Age | Commit message (Collapse) | Author | Files | Lines |
|
When calling vlib_buffer_clone() on a source vlib_buffer with no next
buffer but whose total_length_not_including_first_buffer hadn't been
properly zeroed out, the total_length_not_including_first_buffer of
the clone was set to a wrong value.
(see https://lists.fd.io/g/vpp-dev/topic/19869395)
Change-Id: I4b503ece804e3933bb259be4c2148f84dafbea3e
Signed-off-by: Yoann Desmouceaux <ydesmouc@cisco.com>
|
|
- Currently mempool priv size is getting initialized after releasing buffers
to pool. This is causing mismatch in expected & real metadata size value
and buffers are getting released with wrong offset. (when metadata offset
is in use for a given platform)
- Since private data size is 0 initially, metadata size don't include space
for VLIB_BUFFER_HDR.
Change-Id: I780c4d518104631a3dcf192185bacf58b3598e65
Signed-off-by: Sachin Saxena <sachin.saxena@nxp.com>
|
|
Cause: EVP_MD_CTX object used but not initialized.
Change-Id: I390b2acf580f16415685563fa52e56717efc7be7
Signed-off-by: Radu Nicolau <radu.nicolau@intel.com>
|
|
Change-Id: I088163f10ae5515d7a9115781cc13ef563fafed5
Signed-off-by: Matus Fabian <matfabia@cisco.com>
|
|
Change-Id: Ia1b49d7fd5f32d9a5139df5df636b46264003a63
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I9343672c5765a5a4cb56c99fa5de176ddcac62c7
Signed-off-by: Andrey "Zed" Zaikin <zed.0xff@gmail.com>
|
|
Change-Id: Ieae4ff6429fc5bdcf0e243db40ab7ec00c30730a
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
|
|
next nodes
Use the new frame-at-once functions vlib_get_buffers() and vlib_buffer_enqueue_to_next()
to calculate the buffer pointers and to dispatch the packets after the processing.
This simplifies the dataplane node processing loop.
Change-Id: I454308f847aac76a199f8dd7490c1e176414bde7
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
|
|
- The issue is appearing on ARM platofrms where DPDK drivers are also using
__thread TLS vairables.
- The issue was only appearing with dpdk as plgin to VPP and not if used
as statically link with VPP.
- Using traditional TLS scheme resolved the issue.
Change-Id: Ifb4c667fdd217c2b1d79be8a541a2c983222d95a
Signed-off-by: Sachin Saxena <sachin.saxena@nxp.com>
|
|
- Fix the issue where eal iova mode is Virtual Address (RTE_IOVA_VA) but
setting DMA iova address to Physical address value always.
Change-Id: Ib1e9c1596d95885c7eff11723338121627203e61
Signed-off-by: Sachin Saxena <sachin.saxena@nxp.com>
|
|
Change-Id: I4cc6a20b69cce2aa52768a27c5d455eb098224c8
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Change-Id: I84327197d59c72d0d046dd2cb4071bf74af6fc28
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Move handling of IP neighbor pool full into main thread on entry
creation and make sure static entriesare not deleted for reuse.
Fix IPv6 neighbor handling on interface down and up so that static
entries are not deleted.
Change-Id: I073794949a41a5b86201e519ebe479febfc506c8
Signed-off-by: John Lo <loj@cisco.com>
|
|
Change-Id: I1773d962b373693a737d39c0c97e8c53eb91545a
Signed-off-by: Marek Gradzki <mgradzki@cisco.com>
|
|
Gain is around 6 clocks per packet (22 to 16).
Change-Id: Ia6f4293ea9062368a9a6b235c650591dbc0707d0
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
(VAPI_*BIN).d targets didnt have fake.api.vapi.h* as dependencies
this causes the compilation to proceed before the python script
generates the header files.
Explicit linking of stdc++ is required for clang as errors like
undefined reference to 'new operator' pop up.
Change-Id: I3ca0ef048f392c4a032160ce0e4f7ae759f4c79d
Signed-off-by: Sirshak Das <sirshak.das@arm.com>
Reviewed-by: Brian Brooks <brian.brooks@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
|
|
Old code ~25 clocks/packet, new ~10.
Change-Id: I202cd6cbafb1ab2296939634d674f7ffd28253fc
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
clib_bihash_search_40_8 for session lookups
Use inline version rather than calling the function, this gives slightly better performance.
The straighforward diff uncovered an interesting problem: the stateful ACL IPv4 unit tests would fail
for the "make test" but succeed in "make test-debug". Also, they would succeed even in "make test",
if before calling the clib_bihash_search_inline_2_40_8 we would change the code
to store the key in a temporary variable.
Debugging revealed that the generated optimized code is not what one would expect:
the zeroing of the u64s overlaying the memcpy into ipv4 value of ip46_address_t
made the optimizer not notice the latter, and think that those fields should be
always zero in the bihash, thus generating incorrect assembly for the bihash key
comparison for the ipv4 nodes.
Changing the zeroing to be non-overlapping by zeroing only the pad fields resulted
in the optimizer generating the correct code and the tests pass.
Change-Id: Ib0f55cef2b5fe70c931d17ca4dc32a5755d160cd
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
|
|
the ip4-dhcp-client-detect feature MUST run prior to nat44-out2in, or
inbound dhcp broadcast packets will be dropped. Certain dhcp servers
answer lease renewal dhcp-request packets with broadcast dhcp-acks, leading
to unrecoverable lease loss.
In detail, this constraint:
VNET_FEATURE_INIT (ip4_snat_out2in, static) = {
.arc_name = "ip4-unicast",
.node_name = "nat44-out2in",
.runs_after = VNET_FEATURES ("acl-plugin-in-ip4-fa"),
};
doesn't get the job done:
ip4-unicast:
[17] nat44-out2in
[23] ip4-dhcp-client-detect
[26] ip4-not-enabled
Add a proper constraint:
VNET_FEATURE_INIT (ip4_snat_out2in, static) = {
.arc_name = "ip4-unicast",
.node_name = "nat44-out2in",
.runs_after = VNET_FEATURES ("acl-plugin-in-ip4-fa",
"ip4-dhcp-client-detect"),
};
and the interface feature order is OK, at least in this regard:
ip4-unicast:
[17] ip4-dhcp-client-detect
[18] nat44-out2in
[26] ip4-not-enabled
We need to carefully audit (especially) the ip4-unicast feature arc,
which has [gasp] 37 features on it!
Change-Id: I5e749ead7ab2a25d80839a331de6261e112977ad
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: Ic1fab1f3aba92bbdbfd281459562d1f9697ab465
Signed-off-by: John Lo <loj@cisco.com>
|
|
The option no-multi-seg doesn't take effect for RX since MTU
which is too large is passed to DPDK lib, Which causes PMDs
are running XXX_scattered_rx function. The patch fixes the issue.
Change-Id: I91a6fb23fd118e872c8a52a6c35c36a86cb2c02b
Signed-off-by: Zhiyong Yang <zhiyong.yang@intel.com>
|
|
- fix newreno cwnd computation
- reset snd_una_max on entering recovery
- accept acks beyond snd_nxt but less than snd_congestion when in
recovery
- avoid entering fast recovery multiple times when using sacks
- avoid as much as possible sending small segments when doing fast
retransmit
- more event logging
Change-Id: I19dd151d7704e39d4eae06de3a26f5e124875366
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
per-packet session key
Using a separate session key has proven to be tricky for the following reasons:
- it's a lot of storage to have what looks to be nearly identical to 5tuple,
just maybe with some fields swapped
- shuffling the fields from 5tuple adds to memory pressure
- the fact that the fields do not coincide with the packet memory
means for any staged processing we need to use up a lot of memory
Thus, just add two entries into the bihash table pointing to
the same session entry, so we could match the packets from either
direction.
With this we have the key layout of L3 info (which takes up
the majority of space for IPv6 case) the same as in the packet,
thus, opening up the possibility for other optimizations.
Not having to create and store a separate session key
should also give us a small performance win in itself.
Also, add the routine to show the session bihash in a better
way than a bunch of numbers.
Alas, the memory usage in the bihash obviously doubles.
Change-Id: I8fd2ed4714ad7fc447c4fa224d209bc0b736b371
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
|
|
Should cost at most 1 clock per frame when not enabled.
Add "pcap rx trace..." debug CLI, refactored "pcap tx trace" debug CLI
to avoid duplicating code.
Change-Id: I19ac75d1cf94a6a24c98facbf0753381d37963ea
Signed-off-by: Dave Barach <dbarach@cisco.com>
|
|
Replace clib_warning with vlib_log_warn
Change-Id: I6d0b8d97048b75f4418609264af0c14e19fad79b
Signed-off-by: Juraj Sloboda <jsloboda@cisco.com>
|
|
Thanks to Ning Li <muziding001@163.com> for reporting.
Change-Id: I758bc6760ec5a9ec688172bc162a1873f96ab4f3
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: I0fe60a639c7589dc842d85db092c81c1a7441cb7
Signed-off-by: Jakub Grajciar <jgrajcia@cisco.com>
|
|
- hash is great. But it is a bit too slow for the DP. Use direct array indexing
to quickly retrieve the slave interface.
- the algorithm used by flow hash is great. But it is a bit too slow for the DP.
Use l2_hash_hash() extracted from lb_hash.h which ECMP is using. It makes use
of intrinsic crc32 instruction set.
- shortcut modulo arithmetic when the operand is 2**x (where x up to 4) to
avoid division instruction.
- special case for link count == 1 in bond_tx_fn()
- use clib_mem_unaligned to access data for the packet to avoid alignment error
- Fix some typos for packet tracing.
Change-Id: I8eae3ad497061c5473aa675ba894ee0211120d25
Signed-off-by: Steven <sluong@cisco.com>
|
|
Change-Id: I8335ebf266becf2f42bb3f28a17dfed8d9b08f97
Signed-off-by: Neale Ranns <nranns@cisco.com>
|
|
This compile issue was first reported by Sirshak Das in following thread:
https://lists.fd.io/g/vpp-dev/message/8384
The issue was caused by auto-config shell script auto-config-h.sh regard
quotation mark "" as $CROSS prefix for $CC when CROSS is empty.
Change-Id: Ied535c6d18c4dffacbddabc3ad2087dffe19438d
Signed-off-by: Bin Huang <huangbin.mails@gmail.com>
|
|
bihash_48_8 case:
Scalar code: 6 clocks
SSE4.2 code: 3 clocks
AVX2 code: 2.27 clocks
AVX512 code: 1.5 clocks
Change-Id: I40700175835a1e7321276e47eadbf9771d3c5a68
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Add support for either copying TOS/TC from inner packet to outer,
or set to fixed value.
Change-Id: I716a95f875349acec94317b266c8cf9f2f81a785
Signed-off-by: Ole Troan <ot@cisco.com>
|
|
Broken for years. Duh.
Change-Id: Ie5fb8e802f143aacd3301c45b136b24a8d4f6d74
Signed-off-by: Dave Barach <dave@barachs.net>
|
|
Change-Id: I8cbd1eac80ae4aeb173d02786e9ccf3b4877304d
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Change-Id: I80297e78d93d8cf0d347863e4d2fdb12ea9294ac
Signed-off-by: Klement Sekera <ksekera@cisco.com>
|
|
Fix GRE/IPv6 setting of ip->payload_length (which has never worked).
Change-Id: Ie68f1cc7bbb70489d6ec97356132c783f2345e1e
Signed-off-by: Ole Troan <ot@cisco.com>
|
|
Change-Id: I7a4133c59ff45b0744b48e246a049d9f015026fc
Signed-off-by: Ole Troan <ot@cisco.com>
|
|
Note: The Python, Java and C/C++ bindings must be updated before ip/ip_types.api can be used.
ip_types.api:
typedef ip4_address {
u8 address[4];
};
typedef ip6_address {
u8 address[16];
};
enum address_family {
ADDRESS_IP4 = 0,
ADDRESS_IP6,
};
union address_union {
vl_api_ip4_address_t ip4;
vl_api_ip6_address_t ip6;
};
typedef address {
vl_api_address_family_t af;
vl_api_address_union_t un;
};
Change-Id: I22f67092f24db5bd650a03c6f446a84cd9fd1074
Signed-off-by: Ole Troan <ot@cisco.com>
|
|
Change-Id: Ic9f98c022e32715af395c9ed618589434eb0e526
Signed-off-by: Eyal Bari <ebari@cisco.com>
|
|
Change-Id: I6615bb612bcc3f795b5f822ea55209bb30ef35b5
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
Change-Id: Ic8c5b527395fc99f1e1a72e51f8d41c9b4f415df
Signed-off-by: Jakub Grajciar <jgrajcia@cisco.com>
|
|
This commit splits the functions from fa_node.c
into the pure dataplane node functions (which are multiarch-compiled),
session management node functions (which are compiled only once),
and session find/add/delete functions which are split out into the inlines.
As part of the refactoring:
- get rid of BV() macros in the affected chunk of code,
rather use the explicit bihash function names.
- add the magic trailer to the new files to
ensure make checkstyle watches them.
- move the bihash_template.c include for 40_8 bihash into acl.c
Change-Id: I4d781e9ec4307ea84e92af93c09470ea2bd0c375
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
|
|
Change-Id: I56782652d8ef10304900cc293cfc0502689d800e
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Replace hash with a vector to improve performance.
Plus other minor performance improvements.
Change-Id: I3f0ebd909782ce3727f6360ce5ff5ddd131f8574
Signed-off-by: Radu Nicolau <radu.nicolau@intel.com>
|
|
Change-Id: I37705fb572045f42be4c2dabbd8460c8f8872167
Signed-off-by: Florin Coras <fcoras@cisco.com>
|
|
when flows are enabled on the device
Change-Id: I971764988d5a9e7078468f627205b3fa60736263
Signed-off-by: Eyal Bari <ebari@cisco.com>
|
|
Remove functions which have native C equivalent (i.e. _is_equal can be
replaced with ==, _add with +)
Add SSE4.2, AVX-512 implementations of splat, load_unaligned, store_unaligned,
is_all_zero, is_equal, is_all_equal
Change-Id: Ie80b0e482e7a76248ad79399c2576468532354cd
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
MLX DPDK mlx5_glue.so, compiled under RTE_LIBRTE_MLX5_DLOPEN_DEPS,
provides a run-time check for OFED libraries.
To do so, it links with -libverbs -lmlx5 so that the binding could
occur or fail at runtime (see DPDK 59b91be and VPP 59b91be).
However RPM install fails on systems without OFED installed since
RPM spec has an entry "Requires: libmlx5".
To overcome this, exclude such requirement from the spec.
Same applies to mlx4_glue.so, compiled under RTE_LIBRTE_MLX4_DLOPEN_DEPS
Change-Id: I0ff6efc49581104743cc7e5b1f7cdbc1665ce9ba
Signed-off-by: Igor Mikhailov (imichail) <imichail@cisco.com>
|
|
Change-Id: I6d1218c17ee055275596b9a49767f15994aa1b2b
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
This fixes ARM64 build where we dont have defined u16x8_msb_mask(...)
Change-Id: I864f5134a0d951601810c800f587d173b3b7ef41
Signed-off-by: Damjan Marion <damarion@cisco.com>
|