vma_adjust() does vma_set_policy(vma, vma_policy(next)) and this
is doubly wrong:
1. This leaks vma->vm_policy if it is not NULL and not equal to
next->vm_policy.
This can happen if vma_merge() expands "area", not prev (case 8).
2. This sets the wrong policy if vma_merge() joins prev and area,
area is the vma the caller needs to update and it still has the
old policy.
Revert commit 1444f92c84 ("mm: merging memory blocks resets
mempolicy") which introduced these problems.
Change mbind_range() to recheck mpol_equal() after vma_merge() to fix
the problem that commit tried to address.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Steven T Hampson <steven.t.hampson@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Since all architectures have been converted to use vm_unmapped_area(),
there is no remaining use for the free_area_cache.
Signed-off-by: Michel Lespinasse <walken@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Richard Henderson <rth@twiddle.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It is counterintuitive at best that mmap'ing a hugetlbfs file with
MAP_HUGETLB fails, while mmap'ing it without will a) succeed and b)
return huge pages.
v2: use is_file_hugepages(), as suggested by Jianguo
Signed-off-by: Joern Engel <joern@logfs.org>
Cc: Jianguo Wu <wujianguo@huawei.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
(*->vm_end - *->vm_start) >> PAGE_SHIFT operation is implemented
as a inline funcion vma_pages() in linux/mm.h, so using it.
Signed-off-by: Libin <huawei.libin@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The current kernel returns -EINVAL unless a given mmap length is
"almost" hugepage aligned. This is because in sys_mmap_pgoff() the
given length is passed to vm_mmap_pgoff() as it is without being aligned
with hugepage boundary.
This is a regression introduced in commit 40716e2924 ("hugetlbfs: fix
alignment of huge page requests"), where alignment code is pushed into
hugetlb_file_setup() and the variable len in caller side is not changed.
To fix this, this patch partially reverts that commit, and adds
alignment code in caller side. And it also introduces hstate_sizelog()
in order to get proper hstate to specified hugepage size.
Addresses https://bugzilla.kernel.org/show_bug.cgi?id=56881
[akpm@linux-foundation.org: fix warning when CONFIG_HUGETLB_PAGE=n]
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: <iceman_dvd@yahoo.com>
Cc: Steven Truelove <steven.truelove@utoronto.ca>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix a corner case for MAP_FIXED when requested mapping length is larger
than rlimit for virtual memory. In such case any overlapping mappings
are unmapped before we check for the limit and return ENOMEM.
The check is moved before the loop that unmaps overlapping parts of
existing mappings. When we are about to hit the limit (currently mapped
pages + len > limit) we scan for overlapping pages and check again
accounting for them.
This fixes situation when userspace program expects that the previous
mappings are preserved after the mmap() syscall has returned with error.
(POSIX clearly states that successfull mapping shall replace any
previous mappings.)
This corner case was found and can be tested with LTP testcase:
testcases/open_posix_testsuite/conformance/interfaces/mmap/24-2.c
In this case the mmap, which is clearly over current limit, unmaps
dynamic libraries and the testcase segfaults right after returning into
userspace.
I've also looked at the second instance of the unmapping loop in the
do_brk(). The do_brk() is called from brk() syscall and from vm_brk().
The brk() syscall checks for overlapping mappings and bails out when
there are any (so it can't be triggered from the brk syscall). The
vm_brk() is called only from binmft handlers so it shouldn't be
triggered unless binmft handler created overlapping mappings.
Signed-off-by: Cyril Hrubis <chrubis@suse.cz>
Reviewed-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Alter the admin and user reserves of the previous patches in this series
when memory is added or removed.
If memory is added and the reserves have been eliminated or increased
above the default max, then we'll trust the admin.
If memory is removed and there isn't enough free memory, then we need to
reset the reserves.
Otherwise keep the reserve set by the admin.
The reserve reset code is the same as the reserve initialization code.
I tested hot addition and removal by triggering it via sysfs. The
reserves shrunk when they were set high and memory was removed. They
were reset higher when memory was added again.
[akpm@linux-foundation.org: use register_hotmemory_notifier()]
[akpm@linux-foundation.org: init_user_reserve() and init_admin_reserve can no longer be __meminit]
[fengguang.wu@intel.com: make init_reserve_notifier() static]
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Andrew Shewmaker <agshew@gmail.com>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add an admin_reserve_kbytes knob to allow admins to change the hardcoded
memory reserve to something other than 3%, which may be multiple
gigabytes on large memory systems. Only about 8MB is necessary to
enable recovery in the default mode, and only a few hundred MB are
required even when overcommit is disabled.
This affects OVERCOMMIT_GUESS and OVERCOMMIT_NEVER.
admin_reserve_kbytes is initialized to min(3% free pages, 8MB)
I arrived at 8MB by summing the RSS of sshd or login, bash, and top.
Please see first patch in this series for full background, motivation,
testing, and full changelog.
[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: make init_admin_reserve() static]
Signed-off-by: Andrew Shewmaker <agshew@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add user_reserve_kbytes knob.
Limit the growth of the memory reserved for other user processes to
min(3% current process size, user_reserve_pages). Only about 8MB is
necessary to enable recovery in the default mode, and only a few hundred
MB are required even when overcommit is disabled.
user_reserve_pages defaults to min(3% free pages, 128MB)
I arrived at 128MB by taking the max VSZ of sshd, login, bash, and top ...
then adding the RSS of each.
This only affects OVERCOMMIT_NEVER mode.
Background
1. user reserve
__vm_enough_memory reserves a hardcoded 3% of the current process size for
other applications when overcommit is disabled. This was done so that a
user could recover if they launched a memory hogging process. Without the
reserve, a user would easily run into a message such as:
bash: fork: Cannot allocate memory
2. admin reserve
Additionally, a hardcoded 3% of free memory is reserved for root in both
overcommit 'guess' and 'never' modes. This was intended to prevent a
scenario where root-cant-log-in and perform recovery operations.
Note that this reserve shrinks, and doesn't guarantee a useful reserve.
Motivation
The two hardcoded memory reserves should be updated to account for current
memory sizes.
Also, the admin reserve would be more useful if it didn't shrink too much.
When the current code was originally written, 1GB was considered
"enterprise". Now the 3% reserve can grow to multiple GB on large memory
systems, and it only needs to be a few hundred MB at most to enable a user
or admin to recover a system with an unwanted memory hogging process.
I've found that reducing these reserves is especially beneficial for a
specific type of application load:
* single application system
* one or few processes (e.g. one per core)
* allocating all available memory
* not initializing every page immediately
* long running
I've run scientific clusters with this sort of load. A long running job
sometimes failed many hours (weeks of CPU time) into a calculation. They
weren't initializing all of their memory immediately, and they weren't
using calloc, so I put systems into overcommit 'never' mode. These
clusters run diskless and have no swap.
However, with the current reserves, a user wishing to allocate as much
memory as possible to one process may be prevented from using, for
example, almost 2GB out of 32GB.
The effect is less, but still significant when a user starts a job with
one process per core. I have repeatedly seen a set of processes
requesting the same amount of memory fail because one of them could not
allocate the amount of memory a user would expect to be able to allocate.
For example, Message Passing Interfce (MPI) processes, one per core. And
it is similar for other parallel programming frameworks.
Changing this reserve code will make the overcommit never mode more useful
by allowing applications to allocate nearly all of the available memory.
Also, the new admin_reserve_kbytes will be safer than the current behavior
since the hardcoded 3% of available memory reserve can shrink to something
useless in the case where applications have grabbed all available memory.
Risks
* "bash: fork: Cannot allocate memory"
The downside of the first patch-- which creates a tunable user reserve
that is only used in overcommit 'never' mode--is that an admin can set
it so low that a user may not be able to kill their process, even if
they already have a shell prompt.
Of course, a user can get in the same predicament with the current 3%
reserve--they just have to launch processes until 3% becomes negligible.
* root-cant-log-in problem
The second patch, adding the tunable rootuser_reserve_pages, allows
the admin to shoot themselves in the foot by setting it too small. They
can easily get the system into a state where root-can't-log-in.
However, the new admin_reserve_kbytes will be safer than the current
behavior since the hardcoded 3% of available memory reserve can shrink
to something useless in the case where applications have grabbed all
available memory.
Alternatives
* Memory cgroups provide a more flexible way to limit application memory.
Not everyone wants to set up cgroups or deal with their overhead.
* We could create a fourth overcommit mode which provides smaller reserves.
The size of useful reserves may be drastically different depending
on the whether the system is embedded or enterprise.
* Force users to initialize all of their memory or use calloc.
Some users don't want/expect the system to overcommit when they malloc.
Overcommit 'never' mode is for this scenario, and it should work well.
The new user and admin reserve tunables are simple to use, with low
overhead compared to cgroups. The patches preserve current behavior where
3% of memory is less than 128MB, except that the admin reserve doesn't
shrink to an unusable size under pressure. The code allows admins to tune
for embedded and enterprise usage.
FAQ
* How is the root-cant-login problem addressed?
What happens if admin_reserve_pages is set to 0?
Root is free to shoot themselves in the foot by setting
admin_reserve_kbytes too low.
On x86_64, the minimum useful reserve is:
8MB for overcommit 'guess'
128MB for overcommit 'never'
admin_reserve_pages defaults to min(3% free memory, 8MB)
So, anyone switching to 'never' mode needs to adjust
admin_reserve_pages.
* How do you calculate a minimum useful reserve?
A user or the admin needs enough memory to login and perform
recovery operations, which includes, at a minimum:
sshd or login + bash (or some other shell) + top (or ps, kill, etc.)
For overcommit 'guess', we can sum resident set sizes (RSS)
because we only need enough memory to handle what the recovery
programs will typically use. On x86_64 this is about 8MB.
For overcommit 'never', we can take the max of their virtual sizes (VSZ)
and add the sum of their RSS. We use VSZ instead of RSS because mode
forces us to ensure we can fulfill all of the requested memory allocations--
even if the programs only use a fraction of what they ask for.
On x86_64 this is about 128MB.
When swap is enabled, reserves are useful even when they are as
small as 10MB, regardless of overcommit mode.
When both swap and overcommit are disabled, then the admin should
tune the reserves higher to be absolutley safe. Over 230MB each
was safest in my testing.
* What happens if user_reserve_pages is set to 0?
Note, this only affects overcomitt 'never' mode.
Then a user will be able to allocate all available memory minus
admin_reserve_kbytes.
However, they will easily see a message such as:
"bash: fork: Cannot allocate memory"
And they won't be able to recover/kill their application.
The admin should be able to recover the system if
admin_reserve_kbytes is set appropriately.
* What's the difference between overcommit 'guess' and 'never'?
"Guess" allows an allocation if there are enough free + reclaimable
pages. It has a hardcoded 3% of free pages reserved for root.
"Never" allows an allocation if there is enough swap + a configurable
percentage (default is 50) of physical RAM. It has a hardcoded 3% of
free pages reserved for root, like "Guess" mode. It also has a
hardcoded 3% of the current process size reserved for additional
applications.
* Why is overcommit 'guess' not suitable even when an app eventually
writes to every page? It takes free pages, file pages, available
swap pages, reclaimable slab pages into consideration. In other words,
these are all pages available, then why isn't overcommit suitable?
Because it only looks at the present state of the system. It
does not take into account the memory that other applications have
malloced, but haven't initialized yet. It overcommits the system.
Test Summary
There was little change in behavior in the default overcommit 'guess'
mode with swap enabled before and after the patch. This was expected.
Systems run most predictably (i.e. no oom kills) in overcommit 'never'
mode with swap enabled. This also allowed the most memory to be allocated
to a user application.
Overcommit 'guess' mode without swap is a bad idea. It is easy to
crash the system. None of the other tested combinations crashed.
This matches my experience on the Roadrunner supercomputer.
Without the tunable user reserve, a system in overcommit 'never' mode
and without swap does not allow the admin to recover, although the
admin can.
With the new tunable reserves, a system in overcommit 'never' mode
and without swap can be configured to:
1. maximize user-allocatable memory, running close to the edge of
recoverability
2. maximize recoverability, sacrificing allocatable memory to
ensure that a user cannot take down a system
Test Description
Fedora 18 VM - 4 x86_64 cores, 5725MB RAM, 4GB Swap
System is booted into multiuser console mode, with unnecessary services
turned off. Caches were dropped before each test.
Hogs are user memtester processes that attempt to allocate all free memory
as reported by /proc/meminfo
In overcommit 'never' mode, memory_ratio=100
Test Results
3.9.0-rc1-mm1
Overcommit | Swap | Hogs | MB Got/Wanted | OOMs | User Recovery | Admin Recovery
---------- ---- ---- ------------- ---- ------------- --------------
guess yes 1 5432/5432 no yes yes
guess yes 4 5444/5444 1 yes yes
guess no 1 5302/5449 no yes yes
guess no 4 - crash no no
never yes 1 5460/5460 1 yes yes
never yes 4 5460/5460 1 yes yes
never no 1 5218/5432 no no yes
never no 4 5203/5448 no no yes
3.9.0-rc1-mm1-tunablereserves
User and Admin Recovery show their respective reserves, if applicable.
Overcommit | Swap | Hogs | MB Got/Wanted | OOMs | User Recovery | Admin Recovery
---------- ---- ---- ------------- ---- ------------- --------------
guess yes 1 5419/5419 no - yes 8MB yes
guess yes 4 5436/5436 1 - yes 8MB yes
guess no 1 5440/5440 * - yes 8MB yes
guess no 4 - crash - no 8MB no
* process would successfully mlock, then the oom killer would pick it
never yes 1 5446/5446 no 10MB yes 20MB yes
never yes 4 5456/5456 no 10MB yes 20MB yes
never no 1 5387/5429 no 128MB no 8MB barely
never no 1 5323/5428 no 226MB barely 8MB barely
never no 1 5323/5428 no 226MB barely 8MB barely
never no 1 5359/5448 no 10MB no 10MB barely
never no 1 5323/5428 no 0MB no 10MB barely
never no 1 5332/5428 no 0MB no 50MB yes
never no 1 5293/5429 no 0MB no 90MB yes
never no 1 5001/5427 no 230MB yes 338MB yes
never no 4* 4998/5424 no 230MB yes 338MB yes
* more memtesters were launched, able to allocate approximately another 100MB
Future Work
- Test larger memory systems.
- Test an embedded image.
- Test other architectures.
- Time malloc microbenchmarks.
- Would it be useful to be able to set overcommit policy for
each memory cgroup?
- Some lines are slightly above 80 chars.
Perhaps define a macro to convert between pages and kb?
Other places in the kernel do this.
[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: make init_user_reserve() static]
Signed-off-by: Andrew Shewmaker <agshew@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
On architectures where a pgd entry may be shared between user and kernel
(e.g. ARM+LPAE), freeing page tables needs a ceiling other than 0.
This patch introduces a generic USER_PGTABLES_CEILING that arch code can
override. It is the responsibility of the arch code setting the ceiling
to ensure the complete freeing of the page tables (usually in
pgd_free()).
[catalin.marinas@arm.com: commit log; shift_arg_pages(), asm-generic/pgtables.h changes]
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: <stable@vger.kernel.org> [3.3+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Remove the WARN_ON_ONCE(!mm) check as the comment suggested. Kernel
code calls find_vma only when it is absolutely sure that the mm_struct
arg to it is non-NULL.
Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: k80c <k80ck80c@gmail.com>
Cc: Michel Lespinasse <walken@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
find_vma() can be called by multiple threads with read lock
held on mm->mmap_sem and any of them can update mm->mmap_cache.
Prevent compiler from re-fetching mm->mmap_cache, because other
readers could update it in the meantime:
thread 1 thread 2
|
find_vma() | find_vma()
struct vm_area_struct *vma = NULL; |
vma = mm->mmap_cache; |
if (!(vma && vma->vm_end > addr |
&& vma->vm_start <= addr)) { |
| mm->mmap_cache = vma;
return vma; |
^^ compiler may optimize this |
local variable out and re-read |
mm->mmap_cache |
This issue can be reproduced with gcc-4.8.0-1 on s390x by running
mallocstress testcase from LTP, which triggers:
kernel BUG at mm/rmap.c:1088!
Call Trace:
([<000003d100c57000>] 0x3d100c57000)
[<000000000023a1c0>] do_wp_page+0x2fc/0xa88
[<000000000023baae>] handle_pte_fault+0x41a/0xac8
[<000000000023d832>] handle_mm_fault+0x17a/0x268
[<000000000060507a>] do_protection_exception+0x1e2/0x394
[<0000000000603a04>] pgm_check_handler+0x138/0x13c
[<000003fffcf1f07a>] 0x3fffcf1f07a
Last Breaking-Event-Address:
[<000000000024755e>] page_add_new_anon_rmap+0xc2/0x168
Thanks to Jakub Jelinek for his insight on gcc and helping to
track this down.
Signed-off-by: Jan Stancek <jstancek@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This reverts commit 1869305009 ("mm: introduce VM_POPULATE flag to
better deal with racy userspace programs").
VM_POPULATE only has any effect when userspace plays racy games with
vmas by trying to unmap and remap memory regions that mmap or mlock are
operating on.
Also, the only effect of VM_POPULATE when userspace plays such games is
that it avoids populating new memory regions that get remapped into the
address range that was being operated on by the original mmap or mlock
calls.
Let's remove VM_POPULATE as there isn't any strong argument to mandate a
new vm_flag.
Signed-off-by: Michel Lespinasse <walken@google.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The stack vma is designed to grow automatically (marked with VM_GROWSUP
or VM_GROWSDOWN depending on architecture) when an access is made beyond
the existing boundary. However, particularly if you have not limited
your stack at all ("ulimit -s unlimited"), this can cause the stack to
grow even if the access was really just one past *another* segment.
And that's wrong, especially since we first grow the segment, but then
immediately later enforce the stack guard page on the last page of the
segment. So _despite_ first growing the stack segment as a result of
the access, the kernel will then make the access cause a SIGSEGV anyway!
So do the same logic as the guard page check does, and consider an
access to within one page of the next segment to be a bad access, rather
than growing the stack to abut the next segment.
Reported-and-tested-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull vfs pile (part one) from Al Viro:
"Assorted stuff - cleaning namei.c up a bit, fixing ->d_name/->d_parent
locking violations, etc.
The most visible changes here are death of FS_REVAL_DOT (replaced with
"has ->d_weak_revalidate()") and a new helper getting from struct file
to inode. Some bits of preparation to xattr method interface changes.
Misc patches by various people sent this cycle *and* ocfs2 fixes from
several cycles ago that should've been upstream right then.
PS: the next vfs pile will be xattr stuff."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (46 commits)
saner proc_get_inode() calling conventions
proc: avoid extra pde_put() in proc_fill_super()
fs: change return values from -EACCES to -EPERM
fs/exec.c: make bprm_mm_init() static
ocfs2/dlm: use GFP_ATOMIC inside a spin_lock
ocfs2: fix possible use-after-free with AIO
ocfs2: Fix oops in ocfs2_fast_symlink_readpage() code path
get_empty_filp()/alloc_file() leave both ->f_pos and ->f_version zero
target: writev() on single-element vector is pointless
export kernel_write(), convert open-coded instances
fs: encode_fh: return FILEID_INVALID if invalid fid_type
kill f_vfsmnt
vfs: kill FS_REVAL_DOT by adding a d_weak_revalidate dentry op
nfsd: handle vfs_getattr errors in acl protocol
switch vfs_getattr() to struct path
default SET_PERSONALITY() in linux/elf.h
ceph: prepopulate inodes only when request is aborted
d_hash_and_lookup(): export, switch open-coded instances
9p: switch v9fs_set_create_acl() to inode+fid, do it before d_instantiate()
9p: split dropping the acls from v9fs_set_create_acl()
...
The comment in commit 4fc3f1d66b ("mm/rmap, migration: Make
rmap_walk_anon() and try_to_unmap_anon() more scalable") says:
| Rename anon_vma_[un]lock() => anon_vma_[un]lock_write(),
| to make it clearer that it's an exclusive write-lock in
| that case - suggested by Rik van Riel.
But that commit renames only anon_vma_lock()
Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
swap_lock is heavily contended when I test swap to 3 fast SSD (even
slightly slower than swap to 2 such SSD). The main contention comes
from swap_info_get(). This patch tries to fix the gap with adding a new
per-partition lock.
Global data like nr_swapfiles, total_swap_pages, least_priority and
swap_list are still protected by swap_lock.
nr_swap_pages is an atomic now, it can be changed without swap_lock. In
theory, it's possible get_swap_page() finds no swap pages but actually
there are free swap pages. But sounds not a big problem.
Accessing partition specific data (like scan_swap_map and so on) is only
protected by swap_info_struct.lock.
Changing swap_info_struct.flags need hold swap_lock and
swap_info_struct.lock, because scan_scan_map() will check it. read the
flags is ok with either the locks hold.
If both swap_lock and swap_info_struct.lock must be hold, we always hold
the former first to avoid deadlock.
swap_entry_free() can change swap_list. To delete that code, we add a
new highest_priority_index. Whenever get_swap_page() is called, we
check it. If it's valid, we use it.
It's a pity get_swap_page() still holds swap_lock(). But in practice,
swap_lock() isn't heavily contended in my test with this patch (or I can
say there are other much more heavier bottlenecks like TLB flush). And
BTW, looks get_swap_page() doesn't really need the lock. We never free
swap_info[] and we check SWAP_WRITEOK flag. The only risk without the
lock is we could swapout to some low priority swap, but we can quickly
recover after several rounds of swap, so sounds not a big deal to me.
But I'd prefer to fix this if it's a real problem.
"swap: make each swap partition have one address_space" improved the
swapout speed from 1.7G/s to 2G/s. This patch further improves the
speed to 2.3G/s, so around 15% improvement. It's a multi-process test,
so TLB flush isn't the biggest bottleneck before the patches.
[arnd@arndb.de: fix it for nommu]
[hughd@google.com: add missing unlock]
[minchan@kernel.org: get rid of lockdep whinge on sys_swapon]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
do_mmap_pgoff() rounds up the desired size to the next PAGE_SIZE
multiple, however there was no equivalent code in mm_populate(), which
caused issues.
This could be fixed by introduced the same rounding in mm_populate(),
however I think it's preferable to make do_mmap_pgoff() return populate
as a size rather than as a boolean, so we don't have to duplicate the
size rounding logic in mm_populate().
Signed-off-by: Michel Lespinasse <walken@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Tested-by: Andy Lutomirski <luto@amacapital.net>
Cc: Greg Ungerer <gregungerer@westnet.com.au>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The vm_populate() code populates user mappings without constantly
holding the mmap_sem. This makes it susceptible to racy userspace
programs: the user mappings may change while vm_populate() is running,
and in this case vm_populate() may end up populating the new mapping
instead of the old one.
In order to reduce the possibility of userspace getting surprised by
this behavior, this change introduces the VM_POPULATE vma flag which
gets set on vmas we want vm_populate() to work on. This way
vm_populate() may still end up populating the new mapping after such a
race, but only if the new mapping is also one that the user has
requested (using MAP_SHARED, MAP_LOCKED or mlock) to be populated.
Signed-off-by: Michel Lespinasse <walken@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Tested-by: Andy Lutomirski <luto@amacapital.net>
Cc: Greg Ungerer <gregungerer@westnet.com.au>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In find_extend_vma(), we don't need mlock_vma_pages_range() to verify
the vma type - we know we're working with a stack. So, we can call
directly into __mlock_vma_pages_range(), and remove the last
make_pages_present() call site.
Note that we don't use mm_populate() here, so we can't release the
mmap_sem while allocating new stack pages. This is deemed acceptable,
because the stack vmas grow by a bounded number of pages at a time, and
these are anon pages so we don't have to read from disk to populate
them.
Signed-off-by: Michel Lespinasse <walken@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Tested-by: Andy Lutomirski <luto@amacapital.net>
Cc: Greg Ungerer <gregungerer@westnet.com.au>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
After the MAP_POPULATE handling has been moved to mmap_region() call
sites, the only remaining use of the flags argument is to pass the
MAP_NORESERVE flag. This can be just as easily handled by
do_mmap_pgoff(), so do that and remove the mmap_region() flags
parameter.
[akpm@linux-foundation.org: remove double parens]
Signed-off-by: Michel Lespinasse <walken@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Tested-by: Andy Lutomirski <luto@amacapital.net>
Cc: Greg Ungerer <gregungerer@westnet.com.au>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When creating new mappings using the MAP_POPULATE / MAP_LOCKED flags (or
with MCL_FUTURE in effect), we want to populate the pages within the
newly created vmas. This may take a while as we may have to read pages
from disk, so ideally we want to do this outside of the write-locked
mmap_sem region.
This change introduces mm_populate(), which is used to defer populating
such mappings until after the mmap_sem write lock has been released.
This is implemented as a generalization of the former do_mlock_pages(),
which accomplished the same task but was using during mlock() /
mlockall().
Signed-off-by: Michel Lespinasse <walken@google.com>
Reported-by: Andy Lutomirski <luto@amacapital.net>
Acked-by: Rik van Riel <riel@redhat.com>
Tested-by: Andy Lutomirski <luto@amacapital.net>
Cc: Greg Ungerer <gregungerer@westnet.com.au>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull scheduler changes from Ingo Molnar:
"Main changes:
- scheduler side full-dynticks (user-space execution is undisturbed
and receives no timer IRQs) preparation changes that convert the
cputime accounting code to be full-dynticks ready, from Frederic
Weisbecker.
- Initial sched.h split-up changes, by Clark Williams
- select_idle_sibling() performance improvement by Mike Galbraith:
" 1 tbench pair (worst case) in a 10 core + SMT package:
pre 15.22 MB/sec 1 procs
post 252.01 MB/sec 1 procs "
- sched_rr_get_interval() ABI fix/change. We think this detail is not
used by apps (so it's not an ABI in practice), but lets keep it
under observation.
- misc RT scheduling cleanups, optimizations"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
sched/rt: Add <linux/sched/rt.h> header to <linux/init_task.h>
cputime: Remove irqsave from seqlock readers
sched, powerpc: Fix sched.h split-up build failure
cputime: Restore CPU_ACCOUNTING config defaults for PPC64
sched/rt: Move rt specific bits into new header file
sched/rt: Add a tuning knob to allow changing SCHED_RR timeslice
sched: Move sched.h sysctl bits into separate header
sched: Fix signedness bug in yield_to()
sched: Fix select_idle_sibling() bouncing cow syndrome
sched/rt: Further simplify pick_rt_task()
sched/rt: Do not account zero delta_exec in update_curr_rt()
cputime: Safely read cputime of full dynticks CPUs
kvm: Prepare to add generic guest entry/exit callbacks
cputime: Use accessors to read task cputime stats
cputime: Allow dynamic switch between tick/virtual based cputime accounting
cputime: Generic on-demand virtual cputime accounting
cputime: Move default nsecs_to_cputime() to jiffies based cputime file
cputime: Librarize per nsecs resolution cputime definitions
cputime: Avoid multiplication overflow on utime scaling
context_tracking: Export context state for generic vtime
...
Fix up conflict in kernel/context_tracking.c due to comment additions.
Move the sysctl-related bits from include/linux/sched.h into
a new file: include/linux/sched/sysctl.h. Then update source
files requiring access to those bits by including the new
header file.
Signed-off-by: Clark Williams <williams@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20130207094659.06dced96@riff.lan
Signed-off-by: Ingo Molnar <mingo@kernel.org>
We use rwsem since commit 5a505085f0 ("mm/rmap: Convert the struct
anon_vma::mutex to an rwsem"). And most of comments are converted to
the new rwsem lock; while just 2 more missed from:
$ git grep 'anon_vma->mutex'
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 5a505085f0 ("mm/rmap: Convert the struct anon_vma::mutex to an
rwsem") turned anon_vma mutex to rwsem.
However, the properly annotated nested locking in mm_take_all_locks()
has been converted from
mutex_lock_nest_lock(&anon_vma->root->mutex, &mm->mmap_sem);
to
down_write(&anon_vma->root->rwsem);
which is incomplete, and causes the false positive report from lockdep
below.
Annotate the fact that mmap_sem is used as an outter lock to serialize
taking of all the anon_vma rwsems at once no matter the order, using the
down_write_nest_lock() primitive.
This patch fixes this lockdep report:
=============================================
[ INFO: possible recursive locking detected ]
3.8.0-rc2-00036-g5f73896 #171 Not tainted
---------------------------------------------
qemu-kvm/2315 is trying to acquire lock:
(&anon_vma->rwsem){+.+...}, at: mm_take_all_locks+0x149/0x1b0
but task is already holding lock:
(&anon_vma->rwsem){+.+...}, at: mm_take_all_locks+0x149/0x1b0
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&anon_vma->rwsem);
lock(&anon_vma->rwsem);
*** DEADLOCK ***
May be due to missing lock nesting notation
4 locks held by qemu-kvm/2315:
#0: (&mm->mmap_sem){++++++}, at: do_mmu_notifier_register+0xfc/0x170
#1: (mm_all_locks_mutex){+.+...}, at: mm_take_all_locks+0x36/0x1b0
#2: (&mapping->i_mmap_mutex){+.+...}, at: mm_take_all_locks+0xc9/0x1b0
#3: (&anon_vma->rwsem){+.+...}, at: mm_take_all_locks+0x149/0x1b0
stack backtrace:
Pid: 2315, comm: qemu-kvm Not tainted 3.8.0-rc2-00036-g5f73896 #171
Call Trace:
print_deadlock_bug+0xf2/0x100
validate_chain+0x4f6/0x720
__lock_acquire+0x359/0x580
lock_acquire+0x121/0x190
down_write+0x3f/0x70
mm_take_all_locks+0x149/0x1b0
do_mmu_notifier_register+0x68/0x170
mmu_notifier_register+0xe/0x10
kvm_create_vm+0x22b/0x330 [kvm]
kvm_dev_ioctl+0xf8/0x1a0 [kvm]
do_vfs_ioctl+0x9d/0x350
sys_ioctl+0x91/0xb0
system_call_fastpath+0x16/0x1b
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mel Gorman <mel@csn.ul.ie>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.18 (GNU/Linux)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=ivQa
-----END PGP SIGNATURE-----
Merge tag 'balancenuma-v11' of git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux-balancenuma
Pull Automatic NUMA Balancing bare-bones from Mel Gorman:
"There are three implementations for NUMA balancing, this tree
(balancenuma), numacore which has been developed in tip/master and
autonuma which is in aa.git.
In almost all respects balancenuma is the dumbest of the three because
its main impact is on the VM side with no attempt to be smart about
scheduling. In the interest of getting the ball rolling, it would be
desirable to see this much merged for 3.8 with the view to building
scheduler smarts on top and adapting the VM where required for 3.9.
The most recent set of comparisons available from different people are
mel: https://lkml.org/lkml/2012/12/9/108
mingo: https://lkml.org/lkml/2012/12/7/331
tglx: https://lkml.org/lkml/2012/12/10/437
srikar: https://lkml.org/lkml/2012/12/10/397
The results are a mixed bag. In my own tests, balancenuma does
reasonably well. It's dumb as rocks and does not regress against
mainline. On the other hand, Ingo's tests shows that balancenuma is
incapable of converging for this workloads driven by perf which is bad
but is potentially explained by the lack of scheduler smarts. Thomas'
results show balancenuma improves on mainline but falls far short of
numacore or autonuma. Srikar's results indicate we all suffer on a
large machine with imbalanced node sizes.
My own testing showed that recent numacore results have improved
dramatically, particularly in the last week but not universally.
We've butted heads heavily on system CPU usage and high levels of
migration even when it shows that overall performance is better.
There are also cases where it regresses. Of interest is that for
specjbb in some configurations it will regress for lower numbers of
warehouses and show gains for higher numbers which is not reported by
the tool by default and sometimes missed in treports. Recently I
reported for numacore that the JVM was crashing with
NullPointerExceptions but currently it's unclear what the source of
this problem is. Initially I thought it was in how numacore batch
handles PTEs but I'm no longer think this is the case. It's possible
numacore is just able to trigger it due to higher rates of migration.
These reports were quite late in the cycle so I/we would like to start
with this tree as it contains much of the code we can agree on and has
not changed significantly over the last 2-3 weeks."
* tag 'balancenuma-v11' of git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux-balancenuma: (50 commits)
mm/rmap, migration: Make rmap_walk_anon() and try_to_unmap_anon() more scalable
mm/rmap: Convert the struct anon_vma::mutex to an rwsem
mm: migrate: Account a transhuge page properly when rate limiting
mm: numa: Account for failed allocations and isolations as migration failures
mm: numa: Add THP migration for the NUMA working set scanning fault case build fix
mm: numa: Add THP migration for the NUMA working set scanning fault case.
mm: sched: numa: Delay PTE scanning until a task is scheduled on a new node
mm: sched: numa: Control enabling and disabling of NUMA balancing if !SCHED_DEBUG
mm: sched: numa: Control enabling and disabling of NUMA balancing
mm: sched: Adapt the scanning rate if a NUMA hinting fault does not migrate
mm: numa: Use a two-stage filter to restrict pages being migrated for unlikely task<->node relationships
mm: numa: migrate: Set last_nid on newly allocated page
mm: numa: split_huge_page: Transfer last_nid on tail page
mm: numa: Introduce last_nid to the page frame
sched: numa: Slowly increase the scanning period as NUMA faults are handled
mm: numa: Rate limit setting of pte_numa if node is saturated
mm: numa: Rate limit the amount of memory that is migrated between nodes
mm: numa: Structures for Migrate On Fault per NUMA migration rate limiting
mm: numa: Migrate pages handled during a pmd_numa hinting fault
mm: numa: Migrate on reference policy
...
expand_stack() runs with a shared mmap_sem lock. Because of this, there
could be multiple concurrent stack expansions in the same mm, which may
cause problems in the vma gap update code.
I propose to solve this by taking the mm->page_table_lock around such vma
expansions, in order to avoid the concurrency issue. We only have to
worry about concurrent expand_stack() calls here, since we hold a shared
mmap_sem lock and all vma modificaitons other than expand_stack() are done
under an exclusive mmap_sem lock.
I previously tried to achieve the same effect by making sure all growable
vmas in a given mm would share the same anon_vma, which we already lock
here. However this turned out to be difficult - all of the schemes I
tried for refcounting the growable anon_vma and clearing turned out ugly.
So, I'm now proposing only the minimal fix.
The overhead of taking the page table lock during stack expansion is
expected to be small: glibc doesn't use expandable stacks for the threads
it creates, so having multiple growable stacks is actually uncommon and we
don't expect the page table lock to get bounced between threads.
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
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>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Merge misc updates from Andrew Morton:
"About half of most of MM. Going very early this time due to
uncertainty over the coreautounifiednumasched things. I'll send the
other half of most of MM tomorrow. The rest of MM awaits a slab merge
from Pekka."
* emailed patches from Andrew Morton: (71 commits)
memory_hotplug: ensure every online node has NORMAL memory
memory_hotplug: handle empty zone when online_movable/online_kernel
mm, memory-hotplug: dynamic configure movable memory and portion memory
drivers/base/node.c: cleanup node_state_attr[]
bootmem: fix wrong call parameter for free_bootmem()
avr32, kconfig: remove HAVE_ARCH_BOOTMEM
mm: cma: remove watermark hacks
mm: cma: skip watermarks check for already isolated blocks in split_free_page()
mm, oom: fix race when specifying a thread as the oom origin
mm, oom: change type of oom_score_adj to short
mm: cleanup register_node()
mm, mempolicy: remove duplicate code
mm/vmscan.c: try_to_freeze() returns boolean
mm: introduce putback_movable_pages()
virtio_balloon: introduce migration primitives to balloon pages
mm: introduce compaction and migration for ballooned pages
mm: introduce a common interface for balloon pages mobility
mm: redefine address_space.assoc_mapping
mm: adjust address_space_operations.migratepage() return code
arch/sparc/kernel/sys_sparc_64.c: s/COLOUR/COLOR/
...
Implement vm_unmapped_area() using the rb_subtree_gap and highest_vm_end
information to look up for suitable virtual address space gaps.
struct vm_unmapped_area_info is used to define the desired allocation
request:
- lowest or highest possible address matching the remaining constraints
- desired gap length
- low/high address limits that the gap must fit into
- alignment mask and offset
Also update the generic arch_get_unmapped_area[_topdown] functions to make
use of vm_unmapped_area() instead of implementing a brute force search.
[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Michel Lespinasse <walken@google.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When CONFIG_DEBUG_VM_RB is enabled, check that rb_subtree_gap is correctly
set for every vma and that mm->highest_vm_end is also correct.
Also add an explicit 'bug' variable to track if browse_rb() detected any
invalid condition.
[akpm@linux-foundation.org: repair innovative coding-style inventions]
Signed-off-by: Michel Lespinasse <walken@google.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Define vma->rb_subtree_gap as the largest gap between any vma in the
subtree rooted at that vma, and their predecessor. Or, for a recursive
definition, vma->rb_subtree_gap is the max of:
- vma->vm_start - vma->vm_prev->vm_end
- rb_subtree_gap fields of the vmas pointed by vma->rb.rb_left and
vma->rb.rb_right
This will allow get_unmapped_area_* to find a free area of the right
size in O(log(N)) time, instead of potentially having to do a linear
walk across all the VMAs.
Also define mm->highest_vm_end as the vm_end field of the highest vma,
so that we can easily check if the following gap is suitable.
This does have the potential to make unmapping VMAs more expensive,
especially for processes with very large numbers of VMAs, where the VMA
rbtree can grow quite deep.
Signed-off-by: Michel Lespinasse <walken@google.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There was some desire in large applications using MAP_HUGETLB or
SHM_HUGETLB to use 1GB huge pages on some mappings, and stay with 2MB on
others. This is useful together with NUMA policy: use 2MB interleaving
on some mappings, but 1GB on local mappings.
This patch extends the IPC/SHM syscall interfaces slightly to allow
specifying the page size.
It borrows some upper bits in the existing flag arguments and allows
encoding the log of the desired page size in addition to the *_HUGETLB
flag. When 0 is specified the default size is used, this makes the
change fully compatible.
Extending the internal hugetlb code to handle this is straight forward.
Instead of a single mount it just keeps an array of them and selects the
right mount based on the specified page size. When no page size is
specified it uses the mount of the default page size.
The change is not visible in /proc/mounts because internal mounts don't
appear there. It also has very little overhead: the additional mounts
just consume a super block, but not more memory when not used.
I also exported the new flags to the user headers (they were previously
under __KERNEL__). Right now only symbols for x86 and some other
architecture for 1GB and 2MB are defined. The interface should already
work for all other architectures though. Only architectures that define
multiple hugetlb sizes actually need it (that is currently x86, tile,
powerpc). However tile and powerpc have user configurable hugetlb
sizes, so it's not easy to add defines. A program on those
architectures would need to query sysfs and use the appropiate log2.
[akpm@linux-foundation.org: cleanups]
[rientjes@google.com: fix build]
[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hillf Danton <dhillf@gmail.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
rmap_walk_anon() and try_to_unmap_anon() appears to be too
careful about locking the anon vma: while it needs protection
against anon vma list modifications, it does not need exclusive
access to the list itself.
Transforming this exclusive lock to a read-locked rwsem removes
a global lock from the hot path of page-migration intense
threaded workloads which can cause pathological performance like
this:
96.43% process 0 [kernel.kallsyms] [k] perf_trace_sched_switch
|
--- perf_trace_sched_switch
__schedule
schedule
schedule_preempt_disabled
__mutex_lock_common.isra.6
__mutex_lock_slowpath
mutex_lock
|
|--50.61%-- rmap_walk
| move_to_new_page
| migrate_pages
| migrate_misplaced_page
| __do_numa_page.isra.69
| handle_pte_fault
| handle_mm_fault
| __do_page_fault
| do_page_fault
| page_fault
| __memset_sse2
| |
| --100.00%-- worker_thread
| |
| --100.00%-- start_thread
|
--49.39%-- page_lock_anon_vma
try_to_unmap_anon
try_to_unmap
migrate_pages
migrate_misplaced_page
__do_numa_page.isra.69
handle_pte_fault
handle_mm_fault
__do_page_fault
do_page_fault
page_fault
__memset_sse2
|
--100.00%-- worker_thread
start_thread
With this change applied the profile is now nicely flat
and there's no anon-vma related scheduling/blocking.
Rename anon_vma_[un]lock() => anon_vma_[un]lock_write(),
to make it clearer that it's an exclusive write-lock in
that case - suggested by Rik van Riel.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Turner <pjt@google.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Convert the struct anon_vma::mutex to an rwsem, which will help
in solving a page-migration scalability problem. (Addressed in
a separate patch.)
The conversion is simple and straightforward: in every case
where we mutex_lock()ed we'll now down_write().
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Turner <pjt@google.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Iterating over the vma->anon_vma_chain without anon_vma_lock may cause
NULL ptr deref in anon_vma_interval_tree_verify(), because the node in the
chain might have been removed.
BUG: unable to handle kernel paging request at fffffffffffffff0
IP: [<ffffffff8122c29c>] anon_vma_interval_tree_verify+0xc/0xa0
PGD 4e28067 PUD 4e29067 PMD 0
Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
CPU 0
Pid: 9050, comm: trinity-child64 Tainted: G W 3.7.0-rc2-next-20121025-sasha-00001-g673f98e-dirty #77
RIP: 0010: anon_vma_interval_tree_verify+0xc/0xa0
Process trinity-child64 (pid: 9050, threadinfo ffff880045f80000, task ffff880048eb0000)
Call Trace:
validate_mm+0x58/0x1e0
vma_adjust+0x635/0x6b0
__split_vma.isra.22+0x161/0x220
split_vma+0x24/0x30
sys_madvise+0x5da/0x7b0
tracesys+0xe1/0xe6
RIP anon_vma_interval_tree_verify+0xc/0xa0
CR2: fffffffffffffff0
Figured out by Bob Liu.
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Bob Liu <lliubbo@gmail.com>
Signed-off-by: Michel Lespinasse <walken@google.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It will be useful to be able to access global memory commitment from
device drivers. On the Hyper-V platform, the host has a policy engine to
balance the available physical memory amongst all competing virtual
machines hosted on a given node. This policy engine is driven by a number
of metrics including the memory commitment reported by the guests. The
balloon driver for Linux on Hyper-V will use this function to retrieve
guest memory commitment. This function is also used in Xen self
ballooning code.
[akpm@linux-foundation.org: coding-style tweak]
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
During mremap(), the destination VMA is generally placed after the
original vma in rmap traversal order: in move_vma(), we always have
new_pgoff >= vma->vm_pgoff, and as a result new_vma->vm_pgoff >=
vma->vm_pgoff unless vma_merge() merged the new vma with an adjacent one.
When the destination VMA is placed after the original in rmap traversal
order, we can avoid taking the rmap locks in move_ptes().
Essentially, this reintroduces the optimization that had been disabled in
"mm anon rmap: remove anon_vma_moveto_tail". The difference is that we
don't try to impose the rmap traversal order; instead we just rely on
things being in the desired order in the common case and fall back to
taking locks in the uncommon case. Also we skip the i_mmap_mutex in
addition to the anon_vma lock: in both cases, the vmas are traversed in
increasing vm_pgoff order with ties resolved in tree insertion order.
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Daniel Santos <daniel.santos@pobox.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
anon_vma_clone() expects new_vma->vm_{start,end,pgoff} to be correctly set
so that the new vma can be indexed on the anon interval tree.
copy_vma() was failing to do that, which broke mremap().
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Hugh Dickins <hughd@google.com>
Tested-by: Sasha Levin <levinsasha928@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add a CONFIG_DEBUG_VM_RB build option for the previously existing
DEBUG_MM_RB code. Now that Andi Kleen modified it to avoid using
recursive algorithms, we can expose it a bit more.
Also extend this code to validate_mm() after stack expansion, and to check
that the vma's start and last pgoffs have not changed since the nodes were
inserted on the anon vma interval tree (as it is important that the nodes
be reindexed after each such update).
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Daniel Santos <daniel.santos@pobox.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When a large VMA (anon or private file mapping) is first touched, which
will populate its anon_vma field, and then split into many regions through
the use of mprotect(), the original anon_vma ends up linking all of the
vmas on a linked list. This can cause rmap to become inefficient, as we
have to walk potentially thousands of irrelevent vmas before finding the
one a given anon page might fall into.
By replacing the same_anon_vma linked list with an interval tree (where
each avc's interval is determined by its vma's start and last pgoffs), we
can make rmap efficient for this use case again.
While the change is large, all of its pieces are fairly simple.
Most places that were walking the same_anon_vma list were looking for a
known pgoff, so they can just use the anon_vma_interval_tree_foreach()
interval tree iterator instead. The exception here is ksm, where the
page's index is not known. It would probably be possible to rework ksm so
that the index would be known, but for now I have decided to keep things
simple and just walk the entirety of the interval tree there.
When updating vma's that already have an anon_vma assigned, we must take
care to re-index the corresponding avc's on their interval tree. This is
done through the use of anon_vma_interval_tree_pre_update_vma() and
anon_vma_interval_tree_post_update_vma(), which remove the avc's from
their interval tree before the update and re-insert them after the update.
The anon_vma stays locked during the update, so there is no chance that
rmap would miss the vmas that are being updated.
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Daniel Santos <daniel.santos@pobox.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mremap() had a clever optimization where move_ptes() did not take the
anon_vma lock to avoid a race with anon rmap users such as page migration.
Instead, the avc's were ordered in such a way that the origin vma was
always visited by rmap before the destination. This ordering and the use
of page table locks rmap usage safe. However, we want to replace the use
of linked lists in anon rmap with an interval tree, and this will make it
harder to impose such ordering as the interval tree will always be sorted
by the avc->vma->vm_pgoff value. For now, let's replace the
anon_vma_moveto_tail() ordering function with proper anon_vma locking in
move_ptes(). Once we have the anon interval tree in place, we will
re-introduce an optimization to avoid taking these locks in the most
common cases.
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Daniel Santos <daniel.santos@pobox.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Implement an interval tree as a replacement for the VMA prio_tree. The
algorithms are similar to lib/interval_tree.c; however that code can't be
directly reused as the interval endpoints are not explicitly stored in the
VMA. So instead, the common algorithm is moved into a template and the
details (node type, how to get interval endpoints from the node, etc) are
filled in using the C preprocessor.
Once the interval tree functions are available, using them as a
replacement to the VMA prio tree is a relatively simple, mechanical job.
Signed-off-by: Michel Lespinasse <walken@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
