Remove duplicate space allocation for the pool header. Not significant
w/ CLIB_CACHE_LINE_BYTES >= 64 since the code rounds the size of the
pool header to an even multiple of the cache line size.
Type: fix
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I923f2a60e7565cf2dfbc18d78264bf82ff30c926
(cherry picked from commit 6e495ce428e110665ee9616e0951015963502cac)
No point in checking the return value,
as .sendall() raises on error
(and the previous check was missing "not").
Type: fix
Change-Id: I9e07709ddd7093f91ffef87808abbab264b8aa5a
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
(cherry picked from commit 8921dc675458b238fc03c5aed53d3462bcdbdb3c)
Type: fix
"set int state <interface> down" puts the virtio device link
down. It will not put the link in "UP" state, when
"set int state <interface up>" will be used again to change
the interface admin up. This patch fixes it.
To test:
create tap
set int state tap0 up
set int state tap0 down
sh hardware
sh int
set int state tap0 up
sh int
sh hardware
Change-Id: I3c0e31539f8a2a1e40220e7fb57eedecf408f067
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
(cherry picked from commit 529f0e97b6064039c500adce0d54b738954b2ffa)
Type: fix
Some vhost-backends give used descriptors back in
out-of-order. This patch fixes the native virtio to
handle out-of-order descriptors.
Change-Id: I74ba03a2111dc601be4396c0fa800c33db5554b4
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
(cherry picked from commit 7f6d145accc6e63b150ab4efc282f19cbe996b57)
Fix a bug that caused some input packets to be dropped due to errors of
the type 'ip4 length > l2 length'. The change is related to the second
call to the rdma_device_input_bufs() function that happens when the end
of the ring buffer is reached.
Type: fix
Change-Id: I332d69ab22242b3443a0baca6e5dd86349a54765
Signed-off-by: Elias Rudberg <elias.rudberg@bahnhof.net>
(cherry picked from commit e5ecf3ea4b456afb710f4ed903cd7e4c1ae87859)
Ticket: VPPSUPP-58
1) Previously, host mtu can't be set if tap interface is in namespace.
2) generate the host mac address, if it is not provided.
3) fix the parameters for tap_create_v2 in vat.
4) fix the pretty print of parameters for tap_create_v2 in custom dump.
Type: fix
Change-Id: I18898af90dbd37d773a40b6535dd9c03c9984679
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
While TSO is supported for Intel NIC, Cisco VIC does not work.
The problem is due to txmode offloads is not properly set for
the Cisco VIC when enable-tcp-udp-checksum is configured.
Type: fix
Ticket: VPP-1838
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: I72c41db9b327ed8d08ef70d74e8cc6206d4a102f
For chain buffer, need to traverse b->next_buffer to transmit all buffers
in the chain. Only set EOP at the last descriptor in the chain to signal
this is a chain descriptor.
Introduce slow path to handle ring wrap. This is needed because chain
buffer may consist of multiple pieces and it may span from near the end of
the ring to the beginning of the ring.
Type: fix
Ticket: VPP-1843
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: Id7c872f3e39e09f3566aa63f3cdba8f40736d508
(cherry picked from commit f7ab7b2d9bc0f42c1e766d22d49dd0dc4f28abb6)
In the previous implementation of socket transport for PAPI,
socket methods .send and .recv_into were used.
But they are not guaranteed to send/receive all the data
for the full message. The receive part contained a loop,
but it handled only the main message, not the header.
This patch replaces .send with .sendall
and uses newly defined _read_fixed method.
Also, removed Paul from maintainers,
as he is not active much, lately.
Type: fix
Change-Id: Iae1a68bf8f9e666856b7c7d62ebfe22defc5dfe1
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
(cherry picked from commit 6df2c7954126a316f86908526c3bb4d649f06597)
Previously, self.transport.q got the messages
(at least for socket transport), stored in the encoded (packed) form.
In order to avoid accessing internals for async reads,
a new method is introduced, to perform
blocking reads of decoded (unpacked) messages.
The method is also used in _call_vpp(),
so sync and async reads are kept compatible.
Type: feature
Change-Id: Id49792dfa57c00b1a14a198031c5398d09a9ba20
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
(cherry picked from commit 0938547eaaf5440de28877fa4f873c21bcb8cfbf)
The function vl_socket_read_ready did contain some comments already,
but as they stated, the logic has to be tricky to cover multiple cases.
Comment:
+ Add function-level comment
+ Add comments to describe some of local variables
+ Add many comments to describe internal state at particular lines.
Simplify:
+ Remov mbp_set as it is never needed.
+ Replace msg_len with msgbuf_len to save "+ sizeof (msgbuf_t)".
Improve:
+ Early exit on EAGAIN.
Fix:
+ "n" now only tracks input_buffer.
Previously, it was entering the detection of additional messages
even for unprocessed_input.
+ Set up msg_buffer (including appending to unprocessed_input)
outside full-message-detection loop now,
so it cannot be executed multiple times as before.
Type: fix
Ticket: VPP-1785
Change-Id: I256e34b435be06844458744a13ea37a0e86a96f9
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
(cherry picked from commit 6a6af6ea1a77b5818e717047b5d01251ef6d024a)
The pcap trace filter initial table index lives in
cm->filter_set_by_sw_if_index [0], which corresponds to the "local0"
interface. Debug cli makes sure that folks don't accidentally specify
the "local0" interface. At least it does now...
Fix the "vlib format.c code coverage" test in test/test_vlib.py.
Type: fix
Change-Id: I35320bc2c8f0c6f1f8c12e3529d1938548185151
Signed-off-by: Dave Barach <dave@barachs.net>
(cherry picked from commit 29c6132108be68feb11c8d9bfaaf674cba86ee33)
Configure n-tuple classifier filters which apply to the vpp packet
tracer.
Update the documentation to reflect the new feature.
Add a test vector.
Type: feature
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: Iefa911716c670fc12e4825b937b62044433fec36
(cherry picked from commit 87d24db65facb89ca524c951b8379ca2ec4dbc7a)
If clib_time_verify_frequency() adjusts the clock frequency, transform
total_cpu_time to the new time coordinate space. Otherwise, we break
comparisons with previous clib_time_now() value.
Without this correction, time jumps in one direction or the other
depending on the sign of the frequency change. Reasonably harmless in
most cases, but under perfect storm conditions the wheels fall off.
Type: fix
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I21802c2630e2c87ff817cd732b7d78bc022cd2d7
(cherry picked from commit e52d8d880ac644f07154bc2fb94035a198ed6688)
If an arc declaration includes '.last_in_arc = "some-node"', assume
that folks mean it and add explicit ordering constraints.
Fix the "arp" arc declaration which claimed that the arc ends at
arp-disabled, but the arc really ends at error-drop.
Type: fix
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: Ie2de1fb30091671cbc7c62770903a2e05987f141
(cherry picked from commit 5f9f3c8de8d5d9f83a437661a98e5cc2453705f9)
Add vl_client_connect_to_vlib_thread_fn (...) and export the
memory_client_main_t definition.
If you use this new API, make sure not to miss the setjmp / longjmp
dance shown in .../src/vlibmemory/memory_client.c:rx_thread_fn(...),
which is required for the rx pthread to terminate cleanly; please
process client delete reply messages in the rx thread...
Type: refactor
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: Ia67038ec59e2e14b174c67afca15b2c3f67a4d20
(cherry picked from commit 920180e5e0722c78c258ff26476fd5efa434032d)
In a rare event, we may be skipping processing lacp pdu's when the it is
not in steady state.
Type: fix
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: I4e4f81dfd4e95433879ee66cdf6edb8d8afbe9b0
fib_walk_sync may call adj_alloc which may cause adj_pool to expand. When
that happens, any previous frame which still use the old adj pointer needs to
refresh. Failure to do so may access or update to the old adj memory
unintentionally and crash mysteriously.
Type: fix
Ticket: VPPSUPP-54
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: Ia7c6cb03c1ed9ddbbfb12dd42c8abc7f5b3f210c
Regardless of whether the virtio_net_hdr is sent as a separate
descriptors or in the same descriptor as the data, we always want to
skip the header length - maybe moving to the next descriptor along the
way.
Type: fix
Change-Id: Iaa70aeb310e589639b20f8c7029aaa8d3ce5d307
Signed-off-by: Benoît Ganne <bganne@cisco.com>
(cherry picked from commit 5ecc1e4d433a34845c7bfd761dc990413e6c321b)
Ticket: VPP-1821
Type: fix
Fixes: 6dfd3785e4
When a bond interface is administratively down but the slaves are
up, process inbound LACP packets received over the slaves. This
was the old behavior with bond interfaces in LACP mode and was
altered unintentionally by another change. Restore the old behavior.
Change-Id: I61b0b700211dea4859b6ee447ab83b33197d9d11
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
(cherry picked from commit 854eb6e3ff87ace211a45a8053424d8432bd5755)
Binary API trace replay with multiple worker threads depends in many
cases on worker thread graph replica maintenance. If we (implicitly)
assert a worker thread barrier at the debug CLI level, all graph
replica changes are deferred until the replay operation completes. If
an interface is deleted, the wheels may fall off.
Type: fix
Ticket: VPP-1824
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I9b07d43f8501caa5519e5ff9ae4c19dc2661cc84
Type: fix
The crash occured trying to retreive a NULL path list to walk the path
extensions. A walk shoul not be required, because there should be no
extensins, since all paths are removed. The problem is that when the
paths were added, they were not sorted, hence neither were the
extensions and when they were updated, duplicate extensions were added,
and hence a path removal did not remove them all.
Fix is to make sure paths are sorted.
Change-Id: I069d937de8e7bc8aae3d92f588db4daff727d863
Signed-off-by: Neale Ranns <nranns@cisco.com>
Type: fix
Signed-off-by: John Lo <loj@cisco.com>
Change-Id: I711432f589ee4a4527cf795526d3b4031999f71d
(cherry picked from commit b2e73b1dcb8e9eb3bf74a96fff20a9b27f7e6d73)
For active-backup mode, we transmit on one and only one interface. However,
we might still receive traffic on the backup interface. We should drop them
and strictly process incoming traffic on only the active interface.
Type: fix
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: Idb6b798b30033e84044b151c616be3c157329731
(cherry picked from commit 6dfd3785e4d65418f4330a73bf837912c37b8ec2)
Type: fix
Several tunnels encapsulation use udp as outer header and udp src port
is set by inner header flow hash, such as gtpu, geneve, vxlan, vxlan-gbd
Since flow hash of inner header is already been calculated, keeping it
to vnet_buffere[b]->ip.flow_hash should save load-balance node work to
select ECMP uplinks.
Change-Id: I0e4e2b27178f4fcc5785e221d6d1f3e8747d0d59
Signed-off-by: Shawn Ji <xiaji@tethrnet.com>
(cherry picked from commit 623b4f85e6ee4611ae15bb3103fe30725ca977ed)
Type: fix
On multiworker setup when an app client dies, the
vec_reset_length call fails the assert in
clib_mem_is_heap_object. Same thing might happen for
the clib_warnings
Change-Id: I369f9d2dbe60407c84994a4e8d25f6df7848ca93
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
(cherry picked from commit 5ed3fe3dd4320a7b4080f18de32ef491b5a1c7f0)
Type: fix
Since Vxlan hw offload jumps the ethernet-input node, so needs to
adjust the data offset accordingly
In original code, the current_data is 0 when arriving vxlan-flow-input
node(due to no graph node before it, except the dpdk-input), so this
code block cannot find the correct vxlan header:
enum
{ payload_offset = sizeof (ip4_vxlan_header_t) };
vlib_buffer_advance (b0, payload_offset);
see code in src/vnet/vxlan/decap.c, function vxlan4_flow_input_node
This patch fixes this issue
Signed-off-by: Chenmin Sun <chenmin.sun@intel.com>
Change-Id: Iab4af7a7dc3b69a117a4c9ea1c59662669a6438c
(cherry picked from commit 1ec9fdbf29aedcdd4040feb635971c3f87a1cfdf)
