linux.git/mm, branch v3.10-rc5

arch, mm: Remove tlb_fast_mode()

2013-06-06T01:07:26+00:00

Since the introduction of preemptible mmu_gather TLB fast mode has been
broken. TLB fast mode relies on there being absolutely no concurrency;
it frees pages first and invalidates TLBs later.

However now we can get concurrency and stuff goes *bang*.

This patch removes all tlb_fast_mode() code; it was found the better
option vs trying to patch the hole by entangling tlb invalidation with
the scheduler.

Cc: Thomas Gleixner 
Cc: Russell King 
Cc: Tony Luck 
Reported-by: Max Filippov 
Signed-off-by: Peter Zijlstra 
Signed-off-by: Linus Torvalds

mm/pagewalk.c: walk_page_range should avoid VM_PFNMAP areas

2013-05-24T23:22:53+00:00

A panic can be caused by simply cat'ing /proc//smaps while an
application has a VM_PFNMAP range.  It happened in-house when a
benchmarker was trying to decipher the memory layout of his program.

/proc//smaps and similar walks through a user page table should not
be looking at VM_PFNMAP areas.

Certain tests in walk_page_range() (specifically split_huge_page_pmd())
assume that all the mapped PFN's are backed with page structures.  And
this is not usually true for VM_PFNMAP areas.  This can result in panics
on kernel page faults when attempting to address those page structures.

There are a half dozen callers of walk_page_range() that walk through a
task's entire page table (as N.  Horiguchi pointed out).  So rather than
change all of them, this patch changes just walk_page_range() to ignore
VM_PFNMAP areas.

The logic of hugetlb_vma() is moved back into walk_page_range(), as we
want to test any vma in the range.

VM_PFNMAP areas are used by:
- graphics memory manager   gpu/drm/drm_gem.c
- global reference unit     sgi-gru/grufile.c
- sgi special memory        char/mspec.c
- and probably several out-of-tree modules

[akpm@linux-foundation.org: remove now-unused hugetlb_vma() stub]
Signed-off-by: Cliff Wickman 
Reviewed-by: Naoya Horiguchi 
Cc: Mel Gorman 
Cc: Andrea Arcangeli 
Cc: Dave Hansen 
Cc: David Sterba 
Cc: Johannes Weiner 
Cc: KOSAKI Motohiro 
Cc: "Kirill A. Shutemov" 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm/memory_hotplug.c: fix printk format warnings

2013-05-24T23:22:52+00:00

Fix printk format warnings in mm/memory_hotplug.c by using "%pa":

  mm/memory_hotplug.c: warning: format '%llx' expects argument of type 'long long unsigned int', but argument 2 has type 'resource_size_t' [-Wformat]
  mm/memory_hotplug.c: warning: format '%llx' expects argument of type 'long long unsigned int', but argument 3 has type 'resource_size_t' [-Wformat]

Signed-off-by: Randy Dunlap 
Reported-by: Geert Uytterhoeven 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm/THP: use pmd_populate() to update the pmd with pgtable_t pointer

2013-05-24T23:22:51+00:00

We should not use set_pmd_at to update pmd_t with pgtable_t pointer.
set_pmd_at is used to set pmd with huge pte entries and architectures
like ppc64, clear few flags from the pte when saving a new entry.
Without this change we observe bad pte errors like below on ppc64 with
THP enabled.

  BUG: Bad page map in process ld mm=0xc000001ee39f4780 pte:7fc3f37848000001 pmd:c000001ec0000000

Signed-off-by: Aneesh Kumar K.V 
Cc: Hugh Dickins 
Cc: Benjamin Herrenschmidt 
Reviewed-by: Andrea Arcangeli 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm compaction: fix of improper cache flush in migration code

2013-05-24T23:22:51+00:00

Page 'new' during MIGRATION can't be flushed with flush_cache_page().
Using flush_cache_page(vma, addr, pfn) is justified only if the page is
already placed in process page table, and that is done right after
flush_cache_page().  But without it the arch function has no knowledge
of process PTE and does nothing.

Besides that, flush_cache_page() flushes an application cache page, but
the kernel has a different page virtual address and dirtied it.

Replace it with flush_dcache_page(new) which is the proper usage.

The old page is flushed in try_to_unmap_one() before migration.

This bug takes place in Sead3 board with M14Kc MIPS CPU without cache
aliasing (but Harvard arch - separate I and D cache) in tight memory
environment (128MB) each 1-3days on SOAK test.  It fails in cc1 during
kernel build (SIGILL, SIGBUS, SIGSEG) if CONFIG_COMPACTION is switched
ON.

Signed-off-by: Leonid Yegoshin 
Cc: Leonid Yegoshin 
Acked-by: Rik van Riel 
Cc: Michal Hocko 
Acked-by: Mel Gorman 
Cc: Ralf Baechle 
Cc: Russell King 
Cc: David Miller 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: memcg: remove incorrect VM_BUG_ON for swap cache pages in uncharge

2013-05-24T23:22:51+00:00

Commit 0c59b89c81ea ("mm: memcg: push down PageSwapCache check into
uncharge entry functions") added a VM_BUG_ON() on PageSwapCache in the
uncharge path after checking that page flag once, assuming that the
state is stable in all paths, but this is not the case and the condition
triggers in user environments.  An uncharge after the last page table
reference to the page goes away can race with reclaim adding the page to
swap cache.

Swap cache pages are usually uncharged when they are freed after
swapout, from a path that also handles swap usage accounting and memcg
lifetime management.  However, since the last page table reference is
gone and thus no references to the swap slot left, the swap slot will be
freed shortly when reclaim attempts to write the page to disk.  The
whole swap accounting is not even necessary.

So while the race condition for which this VM_BUG_ON was added is real
and actually existed all along, there are no negative effects.  Remove
the VM_BUG_ON again.

Reported-by: Heiko Carstens 
Reported-by: Lingzhu Xiang 
Signed-off-by: Johannes Weiner 
Acked-by: Hugh Dickins 
Acked-by: Michal Hocko 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: mmu_notifier: re-fix freed page still mapped in secondary MMU

2013-05-24T23:22:51+00:00

Commit 751efd8610d3 ("mmu_notifier_unregister NULL Pointer deref and
multiple ->release()") breaks the fix 3ad3d901bbcf ("mm: mmu_notifier:
fix freed page still mapped in secondary MMU").

Since hlist_for_each_entry_rcu() is changed now, we can not revert that
patch directly, so this patch reverts the commit and simply fix the bug
spotted by that patch

This bug spotted by commit 751efd8610d3 is:

    There is a race condition between mmu_notifier_unregister() and
    __mmu_notifier_release().

    Assume two tasks, one calling mmu_notifier_unregister() as a result
    of a filp_close() ->flush() callout (task A), and the other calling
    mmu_notifier_release() from an mmput() (task B).

                        A                               B
    t1                                            srcu_read_lock()
    t2            if (!hlist_unhashed())
    t3                                            srcu_read_unlock()
    t4            srcu_read_lock()
    t5                                            hlist_del_init_rcu()
    t6                                            synchronize_srcu()
    t7            srcu_read_unlock()
    t8            hlist_del_rcu()  <--- NULL pointer deref.

This can be fixed by using hlist_del_init_rcu instead of hlist_del_rcu.

The another issue spotted in the commit is "multiple ->release()
callouts", we needn't care it too much because it is really rare (e.g,
can not happen on kvm since mmu-notify is unregistered after
exit_mmap()) and the later call of multiple ->release should be fast
since all the pages have already been released by the first call.
Anyway, this issue should be fixed in a separate patch.

-stable suggestions: Any version that has commit 751efd8610d3 need to be
backported.  I find the oldest version has this commit is 3.0-stable.

[akpm@linux-foundation.org: tweak comments]
Signed-off-by: Xiao Guangrong 
Tested-by: Robin Holt 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: Fix virt_to_page() warning

2013-05-22T15:05:16+00:00

virt_to_page() is typically implemented as a macro containing a cast so
that it will accept both pointers and unsigned long without causing a
warning.

But MIPS virt_to_page() uses virt_to_phys which is a function so passing
an unsigned long will cause a warning:

    CC      mm/page_alloc.o
  mm/page_alloc.c: In function ‘free_reserved_area’:
  mm/page_alloc.c:5161:3: warning: passing argument 1 of ‘virt_to_phys’ makes pointer from integer without a cast [enabled by default]
  arch/mips/include/asm/io.h:119:100: note: expected ‘const volatile void *’ but argument is of type ‘long unsigned int’

All others users of virt_to_page() in mm/ are passing a void *.

Signed-off-by: Ralf Baechle 
Reported-by: Eunbong Song 
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: linux-mips@linux-mips.org
Signed-off-by: Linus Torvalds

shm: fix null pointer deref when userspace specifies invalid hugepage size

2013-05-09T21:22:47+00:00

Dave reported an oops triggered by trinity:

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
  IP: newseg+0x10d/0x390
  PGD cf8c1067 PUD cf8c2067 PMD 0
  Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
  CPU: 2 PID: 7636 Comm: trinity-child2 Not tainted 3.9.0+#67
  ...
  Call Trace:
    ipcget+0x182/0x380
    SyS_shmget+0x5a/0x60
    tracesys+0xdd/0xe2

This bug was introduced by commit af73e4d9506d ("hugetlbfs: fix mmap
failure in unaligned size request").

Reported-by: Dave Jones 
Cc: 
Signed-off-by: Li Zefan 
Reviewed-by: Naoya Horiguchi 
Acked-by: Rik van Riel 
Signed-off-by: Linus Torvalds

mm/slab: Fix crash during slab init

2013-05-08T22:02:33+00:00

Commit 8a965b3baa89 ("mm, slab_common: Fix bootstrap creation of kmalloc
caches") introduced a regression that caused us to crash early during
boot.  The commit was introducing ordering of slab creation, making sure
two odd-sized slabs were created after specific powers of two sizes.

But, if any of the power of two slabs were created earlier during boot,
slabs at index 1 or 2 might not get created at all.  This patch makes
sure none of the slabs get skipped.

Tony Lindgren bisected this down to the offending commit, which really
helped because bisect kept bringing me to almost but not quite this one.

Signed-off-by: Chris Mason 
Acked-by: Christoph Lameter 
Acked-by: Tony Lindgren 
Acked-by: Soren Brinkmann 
Tested-by: Tetsuo Handa 
Tested-by: Konrad Rzeszutek Wilk 
Signed-off-by: Linus Torvalds