8 files changed, 505 insertions, 131 deletions

diff --git a/Documentation/vm/.gitignore b/Documentation/vm/.gitignore
index 33e8a023df02..09b164a5700f 100644
--- a/Documentation/vm/.gitignore
+++ b/Documentation/vm/.gitignore
@@ -1 +1,2 @@
+page-types
 slabinfo
diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX
index 2f77ced35df7..e57d6a9dd32b 100644
--- a/Documentation/vm/00-INDEX
+++ b/Documentation/vm/00-INDEX
@@ -6,6 +6,8 @@ balance
         - various information on memory balancing.
 hugetlbpage.txt
         - a brief summary of hugetlbpage support in the Linux kernel.
+ksm.txt
+        - how to use the Kernel Samepage Merging feature.
 locking
         - info on how locking and synchronization is done in the Linux vm code.
 numa
@@ -20,3 +22,5 @@ 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.
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt
index ea8714fcc3ad..82a7bd1800b2 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/vm/hugetlbpage.txt
@@ -18,13 +18,13 @@ First the Linux kernel needs to be built with the CONFIG_HUGETLBFS
 automatically when CONFIG_HUGETLBFS is selected) configuration
 options.
 
-The kernel built with hugepage support should show the number of configured
-hugepages in the system by running the "cat /proc/meminfo" command.
+The kernel built with huge page support should show the number of configured
+huge pages in the system by running the "cat /proc/meminfo" command.
 
 /proc/meminfo also provides information about the total number of hugetlb
 pages configured in the kernel.  It also displays information about the
 number of free hugetlb pages at any time.  It also displays information about
-the configured hugepage size - this is needed for generating the proper
+the configured huge page size - this is needed for generating the proper
 alignment and size of the arguments to the above system calls.
 
 The output of "cat /proc/meminfo" will have lines like:
@@ -37,25 +37,27 @@ HugePages_Surp:  yyy
 Hugepagesize:    zzz kB
 
 where:
-HugePages_Total is the size of the pool of hugepages.
-HugePages_Free is the number of hugepages in the pool that are not yet
-allocated.
-HugePages_Rsvd is short for "reserved," and is the number of hugepages
-for which a commitment to allocate from the pool has been made, but no
-allocation has yet been made. It's vaguely analogous to overcommit.
-HugePages_Surp is short for "surplus," and is the number of hugepages in
-the pool above the value in /proc/sys/vm/nr_hugepages. The maximum
-number of surplus hugepages is controlled by
-/proc/sys/vm/nr_overcommit_hugepages.
+HugePages_Total is the size of the pool of huge pages.
+HugePages_Free  is the number of huge pages in the pool that are not yet
+                allocated.
+HugePages_Rsvd  is short for "reserved," and is the number of huge pages for
+                which a commitment to allocate from the pool has been made,
+                but no allocation has yet been made.  Reserved huge pages
+                guarantee that an application will be able to allocate a
+                huge page from the pool of huge pages at fault time.
+HugePages_Surp  is short for "surplus," and is the number of huge pages in
+                the pool above the value in /proc/sys/vm/nr_hugepages. The
+                maximum number of surplus huge pages is controlled by
+                /proc/sys/vm/nr_overcommit_hugepages.
 
 /proc/filesystems should also show a filesystem of type "hugetlbfs" configured
 in the kernel.
 
 /proc/sys/vm/nr_hugepages indicates the current number of configured hugetlb
 pages in the kernel.  Super user can dynamically request more (or free some
-pre-configured) hugepages.
+pre-configured) huge pages.
 The allocation (or deallocation) of hugetlb pages is possible only if there are
-enough physically contiguous free pages in system (freeing of hugepages is
+enough physically contiguous free pages in system (freeing of huge pages is
 possible only if there are enough hugetlb pages free that can be transferred
 back to regular memory pool).
 
@@ -67,43 +69,82 @@ use either the mmap system call or shared memory system calls to start using
 the huge pages.  It is required that the system administrator preallocate
 enough memory for huge page purposes.
 
-Use the following command to dynamically allocate/deallocate hugepages:
+The administrator can preallocate huge pages on the kernel boot command line by
+specifying the "hugepages=N" parameter, where 'N' = the number of huge pages
+requested.  This is the most reliable method for preallocating huge pages as
+memory has not yet become fragmented.
+
+Some platforms support multiple huge page sizes.  To preallocate huge pages
+of a specific size, one must preceed the huge pages boot command parameters
+with a huge page size selection parameter "hugepagesz=<size>".  <size> must
+be specified in bytes with optional scale suffix [kKmMgG].  The default huge
+page size may be selected with the "default_hugepagesz=<size>" boot parameter.
+
+/proc/sys/vm/nr_hugepages indicates the current number of configured [default
+size] hugetlb pages in the kernel.  Super user can dynamically request more
+(or free some pre-configured) huge pages.
+
+Use the following command to dynamically allocate/deallocate default sized
+huge pages:
 
         echo 20 > /proc/sys/vm/nr_hugepages
 
-This command will try to configure 20 hugepages in the system.  The success
-or failure of allocation depends on the amount of physically contiguous
-memory that is preset in system at this time.  System administrators may want
-to put this command in one of the local rc init files.  This will enable the
-kernel to request huge pages early in the boot process (when the possibility
-of getting physical contiguous pages is still very high). In either
-case, administrators will want to verify the number of hugepages actually
-allocated by checking the sysctl or meminfo.
-
-/proc/sys/vm/nr_overcommit_hugepages indicates how large the pool of
-hugepages can grow, if more hugepages than /proc/sys/vm/nr_hugepages are
-requested by applications. echo'ing any non-zero value into this file
-indicates that the hugetlb subsystem is allowed to try to obtain
-hugepages from the buddy allocator, if the normal pool is exhausted. As
-these surplus hugepages go out of use, they are freed back to the buddy
+This command will try to configure 20 default sized huge pages in the system.
+On a NUMA platform, the kernel will attempt to distribute the huge page pool
+over the all on-line nodes.  These huge pages, allocated when nr_hugepages
+is increased, are called "persistent huge pages".
+
+The success or failure of huge page allocation depends on the amount of
+physically contiguous memory that is preset in system at the time of the
+allocation attempt.  If the kernel is unable to allocate huge pages from
+some nodes in a NUMA system, it will attempt to make up the difference by
+allocating extra pages on other nodes with sufficient available contiguous
+memory, if any.
+
+System administrators may want to put this command in one of the local rc init
+files.  This will enable the kernel to request huge pages early in the boot
+process when the possibility of getting physical contiguous pages is still
+very high.  Administrators can verify the number of huge pages actually
+allocated by checking the sysctl or meminfo.  To check the per node
+distribution of huge pages in a NUMA system, use:
+
+        cat /sys/devices/system/node/node*/meminfo | fgrep Huge
+
+/proc/sys/vm/nr_overcommit_hugepages specifies how large the pool of
+huge pages can grow, if more huge pages than /proc/sys/vm/nr_hugepages are
+requested by applications.  Writing any non-zero value into this file
+indicates that the hugetlb subsystem is allowed to try to obtain "surplus"
+huge pages from the buddy allocator, when the normal pool is exhausted. As
+these surplus huge pages go out of use, they are freed back to the buddy
 allocator.
 
+When increasing the huge page pool size via nr_hugepages, any surplus
+pages will first be promoted to persistent huge pages.  Then, additional
+huge pages will be allocated, if necessary and if possible, to fulfill
+the new huge page pool size.
+
+The administrator may shrink the pool of preallocated huge pages for
+the default huge page size by setting the nr_hugepages sysctl to a
+smaller value.  The kernel will attempt to balance the freeing of huge pages
+across all on-line nodes.  Any free huge pages on the selected nodes will
+be freed back to the buddy allocator.
+
 Caveat: Shrinking the pool via nr_hugepages such that it becomes less
-than the number of hugepages in use will convert the balance to surplus
+than the number of huge pages in use will convert the balance to surplus
 huge pages even if it would exceed the overcommit value.  As long as
 this condition holds, however, no more surplus huge pages will be
 allowed on the system until one of the two sysctls are increased
 sufficiently, or the surplus huge pages go out of use and are freed.
 
-With support for multiple hugepage pools at run-time available, much of
-the hugepage userspace interface has been duplicated in sysfs. The above
-information applies to the default hugepage size (which will be
-controlled by the proc interfaces for backwards compatibility). The root
-hugepage control directory is
+With support for multiple huge page pools at run-time available, much of
+the huge page userspace interface has been duplicated in sysfs. The above
+information applies to the default huge page size which will be
+controlled by the /proc interfaces for backwards compatibility. The root
+huge page control directory in sysfs is:
 
         /sys/kernel/mm/hugepages
 
-For each hugepage size supported by the running kernel, a subdirectory
+For each huge page size supported by the running kernel, a subdirectory
 will exist, of the form
 
         hugepages-${size}kB
@@ -116,9 +157,9 @@ Inside each of these directories, the same set of files will exist:
         resv_hugepages
         surplus_hugepages
 
-which function as described above for the default hugepage-sized case.
+which function as described above for the default huge page-sized case.
 
-If the user applications are going to request hugepages using mmap system
+If the user applications are going to request huge pages using mmap system
 call, then it is required that system administrator mount a file system of
 type hugetlbfs:
 
@@ -127,7 +168,7 @@ type hugetlbfs:
         none /mnt/huge
 
 This command mounts a (pseudo) filesystem of type hugetlbfs on the directory
-/mnt/huge.  Any files created on /mnt/huge uses hugepages.  The uid and gid
+/mnt/huge.  Any files created on /mnt/huge uses huge pages.  The uid and gid
 options sets the owner and group of the root of the file system.  By default
 the uid and gid of the current process are taken.  The mode option sets the
 mode of root of file system to value & 0777.  This value is given in octal.
@@ -146,24 +187,26 @@ Regular chown, chgrp, and chmod commands (with right permissions) could be
 used to change the file attributes on hugetlbfs.
 
 Also, it is important to note that no such mount command is required if the
-applications are going to use only shmat/shmget system calls.  Users who
-wish to use hugetlb page via shared memory segment should be a member of
-a supplementary group and system admin needs to configure that gid into
-/proc/sys/vm/hugetlb_shm_group.  It is possible for same or different
-applications to use any combination of mmaps and shm* calls, though the
-mount of filesystem will be required for using mmap calls.
+applications are going to use only shmat/shmget system calls or mmap with
+MAP_HUGETLB.  Users who wish to use hugetlb page via shared memory segment
+should be a member of a supplementary group and system admin needs to
+configure that gid into /proc/sys/vm/hugetlb_shm_group.  It is possible for
+same or different applications to use any combination of mmaps and shm*
+calls, though the mount of filesystem will be required for using mmap calls
+without MAP_HUGETLB.  For an example of how to use mmap with MAP_HUGETLB see
+map_hugetlb.c.
 
 *******************************************************************
 
 /*
- * Example of using hugepage memory in a user application using Sys V shared
+ * 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 hugepages.
+ * requesting huge pages.
  *
  * For the ia64 architecture, the Linux kernel reserves Region number 4 for
- * hugepages.  That means the addresses starting with 0x800000... will need
+ * huge pages.  That means the addresses starting with 0x800000... will need
  * to be specified.  Specifying a fixed address is not required on ppc64,
  * i386 or x86_64.
  *
@@ -252,14 +295,14 @@ int main(void)
 *******************************************************************
 
 /*
- * Example of using hugepage memory in a user application using the 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 ia64 architecture, Linux kernel reserves Region number 4 for hugepages.
+ * For ia64 architecture, Linux kernel reserves Region number 4 for huge pages.
  * That means the addresses starting with 0x800000... will need to be
  * specified.  Specifying a fixed address is not required on ppc64, i386
  * or x86_64.
diff --git a/Documentation/vm/ksm.txt b/Documentation/vm/ksm.txt
new file mode 100644
index 000000000000..72a22f65960e
--- /dev/null
+++ b/Documentation/vm/ksm.txt
@@ -0,0 +1,89 @@
+How to use the Kernel Samepage Merging feature
+----------------------------------------------
+
+KSM is a memory-saving de-duplication feature, enabled by CONFIG_KSM=y,
+added to the Linux kernel in 2.6.32.  See mm/ksm.c for its implementation,
+and http://lwn.net/Articles/306704/ and http://lwn.net/Articles/330589/
+
+The KSM daemon ksmd periodically scans those areas of user memory which
+have been registered with it, looking for pages of identical content which
+can be replaced by a single write-protected page (which is automatically
+copied if a process later wants to update its content).
+
+KSM was originally developed for use with KVM (where it was known as
+Kernel Shared Memory), to fit more virtual machines into physical memory,
+by sharing the data common between them.  But it can be useful to any
+application which generates many instances of the same data.
+
+KSM only merges anonymous (private) pages, never pagecache (file) pages.
+KSM's merged pages are at present locked into kernel memory for as long
+as they are shared: so cannot be swapped out like the user pages they
+replace (but swapping KSM pages should follow soon in a later release).
+
+KSM only operates on those areas of address space which an application
+has advised to be likely candidates for merging, by using the madvise(2)
+system call: int madvise(addr, length, MADV_MERGEABLE).
+
+The app may call int madvise(addr, length, MADV_UNMERGEABLE) to cancel
+that advice and restore unshared pages: whereupon KSM unmerges whatever
+it merged in that range.  Note: this unmerging call may suddenly require
+more memory than is available - possibly failing with EAGAIN, but more
+probably arousing the Out-Of-Memory killer.
+
+If KSM is not configured into the running kernel, madvise MADV_MERGEABLE
+and MADV_UNMERGEABLE simply fail with EINVAL.  If the running kernel was
+built with CONFIG_KSM=y, those calls will normally succeed: even if the
+the KSM daemon is not currently running, MADV_MERGEABLE still registers
+the range for whenever the KSM daemon is started; even if the range
+cannot contain any pages which KSM could actually merge; even if
+MADV_UNMERGEABLE is applied to a range which was never MADV_MERGEABLE.
+
+Like other madvise calls, they are intended for use on mapped areas of
+the user address space: they will report ENOMEM if the specified range
+includes unmapped gaps (though working on the intervening mapped areas),
+and might fail with EAGAIN if not enough memory for internal structures.
+
+Applications should be considerate in their use of MADV_MERGEABLE,
+restricting its use to areas likely to benefit.  KSM's scans may use
+a lot of processing power, and its kernel-resident pages are a limited
+resource.  Some installations will disable KSM for these reasons.
+
+The KSM daemon is controlled by sysfs files in /sys/kernel/mm/ksm/,
+readable by all but writable only by root:
+
+max_kernel_pages - set to maximum number of kernel pages that KSM may use
+                   e.g. "echo 2000 > /sys/kernel/mm/ksm/max_kernel_pages"
+                   Value 0 imposes no limit on the kernel pages KSM may use;
+                   but note that any process using MADV_MERGEABLE can cause
+                   KSM to allocate these pages, unswappable until it exits.
+                   Default: 2000 (chosen for demonstration purposes)
+
+pages_to_scan    - how many present pages to scan before ksmd goes to sleep
+                   e.g. "echo 200 > /sys/kernel/mm/ksm/pages_to_scan"
+                   Default: 200 (chosen for demonstration purposes)
+
+sleep_millisecs  - how many milliseconds ksmd should sleep before next scan
+                   e.g. "echo 20 > /sys/kernel/mm/ksm/sleep_millisecs"
+                   Default: 20 (chosen for demonstration purposes)
+
+run              - set 0 to stop ksmd from running but keep merged pages,
+                   set 1 to run ksmd e.g. "echo 1 > /sys/kernel/mm/ksm/run",
+                   set 2 to stop ksmd and unmerge all pages currently merged,
+                         but leave mergeable areas registered for next run
+                   Default: 1 (for immediate use by apps which register)
+
+The effectiveness of KSM and MADV_MERGEABLE is shown in /sys/kernel/mm/ksm/:
+
+pages_shared     - how many shared unswappable kernel pages KSM is using
+pages_sharing    - how many more sites are sharing them i.e. how much saved
+pages_unshared   - how many pages unique but repeatedly checked for merging
+pages_volatile   - how many pages changing too fast to be placed in a tree
+full_scans       - how many times all mergeable areas have been scanned
+
+A high ratio of pages_sharing to pages_shared indicates good sharing, but
+a high ratio of pages_unshared to pages_sharing indicates wasted effort.
+pages_volatile embraces several different kinds of activity, but a high
+proportion there would also indicate poor use of madvise MADV_MERGEABLE.
+
+Izik Eidus,
+Hugh Dickins, 30 July 2009
diff --git a/Documentation/vm/locking b/Documentation/vm/locking
index f366fa956179..25fadb448760 100644
--- a/Documentation/vm/locking
+++ b/Documentation/vm/locking
@@ -80,7 +80,7 @@ Note: PTL can also be used to guarantee that no new clones using the
 mm start up ... this is a loose form of stability on mm_users. For
 example, it is used in copy_mm to protect against a racing tlb_gather_mmu
 single address space optimization, so that the zap_page_range (from
-vmtruncate) does not lose sending ipi's to cloned threads that might 
+truncate) does not lose sending ipi's to cloned threads that might
 be spawned underneath it and go to user mode to drag in pte's into tlbs.
 
 swap_lock
diff --git a/Documentation/vm/map_hugetlb.c b/Documentation/vm/map_hugetlb.c
new file mode 100644
index 000000000000..e2bdae37f499
--- /dev/null
+++ b/Documentation/vm/map_hugetlb.c
@@ -0,0 +1,77 @@
+/*
+ * Example of using hugepage memory in a user application using the mmap
+ * system call with MAP_HUGETLB flag.  Before running this program make
+ * sure the administrator has allocated enough default sized huge pages
+ * to cover the 256 MB allocation.
+ *
+ * For ia64 architecture, Linux kernel reserves Region number 4 for hugepages.
+ * That means the addresses starting with 0x800000... will need to be
+ * specified.  Specifying a fixed address is not required on ppc64, i386
+ * or x86_64.
+ */
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+
+#define LENGTH (256UL*1024*1024)
+#define PROTECTION (PROT_READ | PROT_WRITE)
+
+#ifndef MAP_HUGETLB
+#define MAP_HUGETLB 0x40
+#endif
+
+/* Only ia64 requires this */
+#ifdef __ia64__
+#define ADDR (void *)(0x8000000000000000UL)
+#define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_FIXED)
+#else
+#define ADDR (void *)(0x0UL)
+#define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
+#endif
+
+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;
+
+        addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, 0, 0);
+        if (addr == MAP_FAILED) {
+                perror("mmap");
+                exit(1);
+        }
+
+        printf("Returned address is %p\n", addr);
+        check_bytes(addr);
+        write_bytes(addr);
+        read_bytes(addr);
+
+        munmap(addr, LENGTH);
+
+        return 0;
+}
diff --git a/Documentation/vm/page-types.c b/Documentation/vm/page-types.c
index 0833f44ba16b..fa1a30d9e9d5 100644
--- a/Documentation/vm/page-types.c
+++ b/Documentation/vm/page-types.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2009 Wu Fengguang <fengguang.wu@intel.com>
  */
 
+#define _LARGEFILE64_SOURCE
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
@@ -13,12 +14,33 @@
 #include <string.h>
 #include <getopt.h>
 #include <limits.h>
+#include <assert.h>
 #include <sys/types.h>
 #include <sys/errno.h>
 #include <sys/fcntl.h>
 
 
 /*
+ * pagemap kernel ABI bits
+ */
+
+#define PM_ENTRY_BYTES      sizeof(uint64_t)
+#define PM_STATUS_BITS      3
+#define PM_STATUS_OFFSET    (64 - PM_STATUS_BITS)
+#define PM_STATUS_MASK      (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
+#define PM_STATUS(nr)       (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK)
+#define PM_PSHIFT_BITS      6
+#define PM_PSHIFT_OFFSET    (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
+#define PM_PSHIFT_MASK      (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
+#define PM_PSHIFT(x)        (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
+#define PM_PFRAME_MASK      ((1LL << PM_PSHIFT_OFFSET) - 1)
+#define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)
+
+#define PM_PRESENT          PM_STATUS(4LL)
+#define PM_SWAP             PM_STATUS(2LL)
+
+
+/*
  * kernel page flags
  */
 
@@ -126,6 +148,14 @@ static int		nr_addr_ranges;
 static unsigned long    opt_offset[MAX_ADDR_RANGES];
 static unsigned long    opt_size[MAX_ADDR_RANGES];
 
+#define MAX_VMAS        10240
+static int              nr_vmas;
+static unsigned long    pg_start[MAX_VMAS];
+static unsigned long    pg_end[MAX_VMAS];
+static unsigned long    voffset;
+
+static int              pagemap_fd;
+
 #define MAX_BIT_FILTERS 64
 static int              nr_bit_filters;
 static uint64_t         opt_mask[MAX_BIT_FILTERS];
@@ -135,7 +165,6 @@ static int		page_size;
 
 #define PAGES_BATCH     (64 << 10)      /* 64k pages */
 static int              kpageflags_fd;
-static uint64_t         kpageflags_buf[KPF_BYTES * PAGES_BATCH];
 
 #define HASH_SHIFT      13
 #define HASH_SIZE       (1 << HASH_SHIFT)
@@ -158,12 +187,17 @@ static uint64_t 	page_flags[HASH_SIZE];
         type __min2 = (y);                      \
         __min1 < __min2 ? __min1 : __min2; })
 
-unsigned long pages2mb(unsigned long pages)
+#define max_t(type, x, y) ({                    \
+        type __max1 = (x);                      \
+        type __max2 = (y);                      \
+        __max1 > __max2 ? __max1 : __max2; })
+
+static unsigned long pages2mb(unsigned long pages)
 {
         return (pages * page_size) >> 20;
 }
 
-void fatal(const char *x, ...)
+static void fatal(const char *x, ...)
 {
         va_list ap;
 
@@ -178,7 +212,7 @@ void fatal(const char *x, ...)
  * page flag names
  */
 
-char *page_flag_name(uint64_t flags)
+static char *page_flag_name(uint64_t flags)
 {
         static char buf[65];
         int present;
@@ -197,7 +231,7 @@ char *page_flag_name(uint64_t flags)
         return buf;
 }
 
-char *page_flag_longname(uint64_t flags)
+static char *page_flag_longname(uint64_t flags)
 {
         static char buf[1024];
         int i, n;
@@ -221,32 +255,40 @@ char *page_flag_longname(uint64_t flags)
  * page list and summary
  */
 
-void show_page_range(unsigned long offset, uint64_t flags)
+static void show_page_range(unsigned long offset, uint64_t flags)
 {
         static uint64_t      flags0;
+        static unsigned long voff;
         static unsigned long index;
         static unsigned long count;
 
-        if (flags == flags0 && offset == index + count) {
+        if (flags == flags0 && offset == index + count &&
+            (!opt_pid || voffset == voff + count)) {
                 count++;
                 return;
         }
 
-        if (count)
-                printf("%lu\t%lu\t%s\n",
+        if (count) {
+                if (opt_pid)
+                        printf("%lx\t", voff);
+                printf("%lx\t%lx\t%s\n",
                                 index, count, page_flag_name(flags0));
+        }
 
         flags0 = flags;
         index  = offset;
+        voff   = voffset;
         count  = 1;
 }
 
-void show_page(unsigned long offset, uint64_t flags)
+static void show_page(unsigned long offset, uint64_t flags)
 {
-        printf("%lu\t%s\n", offset, page_flag_name(flags));
+        if (opt_pid)
+                printf("%lx\t", voffset);
+        printf("%lx\t%s\n", offset, page_flag_name(flags));
 }
 
-void show_summary(void)
+static void show_summary(void)
 {
         int i;
 
@@ -272,7 +314,7 @@ void show_summary(void)
  * page flag filters
  */
 
-int bit_mask_ok(uint64_t flags)
+static int bit_mask_ok(uint64_t flags)
 {
         int i;
 
@@ -289,7 +331,7 @@ int bit_mask_ok(uint64_t flags)
         return 1;
 }
 
-uint64_t expand_overloaded_flags(uint64_t flags)
+static uint64_t expand_overloaded_flags(uint64_t flags)
 {
         /* SLOB/SLUB overload several page flags */
         if (flags & BIT(SLAB)) {
@@ -308,7 +350,7 @@ uint64_t expand_overloaded_flags(uint64_t flags)
         return flags;
 }
 
-uint64_t well_known_flags(uint64_t flags)
+static uint64_t well_known_flags(uint64_t flags)
 {
         /* hide flags intended only for kernel hacker */
         flags &= ~KPF_HACKERS_BITS;
@@ -325,7 +367,7 @@ uint64_t well_known_flags(uint64_t flags)
  * page frame walker
  */
 
-int hash_slot(uint64_t flags)
+static int hash_slot(uint64_t flags)
 {
         int k = HASH_KEY(flags);
         int i;
@@ -352,7 +394,7 @@ int hash_slot(uint64_t flags)
         exit(EXIT_FAILURE);
 }
 
-void add_page(unsigned long offset, uint64_t flags)
+static void add_page(unsigned long offset, uint64_t flags)
 {
         flags = expand_overloaded_flags(flags);
 
@@ -371,7 +413,7 @@ void add_page(unsigned long offset, uint64_t flags)
         total_pages++;
 }
 
-void walk_pfn(unsigned long index, unsigned long count)
+static void walk_pfn(unsigned long index, unsigned long count)
 {
         unsigned long batch;
         unsigned long n;
@@ -383,6 +425,8 @@ void walk_pfn(unsigned long index, unsigned long count)
         lseek(kpageflags_fd, index * KPF_BYTES, SEEK_SET);
 
         while (count) {
+                uint64_t kpageflags_buf[KPF_BYTES * PAGES_BATCH];
+
                 batch = min_t(unsigned long, count, PAGES_BATCH);
                 n = read(kpageflags_fd, kpageflags_buf, batch * KPF_BYTES);
                 if (n == 0)
@@ -404,7 +448,82 @@ void walk_pfn(unsigned long index, unsigned long count)
         }
 }
 
-void walk_addr_ranges(void)
+
+#define PAGEMAP_BATCH   4096
+static unsigned long task_pfn(unsigned long pgoff)
+{
+        static uint64_t buf[PAGEMAP_BATCH];
+        static unsigned long start;
+        static long count;
+        uint64_t pfn;
+
+        if (pgoff < start || pgoff >= start + count) {
+                if (lseek64(pagemap_fd,
+                            (uint64_t)pgoff * PM_ENTRY_BYTES,
+                            SEEK_SET) < 0) {
+                        perror("pagemap seek");
+                        exit(EXIT_FAILURE);
+                }
+                count = read(pagemap_fd, buf, sizeof(buf));
+                if (count == 0)
+                        return 0;
+                if (count < 0) {
+                        perror("pagemap read");
+                        exit(EXIT_FAILURE);
+                }
+                if (count % PM_ENTRY_BYTES) {
+                        fatal("pagemap read not aligned.\n");
+                        exit(EXIT_FAILURE);
+                }
+                count /= PM_ENTRY_BYTES;
+                start = pgoff;
+        }
+
+        pfn = buf[pgoff - start];
+        if (pfn & PM_PRESENT)
+                pfn = PM_PFRAME(pfn);
+        else
+                pfn = 0;
+
+        return pfn;
+}
+
+static void walk_task(unsigned long index, unsigned long count)
+{
+        int i = 0;
+        const unsigned long end = index + count;
+
+        while (index < end) {
+
+                while (pg_end[i] <= index)
+                        if (++i >= nr_vmas)
+                                return;
+                if (pg_start[i] >= end)
+                        return;
+
+                voffset = max_t(unsigned long, pg_start[i], index);
+                index   = min_t(unsigned long, pg_end[i], end);
+
+                assert(voffset < index);
+                for (; voffset < index; voffset++) {
+                        unsigned long pfn = task_pfn(voffset);
+                        if (pfn)
+                                walk_pfn(pfn, 1);
+                }
+        }
+}
+
+static void add_addr_range(unsigned long offset, unsigned long size)
+{
+        if (nr_addr_ranges >= MAX_ADDR_RANGES)
+                fatal("too many addr ranges\n");
+
+        opt_offset[nr_addr_ranges] = offset;
+        opt_size[nr_addr_ranges] = min_t(unsigned long, size, ULONG_MAX-offset);
+        nr_addr_ranges++;
+}
+
+static void walk_addr_ranges(void)
 {
         int i;
 
@@ -415,10 +534,13 @@ void walk_addr_ranges(void)
         }
 
         if (!nr_addr_ranges)
-                walk_pfn(0, ULONG_MAX);
+                add_addr_range(0, ULONG_MAX);
 
         for (i = 0; i < nr_addr_ranges; i++)
-                walk_pfn(opt_offset[i], opt_size[i]);
+                if (!opt_pid)
+                        walk_pfn(opt_offset[i], opt_size[i]);
+                else
+                        walk_task(opt_offset[i], opt_size[i]);
 
         close(kpageflags_fd);
 }
@@ -428,7 +550,7 @@ void walk_addr_ranges(void)
  * user interface
  */
 
-const char *page_flag_type(uint64_t flag)
+static const char *page_flag_type(uint64_t flag)
 {
         if (flag & KPF_HACKERS_BITS)
                 return "(r)";
@@ -437,7 +559,7 @@ const char *page_flag_type(uint64_t flag)
         return "   ";
 }
 
-void usage(void)
+static void usage(void)
 {
         int i, j;
 
@@ -446,8 +568,8 @@ void usage(void)
 "            -r|--raw                  Raw mode, for kernel developers\n"
 "            -a|--addr    addr-spec    Walk a range of pages\n"
 "            -b|--bits    bits-spec    Walk pages with specified bits\n"
-#if 0 /* planned features */
 "            -p|--pid     pid          Walk process address space\n"
+#if 0 /* planned features */
 "            -f|--file    filename     Walk file address space\n"
 #endif
 "            -l|--list                 Show page details in ranges\n"
@@ -459,7 +581,7 @@ void usage(void)
 "            N+M                       pages range from N to N+M-1\n"
 "            N,M                       pages range from N to M-1\n"
 "            N,                        pages range from N to end\n"
-"            ,M                        pages range from 0 to M\n"
+"            ,M                        pages range from 0 to M-1\n"
 "bits-spec:\n"
 "            bit1,bit2                 (flags & (bit1|bit2)) != 0\n"
 "            bit1,bit2=bit1            (flags & (bit1|bit2)) == bit1\n"
@@ -482,7 +604,7 @@ void usage(void)
                 "(r) raw mode bits  (o) overloaded bits\n");
 }
 
-unsigned long long parse_number(const char *str)
+static unsigned long long parse_number(const char *str)
 {
         unsigned long long n;
 
@@ -494,26 +616,62 @@ unsigned long long parse_number(const char *str)
         return n;
 }
 
-void parse_pid(const char *str)
+static void parse_pid(const char *str)
 {
+        FILE *file;
+        char buf[5000];
+
         opt_pid = parse_number(str);
-}
 
-void parse_file(const char *name)
-{
+        sprintf(buf, "/proc/%d/pagemap", opt_pid);
+        pagemap_fd = open(buf, O_RDONLY);
+        if (pagemap_fd < 0) {
+                perror(buf);
+                exit(EXIT_FAILURE);
+        }
+
+        sprintf(buf, "/proc/%d/maps", opt_pid);
+        file = fopen(buf, "r");
+        if (!file) {
+                perror(buf);
+                exit(EXIT_FAILURE);
+        }
+
+        while (fgets(buf, sizeof(buf), file) != NULL) {
+                unsigned long vm_start;
+                unsigned long vm_end;
+                unsigned long long pgoff;
+                int major, minor;
+                char r, w, x, s;
+                unsigned long ino;
+                int n;
+
+                n = sscanf(buf, "%lx-%lx %c%c%c%c %llx %x:%x %lu",
+                           &vm_start,
+                           &vm_end,
+                           &r, &w, &x, &s,
+                           &pgoff,
+                           &major, &minor,
+                           &ino);
+                if (n < 10) {
+                        fprintf(stderr, "unexpected line: %s\n", buf);
+                        continue;
+                }
+                pg_start[nr_vmas] = vm_start / page_size;
+                pg_end[nr_vmas] = vm_end / page_size;
+                if (++nr_vmas >= MAX_VMAS) {
+                        fprintf(stderr, "too many VMAs\n");
+                        break;
+                }
+        }
+        fclose(file);
 }
 
-void add_addr_range(unsigned long offset, unsigned long size)
+static void parse_file(const char *name)
 {
-        if (nr_addr_ranges >= MAX_ADDR_RANGES)
-                fatal("too much addr ranges\n");
-
-        opt_offset[nr_addr_ranges] = offset;
-        opt_size[nr_addr_ranges] = size;
-        nr_addr_ranges++;
 }
 
-void parse_addr_range(const char *optarg)
+static void parse_addr_range(const char *optarg)
 {
         unsigned long offset;
         unsigned long size;
@@ -547,7 +705,7 @@ void parse_addr_range(const char *optarg)
         add_addr_range(offset, size);
 }
 
-void add_bits_filter(uint64_t mask, uint64_t bits)
+static void add_bits_filter(uint64_t mask, uint64_t bits)
 {
         if (nr_bit_filters >= MAX_BIT_FILTERS)
                 fatal("too much bit filters\n");
@@ -557,7 +715,7 @@ void add_bits_filter(uint64_t mask, uint64_t bits)
         nr_bit_filters++;
 }
 
-uint64_t parse_flag_name(const char *str, int len)
+static uint64_t parse_flag_name(const char *str, int len)
 {
         int i;
 
@@ -577,7 +735,7 @@ uint64_t parse_flag_name(const char *str, int len)
         return parse_number(str);
 }
 
-uint64_t parse_flag_names(const char *str, int all)
+static uint64_t parse_flag_names(const char *str, int all)
 {
         const char *p    = str;
         uint64_t   flags = 0;
@@ -596,7 +754,7 @@ uint64_t parse_flag_names(const char *str, int all)
         return flags;
 }
 
-void parse_bits_mask(const char *optarg)
+static void parse_bits_mask(const char *optarg)
 {
         uint64_t mask;
         uint64_t bits;
@@ -621,7 +779,7 @@ void parse_bits_mask(const char *optarg)
 }
 
 
-struct option opts[] = {
+static struct option opts[] = {
         { "raw"       , 0, NULL, 'r' },
         { "pid"       , 1, NULL, 'p' },
         { "file"      , 1, NULL, 'f' },
@@ -676,8 +834,10 @@ int main(int argc, char *argv[])
                 }
         }
 
+        if (opt_list && opt_pid)
+                printf("voffset\t");
         if (opt_list == 1)
-                printf("offset\tcount\tflags\n");
+                printf("offset\tlen\tflags\n");
         if (opt_list == 2)
                 printf("offset\tflags\n");
 
diff --git a/Documentation/vm/slabinfo.c b/Documentation/vm/slabinfo.c
index df3227605d59..92e729f4b676 100644
--- a/Documentation/vm/slabinfo.c
+++ b/Documentation/vm/slabinfo.c
@@ -87,7 +87,7 @@ int page_size;
 
 regex_t pattern;
 
-void fatal(const char *x, ...)
+static void fatal(const char *x, ...)
 {
         va_list ap;
 
@@ -97,7 +97,7 @@ void fatal(const char *x, ...)
         exit(EXIT_FAILURE);
 }
 
-void usage(void)
+static void usage(void)
 {
         printf("slabinfo 5/7/2007. (c) 2007 sgi.\n\n"
                 "slabinfo [-ahnpvtsz] [-d debugopts] [slab-regexp]\n"
@@ -131,7 +131,7 @@ void usage(void)
         );
 }
 
-unsigned long read_obj(const char *name)
+static unsigned long read_obj(const char *name)
 {
         FILE *f = fopen(name, "r");
 
@@ -151,7 +151,7 @@ unsigned long read_obj(const char *name)
 /*
  * Get the contents of an attribute
  */
-unsigned long get_obj(const char *name)
+static unsigned long get_obj(const char *name)
 {
         if (!read_obj(name))
                 return 0;
@@ -159,7 +159,7 @@ unsigned long get_obj(const char *name)
         return atol(buffer);
 }
 
-unsigned long get_obj_and_str(const char *name, char **x)
+static unsigned long get_obj_and_str(const char *name, char **x)
 {
         unsigned long result = 0;
         char *p;
@@ -178,7 +178,7 @@ unsigned long get_obj_and_str(const char *name, char **x)
         return result;
 }
 
-void set_obj(struct slabinfo *s, const char *name, int n)
+static void set_obj(struct slabinfo *s, const char *name, int n)
 {
         char x[100];
         FILE *f;
@@ -192,7 +192,7 @@ void set_obj(struct slabinfo *s, const char *name, int n)
         fclose(f);
 }
 
-unsigned long read_slab_obj(struct slabinfo *s, const char *name)
+static unsigned long read_slab_obj(struct slabinfo *s, const char *name)
 {
         char x[100];
         FILE *f;
@@ -215,7 +215,7 @@ unsigned long read_slab_obj(struct slabinfo *s, const char *name)
 /*
  * Put a size string together
  */
-int store_size(char *buffer, unsigned long value)
+static int store_size(char *buffer, unsigned long value)
 {
         unsigned long divisor = 1;
         char trailer = 0;
@@ -247,7 +247,7 @@ int store_size(char *buffer, unsigned long value)
         return n;
 }
 
-void decode_numa_list(int *numa, char *t)
+static void decode_numa_list(int *numa, char *t)
 {
         int node;
         int nr;
@@ -272,7 +272,7 @@ void decode_numa_list(int *numa, char *t)
         }
 }
 
-void slab_validate(struct slabinfo *s)
+static void slab_validate(struct slabinfo *s)
 {
         if (strcmp(s->name, "*") == 0)
                 return;
@@ -280,7 +280,7 @@ void slab_validate(struct slabinfo *s)
         set_obj(s, "validate", 1);
 }
 
-void slab_shrink(struct slabinfo *s)
+static void slab_shrink(struct slabinfo *s)
 {
         if (strcmp(s->name, "*") == 0)
                 return;
@@ -290,7 +290,7 @@ void slab_shrink(struct slabinfo *s)
 
 int line = 0;
 
-void first_line(void)
+static void first_line(void)
 {
         if (show_activity)
                 printf("Name                   Objects      Alloc       Free   %%Fast Fallb O\n");
@@ -302,7 +302,7 @@ void first_line(void)
 /*
  * Find the shortest alias of a slab
  */
-struct aliasinfo *find_one_alias(struct slabinfo *find)
+static struct aliasinfo *find_one_alias(struct slabinfo *find)
 {
         struct aliasinfo *a;
         struct aliasinfo *best = NULL;
@@ -318,18 +318,18 @@ struct aliasinfo *find_one_alias(struct slabinfo *find)
         return best;
 }
 
-unsigned long slab_size(struct slabinfo *s)
+static unsigned long slab_size(struct slabinfo *s)
 {
         return  s->slabs * (page_size << s->order);
 }
 
-unsigned long slab_activity(struct slabinfo *s)
+static unsigned long slab_activity(struct slabinfo *s)
 {
         return  s->alloc_fastpath + s->free_fastpath +
                 s->alloc_slowpath + s->free_slowpath;
 }
 
-void slab_numa(struct slabinfo *s, int mode)
+static void slab_numa(struct slabinfo *s, int mode)
 {
         int node;
 
@@ -374,7 +374,7 @@ void slab_numa(struct slabinfo *s, int mode)
         line++;
 }
 
-void show_tracking(struct slabinfo *s)
+static void show_tracking(struct slabinfo *s)
 {
         printf("\n%s: Kernel object allocation\n", s->name);
         printf("-----------------------------------------------------------------------\n");
@@ -392,7 +392,7 @@ void show_tracking(struct slabinfo *s)
 
 }
 
-void ops(struct slabinfo *s)
+static void ops(struct slabinfo *s)
 {
         if (strcmp(s->name, "*") == 0)
                 return;
@@ -405,14 +405,14 @@ void ops(struct slabinfo *s)
                 printf("\n%s has no kmem_cache operations\n", s->name);
 }
 
-const char *onoff(int x)
+static const char *onoff(int x)
 {
         if (x)
                 return "On ";
         return "Off";
 }
 
-void slab_stats(struct slabinfo *s)
+static void slab_stats(struct slabinfo *s)
 {
         unsigned long total_alloc;
         unsigned long total_free;
@@ -477,7 +477,7 @@ void slab_stats(struct slabinfo *s)
                         s->deactivate_to_tail, (s->deactivate_to_tail * 100) / total);
 }
 
-void report(struct slabinfo *s)
+static void report(struct slabinfo *s)
 {
         if (strcmp(s->name, "*") == 0)
                 return;
@@ -518,7 +518,7 @@ void report(struct slabinfo *s)
         slab_stats(s);
 }
 
-void slabcache(struct slabinfo *s)
+static void slabcache(struct slabinfo *s)
 {
         char size_str[20];
         char dist_str[40];
@@ -593,7 +593,7 @@ void slabcache(struct slabinfo *s)
 /*
  * Analyze debug options. Return false if something is amiss.
  */
-int debug_opt_scan(char *opt)
+static int debug_opt_scan(char *opt)
 {
         if (!opt || !opt[0] || strcmp(opt, "-") == 0)
                 return 1;
@@ -642,7 +642,7 @@ int debug_opt_scan(char *opt)
         return 1;
 }
 
-int slab_empty(struct slabinfo *s)
+static int slab_empty(struct slabinfo *s)
 {
         if (s->objects > 0)
                 return 0;
@@ -657,7 +657,7 @@ int slab_empty(struct slabinfo *s)
         return 1;
 }
 
-void slab_debug(struct slabinfo *s)
+static void slab_debug(struct slabinfo *s)
 {
         if (strcmp(s->name, "*") == 0)
                 return;
@@ -717,7 +717,7 @@ void slab_debug(struct slabinfo *s)
                 set_obj(s, "trace", 1);
 }
 
-void totals(void)
+static void totals(void)
 {
         struct slabinfo *s;
 
@@ -976,7 +976,7 @@ void totals(void)
                         b1,     b2,     b3);
 }
 
-void sort_slabs(void)
+static void sort_slabs(void)
 {
         struct slabinfo *s1,*s2;
 
@@ -1005,7 +1005,7 @@ void sort_slabs(void)
         }
 }
 
-void sort_aliases(void)
+static void sort_aliases(void)
 {
         struct aliasinfo *a1,*a2;
 
@@ -1030,7 +1030,7 @@ void sort_aliases(void)
         }
 }
 
-void link_slabs(void)
+static void link_slabs(void)
 {
         struct aliasinfo *a;
         struct slabinfo *s;
@@ -1048,7 +1048,7 @@ void link_slabs(void)
         }
 }
 
-void alias(void)
+static void alias(void)
 {
         struct aliasinfo *a;
         char *active = NULL;
@@ -1079,7 +1079,7 @@ void alias(void)
 }
 
 
-void rename_slabs(void)
+static void rename_slabs(void)
 {
         struct slabinfo *s;
         struct aliasinfo *a;
@@ -1102,12 +1102,12 @@ void rename_slabs(void)
         }
 }
 
-int slab_mismatch(char *slab)
+static int slab_mismatch(char *slab)
 {
         return regexec(&pattern, slab, 0, NULL, 0);
 }
 
-void read_slab_dir(void)
+static void read_slab_dir(void)
 {
         DIR *dir;
         struct dirent *de;
@@ -1209,7 +1209,7 @@ void read_slab_dir(void)
                 fatal("Too many aliases\n");
 }
 
-void output_slabs(void)
+static void output_slabs(void)
 {
         struct slabinfo *slab;