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/dlmfs/userdlm.c | 682 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 682 insertions(+) create mode 100644 fs/ocfs2/dlmfs/userdlm.c (limited to 'fs/ocfs2/dlmfs/userdlm.c') diff --git a/fs/ocfs2/dlmfs/userdlm.c b/fs/ocfs2/dlmfs/userdlm.c new file mode 100644 index 000000000..617c92e7b --- /dev/null +++ b/fs/ocfs2/dlmfs/userdlm.c @@ -0,0 +1,682 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * userdlm.c + * + * Code which implements the kernel side of a minimal userspace + * interface to our DLM. + * + * Many of the functions here are pared down versions of dlmglue.c + * functions. + * + * Copyright (C) 2003, 2004 Oracle. All rights reserved. + */ + +#include +#include + +#include +#include +#include +#include + +#include "../ocfs2_lockingver.h" +#include "../stackglue.h" +#include "userdlm.h" + +#define MLOG_MASK_PREFIX ML_DLMFS +#include "../cluster/masklog.h" + + +static inline struct user_lock_res *user_lksb_to_lock_res(struct ocfs2_dlm_lksb *lksb) +{ + return container_of(lksb, struct user_lock_res, l_lksb); +} + +static inline int user_check_wait_flag(struct user_lock_res *lockres, + int flag) +{ + int ret; + + spin_lock(&lockres->l_lock); + ret = lockres->l_flags & flag; + spin_unlock(&lockres->l_lock); + + return ret; +} + +static inline void user_wait_on_busy_lock(struct user_lock_res *lockres) + +{ + wait_event(lockres->l_event, + !user_check_wait_flag(lockres, USER_LOCK_BUSY)); +} + +static inline void user_wait_on_blocked_lock(struct user_lock_res *lockres) + +{ + wait_event(lockres->l_event, + !user_check_wait_flag(lockres, USER_LOCK_BLOCKED)); +} + +/* I heart container_of... */ +static inline struct ocfs2_cluster_connection * +cluster_connection_from_user_lockres(struct user_lock_res *lockres) +{ + struct dlmfs_inode_private *ip; + + ip = container_of(lockres, + struct dlmfs_inode_private, + ip_lockres); + return ip->ip_conn; +} + +static struct inode * +user_dlm_inode_from_user_lockres(struct user_lock_res *lockres) +{ + struct dlmfs_inode_private *ip; + + ip = container_of(lockres, + struct dlmfs_inode_private, + ip_lockres); + return &ip->ip_vfs_inode; +} + +static inline void user_recover_from_dlm_error(struct user_lock_res *lockres) +{ + spin_lock(&lockres->l_lock); + lockres->l_flags &= ~USER_LOCK_BUSY; + spin_unlock(&lockres->l_lock); +} + +#define user_log_dlm_error(_func, _stat, _lockres) do { \ + mlog(ML_ERROR, "Dlm error %d while calling %s on " \ + "resource %.*s\n", _stat, _func, \ + _lockres->l_namelen, _lockres->l_name); \ +} while (0) + +/* WARNING: This function lives in a world where the only three lock + * levels are EX, PR, and NL. It *will* have to be adjusted when more + * lock types are added. */ +static inline int user_highest_compat_lock_level(int level) +{ + int new_level = DLM_LOCK_EX; + + if (level == DLM_LOCK_EX) + new_level = DLM_LOCK_NL; + else if (level == DLM_LOCK_PR) + new_level = DLM_LOCK_PR; + return new_level; +} + +static void user_ast(struct ocfs2_dlm_lksb *lksb) +{ + struct user_lock_res *lockres = user_lksb_to_lock_res(lksb); + int status; + + mlog(ML_BASTS, "AST fired for lockres %.*s, level %d => %d\n", + lockres->l_namelen, lockres->l_name, lockres->l_level, + lockres->l_requested); + + spin_lock(&lockres->l_lock); + + status = ocfs2_dlm_lock_status(&lockres->l_lksb); + if (status) { + mlog(ML_ERROR, "lksb status value of %u on lockres %.*s\n", + status, lockres->l_namelen, lockres->l_name); + spin_unlock(&lockres->l_lock); + return; + } + + mlog_bug_on_msg(lockres->l_requested == DLM_LOCK_IV, + "Lockres %.*s, requested ivmode. flags 0x%x\n", + lockres->l_namelen, lockres->l_name, lockres->l_flags); + + /* we're downconverting. */ + if (lockres->l_requested < lockres->l_level) { + if (lockres->l_requested <= + user_highest_compat_lock_level(lockres->l_blocking)) { + lockres->l_blocking = DLM_LOCK_NL; + lockres->l_flags &= ~USER_LOCK_BLOCKED; + } + } + + lockres->l_level = lockres->l_requested; + lockres->l_requested = DLM_LOCK_IV; + lockres->l_flags |= USER_LOCK_ATTACHED; + lockres->l_flags &= ~USER_LOCK_BUSY; + + spin_unlock(&lockres->l_lock); + + wake_up(&lockres->l_event); +} + +static inline void user_dlm_grab_inode_ref(struct user_lock_res *lockres) +{ + struct inode *inode; + inode = user_dlm_inode_from_user_lockres(lockres); + if (!igrab(inode)) + BUG(); +} + +static void user_dlm_unblock_lock(struct work_struct *work); + +static void __user_dlm_queue_lockres(struct user_lock_res *lockres) +{ + if (!(lockres->l_flags & USER_LOCK_QUEUED)) { + user_dlm_grab_inode_ref(lockres); + + INIT_WORK(&lockres->l_work, user_dlm_unblock_lock); + + queue_work(user_dlm_worker, &lockres->l_work); + lockres->l_flags |= USER_LOCK_QUEUED; + } +} + +static void __user_dlm_cond_queue_lockres(struct user_lock_res *lockres) +{ + int queue = 0; + + if (!(lockres->l_flags & USER_LOCK_BLOCKED)) + return; + + switch (lockres->l_blocking) { + case DLM_LOCK_EX: + if (!lockres->l_ex_holders && !lockres->l_ro_holders) + queue = 1; + break; + case DLM_LOCK_PR: + if (!lockres->l_ex_holders) + queue = 1; + break; + default: + BUG(); + } + + if (queue) + __user_dlm_queue_lockres(lockres); +} + +static void user_bast(struct ocfs2_dlm_lksb *lksb, int level) +{ + struct user_lock_res *lockres = user_lksb_to_lock_res(lksb); + + mlog(ML_BASTS, "BAST fired for lockres %.*s, blocking %d, level %d\n", + lockres->l_namelen, lockres->l_name, level, lockres->l_level); + + spin_lock(&lockres->l_lock); + lockres->l_flags |= USER_LOCK_BLOCKED; + if (level > lockres->l_blocking) + lockres->l_blocking = level; + + __user_dlm_queue_lockres(lockres); + spin_unlock(&lockres->l_lock); + + wake_up(&lockres->l_event); +} + +static void user_unlock_ast(struct ocfs2_dlm_lksb *lksb, int status) +{ + struct user_lock_res *lockres = user_lksb_to_lock_res(lksb); + + mlog(ML_BASTS, "UNLOCK AST fired for lockres %.*s, flags 0x%x\n", + lockres->l_namelen, lockres->l_name, lockres->l_flags); + + if (status) + mlog(ML_ERROR, "dlm returns status %d\n", status); + + spin_lock(&lockres->l_lock); + /* The teardown flag gets set early during the unlock process, + * so test the cancel flag to make sure that this ast isn't + * for a concurrent cancel. */ + if (lockres->l_flags & USER_LOCK_IN_TEARDOWN + && !(lockres->l_flags & USER_LOCK_IN_CANCEL)) { + lockres->l_level = DLM_LOCK_IV; + } else if (status == DLM_CANCELGRANT) { + /* We tried to cancel a convert request, but it was + * already granted. Don't clear the busy flag - the + * ast should've done this already. */ + BUG_ON(!(lockres->l_flags & USER_LOCK_IN_CANCEL)); + lockres->l_flags &= ~USER_LOCK_IN_CANCEL; + goto out_noclear; + } else { + BUG_ON(!(lockres->l_flags & USER_LOCK_IN_CANCEL)); + /* Cancel succeeded, we want to re-queue */ + lockres->l_requested = DLM_LOCK_IV; /* cancel an + * upconvert + * request. */ + lockres->l_flags &= ~USER_LOCK_IN_CANCEL; + /* we want the unblock thread to look at it again + * now. */ + if (lockres->l_flags & USER_LOCK_BLOCKED) + __user_dlm_queue_lockres(lockres); + } + + lockres->l_flags &= ~USER_LOCK_BUSY; +out_noclear: + spin_unlock(&lockres->l_lock); + + wake_up(&lockres->l_event); +} + +/* + * This is the userdlmfs locking protocol version. + * + * See fs/ocfs2/dlmglue.c for more details on locking versions. + */ +static struct ocfs2_locking_protocol user_dlm_lproto = { + .lp_max_version = { + .pv_major = OCFS2_LOCKING_PROTOCOL_MAJOR, + .pv_minor = OCFS2_LOCKING_PROTOCOL_MINOR, + }, + .lp_lock_ast = user_ast, + .lp_blocking_ast = user_bast, + .lp_unlock_ast = user_unlock_ast, +}; + +static inline void user_dlm_drop_inode_ref(struct user_lock_res *lockres) +{ + struct inode *inode; + inode = user_dlm_inode_from_user_lockres(lockres); + iput(inode); +} + +static void user_dlm_unblock_lock(struct work_struct *work) +{ + int new_level, status; + struct user_lock_res *lockres = + container_of(work, struct user_lock_res, l_work); + struct ocfs2_cluster_connection *conn = + cluster_connection_from_user_lockres(lockres); + + mlog(0, "lockres %.*s\n", lockres->l_namelen, lockres->l_name); + + spin_lock(&lockres->l_lock); + + mlog_bug_on_msg(!(lockres->l_flags & USER_LOCK_QUEUED), + "Lockres %.*s, flags 0x%x\n", + lockres->l_namelen, lockres->l_name, lockres->l_flags); + + /* notice that we don't clear USER_LOCK_BLOCKED here. If it's + * set, we want user_ast clear it. */ + lockres->l_flags &= ~USER_LOCK_QUEUED; + + /* It's valid to get here and no longer be blocked - if we get + * several basts in a row, we might be queued by the first + * one, the unblock thread might run and clear the queued + * flag, and finally we might get another bast which re-queues + * us before our ast for the downconvert is called. */ + if (!(lockres->l_flags & USER_LOCK_BLOCKED)) { + mlog(ML_BASTS, "lockres %.*s USER_LOCK_BLOCKED\n", + lockres->l_namelen, lockres->l_name); + spin_unlock(&lockres->l_lock); + goto drop_ref; + } + + if (lockres->l_flags & USER_LOCK_IN_TEARDOWN) { + mlog(ML_BASTS, "lockres %.*s USER_LOCK_IN_TEARDOWN\n", + lockres->l_namelen, lockres->l_name); + spin_unlock(&lockres->l_lock); + goto drop_ref; + } + + if (lockres->l_flags & USER_LOCK_BUSY) { + if (lockres->l_flags & USER_LOCK_IN_CANCEL) { + mlog(ML_BASTS, "lockres %.*s USER_LOCK_IN_CANCEL\n", + lockres->l_namelen, lockres->l_name); + spin_unlock(&lockres->l_lock); + goto drop_ref; + } + + lockres->l_flags |= USER_LOCK_IN_CANCEL; + spin_unlock(&lockres->l_lock); + + status = ocfs2_dlm_unlock(conn, &lockres->l_lksb, + DLM_LKF_CANCEL); + if (status) + user_log_dlm_error("ocfs2_dlm_unlock", status, lockres); + goto drop_ref; + } + + /* If there are still incompat holders, we can exit safely + * without worrying about re-queueing this lock as that will + * happen on the last call to user_cluster_unlock. */ + if ((lockres->l_blocking == DLM_LOCK_EX) + && (lockres->l_ex_holders || lockres->l_ro_holders)) { + spin_unlock(&lockres->l_lock); + mlog(ML_BASTS, "lockres %.*s, EX/PR Holders %u,%u\n", + lockres->l_namelen, lockres->l_name, + lockres->l_ex_holders, lockres->l_ro_holders); + goto drop_ref; + } + + if ((lockres->l_blocking == DLM_LOCK_PR) + && lockres->l_ex_holders) { + spin_unlock(&lockres->l_lock); + mlog(ML_BASTS, "lockres %.*s, EX Holders %u\n", + lockres->l_namelen, lockres->l_name, + lockres->l_ex_holders); + goto drop_ref; + } + + /* yay, we can downconvert now. */ + new_level = user_highest_compat_lock_level(lockres->l_blocking); + lockres->l_requested = new_level; + lockres->l_flags |= USER_LOCK_BUSY; + mlog(ML_BASTS, "lockres %.*s, downconvert %d => %d\n", + lockres->l_namelen, lockres->l_name, lockres->l_level, new_level); + spin_unlock(&lockres->l_lock); + + /* need lock downconvert request now... */ + status = ocfs2_dlm_lock(conn, new_level, &lockres->l_lksb, + DLM_LKF_CONVERT|DLM_LKF_VALBLK, + lockres->l_name, + lockres->l_namelen); + if (status) { + user_log_dlm_error("ocfs2_dlm_lock", status, lockres); + user_recover_from_dlm_error(lockres); + } + +drop_ref: + user_dlm_drop_inode_ref(lockres); +} + +static inline void user_dlm_inc_holders(struct user_lock_res *lockres, + int level) +{ + switch(level) { + case DLM_LOCK_EX: + lockres->l_ex_holders++; + break; + case DLM_LOCK_PR: + lockres->l_ro_holders++; + break; + default: + BUG(); + } +} + +/* predict what lock level we'll be dropping down to on behalf + * of another node, and return true if the currently wanted + * level will be compatible with it. */ +static inline int +user_may_continue_on_blocked_lock(struct user_lock_res *lockres, + int wanted) +{ + BUG_ON(!(lockres->l_flags & USER_LOCK_BLOCKED)); + + return wanted <= user_highest_compat_lock_level(lockres->l_blocking); +} + +int user_dlm_cluster_lock(struct user_lock_res *lockres, + int level, + int lkm_flags) +{ + int status, local_flags; + struct ocfs2_cluster_connection *conn = + cluster_connection_from_user_lockres(lockres); + + if (level != DLM_LOCK_EX && + level != DLM_LOCK_PR) { + mlog(ML_ERROR, "lockres %.*s: invalid request!\n", + lockres->l_namelen, lockres->l_name); + status = -EINVAL; + goto bail; + } + + mlog(ML_BASTS, "lockres %.*s, level %d, flags = 0x%x\n", + lockres->l_namelen, lockres->l_name, level, lkm_flags); + +again: + if (signal_pending(current)) { + status = -ERESTARTSYS; + goto bail; + } + + spin_lock(&lockres->l_lock); + if (lockres->l_flags & USER_LOCK_IN_TEARDOWN) { + spin_unlock(&lockres->l_lock); + status = -EAGAIN; + goto bail; + } + + /* We only compare against the currently granted level + * here. If the lock is blocked waiting on a downconvert, + * we'll get caught below. */ + if ((lockres->l_flags & USER_LOCK_BUSY) && + (level > lockres->l_level)) { + /* is someone sitting in dlm_lock? If so, wait on + * them. */ + spin_unlock(&lockres->l_lock); + + user_wait_on_busy_lock(lockres); + goto again; + } + + if ((lockres->l_flags & USER_LOCK_BLOCKED) && + (!user_may_continue_on_blocked_lock(lockres, level))) { + /* is the lock is currently blocked on behalf of + * another node */ + spin_unlock(&lockres->l_lock); + + user_wait_on_blocked_lock(lockres); + goto again; + } + + if (level > lockres->l_level) { + local_flags = lkm_flags | DLM_LKF_VALBLK; + if (lockres->l_level != DLM_LOCK_IV) + local_flags |= DLM_LKF_CONVERT; + + lockres->l_requested = level; + lockres->l_flags |= USER_LOCK_BUSY; + spin_unlock(&lockres->l_lock); + + BUG_ON(level == DLM_LOCK_IV); + BUG_ON(level == DLM_LOCK_NL); + + /* call dlm_lock to upgrade lock now */ + status = ocfs2_dlm_lock(conn, level, &lockres->l_lksb, + local_flags, lockres->l_name, + lockres->l_namelen); + if (status) { + if ((lkm_flags & DLM_LKF_NOQUEUE) && + (status != -EAGAIN)) + user_log_dlm_error("ocfs2_dlm_lock", + status, lockres); + user_recover_from_dlm_error(lockres); + goto bail; + } + + user_wait_on_busy_lock(lockres); + goto again; + } + + user_dlm_inc_holders(lockres, level); + spin_unlock(&lockres->l_lock); + + status = 0; +bail: + return status; +} + +static inline void user_dlm_dec_holders(struct user_lock_res *lockres, + int level) +{ + switch(level) { + case DLM_LOCK_EX: + BUG_ON(!lockres->l_ex_holders); + lockres->l_ex_holders--; + break; + case DLM_LOCK_PR: + BUG_ON(!lockres->l_ro_holders); + lockres->l_ro_holders--; + break; + default: + BUG(); + } +} + +void user_dlm_cluster_unlock(struct user_lock_res *lockres, + int level) +{ + if (level != DLM_LOCK_EX && + level != DLM_LOCK_PR) { + mlog(ML_ERROR, "lockres %.*s: invalid request!\n", + lockres->l_namelen, lockres->l_name); + return; + } + + spin_lock(&lockres->l_lock); + user_dlm_dec_holders(lockres, level); + __user_dlm_cond_queue_lockres(lockres); + spin_unlock(&lockres->l_lock); +} + +void user_dlm_write_lvb(struct inode *inode, + const char *val, + unsigned int len) +{ + struct user_lock_res *lockres = &DLMFS_I(inode)->ip_lockres; + char *lvb; + + BUG_ON(len > DLM_LVB_LEN); + + spin_lock(&lockres->l_lock); + + BUG_ON(lockres->l_level < DLM_LOCK_EX); + lvb = ocfs2_dlm_lvb(&lockres->l_lksb); + memcpy(lvb, val, len); + + spin_unlock(&lockres->l_lock); +} + +bool user_dlm_read_lvb(struct inode *inode, char *val) +{ + struct user_lock_res *lockres = &DLMFS_I(inode)->ip_lockres; + char *lvb; + bool ret = true; + + spin_lock(&lockres->l_lock); + + BUG_ON(lockres->l_level < DLM_LOCK_PR); + if (ocfs2_dlm_lvb_valid(&lockres->l_lksb)) { + lvb = ocfs2_dlm_lvb(&lockres->l_lksb); + memcpy(val, lvb, DLM_LVB_LEN); + } else + ret = false; + + spin_unlock(&lockres->l_lock); + return ret; +} + +void user_dlm_lock_res_init(struct user_lock_res *lockres, + struct dentry *dentry) +{ + memset(lockres, 0, sizeof(*lockres)); + + spin_lock_init(&lockres->l_lock); + init_waitqueue_head(&lockres->l_event); + lockres->l_level = DLM_LOCK_IV; + lockres->l_requested = DLM_LOCK_IV; + lockres->l_blocking = DLM_LOCK_IV; + + /* should have been checked before getting here. */ + BUG_ON(dentry->d_name.len >= USER_DLM_LOCK_ID_MAX_LEN); + + memcpy(lockres->l_name, + dentry->d_name.name, + dentry->d_name.len); + lockres->l_namelen = dentry->d_name.len; +} + +int user_dlm_destroy_lock(struct user_lock_res *lockres) +{ + int status = -EBUSY; + struct ocfs2_cluster_connection *conn = + cluster_connection_from_user_lockres(lockres); + + mlog(ML_BASTS, "lockres %.*s\n", lockres->l_namelen, lockres->l_name); + + spin_lock(&lockres->l_lock); + if (lockres->l_flags & USER_LOCK_IN_TEARDOWN) { + spin_unlock(&lockres->l_lock); + goto bail; + } + + lockres->l_flags |= USER_LOCK_IN_TEARDOWN; + + while (lockres->l_flags & USER_LOCK_BUSY) { + spin_unlock(&lockres->l_lock); + + user_wait_on_busy_lock(lockres); + + spin_lock(&lockres->l_lock); + } + + if (lockres->l_ro_holders || lockres->l_ex_holders) { + lockres->l_flags &= ~USER_LOCK_IN_TEARDOWN; + spin_unlock(&lockres->l_lock); + goto bail; + } + + status = 0; + if (!(lockres->l_flags & USER_LOCK_ATTACHED)) { + /* + * lock is never requested, leave USER_LOCK_IN_TEARDOWN set + * to avoid new lock request coming in. + */ + spin_unlock(&lockres->l_lock); + goto bail; + } + + lockres->l_flags |= USER_LOCK_BUSY; + spin_unlock(&lockres->l_lock); + + status = ocfs2_dlm_unlock(conn, &lockres->l_lksb, DLM_LKF_VALBLK); + if (status) { + spin_lock(&lockres->l_lock); + lockres->l_flags &= ~USER_LOCK_IN_TEARDOWN; + lockres->l_flags &= ~USER_LOCK_BUSY; + spin_unlock(&lockres->l_lock); + user_log_dlm_error("ocfs2_dlm_unlock", status, lockres); + goto bail; + } + + user_wait_on_busy_lock(lockres); + + status = 0; +bail: + return status; +} + +static void user_dlm_recovery_handler_noop(int node_num, + void *recovery_data) +{ + /* We ignore recovery events */ + return; +} + +void user_dlm_set_locking_protocol(void) +{ + ocfs2_stack_glue_set_max_proto_version(&user_dlm_lproto.lp_max_version); +} + +struct ocfs2_cluster_connection *user_dlm_register(const struct qstr *name) +{ + int rc; + struct ocfs2_cluster_connection *conn; + + rc = ocfs2_cluster_connect_agnostic(name->name, name->len, + &user_dlm_lproto, + user_dlm_recovery_handler_noop, + NULL, &conn); + if (rc) + mlog_errno(rc); + + return rc ? ERR_PTR(rc) : conn; +} + +void user_dlm_unregister(struct ocfs2_cluster_connection *conn) +{ + ocfs2_cluster_disconnect(conn, 0); +} -- cgit v1.2.3