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(). ... --- fs/ocfs2/cluster/quorum.c | 326 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 326 insertions(+) create mode 100644 fs/ocfs2/cluster/quorum.c (limited to 'fs/ocfs2/cluster/quorum.c') diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c new file mode 100644 index 000000000..189c111bc --- /dev/null +++ b/fs/ocfs2/cluster/quorum.c @@ -0,0 +1,326 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * + * Copyright (C) 2005 Oracle. All rights reserved. + */ + +/* This quorum hack is only here until we transition to some more rational + * approach that is driven from userspace. Honest. No foolin'. + * + * Imagine two nodes lose network connectivity to each other but they're still + * up and operating in every other way. Presumably a network timeout indicates + * that a node is broken and should be recovered. They can't both recover each + * other and both carry on without serialising their access to the file system. + * They need to decide who is authoritative. Now extend that problem to + * arbitrary groups of nodes losing connectivity between each other. + * + * So we declare that a node which has given up on connecting to a majority + * of nodes who are still heartbeating will fence itself. + * + * There are huge opportunities for races here. After we give up on a node's + * connection we need to wait long enough to give heartbeat an opportunity + * to declare the node as truly dead. We also need to be careful with the + * race between when we see a node start heartbeating and when we connect + * to it. + * + * So nodes that are in this transtion put a hold on the quorum decision + * with a counter. As they fall out of this transition they drop the count + * and if they're the last, they fire off the decision. + */ +#include +#include +#include + +#include "heartbeat.h" +#include "nodemanager.h" +#define MLOG_MASK_PREFIX ML_QUORUM +#include "masklog.h" +#include "quorum.h" + +static struct o2quo_state { + spinlock_t qs_lock; + struct work_struct qs_work; + int qs_pending; + int qs_heartbeating; + unsigned long qs_hb_bm[BITS_TO_LONGS(O2NM_MAX_NODES)]; + int qs_connected; + unsigned long qs_conn_bm[BITS_TO_LONGS(O2NM_MAX_NODES)]; + int qs_holds; + unsigned long qs_hold_bm[BITS_TO_LONGS(O2NM_MAX_NODES)]; +} o2quo_state; + +/* this is horribly heavy-handed. It should instead flip the file + * system RO and call some userspace script. */ +static void o2quo_fence_self(void) +{ + /* panic spins with interrupts enabled. with preempt + * threads can still schedule, etc, etc */ + o2hb_stop_all_regions(); + + switch (o2nm_single_cluster->cl_fence_method) { + case O2NM_FENCE_PANIC: + panic("*** ocfs2 is very sorry to be fencing this system by " + "panicing ***\n"); + break; + default: + WARN_ON(o2nm_single_cluster->cl_fence_method >= + O2NM_FENCE_METHODS); + fallthrough; + case O2NM_FENCE_RESET: + printk(KERN_ERR "*** ocfs2 is very sorry to be fencing this " + "system by restarting ***\n"); + emergency_restart(); + break; + } +} + +/* Indicate that a timeout occurred on a heartbeat region write. The + * other nodes in the cluster may consider us dead at that time so we + * want to "fence" ourselves so that we don't scribble on the disk + * after they think they've recovered us. This can't solve all + * problems related to writeout after recovery but this hack can at + * least close some of those gaps. When we have real fencing, this can + * go away as our node would be fenced externally before other nodes + * begin recovery. */ +void o2quo_disk_timeout(void) +{ + o2quo_fence_self(); +} + +static void o2quo_make_decision(struct work_struct *work) +{ + int quorum; + int lowest_hb, lowest_reachable = 0, fence = 0; + struct o2quo_state *qs = &o2quo_state; + + spin_lock(&qs->qs_lock); + + lowest_hb = find_first_bit(qs->qs_hb_bm, O2NM_MAX_NODES); + if (lowest_hb != O2NM_MAX_NODES) + lowest_reachable = test_bit(lowest_hb, qs->qs_conn_bm); + + mlog(0, "heartbeating: %d, connected: %d, " + "lowest: %d (%sreachable)\n", qs->qs_heartbeating, + qs->qs_connected, lowest_hb, lowest_reachable ? "" : "un"); + + if (!test_bit(o2nm_this_node(), qs->qs_hb_bm) || + qs->qs_heartbeating == 1) + goto out; + + if (qs->qs_heartbeating & 1) { + /* the odd numbered cluster case is straight forward -- + * if we can't talk to the majority we're hosed */ + quorum = (qs->qs_heartbeating + 1)/2; + if (qs->qs_connected < quorum) { + mlog(ML_ERROR, "fencing this node because it is " + "only connected to %u nodes and %u is needed " + "to make a quorum out of %u heartbeating nodes\n", + qs->qs_connected, quorum, + qs->qs_heartbeating); + fence = 1; + } + } else { + /* the even numbered cluster adds the possibility of each half + * of the cluster being able to talk amongst themselves.. in + * that case we're hosed if we can't talk to the group that has + * the lowest numbered node */ + quorum = qs->qs_heartbeating / 2; + if (qs->qs_connected < quorum) { + mlog(ML_ERROR, "fencing this node because it is " + "only connected to %u nodes and %u is needed " + "to make a quorum out of %u heartbeating nodes\n", + qs->qs_connected, quorum, + qs->qs_heartbeating); + fence = 1; + } + else if ((qs->qs_connected == quorum) && + !lowest_reachable) { + mlog(ML_ERROR, "fencing this node because it is " + "connected to a half-quorum of %u out of %u " + "nodes which doesn't include the lowest active " + "node %u\n", quorum, qs->qs_heartbeating, + lowest_hb); + fence = 1; + } + } + +out: + if (fence) { + spin_unlock(&qs->qs_lock); + o2quo_fence_self(); + } else { + mlog(ML_NOTICE, "not fencing this node, heartbeating: %d, " + "connected: %d, lowest: %d (%sreachable)\n", + qs->qs_heartbeating, qs->qs_connected, lowest_hb, + lowest_reachable ? "" : "un"); + spin_unlock(&qs->qs_lock); + + } + +} + +static void o2quo_set_hold(struct o2quo_state *qs, u8 node) +{ + assert_spin_locked(&qs->qs_lock); + + if (!test_and_set_bit(node, qs->qs_hold_bm)) { + qs->qs_holds++; + mlog_bug_on_msg(qs->qs_holds == O2NM_MAX_NODES, + "node %u\n", node); + mlog(0, "node %u, %d total\n", node, qs->qs_holds); + } +} + +static void o2quo_clear_hold(struct o2quo_state *qs, u8 node) +{ + assert_spin_locked(&qs->qs_lock); + + if (test_and_clear_bit(node, qs->qs_hold_bm)) { + mlog(0, "node %u, %d total\n", node, qs->qs_holds - 1); + if (--qs->qs_holds == 0) { + if (qs->qs_pending) { + qs->qs_pending = 0; + schedule_work(&qs->qs_work); + } + } + mlog_bug_on_msg(qs->qs_holds < 0, "node %u, holds %d\n", + node, qs->qs_holds); + } +} + +/* as a node comes up we delay the quorum decision until we know the fate of + * the connection. the hold will be droped in conn_up or hb_down. it might be + * perpetuated by con_err until hb_down. if we already have a conn, we might + * be dropping a hold that conn_up got. */ +void o2quo_hb_up(u8 node) +{ + struct o2quo_state *qs = &o2quo_state; + + spin_lock(&qs->qs_lock); + + qs->qs_heartbeating++; + mlog_bug_on_msg(qs->qs_heartbeating == O2NM_MAX_NODES, + "node %u\n", node); + mlog_bug_on_msg(test_bit(node, qs->qs_hb_bm), "node %u\n", node); + set_bit(node, qs->qs_hb_bm); + + mlog(0, "node %u, %d total\n", node, qs->qs_heartbeating); + + if (!test_bit(node, qs->qs_conn_bm)) + o2quo_set_hold(qs, node); + else + o2quo_clear_hold(qs, node); + + spin_unlock(&qs->qs_lock); +} + +/* hb going down releases any holds we might have had due to this node from + * conn_up, conn_err, or hb_up */ +void o2quo_hb_down(u8 node) +{ + struct o2quo_state *qs = &o2quo_state; + + spin_lock(&qs->qs_lock); + + qs->qs_heartbeating--; + mlog_bug_on_msg(qs->qs_heartbeating < 0, + "node %u, %d heartbeating\n", + node, qs->qs_heartbeating); + mlog_bug_on_msg(!test_bit(node, qs->qs_hb_bm), "node %u\n", node); + clear_bit(node, qs->qs_hb_bm); + + mlog(0, "node %u, %d total\n", node, qs->qs_heartbeating); + + o2quo_clear_hold(qs, node); + + spin_unlock(&qs->qs_lock); +} + +/* this tells us that we've decided that the node is still heartbeating + * even though we've lost it's conn. it must only be called after conn_err + * and indicates that we must now make a quorum decision in the future, + * though we might be doing so after waiting for holds to drain. Here + * we'll be dropping the hold from conn_err. */ +void o2quo_hb_still_up(u8 node) +{ + struct o2quo_state *qs = &o2quo_state; + + spin_lock(&qs->qs_lock); + + mlog(0, "node %u\n", node); + + qs->qs_pending = 1; + o2quo_clear_hold(qs, node); + + spin_unlock(&qs->qs_lock); +} + +/* This is analogous to hb_up. as a node's connection comes up we delay the + * quorum decision until we see it heartbeating. the hold will be droped in + * hb_up or hb_down. it might be perpetuated by con_err until hb_down. if + * it's already heartbeating we might be dropping a hold that conn_up got. + * */ +void o2quo_conn_up(u8 node) +{ + struct o2quo_state *qs = &o2quo_state; + + spin_lock(&qs->qs_lock); + + qs->qs_connected++; + mlog_bug_on_msg(qs->qs_connected == O2NM_MAX_NODES, + "node %u\n", node); + mlog_bug_on_msg(test_bit(node, qs->qs_conn_bm), "node %u\n", node); + set_bit(node, qs->qs_conn_bm); + + mlog(0, "node %u, %d total\n", node, qs->qs_connected); + + if (!test_bit(node, qs->qs_hb_bm)) + o2quo_set_hold(qs, node); + else + o2quo_clear_hold(qs, node); + + spin_unlock(&qs->qs_lock); +} + +/* we've decided that we won't ever be connecting to the node again. if it's + * still heartbeating we grab a hold that will delay decisions until either the + * node stops heartbeating from hb_down or the caller decides that the node is + * still up and calls still_up */ +void o2quo_conn_err(u8 node) +{ + struct o2quo_state *qs = &o2quo_state; + + spin_lock(&qs->qs_lock); + + if (test_bit(node, qs->qs_conn_bm)) { + qs->qs_connected--; + mlog_bug_on_msg(qs->qs_connected < 0, + "node %u, connected %d\n", + node, qs->qs_connected); + + clear_bit(node, qs->qs_conn_bm); + + if (test_bit(node, qs->qs_hb_bm)) + o2quo_set_hold(qs, node); + } + + mlog(0, "node %u, %d total\n", node, qs->qs_connected); + + + spin_unlock(&qs->qs_lock); +} + +void o2quo_init(void) +{ + struct o2quo_state *qs = &o2quo_state; + + spin_lock_init(&qs->qs_lock); + INIT_WORK(&qs->qs_work, o2quo_make_decision); +} + +void o2quo_exit(void) +{ + struct o2quo_state *qs = &o2quo_state; + + flush_work(&qs->qs_work); +} -- cgit v1.2.3