FreeBSD source tree https://cgit-dev.freebsd.org/src/atom?h=releng%2F12.2 2020-10-05T16:39:38Z 2020-10-05T16:39:38Z Navdeep Parhar np@FreeBSD.org 2020-10-05T16:39:38Z urn:sha1:f4d391bd542adf0d4c21248d88c2b1e439955e40 cxgbe(4): set up the firmware flowc for the tid before send_abort_rpl. Approved by: re@ (gjb@) Sponsored by: Chelsio Communications 2020-09-21T18:19:48Z Navdeep Parhar np@FreeBSD.org 2020-09-21T18:19:48Z urn:sha1:fe6dbcf75730bec1bb0fb84f49811d4392e7742e r365861: cxgbe(4): Update T4/5/6 firmwares to 1.25.0.0. r365872: cxgbe(4): add the firmware binaries instead of the empty files that were added in r365861. Approved by: re@ (gjb@) 2020-08-26T23:41:46Z Navdeep Parhar np@FreeBSD.org 2020-08-26T23:41:46Z urn:sha1:02dea8a3cb79eda2d3acb4b8602d4c35df07c30e cxgbe(4): Do not display error messages related to the CLIP table if it's not in use by TOE or KTLS. 2020-08-26T23:21:26Z Navdeep Parhar np@FreeBSD.org 2020-08-26T23:21:26Z urn:sha1:3c7e9adfcd3a66f5eae778dc92a6bf098b22cbcc r340023: Check cannot_use_txpkts() rather than needs_tso() in add_to_txpkts(). Currently this is a no-op, but will matter in the future when cannot_use_txpkts() starts checking other conditions than just needs_tso(). r362905: cxgbe(4): changes in the Tx path to help increase tx coalescing. - Ask the firmware for the number of frames that can be stuffed in one work request. - Modify mp_ring to increase the likelihood of tx coalescing when there are just one or two threads that are doing most of the tx. Add teeth to the abdication mechanism by pushing the consumer lock into mp_ring. This reduces the likelihood that a consumer will get stuck with all the work even though it is above its budget. - Add support for coalesced tx WR to the VF driver. This, with the changes above, results in a 7x improvement in the tx pps of the VF driver for some common cases. The firmware vets the L2 headers submitted by the VF driver and it's a big win if the checks are performed for a batch of packets and not each one individually. r362938: cxgbe(4): Fix a bug (introduced in r362905) where some tx traffic wasn't being reported to BPF. r363167: cxgbev(4): Compare at most 16 bytes of the Ethernet header when trying to coalesce tx work requests. Note that Coverity will still treat this as an out-of-bounds access. We do want to compare 16B starting from ethmacdst but cmp_l2hdr was was going beyond that by 2B. cmp_l2hdr was introduced in r362905. Sponsored by: Chelsio Communications 2020-08-26T22:11:22Z John Baldwin jhb@FreeBSD.org 2020-08-26T22:11:22Z urn:sha1:7a490b844c8ca9b1a3058b5f27e17b7b8beff246 2020-08-25T18:21:13Z Navdeep Parhar np@FreeBSD.org 2020-08-25T18:21:13Z urn:sha1:2e66b5bb2cb4afc03c79bef561a0907be19dc524 cxgbe(4): Some updates to the common code. 2020-08-25T18:11:45Z Navdeep Parhar np@FreeBSD.org 2020-08-25T18:11:45Z urn:sha1:540f11f99485c58f5c28b7b13bbf1651329dae79 cxgbei: destroy the worker threads' CV and mutex in stop_worker_threads. 2020-08-25T02:54:48Z Navdeep Parhar np@FreeBSD.org 2020-08-25T02:54:48Z urn:sha1:f96e05aecd96f8f9f6f042a77eeda7d4e869356d cxgbe(4): Add a pointer to the adapter softc in vi_info. There were quite a few places where port_info was being accessed only to get to the adapter. Sponsored by: Chelsio Communications 2020-08-25T02:42:07Z Navdeep Parhar np@FreeBSD.org 2020-08-25T02:42:07Z urn:sha1:26f2034179da6108dac2f31f6b5e9bfb312db7e5 cxgbe(4): Add a tx_len16_to_desc helper. No functional change. Sponsored by: Chelsio Communications 2020-08-25T02:14:36Z Navdeep Parhar np@FreeBSD.org 2020-08-25T02:14:36Z urn:sha1:a884debd536e94692627a94d1f9e8aaa5aa94ca8 All these are rx improvements in the cxgbe(4) driver. r351444: cxgbe(4): Use the same buffer size for TOE rx queues as the NIC rx queues. This is a minor simplification. r357475: cxgbe(4): Initialize the rx buffer's metadata on first-use and not on allocation. refill_fl doesn't touch any part of a freshly allocated cluster after this change. r357479: cxgbe(4): Avoid ext_arg2 in rxb_free. ext_arg2 is the only item in the third cacheline in an mbuf and could be cold by the time rxb_free runs. Put the information needed by rxb_free in the same line as the refcount, which is very likely to be hot given that rxb_free runs when the refcount is decremented and reaches 0. r357481: cxgbe(4): Retire the allow_mbufs_in_cluster optimization. This simplifies the driver's rx fast path as well as the bookkeeping code that tracks various rx buffer sizes and layouts. r357482: cxgbe(4): Treat NIC rx as special and run its handler directly and not via the t4_cpl_handler dispatch table. r358859: cxgbe(4): Do not try to use 0 as an rx buffer address when the driver is already allocating from the safe zone and the allocation fails. This bug was introduced in r357481. r364497: cxgbe(4): Use large clusters for TOE rx queues when TOE+TLS is enabled. Rx is more efficient within the chip when the receive buffer size matches the TLS PDU size. Sponsored by: Chelsio Communications