@@ -74,6 +74,12 @@ Brief summary of control files.
  memory.kmem.tcp.limit_in_bytes  # set/show hard limit for tcp buf memory
  memory.kmem.tcp.usage_in_bytes  # show current tcp buf memory allocation
 
+ memory.kmem.limit_in_bytes	 # set/show hard limit for general kmem memory
+ memory.kmem.usage_in_bytes	 # show current general kmem memory allocation
+ memory.kmem.failcnt		 # show current number of kmem limit hits
+ memory.kmem.max_usage_in_bytes	 # show max kmem usage
+ memory.kmem.slabinfo		 # show cgroup-specific slab usage information
+
 1. History
 
 The memory controller has a long history. A request for comments for the memory

@@ -270,6 +276,14 @@ cgroup may or may not be accounted.
 Currently no soft limit is implemented for kernel memory. It is future work
 to trigger slab reclaim when those limits are reached.
 
+Kernel memory is not accounted until it is limited. Users that want to just
+track kernel memory usage can set the limit value to a big enough value so
+the limit is guaranteed to never hit. A kernel memory limit bigger than the
+current memory limit will have this effect as well.
+
+This guarantes that this extension is backwards compatible to any previous
+memory cgroup version.
+
 2.7.1 Current Kernel Memory resources accounted
 
 * sockets memory pressure: some sockets protocols have memory pressure

@@ -278,6 +292,24 @@ per cgroup, instead of globally.
 
 * tcp memory pressure: sockets memory pressure for the tcp protocol.
 
+* slab/kmalloc:
+
+When slab memory is tracked (memory.kmem.limit_in_bytes != -1ULL), both
+memory.kmem.usage_in_bytes and memory.usage_in_bytes are updated. When
+memory.kmem.limit_in_bytes is left alone, no tracking of slab caches takes
+place.
+
+Because a slab page is shared among many tasks, it is not possible to take
+any meaningful action upon task migration. Slabs created in a cgroup stay
+around until the cgroup is destructed. Information about the slabs used
+by the cgroup is displayed in the cgroup file memory.kmem.slabinfo. The format
+of this file is and should remain compatible with /proc/slabinfo.
+
+Upon cgroup destruction, slabs that holds no live references are destructed.
+Workers are fired to destroy the remaining caches as they objects are freed.
+
+Memory used by dead caches are shown in the proc file /proc/dead_slabinfo
+
 3. User Interface
 
 0. Configuration

@@ -286,6 +318,7 @@ a. Enable CONFIG_CGROUPS
 b. Enable CONFIG_RESOURCE_COUNTERS
 c. Enable CONFIG_CGROUP_MEM_RES_CTLR
 d. Enable CONFIG_CGROUP_MEM_RES_CTLR_SWAP (to use swap extension)
+d. Enable CONFIG_CGROUP_MEM_RES_CTLR_KMEM (to use experimental kmem extension)
 
 1. Prepare the cgroups (see cgroups.txt, Why are cgroups needed?)
 # mount -t tmpfs none /sys/fs/cgroup