linux.git/fs/proc/task_mmu.c, branch v4.6

numa: fix /proc//numa_maps for THP

2016-04-29T02:34:04+00:00

In gather_pte_stats() a THP pmd is cast into a pte, which is wrong
because the layouts may differ depending on the architecture.  On s390
this will lead to inaccurate numa_maps accounting in /proc because of
misguided pte_present() and pte_dirty() checks on the fake pte.

On other architectures pte_present() and pte_dirty() may work by chance,
but there may be an issue with direct-access (dax) mappings w/o
underlying struct pages when HAVE_PTE_SPECIAL is set and THP is
available.  In vm_normal_page() the fake pte will be checked with
pte_special() and because there is no "special" bit in a pmd, this will
always return false and the VM_PFNMAP | VM_MIXEDMAP checking will be
skipped.  On dax mappings w/o struct pages, an invalid struct page
pointer would then be returned that can crash the kernel.

This patch fixes the numa_maps THP handling by introducing new "_pmd"
variants of the can_gather_numa_stats() and vm_normal_page() functions.

Signed-off-by: Gerald Schaefer 
Cc: Naoya Horiguchi 
Cc: "Kirill A . Shutemov" 
Cc: Konstantin Khlebnikov 
Cc: Michal Hocko 
Cc: Vlastimil Babka 
Cc: Jerome Marchand 
Cc: Johannes Weiner 
Cc: Dave Hansen 
Cc: Mel Gorman 
Cc: Dan Williams 
Cc: Martin Schwidefsky 
Cc: Heiko Carstens 
Cc: Michael Holzheu 
Cc: 	[4.3+]
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros

2016-04-04T17:41:08+00:00

PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.

This promise never materialized.  And unlikely will.

We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE.  And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.

Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.

Let's stop pretending that pages in page cache are special.  They are
not.

The changes are pretty straight-forward:

 -  << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> ;

 -  >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> ;

 - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};

 - page_cache_get() -> get_page();

 - page_cache_release() -> put_page();

This patch contains automated changes generated with coccinelle using
script below.  For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.

The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.

There are few places in the code where coccinelle didn't reach.  I'll
fix them manually in a separate patch.  Comments and documentation also
will be addressed with the separate patch.

virtual patch

@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E

@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E

@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT

@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE

@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK

@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)

@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)

@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)

Signed-off-by: Kirill A. Shutemov 
Acked-by: Michal Hocko 
Signed-off-by: Linus Torvalds

x86/mm/pkeys: Dump pkey from VMA in /proc/pid/smaps

2016-02-18T18:46:29+00:00

The protection key can now be just as important as read/write
permissions on a VMA.  We need some debug mechanism to help
figure out if it is in play.  smaps seems like a logical
place to expose it.

arch/x86/kernel/setup.c is a bit of a weirdo place to put
this code, but it already had seq_file.h and there was not
a much better existing place to put it.

We also use no #ifdef.  If protection keys is .config'd out we
will effectively get the same function as if we used the weak
generic function.

Signed-off-by: Dave Hansen 
Reviewed-by: Thomas Gleixner 
Cc: Al Viro 
Cc: Andrew Morton 
Cc: Andy Lutomirski 
Cc: Baoquan He 
Cc: Borislav Petkov 
Cc: Borislav Petkov 
Cc: Brian Gerst 
Cc: Dave Hansen 
Cc: Dave Young 
Cc: Denys Vlasenko 
Cc: H. Peter Anvin 
Cc: Jerome Marchand 
Cc: Jiri Kosina 
Cc: Joerg Roedel 
Cc: Johannes Weiner 
Cc: Kirill A. Shutemov 
Cc: Konstantin Khlebnikov 
Cc: Laurent Dufour 
Cc: Linus Torvalds 
Cc: Mark Salter 
Cc: Mark Williamson 
Cc: Michal Hocko 
Cc: Naoya Horiguchi 
Cc: Paolo Bonzini 
Cc: Peter Zijlstra 
Cc: Rik van Riel 
Cc: Vlastimil Babka 
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/20160212210227.4F8EB3F8@viggo.jf.intel.com
Signed-off-by: Ingo Molnar

proc: revert /proc//maps [stack:TID] annotation

2016-02-03T16:28:43+00:00

Commit b76437579d13 ("procfs: mark thread stack correctly in
proc//maps") added [stack:TID] annotation to /proc//maps.

Finding the task of a stack VMA requires walking the entire thread list,
turning this into quadratic behavior: a thousand threads means a
thousand stacks, so the rendering of /proc//maps needs to look at a
million combinations.

The cost is not in proportion to the usefulness as described in the
patch.

Drop the [stack:TID] annotation to make /proc//maps (and
/proc//numa_maps) usable again for higher thread counts.

The [stack] annotation inside /proc//task//maps is retained, as
identifying the stack VMA there is an O(1) operation.

Siddesh said:
 "The end users needed a way to identify thread stacks programmatically and
  there wasn't a way to do that.  I'm afraid I no longer remember (or have
  access to the resources that would aid my memory since I changed
  employers) the details of their requirement.  However, I did do this on my
  own time because I thought it was an interesting project for me and nobody
  really gave any feedback then as to its utility, so as far as I am
  concerned you could roll back the main thread maps information since the
  information is available in the thread-specific files"

Signed-off-by: Johannes Weiner 
Cc: "Kirill A. Shutemov" 
Cc: Siddhesh Poyarekar 
Cc: Shaohua Li 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

numa: fix /proc//numa_maps for hugetlbfs on s390

2016-02-03T16:28:43+00:00

When working with hugetlbfs ptes (which are actually pmds) is not valid to
directly use pte functions like pte_present() because the hardware bit
layout of pmds and ptes can be different.  This is the case on s390.
Therefore we have to convert the hugetlbfs ptes first into a valid pte
encoding with huge_ptep_get().

Currently the /proc//numa_maps code uses hugetlbfs ptes without
huge_ptep_get().  On s390 this leads to the following two problems:

1) The pte_present() function returns false (instead of true) for
   PROT_NONE hugetlb ptes. Therefore PROT_NONE vmas are missing
   completely in the "numa_maps" output.

2) The pte_dirty() function always returns false for all hugetlb ptes.
   Therefore these pages are reported as "mapped=xxx" instead of
   "dirty=xxx".

Therefore use huge_ptep_get() to correctly convert the hugetlb ptes.

Signed-off-by: Michael Holzheu 
Reviewed-by: Gerald Schaefer 
Cc: 	[4.3+]
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

thp: change pmd_trans_huge_lock() interface to return ptl

2016-01-22T01:20:51+00:00

After THP refcounting rework we have only two possible return values
from pmd_trans_huge_lock(): success and failure.  Return-by-pointer for
ptl doesn't make much sense in this case.

Let's convert pmd_trans_huge_lock() to return ptl on success and NULL on
failure.

Signed-off-by: Kirill A. Shutemov 
Suggested-by: Linus Torvalds 
Cc: Minchan Kim 
Acked-by: Michal Hocko 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

fs/proc/task_mmu.c: add workaround for old compilers

2016-01-21T01:09:18+00:00

For THP=n, HPAGE_PMD_NR in smaps_account() expands to BUILD_BUG().
That's fine since this codepath is eliminated by modern compilers.

But older compilers have not that efficient dead code elimination.  It
causes problem at least with gcc 4.1.2 on m68k:

   fs/built-in.o: In function `smaps_account':
   task_mmu.c:(.text+0x4f8fa): undefined reference to `__compiletime_assert_471'

Let's replace HPAGE_PMD_NR with 1 << compound_order(page).

Signed-off-by: Kirill A. Shutemov 
Reported-by: Geert Uytterhoeven 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm, thp: remove infrastructure for handling splitting PMDs

2016-01-16T01:56:32+00:00

With new refcounting we don't need to mark PMDs splitting.  Let's drop
code to handle this.

Signed-off-by: Kirill A. Shutemov 
Tested-by: Sasha Levin 
Tested-by: Aneesh Kumar K.V 
Acked-by: Vlastimil Babka 
Acked-by: Jerome Marchand 
Cc: Andrea Arcangeli 
Cc: Hugh Dickins 
Cc: Dave Hansen 
Cc: Mel Gorman 
Cc: Rik van Riel 
Cc: Naoya Horiguchi 
Cc: Steve Capper 
Cc: Johannes Weiner 
Cc: Michal Hocko 
Cc: Christoph Lameter 
Cc: David Rientjes 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm, proc: adjust PSS calculation

2016-01-16T01:56:32+00:00

The goal of this patchset is to make refcounting on THP pages cheaper
with simpler semantics and allow the same THP compound page to be mapped
with PMD and PTEs.  This is required to get reasonable THP-pagecache
implementation.

With the new refcounting design it's much easier to protect against
split_huge_page(): simple reference on a page will make you the deal.
It makes gup_fast() implementation simpler and doesn't require
special-case in futex code to handle tail THP pages.

It should improve THP utilization over the system since splitting THP in
one process doesn't necessary lead to splitting the page in all other
processes have the page mapped.

The patchset drastically lower complexity of get_page()/put_page()
codepaths.  I encourage people look on this code before-and-after to
justify time budget on reviewing this patchset.

This patch (of 37):

With new refcounting all subpages of the compound page are not necessary
have the same mapcount.  We need to take into account mapcount of every
sub-page.

Signed-off-by: Kirill A. Shutemov 
Tested-by: Sasha Levin 
Tested-by: Aneesh Kumar K.V 
Acked-by: Jerome Marchand 
Acked-by: Vlastimil Babka 
Cc: Andrea Arcangeli 
Cc: Hugh Dickins 
Cc: Dave Hansen 
Cc: Mel Gorman 
Cc: Rik van Riel 
Cc: Naoya Horiguchi 
Cc: Steve Capper 
Cc: Johannes Weiner 
Cc: Michal Hocko 
Cc: Christoph Lameter 
Cc: David Rientjes 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: rework virtual memory accounting

2016-01-15T00:00:49+00:00

When inspecting a vague code inside prctl(PR_SET_MM_MEM) call (which
testing the RLIMIT_DATA value to figure out if we're allowed to assign
new @start_brk, @brk, @start_data, @end_data from mm_struct) it's been
commited that RLIMIT_DATA in a form it's implemented now doesn't do
anything useful because most of user-space libraries use mmap() syscall
for dynamic memory allocations.

Linus suggested to convert RLIMIT_DATA rlimit into something suitable
for anonymous memory accounting.  But in this patch we go further, and
the changes are bundled together as:

 * keep vma counting if CONFIG_PROC_FS=n, will be used for limits
 * replace mm->shared_vm with better defined mm->data_vm
 * account anonymous executable areas as executable
 * account file-backed growsdown/up areas as stack
 * drop struct file* argument from vm_stat_account
 * enforce RLIMIT_DATA for size of data areas

This way code looks cleaner: now code/stack/data classification depends
only on vm_flags state:

 VM_EXEC & ~VM_WRITE            -> code  (VmExe + VmLib in proc)
 VM_GROWSUP | VM_GROWSDOWN      -> stack (VmStk)
 VM_WRITE & ~VM_SHARED & !stack -> data  (VmData)

The rest (VmSize - VmData - VmStk - VmExe - VmLib) could be called
"shared", but that might be strange beast like readonly-private or VM_IO
area.

 - RLIMIT_AS            limits whole address space "VmSize"
 - RLIMIT_STACK         limits stack "VmStk" (but each vma individually)
 - RLIMIT_DATA          now limits "VmData"

Signed-off-by: Konstantin Khlebnikov 
Signed-off-by: Cyrill Gorcunov 
Cc: Quentin Casasnovas 
Cc: Vegard Nossum 
Acked-by: Linus Torvalds 
Cc: Willy Tarreau 
Cc: Andy Lutomirski 
Cc: Kees Cook 
Cc: Vladimir Davydov 
Cc: Pavel Emelyanov 
Cc: Peter Zijlstra 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds