Down, down in the deepest depths of GFP_NOIO page reclaim, we have
shrink_page_list() calling __remove_mapping() calling __delete_from_
swap_cache() or __delete_from_page_cache().

You would not expect those to need much stack, but in fact they call
radix_tree_delete(): which declares a 192-byte radix_tree_path array on
its stack (to record the node,offsets it visits when descending, in case
it needs to ascend to update them).  And if any tag is still set [1],
that calls radix_tree_tag_clear(), which declares a further such
192-byte radix_tree_path array on the stack.  (At least we have
interrupts disabled here, so won't then be pushing registers too.)

That was probably a good choice when most users were 32-bit (array of
half the size), and adding fields to radix_tree_node would have bloated
it unnecessarily.  But nowadays many are 64-bit, and each
radix_tree_node contains a struct rcu_head, which is only used when
freeing; whereas the radix_tree_path info is only used for updating the
tree (deleting, clearing tags or setting tags if tagged) when a lock
must be held, of no interest when accessing the tree locklessly.

So add a parent pointer to the radix_tree_node, in union with the
rcu_head, and remove all uses of the radix_tree_path.  There would be
space in that union to save the offset when descending as before (we can
argue that a lock must already be held to exclude other users), but
recalculating it when ascending is both easy (a constant shift and a
constant mask) and uncommon, so it seems better just to do that.

Two little optimizations: no need to decrement height when descending,
adjusting shift is enough; and once radix_tree_tag_if_tagged() has set
tag on a node and its ancestors, it need not ascend from that node
again.

perf on the radix tree test harness reports radix_tree_insert() as 2%
slower (now having to set parent), but radix_tree_delete() 24% faster.
Surely that's an exaggeration from rtth's artificially low map shift 3,
but forcing it back to 6 still rates radix_tree_delete() 8% faster.

[1] Can a pagecache tag (dirty, writeback or towrite) actually still be
set at the time of radix_tree_delete()? Perhaps not if the filesystem is
well-behaved.  But although I've not tracked any stack overflow down to
this cause, I have observed a curious case in which a dirty tag is set
and left set on tmpfs: page migration's migrate_page_copy() happens to
use __set_page_dirty_nobuffers() to set PageDirty on the newpage, and
that sets PAGECACHE_TAG_DIRTY as a side-effect - harmless to a
filesystem which doesn't use tags, except for this stack depth issue.
Signed-off-by: NHugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Nai Xia <nai.xia@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

It is not used anymore, remove it
Signed-off-by: NXiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Acked-by: NHugh Dickins <hughd@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Some investigation of a transaction processing workload showed that a
major consumer of cycles in __blockdev_direct_IO is the cache miss while
accessing the block size.  This is because it has to walk the chain from
block_dev to gendisk to queue.

The block size is needed early on to check alignment and sizes.  It's only
done if the check for the inode block size fails.  But the costly block
device state is unconditionally fetched.

- Reorganize the code to only fetch block dev state when actually
  needed.

Then do a prefetch on the block dev early on in the direct IO path.  This
is worth it, because there is substantial code run before we actually
touch the block dev now.

- I also added some unlikelies to make it clear the compiler that block
  device fetch code is not normally executed.

This gave a small, but measurable improvement on a large database
benchmark (about 0.3%)

[akpm@linux-foundation.org: coding-style fixes]
[sfr@canb.auug.org.au: using prefetch requires including prefetch.h]
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NStephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This makes it possible to get from the inode to the request_queue with one
less cache miss.  Used in followon optimization.

The livetime of the pointer is the same as the gendisk.

This assumes that the queue will always stay the same in the gendisk while
it's visible to block_devices.  I think that's safe correct?
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Acked-by: NJeff Moyer <jmoyer@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

In get_more_blocks(), we use dio_count to calcuate fs_count and do some
tricky things to increase fs_count if dio_count isn't aligned.  But
actually it still has some corner cases that can't be coverd.  See the
following example:

	dio_write foo -s 1024 -w 4096

(direct write 4096 bytes at offset 1024).  The same goes if the offset
isn't aligned to fs_blocksize.

In this case, the old calculation counts fs_count to be 1, but actually we
will write into 2 different blocks (if fs_blocksize=4096).  The old code
just works, since it will call get_block twice (and may have to allocate
and create extents twice for filesystems like ext4).  So we'd better call
get_block just once with the proper fs_count.
Signed-off-by: NTao Ma <boyu.mt@taobao.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

drivers/parport/parport_pc.c: In function '__check_irq':
drivers/parport/parport_pc.c:3415: warning: return from incompatible pointer type
drivers/parport/parport_pc.c: In function '__check_dma':
drivers/parport/parport_pc.c:3417: warning: return from incompatible pointer type
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When an oops causes a panic and panic prints another backtrace it's pretty
common to have the original oops data be scrolled away on a 80x50 screen.

The second backtrace is quite redundant and not needed anyways.

So don't print the panic backtrace when oops_in_progress is true.

[akpm@linux-foundation.org: add comment]
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Cc: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The sysctl works on the current task's pid namespace, getting and setting
its last_pid field.

Writing is allowed for CAP_SYS_ADMIN-capable tasks thus making it possible
to create a task with desired pid value.  This ability is required badly
for the checkpoint/restore in userspace.

This approach suits all the parties for now.
Signed-off-by: NPavel Emelyanov <xemul@parallels.com>
Acked-by: NTejun Heo <tj@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Currently no udev events for memory hotplug "online" and "offline" are
generated:

  # udevadm monitor
  # echo offline > /sys/devices/system/memory/memory4/state
  ==> No event

When kdump is loaded, kexec detects the current memory configuration and
stores it in the pre-allocated ELF core header.  Therefore, for kdump it
is necessary to reload the kdump kernel with kexec when the memory
configuration changes (e.g.  for online/offline hotplug memory).

In order to do this automatically, udev rules should be used.  This kernel
patch adds udev events for "online" and "offline".  Together with this
kernel patch, the following udev rules for online/offline have to be added
to "/etc/udev/rules.d/98-kexec.rules":

  SUBSYSTEM=="memory", ACTION=="online", PROGRAM="/etc/init.d/kdump restart"
  SUBSYSTEM=="memory", ACTION=="offline", PROGRAM="/etc/init.d/kdump restart"

[sfr@canb.auug.org.au: fixups for class to subsystem conversion]
Signed-off-by: NMichael Holzheu <holzheu@linux.vnet.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: NStephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Building an ARM target we get the following warnings:

  CC      arch/arm/kernel/setup.o
  In file included from arch/arm/kernel/setup.c:39:
  arch/arm/include/asm/elf.h:102:1: warning: "vmcore_elf64_check_arch" redefined
  In file included from arch/arm/kernel/setup.c:24:
  include/linux/crash_dump.h:30:1: warning: this is the location of the previous definition

Quoting Russell King:

"linux/crash_dump.h makes no attempt to include asm/elf.h, but it depends
on stuff in asm/elf.h to determine how stuff inside this file is defined
at parse time.

So, if asm/elf.h is included after linux/crash_dump.h or not at all, you
get a different result from the situation where asm/elf.h is included
before."

So add elf.h header to crash_dump.h to avoid this problem.

The original discussion about this can be found at:
http://www.spinics.net/lists/arm-kernel/msg154113.htmlSigned-off-by: NFabio Estevam <fabio.estevam@freescale.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: <stable@vger.kernel.org>	[3.2.1]
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When two CPUs call panic at the same time there is a possible race
condition that can stop kdump.  The first CPU calls crash_kexec() and the
second CPU calls smp_send_stop() in panic() before crash_kexec() finished
on the first CPU.  So the second CPU stops the first CPU and therefore
kdump fails:

1st CPU:
  panic()->crash_kexec()->mutex_trylock(&kexec_mutex)-> do kdump

2nd CPU:
  panic()->crash_kexec()->kexec_mutex already held by 1st CPU
       ->smp_send_stop()-> stop 1st CPU (stop kdump)

This patch fixes the problem by introducing a spinlock in panic that
allows only one CPU to process crash_kexec() and the subsequent panic
code.

All other CPUs call the weak function panic_smp_self_stop() that stops the
CPU itself.  This function can be overloaded by architecture code.  For
example "tile" can use their lower-power "nap" instruction for that.
Signed-off-by: NMichael Holzheu <holzheu@linux.vnet.ibm.com>
Acked-by: NChris Metcalf <cmetcalf@tilera.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Currently it is possible to set the crash_size via the sysfs
/sys/kernel/kexec_crash_size even if no crash kernel memory has been
defined with the "crashkernel" parameter.  In this case "crashk_res" is
not initialized and crashk_res.start = crashk_res.end = 0.  Unfortunately
resource_size(&crashk_res) returns 1 in this case.  This breaks the s390
implementation of crash_(un)map_reserved_pages().

To fix the problem the correct "old_size" is now calculated in
crash_shrink_memory().  "old_size is set to "0" if crashk_res is not
initialized.  With this change crash_shrink_memory() will do nothing, when
"crashk_res" is not initialized.  It will return "0" for "echo 0 >
/sys/kernel/kexec_crash_size" and -EINVAL for "echo [not zero] >
/sys/kernel/kexec_crash_size".

In addition to that this patch also simplifies the "ret = -EINVAL" vs.
"ret = 0" logic as suggested by Simon Horman.
Signed-off-by: NMichael Holzheu <holzheu@linux.vnet.ibm.com>
Reviewed-by: NDave Young <dyoung@redhat.com>
Reviewed-by: NWANG Cong <xiyou.wangcong@gmail.com>
Reviewed-by: NSimon Horman <horms@verge.net.au>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When shrinking crashkernel memory using /sys/kernel/kexec_crash_size for
the newly added memory no RAM resource is created at the moment.

Example:

  $ cat /proc/iomem
  00000000-bfffffff : System RAM
    00000000-005b7ac3 : Kernel code
    005b7ac4-009743bf : Kernel data
    009bb000-00a85c33 : Kernel bss
  c0000000-cfffffff : Crash kernel
  d0000000-ffffffff : System RAM

  $ echo 0 > /sys/kernel/kexec_crash_size
  $ cat /proc/iomem
  00000000-bfffffff : System RAM
    00000000-005b7ac3 : Kernel code
    005b7ac4-009743bf : Kernel data
    009bb000-00a85c33 : Kernel bss
                                   <<-- here is System RAM missing
  d0000000-ffffffff : System RAM

One result of this bug is that the memory chunk can never be set offline
using memory hotplug.  With this patch I insert a new "System RAM"
resource for the released memory.  Then the upper example looks like the
following:

  $ echo 0 > /sys/kernel/kexec_crash_size
  $ cat /proc/iomem
  00000000-bfffffff : System RAM
    00000000-005b7ac3 : Kernel code
    005b7ac4-009743bf : Kernel data
    009bb000-00a85c33 : Kernel bss
  c0000000-cfffffff : System RAM   <<-- new rescoure
  d0000000-ffffffff : System RAM

And now I can set chunk c0000000-cfffffff offline.
Signed-off-by: NMichael Holzheu <holzheu@linux.vnet.ibm.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

KMSG_DUMP_KEXEC is useless because we already save kernel messages inside
/proc/vmcore, and it is unsafe to allow modules to do other stuffs in a
crash dump scenario.

[akpm@linux-foundation.org: fix powerpc build]
Signed-off-by: NWANG Cong <xiyou.wangcong@gmail.com>
Reported-by: NVivek Goyal <vgoyal@redhat.com>
Acked-by: NVivek Goyal <vgoyal@redhat.com>
Acked-by: NJarod Wilson <jarod@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.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>

node_to_cpumask() has been replaced by cpumask_of_node(), and wholly
removed since commit 29c337a0 ("cpumask: remove obsolete node_to_cpumask
now everyone uses cpumask_of_node").

So update the comments for setup_node_to_cpumask_map().
Signed-off-by: NWanlong Gao <gaowanlong@cn.fujitsu.com>
Acked-by: NRusty Russell <rusty@rustcorp.com.au>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

If either of the vas or vms arrays are not properly kzalloced, then the
code jumps to the err_free label.

The err_free label runs a loop to check and free each of the array members
of the vas and vms arrays which is not required for this situation as none
of the array members have been allocated till this point.

Eliminate the extra loop we have to go through by introducing a new label
err_free2 and then jumping to it.

[akpm@linux-foundation.org: remove now-unneeded tests]
Signed-off-by: NKautuk Consul <consul.kautuk@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>

There is sometimes confusion between the global putback_lru_pages() in
migrate.c and the static putback_lru_pages() in vmscan.c: rename the
latter putback_inactive_pages(): it helps shrink_inactive_list() rather as
move_active_pages_to_lru() helps shrink_active_list().

Remove unused scan_control arg from putback_inactive_pages() and from
update_isolated_counts().  Move clear_active_flags() inside
update_isolated_counts().  Move NR_ISOLATED accounting up into
shrink_inactive_list() itself, so the balance is clearer.

Do the spin_lock_irq() before calling putback_inactive_pages() and
spin_unlock_irq() after return from it, so that it better matches
update_isolated_counts() and move_active_pages_to_lru().
Signed-off-by: NHugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The isolate_pages() level in vmscan.c offers little but indirection: merge
it into isolate_lru_pages() as the compiler does, and use the names
nr_to_scan and nr_scanned in each case.
Signed-off-by: NHugh Dickins <hughd@google.com>
Reviewed-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

del_page_from_lru() repeats del_page_from_lru_list(), also working out
which LRU the page was on, clearing the relevant bits.  Decouple those
functions: remove del_page_from_lru() and add page_off_lru().
Signed-off-by: NHugh Dickins <hughd@google.com>
Reviewed-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Mostly we use "enum lru_list lru": change those few "l"s to "lru"s.
Signed-off-by: NHugh Dickins <hughd@google.com>
Reviewed-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

checkpatch rightly protests

  WARNING: EXPORT_SYMBOL(foo); should immediately follow its function/variable

so fix the five offenders in mm/swap.c.
Signed-off-by: NHugh Dickins <hughd@google.com>
Reviewed-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

What's so special about ____pagevec_lru_add() that it needs four leading
underscores?  Nothing, it just helped to distinguish from
__pagevec_lru_add() in 2.6.28 development.  Cut two leading underscores.
Signed-off-by: NHugh Dickins <hughd@google.com>
Reviewed-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Replace pagevecs in putback_lru_pages() and move_active_pages_to_lru()
by lists of pages_to_free: then apply Konstantin Khlebnikov's
free_hot_cold_page_list() to them instead of pagevec_release().

Which simplifies the flow (no need to drop and retake lock whenever
pagevec fills up) and reduces stale addresses in stack backtraces
(which often showed through the pagevecs); but more importantly,
removes another 120 bytes from the deepest stacks in page reclaim.
Although I've not recently seen an actual stack overflow here with
a vanilla kernel, move_active_pages_to_lru() has often featured in
deep backtraces.

However, free_hot_cold_page_list() does not handle compound pages
(nor need it: a Transparent HugePage would have been split by the
time it reaches the call in shrink_page_list()), but it is possible
for putback_lru_pages() or move_active_pages_to_lru() to be left
holding the last reference on a THP, so must exclude the unlikely
compound case before putting on pages_to_free.

Remove pagevec_strip(), its work now done in move_active_pages_to_lru().
The pagevec in scan_mapping_unevictable_pages() remains in mm/vmscan.c,
but that is never on the reclaim path, and cannot be replaced by a list.
Signed-off-by: NHugh Dickins <hughd@google.com>
Reviewed-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: NKonstantin Khlebnikov <khlebnikov@openvz.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.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>

If DEBUG_VM, mem_cgroup_print_bad_page() is called whenever bad_page()
shows a "Bad page state" message, removes page from circulation, adds a
taint and continues.  This is at a very low level, often when a spinlock
is held (sometimes when page table lock is held, for example).

We want to recover from this badness, not make it worse: we must not
kmalloc memory here, we must not do a cgroup path lookup via dubious
pointers.  No doubt that code was useful to debug a particular case at one
time, and may be again, but take it out of the mainline kernel.
Signed-off-by: NHugh Dickins <hughd@google.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch started off as a cleanup: __split_huge_page_refcounts() has to
cope with two scenarios, when the hugepage being split is already on LRU,
and when it is not; but why does it have to split that accounting across
three different sites?  Consolidate it in lru_add_page_tail(), handling
evictable and unevictable alike, and use standard add_page_to_lru_list()
when accounting is needed (when the head is not yet on LRU).

But a recent regression in -next, I guess the removal of PageCgroupAcctLRU
test from mem_cgroup_split_huge_fixup(), makes this now a necessary fix:
under load, the MEM_CGROUP_ZSTAT count was wrapping to a huge number,
messing up reclaim calculations and causing a freeze at rmdir of cgroup.

Add a VM_BUG_ON to mem_cgroup_lru_del_list() when we're about to wrap that
count - this has not been the only such incident.  Document that
lru_add_page_tail() is for Transparent HugePages by #ifdef around it.
Signed-off-by: NHugh Dickins <hughd@google.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

If compaction can proceed for a given zone, shrink_zones() does not
reclaim any more pages from it.  After commit [e0c23279: vmscan: abort
reclaim/compaction if compaction can proceed], do_try_to_free_pages()
tries to finish as soon as possible once one zone can compact.

This was intended to prevent slabs being shrunk unnecessarily but there
are side-effects.  One is that a small zone that is ready for compaction
will abort reclaim even if the chances of successfully allocating a THP
from that zone is small.  It also means that reclaim can return too early
even though sc->nr_to_reclaim pages were not reclaimed.

This partially reverts the commit until it is proven that slabs are really
being shrunk unnecessarily but preserves the check to return 1 to avoid
OOM if reclaim was aborted prematurely.

[aarcange@redhat.com: This patch replaces a revert from Andrea]
Signed-off-by: NMel Gorman <mgorman@suse.de>
Reviewed-by: NRik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andy Isaacson <adi@hexapodia.org>
Cc: Nai Xia <nai.xia@gmail.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

In commit e0887c19 ("vmscan: limit direct reclaim for higher order
allocations"), Rik noted that reclaim was too aggressive when THP was
enabled.  In his initial patch he used the number of free pages to decide
if reclaim should abort for compaction.  My feedback was that reclaim and
compaction should be using the same logic when deciding if reclaim should
be aborted.

Unfortunately, this had the effect of reducing THP success rates when the
workload included something like streaming reads that continually
allocated pages.  The window during which compaction could run and return
a THP was too small.

This patch combines Rik's two patches together.  compaction_suitable() is
still used to decide if reclaim should be aborted to allow compaction is
used.  However, it will also ensure that there is a reasonable buffer of
free pages available.  This improves upon the THP allocation success rates
but bounds the number of pages that are freed for compaction.
Signed-off-by: NMel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel<riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andy Isaacson <adi@hexapodia.org>
Cc: Nai Xia <nai.xia@gmail.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch adds a lightweight sync migrate operation MIGRATE_SYNC_LIGHT
mode that avoids writing back pages to backing storage.  Async compaction
maps to MIGRATE_ASYNC while sync compaction maps to MIGRATE_SYNC_LIGHT.
For other migrate_pages users such as memory hotplug, MIGRATE_SYNC is
used.

This avoids sync compaction stalling for an excessive length of time,
particularly when copying files to a USB stick where there might be a
large number of dirty pages backed by a filesystem that does not support
->writepages.

[aarcange@redhat.com: This patch is heavily based on Andrea's work]
[akpm@linux-foundation.org: fix fs/nfs/write.c build]
[akpm@linux-foundation.org: fix fs/btrfs/disk-io.c build]
Signed-off-by: NMel Gorman <mgorman@suse.de>
Reviewed-by: NRik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andy Isaacson <adi@hexapodia.org>
Cc: Nai Xia <nai.xia@gmail.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

If compaction is deferred, direct reclaim is used to try to free enough
pages for the allocation to succeed.  For small high-orders, this has a
reasonable chance of success.  However, if the caller has specified
__GFP_NO_KSWAPD to limit the disruption to the system, it makes more sense
to fail the allocation rather than stall the caller in direct reclaim.
This patch skips direct reclaim if compaction is deferred and the caller
specifies __GFP_NO_KSWAPD.

Async compaction only considers a subset of pages so it is possible for
compaction to be deferred prematurely and not enter direct reclaim even in
cases where it should.  To compensate for this, this patch also defers
compaction only if sync compaction failed.
Signed-off-by: NMel Gorman <mgorman@suse.de>
Acked-by: NMinchan Kim <minchan.kim@gmail.com>
Reviewed-by: Rik van Riel<riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andy Isaacson <adi@hexapodia.org>
Cc: Nai Xia <nai.xia@gmail.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Commit 39deaf85 ("mm: compaction: make isolate_lru_page() filter-aware")
noted that compaction does not migrate dirty or writeback pages and that
is was meaningless to pick the page and re-add it to the LRU list.  This
had to be partially reverted because some dirty pages can be migrated by
compaction without blocking.

This patch updates "mm: compaction: make isolate_lru_page" by skipping
over pages that migration has no possibility of migrating to minimise LRU
disruption.
Signed-off-by: NMel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel<riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: NMinchan Kim <minchan@kernel.org>
Cc: Dave Jones <davej@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andy Isaacson <adi@hexapodia.org>
Cc: Nai Xia <nai.xia@gmail.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Asynchronous compaction is used when allocating transparent hugepages to
avoid blocking for long periods of time.  Due to reports of stalling,
there was a debate on disabling synchronous compaction but this severely
impacted allocation success rates.  Part of the reason was that many dirty
pages are skipped in asynchronous compaction by the following check;

	if (PageDirty(page) && !sync &&
		mapping->a_ops->migratepage != migrate_page)
			rc = -EBUSY;

This skips over all mapping aops using buffer_migrate_page() even though
it is possible to migrate some of these pages without blocking.  This
patch updates the ->migratepage callback with a "sync" parameter.  It is
the responsibility of the callback to fail gracefully if migration would
block.
Signed-off-by: NMel Gorman <mgorman@suse.de>
Reviewed-by: NRik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andy Isaacson <adi@hexapodia.org>
Cc: Nai Xia <nai.xia@gmail.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

During direct reclaim it is possible that reclaim will be aborted so that
compaction can be attempted to satisfy a high-order allocation.  If this
decision is made before any pages are reclaimed, it is possible that 0 is
returned to the page allocator potentially triggering an OOM.  This has
not been observed but it is a possibility so this patch addresses it.
Signed-off-by: NMel Gorman <mgorman@suse.de>
Reviewed-by: NRik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andy Isaacson <adi@hexapodia.org>
Cc: Nai Xia <nai.xia@gmail.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Properly take into account if we isolated a compound page during the lumpy
scan in reclaim and skip over the tail pages when encountered.  This
corrects the values given to the tracepoint for number of lumpy pages
isolated and will avoid breaking the loop early if compound pages smaller
than the requested allocation size are requested.

[mgorman@suse.de: Updated changelog]
Signed-off-by: NAndrea Arcangeli <aarcange@redhat.com>
Signed-off-by: NMel Gorman <mgorman@suse.de>
Reviewed-by: NMinchan Kim <minchan.kim@gmail.com>
Reviewed-by: NRik van Riel <riel@redhat.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andy Isaacson <adi@hexapodia.org>
Cc: Nai Xia <nai.xia@gmail.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When asynchronous compaction was introduced, the
/proc/sys/vm/compact_memory handler should have been updated to always use
synchronous compaction.  This did not happen so this patch addresses it.

The assumption is if a user writes to /proc/sys/vm/compact_memory, they
are willing for that process to stall.
Signed-off-by: NMel Gorman <mgorman@suse.de>
Reviewed-by: NAndrea Arcangeli <aarcange@redhat.com>
Reviewed-by: NRik van Riel <riel@redhat.com>
Reviewed-by: NMinchan Kim <minchan.kim@gmail.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andy Isaacson <adi@hexapodia.org>
Cc: Nai Xia <nai.xia@gmail.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Short summary: There are severe stalls when a USB stick using VFAT is
used with THP enabled that are reduced by this series.  If you are
experiencing this problem, please test and report back and considering I
have seen complaints from openSUSE and Fedora users on this as well as a
few private mails, I'm guessing it's a widespread issue.  This is a new
type of USB-related stall because it is due to synchronous compaction
writing where as in the past the big problem was dirty pages reaching
the end of the LRU and being written by reclaim.

Am cc'ing Andrew this time and this series would replace
mm-do-not-stall-in-synchronous-compaction-for-thp-allocations.patch.
I'm also cc'ing Dave Jones as he might have merged that patch to Fedora
for wider testing and ideally it would be reverted and replaced by this
series.

That said, the later patches could really do with some review.  If this
series is not the answer then a new direction needs to be discussed
because as it is, the stalls are unacceptable as the results in this
leader show.

For testers that try backporting this to 3.1, it won't work because
there is a non-obvious dependency on not writing back pages in direct
reclaim so you need those patches too.

Changelog since V5
o Rebase to 3.2-rc5
o Tidy up the changelogs a bit

Changelog since V4
o Added reviewed-bys, credited Andrea properly for sync-light
o Allow dirty pages without mappings to be considered for migration
o Bound the number of pages freed for compaction
o Isolate PageReclaim pages on their own LRU list

This is against 3.2-rc5 and follows on from discussions on "mm: Do
not stall in synchronous compaction for THP allocations" and "[RFC
PATCH 0/5] Reduce compaction-related stalls". Initially, the proposed
patch eliminated stalls due to compaction which sometimes resulted in
user-visible interactivity problems on browsers by simply never using
sync compaction. The downside was that THP success allocation rates
were lower because dirty pages were not being migrated as reported by
Andrea. His approach at fixing this was nacked on the grounds that
it reverted fixes from Rik merged that reduced the amount of pages
reclaimed as it severely impacted his workloads performance.

This series attempts to reconcile the requirements of maximising THP
usage, without stalling in a user-visible fashion due to compaction
or cheating by reclaiming an excessive number of pages.

Patch 1 partially reverts commit 39deaf85 to allow migration to isolate
	dirty pages. This is because migration can move some dirty
	pages without blocking.

Patch 2 notes that the /proc/sys/vm/compact_memory handler is not using
	synchronous compaction when it should be. This is unrelated
	to the reported stalls but is worth fixing.

Patch 3 checks if we isolated a compound page during lumpy scan and
	account for it properly. For the most part, this affects
	tracing so it's unrelated to the stalls but worth fixing.

Patch 4 notes that it is possible to abort reclaim early for compaction
	and return 0 to the page allocator potentially entering the
	"may oom" path. This has not been observed in practice but
	the rest of the series potentially makes it easier to happen.

Patch 5 adds a sync parameter to the migratepage callback and gives
	the callback responsibility for migrating the page without
	blocking if sync==false. For example, fallback_migrate_page
	will not call writepage if sync==false. This increases the
	number of pages that can be handled by asynchronous compaction
	thereby reducing stalls.

Patch 6 restores filter-awareness to isolate_lru_page for migration.
	In practice, it means that pages under writeback and pages
	without a ->migratepage callback will not be isolated
	for migration.

Patch 7 avoids calling direct reclaim if compaction is deferred but
	makes sure that compaction is only deferred if sync
	compaction was used.

Patch 8 introduces a sync-light migration mechanism that sync compaction
	uses. The objective is to allow some stalls but to not call
	->writepage which can lead to significant user-visible stalls.

Patch 9 notes that while we want to abort reclaim ASAP to allow
	compation to go ahead that we leave a very small window of
	opportunity for compaction to run. This patch allows more pages
	to be freed by reclaim but bounds the number to a reasonable
	level based on the high watermark on each zone.

Patch 10 allows slabs to be shrunk even after compaction_ready() is
	true for one zone. This is to avoid a problem whereby a single
	small zone can abort reclaim even though no pages have been
	reclaimed and no suitably large zone is in a usable state.

Patch 11 fixes a problem with the rate of page scanning. As reclaim is
	rarely stalling on pages under writeback it means that scan
	rates are very high. This is particularly true for direct
	reclaim which is not calling writepage. The vmstat figures
	implied that much of this was busy work with PageReclaim pages
	marked for immediate reclaim. This patch is a prototype that
	moves these pages to their own LRU list.

This has been tested and other than 2 USB keys getting trashed,
nothing horrible fell out. That said, I am a bit unhappy with the
rescue logic in patch 11 but did not find a better way around it. It
does significantly reduce scan rates and System CPU time indicating
it is the right direction to take.

What is of critical importance is that stalls due to compaction
are massively reduced even though sync compaction was still
allowed. Testing from people complaining about stalls copying to USBs
with THP enabled are particularly welcome.

The following tests all involve THP usage and USB keys in some
way. Each test follows this type of pattern

1. Read from some fast fast storage, be it raw device or file. Each time
   the copy finishes, start again until the test ends
2. Write a large file to a filesystem on a USB stick. Each time the copy
   finishes, start again until the test ends
3. When memory is low, start an alloc process that creates a mapping
   the size of physical memory to stress THP allocation. This is the
   "real" part of the test and the part that is meant to trigger
   stalls when THP is enabled. Copying continues in the background.
4. Record the CPU usage and time to execute of the alloc process
5. Record the number of THP allocs and fallbacks as well as the number of THP
   pages in use a the end of the test just before alloc exited
6. Run the test 5 times to get an idea of variability
7. Between each run, sync is run and caches dropped and the test
   waits until nr_dirty is a small number to avoid interference
   or caching between iterations that would skew the figures.

The individual tests were then

writebackCPDeviceBasevfat
	Disable THP, read from a raw device (sda), vfat on USB stick
writebackCPDeviceBaseext4
	Disable THP, read from a raw device (sda), ext4 on USB stick
writebackCPDevicevfat
	THP enabled, read from a raw device (sda), vfat on USB stick
writebackCPDeviceext4
	THP enabled, read from a raw device (sda), ext4 on USB stick
writebackCPFilevfat
	THP enabled, read from a file on fast storage and USB, both vfat
writebackCPFileext4
	THP enabled, read from a file on fast storage and USB, both ext4

The kernels tested were

3.1		3.1
vanilla		3.2-rc5
freemore	Patches 1-10
immediate	Patches 1-11
andrea		The 8 patches Andrea posted as a basis of comparison

The results are very long unfortunately. I'll start with the case
where we are not using THP at all

writebackCPDeviceBasevfat
                   3.1.0-vanilla         rc5-vanilla       freemore-v6r1        isolate-v6r1         andrea-v2r1
System Time         1.28 (    0.00%)   54.49 (-4143.46%)   48.63 (-3687.69%)    4.69 ( -265.11%)   51.88 (-3940.81%)
+/-                 0.06 (    0.00%)    2.45 (-4305.55%)    4.75 (-8430.57%)    7.46 (-13282.76%)    4.76 (-8440.70%)
User Time           0.09 (    0.00%)    0.05 (   40.91%)    0.06 (   29.55%)    0.07 (   15.91%)    0.06 (   27.27%)
+/-                 0.02 (    0.00%)    0.01 (   45.39%)    0.02 (   25.07%)    0.00 (   77.06%)    0.01 (   52.24%)
Elapsed Time      110.27 (    0.00%)   56.38 (   48.87%)   49.95 (   54.70%)   11.77 (   89.33%)   53.43 (   51.54%)
+/-                 7.33 (    0.00%)    3.77 (   48.61%)    4.94 (   32.63%)    6.71 (    8.50%)    4.76 (   35.03%)
THP Active          0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)
+/-                 0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)
Fault Alloc         0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)
+/-                 0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)
Fault Fallback      0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)
+/-                 0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)    0.00 (    0.00%)

The THP figures are obviously all 0 because THP was enabled. The
main thing to watch is the elapsed times and how they compare to
times when THP is enabled later. It's also important to note that
elapsed time is improved by this series as System CPu time is much
reduced.

writebackCPDevicevfat

                   3.1.0-vanilla         rc5-vanilla       freemore-v6r1        isolate-v6r1         andrea-v2r1
System Time         1.22 (    0.00%)   13.89 (-1040.72%)   46.40 (-3709.20%)    4.44 ( -264.37%)   47.37 (-3789.33%)
+/-                 0.06 (    0.00%)   22.82 (-37635.56%)    3.84 (-6249.44%)    6.48 (-10618.92%)    6.60
(-10818.53%)
User Time           0.06 (    0.00%)    0.06 (   -6.90%)    0.05 (   17.24%)    0.05 (   13.79%)    0.04 (   31.03%)
+/-                 0.01 (    0.00%)    0.01 (   33.33%)    0.01 (   33.33%)    0.01 (   39.14%)    0.01 (   25.46%)
Elapsed Time     10445.54 (    0.00%) 2249.92 (   78.46%)   70.06 (   99.33%)   16.59 (   99.84%)  472.43 (
95.48%)
+/-               643.98 (    0.00%)  811.62 (  -26.03%)   10.02 (   98.44%)    7.03 (   98.91%)   59.99 (   90.68%)
THP Active         15.60 (    0.00%)   35.20 (  225.64%)   65.00 (  416.67%)   70.80 (  453.85%)   62.20 (  398.72%)
+/-                18.48 (    0.00%)   51.29 (  277.59%)   15.99 (   86.52%)   37.91 (  205.18%)   22.02 (  119.18%)
Fault Alloc       121.80 (    0.00%)   76.60 (   62.89%)  155.40 (  127.59%)  181.20 (  148.77%)  286.60 (  235.30%)
+/-                73.51 (    0.00%)   61.11 (   83.12%)   34.89 (   47.46%)   31.88 (   43.36%)   68.13 (   92.68%)
Fault Fallback    881.20 (    0.00%)  926.60 (   -5.15%)  847.60 (    3.81%)  822.00 (    6.72%)  716.60 (   18.68%)
+/-                73.51 (    0.00%)   61.26 (   16.67%)   34.89 (   52.54%)   31.65 (   56.94%)   67.75 (    7.84%)
MMTests Statistics: duration
User/Sys Time Running Test (seconds)       3540.88   1945.37    716.04     64.97   1937.03
Total Elapsed Time (seconds)              52417.33  11425.90    501.02    230.95   2520.28

The first thing to note is the "Elapsed Time" for the vanilla kernels
of 2249 seconds versus 56 with THP disabled which might explain the
reports of USB stalls with THP enabled. Applying the patches brings
performance in line with THP-disabled performance while isolating
pages for immediate reclaim from the LRU cuts down System CPU time.

The "Fault Alloc" success rate figures are also improved. The vanilla
kernel only managed to allocate 76.6 pages on average over the course
of 5 iterations where as applying the series allocated 181.20 on
average albeit it is well within variance. It's worth noting that
applies the series at least descreases the amount of variance which
implies an improvement.

Andrea's series had a higher success rate for THP allocations but
at a severe cost to elapsed time which is still better than vanilla
but still much worse than disabling THP altogether. One can bring my
series close to Andrea's by removing this check

        /*
         * If compaction is deferred for high-order allocations, it is because
         * sync compaction recently failed. In this is the case and the caller
         * has requested the system not be heavily disrupted, fail the
         * allocation now instead of entering direct reclaim
         */
        if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD))
                goto nopage;

I didn't include a patch that removed the above check because hurting
overall performance to improve the THP figure is not what the average
user wants. It's something to consider though if someone really wants
to maximise THP usage no matter what it does to the workload initially.

This is summary of vmstat figures from the same test.

                                       3.1.0-vanilla rc5-vanilla freemore-v6r1 isolate-v6r1 andrea-v2r1
Page Ins                                  3257266139  1111844061    17263623    10901575   161423219
Page Outs                                   81054922    30364312     3626530     3657687     8753730
Swap Ins                                        3294        2851        6560        4964        4592
Swap Outs                                     390073      528094      620197      790912      698285
Direct pages scanned                      1077581700  3024951463  1764930052   115140570  5901188831
Kswapd pages scanned                        34826043     7112868     2131265     1686942     1893966
Kswapd pages reclaimed                      28950067     4911036     1246044      966475     1497726
Direct pages reclaimed                     805148398   280167837     3623473     2215044    40809360
Kswapd efficiency                                83%         69%         58%         57%         79%
Kswapd velocity                              664.399     622.521    4253.852    7304.360     751.490
Direct efficiency                                74%          9%          0%          1%          0%
Direct velocity                            20557.737  264745.137 3522673.849  498551.938 2341481.435
Percentage direct scans                          96%         99%         99%         98%         99%
Page writes by reclaim                        722646      529174      620319      791018      699198
Page writes file                              332573        1080         122         106         913
Page writes anon                              390073      528094      620197      790912      698285
Page reclaim immediate                             0  2552514720  1635858848   111281140  5478375032
Page rescued immediate                             0           0           0       87848           0
Slabs scanned                                  23552       23552        9216        8192        9216
Direct inode steals                              231           0           0           0           0
Kswapd inode steals                                0           0           0           0           0
Kswapd skipped wait                            28076         786           0          61           6
THP fault alloc                                  609         383         753         906        1433
THP collapse alloc                                12           6           0           0           6
THP splits                                       536         211         456         593        1136
THP fault fallback                              4406        4633        4263        4110        3583
THP collapse fail                                120         127           0           0           4
Compaction stalls                               1810         728         623         779        3200
Compaction success                               196          53          60          80         123
Compaction failures                             1614         675         563         699        3077
Compaction pages moved                        193158       53545      243185      333457      226688
Compaction move failure                         9952        9396       16424       23676       45070

The main things to look at are

1. Page In/out figures are much reduced by the series.

2. Direct page scanning is incredibly high (264745.137 pages scanned
   per second on the vanilla kernel) but isolating PageReclaim pages
   on their own list reduces the number of pages scanned significantly.

3. The fact that "Page rescued immediate" is a positive number implies
   that we sometimes race removing pages from the LRU_IMMEDIATE list
   that need to be put back on a normal LRU but it happens only for
   0.07% of the pages marked for immediate reclaim.

writebackCPDeviceext4
                   3.1.0-vanilla         rc5-vanilla       freemore-v6r1        isolate-v6r1         andrea-v2r1
System Time         1.51 (    0.00%)    1.77 (  -17.66%)    1.46 (    2.92%)    1.15 (   23.77%)    1.89 (  -25.63%)
+/-                 0.27 (    0.00%)    0.67 ( -148.52%)    0.33 (  -22.76%)    0.30 (  -11.15%)    0.19 (   30.16%)
User Time           0.03 (    0.00%)    0.04 (  -37.50%)    0.05 (  -62.50%)    0.07 ( -112.50%)    0.04 (  -18.75%)
+/-                 0.01 (    0.00%)    0.02 ( -146.64%)    0.02 (  -97.91%)    0.02 (  -75.59%)    0.02 (  -63.30%)
Elapsed Time      124.93 (    0.00%)  114.49 (    8.36%)   96.77 (   22.55%)   27.48 (   78.00%)  205.70 (  -64.65%)
+/-                20.20 (    0.00%)   74.39 ( -268.34%)   59.88 ( -196.48%)    7.72 (   61.79%)   25.03 (  -23.95%)
THP Active        161.80 (    0.00%)   83.60 (   51.67%)  141.20 (   87.27%)   84.60 (   52.29%)   82.60 (   51.05%)
+/-                71.95 (    0.00%)   43.80 (   60.88%)   26.91 (   37.40%)   59.02 (   82.03%)   52.13 (   72.45%)
Fault Alloc       471.40 (    0.00%)  228.60 (   48.49%)  282.20 (   59.86%)  225.20 (   47.77%)  388.40 (   82.39%)
+/-                88.07 (    0.00%)   87.42 (   99.26%)   73.79 (   83.78%)  109.62 (  124.47%)   82.62 (   93.81%)
Fault Fallback    531.60 (    0.00%)  774.60 (  -45.71%)  720.80 (  -35.59%)  777.80 (  -46.31%)  614.80 (  -15.65%)
+/-                88.07 (    0.00%)   87.26 (    0.92%)   73.79 (   16.22%)  109.62 (  -24.47%)   82.29 (    6.56%)
MMTests Statistics: duration
User/Sys Time Running Test (seconds)         50.22     33.76     30.65     24.14    128.45
Total Elapsed Time (seconds)               1113.73   1132.19   1029.45    759.49   1707.26

Similar test but the USB stick is using ext4 instead of vfat. As
ext4 does not use writepage for migration, the large stalls due to
compaction when THP is enabled are not observed. Still, isolating
PageReclaim pages on their own list helped completion time largely
by reducing the number of pages scanned by direct reclaim although
time spend in congestion_wait could also be a factor.

Again, Andrea's series had far higher success rates for THP allocation
at the cost of elapsed time. I didn't look too closely but a quick
look at the vmstat figures tells me kswapd reclaimed 8 times more pages
than the patch series and direct reclaim reclaimed roughly three times
as many pages. It follows that if memory is aggressively reclaimed,
there will be more available for THP.

writebackCPFilevfat
                   3.1.0-vanilla         rc5-vanilla       freemore-v6r1        isolate-v6r1         andrea-v2r1
System Time         1.76 (    0.00%)   29.10 (-1555.52%)   46.01 (-2517.18%)    4.79 ( -172.35%)   54.89 (-3022.53%)
+/-                 0.14 (    0.00%)   25.61 (-18185.17%)    2.15 (-1434.83%)    6.60 (-4610.03%)    9.75
(-6863.76%)
User Time           0.05 (    0.00%)    0.07 (  -45.83%)    0.05 (   -4.17%)    0.06 (  -29.17%)    0.06 (  -16.67%)
+/-                 0.02 (    0.00%)    0.02 (   20.11%)    0.02 (   -3.14%)    0.01 (   31.58%)    0.01 (   47.41%)
Elapsed Time     22520.79 (    0.00%) 1082.85 (   95.19%)   73.30 (   99.67%)   32.43 (   99.86%)  291.84 (  98.70%)
+/-              7277.23 (    0.00%)  706.29 (   90.29%)   19.05 (   99.74%)   17.05 (   99.77%)  125.55 (   98.27%)
THP Active         83.80 (    0.00%)   12.80 (   15.27%)   15.60 (   18.62%)   13.00 (   15.51%)    0.80 (    0.95%)
+/-                66.81 (    0.00%)   20.19 (   30.22%)    5.92 (    8.86%)   15.06 (   22.54%)    1.17 (    1.75%)
Fault Alloc       171.00 (    0.00%)   67.80 (   39.65%)   97.40 (   56.96%)  125.60 (   73.45%)  133.00 (   77.78%)
+/-                82.91 (    0.00%)   30.69 (   37.02%)   53.91 (   65.02%)   55.05 (   66.40%)   21.19 (   25.56%)
Fault Fallback    832.00 (    0.00%)  935.20 (  -12.40%)  906.00 (   -8.89%)  877.40 (   -5.46%)  870.20 (   -4.59%)
+/-                82.91 (    0.00%)   30.69 (   62.98%)   54.01 (   34.86%)   55.05 (   33.60%)   20.91 (   74.78%)
MMTests Statistics: duration
User/Sys Time Running Test (seconds)       7229.81    928.42    704.52     80.68   1330.76
Total Elapsed Time (seconds)             112849.04   5618.69    571.11    360.54   1664.28

In this case, the test is reading/writing only from filesystems but as
it's vfat, it's slow due to calling writepage during compaction. Little
to observe really - the time to complete the test goes way down
with the series applied and THP allocation success rates go up in
comparison to 3.2-rc5.  The success rates are lower than 3.1.0 but
the elapsed time for that kernel is abysmal so it is not really a
sensible comparison.

As before, Andrea's series allocates more THPs at the cost of overall
performance.

writebackCPFileext4
                   3.1.0-vanilla         rc5-vanilla       freemore-v6r1        isolate-v6r1         andrea-v2r1
System Time         1.51 (    0.00%)    1.77 (  -17.66%)    1.46 (    2.92%)    1.15 (   23.77%)    1.89 (  -25.63%)
+/-                 0.27 (    0.00%)    0.67 ( -148.52%)    0.33 (  -22.76%)    0.30 (  -11.15%)    0.19 (   30.16%)
User Time           0.03 (    0.00%)    0.04 (  -37.50%)    0.05 (  -62.50%)    0.07 ( -112.50%)    0.04 (  -18.75%)
+/-                 0.01 (    0.00%)    0.02 ( -146.64%)    0.02 (  -97.91%)    0.02 (  -75.59%)    0.02 (  -63.30%)
Elapsed Time      124.93 (    0.00%)  114.49 (    8.36%)   96.77 (   22.55%)   27.48 (   78.00%)  205.70 (  -64.65%)
+/-                20.20 (    0.00%)   74.39 ( -268.34%)   59.88 ( -196.48%)    7.72 (   61.79%)   25.03 (  -23.95%)
THP Active        161.80 (    0.00%)   83.60 (   51.67%)  141.20 (   87.27%)   84.60 (   52.29%)   82.60 (   51.05%)
+/-                71.95 (    0.00%)   43.80 (   60.88%)   26.91 (   37.40%)   59.02 (   82.03%)   52.13 (   72.45%)
Fault Alloc       471.40 (    0.00%)  228.60 (   48.49%)  282.20 (   59.86%)  225.20 (   47.77%)  388.40 (   82.39%)
+/-                88.07 (    0.00%)   87.42 (   99.26%)   73.79 (   83.78%)  109.62 (  124.47%)   82.62 (   93.81%)
Fault Fallback    531.60 (    0.00%)  774.60 (  -45.71%)  720.80 (  -35.59%)  777.80 (  -46.31%)  614.80 (  -15.65%)
+/-                88.07 (    0.00%)   87.26 (    0.92%)   73.79 (   16.22%)  109.62 (  -24.47%)   82.29 (    6.56%)
MMTests Statistics: duration
User/Sys Time Running Test (seconds)         50.22     33.76     30.65     24.14    128.45
Total Elapsed Time (seconds)               1113.73   1132.19   1029.45    759.49   1707.26

Same type of story - elapsed times go down. In this case, allocation
success rates are roughtly the same. As before, Andrea's has higher
success rates but takes a lot longer.

Overall the series does reduce latencies and while the tests are
inherency racy as alloc competes with the cp processes, the variability
was included. The THP allocation rates are not as high as they could
be but that is because we would have to be more aggressive about
reclaim and compaction impacting overall performance.

This patch:

Commit 39deaf85 ("mm: compaction: make isolate_lru_page() filter-aware")
noted that compaction does not migrate dirty or writeback pages and that
is was meaningless to pick the page and re-add it to the LRU list.

What was missed during review is that asynchronous migration moves dirty
pages if their ->migratepage callback is migrate_page() because these can
be moved without blocking.  This potentially impacted hugepage allocation
success rates by a factor depending on how many dirty pages are in the
system.

This patch partially reverts 39deaf85 to allow migration to isolate dirty
pages again.  This increases how much compaction disrupts the LRU but that
is addressed later in the series.
Signed-off-by: NMel Gorman <mgorman@suse.de>
Reviewed-by: NAndrea Arcangeli <aarcange@redhat.com>
Reviewed-by: NRik van Riel <riel@redhat.com>
Reviewed-by: NMinchan Kim <minchan.kim@gmail.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andy Isaacson <adi@hexapodia.org>
Cc: Nai Xia <nai.xia@gmail.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

In trace_mm_vmscan_lru_isolate(), we don't output 'file' information to
the trace event and it is a bit inconvenient for the user to get the
real information(like pasted below).  mm_vmscan_lru_isolate:
isolate_mode=2 order=0 nr_requested=32 nr_scanned=32 nr_taken=32
contig_taken=0 contig_dirty=0 contig_failed=0

'active' can be obtained by analyzing mode(Thanks go to Minchan and
Mel), So this patch adds 'file' to the trace event and it now looks
like: mm_vmscan_lru_isolate: isolate_mode=2 order=0 nr_requested=32
nr_scanned=32 nr_taken=32 contig_taken=0 contig_dirty=0 contig_failed=0
file=0
Signed-off-by: NTao Ma <boyu.mt@taobao.com>
Acked-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: NMinchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Put the tail subpages of an isolated hugepage under splitting in the lru
reclaim head as they supposedly should be isolated too next.

Queues the subpages in physical order in the lru for non isolated
hugepages under splitting.  That might provide some theoretical cache
benefit to the buddy allocator later.
Signed-off-by: NShaohua Li <shaohua.li@intel.com>
Signed-off-by: NAndrea Arcangeli <aarcange@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

We have tlb_remove_tlb_entry to indicate a pte tlb flush entry should be
flushed, but not a corresponding API for pmd entry.  This isn't a
problem so far because THP is only for x86 currently and tlb_flush()
under x86 will flush entire TLB.  But this is confusion and could be
missed if thp is ported to other arch.

Also convert tlb->need_flush = 1 to a VM_BUG_ON(!tlb->need_flush) in
__tlb_remove_page() as suggested by Andrea Arcangeli.  The
__tlb_remove_page() function is supposed to be called after
tlb_remove_xxx_tlb_entry() and we can catch any misuse.
Signed-off-by: NShaohua Li <shaohua.li@intel.com>
Reviewed-by: NAndrea Arcangeli <aarcange@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

change_protection() will do TLB flush later, don't need duplicate tlb
flush.
Signed-off-by: NShaohua Li <shaohua.li@intel.com>
Reviewed-by: NAndrea Arcangeli <aarcange@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Improve the error code path.  Delete unnecessary sysfs file for example.
Also remove the #ifdef xxx to make code better.
Signed-off-by: NShaohua Li <shaohua.li@intel.com>
Reviewed-by: NAndrea Arcangeli <aarcange@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>