <thomas.monjalon@6wind.com>
Make thash library arch-independent.
Leave unaligned union rte_thash_tuple if no support for SSE3.
Makes 32bit compiler happy by adding ULL suffix.
Signed-off-by: Vladimir Medvedkin <medvedkinv@gmail.com>
When adding with cuckoo hash a key which was already inserted
a new slot is dequeued and then enqueued back, but the enqueue
operation was not done properly.
Fixes: 48a3991196 ("hash: replace with cuckoo hash implementation")
Signed-off-by: Xavier Simonart <xavier.simonart@intel.com>
Acked-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
