Pull user namespace changes from Eric Biederman:
"While small this set of changes is very significant with respect to
containers in general and user namespaces in particular. The user
space interface is now complete.
This set of changes adds support for unprivileged users to create user
namespaces and as a user namespace root to create other namespaces.
The tyranny of supporting suid root preventing unprivileged users from
using cool new kernel features is broken.
This set of changes completes the work on setns, adding support for
the pid, user, mount namespaces.
This set of changes includes a bunch of basic pid namespace
cleanups/simplifications. Of particular significance is the rework of
the pid namespace cleanup so it no longer requires sending out
tendrils into all kinds of unexpected cleanup paths for operation. At
least one case of broken error handling is fixed by this cleanup.
The files under /proc/<pid>/ns/ have been converted from regular files
to magic symlinks which prevents incorrect caching by the VFS,
ensuring the files always refer to the namespace the process is
currently using and ensuring that the ptrace_mayaccess permission
checks are always applied.
The files under /proc/<pid>/ns/ have been given stable inode numbers
so it is now possible to see if different processes share the same
namespaces.
Through the David Miller's net tree are changes to relax many of the
permission checks in the networking stack to allowing the user
namespace root to usefully use the networking stack. Similar changes
for the mount namespace and the pid namespace are coming through my
tree.
Two small changes to add user namespace support were commited here adn
in David Miller's -net tree so that I could complete the work on the
/proc/<pid>/ns/ files in this tree.
Work remains to make it safe to build user namespaces and 9p, afs,
ceph, cifs, coda, gfs2, ncpfs, nfs, nfsd, ocfs2, and xfs so the
Kconfig guard remains in place preventing that user namespaces from
being built when any of those filesystems are enabled.
Future design work remains to allow root users outside of the initial
user namespace to mount more than just /proc and /sys."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (38 commits)
proc: Usable inode numbers for the namespace file descriptors.
proc: Fix the namespace inode permission checks.
proc: Generalize proc inode allocation
userns: Allow unprivilged mounts of proc and sysfs
userns: For /proc/self/{uid,gid}_map derive the lower userns from the struct file
procfs: Print task uids and gids in the userns that opened the proc file
userns: Implement unshare of the user namespace
userns: Implent proc namespace operations
userns: Kill task_user_ns
userns: Make create_new_namespaces take a user_ns parameter
userns: Allow unprivileged use of setns.
userns: Allow unprivileged users to create new namespaces
userns: Allow setting a userns mapping to your current uid.
userns: Allow chown and setgid preservation
userns: Allow unprivileged users to create user namespaces.
userns: Ignore suid and sgid on binaries if the uid or gid can not be mapped
userns: fix return value on mntns_install() failure
vfs: Allow unprivileged manipulation of the mount namespace.
vfs: Only support slave subtrees across different user namespaces
vfs: Add a user namespace reference from struct mnt_namespace
...
There was some desire in large applications using MAP_HUGETLB or
SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on
others. This is useful together with NUMA policy: use 2MB interleaving
on some mappings, but 1GB on local mappings.
This patch extends the IPC/SHM syscall interfaces slightly to allow
specifying the page size.
It borrows some upper bits in the existing flag arguments and allows
encoding the log of the desired page size in addition to the *_HUGETLB
flag. When 0 is specified the default size is used, this makes the
change fully compatible.
Extending the internal hugetlb code to handle this is straight forward.
Instead of a single mount it just keeps an array of them and selects the
right mount based on the specified page size. When no page size is
specified it uses the mount of the default page size.
The change is not visible in /proc/mounts because internal mounts don't
appear there. It also has very little overhead: the additional mounts
just consume a super block, but not more memory when not used.
I also exported the new flags to the user headers (they were previously
under __KERNEL__). Right now only symbols for x86 and some other
architecture for 1GB and 2MB are defined. The interface should already
work for all other architectures though. Only architectures that define
multiple hugetlb sizes actually need it (that is currently x86, tile,
powerpc). However tile and powerpc have user configurable hugetlb
sizes, so it's not easy to add defines. A program on those
architectures would need to query sysfs and use the appropiate log2.
[akpm@linux-foundation.org: cleanups]
[rientjes@google.com: fix build]
[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hillf Danton <dhillf@gmail.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Assign a unique proc inode to each namespace, and use that
inode number to ensure we only allocate at most one proc
inode for every namespace in proc.
A single proc inode per namespace allows userspace to test
to see if two processes are in the same namespace.
This has been a long requested feature and only blocked because
a naive implementation would put the id in a global space and
would ultimately require having a namespace for the names of
namespaces, making migration and certain virtualization tricks
impossible.
We still don't have per superblock inode numbers for proc, which
appears necessary for application unaware checkpoint/restart and
migrations (if the application is using namespace file descriptors)
but that is now allowd by the design if it becomes important.
I have preallocated the ipc and uts initial proc inode numbers so
their structures can be statically initialized.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Modify create_new_namespaces to explicitly take a user namespace
parameter, instead of implicitly through the task_struct.
This allows an implementation of unshare(CLONE_NEWUSER) where
the new user namespace is not stored onto the current task_struct
until after all of the namespaces are created.
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
- Push the permission check from the core setns syscall into
the setns install methods where the user namespace of the
target namespace can be determined, and used in a ns_capable
call.
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Keep a pointer to the audit_names "slot" in struct filename.
Have all of the audit_inode callers pass a struct filename ponter to
audit_inode instead of a string pointer. If the aname field is already
populated, then we can skip walking the list altogether and just use it
directly.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
getname() is intended to copy pathname strings from userspace into a
kernel buffer. The result is just a string in kernel space. It would
however be quite helpful to be able to attach some ancillary info to
the string.
For instance, we could attach some audit-related info to reduce the
amount of audit-related processing needed. When auditing is enabled,
we could also call getname() on the string more than once and not
need to recopy it from userspace.
This patchset converts the getname()/putname() interfaces to return
a struct instead of a string. For now, the struct just tracks the
string in kernel space and the original userland pointer for it.
Later, we'll add other information to the struct as it becomes
convenient.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Currently, this gets set mostly by happenstance when we call into
audit_inode_child. While that might be a little more efficient, it seems
wrong. If the syscall ends up failing before audit_inode_child ever gets
called, then you'll have an audit_names record that shows the full path
but has the parent inode info attached.
Fix this by passing in a parent flag when we call audit_inode that gets
set to the value of LOOKUP_PARENT. We can then fix up the pathname for
the audit entry correctly from the get-go.
While we're at it, clean up the no-op macro for audit_inode in the
!CONFIG_AUDITSYSCALL case.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Commit d6629859b3 ("ipc/mqueue: improve performance of send/recv") and
ce2d52cc ("ipc/mqueue: add rbtree node caching support") introduced an
rbtree of message priorities, and usage of rb_init_node() to initialize
the corresponding nodes. As it turns out, rb_init_node() is unnecessary
here, as the nodes are fully initialized on insertion by rb_link_node()
and the code doesn't access nodes that aren't inserted on the rbtree.
Removing the rb_init_node() calls as I removed that function during
rbtree API cleanups (the only other use of it was in a place that
similarly didn't require it).
Signed-off-by: Michel Lespinasse <walken@google.com>
Acked-by: Doug Ledford <dledford@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull vfs update from Al Viro:
- big one - consolidation of descriptor-related logics; almost all of
that is moved to fs/file.c
(BTW, I'm seriously tempted to rename the result to fd.c. As it is,
we have a situation when file_table.c is about handling of struct
file and file.c is about handling of descriptor tables; the reasons
are historical - file_table.c used to be about a static array of
struct file we used to have way back).
A lot of stray ends got cleaned up and converted to saner primitives,
disgusting mess in android/binder.c is still disgusting, but at least
doesn't poke so much in descriptor table guts anymore. A bunch of
relatively minor races got fixed in process, plus an ext4 struct file
leak.
- related thing - fget_light() partially unuglified; see fdget() in
there (and yes, it generates the code as good as we used to have).
- also related - bits of Cyrill's procfs stuff that got entangled into
that work; _not_ all of it, just the initial move to fs/proc/fd.c and
switch of fdinfo to seq_file.
- Alex's fs/coredump.c spiltoff - the same story, had been easier to
take that commit than mess with conflicts. The rest is a separate
pile, this was just a mechanical code movement.
- a few misc patches all over the place. Not all for this cycle,
there'll be more (and quite a few currently sit in akpm's tree)."
Fix up trivial conflicts in the android binder driver, and some fairly
simple conflicts due to two different changes to the sock_alloc_file()
interface ("take descriptor handling from sock_alloc_file() to callers"
vs "net: Providing protocol type via system.sockprotoname xattr of
/proc/PID/fd entries" adding a dentry name to the socket)
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (72 commits)
MAX_LFS_FILESIZE should be a loff_t
compat: fs: Generic compat_sys_sendfile implementation
fs: push rcu_barrier() from deactivate_locked_super() to filesystems
btrfs: reada_extent doesn't need kref for refcount
coredump: move core dump functionality into its own file
coredump: prevent double-free on an error path in core dumper
usb/gadget: fix misannotations
fcntl: fix misannotations
ceph: don't abuse d_delete() on failure exits
hypfs: ->d_parent is never NULL or negative
vfs: delete surplus inode NULL check
switch simple cases of fget_light to fdget
new helpers: fdget()/fdput()
switch o2hb_region_dev_write() to fget_light()
proc_map_files_readdir(): don't bother with grabbing files
make get_file() return its argument
vhost_set_vring(): turn pollstart/pollstop into bool
switch prctl_set_mm_exe_file() to fget_light()
switch xfs_find_handle() to fget_light()
switch xfs_swapext() to fget_light()
...
Pull user namespace changes from Eric Biederman:
"This is a mostly modest set of changes to enable basic user namespace
support. This allows the code to code to compile with user namespaces
enabled and removes the assumption there is only the initial user
namespace. Everything is converted except for the most complex of the
filesystems: autofs4, 9p, afs, ceph, cifs, coda, fuse, gfs2, ncpfs,
nfs, ocfs2 and xfs as those patches need a bit more review.
The strategy is to push kuid_t and kgid_t values are far down into
subsystems and filesystems as reasonable. Leaving the make_kuid and
from_kuid operations to happen at the edge of userspace, as the values
come off the disk, and as the values come in from the network.
Letting compile type incompatible compile errors (present when user
namespaces are enabled) guide me to find the issues.
The most tricky areas have been the places where we had an implicit
union of uid and gid values and were storing them in an unsigned int.
Those places were converted into explicit unions. I made certain to
handle those places with simple trivial patches.
Out of that work I discovered we have generic interfaces for storing
quota by projid. I had never heard of the project identifiers before.
Adding full user namespace support for project identifiers accounts
for most of the code size growth in my git tree.
Ultimately there will be work to relax privlige checks from
"capable(FOO)" to "ns_capable(user_ns, FOO)" where it is safe allowing
root in a user names to do those things that today we only forbid to
non-root users because it will confuse suid root applications.
While I was pushing kuid_t and kgid_t changes deep into the audit code
I made a few other cleanups. I capitalized on the fact we process
netlink messages in the context of the message sender. I removed
usage of NETLINK_CRED, and started directly using current->tty.
Some of these patches have also made it into maintainer trees, with no
problems from identical code from different trees showing up in
linux-next.
After reading through all of this code I feel like I might be able to
win a game of kernel trivial pursuit."
Fix up some fairly trivial conflicts in netfilter uid/git logging code.
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (107 commits)
userns: Convert the ufs filesystem to use kuid/kgid where appropriate
userns: Convert the udf filesystem to use kuid/kgid where appropriate
userns: Convert ubifs to use kuid/kgid
userns: Convert squashfs to use kuid/kgid where appropriate
userns: Convert reiserfs to use kuid and kgid where appropriate
userns: Convert jfs to use kuid/kgid where appropriate
userns: Convert jffs2 to use kuid and kgid where appropriate
userns: Convert hpfs to use kuid and kgid where appropriate
userns: Convert btrfs to use kuid/kgid where appropriate
userns: Convert bfs to use kuid/kgid where appropriate
userns: Convert affs to use kuid/kgid wherwe appropriate
userns: On alpha modify linux_to_osf_stat to use convert from kuids and kgids
userns: On ia64 deal with current_uid and current_gid being kuid and kgid
userns: On ppc convert current_uid from a kuid before printing.
userns: Convert s390 getting uid and gid system calls to use kuid and kgid
userns: Convert s390 hypfs to use kuid and kgid where appropriate
userns: Convert binder ipc to use kuids
userns: Teach security_path_chown to take kuids and kgids
userns: Add user namespace support to IMA
userns: Convert EVM to deal with kuids and kgids in it's hmac computation
...
- Store the ipc owner and creator with a kuid
- Store the ipc group and the crators group with a kgid.
- Add error handling to ipc_update_perms, allowing it to
fail if the uids and gids can not be converted to kuids
or kgids.
- Modify the proc files to display the ipc creator and
owner in the user namespace of the opener of the proc file.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Rather than #define the options manually in the architecture code, add
Kconfig options for them and select them there instead. This also allows
us to select the compat IPC version parsing automatically for platforms
using the old compat IPC interface.
Reported-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The msgsnd and msgrcv system calls use size_t to represent the size of the
message being transferred. POSIX states that values of msgsz greater than
SSIZE_MAX cause the result to be implementation-defined. On Linux, this
equates to returning -EINVAL if (long) msgsz < 0.
For compat tasks where !CONFIG_ARCH_WANT_OLD_COMPAT_IPC and compat_size_t
is smaller than size_t, negative size values passed from userspace will be
interpreted as positive values by do_msg{rcv,snd} and will fail to exit
early with -EINVAL.
This patch changes the compat prototypes for msg{rcv,snd} so that the
message size is represented as a compat_ssize_t, which we cast to the
native ssize_t type for the core IPC code.
Cc: Arnd Bergmann <arnd@arndb.de>
Acked-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 48b25c43e6 ("ipc: provide generic compat versions of IPC
syscalls") added a new ARCH_WANT_OLD_COMPAT_IPC config option for
architectures to select if their compat target requires the old IPC
syscall interface.
For architectures (such as AArch64) that do not require the internal
calling conventions provided by this option, but have a compat target
where the C library passes the IPC_64 flag explicitly,
compat_ipc_parse_version no longer strips out the flag before calling
the native system call implementation, resulting in unknown SHM/IPC
commands and -EINVAL being returned to userspace.
This patch separates the selection of the internal calling conventions
for the IPC syscalls from the version parsing, allowing architectures to
select __ARCH_WANT_COMPAT_IPC_PARSE_VERSION if they want to use version
parsing whilst retaining the newer syscall calling conventions.
Acked-by: Chris Metcalf <cmetcalf@tilera.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If the SHMLBA definition for a native task differs from the definition for
a compat task, the do_shmat() function would need to handle both.
This patch introduces COMPAT_SHMLBA, which is used by the compat shmat
syscall when calling the ipc code and allows architectures such as AArch64
(where the native SHMLBA is 64k but the compat (AArch32) definition is
16k) to provide the correct semantics for compat IPC system calls.
Cc: David S. Miller <davem@davemloft.net>
Cc: Chris Zankel <chris@zankel.net>
Cc: Arnd Bergmann <arnd@arndb.de>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
boolean "does it have to be exclusive?" flag is passed instead;
Local filesystem should just ignore it - the object is guaranteed
not to be there yet.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Commit 17cf28afea ("mm/fs: remove truncate_range") removed the
truncate_range inode operation in favour of the fallocate file
operation.
When using SYSV IPC shared memory segments, calling madvise with the
MADV_REMOVE advice on an area of shared memory will attempt to invoke
the .fallocate function for the shm_file_operations, which is NULL and
therefore returns -EOPNOTSUPP to userspace. The previous behaviour
would inherit the inode_operations from the underlying tmpfs file and
invoke truncate_range there.
This patch restores the previous behaviour by wrapping the underlying
fallocate function in shm_fallocate, as we do for fsync.
[hughd@google.com: use -ENOTSUPP in shm_fallocate()]
Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull vfs changes from Al Viro.
"A lot of misc stuff. The obvious groups:
* Miklos' atomic_open series; kills the damn abuse of
->d_revalidate() by NFS, which was the major stumbling block for
all work in that area.
* ripping security_file_mmap() and dealing with deadlocks in the
area; sanitizing the neighborhood of vm_mmap()/vm_munmap() in
general.
* ->encode_fh() switched to saner API; insane fake dentry in
mm/cleancache.c gone.
* assorted annotations in fs (endianness, __user)
* parts of Artem's ->s_dirty work (jff2 and reiserfs parts)
* ->update_time() work from Josef.
* other bits and pieces all over the place.
Normally it would've been in two or three pull requests, but
signal.git stuff had eaten a lot of time during this cycle ;-/"
Fix up trivial conflicts in Documentation/filesystems/vfs.txt (the
'truncate_range' inode method was removed by the VM changes, the VFS
update adds an 'update_time()' method), and in fs/btrfs/ulist.[ch] (due
to sparse fix added twice, with other changes nearby).
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (95 commits)
nfs: don't open in ->d_revalidate
vfs: retry last component if opening stale dentry
vfs: nameidata_to_filp(): don't throw away file on error
vfs: nameidata_to_filp(): inline __dentry_open()
vfs: do_dentry_open(): don't put filp
vfs: split __dentry_open()
vfs: do_last() common post lookup
vfs: do_last(): add audit_inode before open
vfs: do_last(): only return EISDIR for O_CREAT
vfs: do_last(): check LOOKUP_DIRECTORY
vfs: do_last(): make ENOENT exit RCU safe
vfs: make follow_link check RCU safe
vfs: do_last(): use inode variable
vfs: do_last(): inline walk_component()
vfs: do_last(): make exit RCU safe
vfs: split do_lookup()
Btrfs: move over to use ->update_time
fs: introduce inode operation ->update_time
reiserfs: get rid of resierfs_sync_super
reiserfs: mark the superblock as dirty a bit later
...
When I wrote the first patch that added the rbtree support for message
queue insertion, it sped up the case where the queue was very full
drastically from the original code. It, however, slowed down the case
where the queue was empty (not drastically though).
This patch caches the last freed rbtree node struct so we can quickly
reuse it when we get a new message. This is the common path for any queue
that very frequently goes from 0 to 1 then back to 0 messages in queue.
Andrew Morton didn't like that we were doing a GFP_ATOMIC allocation in
msg_insert, so this patch attempts to speculatively allocate a new node
struct outside of the spin lock when we know we need it, but will still
fall back to a GFP_ATOMIC allocation if it has to.
Once I added the caching, the necessary various ret = ; spin_unlock
gyrations in mq_timedsend were getting pretty ugly, so this also slightly
refactors that function to streamline the flow of the code and the
function exit.
Finally, while working on getting performance back I made sure that all of
the node structs were always fully initialized when they were first used,
rendering the use of kzalloc unnecessary and a waste of CPU cycles.
The net result of all of this is:
1) We will avoid a GFP_ATOMIC allocation when possible, but fall back
on it when necessary.
2) We will speculatively allocate a node struct using GFP_KERNEL if our
cache is empty (and save the struct to our cache if it's still empty
after we have obtained the spin lock).
3) The performance of the common queue empty case has significantly
improved and is now much more in line with the older performance for
this case.
The performance changes are:
Old mqueue new mqueue new mqueue + caching
queue empty
send/recv 305/288ns 349/318ns 310/322ns
I don't think we'll ever be able to get the recv performance back, but
that's because the old recv performance was a direct result and
consequence of the old methods abysmal send performance. The recv path
simply must do more so that the send path does not incur such a penalty
under higher queue depths.
As it turns out, the new caching code also sped up the various queue full
cases relative to my last patch. That could be because of the difference
between the syscall path in 3.3.4-rc5 and 3.3.4-rc6, or because of the
change in code flow in the mq_timedsend routine. Regardless, I'll take
it. It wasn't huge, and I *would* say it was within the margin for error,
but after many repeated runs what I'm seeing is that the old numbers trend
slightly higher (about 10 to 20ns depending on which test is the one
running).
[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Doug Ledford <dledford@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We already check the mq attr struct if it's passed in, but now that the
admin can set system wide defaults separate from maximums, it's actually
possible to set the defaults to something that would overflow. So, if
there is no attr struct passed in to the open call, check the default
values.
While we are at it, simplify mq_attr_ok() by making it return 0 or an
error condition, so that way if we add more tests to it later, we have the
option of what error should be returned instead of the calling location
having to pick a possibly inaccurate error code.
[akpm@linux-foundation.org: s/ENOMEM/EOVERFLOW/]
Signed-off-by: Doug Ledford <dledford@redhat.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Manfred Spraul <manfred@colorfullife.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
While working on the other parts of the mqueue stuff, I noticed that the
calculation for overflow in mq_attr_ok didn't actually match reality (this
is especially true since my last patch which changed how we account memory
slightly).
In particular, we used to test for overflow using:
msgs * msgsize + msgs * sizeof(struct msg_msg *)
That was never really correct because each message we allocate via
load_msg() is actually a struct msg_msg followed by the data for the
message (and if struct msg_msg + data exceeds PAGE_SIZE we end up
allocating struct msg_msgseg structs too, but accounting for them would
get really tedious, so let's ignore those...they're only a pointer in size
anyway). This patch updates the calculation to be more accurate in
regards to maximum possible memory consumption by the mqueue.
[akpm@linux-foundation.org: add a local to simplify overflow-checking expression]
Signed-off-by: Doug Ledford <dledford@redhat.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Manfred Spraul <manfred@colorfullife.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The existing implementation of the POSIX message queue send and recv
functions is, well, abysmal. Even worse than abysmal. I submitted a
patch to increase the maximum POSIX message queue limit to 65536 due to
customer needs, however, upon looking over the send/recv implementation, I
realized that my customer needs help with that too even if they don't know
it. The basic problem is that, given the fairly typical use case scenario
for a large queue of queueing lots of messages all at the same priority (I
verified with my customer that this is indeed what their app does), the
msg_insert routine is basically a frikkin' bubble sort. I mean, whoa,
that's *so* middle school.
OK, OK, to not slam the original author too much, I'm sure they didn't
envision a queue depth of 50,000+ messages. No one would think that
moving elements in an array, one at a time, and dereferencing each pointer
in that array to check priority of the message being pointed too, again
one at a time, for 50,000+ times would be good. So let's assume that, as
is typical, the users have found a way to break our code simply by using
it in a way we didn't envision. Fair enough.
"So, just how broken is it?", you ask. I wondered the same thing, so I
wrote an app to let me know. It's my next patch. It gave me some
interesting results. Here's what it tested:
Interference with other apps - In continuous mode, the app just sits there
and hits a message queue forever, while you go do something productive on
another terminal using other CPUs. You then measure how long it takes you
to do that something productive. Then you restart the app in fake
continuous mode, and it sits in a tight loop on a CPU while you repeat
your tests. The whole point of this is to keep one CPU tied up (so it
can't be used in your other work) but in one case tied up hitting the
mqueue code so we can see the effect of walking that 65,528 element array
one pointer at a time on the global CPU cache. If it's bad, then it will
slow down your app on the other CPUs just by polluting cache mercilessly.
In the fake case, it will be in a tight loop, but not polluting cache.
Testing the mqueue subsystem directly - Here we just run a number of tests
to see how the mqueue subsystem performs under different conditions. A
couple conditions are known to be worst case for the old system, and some
routines, so this tests all of them.
So, on to the results already:
Subsystem/Test Old New
Time to compile linux
kernel (make -j12 on a
6 core CPU)
Running mqueue test user 49m10.744s user 45m26.294s
sys 5m51.924s sys 4m59.894s
total 55m02.668s total 50m26.188s
Running fake test user 45m32.686s user 45m18.552s
sys 5m12.465s sys 4m56.468s
total 50m45.151s total 50m15.020s
% slowdown from mqueue
cache thrashing ~8% ~.5%
Avg time to send/recv (in nanoseconds per message)
when queue empty 305/288 349/318
when queue full (65528 messages)
constant priority 526589/823 362/314
increasing priority 403105/916 495/445
decreasing priority 73420/594 482/409
random priority 280147/920 546/436
Time to fill/drain queue (65528 messages, in seconds)
constant priority 17.37/.12 .13/.12
increasing priority 4.14/.14 .21/.18
decreasing priority 12.93/.13 .21/.18
random priority 8.88/.16 .22/.17
So, I think the results speak for themselves. It's possible this
implementation could be improved by cacheing at least one priority level
in the node tree (that would bring the queue empty performance more in
line with the old implementation), but this works and is *so* much better
than what we had, especially for the common case of a single priority in
use, that further refinements can be in follow on patches.
[akpm@linux-foundation.org: fix typo in comment, remove stray semicolon]
[levinsasha928@gmail.com: use correct gfp flags in msg_insert]
Signed-off-by: Doug Ledford <dledford@redhat.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Manfred Spraul <manfred@colorfullife.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit b231cca438 ("message queues: increase range limits") changed
mqueue default value when attr parameter is specified NULL from hard
coded value to fs.mqueue.{msg,msgsize}_max sysctl value.
This made large side effect. When user need to use two mqueue
applications 1) using !NULL attr parameter and it require big message
size and 2) using NULL attr parameter and only need small size message,
app (1) require to raise fs.mqueue.msgsize_max and app (2) consume large
memory size even though it doesn't need.
Doug Ledford propsed to switch back it to static hard coded value.
However it also has a compatibility problem. Some applications might
started depend on the default value is tunable.
The solution is to separate default value from maximum value.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Acked-by: Doug Ledford <dledford@redhat.com>
Acked-by: Joe Korty <joe.korty@ccur.com>
Cc: Amerigo Wang <amwang@redhat.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
KMALLOC_MAX_SIZE is not a good threshold. It is extremely high and
problematic. Unfortunately, some silly drivers depend on this and we
can't change it. But any new code needn't use such extreme ugly high
order allocations. It brings us awful fragmentation issues and system
slowdown.
Signed-off-by: KOSAKI Motohiro <mkosaki@jp.fujitsu.com>
Acked-by: Doug Ledford <dledford@redhat.com>
Acked-by: Joe Korty <joe.korty@ccur.com>
Cc: Amerigo Wang <amwang@redhat.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Joe Korty <joe.korty@ccur.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit b231cca438 ("message queues: increase range limits") changed the
maximum size of a message in a message queue from INT_MAX to 8192*128.
Unfortunately, we had customers that relied on a size much larger than
8192*128 on their production systems. After reviewing POSIX, we found
that it is silent on the maximum message size. We did find a couple other
areas in which it was not silent. Fix up the mqueue maximums so that the
customer's system can continue to work, and document both the POSIX and
real world requirements in ipc_namespace.h so that we don't have this
issue crop back up.
Also, commit 9cf18e1dd7 ("ipc: HARD_MSGMAX should be higher not lower
on 64bit") fiddled with HARD_MSGMAX without realizing that the number was
intentionally in place to limit the msg queue depth to one that was small
enough to kmalloc an array of pointers (hence why we divided 128k by
sizeof(long)). If we wish to meet POSIX requirements, we have no choice
but to change our allocation to a vmalloc instead (at least for the large
queue size case). With that, it's possible to increase our allowed
maximum to the POSIX requirements (or more if we choose).
[sfr@canb.auug.org.au: using vmalloc requires including vmalloc.h]
Signed-off-by: Doug Ledford <dledford@redhat.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: Amerigo Wang <amwang@redhat.com>
Cc: Joe Korty <joe.korty@ccur.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In two places we don't enforce the hard limits for CAP_SYS_RESOURCE apps.
In preparation for making more reasonable hard limits, start enforcing
them even on CAP_SYS_RESOURCE.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: Amerigo Wang <amwang@redhat.com>
Cc: Joe Korty <joe.korty@ccur.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit b231cca438 ("message queues: increase range limits") changed
how we create a queue that does not include an attr struct passed to
open so that it creates the queue with whatever the maximum values are.
However, if the admin has set the maximums to allow flexibility in
creating a queue (aka, both a large size and large queue are allowed,
but combined they create a queue too large for the RLIMIT_MSGQUEUE of
the user), then attempts to create a queue without an attr struct will
fail. Switch back to using acceptable defaults regardless of what the
maximums are.
Note: so far, we only know of a few applications that rely on this
behavior (specifically, set the maximums in /proc, then run the
application which calls mq_open() without passing in an attr struct, and
the application expects the newly created message queue to have the
maximum sizes that were set in /proc used on the mq_open() call, and all
of those applications that we know of are actually part of regression
test suites that were coded to do something like this:
for size in 4096 65536 $((1024 * 1024)) $((16 * 1024 * 1024)); do
echo $size > /proc/sys/fs/mqueue/msgsize_max
mq_open || echo "Error opening mq with size $size"
done
These test suites that depend on any behavior like this are broken. The
concept that programs should rely upon the system wide maximum in order
to get their desired results instead of simply using a attr struct to
specify what they want is fundamentally unfriendly programming practice
for any multi-tasking OS.
Fixing this will break those few apps that we know of (and those app
authors recognize the brokenness of their code and the need to fix it).
However, the following patch "mqueue: separate mqueue default value"
allows a workaround in the form of new knobs for the default msg queue
creation parameters for any software out there that we don't already
know about that might rely on this behavior at the moment.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: Amerigo Wang <amwang@redhat.com>
Cc: Joe Korty <joe.korty@ccur.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Since commit b231cca438 ("message queues: increase range limits") on
Oct 18, 2008, calls to mq_open() that did not pass in an attribute
struct and expected to get default values for the size of the queue and
the max message size now get the system wide maximums instead of
hardwired defaults like they used to get.
This was uncovered when one of the earlier patches in this patch set
increased the default system wide maximums at the same time it increased
the hard ceiling on the system wide maximums (a customer specifically
needed the hard ceiling brought back up, the new ceiling that commit
b231cca438 introduced was too low for their production systems). By
increasing the default maximums and not realising they were tied to any
attempt to create a message queue without an attribute struct, I had
inadvertently made it such that all message queue creation attempts
without an attribute struct were failing because the new default
maximums would create a queue that exceeded the default rlimit for
message queue bytes.
As a result, the system wide defaults were brought back down to their
previous levels, and the system wide ceilings on the maximums were
raised to meet the customer's needs. However, the fact that the no
attribute struct behavior of mq_open() could be broken by changing the
system wide maximums for message queues was seen as fundamentally broken
itself. So we hardwired the no attribute case back like it used to be.
But, then we realized that on the very off chance that some piece of
software in the wild depended on that behavior, we could work around
that issue by adding two new knobs to /proc that allowed setting the
defaults for message queues created without an attr struct separately
from the system wide maximums.
What is not an option IMO is to leave the current behavior in place. No
piece of software should ever rely on setting the system wide maximums
in order to get a desired message queue. Such a reliance would be so
fundamentally multitasking OS unfriendly as to not really be tolerable.
Fortunately, we don't know of any software in the wild that uses this
except for a regression test program that caught the issue in the first
place. If there is though, we have made accommodations with the two new
/proc knobs (and that's all the accommodations such fundamentally broken
software can be allowed)..
This patch:
The various defines for minimums and maximums of the sysctl controllable
mqueue values are scattered amongst different files and named
inconsistently. Move them all into ipc_namespace.h and make them have
consistent names. Additionally, make the number of queues per namespace
also have a minimum and maximum and use the same sysctl function as the
other two settable variables.
Signed-off-by: Doug Ledford <dledford@redhat.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Amerigo Wang <amwang@redhat.com>
Cc: Joe Korty <joe.korty@ccur.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.11 (GNU/Linux)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=oLXf
-----END PGP SIGNATURE-----
Merge tag 'writeback' of git://git.kernel.org/pub/scm/linux/kernel/git/wfg/linux
Pull writeback tree from Wu Fengguang:
"Mainly from Jan Kara to avoid iput() in the flusher threads."
* tag 'writeback' of git://git.kernel.org/pub/scm/linux/kernel/git/wfg/linux:
writeback: Avoid iput() from flusher thread
vfs: Rename end_writeback() to clear_inode()
vfs: Move waiting for inode writeback from end_writeback() to evict_inode()
writeback: Refactor writeback_single_inode()
writeback: Remove wb->list_lock from writeback_single_inode()
writeback: Separate inode requeueing after writeback
writeback: Move I_DIRTY_PAGES handling
writeback: Move requeueing when I_SYNC set to writeback_sb_inodes()
writeback: Move clearing of I_SYNC into inode_sync_complete()
writeback: initialize global_dirty_limit
fs: remove 8 bytes of padding from struct writeback_control on 64 bit builds
mm: page-writeback.c: local functions should not be exposed globally
After we moved inode_sync_wait() from end_writeback() it doesn't make sense
to call the function end_writeback() anymore. Rename it to clear_inode()
which well says what the function really does - set I_CLEAR flag.
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
These function are no longer needed replace them with their more useful equivalents.
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Stop relying on user->user_ns which is going away and instead capture
the user_namespace of the process we are supposed to notify.
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Optimize performance and prepare for the removal of the user_ns reference
from user_struct. Remove the slow long walk through cred->user->user_ns and
instead go straight to cred->user_ns.
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Pull arch/tile (really asm-generic) update from Chris Metcalf:
"These are a couple of asm-generic changes that apply to tile."
* git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile:
compat: use sys_sendfile64() implementation for sendfile syscall
[PATCH v3] ipc: provide generic compat versions of IPC syscalls
Merge first batch of patches from Andrew Morton:
"A few misc things and all the MM queue"
* emailed from Andrew Morton <akpm@linux-foundation.org>: (92 commits)
memcg: avoid THP split in task migration
thp: add HPAGE_PMD_* definitions for !CONFIG_TRANSPARENT_HUGEPAGE
memcg: clean up existing move charge code
mm/memcontrol.c: remove unnecessary 'break' in mem_cgroup_read()
mm/memcontrol.c: remove redundant BUG_ON() in mem_cgroup_usage_unregister_event()
mm/memcontrol.c: s/stealed/stolen/
memcg: fix performance of mem_cgroup_begin_update_page_stat()
memcg: remove PCG_FILE_MAPPED
memcg: use new logic for page stat accounting
memcg: remove PCG_MOVE_LOCK flag from page_cgroup
memcg: simplify move_account() check
memcg: remove EXPORT_SYMBOL(mem_cgroup_update_page_stat)
memcg: kill dead prev_priority stubs
memcg: remove PCG_CACHE page_cgroup flag
memcg: let css_get_next() rely upon rcu_read_lock()
cgroup: revert ss_id_lock to spinlock
idr: make idr_get_next() good for rcu_read_lock()
memcg: remove unnecessary thp check in page stat accounting
memcg: remove redundant returns
memcg: enum lru_list lru
...
When calling shmget() with SHM_HUGETLB, shmget aligns the request size to
PAGE_SIZE, but this is not sufficient.
Modify hugetlb_file_setup() to align requests to the huge page size, and
to accept an address argument so that all alignment checks can be
performed in hugetlb_file_setup(), rather than in its callers. Change
newseg() and mmap_pgoff() to match the new prototype and eliminate a now
redundant alignment check.
[akpm@linux-foundation.org: fix build]
Signed-off-by: Steven Truelove <steven.truelove@utoronto.ca>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull vfs pile 1 from Al Viro:
"This is _not_ all; in particular, Miklos' and Jan's stuff is not there
yet."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (64 commits)
ext4: initialization of ext4_li_mtx needs to be done earlier
debugfs-related mode_t whack-a-mole
hfsplus: add an ioctl to bless files
hfsplus: change finder_info to u32
hfsplus: initialise userflags
qnx4: new helper - try_extent()
qnx4: get rid of qnx4_bread/qnx4_getblk
take removal of PF_FORKNOEXEC to flush_old_exec()
trim includes in inode.c
um: uml_dup_mmap() relies on ->mmap_sem being held, but activate_mm() doesn't hold it
um: embed ->stub_pages[] into mmu_context
gadgetfs: list_for_each_safe() misuse
ocfs2: fix leaks on failure exits in module_init
ecryptfs: make register_filesystem() the last potential failure exit
ntfs: forgets to unregister sysctls on register_filesystem() failure
logfs: missing cleanup on register_filesystem() failure
jfs: mising cleanup on register_filesystem() failure
make configfs_pin_fs() return root dentry on success
configfs: configfs_create_dir() has parent dentry in dentry->d_parent
configfs: sanitize configfs_create()
...
When using the "compat" APIs, architectures will generally want to
be able to make direct syscalls to msgsnd(), shmctl(), etc., and
in the kernel we would want them to be handled directly by
compat_sys_xxx() functions, as is true for other compat syscalls.
However, for historical reasons, several of the existing compat IPC
syscalls do not do this. semctl() expects a pointer to the fourth
argument, instead of the fourth argument itself. msgsnd(), msgrcv()
and shmat() expect arguments in different order.
This change adds an ARCH_WANT_OLD_COMPAT_IPC config option that can be
set to preserve this behavior for ports that use it (x86, sparc, powerpc,
s390, and mips). No actual semantics are changed for those architectures,
and there is only a minimal amount of code refactoring in ipc/compat.c.
Newer architectures like tile (and perhaps future architectures such
as arm64 and unicore64) should not select this option, and thus can
avoid having any IPC-specific code at all in their architecture-specific
compat layer. In the same vein, if this option is not selected, IPC_64
mode is assumed, since that's what the <asm-generic> headers expect.
The workaround code in "tile" for msgsnd() and msgrcv() is removed
with this change; it also fixes the bug that shmat() and semctl() were
not being properly handled.
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Commit cc39c6a9bb ("mm: account skipped entries to avoid looping in
find_get_pages") correctly fixed an infinite loop; but left a problem
that find_get_pages() on shmem would return 0 (appearing to callers to
mean end of tree) when it meets a run of nr_pages swap entries.
The only uses of find_get_pages() on shmem are via pagevec_lookup(),
called from invalidate_mapping_pages(), and from shmctl SHM_UNLOCK's
scan_mapping_unevictable_pages(). The first is already commented, and
not worth worrying about; but the second can leave pages on the
Unevictable list after an unusual sequence of swapping and locking.
Fix that by using shmem_find_get_pages_and_swap() (then ignoring the
swap) instead of pagevec_lookup().
But I don't want to contaminate vmscan.c with shmem internals, nor
shmem.c with LRU locking. So move scan_mapping_unevictable_pages() into
shmem.c, renaming it shmem_unlock_mapping(); and rename
check_move_unevictable_page() to check_move_unevictable_pages(), looping
down an array of pages, oftentimes under the same lock.
Leave out the "rotate unevictable list" block: that's a leftover from
when this was used for /proc/sys/vm/scan_unevictable_pages, whose flawed
handling involved looking at pages at tail of LRU.
Was there significance to the sequence first ClearPageUnevictable, then
test page_evictable, then SetPageUnevictable here? I think not, we're
under LRU lock, and have no barriers between those.
Signed-off-by: Hugh Dickins <hughd@google.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shaohua.li@intel.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: <stable@vger.kernel.org> [back to 3.1 but will need respins]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
scan_mapping_unevictable_pages() is used to make SysV SHM_LOCKed pages
evictable again once the shared memory is unlocked. It does this with
pagevec_lookup()s across the whole object (which might occupy most of
memory), and takes 300ms to unlock 7GB here. A cond_resched() every
PAGEVEC_SIZE pages would be good.
However, KOSAKI-san points out that this is called under shmem.c's
info->lock, and it's also under shm.c's shm_lock(), both spinlocks.
There is no strong reason for that: we need to take these pages off the
unevictable list soonish, but those locks are not required for it.
So move the call to scan_mapping_unevictable_pages() from shmem.c's
unlock handling up to shm.c's unlock handling. Remove the recently
added barrier, not needed now we have spin_unlock() before the scan.
Use get_file(), with subsequent fput(), to make sure we have a reference
to mapping throughout scan_mapping_unevictable_pages(): that's something
that was previously guaranteed by the shm_lock().
Remove shmctl's lru_add_drain_all(): we don't fault in pages at SHM_LOCK
time, and we lazily discover them to be Unevictable later, so it serves
no purpose for SHM_LOCK; and serves no purpose for SHM_UNLOCK, since
pages still on pagevec are not marked Unevictable.
The original code avoided redundant rescans by checking VM_LOCKED flag
at its level: now avoid them by checking shp's SHM_LOCKED.
The original code called scan_mapping_unevictable_pages() on a locked
area at shm_destroy() time: perhaps we once had accounting cross-checks
which required that, but not now, so skip the overhead and just let
inode eviction deal with them.
Put check_move_unevictable_page() and scan_mapping_unevictable_pages()
under CONFIG_SHMEM (with stub for the TINY case when ramfs is used),
more as comment than to save space; comment them used for SHM_UNLOCK.
Signed-off-by: Hugh Dickins <hughd@google.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shaohua.li@intel.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michel Lespinasse <walken@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
