So far we just relied on block device to hold a bdi reference for us
while the filesystem is mounted. While that works perfectly fine, it is
a bit awkward that we have a pointer to a refcounted structure in the
superblock without proper reference. So make s_bdi hold a proper
reference to block device's BDI. No filesystem using mount_bdev()
actually changes s_bdi so this is safe and will make bdev filesystems
work the same way as filesystems needing to set up their private bdi.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
Pull namespace updates from Eric Biederman:
"There is a lot here. A lot of these changes result in subtle user
visible differences in kernel behavior. I don't expect anything will
care but I will revert/fix things immediately if any regressions show
up.
From Seth Forshee there is a continuation of the work to make the vfs
ready for unpriviled mounts. We had thought the previous changes
prevented the creation of files outside of s_user_ns of a filesystem,
but it turns we missed the O_CREAT path. Ooops.
Pavel Tikhomirov and Oleg Nesterov worked together to fix a long
standing bug in the implemenation of PR_SET_CHILD_SUBREAPER where only
children that are forked after the prctl are considered and not
children forked before the prctl. The only known user of this prctl
systemd forks all children after the prctl. So no userspace
regressions will occur. Holding earlier forked children to the same
rules as later forked children creates a semantic that is sane enough
to allow checkpoing of processes that use this feature.
There is a long delayed change by Nikolay Borisov to limit inotify
instances inside a user namespace.
Michael Kerrisk extends the API for files used to maniuplate
namespaces with two new trivial ioctls to allow discovery of the
hierachy and properties of namespaces.
Konstantin Khlebnikov with the help of Al Viro adds code that when a
network namespace exits purges it's sysctl entries from the dcache. As
in some circumstances this could use a lot of memory.
Vivek Goyal fixed a bug with stacked filesystems where the permissions
on the wrong inode were being checked.
I continue previous work on ptracing across exec. Allowing a file to
be setuid across exec while being ptraced if the tracer has enough
credentials in the user namespace, and if the process has CAP_SETUID
in it's own namespace. Proc files for setuid or otherwise undumpable
executables are now owned by the root in the user namespace of their
mm. Allowing debugging of setuid applications in containers to work
better.
A bug I introduced with permission checking and automount is now
fixed. The big change is to mark the mounts that the kernel initiates
as a result of an automount. This allows the permission checks in sget
to be safely suppressed for this kind of mount. As the permission
check happened when the original filesystem was mounted.
Finally a special case in the mount namespace is removed preventing
unbounded chains in the mount hash table, and making the semantics
simpler which benefits CRIU.
The vfs fix along with related work in ima and evm I believe makes us
ready to finish developing and merge fully unprivileged mounts of the
fuse filesystem. The cleanups of the mount namespace makes discussing
how to fix the worst case complexity of umount. The stacked filesystem
fixes pave the way for adding multiple mappings for the filesystem
uids so that efficient and safer containers can be implemented"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
proc/sysctl: Don't grab i_lock under sysctl_lock.
vfs: Use upper filesystem inode in bprm_fill_uid()
proc/sysctl: prune stale dentries during unregistering
mnt: Tuck mounts under others instead of creating shadow/side mounts.
prctl: propagate has_child_subreaper flag to every descendant
introduce the walk_process_tree() helper
nsfs: Add an ioctl() to return owner UID of a userns
fs: Better permission checking for submounts
exit: fix the setns() && PR_SET_CHILD_SUBREAPER interaction
vfs: open() with O_CREAT should not create inodes with unknown ids
nsfs: Add an ioctl() to return the namespace type
proc: Better ownership of files for non-dumpable tasks in user namespaces
exec: Remove LSM_UNSAFE_PTRACE_CAP
exec: Test the ptracer's saved cred to see if the tracee can gain caps
exec: Don't reset euid and egid when the tracee has CAP_SETUID
inotify: Convert to using per-namespace limits
We will want to have struct backing_dev_info allocated separately from
struct request_queue. As the first step add pointer to backing_dev_info
to request_queue and convert all users touching it. No functional
changes in this patch.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
To support unprivileged users mounting filesystems two permission
checks have to be performed: a test to see if the user allowed to
create a mount in the mount namespace, and a test to see if
the user is allowed to access the specified filesystem.
The automount case is special in that mounting the original filesystem
grants permission to mount the sub-filesystems, to any user who
happens to stumble across the their mountpoint and satisfies the
ordinary filesystem permission checks.
Attempting to handle the automount case by using override_creds
almost works. It preserves the idea that permission to mount
the original filesystem is permission to mount the sub-filesystem.
Unfortunately using override_creds messes up the filesystems
ordinary permission checks.
Solve this by being explicit that a mount is a submount by introducing
vfs_submount, and using it where appropriate.
vfs_submount uses a new mount internal mount flags MS_SUBMOUNT, to let
sget and friends know that a mount is a submount so they can take appropriate
action.
sget and sget_userns are modified to not perform any permission checks
on submounts.
follow_automount is modified to stop using override_creds as that
has proven problemantic.
do_mount is modified to always remove the new MS_SUBMOUNT flag so
that we know userspace will never by able to specify it.
autofs4 is modified to stop using current_real_cred that was put in
there to handle the previous version of submount permission checking.
cifs is modified to pass the mountpoint all of the way down to vfs_submount.
debugfs is modified to pass the mountpoint all of the way down to
trace_automount by adding a new parameter. To make this change easier
a new typedef debugfs_automount_t is introduced to capture the type of
the debugfs automount function.
Cc: stable@vger.kernel.org
Fixes: 069d5ac9ae ("autofs: Fix automounts by using current_real_cred()->uid")
Fixes: aeaa4a79ff ("fs: Call d_automount with the filesystems creds")
Reviewed-by: Trond Myklebust <trond.myklebust@primarydata.com>
Reviewed-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
The only places that were grabbing dqonoff_mutex are functions turning
quotas on and off and these are properly serialized using s_umount
semaphore. Remove dqonoff_mutex.
Signed-off-by: Jan Kara <jack@suse.cz>
Quota code will need a variant of get_super_thawed() that returns
superblock with s_umount held in exclusive mode to serialize quota on
and quota off operations. Provide this functionality.
Signed-off-by: Jan Kara <jack@suse.cz>
sb_wait_write()->percpu_rwsem_release() fools lockdep to avoid the
false-positives. Now that xfs was fixed by Dave's commit dbad7c9930
("xfs: stop holding ILOCK over filldir callbacks") we can remove it and
change freeze_super() and thaw_super() to run with s_writers.rw_sem locks
held; we add two trivial helpers for that, lockdep_sb_freeze_release()
and lockdep_sb_freeze_acquire().
xfstests-dev/check `grep -il freeze tests/*/???` does not trigger any
warning from lockdep.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Change thaw_super() to check frozen != SB_FREEZE_COMPLETE rather than
frozen == SB_UNFROZEN, otherwise it can race with freeze_super() which
drops sb->s_umount after SB_FREEZE_WRITE to preserve the lock ordering.
In this case thaw_super() will wrongly call s_op->unfreeze_fs() before
it was actually frozen, and call sb_freeze_unlock() which leads to the
unbalanced percpu_up_write(). Unfortunately lockdep can't detect this,
so this triggers misc BUG_ON()'s in kernel/rcu/sync.c.
Reported-and-tested-by: Nikolay Borisov <kernel@kyup.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Pull userns vfs updates from Eric Biederman:
"This tree contains some very long awaited work on generalizing the
user namespace support for mounting filesystems to include filesystems
with a backing store. The real world target is fuse but the goal is
to update the vfs to allow any filesystem to be supported. This
patchset is based on a lot of code review and testing to approach that
goal.
While looking at what is needed to support the fuse filesystem it
became clear that there were things like xattrs for security modules
that needed special treatment. That the resolution of those concerns
would not be fuse specific. That sorting out these general issues
made most sense at the generic level, where the right people could be
drawn into the conversation, and the issues could be solved for
everyone.
At a high level what this patchset does a couple of simple things:
- Add a user namespace owner (s_user_ns) to struct super_block.
- Teach the vfs to handle filesystem uids and gids not mapping into
to kuids and kgids and being reported as INVALID_UID and
INVALID_GID in vfs data structures.
By assigning a user namespace owner filesystems that are mounted with
only user namespace privilege can be detected. This allows security
modules and the like to know which mounts may not be trusted. This
also allows the set of uids and gids that are communicated to the
filesystem to be capped at the set of kuids and kgids that are in the
owning user namespace of the filesystem.
One of the crazier corner casees this handles is the case of inodes
whose i_uid or i_gid are not mapped into the vfs. Most of the code
simply doesn't care but it is easy to confuse the inode writeback path
so no operation that could cause an inode write-back is permitted for
such inodes (aka only reads are allowed).
This set of changes starts out by cleaning up the code paths involved
in user namespace permirted mounts. Then when things are clean enough
adds code that cleanly sets s_user_ns. Then additional restrictions
are added that are possible now that the filesystem superblock
contains owner information.
These changes should not affect anyone in practice, but there are some
parts of these restrictions that are changes in behavior.
- Andy's restriction on suid executables that does not honor the
suid bit when the path is from another mount namespace (think
/proc/[pid]/fd/) or when the filesystem was mounted by a less
privileged user.
- The replacement of the user namespace implicit setting of MNT_NODEV
with implicitly setting SB_I_NODEV on the filesystem superblock
instead.
Using SB_I_NODEV is a stronger form that happens to make this state
user invisible. The user visibility can be managed but it caused
problems when it was introduced from applications reasonably
expecting mount flags to be what they were set to.
There is a little bit of work remaining before it is safe to support
mounting filesystems with backing store in user namespaces, beyond
what is in this set of changes.
- Verifying the mounter has permission to read/write the block device
during mount.
- Teaching the integrity modules IMA and EVM to handle filesystems
mounted with only user namespace root and to reduce trust in their
security xattrs accordingly.
- Capturing the mounters credentials and using that for permission
checks in d_automount and the like. (Given that overlayfs already
does this, and we need the work in d_automount it make sense to
generalize this case).
Furthermore there are a few changes that are on the wishlist:
- Get all filesystems supporting posix acls using the generic posix
acls so that posix_acl_fix_xattr_from_user and
posix_acl_fix_xattr_to_user may be removed. [Maintainability]
- Reducing the permission checks in places such as remount to allow
the superblock owner to perform them.
- Allowing the superblock owner to chown files with unmapped uids and
gids to something that is mapped so the files may be treated
normally.
I am not considering even obvious relaxations of permission checks
until it is clear there are no more corner cases that need to be
locked down and handled generically.
Many thanks to Seth Forshee who kept this code alive, and putting up
with me rewriting substantial portions of what he did to handle more
corner cases, and for his diligent testing and reviewing of my
changes"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (30 commits)
fs: Call d_automount with the filesystems creds
fs: Update i_[ug]id_(read|write) to translate relative to s_user_ns
evm: Translate user/group ids relative to s_user_ns when computing HMAC
dquot: For now explicitly don't support filesystems outside of init_user_ns
quota: Handle quota data stored in s_user_ns in quota_setxquota
quota: Ensure qids map to the filesystem
vfs: Don't create inodes with a uid or gid unknown to the vfs
vfs: Don't modify inodes with a uid or gid unknown to the vfs
cred: Reject inodes with invalid ids in set_create_file_as()
fs: Check for invalid i_uid in may_follow_link()
vfs: Verify acls are valid within superblock's s_user_ns.
userns: Handle -1 in k[ug]id_has_mapping when !CONFIG_USER_NS
fs: Refuse uid/gid changes which don't map into s_user_ns
selinux: Add support for unprivileged mounts from user namespaces
Smack: Handle labels consistently in untrusted mounts
Smack: Add support for unprivileged mounts from user namespaces
fs: Treat foreign mounts as nosuid
fs: Limit file caps to the user namespace of the super block
userns: Remove the now unnecessary FS_USERNS_DEV_MOUNT flag
userns: Remove implicit MNT_NODEV fragility.
...
wait_sb_inodes() currently does a walk of all inodes in the filesystem
to find dirty one to wait on during sync. This is highly inefficient
and wastes a lot of CPU when there are lots of clean cached inodes that
we don't need to wait on.
To avoid this "all inode" walk, we need to track inodes that are
currently under writeback that we need to wait for. We do this by
adding inodes to a writeback list on the sb when the mapping is first
tagged as having pages under writeback. wait_sb_inodes() can then walk
this list of "inodes under IO" and wait specifically just for the inodes
that the current sync(2) needs to wait for.
Define a couple helpers to add/remove an inode from the writeback list
and call them when the overall mapping is tagged for or cleared from
writeback. Update wait_sb_inodes() to walk only the inodes under
writeback due to the sync.
With this change, filesystem sync times are significantly reduced for
fs' with largely populated inode caches and otherwise no other work to
do. For example, on a 16xcpu 2GHz x86-64 server, 10TB XFS filesystem
with a ~10m entry inode cache, sync times are reduced from ~7.3s to less
than 0.1s when the filesystem is fully clean.
Link: http://lkml.kernel.org/r/1466594593-6757-2-git-send-email-bfoster@redhat.com
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Tested-by: Holger Hoffstätte <holger.hoffstaette@applied-asynchrony.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Now that SB_I_NODEV controls the nodev behavior devpts can just clear
this flag during mount. Simplifying the code and making it easier
to audit how the code works. While still preserving the invariant
that s_iflags is only modified during mount.
Acked-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Replace the implict setting of MNT_NODEV on mounts that happen with
just user namespace permissions with an implicit setting of SB_I_NODEV
in s_iflags. The visibility of the implicit MNT_NODEV has caused
problems in the past.
With this change the fragile case where an implicit MNT_NODEV needs to
be preserved in do_remount is removed. Using SB_I_NODEV is much less
fragile as s_iflags are set during the original mount and never
changed.
In do_new_mount with the implicit setting of MNT_NODEV gone, the only
code that can affect mnt_flags is fs_fully_visible so simplify the if
statement and reduce the indentation of the code to make that clear.
Acked-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Allowing a filesystem to be mounted by other than root in the initial
user namespace is a filesystem property not a mount namespace property
and as such should be checked in filesystem specific code. Move the
FS_USERNS_MOUNT test into super.c:sget_userns().
Acked-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Start marking filesystems with a user namespace owner, s_user_ns. In
this change this is only used for permission checks of who may mount a
filesystem. Ultimately s_user_ns will be used for translating ids and
checking capabilities for filesystems mounted from user namespaces.
The default policy for setting s_user_ns is implemented in sget(),
which arranges for s_user_ns to be set to current_user_ns() and to
ensure that the mounter of the filesystem has CAP_SYS_ADMIN in that
user_ns.
The guts of sget are split out into another function sget_userns().
The function sget_userns calls alloc_super with the specified user
namespace or it verifies the existing superblock that was found
has the expected user namespace, and fails with EBUSY when it is not.
This failing prevents users with the wrong privileges mounting a
filesystem.
The reason for the split of sget_userns from sget is that in some
cases such as mount_ns and kernfs_mount_ns a different policy for
permission checking of mounts and setting s_user_ns is necessary, and
the existence of sget_userns() allows those policies to be
implemented.
The helper mount_ns is expected to be used for filesystems such as
proc and mqueuefs which present per namespace information. The
function mount_ns is modified to call sget_userns instead of sget to
ensure the user namespace owner of the namespace whose information is
presented by the filesystem is used on the superblock.
For sysfs and cgroup the appropriate permission checks are already in
place, and kernfs_mount_ns is modified to call sget_userns so that
the init_user_ns is the only user namespace used.
For the cgroup filesystem cgroup namespace mounts are bind mounts of a
subset of the full cgroup filesystem and as such s_user_ns must be the
same for all of them as there is only a single superblock.
Mounts of sysfs that vary based on the network namespace could in principle
change s_user_ns but it keeps the analysis and implementation of kernfs
simpler if that is not supported, and at present there appear to be no
benefits from supporting a different s_user_ns on any sysfs mount.
Getting the details of setting s_user_ns correct has been
a long process. Thanks to Pavel Tikhorirorv who spotted a leak
in sget_userns. Thanks to Seth Forshee who has kept the work alive.
Thanks-to: Seth Forshee <seth.forshee@canonical.com>
Thanks-to: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Acked-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Today what is normally called data (the mount options) is not passed
to fill_super through mount_ns.
Pass the mount options and the namespace separately to mount_ns so
that filesystems such as proc that have mount options, can use
mount_ns.
Pass the user namespace to mount_ns so that the standard permission
check that verifies the mounter has permissions over the namespace can
be performed in mount_ns instead of in each filesystems .mount method.
Thus removing the duplication between mqueuefs and proc in terms of
permission checks. The extra permission check does not currently
affect the rpc_pipefs filesystem and the nfsd filesystem as those
filesystems do not currently allow unprivileged mounts. Without
unpvileged mounts it is guaranteed that the caller has already passed
capable(CAP_SYS_ADMIN) which guarantees extra permission check will
pass.
Update rpc_pipefs and the nfsd filesystem to ensure that the network
namespace reference is always taken in fill_super and always put in kill_sb
so that the logic is simpler and so that errors originating inside of
fill_super do not cause a network namespace leak.
Acked-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
This patch fix spelling typos found in DocBook/filesystem.xml.
It is because the file was generated from comments in code,
I have to fix the comments in codes, instead of xml file.
Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
If cgroup writeback is in use, inodes can be scheduled for
asynchronous wb switching. Before 5ff8eaac16 ("writeback: keep
superblock pinned during cgroup writeback association switches"), this
could race with umount leading to super_block being destroyed while
inodes are pinned for wb switching. 5ff8eaac16 fixed it by bumping
s_active while wb switches are in flight; however, this allowed
in-flight wb switches to make umounts asynchronous when the userland
expected synchronosity - e.g. fsck immediately following umount may
fail because the device is still busy.
This patch removes the problematic super_block pinning and instead
makes generic_shutdown_super() flush in-flight wb switches. wb
switches are now executed on a dedicated isw_wq so that they can be
flushed and isw_nr_in_flight keeps track of the number of in-flight wb
switches so that flushing can be avoided in most cases.
v2: Move cgroup_writeback_umount() further below and add MS_ACTIVE
check in inode_switch_wbs() as Jan an Al suggested.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Tahsin Erdogan <tahsin@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Link: http://lkml.kernel.org/g/CAAeU0aNCq7LGODvVGRU-oU_o-6enii5ey0p1c26D1ZzYwkDc5A@mail.gmail.com
Fixes: 5ff8eaac16 ("writeback: keep superblock pinned during cgroup writeback association switches")
Cc: stable@vger.kernel.org #v4.5
Reviewed-by: Jan Kara <jack@suse.cz>
Tested-by: Tahsin Erdogan <tahsin@google.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Pull trivial tree updates from Jiri Kosina.
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial:
floppy: make local variable non-static
exynos: fixes an incorrect header guard
dt-bindings: fixes some incorrect header guards
cpufreq-dt: correct dead link in documentation
cpufreq: ARM big LITTLE: correct dead link in documentation
treewide: Fix typos in printk
Documentation: filesystem: Fix typo in fs/eventfd.c
fs/super.c: use && instead of & for warn_on condition
Documentation: fix sysfs-ptp
lib: scatterlist: fix Kconfig description
This fixes the following sparse warning:
fs/super.c:1202:9: warning: dubious: x & !y
Bitwise and logical and are equivalent here, but logical was intended.
The generated code is identical, with and without CONFIG_LOCKDEP.
Signed-off-by: Vincent Stehlé <vincent.stehle@freescale.com>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
When competing sync(2) calls walk the same filesystem, they need to
walk the list of inodes on the superblock to find all the inodes
that we need to wait for IO completion on. However, when multiple
wait_sb_inodes() calls do this at the same time, they contend on the
the inode_sb_list_lock and the contention causes system wide
slowdowns. In effect, concurrent sync(2) calls can take longer and
burn more CPU than if they were serialised.
Stop the worst of the contention by adding a per-sb mutex to wrap
around wait_sb_inodes() so that we only execute one sync(2) IO
completion walk per superblock superblock at a time and hence avoid
contention being triggered by concurrent sync(2) calls.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Dave Chinner <dchinner@redhat.com>
The process of reducing contention on per-superblock inode lists
starts with moving the locking to match the per-superblock inode
list. This takes the global lock out of the picture and reduces the
contention problems to within a single filesystem. This doesn't get
rid of contention as the locks still have global CPU scope, but it
does isolate operations on different superblocks form each other.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Dave Chinner <dchinner@redhat.com>
We can remove everything from struct sb_writers except frozen
and add the array of percpu_rw_semaphore's instead.
This patch doesn't remove sb_writers->wait_unfrozen yet, we keep
it for get_super_thawed(). We will probably remove it later.
This change tries to address the following problems:
- Firstly, __sb_start_write() looks simply buggy. It does
__sb_end_write() if it sees ->frozen, but if it migrates
to another CPU before percpu_counter_dec(), sb_wait_write()
can wrongly succeed if there is another task which holds
the same "semaphore": sb_wait_write() can miss the result
of the previous percpu_counter_inc() but see the result
of this percpu_counter_dec().
- As Dave Hansen reports, it is suboptimal. The trivial
microbenchmark that writes to a tmpfs file in a loop runs
12% faster if we change this code to rely on RCU and kill
the memory barriers.
- This code doesn't look simple. It would be better to rely
on the generic locking code.
According to Dave, this change adds the same performance
improvement.
Note: with this change both freeze_super() and thaw_super() will do
synchronize_sched_expedited() 3 times. This is just ugly. But:
- This will be "fixed" by the rcu_sync changes we are going
to merge. After that freeze_super()->percpu_down_write()
will use synchronize_sched(), and thaw_super() won't use
synchronize() at all.
This doesn't need any changes in fs/super.c.
- Once we merge rcu_sync changes, we can also change super.c
so that all wb_write->rw_sem's will share the single ->rss
in struct sb_writes, then freeze_super() will need only one
synchronize_sched().
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Jan Kara <jack@suse.com>
Of course, this patch is ugly as hell. It will be (partially)
reverted later. We add it to ensure that other WIP changes in
percpu_rw_semaphore won't break fs/super.c.
We do not even need this change right now, percpu_free_rwsem()
is fine in atomic context. But we are going to change this, it
will be might_sleep() after we merge the rcu_sync() patches.
And even after that we do not really need destroy_super_work(),
we will kill it in any case. Instead, destroy_super_rcu() should
just check that rss->cb_state == CB_IDLE and do call_rcu() again
in the (very unlikely) case this is not true.
So this is just the temporary kludge which helps us to avoid the
conflicts with the changes which will be (hopefully) routed via
rcu tree.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Jan Kara <jack@suse.com>
Not only we need to avoid the warning from lockdep_sys_exit(), the
caller of freeze_super() can never release this lock. Another thread
can do this, so there is another reason for rwsem_release().
Plus the comment should explain why we have to fool lockdep.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Jan Kara <jack@suse.com>
1. wait_event(frozen < level) without rwsem_acquire_read() is just
wrong from lockdep perspective. If we are going to deadlock
because the caller is buggy, lockdep can't detect this problem.
2. __sb_start_write() can race with thaw_super() + freeze_super(),
and after "goto retry" the 2nd acquire_freeze_lock() is wrong.
3. The "tell lockdep we are doing trylock" hack doesn't look nice.
I think this is correct, but this logic should be more explicit.
Yes, the recursive read_lock() is fine if we hold the lock on a
higher level. But we do not need to fool lockdep. If we can not
deadlock in this case then try-lock must not fail and we can use
use wait == F throughout this code.
Note: as Dave Chinner explains, the "trylock" hack and the fat comment
can be probably removed. But this needs a separate change and it will
be trivial: just kill __sb_start_write() and rename do_sb_start_write()
back to __sb_start_write().
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Jan Kara <jack@suse.com>
Execution of get_anon_bdev concurrently and preemptive kernel all
could bring race condition, it isn't enough to check dev against
its upper limitation with equality operator only.
This patch fix it.
Signed-off-by: Wang YanQing <udknight@gmail.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
The limit equals 32 and is imposed by the number of entries in the
fs_poolid_map and shared_fs_poolid_map. Nowadays it is insufficient,
because with containers on board a Linux host can have hundreds of
active fs mounts.
These maps were introduced by commit 49a9ab815a ("mm: cleancache:
lazy initialization to allow tmem backends to build/run as modules") in
order to allow compiling cleancache drivers as modules. Real pool ids
are stored in these maps while super_block->cleancache_poolid points to
an entry in the map, so that on cleancache registration we can walk over
all (if there are <= 32 of them, of course) cleancache-enabled super
blocks and assign real pool ids.
Actually, there is absolutely no need in these maps, because we can
iterate over all super blocks immediately using iterate_supers. This is
not racy, because cleancache_init_ops is called from mount_fs with
super_block->s_umount held for writing, while iterate_supers takes this
semaphore for reading, so if we call iterate_supers after setting
cleancache_ops, all super blocks that had been created before
cleancache_register_ops was called will be assigned pool ids by the
action function of iterate_supers while all newer super blocks will
receive it in cleancache_init_fs.
This patch therefore removes the maps and hence the artificial limit on
the number of cleancache enabled filesystems.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Stefan Hengelein <ilendir@googlemail.com>
Cc: Florian Schmaus <fschmaus@gmail.com>
Cc: Andor Daam <andor.daam@googlemail.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Bob Liu <lliubbo@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I've noticed significant locking contention in memory reclaimer around
sb_lock inside grab_super_passive(). Grab_super_passive() is called from
two places: in icache/dcache shrinkers (function super_cache_scan) and
from writeback (function __writeback_inodes_wb). Both are required for
progress in memory allocator.
Grab_super_passive() acquires sb_lock to increment sb->s_count and check
sb->s_instances. It seems sb->s_umount locked for read is enough here:
super-block deactivation always runs under sb->s_umount locked for write.
Protecting super-block itself isn't a problem: in super_cache_scan() sb
is protected by shrinker_rwsem: it cannot be freed if its slab shrinkers
are still active. Inside writeback super-block comes from inode from bdi
writeback list under wb->list_lock.
This patch removes locking sb_lock and checks s_instances under s_umount:
generic_shutdown_super() unlinks it under sb->s_umount locked for write.
New variant is called trylock_super() and since it only locks semaphore,
callers must call up_read(&sb->s_umount) instead of drop_super(sb) when
they're done.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Pull misc VFS updates from Al Viro:
"This cycle a lot of stuff sits on topical branches, so I'll be sending
more or less one pull request per branch.
This is the first pile; more to follow in a few. In this one are
several misc commits from early in the cycle (before I went for
separate branches), plus the rework of mntput/dput ordering on umount,
switching to use of fs_pin instead of convoluted games in
namespace_unlock()"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
switch the IO-triggering parts of umount to fs_pin
new fs_pin killing logics
allow attaching fs_pin to a group not associated with some superblock
get rid of the second argument of acct_kill()
take count and rcu_head out of fs_pin
dcache: let the dentry count go down to zero without taking d_lock
pull bumping refcount into ->kill()
kill pin_put()
mode_t whack-a-mole: chelsio
file->f_path.dentry is pinned down for as long as the file is open...
get rid of lustre_dump_dentry()
gut proc_register() a bit
kill d_validate()
ncpfs: get rid of d_validate() nonsense
selinuxfs: don't open-code d_genocide()
Merge third set of updates from Andrew Morton:
- the rest of MM
[ This includes getting rid of the numa hinting bits, in favor of
just generic protnone logic. Yay. - Linus ]
- core kernel
- procfs
- some of lib/ (lots of lib/ material this time)
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (104 commits)
lib/lcm.c: replace include
lib/percpu_ida.c: remove redundant includes
lib/strncpy_from_user.c: replace module.h include
lib/stmp_device.c: replace module.h include
lib/sort.c: move include inside #if 0
lib/show_mem.c: remove redundant include
lib/radix-tree.c: change to simpler include
lib/plist.c: remove redundant include
lib/nlattr.c: remove redundant include
lib/kobject_uevent.c: remove redundant include
lib/llist.c: remove redundant include
lib/md5.c: simplify include
lib/list_sort.c: rearrange includes
lib/genalloc.c: remove redundant include
lib/idr.c: remove redundant include
lib/halfmd4.c: simplify includes
lib/dynamic_queue_limits.c: simplify includes
lib/sort.c: use simpler includes
lib/interval_tree.c: simplify includes
hexdump: make it return number of bytes placed in buffer
...
In super_cache_scan() we divide the number of objects of particular type
by the total number of objects in order to distribute pressure among As a
result, in some corner cases we can get nr_to_scan=0 even if there are
some objects to reclaim, e.g. dentries=1, inodes=1, fs_objects=1,
nr_to_scan=1/3=0.
This is unacceptable for per memcg kmem accounting, because this means
that some objects may never get reclaimed after memcg death, preventing it
from being freed.
This patch therefore assures that super_cache_scan() will scan at least
one object of each type if any.
[akpm@linux-foundation.org: add comment]
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Now, to make any list_lru-based shrinker memcg aware we should only
initialize its list_lru as memcg aware. Let's do it for the general FS
shrinker (super_block::s_shrink).
There are other FS-specific shrinkers that use list_lru for storing
objects, such as XFS and GFS2 dquot cache shrinkers, but since they
reclaim objects that are shared among different cgroups, there is no point
making them memcg aware. It's a big question whether we should account
them to memcg at all.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Glauber Costa <glommer@gmail.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
To make list_lru memcg aware, we need all list_lrus to be kept on a list
protected by a mutex, so that we could sleep while walking over the
list.
Therefore after this change list_lru_destroy may sleep. Fortunately,
there is only one user that calls it from an atomic context - it's
put_super - and we can easily fix it by calling list_lru_destroy before
put_super in destroy_locked_super - anyway we don't longer need lrus by
that time.
Another point that should be noted is that list_lru_destroy is allowed
to be called on an uninitialized zeroed-out object, in which case it is
a no-op. Before this patch this was guaranteed by kfree, but now we
need an explicit check there.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Glauber Costa <glommer@gmail.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We are going to make FS shrinkers memcg-aware. To achieve that, we will
have to pass the memcg to scan to the nr_cached_objects and
free_cached_objects VFS methods, which currently take only the NUMA node
to scan. Since the shrink_control structure already holds the node, and
the memcg to scan will be added to it when we introduce memcg-aware
vmscan, let us consolidate the methods' arguments in this structure to
keep things clean.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Suggested-by: Dave Chinner <david@fromorbit.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Glauber Costa <glommer@gmail.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Kmem accounting of memcg is unusable now, because it lacks slab shrinker
support. That means when we hit the limit we will get ENOMEM w/o any
chance to recover. What we should do then is to call shrink_slab, which
would reclaim old inode/dentry caches from this cgroup. This is what
this patch set is intended to do.
Basically, it does two things. First, it introduces the notion of
per-memcg slab shrinker. A shrinker that wants to reclaim objects per
cgroup should mark itself as SHRINKER_MEMCG_AWARE. Then it will be
passed the memory cgroup to scan from in shrink_control->memcg. For
such shrinkers shrink_slab iterates over the whole cgroup subtree under
the target cgroup and calls the shrinker for each kmem-active memory
cgroup.
Secondly, this patch set makes the list_lru structure per-memcg. It's
done transparently to list_lru users - everything they have to do is to
tell list_lru_init that they want memcg-aware list_lru. Then the
list_lru will automatically distribute objects among per-memcg lists
basing on which cgroup the object is accounted to. This way to make FS
shrinkers (icache, dcache) memcg-aware we only need to make them use
memcg-aware list_lru, and this is what this patch set does.
As before, this patch set only enables per-memcg kmem reclaim when the
pressure goes from memory.limit, not from memory.kmem.limit. Handling
memory.kmem.limit is going to be tricky due to GFP_NOFS allocations, and
it is still unclear whether we will have this knob in the unified
hierarchy.
This patch (of 9):
NUMA aware slab shrinkers use the list_lru structure to distribute
objects coming from different NUMA nodes to different lists. Whenever
such a shrinker needs to count or scan objects from a particular node,
it issues commands like this:
count = list_lru_count_node(lru, sc->nid);
freed = list_lru_walk_node(lru, sc->nid, isolate_func,
isolate_arg, &sc->nr_to_scan);
where sc is an instance of the shrink_control structure passed to it
from vmscan.
To simplify this, let's add special list_lru functions to be used by
shrinkers, list_lru_shrink_count() and list_lru_shrink_walk(), which
consolidate the nid and nr_to_scan arguments in the shrink_control
structure.
This will also allow us to avoid patching shrinkers that use list_lru
when we make shrink_slab() per-memcg - all we will have to do is extend
the shrink_control structure to include the target memcg and make
list_lru_shrink_{count,walk} handle this appropriately.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Suggested-by: Dave Chinner <david@fromorbit.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Glauber Costa <glommer@gmail.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The only user outside of fs/super.c is gone now
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Now that default_backing_dev_info is not used for writeback purposes we can
git rid of it easily:
- instead of using it's name for tracing unregistered bdi we just use
"unknown"
- btrfs and ceph can just assign the default read ahead window themselves
like several other filesystems already do.
- we can assign noop_backing_dev_info as the default one in alloc_super.
All filesystems already either assigned their own or
noop_backing_dev_info.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
Pull vfs updates from Al Viro:
"The big thing in this pile is Eric's unmount-on-rmdir series; we
finally have everything we need for that. The final piece of prereqs
is delayed mntput() - now filesystem shutdown always happens on
shallow stack.
Other than that, we have several new primitives for iov_iter (Matt
Wilcox, culled from his XIP-related series) pushing the conversion to
->read_iter()/ ->write_iter() a bit more, a bunch of fs/dcache.c
cleanups and fixes (including the external name refcounting, which
gives consistent behaviour of d_move() wrt procfs symlinks for long
and short names alike) and assorted cleanups and fixes all over the
place.
This is just the first pile; there's a lot of stuff from various
people that ought to go in this window. Starting with
unionmount/overlayfs mess... ;-/"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (60 commits)
fs/file_table.c: Update alloc_file() comment
vfs: Deduplicate code shared by xattr system calls operating on paths
reiserfs: remove pointless forward declaration of struct nameidata
don't need that forward declaration of struct nameidata in dcache.h anymore
take dname_external() into fs/dcache.c
let path_init() failures treated the same way as subsequent link_path_walk()
fix misuses of f_count() in ppp and netlink
ncpfs: use list_for_each_entry() for d_subdirs walk
vfs: move getname() from callers to do_mount()
gfs2_atomic_open(): skip lookups on hashed dentry
[infiniband] remove pointless assignments
gadgetfs: saner API for gadgetfs_create_file()
f_fs: saner API for ffs_sb_create_file()
jfs: don't hash direct inode
[s390] remove pointless assignment of ->f_op in vmlogrdr ->open()
ecryptfs: ->f_op is never NULL
android: ->f_op is never NULL
nouveau: __iomem misannotations
missing annotation in fs/file.c
fs: namespace: suppress 'may be used uninitialized' warnings
...
total_objects could be 0 and is used as a denom.
While total_objects is a "long", total_objects == 0 unlikely happens for
3.12 and later kernels because 32-bit architectures would not be able to
hold (1 << 32) objects. However, total_objects == 0 may happen for kernels
between 3.1 and 3.11 because total_objects in prune_super() was an "int"
and (e.g.) x86_64 architecture might be able to hold (1 << 32) objects.
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: stable <stable@kernel.org> # 3.1+
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Percpu allocator now supports allocation mask. Add @gfp to
percpu_counter_init() so that !GFP_KERNEL allocation masks can be used
with percpu_counters too.
We could have left percpu_counter_init() alone and added
percpu_counter_init_gfp(); however, the number of users isn't that
high and introducing _gfp variants to all percpu data structures would
be quite ugly, so let's just do the conversion. This is the one with
the most users. Other percpu data structures are a lot easier to
convert.
This patch doesn't make any functional difference.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Jan Kara <jack@suse.cz>
Acked-by: "David S. Miller" <davem@davemloft.net>
Cc: x86@kernel.org
Cc: Jens Axboe <axboe@kernel.dk>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Pull quota, reiserfs, UDF updates from Jan Kara:
"Scalability improvements for quota, a few reiserfs fixes, and couple
of misc cleanups (udf, ext2)"
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
reiserfs: Fix use after free in journal teardown
reiserfs: fix corruption introduced by balance_leaf refactor
udf: avoid redundant memcpy when writing data in ICB
fs/udf: re-use hex_asc_upper_{hi,lo} macros
fs/quota: kernel-doc warning fixes
udf: use linux/uaccess.h
fs/ext2/super.c: Drop memory allocation cast
quota: remove dqptr_sem
quota: simplify remove_inode_dquot_ref()
quota: avoid unnecessary dqget()/dqput() calls
quota: protect Q_GETFMT by dqonoff_mutex
These externs belong in fs/internal.h. Rename (they are not acct-specific
anymore) and move them over there.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
just repeat the frozen check after regaining it, and check that sb
is still alive. If several threads hit acct_auto_close() at the
same time, acct_auto_close() will survive that just fine. And we
really don't want to play with writes and closing the file with
->s_umount held exclusive - it's a deadlock country.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Put these suckers on per-vfsmount and per-superblock lists instead.
Note: right now it's still acct_lock for everything, but that's
going to change.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Remove dqptr_sem to make quota code scalable: Remove the dqptr_sem,
accessing inode->i_dquot now protected by dquot_srcu, and changing
inode->i_dquot is now serialized by dq_data_lock.
Signed-off-by: Lai Siyao <lai.siyao@intel.com>
Signed-off-by: Niu Yawei <yawei.niu@intel.com>
Signed-off-by: Jan Kara <jack@suse.cz>
