linux-stable.git/mm/slab.c, branch linux-4.3.y

mm: slab: only move management objects off-slab for sizes larger than KMALLOC_MIN_SIZE

2016-02-19T22:28:23+00:00

commit d4322d88f5fdf92729dd40f923013414fbb2184d upstream.

On systems with a KMALLOC_MIN_SIZE of 128 (arm64, some mips and powerpc
configurations defining ARCH_DMA_MINALIGN to 128), the first
kmalloc_caches[] entry to be initialised after slab_early_init = 0 is
"kmalloc-128" with index 7.  Depending on the debug kernel configuration,
sizeof(struct kmem_cache) can be larger than 128 resulting in an
INDEX_NODE of 8.

Commit 8fc9cf420b36 ("slab: make more slab management structure off the
slab") enables off-slab management objects for sizes starting with
PAGE_SIZE >> 5 (128 bytes for a 4KB page configuration) and the creation
of the "kmalloc-128" cache would try to place the management objects
off-slab.  However, since KMALLOC_MIN_SIZE is already 128 and
freelist_size == 32 in __kmem_cache_create(), kmalloc_slab(freelist_size)
returns NULL (kmalloc_caches[7] not populated yet).  This triggers the
following bug on arm64:

  kernel BUG at /work/Linux/linux-2.6-aarch64/mm/slab.c:2283!
  Internal error: Oops - BUG: 0 [#1] SMP
  Modules linked in:
  CPU: 0 PID: 0 Comm: swapper Not tainted 4.3.0-rc4+ #540
  Hardware name: Juno (DT)
  PC is at __kmem_cache_create+0x21c/0x280
  LR is at __kmem_cache_create+0x210/0x280
  [...]
  Call trace:
    __kmem_cache_create+0x21c/0x280
    create_boot_cache+0x48/0x80
    create_kmalloc_cache+0x50/0x88
    create_kmalloc_caches+0x4c/0xf4
    kmem_cache_init+0x100/0x118
    start_kernel+0x214/0x33c

This patch introduces an OFF_SLAB_MIN_SIZE definition to avoid off-slab
management objects for sizes equal to or smaller than KMALLOC_MIN_SIZE.

Fixes: 8fc9cf420b36 ("slab: make more slab management structure off the slab")
Signed-off-by: Catalin Marinas 
Reported-by: Geert Uytterhoeven 
Acked-by: Christoph Lameter 
Cc: Pekka Enberg 
Cc: David Rientjes 
Cc: Joonsoo Kim 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

mm/slab: fix unexpected index mapping result of kmalloc_size(INDEX_NODE+1)

2015-10-02T01:42:35+00:00

Commit description is copied from the original post of this bug:

  http://comments.gmane.org/gmane.linux.kernel.mm/135349

Kernels after v3.9 use kmalloc_size(INDEX_NODE + 1) to get the next
larger cache size than the size index INDEX_NODE mapping.  In kernels
3.9 and earlier we used malloc_sizes[INDEX_L3 + 1].cs_size.

However, sometimes we can't get the right output we expected via
kmalloc_size(INDEX_NODE + 1), causing a BUG().

The mapping table in the latest kernel is like:
    index = {0,   1,  2 ,  3,  4,   5,   6,   n}
     size = {0,   96, 192, 8, 16,  32,  64,   2^n}
The mapping table before 3.10 is like this:
    index = {0 , 1 , 2,   3,  4 ,  5 ,  6,   n}
    size  = {32, 64, 96, 128, 192, 256, 512, 2^(n+3)}

The problem on my mips64 machine is as follows:

(1) When configured DEBUG_SLAB && DEBUG_PAGEALLOC && DEBUG_LOCK_ALLOC
    && DEBUG_SPINLOCK, the sizeof(struct kmem_cache_node) will be "150",
    and the macro INDEX_NODE turns out to be "2": #define INDEX_NODE
    kmalloc_index(sizeof(struct kmem_cache_node))

(2) Then the result of kmalloc_size(INDEX_NODE + 1) is 8.

(3) Then "if(size >= kmalloc_size(INDEX_NODE + 1)" will lead to "size
    = PAGE_SIZE".

(4) Then "if ((size >= (PAGE_SIZE >> 3))" test will be satisfied and
    "flags |= CFLGS_OFF_SLAB" will be covered.

(5) if (flags & CFLGS_OFF_SLAB)" test will be satisfied and will go to
    "cachep->slabp_cache = kmalloc_slab(slab_size, 0u)", and the result
    here may be NULL while kernel bootup.

(6) Finally,"BUG_ON(ZERO_OR_NULL_PTR(cachep->slabp_cache));" causes the
    BUG info as the following shows (may be only mips64 has this problem):

This patch fixes the problem of kmalloc_size(INDEX_NODE + 1) and removes
the BUG by adding 'size >= 256' check to guarantee that all necessary
small sized slabs are initialized regardless sequence of slab size in
mapping table.

Fixes: e33660165c90 ("slab: Use common kmalloc_index/kmalloc_size...")
Signed-off-by: Joonsoo Kim 
Reported-by: Liuhailong 
Acked-by: Christoph Lameter 
Cc: Pekka Enberg 
Cc: David Rientjes 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: rename alloc_pages_exact_node() to __alloc_pages_node()

2015-09-08T22:35:28+00:00

alloc_pages_exact_node() was introduced in commit 6484eb3e2a81 ("page
allocator: do not check NUMA node ID when the caller knows the node is
valid") as an optimized variant of alloc_pages_node(), that doesn't
fallback to current node for nid == NUMA_NO_NODE.  Unfortunately the
name of the function can easily suggest that the allocation is
restricted to the given node and fails otherwise.  In truth, the node is
only preferred, unless __GFP_THISNODE is passed among the gfp flags.

The misleading name has lead to mistakes in the past, see for example
commits 5265047ac301 ("mm, thp: really limit transparent hugepage
allocation to local node") and b360edb43f8e ("mm, mempolicy:
migrate_to_node should only migrate to node").

Another issue with the name is that there's a family of
alloc_pages_exact*() functions where 'exact' means exact size (instead
of page order), which leads to more confusion.

To prevent further mistakes, this patch effectively renames
alloc_pages_exact_node() to __alloc_pages_node() to better convey that
it's an optimized variant of alloc_pages_node() not intended for general
usage.  Both functions get described in comments.

It has been also considered to really provide a convenience function for
allocations restricted to a node, but the major opinion seems to be that
__GFP_THISNODE already provides that functionality and we shouldn't
duplicate the API needlessly.  The number of users would be small
anyway.

Existing callers of alloc_pages_exact_node() are simply converted to
call __alloc_pages_node(), with the exception of sba_alloc_coherent()
which open-codes the check for NUMA_NO_NODE, so it is converted to use
alloc_pages_node() instead.  This means it no longer performs some
VM_BUG_ON checks, and since the current check for nid in
alloc_pages_node() uses a 'nid < 0' comparison (which includes
NUMA_NO_NODE), it may hide wrong values which would be previously
exposed.

Both differences will be rectified by the next patch.

To sum up, this patch makes no functional changes, except temporarily
hiding potentially buggy callers.  Restricting the checks in
alloc_pages_node() is left for the next patch which can in turn expose
more existing buggy callers.

Signed-off-by: Vlastimil Babka 
Acked-by: Johannes Weiner 
Acked-by: Robin Holt 
Acked-by: Michal Hocko 
Acked-by: Christoph Lameter 
Acked-by: Michael Ellerman 
Cc: Mel Gorman 
Cc: David Rientjes 
Cc: Greg Thelen 
Cc: Aneesh Kumar K.V 
Cc: Pekka Enberg 
Cc: Joonsoo Kim 
Cc: Naoya Horiguchi 
Cc: Tony Luck 
Cc: Fenghua Yu 
Cc: Arnd Bergmann 
Cc: Benjamin Herrenschmidt 
Cc: Paul Mackerras 
Cc: Gleb Natapov 
Cc: Paolo Bonzini 
Cc: Thomas Gleixner 
Cc: Ingo Molnar 
Cc: "H. Peter Anvin" 
Cc: Cliff Whickman 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

slab: infrastructure for bulk object allocation and freeing

2015-09-04T23:54:41+00:00

Add the basic infrastructure for alloc/free operations on pointer arrays.
It includes a generic function in the common slab code that is used in
this infrastructure patch to create the unoptimized functionality for slab
bulk operations.

Allocators can then provide optimized allocation functions for situations
in which large numbers of objects are needed.  These optimization may
avoid taking locks repeatedly and bypass metadata creation if all objects
in slab pages can be used to provide the objects required.

Allocators can extend the skeletons provided and add their own code to the
bulk alloc and free functions.  They can keep the generic allocation and
freeing and just fall back to those if optimizations would not work (like
for example when debugging is on).

Signed-off-by: Christoph Lameter 
Signed-off-by: Jesper Dangaard Brouer 
Cc: Pekka Enberg 
Cc: David Rientjes 
Cc: Joonsoo Kim 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: make page pfmemalloc check more robust

2015-08-21T21:30:10+00:00

Commit c48a11c7ad26 ("netvm: propagate page->pfmemalloc to skb") added
checks for page->pfmemalloc to __skb_fill_page_desc():

        if (page->pfmemalloc && !page->mapping)
                skb->pfmemalloc = true;

It assumes page->mapping == NULL implies that page->pfmemalloc can be
trusted.  However, __delete_from_page_cache() can set set page->mapping
to NULL and leave page->index value alone.  Due to being in union, a
non-zero page->index will be interpreted as true page->pfmemalloc.

So the assumption is invalid if the networking code can see such a page.
And it seems it can.  We have encountered this with a NFS over loopback
setup when such a page is attached to a new skbuf.  There is no copying
going on in this case so the page confuses __skb_fill_page_desc which
interprets the index as pfmemalloc flag and the network stack drops
packets that have been allocated using the reserves unless they are to
be queued on sockets handling the swapping which is the case here and
that leads to hangs when the nfs client waits for a response from the
server which has been dropped and thus never arrive.

The struct page is already heavily packed so rather than finding another
hole to put it in, let's do a trick instead.  We can reuse the index
again but define it to an impossible value (-1UL).  This is the page
index so it should never see the value that large.  Replace all direct
users of page->pfmemalloc by page_is_pfmemalloc which will hide this
nastiness from unspoiled eyes.

The information will get lost if somebody wants to use page->index
obviously but that was the case before and the original code expected
that the information should be persisted somewhere else if that is
really needed (e.g.  what SLAB and SLUB do).

[akpm@linux-foundation.org: fix blooper in slub]
Fixes: c48a11c7ad26 ("netvm: propagate page->pfmemalloc to skb")
Signed-off-by: Michal Hocko 
Debugged-by: Vlastimil Babka 
Debugged-by: Jiri Bohac 
Cc: Eric Dumazet 
Cc: David Miller 
Acked-by: Mel Gorman 
Cc: 	[3.6+]
Signed-off-by: Andrew Morton 

Signed-off-by: Linus Torvalds

slab: correct size_index table before replacing the bootstrap kmem_cache_node

2015-06-25T00:49:41+00:00

This patch moves the initialization of the size_index table slightly
earlier so that the first few kmem_cache_node's can be safely allocated
when KMALLOC_MIN_SIZE is large.

There are currently two ways to generate indices into kmalloc_caches (via
kmalloc_index() and via the size_index table in slab_common.c) and on some
arches (possibly only MIPS) they potentially disagree with each other
until create_kmalloc_caches() has been called.  It seems that the
intention is that the size_index table is a fast equivalent to
kmalloc_index() and that create_kmalloc_caches() patches the table to
return the correct value for the cases where kmalloc_index()'s
if-statements apply.

The failing sequence was:
* kmalloc_caches contains NULL elements
* kmem_cache_init initialises the element that 'struct
  kmem_cache_node' will be allocated to. For 32-bit Mips, this is a
  56-byte struct and kmalloc_index returns KMALLOC_SHIFT_LOW (7).
* init_list is called which calls kmalloc_node to allocate a 'struct
  kmem_cache_node'.
* kmalloc_slab selects the kmem_caches element using
  size_index[size_index_elem(size)]. For MIPS, size is 56, and the
  expression returns 6.
* This element of kmalloc_caches is NULL and allocation fails.
* If it had not already failed, it would have called
  create_kmalloc_caches() at this point which would have changed
  size_index[size_index_elem(size)] to 7.

I don't believe the bug to be LLVM specific but GCC doesn't normally
encounter the problem.  I haven't been able to identify exactly what GCC
is doing better (probably inlining) but it seems that GCC is managing to
optimize to the point that it eliminates the problematic allocations.
This theory is supported by the fact that GCC can be made to fail in the
same way by changing inline, __inline, __inline__, and __always_inline in
include/linux/compiler-gcc.h such that they don't actually inline things.

Signed-off-by: Daniel Sanders 
Acked-by: Pekka Enberg 
Acked-by: Christoph Lameter 
Cc: Pekka Enberg 
Cc: David Rientjes 
Cc: Joonsoo Kim 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: remove GFP_THISNODE

2015-04-14T23:49:03+00:00

NOTE: this is not about __GFP_THISNODE, this is only about GFP_THISNODE.

GFP_THISNODE is a secret combination of gfp bits that have different
behavior than expected.  It is a combination of __GFP_THISNODE,
__GFP_NORETRY, and __GFP_NOWARN and is special-cased in the page
allocator slowpath to fail without trying reclaim even though it may be
used in combination with __GFP_WAIT.

An example of the problem this creates: commit e97ca8e5b864 ("mm: fix
GFP_THISNODE callers and clarify") fixed up many users of GFP_THISNODE
that really just wanted __GFP_THISNODE.  The problem doesn't end there,
however, because even it was a no-op for alloc_misplaced_dst_page(),
which also sets __GFP_NORETRY and __GFP_NOWARN, and
migrate_misplaced_transhuge_page(), where __GFP_NORETRY and __GFP_NOWAIT
is set in GFP_TRANSHUGE.  Converting GFP_THISNODE to __GFP_THISNODE is a
no-op in these cases since the page allocator special-cases
__GFP_THISNODE && __GFP_NORETRY && __GFP_NOWARN.

It's time to just remove GFP_THISNODE entirely.  We leave __GFP_THISNODE
to restrict an allocation to a local node, but remove GFP_THISNODE and
its obscurity.  Instead, we require that a caller clear __GFP_WAIT if it
wants to avoid reclaim.

This allows the aforementioned functions to actually reclaim as they
should.  It also enables any future callers that want to do
__GFP_THISNODE but also __GFP_NORETRY && __GFP_NOWARN to reclaim.  The
rule is simple: if you don't want to reclaim, then don't set __GFP_WAIT.

Aside: ovs_flow_stats_update() really wants to avoid reclaim as well, so
it is unchanged.

Signed-off-by: David Rientjes 
Acked-by: Vlastimil Babka 
Cc: Christoph Lameter 
Acked-by: Pekka Enberg 
Cc: Joonsoo Kim 
Acked-by: Johannes Weiner 
Cc: Mel Gorman 
Cc: Pravin Shelar 
Cc: Jarno Rajahalme 
Cc: Li Zefan 
Cc: Greg Thelen 
Cc: Tejun Heo 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

slub: make dead caches discard free slabs immediately

2015-02-13T02:54:10+00:00

To speed up further allocations SLUB may store empty slabs in per cpu/node
partial lists instead of freeing them immediately.  This prevents per
memcg caches destruction, because kmem caches created for a memory cgroup
are only destroyed after the last page charged to the cgroup is freed.

To fix this issue, this patch resurrects approach first proposed in [1].
It forbids SLUB to cache empty slabs after the memory cgroup that the
cache belongs to was destroyed.  It is achieved by setting kmem_cache's
cpu_partial and min_partial constants to 0 and tuning put_cpu_partial() so
that it would drop frozen empty slabs immediately if cpu_partial = 0.

The runtime overhead is minimal.  From all the hot functions, we only
touch relatively cold put_cpu_partial(): we make it call
unfreeze_partials() after freezing a slab that belongs to an offline
memory cgroup.  Since slab freezing exists to avoid moving slabs from/to a
partial list on free/alloc, and there can't be allocations from dead
caches, it shouldn't cause any overhead.  We do have to disable preemption
for put_cpu_partial() to achieve that though.

The original patch was accepted well and even merged to the mm tree.
However, I decided to withdraw it due to changes happening to the memcg
core at that time.  I had an idea of introducing per-memcg shrinkers for
kmem caches, but now, as memcg has finally settled down, I do not see it
as an option, because SLUB shrinker would be too costly to call since SLUB
does not keep free slabs on a separate list.  Besides, we currently do not
even call per-memcg shrinkers for offline memcgs.  Overall, it would
introduce much more complexity to both SLUB and memcg than this small
patch.

Regarding to SLAB, there's no problem with it, because it shrinks
per-cpu/node caches periodically.  Thanks to list_lru reparenting, we no
longer keep entries for offline cgroups in per-memcg arrays (such as
memcg_cache_params->memcg_caches), so we do not have to bother if a
per-memcg cache will be shrunk a bit later than it could be.

[1] http://thread.gmane.org/gmane.linux.kernel.mm/118649/focus=118650

Signed-off-by: Vladimir Davydov 
Cc: Christoph Lameter 
Cc: Pekka Enberg 
Cc: David Rientjes 
Cc: Joonsoo Kim 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

slab: link memcg caches of the same kind into a list

2015-02-13T02:54:09+00:00

Sometimes, we need to iterate over all memcg copies of a particular root
kmem cache.  Currently, we use memcg_cache_params->memcg_caches array for
that, because it contains all existing memcg caches.

However, it's a bad practice to keep all caches, including those that
belong to offline cgroups, in this array, because it will be growing
beyond any bounds then.  I'm going to wipe away dead caches from it to
save space.  To still be able to perform iterations over all memcg caches
of the same kind, let us link them into a list.

Signed-off-by: Vladimir Davydov 
Cc: Johannes Weiner 
Cc: Michal Hocko 
Cc: Tejun Heo 
Cc: Christoph Lameter 
Cc: Pekka Enberg 
Cc: David Rientjes 
Cc: Joonsoo Kim 
Cc: Dave Chinner 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

slab: fix cpuset check in fallback_alloc

2014-12-13T20:42:53+00:00

fallback_alloc is called on kmalloc if the preferred node doesn't have
free or partial slabs and there's no pages on the node's free list
(GFP_THISNODE allocations fail).  Before invoking the reclaimer it tries
to locate a free or partial slab on other allowed nodes' lists.  While
iterating over the preferred node's zonelist it skips those zones which
hardwall cpuset check returns false for.  That means that for a task bound
to a specific node using cpusets fallback_alloc will always ignore free
slabs on other nodes and go directly to the reclaimer, which, however, may
allocate from other nodes if cpuset.mem_hardwall is unset (default).  As a
result, we may get lists of free slabs grow without bounds on other nodes,
which is bad, because inactive slabs are only evicted by cache_reap at a
very slow rate and cannot be dropped forcefully.

To reproduce the issue, run a process that will walk over a directory tree
with lots of files inside a cpuset bound to a node that constantly
experiences memory pressure.  Look at num_slabs vs active_slabs growth as
reported by /proc/slabinfo.

To avoid this we should use softwall cpuset check in fallback_alloc.

Signed-off-by: Vladimir Davydov 
Acked-by: Zefan Li 
Acked-by: Christoph Lameter 
Cc: Pekka Enberg 
Cc: David Rientjes 
Cc: Joonsoo Kim 
Cc: Tejun Heo 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds