* page-types: Tool for querying page flags
*
* Copyright (C) 2009 Intel corporation
- * Copyright (C) 2009 Wu Fengguang <fengguang.wu@intel.com>
+ *
+ * Authors: Wu Fengguang <fengguang.wu@intel.com>
+ *
+ * Released under the General Public License (GPL).
*/
+#define _LARGEFILE64_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <unistd.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>
/*
+ * 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_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
[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",
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 int page_size;
-#define PAGES_BATCH (64 << 10) /* 64k pages */
+static int pagemap_fd;
static int kpageflags_fd;
-static uint64_t kpageflags_buf[KPF_BYTES * PAGES_BATCH];
+
+static int opt_hwpoison;
+static int opt_unpoison;
+
+static char *hwpoison_debug_fs = "/debug/hwpoison";
+static int hwpoison_inject_fd;
+static int hwpoison_forget_fd;
#define HASH_SHIFT 13
#define HASH_SIZE (1 << HASH_SHIFT)
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;
exit(EXIT_FAILURE);
}
+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
present = (flags >> i) & 1;
if (!page_flag_names[i]) {
if (present)
- fatal("unkown flag bit %d\n", i);
+ fatal("unknown flag bit %d\n", i);
continue;
}
buf[j++] = present ? page_flag_names[i][0] : '_';
* page list and summary
*/
-static void show_page_range(unsigned long offset, uint64_t flags)
+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) {
+ 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;
}
-static void show_page(unsigned long offset, uint64_t flags)
+static void show_page(unsigned long voffset,
+ 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));
}
static void show_summary(void)
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;
+}
+
+/*
+ * page actions
+ */
+
+static void prepare_hwpoison_fd(void)
+{
+ char buf[100];
+
+ if (opt_hwpoison && !hwpoison_inject_fd) {
+ sprintf(buf, "%s/corrupt-pfn", hwpoison_debug_fs);
+ hwpoison_inject_fd = checked_open(buf, O_WRONLY);
+ }
+
+ if (opt_unpoison && !hwpoison_forget_fd) {
+ sprintf(buf, "%s/renew-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
exit(EXIT_FAILURE);
}
-static void add_page(unsigned long offset, uint64_t flags)
+static void add_page(unsigned long voffset,
+ unsigned long offset, uint64_t flags)
{
- flags = expand_overloaded_flags(flags);
-
- if (!opt_raw)
- flags = well_known_flags(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(offset, flags);
+ show_page_range(voffset, offset, flags);
else if (opt_list == 2)
- show_page(offset, flags);
+ show_page(voffset, offset, flags);
nr_pages[hash_slot(flags)]++;
total_pages++;
}
-static void walk_pfn(unsigned long index, unsigned long count)
+#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;
- unsigned long n;
+ unsigned long pages;
unsigned long i;
- if (index > ULONG_MAX / KPF_BYTES)
- fatal("index overflow: %lu\n", index);
+ 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;
+ }
+}
- lseek(kpageflags_fd, index * KPF_BYTES, SEEK_SET);
+#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, PAGES_BATCH);
- n = read(kpageflags_fd, kpageflags_buf, batch * KPF_BYTES);
- if (n == 0)
+ batch = min_t(unsigned long, count, PAGEMAP_BATCH);
+ pages = pagemap_read(buf, index, batch);
+ if (pages == 0)
break;
- if (n < 0) {
- perror(PROC_KPAGEFLAGS);
- exit(EXIT_FAILURE);
+
+ for (i = 0; i < pages; i++) {
+ pfn = pagemap_pfn(buf[i]);
+ if (pfn)
+ walk_pfn(index + i, pfn, 1);
}
- if (n % KPF_BYTES != 0)
- fatal("partial read: %lu bytes\n", n);
- n = n / KPF_BYTES;
+ 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) {
- for (i = 0; i < n; i++)
- add_page(index + i, kpageflags_buf[i]);
+ while (pg_end[i] <= index)
+ if (++i >= nr_vmas)
+ return;
+ if (pg_start[i] >= end)
+ return;
- index += batch;
- count -= batch;
+ 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 = open(PROC_KPAGEFLAGS, O_RDONLY);
- if (kpageflags_fd < 0) {
- perror(PROC_KPAGEFLAGS);
- exit(EXIT_FAILURE);
- }
+ kpageflags_fd = checked_open(PROC_KPAGEFLAGS, O_RDONLY);
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(0, opt_offset[i], opt_size[i]);
+ else
+ walk_task(opt_offset[i], opt_size[i]);
close(kpageflags_fd);
}
" -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"
" -L|--list-each Show page details one by one\n"
" -N|--no-summary Don't show summay info\n"
+" -X|--hwpoison hwpoison pages\n"
+" -x|--unpoison unpoison pages\n"
" -h|--help Show this usage message\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\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"
static void parse_pid(const char *str)
{
+ FILE *file;
+ char buf[5000];
+
opt_pid = parse_number(str);
-}
-static void parse_file(const char *name)
-{
+ 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 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++;
}
static void parse_addr_range(const char *optarg)
{ "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 }
};
page_size = getpagesize();
while ((c = getopt_long(argc, argv,
- "rp:f:a:b:lLNh", opts, NULL)) != -1) {
+ "rp:f:a:b:lLNXxh", opts, NULL)) != -1) {
switch (c) {
case 'r':
opt_raw = 1;
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);
}
}
+ 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");
walk_addr_ranges();
if (opt_list == 1)
- show_page_range(0, 0); /* drain the buffer */
+ show_page_range(0, 0, 0); /* drain the buffer */
if (opt_no_summary)
return 0;
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff