------------------------------------------------------------------------ r367792 | markj | 2020-11-18 06:27:47 -0800 (Wed, 18 Nov 2020) | 3 lines MFC r367596: iflib: Free full mbuf chains when draining transmit queues ------------------------------------------------------------------------ r367825 | mav | 2020-11-18 18:44:08 -0800 (Wed, 18 Nov 2020) | 2 lines MFC r367625: Fix panic if NVMe is detached before the intrhook call. ------------------------------------------------------------------------ r367836 | kib | 2020-11-19 01:09:19 -0800 (Thu, 19 Nov 2020) | 3 lines MFC r367398: Suspend all writeable local filesystems on power suspend. ------------------------------------------------------------------------ r367837 | kib | 2020-11-19 01:13:23 -0800 (Thu, 19 Nov 2020) | 3 lines MFC r367609: mlx5en: Refactor repeated code to register media type to mlx5e_ifm_add(). ------------------------------------------------------------------------ r367838 | kib | 2020-11-19 01:15:04 -0800 (Thu, 19 Nov 2020) | 3 lines MFC r367610: mlx5en: Register all combinations of FDX/RXPAUSE/TXPAUSE as valid media types. ------------------------------------------------------------------------ r367839 | kib | 2020-11-19 01:16:22 -0800 (Thu, 19 Nov 2020) | 3 lines MFC r367611: mlx5en: stop ignoring pauses and flow in the media reqs. ------------------------------------------------------------------------ r367840 | kib | 2020-11-19 01:17:41 -0800 (Thu, 19 Nov 2020) | 3 lines MFC r367612: mlx5en: Set ifmr_current same as ifmr_active. ------------------------------------------------------------------------ r367855 | mav | 2020-11-19 16:30:07 -0800 (Thu, 19 Nov 2020) | 10 lines MFC r366506, r366511: nvmecontrol: Update wdc module for newer WDC NVMe products Update the to log fetch operation for latest WDC NVMe products. Tested on HGST SN100 (a few years old) and WDC SN720 (more recent). Submitted by: Akhilesh Rn (minor style tweak by me) Github PR: 435 ------------------------------------------------------------------------ r367856 | mav | 2020-11-19 16:30:58 -0800 (Thu, 19 Nov 2020) | 2 lines MFC r367630: Improve nvmecontrol error reporting. ------------------------------------------------------------------------ r367859 | grehan | 2020-11-19 19:33:30 -0800 (Thu, 19 Nov 2020) | 8 lines MFC r367709 Fix regression in AHCI controller settings. PR: 250924 Submitted by: Rolf Stalder Reported by: Rolf Stalder Relnotes: Yes ------------------------------------------------------------------------ r367868 | 0mp | 2020-11-20 02:09:48 -0800 (Fri, 20 Nov 2020) | 7 lines MFC r367419: Fix a typo and remove Xr's to vn(4) and vnconfig(4) "mandoc -Tlint" complained about the Xr to vnconfig, which was removed in r238202. I am not sure but maybe it's time to do the same to vn(4). ------------------------------------------------------------------------ r367871 | 0mp | 2020-11-20 02:27:54 -0800 (Fri, 20 Nov 2020) | 4 lines MFC r367640: Explicitly note in the EXAMPLES section that uname(3) contains more details ------------------------------------------------------------------------ r367914 | mav | 2020-11-20 16:40:59 -0800 (Fri, 20 Nov 2020) | 5 lines MFC r366953: Negotiate iSCSIProtocolLevel of 2 (RFC 7144) in initiator. It does not change anything immediately, but allows further support of Command Priority, Status Qualifier and new task management functions. ------------------------------------------------------------------------ r367939 | markj | 2020-11-22 10:54:14 -0800 (Sun, 22 Nov 2020) | 3 lines MFC r366969, r366973: ntb: Add Intel Xeon Gen3 support ------------------------------------------------------------------------ r367957 | jhibbits | 2020-11-23 08:26:49 -0800 (Mon, 23 Nov 2020) | 6 lines MFC r367807 Fix octeon_pmc post-r334827 Sponsored by: Juniper Networks, Inc ------------------------------------------------------------------------ r367964 | np | 2020-11-23 15:46:07 -0800 (Mon, 23 Nov 2020) | 25 lines MFC r365732 and r366589. r365732: cxgbe(4): Get the count of FCS errors from the MAC and not MPS for T6 ports. The MPS register on the T6 counts something other than FCS errors despite its name. r366589: cxgbe(4): More fixes for the T6 FCS error counter. r365732 was the first attempt to get an accurate count but it was writing to some read-only registers to clear them and that obviously didn't work. Instead, note the counter's value when it is supposed to be cleared and subtract it from future readings. dev..stats.rx_fcs_error should not be serviced from the MPS register for T6. The stats.* sysctls should all use T5_PORT_REG for T5 and above. This must have been missed in the initial T5 support years ago. Fix it while here. Sponsored by: Chelsio Communications ------------------------------------------------------------------------ r367965 | np | 2020-11-23 15:53:21 -0800 (Mon, 23 Nov 2020) | 39 lines MFC r366532 and r366862. r366532: cxgbe(4): knobs to drop various kinds of undesirable frames on ingress. These kind of drops come for free in the sense that they do not use the filter TCAM or any other resource that wouldn't normally be used during rx. Frames dropped by the hardware get counted in the MAC's rx stats but are not delivered to the driver. hw.cxgbe.attack_filter Set to 1 to enable the "attack filter". Default is 0. The attack filter will drop an incoming frame if any of these conditions is true: src ip/ip6 == dst ip/ip6; tcp and src/dst ip is not unicast; src/dst ip is loopback (127.x.y.z); src ip6 is not unicast; src/dst ip6 is loopback (::1/128) or unspecified (::/128); tcp and src/dst ip6 is mcast (ff00::/8). hw.cxgbe.drop_ip_fragments Set to 1 to drop all incoming IP fragments. Default is 0. Note that this drops valid frames. hw.cxgbe.drop_pkts_with_l2_errors Set to 1 to drop incoming frames with Layer 2 length or checksum errors. Default is 1. hw.cxgbe.drop_pkts_with_l3_errors Set to 1 to drop incoming frames with IP version, length, or checksum errors. Default is 0. hw.cxgbe.drop_pkts_with_l4_errors Set to 1 to drop incoming frames with Layer 4 length, checksum, or other errors. Default is 0. r366862: cxgbe(4): Updates to the drop features from r366532. Sponsored by: Chelsio Communications ------------------------------------------------------------------------ r367966 | np | 2020-11-23 15:58:14 -0800 (Mon, 23 Nov 2020) | 8 lines MFC r366694: cxgbe(4): unimplemented cudbg routines should return the correct internal error code and not an errno. Submitted by: Krishnamraju Eraparaju @ Chelsio Sponsored by: Chelsio Communications ------------------------------------------------------------------------ r367967 | np | 2020-11-23 16:02:14 -0800 (Mon, 23 Nov 2020) | 6 lines MFC r366696: cxgbe(4): Do not request FEC when requesting speeds that don't have FEC. Sponsored by: Chelsio Communications ------------------------------------------------------------------------ r367968 | np | 2020-11-23 16:07:22 -0800 (Mon, 23 Nov 2020) | 8 lines MFC r366853: cxgbe(4): Fix page fault in t4_get_lb_stats with 2 port T5 cards. PR: 250449 Reported by: freqlabs@ Sponsored by: Chelsio Communications ------------------------------------------------------------------------ r367969 | np | 2020-11-23 16:12:42 -0800 (Mon, 23 Nov 2020) | 7 lines MFC r366916: cxgbe(4): display correct tid range for T6 based -SO cards. Reported by: Chelsio QA Sponsored by: Chelsio Communications ------------------------------------------------------------------------ r367970 | np | 2020-11-23 16:17:05 -0800 (Mon, 23 Nov 2020) | 19 lines MFC r366929 and r367608. r366929: cxgbe(4): fix the size of the iq/eq maps. The firmware can allocate ingress and egress context ids anywhere from its configured range. Size the iq/eq maps to match the entire range instead of assuming that the firmware always allocates the first available context id. Reported by: Baptiste Wicht @ Verisign r367608: cxgbev(4): Make sure that the iq/eq map sizes are correct for VFs. This should have been part of r366929. Sponsored by: Chelsio Communications ------------------------------------------------------------------------ r367971 | np | 2020-11-23 16:22:33 -0800 (Mon, 23 Nov 2020) | 14 lines MFC r367428 and r367495. r367428: cxgbe(4): Update firmwares to 1.25.0.40. This fixes a potential crash in firmware 1.25.0.0 on the passive open side during TOE operation. r367495: cxgbe(4): Add the firmware binaries missing in r367428. Obtained from: Chelsio Communications Sponsored by: Chelsio Communications ------------------------------------------------------------------------ r367972 | np | 2020-11-23 16:25:03 -0800 (Mon, 23 Nov 2020) | 9 lines MFC r367497: cxgbev(4): Use the MAC address set by the the PF if there is one. Query the firmware for the MAC address set by the PF for the VF and use it instead of the firmware generated MAC if it's available. Sponsored by: Chelsio Communications ------------------------------------------------------------------------ r367973 | np | 2020-11-23 16:27:21 -0800 (Mon, 23 Nov 2020) | 9 lines MFC r367502: cxgbe(4): Allow the PF driver to set a VF's MAC address. The MAC address can be set with the optional mac-addr property in the VF section of the iovctl.conf(5) used to instantiate the VFs. Sponsored by: Chelsio Communications ------------------------------------------------------------------------ r367974 | mav | 2020-11-23 16:30:47 -0800 (Mon, 23 Nov 2020) | 6 lines MFC r366922, r367915, r367916: Pass lower 3 bits of sector_count for FPDMA commands. When this code was written those bits were N/A, but now the lowest bit is Rebuild Assist Recovery Control (RARC). ------------------------------------------------------------------------ r367982 | mav | 2020-11-24 05:17:12 -0800 (Tue, 24 Nov 2020) | 24 lines MFC r367044: Introduce support of SCSI Command Priority. SAM-3 specification introduced concept of Task Priority, that was renamed to Command Priority in SAM-4, and supported by all modern SCSI transports. It provides 15 levels of relative priorities: 1 - highest, 15 - lowest and 0 - default. SAT specification for SATA devices translates priorities 1-3 into NCQ high priority. This change adds new "priority" field into empty spots of struct ccb_scsiio and struct ccb_accept_tio of CAM and struct ctl_scsiio of CTL. Respective support is added into iscsi(4), isp(4), mpr(4), mps(4) and ocs_fc(4) drivers for both initiator and where applicable target roles. Minimal support was added to CTL to receive the priority value from different frontends, pass it between HA controllers and report in few places. This patch does not add consumers of this functionality, so nothing should really change yet, since the field is still set to 0 (default) on initiator and not actively used on target. Those are to be implemented separately. I've confirmed priority working on WD Red SATA disks connected via mpr(4) and properly transferred to CTL target via iscsi(4), isp(4) and ocs_fc(4). While there, added missing tag_action support to ocs_fc(4) initiator role. ------------------------------------------------------------------------ r367983 | kib | 2020-11-24 05:19:31 -0800 (Tue, 24 Nov 2020) | 3 lines MFCr367741: vmem: trivial warning and style fixes. ------------------------------------------------------------------------ r367996 | vmaffione | 2020-11-24 11:55:01 -0800 (Tue, 24 Nov 2020) | 7 lines MFC r367920, r367921 netmap: bridge: update man page with more information Update the man page to describe how it is necessary to enable promiscuous mode and/or disable offloads. ------------------------------------------------------------------------ r368012 | mw | 2020-11-24 19:24:43 -0800 (Tue, 24 Nov 2020) | 13 lines MFC: Merge ENA v2.3.0 driver r367805 Update ENA driver version to v2.3.0 r367803 Rename descriptions of the supported ENA devices r367802 Add ENI metrics for the ENA driver r367801 Add SPDX license tag to the ENA driver files r367800 Add Rx offsets support for the ENA driver r367799 Adjust ENA driver files to latest ena-com changes r367795 Fix completion descriptors alignment for the ENA Obtained from: Semihalf Sponsored by: Amazon, Inc ------------------------------------------------------------------------ r368027 | emaste | 2020-11-25 10:36:38 -0800 (Wed, 25 Nov 2020) | 6 lines MFC r351700: libc: Use musl's optimized memchr Parentheses added to HASZERO macro to avoid a GCC warning. Sponsored by: The FreeBSD Foundation ------------------------------------------------------------------------ r368032 | vmaffione | 2020-11-25 13:20:55 -0800 (Wed, 25 Nov 2020) | 7 lines MFC r367931 netmap: bridge: switch to libnetmap Use the newer libnetmap (included in base) rather than the older nm_open()/nm_close() defined in netmap_user.h ------------------------------------------------------------------------ r368033 | vmaffione | 2020-11-25 13:22:16 -0800 (Wed, 25 Nov 2020) | 7 lines MFC r367932 netmap: pkt-gen: switch to libnetmap Use the newer libnetmap (included in base) rather than the older nm_open()/nm_close() defined in netmap_user.h ------------------------------------------------------------------------ r368034 | vmaffione | 2020-11-25 13:23:13 -0800 (Wed, 25 Nov 2020) | 7 lines MFC r367933 netmap: lb: switch to libnetmap Use the newer libnetmap (included in base) rather than the older nm_open()/nm_close() defined in netmap_user.h ------------------------------------------------------------------------ r368035 | vmaffione | 2020-11-25 13:23:58 -0800 (Wed, 25 Nov 2020) | 7 lines MFC r367934 netmap: nmreplay: switch to libnetmap Use the newer libnetmap (included in base) rather than the older nm_open()/nm_close() defined in netmap_user.h ------------------------------------------------------------------------ r368036 | vmaffione | 2020-11-25 13:24:39 -0800 (Wed, 25 Nov 2020) | 7 lines MFC r367935 netmap: valectl: switch to libnetmap Use the newer libnetmap (included in base) rather than the older nm_open()/nm_close() defined in netmap_user.h ------------------------------------------------------------------------ r368037 | vmaffione | 2020-11-25 13:25:17 -0800 (Wed, 25 Nov 2020) | 7 lines MFC r367936 netmap: bridge: improve readability Multiple cosmetic changes, plus a fix to a verbose print (indicating wrong net->host/host->net direction). ------------------------------------------------------------------------