FreeBSD source tree https://cgit-dev.freebsd.org/src/atom?h=release%2F12.3.0 2021-01-17T13:38:09Z 2021-01-17T13:38:09Z Vincenzo Maffione vmaffione@FreeBSD.org 2021-01-09T22:34:10Z urn:sha1:fa1a4ff944f4b3e841df0cdd67c6373a589ffdd5 Similarly to what done for iflib in 1d238b07d5d4d9660ae0e, this patch prevents access to the krings during the interface reset triggered by netmap_register(). MFC after: 1 week (cherry picked from commit 9ac59d42c0b4b6cd9c36a5dace7f49753c2e175a) netmap: vtnet: enable/disable krings on any interface reinit See 3d65fd97e85ab807f3b for a detailed explanation. PR: 252453 MFC after: 1 week (cherry picked from commit bb714db6d39583a9fbf5d11849c5e2365e7c0d80) netmap: vtnet: fix RX initialization after netmap_reset() At device reset, we must not publish those netmap receive buffers that are owned by userspace (nm_kr_rxspace). MFC after: 1 week (cherry picked from commit 3005e10ddbfbec3ecf46a080607bb0d85986eee5) 2020-06-23T20:41:10Z Vincenzo Maffione vmaffione@FreeBSD.org 2020-06-23T20:41:10Z urn:sha1:e2573c8c1836ac4c91d5fd042c69e0d4932a2ea4 netmap: vtnet: fix races in vtnet_netmap_reg() The nm_register callback needs to call nm_set_native_flags() or nm_clear_native_flags() once the device has been stopped. However, in the current implementation this is not true, as the device is stopped by vtnet_init_locked(). This causes race conditions where the driver crashes as soon as it dequeues netmap buffers assuming they are mbufs (or the other way around). To fix the issue, we extend vtnet_init_locked() with a second argument that, if not zero, will set/clear the netmap flags. This results in a huge simplification of the nm_register callback itself. Also, use netmap_reset() to check if a ring is going to be re-initialized in netmap mode. 2020-06-18T10:03:17Z Vincenzo Maffione vmaffione@FreeBSD.org 2020-06-18T10:03:17Z urn:sha1:eb49c2778b3b0cfc38eb5659ec94a48bd5d251c9 netmap: introduce netmap_kring_on() This function returns NULL if the ring identified by queue id and direction is in netmap mode. Otherwise return the corresponding kring. Use this function to replace vtnet_netmap_queue_on(). 2020-06-10T20:05:53Z Vincenzo Maffione vmaffione@FreeBSD.org 2020-06-10T20:05:53Z urn:sha1:e00de8771ba728c75529e3354b317bc0bb42b632 netmap: vtnet: clean up rxsync disabled logs 2020-06-10T20:05:07Z Vincenzo Maffione vmaffione@FreeBSD.org 2020-06-10T20:05:07Z urn:sha1:beb423280d436e421f6230c6b9062ac63d0179cd netmap: vtnet: fix race condition in rxsync This change prevents a race that happens when rxsync dequeues N-1 rx packets (with N being the size of the netmap rx ring). In this situation, the loop exits without re-enabling the rx interrupts, thus causing the VQ to stall. 2020-06-10T20:04:20Z Vincenzo Maffione vmaffione@FreeBSD.org 2020-06-10T20:04:20Z urn:sha1:0dd06b856e0076af19d1a828f6751342b75c8e49 netmap: vtnet: add vtnrx_nm_refill index to receive queues The new index tracks the next netmap slot that is going to be enqueued into the virtqueue. The index is necessary to prevent the receive VQ and the netmap rx ring from going out of sync, considering that we never enqueue N slots, but at most N-1. This change fixes a bug that causes the VQ and the netmap ring to go out of sync after N-1 packets have been received. 2020-06-10T20:03:11Z Vincenzo Maffione vmaffione@FreeBSD.org 2020-06-10T20:03:11Z urn:sha1:d5255b344c2fdd20c33c5637be76fe11e2b260db netmap: vale: fix disabled logs 2020-06-10T19:58:03Z Vincenzo Maffione vmaffione@FreeBSD.org 2020-06-10T19:58:03Z urn:sha1:5422d37b8a664d341462ca9e350162432fea674f netmap: if_vtnet: avoid netmap ring wraparound netmap assumes the one "slot" is left unused to distinguish the empty ring and full ring conditions. This assumption was violated by vtnet_netmap_rxq_populate(). 2020-06-10T19:57:10Z Vincenzo Maffione vmaffione@FreeBSD.org 2020-06-10T19:57:10Z urn:sha1:e71f4bb392395bee4bb5c4445d190f685d46d585 netmap: if_vtnet: replace vtnet_free_used() The functionality contained in this function is duplicated, as it is already available in vtnet_txq_free_mbufs() and vtnet_rxq_free_mbufs(). 2020-06-10T19:55:36Z Vincenzo Maffione vmaffione@FreeBSD.org 2020-06-10T19:55:36Z urn:sha1:98927bed50c1a504ff68818c080d0cfe3fcbe758 netmap: vtnet: fix RX virtqueue initialization bug The vtnet_netmap_rxq_populate() function erroneously assumed that kring->nr_hwcur = 0, i.e. the kring was in the initial state. However, this is not always the case: for example, when a vtnet reinit is triggered by some changes in the interface flags or capenable. This patch changes the behaviour of vtnet_netmap_kring_refill() so that it always starts publishing the netmap buffers starting from the current value of kring->nr_hwcur.