refs/heads/tmp-28ec98b: Linux 4.4.55 ext4: don't BUG when truncating encrypted inodes on the orphan list dm: flush queued bios when process blocks to avoid deadlock nfit, libnvdimm: fix interleave set cookie calculation s390/kdump: Use "LINUX" ELF note name instead of "CORE" KVM: s390: Fix guest migration for huge guests resulting in panic mvsas: fix misleading indentation serial: samsung: Continue to work if DMA request fails USB: serial: io_ti: fix information leak in completion handler USB: serial: io_ti: fix NULL-deref in interrupt callback USB: iowarrior: fix NULL-deref in write USB: iowarrior: fix NULL-deref at probe USB: serial: omninet: fix reference leaks at open USB: serial: safe_serial: fix information leak in completion handler usb: host: xhci-plat: Fix timeout on removal of hot pluggable xhci controllers usb: host: xhci-dbg: HCIVERSION should be a binary number usb: gadget: function: f_fs: pass companion descriptor along usb: dwc3: gadget: make Set Endpoint Configuration macros safe usb: gadget: dummy_hcd: clear usb_gadget region before registration powerpc: Emulation support for load/store instructions on LE tracing: Add #undef to fix compile error MIPS: Netlogic: Fix CP0_EBASE redefinition warnings MIPS: DEC: Avoid la pseudo-instruction in delay slots mm: memcontrol: avoid unused function warning cpmac: remove hopeless #warning MIPS: ralink: Remove unused rt*_wdt_reset functions MIPS: ralink: Cosmetic change to prom_init(). mtd: pmcmsp: use kstrndup instead of kmalloc+strncpy MIPS: Update lemote2f_defconfig for CPU_FREQ_STAT change MIPS: ip22: Fix ip28 build for modern gcc MIPS: Update ip27_defconfig for SCSI_DH change MIPS: ip27: Disable qlge driver in defconfig MIPS: Update defconfigs for NF_CT_PROTO_DCCP/UDPLITE change crypto: improve gcc optimization flags for serpent and wp512 USB: serial: digi_acceleport: fix OOB-event processing USB: serial: digi_acceleport: fix OOB data sanity check Linux 4.4.54 drivers: hv: Turn off write permission on the hypercall page fat: fix using uninitialized fields of fat_inode/fsinfo_inode libceph: use BUG() instead of BUG_ON(1) drm/i915/dsi: Do not clear DPOUNIT_CLOCK_GATE_DISABLE from vlv_init_display_clock_gating fakelb: fix schedule while atomic drm/atomic: fix an error code in mode_fixup() drm/ttm: Make sure BOs being swapped out are cacheable drm/edid: Add EDID_QUIRK_FORCE_8BPC quirk for Rotel RSX-1058 drm/ast: Fix AST2400 POST failure without BMC FW or VBIOS drm/ast: Call open_key before enable_mmio in POST code drm/ast: Fix test for VGA enabled drm/amdgpu: add more cases to DCE11 possible crtc mask setup mac80211: flush delayed work when entering suspend xtensa: move parse_tag_fdt out of #ifdef CONFIG_BLK_DEV_INITRD pwm: pca9685: Fix period change with same duty cycle nlm: Ensure callback code also checks that the files match target: Fix NULL dereference during LUN lookup + active I/O shutdown ceph: remove req from unsafe list when unregistering it ktest: Fix child exit code processing IB/srp: Fix race conditions related to task management IB/srp: Avoid that duplicate responses trigger a kernel bug IB/IPoIB: Add destination address when re-queue packet IB/ipoib: Fix deadlock between rmmod and set_mode mnt: Tuck mounts under others instead of creating shadow/side mounts. net: mvpp2: fix DMA address calculation in mvpp2_txq_inc_put() s390: use correct input data address for setup_randomness s390: make setup_randomness work s390: TASK_SIZE for kernel threads s390/dcssblk: fix device size calculation in dcssblk_direct_access() s390/qdio: clear DSCI prior to scanning multiple input queues Bluetooth: Add another AR3012 04ca:3018 device KVM: VMX: use correct vmcs_read/write for guest segment selector/base KVM: s390: Disable dirty log retrieval for UCONTROL guests serial: 8250_pci: Add MKS Tenta SCOM-0800 and SCOM-0801 cards tty: n_hdlc: get rid of racy n_hdlc.tbuf TTY: n_hdlc, fix lockdep false positive Linux 4.4.53 scsi: lpfc: Correct WQ creation for pagesize MIPS: IP22: Fix build error due to binutils 2.25 uselessnes. MIPS: IP22: Reformat inline assembler code to modern standards. powerpc/xmon: Fix data-breakpoint dmaengine: ipu: Make sure the interrupt routine checks all interrupts. bcma: use (get|put)_device when probing/removing device driver md linear: fix a race between linear_add() and linear_congested() rtc: sun6i: Switch to the external oscillator rtc: sun6i: Add some locking NFSv4: fix getacl ERANGE for some ACL buffer sizes NFSv4: fix getacl head length estimation NFSv4: Fix memory and state leak in _nfs4_open_and_get_state nfsd: special case truncates some more nfsd: minor nfsd_setattr cleanup rtlwifi: rtl8192c-common: Fix "BUG: KASAN: rtlwifi: Fix alignment issues gfs2: Add missing rcu locking for glock lookup rdma_cm: fail iwarp accepts w/o connection params RDMA/core: Fix incorrect structure packing for booleans Drivers: hv: util: Backup: Fix a rescind processing issue Drivers: hv: util: Fcopy: Fix a rescind processing issue Drivers: hv: util: kvp: Fix a rescind processing issue hv: init percpu_list in hv_synic_alloc() hv: allocate synic pages for all present CPUs usb: gadget: udc: fsl: Add missing complete function. usb: host: xhci: plat: check hcc_params after add hcd usb: musb: da8xx: Remove CPPI 3.0 quirk and methods w1: ds2490: USB transfer buffers need to be DMAable w1: don't leak refcount on slave attach failure in w1_attach_slave_device() can: usb_8dev: Fix memory leak of priv->cmd_msg_buffer iio: pressure: mpl3115: do not rely on structure field ordering iio: pressure: mpl115: do not rely on structure field ordering arm/arm64: KVM: Enforce unconditional flush to PoC when mapping to stage-2 fuse: add missing FR_FORCE crypto: testmgr - Pad aes_ccm_enc_tv_template vector ath9k: use correct OTP register offsets for the AR9340 and AR9550 ath9k: fix race condition in enabling/disabling IRQs ath5k: drop bogus warning on drv_set_key with unsupported cipher target: Fix multi-session dynamic se_node_acl double free OOPs target: Obtain se_node_acl->acl_kref during get_initiator_node_acl samples/seccomp: fix 64-bit comparison macros ext4: return EROFS if device is r/o and journal replay is needed ext4: preserve the needs_recovery flag when the journal is aborted ext4: fix inline data error paths ext4: fix data corruption in data=journal mode ext4: trim allocation requests to group size ext4: do not polute the extents cache while shifting extents ext4: Include forgotten start block on fallocate insert range loop: fix LO_FLAGS_PARTSCAN hang block/loop: fix race between I/O and set_status jbd2: don't leak modified metadata buffers on an aborted journal Fix: Disable sys_membarrier when nohz_full is enabled sd: get disk reference in sd_check_events() scsi: use 'scsi_device_from_queue()' for scsi_dh scsi: aacraid: Reorder Adapter status check scsi: storvsc: properly set residual data length on errors scsi: storvsc: properly handle SRB_ERROR when sense message is present scsi: storvsc: use tagged SRB requests if supported by the device dm stats: fix a leaked s->histogram_boundaries array dm cache: fix corruption seen when using cache > 2TB ipc/shm: Fix shmat mmap nil-page protection mm: do not access page->mapping directly on page_endio mm: vmpressure: fix sending wrong events on underflow mm/page_alloc: fix nodes for reclaim in fast path iommu/vt-d: Tylersburg isoch identity map check is done too late. iommu/vt-d: Fix some macros that are incorrectly specified in intel-iommu regulator: Fix regulator_summary for deviceless consumers staging: rtl: fix possible NULL pointer dereference ALSA: hda - Fix micmute hotkey problem for a lenovo AIO machine ALSA: hda - Add subwoofer support for Dell Inspiron 17 7000 Gaming ALSA: seq: Fix link corruption by event error handling ALSA: ctxfi: Fallback DMA mask to 32bit ALSA: timer: Reject user params with too small ticks ALSA: hda - fix Lewisburg audio issue ALSA: hda/realtek - Cannot adjust speaker's volume on a Dell AIO ARM: dts: at91: Enable DMA on sama5d2_xplained console ARM: dts: at91: Enable DMA on sama5d4_xplained console ARM: at91: define LPDDR types media: fix dm1105.c build error uvcvideo: Fix a wrong macro am437x-vpfe: always assign bpp variable MIPS: Handle microMIPS jumps in the same way as MIPS32/MIPS64 jumps MIPS: Calculate microMIPS ra properly when unwinding the stack MIPS: Fix is_jump_ins() handling of 16b microMIPS instructions MIPS: Fix get_frame_info() handling of microMIPS function size MIPS: Prevent unaligned accesses during stack unwinding MIPS: Clear ISA bit correctly in get_frame_info() MIPS: Lantiq: Keep ethernet enabled during boot MIPS: OCTEON: Fix copy_from_user fault handling for large buffers MIPS: BCM47XX: Fix button inversion for Asus WL-500W MIPS: Fix special case in 64 bit IP checksumming. samples: move mic/mpssd example code from Documentation Linux 4.4.52 kvm: vmx: ensure VMCS is current while enabling PML Revert "usb: chipidea: imx: enable CI_HDRC_SET_NON_ZERO_TTHA" rtlwifi: rtl_usb: Fix for URB leaking when doing ifconfig up/down block: fix double-free in the failure path of cgwb_bdi_init() goldfish: Sanitize the broken interrupt handler x86/platform/goldfish: Prevent unconditional loading USB: serial: ark3116: fix register-accessor error handling USB: serial: opticon: fix CTS retrieval at open USB: serial: spcp8x5: fix modem-status handling USB: serial: ftdi_sio: fix line-status over-reporting USB: serial: ftdi_sio: fix extreme low-latency setting USB: serial: ftdi_sio: fix modem-status error handling USB: serial: cp210x: add new IDs for GE Bx50v3 boards USB: serial: mos7840: fix another NULL-deref at open tty: serial: msm: Fix module autoload net: socket: fix recvmmsg not returning error from sock_error ip: fix IP_CHECKSUM handling irda: Fix lockdep annotations in hashbin_delete(). dccp: fix freeing skb too early for IPV6_RECVPKTINFO packet: Do not call fanout_release from atomic contexts packet: fix races in fanout_add() net/llc: avoid BUG_ON() in skb_orphan() blk-mq: really fix plug list flushing for nomerge queues rtc: interface: ignore expired timers when enqueuing new timers rtlwifi: rtl_usb: Fix missing entry in USB driver's private data Linux 4.4.51 mmc: core: fix multi-bit bus width without high-speed mode bcache: Make gc wakeup sane, remove set_task_state() ntb_transport: Pick an unused queue NTB: ntb_transport: fix debugfs_remove_recursive printk: use rcuidle console tracepoint ARM: 8658/1: uaccess: fix zeroing of 64-bit get_user() futex: Move futex_init() to core_initcall drm/dp/mst: fix kernel oops when turning off secondary monitor drm/radeon: Use mode h/vdisplay fields to hide out of bounds HW cursor Input: elan_i2c - add ELAN0605 to the ACPI table Fix missing sanity check in /dev/sg scsi: don't BUG_ON() empty DMA transfers fuse: fix use after free issue in fuse_dev_do_read() siano: make it work again with CONFIG_VMAP_STACK vfs: fix uninitialized flags in splice_to_pipe() Linux 4.4.50 l2tp: do not use udp_ioctl() ping: fix a null pointer dereference packet: round up linear to header len net: introduce device min_header_len sit: fix a double free on error path sctp: avoid BUG_ON on sctp_wait_for_sndbuf mlx4: Invoke softirqs after napi_reschedule macvtap: read vnet_hdr_size once tun: read vnet_hdr_sz once tcp: avoid infinite loop in tcp_splice_read() ipv6: tcp: add a missing tcp_v6_restore_cb() ip6_gre: fix ip6gre_err() invalid reads netlabel: out of bound access in cipso_v4_validate() ipv4: keep skb->dst around in presence of IP options net: use a work queue to defer net_disable_timestamp() work tcp: fix 0 divide in __tcp_select_window() ipv6: pointer math error in ip6_tnl_parse_tlv_enc_lim() ipv6: fix ip6_tnl_parse_tlv_enc_lim() can: Fix kernel panic at security_sock_rcv_skb Conflicts: drivers/scsi/sd.c drivers/usb/gadget/function/f_fs.c drivers/usb/host/xhci-plat.c CRs-Fixed: 2023471 Change-Id: I396051a8de30271af77b3890d4b19787faa1c31e Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>
526 lines
13 KiB
C
526 lines
13 KiB
C
/*
|
|
* linux/fs/pnode.c
|
|
*
|
|
* (C) Copyright IBM Corporation 2005.
|
|
* Released under GPL v2.
|
|
* Author : Ram Pai (linuxram@us.ibm.com)
|
|
*
|
|
*/
|
|
#include <linux/mnt_namespace.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/nsproxy.h>
|
|
#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 *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 *peer_mnt = mnt, *master = mnt->mnt_master;
|
|
struct mount *slave_mnt;
|
|
|
|
/*
|
|
* slave 'mnt' to a peer mount that has the
|
|
* same root dentry. If none is available then
|
|
* slave it to anything that is available.
|
|
*/
|
|
while ((peer_mnt = next_peer(peer_mnt)) != mnt &&
|
|
peer_mnt->mnt.mnt_root != mnt->mnt.mnt_root) ;
|
|
|
|
if (peer_mnt == mnt) {
|
|
peer_mnt = next_peer(mnt);
|
|
if (peer_mnt == mnt)
|
|
peer_mnt = NULL;
|
|
}
|
|
if (mnt->mnt_group_id && IS_MNT_SHARED(mnt) &&
|
|
list_empty(&mnt->mnt_share))
|
|
mnt_release_group_id(mnt);
|
|
|
|
list_del_init(&mnt->mnt_share);
|
|
mnt->mnt_group_id = 0;
|
|
|
|
if (peer_mnt)
|
|
master = peer_mnt;
|
|
|
|
if (master) {
|
|
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);
|
|
} else {
|
|
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;
|
|
}
|
|
}
|
|
mnt->mnt_master = master;
|
|
CLEAR_MNT_SHARED(mnt);
|
|
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 *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 user_namespace *user_ns;
|
|
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 (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;
|
|
}
|
|
|
|
/* Notice when we are propagating across user namespaces */
|
|
if (m->mnt_ns->user_ns != user_ns)
|
|
type |= CL_UNPRIVILEGED;
|
|
child = copy_tree(last_source, last_source->mnt.mnt_root, type);
|
|
if (IS_ERR(child))
|
|
return PTR_ERR(child);
|
|
child->mnt.mnt_flags &= ~MNT_LOCKED;
|
|
mnt_set_mountpoint(m, mp, child);
|
|
last_dest = m;
|
|
last_source = child;
|
|
if (m->mnt_master != dest_master) {
|
|
read_seqlock_excl(&mount_lock);
|
|
SET_MNT_MARK(m->mnt_master);
|
|
read_sequnlock_excl(&mount_lock);
|
|
}
|
|
hlist_add_head(&child->mnt_hash, list);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
user_ns = current->nsproxy->mnt_ns->user_ns;
|
|
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;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Mark all mounts that the MNT_LOCKED logic will allow to be unmounted.
|
|
*/
|
|
static void mark_umount_candidates(struct mount *mnt)
|
|
{
|
|
struct mount *parent = mnt->mnt_parent;
|
|
struct mount *m;
|
|
|
|
BUG_ON(parent == mnt);
|
|
|
|
for (m = propagation_next(parent, parent); m;
|
|
m = propagation_next(m, parent)) {
|
|
struct mount *child = __lookup_mnt(&m->mnt,
|
|
mnt->mnt_mountpoint);
|
|
if (!child || (child->mnt.mnt_flags & MNT_UMOUNT))
|
|
continue;
|
|
if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) {
|
|
SET_MNT_MARK(child);
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* NOTE: unmounting 'mnt' naturally propagates to all other mounts its
|
|
* parent propagates to.
|
|
*/
|
|
static void __propagate_umount(struct mount *mnt)
|
|
{
|
|
struct mount *parent = mnt->mnt_parent;
|
|
struct mount *m;
|
|
|
|
BUG_ON(parent == mnt);
|
|
|
|
for (m = propagation_next(parent, parent); m;
|
|
m = propagation_next(m, parent)) {
|
|
struct mount *topper;
|
|
struct mount *child = __lookup_mnt(&m->mnt,
|
|
mnt->mnt_mountpoint);
|
|
/*
|
|
* umount the child only if the child has no children
|
|
* and the child is marked safe to unmount.
|
|
*/
|
|
if (!child || !IS_MNT_MARKED(child))
|
|
continue;
|
|
CLEAR_MNT_MARK(child);
|
|
|
|
/* If there is exactly one mount covering all of child
|
|
* replace child with that mount.
|
|
*/
|
|
topper = find_topper(child);
|
|
if (topper)
|
|
mnt_change_mountpoint(child->mnt_parent, child->mnt_mp,
|
|
topper);
|
|
|
|
if (list_empty(&child->mnt_mounts)) {
|
|
list_del_init(&child->mnt_child);
|
|
child->mnt.mnt_flags |= MNT_UMOUNT;
|
|
list_move_tail(&child->mnt_list, &mnt->mnt_list);
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* 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_for_each_entry_reverse(mnt, list, mnt_list)
|
|
mark_umount_candidates(mnt);
|
|
|
|
list_for_each_entry(mnt, list, mnt_list)
|
|
__propagate_umount(mnt);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Iterates over all slaves, and slaves of slaves.
|
|
*/
|
|
static struct mount *next_descendent(struct mount *root, struct mount *cur)
|
|
{
|
|
if (!IS_MNT_NEW(cur) && !list_empty(&cur->mnt_slave_list))
|
|
return first_slave(cur);
|
|
do {
|
|
if (cur->mnt_slave.next != &cur->mnt_master->mnt_slave_list)
|
|
return next_slave(cur);
|
|
cur = cur->mnt_master;
|
|
} while (cur != root);
|
|
return NULL;
|
|
}
|
|
|
|
void propagate_remount(struct mount *mnt)
|
|
{
|
|
struct mount *m = mnt;
|
|
struct super_block *sb = mnt->mnt.mnt_sb;
|
|
|
|
if (sb->s_op->copy_mnt_data) {
|
|
m = next_descendent(mnt, m);
|
|
while (m) {
|
|
sb->s_op->copy_mnt_data(m->mnt.data, mnt->mnt.data);
|
|
m = next_descendent(mnt, m);
|
|
}
|
|
}
|
|
}
|