Merge branch 'akpm' (Andrew's patch-bomb)

Merge Andrew's second set of patches: - MM - a few random fixes - a couple of RTC leftovers * emailed patches from Andrew Morton <[email protected]>: (120 commits) rtc/rtc-88pm80x: remove unneed devm_kfree rtc/rtc-88pm80x: assign ret only when rtc_register_driver fails mm: hugetlbfs: close race during teardown of hugetlbfs shared page tables tmpfs: distribute interleave better across nodes mm: remove redundant initialization mm: warn if pg_data_t isn't initialized with zero mips: zero out pg_data_t when it's allocated memcg: gix memory accounting scalability in shrink_page_list mm/sparse: remove index_init_lock mm/sparse: more checks on mem_section number mm/sparse: optimize sparse_index_alloc memcg: add mem_cgroup_from_css() helper memcg: further prevent OOM with too many dirty pages memcg: prevent OOM with too many dirty pages mm: mmu_notifier: fix freed page still mapped in secondary MMU mm: memcg: only check anon swapin page charges for swap cache mm: memcg: only check swap cache pages for repeated charging mm: memcg: split swapin charge function into private and public part mm: memcg: remove needless !mm fixup to init_mm when charging mm: memcg: remove unneeded shmem charge type ...
kishon · Aug 1, 2012 · ac694db · ac694db
2 parents a40a1d3 + 437ea90
commit ac694db
Show file tree

Hide file tree

Showing 131 changed files with 3,174 additions and 1,060 deletions.
diff --git a/Documentation/ABI/obsolete/proc-sys-vm-nr_pdflush_threads b/Documentation/ABI/obsolete/proc-sys-vm-nr_pdflush_threads
@@ -0,0 +1,5 @@
+What:		/proc/sys/vm/nr_pdflush_threads
+Date:		June 2012
+Contact:	Wanpeng Li <[email protected]>
+Description: Since pdflush is replaced by per-BDI flusher, the interface of old pdflush
+             exported in /proc/sys/vm/ should be removed.
diff --git a/Documentation/cgroups/hugetlb.txt b/Documentation/cgroups/hugetlb.txt
@@ -0,0 +1,45 @@
+HugeTLB Controller
+-------------------
+
+The HugeTLB controller allows to limit the HugeTLB usage per control group and
+enforces the controller limit during page fault. Since HugeTLB doesn't
+support page reclaim, enforcing the limit at page fault time implies that,
+the application will get SIGBUS signal if it tries to access HugeTLB pages
+beyond its limit. This requires the application to know beforehand how much
+HugeTLB pages it would require for its use.
+
+HugeTLB controller can be created by first mounting the cgroup filesystem.
+
+# mount -t cgroup -o hugetlb none /sys/fs/cgroup
+
+With the above step, the initial or the parent HugeTLB group becomes
+visible at /sys/fs/cgroup. At bootup, this group includes all the tasks in
+the system. /sys/fs/cgroup/tasks lists the tasks in this cgroup.
+
+New groups can be created under the parent group /sys/fs/cgroup.
+
+# cd /sys/fs/cgroup
+# mkdir g1
+# echo $$ > g1/tasks
+
+The above steps create a new group g1 and move the current shell
+process (bash) into it.
+
+Brief summary of control files
+
+ hugetlb.<hugepagesize>.limit_in_bytes     # set/show limit of "hugepagesize" hugetlb usage
+ hugetlb.<hugepagesize>.max_usage_in_bytes # show max "hugepagesize" hugetlb  usage recorded
+ hugetlb.<hugepagesize>.usage_in_bytes     # show current res_counter usage for "hugepagesize" hugetlb
+ hugetlb.<hugepagesize>.failcnt		   # show the number of allocation failure due to HugeTLB limit
+
+For a system supporting two hugepage size (16M and 16G) the control
+files include:
+
+hugetlb.16GB.limit_in_bytes
+hugetlb.16GB.max_usage_in_bytes
+hugetlb.16GB.usage_in_bytes
+hugetlb.16GB.failcnt
+hugetlb.16MB.limit_in_bytes
+hugetlb.16MB.max_usage_in_bytes
+hugetlb.16MB.usage_in_bytes
+hugetlb.16MB.failcnt
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
@@ -73,6 +73,8 @@ Brief summary of control files.
 
  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
+ memory.kmem.tcp.max_usage_in_bytes # show max tcp buf memory usage recorded
 
 1. History
 
@@ -187,12 +189,12 @@ the cgroup that brought it in -- this will happen on memory pressure).
 But see section 8.2: when moving a task to another cgroup, its pages may
 be recharged to the new cgroup, if move_charge_at_immigrate has been chosen.
 
-Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used.
+Exception: If CONFIG_CGROUP_CGROUP_MEMCG_SWAP is not used.
 When you do swapoff and make swapped-out pages of shmem(tmpfs) to
 be backed into memory in force, charges for pages are accounted against the
 caller of swapoff rather than the users of shmem.
 
-2.4 Swap Extension (CONFIG_CGROUP_MEM_RES_CTLR_SWAP)
+2.4 Swap Extension (CONFIG_MEMCG_SWAP)
 
 Swap Extension allows you to record charge for swap. A swapped-in page is
 charged back to original page allocator if possible.
@@ -259,7 +261,7 @@ When oom event notifier is registered, event will be delivered.
   per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
   zone->lru_lock, it has no lock of its own.
 
-2.7 Kernel Memory Extension (CONFIG_CGROUP_MEM_RES_CTLR_KMEM)
+2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM)
 
 With the Kernel memory extension, the Memory Controller is able to limit
 the amount of kernel memory used by the system. Kernel memory is fundamentally
@@ -286,8 +288,8 @@ per cgroup, instead of globally.
 
 a. Enable CONFIG_CGROUPS
 b. Enable CONFIG_RESOURCE_COUNTERS
-c. Enable CONFIG_CGROUP_MEM_RES_CTLR
-d. Enable CONFIG_CGROUP_MEM_RES_CTLR_SWAP (to use swap extension)
+c. Enable CONFIG_MEMCG
+d. Enable CONFIG_MEMCG_SWAP (to use swap extension)
 
 1. Prepare the cgroups (see cgroups.txt, Why are cgroups needed?)
 # mount -t tmpfs none /sys/fs/cgroup

diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
@@ -13,6 +13,14 @@ Who:	Jim Cromie <[email protected]>, Jason Baron <[email protected]>
 
 ---------------------------
 
+What: /proc/sys/vm/nr_pdflush_threads
+When: 2012
+Why: Since pdflush is deprecated, the interface exported in /proc/sys/vm/
+     should be removed.
+Who: Wanpeng Li <[email protected]>
+
+---------------------------
+
 What:	CONFIG_APM_CPU_IDLE, and its ability to call APM BIOS in idle
 When:	2012
 Why:	This optional sub-feature of APM is of dubious reliability,

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
@@ -206,6 +206,8 @@ prototypes:
 	int (*launder_page)(struct page *);
 	int (*is_partially_uptodate)(struct page *, read_descriptor_t *, unsigned long);
 	int (*error_remove_page)(struct address_space *, struct page *);
+	int (*swap_activate)(struct file *);
+	int (*swap_deactivate)(struct file *);
 
 locking rules:
 	All except set_page_dirty and freepage may block
@@ -229,6 +231,8 @@ migratepage:		yes (both)
 launder_page:		yes
 is_partially_uptodate:	yes
 error_remove_page:	yes
+swap_activate:		no
+swap_deactivate:	no
 
 	->write_begin(), ->write_end(), ->sync_page() and ->readpage()
 may be called from the request handler (/dev/loop).
@@ -330,6 +334,15 @@ cleaned, or an error value if not. Note that in order to prevent the page
 getting mapped back in and redirtied, it needs to be kept locked
 across the entire operation.
 
+	->swap_activate will be called with a non-zero argument on
+files backing (non block device backed) swapfiles. A return value
+of zero indicates success, in which case this file can be used for
+backing swapspace. The swapspace operations will be proxied to the
+address space operations.
+
+	->swap_deactivate() will be called in the sys_swapoff()
+path after ->swap_activate() returned success.
+
 ----------------------- file_lock_operations ------------------------------
 prototypes:
 	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);

diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
@@ -592,6 +592,8 @@ struct address_space_operations {
 	int (*migratepage) (struct page *, struct page *);
 	int (*launder_page) (struct page *);
 	int (*error_remove_page) (struct mapping *mapping, struct page *page);
+	int (*swap_activate)(struct file *);
+	int (*swap_deactivate)(struct file *);
 };
 
   writepage: called by the VM to write a dirty page to backing store.
@@ -760,6 +762,16 @@ struct address_space_operations {
 	Setting this implies you deal with pages going away under you,
 	unless you have them locked or reference counts increased.
 
+  swap_activate: Called when swapon is used on a file to allocate
+	space if necessary and pin the block lookup information in
+	memory. A return value of zero indicates success,
+	in which case this file can be used to back swapspace. The
+	swapspace operations will be proxied to this address space's
+	->swap_{out,in} methods.
+
+  swap_deactivate: Called during swapoff on files where swap_activate
+	was successful.
+
 
 The File Object
 ===============

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
@@ -42,7 +42,6 @@ Currently, these files are in /proc/sys/vm:
 - mmap_min_addr
 - nr_hugepages
 - nr_overcommit_hugepages
-- nr_pdflush_threads
 - nr_trim_pages         (only if CONFIG_MMU=n)
 - numa_zonelist_order
 - oom_dump_tasks
@@ -426,16 +425,6 @@ See Documentation/vm/hugetlbpage.txt
 
 ==============================================================
 
-nr_pdflush_threads
-
-The current number of pdflush threads.  This value is read-only.
-The value changes according to the number of dirty pages in the system.
-
-When necessary, additional pdflush threads are created, one per second, up to
-nr_pdflush_threads_max.
-
-==============================================================
-
 nr_trim_pages
 
 This is available only on NOMMU kernels.
@@ -502,9 +491,10 @@ oom_dump_tasks
 
 Enables a system-wide task dump (excluding kernel threads) to be
 produced when the kernel performs an OOM-killing and includes such
-information as pid, uid, tgid, vm size, rss, cpu, oom_adj score, and
-name.  This is helpful to determine why the OOM killer was invoked
-and to identify the rogue task that caused it.
+information as pid, uid, tgid, vm size, rss, nr_ptes, swapents,
+oom_score_adj score, and name.  This is helpful to determine why the
+OOM killer was invoked, to identify the rogue task that caused it,
+and to determine why the OOM killer chose the task it did to kill.
 
 If this is set to zero, this information is suppressed.  On very
 large systems with thousands of tasks it may not be feasible to dump
@@ -574,16 +564,24 @@ of physical RAM.  See above.
 
 page-cluster
 
-page-cluster controls the number of pages which are written to swap in
-a single attempt.  The swap I/O size.
+page-cluster controls the number of pages up to which consecutive pages
+are read in from swap in a single attempt. This is the swap counterpart
+to page cache readahead.
+The mentioned consecutivity is not in terms of virtual/physical addresses,
+but consecutive on swap space - that means they were swapped out together.
 
 It is a logarithmic value - setting it to zero means "1 page", setting
 it to 1 means "2 pages", setting it to 2 means "4 pages", etc.
+Zero disables swap readahead completely.
 
 The default value is three (eight pages at a time).  There may be some
 small benefits in tuning this to a different value if your workload is
 swap-intensive.
 
+Lower values mean lower latencies for initial faults, but at the same time
+extra faults and I/O delays for following faults if they would have been part of
+that consecutive pages readahead would have brought in.
+
 =============================================================
 
 panic_on_oom

diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
@@ -2353,7 +2353,6 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 	 */
 	insert_vm_struct(mm, vma);
 
-	mm->total_vm  += size >> PAGE_SHIFT;
 	vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file,
 							vma_pages(vma));
 	up_write(&task->mm->mmap_sem);

diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
@@ -401,6 +401,7 @@ static void __init node_mem_init(cnodeid_t node)
 	 * Allocate the node data structures on the node first.
 	 */
 	__node_data[node] = __va(slot_freepfn << PAGE_SHIFT);
+	memset(__node_data[node], 0, PAGE_SIZE);
 
 	NODE_DATA(node)->bdata = &bootmem_node_data[node];
 	NODE_DATA(node)->node_start_pfn = start_pfn;

diff --git a/arch/powerpc/configs/chroma_defconfig b/arch/powerpc/configs/chroma_defconfig
@@ -21,8 +21,8 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_NAMESPACES=y
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y

diff --git a/arch/s390/defconfig b/arch/s390/defconfig
@@ -16,7 +16,7 @@ CONFIG_CGROUPS=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEMCG=y
 CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y

diff --git a/arch/sh/configs/apsh4ad0a_defconfig b/arch/sh/configs/apsh4ad0a_defconfig
@@ -11,7 +11,7 @@ CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEMCG=y
 CONFIG_BLK_CGROUP=y
 CONFIG_NAMESPACES=y
 CONFIG_BLK_DEV_INITRD=y

diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig
@@ -18,8 +18,8 @@ CONFIG_CPUSETS=y
 # CONFIG_PROC_PID_CPUSET is not set
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y

diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig
@@ -11,7 +11,7 @@ CONFIG_CGROUP_DEBUG=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEMCG=y
 CONFIG_RELAY=y
 CONFIG_NAMESPACES=y
 CONFIG_UTS_NS=y

diff --git a/arch/sh/configs/shx3_defconfig b/arch/sh/configs/shx3_defconfig
@@ -13,7 +13,7 @@ CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEMCG=y
 CONFIG_RELAY=y
 CONFIG_NAMESPACES=y
 CONFIG_UTS_NS=y

diff --git a/arch/sh/configs/urquell_defconfig b/arch/sh/configs/urquell_defconfig
@@ -15,8 +15,8 @@ CONFIG_CPUSETS=y
 # CONFIG_PROC_PID_CPUSET is not set
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_DEV_INITRD=y

diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig
@@ -18,8 +18,8 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y

diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig
@@ -17,8 +17,8 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y

diff --git a/arch/um/defconfig b/arch/um/defconfig
@@ -155,10 +155,10 @@ CONFIG_CPUSETS=y
 CONFIG_PROC_PID_CPUSET=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
-# CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED is not set
-# CONFIG_CGROUP_MEM_RES_CTLR_KMEM is not set
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
+# CONFIG_CGROUP_MEMCG_SWAP_ENABLED is not set
+# CONFIG_CGROUP_MEMCG_KMEM is not set
 CONFIG_CGROUP_SCHED=y
 CONFIG_FAIR_GROUP_SCHED=y
 # CONFIG_CFS_BANDWIDTH is not set

diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
@@ -7,6 +7,7 @@ config ZONE_DMA
 config XTENSA
 	def_bool y
 	select HAVE_IDE
+	select GENERIC_ATOMIC64
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES

diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
@@ -196,6 +196,7 @@ config CMA
 	bool "Contiguous Memory Allocator (EXPERIMENTAL)"
 	depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK && EXPERIMENTAL
 	select MIGRATION
+	select MEMORY_ISOLATION
 	help
 	  This enables the Contiguous Memory Allocator which allows drivers
 	  to allocate big physically-contiguous blocks of memory for use with