linux-toradex.git/mm, branch v2.6.22.7

do not limit locked memory when RLIMIT_MEMLOCK is RLIM_INFINITY

2007-08-09T21:27:41+00:00

Fix a bug in mm/mlock.c on 32-bit architectures that prevents a user from
locking more than 4GB of shared memory, or allocating more than 4GB of
shared memory in hugepages, when rlim[RLIMIT_MEMLOCK] is set to
RLIM_INFINITY.

Signed-off-by: Herbert van den Bergh 
Acked-by: Chris Mason 
Signed-off-by: Andrew Morton 
Signed-off-by: Greg Kroah-Hartman

hugetlb: fix race in alloc_fresh_huge_page()

2007-08-09T21:27:40+00:00

That static `nid' index needs locking.  Without it we can end up calling
alloc_pages_node() with an illegal node ID and the kernel crashes.

Acked-by: Gurudas Pai 
Signed-off-by: Andrew Morton 
Signed-off-by: Greg Kroah-Hartman

readahead: MIN_RA_PAGES/MAX_RA_PAGES macros

2007-08-09T21:27:39+00:00

Define two convenient macros for read-ahead:
	- MAX_RA_PAGES: rounded down counterpart of VM_MAX_READAHEAD
	- MIN_RA_PAGES: rounded _up_ counterpart of VM_MIN_READAHEAD

Note that the rounded up MIN_RA_PAGES will work flawlessly with _large_
page sizes like 64k.

Signed-off-by: Fengguang Wu 
Cc: Steven Pratt 
Cc: Ram Pai 
Cc: Rusty Russell 
Signed-off-by: Andrew Morton 
Signed-off-by: Greg Kroah-Hartman

mm: double mark_page_accessed() in read_cache_page_async()

2007-07-08T17:13:21+00:00

Fix a post-2.6.21 regression.

read_cache_page_async() has two invocations of mark_page_accessed() which will
launch pages right onto the active list.

Remove the first one, keeping the latter one.  This avoids marking unwanted
pages active (in the retry loop).

Signed-off-by: Peter Zijlstra 
Acked-by: Nick Piggin 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

slub: remove useless EXPORT_SYMBOL

2007-07-06T18:45:11+00:00

kmem_cache_open is static. EXPORT_SYMBOL was leftover from some earlier
time period where kmem_cache_open was usable outside of slub.

(Fixes powerpc build error)

Signed-off-by: Chrsitoph Lameter 
Cc: Johannes Berg 
Cc: Benjamin Herrenschmidt 
Cc: Paul Mackerras 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: fixup /proc/vmstat output

2007-07-06T17:26:50+00:00

Line up the vmstat_text with zone_stat_item

enum zone_stat_item {
	/* First 128 byte cacheline (assuming 64 bit words) */
	NR_FREE_PAGES,
	NR_INACTIVE,
	NR_ACTIVE,

We current have nr_active and nr_inactive reversed.

[ "OK with patch, though using initializers canbe handy to prevent such
   things in future:

	static const char * const vmstat_text[] = {
		[NR_FREE_PAGES] = "nr_free_pages",
		..."
							 - Alexey ]

Signed-off-by: Peter Zijlstra 
Acked-by: Alexey Dobriyan 
Signed-off-by: Linus Torvalds

Fix slab redzone alignment

2007-07-05T22:54:13+00:00

Commit b46b8f19c9cd435ecac4d9d12b39d78c137ecd66 fixed a couple of bugs
by switching the redzone to 64 bits. Unfortunately, it neglected to
ensure that the _second_ redzone, after the slab object, is aligned
correctly. This caused illegal instruction faults on sparc32, which for
some reason not entirely clear to me are not trapped and fixed up.

Two things need to be done to fix this:
  - increase the object size, rounding up to alignof(long long) so
    that the second redzone can be aligned correctly.
  - If SLAB_STORE_USER is set but alignof(long long)==8, allow a
    full 64 bits of space for the user word at the end of the buffer,
    even though we may not _use_ the whole 64 bits.

This patch should be a no-op on any 64-bit architecture or any 32-bit
architecture where alignof(long long) == 4. Of the others, it's tested
on ppc32 by myself and a very similar patch was tested on sparc32 by
Mark Fortescue, who reported the new problem.

Also, fix the conditions for FORCED_DEBUG, which hadn't been adjusted to
the new sizes. Again noticed by Mark.

Signed-off-by: David Woodhouse 
Signed-off-by: Linus Torvalds

SLUB: Make lockdep happy by not calling add_partial with interrupts enabled during bootstrap

2007-07-03T20:56:13+00:00

If we move the local_irq_enable() to the end of the function then
add_partial() in early_kmem_cache_node_alloc() will be called
with interrupts disabled like during regular operations.

This makes lockdep happy.

Signed-off-by: Christoph Lameter 
Tested-by: Andre Noll 
Acked-by: Ingo Molnar 
Signed-off-by: Linus Torvalds

SLAB: remove WARN_ON_ONCE for zero sized objects for 2.6.22 release

2007-07-01T19:29:43+00:00

We agreed to remove the WARN_ON_ONCE before 2.6.22 is released.

Signed-off-by: Christoph Lameter 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: kill validate_anon_vma to avoid mapcount BUG

2007-06-28T18:34:53+00:00

validate_anon_vma gave a useful check on the integrity of the anon_vma list
when Andrea was developing obj rmap; but it was not enabled in SLES9
itself, nor in mainline, until Nick changed commented-out RMAP_DEBUG to
configurable CONFIG_DEBUG_VM in 2.6.17.  Now Petr Vandrovec reports that
its BUG_ON(mapcount > 100000) can easily crash a CONFIG_DEBUG_VM=y system.

That limit was just an arbitrary number to protect against an infinite
loop.  We could raise it to something enormous (depending on sizeof struct
vma and size of memory?); but I rather think validate_anon_vma has outlived
its usefulness, and is better just removed - which gives a magnificent
performance boost to anything like Petr's test program ;)

Of course, a very long anon_vma list is bad news for preemption latency,
and I believe there has been one recent report of such: let's not forget
that, but validate_anon_vma only makes it worse not better.

Signed-off-by: Hugh Dickins 
Cc: Petr Vandrovec 
Acked-by: Nick Piggin 
Cc: Andrea Arcangeli 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds