summaryrefslogtreecommitdiffstats
path: root/src/vnet/devices/virtio
AgeCommit message (Collapse)AuthorFilesLines
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
2021-07-15misc: replace CLIB_PREFETCH with clib_prefetch_{load,store}Damjan Marion2-14/+14
Type: refactor Change-Id: Id10cbf52e8f2dd809080a228d8fa282308be84ac Signed-off-by: Damjan Marion <damarion@cisco.com>
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
2021-06-07pg: 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 Kazmi4-5/+5
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>
2021-05-04virtio: add simple drop counter for interfaceMohsin Kazmi1-30/+33
Type: improvement Change-Id: I4ac6b1a6553e26a5c26b6761fa3c4cc5d4925486 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2021-05-04virtio: fix the interruptMohsin Kazmi3-162/+202
Type: fix virtio/tap interfaces set the empty buffers in the input node for receiving data. Backend uses those buffers, fills them with data and notifies the virtio/tap driver. But virtio/tap driver gets into stall state if interface is created and configured through exec script on VPP startup.conf and put the interface in interrupt mode while VPP is only configured with main thread. This patch fixes the problem by prefilling buffers during the interface creation. Change-Id: Ibc4d0e70e127ccc4b7cf8b2b18406ae4b02c73b4 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2021-05-01vlib: refactor trajectory trace debug featureBenoît Ganne2-6/+0
trajectory trace has been broken for a while because we used to save the buffer trajectory in a vector pointed to in opaque2. This does not work well when opaque2 is copied (eg. because of a clone) as 2 buffers end up sharing the same vector. This dedicates a full cacheline in the buffer metadata instead when trajectory is compiled in. No dynamic allocation, no sharing, no tears. Type: refactor Change-Id: I6a028ca1b48d38f393a36979e5e452c2dd48ad3f Signed-off-by: Benoît Ganne <bganne@cisco.com>
2021-04-05vhost: Crash upon disconnectSteven Luong1-1/+1
Patch 24601 introduced description into template. In vhost_user_process, template is reused inside the while loop to call clib_file_add. But description is allocated outside of the loop only once. As a result, the same storage for description is being referenced by all instances of call to clib_file_add. As long as we don't call clib_file_del, we may be good with multiple fds sharing the same storage for the description. When one of the fds disconnects and frees the description, the other fds is holding onto the free memory pointer. Bad news eventually happens when another fd disconnects and frees the description that was already free previously. The fix is to move the allocation of description inside the loop to avoid sharing. Type: fix Fixes: gerrit.fd.io/r/c/vpp/+/24601 Signed-off-by: Steven Luong <sluong@cisco.com> Change-Id: Ie670931acdc2c7b851982d98fd0d837284a19036
2021-03-24virtio: improve compilation timeDamjan Marion1-64/+57
Type: improvement Change-Id: I56dadb852f63da0597ddf4db395a22afdf2d9cc0 Signed-off-by: Damjan Marion <damarion@cisco.com>
2021-03-19interface: add capabilities flagsMohsin Kazmi3-16/+21
Type: improvement This patch adds flags to represent the modern NICs capabilities. Change-Id: I96d38d9ab7eac55974d72795cd100d8337168e1e Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2021-02-26virtio: place the event fds on worker threads for pci deviceMohsin Kazmi1-0/+11
Type: improvement Change-Id: I8322bca1a9aa75c97c0fe2ff24b2f65fc43242ce Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2021-02-24virtio: enable the interrupt support for uio_pci_genericMohsin Kazmi1-11/+4
Type: improvement Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com> Change-Id: Ic25ffe9c8e37826733cfb9e62cefb491bb3322bc
2021-02-15vlib: refactor checksum offload supportMohsin Kazmi4-30/+36
Type: refactor This patch refactors the offload flags in vlib_buffer_t. There are two main reasons behind this refactoring. First, offload flags are insufficient to represent outer and inner headers offloads. Second, room for these flags in first cacheline of vlib_buffer_t is also limited. This patch introduces a generic offload flag in first cacheline. And detailed offload flags in 2nd cacheline of the structure for performance optimization. Change-Id: Icc363a142fb9208ec7113ab5bbfc8230181f6004 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2021-02-08virtio: use vpp clib_memset instead glibc memsetMohsin Kazmi1-2/+2
Type: improvement Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com> Change-Id: Ib3cefe5d27286c4853eb0c0e1803a94787a62c97
2021-02-08virtio: add atomic call for kickingMohsin Kazmi2-20/+6
Type: fix Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com> Change-Id: I41faa2ca249ff75e564a732af896e6b5d76bf665
2021-02-01tap: fix the interrupt handlingMohsin Kazmi1-3/+4
Type: fix Interrupt are suppressed from kernel on tx path. Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com> Change-Id: I9f39f343b7e16bad09910766adf0b09654721f67
2021-01-27vhost: vhost interface hardware address not setSteven Luong3-6/+9
The check args->hwaddr is always true and it always copies the mac address from args->hwaddr even though none was set. Check args->use_custom_mac instead. Type: fix Fixes: gerrit 29970 Signed-off-by: Steven Luong <sluong@cisco.com> Change-Id: I0c51bf1ea79b02c4fbdc3c52e694f186bdd96600
2021-01-21interface: rx queue infra rework, part oneDamjan Marion8-163/+128
Type: improvement Change-Id: I4008cadfd5141f921afbdc09a3ebcd1dcf88eb29 Signed-off-by: Damjan Marion <damarion@cisco.com>
2021-01-08vhost: Add event index for interrupt notification to driverSteven Luong8-192/+506
VPP only supports a poor man's approach for interrupt notification to the driver. It uses a simple binary flag for "interrupt needed" or "interrupt not needed". Most drivers support more sophisticated event index already. This feature is to add the long due missing feature and make it configurable, off by default. Type: feature Signed-off-by: Steven Luong <sluong@cisco.com> Change-Id: I68dab7dd07045cafb49af97b7f70db9b8131ae03
2021-01-05tap: fix the buffering index for groMohsin Kazmi1-6/+8
Type: fix Fixes: 587f9130424fd451e4ba823240d02f655fb197d1 Change-Id: Ia1739fad6a36fa658aece157d7adea8bbaa751d2 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2020-12-28vlib: add missing file template descriptionsPaul Vinciguerra1-0/+4
Add descriptions to clib_file_t template structures so that sockets can be identified via the 'show unix file' cli command. Type: fix Change-Id: Ibf82d55aa6c7b1126bd252b76d0dc8b7076f5046 Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
2020-12-25virtio: Extend vhost multi-queues support beyond 8 queue pairsSteven Luong3-60/+122
Current vhost multi-queues support has a hard limit of 8 queue pairs due to static vring array. This limit was raised in qemu. VPP should support more than 8 queue pairs also. Change static vring allocation to dynamic. When the interface is created, we allocate 8 queue pairs to begin with. We also keep track of how many queue pairs that the interface actually uses. We reply VHOST_USER_GET_QUEUE_NUM with 128 as our maximum number of support queue pair. When qemu starts initializing queue pair greater than 8, we expand the vrings as needed on demand. Type: improvement Signed-off-by: Steven Luong <sluong@cisco.com> Change-Id: I4a02d987d52d1bbe601b00e71f650fe6ebfcc0d7
2020-12-14misc: move to new pool_foreach macrosDamjan Marion5-30/+25
Type: refactor Change-Id: Ie67dc579e88132ddb1ee4a34cb69f96920101772 Signed-off-by: Damjan Marion <damarion@cisco.com>
2020-12-14vppinfra: simpler and faster pool_foreachDamjan Marion1-0/+1
- reduces number of instructions generated 4 times compared to old code - adds pool_foreach2 which is more friendly to clang-format Type: improvement Change-Id: I51e9c7fb09655c60d883987dadf5b2666c12b3f7 Signed-off-by: Damjan Marion <damarion@cisco.com>
2020-12-11virtio: fix vrings overflow in vhost_userBenoît Ganne1-1/+10
Type: fix Change-Id: I7ca955882c0e263a9ace4b14021e51488564e411 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2020-12-04virtio: fix the interrupt handling for packed queuesMohsin Kazmi1-5/+25
Type: fix Change-Id: I2cc1cfd519e5b3502c59cf72e95e454f9122b8e5 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2020-12-04virtio: fix the len offsetMohsin Kazmi1-2/+2
Type: fix Change-Id: I8ce1df5c97941fb645b33476db9cfc74f1395b15 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2020-12-03virtio: fix the offloads in tx pathMohsin Kazmi1-4/+2
Type: fix Change-Id: I1f1f0b6e8c5ef8bc9f2aca4bdc78e89fa951b841 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2020-11-23virtio: fix overflow in case of buffering + dropBenoît Ganne1-1/+0
Type: fix Fixes: 2e6f624f1f82ae0351dd05ad5d930d6876105519 Change-Id: Ib41c82ea1e8430afc920250fb0d054a2fb2d08c9 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2020-11-17virtio: virtio: implement packed queues from virtio 1.1Mohsin Kazmi8-135/+1037
Type: feature Change-Id: I12703371541298efa029903d6762b1cd1f7322ca Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2020-11-12virtio: fix the index issueMohsin Kazmi1-7/+15
Type: fix Fixes: 587f9130424fd451e4ba823240d02f655fb197d1 Change-Id: I230993a54c84e22e324de2a8defeda83c517d733 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2020-11-09vlib: fix trace number accountingBenoît Ganne2-16/+17
When using classifier to filter traces, not all packets will be traced. In that case, we should only count traced packets. Type: fix Change-Id: I87d1e217b580ebff8c6ade7860eb43950420ae78 Signed-off-by: Benoît Ganne <bganne@cisco.com>
2020-11-05tap: allow change of carrier state on hostMatthew Smith2-0/+2
Type: feature Add a function to adjust the link state of the host side of a tap interface. If an application (e.g. route protocol daemons) running on the host uses netlink to monitor interface state, a plugin could use this function to communicate a loss of connectivity to the application by making the interface appear to go down. Requires a somewhat recent kernel. E.g. it does not have any effect on CentOS 7 but it works on CentOS 8. Change-Id: I677ee7889d2eb142e2395bea98f0b4d7e7e7f810 Signed-off-by: Matthew Smith <mgsmith@netgate.com>
2020-11-05virtio: misc optimizationsDamjan Marion1-35/+41
Type: improvement Change-Id: Iaf98a60e37dd28828feca365b8fdc5d2f7ae6935 Signed-off-by: Damjan Marion <damarion@cisco.com>
2020-11-05virtio: move retry logic to outer functionDamjan Marion1-8/+9
Improves compile time.... Type: improvement Change-Id: I310a2e55e5e488a953d65fd065f7795a43d2e9a7 Signed-off-by: Damjan Marion <damarion@cisco.com>
2020-10-28misc: Break the big IP header files to improve compile timeNeale Ranns4-7/+1
Type: refactor Signed-off-by: Neale Ranns <neale.ranns@cisco.com> Change-Id: Id1801519638a9b97175847d7ed58824fb83433d6
2020-10-28virtio: fix the buffer array indexMohsin Kazmi1-1/+1
Type: fix Fixes: 2e6f624f1f82ae0351dd05ad5d930d6876105519 Change-Id: I24a9822d1968a134c7e41221f48296cc8a67dd91 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2020-10-26virtio: improve the compile timeMohsin Kazmi1-36/+32
Type: improvement packet buffering is common code to tun/tap/virtio. Change-Id: I59a339f268a28a0c32756e52d10d1ed6b207db42 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2020-10-26virtio: reduce the compile time for device.cMohsin Kazmi1-15/+19
Type: improvement GRO is common to tap/tun/virtio devices. Hence move to common place. Change-Id: Ibb099f3a80f493ddb934df6bb7640f7c9c370fd5 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2020-10-22virtio: checksum error reported for ip6 traffic with GSO enableSteven Luong2-11/+1
When GSO is enabled, vhost clears the checksum field prior to transmitting the packet. Some newer kernel version does not like that and complains about checksum error. This was seen with ip6 traffic. Type: fix Signed-off-by: Steven Luong <sluong@cisco.com> Change-Id: I7c6f2a6148f4a30107bfa8b078f5990e64300cf1
2020-10-21virtio: run process to send interrupts to input nodesMohsin Kazmi3-17/+111
Type: improvement virtio interfaces support packet coalescing and buffering which depends on timer expiry to flush the stored packets periodically. virtio input node checks timer expiry and schedules tx queue accordingly. In poll mode, timer expiry is handled naturally, as input node runs periodically. In interrupt mode, virtio input node depends on the interrupts send from backend. Stored packets could starve, if there would not be interrupts to input node. This patch implements a process node which periodically sends interrupt to virtio input node given coalescing or buffering feature is enabled on an interface. Change-Id: Ic38f749f74b001073d4d0579dca149d0a4cea039 Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
2020-10-21virtio: improve input node performanceDamjan Marion1-13/+26
- Avoid feature arc lookup per packet, as all packets belong to the same interface - don't validate enqueue for l2 packets, as they all have same destionation Type: improvement Change-Id: I32ddd801f219eab9281736abafdc91a4ff9e0989 Signed-off-by: Damjan Marion <damarion@cisco.com>
2020-10-21virtio: move lock and kick to outer functionDamjan Marion1-31/+28
Type: improvement Change-Id: I4fdcb40142e8cc9f5f1d0035116659543d5d92fe Signed-off-by: Damjan Marion <damarion@cisco.com>