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
  ...

Documentation/ABI/stable/sysfs-devices-node

@@ -1,7 +1,101 @@
+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

Documentation/cgroups/memory.txt

@@ -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

@@ -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

@@ -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

@@ -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

arch/x86/platform/iris/iris.c

@@ -23,6 +23,7 @@
 
 #include <linux/moduleparam.h>
 #include <linux/module.h>
+#include <linux/platform_device.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/delay.h>
@@ -62,29 +63,75 @@ static void iris_power_off(void)
  * by reading its input port and seeing whether the read value is
  * meaningful.
  */
-static int iris_init(void)
+static int iris_probe(struct platform_device *pdev)
 {
-	unsigned char status;
-	if (force != 1) {
-		printk(KERN_ERR "The force parameter has not been set to 1 so the Iris poweroff handler will not be installed.\n");
-		return -ENODEV;
-	}
-	status = inb(IRIS_GIO_INPUT);
+	unsigned char status = inb(IRIS_GIO_INPUT);
 	if (status == IRIS_GIO_NODEV) {
-		printk(KERN_ERR "This machine does not seem to be an Iris. Power_off handler not installed.\n");
+		printk(KERN_ERR "This machine does not seem to be an Iris. "
+			"Power off handler not installed.\n");
 		return -ENODEV;
 	}
 	old_pm_power_off = pm_power_off;
 	pm_power_off = &iris_power_off;
 	printk(KERN_INFO "Iris power_off handler installed.\n");
-
 	return 0;
 }
 
-static void iris_exit(void)
+static int iris_remove(struct platform_device *pdev)
 {
 	pm_power_off = old_pm_power_off;
 	printk(KERN_INFO "Iris power_off handler uninstalled.\n");
+	return 0;
+}
+
+static struct platform_driver iris_driver = {
+	.driver		= {
+		.name   = "iris",
+		.owner  = THIS_MODULE,
+	},
+	.probe          = iris_probe,
+	.remove         = iris_remove,
+};
+
+static struct resource iris_resources[] = {
+	{
+		.start  = IRIS_GIO_BASE,
+		.end    = IRIS_GIO_OUTPUT,
+		.flags  = IORESOURCE_IO,
+		.name   = "address"
+	}
+};
+
+static struct platform_device *iris_device;
+
+static int iris_init(void)
+{
+	int ret;
+	if (force != 1) {
+		printk(KERN_ERR "The force parameter has not been set to 1."
+			" The Iris poweroff handler will not be installed.\n");
+		return -ENODEV;
+	}
+	ret = platform_driver_register(&iris_driver);
+	if (ret < 0) {
+		printk(KERN_ERR "Failed to register iris platform driver: %d\n",
+			ret);
+		return ret;
+	}
+	iris_device = platform_device_register_simple("iris", (-1),
+				iris_resources, ARRAY_SIZE(iris_resources));
+	if (IS_ERR(iris_device)) {
+		printk(KERN_ERR "Failed to register iris platform device\n");
+		platform_driver_unregister(&iris_driver);
+		return PTR_ERR(iris_device);
+	}
+	return 0;
+}
+
+static void iris_exit(void)
+{
+	platform_device_unregister(iris_device);
+	platform_driver_unregister(&iris_driver);
 }
 
 module_init(iris_init);

drivers/message/fusion/mptscsih.c

@@ -792,6 +792,7 @@ mptscsih_io_done(MPT_ADAPTER *ioc, MPT_FRAME_HDR *mf, MPT_FRAME_HDR *mr)
 			 * than an unsolicited DID_ABORT.
 			 */
 			sc->result = DID_RESET << 16;
+			break;
 
 		case MPI_IOCSTATUS_SCSI_EXT_TERMINATED:		/* 0x004C */
 			if (ioc->bus_type == FC)

drivers/video/backlight/locomolcd.c

@@ -107,7 +107,6 @@ void locomolcd_power(int on)
 }
 EXPORT_SYMBOL(locomolcd_power);
 
-
 static int current_intensity;
 
 static int locomolcd_set_intensity(struct backlight_device *bd)
@@ -122,13 +121,25 @@ static int locomolcd_set_intensity(struct backlight_device *bd)
 		intensity = 0;
 
 	switch (intensity) {
-	/* AC and non-AC are handled differently, but produce same results in sharp code? */
-	case 0: locomo_frontlight_set(locomolcd_dev, 0, 0, 161); break;
-	case 1: locomo_frontlight_set(locomolcd_dev, 117, 0, 161); break;
-	case 2: locomo_frontlight_set(locomolcd_dev, 163, 0, 148); break;
-	case 3: locomo_frontlight_set(locomolcd_dev, 194, 0, 161); break;
-	case 4: locomo_frontlight_set(locomolcd_dev, 194, 1, 161); break;
-
+	/*
+	 * AC and non-AC are handled differently,
+	 * but produce same results in sharp code?
+	 */
+	case 0:
+		locomo_frontlight_set(locomolcd_dev, 0, 0, 161);
+		break;
+	case 1:
+		locomo_frontlight_set(locomolcd_dev, 117, 0, 161);
+		break;
+	case 2:
+		locomo_frontlight_set(locomolcd_dev, 163, 0, 148);
+		break;
+	case 3:
+		locomo_frontlight_set(locomolcd_dev, 194, 0, 161);
+		break;
+	case 4:
+		locomo_frontlight_set(locomolcd_dev, 194, 1, 161);
+		break;
 	default:
 		return -ENODEV;
 	}
@@ -175,9 +186,11 @@ static int locomolcd_probe(struct locomo_dev *ldev)
 
 	locomo_gpio_set_dir(ldev->dev.parent, LOCOMO_GPIO_FL_VR, 0);
 
-	/* the poodle_lcd_power function is called for the first time
+	/*
+	 * the poodle_lcd_power function is called for the first time
 	 * from fs_initcall, which is before locomo is activated.
-	 * We need to recall poodle_lcd_power here*/
+	 * We need to recall poodle_lcd_power here
+	 */
 	if (machine_is_poodle())
 		locomolcd_power(1);
 
@@ -190,8 +203,8 @@ static int locomolcd_probe(struct locomo_dev *ldev)
 							&ldev->dev, NULL,
 							&locomobl_data, &props);
 
-	if (IS_ERR (locomolcd_bl_device))
-		return PTR_ERR (locomolcd_bl_device);
+	if (IS_ERR(locomolcd_bl_device))
+		return PTR_ERR(locomolcd_bl_device);
 
 	/* Set up frontlight so that screen is readable */
 	locomolcd_bl_device->props.brightness = 2;
@@ -226,7 +239,6 @@ static struct locomo_driver poodle_lcd_driver = {
 	.resume = locomolcd_resume,
 };
 
-
 static int __init locomolcd_init(void)
 {
 	return locomo_driver_register(&poodle_lcd_driver);

fs/ceph/export.c

@@ -56,13 +56,15 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len,
 	struct ceph_nfs_confh *cfh = (void *)rawfh;
 	int connected_handle_length = sizeof(*cfh)/4;
 	int handle_length = sizeof(*fh)/4;
-	struct dentry *dentry = d_find_alias(inode);
+	struct dentry *dentry;
 	struct dentry *parent;
 
 	/* don't re-export snaps */
 	if (ceph_snap(inode) != CEPH_NOSNAP)
 		return -EINVAL;
 
+	dentry = d_find_alias(inode);
+
 	/* if we found an alias, generate a connectable fh */
 	if (*max_len >= connected_handle_length && dentry) {
 		dout("encode_fh %p connectable\n", dentry);

include/linux/gfp.h

@@ -30,6 +30,7 @@ struct vm_area_struct;
 #define ___GFP_HARDWALL		0x20000u
 #define ___GFP_THISNODE		0x40000u
 #define ___GFP_RECLAIMABLE	0x80000u
+#define ___GFP_KMEMCG		0x100000u
 #define ___GFP_NOTRACK		0x200000u
 #define ___GFP_NO_KSWAPD	0x400000u
 #define ___GFP_OTHER_NODE	0x800000u
@@ -89,6 +90,7 @@ struct vm_area_struct;
 
 #define __GFP_NO_KSWAPD	((__force gfp_t)___GFP_NO_KSWAPD)
 #define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
+#define __GFP_KMEMCG	((__force gfp_t)___GFP_KMEMCG) /* Allocation comes from a memcg-accounted resource */
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)	/* Allocator intends to dirty page */
 
 /*
@@ -365,6 +367,9 @@ extern void free_pages(unsigned long addr, unsigned int order);
 extern void free_hot_cold_page(struct page *page, int cold);
 extern void free_hot_cold_page_list(struct list_head *list, int cold);
 
+extern void __free_memcg_kmem_pages(struct page *page, unsigned int order);
+extern void free_memcg_kmem_pages(unsigned long addr, unsigned int order);
+
 #define __free_page(page) __free_pages((page), 0)
 #define free_page(addr) free_pages((addr), 0)
 

include/linux/hugetlb_cgroup.h

@@ -62,7 +62,7 @@ extern void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
 					 struct page *page);
 extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
 					   struct hugetlb_cgroup *h_cg);
-extern int hugetlb_cgroup_file_init(int idx) __init;
+extern void hugetlb_cgroup_file_init(void) __init;
 extern void hugetlb_cgroup_migrate(struct page *oldhpage,
 				   struct page *newhpage);
 
@@ -111,9 +111,8 @@ hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
 	return;
 }
 
-static inline int __init hugetlb_cgroup_file_init(int idx)
+static inline void hugetlb_cgroup_file_init(void)
 {
-	return 0;
 }
 
 static inline void hugetlb_cgroup_migrate(struct page *oldhpage,

include/linux/memcontrol.h

@@ -21,11 +21,14 @@
 #define _LINUX_MEMCONTROL_H
 #include <linux/cgroup.h>
 #include <linux/vm_event_item.h>
+#include <linux/hardirq.h>
+#include <linux/jump_label.h>
 
 struct mem_cgroup;
 struct page_cgroup;
 struct page;
 struct mm_struct;
+struct kmem_cache;
 
 /* Stats that can be updated by kernel. */
 enum mem_cgroup_page_stat_item {
@@ -414,5 +417,211 @@ static inline void sock_release_memcg(struct sock *sk)
 {
 }
 #endif /* CONFIG_INET && CONFIG_MEMCG_KMEM */
+
+#ifdef CONFIG_MEMCG_KMEM
+extern struct static_key memcg_kmem_enabled_key;
+
+extern int memcg_limited_groups_array_size;
+
+/*
+ * Helper macro to loop through all memcg-specific caches. Callers must still
+ * check if the cache is valid (it is either valid or NULL).
+ * the slab_mutex must be held when looping through those caches
+ */
+#define for_each_memcg_cache_index(_idx)	\
+	for ((_idx) = 0; i < memcg_limited_groups_array_size; (_idx)++)
+
+static inline bool memcg_kmem_enabled(void)
+{
+	return static_key_false(&memcg_kmem_enabled_key);
+}
+
+/*
+ * In general, we'll do everything in our power to not incur in any overhead
+ * for non-memcg users for the kmem functions. Not even a function call, if we
+ * can avoid it.
+ *
+ * Therefore, we'll inline all those functions so that in the best case, we'll
+ * see that kmemcg is off for everybody and proceed quickly.  If it is on,
+ * we'll still do most of the flag checking inline. We check a lot of
+ * conditions, but because they are pretty simple, they are expected to be
+ * fast.
+ */
+bool __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg,
+					int order);
+void __memcg_kmem_commit_charge(struct page *page,
+				       struct mem_cgroup *memcg, int order);
+void __memcg_kmem_uncharge_pages(struct page *page, int order);
+
+int memcg_cache_id(struct mem_cgroup *memcg);
+int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
+			 struct kmem_cache *root_cache);
+void memcg_release_cache(struct kmem_cache *cachep);
+void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep);
+
+int memcg_update_cache_size(struct kmem_cache *s, int num_groups);
+void memcg_update_array_size(int num_groups);
+
+struct kmem_cache *
+__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
+
+void mem_cgroup_destroy_cache(struct kmem_cache *cachep);
+void kmem_cache_destroy_memcg_children(struct kmem_cache *s);
+
+/**
+ * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
+ * @gfp: the gfp allocation flags.
+ * @memcg: a pointer to the memcg this was charged against.
+ * @order: allocation order.
+ *
+ * returns true if the memcg where the current task belongs can hold this
+ * allocation.
+ *
+ * We return true automatically if this allocation is not to be accounted to
+ * any memcg.
+ */
+static inline bool
+memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
+{
+	if (!memcg_kmem_enabled())
+		return true;
+
+	/*
+	 * __GFP_NOFAIL allocations will move on even if charging is not
+	 * possible. Therefore we don't even try, and have this allocation
+	 * unaccounted. We could in theory charge it with
+	 * res_counter_charge_nofail, but we hope those allocations are rare,
+	 * and won't be worth the trouble.
+	 */
+	if (!(gfp & __GFP_KMEMCG) || (gfp & __GFP_NOFAIL))
+		return true;
+	if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
+		return true;
+
+	/* If the test is dying, just let it go. */
+	if (unlikely(fatal_signal_pending(current)))
+		return true;
+
+	return __memcg_kmem_newpage_charge(gfp, memcg, order);
+}
+
+/**
+ * memcg_kmem_uncharge_pages: uncharge pages from memcg
+ * @page: pointer to struct page being freed
+ * @order: allocation order.
+ *
+ * there is no need to specify memcg here, since it is embedded in page_cgroup
+ */
+static inline void
+memcg_kmem_uncharge_pages(struct page *page, int order)
+{
+	if (memcg_kmem_enabled())
+		__memcg_kmem_uncharge_pages(page, order);
+}
+
+/**
+ * memcg_kmem_commit_charge: embeds correct memcg in a page
+ * @page: pointer to struct page recently allocated
+ * @memcg: the memcg structure we charged against
+ * @order: allocation order.
+ *
+ * Needs to be called after memcg_kmem_newpage_charge, regardless of success or
+ * failure of the allocation. if @page is NULL, this function will revert the
+ * charges. Otherwise, it will commit the memcg given by @memcg to the
+ * corresponding page_cgroup.
+ */
+static inline void
+memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
+{
+	if (memcg_kmem_enabled() && memcg)
+		__memcg_kmem_commit_charge(page, memcg, order);
+}
+
+/**
+ * memcg_kmem_get_cache: selects the correct per-memcg cache for allocation
+ * @cachep: the original global kmem cache
+ * @gfp: allocation flags.
+ *
+ * This function assumes that the task allocating, which determines the memcg
+ * in the page allocator, belongs to the same cgroup throughout the whole
+ * process.  Misacounting can happen if the task calls memcg_kmem_get_cache()
+ * while belonging to a cgroup, and later on changes. This is considered
+ * acceptable, and should only happen upon task migration.
+ *
+ * Before the cache is created by the memcg core, there is also a possible
+ * imbalance: the task belongs to a memcg, but the cache being allocated from
+ * is the global cache, since the child cache is not yet guaranteed to be
+ * ready. This case is also fine, since in this case the GFP_KMEMCG will not be
+ * passed and the page allocator will not attempt any cgroup accounting.
+ */
+static __always_inline struct kmem_cache *
+memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
+{
+	if (!memcg_kmem_enabled())
+		return cachep;
+	if (gfp & __GFP_NOFAIL)
+		return cachep;
+	if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
+		return cachep;
+	if (unlikely(fatal_signal_pending(current)))
+		return cachep;
+
+	return __memcg_kmem_get_cache(cachep, gfp);
+}
+#else
+#define for_each_memcg_cache_index(_idx)	\
+	for (; NULL; )
+
+static inline bool memcg_kmem_enabled(void)
+{
+	return false;
+}
+
+static inline bool
+memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
+{
+	return true;
+}
+
+static inline void memcg_kmem_uncharge_pages(struct page *page, int order)
+{
+}
+
+static inline void
+memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
+{
+}
+
+static inline int memcg_cache_id(struct mem_cgroup *memcg)
+{
+	return -1;
+}
+
+static inline int
+memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
+		     struct kmem_cache *root_cache)
+{
+	return 0;
+}
+
+static inline void memcg_release_cache(struct kmem_cache *cachep)
+{
+}
+
+static inline void memcg_cache_list_add(struct mem_cgroup *memcg,
+					struct kmem_cache *s)
+{
+}
+
+static inline struct kmem_cache *
+memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
+{
+	return cachep;
+}
+
+static inline void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */
 

include/linux/res_counter.h

@@ -125,14 +125,16 @@ int res_counter_charge_nofail(struct res_counter *counter,
  *
  * these calls check for usage underflow and show a warning on the console
  * _locked call expects the counter->lock to be taken
+ *
+ * returns the total charges still present in @counter.
  */
 
-void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val);
-void res_counter_uncharge(struct res_counter *counter, unsigned long val);
+u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val);
+u64 res_counter_uncharge(struct res_counter *counter, unsigned long val);
 
-void res_counter_uncharge_until(struct res_counter *counter,
-				struct res_counter *top,
-				unsigned long val);
+u64 res_counter_uncharge_until(struct res_counter *counter,
+			       struct res_counter *top,
+			       unsigned long val);
 /**
  * res_counter_margin - calculate chargeable space of a counter
  * @cnt: the counter

include/linux/sched.h

@@ -1597,6 +1597,7 @@ struct task_struct {
 		unsigned long nr_pages;	/* uncharged usage */
 		unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
 	} memcg_batch;
+	unsigned int memcg_kmem_skip_account;
 #endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	atomic_t ptrace_bp_refcnt;

include/linux/slab.h

@@ -11,6 +11,8 @@
 
 #include <linux/gfp.h>
 #include <linux/types.h>
+#include <linux/workqueue.h>
+
 
 /*
  * Flags to pass to kmem_cache_create().
@@ -116,6 +118,7 @@ struct kmem_cache {
 };
 #endif
 
+struct mem_cgroup;
 /*
  * struct kmem_cache related prototypes
  */
@@ -125,6 +128,9 @@ int slab_is_available(void);
 struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
 			unsigned long,
 			void (*)(void *));
+struct kmem_cache *
+kmem_cache_create_memcg(struct mem_cgroup *, const char *, size_t, size_t,
+			unsigned long, void (*)(void *), struct kmem_cache *);
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
 void kmem_cache_free(struct kmem_cache *, void *);
@@ -175,6 +181,48 @@ void kmem_cache_free(struct kmem_cache *, void *);
 #ifndef ARCH_SLAB_MINALIGN
 #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
 #endif
+/*
+ * This is the main placeholder for memcg-related information in kmem caches.
+ * struct kmem_cache will hold a pointer to it, so the memory cost while
+ * disabled is 1 pointer. The runtime cost while enabled, gets bigger than it
+ * would otherwise be if that would be bundled in kmem_cache: we'll need an
+ * extra pointer chase. But the trade off clearly lays in favor of not
+ * penalizing non-users.
+ *
+ * Both the root cache and the child caches will have it. For the root cache,
+ * this will hold a dynamically allocated array large enough to hold
+ * information about the currently limited memcgs in the system.
+ *
+ * Child caches will hold extra metadata needed for its operation. Fields are:
+ *
+ * @memcg: pointer to the memcg this cache belongs to
+ * @list: list_head for the list of all caches in this memcg
+ * @root_cache: pointer to the global, root cache, this cache was derived from
+ * @dead: set to true after the memcg dies; the cache may still be around.
+ * @nr_pages: number of pages that belongs to this cache.
+ * @destroy: worker to be called whenever we are ready, or believe we may be
+ *           ready, to destroy this cache.
+ */
+struct memcg_cache_params {
+	bool is_root_cache;
+	union {
+		struct kmem_cache *memcg_caches[0];
+		struct {
+			struct mem_cgroup *memcg;
+			struct list_head list;
+			struct kmem_cache *root_cache;
+			bool dead;
+			atomic_t nr_pages;
+			struct work_struct destroy;
+		};
+	};
+};
+
+int memcg_update_all_caches(int num_memcgs);
+
+struct seq_file;
+int cache_show(struct kmem_cache *s, struct seq_file *m);
+void print_slabinfo_header(struct seq_file *m);
 
 /*
  * Common kmalloc functions provided by all allocators

include/linux/slab_def.h

@@ -81,6 +81,9 @@ struct kmem_cache {
 	 */
 	int obj_offset;
 #endif /* CONFIG_DEBUG_SLAB */
+#ifdef CONFIG_MEMCG_KMEM
+	struct memcg_cache_params *memcg_params;
+#endif
 
 /* 6) per-cpu/per-node data, touched during every alloc/free */
 	/*

include/linux/slub_def.h

@@ -101,6 +101,10 @@ struct kmem_cache {
 #ifdef CONFIG_SYSFS
 	struct kobject kobj;	/* For sysfs */
 #endif
+#ifdef CONFIG_MEMCG_KMEM
+	struct memcg_cache_params *memcg_params;
+	int max_attr_size; /* for propagation, maximum size of a stored attr */
+#endif
 
 #ifdef CONFIG_NUMA
 	/*
@@ -222,7 +226,10 @@ void *__kmalloc(size_t size, gfp_t flags);
 static __always_inline void *
 kmalloc_order(size_t size, gfp_t flags, unsigned int order)
 {
-	void *ret = (void *) __get_free_pages(flags | __GFP_COMP, order);
+	void *ret;
+
+	flags |= (__GFP_COMP | __GFP_KMEMCG);
+	ret = (void *) __get_free_pages(flags, order);
 	kmemleak_alloc(ret, size, 1, flags);
 	return ret;
 }

include/linux/thread_info.h

@@ -61,6 +61,8 @@ extern long do_no_restart_syscall(struct restart_block *parm);
 # define THREADINFO_GFP		(GFP_KERNEL | __GFP_NOTRACK)
 #endif
 
+#define THREADINFO_GFP_ACCOUNTED (THREADINFO_GFP | __GFP_KMEMCG)
+
 /*
  * flag set/clear/test wrappers
  * - pass TIF_xxxx constants to these functions

include/trace/events/gfpflags.h

@@ -34,6 +34,7 @@
 	{(unsigned long)__GFP_HARDWALL,		"GFP_HARDWALL"},	\
 	{(unsigned long)__GFP_THISNODE,		"GFP_THISNODE"},	\
 	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\
+	{(unsigned long)__GFP_KMEMCG,		"GFP_KMEMCG"},		\
 	{(unsigned long)__GFP_MOVABLE,		"GFP_MOVABLE"},		\
 	{(unsigned long)__GFP_NOTRACK,		"GFP_NOTRACK"},		\
 	{(unsigned long)__GFP_NO_KSWAPD,	"GFP_NO_KSWAPD"},	\

init/Kconfig

@@ -882,7 +882,7 @@ config MEMCG_SWAP_ENABLED
 config MEMCG_KMEM
 	bool "Memory Resource Controller Kernel Memory accounting (EXPERIMENTAL)"
 	depends on MEMCG && EXPERIMENTAL
-	default n
+	depends on SLUB || SLAB
 	help
 	  The Kernel Memory extension for Memory Resource Controller can limit
 	  the amount of memory used by kernel objects in the system. Those are

kernel/fork.c

@@ -146,7 +146,7 @@ void __weak arch_release_thread_info(struct thread_info *ti)
 static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
 						  int node)
 {
-	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
+	struct page *page = alloc_pages_node(node, THREADINFO_GFP_ACCOUNTED,
 					     THREAD_SIZE_ORDER);
 
 	return page ? page_address(page) : NULL;
@@ -154,7 +154,7 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
 
 static inline void free_thread_info(struct thread_info *ti)
 {
-	free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
+	free_memcg_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER);
 }
 # else
 static struct kmem_cache *thread_info_cache;

kernel/irq/manage.c

@@ -818,7 +818,7 @@ static void irq_thread_dtor(struct callback_head *unused)
 	action = kthread_data(tsk);
 
 	pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
-	       tsk->comm ? tsk->comm : "", tsk->pid, action->irq);
+	       tsk->comm, tsk->pid, action->irq);
 
 
 	desc = irq_to_desc(action->irq);

kernel/res_counter.c

@@ -86,33 +86,39 @@ int res_counter_charge_nofail(struct res_counter *counter, unsigned long val,
 	return __res_counter_charge(counter, val, limit_fail_at, true);
 }
 
-void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
+u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
 {
 	if (WARN_ON(counter->usage < val))
 		val = counter->usage;
 
 	counter->usage -= val;
+	return counter->usage;
 }
 
-void res_counter_uncharge_until(struct res_counter *counter,
-				struct res_counter *top,
-				unsigned long val)
+u64 res_counter_uncharge_until(struct res_counter *counter,
+			       struct res_counter *top,
+			       unsigned long val)
 {
 	unsigned long flags;
 	struct res_counter *c;
+	u64 ret = 0;
 
 	local_irq_save(flags);
 	for (c = counter; c != top; c = c->parent) {
+		u64 r;
 		spin_lock(&c->lock);
-		res_counter_uncharge_locked(c, val);
+		r = res_counter_uncharge_locked(c, val);
+		if (c == counter)
+			ret = r;
 		spin_unlock(&c->lock);
 	}
 	local_irq_restore(flags);
+	return ret;
 }
 
-void res_counter_uncharge(struct res_counter *counter, unsigned long val)
+u64 res_counter_uncharge(struct res_counter *counter, unsigned long val)
 {
-	res_counter_uncharge_until(counter, NULL, val);
+	return res_counter_uncharge_until(counter, NULL, val);
 }
 
 static inline unsigned long long *

mm/Kconfig

@@ -149,7 +149,18 @@ config MOVABLE_NODE
 	depends on NO_BOOTMEM
 	depends on X86_64
 	depends on NUMA
-	depends on BROKEN
+	default n
+	help
+	  Allow a node to have only movable memory.  Pages used by the kernel,
+	  such as direct mapping pages cannot be migrated.  So the corresponding
+	  memory device cannot be hotplugged.  This option allows users to
+	  online all the memory of a node as movable memory so that the whole
+	  node can be hotplugged.  Users who don't use the memory hotplug
+	  feature are fine with this option on since they don't online memory
+	  as movable.
+
+	  Say Y here if you want to hotplug a whole node.
+	  Say N here if you want kernel to use memory on all nodes evenly.
 
 # eventually, we can have this option just 'select SPARSEMEM'
 config MEMORY_HOTPLUG

mm/hugetlb.c

@@ -1906,14 +1906,12 @@ static int __init hugetlb_init(void)
 		default_hstate.max_huge_pages = default_hstate_max_huge_pages;
 
 	hugetlb_init_hstates();
-
 	gather_bootmem_prealloc();
-
 	report_hugepages();
 
 	hugetlb_sysfs_init();
-
 	hugetlb_register_all_nodes();
+	hugetlb_cgroup_file_init();
 
 	return 0;
 }
@@ -1943,13 +1941,6 @@ void __init hugetlb_add_hstate(unsigned order)
 	h->next_nid_to_free = first_node(node_states[N_MEMORY]);
 	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
 					huge_page_size(h)/1024);
-	/*
-	 * Add cgroup control files only if the huge page consists
-	 * of more than two normal pages. This is because we use
-	 * page[2].lru.next for storing cgoup details.
-	 */
-	if (order >= HUGETLB_CGROUP_MIN_ORDER)
-		hugetlb_cgroup_file_init(hugetlb_max_hstate - 1);
 
 	parsed_hstate = h;
 }

mm/hugetlb_cgroup.c

@@ -333,7 +333,7 @@ static char *mem_fmt(char *buf, int size, unsigned long hsize)
 	return buf;
 }
 
-int __init hugetlb_cgroup_file_init(int idx)
+static void __init __hugetlb_cgroup_file_init(int idx)
 {
 	char buf[32];
 	struct cftype *cft;
@@ -375,7 +375,22 @@ int __init hugetlb_cgroup_file_init(int idx)
 
 	WARN_ON(cgroup_add_cftypes(&hugetlb_subsys, h->cgroup_files));
 
-	return 0;
+	return;
+}
+
+void __init hugetlb_cgroup_file_init(void)
+{
+	struct hstate *h;
+
+	for_each_hstate(h) {
+		/*
+		 * Add cgroup control files only if the huge page consists
+		 * of more than two normal pages. This is because we use
+		 * page[2].lru.next for storing cgroup details.
+		 */
+		if (huge_page_order(h) >= HUGETLB_CGROUP_MIN_ORDER)
+			__hugetlb_cgroup_file_init(hstate_index(h));
+	}
 }
 
 /*

mm/kmemleak.c

@@ -1556,7 +1556,8 @@ static int dump_str_object_info(const char *str)
 	struct kmemleak_object *object;
 	unsigned long addr;
 
-	addr= simple_strtoul(str, NULL, 0);
+	if (kstrtoul(str, 0, &addr))
+		return -EINVAL;
 	object = find_and_get_object(addr, 0);
 	if (!object) {
 		pr_info("Unknown object at 0x%08lx\n", addr);

mm/memcontrol.c

@@ -10,6 +10,10 @@
  * Copyright (C) 2009 Nokia Corporation
  * Author: Kirill A. Shutemov
  *
+ * Kernel Memory Controller
+ * Copyright (C) 2012 Parallels Inc. and Google Inc.
+ * Authors: Glauber Costa and Suleiman Souhlal
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
@@ -267,6 +271,10 @@ struct mem_cgroup {
 		struct work_struct work_freeing;
 	};
 
+	/*
+	 * the counter to account for kernel memory usage.
+	 */
+	struct res_counter kmem;
 	/*
 	 * Per cgroup active and inactive list, similar to the
 	 * per zone LRU lists.
@@ -282,6 +290,7 @@ struct mem_cgroup {
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
 	bool use_hierarchy;
+	unsigned long kmem_account_flags; /* See KMEM_ACCOUNTED_*, below */
 
 	bool		oom_lock;
 	atomic_t	under_oom;
@@ -332,8 +341,61 @@ struct mem_cgroup {
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
 	struct tcp_memcontrol tcp_mem;
 #endif
+#if defined(CONFIG_MEMCG_KMEM)
+	/* analogous to slab_common's slab_caches list. per-memcg */
+	struct list_head memcg_slab_caches;
+	/* Not a spinlock, we can take a lot of time walking the list */
+	struct mutex slab_caches_mutex;
+        /* Index in the kmem_cache->memcg_params->memcg_caches array */
+	int kmemcg_id;
+#endif
 };
 
+/* internal only representation about the status of kmem accounting. */
+enum {
+	KMEM_ACCOUNTED_ACTIVE = 0, /* accounted by this cgroup itself */
+	KMEM_ACCOUNTED_ACTIVATED, /* static key enabled. */
+	KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */
+};
+
+/* We account when limit is on, but only after call sites are patched */
+#define KMEM_ACCOUNTED_MASK \
+		((1 << KMEM_ACCOUNTED_ACTIVE) | (1 << KMEM_ACCOUNTED_ACTIVATED))
+
+#ifdef CONFIG_MEMCG_KMEM
+static inline void memcg_kmem_set_active(struct mem_cgroup *memcg)
+{
+	set_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
+}
+
+static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+{
+	return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
+}
+
+static void memcg_kmem_set_activated(struct mem_cgroup *memcg)
+{
+	set_bit(KMEM_ACCOUNTED_ACTIVATED, &memcg->kmem_account_flags);
+}
+
+static void memcg_kmem_clear_activated(struct mem_cgroup *memcg)
+{
+	clear_bit(KMEM_ACCOUNTED_ACTIVATED, &memcg->kmem_account_flags);
+}
+
+static void memcg_kmem_mark_dead(struct mem_cgroup *memcg)
+{
+	if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags))
+		set_bit(KMEM_ACCOUNTED_DEAD, &memcg->kmem_account_flags);
+}
+
+static bool memcg_kmem_test_and_clear_dead(struct mem_cgroup *memcg)
+{
+	return test_and_clear_bit(KMEM_ACCOUNTED_DEAD,
+				  &memcg->kmem_account_flags);
+}
+#endif
+
 /* Stuffs for move charges at task migration. */
 /*
  * Types of charges to be moved. "move_charge_at_immitgrate" is treated as a
@@ -388,9 +450,13 @@ enum charge_type {
 };
 
 /* for encoding cft->private value on file */
-#define _MEM			(0)
-#define _MEMSWAP		(1)
-#define _OOM_TYPE		(2)
+enum res_type {
+	_MEM,
+	_MEMSWAP,
+	_OOM_TYPE,
+	_KMEM,
+};
+
 #define MEMFILE_PRIVATE(x, val)	((x) << 16 | (val))
 #define MEMFILE_TYPE(val)	((val) >> 16 & 0xffff)
 #define MEMFILE_ATTR(val)	((val) & 0xffff)
@@ -487,6 +553,75 @@ static void disarm_sock_keys(struct mem_cgroup *memcg)
 }
 #endif
 
+#ifdef CONFIG_MEMCG_KMEM
+/*
+ * This will be the memcg's index in each cache's ->memcg_params->memcg_caches.
+ * There are two main reasons for not using the css_id for this:
+ *  1) this works better in sparse environments, where we have a lot of memcgs,
+ *     but only a few kmem-limited. Or also, if we have, for instance, 200
+ *     memcgs, and none but the 200th is kmem-limited, we'd have to have a
+ *     200 entry array for that.
+ *
+ *  2) In order not to violate the cgroup API, we would like to do all memory
+ *     allocation in ->create(). At that point, we haven't yet allocated the
+ *     css_id. Having a separate index prevents us from messing with the cgroup
+ *     core for this
+ *
+ * The current size of the caches array is stored in
+ * memcg_limited_groups_array_size.  It will double each time we have to
+ * increase it.
+ */
+static DEFINE_IDA(kmem_limited_groups);
+int memcg_limited_groups_array_size;
+
+/*
+ * MIN_SIZE is different than 1, because we would like to avoid going through
+ * the alloc/free process all the time. In a small machine, 4 kmem-limited
+ * cgroups is a reasonable guess. In the future, it could be a parameter or
+ * tunable, but that is strictly not necessary.
+ *
+ * MAX_SIZE should be as large as the number of css_ids. Ideally, we could get
+ * this constant directly from cgroup, but it is understandable that this is
+ * better kept as an internal representation in cgroup.c. In any case, the
+ * css_id space is not getting any smaller, and we don't have to necessarily
+ * increase ours as well if it increases.
+ */
+#define MEMCG_CACHES_MIN_SIZE 4
+#define MEMCG_CACHES_MAX_SIZE 65535
+
+/*
+ * A lot of the calls to the cache allocation functions are expected to be
+ * inlined by the compiler. Since the calls to memcg_kmem_get_cache are
+ * conditional to this static branch, we'll have to allow modules that does
+ * kmem_cache_alloc and the such to see this symbol as well
+ */
+struct static_key memcg_kmem_enabled_key;
+EXPORT_SYMBOL(memcg_kmem_enabled_key);
+
+static void disarm_kmem_keys(struct mem_cgroup *memcg)
+{
+	if (memcg_kmem_is_active(memcg)) {
+		static_key_slow_dec(&memcg_kmem_enabled_key);
+		ida_simple_remove(&kmem_limited_groups, memcg->kmemcg_id);
+	}
+	/*
+	 * This check can't live in kmem destruction function,
+	 * since the charges will outlive the cgroup
+	 */
+	WARN_ON(res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0);
+}
+#else
+static void disarm_kmem_keys(struct mem_cgroup *memcg)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
+static void disarm_static_keys(struct mem_cgroup *memcg)
+{
+	disarm_sock_keys(memcg);
+	disarm_kmem_keys(memcg);
+}
+
 static void drain_all_stock_async(struct mem_cgroup *memcg);
 
 static struct mem_cgroup_per_zone *
@@ -1453,6 +1588,10 @@ done:
 		res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10,
 		res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10,
 		res_counter_read_u64(&memcg->memsw, RES_FAILCNT));
+	printk(KERN_INFO "kmem: usage %llukB, limit %llukB, failcnt %llu\n",
+		res_counter_read_u64(&memcg->kmem, RES_USAGE) >> 10,
+		res_counter_read_u64(&memcg->kmem, RES_LIMIT) >> 10,
+		res_counter_read_u64(&memcg->kmem, RES_FAILCNT));
 }
 
 /*
@@ -2060,20 +2199,28 @@ struct memcg_stock_pcp {
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
 static DEFINE_MUTEX(percpu_charge_mutex);
 
-/*
- * Try to consume stocked charge on this cpu. If success, one page is consumed
- * from local stock and true is returned. If the stock is 0 or charges from a
- * cgroup which is not current target, returns false. This stock will be
- * refilled.
+/**
+ * consume_stock: Try to consume stocked charge on this cpu.
+ * @memcg: memcg to consume from.
+ * @nr_pages: how many pages to charge.
+ *
+ * The charges will only happen if @memcg matches the current cpu's memcg
+ * stock, and at least @nr_pages are available in that stock.  Failure to
+ * service an allocation will refill the stock.
+ *
+ * returns true if successful, false otherwise.
  */
-static bool consume_stock(struct mem_cgroup *memcg)
+static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	struct memcg_stock_pcp *stock;
 	bool ret = true;
 
+	if (nr_pages > CHARGE_BATCH)
+		return false;
+
 	stock = &get_cpu_var(memcg_stock);
-	if (memcg == stock->cached && stock->nr_pages)
-		stock->nr_pages--;
+	if (memcg == stock->cached && stock->nr_pages >= nr_pages)
+		stock->nr_pages -= nr_pages;
 	else /* need to call res_counter_charge */
 		ret = false;
 	put_cpu_var(memcg_stock);
@@ -2250,7 +2397,8 @@ enum {
 };
 
 static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
-				unsigned int nr_pages, bool oom_check)
+				unsigned int nr_pages, unsigned int min_pages,
+				bool oom_check)
 {
 	unsigned long csize = nr_pages * PAGE_SIZE;
 	struct mem_cgroup *mem_over_limit;
@@ -2273,18 +2421,18 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	} else
 		mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
 	/*
-	 * nr_pages can be either a huge page (HPAGE_PMD_NR), a batch
-	 * of regular pages (CHARGE_BATCH), or a single regular page (1).
-	 *
 	 * Never reclaim on behalf of optional batching, retry with a
 	 * single page instead.
 	 */
-	if (nr_pages == CHARGE_BATCH)
+	if (nr_pages > min_pages)
 		return CHARGE_RETRY;
 
 	if (!(gfp_mask & __GFP_WAIT))
 		return CHARGE_WOULDBLOCK;
 
+	if (gfp_mask & __GFP_NORETRY)
+		return CHARGE_NOMEM;
+
 	ret = mem_cgroup_reclaim(mem_over_limit, gfp_mask, flags);
 	if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
 		return CHARGE_RETRY;
@@ -2297,7 +2445,7 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	 * unlikely to succeed so close to the limit, and we fall back
 	 * to regular pages anyway in case of failure.
 	 */
-	if (nr_pages == 1 && ret)
+	if (nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER) && ret)
 		return CHARGE_RETRY;
 
 	/*
@@ -2371,7 +2519,7 @@ again:
 		memcg = *ptr;
 		if (mem_cgroup_is_root(memcg))
 			goto done;
-		if (nr_pages == 1 && consume_stock(memcg))
+		if (consume_stock(memcg, nr_pages))
 			goto done;
 		css_get(&memcg->css);
 	} else {
@@ -2396,7 +2544,7 @@ again:
 			rcu_read_unlock();
 			goto done;
 		}
-		if (nr_pages == 1 && consume_stock(memcg)) {
+		if (consume_stock(memcg, nr_pages)) {
 			/*
 			 * It seems dagerous to access memcg without css_get().
 			 * But considering how consume_stok works, it's not
@@ -2431,7 +2579,8 @@ again:
 			nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
 		}
 
-		ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, oom_check);
+		ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, nr_pages,
+		    oom_check);
 		switch (ret) {
 		case CHARGE_OK:
 			break;
@@ -2624,183 +2773,943 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	memcg_check_events(memcg, page);
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static DEFINE_MUTEX(set_limit_mutex);
+
+#ifdef CONFIG_MEMCG_KMEM
+static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg)
+{
+	return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg) &&
+		(memcg->kmem_account_flags & KMEM_ACCOUNTED_MASK);
+}
 
-#define PCGF_NOCOPY_AT_SPLIT (1 << PCG_LOCK | 1 << PCG_MIGRATION)
 /*
- * Because tail pages are not marked as "used", set it. We're under
- * zone->lru_lock, 'splitting on pmd' and compound_lock.
- * charge/uncharge will be never happen and move_account() is done under
- * compound_lock(), so we don't have to take care of races.
+ * This is a bit cumbersome, but it is rarely used and avoids a backpointer
+ * in the memcg_cache_params struct.
  */
-void mem_cgroup_split_huge_fixup(struct page *head)
+static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p)
 {
-	struct page_cgroup *head_pc = lookup_page_cgroup(head);
-	struct page_cgroup *pc;
-	int i;
+	struct kmem_cache *cachep;
 
-	if (mem_cgroup_disabled())
-		return;
-	for (i = 1; i < HPAGE_PMD_NR; i++) {
-		pc = head_pc + i;
-		pc->mem_cgroup = head_pc->mem_cgroup;
-		smp_wmb();/* see __commit_charge() */
-		pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT;
-	}
+	VM_BUG_ON(p->is_root_cache);
+	cachep = p->root_cache;
+	return cachep->memcg_params->memcg_caches[memcg_cache_id(p->memcg)];
 }
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-/**
- * mem_cgroup_move_account - move account of the page
- * @page: the page
- * @nr_pages: number of regular pages (>1 for huge pages)
- * @pc:	page_cgroup of the page.
- * @from: mem_cgroup which the page is moved from.
- * @to:	mem_cgroup which the page is moved to. @from != @to.
- *
- * The caller must confirm following.
- * - page is not on LRU (isolate_page() is useful.)
- * - compound_lock is held when nr_pages > 1
- *
- * This function doesn't do "charge" to new cgroup and doesn't do "uncharge"
- * from old cgroup.
- */
-static int mem_cgroup_move_account(struct page *page,
-				   unsigned int nr_pages,
-				   struct page_cgroup *pc,
-				   struct mem_cgroup *from,
-				   struct mem_cgroup *to)
+#ifdef CONFIG_SLABINFO
+static int mem_cgroup_slabinfo_read(struct cgroup *cont, struct cftype *cft,
+					struct seq_file *m)
 {
-	unsigned long flags;
-	int ret;
-	bool anon = PageAnon(page);
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	struct memcg_cache_params *params;
 
-	VM_BUG_ON(from == to);
-	VM_BUG_ON(PageLRU(page));
-	/*
-	 * The page is isolated from LRU. So, collapse function
-	 * will not handle this page. But page splitting can happen.
-	 * Do this check under compound_page_lock(). The caller should
-	 * hold it.
-	 */
-	ret = -EBUSY;
-	if (nr_pages > 1 && !PageTransHuge(page))
-		goto out;
+	if (!memcg_can_account_kmem(memcg))
+		return -EIO;
 
-	lock_page_cgroup(pc);
+	print_slabinfo_header(m);
 
-	ret = -EINVAL;
-	if (!PageCgroupUsed(pc) || pc->mem_cgroup != from)
-		goto unlock;
+	mutex_lock(&memcg->slab_caches_mutex);
+	list_for_each_entry(params, &memcg->memcg_slab_caches, list)
+		cache_show(memcg_params_to_cache(params), m);
+	mutex_unlock(&memcg->slab_caches_mutex);
 
-	move_lock_mem_cgroup(from, &flags);
+	return 0;
+}
+#endif
 
-	if (!anon && page_mapped(page)) {
-		/* Update mapped_file data for mem_cgroup */
-		preempt_disable();
-		__this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
-		__this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
-		preempt_enable();
-	}
-	mem_cgroup_charge_statistics(from, anon, -nr_pages);
+static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
+{
+	struct res_counter *fail_res;
+	struct mem_cgroup *_memcg;
+	int ret = 0;
+	bool may_oom;
+
+	ret = res_counter_charge(&memcg->kmem, size, &fail_res);
+	if (ret)
+		return ret;
 
-	/* caller should have done css_get */
-	pc->mem_cgroup = to;
-	mem_cgroup_charge_statistics(to, anon, nr_pages);
-	move_unlock_mem_cgroup(from, &flags);
-	ret = 0;
-unlock:
-	unlock_page_cgroup(pc);
 	/*
-	 * check events
+	 * Conditions under which we can wait for the oom_killer. Those are
+	 * the same conditions tested by the core page allocator
 	 */
-	memcg_check_events(to, page);
-	memcg_check_events(from, page);
-out:
+	may_oom = (gfp & __GFP_FS) && !(gfp & __GFP_NORETRY);
+
+	_memcg = memcg;
+	ret = __mem_cgroup_try_charge(NULL, gfp, size >> PAGE_SHIFT,
+				      &_memcg, may_oom);
+
+	if (ret == -EINTR)  {
+		/*
+		 * __mem_cgroup_try_charge() chosed to bypass to root due to
+		 * OOM kill or fatal signal.  Since our only options are to
+		 * either fail the allocation or charge it to this cgroup, do
+		 * it as a temporary condition. But we can't fail. From a
+		 * kmem/slab perspective, the cache has already been selected,
+		 * by mem_cgroup_kmem_get_cache(), so it is too late to change
+		 * our minds.
+		 *
+		 * This condition will only trigger if the task entered
+		 * memcg_charge_kmem in a sane state, but was OOM-killed during
+		 * __mem_cgroup_try_charge() above. Tasks that were already
+		 * dying when the allocation triggers should have been already
+		 * directed to the root cgroup in memcontrol.h
+		 */
+		res_counter_charge_nofail(&memcg->res, size, &fail_res);
+		if (do_swap_account)
+			res_counter_charge_nofail(&memcg->memsw, size,
+						  &fail_res);
+		ret = 0;
+	} else if (ret)
+		res_counter_uncharge(&memcg->kmem, size);
+
 	return ret;
 }
 
-/**
- * mem_cgroup_move_parent - moves page to the parent group
- * @page: the page to move
- * @pc: page_cgroup of the page
- * @child: page's cgroup
- *
- * move charges to its parent or the root cgroup if the group has no
- * parent (aka use_hierarchy==0).
- * Although this might fail (get_page_unless_zero, isolate_lru_page or
- * mem_cgroup_move_account fails) the failure is always temporary and
- * it signals a race with a page removal/uncharge or migration. In the
- * first case the page is on the way out and it will vanish from the LRU
- * on the next attempt and the call should be retried later.
- * Isolation from the LRU fails only if page has been isolated from
- * the LRU since we looked at it and that usually means either global
- * reclaim or migration going on. The page will either get back to the
- * LRU or vanish.
- * Finaly mem_cgroup_move_account fails only if the page got uncharged
- * (!PageCgroupUsed) or moved to a different group. The page will
- * disappear in the next attempt.
- */
-static int mem_cgroup_move_parent(struct page *page,
-				  struct page_cgroup *pc,
-				  struct mem_cgroup *child)
+static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size)
 {
-	struct mem_cgroup *parent;
-	unsigned int nr_pages;
-	unsigned long uninitialized_var(flags);
-	int ret;
+	res_counter_uncharge(&memcg->res, size);
+	if (do_swap_account)
+		res_counter_uncharge(&memcg->memsw, size);
 
-	VM_BUG_ON(mem_cgroup_is_root(child));
+	/* Not down to 0 */
+	if (res_counter_uncharge(&memcg->kmem, size))
+		return;
 
-	ret = -EBUSY;
-	if (!get_page_unless_zero(page))
-		goto out;
-	if (isolate_lru_page(page))
-		goto put;
+	if (memcg_kmem_test_and_clear_dead(memcg))
+		mem_cgroup_put(memcg);
+}
 
-	nr_pages = hpage_nr_pages(page);
+void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep)
+{
+	if (!memcg)
+		return;
 
-	parent = parent_mem_cgroup(child);
+	mutex_lock(&memcg->slab_caches_mutex);
+	list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches);
+	mutex_unlock(&memcg->slab_caches_mutex);
+}
+
+/*
+ * helper for acessing a memcg's index. It will be used as an index in the
+ * child cache array in kmem_cache, and also to derive its name. This function
+ * will return -1 when this is not a kmem-limited memcg.
+ */
+int memcg_cache_id(struct mem_cgroup *memcg)
+{
+	return memcg ? memcg->kmemcg_id : -1;
+}
+
+/*
+ * This ends up being protected by the set_limit mutex, during normal
+ * operation, because that is its main call site.
+ *
+ * But when we create a new cache, we can call this as well if its parent
+ * is kmem-limited. That will have to hold set_limit_mutex as well.
+ */
+int memcg_update_cache_sizes(struct mem_cgroup *memcg)
+{
+	int num, ret;
+
+	num = ida_simple_get(&kmem_limited_groups,
+				0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL);
+	if (num < 0)
+		return num;
 	/*
-	 * If no parent, move charges to root cgroup.
+	 * After this point, kmem_accounted (that we test atomically in
+	 * the beginning of this conditional), is no longer 0. This
+	 * guarantees only one process will set the following boolean
+	 * to true. We don't need test_and_set because we're protected
+	 * by the set_limit_mutex anyway.
 	 */
-	if (!parent)
-		parent = root_mem_cgroup;
+	memcg_kmem_set_activated(memcg);
 
-	if (nr_pages > 1) {
-		VM_BUG_ON(!PageTransHuge(page));
-		flags = compound_lock_irqsave(page);
+	ret = memcg_update_all_caches(num+1);
+	if (ret) {
+		ida_simple_remove(&kmem_limited_groups, num);
+		memcg_kmem_clear_activated(memcg);
+		return ret;
 	}
 
-	ret = mem_cgroup_move_account(page, nr_pages,
-				pc, child, parent);
-	if (!ret)
-		__mem_cgroup_cancel_local_charge(child, nr_pages);
+	memcg->kmemcg_id = num;
+	INIT_LIST_HEAD(&memcg->memcg_slab_caches);
+	mutex_init(&memcg->slab_caches_mutex);
+	return 0;
+}
 
-	if (nr_pages > 1)
-		compound_unlock_irqrestore(page, flags);
-	putback_lru_page(page);
-put:
-	put_page(page);
-out:
-	return ret;
+static size_t memcg_caches_array_size(int num_groups)
+{
+	ssize_t size;
+	if (num_groups <= 0)
+		return 0;
+
+	size = 2 * num_groups;
+	if (size < MEMCG_CACHES_MIN_SIZE)
+		size = MEMCG_CACHES_MIN_SIZE;
+	else if (size > MEMCG_CACHES_MAX_SIZE)
+		size = MEMCG_CACHES_MAX_SIZE;
+
+	return size;
 }
 
 /*
- * Charge the memory controller for page usage.
- * Return
- * 0 if the charge was successful
- * < 0 if the cgroup is over its limit
+ * We should update the current array size iff all caches updates succeed. This
+ * can only be done from the slab side. The slab mutex needs to be held when
+ * calling this.
  */
-static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
-				gfp_t gfp_mask, enum charge_type ctype)
+void memcg_update_array_size(int num)
 {
-	struct mem_cgroup *memcg = NULL;
-	unsigned int nr_pages = 1;
-	bool oom = true;
-	int ret;
+	if (num > memcg_limited_groups_array_size)
+		memcg_limited_groups_array_size = memcg_caches_array_size(num);
+}
 
-	if (PageTransHuge(page)) {
+int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
+{
+	struct memcg_cache_params *cur_params = s->memcg_params;
+
+	VM_BUG_ON(s->memcg_params && !s->memcg_params->is_root_cache);
+
+	if (num_groups > memcg_limited_groups_array_size) {
+		int i;
+		ssize_t size = memcg_caches_array_size(num_groups);
+
+		size *= sizeof(void *);
+		size += sizeof(struct memcg_cache_params);
+
+		s->memcg_params = kzalloc(size, GFP_KERNEL);
+		if (!s->memcg_params) {
+			s->memcg_params = cur_params;
+			return -ENOMEM;
+		}
+
+		s->memcg_params->is_root_cache = true;
+
+		/*
+		 * There is the chance it will be bigger than
+		 * memcg_limited_groups_array_size, if we failed an allocation
+		 * in a cache, in which case all caches updated before it, will
+		 * have a bigger array.
+		 *
+		 * But if that is the case, the data after
+		 * memcg_limited_groups_array_size is certainly unused
+		 */
+		for (i = 0; i < memcg_limited_groups_array_size; i++) {
+			if (!cur_params->memcg_caches[i])
+				continue;
+			s->memcg_params->memcg_caches[i] =
+						cur_params->memcg_caches[i];
+		}
+
+		/*
+		 * Ideally, we would wait until all caches succeed, and only
+		 * then free the old one. But this is not worth the extra
+		 * pointer per-cache we'd have to have for this.
+		 *
+		 * It is not a big deal if some caches are left with a size
+		 * bigger than the others. And all updates will reset this
+		 * anyway.
+		 */
+		kfree(cur_params);
+	}
+	return 0;
+}
+
+int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
+			 struct kmem_cache *root_cache)
+{
+	size_t size = sizeof(struct memcg_cache_params);
+
+	if (!memcg_kmem_enabled())
+		return 0;
+
+	if (!memcg)
+		size += memcg_limited_groups_array_size * sizeof(void *);
+
+	s->memcg_params = kzalloc(size, GFP_KERNEL);
+	if (!s->memcg_params)
+		return -ENOMEM;
+
+	if (memcg) {
+		s->memcg_params->memcg = memcg;
+		s->memcg_params->root_cache = root_cache;
+	}
+	return 0;
+}
+
+void memcg_release_cache(struct kmem_cache *s)
+{
+	struct kmem_cache *root;
+	struct mem_cgroup *memcg;
+	int id;
+
+	/*
+	 * This happens, for instance, when a root cache goes away before we
+	 * add any memcg.
+	 */
+	if (!s->memcg_params)
+		return;
+
+	if (s->memcg_params->is_root_cache)
+		goto out;
+
+	memcg = s->memcg_params->memcg;
+	id  = memcg_cache_id(memcg);
+
+	root = s->memcg_params->root_cache;
+	root->memcg_params->memcg_caches[id] = NULL;
+	mem_cgroup_put(memcg);
+
+	mutex_lock(&memcg->slab_caches_mutex);
+	list_del(&s->memcg_params->list);
+	mutex_unlock(&memcg->slab_caches_mutex);
+
+out:
+	kfree(s->memcg_params);
+}
+
+/*
+ * During the creation a new cache, we need to disable our accounting mechanism
+ * altogether. This is true even if we are not creating, but rather just
+ * enqueing new caches to be created.
+ *
+ * This is because that process will trigger allocations; some visible, like
+ * explicit kmallocs to auxiliary data structures, name strings and internal
+ * cache structures; some well concealed, like INIT_WORK() that can allocate
+ * objects during debug.
+ *
+ * If any allocation happens during memcg_kmem_get_cache, we will recurse back
+ * to it. This may not be a bounded recursion: since the first cache creation
+ * failed to complete (waiting on the allocation), we'll just try to create the
+ * cache again, failing at the same point.
+ *
+ * memcg_kmem_get_cache is prepared to abort after seeing a positive count of
+ * memcg_kmem_skip_account. So we enclose anything that might allocate memory
+ * inside the following two functions.
+ */
+static inline void memcg_stop_kmem_account(void)
+{
+	VM_BUG_ON(!current->mm);
+	current->memcg_kmem_skip_account++;
+}
+
+static inline void memcg_resume_kmem_account(void)
+{
+	VM_BUG_ON(!current->mm);
+	current->memcg_kmem_skip_account--;
+}
+
+static void kmem_cache_destroy_work_func(struct work_struct *w)
+{
+	struct kmem_cache *cachep;
+	struct memcg_cache_params *p;
+
+	p = container_of(w, struct memcg_cache_params, destroy);
+
+	cachep = memcg_params_to_cache(p);
+
+	/*
+	 * If we get down to 0 after shrink, we could delete right away.
+	 * However, memcg_release_pages() already puts us back in the workqueue
+	 * in that case. If we proceed deleting, we'll get a dangling
+	 * reference, and removing the object from the workqueue in that case
+	 * is unnecessary complication. We are not a fast path.
+	 *
+	 * Note that this case is fundamentally different from racing with
+	 * shrink_slab(): if memcg_cgroup_destroy_cache() is called in
+	 * kmem_cache_shrink, not only we would be reinserting a dead cache
+	 * into the queue, but doing so from inside the worker racing to
+	 * destroy it.
+	 *
+	 * So if we aren't down to zero, we'll just schedule a worker and try
+	 * again
+	 */
+	if (atomic_read(&cachep->memcg_params->nr_pages) != 0) {
+		kmem_cache_shrink(cachep);
+		if (atomic_read(&cachep->memcg_params->nr_pages) == 0)
+			return;
+	} else
+		kmem_cache_destroy(cachep);
+}
+
+void mem_cgroup_destroy_cache(struct kmem_cache *cachep)
+{
+	if (!cachep->memcg_params->dead)
+		return;
+
+	/*
+	 * There are many ways in which we can get here.
+	 *
+	 * We can get to a memory-pressure situation while the delayed work is
+	 * still pending to run. The vmscan shrinkers can then release all
+	 * cache memory and get us to destruction. If this is the case, we'll
+	 * be executed twice, which is a bug (the second time will execute over
+	 * bogus data). In this case, cancelling the work should be fine.
+	 *
+	 * But we can also get here from the worker itself, if
+	 * kmem_cache_shrink is enough to shake all the remaining objects and
+	 * get the page count to 0. In this case, we'll deadlock if we try to
+	 * cancel the work (the worker runs with an internal lock held, which
+	 * is the same lock we would hold for cancel_work_sync().)
+	 *
+	 * Since we can't possibly know who got us here, just refrain from
+	 * running if there is already work pending
+	 */
+	if (work_pending(&cachep->memcg_params->destroy))
+		return;
+	/*
+	 * We have to defer the actual destroying to a workqueue, because
+	 * we might currently be in a context that cannot sleep.
+	 */
+	schedule_work(&cachep->memcg_params->destroy);
+}
+
+static char *memcg_cache_name(struct mem_cgroup *memcg, struct kmem_cache *s)
+{
+	char *name;
+	struct dentry *dentry;
+
+	rcu_read_lock();
+	dentry = rcu_dereference(memcg->css.cgroup->dentry);
+	rcu_read_unlock();
+
+	BUG_ON(dentry == NULL);
+
+	name = kasprintf(GFP_KERNEL, "%s(%d:%s)", s->name,
+			 memcg_cache_id(memcg), dentry->d_name.name);
+
+	return name;
+}
+
+static struct kmem_cache *kmem_cache_dup(struct mem_cgroup *memcg,
+					 struct kmem_cache *s)
+{
+	char *name;
+	struct kmem_cache *new;
+
+	name = memcg_cache_name(memcg, s);
+	if (!name)
+		return NULL;
+
+	new = kmem_cache_create_memcg(memcg, name, s->object_size, s->align,
+				      (s->flags & ~SLAB_PANIC), s->ctor, s);
+
+	if (new)
+		new->allocflags |= __GFP_KMEMCG;
+
+	kfree(name);
+	return new;
+}
+
+/*
+ * This lock protects updaters, not readers. We want readers to be as fast as
+ * they can, and they will either see NULL or a valid cache value. Our model
+ * allow them to see NULL, in which case the root memcg will be selected.
+ *
+ * We need this lock because multiple allocations to the same cache from a non
+ * will span more than one worker. Only one of them can create the cache.
+ */
+static DEFINE_MUTEX(memcg_cache_mutex);
+static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
+						  struct kmem_cache *cachep)
+{
+	struct kmem_cache *new_cachep;
+	int idx;
+
+	BUG_ON(!memcg_can_account_kmem(memcg));
+
+	idx = memcg_cache_id(memcg);
+
+	mutex_lock(&memcg_cache_mutex);
+	new_cachep = cachep->memcg_params->memcg_caches[idx];
+	if (new_cachep)
+		goto out;
+
+	new_cachep = kmem_cache_dup(memcg, cachep);
+	if (new_cachep == NULL) {
+		new_cachep = cachep;
+		goto out;
+	}
+
+	mem_cgroup_get(memcg);
+	atomic_set(&new_cachep->memcg_params->nr_pages , 0);
+
+	cachep->memcg_params->memcg_caches[idx] = new_cachep;
+	/*
+	 * the readers won't lock, make sure everybody sees the updated value,
+	 * so they won't put stuff in the queue again for no reason
+	 */
+	wmb();
+out:
+	mutex_unlock(&memcg_cache_mutex);
+	return new_cachep;
+}
+
+void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
+{
+	struct kmem_cache *c;
+	int i;
+
+	if (!s->memcg_params)
+		return;
+	if (!s->memcg_params->is_root_cache)
+		return;
+
+	/*
+	 * If the cache is being destroyed, we trust that there is no one else
+	 * requesting objects from it. Even if there are, the sanity checks in
+	 * kmem_cache_destroy should caught this ill-case.
+	 *
+	 * Still, we don't want anyone else freeing memcg_caches under our
+	 * noses, which can happen if a new memcg comes to life. As usual,
+	 * we'll take the set_limit_mutex to protect ourselves against this.
+	 */
+	mutex_lock(&set_limit_mutex);
+	for (i = 0; i < memcg_limited_groups_array_size; i++) {
+		c = s->memcg_params->memcg_caches[i];
+		if (!c)
+			continue;
+
+		/*
+		 * We will now manually delete the caches, so to avoid races
+		 * we need to cancel all pending destruction workers and
+		 * proceed with destruction ourselves.
+		 *
+		 * kmem_cache_destroy() will call kmem_cache_shrink internally,
+		 * and that could spawn the workers again: it is likely that
+		 * the cache still have active pages until this very moment.
+		 * This would lead us back to mem_cgroup_destroy_cache.
+		 *
+		 * But that will not execute at all if the "dead" flag is not
+		 * set, so flip it down to guarantee we are in control.
+		 */
+		c->memcg_params->dead = false;
+		cancel_work_sync(&c->memcg_params->destroy);
+		kmem_cache_destroy(c);
+	}
+	mutex_unlock(&set_limit_mutex);
+}
+
+struct create_work {
+	struct mem_cgroup *memcg;
+	struct kmem_cache *cachep;
+	struct work_struct work;
+};
+
+static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg)
+{
+	struct kmem_cache *cachep;
+	struct memcg_cache_params *params;
+
+	if (!memcg_kmem_is_active(memcg))
+		return;
+
+	mutex_lock(&memcg->slab_caches_mutex);
+	list_for_each_entry(params, &memcg->memcg_slab_caches, list) {
+		cachep = memcg_params_to_cache(params);
+		cachep->memcg_params->dead = true;
+		INIT_WORK(&cachep->memcg_params->destroy,
+				  kmem_cache_destroy_work_func);
+		schedule_work(&cachep->memcg_params->destroy);
+	}
+	mutex_unlock(&memcg->slab_caches_mutex);
+}
+
+static void memcg_create_cache_work_func(struct work_struct *w)
+{
+	struct create_work *cw;
+
+	cw = container_of(w, struct create_work, work);
+	memcg_create_kmem_cache(cw->memcg, cw->cachep);
+	/* Drop the reference gotten when we enqueued. */
+	css_put(&cw->memcg->css);
+	kfree(cw);
+}
+
+/*
+ * Enqueue the creation of a per-memcg kmem_cache.
+ * Called with rcu_read_lock.
+ */
+static void __memcg_create_cache_enqueue(struct mem_cgroup *memcg,
+					 struct kmem_cache *cachep)
+{
+	struct create_work *cw;
+
+	cw = kmalloc(sizeof(struct create_work), GFP_NOWAIT);
+	if (cw == NULL)
+		return;
+
+	/* The corresponding put will be done in the workqueue. */
+	if (!css_tryget(&memcg->css)) {
+		kfree(cw);
+		return;
+	}
+
+	cw->memcg = memcg;
+	cw->cachep = cachep;
+
+	INIT_WORK(&cw->work, memcg_create_cache_work_func);
+	schedule_work(&cw->work);
+}
+
+static void memcg_create_cache_enqueue(struct mem_cgroup *memcg,
+				       struct kmem_cache *cachep)
+{
+	/*
+	 * We need to stop accounting when we kmalloc, because if the
+	 * corresponding kmalloc cache is not yet created, the first allocation
+	 * in __memcg_create_cache_enqueue will recurse.
+	 *
+	 * However, it is better to enclose the whole function. Depending on
+	 * the debugging options enabled, INIT_WORK(), for instance, can
+	 * trigger an allocation. This too, will make us recurse. Because at
+	 * this point we can't allow ourselves back into memcg_kmem_get_cache,
+	 * the safest choice is to do it like this, wrapping the whole function.
+	 */
+	memcg_stop_kmem_account();
+	__memcg_create_cache_enqueue(memcg, cachep);
+	memcg_resume_kmem_account();
+}
+/*
+ * Return the kmem_cache we're supposed to use for a slab allocation.
+ * We try to use the current memcg's version of the cache.
+ *
+ * If the cache does not exist yet, if we are the first user of it,
+ * we either create it immediately, if possible, or create it asynchronously
+ * in a workqueue.
+ * In the latter case, we will let the current allocation go through with
+ * the original cache.
+ *
+ * Can't be called in interrupt context or from kernel threads.
+ * This function needs to be called with rcu_read_lock() held.
+ */
+struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep,
+					  gfp_t gfp)
+{
+	struct mem_cgroup *memcg;
+	int idx;
+
+	VM_BUG_ON(!cachep->memcg_params);
+	VM_BUG_ON(!cachep->memcg_params->is_root_cache);
+
+	if (!current->mm || current->memcg_kmem_skip_account)
+		return cachep;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_task(rcu_dereference(current->mm->owner));
+	rcu_read_unlock();
+
+	if (!memcg_can_account_kmem(memcg))
+		return cachep;
+
+	idx = memcg_cache_id(memcg);
+
+	/*
+	 * barrier to mare sure we're always seeing the up to date value.  The
+	 * code updating memcg_caches will issue a write barrier to match this.
+	 */
+	read_barrier_depends();
+	if (unlikely(cachep->memcg_params->memcg_caches[idx] == NULL)) {
+		/*
+		 * If we are in a safe context (can wait, and not in interrupt
+		 * context), we could be be predictable and return right away.
+		 * This would guarantee that the allocation being performed
+		 * already belongs in the new cache.
+		 *
+		 * However, there are some clashes that can arrive from locking.
+		 * For instance, because we acquire the slab_mutex while doing
+		 * kmem_cache_dup, this means no further allocation could happen
+		 * with the slab_mutex held.
+		 *
+		 * Also, because cache creation issue get_online_cpus(), this
+		 * creates a lock chain: memcg_slab_mutex -> cpu_hotplug_mutex,
+		 * that ends up reversed during cpu hotplug. (cpuset allocates
+		 * a bunch of GFP_KERNEL memory during cpuup). Due to all that,
+		 * better to defer everything.
+		 */
+		memcg_create_cache_enqueue(memcg, cachep);
+		return cachep;
+	}
+
+	return cachep->memcg_params->memcg_caches[idx];
+}
+EXPORT_SYMBOL(__memcg_kmem_get_cache);
+
+/*
+ * We need to verify if the allocation against current->mm->owner's memcg is
+ * possible for the given order. But the page is not allocated yet, so we'll
+ * need a further commit step to do the final arrangements.
+ *
+ * It is possible for the task to switch cgroups in this mean time, so at
+ * commit time, we can't rely on task conversion any longer.  We'll then use
+ * the handle argument to return to the caller which cgroup we should commit
+ * against. We could also return the memcg directly and avoid the pointer
+ * passing, but a boolean return value gives better semantics considering
+ * the compiled-out case as well.
+ *
+ * Returning true means the allocation is possible.
+ */
+bool
+__memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
+{
+	struct mem_cgroup *memcg;
+	int ret;
+
+	*_memcg = NULL;
+	memcg = try_get_mem_cgroup_from_mm(current->mm);
+
+	/*
+	 * very rare case described in mem_cgroup_from_task. Unfortunately there
+	 * isn't much we can do without complicating this too much, and it would
+	 * be gfp-dependent anyway. Just let it go
+	 */
+	if (unlikely(!memcg))
+		return true;
+
+	if (!memcg_can_account_kmem(memcg)) {
+		css_put(&memcg->css);
+		return true;
+	}
+
+	ret = memcg_charge_kmem(memcg, gfp, PAGE_SIZE << order);
+	if (!ret)
+		*_memcg = memcg;
+
+	css_put(&memcg->css);
+	return (ret == 0);
+}
+
+void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
+			      int order)
+{
+	struct page_cgroup *pc;
+
+	VM_BUG_ON(mem_cgroup_is_root(memcg));
+
+	/* The page allocation failed. Revert */
+	if (!page) {
+		memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
+		return;
+	}
+
+	pc = lookup_page_cgroup(page);
+	lock_page_cgroup(pc);
+	pc->mem_cgroup = memcg;
+	SetPageCgroupUsed(pc);
+	unlock_page_cgroup(pc);
+}
+
+void __memcg_kmem_uncharge_pages(struct page *page, int order)
+{
+	struct mem_cgroup *memcg = NULL;
+	struct page_cgroup *pc;
+
+
+	pc = lookup_page_cgroup(page);
+	/*
+	 * Fast unlocked return. Theoretically might have changed, have to
+	 * check again after locking.
+	 */
+	if (!PageCgroupUsed(pc))
+		return;
+
+	lock_page_cgroup(pc);
+	if (PageCgroupUsed(pc)) {
+		memcg = pc->mem_cgroup;
+		ClearPageCgroupUsed(pc);
+	}
+	unlock_page_cgroup(pc);
+
+	/*
+	 * We trust that only if there is a memcg associated with the page, it
+	 * is a valid allocation
+	 */
+	if (!memcg)
+		return;
+
+	VM_BUG_ON(mem_cgroup_is_root(memcg));
+	memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
+}
+#else
+static inline void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+#define PCGF_NOCOPY_AT_SPLIT (1 << PCG_LOCK | 1 << PCG_MIGRATION)
+/*
+ * Because tail pages are not marked as "used", set it. We're under
+ * zone->lru_lock, 'splitting on pmd' and compound_lock.
+ * charge/uncharge will be never happen and move_account() is done under
+ * compound_lock(), so we don't have to take care of races.
+ */
+void mem_cgroup_split_huge_fixup(struct page *head)
+{
+	struct page_cgroup *head_pc = lookup_page_cgroup(head);
+	struct page_cgroup *pc;
+	int i;
+
+	if (mem_cgroup_disabled())
+		return;
+	for (i = 1; i < HPAGE_PMD_NR; i++) {
+		pc = head_pc + i;
+		pc->mem_cgroup = head_pc->mem_cgroup;
+		smp_wmb();/* see __commit_charge() */
+		pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT;
+	}
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+/**
+ * mem_cgroup_move_account - move account of the page
+ * @page: the page
+ * @nr_pages: number of regular pages (>1 for huge pages)
+ * @pc:	page_cgroup of the page.
+ * @from: mem_cgroup which the page is moved from.
+ * @to:	mem_cgroup which the page is moved to. @from != @to.
+ *
+ * The caller must confirm following.
+ * - page is not on LRU (isolate_page() is useful.)
+ * - compound_lock is held when nr_pages > 1
+ *
+ * This function doesn't do "charge" to new cgroup and doesn't do "uncharge"
+ * from old cgroup.
+ */
+static int mem_cgroup_move_account(struct page *page,
+				   unsigned int nr_pages,
+				   struct page_cgroup *pc,
+				   struct mem_cgroup *from,
+				   struct mem_cgroup *to)
+{
+	unsigned long flags;
+	int ret;
+	bool anon = PageAnon(page);
+
+	VM_BUG_ON(from == to);
+	VM_BUG_ON(PageLRU(page));
+	/*
+	 * The page is isolated from LRU. So, collapse function
+	 * will not handle this page. But page splitting can happen.
+	 * Do this check under compound_page_lock(). The caller should
+	 * hold it.
+	 */
+	ret = -EBUSY;
+	if (nr_pages > 1 && !PageTransHuge(page))
+		goto out;
+
+	lock_page_cgroup(pc);
+
+	ret = -EINVAL;
+	if (!PageCgroupUsed(pc) || pc->mem_cgroup != from)
+		goto unlock;
+
+	move_lock_mem_cgroup(from, &flags);
+
+	if (!anon && page_mapped(page)) {
+		/* Update mapped_file data for mem_cgroup */
+		preempt_disable();
+		__this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
+		__this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
+		preempt_enable();
+	}
+	mem_cgroup_charge_statistics(from, anon, -nr_pages);
+
+	/* caller should have done css_get */
+	pc->mem_cgroup = to;
+	mem_cgroup_charge_statistics(to, anon, nr_pages);
+	move_unlock_mem_cgroup(from, &flags);
+	ret = 0;
+unlock:
+	unlock_page_cgroup(pc);
+	/*
+	 * check events
+	 */
+	memcg_check_events(to, page);
+	memcg_check_events(from, page);
+out:
+	return ret;
+}
+
+/**
+ * mem_cgroup_move_parent - moves page to the parent group
+ * @page: the page to move
+ * @pc: page_cgroup of the page
+ * @child: page's cgroup
+ *
+ * move charges to its parent or the root cgroup if the group has no
+ * parent (aka use_hierarchy==0).
+ * Although this might fail (get_page_unless_zero, isolate_lru_page or
+ * mem_cgroup_move_account fails) the failure is always temporary and
+ * it signals a race with a page removal/uncharge or migration. In the
+ * first case the page is on the way out and it will vanish from the LRU
+ * on the next attempt and the call should be retried later.
+ * Isolation from the LRU fails only if page has been isolated from
+ * the LRU since we looked at it and that usually means either global
+ * reclaim or migration going on. The page will either get back to the
+ * LRU or vanish.
+ * Finaly mem_cgroup_move_account fails only if the page got uncharged
+ * (!PageCgroupUsed) or moved to a different group. The page will
+ * disappear in the next attempt.
+ */
+static int mem_cgroup_move_parent(struct page *page,
+				  struct page_cgroup *pc,
+				  struct mem_cgroup *child)
+{
+	struct mem_cgroup *parent;
+	unsigned int nr_pages;
+	unsigned long uninitialized_var(flags);
+	int ret;
+
+	VM_BUG_ON(mem_cgroup_is_root(child));
+
+	ret = -EBUSY;
+	if (!get_page_unless_zero(page))
+		goto out;
+	if (isolate_lru_page(page))
+		goto put;
+
+	nr_pages = hpage_nr_pages(page);
+
+	parent = parent_mem_cgroup(child);
+	/*
+	 * If no parent, move charges to root cgroup.
+	 */
+	if (!parent)
+		parent = root_mem_cgroup;
+
+	if (nr_pages > 1) {
+		VM_BUG_ON(!PageTransHuge(page));
+		flags = compound_lock_irqsave(page);
+	}
+
+	ret = mem_cgroup_move_account(page, nr_pages,
+				pc, child, parent);
+	if (!ret)
+		__mem_cgroup_cancel_local_charge(child, nr_pages);
+
+	if (nr_pages > 1)
+		compound_unlock_irqrestore(page, flags);
+	putback_lru_page(page);
+put:
+	put_page(page);
+out:
+	return ret;
+}
+
+/*
+ * Charge the memory controller for page usage.
+ * Return
+ * 0 if the charge was successful
+ * < 0 if the cgroup is over its limit
+ */
+static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
+				gfp_t gfp_mask, enum charge_type ctype)
+{
+	struct mem_cgroup *memcg = NULL;
+	unsigned int nr_pages = 1;
+	bool oom = true;
+	int ret;
+
+	if (PageTransHuge(page)) {
 		nr_pages <<= compound_order(page);
 		VM_BUG_ON(!PageTransHuge(page));
 		/*
@@ -3486,8 +4395,6 @@ void mem_cgroup_print_bad_page(struct page *page)
 }
 #endif
 
-static DEFINE_MUTEX(set_limit_mutex);
-
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 				unsigned long long val)
 {
@@ -3772,6 +4679,7 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
 {
 	int node, zid;
+	u64 usage;
 
 	do {
 		/* This is for making all *used* pages to be on LRU. */
@@ -3792,13 +4700,20 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
 		cond_resched();
 
 		/*
+		 * Kernel memory may not necessarily be trackable to a specific
+		 * process. So they are not migrated, and therefore we can't
+		 * expect their value to drop to 0 here.
+		 * Having res filled up with kmem only is enough.
+		 *
 		 * This is a safety check because mem_cgroup_force_empty_list
 		 * could have raced with mem_cgroup_replace_page_cache callers
 		 * so the lru seemed empty but the page could have been added
 		 * right after the check. RES_USAGE should be safe as we always
 		 * charge before adding to the LRU.
 		 */
-	} while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0);
+		usage = res_counter_read_u64(&memcg->res, RES_USAGE) -
+			res_counter_read_u64(&memcg->kmem, RES_USAGE);
+	} while (usage > 0);
 }
 
 /*
@@ -3942,7 +4857,8 @@ static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 	char str[64];
 	u64 val;
-	int type, name, len;
+	int name, len;
+	enum res_type type;
 
 	type = MEMFILE_TYPE(cft->private);
 	name = MEMFILE_ATTR(cft->private);
@@ -3963,6 +4879,9 @@ static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
 		else
 			val = res_counter_read_u64(&memcg->memsw, name);
 		break;
+	case _KMEM:
+		val = res_counter_read_u64(&memcg->kmem, name);
+		break;
 	default:
 		BUG();
 	}
@@ -3970,6 +4889,125 @@ static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
 	len = scnprintf(str, sizeof(str), "%llu\n", (unsigned long long)val);
 	return simple_read_from_buffer(buf, nbytes, ppos, str, len);
 }
+
+static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
+{
+	int ret = -EINVAL;
+#ifdef CONFIG_MEMCG_KMEM
+	bool must_inc_static_branch = false;
+
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	/*
+	 * For simplicity, we won't allow this to be disabled.  It also can't
+	 * be changed if the cgroup has children already, or if tasks had
+	 * already joined.
+	 *
+	 * If tasks join before we set the limit, a person looking at
+	 * kmem.usage_in_bytes will have no way to determine when it took
+	 * place, which makes the value quite meaningless.
+	 *
+	 * After it first became limited, changes in the value of the limit are
+	 * of course permitted.
+	 *
+	 * Taking the cgroup_lock is really offensive, but it is so far the only
+	 * way to guarantee that no children will appear. There are plenty of
+	 * other offenders, and they should all go away. Fine grained locking
+	 * is probably the way to go here. When we are fully hierarchical, we
+	 * can also get rid of the use_hierarchy check.
+	 */
+	cgroup_lock();
+	mutex_lock(&set_limit_mutex);
+	if (!memcg->kmem_account_flags && val != RESOURCE_MAX) {
+		if (cgroup_task_count(cont) || (memcg->use_hierarchy &&
+						!list_empty(&cont->children))) {
+			ret = -EBUSY;
+			goto out;
+		}
+		ret = res_counter_set_limit(&memcg->kmem, val);
+		VM_BUG_ON(ret);
+
+		ret = memcg_update_cache_sizes(memcg);
+		if (ret) {
+			res_counter_set_limit(&memcg->kmem, RESOURCE_MAX);
+			goto out;
+		}
+		must_inc_static_branch = true;
+		/*
+		 * kmem charges can outlive the cgroup. In the case of slab
+		 * pages, for instance, a page contain objects from various
+		 * processes, so it is unfeasible to migrate them away. We
+		 * need to reference count the memcg because of that.
+		 */
+		mem_cgroup_get(memcg);
+	} else
+		ret = res_counter_set_limit(&memcg->kmem, val);
+out:
+	mutex_unlock(&set_limit_mutex);
+	cgroup_unlock();
+
+	/*
+	 * We are by now familiar with the fact that we can't inc the static
+	 * branch inside cgroup_lock. See disarm functions for details. A
+	 * worker here is overkill, but also wrong: After the limit is set, we
+	 * must start accounting right away. Since this operation can't fail,
+	 * we can safely defer it to here - no rollback will be needed.
+	 *
+	 * The boolean used to control this is also safe, because
+	 * KMEM_ACCOUNTED_ACTIVATED guarantees that only one process will be
+	 * able to set it to true;
+	 */
+	if (must_inc_static_branch) {
+		static_key_slow_inc(&memcg_kmem_enabled_key);
+		/*
+		 * setting the active bit after the inc will guarantee no one
+		 * starts accounting before all call sites are patched
+		 */
+		memcg_kmem_set_active(memcg);
+	}
+
+#endif
+	return ret;
+}
+
+static int memcg_propagate_kmem(struct mem_cgroup *memcg)
+{
+	int ret = 0;
+	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+	if (!parent)
+		goto out;
+
+	memcg->kmem_account_flags = parent->kmem_account_flags;
+#ifdef CONFIG_MEMCG_KMEM
+	/*
+	 * When that happen, we need to disable the static branch only on those
+	 * memcgs that enabled it. To achieve this, we would be forced to
+	 * complicate the code by keeping track of which memcgs were the ones
+	 * that actually enabled limits, and which ones got it from its
+	 * parents.
+	 *
+	 * It is a lot simpler just to do static_key_slow_inc() on every child
+	 * that is accounted.
+	 */
+	if (!memcg_kmem_is_active(memcg))
+		goto out;
+
+	/*
+	 * destroy(), called if we fail, will issue static_key_slow_inc() and
+	 * mem_cgroup_put() if kmem is enabled. We have to either call them
+	 * unconditionally, or clear the KMEM_ACTIVE flag. I personally find
+	 * this more consistent, since it always leads to the same destroy path
+	 */
+	mem_cgroup_get(memcg);
+	static_key_slow_inc(&memcg_kmem_enabled_key);
+
+	mutex_lock(&set_limit_mutex);
+	ret = memcg_update_cache_sizes(memcg);
+	mutex_unlock(&set_limit_mutex);
+#endif
+out:
+	return ret;
+}
+
 /*
  * The user of this function is...
  * RES_LIMIT.
@@ -3978,7 +5016,8 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
 			    const char *buffer)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
-	int type, name;
+	enum res_type type;
+	int name;
 	unsigned long long val;
 	int ret;
 
@@ -4000,8 +5039,12 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
 			break;
 		if (type == _MEM)
 			ret = mem_cgroup_resize_limit(memcg, val);
-		else
+		else if (type == _MEMSWAP)
 			ret = mem_cgroup_resize_memsw_limit(memcg, val);
+		else if (type == _KMEM)
+			ret = memcg_update_kmem_limit(cont, val);
+		else
+			return -EINVAL;
 		break;
 	case RES_SOFT_LIMIT:
 		ret = res_counter_memparse_write_strategy(buffer, &val);
@@ -4054,7 +5097,8 @@ out:
 static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
-	int type, name;
+	int name;
+	enum res_type type;
 
 	type = MEMFILE_TYPE(event);
 	name = MEMFILE_ATTR(event);
@@ -4066,14 +5110,22 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
 	case RES_MAX_USAGE:
 		if (type == _MEM)
 			res_counter_reset_max(&memcg->res);
-		else
+		else if (type == _MEMSWAP)
 			res_counter_reset_max(&memcg->memsw);
+		else if (type == _KMEM)
+			res_counter_reset_max(&memcg->kmem);
+		else
+			return -EINVAL;
 		break;
 	case RES_FAILCNT:
 		if (type == _MEM)
 			res_counter_reset_failcnt(&memcg->res);
-		else
+		else if (type == _MEMSWAP)
 			res_counter_reset_failcnt(&memcg->memsw);
+		else if (type == _KMEM)
+			res_counter_reset_failcnt(&memcg->kmem);
+		else
+			return -EINVAL;
 		break;
 	}
 
@@ -4390,7 +5442,7 @@ static int mem_cgroup_usage_register_event(struct cgroup *cgrp,
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
-	int type = MEMFILE_TYPE(cft->private);
+	enum res_type type = MEMFILE_TYPE(cft->private);
 	u64 threshold, usage;
 	int i, size, ret;
 
@@ -4473,7 +5525,7 @@ static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
-	int type = MEMFILE_TYPE(cft->private);
+	enum res_type type = MEMFILE_TYPE(cft->private);
 	u64 usage;
 	int i, j, size;
 
@@ -4551,7 +5603,7 @@ static int mem_cgroup_oom_register_event(struct cgroup *cgrp,
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
 	struct mem_cgroup_eventfd_list *event;
-	int type = MEMFILE_TYPE(cft->private);
+	enum res_type type = MEMFILE_TYPE(cft->private);
 
 	BUG_ON(type != _OOM_TYPE);
 	event = kmalloc(sizeof(*event),	GFP_KERNEL);
@@ -4576,7 +5628,7 @@ static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp,
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
 	struct mem_cgroup_eventfd_list *ev, *tmp;
-	int type = MEMFILE_TYPE(cft->private);
+	enum res_type type = MEMFILE_TYPE(cft->private);
 
 	BUG_ON(type != _OOM_TYPE);
 
@@ -4635,12 +5687,33 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
 #ifdef CONFIG_MEMCG_KMEM
 static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
+	int ret;
+
+	memcg->kmemcg_id = -1;
+	ret = memcg_propagate_kmem(memcg);
+	if (ret)
+		return ret;
+
 	return mem_cgroup_sockets_init(memcg, ss);
 };
 
 static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
 {
 	mem_cgroup_sockets_destroy(memcg);
+
+	memcg_kmem_mark_dead(memcg);
+
+	if (res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0)
+		return;
+
+	/*
+	 * Charges already down to 0, undo mem_cgroup_get() done in the charge
+	 * path here, being careful not to race with memcg_uncharge_kmem: it is
+	 * possible that the charges went down to 0 between mark_dead and the
+	 * res_counter read, so in that case, we don't need the put
+	 */
+	if (memcg_kmem_test_and_clear_dead(memcg))
+		mem_cgroup_put(memcg);
 }
 #else
 static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
@@ -4748,6 +5821,37 @@ static struct cftype mem_cgroup_files[] = {
 		.trigger = mem_cgroup_reset,
 		.read = mem_cgroup_read,
 	},
+#endif
+#ifdef CONFIG_MEMCG_KMEM
+	{
+		.name = "kmem.limit_in_bytes",
+		.private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
+		.write_string = mem_cgroup_write,
+		.read = mem_cgroup_read,
+	},
+	{
+		.name = "kmem.usage_in_bytes",
+		.private = MEMFILE_PRIVATE(_KMEM, RES_USAGE),
+		.read = mem_cgroup_read,
+	},
+	{
+		.name = "kmem.failcnt",
+		.private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT),
+		.trigger = mem_cgroup_reset,
+		.read = mem_cgroup_read,
+	},
+	{
+		.name = "kmem.max_usage_in_bytes",
+		.private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE),
+		.trigger = mem_cgroup_reset,
+		.read = mem_cgroup_read,
+	},
+#ifdef CONFIG_SLABINFO
+	{
+		.name = "kmem.slabinfo",
+		.read_seq_string = mem_cgroup_slabinfo_read,
+	},
+#endif
 #endif
 	{ },	/* terminate */
 };
@@ -4816,16 +5920,29 @@ out_free:
 }
 
 /*
- * Helpers for freeing a kmalloc()ed/vzalloc()ed mem_cgroup by RCU,
- * but in process context.  The work_freeing structure is overlaid
- * on the rcu_freeing structure, which itself is overlaid on memsw.
+ * At destroying mem_cgroup, references from swap_cgroup can remain.
+ * (scanning all at force_empty is too costly...)
+ *
+ * Instead of clearing all references at force_empty, we remember
+ * the number of reference from swap_cgroup and free mem_cgroup when
+ * it goes down to 0.
+ *
+ * Removal of cgroup itself succeeds regardless of refs from swap.
  */
-static void free_work(struct work_struct *work)
+
+static void __mem_cgroup_free(struct mem_cgroup *memcg)
 {
-	struct mem_cgroup *memcg;
+	int node;
 	int size = sizeof(struct mem_cgroup);
 
-	memcg = container_of(work, struct mem_cgroup, work_freeing);
+	mem_cgroup_remove_from_trees(memcg);
+	free_css_id(&mem_cgroup_subsys, &memcg->css);
+
+	for_each_node(node)
+		free_mem_cgroup_per_zone_info(memcg, node);
+
+	free_percpu(memcg->stat);
+
 	/*
 	 * We need to make sure that (at least for now), the jump label
 	 * destruction code runs outside of the cgroup lock. This is because
@@ -4837,45 +5954,34 @@ static void free_work(struct work_struct *work)
 	 * to move this code around, and make sure it is outside
 	 * the cgroup_lock.
 	 */
-	disarm_sock_keys(memcg);
+	disarm_static_keys(memcg);
 	if (size < PAGE_SIZE)
 		kfree(memcg);
 	else
 		vfree(memcg);
 }
 
-static void free_rcu(struct rcu_head *rcu_head)
-{
-	struct mem_cgroup *memcg;
-
-	memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing);
-	INIT_WORK(&memcg->work_freeing, free_work);
-	schedule_work(&memcg->work_freeing);
-}
 
 /*
- * At destroying mem_cgroup, references from swap_cgroup can remain.
- * (scanning all at force_empty is too costly...)
- *
- * Instead of clearing all references at force_empty, we remember
- * the number of reference from swap_cgroup and free mem_cgroup when
- * it goes down to 0.
- *
- * Removal of cgroup itself succeeds regardless of refs from swap.
+ * Helpers for freeing a kmalloc()ed/vzalloc()ed mem_cgroup by RCU,
+ * but in process context.  The work_freeing structure is overlaid
+ * on the rcu_freeing structure, which itself is overlaid on memsw.
  */
-
-static void __mem_cgroup_free(struct mem_cgroup *memcg)
+static void free_work(struct work_struct *work)
 {
-	int node;
+	struct mem_cgroup *memcg;
 
-	mem_cgroup_remove_from_trees(memcg);
-	free_css_id(&mem_cgroup_subsys, &memcg->css);
+	memcg = container_of(work, struct mem_cgroup, work_freeing);
+	__mem_cgroup_free(memcg);
+}
 
-	for_each_node(node)
-		free_mem_cgroup_per_zone_info(memcg, node);
+static void free_rcu(struct rcu_head *rcu_head)
+{
+	struct mem_cgroup *memcg;
 
-	free_percpu(memcg->stat);
-	call_rcu(&memcg->rcu_freeing, free_rcu);
+	memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing);
+	INIT_WORK(&memcg->work_freeing, free_work);
+	schedule_work(&memcg->work_freeing);
 }
 
 static void mem_cgroup_get(struct mem_cgroup *memcg)
@@ -4887,7 +5993,7 @@ static void __mem_cgroup_put(struct mem_cgroup *memcg, int count)
 {
 	if (atomic_sub_and_test(count, &memcg->refcnt)) {
 		struct mem_cgroup *parent = parent_mem_cgroup(memcg);
-		__mem_cgroup_free(memcg);
+		call_rcu(&memcg->rcu_freeing, free_rcu);
 		if (parent)
 			mem_cgroup_put(parent);
 	}
@@ -4994,6 +6100,8 @@ mem_cgroup_css_alloc(struct cgroup *cont)
 	if (parent && parent->use_hierarchy) {
 		res_counter_init(&memcg->res, &parent->res);
 		res_counter_init(&memcg->memsw, &parent->memsw);
+		res_counter_init(&memcg->kmem, &parent->kmem);
+
 		/*
 		 * We increment refcnt of the parent to ensure that we can
 		 * safely access it on res_counter_charge/uncharge.
@@ -5004,6 +6112,7 @@ mem_cgroup_css_alloc(struct cgroup *cont)
 	} else {
 		res_counter_init(&memcg->res, NULL);
 		res_counter_init(&memcg->memsw, NULL);
+		res_counter_init(&memcg->kmem, NULL);
 		/*
 		 * Deeper hierachy with use_hierarchy == false doesn't make
 		 * much sense so let cgroup subsystem know about this
@@ -5043,6 +6152,7 @@ static void mem_cgroup_css_offline(struct cgroup *cont)
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
 	mem_cgroup_reparent_charges(memcg);
+	mem_cgroup_destroy_all_caches(memcg);
 }
 
 static void mem_cgroup_css_free(struct cgroup *cont)

mm/memory_hotplug.c

@@ -590,18 +590,21 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 }
 
 #ifdef CONFIG_MOVABLE_NODE
-/* when CONFIG_MOVABLE_NODE, we allow online node don't have normal memory */
+/*
+ * When CONFIG_MOVABLE_NODE, we permit onlining of a node which doesn't have
+ * normal memory.
+ */
 static bool can_online_high_movable(struct zone *zone)
 {
 	return true;
 }
-#else /* #ifdef CONFIG_MOVABLE_NODE */
+#else /* CONFIG_MOVABLE_NODE */
 /* ensure every online node has NORMAL memory */
 static bool can_online_high_movable(struct zone *zone)
 {
 	return node_state(zone_to_nid(zone), N_NORMAL_MEMORY);
 }
-#endif /* #ifdef CONFIG_MOVABLE_NODE */
+#endif /* CONFIG_MOVABLE_NODE */
 
 /* check which state of node_states will be changed when online memory */
 static void node_states_check_changes_online(unsigned long nr_pages,
@@ -1112,12 +1115,15 @@ check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 }
 
 #ifdef CONFIG_MOVABLE_NODE
-/* when CONFIG_MOVABLE_NODE, we allow online node don't have normal memory */
+/*
+ * When CONFIG_MOVABLE_NODE, we permit offlining of a node which doesn't have
+ * normal memory.
+ */
 static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
 {
 	return true;
 }
-#else /* #ifdef CONFIG_MOVABLE_NODE */
+#else /* CONFIG_MOVABLE_NODE */
 /* ensure the node has NORMAL memory if it is still online */
 static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
 {
@@ -1141,7 +1147,7 @@ static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
 	 */
 	return present_pages == 0;
 }
-#endif /* #ifdef CONFIG_MOVABLE_NODE */
+#endif /* CONFIG_MOVABLE_NODE */
 
 /* check which state of node_states will be changed when offline memory */
 static void node_states_check_changes_offline(unsigned long nr_pages,

mm/mprotect.c

@@ -114,7 +114,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 #ifdef CONFIG_NUMA_BALANCING
 static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
-		pmd_t *pmd)
+				       pmd_t *pmd)
 {
 	spin_lock(&mm->page_table_lock);
 	set_pmd_at(mm, addr & PMD_MASK, pmd, pmd_mknuma(*pmd));
@@ -122,15 +122,15 @@ static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
 }
 #else
 static inline void change_pmd_protnuma(struct mm_struct *mm, unsigned long addr,
-		pmd_t *pmd)
+				       pmd_t *pmd)
 {
 	BUG();
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
-static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
-		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable, int prot_numa)
+static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
+		pud_t *pud, unsigned long addr, unsigned long end,
+		pgprot_t newprot, int dirty_accountable, int prot_numa)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -143,7 +143,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *
 		if (pmd_trans_huge(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE)
 				split_huge_page_pmd(vma, addr, pmd);
-			else if (change_huge_pmd(vma, pmd, addr, newprot, prot_numa)) {
+			else if (change_huge_pmd(vma, pmd, addr, newprot,
+						 prot_numa)) {
 				pages += HPAGE_PMD_NR;
 				continue;
 			}
@@ -167,9 +168,9 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, pud_t *
 	return pages;
 }
 
-static inline unsigned long change_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
-		unsigned long addr, unsigned long end, pgprot_t newprot,
-		int dirty_accountable, int prot_numa)
+static inline unsigned long change_pud_range(struct vm_area_struct *vma,
+		pgd_t *pgd, unsigned long addr, unsigned long end,
+		pgprot_t newprot, int dirty_accountable, int prot_numa)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -304,7 +305,8 @@ success:
 		dirty_accountable = 1;
 	}
 
-	change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable, 0);
+	change_protection(vma, start, end, vma->vm_page_prot,
+			  dirty_accountable, 0);
 
 	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
 	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
@@ -361,8 +363,7 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 		error = -EINVAL;
 		if (!(vma->vm_flags & VM_GROWSDOWN))
 			goto out;
-	}
-	else {
+	} else {
 		if (vma->vm_start > start)
 			goto out;
 		if (unlikely(grows & PROT_GROWSUP)) {
@@ -378,9 +379,10 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 	for (nstart = start ; ; ) {
 		unsigned long newflags;
 
-		/* Here we know that  vma->vm_start <= nstart < vma->vm_end. */
+		/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
 
-		newflags = vm_flags | (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
+		newflags = vm_flags;
+		newflags |= (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
 
 		/* newflags >> 4 shift VM_MAY% in place of VM_% */
 		if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) {

mm/page_alloc.c

@@ -371,8 +371,7 @@ static int destroy_compound_page(struct page *page, unsigned long order)
 	int nr_pages = 1 << order;
 	int bad = 0;
 
-	if (unlikely(compound_order(page) != order) ||
-	    unlikely(!PageHead(page))) {
+	if (unlikely(compound_order(page) != order)) {
 		bad_page(page);
 		bad++;
 	}
@@ -2613,6 +2612,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	int migratetype = allocflags_to_migratetype(gfp_mask);
 	unsigned int cpuset_mems_cookie;
 	int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET;
+	struct mem_cgroup *memcg = NULL;
 
 	gfp_mask &= gfp_allowed_mask;
 
@@ -2631,6 +2631,13 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (unlikely(!zonelist->_zonerefs->zone))
 		return NULL;
 
+	/*
+	 * Will only have any effect when __GFP_KMEMCG is set.  This is
+	 * verified in the (always inline) callee
+	 */
+	if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order))
+		return NULL;
+
 retry_cpuset:
 	cpuset_mems_cookie = get_mems_allowed();
 
@@ -2666,6 +2673,8 @@ out:
 	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
 		goto retry_cpuset;
 
+	memcg_kmem_commit_charge(page, memcg, order);
+
 	return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);
@@ -2718,6 +2727,31 @@ void free_pages(unsigned long addr, unsigned int order)
 
 EXPORT_SYMBOL(free_pages);
 
+/*
+ * __free_memcg_kmem_pages and free_memcg_kmem_pages will free
+ * pages allocated with __GFP_KMEMCG.
+ *
+ * Those pages are accounted to a particular memcg, embedded in the
+ * corresponding page_cgroup. To avoid adding a hit in the allocator to search
+ * for that information only to find out that it is NULL for users who have no
+ * interest in that whatsoever, we provide these functions.
+ *
+ * The caller knows better which flags it relies on.
+ */
+void __free_memcg_kmem_pages(struct page *page, unsigned int order)
+{
+	memcg_kmem_uncharge_pages(page, order);
+	__free_pages(page, order);
+}
+
+void free_memcg_kmem_pages(unsigned long addr, unsigned int order)
+{
+	if (addr != 0) {
+		VM_BUG_ON(!virt_addr_valid((void *)addr));
+		__free_memcg_kmem_pages(virt_to_page((void *)addr), order);
+	}
+}
+
 static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size)
 {
 	if (addr) {

mm/slab.c

@@ -87,7 +87,6 @@
  */
 
 #include	<linux/slab.h>
-#include	"slab.h"
 #include	<linux/mm.h>
 #include	<linux/poison.h>
 #include	<linux/swap.h>
@@ -128,6 +127,8 @@
 
 #include	"internal.h"
 
+#include	"slab.h"
+
 /*
  * DEBUG	- 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON.
  *		  0 for faster, smaller code (especially in the critical paths).
@@ -641,6 +642,26 @@ static void init_node_lock_keys(int q)
 	}
 }
 
+static void on_slab_lock_classes_node(struct kmem_cache *cachep, int q)
+{
+	struct kmem_list3 *l3;
+	l3 = cachep->nodelists[q];
+	if (!l3)
+		return;
+
+	slab_set_lock_classes(cachep, &on_slab_l3_key,
+			&on_slab_alc_key, q);
+}
+
+static inline void on_slab_lock_classes(struct kmem_cache *cachep)
+{
+	int node;
+
+	VM_BUG_ON(OFF_SLAB(cachep));
+	for_each_node(node)
+		on_slab_lock_classes_node(cachep, node);
+}
+
 static inline void init_lock_keys(void)
 {
 	int node;
@@ -657,6 +678,14 @@ static inline void init_lock_keys(void)
 {
 }
 
+static inline void on_slab_lock_classes(struct kmem_cache *cachep)
+{
+}
+
+static inline void on_slab_lock_classes_node(struct kmem_cache *cachep, int node)
+{
+}
+
 static void slab_set_debugobj_lock_classes_node(struct kmem_cache *cachep, int node)
 {
 }
@@ -1385,6 +1414,9 @@ static int __cpuinit cpuup_prepare(long cpu)
 		free_alien_cache(alien);
 		if (cachep->flags & SLAB_DEBUG_OBJECTS)
 			slab_set_debugobj_lock_classes_node(cachep, node);
+		else if (!OFF_SLAB(cachep) &&
+			 !(cachep->flags & SLAB_DESTROY_BY_RCU))
+			on_slab_lock_classes_node(cachep, node);
 	}
 	init_node_lock_keys(node);
 
@@ -1863,6 +1895,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 		if (page->pfmemalloc)
 			SetPageSlabPfmemalloc(page + i);
 	}
+	memcg_bind_pages(cachep, cachep->gfporder);
 
 	if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
 		kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid);
@@ -1899,9 +1932,11 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr)
 		__ClearPageSlab(page);
 		page++;
 	}
+
+	memcg_release_pages(cachep, cachep->gfporder);
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += nr_freed;
-	free_pages((unsigned long)addr, cachep->gfporder);
+	free_memcg_kmem_pages((unsigned long)addr, cachep->gfporder);
 }
 
 static void kmem_rcu_free(struct rcu_head *head)
@@ -2489,7 +2524,8 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 		WARN_ON_ONCE(flags & SLAB_DESTROY_BY_RCU);
 
 		slab_set_debugobj_lock_classes(cachep);
-	}
+	} else if (!OFF_SLAB(cachep) && !(flags & SLAB_DESTROY_BY_RCU))
+		on_slab_lock_classes(cachep);
 
 	return 0;
 }
@@ -3453,6 +3489,8 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	if (slab_should_failslab(cachep, flags))
 		return NULL;
 
+	cachep = memcg_kmem_get_cache(cachep, flags);
+
 	cache_alloc_debugcheck_before(cachep, flags);
 	local_irq_save(save_flags);
 
@@ -3538,6 +3576,8 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
 	if (slab_should_failslab(cachep, flags))
 		return NULL;
 
+	cachep = memcg_kmem_get_cache(cachep, flags);
+
 	cache_alloc_debugcheck_before(cachep, flags);
 	local_irq_save(save_flags);
 	objp = __do_cache_alloc(cachep, flags);
@@ -3851,6 +3891,9 @@ EXPORT_SYMBOL(__kmalloc);
 void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 {
 	unsigned long flags;
+	cachep = cache_from_obj(cachep, objp);
+	if (!cachep)
+		return;
 
 	local_irq_save(flags);
 	debug_check_no_locks_freed(objp, cachep->object_size);
@@ -3998,7 +4041,7 @@ static void do_ccupdate_local(void *info)
 }
 
 /* Always called with the slab_mutex held */
-static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
+static int __do_tune_cpucache(struct kmem_cache *cachep, int limit,
 				int batchcount, int shared, gfp_t gfp)
 {
 	struct ccupdate_struct *new;
@@ -4041,12 +4084,49 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
 	return alloc_kmemlist(cachep, gfp);
 }
 
+static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
+				int batchcount, int shared, gfp_t gfp)
+{
+	int ret;
+	struct kmem_cache *c = NULL;
+	int i = 0;
+
+	ret = __do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
+
+	if (slab_state < FULL)
+		return ret;
+
+	if ((ret < 0) || !is_root_cache(cachep))
+		return ret;
+
+	VM_BUG_ON(!mutex_is_locked(&slab_mutex));
+	for_each_memcg_cache_index(i) {
+		c = cache_from_memcg(cachep, i);
+		if (c)
+			/* return value determined by the parent cache only */
+			__do_tune_cpucache(c, limit, batchcount, shared, gfp);
+	}
+
+	return ret;
+}
+
 /* Called with slab_mutex held always */
 static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
 {
 	int err;
-	int limit, shared;
+	int limit = 0;
+	int shared = 0;
+	int batchcount = 0;
+
+	if (!is_root_cache(cachep)) {
+		struct kmem_cache *root = memcg_root_cache(cachep);
+		limit = root->limit;
+		shared = root->shared;
+		batchcount = root->batchcount;
+	}
 
+	if (limit && shared && batchcount)
+		goto skip_setup;
 	/*
 	 * The head array serves three purposes:
 	 * - create a LIFO ordering, i.e. return objects that are cache-warm
@@ -4088,7 +4168,9 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
 	if (limit > 32)
 		limit = 32;
 #endif
-	err = do_tune_cpucache(cachep, limit, (limit + 1) / 2, shared, gfp);
+	batchcount = (limit + 1) / 2;
+skip_setup:
+	err = do_tune_cpucache(cachep, limit, batchcount, shared, gfp);
 	if (err)
 		printk(KERN_ERR "enable_cpucache failed for %s, error %d.\n",
 		       cachep->name, -err);

mm/slab.h

@@ -43,12 +43,15 @@ extern struct kmem_cache *create_kmalloc_cache(const char *name, size_t size,
 extern void create_boot_cache(struct kmem_cache *, const char *name,
 			size_t size, unsigned long flags);
 
+struct mem_cgroup;
 #ifdef CONFIG_SLUB
-struct kmem_cache *__kmem_cache_alias(const char *name, size_t size,
-	size_t align, unsigned long flags, void (*ctor)(void *));
+struct kmem_cache *
+__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size,
+		   size_t align, unsigned long flags, void (*ctor)(void *));
 #else
-static inline struct kmem_cache *__kmem_cache_alias(const char *name, size_t size,
-	size_t align, unsigned long flags, void (*ctor)(void *))
+static inline struct kmem_cache *
+__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size,
+		   size_t align, unsigned long flags, void (*ctor)(void *))
 { return NULL; }
 #endif
 
@@ -100,4 +103,130 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
 void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s);
 ssize_t slabinfo_write(struct file *file, const char __user *buffer,
 		       size_t count, loff_t *ppos);
+
+#ifdef CONFIG_MEMCG_KMEM
+static inline bool is_root_cache(struct kmem_cache *s)
+{
+	return !s->memcg_params || s->memcg_params->is_root_cache;
+}
+
+static inline bool cache_match_memcg(struct kmem_cache *cachep,
+				     struct mem_cgroup *memcg)
+{
+	return (is_root_cache(cachep) && !memcg) ||
+				(cachep->memcg_params->memcg == memcg);
+}
+
+static inline void memcg_bind_pages(struct kmem_cache *s, int order)
+{
+	if (!is_root_cache(s))
+		atomic_add(1 << order, &s->memcg_params->nr_pages);
+}
+
+static inline void memcg_release_pages(struct kmem_cache *s, int order)
+{
+	if (is_root_cache(s))
+		return;
+
+	if (atomic_sub_and_test((1 << order), &s->memcg_params->nr_pages))
+		mem_cgroup_destroy_cache(s);
+}
+
+static inline bool slab_equal_or_root(struct kmem_cache *s,
+					struct kmem_cache *p)
+{
+	return (p == s) ||
+		(s->memcg_params && (p == s->memcg_params->root_cache));
+}
+
+/*
+ * We use suffixes to the name in memcg because we can't have caches
+ * created in the system with the same name. But when we print them
+ * locally, better refer to them with the base name
+ */
+static inline const char *cache_name(struct kmem_cache *s)
+{
+	if (!is_root_cache(s))
+		return s->memcg_params->root_cache->name;
+	return s->name;
+}
+
+static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx)
+{
+	return s->memcg_params->memcg_caches[idx];
+}
+
+static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
+{
+	if (is_root_cache(s))
+		return s;
+	return s->memcg_params->root_cache;
+}
+#else
+static inline bool is_root_cache(struct kmem_cache *s)
+{
+	return true;
+}
+
+static inline bool cache_match_memcg(struct kmem_cache *cachep,
+				     struct mem_cgroup *memcg)
+{
+	return true;
+}
+
+static inline void memcg_bind_pages(struct kmem_cache *s, int order)
+{
+}
+
+static inline void memcg_release_pages(struct kmem_cache *s, int order)
+{
+}
+
+static inline bool slab_equal_or_root(struct kmem_cache *s,
+				      struct kmem_cache *p)
+{
+	return true;
+}
+
+static inline const char *cache_name(struct kmem_cache *s)
+{
+	return s->name;
+}
+
+static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx)
+{
+	return NULL;
+}
+
+static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
+{
+	return s;
+}
+#endif
+
+static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
+{
+	struct kmem_cache *cachep;
+	struct page *page;
+
+	/*
+	 * When kmemcg is not being used, both assignments should return the
+	 * same value. but we don't want to pay the assignment price in that
+	 * case. If it is not compiled in, the compiler should be smart enough
+	 * to not do even the assignment. In that case, slab_equal_or_root
+	 * will also be a constant.
+	 */
+	if (!memcg_kmem_enabled() && !unlikely(s->flags & SLAB_DEBUG_FREE))
+		return s;
+
+	page = virt_to_head_page(x);
+	cachep = page->slab_cache;
+	if (slab_equal_or_root(cachep, s))
+		return cachep;
+
+	pr_err("%s: Wrong slab cache. %s but object is from %s\n",
+		__FUNCTION__, cachep->name, s->name);
+	WARN_ON_ONCE(1);
+	return s;
+}
 #endif

mm/slab_common.c

@@ -18,6 +18,7 @@
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/page.h>
+#include <linux/memcontrol.h>
 
 #include "slab.h"
 
@@ -27,7 +28,8 @@ DEFINE_MUTEX(slab_mutex);
 struct kmem_cache *kmem_cache;
 
 #ifdef CONFIG_DEBUG_VM
-static int kmem_cache_sanity_check(const char *name, size_t size)
+static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
+				   size_t size)
 {
 	struct kmem_cache *s = NULL;
 
@@ -53,7 +55,13 @@ static int kmem_cache_sanity_check(const char *name, size_t size)
 			continue;
 		}
 
-		if (!strcmp(s->name, name)) {
+		/*
+		 * For simplicity, we won't check this in the list of memcg
+		 * caches. We have control over memcg naming, and if there
+		 * aren't duplicates in the global list, there won't be any
+		 * duplicates in the memcg lists as well.
+		 */
+		if (!memcg && !strcmp(s->name, name)) {
 			pr_err("%s (%s): Cache name already exists.\n",
 			       __func__, name);
 			dump_stack();
@@ -66,12 +74,41 @@ static int kmem_cache_sanity_check(const char *name, size_t size)
 	return 0;
 }
 #else
-static inline int kmem_cache_sanity_check(const char *name, size_t size)
+static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg,
+					  const char *name, size_t size)
 {
 	return 0;
 }
 #endif
 
+#ifdef CONFIG_MEMCG_KMEM
+int memcg_update_all_caches(int num_memcgs)
+{
+	struct kmem_cache *s;
+	int ret = 0;
+	mutex_lock(&slab_mutex);
+
+	list_for_each_entry(s, &slab_caches, list) {
+		if (!is_root_cache(s))
+			continue;
+
+		ret = memcg_update_cache_size(s, num_memcgs);
+		/*
+		 * See comment in memcontrol.c, memcg_update_cache_size:
+		 * Instead of freeing the memory, we'll just leave the caches
+		 * up to this point in an updated state.
+		 */
+		if (ret)
+			goto out;
+	}
+
+	memcg_update_array_size(num_memcgs);
+out:
+	mutex_unlock(&slab_mutex);
+	return ret;
+}
+#endif
+
 /*
  * Figure out what the alignment of the objects will be given a set of
  * flags, a user specified alignment and the size of the objects.
@@ -125,8 +162,10 @@ unsigned long calculate_alignment(unsigned long flags,
  * as davem.
  */
 
-struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align,
-		unsigned long flags, void (*ctor)(void *))
+struct kmem_cache *
+kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
+			size_t align, unsigned long flags, void (*ctor)(void *),
+			struct kmem_cache *parent_cache)
 {
 	struct kmem_cache *s = NULL;
 	int err = 0;
@@ -134,7 +173,7 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align
 	get_online_cpus();
 	mutex_lock(&slab_mutex);
 
-	if (!kmem_cache_sanity_check(name, size) == 0)
+	if (!kmem_cache_sanity_check(memcg, name, size) == 0)
 		goto out_locked;
 
 	/*
@@ -145,7 +184,7 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align
 	 */
 	flags &= CACHE_CREATE_MASK;
 
-	s = __kmem_cache_alias(name, size, align, flags, ctor);
+	s = __kmem_cache_alias(memcg, name, size, align, flags, ctor);
 	if (s)
 		goto out_locked;
 
@@ -154,6 +193,13 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align
 		s->object_size = s->size = size;
 		s->align = calculate_alignment(flags, align, size);
 		s->ctor = ctor;
+
+		if (memcg_register_cache(memcg, s, parent_cache)) {
+			kmem_cache_free(kmem_cache, s);
+			err = -ENOMEM;
+			goto out_locked;
+		}
+
 		s->name = kstrdup(name, GFP_KERNEL);
 		if (!s->name) {
 			kmem_cache_free(kmem_cache, s);
@@ -163,10 +209,9 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align
 
 		err = __kmem_cache_create(s, flags);
 		if (!err) {
-
 			s->refcount = 1;
 			list_add(&s->list, &slab_caches);
-
+			memcg_cache_list_add(memcg, s);
 		} else {
 			kfree(s->name);
 			kmem_cache_free(kmem_cache, s);
@@ -194,10 +239,20 @@ out_locked:
 
 	return s;
 }
+
+struct kmem_cache *
+kmem_cache_create(const char *name, size_t size, size_t align,
+		  unsigned long flags, void (*ctor)(void *))
+{
+	return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor, NULL);
+}
 EXPORT_SYMBOL(kmem_cache_create);
 
 void kmem_cache_destroy(struct kmem_cache *s)
 {
+	/* Destroy all the children caches if we aren't a memcg cache */
+	kmem_cache_destroy_memcg_children(s);
+
 	get_online_cpus();
 	mutex_lock(&slab_mutex);
 	s->refcount--;
@@ -209,6 +264,7 @@ void kmem_cache_destroy(struct kmem_cache *s)
 			if (s->flags & SLAB_DESTROY_BY_RCU)
 				rcu_barrier();
 
+			memcg_release_cache(s);
 			kfree(s->name);
 			kmem_cache_free(kmem_cache, s);
 		} else {
@@ -267,7 +323,7 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
 
 
 #ifdef CONFIG_SLABINFO
-static void print_slabinfo_header(struct seq_file *m)
+void print_slabinfo_header(struct seq_file *m)
 {
 	/*
 	 * Output format version, so at least we can change it
@@ -311,16 +367,43 @@ static void s_stop(struct seq_file *m, void *p)
 	mutex_unlock(&slab_mutex);
 }
 
-static int s_show(struct seq_file *m, void *p)
+static void
+memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
+{
+	struct kmem_cache *c;
+	struct slabinfo sinfo;
+	int i;
+
+	if (!is_root_cache(s))
+		return;
+
+	for_each_memcg_cache_index(i) {
+		c = cache_from_memcg(s, i);
+		if (!c)
+			continue;
+
+		memset(&sinfo, 0, sizeof(sinfo));
+		get_slabinfo(c, &sinfo);
+
+		info->active_slabs += sinfo.active_slabs;
+		info->num_slabs += sinfo.num_slabs;
+		info->shared_avail += sinfo.shared_avail;
+		info->active_objs += sinfo.active_objs;
+		info->num_objs += sinfo.num_objs;
+	}
+}
+
+int cache_show(struct kmem_cache *s, struct seq_file *m)
 {
-	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
 	struct slabinfo sinfo;
 
 	memset(&sinfo, 0, sizeof(sinfo));
 	get_slabinfo(s, &sinfo);
 
+	memcg_accumulate_slabinfo(s, &sinfo);
+
 	seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d",
-		   s->name, sinfo.active_objs, sinfo.num_objs, s->size,
+		   cache_name(s), sinfo.active_objs, sinfo.num_objs, s->size,
 		   sinfo.objects_per_slab, (1 << sinfo.cache_order));
 
 	seq_printf(m, " : tunables %4u %4u %4u",
@@ -332,6 +415,15 @@ static int s_show(struct seq_file *m, void *p)
 	return 0;
 }
 
+static int s_show(struct seq_file *m, void *p)
+{
+	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
+
+	if (!is_root_cache(s))
+		return 0;
+	return cache_show(s, m);
+}
+
 /*
  * slabinfo_op - iterator that generates /proc/slabinfo
  *

mm/slob.c

@@ -58,7 +58,6 @@
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include "slab.h"
 
 #include <linux/mm.h>
 #include <linux/swap.h> /* struct reclaim_state */
@@ -73,6 +72,7 @@
 
 #include <linux/atomic.h>
 
+#include "slab.h"
 /*
  * slob_block has a field 'units', which indicates size of block if +ve,
  * or offset of next block if -ve (in SLOB_UNITs).

mm/slub.c

@@ -31,6 +31,7 @@
 #include <linux/fault-inject.h>
 #include <linux/stacktrace.h>
 #include <linux/prefetch.h>
+#include <linux/memcontrol.h>
 
 #include <trace/events/kmem.h>
 
@@ -200,13 +201,14 @@ enum track_item { TRACK_ALLOC, TRACK_FREE };
 static int sysfs_slab_add(struct kmem_cache *);
 static int sysfs_slab_alias(struct kmem_cache *, const char *);
 static void sysfs_slab_remove(struct kmem_cache *);
-
+static void memcg_propagate_slab_attrs(struct kmem_cache *s);
 #else
 static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
 static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
 							{ return 0; }
 static inline void sysfs_slab_remove(struct kmem_cache *s) { }
 
+static inline void memcg_propagate_slab_attrs(struct kmem_cache *s) { }
 #endif
 
 static inline void stat(const struct kmem_cache *s, enum stat_item si)
@@ -1343,6 +1345,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	void *start;
 	void *last;
 	void *p;
+	int order;
 
 	BUG_ON(flags & GFP_SLAB_BUG_MASK);
 
@@ -1351,7 +1354,9 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	if (!page)
 		goto out;
 
+	order = compound_order(page);
 	inc_slabs_node(s, page_to_nid(page), page->objects);
+	memcg_bind_pages(s, order);
 	page->slab_cache = s;
 	__SetPageSlab(page);
 	if (page->pfmemalloc)
@@ -1360,7 +1365,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	start = page_address(page);
 
 	if (unlikely(s->flags & SLAB_POISON))
-		memset(start, POISON_INUSE, PAGE_SIZE << compound_order(page));
+		memset(start, POISON_INUSE, PAGE_SIZE << order);
 
 	last = start;
 	for_each_object(p, s, start, page->objects) {
@@ -1401,10 +1406,12 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 
 	__ClearPageSlabPfmemalloc(page);
 	__ClearPageSlab(page);
+
+	memcg_release_pages(s, order);
 	reset_page_mapcount(page);
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += pages;
-	__free_pages(page, order);
+	__free_memcg_kmem_pages(page, order);
 }
 
 #define need_reserve_slab_rcu						\
@@ -2322,6 +2329,7 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s,
 	if (slab_pre_alloc_hook(s, gfpflags))
 		return NULL;
 
+	s = memcg_kmem_get_cache(s, gfpflags);
 redo:
 
 	/*
@@ -2610,19 +2618,10 @@ redo:
 
 void kmem_cache_free(struct kmem_cache *s, void *x)
 {
-	struct page *page;
-
-	page = virt_to_head_page(x);
-
-	if (kmem_cache_debug(s) && page->slab_cache != s) {
-		pr_err("kmem_cache_free: Wrong slab cache. %s but object"
-			" is from  %s\n", page->slab_cache->name, s->name);
-		WARN_ON_ONCE(1);
+	s = cache_from_obj(s, x);
+	if (!s)
 		return;
-	}
-
-	slab_free(s, page, x, _RET_IP_);
-
+	slab_free(s, virt_to_head_page(x), x, _RET_IP_);
 	trace_kmem_cache_free(_RET_IP_, x);
 }
 EXPORT_SYMBOL(kmem_cache_free);
@@ -3154,8 +3153,19 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
 {
 	int rc = kmem_cache_close(s);
 
-	if (!rc)
+	if (!rc) {
+		/*
+		 * We do the same lock strategy around sysfs_slab_add, see
+		 * __kmem_cache_create. Because this is pretty much the last
+		 * operation we do and the lock will be released shortly after
+		 * that in slab_common.c, we could just move sysfs_slab_remove
+		 * to a later point in common code. We should do that when we
+		 * have a common sysfs framework for all allocators.
+		 */
+		mutex_unlock(&slab_mutex);
 		sysfs_slab_remove(s);
+		mutex_lock(&slab_mutex);
+	}
 
 	return rc;
 }
@@ -3292,7 +3302,7 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 	struct page *page;
 	void *ptr = NULL;
 
-	flags |= __GFP_COMP | __GFP_NOTRACK;
+	flags |= __GFP_COMP | __GFP_NOTRACK | __GFP_KMEMCG;
 	page = alloc_pages_node(node, flags, get_order(size));
 	if (page)
 		ptr = page_address(page);
@@ -3398,7 +3408,7 @@ void kfree(const void *x)
 	if (unlikely(!PageSlab(page))) {
 		BUG_ON(!PageCompound(page));
 		kmemleak_free(x);
-		__free_pages(page, compound_order(page));
+		__free_memcg_kmem_pages(page, compound_order(page));
 		return;
 	}
 	slab_free(page->slab_cache, page, object, _RET_IP_);
@@ -3786,7 +3796,7 @@ static int slab_unmergeable(struct kmem_cache *s)
 	return 0;
 }
 
-static struct kmem_cache *find_mergeable(size_t size,
+static struct kmem_cache *find_mergeable(struct mem_cgroup *memcg, size_t size,
 		size_t align, unsigned long flags, const char *name,
 		void (*ctor)(void *))
 {
@@ -3822,17 +3832,21 @@ static struct kmem_cache *find_mergeable(size_t size,
 		if (s->size - size >= sizeof(void *))
 			continue;
 
+		if (!cache_match_memcg(s, memcg))
+			continue;
+
 		return s;
 	}
 	return NULL;
 }
 
-struct kmem_cache *__kmem_cache_alias(const char *name, size_t size,
-		size_t align, unsigned long flags, void (*ctor)(void *))
+struct kmem_cache *
+__kmem_cache_alias(struct mem_cgroup *memcg, const char *name, size_t size,
+		   size_t align, unsigned long flags, void (*ctor)(void *))
 {
 	struct kmem_cache *s;
 
-	s = find_mergeable(size, align, flags, name, ctor);
+	s = find_mergeable(memcg, size, align, flags, name, ctor);
 	if (s) {
 		s->refcount++;
 		/*
@@ -3863,6 +3877,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags)
 	if (slab_state <= UP)
 		return 0;
 
+	memcg_propagate_slab_attrs(s);
 	mutex_unlock(&slab_mutex);
 	err = sysfs_slab_add(s);
 	mutex_lock(&slab_mutex);
@@ -5096,10 +5111,95 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 		return -EIO;
 
 	err = attribute->store(s, buf, len);
+#ifdef CONFIG_MEMCG_KMEM
+	if (slab_state >= FULL && err >= 0 && is_root_cache(s)) {
+		int i;
 
+		mutex_lock(&slab_mutex);
+		if (s->max_attr_size < len)
+			s->max_attr_size = len;
+
+		/*
+		 * This is a best effort propagation, so this function's return
+		 * value will be determined by the parent cache only. This is
+		 * basically because not all attributes will have a well
+		 * defined semantics for rollbacks - most of the actions will
+		 * have permanent effects.
+		 *
+		 * Returning the error value of any of the children that fail
+		 * is not 100 % defined, in the sense that users seeing the
+		 * error code won't be able to know anything about the state of
+		 * the cache.
+		 *
+		 * Only returning the error code for the parent cache at least
+		 * has well defined semantics. The cache being written to
+		 * directly either failed or succeeded, in which case we loop
+		 * through the descendants with best-effort propagation.
+		 */
+		for_each_memcg_cache_index(i) {
+			struct kmem_cache *c = cache_from_memcg(s, i);
+			if (c)
+				attribute->store(c, buf, len);
+		}
+		mutex_unlock(&slab_mutex);
+	}
+#endif
 	return err;
 }
 
+static void memcg_propagate_slab_attrs(struct kmem_cache *s)
+{
+#ifdef CONFIG_MEMCG_KMEM
+	int i;
+	char *buffer = NULL;
+
+	if (!is_root_cache(s))
+		return;
+
+	/*
+	 * This mean this cache had no attribute written. Therefore, no point
+	 * in copying default values around
+	 */
+	if (!s->max_attr_size)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(slab_attrs); i++) {
+		char mbuf[64];
+		char *buf;
+		struct slab_attribute *attr = to_slab_attr(slab_attrs[i]);
+
+		if (!attr || !attr->store || !attr->show)
+			continue;
+
+		/*
+		 * It is really bad that we have to allocate here, so we will
+		 * do it only as a fallback. If we actually allocate, though,
+		 * we can just use the allocated buffer until the end.
+		 *
+		 * Most of the slub attributes will tend to be very small in
+		 * size, but sysfs allows buffers up to a page, so they can
+		 * theoretically happen.
+		 */
+		if (buffer)
+			buf = buffer;
+		else if (s->max_attr_size < ARRAY_SIZE(mbuf))
+			buf = mbuf;
+		else {
+			buffer = (char *) get_zeroed_page(GFP_KERNEL);
+			if (WARN_ON(!buffer))
+				continue;
+			buf = buffer;
+		}
+
+		attr->show(s->memcg_params->root_cache, buf);
+		attr->store(s, buf, strlen(buf));
+	}
+
+	if (buffer)
+		free_page((unsigned long)buffer);
+#endif
+}
+
 static const struct sysfs_ops slab_sysfs_ops = {
 	.show = slab_attr_show,
 	.store = slab_attr_store,
@@ -5156,6 +5256,12 @@ static char *create_unique_id(struct kmem_cache *s)
 	if (p != name + 1)
 		*p++ = '-';
 	p += sprintf(p, "%07d", s->size);
+
+#ifdef CONFIG_MEMCG_KMEM
+	if (!is_root_cache(s))
+		p += sprintf(p, "-%08d", memcg_cache_id(s->memcg_params->memcg));
+#endif
+
 	BUG_ON(p > name + ID_STR_LENGTH - 1);
 	return name;
 }

mm/vmscan.c

@@ -1177,7 +1177,11 @@ int isolate_lru_page(struct page *page)
 }
 
 /*
- * Are there way too many processes in the direct reclaim path already?
+ * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and
+ * then get resheduled. When there are massive number of tasks doing page
+ * allocation, such sleeping direct reclaimers may keep piling up on each CPU,
+ * the LRU list will go small and be scanned faster than necessary, leading to
+ * unnecessary swapping, thrashing and OOM.
  */
 static int too_many_isolated(struct zone *zone, int file,
 		struct scan_control *sc)
@@ -1198,6 +1202,14 @@ static int too_many_isolated(struct zone *zone, int file,
 		isolated = zone_page_state(zone, NR_ISOLATED_ANON);
 	}
 
+	/*
+	 * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they
+	 * won't get blocked by normal direct-reclaimers, forming a circular
+	 * deadlock.
+	 */
+	if ((sc->gfp_mask & GFP_IOFS) == GFP_IOFS)
+		inactive >>= 3;
+
 	return isolated > inactive;
 }
 

scripts/coccinelle/api/d_find_alias.cocci

@@ -0,0 +1,80 @@
+/// Make sure calls to d_find_alias() have a corresponding call to dput().
+//
+// Keywords: d_find_alias, dput
+//
+// Confidence: Moderate
+// URL: http://coccinelle.lip6.fr/
+// Options: -include_headers
+
+virtual context
+virtual org
+virtual patch
+virtual report
+
+@r exists@
+local idexpression struct dentry *dent;
+expression E, E1;
+statement S1, S2;
+position p1, p2;
+@@
+(
+	if (!(dent@p1 = d_find_alias(...))) S1
+|
+	dent@p1 = d_find_alias(...)
+)
+
+<...when != dput(dent)
+    when != if (...) { <+... dput(dent) ...+> }
+    when != true !dent || ...
+    when != dent = E
+    when != E = dent
+if (!dent || ...) S2
+...>
+(
+	return <+...dent...+>;
+|
+	return @p2 ...;
+|
+	dent@p2 = E1;
+|
+	E1 = dent;
+)
+
+@depends on context@
+local idexpression struct dentry *r.dent;
+position r.p1,r.p2;
+@@
+* dent@p1 = ...
+  ...
+(
+* return@p2 ...;
+|
+* dent@p2
+)
+
+
+@script:python depends on org@
+p1 << r.p1;
+p2 << r.p2;
+@@
+cocci.print_main("Missing call to dput()",p1)
+cocci.print_secs("",p2)
+
+@depends on patch@
+local idexpression struct dentry *r.dent;
+position r.p2;
+@@
+(
++ dput(dent);
+  return @p2 ...;
+|
++ dput(dent);
+  dent@p2 = ...;
+)
+
+@script:python depends on report@
+p1 << r.p1;
+p2 << r.p2;
+@@
+msg = "Missing call to dput() at line %s."
+coccilib.report.print_report(p1[0], msg % (p2[0].line))