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/pnode.c | 602 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 602 insertions(+) create mode 100644 fs/pnode.c (limited to 'fs/pnode.c') diff --git a/fs/pnode.c b/fs/pnode.c new file mode 100644 index 000000000..468e4e65a --- /dev/null +++ b/fs/pnode.c @@ -0,0 +1,602 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/pnode.c + * + * (C) Copyright IBM Corporation 2005. + * Author : Ram Pai (linuxram@us.ibm.com) + */ +#include +#include +#include +#include +#include +#include "internal.h" +#include "pnode.h" + +/* return the next shared peer mount of @p */ +static inline struct mount *next_peer(struct mount *p) +{ + return list_entry(p->mnt_share.next, struct mount, mnt_share); +} + +static inline struct mount *first_slave(struct mount *p) +{ + return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave); +} + +static inline struct mount *last_slave(struct mount *p) +{ + return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave); +} + +static inline struct mount *next_slave(struct mount *p) +{ + return list_entry(p->mnt_slave.next, struct mount, mnt_slave); +} + +static struct mount *get_peer_under_root(struct mount *mnt, + struct mnt_namespace *ns, + const struct path *root) +{ + struct mount *m = mnt; + + do { + /* Check the namespace first for optimization */ + if (m->mnt_ns == ns && is_path_reachable(m, m->mnt.mnt_root, root)) + return m; + + m = next_peer(m); + } while (m != mnt); + + return NULL; +} + +/* + * Get ID of closest dominating peer group having a representative + * under the given root. + * + * Caller must hold namespace_sem + */ +int get_dominating_id(struct mount *mnt, const struct path *root) +{ + struct mount *m; + + for (m = mnt->mnt_master; m != NULL; m = m->mnt_master) { + struct mount *d = get_peer_under_root(m, mnt->mnt_ns, root); + if (d) + return d->mnt_group_id; + } + + return 0; +} + +static int do_make_slave(struct mount *mnt) +{ + struct mount *master, *slave_mnt; + + if (list_empty(&mnt->mnt_share)) { + if (IS_MNT_SHARED(mnt)) { + mnt_release_group_id(mnt); + CLEAR_MNT_SHARED(mnt); + } + master = mnt->mnt_master; + if (!master) { + struct list_head *p = &mnt->mnt_slave_list; + while (!list_empty(p)) { + slave_mnt = list_first_entry(p, + struct mount, mnt_slave); + list_del_init(&slave_mnt->mnt_slave); + slave_mnt->mnt_master = NULL; + } + return 0; + } + } else { + struct mount *m; + /* + * slave 'mnt' to a peer mount that has the + * same root dentry. If none is available then + * slave it to anything that is available. + */ + for (m = master = next_peer(mnt); m != mnt; m = next_peer(m)) { + if (m->mnt.mnt_root == mnt->mnt.mnt_root) { + master = m; + break; + } + } + list_del_init(&mnt->mnt_share); + mnt->mnt_group_id = 0; + CLEAR_MNT_SHARED(mnt); + } + list_for_each_entry(slave_mnt, &mnt->mnt_slave_list, mnt_slave) + slave_mnt->mnt_master = master; + list_move(&mnt->mnt_slave, &master->mnt_slave_list); + list_splice(&mnt->mnt_slave_list, master->mnt_slave_list.prev); + INIT_LIST_HEAD(&mnt->mnt_slave_list); + mnt->mnt_master = master; + return 0; +} + +/* + * vfsmount lock must be held for write + */ +void change_mnt_propagation(struct mount *mnt, int type) +{ + if (type == MS_SHARED) { + set_mnt_shared(mnt); + return; + } + do_make_slave(mnt); + if (type != MS_SLAVE) { + list_del_init(&mnt->mnt_slave); + mnt->mnt_master = NULL; + if (type == MS_UNBINDABLE) + mnt->mnt.mnt_flags |= MNT_UNBINDABLE; + else + mnt->mnt.mnt_flags &= ~MNT_UNBINDABLE; + } +} + +/* + * get the next mount in the propagation tree. + * @m: the mount seen last + * @origin: the original mount from where the tree walk initiated + * + * Note that peer groups form contiguous segments of slave lists. + * We rely on that in get_source() to be able to find out if + * vfsmount found while iterating with propagation_next() is + * a peer of one we'd found earlier. + */ +static struct mount *propagation_next(struct mount *m, + struct mount *origin) +{ + /* are there any slaves of this mount? */ + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) + return first_slave(m); + + while (1) { + struct mount *master = m->mnt_master; + + if (master == origin->mnt_master) { + struct mount *next = next_peer(m); + return (next == origin) ? NULL : next; + } else if (m->mnt_slave.next != &master->mnt_slave_list) + return next_slave(m); + + /* back at master */ + m = master; + } +} + +static struct mount *skip_propagation_subtree(struct mount *m, + struct mount *origin) +{ + /* + * Advance m such that propagation_next will not return + * the slaves of m. + */ + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) + m = last_slave(m); + + return m; +} + +static struct mount *next_group(struct mount *m, struct mount *origin) +{ + while (1) { + while (1) { + struct mount *next; + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) + return first_slave(m); + next = next_peer(m); + if (m->mnt_group_id == origin->mnt_group_id) { + if (next == origin) + return NULL; + } else if (m->mnt_slave.next != &next->mnt_slave) + break; + m = next; + } + /* m is the last peer */ + while (1) { + struct mount *master = m->mnt_master; + if (m->mnt_slave.next != &master->mnt_slave_list) + return next_slave(m); + m = next_peer(master); + if (master->mnt_group_id == origin->mnt_group_id) + break; + if (master->mnt_slave.next == &m->mnt_slave) + break; + m = master; + } + if (m == origin) + return NULL; + } +} + +/* all accesses are serialized by namespace_sem */ +static struct mount *last_dest, *first_source, *last_source, *dest_master; +static struct mountpoint *mp; +static struct hlist_head *list; + +static inline bool peers(struct mount *m1, struct mount *m2) +{ + return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id; +} + +static int propagate_one(struct mount *m) +{ + struct mount *child; + int type; + /* skip ones added by this propagate_mnt() */ + if (IS_MNT_NEW(m)) + return 0; + /* skip if mountpoint isn't covered by it */ + if (!is_subdir(mp->m_dentry, m->mnt.mnt_root)) + return 0; + if (peers(m, last_dest)) { + type = CL_MAKE_SHARED; + } else { + struct mount *n, *p; + bool done; + for (n = m; ; n = p) { + p = n->mnt_master; + if (p == dest_master || IS_MNT_MARKED(p)) + break; + } + do { + struct mount *parent = last_source->mnt_parent; + if (peers(last_source, first_source)) + break; + done = parent->mnt_master == p; + if (done && peers(n, parent)) + break; + last_source = last_source->mnt_master; + } while (!done); + + type = CL_SLAVE; + /* beginning of peer group among the slaves? */ + if (IS_MNT_SHARED(m)) + type |= CL_MAKE_SHARED; + } + + child = copy_tree(last_source, last_source->mnt.mnt_root, type); + if (IS_ERR(child)) + return PTR_ERR(child); + read_seqlock_excl(&mount_lock); + mnt_set_mountpoint(m, mp, child); + if (m->mnt_master != dest_master) + SET_MNT_MARK(m->mnt_master); + read_sequnlock_excl(&mount_lock); + last_dest = m; + last_source = child; + hlist_add_head(&child->mnt_hash, list); + return count_mounts(m->mnt_ns, child); +} + +/* + * mount 'source_mnt' under the destination 'dest_mnt' at + * dentry 'dest_dentry'. And propagate that mount to + * all the peer and slave mounts of 'dest_mnt'. + * Link all the new mounts into a propagation tree headed at + * source_mnt. Also link all the new mounts using ->mnt_list + * headed at source_mnt's ->mnt_list + * + * @dest_mnt: destination mount. + * @dest_dentry: destination dentry. + * @source_mnt: source mount. + * @tree_list : list of heads of trees to be attached. + */ +int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, + struct mount *source_mnt, struct hlist_head *tree_list) +{ + struct mount *m, *n; + int ret = 0; + + /* + * we don't want to bother passing tons of arguments to + * propagate_one(); everything is serialized by namespace_sem, + * so globals will do just fine. + */ + last_dest = dest_mnt; + first_source = source_mnt; + last_source = source_mnt; + mp = dest_mp; + list = tree_list; + dest_master = dest_mnt->mnt_master; + + /* all peers of dest_mnt, except dest_mnt itself */ + for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) { + ret = propagate_one(n); + if (ret) + goto out; + } + + /* all slave groups */ + for (m = next_group(dest_mnt, dest_mnt); m; + m = next_group(m, dest_mnt)) { + /* everything in that slave group */ + n = m; + do { + ret = propagate_one(n); + if (ret) + goto out; + n = next_peer(n); + } while (n != m); + } +out: + read_seqlock_excl(&mount_lock); + hlist_for_each_entry(n, tree_list, mnt_hash) { + m = n->mnt_parent; + if (m->mnt_master != dest_mnt->mnt_master) + CLEAR_MNT_MARK(m->mnt_master); + } + read_sequnlock_excl(&mount_lock); + return ret; +} + +static struct mount *find_topper(struct mount *mnt) +{ + /* If there is exactly one mount covering mnt completely return it. */ + struct mount *child; + + if (!list_is_singular(&mnt->mnt_mounts)) + return NULL; + + child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child); + if (child->mnt_mountpoint != mnt->mnt.mnt_root) + return NULL; + + return child; +} + +/* + * return true if the refcount is greater than count + */ +static inline int do_refcount_check(struct mount *mnt, int count) +{ + return mnt_get_count(mnt) > count; +} + +/* + * check if the mount 'mnt' can be unmounted successfully. + * @mnt: the mount to be checked for unmount + * NOTE: unmounting 'mnt' would naturally propagate to all + * other mounts its parent propagates to. + * Check if any of these mounts that **do not have submounts** + * have more references than 'refcnt'. If so return busy. + * + * vfsmount lock must be held for write + */ +int propagate_mount_busy(struct mount *mnt, int refcnt) +{ + struct mount *m, *child, *topper; + struct mount *parent = mnt->mnt_parent; + + if (mnt == parent) + return do_refcount_check(mnt, refcnt); + + /* + * quickly check if the current mount can be unmounted. + * If not, we don't have to go checking for all other + * mounts + */ + if (!list_empty(&mnt->mnt_mounts) || do_refcount_check(mnt, refcnt)) + return 1; + + for (m = propagation_next(parent, parent); m; + m = propagation_next(m, parent)) { + int count = 1; + child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); + if (!child) + continue; + + /* Is there exactly one mount on the child that covers + * it completely whose reference should be ignored? + */ + topper = find_topper(child); + if (topper) + count += 1; + else if (!list_empty(&child->mnt_mounts)) + continue; + + if (do_refcount_check(child, count)) + return 1; + } + return 0; +} + +/* + * Clear MNT_LOCKED when it can be shown to be safe. + * + * mount_lock lock must be held for write + */ +void propagate_mount_unlock(struct mount *mnt) +{ + struct mount *parent = mnt->mnt_parent; + struct mount *m, *child; + + BUG_ON(parent == mnt); + + for (m = propagation_next(parent, parent); m; + m = propagation_next(m, parent)) { + child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); + if (child) + child->mnt.mnt_flags &= ~MNT_LOCKED; + } +} + +static void umount_one(struct mount *mnt, struct list_head *to_umount) +{ + CLEAR_MNT_MARK(mnt); + mnt->mnt.mnt_flags |= MNT_UMOUNT; + list_del_init(&mnt->mnt_child); + list_del_init(&mnt->mnt_umounting); + list_move_tail(&mnt->mnt_list, to_umount); +} + +/* + * NOTE: unmounting 'mnt' naturally propagates to all other mounts its + * parent propagates to. + */ +static bool __propagate_umount(struct mount *mnt, + struct list_head *to_umount, + struct list_head *to_restore) +{ + bool progress = false; + struct mount *child; + + /* + * The state of the parent won't change if this mount is + * already unmounted or marked as without children. + */ + if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED)) + goto out; + + /* Verify topper is the only grandchild that has not been + * speculatively unmounted. + */ + list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { + if (child->mnt_mountpoint == mnt->mnt.mnt_root) + continue; + if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child)) + continue; + /* Found a mounted child */ + goto children; + } + + /* Mark mounts that can be unmounted if not locked */ + SET_MNT_MARK(mnt); + progress = true; + + /* If a mount is without children and not locked umount it. */ + if (!IS_MNT_LOCKED(mnt)) { + umount_one(mnt, to_umount); + } else { +children: + list_move_tail(&mnt->mnt_umounting, to_restore); + } +out: + return progress; +} + +static void umount_list(struct list_head *to_umount, + struct list_head *to_restore) +{ + struct mount *mnt, *child, *tmp; + list_for_each_entry(mnt, to_umount, mnt_list) { + list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) { + /* topper? */ + if (child->mnt_mountpoint == mnt->mnt.mnt_root) + list_move_tail(&child->mnt_umounting, to_restore); + else + umount_one(child, to_umount); + } + } +} + +static void restore_mounts(struct list_head *to_restore) +{ + /* Restore mounts to a clean working state */ + while (!list_empty(to_restore)) { + struct mount *mnt, *parent; + struct mountpoint *mp; + + mnt = list_first_entry(to_restore, struct mount, mnt_umounting); + CLEAR_MNT_MARK(mnt); + list_del_init(&mnt->mnt_umounting); + + /* Should this mount be reparented? */ + mp = mnt->mnt_mp; + parent = mnt->mnt_parent; + while (parent->mnt.mnt_flags & MNT_UMOUNT) { + mp = parent->mnt_mp; + parent = parent->mnt_parent; + } + if (parent != mnt->mnt_parent) + mnt_change_mountpoint(parent, mp, mnt); + } +} + +static void cleanup_umount_visitations(struct list_head *visited) +{ + while (!list_empty(visited)) { + struct mount *mnt = + list_first_entry(visited, struct mount, mnt_umounting); + list_del_init(&mnt->mnt_umounting); + } +} + +/* + * collect all mounts that receive propagation from the mount in @list, + * and return these additional mounts in the same list. + * @list: the list of mounts to be unmounted. + * + * vfsmount lock must be held for write + */ +int propagate_umount(struct list_head *list) +{ + struct mount *mnt; + LIST_HEAD(to_restore); + LIST_HEAD(to_umount); + LIST_HEAD(visited); + + /* Find candidates for unmounting */ + list_for_each_entry_reverse(mnt, list, mnt_list) { + struct mount *parent = mnt->mnt_parent; + struct mount *m; + + /* + * If this mount has already been visited it is known that it's + * entire peer group and all of their slaves in the propagation + * tree for the mountpoint has already been visited and there is + * no need to visit them again. + */ + if (!list_empty(&mnt->mnt_umounting)) + continue; + + list_add_tail(&mnt->mnt_umounting, &visited); + for (m = propagation_next(parent, parent); m; + m = propagation_next(m, parent)) { + struct mount *child = __lookup_mnt(&m->mnt, + mnt->mnt_mountpoint); + if (!child) + continue; + + if (!list_empty(&child->mnt_umounting)) { + /* + * If the child has already been visited it is + * know that it's entire peer group and all of + * their slaves in the propgation tree for the + * mountpoint has already been visited and there + * is no need to visit this subtree again. + */ + m = skip_propagation_subtree(m, parent); + continue; + } else if (child->mnt.mnt_flags & MNT_UMOUNT) { + /* + * We have come accross an partially unmounted + * mount in list that has not been visited yet. + * Remember it has been visited and continue + * about our merry way. + */ + list_add_tail(&child->mnt_umounting, &visited); + continue; + } + + /* Check the child and parents while progress is made */ + while (__propagate_umount(child, + &to_umount, &to_restore)) { + /* Is the parent a umount candidate? */ + child = child->mnt_parent; + if (list_empty(&child->mnt_umounting)) + break; + } + } + } + + umount_list(&to_umount, &to_restore); + restore_mounts(&to_restore); + cleanup_umount_visitations(&visited); + list_splice_tail(&to_umount, list); + + return 0; +} -- cgit v1.2.3