| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20120201063420.GA10204@darkstar.nay.redhat.com>
Date: Wed, 1 Feb 2012 14:34:20 +0800
From: Dave Young <dyoung@...hat.com>
To: linux-kernel@...r.kernel.org
Subject: [PATCH] move vm tools from Documentation/vm/ to tools/
tools/ is the better place for vm tools which are used by many people.
Moving them to tools also make them open to more users instead of hide in
Documentation folder.
Also fixed several coding style problem.
Signed-off-by: Dave Young <dyoung@...hat.com>
---
Documentation/vm/Makefile | 8 -
Documentation/vm/hugepage-mmap.c | 91 ----
Documentation/vm/hugepage-shm.c | 98 ----
Documentation/vm/map_hugetlb.c | 77 ---
Documentation/vm/page-types.c | 1100 --------------------------------------
tools/vm/Makefile | 11 +
tools/vm/hugepage-mmap.c | 91 ++++
tools/vm/hugepage-shm.c | 99 ++++
tools/vm/map_hugetlb.c | 77 +++
tools/vm/page-types.c | 1100 ++++++++++++++++++++++++++++++++++++++
10 files changed, 1378 insertions(+), 1374 deletions(-)
delete mode 100644 Documentation/vm/Makefile
delete mode 100644 Documentation/vm/hugepage-mmap.c
delete mode 100644 Documentation/vm/hugepage-shm.c
delete mode 100644 Documentation/vm/map_hugetlb.c
delete mode 100644 Documentation/vm/page-types.c
create mode 100644 tools/vm/Makefile
create mode 100644 tools/vm/hugepage-mmap.c
create mode 100644 tools/vm/hugepage-shm.c
create mode 100644 tools/vm/map_hugetlb.c
create mode 100644 tools/vm/page-types.c
diff --git a/Documentation/vm/Makefile b/Documentation/vm/Makefile
deleted file mode 100644
index 3fa4d06..0000000
--- a/Documentation/vm/Makefile
+++ /dev/null
@@ -1,8 +0,0 @@
-# kbuild trick to avoid linker error. Can be omitted if a module is built.
-obj- := dummy.o
-
-# List of programs to build
-hostprogs-y := 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
deleted file mode 100644
index db0dd9a..0000000
--- a/Documentation/vm/hugepage-mmap.c
+++ /dev/null
@@ -1,91 +0,0 @@
-/*
- * 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
deleted file mode 100644
index 07956d8..0000000
--- a/Documentation/vm/hugepage-shm.c
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * 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/map_hugetlb.c b/Documentation/vm/map_hugetlb.c
deleted file mode 100644
index eda1a6d..0000000
--- a/Documentation/vm/map_hugetlb.c
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * 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 0x40000 /* arch specific */
-#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
-
-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;
-
- 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
deleted file mode 100644
index 7445caa..0000000
--- a/Documentation/vm/page-types.c
+++ /dev/null
@@ -1,1100 +0,0 @@
-/*
- * page-types: Tool for querying page flags
- *
- * 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; version 2.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should find a copy of v2 of the GNU General Public License somewhere on
- * your Linux system; if not, write to the Free Software Foundation, Inc., 59
- * Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
- * Copyright (C) 2009 Intel corporation
- *
- * Authors: Wu Fengguang <fengguang.wu@...el.com>
- */
-
-#define _LARGEFILE64_SOURCE
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <stdint.h>
-#include <stdarg.h>
-#include <string.h>
-#include <getopt.h>
-#include <limits.h>
-#include <assert.h>
-#include <sys/types.h>
-#include <sys/errno.h>
-#include <sys/fcntl.h>
-#include <sys/mount.h>
-#include <sys/statfs.h>
-#include "../../include/linux/magic.h"
-
-
-#ifndef MAX_PATH
-# define MAX_PATH 256
-#endif
-
-#ifndef STR
-# define _STR(x) #x
-# define STR(x) _STR(x)
-#endif
-
-/*
- * 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
- */
-
-#define KPF_BYTES 8
-#define PROC_KPAGEFLAGS "/proc/kpageflags"
-
-/* copied from kpageflags_read() */
-#define KPF_LOCKED 0
-#define KPF_ERROR 1
-#define KPF_REFERENCED 2
-#define KPF_UPTODATE 3
-#define KPF_DIRTY 4
-#define KPF_LRU 5
-#define KPF_ACTIVE 6
-#define KPF_SLAB 7
-#define KPF_WRITEBACK 8
-#define KPF_RECLAIM 9
-#define KPF_BUDDY 10
-
-/* [11-20] new additions in 2.6.31 */
-#define KPF_MMAP 11
-#define KPF_ANON 12
-#define KPF_SWAPCACHE 13
-#define KPF_SWAPBACKED 14
-#define KPF_COMPOUND_HEAD 15
-#define KPF_COMPOUND_TAIL 16
-#define KPF_HUGE 17
-#define KPF_UNEVICTABLE 18
-#define KPF_HWPOISON 19
-#define KPF_NOPAGE 20
-#define KPF_KSM 21
-
-/* [32-] kernel hacking assistances */
-#define KPF_RESERVED 32
-#define KPF_MLOCKED 33
-#define KPF_MAPPEDTODISK 34
-#define KPF_PRIVATE 35
-#define KPF_PRIVATE_2 36
-#define KPF_OWNER_PRIVATE 37
-#define KPF_ARCH 38
-#define KPF_UNCACHED 39
-
-/* [48-] take some arbitrary free slots for expanding overloaded flags
- * not part of kernel API
- */
-#define KPF_READAHEAD 48
-#define KPF_SLOB_FREE 49
-#define KPF_SLUB_FROZEN 50
-#define KPF_SLUB_DEBUG 51
-
-#define KPF_ALL_BITS ((uint64_t)~0ULL)
-#define KPF_HACKERS_BITS (0xffffULL << 32)
-#define KPF_OVERLOADED_BITS (0xffffULL << 48)
-#define BIT(name) (1ULL << KPF_##name)
-#define BITS_COMPOUND (BIT(COMPOUND_HEAD) | BIT(COMPOUND_TAIL))
-
-static const char *page_flag_names[] = {
- [KPF_LOCKED] = "L:locked",
- [KPF_ERROR] = "E:error",
- [KPF_REFERENCED] = "R:referenced",
- [KPF_UPTODATE] = "U:uptodate",
- [KPF_DIRTY] = "D:dirty",
- [KPF_LRU] = "l:lru",
- [KPF_ACTIVE] = "A:active",
- [KPF_SLAB] = "S:slab",
- [KPF_WRITEBACK] = "W:writeback",
- [KPF_RECLAIM] = "I:reclaim",
- [KPF_BUDDY] = "B:buddy",
-
- [KPF_MMAP] = "M:mmap",
- [KPF_ANON] = "a:anonymous",
- [KPF_SWAPCACHE] = "s:swapcache",
- [KPF_SWAPBACKED] = "b:swapbacked",
- [KPF_COMPOUND_HEAD] = "H:compound_head",
- [KPF_COMPOUND_TAIL] = "T:compound_tail",
- [KPF_HUGE] = "G:huge",
- [KPF_UNEVICTABLE] = "u:unevictable",
- [KPF_HWPOISON] = "X:hwpoison",
- [KPF_NOPAGE] = "n:nopage",
- [KPF_KSM] = "x:ksm",
-
- [KPF_RESERVED] = "r:reserved",
- [KPF_MLOCKED] = "m:mlocked",
- [KPF_MAPPEDTODISK] = "d:mappedtodisk",
- [KPF_PRIVATE] = "P:private",
- [KPF_PRIVATE_2] = "p:private_2",
- [KPF_OWNER_PRIVATE] = "O:owner_private",
- [KPF_ARCH] = "h:arch",
- [KPF_UNCACHED] = "c:uncached",
-
- [KPF_READAHEAD] = "I:readahead",
- [KPF_SLOB_FREE] = "P:slob_free",
- [KPF_SLUB_FROZEN] = "A:slub_frozen",
- [KPF_SLUB_DEBUG] = "E:slub_debug",
-};
-
-
-static const char *debugfs_known_mountpoints[] = {
- "/sys/kernel/debug",
- "/debug",
- 0,
-};
-
-/*
- * data structures
- */
-
-static int opt_raw; /* for kernel developers */
-static int opt_list; /* list pages (in ranges) */
-static int opt_no_summary; /* don't show summary */
-static pid_t opt_pid; /* process to walk */
-
-#define MAX_ADDR_RANGES 1024
-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];
-
-#define MAX_BIT_FILTERS 64
-static int nr_bit_filters;
-static uint64_t opt_mask[MAX_BIT_FILTERS];
-static uint64_t opt_bits[MAX_BIT_FILTERS];
-
-static int page_size;
-
-static int pagemap_fd;
-static int kpageflags_fd;
-
-static int opt_hwpoison;
-static int opt_unpoison;
-
-static char hwpoison_debug_fs[MAX_PATH+1];
-static int hwpoison_inject_fd;
-static int hwpoison_forget_fd;
-
-#define HASH_SHIFT 13
-#define HASH_SIZE (1 << HASH_SHIFT)
-#define HASH_MASK (HASH_SIZE - 1)
-#define HASH_KEY(flags) (flags & HASH_MASK)
-
-static unsigned long total_pages;
-static unsigned long nr_pages[HASH_SIZE];
-static uint64_t page_flags[HASH_SIZE];
-
-
-/*
- * helper functions
- */
-
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-
-#define min_t(type, x, y) ({ \
- type __min1 = (x); \
- type __min2 = (y); \
- __min1 < __min2 ? __min1 : __min2; })
-
-#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;
-}
-
-static void fatal(const char *x, ...)
-{
- va_list ap;
-
- va_start(ap, x);
- vfprintf(stderr, x, ap);
- va_end(ap);
- exit(EXIT_FAILURE);
-}
-
-static int checked_open(const char *pathname, int flags)
-{
- int fd = open(pathname, flags);
-
- if (fd < 0) {
- perror(pathname);
- exit(EXIT_FAILURE);
- }
-
- return fd;
-}
-
-/*
- * pagemap/kpageflags routines
- */
-
-static unsigned long do_u64_read(int fd, char *name,
- uint64_t *buf,
- unsigned long index,
- unsigned long count)
-{
- long bytes;
-
- if (index > ULONG_MAX / 8)
- fatal("index overflow: %lu\n", index);
-
- if (lseek(fd, index * 8, SEEK_SET) < 0) {
- perror(name);
- exit(EXIT_FAILURE);
- }
-
- bytes = read(fd, buf, count * 8);
- if (bytes < 0) {
- perror(name);
- exit(EXIT_FAILURE);
- }
- if (bytes % 8)
- fatal("partial read: %lu bytes\n", bytes);
-
- return bytes / 8;
-}
-
-static unsigned long kpageflags_read(uint64_t *buf,
- unsigned long index,
- unsigned long pages)
-{
- return do_u64_read(kpageflags_fd, PROC_KPAGEFLAGS, buf, index, pages);
-}
-
-static unsigned long pagemap_read(uint64_t *buf,
- unsigned long index,
- unsigned long pages)
-{
- return do_u64_read(pagemap_fd, "/proc/pid/pagemap", buf, index, pages);
-}
-
-static unsigned long pagemap_pfn(uint64_t val)
-{
- unsigned long pfn;
-
- if (val & PM_PRESENT)
- pfn = PM_PFRAME(val);
- else
- pfn = 0;
-
- return pfn;
-}
-
-
-/*
- * page flag names
- */
-
-static char *page_flag_name(uint64_t flags)
-{
- static char buf[65];
- int present;
- int i, j;
-
- for (i = 0, j = 0; i < ARRAY_SIZE(page_flag_names); i++) {
- present = (flags >> i) & 1;
- if (!page_flag_names[i]) {
- if (present)
- fatal("unknown flag bit %d\n", i);
- continue;
- }
- buf[j++] = present ? page_flag_names[i][0] : '_';
- }
-
- return buf;
-}
-
-static char *page_flag_longname(uint64_t flags)
-{
- static char buf[1024];
- int i, n;
-
- for (i = 0, n = 0; i < ARRAY_SIZE(page_flag_names); i++) {
- if (!page_flag_names[i])
- continue;
- if ((flags >> i) & 1)
- n += snprintf(buf + n, sizeof(buf) - n, "%s,",
- page_flag_names[i] + 2);
- }
- if (n)
- n--;
- buf[n] = '\0';
-
- return buf;
-}
-
-
-/*
- * page list and summary
- */
-
-static void show_page_range(unsigned long voffset,
- 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 &&
- (!opt_pid || voffset == voff + count)) {
- count++;
- return;
- }
-
- 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;
-}
-
-static void show_page(unsigned long voffset,
- unsigned long offset, uint64_t flags)
-{
- if (opt_pid)
- printf("%lx\t", voffset);
- printf("%lx\t%s\n", offset, page_flag_name(flags));
-}
-
-static void show_summary(void)
-{
- int i;
-
- printf(" flags\tpage-count MB"
- " symbolic-flags\t\t\tlong-symbolic-flags\n");
-
- for (i = 0; i < ARRAY_SIZE(nr_pages); i++) {
- if (nr_pages[i])
- printf("0x%016llx\t%10lu %8lu %s\t%s\n",
- (unsigned long long)page_flags[i],
- nr_pages[i],
- pages2mb(nr_pages[i]),
- page_flag_name(page_flags[i]),
- page_flag_longname(page_flags[i]));
- }
-
- printf(" total\t%10lu %8lu\n",
- total_pages, pages2mb(total_pages));
-}
-
-
-/*
- * page flag filters
- */
-
-static int bit_mask_ok(uint64_t flags)
-{
- int i;
-
- for (i = 0; i < nr_bit_filters; i++) {
- if (opt_bits[i] == KPF_ALL_BITS) {
- if ((flags & opt_mask[i]) == 0)
- return 0;
- } else {
- if ((flags & opt_mask[i]) != opt_bits[i])
- return 0;
- }
- }
-
- return 1;
-}
-
-static uint64_t expand_overloaded_flags(uint64_t flags)
-{
- /* SLOB/SLUB overload several page flags */
- if (flags & BIT(SLAB)) {
- if (flags & BIT(PRIVATE))
- flags ^= BIT(PRIVATE) | BIT(SLOB_FREE);
- if (flags & BIT(ACTIVE))
- flags ^= BIT(ACTIVE) | BIT(SLUB_FROZEN);
- if (flags & BIT(ERROR))
- flags ^= BIT(ERROR) | BIT(SLUB_DEBUG);
- }
-
- /* PG_reclaim is overloaded as PG_readahead in the read path */
- if ((flags & (BIT(RECLAIM) | BIT(WRITEBACK))) == BIT(RECLAIM))
- flags ^= BIT(RECLAIM) | BIT(READAHEAD);
-
- return flags;
-}
-
-static uint64_t well_known_flags(uint64_t flags)
-{
- /* hide flags intended only for kernel hacker */
- flags &= ~KPF_HACKERS_BITS;
-
- /* hide non-hugeTLB compound pages */
- if ((flags & BITS_COMPOUND) && !(flags & BIT(HUGE)))
- flags &= ~BITS_COMPOUND;
-
- return flags;
-}
-
-static uint64_t kpageflags_flags(uint64_t flags)
-{
- flags = expand_overloaded_flags(flags);
-
- if (!opt_raw)
- flags = well_known_flags(flags);
-
- return flags;
-}
-
-/* verify that a mountpoint is actually a debugfs instance */
-static int debugfs_valid_mountpoint(const char *debugfs)
-{
- struct statfs st_fs;
-
- if (statfs(debugfs, &st_fs) < 0)
- return -ENOENT;
- else if (st_fs.f_type != (long) DEBUGFS_MAGIC)
- return -ENOENT;
-
- return 0;
-}
-
-/* find the path to the mounted debugfs */
-static const char *debugfs_find_mountpoint(void)
-{
- const char **ptr;
- char type[100];
- FILE *fp;
-
- ptr = debugfs_known_mountpoints;
- while (*ptr) {
- if (debugfs_valid_mountpoint(*ptr) == 0) {
- strcpy(hwpoison_debug_fs, *ptr);
- return hwpoison_debug_fs;
- }
- ptr++;
- }
-
- /* give up and parse /proc/mounts */
- fp = fopen("/proc/mounts", "r");
- if (fp == NULL)
- perror("Can't open /proc/mounts for read");
-
- while (fscanf(fp, "%*s %"
- STR(MAX_PATH)
- "s %99s %*s %*d %*d\n",
- hwpoison_debug_fs, type) == 2) {
- if (strcmp(type, "debugfs") == 0)
- break;
- }
- fclose(fp);
-
- if (strcmp(type, "debugfs") != 0)
- return NULL;
-
- return hwpoison_debug_fs;
-}
-
-/* mount the debugfs somewhere if it's not mounted */
-
-static void debugfs_mount(void)
-{
- const char **ptr;
-
- /* see if it's already mounted */
- if (debugfs_find_mountpoint())
- return;
-
- ptr = debugfs_known_mountpoints;
- while (*ptr) {
- if (mount(NULL, *ptr, "debugfs", 0, NULL) == 0) {
- /* save the mountpoint */
- strcpy(hwpoison_debug_fs, *ptr);
- break;
- }
- ptr++;
- }
-
- if (*ptr == NULL) {
- perror("mount debugfs");
- exit(EXIT_FAILURE);
- }
-}
-
-/*
- * page actions
- */
-
-static void prepare_hwpoison_fd(void)
-{
- char buf[MAX_PATH + 1];
-
- debugfs_mount();
-
- if (opt_hwpoison && !hwpoison_inject_fd) {
- snprintf(buf, MAX_PATH, "%s/hwpoison/corrupt-pfn",
- hwpoison_debug_fs);
- hwpoison_inject_fd = checked_open(buf, O_WRONLY);
- }
-
- if (opt_unpoison && !hwpoison_forget_fd) {
- snprintf(buf, MAX_PATH, "%s/hwpoison/unpoison-pfn",
- hwpoison_debug_fs);
- hwpoison_forget_fd = checked_open(buf, O_WRONLY);
- }
-}
-
-static int hwpoison_page(unsigned long offset)
-{
- char buf[100];
- int len;
-
- len = sprintf(buf, "0x%lx\n", offset);
- len = write(hwpoison_inject_fd, buf, len);
- if (len < 0) {
- perror("hwpoison inject");
- return len;
- }
- return 0;
-}
-
-static int unpoison_page(unsigned long offset)
-{
- char buf[100];
- int len;
-
- len = sprintf(buf, "0x%lx\n", offset);
- len = write(hwpoison_forget_fd, buf, len);
- if (len < 0) {
- perror("hwpoison forget");
- return len;
- }
- return 0;
-}
-
-/*
- * page frame walker
- */
-
-static int hash_slot(uint64_t flags)
-{
- int k = HASH_KEY(flags);
- int i;
-
- /* Explicitly reserve slot 0 for flags 0: the following logic
- * cannot distinguish an unoccupied slot from slot (flags==0).
- */
- if (flags == 0)
- return 0;
-
- /* search through the remaining (HASH_SIZE-1) slots */
- for (i = 1; i < ARRAY_SIZE(page_flags); i++, k++) {
- if (!k || k >= ARRAY_SIZE(page_flags))
- k = 1;
- if (page_flags[k] == 0) {
- page_flags[k] = flags;
- return k;
- }
- if (page_flags[k] == flags)
- return k;
- }
-
- fatal("hash table full: bump up HASH_SHIFT?\n");
- exit(EXIT_FAILURE);
-}
-
-static void add_page(unsigned long voffset,
- unsigned long offset, uint64_t flags)
-{
- flags = kpageflags_flags(flags);
-
- if (!bit_mask_ok(flags))
- return;
-
- if (opt_hwpoison)
- hwpoison_page(offset);
- if (opt_unpoison)
- unpoison_page(offset);
-
- if (opt_list == 1)
- show_page_range(voffset, offset, flags);
- else if (opt_list == 2)
- show_page(voffset, offset, flags);
-
- nr_pages[hash_slot(flags)]++;
- total_pages++;
-}
-
-#define KPAGEFLAGS_BATCH (64 << 10) /* 64k pages */
-static void walk_pfn(unsigned long voffset,
- unsigned long index,
- unsigned long count)
-{
- uint64_t buf[KPAGEFLAGS_BATCH];
- unsigned long batch;
- long pages;
- unsigned long i;
-
- while (count) {
- batch = min_t(unsigned long, count, KPAGEFLAGS_BATCH);
- pages = kpageflags_read(buf, index, batch);
- if (pages == 0)
- break;
-
- for (i = 0; i < pages; i++)
- add_page(voffset + i, index + i, buf[i]);
-
- index += pages;
- count -= pages;
- }
-}
-
-#define PAGEMAP_BATCH (64 << 10)
-static void walk_vma(unsigned long index, unsigned long count)
-{
- uint64_t buf[PAGEMAP_BATCH];
- unsigned long batch;
- unsigned long pages;
- unsigned long pfn;
- unsigned long i;
-
- while (count) {
- batch = min_t(unsigned long, count, PAGEMAP_BATCH);
- pages = pagemap_read(buf, index, batch);
- if (pages == 0)
- break;
-
- for (i = 0; i < pages; i++) {
- pfn = pagemap_pfn(buf[i]);
- if (pfn)
- walk_pfn(index + i, pfn, 1);
- }
-
- index += pages;
- count -= pages;
- }
-}
-
-static void walk_task(unsigned long index, unsigned long count)
-{
- const unsigned long end = index + count;
- unsigned long start;
- int i = 0;
-
- while (index < end) {
-
- while (pg_end[i] <= index)
- if (++i >= nr_vmas)
- return;
- if (pg_start[i] >= end)
- return;
-
- start = max_t(unsigned long, pg_start[i], index);
- index = min_t(unsigned long, pg_end[i], end);
-
- assert(start < index);
- walk_vma(start, index - start);
- }
-}
-
-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;
-
- kpageflags_fd = checked_open(PROC_KPAGEFLAGS, O_RDONLY);
-
- if (!nr_addr_ranges)
- add_addr_range(0, ULONG_MAX);
-
- for (i = 0; i < nr_addr_ranges; i++)
- if (!opt_pid)
- walk_pfn(0, opt_offset[i], opt_size[i]);
- else
- walk_task(opt_offset[i], opt_size[i]);
-
- close(kpageflags_fd);
-}
-
-
-/*
- * user interface
- */
-
-static const char *page_flag_type(uint64_t flag)
-{
- if (flag & KPF_HACKERS_BITS)
- return "(r)";
- if (flag & KPF_OVERLOADED_BITS)
- return "(o)";
- return " ";
-}
-
-static void usage(void)
-{
- int i, j;
-
- printf(
-"page-types [options]\n"
-" -r|--raw Raw mode, for kernel developers\n"
-" -d|--describe flags Describe flags\n"
-" -a|--addr addr-spec Walk a range of pages\n"
-" -b|--bits bits-spec Walk pages with specified bits\n"
-" -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"
-" -L|--list-each Show page details one by one\n"
-" -N|--no-summary Don't show summary info\n"
-" -X|--hwpoison hwpoison pages\n"
-" -x|--unpoison unpoison pages\n"
-" -h|--help Show this usage message\n"
-"flags:\n"
-" 0x10 bitfield format, e.g.\n"
-" anon bit-name, e.g.\n"
-" 0x10,anon comma-separated list, e.g.\n"
-"addr-spec:\n"
-" N one page at offset N (unit: pages)\n"
-" 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-1\n"
-"bits-spec:\n"
-" bit1,bit2 (flags & (bit1|bit2)) != 0\n"
-" bit1,bit2=bit1 (flags & (bit1|bit2)) == bit1\n"
-" bit1,~bit2 (flags & (bit1|bit2)) == bit1\n"
-" =bit1,bit2 flags == (bit1|bit2)\n"
-"bit-names:\n"
- );
-
- for (i = 0, j = 0; i < ARRAY_SIZE(page_flag_names); i++) {
- if (!page_flag_names[i])
- continue;
- printf("%16s%s", page_flag_names[i] + 2,
- page_flag_type(1ULL << i));
- if (++j > 3) {
- j = 0;
- putchar('\n');
- }
- }
- printf("\n "
- "(r) raw mode bits (o) overloaded bits\n");
-}
-
-static unsigned long long parse_number(const char *str)
-{
- unsigned long long n;
-
- n = strtoll(str, NULL, 0);
-
- if (n == 0 && str[0] != '0')
- fatal("invalid name or number: %s\n", str);
-
- return n;
-}
-
-static void parse_pid(const char *str)
-{
- FILE *file;
- char buf[5000];
-
- opt_pid = parse_number(str);
-
- sprintf(buf, "/proc/%d/pagemap", opt_pid);
- pagemap_fd = checked_open(buf, O_RDONLY);
-
- 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);
-}
-
-static void parse_file(const char *name)
-{
-}
-
-static void parse_addr_range(const char *optarg)
-{
- unsigned long offset;
- unsigned long size;
- char *p;
-
- p = strchr(optarg, ',');
- if (!p)
- p = strchr(optarg, '+');
-
- if (p == optarg) {
- offset = 0;
- size = parse_number(p + 1);
- } else if (p) {
- offset = parse_number(optarg);
- if (p[1] == '\0')
- size = ULONG_MAX;
- else {
- size = parse_number(p + 1);
- if (*p == ',') {
- if (size < offset)
- fatal("invalid range: %lu,%lu\n",
- offset, size);
- size -= offset;
- }
- }
- } else {
- offset = parse_number(optarg);
- size = 1;
- }
-
- add_addr_range(offset, size);
-}
-
-static void add_bits_filter(uint64_t mask, uint64_t bits)
-{
- if (nr_bit_filters >= MAX_BIT_FILTERS)
- fatal("too much bit filters\n");
-
- opt_mask[nr_bit_filters] = mask;
- opt_bits[nr_bit_filters] = bits;
- nr_bit_filters++;
-}
-
-static uint64_t parse_flag_name(const char *str, int len)
-{
- int i;
-
- if (!*str || !len)
- return 0;
-
- if (len <= 8 && !strncmp(str, "compound", len))
- return BITS_COMPOUND;
-
- for (i = 0; i < ARRAY_SIZE(page_flag_names); i++) {
- if (!page_flag_names[i])
- continue;
- if (!strncmp(str, page_flag_names[i] + 2, len))
- return 1ULL << i;
- }
-
- return parse_number(str);
-}
-
-static uint64_t parse_flag_names(const char *str, int all)
-{
- const char *p = str;
- uint64_t flags = 0;
-
- while (1) {
- if (*p == ',' || *p == '=' || *p == '\0') {
- if ((*str != '~') || (*str == '~' && all && *++str))
- flags |= parse_flag_name(str, p - str);
- if (*p != ',')
- break;
- str = p + 1;
- }
- p++;
- }
-
- return flags;
-}
-
-static void parse_bits_mask(const char *optarg)
-{
- uint64_t mask;
- uint64_t bits;
- const char *p;
-
- p = strchr(optarg, '=');
- if (p == optarg) {
- mask = KPF_ALL_BITS;
- bits = parse_flag_names(p + 1, 0);
- } else if (p) {
- mask = parse_flag_names(optarg, 0);
- bits = parse_flag_names(p + 1, 0);
- } else if (strchr(optarg, '~')) {
- mask = parse_flag_names(optarg, 1);
- bits = parse_flag_names(optarg, 0);
- } else {
- mask = parse_flag_names(optarg, 0);
- bits = KPF_ALL_BITS;
- }
-
- add_bits_filter(mask, bits);
-}
-
-static void describe_flags(const char *optarg)
-{
- uint64_t flags = parse_flag_names(optarg, 0);
-
- printf("0x%016llx\t%s\t%s\n",
- (unsigned long long)flags,
- page_flag_name(flags),
- page_flag_longname(flags));
-}
-
-static const struct option opts[] = {
- { "raw" , 0, NULL, 'r' },
- { "pid" , 1, NULL, 'p' },
- { "file" , 1, NULL, 'f' },
- { "addr" , 1, NULL, 'a' },
- { "bits" , 1, NULL, 'b' },
- { "describe" , 1, NULL, 'd' },
- { "list" , 0, NULL, 'l' },
- { "list-each" , 0, NULL, 'L' },
- { "no-summary", 0, NULL, 'N' },
- { "hwpoison" , 0, NULL, 'X' },
- { "unpoison" , 0, NULL, 'x' },
- { "help" , 0, NULL, 'h' },
- { NULL , 0, NULL, 0 }
-};
-
-int main(int argc, char *argv[])
-{
- int c;
-
- page_size = getpagesize();
-
- while ((c = getopt_long(argc, argv,
- "rp:f:a:b:d:lLNXxh", opts, NULL)) != -1) {
- switch (c) {
- case 'r':
- opt_raw = 1;
- break;
- case 'p':
- parse_pid(optarg);
- break;
- case 'f':
- parse_file(optarg);
- break;
- case 'a':
- parse_addr_range(optarg);
- break;
- case 'b':
- parse_bits_mask(optarg);
- break;
- case 'd':
- describe_flags(optarg);
- exit(0);
- case 'l':
- opt_list = 1;
- break;
- case 'L':
- opt_list = 2;
- break;
- case 'N':
- opt_no_summary = 1;
- break;
- case 'X':
- opt_hwpoison = 1;
- prepare_hwpoison_fd();
- break;
- case 'x':
- opt_unpoison = 1;
- prepare_hwpoison_fd();
- break;
- case 'h':
- usage();
- exit(0);
- default:
- usage();
- exit(1);
- }
- }
-
- if (opt_list && opt_pid)
- printf("voffset\t");
- if (opt_list == 1)
- printf("offset\tlen\tflags\n");
- if (opt_list == 2)
- printf("offset\tflags\n");
-
- walk_addr_ranges();
-
- if (opt_list == 1)
- show_page_range(0, 0, 0); /* drain the buffer */
-
- if (opt_no_summary)
- return 0;
-
- if (opt_list)
- printf("\n\n");
-
- show_summary();
-
- return 0;
-}
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
new file mode 100644
index 0000000..b4f9fdd
--- /dev/null
+++ b/tools/vm/Makefile
@@ -0,0 +1,11 @@
+# Makefile for vm tools
+
+CC = $(CROSS_COMPILE)gcc
+CFLAGS = -Wall -Wextra
+
+all: page-types hugepage-mmap hugepage-shm map_hugetlb
+%: %.c
+ $(CC) $(CFLAGS) -o $@ $^
+
+clean:
+ $(RM) page-types hugepage-mmap hugepage-shm map_hugetlb
diff --git a/tools/vm/hugepage-mmap.c b/tools/vm/hugepage-mmap.c
new file mode 100644
index 0000000..db0dd9a
--- /dev/null
+++ b/tools/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/tools/vm/hugepage-shm.c b/tools/vm/hugepage-shm.c
new file mode 100644
index 0000000..7c8c19e
--- /dev/null
+++ b/tools/vm/hugepage-shm.c
@@ -0,0 +1,99 @@
+/*
+ * 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;
+
+ shmid = shmget(2, LENGTH,
+ (SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W) < 0);
+ if (shmid < 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/tools/vm/map_hugetlb.c b/tools/vm/map_hugetlb.c
new file mode 100644
index 0000000..eda1a6d
--- /dev/null
+++ b/tools/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 0x40000 /* arch specific */
+#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
+
+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;
+
+ 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/tools/vm/page-types.c b/tools/vm/page-types.c
new file mode 100644
index 0000000..89dd173
--- /dev/null
+++ b/tools/vm/page-types.c
@@ -0,0 +1,1100 @@
+/*
+ * page-types: Tool for querying page flags
+ *
+ * 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; version 2.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should find a copy of v2 of the GNU General Public License somewhere on
+ * your Linux system; if not, write to the Free Software Foundation, Inc., 59
+ * Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Copyright (C) 2009 Intel corporation
+ *
+ * Authors: Wu Fengguang <fengguang.wu@...el.com>
+ */
+
+#define _LARGEFILE64_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdint.h>
+#include <stdarg.h>
+#include <string.h>
+#include <getopt.h>
+#include <limits.h>
+#include <assert.h>
+#include <sys/types.h>
+#include <sys/errno.h>
+#include <sys/fcntl.h>
+#include <sys/mount.h>
+#include <sys/statfs.h>
+#include "../../include/linux/magic.h"
+
+
+#ifndef MAX_PATH
+# define MAX_PATH 256
+#endif
+
+#ifndef STR
+# define _STR(x) #x
+# define STR(x) _STR(x)
+#endif
+
+/*
+ * 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
+ */
+
+#define KPF_BYTES 8
+#define PROC_KPAGEFLAGS "/proc/kpageflags"
+
+/* copied from kpageflags_read() */
+#define KPF_LOCKED 0
+#define KPF_ERROR 1
+#define KPF_REFERENCED 2
+#define KPF_UPTODATE 3
+#define KPF_DIRTY 4
+#define KPF_LRU 5
+#define KPF_ACTIVE 6
+#define KPF_SLAB 7
+#define KPF_WRITEBACK 8
+#define KPF_RECLAIM 9
+#define KPF_BUDDY 10
+
+/* [11-20] new additions in 2.6.31 */
+#define KPF_MMAP 11
+#define KPF_ANON 12
+#define KPF_SWAPCACHE 13
+#define KPF_SWAPBACKED 14
+#define KPF_COMPOUND_HEAD 15
+#define KPF_COMPOUND_TAIL 16
+#define KPF_HUGE 17
+#define KPF_UNEVICTABLE 18
+#define KPF_HWPOISON 19
+#define KPF_NOPAGE 20
+#define KPF_KSM 21
+
+/* [32-] kernel hacking assistances */
+#define KPF_RESERVED 32
+#define KPF_MLOCKED 33
+#define KPF_MAPPEDTODISK 34
+#define KPF_PRIVATE 35
+#define KPF_PRIVATE_2 36
+#define KPF_OWNER_PRIVATE 37
+#define KPF_ARCH 38
+#define KPF_UNCACHED 39
+
+/* [48-] take some arbitrary free slots for expanding overloaded flags
+ * not part of kernel API
+ */
+#define KPF_READAHEAD 48
+#define KPF_SLOB_FREE 49
+#define KPF_SLUB_FROZEN 50
+#define KPF_SLUB_DEBUG 51
+
+#define KPF_ALL_BITS ((uint64_t)~0ULL)
+#define KPF_HACKERS_BITS (0xffffULL << 32)
+#define KPF_OVERLOADED_BITS (0xffffULL << 48)
+#define BIT(name) (1ULL << KPF_##name)
+#define BITS_COMPOUND (BIT(COMPOUND_HEAD) | BIT(COMPOUND_TAIL))
+
+static const char * const page_flag_names[] = {
+ [KPF_LOCKED] = "L:locked",
+ [KPF_ERROR] = "E:error",
+ [KPF_REFERENCED] = "R:referenced",
+ [KPF_UPTODATE] = "U:uptodate",
+ [KPF_DIRTY] = "D:dirty",
+ [KPF_LRU] = "l:lru",
+ [KPF_ACTIVE] = "A:active",
+ [KPF_SLAB] = "S:slab",
+ [KPF_WRITEBACK] = "W:writeback",
+ [KPF_RECLAIM] = "I:reclaim",
+ [KPF_BUDDY] = "B:buddy",
+
+ [KPF_MMAP] = "M:mmap",
+ [KPF_ANON] = "a:anonymous",
+ [KPF_SWAPCACHE] = "s:swapcache",
+ [KPF_SWAPBACKED] = "b:swapbacked",
+ [KPF_COMPOUND_HEAD] = "H:compound_head",
+ [KPF_COMPOUND_TAIL] = "T:compound_tail",
+ [KPF_HUGE] = "G:huge",
+ [KPF_UNEVICTABLE] = "u:unevictable",
+ [KPF_HWPOISON] = "X:hwpoison",
+ [KPF_NOPAGE] = "n:nopage",
+ [KPF_KSM] = "x:ksm",
+
+ [KPF_RESERVED] = "r:reserved",
+ [KPF_MLOCKED] = "m:mlocked",
+ [KPF_MAPPEDTODISK] = "d:mappedtodisk",
+ [KPF_PRIVATE] = "P:private",
+ [KPF_PRIVATE_2] = "p:private_2",
+ [KPF_OWNER_PRIVATE] = "O:owner_private",
+ [KPF_ARCH] = "h:arch",
+ [KPF_UNCACHED] = "c:uncached",
+
+ [KPF_READAHEAD] = "I:readahead",
+ [KPF_SLOB_FREE] = "P:slob_free",
+ [KPF_SLUB_FROZEN] = "A:slub_frozen",
+ [KPF_SLUB_DEBUG] = "E:slub_debug",
+};
+
+
+static const char * const debugfs_known_mountpoints[] = {
+ "/sys/kernel/debug",
+ "/debug",
+ 0,
+};
+
+/*
+ * data structures
+ */
+
+static int opt_raw; /* for kernel developers */
+static int opt_list; /* list pages (in ranges) */
+static int opt_no_summary; /* don't show summary */
+static pid_t opt_pid; /* process to walk */
+
+#define MAX_ADDR_RANGES 1024
+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];
+
+#define MAX_BIT_FILTERS 64
+static int nr_bit_filters;
+static uint64_t opt_mask[MAX_BIT_FILTERS];
+static uint64_t opt_bits[MAX_BIT_FILTERS];
+
+static int page_size;
+
+static int pagemap_fd;
+static int kpageflags_fd;
+
+static int opt_hwpoison;
+static int opt_unpoison;
+
+static char hwpoison_debug_fs[MAX_PATH+1];
+static int hwpoison_inject_fd;
+static int hwpoison_forget_fd;
+
+#define HASH_SHIFT 13
+#define HASH_SIZE (1 << HASH_SHIFT)
+#define HASH_MASK (HASH_SIZE - 1)
+#define HASH_KEY(flags) (flags & HASH_MASK)
+
+static unsigned long total_pages;
+static unsigned long nr_pages[HASH_SIZE];
+static uint64_t page_flags[HASH_SIZE];
+
+
+/*
+ * helper functions
+ */
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+#define min_t(type, x, y) ({ \
+ type __min1 = (x); \
+ type __min2 = (y); \
+ __min1 < __min2 ? __min1 : __min2; })
+
+#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;
+}
+
+static void fatal(const char *x, ...)
+{
+ va_list ap;
+
+ va_start(ap, x);
+ vfprintf(stderr, x, ap);
+ va_end(ap);
+ exit(EXIT_FAILURE);
+}
+
+static int checked_open(const char *pathname, int flags)
+{
+ int fd = open(pathname, flags);
+
+ if (fd < 0) {
+ perror(pathname);
+ exit(EXIT_FAILURE);
+ }
+
+ return fd;
+}
+
+/*
+ * pagemap/kpageflags routines
+ */
+
+static unsigned long do_u64_read(int fd, char *name,
+ uint64_t *buf,
+ unsigned long index,
+ unsigned long count)
+{
+ long bytes;
+
+ if (index > ULONG_MAX / 8)
+ fatal("index overflow: %lu\n", index);
+
+ if (lseek(fd, index * 8, SEEK_SET) < 0) {
+ perror(name);
+ exit(EXIT_FAILURE);
+ }
+
+ bytes = read(fd, buf, count * 8);
+ if (bytes < 0) {
+ perror(name);
+ exit(EXIT_FAILURE);
+ }
+ if (bytes % 8)
+ fatal("partial read: %lu bytes\n", bytes);
+
+ return bytes / 8;
+}
+
+static unsigned long kpageflags_read(uint64_t *buf,
+ unsigned long index,
+ unsigned long pages)
+{
+ return do_u64_read(kpageflags_fd, PROC_KPAGEFLAGS, buf, index, pages);
+}
+
+static unsigned long pagemap_read(uint64_t *buf,
+ unsigned long index,
+ unsigned long pages)
+{
+ return do_u64_read(pagemap_fd, "/proc/pid/pagemap", buf, index, pages);
+}
+
+static unsigned long pagemap_pfn(uint64_t val)
+{
+ unsigned long pfn;
+
+ if (val & PM_PRESENT)
+ pfn = PM_PFRAME(val);
+ else
+ pfn = 0;
+
+ return pfn;
+}
+
+
+/*
+ * page flag names
+ */
+
+static char *page_flag_name(uint64_t flags)
+{
+ static char buf[65];
+ int present;
+ int i, j;
+
+ for (i = 0, j = 0; i < ARRAY_SIZE(page_flag_names); i++) {
+ present = (flags >> i) & 1;
+ if (!page_flag_names[i]) {
+ if (present)
+ fatal("unknown flag bit %d\n", i);
+ continue;
+ }
+ buf[j++] = present ? page_flag_names[i][0] : '_';
+ }
+
+ return buf;
+}
+
+static char *page_flag_longname(uint64_t flags)
+{
+ static char buf[1024];
+ int i, n;
+
+ for (i = 0, n = 0; i < ARRAY_SIZE(page_flag_names); i++) {
+ if (!page_flag_names[i])
+ continue;
+ if ((flags >> i) & 1)
+ n += snprintf(buf + n, sizeof(buf) - n, "%s,",
+ page_flag_names[i] + 2);
+ }
+ if (n)
+ n--;
+ buf[n] = '\0';
+
+ return buf;
+}
+
+
+/*
+ * page list and summary
+ */
+
+static void show_page_range(unsigned long voffset,
+ 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 &&
+ (!opt_pid || voffset == voff + count)) {
+ count++;
+ return;
+ }
+
+ 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;
+}
+
+static void show_page(unsigned long voffset,
+ unsigned long offset, uint64_t flags)
+{
+ if (opt_pid)
+ printf("%lx\t", voffset);
+ printf("%lx\t%s\n", offset, page_flag_name(flags));
+}
+
+static void show_summary(void)
+{
+ int i;
+
+ printf(" flags\tpage-count MB"
+ " symbolic-flags\t\t\tlong-symbolic-flags\n");
+
+ for (i = 0; i < ARRAY_SIZE(nr_pages); i++) {
+ if (nr_pages[i])
+ printf("0x%016llx\t%10lu %8lu %s\t%s\n",
+ (unsigned long long)page_flags[i],
+ nr_pages[i],
+ pages2mb(nr_pages[i]),
+ page_flag_name(page_flags[i]),
+ page_flag_longname(page_flags[i]));
+ }
+
+ printf(" total\t%10lu %8lu\n",
+ total_pages, pages2mb(total_pages));
+}
+
+
+/*
+ * page flag filters
+ */
+
+static int bit_mask_ok(uint64_t flags)
+{
+ int i;
+
+ for (i = 0; i < nr_bit_filters; i++) {
+ if (opt_bits[i] == KPF_ALL_BITS) {
+ if ((flags & opt_mask[i]) == 0)
+ return 0;
+ } else {
+ if ((flags & opt_mask[i]) != opt_bits[i])
+ return 0;
+ }
+ }
+
+ return 1;
+}
+
+static uint64_t expand_overloaded_flags(uint64_t flags)
+{
+ /* SLOB/SLUB overload several page flags */
+ if (flags & BIT(SLAB)) {
+ if (flags & BIT(PRIVATE))
+ flags ^= BIT(PRIVATE) | BIT(SLOB_FREE);
+ if (flags & BIT(ACTIVE))
+ flags ^= BIT(ACTIVE) | BIT(SLUB_FROZEN);
+ if (flags & BIT(ERROR))
+ flags ^= BIT(ERROR) | BIT(SLUB_DEBUG);
+ }
+
+ /* PG_reclaim is overloaded as PG_readahead in the read path */
+ if ((flags & (BIT(RECLAIM) | BIT(WRITEBACK))) == BIT(RECLAIM))
+ flags ^= BIT(RECLAIM) | BIT(READAHEAD);
+
+ return flags;
+}
+
+static uint64_t well_known_flags(uint64_t flags)
+{
+ /* hide flags intended only for kernel hacker */
+ flags &= ~KPF_HACKERS_BITS;
+
+ /* hide non-hugeTLB compound pages */
+ if ((flags & BITS_COMPOUND) && !(flags & BIT(HUGE)))
+ flags &= ~BITS_COMPOUND;
+
+ return flags;
+}
+
+static uint64_t kpageflags_flags(uint64_t flags)
+{
+ flags = expand_overloaded_flags(flags);
+
+ if (!opt_raw)
+ flags = well_known_flags(flags);
+
+ return flags;
+}
+
+/* verify that a mountpoint is actually a debugfs instance */
+static int debugfs_valid_mountpoint(const char *debugfs)
+{
+ struct statfs st_fs;
+
+ if (statfs(debugfs, &st_fs) < 0)
+ return -ENOENT;
+ else if (st_fs.f_type != (long) DEBUGFS_MAGIC)
+ return -ENOENT;
+
+ return 0;
+}
+
+/* find the path to the mounted debugfs */
+static const char *debugfs_find_mountpoint(void)
+{
+ const char **ptr;
+ char type[100];
+ FILE *fp;
+
+ ptr = debugfs_known_mountpoints;
+ while (*ptr) {
+ if (debugfs_valid_mountpoint(*ptr) == 0) {
+ strcpy(hwpoison_debug_fs, *ptr);
+ return hwpoison_debug_fs;
+ }
+ ptr++;
+ }
+
+ /* give up and parse /proc/mounts */
+ fp = fopen("/proc/mounts", "r");
+ if (fp == NULL)
+ perror("Can't open /proc/mounts for read");
+
+ while (fscanf(fp, "%*s %"
+ STR(MAX_PATH)
+ "s %99s %*s %*d %*d\n",
+ hwpoison_debug_fs, type) == 2) {
+ if (strcmp(type, "debugfs") == 0)
+ break;
+ }
+ fclose(fp);
+
+ if (strcmp(type, "debugfs") != 0)
+ return NULL;
+
+ return hwpoison_debug_fs;
+}
+
+/* mount the debugfs somewhere if it's not mounted */
+
+static void debugfs_mount(void)
+{
+ const char **ptr;
+
+ /* see if it's already mounted */
+ if (debugfs_find_mountpoint())
+ return;
+
+ ptr = debugfs_known_mountpoints;
+ while (*ptr) {
+ if (mount(NULL, *ptr, "debugfs", 0, NULL) == 0) {
+ /* save the mountpoint */
+ strcpy(hwpoison_debug_fs, *ptr);
+ break;
+ }
+ ptr++;
+ }
+
+ if (*ptr == NULL) {
+ perror("mount debugfs");
+ exit(EXIT_FAILURE);
+ }
+}
+
+/*
+ * page actions
+ */
+
+static void prepare_hwpoison_fd(void)
+{
+ char buf[MAX_PATH + 1];
+
+ debugfs_mount();
+
+ if (opt_hwpoison && !hwpoison_inject_fd) {
+ snprintf(buf, MAX_PATH, "%s/hwpoison/corrupt-pfn",
+ hwpoison_debug_fs);
+ hwpoison_inject_fd = checked_open(buf, O_WRONLY);
+ }
+
+ if (opt_unpoison && !hwpoison_forget_fd) {
+ snprintf(buf, MAX_PATH, "%s/hwpoison/unpoison-pfn",
+ hwpoison_debug_fs);
+ hwpoison_forget_fd = checked_open(buf, O_WRONLY);
+ }
+}
+
+static int hwpoison_page(unsigned long offset)
+{
+ char buf[100];
+ int len;
+
+ len = sprintf(buf, "0x%lx\n", offset);
+ len = write(hwpoison_inject_fd, buf, len);
+ if (len < 0) {
+ perror("hwpoison inject");
+ return len;
+ }
+ return 0;
+}
+
+static int unpoison_page(unsigned long offset)
+{
+ char buf[100];
+ int len;
+
+ len = sprintf(buf, "0x%lx\n", offset);
+ len = write(hwpoison_forget_fd, buf, len);
+ if (len < 0) {
+ perror("hwpoison forget");
+ return len;
+ }
+ return 0;
+}
+
+/*
+ * page frame walker
+ */
+
+static int hash_slot(uint64_t flags)
+{
+ int k = HASH_KEY(flags);
+ int i;
+
+ /* Explicitly reserve slot 0 for flags 0: the following logic
+ * cannot distinguish an unoccupied slot from slot (flags==0).
+ */
+ if (flags == 0)
+ return 0;
+
+ /* search through the remaining (HASH_SIZE-1) slots */
+ for (i = 1; i < ARRAY_SIZE(page_flags); i++, k++) {
+ if (!k || k >= ARRAY_SIZE(page_flags))
+ k = 1;
+ if (page_flags[k] == 0) {
+ page_flags[k] = flags;
+ return k;
+ }
+ if (page_flags[k] == flags)
+ return k;
+ }
+
+ fatal("hash table full: bump up HASH_SHIFT?\n");
+ exit(EXIT_FAILURE);
+}
+
+static void add_page(unsigned long voffset,
+ unsigned long offset, uint64_t flags)
+{
+ flags = kpageflags_flags(flags);
+
+ if (!bit_mask_ok(flags))
+ return;
+
+ if (opt_hwpoison)
+ hwpoison_page(offset);
+ if (opt_unpoison)
+ unpoison_page(offset);
+
+ if (opt_list == 1)
+ show_page_range(voffset, offset, flags);
+ else if (opt_list == 2)
+ show_page(voffset, offset, flags);
+
+ nr_pages[hash_slot(flags)]++;
+ total_pages++;
+}
+
+#define KPAGEFLAGS_BATCH (64 << 10) /* 64k pages */
+static void walk_pfn(unsigned long voffset,
+ unsigned long index,
+ unsigned long count)
+{
+ uint64_t buf[KPAGEFLAGS_BATCH];
+ unsigned long batch;
+ long pages;
+ unsigned long i;
+
+ while (count) {
+ batch = min_t(unsigned long, count, KPAGEFLAGS_BATCH);
+ pages = kpageflags_read(buf, index, batch);
+ if (pages == 0)
+ break;
+
+ for (i = 0; i < pages; i++)
+ add_page(voffset + i, index + i, buf[i]);
+
+ index += pages;
+ count -= pages;
+ }
+}
+
+#define PAGEMAP_BATCH (64 << 10)
+static void walk_vma(unsigned long index, unsigned long count)
+{
+ uint64_t buf[PAGEMAP_BATCH];
+ unsigned long batch;
+ unsigned long pages;
+ unsigned long pfn;
+ unsigned long i;
+
+ while (count) {
+ batch = min_t(unsigned long, count, PAGEMAP_BATCH);
+ pages = pagemap_read(buf, index, batch);
+ if (pages == 0)
+ break;
+
+ for (i = 0; i < pages; i++) {
+ pfn = pagemap_pfn(buf[i]);
+ if (pfn)
+ walk_pfn(index + i, pfn, 1);
+ }
+
+ index += pages;
+ count -= pages;
+ }
+}
+
+static void walk_task(unsigned long index, unsigned long count)
+{
+ const unsigned long end = index + count;
+ unsigned long start;
+ int i = 0;
+
+ while (index < end) {
+
+ while (pg_end[i] <= index)
+ if (++i >= nr_vmas)
+ return;
+ if (pg_start[i] >= end)
+ return;
+
+ start = max_t(unsigned long, pg_start[i], index);
+ index = min_t(unsigned long, pg_end[i], end);
+
+ assert(start < index);
+ walk_vma(start, index - start);
+ }
+}
+
+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;
+
+ kpageflags_fd = checked_open(PROC_KPAGEFLAGS, O_RDONLY);
+
+ if (!nr_addr_ranges)
+ add_addr_range(0, ULONG_MAX);
+
+ for (i = 0; i < nr_addr_ranges; i++)
+ if (!opt_pid)
+ walk_pfn(0, opt_offset[i], opt_size[i]);
+ else
+ walk_task(opt_offset[i], opt_size[i]);
+
+ close(kpageflags_fd);
+}
+
+
+/*
+ * user interface
+ */
+
+static const char *page_flag_type(uint64_t flag)
+{
+ if (flag & KPF_HACKERS_BITS)
+ return "(r)";
+ if (flag & KPF_OVERLOADED_BITS)
+ return "(o)";
+ return " ";
+}
+
+static void usage(void)
+{
+ int i, j;
+
+ printf(
+"page-types [options]\n"
+" -r|--raw Raw mode, for kernel developers\n"
+" -d|--describe flags Describe flags\n"
+" -a|--addr addr-spec Walk a range of pages\n"
+" -b|--bits bits-spec Walk pages with specified bits\n"
+" -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"
+" -L|--list-each Show page details one by one\n"
+" -N|--no-summary Don't show summary info\n"
+" -X|--hwpoison hwpoison pages\n"
+" -x|--unpoison unpoison pages\n"
+" -h|--help Show this usage message\n"
+"flags:\n"
+" 0x10 bitfield format, e.g.\n"
+" anon bit-name, e.g.\n"
+" 0x10,anon comma-separated list, e.g.\n"
+"addr-spec:\n"
+" N one page at offset N (unit: pages)\n"
+" 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-1\n"
+"bits-spec:\n"
+" bit1,bit2 (flags & (bit1|bit2)) != 0\n"
+" bit1,bit2=bit1 (flags & (bit1|bit2)) == bit1\n"
+" bit1,~bit2 (flags & (bit1|bit2)) == bit1\n"
+" =bit1,bit2 flags == (bit1|bit2)\n"
+"bit-names:\n"
+ );
+
+ for (i = 0, j = 0; i < ARRAY_SIZE(page_flag_names); i++) {
+ if (!page_flag_names[i])
+ continue;
+ printf("%16s%s", page_flag_names[i] + 2,
+ page_flag_type(1ULL << i));
+ if (++j > 3) {
+ j = 0;
+ putchar('\n');
+ }
+ }
+ printf("\n "
+ "(r) raw mode bits (o) overloaded bits\n");
+}
+
+static unsigned long long parse_number(const char *str)
+{
+ unsigned long long n;
+
+ n = strtoll(str, NULL, 0);
+
+ if (n == 0 && str[0] != '0')
+ fatal("invalid name or number: %s\n", str);
+
+ return n;
+}
+
+static void parse_pid(const char *str)
+{
+ FILE *file;
+ char buf[5000];
+
+ opt_pid = parse_number(str);
+
+ sprintf(buf, "/proc/%d/pagemap", opt_pid);
+ pagemap_fd = checked_open(buf, O_RDONLY);
+
+ 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);
+}
+
+static void parse_file(const char *name)
+{
+}
+
+static void parse_addr_range(const char *optarg)
+{
+ unsigned long offset;
+ unsigned long size;
+ char *p;
+
+ p = strchr(optarg, ',');
+ if (!p)
+ p = strchr(optarg, '+');
+
+ if (p == optarg) {
+ offset = 0;
+ size = parse_number(p + 1);
+ } else if (p) {
+ offset = parse_number(optarg);
+ if (p[1] == '\0')
+ size = ULONG_MAX;
+ else {
+ size = parse_number(p + 1);
+ if (*p == ',') {
+ if (size < offset)
+ fatal("invalid range: %lu,%lu\n",
+ offset, size);
+ size -= offset;
+ }
+ }
+ } else {
+ offset = parse_number(optarg);
+ size = 1;
+ }
+
+ add_addr_range(offset, size);
+}
+
+static void add_bits_filter(uint64_t mask, uint64_t bits)
+{
+ if (nr_bit_filters >= MAX_BIT_FILTERS)
+ fatal("too much bit filters\n");
+
+ opt_mask[nr_bit_filters] = mask;
+ opt_bits[nr_bit_filters] = bits;
+ nr_bit_filters++;
+}
+
+static uint64_t parse_flag_name(const char *str, int len)
+{
+ int i;
+
+ if (!*str || !len)
+ return 0;
+
+ if (len <= 8 && !strncmp(str, "compound", len))
+ return BITS_COMPOUND;
+
+ for (i = 0; i < ARRAY_SIZE(page_flag_names); i++) {
+ if (!page_flag_names[i])
+ continue;
+ if (!strncmp(str, page_flag_names[i] + 2, len))
+ return 1ULL << i;
+ }
+
+ return parse_number(str);
+}
+
+static uint64_t parse_flag_names(const char *str, int all)
+{
+ const char *p = str;
+ uint64_t flags = 0;
+
+ while (1) {
+ if (*p == ',' || *p == '=' || *p == '\0') {
+ if ((*str != '~') || (*str == '~' && all && *++str))
+ flags |= parse_flag_name(str, p - str);
+ if (*p != ',')
+ break;
+ str = p + 1;
+ }
+ p++;
+ }
+
+ return flags;
+}
+
+static void parse_bits_mask(const char *optarg)
+{
+ uint64_t mask;
+ uint64_t bits;
+ const char *p;
+
+ p = strchr(optarg, '=');
+ if (p == optarg) {
+ mask = KPF_ALL_BITS;
+ bits = parse_flag_names(p + 1, 0);
+ } else if (p) {
+ mask = parse_flag_names(optarg, 0);
+ bits = parse_flag_names(p + 1, 0);
+ } else if (strchr(optarg, '~')) {
+ mask = parse_flag_names(optarg, 1);
+ bits = parse_flag_names(optarg, 0);
+ } else {
+ mask = parse_flag_names(optarg, 0);
+ bits = KPF_ALL_BITS;
+ }
+
+ add_bits_filter(mask, bits);
+}
+
+static void describe_flags(const char *optarg)
+{
+ uint64_t flags = parse_flag_names(optarg, 0);
+
+ printf("0x%016llx\t%s\t%s\n",
+ (unsigned long long)flags,
+ page_flag_name(flags),
+ page_flag_longname(flags));
+}
+
+static const struct option opts[] = {
+ { "raw" , 0, NULL, 'r' },
+ { "pid" , 1, NULL, 'p' },
+ { "file" , 1, NULL, 'f' },
+ { "addr" , 1, NULL, 'a' },
+ { "bits" , 1, NULL, 'b' },
+ { "describe" , 1, NULL, 'd' },
+ { "list" , 0, NULL, 'l' },
+ { "list-each" , 0, NULL, 'L' },
+ { "no-summary", 0, NULL, 'N' },
+ { "hwpoison" , 0, NULL, 'X' },
+ { "unpoison" , 0, NULL, 'x' },
+ { "help" , 0, NULL, 'h' },
+ { NULL , 0, NULL, 0 }
+};
+
+int main(int argc, char *argv[])
+{
+ int c;
+
+ page_size = getpagesize();
+
+ while ((c = getopt_long(argc, argv,
+ "rp:f:a:b:d:lLNXxh", opts, NULL)) != -1) {
+ switch (c) {
+ case 'r':
+ opt_raw = 1;
+ break;
+ case 'p':
+ parse_pid(optarg);
+ break;
+ case 'f':
+ parse_file(optarg);
+ break;
+ case 'a':
+ parse_addr_range(optarg);
+ break;
+ case 'b':
+ parse_bits_mask(optarg);
+ break;
+ case 'd':
+ describe_flags(optarg);
+ exit(0);
+ case 'l':
+ opt_list = 1;
+ break;
+ case 'L':
+ opt_list = 2;
+ break;
+ case 'N':
+ opt_no_summary = 1;
+ break;
+ case 'X':
+ opt_hwpoison = 1;
+ prepare_hwpoison_fd();
+ break;
+ case 'x':
+ opt_unpoison = 1;
+ prepare_hwpoison_fd();
+ break;
+ case 'h':
+ usage();
+ exit(0);
+ default:
+ usage();
+ exit(1);
+ }
+ }
+
+ if (opt_list && opt_pid)
+ printf("voffset\t");
+ if (opt_list == 1)
+ printf("offset\tlen\tflags\n");
+ if (opt_list == 2)
+ printf("offset\tflags\n");
+
+ walk_addr_ranges();
+
+ if (opt_list == 1)
+ show_page_range(0, 0, 0); /* drain the buffer */
+
+ if (opt_no_summary)
+ return 0;
+
+ if (opt_list)
+ printf("\n\n");
+
+ show_summary();
+
+ return 0;
+}
--
1.7.4.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists