affs: add mount option to avoid filename truncates
Normal behavior for filenames exceeding specific filesystem limits is to
refuse operation.
AFFS standard name length being only 30 characters against 255 for usual
Linux filesystems, original implementation does filename truncate by
default with a define value AFFS_NO_TRUNCATE which can be enabled but
needs module compilation.
This patch adds 'nofilenametruncate' mount option so that user can
easily activate that feature and avoid a lot of problems (eg overwrite
files ...)
Signed-off-by: Fabian Frederick <fabf@skynet.be> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
fs/affs/dir.c: unlock/brelse dir on failure + code clean-up
Commit 0edf977d2ae3 ("[readdir] convert affs") returns directly -EIO
without unlocking dir inode and releasing dir bh when second affs_bread
sequence fails. This patch restores initial behaviour. It also fixes
pr_debug and affs_error to fit in 80 columns + removes reference to
filldir (replaced by dir_emit in the commit above).
Signed-off-by: Fabian Frederick <fabf@skynet.be> 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>
Liu Hua [Mon, 7 Apr 2014 22:38:57 +0000 (15:38 -0700)]
hung_task: check the value of "sysctl_hung_task_timeout_sec"
As sysctl_hung_task_timeout_sec is unsigned long, when this value is
larger then LONG_MAX/HZ, the function schedule_timeout_interruptible in
watchdog will return immediately without sleep and with print :
rapidio: rework device hierarchy and introduce mport class of devices
This patch removes an artificial RapidIO bus root device and establishes
actual device hierarchy by providing reference to real parent devices.
It also introduces device class for RapidIO controller devices (on-chip
or an eternal bridge, known as "mport").
Existing implementation was sufficient for SoC-based platforms that have
a single RapidIO controller. With introduction of devices using
multiple RapidIO controllers and PCIe-to-RapidIO bridges the old scheme
is very limiting or does not work at all. The implemented changes allow
to properly reference platform's local RapidIO mport devices and provide
device details needed for upper layers.
This change to RapidIO device hierarchy does not break any known
existing kernel or user space interfaces.
Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Cc: Li Yang <leoli@freescale.com> Cc: Kumar Gala <galak@kernel.crashing.org> Cc: Andre van Herk <andre.van.herk@prodrive-technologies.com> Cc: Stef van Os <stef.van.os@prodrive-technologies.com> Cc: Jerry Jacobs <jerry.jacobs@prodrive-technologies.com> Cc: Arno Tiemersma <arno.tiemersma@prodrive-technologies.com> Cc: Rob Landley <rob@landley.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
drivers/rapidio/devices/tsi721_dma.c: optimize use of BDMA descriptors
Combine SG entries describing single contiguous memory block into one
Tsi721 BDMA descriptor. This reduces number of hardware descriptors
required for large data transfers and improves performance on the PCIe
side by reducing number of descriptor fetch requests.
Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com> Cc: Matt Porter <mporter@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Replace rcu_assign_pointer(x, NULL) with RCU_INIT_POINTER(x, NULL)
The rcu_assign_pointer() ensures that the initialization of a structure
is carried out before storing a pointer to that structure. And in the
case of the NULL pointer, there is no structure to initialize.
So, rcu_assign_pointer(p, NULL) can be safely converted to
RCU_INIT_POINTER(p, NULL)
WANG Chao [Mon, 7 Apr 2014 22:38:51 +0000 (15:38 -0700)]
vmcore: continue vmcore initialization if PT_NOTE is found empty
Currently when an empty PT_NOTE is detected, vmcore initialization
fails. It sounds too harsh. Because PT_NOTE could be empty, for
example, one offlined a cpu but never restarted kdump service, and after
crash, PT_NOTE program header is there but no data contains. It's
better to warn about the empty PT_NOTE and continue to initialise
vmcore.
And ultimately the multiple PT_NOTE are merged into a single one, all
empty PT_NOTE are discarded naturally during the merge. So empty
PT_NOTE is not visible to user space and vmcore is as good as expected.
Signed-off-by: WANG Chao <chaowang@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com> Cc: Greg Pearson <greg.pearson@hp.com> Cc: Baoquan He <bhe@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
wait: WSTOPPED|WCONTINUED doesn't work if a zombie leader is traced by another process
Even if the main thread is dead the process still can stop/continue.
However, if the leader is ptraced wait_consider_task(ptrace => false)
always skips wait_task_stopped/wait_task_continued, so WSTOPPED or
WCONTINUED can never work for the natural parent in this case.
Move the "A zombie ptracee is only visible to its ptracer" check into the
"if (!delay_group_leader(p))" block. ->notask_error is cleared by the
"fall through" code below.
This depends on the previous change, wait_task_stopped/continued must be
avoided if !delay_group_leader() and the tracer is ->real_parent.
Otherwise WSTOPPED|WEXITED could wrongly report "stopped" when the child
is already dead (single-threaded or not). If it is traced by another task
then the "stopped" state is fine until the debugger detaches and reveals a
zombie state.
Without this patch it hangs in waitpid(WSTOPPED), wait_task_stopped() is
never called.
Note: this doesn't fix all problems with a zombie delay_group_leader(),
WCONTINUED | WEXITED check is not exactly right. debugger can't assume it
will be notified if another thread reaps the whole thread group.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Jan Kratochvil <jan.kratochvil@redhat.com> Cc: Lennart Poettering <lpoetter@redhat.com> Cc: Michal Schmidt <mschmidt@redhat.com> Cc: Roland McGrath <roland@hack.frob.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>
it hangs in waitpid(WSTOPPED) despite the fact it has a single zombie
child. This is because wait_consider_task(ptrace => 0) sees p->ptrace and
cleares ->notask_error assuming that the debugger should detach and notify
us.
Change wait_consider_task(ptrace => 0) to pretend that ptrace == T if the
child is traced by us. This really simplifies the logic and allows us to
do more fixes, see the next changes. This also hides the unwanted group
stop state automatically, we can remove another ptrace_reparented() check.
Unfortunately, this adds the following behavioural changes:
1. Before this patch wait(WEXITED | __WNOTHREAD) does not reap
a natural child if it is traced by the caller's sub-thread.
Hopefully nobody will ever notice this change, and I think
that nobody should rely on this behaviour anyway.
2. SIGNAL_STOP_CONTINUED is no longer hidden from debugger if
it is real parent.
While this change comes as a side effect, I think it is good
by itself. The group continued state can not be consumed by
another process in this case, it doesn't depend on ptrace,
it doesn't make sense to hide it from real parent.
Perhaps we should add the thread_group_leader() check before
wait_task_continued()? May be, but this shouldn't depend on
ptrace_reparented().
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Jan Kratochvil <jan.kratochvil@redhat.com> Cc: Lennart Poettering <lpoetter@redhat.com> Cc: Michal Schmidt <mschmidt@redhat.com> Cc: Roland McGrath <roland@hack.frob.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>
wait: swap EXIT_ZOMBIE and EXIT_DEAD to hide EXIT_TRACE from user-space
get_task_state() uses the most significant bit to report the state to
user-space, this means that EXIT_ZOMBIE->EXIT_TRACE->EXIT_DEAD transition
can be noticed via /proc as Z -> X -> Z change. Note that this was
possible even before EXIT_TRACE was introduced.
This is not really bad but imho it make sense to hide EXIT_TRACE from
user-space completely. So the patch simply swaps EXIT_ZOMBIE and
EXIT_DEAD, this way EXIT_TRACE will be seen as EXIT_ZOMBIE by user-space.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Jan Kratochvil <jan.kratochvil@redhat.com> Cc: Michal Schmidt <mschmidt@redhat.com> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Lennart Poettering <lpoetter@redhat.com> Cc: Roland McGrath <roland@hack.frob.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>
wait: use EXIT_TRACE only if thread_group_leader(zombie)
wait_task_zombie() always uses EXIT_TRACE/ptrace_unlink() if
ptrace_reparented(). This is suboptimal and a bit confusing: we do not
need do_notify_parent(p) if !thread_group_leader(p) and in this case we
also do not need ptrace_unlink(), we can rely on ptrace_release_task().
Change wait_task_zombie() to check thread_group_leader() along with
ptrace_reparented() and simplify the final p->exit_state transition.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Tested-by: Michal Schmidt <mschmidt@redhat.com> Cc: Jan Kratochvil <jan.kratochvil@redhat.com> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Lennart Poettering <lpoetter@redhat.com> Cc: Roland McGrath <roland@hack.frob.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>
wait: introduce EXIT_TRACE to avoid the racy EXIT_DEAD->EXIT_ZOMBIE transition
wait_task_zombie() first does EXIT_ZOMBIE->EXIT_DEAD transition and
drops tasklist_lock. If this task is not the natural child and it is
traced, we change its state back to EXIT_ZOMBIE for ->real_parent.
The last transition is racy, this is even documented in 50b8d257486a
"ptrace: partially fix the do_wait(WEXITED) vs EXIT_DEAD->EXIT_ZOMBIE
race". wait_consider_task() tries to detect this transition and clear
->notask_error but we can't rely on ptrace_reparented(), debugger can
exit and do ptrace_unlink() before its sub-thread sets EXIT_ZOMBIE.
And there is another problem which were missed before: this transition
can also race with reparent_leader() which doesn't reset >exit_signal if
EXIT_DEAD, assuming that this task must be reaped by someone else. So
the tracee can be re-parented with ->exit_signal != SIGCHLD, and if
/sbin/init doesn't use __WALL it becomes unreapable. This was fixed by
the previous commit, but it was the temporary hack.
1. Add the new exit_state, EXIT_TRACE. It means that the task is the
traced zombie, debugger is going to detach and notify its natural
parent.
This new state is actually EXIT_ZOMBIE | EXIT_DEAD. This way we
can avoid the changes in proc/kgdb code, get_task_state() still
reports "X (dead)" in this case.
Note: with or without this change userspace can see Z -> X -> Z
transition. Not really bad, but probably makes sense to fix.
2. Change wait_task_zombie() to use EXIT_TRACE instead of EXIT_DEAD
if we need to notify the ->real_parent.
3. Revert the previous hack in reparent_leader(), now that EXIT_DEAD
is always the final state we can safely ignore such a task.
4. Change wait_consider_task() to check EXIT_TRACE separately and kill
the racy and no longer needed ptrace_reparented() case.
If ptrace == T an EXIT_TRACE thread should be simply ignored, the
owner of this state is going to ptrace_unlink() this task. We can
pretend that it was already removed from ->ptraced list.
Otherwise we should skip this thread too but clear ->notask_error,
we must be the natural parent and debugger is going to untrace and
notify us. IOW, this doesn't differ from "EXIT_ZOMBIE && p->ptrace"
even if the task was already untraced.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Reported-by: Jan Kratochvil <jan.kratochvil@redhat.com> Reported-by: Michal Schmidt <mschmidt@redhat.com> Tested-by: Michal Schmidt <mschmidt@redhat.com> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Lennart Poettering <lpoetter@redhat.com> Cc: Roland McGrath <roland@hack.frob.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>
wait: fix reparent_leader() vs EXIT_DEAD->EXIT_ZOMBIE race
wait_task_zombie() first does EXIT_ZOMBIE->EXIT_DEAD transition and
drops tasklist_lock. If this task is not the natural child and it is
traced, we change its state back to EXIT_ZOMBIE for ->real_parent.
The last transition is racy, this is even documented in 50b8d257486a
"ptrace: partially fix the do_wait(WEXITED) vs EXIT_DEAD->EXIT_ZOMBIE
race". wait_consider_task() tries to detect this transition and clear
->notask_error but we can't rely on ptrace_reparented(), debugger can
exit and do ptrace_unlink() before its sub-thread sets EXIT_ZOMBIE.
And there is another problem which were missed before: this transition
can also race with reparent_leader() which doesn't reset >exit_signal if
EXIT_DEAD, assuming that this task must be reaped by someone else. So
the tracee can be re-parented with ->exit_signal != SIGCHLD, and if
/sbin/init doesn't use __WALL it becomes unreapable.
Change reparent_leader() to update ->exit_signal even if EXIT_DEAD.
Note: this is the simple temporary hack for -stable, it doesn't try to
solve all problems, it will be reverted by the next changes.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Reported-by: Jan Kratochvil <jan.kratochvil@redhat.com> Reported-by: Michal Schmidt <mschmidt@redhat.com> Tested-by: Michal Schmidt <mschmidt@redhat.com> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Lennart Poettering <lpoetter@redhat.com> Cc: Roland McGrath <roland@hack.frob.com> Cc: Tejun Heo <tj@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
exec: kill bprm->tcomm[], simplify the "basename" logic
Starting from commit c4ad8f98bef7 ("execve: use 'struct filename *' for
executable name passing") bprm->filename can not go away after
flush_old_exec(), so we do not need to save the binary name in
bprm->tcomm[] added by 96e02d158678 ("exec: fix use-after-free bug in
setup_new_exec()").
And there was never need for filename_to_taskname-like code, we can
simply do set_task_comm(kbasename(filename).
This patch has to change set_task_comm() and trace_task_rename() to
accept "const char *", but I think this change is also good.
Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The /proc/*/pagemap contain sensitive information and currently its mode
is 0444. Change this to 0400, so the VFS will prevent unprivileged
processes from getting file descriptors on arbitrary privileged
/proc/*/pagemap files.
This reduces the scope of address space leaking and bypasses by protecting
already running processes.
Signed-off-by: Djalal Harouni <tixxdz@opendz.org> Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Andy Lutomirski <luto@amacapital.net> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
procfs: make /proc/*/{stack,syscall,personality} 0400
These procfs files contain sensitive information and currently their
mode is 0444. Change this to 0400, so the VFS will be able to block
unprivileged processes from getting file descriptors on arbitrary
privileged /proc/*/{stack,syscall,personality} files.
This reduces the scope of ASLR leaking and bypasses by protecting already
running processes.
Signed-off-by: Djalal Harouni <tixxdz@opendz.org> Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Andy Lutomirski <luto@amacapital.net> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Replace rcu_assign_pointer(x, NULL) with RCU_INIT_POINTER(x, NULL)
The rcu_assign_pointer() ensures that the initialization of a structure
is carried out before storing a pointer to that structure. And in the
case of the NULL pointer, there is no structure to initialize. So,
rcu_assign_pointer(p, NULL) can be safely converted to
RCU_INIT_POINTER(p, NULL)
Signed-off-by: Monam Agarwal <monamagarwal123@gmail.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently we don't have a way how to determing from which mount point
file has been opened. This information is required for proper dumping
and restoring file descriptos due to presence of mount namespaces. It's
possible, that two file descriptors are opened using the same paths, but
one fd references mount point from one namespace while the other fd --
from other namespace.
$ ls -l /proc/1/fd/1
lrwx------ 1 root root 64 Mar 19 23:54 /proc/1/fd/1 -> /dev/null
kernel/exit.c: call proc_exit_connector() after exit_state is set
The process events connector delivers a notification when a process
exits. This is really convenient for a process that spawns and wants to
monitor its children through an epoll-able() interface.
Unfortunately, there is a small window between when the event is
delivered and the child become wait()-able.
This is creates a race if the parent wants to make sure that it knows
about the exit, e.g
pid_t pid = fork();
if (pid > 0) {
register_interest_for_pid(pid);
if (waitpid(pid, NULL, WNOHANG) > 0)
{
/* We might have raced with exit() */
}
return;
}
/* Child */
execve(...)
register_interest_for_pid() would be telling the the connector socket
reader to pay attention to events related to pid.
Though this is not a bug, I think it would make the connector a bit more
usable if this race was closed by simply moving the call to
proc_exit_connector() from just before exit_notify() to right after.
Oleg said:
: Even with this patch the code above is still "racy" if the child is
: multi-threaded. Plus it should obviously filter-out subthreads. And
: afaics there is no way to make it reliable, even if you change the code
: above so that waitpid() is called only after the last thread exits WNOHANG
: still can fail.
Signed-off-by: Guillaume Morin <guillaume@morinfr.org> Cc: Matt Helsley <matt.helsley@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: David S. Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
exit: move check_stack_usage() to the end of do_exit()
It is not clear why check_stack_usage() is called so early and thus it
never checks the stack usage in, say, exit_notify() or
flush_ptrace_hw_breakpoint() or other functions which are only called by
do_exit().
Move the callsite down to the last preempt_disable/schedule.
Minchan Kim [Mon, 7 Apr 2014 22:38:27 +0000 (15:38 -0700)]
mm/zswap: support multiple swap devices
Cai Liu reporeted that now zbud pool pages counting has a problem when
multiple swap is used because it just counts only one swap intead of all
of swap so zswap cannot control writeback properly. The result is
unnecessary writeback or no writeback when we should really writeback.
IOW, it made zswap crazy.
Another problem in zswap is:
For example, let's assume we use two swap A and B with different
priority and A already has charged 19% long time ago and let's assume
that A swap is full now so VM start to use B so that B has charged 1%
recently. It menas zswap charged (19% + 1%) is full by default. Then,
if VM want to swap out more pages into B, zbud_reclaim_page would be
evict one of pages in B's pool and it would be repeated continuously.
It's totally LRU reverse problem and swap thrashing in B would happen.
This patch makes zswap consider mutliple swap by creating *a* zbud pool
which will be shared by multiple swap so all of zswap pages in multiple
swap keep order by LRU so it can prevent above two problems.
Signed-off-by: Minchan Kim <minchan@kernel.org> Reported-by: Cai Liu <cai.liu@samsung.com> Suggested-by: Weijie Yang <weijie.yang.kh@gmail.com> Cc: Seth Jennings <sjennings@variantweb.net> Reviewed-by: Bob Liu <bob.liu@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Joonsoo Kim [Mon, 7 Apr 2014 22:38:24 +0000 (15:38 -0700)]
zram: support REQ_DISCARD
zram is ram based block device and can be used by backend of filesystem.
When filesystem deletes a file, it normally doesn't do anything on data
block of that file. It just marks on metadata of that file. This
behavior has no problem on disk based block device, but has problems on
ram based block device, since we can't free memory used for data block.
To overcome this disadvantage, there is REQ_DISCARD functionality. If
block device support REQ_DISCARD and filesystem is mounted with discard
option, filesystem sends REQ_DISCARD to block device whenever some data
blocks are discarded. All we have to do is to handle this request.
This patch implements to flag up QUEUE_FLAG_DISCARD and handle this
REQ_DISCARD request. With it, we can free memory used by zram if it isn't
used.
Minchan Kim [Mon, 7 Apr 2014 22:38:21 +0000 (15:38 -0700)]
zram: propagate error to user
When we initialized zcomp with single, we couldn't change
max_comp_streams without zram reset but current interface doesn't show
any error to user and even it changes max_comp_streams's value without
any effect so it would make user very confusing.
This patch prevents max_comp_streams's change when zcomp was initialized
as single zcomp and emit the error to user(ex, echo).
[akpm@linux-foundation.org: don't return with the lock held, per Sergey]
[fengguang.wu@intel.com: fix coccinelle warnings] Signed-off-by: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchan@redhat.com> Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Signed-off-by: Fengguang Wu <fengguang.wu@intel.com> Cc: 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>
zram: return error-valued pointer from zcomp_create()
Instead of returning just NULL, return ERR_PTR from zcomp_create() if
compressing backend creation has failed. ERR_PTR(-EINVAL) for unsupported
compression algorithm request, ERR_PTR(-ENOMEM) for allocation (zcomp or
compression stream) error.
Perform IS_ERR() check of returned from zcomp_create() value in
disksize_store() and set return code to PTR_ERR().
While fixing lockdep spew of ->init_lock reported by Sasha Levin [1],
Minchan Kim noted [2] that it's better to move compression backend
allocation (using GPF_KERNEL) out of the ->init_lock lock, same way as
with zram_meta_alloc(), in order to prevent the same lockdep spew.
Introduce LZ4 compression backend and make it available for selection.
LZ4 support is optional and requires user to set ZRAM_LZ4_COMPRESS config
option. The default compression backend is LZO.
This patch allows to change max_comp_streams on initialised zcomp.
Introduce zcomp set_max_streams() knob, zcomp_strm_multi_set_max_streams()
and zcomp_strm_single_set_max_streams() callbacks to change streams limit
for zcomp_strm_multi and zcomp_strm_single, accordingly. set_max_streams
for single steam zcomp does nothing.
If user has lowered the limit, then zcomp_strm_multi_set_max_streams()
attempts to immediately free extra streams (as much as it can, depending
on idle streams availability).
Note, this patch does not allow to change stream 'policy' from single to
multi stream (or vice versa) on already initialised compression backend.
Existing zram (zcomp) implementation has only one compression stream
(buffer and algorithm private part), so in order to prevent data
corruption only one write (compress operation) can use this compression
stream, forcing all concurrent write operations to wait for stream lock
to be released. This patch changes zcomp to keep a compression streams
list of user-defined size (via sysfs device attr). Each write operation
still exclusively holds compression stream, the difference is that we
can have N write operations (depending on size of streams list)
executing in parallel. See TEST section later in commit message for
performance data.
Introduce struct zcomp_strm_multi and a set of functions to manage
zcomp_strm stream access. zcomp_strm_multi has a list of idle
zcomp_strm structs, spinlock to protect idle list and wait queue, making
it possible to perform parallel compressions.
The following set of functions added:
- zcomp_strm_multi_find()/zcomp_strm_multi_release()
find and release a compression stream, implement required locking
- zcomp_strm_multi_create()/zcomp_strm_multi_destroy()
create and destroy zcomp_strm_multi
zcomp ->strm_find() and ->strm_release() callbacks are set during
initialisation to zcomp_strm_multi_find()/zcomp_strm_multi_release()
correspondingly.
Each time zcomp issues a zcomp_strm_multi_find() call, the following set
of operations performed:
- spin lock strm_lock
- if idle list is not empty, remove zcomp_strm from idle list, spin
unlock and return zcomp stream pointer to caller
- if idle list is empty, current adds itself to wait queue. it will be
awaken by zcomp_strm_multi_release() caller.
zcomp_strm_multi_release():
- spin lock strm_lock
- add zcomp stream to idle list
- spin unlock, wake up sleeper
Minchan Kim reported that spinlock-based locking scheme has demonstrated
a severe perfomance regression for single compression stream case,
comparing to mutex-based (see https://lkml.org/lkml/2014/2/18/16)
When only one compression stream available, mutex with spin on owner
tends to perform much better than frequent wait_event()/wake_up(). This
is why single stream implemented as a special case with mutex locking.
Introduce and document zram device attribute max_comp_streams. This
attr shows and stores current zcomp's max number of zcomp streams
(max_strm). Extend zcomp's zcomp_create() with `max_strm' parameter.
`max_strm' limits the number of zcomp_strm structs in compression
backend's idle list (max_comp_streams).
max_comp_streams used during initialisation as follows:
-- passing to zcomp_create() max_strm equals to 1 will initialise zcomp
using single compression stream zcomp_strm_single (mutex-based locking).
-- passing to zcomp_create() max_strm greater than 1 will initialise zcomp
using multi compression stream zcomp_strm_multi (spinlock-based locking).
default max_comp_streams value is 1, meaning that zram with single stream
will be initialised.
Later patch will introduce configuration knob to change max_comp_streams
on already initialised and used zcomp.
This is preparation patch to add multi stream support to zcomp.
Introduce struct zcomp_strm_single and a set of functions to manage
zcomp_strm stream access. zcomp_strm_single implements single compession
stream, same way as current zcomp implementation. This moves zcomp_strm
stream control and locking from zcomp, so compressing backend zcomp is not
aware of required locking.
Single and multi streams require different locking schemes. Minchan Kim
reported that spinlock-based locking scheme (which is used in multi stream
implementation) has demonstrated a severe perfomance regression for single
compression stream case, comparing to mutex-based. see
https://lkml.org/lkml/2014/2/18/16
The following set of functions added:
- zcomp_strm_single_find()/zcomp_strm_single_release()
find and release a compression stream, implement required locking
- zcomp_strm_single_create()/zcomp_strm_single_destroy()
create and destroy zcomp_strm_single
New ->strm_find() and ->strm_release() callbacks added to zcomp, which are
set to zcomp_strm_single_find() and zcomp_strm_single_release() during
initialisation. Instead of direct locking and zcomp_strm access from
zcomp_strm_find() and zcomp_strm_release(), zcomp now calls ->strm_find()
and ->strm_release() correspondingly.
ZRAM performs direct LZO compression algorithm calls, making it the one
and only option. While LZO is generally performs well, LZ4 algorithm
tends to have a faster decompression (see http://code.google.com/p/lz4/
for full report)
Name Ratio C.speed D.speed
MB/s MB/s
LZ4 (r101) 2.084 422 1820
LZO 2.06 2.106 414 600
Thus, users who have mostly read (decompress) usage scenarious or mixed
workflow (writes with relatively high read ops number) will benefit from
using LZ4 compression backend.
Introduce compressing backend abstraction zcomp in order to support
multiple compression algorithms with the following set of operations:
.create
.destroy
.compress
.decompress
Schematically zram write() usually contains the following steps:
0) preparation (decompression of partioal IO, etc.)
1) lock buffer_lock mutex (protects meta compress buffers)
2) compress (using meta compress buffers)
3) alloc and map zs_pool object
4) copy compressed data (from meta compress buffers) to object allocated by 3)
5) free previous pool page, assign a new one
6) unlock buffer_lock mutex
As we can see, compressing buffers must remain untouched from 1) to 4),
because, otherwise, concurrent write() can overwrite data. At the same
time, zram_meta must be aware of a) specific compression algorithm memory
requirements and b) necessary locking to protect compression buffers. To
remove requirement a) new struct zcomp_strm introduced, which contains a
compress/decompress `buffer' and compression algorithm `private' part.
While struct zcomp implements zcomp_strm stream handling and locking and
removes requirement b) from zram meta. zcomp ->create() and ->destroy(),
respectively, allocate and deallocate algorithm specific zcomp_strm
`private' part.
Every zcomp has zcomp stream and mutex to protect its compression stream.
Stream usage semantics remains the same -- only one write can hold stream
lock and use its buffers. zcomp_strm_find() turns caller into exclusive
user of a stream (holding stream mutex until zram release stream), and
zcomp_strm_release() makes zcomp stream available (unlock the stream
mutex). Hence no concurrent write (compression) operations possible at
the moment.
allocate new `zram_meta' in disksize_store() only for uninitialised zram
device, saving a number of allocations and deallocations in case if
disksize_store() was called on currently used device. at the same time
zram_meta stack variable is not necessary, because we can set ->meta
directly. there is also no need in setting QUEUE_FLAG_NONROT queue on
every disksize_store(), set it once during device creation.
This is a preparation patch for stats code duplication removal.
1) use atomic64_t for `pages_zero' and `pages_stored' zram stats.
2) `compr_size' and `pages_zero' struct zram_stats members did not
follow the existing device attr naming scheme: zram_stats.ATTR has
ATTR_show() function. rename them:
Minchan Kim's note:
If we really have trouble with atomic stat operation, we could
change it with percpu_counter so that it could solve atomic overhead and
unnecessary memory space by introducing unsigned long instead of 64bit
atomic_t.
Remove `good' and `bad' compressed sub-requests stats. RW request may
cause a number of RW sub-requests. zram used to account `good' compressed
sub-queries (with compressed size less than 50% of original size), `bad'
compressed sub-queries (with compressed size greater that 75% of original
size), leaving sub-requests with compression size between 50% and 75% of
original size not accounted and not reported. zram already accounts each
sub-request's compression size so we can calculate real device compression
ratio.
zram: do not pass rw argument to __zram_make_request()
Do not pass rw argument down the __zram_make_request() -> zram_bvec_rw()
chain, decode it in zram_bvec_rw() instead. Besides, this is the place
where we distinguish READ and WRITE bio data directions, so account zram
RW stats here, instead of __zram_make_request(). This also allows to
account a real number of zram READ/WRITE operations, not just requests
(single RW request may cause a number of zram RW ops with separate
locking, compression/decompression, etc).
Introduce init_done() helper function which allows us to drop `init_done'
struct zram member. init_done() uses the fact that ->init_done == 1
equals to ->meta != NULL.
John Hubbard [Mon, 7 Apr 2014 22:37:59 +0000 (15:37 -0700)]
mm/page_alloc.c: change mm debug routines back to EXPORT_SYMBOL
A new dump_page() routine was recently added, and marked
EXPORT_SYMBOL_GPL. dump_page() was also added to the VM_BUG_ON_PAGE()
macro, and so the end result is that non-GPL code can no longer call
get_page() and a few other routines.
This only happens if the kernel was compiled with CONFIG_DEBUG_VM.
Change dump_page() to be EXPORT_SYMBOL.
Longer explanation:
Prior to commit 309381feaee5 ("mm: dump page when hitting a VM_BUG_ON
using VM_BUG_ON_PAGE") , it was possible to build MIT-licensed (non-GPL)
drivers on Fedora. Fedora is semi-unique, in that it sets
CONFIG_VM_DEBUG.
Because Fedora sets CONFIG_VM_DEBUG, they end up pulling in dump_page(),
via VM_BUG_ON_PAGE, via get_page(). As one of the authors of NVIDIA's
new, open source, "UVM-Lite" kernel module, I originally choose to use
the kernel's get_page() routine from within nvidia_uvm_page_cache.c,
because get_page() has always seemed to be very clearly intended for use
by non-GPL, driver code.
So I'm hoping that making get_page() widely accessible again will not be
too controversial. We did check with Fedora first, and they responded
(https://bugzilla.redhat.com/show_bug.cgi?id=1074710#c3) that we should
try to get upstream changed, before asking Fedora to change. Their
reasoning seems beneficial to Linux: leaving CONFIG_DEBUG_VM set allows
Fedora to help catch mm bugs.
Signed-off-by: John Hubbard <jhubbard@nvidia.com> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Josh Boyer <jwboyer@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
numa: use LAST_CPUPID_SHIFT to calculate LAST_CPUPID_MASK
LAST_CPUPID_MASK is calculated using LAST_CPUPID_WIDTH. However
LAST_CPUPID_WIDTH itself can be 0. (when LAST_CPUPID_NOT_IN_PAGE_FLAGS is
set). In such a case LAST_CPUPID_MASK turns out to be 0.
But with recent commit 1ae71d0319: (mm: numa: bugfix for
LAST_CPUPID_NOT_IN_PAGE_FLAGS) if LAST_CPUPID_MASK is 0,
page_cpupid_xchg_last() and page_cpupid_reset_last() causes
page->_last_cpupid to be set to 0.
This causes performance regression. Its almost as if numa_balancing is
off.
Fix LAST_CPUPID_MASK by using LAST_CPUPID_SHIFT instead of
LAST_CPUPID_WIDTH.
Some performance numbers and perf stats with and without the fix.
(3.14-rc6)
----------
numa01
Performance counter stats for '/usr/bin/time -f %e %S %U %c %w -o start_bench.out -a ./numa01':
mm: hugetlb: fix softlockup when a large number of hugepages are freed.
When I decrease the value of nr_hugepage in procfs a lot, softlockup
happens. It is because there is no chance of context switch during this
process.
On the other hand, when I allocate a large number of hugepages, there is
some chance of context switch. Hence softlockup doesn't happen during
this process. So it's necessary to add the context switch in the
freeing process as same as allocating process to avoid softlockup.
When I freed 12 TB hugapages with kernel-2.6.32-358.el6, the freeing
process occupied a CPU over 150 seconds and following softlockup message
appeared twice or more.
BUG: soft lockup - CPU#16 stuck for 67s! [sh:12883] ...
Pid: 12883, comm: sh Not tainted 2.6.32-358.el6.x86_64 #1
Call Trace:
free_pool_huge_page+0xb8/0xd0
set_max_huge_pages+0x128/0x190
hugetlb_sysctl_handler_common+0x113/0x140
hugetlb_sysctl_handler+0x1e/0x20
proc_sys_call_handler+0x97/0xd0
proc_sys_write+0x14/0x20
vfs_write+0xb8/0x1a0
sys_write+0x51/0x90
__audit_syscall_exit+0x265/0x290
system_call_fastpath+0x16/0x1b
I have not confirmed this problem with upstream kernels because I am not
able to prepare the machine equipped with 12TB memory now. However I
confirmed that the amount of decreasing hugepages was directly
proportional to the amount of required time.
I measured required times on a smaller machine. It showed 130-145
hugepages decreased in a millisecond.
mm: try_to_unmap_cluster() should lock_page() before mlocking
A BUG_ON(!PageLocked) was triggered in mlock_vma_page() by Sasha Levin
fuzzing with trinity. The call site try_to_unmap_cluster() does not lock
the pages other than its check_page parameter (which is already locked).
The BUG_ON in mlock_vma_page() is not documented and its purpose is
somewhat unclear, but apparently it serializes against page migration,
which could otherwise fail to transfer the PG_mlocked flag. This would
not be fatal, as the page would be eventually encountered again, but
NR_MLOCK accounting would become distorted nevertheless. This patch adds
a comment to the BUG_ON in mlock_vma_page() and munlock_vma_page() to that
effect.
The call site try_to_unmap_cluster() is fixed so that for page !=
check_page, trylock_page() is attempted (to avoid possible deadlocks as we
already have check_page locked) and mlock_vma_page() is performed only
upon success. If the page lock cannot be obtained, the page is left
without PG_mlocked, which is again not a problem in the whole unevictable
memory design.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Bob Liu <bob.liu@oracle.com> Reported-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Michel Lespinasse <walken@google.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Mon, 7 Apr 2014 22:37:48 +0000 (15:37 -0700)]
mm: page_alloc: spill to remote nodes before waking kswapd
On NUMA systems, a node may start thrashing cache or even swap anonymous
pages while there are still free pages on remote nodes.
This is a result of commits 81c0a2bb515f ("mm: page_alloc: fair zone
allocator policy") and fff4068cba48 ("mm: page_alloc: revert NUMA aspect
of fair allocation policy").
Before those changes, the allocator would first try all allowed zones,
including those on remote nodes, before waking any kswapds. But now,
the allocator fastpath doubles as the fairness pass, which in turn can
only consider the local node to prevent remote spilling based on
exhausted fairness batches alone. Remote nodes are only considered in
the slowpath, after the kswapds are woken up. But if remote nodes still
have free memory, kswapd should not be woken to rebalance the local node
or it may thrash cash or swap prematurely.
Fix this by adding one more unfair pass over the zonelist that is
allowed to spill to remote nodes after the local fairness pass fails but
before entering the slowpath and waking the kswapds.
This also gets rid of the GFP_THISNODE exemption from the fairness
protocol because the unfair pass is no longer tied to kswapd, which
GFP_THISNODE is not allowed to wake up.
However, because remote spills can be more frequent now - we prefer them
over local kswapd reclaim - the allocation batches on remote nodes could
underflow more heavily. When resetting the batches, use
atomic_long_read() directly instead of zone_page_state() to calculate the
delta as the latter filters negative counter values.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: <stable@kernel.org> [3.12+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Some callsites pass a memcg directly, some callsites pass an mm that
then has to be translated to a memcg. This makes for a terrible
function interface.
Just push the mm-to-memcg translation into the respective callsites and
always pass a memcg to mem_cgroup_try_charge().
[mhocko@suse.cz: add charge mm helper] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michal Hocko [Mon, 7 Apr 2014 22:37:44 +0000 (15:37 -0700)]
memcg: do not replicate get_mem_cgroup_from_mm in __mem_cgroup_try_charge
__mem_cgroup_try_charge duplicates get_mem_cgroup_from_mm for charges
which came without a memcg. The only reason seems to be a tiny
optimization when css_tryget is not called if the charge can be consumed
from the stock. Nevertheless css_tryget is very cheap since it has been
reworked to use per-cpu counting so this optimization doesn't give us
anything these days.
So let's drop the code duplication so that the code is more readable.
Signed-off-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Mon, 7 Apr 2014 22:37:43 +0000 (15:37 -0700)]
memcg: get_mem_cgroup_from_mm()
Instead of returning NULL from try_get_mem_cgroup_from_mm() when the mm
owner is exiting, just return root_mem_cgroup. This makes sense for all
callsites and gets rid of some of them having to fallback manually.
[fengguang.wu@intel.com: fix warnings] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Fengguang Wu <fengguang.wu@intel.com> Acked-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Mon, 7 Apr 2014 22:37:41 +0000 (15:37 -0700)]
mm: memcg: push !mm handling out to page cache charge function
Only page cache charges can happen without an mm context, so push this
special case out of the inner core and into the cache charge function.
An ancient comment explains that the mm can also be NULL in case the
task is currently being migrated, but that is not actually true with the
current case, so just remove it.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Johannes Weiner [Mon, 7 Apr 2014 22:37:41 +0000 (15:37 -0700)]
mm: memcg: inline mem_cgroup_charge_common()
mem_cgroup_charge_common() is used by both cache and anon pages, but
most of its body only applies to anon pages and the remainder is not
worth having in a separate function.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It used to disable preemption and run sanity checks but now it's only
taking a number out of one percpu counter and putting it into another.
Do this directly in the callsite and save the indirection.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Gioh Kim [Mon, 7 Apr 2014 22:37:37 +0000 (15:37 -0700)]
mm/vmalloc.c: enhance vm_map_ram() comment
vm_map_ram() has a fragmentation problem when it cannot purge a
chunk(ie, 4M address space) if there is a pinning object in that
addresss space. So it could consume all VMALLOC address space easily.
We can fix the fragmentation problem by using vmap instead of
vm_map_ram() but vmap() is known to be slow compared to vm_map_ram().
Minchan said vm_map_ram is 5 times faster than vmap in his tests. So I
thought we should fix fragment problem of vm_map_ram because our
proprietary GPU driver has used it heavily.
On second thought, it's not an easy because we should reuse freed space
for solving the problem and it could make more IPI and bitmap operation
for searching hole. It could mitigate API's goal which is very fast
mapping. And even fragmentation problem wouldn't show in 64 bit
machine.
Another option is that the user should separate long-life and short-life
object and use vmap for long-life but vm_map_ram for short-life. If we
inform the user about the characteristic of vm_map_ram the user can
choose one according to the page lifetime.
Let's add some notice messages to user.
[akpm@linux-foundation.org: tweak comment text] Signed-off-by: Gioh Kim <gioh.kim@lge.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add unlikely and likely hints to the function mempool_free. It lays out
the code in such a way that the common path is executed straighforward and
saves a cache line.
David Rientjes [Mon, 7 Apr 2014 22:37:34 +0000 (15:37 -0700)]
mm, compaction: determine isolation mode only once
The conditions that control the isolation mode in
isolate_migratepages_range() do not change during the iteration, so
extract them out and only define the value once.
This actually does have an effect, gcc doesn't optimize it itself because
of cc->sync.
Signed-off-by: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
David Rientjes [Mon, 7 Apr 2014 22:37:30 +0000 (15:37 -0700)]
mm, mempolicy: remove per-process flag
PF_MEMPOLICY is an unnecessary optimization for CONFIG_SLAB users.
There's no significant performance degradation to checking
current->mempolicy rather than current->flags & PF_MEMPOLICY in the
allocation path, especially since this is considered unlikely().
Running TCP_RR with netperf-2.4.5 through localhost on 16 cpu machine with
64GB of memory and without a mempolicy:
Per-process flags are a scarce resource so we should free them up whenever
possible and make them available. We'll be using it shortly for memcg oom
reserves.
Signed-off-by: David Rientjes <rientjes@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Tim Hockin <thockin@google.com> Cc: Christoph Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
David Rientjes [Mon, 7 Apr 2014 22:37:29 +0000 (15:37 -0700)]
mm, mempolicy: rename slab_node for clarity
slab_node() is actually a mempolicy function, so rename it to
mempolicy_slab_node() to make it clearer that it used for processes with
mempolicies.
At the same time, cleanup its code by saving numa_mem_id() in a local
variable (since we require a node with memory, not just any node) and
remove an obsolete comment that assumes the mempolicy is actually passed
into the function.
Signed-off-by: David Rientjes <rientjes@google.com> Acked-by: Christoph Lameter <cl@linux.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Tim Hockin <thockin@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm: use macros from compiler.h instead of __attribute__((...))
To increase compiler portability there is <linux/compiler.h> which
provides convenience macros for various gcc constructs. Eg: __weak for
__attribute__((weak)). I've replaced all instances of gcc attributes with
the right macro in the memory management (/mm) subsystem.
[akpm@linux-foundation.org: while-we're-there consistency tweaks] Signed-off-by: Gideon Israel Dsouza <gidisrael@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch is a continuation of efforts trying to optimize find_vma(),
avoiding potentially expensive rbtree walks to locate a vma upon faults.
The original approach (https://lkml.org/lkml/2013/11/1/410), where the
largest vma was also cached, ended up being too specific and random,
thus further comparison with other approaches were needed. There are
two things to consider when dealing with this, the cache hit rate and
the latency of find_vma(). Improving the hit-rate does not necessarily
translate in finding the vma any faster, as the overhead of any fancy
caching schemes can be too high to consider.
We currently cache the last used vma for the whole address space, which
provides a nice optimization, reducing the total cycles in find_vma() by
up to 250%, for workloads with good locality. On the other hand, this
simple scheme is pretty much useless for workloads with poor locality.
Analyzing ebizzy runs shows that, no matter how many threads are
running, the mmap_cache hit rate is less than 2%, and in many situations
below 1%.
The proposed approach is to replace this scheme with a small per-thread
cache, maximizing hit rates at a very low maintenance cost.
Invalidations are performed by simply bumping up a 32-bit sequence
number. The only expensive operation is in the rare case of a seq
number overflow, where all caches that share the same address space are
flushed. Upon a miss, the proposed replacement policy is based on the
page number that contains the virtual address in question. Concretely,
the following results are seen on an 80 core, 8 socket x86-64 box:
1) System bootup: Most programs are single threaded, so the per-thread
scheme does improve ~50% hit rate by just adding a few more slots to
the cache.
4) Ebizzy: There's a fair amount of variation from run to run, but this
approach always shows nearly perfect hit rates, while baseline is just
about non-existent. The amounts of cycles can fluctuate between
anywhere from ~60 to ~116 for the baseline scheme, but this approach
reduces it considerably. For instance, with 80 threads:
Here's new version of faultaround patchset. It took a while to tune it
and collect performance data.
First patch adds new callback ->map_pages to vm_operations_struct.
->map_pages() is called when VM asks to map easy accessible pages.
Filesystem should find and map pages associated with offsets from
"pgoff" till "max_pgoff". ->map_pages() is called with page table
locked and must not block. If it's not possible to reach a page without
blocking, filesystem should skip it. Filesystem should use do_set_pte()
to setup page table entry. Pointer to entry associated with offset
"pgoff" is passed in "pte" field in vm_fault structure. Pointers to
entries for other offsets should be calculated relative to "pte".
Currently VM use ->map_pages only on read page fault path. We try to
map FAULT_AROUND_PAGES a time. FAULT_AROUND_PAGES is 16 for now.
Performance data for different FAULT_AROUND_ORDER is below.
TODO:
- implement ->map_pages() for shmem/tmpfs;
- modify get_user_pages() to be able to use ->map_pages() and implement
mmap(MAP_POPULATE|MAP_NONBLOCK) on top.
=========================================================================
Tested on 4-socket machine (120 threads) with 128GiB of RAM.
Few real-world workloads. The sweet spot for FAULT_AROUND_ORDER here is
somewhere between 3 and 5. Let's say 4 :)
Introduce new vm_ops callback ->map_pages() and uses it for mapping easy
accessible pages around fault address.
On read page fault, if filesystem provides ->map_pages(), we try to map up
to FAULT_AROUND_PAGES pages around page fault address in hope to reduce
number of minor page faults.
We call ->map_pages first and use ->fault() as fallback if page by the
offset is not ready to be mapped (cold page cache or something).
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Matthew Wilcox <matthew.r.wilcox@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Dave Chinner <david@fromorbit.com> Cc: Ning Qu <quning@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
After this patch 'page-types' can walk over a file's mappings and
analyze populated page cache pages mostly without disturbing its state.
It maps chunk of file, marks VMA as MADV_RANDOM to turn off readahead,
pokes VMA via mincore() to determine cached pages, triggers page-fault
only for them, and finally gathers information via pagemap/kpageflags.
Before unmap it marks VMA as MADV_SEQUENTIAL for ignoring reference
bits.
usage: page-types -f <path>
If <path> is directory it will analyse all files in all subdirectories.
Symlinks are not followed as well as mount points. Hardlinks aren't
handled, they'll be dumped as many times as they are found. Recursive
walk brings all dentries into dcache and populates page cache of
block-devices aka 'Buffers'.
Probably it's worth to add ioctl for dumping file page cache as array of
PFNs as a replacement for this hackish juggling with
mmap/madvise/mincore/pagemap. Also recursive walk could be replaced
with dumping cached inodes via some ioctl or debugfs interface followed
by openning them via open_by_handle_at, this would fix hardlinks
handling and unneeded population of dcache and buffers. This interface
might be used as data source for constructing readahead plans and for
background optimizations of actively used files.
collateral changes:
+ fix 64-bit LFS: define _FILE_OFFSET_BITS instead of _LARGEFILE64_SOURCE
+ replace lseek + read with single pread
+ make show_page_range() reusable after flush
There's no reason to enable split page table lock if don't have page
tables.
It also triggers build error at least on ARM since we don't define
pmd_page() for !MMU.
In file included from arch/arm/kernel/asm-offsets.c:14:0:
include/linux/mm.h: In function 'pte_lockptr':
include/linux/mm.h:1392:2: error: implicit declaration of function 'pmd_page' [-Werror=implicit-function-declaration]
include/linux/mm.h:1392:2: warning: passing argument 1 of 'ptlock_ptr' makes pointer from integer without a cast [enabled by default]
include/linux/mm.h:1384:27: note: expected 'struct page *' but argument is of type 'int'
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reported-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Alex Thorlton [Mon, 7 Apr 2014 22:37:12 +0000 (15:37 -0700)]
exec: kill the unnecessary mm->def_flags setting in load_elf_binary()
load_elf_binary() sets current->mm->def_flags = def_flags and def_flags
is always zero. Not only this looks strange, this is unnecessary
because mm_init() has already set ->def_flags = 0.
Signed-off-by: Alex Thorlton <athorlton@sgi.com> Suggested-by: Oleg Nesterov <oleg@redhat.com> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: David Rientjes <rientjes@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Alex Thorlton [Mon, 7 Apr 2014 22:37:10 +0000 (15:37 -0700)]
mm, thp: add VM_INIT_DEF_MASK and PRCTL_THP_DISABLE
Add VM_INIT_DEF_MASK, to allow us to set the default flags for VMs. It
also adds a prctl control which allows us to set the THP disable bit in
mm->def_flags so that VMs will pick up the setting as they are created.
Signed-off-by: Alex Thorlton <athorlton@sgi.com> Suggested-by: Oleg Nesterov <oleg@redhat.com> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: David Rientjes <rientjes@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Alex Thorlton [Mon, 7 Apr 2014 22:37:09 +0000 (15:37 -0700)]
mm: revert "thp: make MADV_HUGEPAGE check for mm->def_flags"
The main motivation behind this patch is to provide a way to disable THP
for jobs where the code cannot be modified, and using a malloc hook with
madvise is not an option (i.e. statically allocated data). This patch
allows us to do just that, without affecting other jobs running on the
system.
We need to do this sort of thing for jobs where THP hurts performance,
due to the possibility of increased remote memory accesses that can be
created by situations such as the following:
When you touch 1 byte of an untouched, contiguous 2MB chunk, a THP will
be handed out, and the THP will be stuck on whatever node the chunk was
originally referenced from. If many remote nodes need to do work on
that same chunk, they'll be making remote accesses.
With THP disabled, 4K pages can be handed out to separate nodes as
they're needed, greatly reducing the amount of remote accesses to
memory.
This patch is based on some of my work combined with some
suggestions/patches given by Oleg Nesterov. The main goal here is to
add a prctl switch to allow us to disable to THP on a per mm_struct
basis.
Here's a bit of test data with the new patch in place...
First with the flag unset:
# perf stat -a ./prctl_wrapper_mmv3 0 ./thp_pthread -C 0 -m 0 -c 512 -b 256g
Setting thp_disabled for this task...
thp_disable: 0
Set thp_disabled state to 0
Process pid = 18027
PF/
MAX MIN TOTCPU/ TOT_PF/ TOT_PF/ WSEC/
TYPE: CPUS WALL WALL SYS USER TOTCPU CPU WALL_SEC SYS_SEC CPU NODES
512 1.120 0.060 0.000 0.110 0.110 0.000 28571428864 -922337203685477580855803572 23
# perf stat -a ./prctl_wrapper_mmv3 1 ./thp_pthread -C 0 -m 0 -c 512 -b 256g
Setting thp_disabled for this task...
thp_disable: 1
Set thp_disabled state to 1
Process pid = 144957
PF/
MAX MIN TOTCPU/ TOT_PF/ TOT_PF/ WSEC/
TYPE: CPUS WALL WALL SYS USER TOTCPU CPU WALL_SEC SYS_SEC CPU NODES
512 0.620 0.260 0.250 0.320 0.570 0.001 51612901376128000000000100806448 23
As with previous versions of the patch, We're getting about a 2x
performance increase here. Here's a link to the test case I used, along
with the little wrapper to activate the flag:
Revert commit 8e72033f2a48 and add in code to fix up any issues caused
by the revert.
The revert is necessary because hugepage_madvise would return -EINVAL
when VM_NOHUGEPAGE is set, which will break subsequent chunks of this
patch set.
Here's a snip of an e-mail from Gerald detailing the original purpose of
this code, and providing justification for the revert:
"The intent of commit 8e72033f2a48 was to guard against any future
programming errors that may result in an madvice(MADV_HUGEPAGE) on
guest mappings, which would crash the kernel.
Martin suggested adding the bit to arch/s390/mm/pgtable.c, if 8e72033f2a48 was to be reverted, because that check will also prevent
a kernel crash in the case described above, it will now send a
SIGSEGV instead.
This would now also allow to do the madvise on other parts, if
needed, so it is a more flexible approach. One could also say that
it would have been better to do it this way right from the
beginning..."
Signed-off-by: Alex Thorlton <athorlton@sgi.com> Suggested-by: Oleg Nesterov <oleg@redhat.com> Tested-by: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Joonsoo Kim [Mon, 7 Apr 2014 22:37:06 +0000 (15:37 -0700)]
mm/compaction: check pageblock suitability once per pageblock
isolation_suitable() and migrate_async_suitable() is used to be sure
that this pageblock range is fine to be migragted. It isn't needed to
call it on every page. Current code do well if not suitable, but, don't
do well when suitable.
1) It re-checks isolation_suitable() on each page of a pageblock that was
already estabilished as suitable.
2) It re-checks migrate_async_suitable() on each page of a pageblock that
was not entered through the next_pageblock: label, because
last_pageblock_nr is not otherwise updated.
This patch fixes situation by 1) calling isolation_suitable() only once
per pageblock and 2) always updating last_pageblock_nr to the pageblock
that was just checked.
Additionally, move PageBuddy() check after pageblock unit check, since
pageblock check is the first thing we should do and makes things more
simple.
[vbabka@suse.cz: rephrase commit description] Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Joonsoo Kim [Mon, 7 Apr 2014 22:37:05 +0000 (15:37 -0700)]
mm/compaction: change the timing to check to drop the spinlock
It is odd to drop the spinlock when we scan (SWAP_CLUSTER_MAX - 1) th
pfn page. This may results in below situation while isolating
migratepage.
1. try isolate 0x0 ~ 0x200 pfn pages.
2. When low_pfn is 0x1ff, ((low_pfn+1) % SWAP_CLUSTER_MAX) == 0, so drop
the spinlock.
3. Then, to complete isolating, retry to aquire the lock.
I think that it is better to use SWAP_CLUSTER_MAX th pfn for checking the
criteria about dropping the lock. This has no harm 0x0 pfn, because, at
this time, locked variable would be false.
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Joonsoo Kim [Mon, 7 Apr 2014 22:37:04 +0000 (15:37 -0700)]
mm/compaction: do not call suitable_migration_target() on every page
suitable_migration_target() checks that pageblock is suitable for
migration target. In isolate_freepages_block(), it is called on every
page and this is inefficient. So make it called once per pageblock.
suitable_migration_target() also checks if page is highorder or not, but
it's criteria for highorder is pageblock order. So calling it once
within pageblock range has no problem.
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Joonsoo Kim [Mon, 7 Apr 2014 22:37:03 +0000 (15:37 -0700)]
mm/compaction: disallow high-order page for migration target
Purpose of compaction is to get a high order page. Currently, if we
find high-order page while searching migration target page, we break it
to order-0 pages and use them as migration target. It is contrary to
purpose of compaction, so disallow high-order page to be used for
migration target.
Additionally, clean-up logic in suitable_migration_target() to simplify
the code. There is no functional changes from this clean-up.
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Mel Gorman <mgorman@suse.de> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
projects / mirror_ubuntu-focal-kernel.git / log