summaryrefslogtreecommitdiffstats
path: root/Documentation/vm
diff options
context:
space:
mode:
Diffstat (limited to 'Documentation/vm')
-rw-r--r--Documentation/vm/00-INDEX16
-rw-r--r--Documentation/vm/Makefile2
-rw-r--r--Documentation/vm/hugepage-mmap.c91
-rw-r--r--Documentation/vm/hugepage-shm.c98
-rw-r--r--Documentation/vm/hugetlbpage.txt169
-rw-r--r--Documentation/vm/map_hugetlb.c8
-rw-r--r--Documentation/vm/numa186
-rw-r--r--Documentation/vm/numa_memory_policy.txt4
-rw-r--r--Documentation/vm/slub.txt1
9 files changed, 360 insertions, 215 deletions
diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX
index e57d6a9dd32b..dca82d7c83d8 100644
--- a/Documentation/vm/00-INDEX
+++ b/Documentation/vm/00-INDEX
@@ -4,23 +4,35 @@ active_mm.txt
- An explanation from Linus about tsk->active_mm vs tsk->mm.
balance
- various information on memory balancing.
+hugepage-mmap.c
+ - Example app using huge page memory with the mmap system call.
+hugepage-shm.c
+ - Example app using huge page memory with Sys V shared memory system calls.
hugetlbpage.txt
- a brief summary of hugetlbpage support in the Linux kernel.
+hwpoison.txt
+ - explains what hwpoison is
ksm.txt
- how to use the Kernel Samepage Merging feature.
locking
- info on how locking and synchronization is done in the Linux vm code.
+map_hugetlb.c
+ - an example program that uses the MAP_HUGETLB mmap flag.
numa
- information about NUMA specific code in the Linux vm.
numa_memory_policy.txt
- documentation of concepts and APIs of the 2.6 memory policy support.
overcommit-accounting
- description of the Linux kernels overcommit handling modes.
+page-types.c
+ - Tool for querying page flags
page_migration
- description of page migration in NUMA systems.
+pagemap.txt
+ - pagemap, from the userspace perspective
slabinfo.c
- source code for a tool to get reports about slabs.
slub.txt
- a short users guide for SLUB.
-map_hugetlb.c
- - an example program that uses the MAP_HUGETLB mmap flag.
+unevictable-lru.txt
+ - Unevictable LRU infrastructure
diff --git a/Documentation/vm/Makefile b/Documentation/vm/Makefile
index 5bd269b3731a..9dcff328b964 100644
--- a/Documentation/vm/Makefile
+++ b/Documentation/vm/Makefile
@@ -2,7 +2,7 @@
obj- := dummy.o
# List of programs to build
-hostprogs-y := slabinfo page-types
+hostprogs-y := slabinfo page-types hugepage-mmap hugepage-shm map_hugetlb
# Tell kbuild to always build the programs
always := $(hostprogs-y)
diff --git a/Documentation/vm/hugepage-mmap.c b/Documentation/vm/hugepage-mmap.c
new file mode 100644
index 000000000000..db0dd9a33d54
--- /dev/null
+++ b/Documentation/vm/hugepage-mmap.c
@@ -0,0 +1,91 @@
+/*
+ * hugepage-mmap:
+ *
+ * Example of using huge page memory in a user application using the mmap
+ * system call. Before running this application, make sure that the
+ * administrator has mounted the hugetlbfs filesystem (on some directory
+ * like /mnt) using the command mount -t hugetlbfs nodev /mnt. In this
+ * example, the app is requesting memory of size 256MB that is backed by
+ * huge pages.
+ *
+ * For the ia64 architecture, the Linux kernel reserves Region number 4 for
+ * huge pages. That means that if one requires a fixed address, a huge page
+ * aligned address starting with 0x800000... will be required. If a fixed
+ * address is not required, the kernel will select an address in the proper
+ * range.
+ * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+
+#define FILE_NAME "/mnt/hugepagefile"
+#define LENGTH (256UL*1024*1024)
+#define PROTECTION (PROT_READ | PROT_WRITE)
+
+/* Only ia64 requires this */
+#ifdef __ia64__
+#define ADDR (void *)(0x8000000000000000UL)
+#define FLAGS (MAP_SHARED | MAP_FIXED)
+#else
+#define ADDR (void *)(0x0UL)
+#define FLAGS (MAP_SHARED)
+#endif
+
+static void check_bytes(char *addr)
+{
+ printf("First hex is %x\n", *((unsigned int *)addr));
+}
+
+static void write_bytes(char *addr)
+{
+ unsigned long i;
+
+ for (i = 0; i < LENGTH; i++)
+ *(addr + i) = (char)i;
+}
+
+static void read_bytes(char *addr)
+{
+ unsigned long i;
+
+ check_bytes(addr);
+ for (i = 0; i < LENGTH; i++)
+ if (*(addr + i) != (char)i) {
+ printf("Mismatch at %lu\n", i);
+ break;
+ }
+}
+
+int main(void)
+{
+ void *addr;
+ int fd;
+
+ fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755);
+ if (fd < 0) {
+ perror("Open failed");
+ exit(1);
+ }
+
+ addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, fd, 0);
+ if (addr == MAP_FAILED) {
+ perror("mmap");
+ unlink(FILE_NAME);
+ exit(1);
+ }
+
+ printf("Returned address is %p\n", addr);
+ check_bytes(addr);
+ write_bytes(addr);
+ read_bytes(addr);
+
+ munmap(addr, LENGTH);
+ close(fd);
+ unlink(FILE_NAME);
+
+ return 0;
+}
diff --git a/Documentation/vm/hugepage-shm.c b/Documentation/vm/hugepage-shm.c
new file mode 100644
index 000000000000..07956d8592c9
--- /dev/null
+++ b/Documentation/vm/hugepage-shm.c
@@ -0,0 +1,98 @@
+/*
+ * hugepage-shm:
+ *
+ * Example of using huge page memory in a user application using Sys V shared
+ * memory system calls. In this example the app is requesting 256MB of
+ * memory that is backed by huge pages. The application uses the flag
+ * SHM_HUGETLB in the shmget system call to inform the kernel that it is
+ * requesting huge pages.
+ *
+ * For the ia64 architecture, the Linux kernel reserves Region number 4 for
+ * huge pages. That means that if one requires a fixed address, a huge page
+ * aligned address starting with 0x800000... will be required. If a fixed
+ * address is not required, the kernel will select an address in the proper
+ * range.
+ * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
+ *
+ * Note: The default shared memory limit is quite low on many kernels,
+ * you may need to increase it via:
+ *
+ * echo 268435456 > /proc/sys/kernel/shmmax
+ *
+ * This will increase the maximum size per shared memory segment to 256MB.
+ * The other limit that you will hit eventually is shmall which is the
+ * total amount of shared memory in pages. To set it to 16GB on a system
+ * with a 4kB pagesize do:
+ *
+ * echo 4194304 > /proc/sys/kernel/shmall
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/ipc.h>
+#include <sys/shm.h>
+#include <sys/mman.h>
+
+#ifndef SHM_HUGETLB
+#define SHM_HUGETLB 04000
+#endif
+
+#define LENGTH (256UL*1024*1024)
+
+#define dprintf(x) printf(x)
+
+/* Only ia64 requires this */
+#ifdef __ia64__
+#define ADDR (void *)(0x8000000000000000UL)
+#define SHMAT_FLAGS (SHM_RND)
+#else
+#define ADDR (void *)(0x0UL)
+#define SHMAT_FLAGS (0)
+#endif
+
+int main(void)
+{
+ int shmid;
+ unsigned long i;
+ char *shmaddr;
+
+ if ((shmid = shmget(2, LENGTH,
+ SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W)) < 0) {
+ perror("shmget");
+ exit(1);
+ }
+ printf("shmid: 0x%x\n", shmid);
+
+ shmaddr = shmat(shmid, ADDR, SHMAT_FLAGS);
+ if (shmaddr == (char *)-1) {
+ perror("Shared memory attach failure");
+ shmctl(shmid, IPC_RMID, NULL);
+ exit(2);
+ }
+ printf("shmaddr: %p\n", shmaddr);
+
+ dprintf("Starting the writes:\n");
+ for (i = 0; i < LENGTH; i++) {
+ shmaddr[i] = (char)(i);
+ if (!(i % (1024 * 1024)))
+ dprintf(".");
+ }
+ dprintf("\n");
+
+ dprintf("Starting the Check...");
+ for (i = 0; i < LENGTH; i++)
+ if (shmaddr[i] != (char)i)
+ printf("\nIndex %lu mismatched\n", i);
+ dprintf("Done.\n");
+
+ if (shmdt((const void *)shmaddr) != 0) {
+ perror("Detach failure");
+ shmctl(shmid, IPC_RMID, NULL);
+ exit(3);
+ }
+
+ shmctl(shmid, IPC_RMID, NULL);
+
+ return 0;
+}
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt
index bc31636973e3..457634c1e03e 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/vm/hugetlbpage.txt
@@ -299,176 +299,11 @@ map_hugetlb.c.
*******************************************************************
/*
- * Example of using huge page memory in a user application using Sys V shared
- * memory system calls. In this example the app is requesting 256MB of
- * memory that is backed by huge pages. The application uses the flag
- * SHM_HUGETLB in the shmget system call to inform the kernel that it is
- * requesting huge pages.
- *
- * For the ia64 architecture, the Linux kernel reserves Region number 4 for
- * huge pages. That means that if one requires a fixed address, a huge page
- * aligned address starting with 0x800000... will be required. If a fixed
- * address is not required, the kernel will select an address in the proper
- * range.
- * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
- *
- * Note: The default shared memory limit is quite low on many kernels,
- * you may need to increase it via:
- *
- * echo 268435456 > /proc/sys/kernel/shmmax
- *
- * This will increase the maximum size per shared memory segment to 256MB.
- * The other limit that you will hit eventually is shmall which is the
- * total amount of shared memory in pages. To set it to 16GB on a system
- * with a 4kB pagesize do:
- *
- * echo 4194304 > /proc/sys/kernel/shmall
+ * hugepage-shm: see Documentation/vm/hugepage-shm.c
*/
-#include <stdlib.h>
-#include <stdio.h>
-#include <sys/types.h>
-#include <sys/ipc.h>
-#include <sys/shm.h>
-#include <sys/mman.h>
-
-#ifndef SHM_HUGETLB
-#define SHM_HUGETLB 04000
-#endif
-
-#define LENGTH (256UL*1024*1024)
-
-#define dprintf(x) printf(x)
-
-#define ADDR (void *)(0x0UL) /* let kernel choose address */
-#define SHMAT_FLAGS (0)
-
-int main(void)
-{
- int shmid;
- unsigned long i;
- char *shmaddr;
-
- if ((shmid = shmget(2, LENGTH,
- SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W)) < 0) {
- perror("shmget");
- exit(1);
- }
- printf("shmid: 0x%x\n", shmid);
-
- shmaddr = shmat(shmid, ADDR, SHMAT_FLAGS);
- if (shmaddr == (char *)-1) {
- perror("Shared memory attach failure");
- shmctl(shmid, IPC_RMID, NULL);
- exit(2);
- }
- printf("shmaddr: %p\n", shmaddr);
-
- dprintf("Starting the writes:\n");
- for (i = 0; i < LENGTH; i++) {
- shmaddr[i] = (char)(i);
- if (!(i % (1024 * 1024)))
- dprintf(".");
- }
- dprintf("\n");
-
- dprintf("Starting the Check...");
- for (i = 0; i < LENGTH; i++)
- if (shmaddr[i] != (char)i)
- printf("\nIndex %lu mismatched\n", i);
- dprintf("Done.\n");
-
- if (shmdt((const void *)shmaddr) != 0) {
- perror("Detach failure");
- shmctl(shmid, IPC_RMID, NULL);
- exit(3);
- }
-
- shmctl(shmid, IPC_RMID, NULL);
-
- return 0;
-}
*******************************************************************
/*
- * Example of using huge page memory in a user application using the mmap
- * system call. Before running this application, make sure that the
- * administrator has mounted the hugetlbfs filesystem (on some directory
- * like /mnt) using the command mount -t hugetlbfs nodev /mnt. In this
- * example, the app is requesting memory of size 256MB that is backed by
- * huge pages.
- *
- * For the ia64 architecture, the Linux kernel reserves Region number 4 for
- * huge pages. That means that if one requires a fixed address, a huge page
- * aligned address starting with 0x800000... will be required. If a fixed
- * address is not required, the kernel will select an address in the proper
- * range.
- * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
+ * hugepage-mmap: see Documentation/vm/hugepage-mmap.c
*/
-#include <stdlib.h>
-#include <stdio.h>
-#include <unistd.h>
-#include <sys/mman.h>
-#include <fcntl.h>
-
-#define FILE_NAME "/mnt/hugepagefile"
-#define LENGTH (256UL*1024*1024)
-#define PROTECTION (PROT_READ | PROT_WRITE)
-
-#define ADDR (void *)(0x0UL) /* let kernel choose address */
-#define FLAGS (MAP_SHARED)
-
-void check_bytes(char *addr)
-{
- printf("First hex is %x\n", *((unsigned int *)addr));
-}
-
-void write_bytes(char *addr)
-{
- unsigned long i;
-
- for (i = 0; i < LENGTH; i++)
- *(addr + i) = (char)i;
-}
-
-void read_bytes(char *addr)
-{
- unsigned long i;
-
- check_bytes(addr);
- for (i = 0; i < LENGTH; i++)
- if (*(addr + i) != (char)i) {
- printf("Mismatch at %lu\n", i);
- break;
- }
-}
-
-int main(void)
-{
- void *addr;
- int fd;
-
- fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755);
- if (fd < 0) {
- perror("Open failed");
- exit(1);
- }
-
- addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, fd, 0);
- if (addr == MAP_FAILED) {
- perror("mmap");
- unlink(FILE_NAME);
- exit(1);
- }
-
- printf("Returned address is %p\n", addr);
- check_bytes(addr);
- write_bytes(addr);
- read_bytes(addr);
-
- munmap(addr, LENGTH);
- close(fd);
- unlink(FILE_NAME);
-
- return 0;
-}
diff --git a/Documentation/vm/map_hugetlb.c b/Documentation/vm/map_hugetlb.c
index e2bdae37f499..eda1a6d3578a 100644
--- a/Documentation/vm/map_hugetlb.c
+++ b/Documentation/vm/map_hugetlb.c
@@ -19,7 +19,7 @@
#define PROTECTION (PROT_READ | PROT_WRITE)
#ifndef MAP_HUGETLB
-#define MAP_HUGETLB 0x40
+#define MAP_HUGETLB 0x40000 /* arch specific */
#endif
/* Only ia64 requires this */
@@ -31,12 +31,12 @@
#define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
#endif
-void check_bytes(char *addr)
+static void check_bytes(char *addr)
{
printf("First hex is %x\n", *((unsigned int *)addr));
}
-void write_bytes(char *addr)
+static void write_bytes(char *addr)
{
unsigned long i;
@@ -44,7 +44,7 @@ void write_bytes(char *addr)
*(addr + i) = (char)i;
}
-void read_bytes(char *addr)
+static void read_bytes(char *addr)
{
unsigned long i;
diff --git a/Documentation/vm/numa b/Documentation/vm/numa
index e93ad9425e2a..a200a386429d 100644
--- a/Documentation/vm/numa
+++ b/Documentation/vm/numa
@@ -1,41 +1,149 @@
Started Nov 1999 by Kanoj Sarcar <kanoj@sgi.com>
-The intent of this file is to have an uptodate, running commentary
-from different people about NUMA specific code in the Linux vm.
-
-What is NUMA? It is an architecture where the memory access times
-for different regions of memory from a given processor varies
-according to the "distance" of the memory region from the processor.
-Each region of memory to which access times are the same from any
-cpu, is called a node. On such architectures, it is beneficial if
-the kernel tries to minimize inter node communications. Schemes
-for this range from kernel text and read-only data replication
-across nodes, and trying to house all the data structures that
-key components of the kernel need on memory on that node.
-
-Currently, all the numa support is to provide efficient handling
-of widely discontiguous physical memory, so architectures which
-are not NUMA but can have huge holes in the physical address space
-can use the same code. All this code is bracketed by CONFIG_DISCONTIGMEM.
-
-The initial port includes NUMAizing the bootmem allocator code by
-encapsulating all the pieces of information into a bootmem_data_t
-structure. Node specific calls have been added to the allocator.
-In theory, any platform which uses the bootmem allocator should
-be able to put the bootmem and mem_map data structures anywhere
-it deems best.
-
-Each node's page allocation data structures have also been encapsulated
-into a pg_data_t. The bootmem_data_t is just one part of this. To
-make the code look uniform between NUMA and regular UMA platforms,
-UMA platforms have a statically allocated pg_data_t too (contig_page_data).
-For the sake of uniformity, the function num_online_nodes() is also defined
-for all platforms. As we run benchmarks, we might decide to NUMAize
-more variables like low_on_memory, nr_free_pages etc into the pg_data_t.
-
-The NUMA aware page allocation code currently tries to allocate pages
-from different nodes in a round robin manner. This will be changed to
-do concentratic circle search, starting from current node, once the
-NUMA port achieves more maturity. The call alloc_pages_node has been
-added, so that drivers can make the call and not worry about whether
-it is running on a NUMA or UMA platform.
+What is NUMA?
+
+This question can be answered from a couple of perspectives: the
+hardware view and the Linux software view.
+
+From the hardware perspective, a NUMA system is a computer platform that
+comprises multiple components or assemblies each of which may contain 0
+or more CPUs, local memory, and/or IO buses. For brevity and to
+disambiguate the hardware view of these physical components/assemblies
+from the software abstraction thereof, we'll call the components/assemblies
+'cells' in this document.
+
+Each of the 'cells' may be viewed as an SMP [symmetric multi-processor] subset
+of the system--although some components necessary for a stand-alone SMP system
+may not be populated on any given cell. The cells of the NUMA system are
+connected together with some sort of system interconnect--e.g., a crossbar or
+point-to-point link are common types of NUMA system interconnects. Both of
+these types of interconnects can be aggregated to create NUMA platforms with
+cells at multiple distances from other cells.
+
+For Linux, the NUMA platforms of interest are primarily what is known as Cache
+Coherent NUMA or ccNUMA systems. With ccNUMA systems, all memory is visible
+to and accessible from any CPU attached to any cell and cache coherency
+is handled in hardware by the processor caches and/or the system interconnect.
+
+Memory access time and effective memory bandwidth varies depending on how far
+away the cell containing the CPU or IO bus making the memory access is from the
+cell containing the target memory. For example, access to memory by CPUs
+attached to the same cell will experience faster access times and higher
+bandwidths than accesses to memory on other, remote cells. NUMA platforms
+can have cells at multiple remote distances from any given cell.
+
+Platform vendors don't build NUMA systems just to make software developers'
+lives interesting. Rather, this architecture is a means to provide scalable
+memory bandwidth. However, to achieve scalable memory bandwidth, system and
+application software must arrange for a large majority of the memory references
+[cache misses] to be to "local" memory--memory on the same cell, if any--or
+to the closest cell with memory.
+
+This leads to the Linux software view of a NUMA system:
+
+Linux divides the system's hardware resources into multiple software
+abstractions called "nodes". Linux maps the nodes onto the physical cells
+of the hardware platform, abstracting away some of the details for some
+architectures. As with physical cells, software nodes may contain 0 or more
+CPUs, memory and/or IO buses. And, again, memory accesses to memory on
+"closer" nodes--nodes that map to closer cells--will generally experience
+faster access times and higher effective bandwidth than accesses to more
+remote cells.
+
+For some architectures, such as x86, Linux will "hide" any node representing a
+physical cell that has no memory attached, and reassign any CPUs attached to
+that cell to a node representing a cell that does have memory. Thus, on
+these architectures, one cannot assume that all CPUs that Linux associates with
+a given node will see the same local memory access times and bandwidth.
+
+In addition, for some architectures, again x86 is an example, Linux supports
+the emulation of additional nodes. For NUMA emulation, linux will carve up
+the existing nodes--or the system memory for non-NUMA platforms--into multiple
+nodes. Each emulated node will manage a fraction of the underlying cells'
+physical memory. NUMA emluation is useful for testing NUMA kernel and
+application features on non-NUMA platforms, and as a sort of memory resource
+management mechanism when used together with cpusets.
+[see Documentation/cgroups/cpusets.txt]
+
+For each node with memory, Linux constructs an independent memory management
+subsystem, complete with its own free page lists, in-use page lists, usage
+statistics and locks to mediate access. In addition, Linux constructs for
+each memory zone [one or more of DMA, DMA32, NORMAL, HIGH_MEMORY, MOVABLE],
+an ordered "zonelist". A zonelist specifies the zones/nodes to visit when a
+selected zone/node cannot satisfy the allocation request. This situation,
+when a zone has no available memory to satisfy a request, is called
+"overflow" or "fallback".
+
+Because some nodes contain multiple zones containing different types of
+memory, Linux must decide whether to order the zonelists such that allocations
+fall back to the same zone type on a different node, or to a different zone
+type on the same node. This is an important consideration because some zones,
+such as DMA or DMA32, represent relatively scarce resources. Linux chooses
+a default zonelist order based on the sizes of the various zone types relative
+to the total memory of the node and the total memory of the system. The
+default zonelist order may be overridden using the numa_zonelist_order kernel
+boot parameter or sysctl. [see Documentation/kernel-parameters.txt and
+Documentation/sysctl/vm.txt]
+
+By default, Linux will attempt to satisfy memory allocation requests from the
+node to which the CPU that executes the request is assigned. Specifically,
+Linux will attempt to allocate from the first node in the appropriate zonelist
+for the node where the request originates. This is called "local allocation."
+If the "local" node cannot satisfy the request, the kernel will examine other
+nodes' zones in the selected zonelist looking for the first zone in the list
+that can satisfy the request.
+
+Local allocation will tend to keep subsequent access to the allocated memory
+"local" to the underlying physical resources and off the system interconnect--
+as long as the task on whose behalf the kernel allocated some memory does not
+later migrate away from that memory. The Linux scheduler is aware of the
+NUMA topology of the platform--embodied in the "scheduling domains" data
+structures [see Documentation/scheduler/sched-domains.txt]--and the scheduler
+attempts to minimize task migration to distant scheduling domains. However,
+the scheduler does not take a task's NUMA footprint into account directly.
+Thus, under sufficient imbalance, tasks can migrate between nodes, remote
+from their initial node and kernel data structures.
+
+System administrators and application designers can restrict a task's migration
+to improve NUMA locality using various CPU affinity command line interfaces,
+such as taskset(1) and numactl(1), and program interfaces such as
+sched_setaffinity(2). Further, one can modify the kernel's default local
+allocation behavior using Linux NUMA memory policy.
+[see Documentation/vm/numa_memory_policy.]
+
+System administrators can restrict the CPUs and nodes' memories that a non-
+privileged user can specify in the scheduling or NUMA commands and functions
+using control groups and CPUsets. [see Documentation/cgroups/CPUsets.txt]
+
+On architectures that do not hide memoryless nodes, Linux will include only
+zones [nodes] with memory in the zonelists. This means that for a memoryless
+node the "local memory node"--the node of the first zone in CPU's node's
+zonelist--will not be the node itself. Rather, it will be the node that the
+kernel selected as the nearest node with memory when it built the zonelists.
+So, default, local allocations will succeed with the kernel supplying the
+closest available memory. This is a consequence of the same mechanism that
+allows such allocations to fallback to other nearby nodes when a node that
+does contain memory overflows.
+
+Some kernel allocations do not want or cannot tolerate this allocation fallback
+behavior. Rather they want to be sure they get memory from the specified node
+or get notified that the node has no free memory. This is usually the case when
+a subsystem allocates per CPU memory resources, for example.
+
+A typical model for making such an allocation is to obtain the node id of the
+node to which the "current CPU" is attached using one of the kernel's
+numa_node_id() or CPU_to_node() functions and then request memory from only
+the node id returned. When such an allocation fails, the requesting subsystem
+may revert to its own fallback path. The slab kernel memory allocator is an
+example of this. Or, the subsystem may choose to disable or not to enable
+itself on allocation failure. The kernel profiling subsystem is an example of
+this.
+
+If the architecture supports--does not hide--memoryless nodes, then CPUs
+attached to memoryless nodes would always incur the fallback path overhead
+or some subsystems would fail to initialize if they attempted to allocated
+memory exclusively from a node without memory. To support such
+architectures transparently, kernel subsystems can use the numa_mem_id()
+or cpu_to_mem() function to locate the "local memory node" for the calling or
+specified CPU. Again, this is the same node from which default, local page
+allocations will be attempted.
diff --git a/Documentation/vm/numa_memory_policy.txt b/Documentation/vm/numa_memory_policy.txt
index be45dbb9d7f2..6690fc34ef6d 100644
--- a/Documentation/vm/numa_memory_policy.txt
+++ b/Documentation/vm/numa_memory_policy.txt
@@ -45,7 +45,7 @@ most general to most specific:
to establish the task policy for a child task exec()'d from an
executable image that has no awareness of memory policy. See the
MEMORY POLICY APIS section, below, for an overview of the system call
- that a task may use to set/change it's task/process policy.
+ that a task may use to set/change its task/process policy.
In a multi-threaded task, task policies apply only to the thread
[Linux kernel task] that installs the policy and any threads
@@ -301,7 +301,7 @@ decrement this reference count, respectively. mpol_put() will only free
the structure back to the mempolicy kmem cache when the reference count
goes to zero.
-When a new memory policy is allocated, it's reference count is initialized
+When a new memory policy is allocated, its reference count is initialized
to '1', representing the reference held by the task that is installing the
new policy. When a pointer to a memory policy structure is stored in another
structure, another reference is added, as the task's reference will be dropped
diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt
index b37300edf27c..07375e73981a 100644
--- a/Documentation/vm/slub.txt
+++ b/Documentation/vm/slub.txt
@@ -41,6 +41,7 @@ Possible debug options are
P Poisoning (object and padding)
U User tracking (free and alloc)
T Trace (please only use on single slabs)
+ A Toggle failslab filter mark for the cache
O Switch debugging off for caches that would have
caused higher minimum slab orders
- Switch all debugging off (useful if the kernel is
OpenPOWER on IntegriCloud