Update the x86_64 arch_get_unmapped_area[_topdown] functions to make use
of vm_unmapped_area() instead of implementing a brute force search.
Signed-off-by: NMichel Lespinasse <walken@google.com>
Reviewed-by: NRik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Implement vm_unmapped_area() using the rb_subtree_gap and highest_vm_end
information to look up for suitable virtual address space gaps.

struct vm_unmapped_area_info is used to define the desired allocation
request:
 - lowest or highest possible address matching the remaining constraints
 - desired gap length
 - low/high address limits that the gap must fit into
 - alignment mask and offset

Also update the generic arch_get_unmapped_area[_topdown] functions to make
use of vm_unmapped_area() instead of implementing a brute force search.

[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: NMichel Lespinasse <walken@google.com>
Reviewed-by: NRik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The kernel walks the VMA rbtree in various places, including the page
fault path.  However, the vm_rb node spanned two cache lines, on 64 bit
systems with 64 byte cache lines (most x86 systems).

Rearrange vm_area_struct a little, so all the information we need to do a
VMA tree walk is in the first cache line.

[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: NMichel Lespinasse <walken@google.com>
Signed-off-by: NRik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When CONFIG_DEBUG_VM_RB is enabled, check that rb_subtree_gap is correctly
set for every vma and that mm->highest_vm_end is also correct.

Also add an explicit 'bug' variable to track if browse_rb() detected any
invalid condition.

[akpm@linux-foundation.org: repair innovative coding-style inventions]
Signed-off-by: NMichel Lespinasse <walken@google.com>
Reviewed-by: NRik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Define vma->rb_subtree_gap as the largest gap between any vma in the
subtree rooted at that vma, and their predecessor.  Or, for a recursive
definition, vma->rb_subtree_gap is the max of:

 - vma->vm_start - vma->vm_prev->vm_end
 - rb_subtree_gap fields of the vmas pointed by vma->rb.rb_left and
   vma->rb.rb_right

This will allow get_unmapped_area_* to find a free area of the right
size in O(log(N)) time, instead of potentially having to do a linear
walk across all the VMAs.

Also define mm->highest_vm_end as the vm_end field of the highest vma,
so that we can easily check if the following gap is suitable.

This does have the potential to make unmapping VMAs more expensive,
especially for processes with very large numbers of VMAs, where the VMA
rbtree can grow quite deep.
Signed-off-by: NMichel Lespinasse <walken@google.com>
Reviewed-by: NRik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Also remove -Wextra because gcc-4.6 emits lots of irritating
signed/unsigned comparison warnings.
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

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: NAndi Kleen <ak@linux.intel.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Acked-by: NRik van Riel <riel@redhat.com>
Acked-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hillf Danton <dhillf@gmail.com>
Signed-off-by: NDavid Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

action_result() fails to print out "dirty" even if an error occurred on
a dirty pagecache, because when we check PageDirty in action_result() it
was cleared after page isolation even if it's dirty before error
handling.  This can break some applications that monitor this message,
so should be fixed.

There are several callers of action_result() except page_action(), but
either of them are not for LRU pages but for free pages or kernel pages,
so we don't have to consider dirty or not for them.

Note that PG_dirty can be set outside page locks as described in commit
6746aff7 ("HWPOISON: shmem: call set_page_dirty() with locked
page"), so this patch does not completely closes the race window, but
just narrows it.
Signed-off-by: NNaoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reviewed-by: NAndi Kleen <ak@linux.intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: "Jun'ichi Nomura" <j-nomura@ce.jp.nec.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This can help to catch the case where hardware is writing after dma free.

[akpm@linux-foundation.org: tidy code, fix comment, use sizeof(page->offset), use pr_err()]
Signed-off-by: NMatthieu Castet <matthieu.castet@parrot.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Exiting threads, those with PF_EXITING set, can pagefault and require
memory before they can make forward progress.  This happens, for instance,
when a process must fault task->robust_list, a userspace structure, before
detaching its memory.

These threads also aren't guaranteed to get access to memory reserves
unless oom killed or killed from userspace.  The oom killer won't grant
memory reserves if other threads are also exiting other than current and
stalling at the same point.  This prevents needlessly killing processes
when others are already exiting.

Instead of special casing all the possible situations between PF_EXITING
getting set and a thread detaching its mm where it may allocate memory,
which probably wouldn't get updated when a change is made to the exit
path, the solution is to give all exiting threads access to memory
reserves if they call the oom killer.  This allows them to quickly
allocate, detach its mm, and free the memory it represents.

Summary of Luigi's bug report:

: He had an oom condition where threads were faulting on task->robust_list
: and repeatedly called the oom killer but it would defer killing a thread
: because it saw other PF_EXITING threads.  This can happen anytime we need
: to allocate memory after setting PF_EXITING and before detaching our mm;
: if there are other threads in the same state then the oom killer won't do
: anything unless one of them happens to be killed from userspace.
:
: So instead of only deferring for PF_EXITING and !task->robust_list, it's
: better to just give them access to memory reserves to prevent a potential
: livelock so that any other faults that may be introduced in the future in
: the exit path don't cause the same problem (and hopefully we don't allow
: too many of those!).
Signed-off-by: NDavid Rientjes <rientjes@google.com>
Acked-by: NMinchan Kim <minchan@kernel.org>
Tested-by: NLuigi Semenzato <semenzato@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

mem_cgroup_charge_common() is invoked as the entry point for cgroup limits
charge rather than mem_cgroup_charge(), as the later has been removed for
years.  Update the cgroup/memory.txt to reflect this change.
Signed-off-by: NJie Liu <jeff.liu@oracle.com>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

On x86 memory accesses to pages without the ACCESSED flag set result in
the ACCESSED flag being set automatically.  With the ARM architecture a
page access fault is raised instead (and it will continue to be raised
until the ACCESSED flag is set for the appropriate PTE/PMD).

For normal memory pages, handle_pte_fault will call pte_mkyoung
(effectively setting the ACCESSED flag).  For transparent huge pages,
pmd_mkyoung will only be called for a write fault.

This patch ensures that faults on transparent hugepages which do not
result in a CoW update the access flags for the faulting pmd.
Signed-off-by: NWill Deacon <will.deacon@arm.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: NKirill A. Shutemov <kirill@shutemov.name>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: NJohannes Weiner <hannes@cmpxchg.org>
Cc: Ni zhan Chen <nizhan.chen@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

In flush_all_zero_pkmaps(), we have an index of the pkmap associated with
the page.  Using this index, we can simply get virtual address of the
page.  So change it.
Signed-off-by: NJoonsoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: NMinchan Kim <minchan@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

We can find free page_address_map instance without the page_address_pool.
So remove it.
Signed-off-by: NJoonsoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: NMinchan Kim <minchan@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The pool_lock protects the page_address_pool from concurrent access.  But,
access to the page_address_pool is already protected by kmap_lock.  So
remove it.
Signed-off-by: NJoonsoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: NMinchan Kin <minchan@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

To calculate an index of pkmap, using PKMAP_NR() is more understandable
and maintainable, so change it.
Signed-off-by: NJoonsoo Kim <js1304@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: NMinchan Kim <minchan@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The call to frontswap_init() was added within enable_swap_info(), which
was called not only during sys_swapon, but also to reinsert the swap_info
into the swap_list in case of failure of try_to_unuse() within
sys_swapoff.  This means that frontswap_init() might be called more than
once for the same swap area.

While as far as I could see no frontswap implementation has any problem
with it (and in fact, all the ones I found ignore the parameter passed to
frontswap_init), this could change in the future.

To prevent future problems, move the call to frontswap_init() to outside
the code shared between sys_swapon and sys_swapoff.
Signed-off-by: NCesar Eduardo Barros <cesarb@cesarb.net>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: NDan Magenheimer <dan.magenheimer@oracle.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The block within sys_swapoff() which re-inserts the swap_info into the
swap_list in case of failure of try_to_unuse() reads a few values outside
the swap_lock.  While this is safe at that point, it is subtle code.

Simplify the code by moving the reading of these values to a separate
function, refactoring it a bit so they are read from within the swap_lock.
 This is easier to understand, and matches better the way it worked before
I unified the insertion of the swap_info from both sys_swapon and
sys_swapoff.

This change should make no functional difference.  The only real change is
moving the read of two or three structure fields to within the lock
(frontswap_map_get() is nothing more than a read of p->frontswap_map).
Signed-off-by: NCesar Eduardo Barros <cesarb@cesarb.net>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

If we have more inactive file pages than active file pages, we skip
scanning the active file pages altogether, with the idea that we do not
want to evict the working set when there is plenty of streaming IO in the
cache.

However, the code forgot to also skip scanning anonymous pages in that
situation.  That leads to the curious situation of keeping the active file
pages protected from being paged out when there are lots of inactive file
pages, while still scanning and evicting anonymous pages.

This patch fixes that situation, by only evicting file pages when we have
plenty of them and most are inactive.

[akpm@linux-foundation.org: adjust comment layout]
Signed-off-by: NRik van Riel <riel@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Add comments that dirty bit in storage key gets set whenever page content
is changed.  Hopefully if someone will use this function, he'll have a
look at one of the two places where we comment on this.
Signed-off-by: NJan Kara <jack@suse.cz>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

If we hot-remove memory only and leave the cpus alive, the corresponding
node will not be removed.  But the node_start_pfn and node_spanned_pages
in pg_data will be reset to 0.  In this case, when we hot-add the memory
back next time, the node_start_pfn will always be 0 because no pfn is less
than 0.  After that, if we hot-remove the memory again, it will cause
kernel panic in function find_biggest_section_pfn() when it tries to scan
all the pfns.

The zone will also have the same problem.

This patch sets start_pfn to the start_pfn of the section being added when
spanned_pages of the zone or pg_data is 0.

  ---How to reproduce---

1. hot-add a container with some memory and cpus;
2. hot-remove the container's memory, and leave cpus there;
3. hot-add these memory again;
4. hot-remove them again;

then, the kernel will panic.

  ---Call trace---

  BUG: unable to handle kernel paging request at 00000fff82a8cc38
  IP: [<ffffffff811c0d55>] find_biggest_section_pfn+0xe5/0x180
  ......
  Call Trace:
   [<ffffffff811c1124>] __remove_zone+0x184/0x1b0
   [<ffffffff811c11dc>] __remove_section+0x8c/0xb0
   [<ffffffff811c12e7>] __remove_pages+0xe7/0x120
   [<ffffffff81654f7c>] arch_remove_memory+0x2c/0x80
   [<ffffffff81655bb6>] remove_memory+0x56/0x90
   [<ffffffff813da0c8>] acpi_memory_device_remove_memory+0x48/0x73
   [<ffffffff813da55a>] acpi_memory_device_notify+0x153/0x274
   [<ffffffff813b6786>] acpi_ev_notify_dispatch+0x41/0x5f
   [<ffffffff813a3867>] acpi_os_execute_deferred+0x27/0x34
   [<ffffffff81090589>] process_one_work+0x219/0x680
   [<ffffffff810923be>] worker_thread+0x12e/0x320
   [<ffffffff81098396>] kthread+0xc6/0xd0
   [<ffffffff8167c7c4>] kernel_thread_helper+0x4/0x10
  ......
  ---[ end trace 96d845dbf33fee11 ]---
Signed-off-by: NTang Chen <tangchen@cn.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

SLUB only focuses on the nodes which have normal memory and it ignores the
other node's hot-adding and hot-removing.

Aka: if some memory of a node which has no onlined memory is online, but
this new memory onlined is not normal memory (for example, highmem), we
should not allocate kmem_cache_node for SLUB.

And if the last normal memory is offlined, but the node still has memory,
we should remove kmem_cache_node for that node.  (The current code delays
it when all of the memory is offlined)

So we only do something when marg->status_change_nid_normal > 0.
marg->status_change_nid is not suitable here.

The same problem doesn't exist in SLAB, because SLAB allocates kmem_list3
for every node even the node don't have normal memory, SLAB tolerates
kmem_list3 on alien nodes.  SLUB only focuses on the nodes which have
normal memory, it don't tolerate alien kmem_cache_node.  The patch makes
SLUB become self-compatible and avoids WARNs and BUGs in rare conditions.
Signed-off-by: NLai Jiangshan <laijs@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Rob Landley <rob@landley.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Greg Kroah-Hartman <gregkh@suse.de>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Acked-by: NChristoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Currently memory_hotplug only manages the node_states[N_HIGH_MEMORY], it
forgets to manage node_states[N_NORMAL_MEMORY].  This may cause
node_states[N_NORMAL_MEMORY] to become incorrect.

Example, if a node is empty before online, and we online a memory which is
in ZONE_NORMAL.  And after online, node_states[N_HIGH_MEMORY] is correct,
but node_states[N_NORMAL_MEMORY] is incorrect, the online code doesn't set
the new online node to node_states[N_NORMAL_MEMORY].

The same thing will happen when offlining (the offline code doesn't clear
the node from node_states[N_NORMAL_MEMORY] when needed).  Some memory
managment code depends node_states[N_NORMAL_MEMORY], so we have to fix up
the node_states[N_NORMAL_MEMORY].

We add node_states_check_changes_online() and
node_states_check_changes_offline() to detect whether
node_states[N_HIGH_MEMORY] and node_states[N_NORMAL_MEMORY] are changed
while hotpluging.

Also add @status_change_nid_normal to struct memory_notify, thus the
memory hotplug callbacks know whether the node_states[N_NORMAL_MEMORY] are
changed.  (We can add a @flags and reuse @status_change_nid instead of
introducing @status_change_nid_normal, but it will add much more
complexity in memory hotplug callback in every subsystem.  So introducing
@status_change_nid_normal is better and it doesn't change the sematics of
@status_change_nid)
Signed-off-by: NLai Jiangshan <laijs@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Rob Landley <rob@landley.net>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Greg Kroah-Hartman <gregkh@suse.de>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

We use __free_page() to put a page to buddy system when onlining pages.
__free_page() will store NR_FREE_PAGES in zone's pcp.vm_stat_diff, so we
should allocate zone's pcp before onlining pages, otherwise we will lose
some free pages.

[mhocko@suse.cz: make zone_pcp_reset independent of MEMORY_HOTREMOVE]
Signed-off-by: NWen Congyang <wency@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: NMichal Hocko <mhocko@suse.cz>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

If sparse memory vmemmap is enabled, we can't free the memory to store
struct page when a memory device is hotremoved, because we may store
struct page in the memory to manage the memory which doesn't belong to
this memory device.  When we hotadded this memory device again, we will
reuse this memory to store struct page, and struct page may contain some
obsolete information, and we will get bad-page state:

  init_memory_mapping: [mem 0x80000000-0x9fffffff]
  Built 2 zonelists in Node order, mobility grouping on.  Total pages: 547617
  Policy zone: Normal
  BUG: Bad page state in process bash  pfn:9b6dc
  page:ffffea0002200020 count:0 mapcount:0 mapping:          (null) index:0xfdfdfdfdfdfdfdfd
  page flags: 0x2fdfdfdfd5df9fd(locked|referenced|uptodate|dirty|lru|active|slab|owner_priv_1|private|private_2|writeback|head|tail|swapcache|reclaim|swapbacked|unevictable|uncached|compound_lock)
  Modules linked in: netconsole acpiphp pci_hotplug acpi_memhotplug loop kvm_amd kvm microcode tpm_tis tpm tpm_bios evdev psmouse serio_raw i2c_piix4 i2c_core parport_pc parport processor button thermal_sys ext3 jbd mbcache sg sr_mod cdrom ata_generic virtio_net ata_piix virtio_blk libata virtio_pci virtio_ring virtio scsi_mod
  Pid: 988, comm: bash Not tainted 3.6.0-rc7-guest #12
  Call Trace:
   [<ffffffff810e9b30>] ? bad_page+0xb0/0x100
   [<ffffffff810ea4c3>] ? free_pages_prepare+0xb3/0x100
   [<ffffffff810ea668>] ? free_hot_cold_page+0x48/0x1a0
   [<ffffffff8112cc08>] ? online_pages_range+0x68/0xa0
   [<ffffffff8112cba0>] ? __online_page_increment_counters+0x10/0x10
   [<ffffffff81045561>] ? walk_system_ram_range+0x101/0x110
   [<ffffffff814c4f95>] ? online_pages+0x1a5/0x2b0
   [<ffffffff8135663d>] ? __memory_block_change_state+0x20d/0x270
   [<ffffffff81356756>] ? store_mem_state+0xb6/0xf0
   [<ffffffff8119e482>] ? sysfs_write_file+0xd2/0x160
   [<ffffffff8113769a>] ? vfs_write+0xaa/0x160
   [<ffffffff81137977>] ? sys_write+0x47/0x90
   [<ffffffff814e2f25>] ? async_page_fault+0x25/0x30
   [<ffffffff814ea239>] ? system_call_fastpath+0x16/0x1b
  Disabling lock debugging due to kernel taint

This patch clears the memory to store struct page to avoid unexpected error.
Signed-off-by: NWen Congyang <wency@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Acked-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Reported-by: NVasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When calling unregister_node(), the function shows following message at
device_release().

"Device 'node2' does not have a release() function, it is broken and must
be fixed."

The reason is node's device struct does not have a release() function.

So the patch registers node_device_release() to the device's release()
function for suppressing the warning message.  Additionally, the patch
adds memset() to initialize a node struct into register_node().  Because
the node struct is part of node_devices[] array and it cannot be freed by
node_device_release().  So if system reuses the node struct, it has a
garbage.
Signed-off-by: NYasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Signed-off-by: NWen Congyang <wency@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

We use a static array to store struct node.  In many cases, we don't have
too many nodes, and some memory will be unused.  Convert it to per-device
dynamically allocated memory.
Signed-off-by: NWen Congyang <wency@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

NR_FREE_PAGES will be wrong after offlining pages.  We add/dec
NR_FREE_PAGES like this now:

1. move all pages in buddy system to MIGRATE_ISOLATE, and dec NR_FREE_PAGES

2. don't add NR_FREE_PAGES when it is freed and the migratetype is
   MIGRATE_ISOLATE

3. dec NR_FREE_PAGES when offlining isolated pages.

4. add NR_FREE_PAGES when undoing isolate pages.

When we come to step 3, all pages are in MIGRATE_ISOLATE list, and
NR_FREE_PAGES are right.  When we come to step4, all pages are not in
buddy system, so we don't change NR_FREE_PAGES in this step, but we change
NR_FREE_PAGES in step3.  So NR_FREE_PAGES is wrong after offlining pages.
So there is no need to change NR_FREE_PAGES in step3.

This patch also fixs a problem in step2: if the migratetype is
MIGRATE_ISOLATE, we should not add NR_FRR_PAGES when we remove pages from
pcppages.
Signed-off-by: NWen Congyang <wency@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Jianguo Wu <wujianguo106@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When a memory block is onlined, we will try allocate memory on that node
to store page_cgroup.  If onlining the memory block failed, we don't
offline the page cgroup, and we have no chance to offline this page cgroup
unless the memory block is onlined successfully again.  It will cause that
we can't hot-remove the memory device on that node, because some memory is
used to store page cgroup.  If onlining the memory block is failed, there
is no need to stort page cgroup for this memory.  So auto offline
page_cgroup when onlining memory block failed.
Signed-off-by: NWen Congyang <wency@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Acked-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When we hotremove a memory device, we will free the memory to store struct
page.  If the page is hwpoisoned page, we should decrease mce_bad_pages.

[akpm@linux-foundation.org: cleanup ifdefs]
Signed-off-by: NWen Congyang <wency@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

hwpoisoned may be set when we offline a page by the sysfs interface
/sys/devices/system/memory/soft_offline_page or
/sys/devices/system/memory/hard_offline_page. If we don't clear
this flag when onlining pages, this page can't be freed, and will
not in free list. So we can't offline these pages again. So we
should skip such page when offlining pages.
Signed-off-by: NWen Congyang <wency@cn.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When calling remove_memory_block(), the function shows following message
at device_release().

"Device 'memory528' does not have a release() function, it is broken and
must be fixed."

The reason is memory_block's device struct does not have a release()
function.

So the patch registers memory_block_release() to the device's release()
function for suppressing the warning message.  Additionally, the patch
moves kfree(mem) into the release function since the release function is
prepared as a means to free a memory_block struct.
Signed-off-by: NYasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Acked-by: NDavid Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Acked-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Wen Congyang <wency@cn.fujitsu.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Introduce mk_huge_pmd() to simplify the code
Signed-off-by: NBob Liu <lliubbo@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Ni zhan Chen <nizhan.chen@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Multiple places do the same check.
Signed-off-by: NBob Liu <lliubbo@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Ni zhan Chen <nizhan.chen@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Several place need to find the pmd by(mm_struct, address), so introduce a
function to simplify it.

[akpm@linux-foundation.org: fix warning]
Signed-off-by: NBob Liu <lliubbo@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Ni zhan Chen <nizhan.chen@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

There are duplicated places using release_pte_pages().
And release_all_pte_pages() can be removed.
Signed-off-by: NBob Liu <lliubbo@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Ni zhan Chen <nizhan.chen@gmail.com>
Acked-by: NDavid Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

We don't need custom COMPACTION_BUILD anymore, since we have handy
IS_ENABLED().
Signed-off-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: NMinchan Kim <minchan@kernel.org>
Acked-by: NDavid Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

We don't need custom NUMA_BUILD anymore, since we have handy
IS_ENABLED().
Signed-off-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: NDavid Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

mem_cgroup_out_of_memory() is only referenced from within file scope, so
it can be marked static.
Signed-off-by: NDavid Rientjes <rientjes@google.com>
Acked-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: NMichal Hocko <mhocko@suse.cz>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This is useful to diagnose the reason for page allocation failure for
cases where there appear to be several free pages.

Example, with this alloc_pages(GFP_ATOMIC) failure:

 swapper/0: page allocation failure: order:0, mode:0x0
 ...
 Mem-info:
 Normal per-cpu:
 CPU    0: hi:   90, btch:  15 usd:  48
 CPU    1: hi:   90, btch:  15 usd:  21
 active_anon:0 inactive_anon:0 isolated_anon:0
  active_file:0 inactive_file:84 isolated_file:0
  unevictable:0 dirty:0 writeback:0 unstable:0
  free:4026 slab_reclaimable:75 slab_unreclaimable:484
  mapped:0 shmem:0 pagetables:0 bounce:0
 Normal free:16104kB min:2296kB low:2868kB high:3444kB active_anon:0kB
 inactive_anon:0kB active_file:0kB inactive_file:336kB unevictable:0kB
 isolated(anon):0kB isolated(file):0kB present:331776kB mlocked:0kB
 dirty:0kB writeback:0kB mapped:0kB shmem:0kB slab_reclaimable:300kB
 slab_unreclaimable:1936kB kernel_stack:328kB pagetables:0kB unstable:0kB
 bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no
 lowmem_reserve[]: 0 0

Before the patch, it's hard (for me, at least) to say why all these free
chunks weren't considered for allocation:

 Normal: 0*4kB 0*8kB 0*16kB 0*32kB 0*64kB 0*128kB 1*256kB 1*512kB
 1*1024kB 1*2048kB 3*4096kB = 16128kB

After the patch, it's obvious that the reason is that all of these are
in the MIGRATE_CMA (C) freelist:

 Normal: 0*4kB 0*8kB 0*16kB 0*32kB 0*64kB 0*128kB 1*256kB (C) 1*512kB
 (C) 1*1024kB (C) 1*2048kB (C) 3*4096kB (C) = 16128kB
Signed-off-by: NRabin Vincent <rabin.vincent@stericsson.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>