summaryrefslogtreecommitdiffstats
path: root/src/vnet/devices/devices.c
AgeCommit message (Collapse)AuthorFilesLines
2020-09-09interface: support configuring RSS steering queuesChenmin Sun1-2/+0
This patch adds the RSS steering queues set interface, and it's implementation in DPDK device: /* Interface to set rss queues of the interface */ typedef clib_error_t *(vnet_interface_rss_queues_set_t) (struct vnet_main_t * vnm, struct vnet_hw_interface_t * hi, clib_bitmap_t *bitmap); This patch also introduces a command line to set the RSS queues: set interface rss queues <interface> <list <queue-list>> To display the rss queues, use "show hardware-interfaces" Below is the example to configure rss queues for interface Gig0: vpp# set interface rss queues Gig0 list 0,2,4-7 vpp# show hardware-interfaces brief Name Idx Link Hardware VirtualFunctionEthernet18/1/0 1 down VirtualFunctionEthernet18/1/0 Link speed: unknown RSS queues: 0 2 4 5 6 7 local0 0 down local0 Link speed: unknown vpp# Users can also configure the rss queues on a dpdk interface in startup.conf: dpdk { dev 0000:18:01.0 { rss-queues 0,2,5-7 } } Type: feature Signed-off-by: Chenmin Sun <chenmin.sun@intel.com> Change-Id: I1835595a1c54016a84eabee9fd62ce137935385d
2018-11-26Add a feature arc consistency checkDave Barach1-0/+1
Verify that last node in the computed feature order matches reality. This check doesn't make sense in all cases, so we skip it if the newly-added vnet_feature_arc_registration_t ".last_in_arc" datum is a NULL pointer. Change-Id: Ia99c3e2b2da2e4780a7d5bc71670c5742a66fef2 Signed-off-by: Dave Barach <dave@barachs.net>
2017-11-21dpdk: add l2_hdr_offset and l3_hdr_offset in vlib_buffer_tDamjan Marion1-0/+10
Change-Id: I0a6d1257e391c3b6f7da6498bd5f7d4c545d17e9 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-09-07Devices: Set interface rx-mode may cause SIGSEGV with nonexistent queueSteven1-0/+8
When I type in set interface rx-mode with a nonexistent queue, I got a crash with the following traceback. It looks like the vm is NULL when vlib_node_get_runtime is called. DBGvpp# sh int rx Thread 0 (vpp_main): node dpdk-input: TenGigabitEthernet5/0/0 queue 0 (polling) TenGigabitEthernet5/0/1 queue 0 (polling) TenGigabitEthernet7/0/0 queue 0 (polling) TenGigabitEthernet7/0/1 queue 0 (polling) node vhost-user-input: VirtualEthernet0/0/2 queue 0 (adaptive) DBGvpp# set interface rx-mode VirtualEthernet0/0/2 queue 1 polling Thread 1 "vpp_main" received signal SIGSEGV, Segmentation fault. 0x00007ffff6d4e0bc in vlib_node_get_runtime (vm=0x0, node_index=125) at /home/sluong/vpp/build-data/../src/vlib/node_funcs.h:92 92 vlib_node_t *n = vec_elt (nm->nodes, node_index); (gdb) where at /home/sluong/vpp/build-data/../src/vlib/node_funcs.h:92 at /home/sluong/vpp/build-data/../src/vlib/node_funcs.h:112 vnm=0x6f0fa0 <vnet_main>, hw_if_index=7, queue_id=1, mode=0x7fffb62099e8) at /home/sluong/vpp/build-data/../src/vnet/devices/devices.c:307 hw_if_index=7, queue_id=1, mode=VNET_HW_INTERFACE_RX_MODE_POLLING) at /home/sluong/vpp/build-data/../src/vnet/interface_cli.c:1192 vm=0x7ffff7b9d440 <vlib_global_main>, input=0x7fffb6209ef0, cmd=0x7fffb61d5d14) at /home/sluong/vpp/build-data/../src/vnet/interface_cli.c:1288 vm=0x7ffff7b9d440 <vlib_global_main>, cm=0x7ffff7b9d630 <vlib_global_main+496>, input=0x7fffb6209ef0, parent_command_index=18) at /home/sluong/vpp/build-data/../src/vlib/cli.c:588 vm=0x7ffff7b9d440 <vlib_global_main>, cm=0x7ffff7b9d630 <vlib_global_main+496>, input=0x7fffb6209ef0, parent_command_index=12) The fix is to add a check for vec_len(hw->input_node_thread_index_by_queue) and vec_len (hw->rx_mode_by_queue) to reject the command if the queue_id is out of bound. While at it, I notice inputting queue_id=-1 is being interpreted as all queues. An easy fix is to not overload the queue_id variable with -1 to mean something else. Change-Id: Id70ec3e7d06ccc67635e6d28ef53420bdac4a988 Signed-off-by: Steven <sluong@cisco.com>
2017-08-01P2P EthernetPavel Kotucek1-0/+6
Change-Id: Idb97e573961b3bc2acdeef77582314590795f8c3 Signed-off-by: Pavel Kotucek <pkotucek@cisco.com>
2017-06-21Introduce default rx mode for device driversDamjan Marion1-0/+3
If interface is down and queues are not configured then we are not able to change rx-mode. This change introducess default mode which is stored per interface and applied if driver wants. Change-Id: I70149c21c1530eafc148d5e4aa03fbee53dec62f Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-06-16Add missing barrier sync to rx placement infra codeDamjan Marion1-5/+15
Change-Id: I25ccf8260dbe7e1550aee3904a688fc135ce1f03 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-05-22vhost: migrate to use device infra for worker thread assignment, rx-mode.Steven1-0/+20
and add adaptive mode support to receive queue - Migrate vhost to use device infra which does the interface/queue to worker thread assignment. - Retire vhost thread CLI and corresponding code which assigns interface/queue to worker thread. set interface placement should be used instead to customize the interface/queue to worker thread assignment. - Retire vhost interrupt/polling option when creating vhost-user interface. Instead, set interface rx-mode should be used. - Add code in vnet_device_input_unassign_thread to change the node state to interrupt if the last polling interface has left the worker thread for the device of the corresponding interface/queue. - Add adaptive mode support. The node state is set to interrupt initially. When the scheduler detects a burst of traffic, it switches the input node to polling. Then we inform the device that we don't need interrupt notification. When the traffic subsides, the scheduler switches the input node back to interrupt. Then we immediately tell the driver that we want interrupt notification again. - Remove some duplicate code in vlib/main.c Change-Id: Id19bb1b9e50e6521c6464f470f5825c26924d3a8 Signed-off-by: Steven <sluong@cisco.com>
2017-05-10device: Add callback for set interface rx-modeSteven1-0/+1
- When the interface rx-mode is changed via CLI, the corresponding device may want to know about it and to reset the driver. This patch is to add the callback. - In the function vnet_hw_interface_set_rx_mode, it appears it is missing a line hw->rx_mode_by_queue[queue_id] = mode because the function is checking if the new mode is the same as hw->rx_mode_by_queue which is initialized to POLLING. So if the function is called to change the mode to interrupt, it just returns without doing anything. This is the check that I am talking about in the same function. if (hw->rx_mode_by_queue[queue_id] == mode) return 0; Change-Id: Iaca2651c43e0ae3fda6fd8dc128e247b0851cc65 Signed-off-by: Steven <sluong@cisco.com>
2017-05-02Add interface rx mode commands, unify rx mode and placement CLIDamjan Marion1-150/+22
Change-Id: Ib506c3e9d66170f29e3266ad6dc4d32b829befba Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-04-11Devices: set interface placement does not remove the old interface placementSteven1-3/+0
The command set interface placement is supposed to remove the existing interface placement and add a new interface placement based on the given options. My quick test for the CLI shows that the old interface placement continues to exist. But the new interface placement is also added. The bug exists in vnet_device_input_unassign_thread which checks the old thread index is the same as the passed thread index and skips the deletion if they are the same. The fix is to remove the check which is not supposed to be there. Change-Id: Ib055721fad47513949a03b3cb6dc292bd19fd1e8 Signed-off-by: Steven <sluong@cisco.com>
2017-04-10Common device-input interrupt infraDamjan Marion1-16/+119
Change-Id: I23b588eb56a3f5690158449a1f9bc8053cd3d251 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-04-06Use thread local storage for thread indexDamjan Marion1-30/+31
This patch deprecates stack-based thread identification, Also removes requirement that thread stacks are adjacent. Finally, possibly annoying for some folks, it renames all occurences of cpu_index and cpu_number with thread index. Using word "cpu" is misleading here as thread can be migrated ti different CPU, and also it is not related to linux cpu index. Change-Id: I68cdaf661e701d2336fc953dcb9978d10a70f7c1 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-03-20vnet: add device-input threadplacement infraDamjan Marion1-0/+240
This change adds two new debug CLI command: - "show interface placmenet" to display which thread (main or worker) is responsible for processing interface rx queue vpp# show interface placement Thread 0 (vpp_main): node af-packet-input: host-vpp1 queue 0 Thread 1 (vpp_wk_0): node af-packet-input: host-virbr0 queue 0 Thread 2 (vpp_wk_1): node af-packet-input: host-vpp2 queue 0 host-lxcbr0 queue 0 - "set interface placmenet" to assign thread (main or worker) which process specific interface rx queue vpp# set interface placement host-vpp1 queue 0 main Change-Id: Id4dd00cf2b05e10fae2125ac7cb4411b446c5e9c Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-03-17Fix IP feature ordering.Neale Ranns1-1/+0
Drop comes before lookup when enabled. is_first_or_last is not required when setting a feature, the anchor is added in find_config_with_features(). Don't make the PG interfaces automatically L3 enabled, this way we can have tests that check the L3 protocol disbaled behaviour. Change-Id: Icef22a920b27ff9cec6ab2da6b05f05c532cb60f Signed-off-by: Neale Ranns <nranns@cisco.com>
2017-03-01devices: vnet_get_aggregate_rx_packets should not be dpdk specificDamjan Marion1-0/+14
Change-Id: I1152db4b7d1602653d7d8b2c6cb28cf5c526c4ca Signed-off-by: Damjan Marion <damarion@cisco.com>
2016-12-28Reorganize source tree to use single autotools instanceDamjan Marion1-0/+91
Change-Id: I7b51f88292e057c6443b12224486f2d0c9f8ae23 Signed-off-by: Damjan Marion <damarion@cisco.com>