Commit 673ab878 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'akpm' (more patches from Andrew) 

Merge patches from Andrew Morton:
 "Most of the rest of MM, plus a few dribs and drabs.

  I still have quite a few irritating patches left around: ones with
  dubious testing results, lack of review, ones which should have gone
  via maintainer trees but the maintainers are slack, etc.

  I need to be more activist in getting these things wrapped up outside
  the merge window, but they're such a PITA."

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (48 commits)
  mm/vmscan.c: avoid possible deadlock caused by too_many_isolated()
  vmscan: comment too_many_isolated()
  mm/kmemleak.c: remove obsolete simple_strtoul
  mm/memory_hotplug.c: improve comments
  mm/hugetlb: create hugetlb cgroup file in hugetlb_init
  mm/mprotect.c: coding-style cleanups
  Documentation: ABI: /sys/devices/system/node/
  slub: drop mutex before deleting sysfs entry
  memcg: add comments clarifying aspects of cache attribute propagation
  kmem: add slab-specific documentation about the kmem controller
  slub: slub-specific propagation changes
  slab: propagate tunable values
  memcg: aggregate memcg cache values in slabinfo
  memcg/sl[au]b: shrink dead caches
  memcg/sl[au]b: track all the memcg children of a kmem_cache
  memcg: destroy memcg caches
  sl[au]b: allocate objects from memcg cache
  sl[au]b: always get the cache from its page in kmem_cache_free()
  memcg: skip memcg kmem allocations in specified code regions
  memcg: infrastructure to match an allocation to the right cache
  ...
parents d7b96ca5 3cf23841

Documentation/ABI/stable/sysfs-devices-node

+95 −1
Original line number Diff line number Diff line 
What:		/sys/devices/system/node/possible

Date:		October 2002

Contact:	Linux Memory Management list <linux-mm@kvack.org>

Description:

		Nodes that could be possibly become online at some point.



What:		/sys/devices/system/node/online

Date:		October 2002

Contact:	Linux Memory Management list <linux-mm@kvack.org>

Description:

		Nodes that are online.



What:		/sys/devices/system/node/has_normal_memory

Date:		October 2002

Contact:	Linux Memory Management list <linux-mm@kvack.org>

Description:

		Nodes that have regular memory.



What:		/sys/devices/system/node/has_cpu

Date:		October 2002

Contact:	Linux Memory Management list <linux-mm@kvack.org>

Description:

		Nodes that have one or more CPUs.



What:		/sys/devices/system/node/has_high_memory

Date:		October 2002

Contact:	Linux Memory Management list <linux-mm@kvack.org>

Description:

		Nodes that have regular or high memory.

		Depends on CONFIG_HIGHMEM.



What:		/sys/devices/system/node/nodeX

Date:		October 2002

Contact:	Linux Memory Management list <linux-mm@kvack.org>

Description:

		When CONFIG_NUMA is enabled, this is a directory containing

		information on node X such as what CPUs are local to the

		node.
 
		node. Each file is detailed next.



What:		/sys/devices/system/node/nodeX/cpumap

Date:		October 2002

Contact:	Linux Memory Management list <linux-mm@kvack.org>

Description:

		The node's cpumap.



What:		/sys/devices/system/node/nodeX/cpulist

Date:		October 2002

Contact:	Linux Memory Management list <linux-mm@kvack.org>

Description:

		The CPUs associated to the node.



What:		/sys/devices/system/node/nodeX/meminfo

Date:		October 2002

Contact:	Linux Memory Management list <linux-mm@kvack.org>

Description:

		Provides information about the node's distribution and memory

		utilization. Similar to /proc/meminfo, see Documentation/filesystems/proc.txt



What:		/sys/devices/system/node/nodeX/numastat

Date:		October 2002

Contact:	Linux Memory Management list <linux-mm@kvack.org>

Description:

		The node's hit/miss statistics, in units of pages.

		See Documentation/numastat.txt



What:		/sys/devices/system/node/nodeX/distance

Date:		October 2002

Contact:	Linux Memory Management list <linux-mm@kvack.org>

Description:

		Distance between the node and all the other nodes

		in the system.



What:		/sys/devices/system/node/nodeX/vmstat

Date:		October 2002

Contact:	Linux Memory Management list <linux-mm@kvack.org>

Description:

		The node's zoned virtual memory statistics.

		This is a superset of numastat.



What:		/sys/devices/system/node/nodeX/compact

Date:		February 2010

Contact:	Mel Gorman <mel@csn.ul.ie>

Description:

		When this file is written to, all memory within that node

		will be compacted. When it completes, memory will be freed

		into blocks which have as many contiguous pages as possible



What:		/sys/devices/system/node/nodeX/scan_unevictable_pages

Date:		October 2008

Contact:	Lee Schermerhorn <lee.schermerhorn@hp.com>

Description:

		When set, it triggers scanning the node's unevictable lists

		and move any pages that have become evictable onto the respective

		zone's inactive list. See mm/vmscan.c



What:		/sys/devices/system/node/nodeX/hugepages/hugepages-<size>/

Date:		December 2009

Contact:	Lee Schermerhorn <lee.schermerhorn@hp.com>

Description:

		The node's huge page size control/query attributes.

		See Documentation/vm/hugetlbpage.txt
 
 No newline at end of file

Documentation/cgroups/memory.txt

+65 −1
Original line number Diff line number Diff line
@@ -71,6 +71,11 @@ Brief summary of control files. 
 memory.oom_control		 # set/show oom controls.

 memory.numa_stat		 # show the number of memory usage per numa node



 memory.kmem.limit_in_bytes      # set/show hard limit for kernel memory

 memory.kmem.usage_in_bytes      # show current kernel memory allocation

 memory.kmem.failcnt             # show the number of kernel memory usage hits limits

 memory.kmem.max_usage_in_bytes  # show max kernel memory usage recorded



 memory.kmem.tcp.limit_in_bytes  # set/show hard limit for tcp buf memory

 memory.kmem.tcp.usage_in_bytes  # show current tcp buf memory allocation

 memory.kmem.tcp.failcnt            # show the number of tcp buf memory usage hits limits
@@ -268,20 +273,73 @@ the amount of kernel memory used by the system. Kernel memory is fundamentally 
different than user memory, since it can't be swapped out, which makes it

possible to DoS the system by consuming too much of this precious resource.



Kernel memory won't be accounted at all until limit on a group is set. This

allows for existing setups to continue working without disruption.  The limit

cannot be set if the cgroup have children, or if there are already tasks in the

cgroup. Attempting to set the limit under those conditions will return -EBUSY.

When use_hierarchy == 1 and a group is accounted, its children will

automatically be accounted regardless of their limit value.



After a group is first limited, it will be kept being accounted until it

is removed. The memory limitation itself, can of course be removed by writing

-1 to memory.kmem.limit_in_bytes. In this case, kmem will be accounted, but not

limited.



Kernel memory limits are not imposed for the root cgroup. Usage for the root

cgroup may or may not be accounted.

cgroup may or may not be accounted. The memory used is accumulated into

memory.kmem.usage_in_bytes, or in a separate counter when it makes sense.

(currently only for tcp).

The main "kmem" counter is fed into the main counter, so kmem charges will

also be visible from the user counter.



Currently no soft limit is implemented for kernel memory. It is future work

to trigger slab reclaim when those limits are reached.



2.7.1 Current Kernel Memory resources accounted



* stack pages: every process consumes some stack pages. By accounting into

kernel memory, we prevent new processes from being created when the kernel

memory usage is too high.



* slab pages: pages allocated by the SLAB or SLUB allocator are tracked. A copy

of each kmem_cache is created everytime the cache is touched by the first time

from inside the memcg. The creation is done lazily, so some objects can still be

skipped while the cache is being created. All objects in a slab page should

belong to the same memcg. This only fails to hold when a task is migrated to a

different memcg during the page allocation by the cache.



* sockets memory pressure: some sockets protocols have memory pressure

thresholds. The Memory Controller allows them to be controlled individually

per cgroup, instead of globally.



* tcp memory pressure: sockets memory pressure for the tcp protocol.



2.7.3 Common use cases



Because the "kmem" counter is fed to the main user counter, kernel memory can

never be limited completely independently of user memory. Say "U" is the user

limit, and "K" the kernel limit. There are three possible ways limits can be

set:



    U != 0, K = unlimited:

    This is the standard memcg limitation mechanism already present before kmem

    accounting. Kernel memory is completely ignored.



    U != 0, K < U:

    Kernel memory is a subset of the user memory. This setup is useful in

    deployments where the total amount of memory per-cgroup is overcommited.

    Overcommiting kernel memory limits is definitely not recommended, since the

    box can still run out of non-reclaimable memory.

    In this case, the admin could set up K so that the sum of all groups is

    never greater than the total memory, and freely set U at the cost of his

    QoS.



    U != 0, K >= U:

    Since kmem charges will also be fed to the user counter and reclaim will be

    triggered for the cgroup for both kinds of memory. This setup gives the

    admin a unified view of memory, and it is also useful for people who just

    want to track kernel memory usage.



3. User Interface



0. Configuration
@@ -290,6 +348,7 @@ a. Enable CONFIG_CGROUPS 
b. Enable CONFIG_RESOURCE_COUNTERS

c. Enable CONFIG_MEMCG

d. Enable CONFIG_MEMCG_SWAP (to use swap extension)

d. Enable CONFIG_MEMCG_KMEM (to use kmem extension)



1. Prepare the cgroups (see cgroups.txt, Why are cgroups needed?)

# mount -t tmpfs none /sys/fs/cgroup
@@ -406,6 +465,11 @@ About use_hierarchy, see Section 6. 
  Because rmdir() moves all pages to parent, some out-of-use page caches can be

  moved to the parent. If you want to avoid that, force_empty will be useful.



  Also, note that when memory.kmem.limit_in_bytes is set the charges due to

  kernel pages will still be seen. This is not considered a failure and the

  write will still return success. In this case, it is expected that

  memory.kmem.usage_in_bytes == memory.usage_in_bytes.



  About use_hierarchy, see Section 6.



5.2 stat file

Documentation/cgroups/resource_counter.txt

+4 −3
Original line number Diff line number Diff line
@@ -83,16 +83,17 @@ to work with it. 
	res_counter->lock internally (it must be called with res_counter->lock

	held). The force parameter indicates whether we can bypass the limit.



 e. void res_counter_uncharge[_locked]

 e. u64 res_counter_uncharge[_locked]

			(struct res_counter *rc, unsigned long val)



	When a resource is released (freed) it should be de-accounted

	from the resource counter it was accounted to.  This is called

	"uncharging".

	"uncharging". The return value of this function indicate the amount

	of charges still present in the counter.



	The _locked routines imply that the res_counter->lock is taken.



 f. void res_counter_uncharge_until

 f. u64 res_counter_uncharge_until

		(struct res_counter *rc, struct res_counter *top,

		 unsinged long val)

arch/cris/include/asm/io.h

+33 −6
Original line number Diff line number Diff line
@@ -133,12 +133,39 @@ static inline void writel(unsigned int b, volatile void __iomem *addr) 
#define insb(port,addr,count) (cris_iops ? cris_iops->read_io(port,addr,1,count) : 0)

#define insw(port,addr,count) (cris_iops ? cris_iops->read_io(port,addr,2,count) : 0)

#define insl(port,addr,count) (cris_iops ? cris_iops->read_io(port,addr,4,count) : 0)

#define outb(data,port) if (cris_iops) cris_iops->write_io(port,(void*)(unsigned)data,1,1)

#define outw(data,port) if (cris_iops) cris_iops->write_io(port,(void*)(unsigned)data,2,1)

#define outl(data,port) if (cris_iops) cris_iops->write_io(port,(void*)(unsigned)data,4,1)

#define outsb(port,addr,count) if(cris_iops) cris_iops->write_io(port,(void*)addr,1,count)

#define outsw(port,addr,count) if(cris_iops) cris_iops->write_io(port,(void*)addr,2,count)

#define outsl(port,addr,count) if(cris_iops) cris_iops->write_io(port,(void*)addr,3,count)

static inline void outb(unsigned char data, unsigned int port)

{

	if (cris_iops)

		cris_iops->write_io(port, (void *) &data, 1, 1);

}

static inline void outw(unsigned short data, unsigned int port)

{

	if (cris_iops)

		cris_iops->write_io(port, (void *) &data, 2, 1);

}

static inline void outl(unsigned int data, unsigned int port)

{

	if (cris_iops)

		cris_iops->write_io(port, (void *) &data, 4, 1);

}

static inline void outsb(unsigned int port, const void *addr,

			 unsigned long count)

{

	if (cris_iops)

		cris_iops->write_io(port, (void *)addr, 1, count);

}

static inline void outsw(unsigned int port, const void *addr,

			 unsigned long count)

{

	if (cris_iops)

		cris_iops->write_io(port, (void *)addr, 2, count);

}

static inline void outsl(unsigned int port, const void *addr,

			 unsigned long count)

{

	if (cris_iops)

		cris_iops->write_io(port, (void *)addr, 4, count);

}



/*

 * Convert a physical pointer to a virtual kernel pointer for /dev/mem

arch/h8300/Kconfig

+1 −0
Original line number Diff line number Diff line
@@ -3,6 +3,7 @@ config H8300 
	default y

	select HAVE_IDE

	select HAVE_GENERIC_HARDIRQS

	select GENERIC_ATOMIC64

	select HAVE_UID16

	select ARCH_WANT_IPC_PARSE_VERSION

	select GENERIC_IRQ_SHOW

CRA Git | Maintained and supported by SUSTech CRA and CCSE