From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- .../testing/selftests/powerpc/eeh/eeh-functions.sh | 245 +++++++++++++++++++++ 1 file changed, 245 insertions(+) create mode 100644 tools/testing/selftests/powerpc/eeh/eeh-functions.sh (limited to 'tools/testing/selftests/powerpc/eeh/eeh-functions.sh') diff --git a/tools/testing/selftests/powerpc/eeh/eeh-functions.sh b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh new file mode 100644 index 000000000..70daa3925 --- /dev/null +++ b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh @@ -0,0 +1,245 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-only + +export KSELFTESTS_SKIP=4 + +log() { + echo >/dev/stderr $* +} + +pe_ok() { + local dev="$1" + local path="/sys/bus/pci/devices/$dev/eeh_pe_state" + + # if a driver doesn't support the error handling callbacks then the + # device is recovered by removing and re-probing it. This causes the + # sysfs directory to disappear so read the PE state once and squash + # any potential error messages + local eeh_state="$(cat $path 2>/dev/null)" + if [ -z "$eeh_state" ]; then + return 1; + fi + + local fw_state="$(echo $eeh_state | cut -d' ' -f1)" + local sw_state="$(echo $eeh_state | cut -d' ' -f2)" + + # If EEH_PE_ISOLATED or EEH_PE_RECOVERING are set then the PE is in an + # error state or being recovered. Either way, not ok. + if [ "$((sw_state & 0x3))" -ne 0 ] ; then + return 1 + fi + + # A functioning PE should have the EEH_STATE_MMIO_ACTIVE and + # EEH_STATE_DMA_ACTIVE flags set. For some goddamn stupid reason + # the platform backends set these when the PE is in reset. The + # RECOVERING check above should stop any false positives though. + if [ "$((fw_state & 0x18))" -ne "$((0x18))" ] ; then + return 1 + fi + + return 0; +} + +eeh_supported() { + test -e /proc/powerpc/eeh && \ + grep -q 'EEH Subsystem is enabled' /proc/powerpc/eeh +} + +eeh_test_prep() { + if ! eeh_supported ; then + echo "EEH not supported on this system, skipping" + exit $KSELFTESTS_SKIP; + fi + + if [ ! -e "/sys/kernel/debug/powerpc/eeh_dev_check" ] && \ + [ ! -e "/sys/kernel/debug/powerpc/eeh_dev_break" ] ; then + log "debugfs EEH testing files are missing. Is debugfs mounted?" + exit $KSELFTESTS_SKIP; + fi + + # Bump the max freeze count to something absurd so we don't + # trip over it while breaking things. + echo 5000 > /sys/kernel/debug/powerpc/eeh_max_freezes +} + +eeh_can_break() { + # skip bridges since we can't recover them (yet...) + if [ -e "/sys/bus/pci/devices/$dev/pci_bus" ] ; then + log "$dev, Skipped: bridge" + return 1; + fi + + # The ahci driver doesn't support error recovery. If the ahci device + # happens to be hosting the root filesystem, and then we go and break + # it the system will generally go down. We should probably fix that + # at some point + if [ "ahci" = "$(basename $(realpath /sys/bus/pci/devices/$dev/driver))" ] ; then + log "$dev, Skipped: ahci doesn't support recovery" + return 1; + fi + + # Don't inject errosr into an already-frozen PE. This happens with + # PEs that contain multiple PCI devices (e.g. multi-function cards) + # and injecting new errors during the recovery process will probably + # result in the recovery failing and the device being marked as + # failed. + if ! pe_ok $dev ; then + log "$dev, Skipped: Bad initial PE state" + return 1; + fi + + return 0 +} + +eeh_one_dev() { + local dev="$1" + + # Using this function from the command line is sometimes useful for + # testing so check that the argument is a well-formed sysfs device + # name. + if ! test -e /sys/bus/pci/devices/$dev/ ; then + log "Error: '$dev' must be a sysfs device name (DDDD:BB:DD.F)" + return 1; + fi + + # Break it + echo $dev >/sys/kernel/debug/powerpc/eeh_dev_break + + # Force an EEH device check. If the kernel has already + # noticed the EEH (due to a driver poll or whatever), this + # is a no-op. + echo $dev >/sys/kernel/debug/powerpc/eeh_dev_check + + # Default to a 60s timeout when waiting for a device to recover. This + # is an arbitrary default which can be overridden by setting the + # EEH_MAX_WAIT environmental variable when required. + + # The current record holder for longest recovery time is: + # "Adaptec Series 8 12G SAS/PCIe 3" at 39 seconds + max_wait=${EEH_MAX_WAIT:=60} + + for i in `seq 0 ${max_wait}` ; do + if pe_ok $dev ; then + break; + fi + log "$dev, waited $i/${max_wait}" + sleep 1 + done + + if ! pe_ok $dev ; then + log "$dev, Failed to recover!" + return 1; + fi + + log "$dev, Recovered after $i seconds" + return 0; +} + +eeh_has_driver() { + test -e /sys/bus/pci/devices/$1/driver; + return $? +} + +eeh_can_recover() { + # we'll get an IO error if the device's current driver doesn't support + # error recovery + echo $1 > '/sys/kernel/debug/powerpc/eeh_dev_can_recover' 2>/dev/null + + return $? +} + +eeh_find_all_pfs() { + devices="" + + # SR-IOV on pseries requires hypervisor support, so check for that + is_pseries="" + if grep -q pSeries /proc/cpuinfo ; then + if [ ! -f /proc/device-tree/rtas/ibm,open-sriov-allow-unfreeze ] || + [ ! -f /proc/device-tree/rtas/ibm,open-sriov-map-pe-number ] ; then + return 1; + fi + + is_pseries="true" + fi + + for dev in `ls -1 /sys/bus/pci/devices/` ; do + sysfs="/sys/bus/pci/devices/$dev" + if [ ! -e "$sysfs/sriov_numvfs" ] ; then + continue + fi + + # skip unsupported PFs on pseries + if [ -z "$is_pseries" ] && + [ ! -f "$sysfs/of_node/ibm,is-open-sriov-pf" ] && + [ ! -f "$sysfs/of_node/ibm,open-sriov-vf-bar-info" ] ; then + continue; + fi + + # no driver, no vfs + if ! eeh_has_driver $dev ; then + continue + fi + + devices="$devices $dev" + done + + if [ -z "$devices" ] ; then + return 1; + fi + + echo $devices + return 0; +} + +# attempts to enable one VF on each PF so we can do VF specific tests. +# stdout: list of enabled VFs, one per line +# return code: 0 if vfs are found, 1 otherwise +eeh_enable_vfs() { + pf_list="$(eeh_find_all_pfs)" + + vfs=0 + for dev in $pf_list ; do + pf_sysfs="/sys/bus/pci/devices/$dev" + + # make sure we have a single VF + echo 0 > "$pf_sysfs/sriov_numvfs" + echo 1 > "$pf_sysfs/sriov_numvfs" + if [ "$?" != 0 ] ; then + log "Unable to enable VFs on $pf, skipping" + continue; + fi + + vf="$(basename $(realpath "$pf_sysfs/virtfn0"))" + if [ $? != 0 ] ; then + log "unable to find enabled vf on $pf" + echo 0 > "$pf_sysfs/sriov_numvfs" + continue; + fi + + if ! eeh_can_break $vf ; then + log "skipping " + + echo 0 > "$pf_sysfs/sriov_numvfs" + continue; + fi + + vfs="$((vfs + 1))" + echo $vf + done + + test "$vfs" != 0 + return $? +} + +eeh_disable_vfs() { + pf_list="$(eeh_find_all_pfs)" + if [ -z "$pf_list" ] ; then + return 1; + fi + + for dev in $pf_list ; do + echo 0 > "/sys/bus/pci/devices/$dev/sriov_numvfs" + done + + return 0; +} -- cgit v1.2.3