Update page-types

page-types is a utility to be used to translate address from
VA to PA. It has been updated in upstream kernel to accommodate
changes in the kernel. So it should be updated in mce-test, too.

Signed-off-by: Wen Jin <wenx.jin@intel.com>
Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>

5 files changed, 460 insertions, 114 deletions

diff --git a/tools/page-types/debugfs.h b/tools/page-types/debugfs.h
new file mode 100644
index 0000000..4550236
--- /dev/null
+++ b/tools/page-types/debugfs.h
@@ -0,0 +1,23 @@
+#ifndef __API_DEBUGFS_H__
+#define __API_DEBUGFS_H__
+
+#include "findfs.h"
+
+#ifndef DEBUGFS_MAGIC
+#define DEBUGFS_MAGIC          0x64626720
+#endif
+
+#ifndef PERF_DEBUGFS_ENVIRONMENT
+#define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR"
+#endif
+
+bool debugfs_configured(void);
+const char *debugfs_find_mountpoint(void);
+char *debugfs_mount(const char *mountpoint);
+
+extern char debugfs_mountpoint[];
+
+int debugfs__strerror_open(int err, char *buf, size_t size, const char *filename);
+int debugfs__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name);
+
+#endif /* __API_DEBUGFS_H__ */
diff --git a/tools/page-types/findfs.h b/tools/page-types/findfs.h
new file mode 100644
index 0000000..b6f5d05
--- /dev/null
+++ b/tools/page-types/findfs.h
@@ -0,0 +1,23 @@
+#ifndef __API_FINDFS_H__
+#define __API_FINDFS_H__
+
+#include <stdbool.h>
+
+#define _STR(x) #x
+#define STR(x) _STR(x)
+
+/*
+ * On most systems <limits.h> would have given us this, but  not on some systems
+ * (e.g. GNU/Hurd).
+ */
+#ifndef PATH_MAX
+#define PATH_MAX 4096
+#endif
+
+const char *find_mountpoint(const char *fstype, long magic,
+			    char *mountpoint, int len,
+			    const char * const *known_mountpoints);
+
+int valid_mountpoint(const char *mount, long magic);
+
+#endif /* __API_FINDFS_H__ */
diff --git a/tools/page-types/kernel-page-flags.h b/tools/page-types/kernel-page-flags.h
new file mode 100644
index 0000000..5da5f87
--- /dev/null
+++ b/tools/page-types/kernel-page-flags.h
@@ -0,0 +1,39 @@
+#ifndef _UAPILINUX_KERNEL_PAGE_FLAGS_H
+#define _UAPILINUX_KERNEL_PAGE_FLAGS_H
+
+/*
+ * Stable page flag bits exported to user space
+ */
+
+#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
+#define KPF_THP			22
+#define KPF_BALLOON		23
+#define KPF_ZERO_PAGE		24
+#define KPF_IDLE		25
+
+
+#endif /* _UAPILINUX_KERNEL_PAGE_FLAGS_H */
diff --git a/tools/page-types/magic.h b/tools/page-types/magic.h
new file mode 100644
index 0000000..e5124a7
--- /dev/null
+++ b/tools/page-types/magic.h
@@ -0,0 +1,79 @@
+#ifndef __LINUX_MAGIC_H__
+#define __LINUX_MAGIC_H__
+
+#define ADFS_SUPER_MAGIC	0xadf5
+#define AFFS_SUPER_MAGIC	0xadff
+#define AFS_SUPER_MAGIC                0x5346414F
+#define AUTOFS_SUPER_MAGIC	0x0187
+#define CODA_SUPER_MAGIC	0x73757245
+#define CRAMFS_MAGIC		0x28cd3d45	/* some random number */
+#define CRAMFS_MAGIC_WEND	0x453dcd28	/* magic number with the wrong endianess */
+#define DEBUGFS_MAGIC          0x64626720
+#define SECURITYFS_MAGIC	0x73636673
+#define SELINUX_MAGIC		0xf97cff8c
+#define SMACK_MAGIC		0x43415d53	/* "SMAC" */
+#define RAMFS_MAGIC		0x858458f6	/* some random number */
+#define TMPFS_MAGIC		0x01021994
+#define HUGETLBFS_MAGIC 	0x958458f6	/* some random number */
+#define SQUASHFS_MAGIC		0x73717368
+#define ECRYPTFS_SUPER_MAGIC	0xf15f
+#define EFS_SUPER_MAGIC		0x414A53
+#define EXT2_SUPER_MAGIC	0xEF53
+#define EXT3_SUPER_MAGIC	0xEF53
+#define XENFS_SUPER_MAGIC	0xabba1974
+#define EXT4_SUPER_MAGIC	0xEF53
+#define BTRFS_SUPER_MAGIC	0x9123683E
+#define NILFS_SUPER_MAGIC	0x3434
+#define F2FS_SUPER_MAGIC	0xF2F52010
+#define HPFS_SUPER_MAGIC	0xf995e849
+#define ISOFS_SUPER_MAGIC	0x9660
+#define JFFS2_SUPER_MAGIC	0x72b6
+#define PSTOREFS_MAGIC		0x6165676C
+#define EFIVARFS_MAGIC		0xde5e81e4
+#define HOSTFS_SUPER_MAGIC	0x00c0ffee
+
+#define MINIX_SUPER_MAGIC	0x137F		/* minix v1 fs, 14 char names */
+#define MINIX_SUPER_MAGIC2	0x138F		/* minix v1 fs, 30 char names */
+#define MINIX2_SUPER_MAGIC	0x2468		/* minix v2 fs, 14 char names */
+#define MINIX2_SUPER_MAGIC2	0x2478		/* minix v2 fs, 30 char names */
+#define MINIX3_SUPER_MAGIC	0x4d5a		/* minix v3 fs, 60 char names */
+
+#define MSDOS_SUPER_MAGIC	0x4d44		/* MD */
+#define NCP_SUPER_MAGIC		0x564c		/* Guess, what 0x564c is :-) */
+#define NFS_SUPER_MAGIC		0x6969
+#define OPENPROM_SUPER_MAGIC	0x9fa1
+#define QNX4_SUPER_MAGIC	0x002f		/* qnx4 fs detection */
+#define QNX6_SUPER_MAGIC	0x68191122	/* qnx6 fs detection */
+
+#define REISERFS_SUPER_MAGIC	0x52654973	/* used by gcc */
+					/* used by file system utilities that
+					   look at the superblock, etc.  */
+#define REISERFS_SUPER_MAGIC_STRING	"ReIsErFs"
+#define REISER2FS_SUPER_MAGIC_STRING	"ReIsEr2Fs"
+#define REISER2FS_JR_SUPER_MAGIC_STRING	"ReIsEr3Fs"
+
+#define SMB_SUPER_MAGIC		0x517B
+#define CGROUP_SUPER_MAGIC	0x27e0eb
+
+
+#define STACK_END_MAGIC		0x57AC6E9D
+
+#define TRACEFS_MAGIC          0x74726163
+
+#define V9FS_MAGIC		0x01021997
+
+#define BDEVFS_MAGIC            0x62646576
+#define BINFMTFS_MAGIC          0x42494e4d
+#define DEVPTS_SUPER_MAGIC	0x1cd1
+#define FUTEXFS_SUPER_MAGIC	0xBAD1DEA
+#define PIPEFS_MAGIC            0x50495045
+#define PROC_SUPER_MAGIC	0x9fa0
+#define SOCKFS_MAGIC		0x534F434B
+#define SYSFS_MAGIC		0x62656572
+#define USBDEVICE_SUPER_MAGIC	0x9fa2
+#define MTD_INODE_FS_MAGIC      0x11307854
+#define ANON_INODE_FS_MAGIC	0x09041934
+#define BTRFS_TEST_MAGIC	0x73727279
+#define NSFS_MAGIC		0x6e736673
+
+#endif /* __LINUX_MAGIC_H__ */
diff --git a/tools/page-types/page-types.c b/tools/page-types/page-types.c
index 35f5769..fcd4480 100644
--- a/tools/page-types/page-types.c
+++ b/tools/page-types/page-types.c
@@ -19,7 +19,8 @@
  * Authors: Wu Fengguang <fengguang.wu@intel.com>
  */
 
-#define _LARGEFILE64_SOURCE
+#define _FILE_OFFSET_BITS 64
+#define _GNU_SOURCE
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
@@ -29,12 +30,19 @@
 #include <getopt.h>
 #include <limits.h>
 #include <assert.h>
+#include <ftw.h>
+#include <time.h>
+#include <setjmp.h>
+#include <signal.h>
 #include <sys/types.h>
 #include <sys/errno.h>
 #include <sys/fcntl.h>
 #include <sys/mount.h>
 #include <sys/statfs.h>
-
+#include <sys/mman.h>
+#include "magic.h"
+#include "kernel-page-flags.h"
+#include "debugfs.h"
 
 #ifndef MAX_PATH
 # define MAX_PATH 256
@@ -49,21 +57,15 @@
  * 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)
-
+#define PM_ENTRY_BYTES		8
+#define PM_PFRAME_BITS		55
+#define PM_PFRAME_MASK		((1LL << PM_PFRAME_BITS) - 1)
+#define PM_PFRAME(x)		((x) & PM_PFRAME_MASK)
+#define PM_SOFT_DIRTY		(1ULL << 55)
+#define PM_MMAP_EXCLUSIVE	(1ULL << 56)
+#define PM_FILE			(1ULL << 61)
+#define PM_SWAP			(1ULL << 62)
+#define PM_PRESENT		(1ULL << 63)
 
 /*
  * kernel page flags
@@ -72,33 +74,6 @@
 #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
-#define KPF_THP			22
-
 /* [32-] kernel hacking assistances */
 #define KPF_RESERVED		32
 #define KPF_MLOCKED		33
@@ -108,6 +83,7 @@
 #define KPF_OWNER_PRIVATE	37
 #define KPF_ARCH		38
 #define KPF_UNCACHED		39
+#define KPF_SOFTDIRTY		40
 
 /* [48-] take some arbitrary free slots for expanding overloaded flags
  * not part of kernel API
@@ -116,6 +92,8 @@
 #define KPF_SLOB_FREE		49
 #define KPF_SLUB_FROZEN		50
 #define KPF_SLUB_DEBUG		51
+#define KPF_FILE		62
+#define KPF_MMAP_EXCLUSIVE	63
 
 #define KPF_ALL_BITS		((uint64_t)~0ULL)
 #define KPF_HACKERS_BITS	(0xffffULL << 32)
@@ -123,9 +101,6 @@
 #define BIT(name)		(1ULL << KPF_##name)
 #define BITS_COMPOUND		(BIT(COMPOUND_HEAD) | BIT(COMPOUND_TAIL))
 
-/* copied from include/uapi/linux/magic.h */
-#define DEBUGFS_MAGIC          0x64626720
-
 static const char * const page_flag_names[] = {
 	[KPF_LOCKED]		= "L:locked",
 	[KPF_ERROR]		= "E:error",
@@ -151,6 +126,8 @@ static const char * const page_flag_names[] = {
 	[KPF_NOPAGE]		= "n:nopage",
 	[KPF_KSM]		= "x:ksm",
 	[KPF_THP]		= "t:thp",
+	[KPF_BALLOON]		= "o:balloon",
+	[KPF_ZERO_PAGE]		= "z:zero_page",
 
 	[KPF_RESERVED]		= "r:reserved",
 	[KPF_MLOCKED]		= "m:mlocked",
@@ -160,11 +137,15 @@ static const char * const page_flag_names[] = {
 	[KPF_OWNER_PRIVATE]	= "O:owner_private",
 	[KPF_ARCH]		= "h:arch",
 	[KPF_UNCACHED]		= "c:uncached",
+	[KPF_SOFTDIRTY]		= "f:softdirty",
 
 	[KPF_READAHEAD]		= "I:readahead",
 	[KPF_SLOB_FREE]		= "P:slob_free",
 	[KPF_SLUB_FROZEN]	= "A:slub_frozen",
 	[KPF_SLUB_DEBUG]	= "E:slub_debug",
+
+	[KPF_FILE]		= "F:file",
+	[KPF_MMAP_EXCLUSIVE]	= "1:mmap_exclusive",
 };
 
 
@@ -182,6 +163,7 @@ 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 */
+const char *		opt_file;
 
 #define MAX_ADDR_RANGES	1024
 static int		nr_addr_ranges;
@@ -206,7 +188,7 @@ static int		kpageflags_fd;
 static int		opt_hwpoison;
 static int		opt_unpoison;
 
-static char		hwpoison_debug_fs[MAX_PATH+1];
+static char		*hwpoison_debug_fs;
 static int		hwpoison_inject_fd;
 static int		hwpoison_forget_fd;
 
@@ -277,12 +259,7 @@ static unsigned long do_u64_read(int fd, char *name,
 	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);
+	bytes = pread(fd, buf, count * 8, (off_t)index * 8);
 	if (bytes < 0) {
 		perror(name);
 		exit(EXIT_FAILURE);
@@ -367,8 +344,8 @@ static char *page_flag_longname(uint64_t flags)
  * page list and summary
  */
 
-static void show_page_range(unsigned long voffset,
-			    unsigned long offset, uint64_t flags)
+static void show_page_range(unsigned long voffset, unsigned long offset,
+			    unsigned long size, uint64_t flags)
 {
 	static uint64_t      flags0;
 	static unsigned long voff;
@@ -376,14 +353,16 @@ static void show_page_range(unsigned long voffset,
 	static unsigned long count;
 
 	if (flags == flags0 && offset == index + count &&
-	    (!opt_pid || voffset == voff + count)) {
-		count++;
+	    size && voffset == voff + count) {
+		count += size;
 		return;
 	}
 
 	if (count) {
 		if (opt_pid)
 			printf("%lx\t", voff);
+		if (opt_file)
+			printf("%lu\t", voff);
 		printf("%lx\t%lx\t%s\n",
 				index, count, page_flag_name(flags0));
 	}
@@ -391,7 +370,12 @@ static void show_page_range(unsigned long voffset,
 	flags0 = flags;
 	index  = offset;
 	voff   = voffset;
-	count  = 1;
+	count  = size;
+}
+
+static void flush_page_range(void)
+{
+	show_page_range(0, 0, 0, 0);
 }
 
 static void show_page(unsigned long voffset,
@@ -399,6 +383,8 @@ static void show_page(unsigned long voffset,
 {
 	if (opt_pid)
 		printf("%lx\t", voffset);
+	if (opt_file)
+		printf("%lu\t", voffset);
 	printf("%lx\t%s\n", offset, page_flag_name(flags));
 }
 
@@ -445,7 +431,7 @@ static int bit_mask_ok(uint64_t flags)
 	return 1;
 }
 
-static uint64_t expand_overloaded_flags(uint64_t flags)
+static uint64_t expand_overloaded_flags(uint64_t flags, uint64_t pme)
 {
 	/* SLOB/SLUB overload several page flags */
 	if (flags & BIT(SLAB)) {
@@ -461,6 +447,13 @@ static uint64_t expand_overloaded_flags(uint64_t flags)
 	if ((flags & (BIT(RECLAIM) | BIT(WRITEBACK))) == BIT(RECLAIM))
 		flags ^= BIT(RECLAIM) | BIT(READAHEAD);
 
+	if (pme & PM_SOFT_DIRTY)
+		flags |= BIT(SOFTDIRTY);
+	if (pme & PM_FILE)
+		flags |= BIT(FILE);
+	if (pme & PM_MMAP_EXCLUSIVE)
+		flags |= BIT(MMAP_EXCLUSIVE);
+
 	return flags;
 }
 
@@ -476,91 +469,123 @@ static uint64_t well_known_flags(uint64_t flags)
 	return flags;
 }
 
-static uint64_t kpageflags_flags(uint64_t flags)
+static uint64_t kpageflags_flags(uint64_t flags, uint64_t pme)
 {
-	flags = expand_overloaded_flags(flags);
-
-	if (!opt_raw)
+	if (opt_raw)
+		flags = expand_overloaded_flags(flags, pme);
+	else
 		flags = well_known_flags(flags);
 
 	return flags;
 }
 
-/* verify that a mountpoint is actually a debugfs instance */
-static int debugfs_valid_mountpoint(const char *debugfs)
+
+int valid_mountpoint(const char *mount, long magic)
 {
 	struct statfs st_fs;
 
-	if (statfs(debugfs, &st_fs) < 0)
+	if (statfs(mount, &st_fs) < 0)
 		return -ENOENT;
-	else if (st_fs.f_type != (long) DEBUGFS_MAGIC)
+	else if ((long)st_fs.f_type != magic)
 		return -ENOENT;
 
 	return 0;
 }
 
-/* find the path to the mounted debugfs */
-static const char *debugfs_find_mountpoint(void)
+/* find the path to a mounted file system */
+const char *find_mountpoint(const char *fstype, long magic,
+			     char *mountpoint, int len,
+			     const char * const *known_mountpoints)
 {
-	const char *const *ptr;
+	const char * const *ptr;
+	char format[128];
 	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;
+	if (known_mountpoints) {
+		ptr = known_mountpoints;
+		while (*ptr) {
+			if (valid_mountpoint(*ptr, magic) == 0) {
+				strncpy(mountpoint, *ptr, len - 1);
+				mountpoint[len-1] = 0;
+				return mountpoint;
+			}
+			ptr++;
 		}
-		ptr++;
 	}
 
 	/* give up and parse /proc/mounts */
 	fp = fopen("/proc/mounts", "r");
 	if (fp == NULL)
-		perror("Can't open /proc/mounts for read");
+		return NULL;
+
+	snprintf(format, 128, "%%*s %%%ds %%99s %%*s %%*d %%*d\n", len);
 
-	while (fscanf(fp, "%*s %"
-		      STR(MAX_PATH)
-		      "s %99s %*s %*d %*d\n",
-		      hwpoison_debug_fs, type) == 2) {
-		if (strcmp(type, "debugfs") == 0)
+	while (fscanf(fp, format, mountpoint, type) == 2) {
+		if (strcmp(type, fstype) == 0)
 			break;
 	}
 	fclose(fp);
 
-	if (strcmp(type, "debugfs") != 0)
+	if (strcmp(type, fstype) != 0)
 		return NULL;
 
-	return hwpoison_debug_fs;
+	return mountpoint;
 }
 
-/* mount the debugfs somewhere if it's not mounted */
 
-static void debugfs_mount(void)
+#ifndef DEBUGFS_DEFAULT_PATH
+#define DEBUGFS_DEFAULT_PATH            "/sys/kernel/debug"
+#endif
+
+char debugfs_mountpoint[PATH_MAX + 1] = DEBUGFS_DEFAULT_PATH;
+static bool debugfs_found;
+
+/* find the path to the mounted debugfs */
+const char *debugfs_find_mountpoint(void)
 {
-	const char *const *ptr;
+	const char *ret;
 
+	if (debugfs_found)
+		return (const char *)debugfs_mountpoint;
+
+	ret = find_mountpoint("debugfs", (long) DEBUGFS_MAGIC,
+			      debugfs_mountpoint, PATH_MAX + 1,
+			      debugfs_known_mountpoints);
+	if (ret)
+		debugfs_found = true;
+
+	return ret;
+}
+
+
+/* mount the debugfs somewhere if it's not mounted */
+char *debugfs_mount(const char *mountpoint)
+{
 	/* 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++;
+		goto out;
+
+	/* if not mounted and no argument */
+	if (mountpoint == NULL) {
+		/* see if environment variable set */
+		mountpoint = getenv(PERF_DEBUGFS_ENVIRONMENT);
+		/* if no environment variable, use default */
+		if (mountpoint == NULL)
+			mountpoint = DEBUGFS_DEFAULT_PATH;
 	}
 
-	if (*ptr == NULL) {
-		perror("mount debugfs");
-		exit(EXIT_FAILURE);
-	}
+	if (mount(NULL, mountpoint, "debugfs", 0, NULL) < 0)
+		return NULL;
+
+	/* save the mountpoint */
+	debugfs_found = true;
+	strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint));
+out:
+	return debugfs_mountpoint;
 }
 
+
 /*
  * page actions
  */
@@ -569,7 +594,11 @@ static void prepare_hwpoison_fd(void)
 {
 	char buf[MAX_PATH + 1];
 
-	debugfs_mount();
+	hwpoison_debug_fs = debugfs_mount(NULL);
+	if (!hwpoison_debug_fs) {
+		perror("mount debugfs");
+		exit(EXIT_FAILURE);
+	}
 
 	if (opt_hwpoison && !hwpoison_inject_fd) {
 		snprintf(buf, MAX_PATH, "%s/hwpoison/corrupt-pfn",
@@ -644,9 +673,9 @@ static size_t hash_slot(uint64_t flags)
 }
 
 static void add_page(unsigned long voffset,
-		     unsigned long offset, uint64_t flags)
+		     unsigned long offset, uint64_t flags, uint64_t pme)
 {
-	flags = kpageflags_flags(flags);
+	flags = kpageflags_flags(flags, pme);
 
 	if (!bit_mask_ok(flags))
 		return;
@@ -657,7 +686,7 @@ static void add_page(unsigned long voffset,
 		unpoison_page(offset);
 
 	if (opt_list == 1)
-		show_page_range(voffset, offset, flags);
+		show_page_range(voffset, offset, 1, flags);
 	else if (opt_list == 2)
 		show_page(voffset, offset, flags);
 
@@ -668,7 +697,8 @@ static void add_page(unsigned long voffset,
 #define KPAGEFLAGS_BATCH	(64 << 10)	/* 64k pages */
 static void walk_pfn(unsigned long voffset,
 		     unsigned long index,
-		     unsigned long count)
+		     unsigned long count,
+		     uint64_t pme)
 {
 	uint64_t buf[KPAGEFLAGS_BATCH];
 	unsigned long batch;
@@ -682,7 +712,7 @@ static void walk_pfn(unsigned long voffset,
 			break;
 
 		for (i = 0; i < pages; i++)
-			add_page(voffset + i, index + i, buf[i]);
+			add_page(voffset + i, index + i, buf[i], pme);
 
 		index += pages;
 		count -= pages;
@@ -707,7 +737,7 @@ static void walk_vma(unsigned long index, unsigned long count)
 		for (i = 0; i < pages; i++) {
 			pfn = pagemap_pfn(buf[i]);
 			if (pfn)
-				walk_pfn(index + i, pfn, 1);
+				walk_pfn(index + i, pfn, 1, buf[i]);
 		}
 
 		index += pages;
@@ -758,7 +788,7 @@ static void walk_addr_ranges(void)
 
 	for (i = 0; i < nr_addr_ranges; i++)
 		if (!opt_pid)
-			walk_pfn(0, opt_offset[i], opt_size[i]);
+			walk_pfn(opt_offset[i], opt_offset[i], opt_size[i], 0);
 		else
 			walk_task(opt_offset[i], opt_size[i]);
 
@@ -790,9 +820,7 @@ static void usage(void)
 "            -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"
@@ -890,8 +918,157 @@ static void parse_pid(const char *str)
 	fclose(file);
 }
 
+static void show_file(const char *name, const struct stat *st)
+{
+	unsigned long long size = st->st_size;
+	char atime[64], mtime[64];
+	long now = time(NULL);
+
+	printf("%s\tInode: %u\tSize: %llu (%llu pages)\n",
+			name, (unsigned)st->st_ino,
+			size, (size + page_size - 1) / page_size);
+
+	strftime(atime, sizeof(atime), "%c", localtime(&st->st_atime));
+	strftime(mtime, sizeof(mtime), "%c", localtime(&st->st_mtime));
+
+	printf("Modify: %s (%ld seconds ago)\nAccess: %s (%ld seconds ago)\n",
+			mtime, now - st->st_mtime,
+			atime, now - st->st_atime);
+}
+
+static sigjmp_buf sigbus_jmp;
+
+static void * volatile sigbus_addr;
+
+static void sigbus_handler(int sig, siginfo_t *info, void *ucontex)
+{
+	(void)sig;
+	(void)ucontex;
+	sigbus_addr = info ? info->si_addr : NULL;
+	siglongjmp(sigbus_jmp, 1);
+}
+
+static struct sigaction sigbus_action = {
+	.sa_sigaction = sigbus_handler,
+	.sa_flags = SA_SIGINFO,
+};
+
+static void walk_file(const char *name, const struct stat *st)
+{
+	uint8_t vec[PAGEMAP_BATCH];
+	uint64_t buf[PAGEMAP_BATCH], flags;
+	unsigned long nr_pages, pfn, i;
+	off_t off, end = st->st_size;
+	int fd;
+	ssize_t len;
+	void *ptr;
+	int first = 1;
+
+	fd = checked_open(name, O_RDONLY|O_NOATIME|O_NOFOLLOW);
+
+	for (off = 0; off < end; off += len) {
+		nr_pages = (end - off + page_size - 1) / page_size;
+		if (nr_pages > PAGEMAP_BATCH)
+			nr_pages = PAGEMAP_BATCH;
+		len = nr_pages * page_size;
+
+		ptr = mmap(NULL, len, PROT_READ, MAP_SHARED, fd, off);
+		if (ptr == MAP_FAILED)
+			fatal("mmap failed: %s", name);
+
+		/* determine cached pages */
+		if (mincore(ptr, len, vec))
+			fatal("mincore failed: %s", name);
+
+		/* turn off readahead */
+		if (madvise(ptr, len, MADV_RANDOM))
+			fatal("madvice failed: %s", name);
+
+		if (sigsetjmp(sigbus_jmp, 1)) {
+			end = off + sigbus_addr ? sigbus_addr - ptr : 0;
+			fprintf(stderr, "got sigbus at offset %lld: %s\n",
+					(long long)end, name);
+			goto got_sigbus;
+		}
+
+		/* populate ptes */
+		for (i = 0; i < nr_pages ; i++) {
+			if (vec[i] & 1)
+				(void)*(volatile int *)(ptr + i * page_size);
+		}
+got_sigbus:
+
+		/* turn off harvesting reference bits */
+		if (madvise(ptr, len, MADV_SEQUENTIAL))
+			fatal("madvice failed: %s", name);
+
+		if (pagemap_read(buf, (unsigned long)ptr / page_size,
+					nr_pages) != nr_pages)
+			fatal("cannot read pagemap");
+
+		munmap(ptr, len);
+
+		for (i = 0; i < nr_pages; i++) {
+			pfn = pagemap_pfn(buf[i]);
+			if (!pfn)
+				continue;
+			if (!kpageflags_read(&flags, pfn, 1))
+				continue;
+			if (first && opt_list) {
+				first = 0;
+				flush_page_range();
+				show_file(name, st);
+			}
+			add_page(off / page_size + i, pfn, flags, buf[i]);
+		}
+	}
+
+	close(fd);
+}
+
+int walk_tree(const char *name, const struct stat *st, int type, struct FTW *f)
+{
+	(void)f;
+	switch (type) {
+	case FTW_F:
+		if (S_ISREG(st->st_mode))
+			walk_file(name, st);
+		break;
+	case FTW_DNR:
+		fprintf(stderr, "cannot read dir: %s\n", name);
+		break;
+	}
+	return 0;
+}
+
+static void walk_page_cache(void)
+{
+	struct stat st;
+
+	kpageflags_fd = checked_open(PROC_KPAGEFLAGS, O_RDONLY);
+	pagemap_fd = checked_open("/proc/self/pagemap", O_RDONLY);
+	sigaction(SIGBUS, &sigbus_action, NULL);
+
+	if (stat(opt_file, &st))
+		fatal("stat failed: %s\n", opt_file);
+
+	if (S_ISREG(st.st_mode)) {
+		walk_file(opt_file, &st);
+	} else if (S_ISDIR(st.st_mode)) {
+		/* do not follow symlinks and mountpoints */
+		if (nftw(opt_file, walk_tree, 64, FTW_MOUNT | FTW_PHYS) < 0)
+			fatal("nftw failed: %s\n", opt_file);
+	} else
+		fatal("unhandled file type: %s\n", opt_file);
+
+	close(kpageflags_fd);
+	close(pagemap_fd);
+	signal(SIGBUS, SIG_DFL);
+}
+
 static void parse_file(const char *name)
 {
+	opt_file = name;
 }
 
 static void parse_addr_range(const char *optarg)
@@ -1082,15 +1259,20 @@ int main(int argc, char *argv[])
 
 	if (opt_list && opt_pid)
 		printf("voffset\t");
+	if (opt_list && opt_file)
+		printf("foffset\t");
 	if (opt_list == 1)
 		printf("offset\tlen\tflags\n");
 	if (opt_list == 2)
 		printf("offset\tflags\n");
 
-	walk_addr_ranges();
+	if (opt_file)
+		walk_page_cache();
+	else
+		walk_addr_ranges();
 
 	if (opt_list == 1)
-		show_page_range(0, 0, 0);  /* drain the buffer */
+		flush_page_range();
 
 	if (opt_no_summary)
 		return 0;