Matthew Leach [Thu, 29 Nov 2012 03:18:15 +0000 (14:18 +1100)]
include/linux/init.h: use the stringify operator for the __define_initcall macro
Currently the __define_initcall() macro takes three arguments, fn, id and
level. The level argument is exactly the same as the id argument but
wrapped in quotes. To overcome this need to specify three arguments to
the __define_initcall macro, where one argument is the stringification of
another, we can just use the stringification macro instead.
Signed-off-by: Matthew Leach <matthew@mattleach.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Wen Congyang [Thu, 29 Nov 2012 03:18:15 +0000 (14:18 +1100)]
Documentation/kernel-parameters.txt: update mem= option's spec according to its implementation
Current mem= implementation seems buggy because the specification and
implementation don't match. The current mem= has been working for many
years and it's not buggy - it works as expected. So we should update the
specification.
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com> Cc: Rob Landley <rob@landley.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Xi Wang [Thu, 29 Nov 2012 03:18:14 +0000 (14:18 +1100)]
mm/dmapool.c: fix null dev in dma_pool_create()
A few drivers invoke dma_pool_create() with a null dev. Note that dev is
dereferenced in dev_to_node(dev), causing a null pointer dereference.
A long term solution is to disallow null dev. Once the drivers are fixed,
we can simplify the core code here. For now we add WARN_ON(!dev) to
notify the driver maintainers and avoid the null pointer dereference.
Signed-off-by: Xi Wang <xi.wang@gmail.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Xi Wang [Thu, 29 Nov 2012 03:18:14 +0000 (14:18 +1100)]
drivers/usb/gadget/amd5536udc.c: avoid calling dma_pool_create() with NULL dev
Calling dma_pool_create() with dev==NULL will oops on a NUMA machine.
Rather than changing dma_pool_create() we wish to disallow passing
dev==NULL. This requires fixing up the small number of drivers which are
passing in dev==NULL.
Use &dev->pdev->dev instead of NULL.
Signed-off-by: Xi Wang <xi.wang@gmail.com> Cc: Felipe Balbi <balbi@ti.com> Cc: Greg KH <greg@kroah.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Wanpeng Li [Thu, 29 Nov 2012 03:18:14 +0000 (14:18 +1100)]
mm/memblock: reduce overhead in binary search
When checking that the indicated address belongs to the memory region, the
memory regions are checked one by one through a binary search, which will
be time consuming.
If the indicated address isn't in the memory region, then we needn't do
the time-consuming search. Add a check on the indicated address for that
purpose.
Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Gavin Shan <shangw@linux.vnet.ibm.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Shaohua Li [Thu, 29 Nov 2012 03:18:13 +0000 (14:18 +1100)]
swap: add a simple detector for inappropriate swapin readahead
The swapin readahead does a blind readahead whether or not the swapin is
sequential. This is ok for harddisk because large reads have relatively
small costs and if the readahead pages are unneeded they can be reclaimed
easily. But for SSD devices large reads are more expensive than small
one. If readahead pages are unneeded, reading them in caused significant
overhead
This patch addes a simple random read detection similar to file mmap
readahead. If a random read is detected, swapin readahead will be
skipped. This improves a lot for a swap workload with random IO in a fast
SSD.
I run anonymous mmap write micro benchmark, which will triger swapin/swapout.
For both harddisk and SSD, the randwrite swap workload run time is reduced
significantly. Sequential write swap workload hasn't chanage.
Interestingly, the randwrite harddisk test is improved too. This might be
because swapin readahead needs to allocate extra memory, which further
tights memory pressure, so more swapout/swapin.
Signed-off-by: Shaohua Li <shli@fusionio.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@openvz.org> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Michal Hocko [Thu, 29 Nov 2012 03:18:13 +0000 (14:18 +1100)]
drop_caches: add some documentation and info message
I would like to resurrect Dave's patch. The last time it was posted was
here https://lkml.org/lkml/2010/9/16/250 and there didn't seem to be any
strong opposition.
Kosaki was worried about possible excessive logging when somebody drops
caches too often (but then he claimed he didn't have a strong opinion on
that) but I would say opposite. If somebody does that then I would really
like to know that from the log when supporting a system because it almost
for sure means that there is something fishy going on. It is also worth
mentioning that only root can write drop caches so this is not an flooding
attack vector.
I am bringing that up again because this can be really helpful when
chasing strange performance issues which (surprise surprise) turn out to
be related to artificially dropped caches done because the admin thinks
this would help...
I have just refreshed the original patch on top of the current mm tree
but I could live with KERN_INFO as well if people think that KERN_NOTICE
is too hysterical.
: From: Dave Hansen <dave@linux.vnet.ibm.com>
: Date: Fri, 12 Oct 2012 14:30:54 +0200
:
: There is plenty of anecdotal evidence and a load of blog posts
: suggesting that using "drop_caches" periodically keeps your system
: running in "tip top shape". Perhaps adding some kernel
: documentation will increase the amount of accurate data on its use.
:
: If we are not shrinking caches effectively, then we have real bugs.
: Using drop_caches will simply mask the bugs and make them harder
: to find, but certainly does not fix them, nor is it an appropriate
: "workaround" to limit the size of the caches.
:
: It's a great debugging tool, and is really handy for doing things
: like repeatable benchmark runs. So, add a bit more documentation
: about it, and add a little KERN_NOTICE. It should help developers
: who are chasing down reclaim-related bugs.
[mhocko@suse.cz: refreshed to current -mm tree] Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Jiang Liu [Thu, 29 Nov 2012 03:18:12 +0000 (14:18 +1100)]
mm: provide more accurate estimation of pages occupied by memmap
If SPARSEMEM is enabled, it won't build page structures for non-existing
pages (holes) within a zone, so provide a more accurate estimation of
pages occupied by memmap if there are bigger holes within the zone.
And pages for highmem zones' memmap will be allocated from lowmem, so
charge nr_kernel_pages for that.
Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Maciej Rutecki <maciej.rutecki@gmail.com> Cc: Chris Clayton <chris2553@googlemail.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan@kernel.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Robert Jarzmik [Thu, 29 Nov 2012 03:18:11 +0000 (14:18 +1100)]
mm: trace filemap add and del
Use the events API to trace filemap loading and unloading of file pieces
into the page cache.
This patch aims at tracing the eviction reload cycle of executable and
shared libraries pages in a memory constrained environment.
The typical usage is to spot a specific device and inode (for example
/lib/libc.so) to see the eviction cycles, and find out if frequently used
code is rather spread across many pages (bad) or coallesced (good).
Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr> Cc: Dave Chinner <david@fromorbit.com> Cc: Hugh Dickins <hughd@google.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
During fixing bugs caused by inaccurate zone->present_pages, we found
zone->present_pages has been abused. The field zone->present_pages may
have different meanings in different contexts:
1) pages existing in a zone.
2) pages managed by the buddy system.
For more discussions about the issue, please refer to:
http://lkml.org/lkml/2012/11/5/866
https://patchwork.kernel.org/patch/1346751/
This patchset tries to introduce a new field named "managed_pages" to
struct zone, which counts "pages managed by the buddy system". And revert
zone->present_pages to count "physical pages existing in a zone", which
also keep in consistence with pgdat->node_present_pages.
We will set an initial value for zone->managed_pages in function
free_area_init_core() and will adjust it later if the initial value is
inaccurate.
For DMA/normal zones, the initial value is set to:
Later zone->managed_pages will be adjusted to the accurate value when the
bootmem allocator frees all free pages to the buddy system in function
free_all_bootmem_node() and free_all_bootmem().
The bootmem allocator doesn't touch highmem pages, so highmem zones'
managed_pages is set to the accurate value "spanned_pages - absent_pages"
in function free_area_init_core() and won't be updated anymore.
This patch also adds a new field "managed_pages" to /proc/zoneinfo
and sysrq showmem.
Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Maciej Rutecki <maciej.rutecki@gmail.com> Cc: Chris Clayton <chris2553@googlemail.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan@kernel.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
David Rientjes [Thu, 29 Nov 2012 03:18:10 +0000 (14:18 +1100)]
mm, oom: remove statically defined arch functions of same name
out_of_memory() is a globally defined function to call the oom killer.
x86, sh, and powerpc all use a function of the same name within file scope
in their respective fault.c unnecessarily. Inline the functions into the
pagefault handlers to clean the code up.
Signed-off-by: David Rientjes <rientjes@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Mundt <lethal@linux-sh.org> Reviewed-by: Michal Hocko <mhocko@suse.cz> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
David Rientjes [Thu, 29 Nov 2012 03:18:09 +0000 (14:18 +1100)]
mm, oom: remove redundant sleep in pagefault oom handler
out_of_memory() will already cause current to schedule if it has not been
killed, so doing it again in pagefault_out_of_memory() is redundant.
Remove it.
Signed-off-by: David Rientjes <rientjes@google.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
David Rientjes [Thu, 29 Nov 2012 03:18:09 +0000 (14:18 +1100)]
mm, oom: cleanup pagefault oom handler
To lock the entire system from parallel oom killing, it's possible to pass
in a zonelist with all zones rather than using for_each_populated_zone()
for the iteration. This obsoletes try_set_system_oom() and
clear_system_oom() so that they can be removed.
Signed-off-by: David Rientjes <rientjes@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Lai Jiangshan [Thu, 29 Nov 2012 03:18:08 +0000 (14:18 +1100)]
numa: add CONFIG_MOVABLE_NODE for movable-dedicated node
We need a node which only contains movable memory. This feature is very
important for node hotplug. If a node has normal/highmem, the memory may
be used by the kernel and can't be offlined. If the node only contains
movable memory, we can offline the memory and the node.
All are prepared, we can actually introduce N_MEMORY.
add CONFIG_MOVABLE_NODE make we can use it for movable-dedicated node
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Tested-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Greg KH <greg@kroah.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
David Rientjes [Thu, 29 Nov 2012 03:18:08 +0000 (14:18 +1100)]
mm, memcg: avoid unnecessary function call when memcg is disabled
While profiling numa/core v16 with cgroup_disable=memory on the command
line, I noticed mem_cgroup_count_vm_event() still showed up as high as
0.60% in perftop.
This occurs because the function is called extremely often even when memcg
is disabled.
To fix this, inline the check for mem_cgroup_disabled() so we avoid the
unnecessary function call if memcg is disabled.
Signed-off-by: David Rientjes <rientjes@google.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Glauber Costa <glommer@parallels.com> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Joonsoo Kim [Thu, 29 Nov 2012 03:18:07 +0000 (14:18 +1100)]
mm: WARN_ON_ONCE if f_op->mmap() change vma's start address
During reviewing the source code, I found a comment which mention that
after f_op->mmap(), vma's start address can be changed. I didn't verify
that it is really possible, because there are so many f_op->mmap()
implementation. But if there are some mmap() which change vma's start
address, it is possible error situation, because we already prepare prev
vma, rb_link and rb_parent and these are related to original address.
So add WARN_ON_ONCE for finding that this situtation really happens.
Signed-off-by: Joonsoo Kim <js1304@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The user will be confused(why this function just counts for high or
normal memory node? does it counts for ZONE_MOVABLE's lru pages?)
until someone else tell them N_HIGH_MEMORY is reused to stand for
nodes that have any memory.
A.cont) If we introduce N_MEMORY, we can reduce this confusing
AND make the code more clearly:
A.example 2) mm/page_cgroup.c use N_HIGH_MEMORY twice:
One is in page_cgroup_init(void):
for_each_node_state(nid, N_HIGH_MEMORY) {
It means if the node have memory, we will allocate page_cgroup map for
the node. We should use N_MEMORY instead here to gaim more clearly.
The second using is in alloc_page_cgroup():
if (node_state(nid, N_HIGH_MEMORY))
addr = vzalloc_node(size, nid);
It means if the node has high or normal memory that can be allocated
from kernel. We should keep N_HIGH_MEMORY here, and it will be better
if the "any memory" semantic of N_HIGH_MEMORY is removed.
B) This reusing is out-dated if we introduce MOVABLE-dedicated node.
The MOVABLE-dedicated node should not appear in
node_stats[N_HIGH_MEMORY] nor node_stats[N_NORMAL_MEMORY],
because MOVABLE-dedicated node has no high or normal memory.
In x86_64, N_HIGH_MEMORY=N_NORMAL_MEMORY, if a MOVABLE-dedicated node
is in node_stats[N_HIGH_MEMORY], it is also means it is in
node_stats[N_NORMAL_MEMORY], it causes SLUB wrong.
The slub uses
for_each_node_state(nid, N_NORMAL_MEMORY)
and creates kmem_cache_node for MOVABLE-dedicated node and cause problem.
In one word, we need a N_MEMORY. We just intrude it as an alias to
N_HIGH_MEMORY and fix all im-proper usages of N_HIGH_MEMORY in late
patches.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Acked-by: Christoph Lameter <cl@linux.com> Acked-by: Hillf Danton <dhillf@gmail.com> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com> Cc: Lin Feng <linfeng@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Marek Szyprowski [Thu, 29 Nov 2012 03:18:02 +0000 (14:18 +1100)]
mm: use migrate_prep() instead of migrate_prep_local()
__alloc_contig_migrate_range() should use all possible ways to get all the
pages migrated from the given memory range, so pruning per-cpu lru lists
for all CPUs is required, regadless the cost of such operation. Otherwise
some pages which got stuck at per-cpu lru list might get missed by
migration procedure causing the contiguous allocation to fail.
Reported-by: SeongHwan Yoon <sunghwan.yun@samsung.com> Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com> Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com> Acked-by: Michal Nazarewicz <mina86@mina86.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
thp, vmstat: implement HZP_ALLOC and HZP_ALLOC_FAILED events
hzp_alloc is incremented every time a huge zero page is successfully
allocated. It includes allocations which where dropped due
race with other allocation. Note, it doesn't count every map
of the huge zero page, only its allocation.
hzp_alloc_failed is incremented if kernel fails to allocate huge zero
page and falls back to using small pages.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: "H. Peter Anvin" <hpa@linux.intel.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
thp, vmstat: implement HZP_ALLOC and HZP_ALLOC_FAILED events
hzp_alloc is incremented every time a huge zero page is successfully
allocated. It includes allocations which where dropped due
race with other allocation. Note, it doesn't count every map
of the huge zero page, only its allocation.
hzp_alloc_failed is incremented if kernel fails to allocate huge zero
page and falls back to using small pages.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: "H. Peter Anvin" <hpa@linux.intel.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
H. Peter Anvin doesn't like huge zero page which sticks in memory forever
after the first allocation. Here's implementation of lockless refcounting
for huge zero page.
We have two basic primitives: {get,put}_huge_zero_page(). They
manipulate reference counter.
If counter is 0, get_huge_zero_page() allocates a new huge page and takes
two references: one for caller and one for shrinker. We free the page
only in shrinker callback if counter is 1 (only shrinker has the
reference).
put_huge_zero_page() only decrements counter. Counter is never zero in
put_huge_zero_page() since shrinker holds on reference.
Freeing huge zero page in shrinker callback helps to avoid frequent
allocate-free.
Refcounting has cost. On 4 socket machine I observe ~1% slowdown on
parallel (40 processes) read page faulting comparing to lazy huge page
allocation. I think it's pretty reasonable for synthetic benchmark.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: "H. Peter Anvin" <hpa@linux.intel.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
On write access to huge zero page we alloc a new huge page and clear it.
If ENOMEM, graceful fallback: we create a new pmd table and set pte
around fault address to newly allocated normal (4k) page. All other ptes
in the pmd set to normal zero page.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: "H. Peter Anvin" <hpa@linux.intel.com> Cc: Mel Gorman <mel@csn.ul.ie> Acked-by: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
On write access to huge zero page we alloc a new huge page and clear it.
If ENOMEM, graceful fallback: we create a new pmd table and set pte around
fault address to newly allocated normal (4k) page. All other ptes in the
pmd set to normal zero page.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: "H. Peter Anvin" <hpa@linux.intel.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
David Rientjes [Thu, 29 Nov 2012 03:17:35 +0000 (14:17 +1100)]
thp: copy_huge_pmd(): copy huge zero page v6 fix
Fix comment
Signed-off-by: David Rientjes <rientjes@google.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
During testing I noticed big (up to 2.5 times) memory consumption overhead
on some workloads (e.g. ft.A from NPB) if THP is enabled.
The main reason for that big difference is lacking zero page in THP case.
We have to allocate a real page on read page fault.
A program to demonstrate the issue:
#include <assert.h>
#include <stdlib.h>
#include <unistd.h>
#define MB 1024*1024
int main(int argc, char **argv)
{
char *p;
int i;
posix_memalign((void **)&p, 2 * MB, 200 * MB);
for (i = 0; i < 200 * MB; i+= 4096)
assert(p[i] == 0);
pause();
return 0;
}
With thp-never RSS is about 400k, but with thp-always it's 200M. After
the patcheset thp-always RSS is 400k too.
Design overview.
Huge zero page (hzp) is a non-movable huge page (2M on x86-64) filled with
zeros. The way how we allocate it changes in the patchset:
- [01/10] simplest way: hzp allocated on boot time in hugepage_init();
- [09/10] lazy allocation on first use;
- [10/10] lockless refcounting + shrinker-reclaimable hzp;
We setup it in do_huge_pmd_anonymous_page() if area around fault address
is suitable for THP and we've got read page fault. If we fail to setup
hzp (ENOMEM) we fallback to handle_pte_fault() as we normally do in THP.
On wp fault to hzp we allocate real memory for the huge page and clear it.
If ENOMEM, graceful fallback: we create a new pmd table and set pte
around fault address to newly allocated normal (4k) page. All other ptes
in the pmd set to normal zero page.
We cannot split hzp (and it's bug if we try), but we can split the pmd
which points to it. On splitting the pmd we create a table with all ptes
set to normal zero page.
===
By hpa's request I've tried alternative approach for hzp implementation
(see Virtual huge zero page patchset): pmd table with all entries set to
zero page. This way should be more cache friendly, but it increases TLB
pressure.
The problem with virtual huge zero page: it requires per-arch enabling.
We need a way to mark that pmd table has all ptes set to zero page.
Some numbers to compare two implementations (on 4s Westmere-EX):
Mirobenchmark1
==============
test:
posix_memalign((void **)&p, 2 * MB, 8 * GB);
for (i = 0; i < 100; i++) {
assert(memcmp(p, p + 4*GB, 4*GB) == 0);
asm volatile ("": : :"memory");
}
hzp:
Performance counter stats for './test_memcmp' (5 runs):
Lai Jiangshan [Thu, 29 Nov 2012 03:17:33 +0000 (14:17 +1100)]
memory_hotplug: ensure every online node has NORMAL memory
Old memory hotplug code and new online/movable may cause a online node
don't have any normal memory, but memory-management acts bad when we have
nodes which is online but don't have any normal memory. Example: it may
cause a bound task fail on all kernel allocation and cause the task can't
create task or create other kernel object.
So we disable non-normal-memory-node here, we will enable it when we
prepared.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Greg KH <greg@kroah.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Lai Jiangshan [Thu, 29 Nov 2012 03:17:32 +0000 (14:17 +1100)]
mm, memory-hotplug: dynamic configure movable memory and portion memory
Add online_movable and online_kernel for logic memory hotplug. This is
the dynamic version of "movablecore" & "kernelcore".
We have the same reason to introduce it as to introduce "movablecore" &
"kernelcore". It has the same motive as "movablecore" & "kernelcore", but
it is dynamic/running-time:
o We can configure memory as kernelcore or movablecore after boot.
Userspace workload is increased, we need more hugepage, we can't use
"online_movable" to add memory and allow the system use more
THP(transparent-huge-page), vice-verse when kernel workload is increase.
Also help for virtualization to dynamic configure host/guest's memory,
to save/(reduce waste) memory.
Memory capacity on Demand
o When a new node is physically online after boot, we need to use
"online_movable" or "online_kernel" to configure/portion it as we
expected when we logic-online it.
This configuration also helps for physically-memory-migrate.
o all benefit as the same as existed "movablecore" & "kernelcore".
o Preparing for movable-node, which is very important for power-saving,
hardware partitioning and high-available-system(hardware fault
management).
(Note, we don't introduce movable-node here.)
Action behavior:
When a memoryblock/memorysection is onlined by "online_movable", the kernel
will not have directly reference to the page of the memoryblock,
thus we can remove that memory any time when needed.
When it is online by "online_kernel", the kernel can use it.
When it is online by "online", the zone type doesn't changed.
Current constraints:
Only the memoryblock which is adjacent to the ZONE_MOVABLE
can be online from ZONE_NORMAL to ZONE_MOVABLE.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Greg KH <greg@kroah.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Marek Szyprowski [Thu, 29 Nov 2012 03:17:32 +0000 (14:17 +1100)]
mm: cma: WARN if freed memory is still in use
Memory returned to free_contig_range() must have no other references. Let
kernel to complain loudly if page reference count is not equal to 1.
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com> Reviewed-by: Kyungmin Park <kyungmin.park@samsung.com> Acked-by: Michal Nazarewicz <mina86@mina86.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Joonsoo Kim [Thu, 29 Nov 2012 03:17:31 +0000 (14:17 +1100)]
bootmem: fix wrong call parameter for free_bootmem()
It is strange that alloc_bootmem() returns a virtual address and
free_bootmem() requires a physical address. Anyway, free_bootmem()'s
first parameter should be physical address.
There are some call sites for free_bootmem() with virtual address. So fix
them.
Signed-off-by: Joonsoo Kim <js1304@gmail.com> Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Marek Szyprowski [Thu, 29 Nov 2012 03:17:29 +0000 (14:17 +1100)]
mm: cma: remove watermark hacks
Commits 2139cbe627b89 ("cma: fix counting of isolated pages") and d95ea5d18e69951 ("cma: fix watermark checking") introduced a reliable
method of free page accounting when memory is being allocated from CMA
regions, so the workaround introduced earlier by commit 49f223a9cd96c72
("mm: trigger page reclaim in alloc_contig_range() to stabilise
watermarks") can be finally removed.
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Mel Gorman <mel@csn.ul.ie> Acked-by: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Propagate
mm-fix-incorrect-nr_free_pages-accounting-appears-like-memory-leak.patch
through mm-cma-skip-watermarks-check-for-already-isolated-blocks-in-split_free_page.patch
Cc: Arnd Bergmann <arnd@arndb.de> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Marek Szyprowski [Thu, 29 Nov 2012 03:17:28 +0000 (14:17 +1100)]
mm: cma: skip watermarks check for already isolated blocks in split_free_page()
Since commit 2139cbe627b8 ("cma: fix counting of isolated pages") free
pages in isolated pageblocks are not accounted to NR_FREE_PAGES counters,
so watermarks check is not required if one operates on a free page in
isolated pageblock.
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Mel Gorman <mel@csn.ul.ie> Acked-by: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
David Rientjes [Thu, 29 Nov 2012 03:17:28 +0000 (14:17 +1100)]
mm, oom: fix race when specifying a thread as the oom origin
test_set_oom_score_adj() and compare_swap_oom_score_adj() are used to
specify that current should be killed first if an oom condition occurs in
between the two calls.
The usage is
short oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
...
compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj);
to store the thread's oom_score_adj, temporarily change it to the maximum
score possible, and then restore the old value if it is still the same.
This happens to still be racy, however, if the user writes
OOM_SCORE_ADJ_MAX to /proc/pid/oom_score_adj in between the two calls.
The compare_swap_oom_score_adj() will then incorrectly reset the old value
prior to the write of OOM_SCORE_ADJ_MAX.
To fix this, introduce a new oom_flags_t member in struct signal_struct
that will be used for per-thread oom killer flags. KSM and swapoff can
now use a bit in this member to specify that threads should be killed
first in oom conditions without playing around with oom_score_adj.
This also allows the correct oom_score_adj to always be shown when reading
/proc/pid/oom_score.
Signed-off-by: David Rientjes <rientjes@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Cc: Anton Vorontsov <anton.vorontsov@linaro.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
David Rientjes [Thu, 29 Nov 2012 03:17:28 +0000 (14:17 +1100)]
mm, oom: change type of oom_score_adj to short
The maximum oom_score_adj is 1000 and the minimum oom_score_adj is -1000,
so this range can be represented by the signed short type with no
functional change. The extra space this frees up in struct signal_struct
will be used for per-thread oom kill flags in the next patch.
Signed-off-by: David Rientjes <rientjes@google.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Michal Hocko <mhocko@suse.cz> Cc: Anton Vorontsov <anton.vorontsov@linaro.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Rafael Aquini [Thu, 29 Nov 2012 03:17:26 +0000 (14:17 +1100)]
mm: introduce putback_movable_pages()
The PATCH "mm: introduce compaction and migration for virtio ballooned pages"
hacks around putback_lru_pages() in order to allow ballooned pages to be
re-inserted on balloon page list as if a ballooned page was like a LRU page.
As ballooned pages are not legitimate LRU pages, this patch introduces
putback_movable_pages() to properly cope with cases where the isolated
pageset contains ballooned pages and LRU pages, thus fixing the mentioned
inelegant hack around putback_lru_pages().
Signed-off-by: Rafael Aquini <aquini@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Andi Kleen <andi@firstfloor.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
drivers/virtio/virtio_balloon.c: In function 'fill_balloon':
drivers/virtio/virtio_balloon.c:142:4: warning: format '%zu' expects argument of type 'size_t', but argument 3 has type 'long unsigned int' [-Wformat]
The type of PAGE_SIZE is different on different architectures (or at
least, it used to be). Make things predictable.
Cc: Rafael Aquini <aquini@redhat.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Rafael Aquini [Thu, 29 Nov 2012 03:17:25 +0000 (14:17 +1100)]
virtio_balloon: introduce migration primitives to balloon pages
Memory fragmentation introduced by ballooning might reduce significantly
the number of 2MB contiguous memory blocks that can be used within a guest,
thus imposing performance penalties associated with the reduced number of
transparent huge pages that could be used by the guest workload.
Besides making balloon pages movable at allocation time and introducing
the necessary primitives to perform balloon page migration/compaction,
this patch also introduces the following locking scheme, in order to
enhance the syncronization methods for accessing elements of struct
virtio_balloon, thus providing protection against concurrent access
introduced by parallel memory migration threads.
- balloon_lock (mutex) : synchronizes the access demand to elements of
struct virtio_balloon and its queue operations;
Signed-off-by: Rafael Aquini <aquini@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Andi Kleen <andi@firstfloor.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Rafael Aquini [Thu, 29 Nov 2012 03:17:25 +0000 (14:17 +1100)]
mm: introduce compaction and migration for ballooned pages
Memory fragmentation introduced by ballooning might reduce significantly
the number of 2MB contiguous memory blocks that can be used within a guest,
thus imposing performance penalties associated with the reduced number of
transparent huge pages that could be used by the guest workload.
This patch introduces the helper functions as well as the necessary changes
to teach compaction and migration bits how to cope with pages which are
part of a guest memory balloon, in order to make them movable by memory
compaction procedures.
Signed-off-by: Rafael Aquini <aquini@redhat.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
David Rientjes [Thu, 29 Nov 2012 03:17:24 +0000 (14:17 +1100)]
mm: introduce a common interface for balloon pages mobility fix
It's useful to keep memory defragmented so that all high-order page
allocations have a chance to succeed, not simply transparent hugepages.
Thus, allow balloon compaction for any system with memory compaction
enabled, which is the defconfig.
Signed-off-by: David Rientjes <rientjes@google.com> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Rafael Aquini <aquini@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Rafael Aquini [Thu, 29 Nov 2012 03:17:24 +0000 (14:17 +1100)]
mm: fix balloon_page_movable() page->flags check
Fix the following crash by fixing and enhancing the way page->flags are
tested to identify a ballooned page.
BUG: unable to handle kernel NULL pointer dereference at 0000000000000194
IP: [<ffffffff8122b354>] isolate_migratepages_range+0x344/0x7b0
The NULL pointer deref was taking place because balloon_page_movable()
page->flags tests were incomplete and we ended up inadvertently poking at
private pages.
Signed-off-by: Rafael Aquini <aquini@redhat.com> Reported-by: Sasha Levin <levinsasha928@gmail.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Rafael Aquini [Thu, 29 Nov 2012 03:17:24 +0000 (14:17 +1100)]
mm: introduce a common interface for balloon pages mobility
Memory fragmentation introduced by ballooning might reduce significantly
the number of 2MB contiguous memory blocks that can be used within a guest,
thus imposing performance penalties associated with the reduced number of
transparent huge pages that could be used by the guest workload.
This patch introduces a common interface to help a balloon driver on
making its page set movable to compaction, and thus allowing the system
to better leverage the compation efforts on memory defragmentation.
Signed-off-by: Rafael Aquini <aquini@redhat.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Rafael Aquini [Thu, 29 Nov 2012 03:17:23 +0000 (14:17 +1100)]
mm: redefine address_space.assoc_mapping
Overhaul struct address_space.assoc_mapping renaming it to
address_space.private_data and its type is redefined to void*. By this
approach we consistently name the .private_* elements from struct
address_space as well as allow extended usage for address_space
association with other data structures through ->private_data.
Also, all users of old ->assoc_mapping element are converted to reflect
its new name and type change (->private_data).
Signed-off-by: Rafael Aquini <aquini@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Andi Kleen <andi@firstfloor.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Memory fragmentation introduced by ballooning might reduce significantly
the number of 2MB contiguous memory blocks that can be used within a
guest, thus imposing performance penalties associated with the reduced
number of transparent huge pages that could be used by the guest workload.
This patch-set follows the main idea discussed at 2012 LSFMMS session:
"Ballooning for transparent huge pages" -- http://lwn.net/Articles/490114/
to introduce the required changes to the virtio_balloon driver, as well as
the changes to the core compaction & migration bits, in order to make
those subsystems aware of ballooned pages and allow memory balloon pages
become movable within a guest, thus avoiding the aforementioned
fragmentation issue
Following are numbers that prove this patch benefits on allowing
compaction to be more effective at memory ballooned guests.
Results for STRESS-HIGHALLOC benchmark, from Mel Gorman's mmtests suite,
running on a 4gB RAM KVM guest which was ballooning 512mB RAM in 64mB
chunks, at every minute (inflating/deflating), while test was running:
Introduce MIGRATEPAGE_SUCCESS as the default return code for
address_space_operations.migratepage() method and documents the expected
return code for the same method in failure cases.
Signed-off-by: Rafael Aquini <aquini@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Andi Kleen <andi@firstfloor.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
projects / karo-tx-linux.git / log