+++ /dev/null
-From 839d42687dfce0ed0ea2c6bd8d707cc0e276fbe7 Mon Sep 17 00:00:00 2001
-From: "Eric W. Biederman" <ebiederm@xmission.com>
-Date: Fri, 20 Jan 2017 18:28:35 +1300
-Subject: [PATCH 013/251] mnt: Tuck mounts under others instead of creating
- shadow/side mounts.
-Status: RO
-Content-Length: 13585
-Lines: 423
-
-commit 1064f874abc0d05eeed8993815f584d847b72486 upstream.
-
-Ever since mount propagation was introduced in cases where a mount in
-propagated to parent mount mountpoint pair that is already in use the
-code has placed the new mount behind the old mount in the mount hash
-table.
-
-This implementation detail is problematic as it allows creating
-arbitrary length mount hash chains.
-
-Furthermore it invalidates the constraint maintained elsewhere in the
-mount code that a parent mount and a mountpoint pair will have exactly
-one mount upon them. Making it hard to deal with and to talk about
-this special case in the mount code.
-
-Modify mount propagation to notice when there is already a mount at
-the parent mount and mountpoint where a new mount is propagating to
-and place that preexisting mount on top of the new mount.
-
-Modify unmount propagation to notice when a mount that is being
-unmounted has another mount on top of it (and no other children), and
-to replace the unmounted mount with the mount on top of it.
-
-Move the MNT_UMUONT test from __lookup_mnt_last into
-__propagate_umount as that is the only call of __lookup_mnt_last where
-MNT_UMOUNT may be set on any mount visible in the mount hash table.
-
-These modifications allow:
- - __lookup_mnt_last to be removed.
- - attach_shadows to be renamed __attach_mnt and its shadow
- handling to be removed.
- - commit_tree to be simplified
- - copy_tree to be simplified
-
-The result is an easier to understand tree of mounts that does not
-allow creation of arbitrary length hash chains in the mount hash table.
-
-The result is also a very slight userspace visible difference in semantics.
-The following two cases now behave identically, where before order
-mattered:
-
-case 1: (explicit user action)
- B is a slave of A
- mount something on A/a , it will propagate to B/a
- and than mount something on B/a
-
-case 2: (tucked mount)
- B is a slave of A
- mount something on B/a
- and than mount something on A/a
-
-Histroically umount A/a would fail in case 1 and succeed in case 2.
-Now umount A/a succeeds in both configurations.
-
-This very small change in semantics appears if anything to be a bug
-fix to me and my survey of userspace leads me to believe that no programs
-will notice or care of this subtle semantic change.
-
-v2: Updated to mnt_change_mountpoint to not call dput or mntput
-and instead to decrement the counts directly. It is guaranteed
-that there will be other references when mnt_change_mountpoint is
-called so this is safe.
-
-v3: Moved put_mountpoint under mount_lock in attach_recursive_mnt
- As the locking in fs/namespace.c changed between v2 and v3.
-
-v4: Reworked the logic in propagate_mount_busy and __propagate_umount
- that detects when a mount completely covers another mount.
-
-v5: Removed unnecessary tests whose result is alwasy true in
- find_topper and attach_recursive_mnt.
-
-v6: Document the user space visible semantic difference.
-
-Fixes: b90fa9ae8f51 ("[PATCH] shared mount handling: bind and rbind")
-Tested-by: Andrei Vagin <avagin@virtuozzo.com>
-Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
-Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
----
- fs/mount.h | 1 -
- fs/namespace.c | 109 +++++++++++++++++++++++++++++++--------------------------
- fs/pnode.c | 61 +++++++++++++++++++++++++-------
- fs/pnode.h | 2 ++
- 4 files changed, 110 insertions(+), 63 deletions(-)
-
-diff --git a/fs/mount.h b/fs/mount.h
-index 14db05d424f7..3dc7dea5a357 100644
---- a/fs/mount.h
-+++ b/fs/mount.h
-@@ -86,7 +86,6 @@ static inline int is_mounted(struct vfsmount *mnt)
- }
-
- extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *);
--extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *);
-
- extern int __legitimize_mnt(struct vfsmount *, unsigned);
- extern bool legitimize_mnt(struct vfsmount *, unsigned);
-diff --git a/fs/namespace.c b/fs/namespace.c
-index da98a1bbd8b5..7df3d406d3e0 100644
---- a/fs/namespace.c
-+++ b/fs/namespace.c
-@@ -638,28 +638,6 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
- }
-
- /*
-- * find the last mount at @dentry on vfsmount @mnt.
-- * mount_lock must be held.
-- */
--struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
--{
-- struct mount *p, *res = NULL;
-- p = __lookup_mnt(mnt, dentry);
-- if (!p)
-- goto out;
-- if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-- res = p;
-- hlist_for_each_entry_continue(p, mnt_hash) {
-- if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry)
-- break;
-- if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-- res = p;
-- }
--out:
-- return res;
--}
--
--/*
- * lookup_mnt - Return the first child mount mounted at path
- *
- * "First" means first mounted chronologically. If you create the
-@@ -879,6 +857,13 @@ void mnt_set_mountpoint(struct mount *mnt,
- hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
- }
-
-+static void __attach_mnt(struct mount *mnt, struct mount *parent)
-+{
-+ hlist_add_head_rcu(&mnt->mnt_hash,
-+ m_hash(&parent->mnt, mnt->mnt_mountpoint));
-+ list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
-+}
-+
- /*
- * vfsmount lock must be held for write
- */
-@@ -887,28 +872,45 @@ static void attach_mnt(struct mount *mnt,
- struct mountpoint *mp)
- {
- mnt_set_mountpoint(parent, mp, mnt);
-- hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry));
-- list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
-+ __attach_mnt(mnt, parent);
- }
-
--static void attach_shadowed(struct mount *mnt,
-- struct mount *parent,
-- struct mount *shadows)
-+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt)
- {
-- if (shadows) {
-- hlist_add_behind_rcu(&mnt->mnt_hash, &shadows->mnt_hash);
-- list_add(&mnt->mnt_child, &shadows->mnt_child);
-- } else {
-- hlist_add_head_rcu(&mnt->mnt_hash,
-- m_hash(&parent->mnt, mnt->mnt_mountpoint));
-- list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
-- }
-+ struct mountpoint *old_mp = mnt->mnt_mp;
-+ struct dentry *old_mountpoint = mnt->mnt_mountpoint;
-+ struct mount *old_parent = mnt->mnt_parent;
-+
-+ list_del_init(&mnt->mnt_child);
-+ hlist_del_init(&mnt->mnt_mp_list);
-+ hlist_del_init_rcu(&mnt->mnt_hash);
-+
-+ attach_mnt(mnt, parent, mp);
-+
-+ put_mountpoint(old_mp);
-+
-+ /*
-+ * Safely avoid even the suggestion this code might sleep or
-+ * lock the mount hash by taking advantage of the knowledge that
-+ * mnt_change_mountpoint will not release the final reference
-+ * to a mountpoint.
-+ *
-+ * During mounting, the mount passed in as the parent mount will
-+ * continue to use the old mountpoint and during unmounting, the
-+ * old mountpoint will continue to exist until namespace_unlock,
-+ * which happens well after mnt_change_mountpoint.
-+ */
-+ spin_lock(&old_mountpoint->d_lock);
-+ old_mountpoint->d_lockref.count--;
-+ spin_unlock(&old_mountpoint->d_lock);
-+
-+ mnt_add_count(old_parent, -1);
- }
-
- /*
- * vfsmount lock must be held for write
- */
--static void commit_tree(struct mount *mnt, struct mount *shadows)
-+static void commit_tree(struct mount *mnt)
- {
- struct mount *parent = mnt->mnt_parent;
- struct mount *m;
-@@ -923,7 +925,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows)
-
- list_splice(&head, n->list.prev);
-
-- attach_shadowed(mnt, parent, shadows);
-+ __attach_mnt(mnt, parent);
- touch_mnt_namespace(n);
- }
-
-@@ -1718,7 +1720,6 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
- continue;
-
- for (s = r; s; s = next_mnt(s, r)) {
-- struct mount *t = NULL;
- if (!(flag & CL_COPY_UNBINDABLE) &&
- IS_MNT_UNBINDABLE(s)) {
- s = skip_mnt_tree(s);
-@@ -1740,14 +1741,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
- goto out;
- lock_mount_hash();
- list_add_tail(&q->mnt_list, &res->mnt_list);
-- mnt_set_mountpoint(parent, p->mnt_mp, q);
-- if (!list_empty(&parent->mnt_mounts)) {
-- t = list_last_entry(&parent->mnt_mounts,
-- struct mount, mnt_child);
-- if (t->mnt_mp != p->mnt_mp)
-- t = NULL;
-- }
-- attach_shadowed(q, parent, t);
-+ attach_mnt(q, parent, p->mnt_mp);
- unlock_mount_hash();
- }
- }
-@@ -1925,10 +1919,18 @@ static int attach_recursive_mnt(struct mount *source_mnt,
- struct path *parent_path)
- {
- HLIST_HEAD(tree_list);
-+ struct mountpoint *smp;
- struct mount *child, *p;
- struct hlist_node *n;
- int err;
-
-+ /* Preallocate a mountpoint in case the new mounts need
-+ * to be tucked under other mounts.
-+ */
-+ smp = get_mountpoint(source_mnt->mnt.mnt_root);
-+ if (IS_ERR(smp))
-+ return PTR_ERR(smp);
-+
- if (IS_MNT_SHARED(dest_mnt)) {
- err = invent_group_ids(source_mnt, true);
- if (err)
-@@ -1948,16 +1950,19 @@ static int attach_recursive_mnt(struct mount *source_mnt,
- touch_mnt_namespace(source_mnt->mnt_ns);
- } else {
- mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
-- commit_tree(source_mnt, NULL);
-+ commit_tree(source_mnt);
- }
-
- hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
- struct mount *q;
- hlist_del_init(&child->mnt_hash);
-- q = __lookup_mnt_last(&child->mnt_parent->mnt,
-- child->mnt_mountpoint);
-- commit_tree(child, q);
-+ q = __lookup_mnt(&child->mnt_parent->mnt,
-+ child->mnt_mountpoint);
-+ if (q)
-+ mnt_change_mountpoint(child, smp, q);
-+ commit_tree(child);
- }
-+ put_mountpoint(smp);
- unlock_mount_hash();
-
- return 0;
-@@ -1970,6 +1975,10 @@ static int attach_recursive_mnt(struct mount *source_mnt,
- unlock_mount_hash();
- cleanup_group_ids(source_mnt, NULL);
- out:
-+ read_seqlock_excl(&mount_lock);
-+ put_mountpoint(smp);
-+ read_sequnlock_excl(&mount_lock);
-+
- return err;
- }
-
-diff --git a/fs/pnode.c b/fs/pnode.c
-index 99899705b105..b9f2af59b9a6 100644
---- a/fs/pnode.c
-+++ b/fs/pnode.c
-@@ -324,6 +324,21 @@ out:
- 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
- */
-@@ -344,9 +359,8 @@ static inline int do_refcount_check(struct mount *mnt, int count)
- */
- int propagate_mount_busy(struct mount *mnt, int refcnt)
- {
-- struct mount *m, *child;
-+ struct mount *m, *child, *topper;
- struct mount *parent = mnt->mnt_parent;
-- int ret = 0;
-
- if (mnt == parent)
- return do_refcount_check(mnt, refcnt);
-@@ -361,12 +375,24 @@ int propagate_mount_busy(struct mount *mnt, int refcnt)
-
- for (m = propagation_next(parent, parent); m;
- m = propagation_next(m, parent)) {
-- child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint);
-- if (child && list_empty(&child->mnt_mounts) &&
-- (ret = do_refcount_check(child, 1)))
-- break;
-+ 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 ret;
-+ return 0;
- }
-
- /*
-@@ -383,7 +409,7 @@ void propagate_mount_unlock(struct mount *mnt)
-
- for (m = propagation_next(parent, parent); m;
- m = propagation_next(m, parent)) {
-- child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint);
-+ child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
- if (child)
- child->mnt.mnt_flags &= ~MNT_LOCKED;
- }
-@@ -401,9 +427,11 @@ static void mark_umount_candidates(struct mount *mnt)
-
- for (m = propagation_next(parent, parent); m;
- m = propagation_next(m, parent)) {
-- struct mount *child = __lookup_mnt_last(&m->mnt,
-+ struct mount *child = __lookup_mnt(&m->mnt,
- mnt->mnt_mountpoint);
-- if (child && (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m))) {
-+ if (!child || (child->mnt.mnt_flags & MNT_UMOUNT))
-+ continue;
-+ if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) {
- SET_MNT_MARK(child);
- }
- }
-@@ -422,8 +450,8 @@ static void __propagate_umount(struct mount *mnt)
-
- for (m = propagation_next(parent, parent); m;
- m = propagation_next(m, parent)) {
--
-- struct mount *child = __lookup_mnt_last(&m->mnt,
-+ struct mount *topper;
-+ struct mount *child = __lookup_mnt(&m->mnt,
- mnt->mnt_mountpoint);
- /*
- * umount the child only if the child has no children
-@@ -432,6 +460,15 @@ static void __propagate_umount(struct mount *mnt)
- 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;
-diff --git a/fs/pnode.h b/fs/pnode.h
-index 0fcdbe7ca648..623f01772bec 100644
---- a/fs/pnode.h
-+++ b/fs/pnode.h
-@@ -49,6 +49,8 @@ int get_dominating_id(struct mount *mnt, const struct path *root);
- unsigned int mnt_get_count(struct mount *mnt);
- void mnt_set_mountpoint(struct mount *, struct mountpoint *,
- struct mount *);
-+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp,
-+ struct mount *mnt);
- struct mount *copy_tree(struct mount *, struct dentry *, int);
- bool is_path_reachable(struct mount *, struct dentry *,
- const struct path *root);
---
-2.12.2
-
-From ba46d8fab00a8e1538df241681d9161c8ec85778 Mon Sep 17 00:00:00 2001
-From: Ilya Dryomov <idryomov@gmail.com>
-Date: Tue, 21 Mar 2017 13:44:28 +0100
-Subject: [PATCH 225/251] libceph: force GFP_NOIO for socket allocations
-Status: RO
-Content-Length: 4579
-Lines: 104
-
-commit 633ee407b9d15a75ac9740ba9d3338815e1fcb95 upstream.
-
-sock_alloc_inode() allocates socket+inode and socket_wq with
-GFP_KERNEL, which is not allowed on the writeback path:
-
- Workqueue: ceph-msgr con_work [libceph]
- ffff8810871cb018 0000000000000046 0000000000000000 ffff881085d40000
- 0000000000012b00 ffff881025cad428 ffff8810871cbfd8 0000000000012b00
- ffff880102fc1000 ffff881085d40000 ffff8810871cb038 ffff8810871cb148
- Call Trace:
- [<ffffffff816dd629>] schedule+0x29/0x70
- [<ffffffff816e066d>] schedule_timeout+0x1bd/0x200
- [<ffffffff81093ffc>] ? ttwu_do_wakeup+0x2c/0x120
- [<ffffffff81094266>] ? ttwu_do_activate.constprop.135+0x66/0x70
- [<ffffffff816deb5f>] wait_for_completion+0xbf/0x180
- [<ffffffff81097cd0>] ? try_to_wake_up+0x390/0x390
- [<ffffffff81086335>] flush_work+0x165/0x250
- [<ffffffff81082940>] ? worker_detach_from_pool+0xd0/0xd0
- [<ffffffffa03b65b1>] xlog_cil_force_lsn+0x81/0x200 [xfs]
- [<ffffffff816d6b42>] ? __slab_free+0xee/0x234
- [<ffffffffa03b4b1d>] _xfs_log_force_lsn+0x4d/0x2c0 [xfs]
- [<ffffffff811adc1e>] ? lookup_page_cgroup_used+0xe/0x30
- [<ffffffffa039a723>] ? xfs_reclaim_inode+0xa3/0x330 [xfs]
- [<ffffffffa03b4dcf>] xfs_log_force_lsn+0x3f/0xf0 [xfs]
- [<ffffffffa039a723>] ? xfs_reclaim_inode+0xa3/0x330 [xfs]
- [<ffffffffa03a62c6>] xfs_iunpin_wait+0xc6/0x1a0 [xfs]
- [<ffffffff810aa250>] ? wake_atomic_t_function+0x40/0x40
- [<ffffffffa039a723>] xfs_reclaim_inode+0xa3/0x330 [xfs]
- [<ffffffffa039ac07>] xfs_reclaim_inodes_ag+0x257/0x3d0 [xfs]
- [<ffffffffa039bb13>] xfs_reclaim_inodes_nr+0x33/0x40 [xfs]
- [<ffffffffa03ab745>] xfs_fs_free_cached_objects+0x15/0x20 [xfs]
- [<ffffffff811c0c18>] super_cache_scan+0x178/0x180
- [<ffffffff8115912e>] shrink_slab_node+0x14e/0x340
- [<ffffffff811afc3b>] ? mem_cgroup_iter+0x16b/0x450
- [<ffffffff8115af70>] shrink_slab+0x100/0x140
- [<ffffffff8115e425>] do_try_to_free_pages+0x335/0x490
- [<ffffffff8115e7f9>] try_to_free_pages+0xb9/0x1f0
- [<ffffffff816d56e4>] ? __alloc_pages_direct_compact+0x69/0x1be
- [<ffffffff81150cba>] __alloc_pages_nodemask+0x69a/0xb40
- [<ffffffff8119743e>] alloc_pages_current+0x9e/0x110
- [<ffffffff811a0ac5>] new_slab+0x2c5/0x390
- [<ffffffff816d71c4>] __slab_alloc+0x33b/0x459
- [<ffffffff815b906d>] ? sock_alloc_inode+0x2d/0xd0
- [<ffffffff8164bda1>] ? inet_sendmsg+0x71/0xc0
- [<ffffffff815b906d>] ? sock_alloc_inode+0x2d/0xd0
- [<ffffffff811a21f2>] kmem_cache_alloc+0x1a2/0x1b0
- [<ffffffff815b906d>] sock_alloc_inode+0x2d/0xd0
- [<ffffffff811d8566>] alloc_inode+0x26/0xa0
- [<ffffffff811da04a>] new_inode_pseudo+0x1a/0x70
- [<ffffffff815b933e>] sock_alloc+0x1e/0x80
- [<ffffffff815ba855>] __sock_create+0x95/0x220
- [<ffffffff815baa04>] sock_create_kern+0x24/0x30
- [<ffffffffa04794d9>] con_work+0xef9/0x2050 [libceph]
- [<ffffffffa04aa9ec>] ? rbd_img_request_submit+0x4c/0x60 [rbd]
- [<ffffffff81084c19>] process_one_work+0x159/0x4f0
- [<ffffffff8108561b>] worker_thread+0x11b/0x530
- [<ffffffff81085500>] ? create_worker+0x1d0/0x1d0
- [<ffffffff8108b6f9>] kthread+0xc9/0xe0
- [<ffffffff8108b630>] ? flush_kthread_worker+0x90/0x90
- [<ffffffff816e1b98>] ret_from_fork+0x58/0x90
- [<ffffffff8108b630>] ? flush_kthread_worker+0x90/0x90
-
-Use memalloc_noio_{save,restore}() to temporarily force GFP_NOIO here.
-
-Link: http://tracker.ceph.com/issues/19309
-Reported-by: Sergey Jerusalimov <wintchester@gmail.com>
-Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
-Reviewed-by: Jeff Layton <jlayton@redhat.com>
-Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
----
- net/ceph/messenger.c | 6 ++++++
- 1 file changed, 6 insertions(+)
-
-diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
-index b8d927c56494..a6b2f2138c9d 100644
---- a/net/ceph/messenger.c
-+++ b/net/ceph/messenger.c
-@@ -7,6 +7,7 @@
- #include <linux/kthread.h>
- #include <linux/net.h>
- #include <linux/nsproxy.h>
-+#include <linux/sched.h>
- #include <linux/slab.h>
- #include <linux/socket.h>
- #include <linux/string.h>
-@@ -478,11 +479,16 @@ static int ceph_tcp_connect(struct ceph_connection *con)
- {
- struct sockaddr_storage *paddr = &con->peer_addr.in_addr;
- struct socket *sock;
-+ unsigned int noio_flag;
- int ret;
-
- BUG_ON(con->sock);
-+
-+ /* sock_create_kern() allocates with GFP_KERNEL */
-+ noio_flag = memalloc_noio_save();
- ret = sock_create_kern(read_pnet(&con->msgr->net), paddr->ss_family,
- SOCK_STREAM, IPPROTO_TCP, &sock);
-+ memalloc_noio_restore(noio_flag);
- if (ret)
- return ret;
- sock->sk->sk_allocation = GFP_NOFS;
---
-2.12.2
-
projects / thirdparty / kernel / stable-queue.git / commitdiff
