linux-2.6-microblaze.git
10 years agolib: bitmap: add missing mask in bitmap_and
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:22 +0000 (16:10 -0700)]
lib: bitmap: add missing mask in bitmap_and

Apparently, bitmap_and is supposed to return whether the new bitmap is
empty.  But it didn't take potential garbage bits in the last word into
account.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: add missing mask in bitmap_shift_right
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:20 +0000 (16:10 -0700)]
lib: bitmap: add missing mask in bitmap_shift_right

There is no guarantee that *src does not contain garbage bits outside
the lower nbits, so we need to mask it before the shift-and-assign.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: micro-optimize bitmap_allocate_region
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:18 +0000 (16:10 -0700)]
lib: bitmap: micro-optimize bitmap_allocate_region

__reg_op(..., REG_OP_ALLOC) always returns 0, so we might as well use that
and save an instruction.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: change parameter of bitmap_*_region to unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:16 +0000 (16:10 -0700)]
lib: bitmap: change parameter of bitmap_*_region to unsigned

Changing the pos parameter of __reg_op to unsigned allows the compiler
to generate slightly smaller and simpler code.  Also update its callers
bitmap_*_region to receive and pass unsigned int.  The return types of
bitmap_find_free_region and bitmap_allocate_region are still int to
allow a negative error code to be returned.  An int is certainly capable
of representing any realistic return value.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: fix typo in kerneldoc for bitmap_pos_to_ord
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:14 +0000 (16:10 -0700)]
lib: bitmap: fix typo in kerneldoc for bitmap_pos_to_ord

A few lines above, it was stated that positions for non-set bits are
mapped to -1, which is obviously also what the code does.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: simplify bitmap_parselist
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:12 +0000 (16:10 -0700)]
lib: bitmap: simplify bitmap_parselist

We want len to be the index of the first '\n', or the length of the
string if there is no newline.  This is a good example of the usefulness
of strchrnul().  Use that instead, thus eliminating a branch and a call
to strlen().

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make the start index of bitmap_clear unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:10 +0000 (16:10 -0700)]
lib: bitmap: make the start index of bitmap_clear unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "start" is non-negative.

Also, use the names "start" and "len" for the two parameters for
consistency with bitmap_set.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make the start index of bitmap_set unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:07 +0000 (16:10 -0700)]
lib: bitmap: make the start index of bitmap_set unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "start" is non-negative.

Also, use the names "start" and "len" for the two parameters in both
header file and implementation, instead of the previous mix.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_weight unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:05 +0000 (16:10 -0700)]
lib: bitmap: make nbits parameter of bitmap_weight unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

I didn't change the return type, since that might change the semantics
of some expression containing a call to bitmap_weight(). Certainly an
int is capable of holding the result.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_subset unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:03 +0000 (16:10 -0700)]
lib: bitmap: make nbits parameter of bitmap_subset unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_intersects unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:10:01 +0000 (16:10 -0700)]
lib: bitmap: make nbits parameter of bitmap_intersects unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_{and,or,xor,andnot} unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:59 +0000 (16:09 -0700)]
lib: bitmap: make nbits parameter of bitmap_{and,or,xor,andnot} unsigned

This change is only for consistency with the changes to the other
bitmap_* functions; it doesn't change the size of the generated code:
inside BITS_TO_LONGS there is a sizeof(long), which causes bits to be
interpreted as unsigned anyway.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: remove unnecessary mask from bitmap_complement
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:57 +0000 (16:09 -0700)]
lib: bitmap: remove unnecessary mask from bitmap_complement

Since the extra bits are "don't care", there is no reason to mask the
last word to the used bits when complementing.  This shaves off yet a
few bytes.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_complement unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:55 +0000 (16:09 -0700)]
lib: bitmap: make nbits parameter of bitmap_complement unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_equal unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:53 +0000 (16:09 -0700)]
lib: bitmap: make nbits parameter of bitmap_equal unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_full unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:51 +0000 (16:09 -0700)]
lib: bitmap: make nbits parameter of bitmap_full unsigned

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: bitmap: make nbits parameter of bitmap_empty unsigned
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:49 +0000 (16:09 -0700)]
lib: bitmap: make nbits parameter of bitmap_empty unsigned

Many functions in lib/bitmap.c start with an expression such as lim =
bits/BITS_PER_LONG.  Since bits has type (signed) int, and since gcc
cannot know that it is in fact non-negative, it generates worse code
than it could.  These patches, mostly consisting of changing various
parameters to unsigned, gives a slight overall code reduction:

  add/remove: 1/1 grow/shrink: 8/16 up/down: 251/-414 (-163)
  function                                     old     new   delta
  tick_device_uses_broadcast                   335     425     +90
  __irq_alloc_descs                            498     554     +56
  __bitmap_andnot                               73     115     +42
  __bitmap_and                                  70     101     +31
  bitmap_weight                                  -      11     +11
  copy_hugetlb_page_range                      752     762     +10
  follow_hugetlb_page                          846     854      +8
  hugetlb_init                                1415    1417      +2
  hugetlb_nrpages_setup                        130     131      +1
  hugetlb_add_hstate                           377     376      -1
  bitmap_allocate_region                        82      80      -2
  select_task_rq_fair                         2202    2191     -11
  hweight_long                                  66      55     -11
  __reg_op                                     230     219     -11
  dm_stats_message                            2849    2833     -16
  bitmap_parselist                              92      74     -18
  __bitmap_weight                              115      97     -18
  __bitmap_subset                              153     129     -24
  __bitmap_full                                128     104     -24
  __bitmap_empty                               120      96     -24
  bitmap_set                                   179     149     -30
  bitmap_clear                                 185     155     -30
  __bitmap_equal                               136     105     -31
  __bitmap_intersects                          148     108     -40
  __bitmap_complement                          109      67     -42
  tick_device_setup_broadcast_func.isra         81       -     -81

[The increases in __bitmap_and{,not} are due to bug fixes 17/18,18/18.
No idea why bitmap_weight suddenly appears.] While 163 bytes treewide is
insignificant, I believe the bitmap functions are often called with
locks held, so saving even a few cycles might be worth it.

While making these changes, I found a few other things that might be
worth including.  16,17,18 are actual bug fixes.  The rest shouldn't
change the behaviour of any of the functions, provided no-one passed
negative nbits values.  If something should come up, it should be fairly
bisectable.

A few issues I thought about, but didn't know what to do with:

* Many of the functions misbehave if nbits is compile-time 0; the
  out-of-line functions generally handle 0 correctly.  bitmap_fill() is
  particularly bad, whether the 0 is known at compile time or not.  It
  would probably be nice to add detection of at least compile-time 0 and
  handle that appropriately.

* I didn't change __bitmap_shift_{left,right} to use unsigned because I
  want to fully understand why the algorithm works before making that
  change.  However, AFAICT, they behave correctly for all (positive) shift
  amounts.  This is not the case for the small_const_nbits versions.  If
  for example nbits = n = BITS_PER_LONG, the shift operators turn into
  no-ops (at least on x86), so one get *dst = *src, whereas one would
  expect to get *dst=0.  That difference in behaviour is somewhat
  annoying.

This patch (of 18):

The compiler can generate slightly smaller and simpler code when it
knows that "nbits" is non-negative.  Since no-one passes a negative
bit-count, this shouldn't affect the semantics.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib/list_sort.c: convert to pr_foo
Andrew Morton [Wed, 6 Aug 2014 23:09:46 +0000 (16:09 -0700)]
lib/list_sort.c: convert to pr_foo

Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Don Mullis <don.mullis@gmail.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: list_sort.c: Limit number of unused cmp callbacks
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:44 +0000 (16:09 -0700)]
lib: list_sort.c: Limit number of unused cmp callbacks

The helper merge_and_restore_back_links() makes sure to call the
caller's cmp function during the final ->prev pointer fixup, so that the
cmp function may call cond_resched().  However, if the cmp function does
not call cond_resched() at all, this is entirely redundant.  If it does,
doing at least two function calls for every two pointer assignments is a
bit excessive.  This patch limits the calls to once for every 256
iterations.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Don Mullis <don.mullis@gmail.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: list_sort_test(): simplify and harden cleanup
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:42 +0000 (16:09 -0700)]
lib: list_sort_test(): simplify and harden cleanup

There is no reason to maintain the list structure while freeing the
debug elements.  Aside from the redundant pointer manipulations, it is
also inefficient from a locality-of-reference viewpoint, since they are
visited in a random order (wrt.  the order they were allocated).
Furthermore, if we jumped to exit: after detecting list corruption, it
is actually dangerous.

So just free the elements in the order they were allocated, using the
backing array elts.  Allocate that using kcalloc(), so that if
allocation of one of the debug element fails, we just end up calling
kfree(NULL) for the trailing elements.

Minor details: Use sizeof(*elts) instead of sizeof(void *), and return
err immediately when allocation of elts fails, to avoid introducing
another label just before the final return statement.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Don Mullis <don.mullis@gmail.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: list_sort_test(): add extra corruption check
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:40 +0000 (16:09 -0700)]
lib: list_sort_test(): add extra corruption check

Add a check to make sure that the prev pointer of the list head points
to the last element on the list.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Don Mullis <don.mullis@gmail.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: list_sort_test(): return -ENOMEM when allocation fails
Rasmus Villemoes [Wed, 6 Aug 2014 23:09:38 +0000 (16:09 -0700)]
lib: list_sort_test(): return -ENOMEM when allocation fails

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Don Mullis <don.mullis@gmail.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agokernel.h: remove deprecated pack_hex_byte
Joe Perches [Wed, 6 Aug 2014 23:09:36 +0000 (16:09 -0700)]
kernel.h: remove deprecated pack_hex_byte

It's been nearly 3 years now since commit 55036ba76b2d ("lib: rename
pack_hex_byte() to hex_byte_pack()") so it's time to remove this
deprecated and unused static inline.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib/test-kstrtox.c: use ARRAY_SIZE instead of sizeof/sizeof[0]
Fabian Frederick [Wed, 6 Aug 2014 23:09:33 +0000 (16:09 -0700)]
lib/test-kstrtox.c: use ARRAY_SIZE instead of sizeof/sizeof[0]

Use kernel.h definition.

Signed-off-by: Fabian Frederick <fabf@skynet.be>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib/string_helpers.c: constify static arrays
Mathias Krause [Wed, 6 Aug 2014 23:09:31 +0000 (16:09 -0700)]
lib/string_helpers.c: constify static arrays

Complement commit 68aecfb97978 ("lib/string_helpers.c: make arrays
static") by making the arrays const -- not only pointing to const
strings.  This moves them out of the data section to the r/o data
section:

   text    data     bss     dec     hex filename
   1150     176       0    1326     52e lib/string_helpers.old.o
   1326       0       0    1326     52e lib/string_helpers.new.o

Signed-off-by: Mathias Krause <minipli@googlemail.com>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib/cmdline.c: add size unit t/p/e to memparse
Gui Hecheng [Wed, 6 Aug 2014 23:09:29 +0000 (16:09 -0700)]
lib/cmdline.c: add size unit t/p/e to memparse

For modern filesystems such as btrfs, t/p/e size level operations are
common.  add size unit t/p/e parsing to memparse

Signed-off-by: Gui Hecheng <guihc.fnst@cn.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Reviewed-by: Satoru Takeuchi <takeuchi_satoru@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolibata: Use glob_match from lib/glob.c
George Spelvin [Wed, 6 Aug 2014 23:09:27 +0000 (16:09 -0700)]
libata: Use glob_match from lib/glob.c

The function may be useful for other drivers, so export it.  (Suggested
by Tejun Heo.)

Note that I inverted the return value of glob_match; returning true on
match seemed to make more sense.

Signed-off-by: George Spelvin <linux@horizon.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib/glob.c: add CONFIG_GLOB_SELFTEST
George Spelvin [Wed, 6 Aug 2014 23:09:25 +0000 (16:09 -0700)]
lib/glob.c: add CONFIG_GLOB_SELFTEST

This was useful during development, and is retained for future
regression testing.

GCC appears to have no way to place string literals in a particular
section; adding __initconst to a char pointer leaves the string itself
in the default string section, where it will not be thrown away after
module load.

Thus all string constants are kept in explicitly declared and named
arrays.  Sorry this makes printk a bit harder to read.  At least the
tests are more compact.

Signed-off-by: George Spelvin <linux@horizon.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolib: add lib/glob.c
George Spelvin [Wed, 6 Aug 2014 23:09:23 +0000 (16:09 -0700)]
lib: add lib/glob.c

This is a helper function from drivers/ata/libata_core.c, where it is
used to blacklist particular device models.  It's being moved to lib/ so
other drivers may use it for the same purpose.

This implementation in non-recursive, so is safe for the kernel stack.

[akpm@linux-foundation.org: fix sparse warning]
Signed-off-by: George Spelvin <linux@horizon.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agozlib: clean up some dead code
Sergey Senozhatsky [Wed, 6 Aug 2014 23:09:21 +0000 (16:09 -0700)]
zlib: clean up some dead code

Cleanup unused `if 0'-ed functions, which have been dead since 2006
(commits 87c2ce3b9305 ("lib/zlib*: cleanups") by Adrian Bunk and
4f3865fb57a0 ("zlib_inflate: Upgrade library code to a recent version")
by Richard Purdie):

 - zlib_deflateSetDictionary
 - zlib_deflateParams
 - zlib_deflateCopy
 - zlib_inflateSync
 - zlib_syncsearch
 - zlib_inflateSetDictionary
 - zlib_inflatePrime

Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoklist: use same naming scheme as hlist for klist_add_after()
Ken Helias [Wed, 6 Aug 2014 23:09:18 +0000 (16:09 -0700)]
klist: use same naming scheme as hlist for klist_add_after()

The name was modified from hlist_add_after() to hlist_add_behind() when
adjusting the order of arguments to match the one with
klist_add_after().  This is necessary to break old code when it would
use it the wrong way.

Make klist follow this naming scheme for consistency.

Signed-off-by: Ken Helias <kenhelias@firemail.de>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolist: fix order of arguments for hlist_add_after(_rcu)
Ken Helias [Wed, 6 Aug 2014 23:09:16 +0000 (16:09 -0700)]
list: fix order of arguments for hlist_add_after(_rcu)

All other add functions for lists have the new item as first argument
and the position where it is added as second argument.  This was changed
for no good reason in this function and makes using it unnecessary
confusing.

The name was changed to hlist_add_behind() to cause unconverted code to
generate a compile error instead of using the wrong parameter order.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Ken Helias <kenhelias@firemail.de>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> [intel driver bits]
Cc: Hugh Dickins <hughd@google.com>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agolist: make hlist_add_after() argument names match hlist_add_after_rcu()
Ken Helias [Wed, 6 Aug 2014 23:09:14 +0000 (16:09 -0700)]
list: make hlist_add_after() argument names match hlist_add_after_rcu()

The argument names for hlist_add_after() are poorly chosen because they
look the same as the ones for hlist_add_before() but have to be used
differently.

hlist_add_after_rcu() has made a better choice.

Signed-off-by: Ken Helias <kenhelias@firemail.de>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agokernel/printk/printk.c: fix bool assignements
Neil Zhang [Wed, 6 Aug 2014 23:09:12 +0000 (16:09 -0700)]
kernel/printk/printk.c: fix bool assignements

Fix coccinelle warnings.

Signed-off-by: Neil Zhang <zhangwm@marvell.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: enable interrupts before calling console_trylock_for_printk()
Jan Kara [Wed, 6 Aug 2014 23:09:10 +0000 (16:09 -0700)]
printk: enable interrupts before calling console_trylock_for_printk()

We need interrupts disabled when calling console_trylock_for_printk()
only so that cpu id we pass to can_use_console() remains valid (for
other things console_sem provides all the exclusion we need and
deadlocks on console_sem due to interrupts are impossible because we use
down_trylock()).  However if we are rescheduled, we are guaranteed to
run on an online cpu so we can easily just get the cpu id in
can_use_console().

We can lose a bit of performance when we enable interrupts in
vprintk_emit() and then disable them again in console_unlock() but OTOH
it can somewhat reduce interrupt latency caused by console_unlock().

We differ from (reverted) commit 939f04bec1a4 in that we avoid calling
console_unlock() from vprintk_emit() with lockdep enabled as that has
unveiled quite some bugs leading to system freezes during boot (e.g.
  https://lkml.org/lkml/2014/5/30/242,
  https://lkml.org/lkml/2014/6/28/521).

Signed-off-by: Jan Kara <jack@suse.cz>
Tested-by: Andreas Bombe <aeb@debian.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: miscellaneous cleanups
Alex Elder [Wed, 6 Aug 2014 23:09:08 +0000 (16:09 -0700)]
printk: miscellaneous cleanups

Some small cleanups to kernel/printk/printk.c.  None of them should
cause any change in behavior.

  - When CONFIG_PRINTK is defined, parenthesize the value of LOG_LINE_MAX.
  - When CONFIG_PRINTK is *not* defined, there is an extra LOG_LINE_MAX
    definition; delete it.
  - Pull an assignment out of a conditional expression in console_setup().
  - Use isdigit() in console_setup() rather than open coding it.
  - In update_console_cmdline(), drop a NUL-termination assignment;
    the strlcpy() call that precedes it guarantees it's not needed.
  - Simplify some logic in printk_timed_ratelimit().

Signed-off-by: Alex Elder <elder@linaro.org>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Jan Kara <jack@suse.cz>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: use a clever macro
Alex Elder [Wed, 6 Aug 2014 23:09:05 +0000 (16:09 -0700)]
printk: use a clever macro

Use the IS_ENABLED() macro rather than #ifdef blocks to set certain
global values.

Signed-off-by: Alex Elder <elder@linaro.org>
Acked-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: fix some comments
Alex Elder [Wed, 6 Aug 2014 23:09:03 +0000 (16:09 -0700)]
printk: fix some comments

Fix a few comments that don't accurately describe their corresponding
code.  It also fixes some minor typographical errors.

Signed-off-by: Alex Elder <elder@linaro.org>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Jan Kara <jack@suse.cz>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: rename DEFAULT_MESSAGE_LOGLEVEL
Alex Elder [Wed, 6 Aug 2014 23:09:01 +0000 (16:09 -0700)]
printk: rename DEFAULT_MESSAGE_LOGLEVEL

Commit a8fe19ebfbfd ("kernel/printk: use symbolic defines for console
loglevels") makes consistent use of symbolic values for printk() log
levels.

The naming scheme used is different from the one used for
DEFAULT_MESSAGE_LOGLEVEL though.  Change that symbol name to be
MESSAGE_LOGLEVEL_DEFAULT for consistency.  And because the value of that
symbol comes from a similarly-named config option, rename
CONFIG_DEFAULT_MESSAGE_LOGLEVEL as well.

Signed-off-by: Alex Elder <elder@linaro.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Jan Kara <jack@suse.cz>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: tweak do_syslog() to match comments
Alex Elder [Wed, 6 Aug 2014 23:08:59 +0000 (16:08 -0700)]
printk: tweak do_syslog() to match comments

In do_syslog() there's a path used by kmsg_poll() and kmsg_read() that
only needs to know whether there's any data available to read (and not
its size).  These callers only check for non-zero return.  As a
shortcut, do_syslog() returns the difference between what has been
logged and what has been "seen."

The comments say that the "count of records" should be returned but it's
not.  Instead it returns (log_next_idx - syslog_idx), which is a
difference between buffer offsets--and the result could be negative.

The behavior is the same (it'll be zero or not in the same cases), but
the count of records is more meaningful and it matches what the comments
say.  So change the code to return that.

Signed-off-by: Alex Elder <elder@linaro.org>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Joe Perches <joe@perches.com>
Cc: John Stultz <john.stultz@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: allow increasing the ring buffer depending on the number of CPUs
Luis R. Rodriguez [Wed, 6 Aug 2014 23:08:56 +0000 (16:08 -0700)]
printk: allow increasing the ring buffer depending on the number of CPUs

The default size of the ring buffer is too small for machines with a
large amount of CPUs under heavy load.  What ends up happening when
debugging is the ring buffer overlaps and chews up old messages making
debugging impossible unless the size is passed as a kernel parameter.
An idle system upon boot up will on average spew out only about one or
two extra lines but where this really matters is on heavy load and that
will vary widely depending on the system and environment.

There are mechanisms to help increase the kernel ring buffer for tracing
through debugfs, and those interfaces even allow growing the kernel ring
buffer per CPU.  We also have a static value which can be passed upon
boot.  Relying on debugfs however is not ideal for production, and
relying on the value passed upon bootup is can only used *after* an
issue has creeped up.  Instead of being reactive this adds a proactive
measure which lets you scale the amount of contributions you'd expect to
the kernel ring buffer under load by each CPU in the worst case
scenario.

We use num_possible_cpus() to avoid complexities which could be
introduced by dynamically changing the ring buffer size at run time,
num_possible_cpus() lets us use the upper limit on possible number of
CPUs therefore avoiding having to deal with hotplugging CPUs on and off.
This introduces the kernel configuration option LOG_CPU_MAX_BUF_SHIFT
which is used to specify the maximum amount of contributions to the
kernel ring buffer in the worst case before the kernel ring buffer flips
over, the size is specified as a power of 2.  The total amount of
contributions made by each CPU must be greater than half of the default
kernel ring buffer size (1 << LOG_BUF_SHIFT bytes) in order to trigger
an increase upon bootup.  The kernel ring buffer is increased to the
next power of two that would fit the required minimum kernel ring buffer
size plus the additional CPU contribution.  For example if LOG_BUF_SHIFT
is 18 (256 KB) you'd require at least 128 KB contributions by other CPUs
in order to trigger an increase of the kernel ring buffer.  With a
LOG_CPU_BUF_SHIFT of 12 (4 KB) you'd require at least anything over > 64
possible CPUs to trigger an increase.  If you had 128 possible CPUs the
amount of minimum required kernel ring buffer bumps to:

   ((1 << 18) + ((128 - 1) * (1 << 12))) / 1024 = 764 KB

Since we require the ring buffer to be a power of two the new required
size would be 1024 KB.

This CPU contributions are ignored when the "log_buf_len" kernel
parameter is used as it forces the exact size of the ring buffer to an
expected power of two value.

[pmladek@suse.cz: fix build]
Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.cz>
Tested-by: Davidlohr Bueso <davidlohr@hp.com>
Tested-by: Petr Mladek <pmladek@suse.cz>
Reviewed-by: Davidlohr Bueso <davidlohr@hp.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Stephen Warren <swarren@wwwdotorg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Joe Perches <joe@perches.com>
Cc: Arun KS <arunks.linux@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: make dynamic units clear for the kernel ring buffer
Luis R. Rodriguez [Wed, 6 Aug 2014 23:08:54 +0000 (16:08 -0700)]
printk: make dynamic units clear for the kernel ring buffer

Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com>
Suggested-by: Davidlohr Bueso <davidlohr@hp.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Stephen Warren <swarren@wwwdotorg.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Joe Perches <joe@perches.com>
Cc: Arun KS <arunks.linux@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: move power of 2 practice of ring buffer size to a helper
Luis R. Rodriguez [Wed, 6 Aug 2014 23:08:52 +0000 (16:08 -0700)]
printk: move power of 2 practice of ring buffer size to a helper

In practice the power of 2 practice of the size of the kernel ring
buffer remains purely historical but not a requirement, specially now
that we have LOG_ALIGN and use it for both static and dynamic
allocations.  It could have helped with implicit alignment back in the
days given the even the dynamically sized ring buffer was guaranteed to
be aligned so long as CONFIG_LOG_BUF_SHIFT was set to produce a
__LOG_BUF_LEN which is architecture aligned, since log_buf_len=n would
be allowed only if it was > __LOG_BUF_LEN and we always ended up
rounding the log_buf_len=n to the next power of 2 with
roundup_pow_of_two(), any multiple of 2 then should be also architecture
aligned.  These assumptions of course relied heavily on
CONFIG_LOG_BUF_SHIFT producing an aligned value but users can always
change this.

We now have precise alignment requirements set for the log buffer size
for both static and dynamic allocations, but lets upkeep the old
practice of using powers of 2 for its size to help with easy expected
scalable values and the allocators for dynamic allocations.  We'll reuse
this later so move this into a helper.

Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Stephen Warren <swarren@wwwdotorg.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Joe Perches <joe@perches.com>
Cc: Arun KS <arunks.linux@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoprintk: make dynamic kernel ring buffer alignment explicit
Luis R. Rodriguez [Wed, 6 Aug 2014 23:08:49 +0000 (16:08 -0700)]
printk: make dynamic kernel ring buffer alignment explicit

We have to consider alignment for the ring buffer both for the default
static size, and then also for when an dynamic allocation is made when
the log_buf_len=n kernel parameter is passed to set the size
specifically to a size larger than the default size set by the
architecture through CONFIG_LOG_BUF_SHIFT.

The default static kernel ring buffer can be aligned properly if
architectures set CONFIG_LOG_BUF_SHIFT properly, we provide ranges for
the size though so even if CONFIG_LOG_BUF_SHIFT has a sensible aligned
value it can be reduced to a non aligned value.  Commit 6ebb017de9
("printk: Fix alignment of buf causing crash on ARM EABI") by Andrew
Lunn ensures the static buffer is always aligned and the decision of
alignment is done by the compiler by using __alignof__(struct log).

When log_buf_len=n is used we allocate the ring buffer dynamically.
Dynamic allocation varies, for the early allocation called before
setup_arch() memblock_virt_alloc() requests a page aligment and for the
default kernel allocation memblock_virt_alloc_nopanic() requests no
special alignment, which in turn ends up aligning the allocation to
SMP_CACHE_BYTES, which is L1 cache aligned.

Since we already have the required alignment for the kernel ring buffer
though we can do better and request explicit alignment for LOG_ALIGN.
This does that to be safe and make dynamic allocation alignment
explicit.

Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com>
Tested-by: Petr Mladek <pmladek@suse.cz>
Acked-by: Petr Mladek <pmladek@suse.cz>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Stephen Warren <swarren@wwwdotorg.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Joe Perches <joe@perches.com>
Cc: Arun KS <arunks.linux@gmail.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoinclude/linux/byteorder/generic.h: minor comment fix
Geoff Levand [Wed, 6 Aug 2014 23:08:47 +0000 (16:08 -0700)]
include/linux/byteorder/generic.h: minor comment fix

Signed-off-by: Geoff Levand <geoff@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agofs.h, drivers/hwmon/asus_atk0110.c: fix DEFINE_SIMPLE_ATTRIBUTE semicolon definition...
Joe Perches [Wed, 6 Aug 2014 23:08:45 +0000 (16:08 -0700)]
fs.h, drivers/hwmon/asus_atk0110.c: fix DEFINE_SIMPLE_ATTRIBUTE semicolon definition and use

The DEFINE_SIMPLE_ATTRIBUTE macro should not end in a ; Fix the one use
in the kernel tree that did not have a semicolon.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Luca Tettamanti <kronos.it@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years ago./Makefile: tell gcc optimizer to never introduce new data races
Jiri Kosina [Wed, 6 Aug 2014 23:08:43 +0000 (16:08 -0700)]
./Makefile: tell gcc optimizer to never introduce new data races

We have been chasing a memory corruption bug, which turned out to be
caused by very old gcc (4.3.4), which happily turned conditional load
into a non-conditional one, and that broke correctness (the condition
was met only if lock was held) and corrupted memory.

This particular problem with that particular code did not happen when
never gccs were used.  I've brought this up with our gcc folks, as I
wanted to make sure that this can't really happen again, and it turns
out it actually can.

Quoting Martin Jambor <mjambor@suse.cz>:
 "More current GCCs are more careful when it comes to replacing a
  conditional load with a non-conditional one, most notably they check
  that a store happens in each iteration of _a_ loop but they assume
  loops are executed.  They also perform a simple check whether the
  store cannot trap which currently passes only for non-const
  variables.  A simple testcase demonstrating it on an x86_64 is for
  example the following:

  $ cat cond_store.c

  int g_1 = 1;

  int g_2[1024] __attribute__((section ("safe_section"), aligned (4096)));

  int c = 4;

  int __attribute__ ((noinline))
  foo (void)
  {
    int l;
    for (l = 0; (l != 4); l++) {
      if (g_1)
        return l;
      for (g_2[0] = 0; (g_2[0] >= 26); ++g_2[0])
        ;
    }
    return 2;
  }

  int main (int argc, char* argv[])
  {
    if (mprotect (g_2, sizeof(g_2), PROT_READ) == -1)
      {
        int e = errno;
        error (e, e, "mprotect error %i", e);
      }
    foo ();
    __builtin_printf("OK\n");
    return 0;
  }
  /* EOF */
  $ ~/gcc/trunk/inst/bin/gcc cond_store.c -O2 --param allow-store-data-races=0
  $ ./a.out
  OK
  $ ~/gcc/trunk/inst/bin/gcc cond_store.c -O2 --param allow-store-data-races=1
  $ ./a.out
  Segmentation fault

  The testcase fails the same at least with 4.9, 4.8 and 4.7.  Therefore
  I would suggest building kernels with this parameter set to zero. I
  also agree with Jikos that the default should be changed for -O2.  I
  have run most of the SPEC 2k6 CPU benchmarks (gamess and dealII
  failed, at -O2, not sure why) compiled with and without this option
  and did not see any real difference between respective run-times"

Hopefully the default will be changed in newer gccs, but let's force it
for kernel builds so that we are on a safe side even when older gcc are
used.

The code in question was out-of-tree printk-in-NMI (yeah, surprise
suprise, once again) patch written by Petr Mladek, let me quote his
comment from our internal bugzilla:

 "I have spent few days investigating inconsistent state of kernel ring buffer.
  It went out that it was caused by speculative store generated by
  gcc-4.3.4.

  The problem is in assembly generated for make_free_space(). The functions is
  called the following way:

  + vprintk_emit();
      + log = MAIN_LOG; // with logbuf_lock
         or
         log = NMI_LOG; // with nmi_logbuf_lock
         cont_add(log, ...);
          + cont_flush(log, ...);
              + log_store(log, ...);
                    + log_make_free_space(log, ...);

  If called with log = NMI_LOG then only nmi_log_* global variables are safe to
  modify but the generated code does store also into (main_)log_* global
  variables:

  <log_make_free_space>:
         55                      push   %rbp
         89 f6                   mov    %esi,%esi

         48 8b 05 03 99 51 01    mov    0x1519903(%rip),%rax       # ffffffff82620868 <nmi_log_next_id>
         44 8b 1d ec 98 51 01    mov    0x15198ec(%rip),%r11d      # ffffffff82620858 <log_next_idx>
         8b 35 36 60 14 01       mov    0x1146036(%rip),%esi       # ffffffff8224cfa8 <log_buf_len>
         44 8b 35 33 60 14 01    mov    0x1146033(%rip),%r14d      # ffffffff8224cfac <nmi_log_buf_len>
         4c 8b 2d d0 98 51 01    mov    0x15198d0(%rip),%r13       # ffffffff82620850 <log_next_seq>
         4c 8b 25 11 61 14 01    mov    0x1146111(%rip),%r12       # ffffffff8224d098 <log_buf>
         49 89 c2                mov    %rax,%r10
         48 21 c2                and    %rax,%rdx
         48 8b 1d 0c 99 55 01    mov    0x155990c(%rip),%rbx       # ffffffff826608a0 <nmi_log_buf>
         49 c1 ea 20             shr    $0x20,%r10
         48 89 55 d0             mov    %rdx,-0x30(%rbp)
         44 29 de                sub    %r11d,%esi
         45 29 d6                sub    %r10d,%r14d
         4c 8b 0d 97 98 51 01    mov    0x1519897(%rip),%r9 # ffffffff82620840 <log_first_seq>
         eb 7e                   jmp    ffffffff81107029 <log_make_free_space+0xe9>
  [...]
         85 ff                   test   %edi,%edi                  # edi = 1 for NMI_LOG
         4c 89 e8                mov    %r13,%rax
         4c 89 ca                mov    %r9,%rdx
         74 0a                   je     ffffffff8110703d <log_make_free_space+0xfd>
         8b 15 27 98 51 01       mov    0x1519827(%rip),%edx       # ffffffff82620860 <nmi_log_first_id>
         48 8b 45 d0             mov    -0x30(%rbp),%rax
         48 39 c2                cmp    %rax,%rdx                  # end of loop
         0f 84 da 00 00 00       je     ffffffff81107120 <log_make_free_space+0x1e0>
  [...]
         85 ff                   test   %edi,%edi                  # edi = 1 for NMI_LOG
         4c 89 0d 17 97 51 01    mov    %r9,0x1519717(%rip)        # ffffffff82620840 <log_first_seq>
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^
                                 KABOOOM
         74 35                   je     ffffffff81107160  <log_make_free_space+0x220>

  It stores log_first_seq when edi == NMI_LOG. This instructions are used also
  when edi == MAIN_LOG but the store is done speculatively before the condition
  is decided.  It is unsafe because we do not have "logbuf_lock" in NMI context
  and some other process migh modify "log_first_seq" in parallel"

I believe that the best course of action is both

 - building kernel (and anything multi-threaded, I guess) with that
   optimization turned off
 - persuade gcc folks to change the default for future releases

Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Cc: Martin Jambor <mjambor@suse.cz>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Marek Polacek <polacek@redhat.com>
Cc: Jakub Jelinek <jakub@redhat.com>
Cc: Steven Noonan <steven@uplinklabs.net>
Cc: Richard Biener <richard.guenther@gmail.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm/zpool: update zswap to use zpool
Dan Streetman [Wed, 6 Aug 2014 23:08:40 +0000 (16:08 -0700)]
mm/zpool: update zswap to use zpool

Change zswap to use the zpool api instead of directly using zbud.  Add a
boot-time param to allow selecting which zpool implementation to use,
with zbud as the default.

Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Tested-by: Seth Jennings <sjennings@variantweb.net>
Cc: Weijie Yang <weijie.yang@samsung.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm/zpool: zbud/zsmalloc implement zpool
Dan Streetman [Wed, 6 Aug 2014 23:08:38 +0000 (16:08 -0700)]
mm/zpool: zbud/zsmalloc implement zpool

Update zbud and zsmalloc to implement the zpool api.

[fengguang.wu@intel.com: make functions static]
Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Tested-by: Seth Jennings <sjennings@variantweb.net>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm/zpool: implement common zpool api to zbud/zsmalloc
Dan Streetman [Wed, 6 Aug 2014 23:08:36 +0000 (16:08 -0700)]
mm/zpool: implement common zpool api to zbud/zsmalloc

Add zpool api.

zpool provides an interface for memory storage, typically of compressed
memory.  Users can select what backend to use; currently the only
implementations are zbud, a low density implementation with up to two
compressed pages per storage page, and zsmalloc, a higher density
implementation with multiple compressed pages per storage page.

Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Tested-by: Seth Jennings <sjennings@variantweb.net>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm/zbud: change zbud_alloc size type to size_t
Dan Streetman [Wed, 6 Aug 2014 23:08:33 +0000 (16:08 -0700)]
mm/zbud: change zbud_alloc size type to size_t

Change the type of the zbud_alloc() size param from unsigned int to
size_t.

Technically, this should not make any difference, as the zbud
implementation already restricts the size to well within either type's
limits; but as zsmalloc (and kmalloc) use size_t, and zpool will use
size_t, this brings the size parameter type in line with zsmalloc/zpool.

Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Acked-by: Seth Jennings <sjennings@variantweb.net>
Tested-by: Seth Jennings <sjennings@variantweb.net>
Cc: Weijie Yang <weijie.yang@samsung.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agozram: replace global tb_lock with fine grain lock
Weijie Yang [Wed, 6 Aug 2014 23:08:31 +0000 (16:08 -0700)]
zram: replace global tb_lock with fine grain lock

Currently, we use a rwlock tb_lock to protect concurrent access to the
whole zram meta table.  However, according to the actual access model,
there is only a small chance for upper user to access the same
table[index], so the current lock granularity is too big.

The idea of optimization is to change the lock granularity from whole
meta table to per table entry (table -> table[index]), so that we can
protect concurrent access to the same table[index], meanwhile allow the
maximum concurrency.

With this in mind, several kinds of locks which could be used as a
per-entry lock were tested and compared:

Test environment:
x86-64 Intel Core2 Q8400, system memory 4GB, Ubuntu 12.04,
kernel v3.15.0-rc3 as base, zram with 4 max_comp_streams LZO.

iozone test:
iozone -t 4 -R -r 16K -s 200M -I +Z
(1GB zram with ext4 filesystem, take the average of 10 tests, KB/s)

      Test       base      CAS    spinlock    rwlock   bit_spinlock
-------------------------------------------------------------------
 Initial write  1381094   1425435   1422860   1423075   1421521
       Rewrite  1529479   1641199   1668762   1672855   1654910
          Read  8468009  11324979  11305569  11117273  10997202
       Re-read  8467476  11260914  11248059  11145336  10906486
  Reverse Read  6821393   8106334   8282174   8279195   8109186
   Stride read  7191093   8994306   9153982   8961224   9004434
   Random read  7156353   8957932   9167098   8980465   8940476
Mixed workload  4172747   5680814   5927825   5489578   5972253
  Random write  1483044   1605588   1594329   1600453   1596010
        Pwrite  1276644   1303108   1311612   1314228   1300960
         Pread  4324337   4632869   4618386   4457870   4500166

To enhance the possibility of access the same table[index] concurrently,
set zram a small disksize(10MB) and let threads run with large loop
count.

fio test:
fio --bs=32k --randrepeat=1 --randseed=100 --refill_buffers
--scramble_buffers=1 --direct=1 --loops=3000 --numjobs=4
--filename=/dev/zram0 --name=seq-write --rw=write --stonewall
--name=seq-read --rw=read --stonewall --name=seq-readwrite
--rw=rw --stonewall --name=rand-readwrite --rw=randrw --stonewall
(10MB zram raw block device, take the average of 10 tests, KB/s)

    Test     base     CAS    spinlock    rwlock  bit_spinlock
-------------------------------------------------------------
seq-write   933789   999357   1003298    995961   1001958
 seq-read  5634130  6577930   6380861   6243912   6230006
   seq-rw  1405687  1638117   1640256   1633903   1634459
  rand-rw  1386119  1614664   1617211   1609267   1612471

All the optimization methods show a higher performance than the base,
however, it is hard to say which method is the most appropriate.

On the other hand, zram is mostly used on small embedded system, so we
don't want to increase any memory footprint.

This patch pick the bit_spinlock method, pack object size and page_flag
into an unsigned long table.value, so as to not increase any memory
overhead on both 32-bit and 64-bit system.

On the third hand, even though different kinds of locks have different
performances, we can ignore this difference, because: if zram is used as
zram swapfile, the swap subsystem can prevent concurrent access to the
same swapslot; if zram is used as zram-blk for set up filesystem on it,
the upper filesystem and the page cache also prevent concurrent access
of the same block mostly.  So we can ignore the different performances
among locks.

Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Reviewed-by: Davidlohr Bueso <davidlohr@hp.com>
Signed-off-by: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agozram: use size_t instead of u16
Minchan Kim [Wed, 6 Aug 2014 23:08:29 +0000 (16:08 -0700)]
zram: use size_t instead of u16

Some architectures (eg, hexagon and PowerPC) could use PAGE_SHIFT of 16
or more.  In these cases u16 is not sufficiently large to represent a
compressed page's size so use size_t.

Signed-off-by: Minchan Kim <minchan@kernel.org>
Reported-by: Weijie Yang <weijie.yang@samsung.com>
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agozram: remove unused SECTOR_SIZE define
Sergey Senozhatsky [Wed, 6 Aug 2014 23:08:27 +0000 (16:08 -0700)]
zram: remove unused SECTOR_SIZE define

Drop SECTOR_SIZE define, because it's not used.

Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agozram: rename struct `table' to `zram_table_entry'
Sergey Senozhatsky [Wed, 6 Aug 2014 23:08:25 +0000 (16:08 -0700)]
zram: rename struct `table' to `zram_table_entry'

Andrew Morton has recently noted that `struct table' actually represents
table entry and, thus, should be renamed.  Rename to `zram_table_entry'.

Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Weijie Yang <weijie.yang@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm/highmem: make kmap cache coloring aware
Max Filippov [Wed, 6 Aug 2014 23:08:23 +0000 (16:08 -0700)]
mm/highmem: make kmap cache coloring aware

User-visible effect:
 Architectures that choose this method of maintaining cache coherency
(MIPS and xtensa currently) are able to use high memory on cores with
aliasing data cache.  Without this fix such architectures can not use
high memory (in case of xtensa it means that at most 128 MBytes of
physical memory is available).

The problem:
 VIPT cache with way size larger than MMU page size may suffer from
aliasing problem: a single physical address accessed via different
virtual addresses may end up in multiple locations in the cache.
Virtual mappings of a physical address that always get cached in
different cache locations are said to have different colors.  L1 caching
hardware usually doesn't handle this situation leaving it up to
software.  Software must avoid this situation as it leads to data
corruption.

What can be done:
 One way to handle this is to flush and invalidate data cache every time
page mapping changes color.  The other way is to always map physical
page at a virtual address with the same color.  Low memory pages already
have this property.  Giving architecture a way to control color of high
memory page mapping allows reusing of existing low memory cache alias
handling code.

How this is done with this patch:
 Provide hooks that allow architectures with aliasing cache to align
mapping address of high pages according to their color.  Such
architectures may enforce similar coloring of low- and high-memory page
mappings and reuse existing cache management functions to support
highmem.

This code is based on the implementation of similar feature for MIPS by
Leonid Yegoshin.

Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Cc: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Marc Gauthier <marc@cadence.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Steven Hill <Steven.Hill@imgtec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agommu_notifier: add call_srcu and sync function for listener to delay call and sync
Peter Zijlstra [Wed, 6 Aug 2014 23:08:20 +0000 (16:08 -0700)]
mmu_notifier: add call_srcu and sync function for listener to delay call and sync

When kernel device drivers or subsystems want to bind their lifespan to
t= he lifespan of the mm_struct, they usually use one of the following
methods:

1. Manually calling a function in the interested kernel module.  The
   funct= ion call needs to be placed in mmput.  This method was rejected
   by several ker= nel maintainers.

2. Registering to the mmu notifier release mechanism.

The problem with the latter approach is that the mmu_notifier_release
cal= lback is called from__mmu_notifier_release (called from exit_mmap).
That functi= on iterates over the list of mmu notifiers and don't expect
the release call= back function to remove itself from the list.
Therefore, the callback function= in the kernel module can't release the
mmu_notifier_object, which is actuall= y the kernel module's object
itself.  As a result, the destruction of the kernel module's object must
to be done in a delayed fashion.

This patch adds support for this delayed callback, by adding a new
mmu_notifier_call_srcu function that receives a function ptr and calls
th= at function with call_srcu.  In that function, the kernel module
releases its object.  To use mmu_notifier_call_srcu, the calling module
needs to call b= efore that a new function called
mmu_notifier_unregister_no_release that as its= name implies,
unregisters a notifier without calling its notifier release call= back.

This patch also adds a function that will call barrier_srcu so those
kern= el modules can sync with mmu_notifier.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Signed-off-by: Oded Gabbay <oded.gabbay@amd.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: BUG when __kmap_atomic_idx equals KM_TYPE_NR
Chintan Pandya [Wed, 6 Aug 2014 23:08:18 +0000 (16:08 -0700)]
mm: BUG when __kmap_atomic_idx equals KM_TYPE_NR

__kmap_atomic_idx is per_cpu variable.  Each CPU can use KM_TYPE_NR
entries from FIXMAP i.e.  from 0 to KM_TYPE_NR - 1.  Allowing
__kmap_atomic_idx to over- shoot to KM_TYPE_NR can mess up with next
CPU's 0th entry which is a bug.  Hence BUG_ON if __kmap_atomic_idx >=
KM_TYPE_NR.

Fix the off-by-on in this test.

Signed-off-by: Chintan Pandya <cpandya@codeaurora.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: memcontrol: clean up reclaim size variable use in try_charge()
Johannes Weiner [Wed, 6 Aug 2014 23:08:16 +0000 (16:08 -0700)]
mm: memcontrol: clean up reclaim size variable use in try_charge()

Charge reclaim and OOM currently use the charge batch variable, but
batching is already disabled at that point.  To simplify the charge
logic, the batch variable is reset to the original request size when
reclaim is entered, so it's functionally equal, but it's misleading.

Switch reclaim/OOM to nr_pages, which is the original request size.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agokernel/smp.c:on_each_cpu_cond(): fix warning in fallback path
Sasha Levin [Wed, 6 Aug 2014 23:08:14 +0000 (16:08 -0700)]
kernel/smp.c:on_each_cpu_cond(): fix warning in fallback path

The rarely-executed memry-allocation-failed callback path generates a
WARN_ON_ONCE() when smp_call_function_single() succeeds.  Presumably
it's supposed to warn on failures.

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Christoph Lameter <cl@gentwo.org>
Cc: Gilad Ben-Yossef <gilad@benyossef.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Tejun Heo <htejun@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: change confusing #ifdef use in __access_remote_vm
Rik van Riel [Wed, 6 Aug 2014 23:08:12 +0000 (16:08 -0700)]
mm: change confusing #ifdef use in __access_remote_vm

This patch changes confusing #ifdef use in __access_remote_vm into
merely ugly #ifdef use.

Addresses bug https://bugzilla.kernel.org/show_bug.cgi?id=81651

Signed-off-by: Rik van Riel <riel@redhat.com>
Reported-by: David Binderman <dcb314@hotmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: softdirty: respect VM_SOFTDIRTY in PTE holes
Peter Feiner [Wed, 6 Aug 2014 23:08:09 +0000 (16:08 -0700)]
mm: softdirty: respect VM_SOFTDIRTY in PTE holes

After a VMA is created with the VM_SOFTDIRTY flag set, /proc/pid/pagemap
should report that the VMA's virtual pages are soft-dirty until
VM_SOFTDIRTY is cleared (i.e., by the next write of "4" to
/proc/pid/clear_refs).  However, pagemap ignores the VM_SOFTDIRTY flag
for virtual addresses that fall in PTE holes (i.e., virtual addresses
that don't have a PMD, PUD, or PGD allocated yet).

To observe this bug, use mmap to create a VMA large enough such that
there's a good chance that the VMA will occupy an unused PMD, then test
the soft-dirty bit on its pages.  In practice, I found that a VMA that
covered a PMD's worth of address space was big enough.

This patch adds the necessary VMA lookup to the PTE hole callback in
/proc/pid/pagemap's page walk and sets soft-dirty according to the VMAs'
VM_SOFTDIRTY flag.

Signed-off-by: Peter Feiner <pfeiner@google.com>
Acked-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Hugh Dickins <hughd@google.com>
Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: mark fault_around_bytes __read_mostly
Kirill A. Shutemov [Wed, 6 Aug 2014 23:08:07 +0000 (16:08 -0700)]
mm: mark fault_around_bytes __read_mostly

fault_around_bytes can only be changed via debugfs.  Let's mark it
read-mostly.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Suggested-by: David Rientjes <rientjes@google.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Andrey Ryabinin <a.ryabinin@samsung.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: close race between do_fault_around() and fault_around_bytes_set()
Kirill A. Shutemov [Wed, 6 Aug 2014 23:08:05 +0000 (16:08 -0700)]
mm: close race between do_fault_around() and fault_around_bytes_set()

Things can go wrong if fault_around_bytes will be changed under
do_fault_around(): between fault_around_mask() and fault_around_pages().

Let's read fault_around_bytes only once during do_fault_around() and
calculate mask based on the reading.

Note: fault_around_bytes can only be updated via debug interface.  Also
I've tried but was not able to trigger a bad behaviour without the
patch.  So I would not consider this patch as urgent.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Andrey Ryabinin <a.ryabinin@samsung.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomemcg, vmscan: Fix forced scan of anonymous pages
Jerome Marchand [Wed, 6 Aug 2014 23:08:03 +0000 (16:08 -0700)]
memcg, vmscan: Fix forced scan of anonymous pages

When memory cgoups are enabled, the code that decides to force to scan
anonymous pages in get_scan_count() compares global values (free,
high_watermark) to a value that is restricted to a memory cgroup (file).
It make the code over-eager to force anon scan.

For instance, it will force anon scan when scanning a memcg that is
mainly populated by anonymous page, even when there is plenty of file
pages to get rid of in others memcgs, even when swappiness == 0.  It
breaks user's expectation about swappiness and hurts performance.

This patch makes sure that forced anon scan only happens when there not
enough file pages for the all zone, not just in one random memcg.

[hannes@cmpxchg.org: cleanups]
Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm, vmscan: fix an outdated comment still mentioning get_scan_ratio
Jerome Marchand [Wed, 6 Aug 2014 23:08:01 +0000 (16:08 -0700)]
mm, vmscan: fix an outdated comment still mentioning get_scan_ratio

Quite a while ago, get_scan_ratio() has been renamed get_scan_count(),
however a comment in shrink_active_list() still mention it.  This patch
fixes the outdated comment.

Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm, oom: remove unnecessary exit_state check
David Rientjes [Wed, 6 Aug 2014 23:07:58 +0000 (16:07 -0700)]
mm, oom: remove unnecessary exit_state check

The oom killer scans each process and determines whether it is eligible
for oom kill or whether the oom killer should abort because of
concurrent memory freeing.  It will abort when an eligible process is
found to have TIF_MEMDIE set, meaning it has already been oom killed and
we're waiting for it to exit.

Processes with task->mm == NULL should not be considered because they
are either kthreads or have already detached their memory and killing
them would not lead to memory freeing.  That memory is only freed after
exit_mm() has returned, however, and not when task->mm is first set to
NULL.

Clear TIF_MEMDIE after exit_mm()'s mmput() so that an oom killed process
is no longer considered for oom kill, but only until exit_mm() has
returned.  This was fragile in the past because it relied on
exit_notify() to be reached before no longer considering TIF_MEMDIE
processes.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: fix potential infinite loop in dissolve_free_huge_pages()
Li Zhong [Wed, 6 Aug 2014 23:07:56 +0000 (16:07 -0700)]
mm: fix potential infinite loop in dissolve_free_huge_pages()

It is possible for some platforms, such as powerpc to set HPAGE_SHIFT to
0 to indicate huge pages not supported.

When this is the case, hugetlbfs could be disabled during boot time:
hugetlbfs: disabling because there are no supported hugepage sizes

Then in dissolve_free_huge_pages(), order is kept maximum (64 for
64bits), and the for loop below won't end: for (pfn = start_pfn; pfn <
end_pfn; pfn += 1 << order)

As suggested by Naoya, below fix checks hugepages_supported() before
calling dissolve_free_huge_pages().

[rientjes@google.com: no legitimate reason to call dissolve_free_huge_pages() when !hugepages_supported()]
Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>
Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: <stable@vger.kernel.org> [3.12+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm, thp: restructure thp avoidance of light synchronous migration
David Rientjes [Wed, 6 Aug 2014 23:07:54 +0000 (16:07 -0700)]
mm, thp: restructure thp avoidance of light synchronous migration

__GFP_NO_KSWAPD, once the way to determine if an allocation was for thp
or not, has gained more users.  Their use is not necessarily wrong, they
are trying to do a memory allocation that can easily fail without
disturbing kswapd, so the bit has gained additional usecases.

This restructures the check to determine whether MIGRATE_SYNC_LIGHT
should be used for memory compaction in the page allocator.  Rather than
testing solely for __GFP_NO_KSWAPD, test for all bits that must be set
for thp allocations.

This also moves the check to be done only after the page allocator is
aborted for deferred or contended memory compaction since setting
migration_mode for this case is pointless.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm, oom: rename zonelist locking functions
David Rientjes [Wed, 6 Aug 2014 23:07:52 +0000 (16:07 -0700)]
mm, oom: rename zonelist locking functions

try_set_zonelist_oom() and clear_zonelist_oom() are not named properly
to imply that they require locking semantics to avoid out_of_memory()
being reordered.

zone_scan_lock is required for both functions to ensure that there is
proper locking synchronization.

Rename try_set_zonelist_oom() to oom_zonelist_trylock() and rename
clear_zonelist_oom() to oom_zonelist_unlock() to imply there is proper
locking semantics.

At the same time, convert oom_zonelist_trylock() to return bool instead
of int since only success and failure are tested.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
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>
10 years agomm, oom: ensure memoryless node zonelist always includes zones
David Rientjes [Wed, 6 Aug 2014 23:07:50 +0000 (16:07 -0700)]
mm, oom: ensure memoryless node zonelist always includes zones

With memoryless node support being worked on, it's possible that for
optimizations that a node may not have a non-NULL zonelist.  When
CONFIG_NUMA is enabled and node 0 is memoryless, this means the zonelist
for first_online_node may become NULL.

The oom killer requires a zonelist that includes all memory zones for
the sysrq trigger and pagefault out of memory handler.

Ensure that a non-NULL zonelist is always passed to the oom killer.

[akpm@linux-foundation.org: fix non-numa build]
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
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>
10 years agomemory-hotplug: sh: suitable memory should go to ZONE_MOVABLE
Wang Nan [Wed, 6 Aug 2014 23:07:47 +0000 (16:07 -0700)]
memory-hotplug: sh: suitable memory should go to ZONE_MOVABLE

This patch introduces zone_for_memory() to arch_add_memory() on sh to
ensure new, higher memory added into ZONE_MOVABLE if movable zone has
already setup.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: "Mel Gorman" <mgorman@suse.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomemory-hotplug: ppc: suitable memory should go to ZONE_MOVABLE
Wang Nan [Wed, 6 Aug 2014 23:07:45 +0000 (16:07 -0700)]
memory-hotplug: ppc: suitable memory should go to ZONE_MOVABLE

This patch introduces zone_for_memory() to arch_add_memory() on powerpc
to ensure new, higher memory added into ZONE_MOVABLE if movable zone has
already setup.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: "Mel Gorman" <mgorman@suse.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomemory-hotplug: ia64: suitable memory should go to ZONE_MOVABLE
Wang Nan [Wed, 6 Aug 2014 23:07:43 +0000 (16:07 -0700)]
memory-hotplug: ia64: suitable memory should go to ZONE_MOVABLE

This patch introduces zone_for_memory() to arch_add_memory() on ia64 to
ensure new, higher memory added into ZONE_MOVABLE if movable zone has
already setup.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: "Mel Gorman" <mgorman@suse.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomemory-hotplug: x86_32: suitable memory should go to ZONE_MOVABLE
Wang Nan [Wed, 6 Aug 2014 23:07:40 +0000 (16:07 -0700)]
memory-hotplug: x86_32: suitable memory should go to ZONE_MOVABLE

This patch introduces zone_for_memory() to arch_add_memory() on x86_32
to ensure new, higher memory added into ZONE_MOVABLE if movable zone has
already setup.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: "Mel Gorman" <mgorman@suse.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomemory-hotplug: x86_64: suitable memory should go to ZONE_MOVABLE
Wang Nan [Wed, 6 Aug 2014 23:07:38 +0000 (16:07 -0700)]
memory-hotplug: x86_64: suitable memory should go to ZONE_MOVABLE

This patch introduces zone_for_memory() to arch_add_memory() on x86_64
to ensure new, higher memory added into ZONE_MOVABLE if movable zone has
already setup.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: "Mel Gorman" <mgorman@suse.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomemory-hotplug: add zone_for_memory() for selecting zone for new memory
Wang Nan [Wed, 6 Aug 2014 23:07:36 +0000 (16:07 -0700)]
memory-hotplug: add zone_for_memory() for selecting zone for new memory

This series of patches fixes a problem when adding memory in bad manner.
For example: for a x86_64 machine booted with "mem=400M" and with 2GiB
memory installed, following commands cause problem:

  # echo 0x40000000 > /sys/devices/system/memory/probe
 [   28.613895] init_memory_mapping: [mem 0x40000000-0x47ffffff]
  # echo 0x48000000 > /sys/devices/system/memory/probe
 [   28.693675] init_memory_mapping: [mem 0x48000000-0x4fffffff]
  # echo online_movable > /sys/devices/system/memory/memory9/state
  # echo 0x50000000 > /sys/devices/system/memory/probe
 [   29.084090] init_memory_mapping: [mem 0x50000000-0x57ffffff]
  # echo 0x58000000 > /sys/devices/system/memory/probe
 [   29.151880] init_memory_mapping: [mem 0x58000000-0x5fffffff]
  # echo online_movable > /sys/devices/system/memory/memory11/state
  # echo online> /sys/devices/system/memory/memory8/state
  # echo online> /sys/devices/system/memory/memory10/state
  # echo offline> /sys/devices/system/memory/memory9/state
 [   30.558819] Offlined Pages 32768
  # free
              total       used       free     shared    buffers     cached
 Mem:        780588 18014398509432020     830552          0          0      51180
 -/+ buffers/cache: 18014398509380840     881732
 Swap:            0          0          0

This is because the above commands probe higher memory after online a
section with online_movable, which causes ZONE_HIGHMEM (or ZONE_NORMAL
for systems without ZONE_HIGHMEM) overlaps ZONE_MOVABLE.

After the second online_movable, the problem can be observed from
zoneinfo:

  # cat /proc/zoneinfo
  ...
  Node 0, zone  Movable
    pages free     65491
          min      250
          low      312
          high     375
          scanned  0
          spanned  18446744073709518848
          present  65536
          managed  65536
  ...

This series of patches solve the problem by checking ZONE_MOVABLE when
choosing zone for new memory.  If new memory is inside or higher than
ZONE_MOVABLE, makes it go there instead.

After applying this series of patches, following are free and zoneinfo
result (after offlining memory9):

  bash-4.2# free
                total       used       free     shared    buffers     cached
   Mem:        780956      80112     700844          0          0      51180
   -/+ buffers/cache:      28932     752024
   Swap:            0          0          0

  bash-4.2# cat /proc/zoneinfo

  Node 0, zone      DMA
    pages free     3389
          min      14
          low      17
          high     21
          scanned  0
          spanned  4095
          present  3998
          managed  3977
      nr_free_pages 3389
  ...
    start_pfn:         1
    inactive_ratio:    1
  Node 0, zone    DMA32
    pages free     73724
          min      341
          low      426
          high     511
          scanned  0
          spanned  98304
          present  98304
          managed  92958
      nr_free_pages 73724
    ...
    start_pfn:         4096
    inactive_ratio:    1
  Node 0, zone   Normal
    pages free     32630
          min      120
          low      150
          high     180
          scanned  0
          spanned  32768
          present  32768
          managed  32768
      nr_free_pages 32630
  ...
    start_pfn:         262144
    inactive_ratio:    1
  Node 0, zone  Movable
    pages free     65476
          min      241
          low      301
          high     361
          scanned  0
          spanned  98304
          present  65536
          managed  65536
      nr_free_pages 65476
  ...
    start_pfn:         294912
    inactive_ratio:    1

This patch (of 7):

Introduce zone_for_memory() in arch independent code for
arch_add_memory() use.

Many arch_add_memory() function simply selects ZONE_HIGHMEM or
ZONE_NORMAL and add new memory into it.  However, with the existance of
ZONE_MOVABLE, the selection method should be carefully considered: if
new, higher memory is added after ZONE_MOVABLE is setup, the default
zone and ZONE_MOVABLE may overlap each other.

should_add_memory_movable() checks the status of ZONE_MOVABLE.  If it
has already contain memory, compare the address of new memory and
movable memory.  If new memory is higher than movable, it should be
added into ZONE_MOVABLE instead of default zone.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: "Mel Gorman" <mgorman@suse.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agoslub: remove kmemcg id from create_unique_id
Vladimir Davydov [Wed, 6 Aug 2014 23:07:33 +0000 (16:07 -0700)]
slub: remove kmemcg id from create_unique_id

This function is never called for memcg caches, because they are
unmergeable, so remove the dead code.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Reviewed-by: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm, writeback: prevent race when calculating dirty limits
David Rientjes [Wed, 6 Aug 2014 23:07:31 +0000 (16:07 -0700)]
mm, writeback: prevent race when calculating dirty limits

Setting vm_dirty_bytes and dirty_background_bytes is not protected by
any serialization.

Therefore, it's possible for either variable to change value after the
test in global_dirty_limits() to determine whether available_memory
needs to be initialized or not.

Always ensure that available_memory is properly initialized.

Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
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>
10 years agomm, thp: only collapse hugepages to nodes with affinity for zone_reclaim_mode
David Rientjes [Wed, 6 Aug 2014 23:07:29 +0000 (16:07 -0700)]
mm, thp: only collapse hugepages to nodes with affinity for zone_reclaim_mode

Commit 9f1b868a13ac ("mm: thp: khugepaged: add policy for finding target
node") improved the previous khugepaged logic which allocated a
transparent hugepages from the node of the first page being collapsed.

However, it is still possible to collapse pages to remote memory which
may suffer from additional access latency.  With the current policy, it
is possible that 255 pages (with PAGE_SHIFT == 12) will be collapsed
remotely if the majority are allocated from that node.

When zone_reclaim_mode is enabled, it means the VM should make every
attempt to allocate locally to prevent NUMA performance degradation.  In
this case, we do not want to collapse hugepages to remote nodes that
would suffer from increased access latency.  Thus, when
zone_reclaim_mode is enabled, only allow collapsing to nodes with
RECLAIM_DISTANCE or less.

There is no functional change for systems that disable
zone_reclaim_mode.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm/shmem.c: remove the unused gfp arg to shmem_add_to_page_cache()
Wang Sheng-Hui [Wed, 6 Aug 2014 23:07:26 +0000 (16:07 -0700)]
mm/shmem.c: remove the unused gfp arg to shmem_add_to_page_cache()

The gfp arg is not used in shmem_add_to_page_cache.  Remove this unused
arg.

Signed-off-by: Wang Sheng-Hui <shhuiw@gmail.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: describe mmap_sem rules for __lock_page_or_retry() and callers
Paul Cassella [Wed, 6 Aug 2014 23:07:24 +0000 (16:07 -0700)]
mm: describe mmap_sem rules for __lock_page_or_retry() and callers

Add a comment describing the circumstances in which
__lock_page_or_retry() will or will not release the mmap_sem when
returning 0.

Add comments to lock_page_or_retry()'s callers (filemap_fault(),
do_swap_page()) noting the impact on VM_FAULT_RETRY returns.

Add comments on up the call tree, particularly replacing the false "We
return with mmap_sem still held" comments.

Signed-off-by: Paul Cassella <cassella@cray.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: page_alloc: reduce cost of the fair zone allocation policy
Mel Gorman [Wed, 6 Aug 2014 23:07:22 +0000 (16:07 -0700)]
mm: page_alloc: reduce cost of the fair zone allocation policy

The fair zone allocation policy round-robins allocations between zones
within a node to avoid age inversion problems during reclaim.  If the
first allocation fails, the batch counts are reset and a second attempt
made before entering the slow path.

One assumption made with this scheme is that batches expire at roughly
the same time and the resets each time are justified.  This assumption
does not hold when zones reach their low watermark as the batches will
be consumed at uneven rates.  Allocation failure due to watermark
depletion result in additional zonelist scans for the reset and another
watermark check before hitting the slowpath.

On UMA, the benefit is negligible -- around 0.25%.  On 4-socket NUMA
machine it's variable due to the variability of measuring overhead with
the vmstat changes.  The system CPU overhead comparison looks like

          3.16.0-rc3  3.16.0-rc3  3.16.0-rc3
             vanilla   vmstat-v5 lowercost-v5
User          746.94      774.56      802.00
System      65336.22    32847.27    40852.33
Elapsed     27553.52    27415.04    27368.46

However it is worth noting that the overall benchmark still completed
faster and intuitively it makes sense to take as few passes as possible
through the zonelists.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: page_alloc: abort fair zone allocation policy when remotes nodes are encountered
Mel Gorman [Wed, 6 Aug 2014 23:07:20 +0000 (16:07 -0700)]
mm: page_alloc: abort fair zone allocation policy when remotes nodes are encountered

The purpose of numa_zonelist_order=zone is to preserve lower zones for
use with 32-bit devices.  If locality is preferred then the
numa_zonelist_order=node policy should be used.

Unfortunately, the fair zone allocation policy overrides this by
skipping zones on remote nodes until the lower one is found.  While this
makes sense from a page aging and performance perspective, it breaks the
expected zonelist policy.  This patch restores the expected behaviour
for zone-list ordering.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: vmscan: only update per-cpu thresholds for online CPU
Mel Gorman [Wed, 6 Aug 2014 23:07:18 +0000 (16:07 -0700)]
mm: vmscan: only update per-cpu thresholds for online CPU

When kswapd is awake reclaiming, the per-cpu stat thresholds are lowered
to get more accurate counts to avoid breaching watermarks.  This
threshold update iterates over all possible CPUs which is unnecessary.
Only online CPUs need to be updated.  If a new CPU is onlined,
refresh_zone_stat_thresholds() will set the thresholds correctly.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: move zone->pages_scanned into a vmstat counter
Mel Gorman [Wed, 6 Aug 2014 23:07:16 +0000 (16:07 -0700)]
mm: move zone->pages_scanned into a vmstat counter

zone->pages_scanned is a write-intensive cache line during page reclaim
and it's also updated during page free.  Move the counter into vmstat to
take advantage of the per-cpu updates and do not update it in the free
paths unless necessary.

On a small UMA machine running tiobench the difference is marginal.  On
a 4-node machine the overhead is more noticable.  Note that automatic
NUMA balancing was disabled for this test as otherwise the system CPU
overhead is unpredictable.

          3.16.0-rc3  3.16.0-rc3  3.16.0-rc3
             vanillarearrange-v5   vmstat-v5
User          746.94      759.78      774.56
System      65336.22    58350.98    32847.27
Elapsed     27553.52    27282.02    27415.04

Note that the overhead reduction will vary depending on where exactly
pages are allocated and freed.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: rearrange zone fields into read-only, page alloc, statistics and page reclaim...
Mel Gorman [Wed, 6 Aug 2014 23:07:14 +0000 (16:07 -0700)]
mm: rearrange zone fields into read-only, page alloc, statistics and page reclaim lines

The arrangement of struct zone has changed over time and now it has
reached the point where there is some inappropriate sharing going on.
On x86-64 for example

o The zone->node field is shared with the zone lock and zone->node is
  accessed frequently from the page allocator due to the fair zone
  allocation policy.

o span_seqlock is almost never used by shares a line with free_area

o Some zone statistics share a cache line with the LRU lock so
  reclaim-intensive and allocator-intensive workloads can bounce the cache
  line on a stat update

This patch rearranges struct zone to put read-only and read-mostly
fields together and then splits the page allocator intensive fields, the
zone statistics and the page reclaim intensive fields into their own
cache lines.  Note that the type of lowmem_reserve changes due to the
watermark calculations being signed and avoiding a signed/unsigned
conversion there.

On the test configuration I used the overall size of struct zone shrunk
by one cache line.  On smaller machines, this is not likely to be
noticable.  However, on a 4-node NUMA machine running tiobench the
system CPU overhead is reduced by this patch.

          3.16.0-rc3  3.16.0-rc3
             vanillarearrange-v5r9
User          746.94      759.78
System      65336.22    58350.98
Elapsed     27553.52    27282.02

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: pagemap: avoid unnecessary overhead when tracepoints are deactivated
Mel Gorman [Wed, 6 Aug 2014 23:07:11 +0000 (16:07 -0700)]
mm: pagemap: avoid unnecessary overhead when tracepoints are deactivated

This was formerly the series "Improve sequential read throughput" which
noted some major differences in performance of tiobench since 3.0.
While there are a number of factors, two that dominated were the
introduction of the fair zone allocation policy and changes to CFQ.

The behaviour of fair zone allocation policy makes more sense than
tiobench as a benchmark and CFQ defaults were not changed due to
insufficient benchmarking.

This series is what's left.  It's one functional fix to the fair zone
allocation policy when used on NUMA machines and a reduction of overhead
in general.  tiobench was used for the comparison despite its flaws as
an IO benchmark as in this case we are primarily interested in the
overhead of page allocator and page reclaim activity.

On UMA, it makes little difference to overhead

          3.16.0-rc3   3.16.0-rc3
             vanilla lowercost-v5
User          383.61      386.77
System        403.83      401.74
Elapsed      5411.50     5413.11

On a 4-socket NUMA machine it's a bit more noticable

          3.16.0-rc3   3.16.0-rc3
             vanilla lowercost-v5
User          746.94      802.00
System      65336.22    40852.33
Elapsed     27553.52    27368.46

This patch (of 6):

The LRU insertion and activate tracepoints take PFN as a parameter
forcing the overhead to the caller.  Move the overhead to the tracepoint
fast-assign method to ensure the cost is only incurred when the
tracepoint is active.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: trace-vmscan-postprocess.pl: report the number of file/anon pages respectively
Chen Yucong [Wed, 6 Aug 2014 23:07:09 +0000 (16:07 -0700)]
mm: trace-vmscan-postprocess.pl: report the number of file/anon pages respectively

Until now, the reporting from trace-vmscan-postprocess.pl is not very
useful because we cannot directly use this script for checking the
file/anon ratio of scanning.  This patch aims to report respectively the
number of file/anon pages which were scanned/reclaimed by kswapd or
direct-reclaim.  Sample output is usually something like the following.

Summary
Direct reclaims:                          8823
Direct reclaim pages scanned:             2438797
Direct reclaim file pages scanned:        1315200
Direct reclaim anon pages scanned:        1123597
Direct reclaim pages reclaimed:           446139
Direct reclaim file pages reclaimed:      378668
Direct reclaim anon pages reclaimed:      67471
Direct reclaim write file sync I/O:       0
Direct reclaim write anon sync I/O:       0
Direct reclaim write file async I/O:      0
Direct reclaim write anon async I/O:      4240
Wake kswapd requests:                     122310
Time stalled direct reclaim:              13.78 seconds

Kswapd wakeups:                           25817
Kswapd pages scanned:                     170779115
Kswapd file pages scanned:                162725123
Kswapd anon pages scanned:                8053992
Kswapd pages reclaimed:                   129065738
Kswapd file pages reclaimed:              128500930
Kswapd anon pages reclaimed:              564808
Kswapd reclaim write file sync I/O:       0
Kswapd reclaim write anon sync I/O:       0
Kswapd reclaim write file async I/O:      36
Kswapd reclaim write anon async I/O:      730730
Time kswapd awake:                        1015.50 seconds

Signed-off-by: Chen Yucong <slaoub@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: update the description for vm_total_pages
Wang Sheng-Hui [Wed, 6 Aug 2014 23:07:07 +0000 (16:07 -0700)]
mm: update the description for vm_total_pages

vm_total_pages is calculated by nr_free_pagecache_pages(), which counts
the number of pages which are beyond the high watermark within all
zones.  So vm_total_pages is not equal to total number of pages which
the VM controls.

Signed-off-by: Wang Sheng-Hui <shhuiw@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm/memory.c: don't forget to set softdirty on file mapped fault
Cyrill Gorcunov [Wed, 6 Aug 2014 23:07:05 +0000 (16:07 -0700)]
mm/memory.c: don't forget to set softdirty on file mapped fault

Otherwise we may not notice that pte was softdirty because
pte_mksoft_dirty helper _returns_ new pte but doesn't modify the
argument.

In case if page fault happend on dirty filemapping the newly created pte
may loose softdirty bit thus if a userspace program is tracking memory
changes with help of a memory tracker (CONFIG_MEM_SOFT_DIRTY) it might
miss modification of a memory page (which in worts case may lead to data
inconsistency).

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agodrivers/firmware/memmap.c: don't allocate firmware_map_entry of same memory range
Yasuaki Ishimatsu [Wed, 6 Aug 2014 23:07:03 +0000 (16:07 -0700)]
drivers/firmware/memmap.c: don't allocate firmware_map_entry of same memory range

When limiting memory by mem= and ACPI DSDT table has PNP0C80,
firmware_map_entrys of same memory range are allocated and memmap X
sysfses which have same memory range are created as follows:

  # cat /sys/firmware/memmap/0/*
  0x407ffffffff
  0x40000000000
  System RAM
  # cat /sys/firmware/memmap/33/*
  0x407ffffffff
  0x40000000000
  System RAM
  # cat /sys/firmware/memmap/35/*
  0x407ffffffff
  0x40000000000
  System RAM

In this case, when hot-removing memory, kernel panic occurs, showing
following call trace:

  BUG: unable to handle kernel paging request at 00000001003e000b
  IP: sysfs_open_file+0x46/0x2b0
  PGD 203a89fe067 PUD 0
  Oops: 0000 [#1] SMP
  ...
  Call Trace:
    do_dentry_open+0x1ef/0x2a0
    finish_open+0x31/0x40
    do_last+0x57c/0x1220
    path_openat+0xc2/0x4c0
    do_filp_open+0x4b/0xb0
    do_sys_open+0xf3/0x1f0
    SyS_open+0x1e/0x20
    system_call_fastpath+0x16/0x1b

The problem occurs as follows:

When calling e820_reserve_resources(), firmware_map_entrys of all e820
memory map are allocated.  And all firmware_map_entrys is added
map_entries list as follows:

map_entries
 -> +--- entry A --------+ -> ...
    | start 0x407ffffffff|
    | end   0x40000000000|
    | type  System RAM   |
    +--------------------+

After that, if ACPI DSDT table has PNP0C80 and the memory range is
limited by mem=, the PNP0C80 is hot-added.  Then firmware_map_entry of
PNP0C80 is allocated and added map_entries list as follows:

map_entries
 -> +--- entry A --------+ -> ... -> +--- entry B --------+
    | start 0x407ffffffff|           | start 0x407ffffffff|
    | end   0x40000000000|           | end   0x40000000000|
    | type  System RAM   |           | type  System RAM   |
    +--------------------+           +--------------------+

Then memmap 0 sysfs for entry B is created.

After that, firmware_memmap_init() creates memmap sysfses of all
firmware_map_entrys in map_entries list.  As a result, memmap 33 sysfs
for entry A and memmap 35 sysfs for entry B are created.  But kobject of
entry B has been used by memmap 0 sysfs.  So when creating memmap 35
sysfs, the kobject is broken.

If hot-removing memory, memmap 0 sysfs is destroyed and kobject of
memmap 0 sysfs is freed.  But the kobject can be accessed via memmap 35
sysfs.  So when open memmap 35 sysfs, kernel panic occurs.

This patch checks whether there is firmware_map_entry of same memory
range in map_entries list and don't allocate firmware_map_entry of same
memroy range.

Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Santosh Shilimkar <santosh.shilimkar@ti.com>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agodrivers/firmware/memmap.c: pass the correct argument to firmware_map_find_entry_bootmem()
Yasuaki Ishimatsu [Wed, 6 Aug 2014 23:07:00 +0000 (16:07 -0700)]
drivers/firmware/memmap.c: pass the correct argument to firmware_map_find_entry_bootmem()

firmware_map_add_hotplug() calls firmware_map_find_entry_bootmem() to
get free firmware_map_entry.  But end arguments is not correct.  So
firmware_map_find_entry_bootmem() cannot not find firmware_map_entry.

The patch passes the correct end argument to firmware_map_find_entry_bootmem().

Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: Santosh Shilimkar <santosh.shilimkar@ti.com>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm/vmalloc.c: clean up map_vm_area third argument
WANG Chao [Wed, 6 Aug 2014 23:06:58 +0000 (16:06 -0700)]
mm/vmalloc.c: clean up map_vm_area third argument

Currently map_vm_area() takes (struct page *** pages) as third argument,
and after mapping, it moves (*pages) to point to (*pages +
nr_mappped_pages).

It looks like this kind of increment is useless to its caller these
days.  The callers don't care about the increments and actually they're
trying to avoid this by passing another copy to map_vm_area().

The caller can always guarantee all the pages can be mapped into vm_area
as specified in first argument and the caller only cares about whether
map_vm_area() fails or not.

This patch cleans up the pointer movement in map_vm_area() and updates
its callers accordingly.

Signed-off-by: WANG Chao <chaowang@redhat.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm: make copy_pte_range static again
Jerome Marchand [Wed, 6 Aug 2014 23:06:56 +0000 (16:06 -0700)]
mm: make copy_pte_range static again

Commit 71e3aac0724f ("thp: transparent hugepage core") adds
copy_pte_range prototype to huge_mm.h.  I'm not sure why (or if) this
function have been used outside of memory.c, but it currently isn't.
This patch makes copy_pte_range() static again.

Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm, hugetlb: remove hugetlb_zero and hugetlb_infinity
David Rientjes [Wed, 6 Aug 2014 23:06:54 +0000 (16:06 -0700)]
mm, hugetlb: remove hugetlb_zero and hugetlb_infinity

They are unnecessary: "zero" can be used in place of "hugetlb_zero" and
passing extra2 == NULL is equivalent to infinity.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reviewed-by: Luiz Capitulino <lcapitulino@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm, hugetlb: generalize writes to nr_hugepages
David Rientjes [Wed, 6 Aug 2014 23:06:51 +0000 (16:06 -0700)]
mm, hugetlb: generalize writes to nr_hugepages

Three different interfaces alter the maximum number of hugepages for an
hstate:

 - /proc/sys/vm/nr_hugepages for global number of hugepages of the default
   hstate,

 - /sys/kernel/mm/hugepages/hugepages-X/nr_hugepages for global number of
   hugepages for a specific hstate, and

 - /sys/kernel/mm/hugepages/hugepages-X/nr_hugepages/mempolicy for number of
   hugepages for a specific hstate over the set of allowed nodes.

Generalize the code so that a single function handles all of these
writes instead of duplicating the code in two different functions.

This decreases the number of lines of code, but also reduces the size of
.text by about half a percent since set_max_huge_pages() can be inlined.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reviewed-by: Luiz Capitulino <lcapitulino@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Acked-by: Davidlohr Bueso <davidlohr@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agohwpoison: fix race with changing page during offlining
Andi Kleen [Wed, 6 Aug 2014 23:06:49 +0000 (16:06 -0700)]
hwpoison: fix race with changing page during offlining

When a hwpoison page is locked it could change state due to parallel
modifications.  The original compound page can be torn down and then
this 4k page becomes part of a differently-size compound page is is a
standalone regular page.

Check after the lock if the page is still the same compound page.

We could go back, grab the new head page and try again but it should be
quite rare, so I thought this was safest.  A retry loop would be more
difficult to test and may have more side effects.

The hwpoison code by design only tries to handle cases that are
reasonably common in workloads, as visible in page-flags.

I'm not really that concerned about handling this (likely rare case),
just not crashing on it.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm,hugetlb: simplify error handling in hugetlb_cow()
Davidlohr Bueso [Wed, 6 Aug 2014 23:06:47 +0000 (16:06 -0700)]
mm,hugetlb: simplify error handling in hugetlb_cow()

When returning from hugetlb_cow(), we always (1) put back the refcount
for each referenced page -- always 'old', and 'new' if allocation was
successful.  And (2) retake the page table lock right before returning,
as the callers expects.  This logic can be simplified and encapsulated,
as proposed in this patch.  In addition to cleaner code, we also shave a
few bytes off the instruction text:

   text    data     bss     dec     hex filename
  28399     462   41328   70189   1122d mm/hugetlb.o-baseline
  28367     462   41328   70157   1120d mm/hugetlb.o-patched

Passes libhugetlbfs testcases.

Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
10 years agomm,hugetlb: make unmap_ref_private() return void
Davidlohr Bueso [Wed, 6 Aug 2014 23:06:45 +0000 (16:06 -0700)]
mm,hugetlb: make unmap_ref_private() return void

This function always returns 1, thus no need to check return value in
hugetlb_cow().  By doing so, we can get rid of the unnecessary WARN_ON
call.  While this logic perhaps existed as a way of identifying future
unmap_ref_private() mishandling, reality is it serves no apparent
purpose.

Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>