aboutsummaryrefslogtreecommitdiffstats
path: root/src/vnet/devices
AgeCommit message (Collapse)AuthorFilesLines
2022-02-18vnet: add set_max_frame_size callbacks for several interfacesArtem Glazychev1-0/+9
This is required after distinguishing between max_frame_size and MTU Type: fix Signed-off-by: Artem Glazychev <artem.glazychev@xored.com> Change-Id: Ie642bee4e30ca76903bb8be5eeb6914c2c09bf35
2022-02-15tcp: Do not include the tcp_packet.h file in the ip4_packet.hNeale Ranns3-0/+3
Type: refactor IP4 does not depend on TCP (it's the other way around). This upside down dependency leads to some nasty circular includes when trying to use ip46_address.h in interface.h Signed-off-by: Neale Ranns <neale@graphiant.com> Change-Id: I4a1bd21543b08b9c1cf1e5563da738414734a878
2022-02-01virtio: coverity woes -- divide by zeroSteven Luong1-0/+7
Coverity complains the expression, j % vif->num_txq, may encounter divide by zero. While there is little chance that vif->num_txq is zero, it is easy to prevent divide by zero if vif->num_txq is ever zero. Type: fix Fixes: I337ec63d0868f665329d68eadf1744e080b73a0d Signed-off-by: Steven Luong <sluong@cisco.com> Change-Id: I2e91f296737ce266ab70fffc1f442cc600724fa2
2022-01-18virtio: remove admin-up flag during interface creationMohsin Kazmi2-4/+0
Type: fix During the interface creation time, (by default) admin-up flag is locally set for tap and virtio interfaces. While, in VPP the state of these interfaces are still admin-down. User needs to explicitly call 'set interface state <interface-name> up' to admin-up the newly created tap or virtio interface(s) in VPP. So, this behavior is inconsistent. This patch fixes the issue to have consistent behavior for given interface between local and global administration state. Change-Id: Ifd8904a09fbdbe7b386874ac3231dc0527064518 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2022-01-18vnet: distinguish between max_frame_size and MTUDamjan Marion2-10/+10
Type: improvement Change-Id: I3659de6599f402c92e3855e3bf0e5e3388f2bea0 Signed-off-by: Damjan Marion <damarion@cisco.com>
2022-01-17interface: improve MTU handlingDamjan Marion1-21/+16
- per hw-interface-class handlers - ethernet set_mtu callback - driver can now refuse MTU change Type: improvement Change-Id: I3d37c9129930ebec7bb70caf4263025413873048 Signed-off-by: Damjan Marion <damarion@cisco.com>
2022-01-11linux-cp: Add VPP->Linux synchronizationPim van Pelt2-1/+46
Part 1 -- notes in https://ipng.ch/s/articles/2021/08/13/vpp-2.html Add the ability for VPP to copy out (sync) its state from the dataplane to Linux Interface Pairs, when they exist. Gated by a configuration flag (linux-cp { lcp-sync }), and by a CLI option to toggle on/off, synchronize the following events: - Interface state changes - Interface MTU changes - Interface IPv4/IPv6 address add/deletion In VPP, subints can have any link state and MTU, orthogonal to their phy. In Linux, setting admin-down on a phy forces its children to be down as well. Also, in Linux, MTU of children must not exceed that of the phy. Add a state synchronizer which walks over phy+subints to ensure Linux and VPP end up in the same consistent state. Part 2 -- notes in https://ipng.ch/s/articles/2021/08/15/vpp-3.html Add the ability for VPP to autocreate sub-interfaces of existing Linux Interface pairs. Gated by a configuration flag (linux-cp { lcp-auto-subint }), and by a CLI option to toggle on/off, synchronize the following event: - Sub-interface creation (dot1q, dot1ad, QinQ and QinAD) A few other changes: - Add two functions into netlink.[ch] to delete ip4 and ip6 addresses. - Remove a spurious logline (printing MTU) in netlink.c. - Resolve a TODO around vnet_sw_interface_supports_addressing() Type: improvement Signed-off-by: Pim van Pelt <pim@ipng.nl> Change-Id: I34fc070e80af4013be58d7a8cbf64296cc760e4e Signed-off-by: Pim van Pelt <pim@ipng.nl>
2022-01-10interface: refactor interface capabilities code, part 2Damjan Marion4-57/+57
Type: improvement Signed-off-by: Damjan Marion <damarion@cisco.com> Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com> Change-Id: Ie595e69af8657b0ee18a84ac71c5d433108d9ef8
2022-01-07ethernet: new interface registration functionDamjan Marion5-56/+28
Prep for supporting multiple callbacks, optional args, etc. Type: improvement Change-Id: I96244c098712e8213374678623f12527b0e7f387 Signed-off-by: Damjan Marion <damarion@cisco.com>
2022-01-06tap: add num_tx_queues APINathan Skrzypczak5-5/+181
This adds a create_tap_v3 api that has a num_tx_queues parameter allowing to create more than num_workers queues, following on multi TX support Type: feature Change-Id: Idce433147e8dd165f842241d6c76e041e1b1c9b8 Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2022-01-05interface: refactor interface capabilities codeDamjan Marion5-38/+30
Make it shorter to type, easier to debug, make adding callbacks in future simpler. Type: improvement Change-Id: I6cdd6375e36da23bd452a7c7273ff42789e94433 Signed-off-by: Damjan Marion <damarion@cisco.com>
2021-12-14virtio: integrate with new tx infraMohsin Kazmi8-53/+237
Type: improvement Change-Id: I337ec63d0868f665329d68eadf1744e080b73a0d Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2021-12-03interface: add multi tx-queues support for new tx infraMohsin Kazmi1-4/+2
Type: feature Change-Id: I231f782b3c56dc2b10321e4569ac7acdad1c11da Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2021-11-27devices: fix af_packet GSO checkNathan Skrzypczak1-1/+6
Type: fix This fixes the GSO size calculation in af_packet which didn't include the ethernet size. This is not ideal, as we default to the host side mtu to check whether a packet is GSO or not and to set the GSO size. But there doesn't seem to be more info passed with the packets. Change-Id: I9769e1dd21d5989b4cf67295352b5535454f88d1 Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2021-11-23devices: support build on older kernelsFlorin Coras1-0/+3
Type: improvement Signed-off-by: Florin Coras <fcoras@cisco.com> Change-Id: I10af028b5e57b36b8015b02240f1e4e9a42d0898
2021-11-12virtio: improve the inline of clib_memcpy_fastMohsin Kazmi1-1/+1
Type: refactor Change-Id: Ia13a9cf6480aac280f3d287c59908e84c29c3443 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2021-11-05devices: remove dead code in pipeDamjan Marion1-2/+1
Type: refactor Change-Id: If4a0484afebe53d53d79ab5cb72299e6298cfee7 Signed-off-by: Damjan Marion <damarion@cisco.com>
2021-11-05virtio: fix the initializationMohsin Kazmi1-1/+1
Type: fix Fixes: d96b28ac0917 ("virtio: improve input node performance") vlib_buffer_t is defined on stack to be used for input feature arc lookup once per frame call for performance reasons. The definition is missing the initialization to avoid the assignment of garbage value. Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com> Change-Id: Ie7930186bbd8240c44d257808ebd31e06e854b29
2021-10-29devices: default mode eth in the apiNathan Skrzypczak2-2/+4
Type: fix https://gerrit.fd.io/r/c/vpp/+/34027 added support for l3 mode, but as the eth_mode constant was set to 1 we did default to l3 mode in the api. This reverts to the original logic. Change-Id: If8b90b300d3868de5233dfa1f33ec975853cba11 Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2021-10-28tap: handle null namespace and bridge correctlyMatthew Smith1-2/+4
Type: fix In tap_create_if(), if args->host_namespace or args->host_bridge are null because no values were set for those, the virtio_if_t entry in virtio_main.interfaces ends up getting populated with values of "(nil)" in net_ns or host_bridge, respectively. Check whether args->host_namespace and args->host_bridge are null before trying to set the corresponding fields on virtio_if_t. Change-Id: I8e1e66a6d7b246e7c66fece406d116ffb1312c64 Signed-off-by: Matthew Smith <mgsmith@netgate.com>
2021-10-27devices: fix coverity warning/don't leak fdKlement Sekera1-1/+2
Move socket creation past code which returns from function to avoid leaking the socket in case of an early error return. Type: fix Signed-off-by: Klement Sekera <ksekera@cisco.com> Change-Id: I9e18bd32022441c17ca920d1c2458b058b76c3c0
2021-10-22devices: add support for l3 af_packet interfaceMohsin Kazmi5-37/+106
Type: improvement Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com> Change-Id: Ia6b9d4ac55be2216887bfdb99be4021f6a96f166
2021-10-06docs: vnet comment nitfixesNathan Skrzypczak1-31/+37
Type: improvement Change-Id: Iac01d7830b53819ace8f199554be10ab89ecdb97 Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2021-10-05tap: free the tap_fds vec on interface deletionMohsin Kazmi1-0/+1
Type: fix Tap fds are stored in vector array but deleting tap was not freeing this vector. This patch fixes it. Change-Id: I5228e3b9f432c69cf2656b2ee7402360d775964b Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2021-10-04virtio: remove control queue support from virtio_show() for tap/tunMohsin Kazmi1-6/+0
Type: fix Tap/Tun interfaces do not have control queue. This patch removes the support of control queue from virtio_show() which is used by show tap/tun cli. Change-Id: Ib89144ad488ed548fb1ce50ee232a1b8659ccf29 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2021-10-01devices: add support for pseudo header checksumMohsin Kazmi3-15/+49
Type: improvement Linux uses pseudo header checksum when checksum of l4 is offloaded. This patch adds similar support in virtual interfaces. Change-Id: I6a94d1104e59356f95057e7c122e3be9cd8659a3 Signed-off-by: Aloys Augustin <aloaugus@cisco.com> Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2021-09-29tap: Fix tap create with nsNathan Skrzypczak1-55/+24
This fixes the interface creation passing a netns. [0] made the renaming of the new tuntap interface before switching netns Thus, preventing creating an interface in another netns if one exists in VPP's netns with the same name. This also fixes restore netns on errors Type: fix [0] https://gerrit.fd.io/r/c/vpp/+/33696 Change-Id: I5c83bb37d664057bcf231cd0c636f0e51aa542ad Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2021-09-28devices: Add queues params in create_ifNathan Skrzypczak7-96/+185
Type: feature Change-Id: I027ff2c5c905a7ccebd3705a58e35218a94f4880 Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2021-09-27virtio: Still init unused txqNathan Skrzypczak1-17/+0
Type: fix For some virtio backends, packets don't seem to flow if all the queues that have been requested are not initialized Change-Id: I41765d668497ff954e6d69d36836590947fd93b1 Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2021-09-27tap: move the api msg_id_base to tap_main_tMohsin Kazmi2-3/+3
Type: fix Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com> Change-Id: Ia4065550a7ad1109e3a2592ef2c21b5e23fa85b5
2021-09-22tap: remove cxq_vring from tap/tunMohsin Kazmi1-1/+0
Type: fix virtio_if_t is shared data struct between tap, tun and virtio pci. cxq_vring is virtio pci specific element. It shouldn't be set or accessed in tap driver. Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com> Change-Id: I8b34570f61b38d8b9d79d5b0669bda0f89ebc28c
2021-09-22virtio: fix the type of argument in virtio_show()Mohsin Kazmi2-7/+8
Type: fix virtio have three different interfaces (tap, tun and native virtio). virtio_show() is used by CLI commands to show information about these interfaces. It uses interface type to print interface specific information. virtio_show() should use proper type for virtio interfaces (TAP, TUN, VIRTIO). Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com> Change-Id: I2043dc2cfe2e2f6c7c9348b8494aa4a27cab31f3
2021-09-15tap: set device name on creation via TUNSETIFFDuncan Eastoe1-17/+8
Type: fix Currently when a new TAP/TUN device is created from tap_create_if() via the TUNSETIFF ioctl(), a name is allocated by the kernel (eg. tap0). If the caller supplied a name this is subsequently set via netlink, after the device has been created. Now we request the kernel to create the new device with the caller's requested name in the first instance, thus avoiding the need to rename the device, and therefore avoiding a window where the device exists with a different name. This can be beneficial, for example, when writing systemd-udevd link files [1]. Having the TAP/TUN devices created with the requested name ensures they can be correctly matched by the OriginalName option. Writing link files might be necessary, for example, to avoid VPP and systemd-udevd racing to set the MAC address on a newly created TAP interface. systemd-udevd can be configured to not manipulate the MAC addresses of matched interfaces. These changes also resolve an issue where the created device would not be renamed if the caller requested it be moved to a different network namespace, since vnet_netlink_set_link_name() was not called in that case. [1] https://www.freedesktop.org/software/systemd/man/systemd.link.html Signed-off-by: Duncan Eastoe <duncan@graphiant.com> Change-Id: I3d657632856d03979d6b914225c3c841c379e0a1
2021-09-07devices: restore regular af-packet tx pathMohammed Hawari2-21/+28
This change restores the af_packet tx path prior in use prior to Change Idf0bdd88990254a614962c2f7bc3e0292ccfd61a but fixes the stalling issue by ensuring that the next tx frame pointer is only incremented when a new tx frame is used. This change also enables the af_packet PACKET_QDISC_BYPASS option, for better performance. Change-Id: I65dde648ed66d21654847a900ceda5a8980ae6ec Type: improvement Signed-off-by: Mohammed Hawari <mohammed@hawari.fr>
2021-08-26vhost: migrate to new TX infraSteven Luong3-88/+67
Take advantage of the new TX infra and support manual thread placement Type: improvement Signed-off-by: Steven Luong <sluong@cisco.com> Change-Id: Id8023846a2eb59125fcf2f80f4f11eb681cf14dc
2021-08-20vlib: add format_vnet_buffer_no_chainBenoît Ganne1-3/+2
- add format_vnet_buffer and format_vnet_buffer_no_chain to mirror format_vlib_buffer and format_vlib_buffer_no_chain - format_vnet_buffer used to be the "no chain" version, replace all of its current use with the corresponding format_vnet_buffer_no_chain - add a function to dump vnet buffer details from gdb Type: improvement Change-Id: I143ce845f80e7ef937ea33a557b6e3b5988c5b8f Signed-off-by: Benoît Ganne <bganne@cisco.com>
2021-08-18vhost: interrupt mode support with mqSteven Luong3-138/+209
vhost interrupt mode support with mq does not work when coalesce frame is not configured to 0. When packed-ring is configured, we were also setting the wrong flag for want-interrupt. No need to trigger an interrupt to RX infra if there is at least one queue in the same thread that is doing polling. Type: fix Signed-off-by: Steven Luong <sluong@cisco.com> Change-Id: I8e64250f2aa6bf611a777a53e4d2c1076d83305f
2021-07-22vppinfra: add abstract socket & netns fnsNathan Skrzypczak1-32/+14
* Add clib_socket_init support for abstract sockets if name starts with an '@' * Add clib_socket_init_netns to open socket in netns * Add clib_netns_open Type: feature Change-Id: I89637ad657c702ec38ddecb5c03a1673d0dfb104 Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
2021-07-15misc: replace CLIB_PREFETCH with clib_prefetch_{load,store}Damjan Marion3-16/+16
Type: refactor Change-Id: Id10cbf52e8f2dd809080a228d8fa282308be84ac Signed-off-by: Damjan Marion <damarion@cisco.com>
2021-07-08tap: Set the MTU on the TUN deivceNeale Ranns1-0/+13
Type: fix For a TAP device the MTU is set via the ethernet_register for TUN we need to do it explicitly (like we do for other tunnel types). Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com> Signed-off-by: Neale Ranns <neale@graphiant.com> Change-Id: Ie6a13c795acb35b53f8d99b05c70c3e73a7b428e
2021-06-23virtio: api cleanupFilip Tehlar2-49/+13
Use autogenerated code. Does not change API definitions. Type: improvement Signed-off-by: Filip Tehlar <ftehlar@cisco.com> Change-Id: I4f9316b16f16a48e2042aa17db596bfd181bd314
2021-06-22virtio: api cleanupFilip Tehlar1-54/+9
Use autogenerated code. Does not change API definitions. Type: improvement Signed-off-by: Filip Tehlar <ftehlar@cisco.com> Change-Id: I047310b8c9fcc51dcfb187710ff59b7895abe217
2021-06-22devices: af_packet api cleanupFilip Tehlar1-53/+8
Use autogenerated code. Does not change API definitions. Type: improvement Signed-off-by: Filip Tehlar <ftehlar@cisco.com> Change-Id: Ic7979755494a2fd23b9fa3d74e14f6b9ea0a46d0
2021-06-22devices: tapv2 api cleanupFilip Tehlar1-49/+12
Use autogenerated code. Does not change API definitions. Type: improvement Signed-off-by: Filip Tehlar <ftehlar@cisco.com> Change-Id: I0a2c1cbbe798ddf9d08da78bf0b458a0f54fa13a
2021-06-22devices: api cleanupFilip Tehlar1-52/+8
Use autogenerated code. Does not change API definitions. Type: improvement Signed-off-by: Filip Tehlar <ftehlar@cisco.com> Change-Id: I03f51393a92bae45608d9fc9f53164f3b0add3cd
2021-06-07pg: Reduce the inclusion of pg.hNeale Ranns1-0/+3
Type: style reduce the number of files recompiled after changing pg.h from 1110 to 102. Signed-off-by: Neale Ranns <neale@graphiant.com> Change-Id: I50611eba818eeb3a2dffd437a3c72c77766bed80
2021-05-17virtio: add the checks for descriptors chain lenMohsin Kazmi1-0/+23
Type: fix virtio uses indirect descriptors for chain buffers. indirect descriptor chain is mapped on a vlib_buffer_t. Single descriptor is 16 bytes and vlib_buffer_t has 2048 bytes space. So maximum long chain can have 128 (=2048/16) indirect descriptors. This patch adds check to make sure descriptors chain len should not exceed 128. Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com> Change-Id: I060cfb7709568f42c9b5634527172690ce66a1a3
2021-05-08vhost: low performance in interrupt mode in some casesSteven Luong1-35/+19
When vhost and another interface, say tap, are configured for interrupt mode, performance number may be very low from vhost. Further analysis discovers that when vhost posts an interrupt to the RX infra, there is a 10 msec delay in waking up its input routine. The delay is due to vhost posts the interrupt from the main thread which tries to wake up the worker thread. The fix is for vhost to move the posting interrupt call to the corresponding input worker thread by calling vnet_hw_if_set_rx_queue_file_index() to set it up. While at it, streamline the function vhost_user_kickfd_read_ready() since it will be called from the worker thread. Type: fix Signed-off-by: Steven Luong <sluong@cisco.com> Change-Id: I9beedcd33e1558c8335da4ee7fadc51c29ee4589
2021-05-06vlib: fix the offload flags sizeMohsin Kazmi5-6/+6
Type: fix Change-Id: I433fe3799975fe3ba00fa30226f6e8dae34e88fc Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2021-05-05vlib: move offload flags to 1st cacheline in vlib_buffer_tMohsin Kazmi2-3/+3
Type: improvement Some tests i.e. ipsec see performance regression when offload flags are moved to 2nd cacheline. This patch moves them back to 1st cacheline. Change-Id: I6ead45ff6d2c467b0d248f409e27c2ba31758741 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>