summaryrefslogtreecommitdiffstats
path: root/kernel/tools/vm
diff options
context:
space:
mode:
authorYunhong Jiang <yunhong.jiang@intel.com>2015-08-04 12:17:53 -0700
committerYunhong Jiang <yunhong.jiang@intel.com>2015-08-04 15:44:42 -0700
commit9ca8dbcc65cfc63d6f5ef3312a33184e1d726e00 (patch)
tree1c9cafbcd35f783a87880a10f85d1a060db1a563 /kernel/tools/vm
parent98260f3884f4a202f9ca5eabed40b1354c489b29 (diff)
Add the rt linux 4.1.3-rt3 as base
Import the rt linux 4.1.3-rt3 as OPNFV kvm base. It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and the base is: commit 0917f823c59692d751951bf5ea699a2d1e2f26a2 Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Date: Sat Jul 25 12:13:34 2015 +0200 Prepare v4.1.3-rt3 Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> We lose all the git history this way and it's not good. We should apply another opnfv project repo in future. Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423 Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>
Diffstat (limited to 'kernel/tools/vm')
-rw-r--r--kernel/tools/vm/.gitignore2
-rw-r--r--kernel/tools/vm/Makefile22
-rw-r--r--kernel/tools/vm/page-types.c1178
-rw-r--r--kernel/tools/vm/page_owner_sort.c144
-rw-r--r--kernel/tools/vm/slabinfo.c1393
5 files changed, 2739 insertions, 0 deletions
diff --git a/kernel/tools/vm/.gitignore b/kernel/tools/vm/.gitignore
new file mode 100644
index 000000000..44f095fa2
--- /dev/null
+++ b/kernel/tools/vm/.gitignore
@@ -0,0 +1,2 @@
+slabinfo
+page-types
diff --git a/kernel/tools/vm/Makefile b/kernel/tools/vm/Makefile
new file mode 100644
index 000000000..93aadaf7f
--- /dev/null
+++ b/kernel/tools/vm/Makefile
@@ -0,0 +1,22 @@
+# Makefile for vm tools
+#
+TARGETS=page-types slabinfo page_owner_sort
+
+LIB_DIR = ../lib/api
+LIBS = $(LIB_DIR)/libapi.a
+
+CC = $(CROSS_COMPILE)gcc
+CFLAGS = -Wall -Wextra -I../lib/
+LDFLAGS = $(LIBS)
+
+$(TARGETS): $(LIBS)
+
+$(LIBS):
+ make -C $(LIB_DIR)
+
+%: %.c
+ $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS)
+
+clean:
+ $(RM) page-types slabinfo page_owner_sort
+ make -C $(LIB_DIR) clean
diff --git a/kernel/tools/vm/page-types.c b/kernel/tools/vm/page-types.c
new file mode 100644
index 000000000..8bdf16b8b
--- /dev/null
+++ b/kernel/tools/vm/page-types.c
@@ -0,0 +1,1178 @@
+/*
+ * 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@intel.com>
+ */
+
+#define _FILE_OFFSET_BITS 64
+#define _GNU_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 <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 "../../include/uapi/linux/magic.h"
+#include "../../include/uapi/linux/kernel-page-flags.h"
+#include <api/fs/debugfs.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) (((uint64_t) (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_SOFT_DIRTY (1LL)
+#define PM_PRESENT PM_STATUS(4LL)
+#define PM_SWAP PM_STATUS(2LL)
+#define PM_SOFT_DIRTY __PM_PSHIFT(__PM_SOFT_DIRTY)
+
+
+/*
+ * kernel page flags
+ */
+
+#define KPF_BYTES 8
+#define PROC_KPAGEFLAGS "/proc/kpageflags"
+
+/* [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
+#define KPF_SOFTDIRTY 40
+
+/* [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_THP] = "t:thp",
+ [KPF_BALLOON] = "o:balloon",
+ [KPF_ZERO_PAGE] = "z:zero_page",
+
+ [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_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",
+};
+
+
+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 */
+const char * opt_file;
+
+#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;
+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);
+
+ bytes = pread(fd, buf, count * 8, (off_t)index * 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;
+ size_t 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];
+ size_t 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,
+ unsigned long size, 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 &&
+ 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));
+ }
+
+ flags0 = flags;
+ index = offset;
+ voff = voffset;
+ count = size;
+}
+
+static void flush_page_range(void)
+{
+ show_page_range(0, 0, 0, 0);
+}
+
+static void show_page(unsigned long voffset,
+ unsigned long offset, uint64_t flags)
+{
+ if (opt_pid)
+ printf("%lx\t", voffset);
+ if (opt_file)
+ printf("%lu\t", voffset);
+ printf("%lx\t%s\n", offset, page_flag_name(flags));
+}
+
+static void show_summary(void)
+{
+ size_t 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, uint64_t pme)
+{
+ /* 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);
+
+ if (pme & PM_SOFT_DIRTY)
+ flags |= BIT(SOFTDIRTY);
+
+ 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, uint64_t pme)
+{
+ if (opt_raw)
+ flags = expand_overloaded_flags(flags, pme);
+ else
+ flags = well_known_flags(flags);
+
+ return flags;
+}
+
+/*
+ * page actions
+ */
+
+static void prepare_hwpoison_fd(void)
+{
+ char buf[MAX_PATH + 1];
+
+ 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",
+ 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 size_t hash_slot(uint64_t flags)
+{
+ size_t k = HASH_KEY(flags);
+ size_t 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, uint64_t pme)
+{
+ flags = kpageflags_flags(flags, pme);
+
+ 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, 1, 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 pme)
+{
+ uint64_t buf[KPAGEFLAGS_BATCH];
+ unsigned long batch;
+ unsigned 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], pme);
+
+ 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, buf[i]);
+ }
+
+ 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(opt_offset[i], opt_offset[i], opt_size[i], 0);
+ 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)
+{
+ size_t 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"
+" -f|--file filename Walk file address space\n"
+" -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 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)
+{
+ 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)
+{
+ size_t 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 && opt_file)
+ printf("foffset\t");
+ if (opt_list == 1)
+ printf("offset\tlen\tflags\n");
+ if (opt_list == 2)
+ printf("offset\tflags\n");
+
+ if (opt_file)
+ walk_page_cache();
+ else
+ walk_addr_ranges();
+
+ if (opt_list == 1)
+ flush_page_range();
+
+ if (opt_no_summary)
+ return 0;
+
+ if (opt_list)
+ printf("\n\n");
+
+ show_summary();
+
+ return 0;
+}
diff --git a/kernel/tools/vm/page_owner_sort.c b/kernel/tools/vm/page_owner_sort.c
new file mode 100644
index 000000000..77147b42d
--- /dev/null
+++ b/kernel/tools/vm/page_owner_sort.c
@@ -0,0 +1,144 @@
+/*
+ * User-space helper to sort the output of /sys/kernel/debug/page_owner
+ *
+ * Example use:
+ * cat /sys/kernel/debug/page_owner > page_owner_full.txt
+ * grep -v ^PFN page_owner_full.txt > page_owner.txt
+ * ./sort page_owner.txt sorted_page_owner.txt
+*/
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <string.h>
+
+struct block_list {
+ char *txt;
+ int len;
+ int num;
+};
+
+
+static struct block_list *list;
+static int list_size;
+static int max_size;
+
+struct block_list *block_head;
+
+int read_block(char *buf, int buf_size, FILE *fin)
+{
+ char *curr = buf, *const buf_end = buf + buf_size;
+
+ while (buf_end - curr > 1 && fgets(curr, buf_end - curr, fin)) {
+ if (*curr == '\n') /* empty line */
+ return curr - buf;
+ curr += strlen(curr);
+ }
+
+ return -1; /* EOF or no space left in buf. */
+}
+
+static int compare_txt(const void *p1, const void *p2)
+{
+ const struct block_list *l1 = p1, *l2 = p2;
+
+ return strcmp(l1->txt, l2->txt);
+}
+
+static int compare_num(const void *p1, const void *p2)
+{
+ const struct block_list *l1 = p1, *l2 = p2;
+
+ return l2->num - l1->num;
+}
+
+static void add_list(char *buf, int len)
+{
+ if (list_size != 0 &&
+ len == list[list_size-1].len &&
+ memcmp(buf, list[list_size-1].txt, len) == 0) {
+ list[list_size-1].num++;
+ return;
+ }
+ if (list_size == max_size) {
+ printf("max_size too small??\n");
+ exit(1);
+ }
+ list[list_size].txt = malloc(len+1);
+ list[list_size].len = len;
+ list[list_size].num = 1;
+ memcpy(list[list_size].txt, buf, len);
+ list[list_size].txt[len] = 0;
+ list_size++;
+ if (list_size % 1000 == 0) {
+ printf("loaded %d\r", list_size);
+ fflush(stdout);
+ }
+}
+
+#define BUF_SIZE 1024
+
+int main(int argc, char **argv)
+{
+ FILE *fin, *fout;
+ char buf[BUF_SIZE];
+ int ret, i, count;
+ struct block_list *list2;
+ struct stat st;
+
+ if (argc < 3) {
+ printf("Usage: ./program <input> <output>\n");
+ perror("open: ");
+ exit(1);
+ }
+
+ fin = fopen(argv[1], "r");
+ fout = fopen(argv[2], "w");
+ if (!fin || !fout) {
+ printf("Usage: ./program <input> <output>\n");
+ perror("open: ");
+ exit(1);
+ }
+
+ fstat(fileno(fin), &st);
+ max_size = st.st_size / 100; /* hack ... */
+
+ list = malloc(max_size * sizeof(*list));
+
+ for ( ; ; ) {
+ ret = read_block(buf, BUF_SIZE, fin);
+ if (ret < 0)
+ break;
+
+ add_list(buf, ret);
+ }
+
+ printf("loaded %d\n", list_size);
+
+ printf("sorting ....\n");
+
+ qsort(list, list_size, sizeof(list[0]), compare_txt);
+
+ list2 = malloc(sizeof(*list) * list_size);
+
+ printf("culling\n");
+
+ for (i = count = 0; i < list_size; i++) {
+ if (count == 0 ||
+ strcmp(list2[count-1].txt, list[i].txt) != 0) {
+ list2[count++] = list[i];
+ } else {
+ list2[count-1].num += list[i].num;
+ }
+ }
+
+ qsort(list2, count, sizeof(list[0]), compare_num);
+
+ for (i = 0; i < count; i++)
+ fprintf(fout, "%d times:\n%s\n", list2[i].num, list2[i].txt);
+
+ return 0;
+}
diff --git a/kernel/tools/vm/slabinfo.c b/kernel/tools/vm/slabinfo.c
new file mode 100644
index 000000000..808d5a9d5
--- /dev/null
+++ b/kernel/tools/vm/slabinfo.c
@@ -0,0 +1,1393 @@
+/*
+ * Slabinfo: Tool to get reports about slabs
+ *
+ * (C) 2007 sgi, Christoph Lameter
+ * (C) 2011 Linux Foundation, Christoph Lameter
+ *
+ * Compile with:
+ *
+ * gcc -o slabinfo slabinfo.c
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <strings.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdarg.h>
+#include <getopt.h>
+#include <regex.h>
+#include <errno.h>
+
+#define MAX_SLABS 500
+#define MAX_ALIASES 500
+#define MAX_NODES 1024
+
+struct slabinfo {
+ char *name;
+ int alias;
+ int refs;
+ int aliases, align, cache_dma, cpu_slabs, destroy_by_rcu;
+ int hwcache_align, object_size, objs_per_slab;
+ int sanity_checks, slab_size, store_user, trace;
+ int order, poison, reclaim_account, red_zone;
+ unsigned long partial, objects, slabs, objects_partial, objects_total;
+ unsigned long alloc_fastpath, alloc_slowpath;
+ unsigned long free_fastpath, free_slowpath;
+ unsigned long free_frozen, free_add_partial, free_remove_partial;
+ unsigned long alloc_from_partial, alloc_slab, free_slab, alloc_refill;
+ unsigned long cpuslab_flush, deactivate_full, deactivate_empty;
+ unsigned long deactivate_to_head, deactivate_to_tail;
+ unsigned long deactivate_remote_frees, order_fallback;
+ unsigned long cmpxchg_double_cpu_fail, cmpxchg_double_fail;
+ unsigned long alloc_node_mismatch, deactivate_bypass;
+ unsigned long cpu_partial_alloc, cpu_partial_free;
+ int numa[MAX_NODES];
+ int numa_partial[MAX_NODES];
+} slabinfo[MAX_SLABS];
+
+struct aliasinfo {
+ char *name;
+ char *ref;
+ struct slabinfo *slab;
+} aliasinfo[MAX_ALIASES];
+
+int slabs = 0;
+int actual_slabs = 0;
+int aliases = 0;
+int alias_targets = 0;
+int highest_node = 0;
+
+char buffer[4096];
+
+int show_empty = 0;
+int show_report = 0;
+int show_alias = 0;
+int show_slab = 0;
+int skip_zero = 1;
+int show_numa = 0;
+int show_track = 0;
+int show_first_alias = 0;
+int validate = 0;
+int shrink = 0;
+int show_inverted = 0;
+int show_single_ref = 0;
+int show_totals = 0;
+int sort_size = 0;
+int sort_active = 0;
+int set_debug = 0;
+int show_ops = 0;
+int show_activity = 0;
+
+/* Debug options */
+int sanity = 0;
+int redzone = 0;
+int poison = 0;
+int tracking = 0;
+int tracing = 0;
+
+int page_size;
+
+regex_t pattern;
+
+static void fatal(const char *x, ...)
+{
+ va_list ap;
+
+ va_start(ap, x);
+ vfprintf(stderr, x, ap);
+ va_end(ap);
+ exit(EXIT_FAILURE);
+}
+
+static void usage(void)
+{
+ printf("slabinfo 4/15/2011. (c) 2007 sgi/(c) 2011 Linux Foundation.\n\n"
+ "slabinfo [-ahnpvtsz] [-d debugopts] [slab-regexp]\n"
+ "-a|--aliases Show aliases\n"
+ "-A|--activity Most active slabs first\n"
+ "-d<options>|--debug=<options> Set/Clear Debug options\n"
+ "-D|--display-active Switch line format to activity\n"
+ "-e|--empty Show empty slabs\n"
+ "-f|--first-alias Show first alias\n"
+ "-h|--help Show usage information\n"
+ "-i|--inverted Inverted list\n"
+ "-l|--slabs Show slabs\n"
+ "-n|--numa Show NUMA information\n"
+ "-o|--ops Show kmem_cache_ops\n"
+ "-s|--shrink Shrink slabs\n"
+ "-r|--report Detailed report on single slabs\n"
+ "-S|--Size Sort by size\n"
+ "-t|--tracking Show alloc/free information\n"
+ "-T|--Totals Show summary information\n"
+ "-v|--validate Validate slabs\n"
+ "-z|--zero Include empty slabs\n"
+ "-1|--1ref Single reference\n"
+ "\nValid debug options (FZPUT may be combined)\n"
+ "a / A Switch on all debug options (=FZUP)\n"
+ "- Switch off all debug options\n"
+ "f / F Sanity Checks (SLAB_DEBUG_FREE)\n"
+ "z / Z Redzoning\n"
+ "p / P Poisoning\n"
+ "u / U Tracking\n"
+ "t / T Tracing\n"
+ );
+}
+
+static unsigned long read_obj(const char *name)
+{
+ FILE *f = fopen(name, "r");
+
+ if (!f)
+ buffer[0] = 0;
+ else {
+ if (!fgets(buffer, sizeof(buffer), f))
+ buffer[0] = 0;
+ fclose(f);
+ if (buffer[strlen(buffer)] == '\n')
+ buffer[strlen(buffer)] = 0;
+ }
+ return strlen(buffer);
+}
+
+
+/*
+ * Get the contents of an attribute
+ */
+static unsigned long get_obj(const char *name)
+{
+ if (!read_obj(name))
+ return 0;
+
+ return atol(buffer);
+}
+
+static unsigned long get_obj_and_str(const char *name, char **x)
+{
+ unsigned long result = 0;
+ char *p;
+
+ *x = NULL;
+
+ if (!read_obj(name)) {
+ x = NULL;
+ return 0;
+ }
+ result = strtoul(buffer, &p, 10);
+ while (*p == ' ')
+ p++;
+ if (*p)
+ *x = strdup(p);
+ return result;
+}
+
+static void set_obj(struct slabinfo *s, const char *name, int n)
+{
+ char x[100];
+ FILE *f;
+
+ snprintf(x, 100, "%s/%s", s->name, name);
+ f = fopen(x, "w");
+ if (!f)
+ fatal("Cannot write to %s\n", x);
+
+ fprintf(f, "%d\n", n);
+ fclose(f);
+}
+
+static unsigned long read_slab_obj(struct slabinfo *s, const char *name)
+{
+ char x[100];
+ FILE *f;
+ size_t l;
+
+ snprintf(x, 100, "%s/%s", s->name, name);
+ f = fopen(x, "r");
+ if (!f) {
+ buffer[0] = 0;
+ l = 0;
+ } else {
+ l = fread(buffer, 1, sizeof(buffer), f);
+ buffer[l] = 0;
+ fclose(f);
+ }
+ return l;
+}
+
+
+/*
+ * Put a size string together
+ */
+static int store_size(char *buffer, unsigned long value)
+{
+ unsigned long divisor = 1;
+ char trailer = 0;
+ int n;
+
+ if (value > 1000000000UL) {
+ divisor = 100000000UL;
+ trailer = 'G';
+ } else if (value > 1000000UL) {
+ divisor = 100000UL;
+ trailer = 'M';
+ } else if (value > 1000UL) {
+ divisor = 100;
+ trailer = 'K';
+ }
+
+ value /= divisor;
+ n = sprintf(buffer, "%ld",value);
+ if (trailer) {
+ buffer[n] = trailer;
+ n++;
+ buffer[n] = 0;
+ }
+ if (divisor != 1) {
+ memmove(buffer + n - 2, buffer + n - 3, 4);
+ buffer[n-2] = '.';
+ n++;
+ }
+ return n;
+}
+
+static void decode_numa_list(int *numa, char *t)
+{
+ int node;
+ int nr;
+
+ memset(numa, 0, MAX_NODES * sizeof(int));
+
+ if (!t)
+ return;
+
+ while (*t == 'N') {
+ t++;
+ node = strtoul(t, &t, 10);
+ if (*t == '=') {
+ t++;
+ nr = strtoul(t, &t, 10);
+ numa[node] = nr;
+ if (node > highest_node)
+ highest_node = node;
+ }
+ while (*t == ' ')
+ t++;
+ }
+}
+
+static void slab_validate(struct slabinfo *s)
+{
+ if (strcmp(s->name, "*") == 0)
+ return;
+
+ set_obj(s, "validate", 1);
+}
+
+static void slab_shrink(struct slabinfo *s)
+{
+ if (strcmp(s->name, "*") == 0)
+ return;
+
+ set_obj(s, "shrink", 1);
+}
+
+int line = 0;
+
+static void first_line(void)
+{
+ if (show_activity)
+ printf("Name Objects Alloc Free %%Fast Fallb O CmpX UL\n");
+ else
+ printf("Name Objects Objsize Space "
+ "Slabs/Part/Cpu O/S O %%Fr %%Ef Flg\n");
+}
+
+/*
+ * Find the shortest alias of a slab
+ */
+static struct aliasinfo *find_one_alias(struct slabinfo *find)
+{
+ struct aliasinfo *a;
+ struct aliasinfo *best = NULL;
+
+ for(a = aliasinfo;a < aliasinfo + aliases; a++) {
+ if (a->slab == find &&
+ (!best || strlen(best->name) < strlen(a->name))) {
+ best = a;
+ if (strncmp(a->name,"kmall", 5) == 0)
+ return best;
+ }
+ }
+ return best;
+}
+
+static unsigned long slab_size(struct slabinfo *s)
+{
+ return s->slabs * (page_size << s->order);
+}
+
+static unsigned long slab_activity(struct slabinfo *s)
+{
+ return s->alloc_fastpath + s->free_fastpath +
+ s->alloc_slowpath + s->free_slowpath;
+}
+
+static void slab_numa(struct slabinfo *s, int mode)
+{
+ int node;
+
+ if (strcmp(s->name, "*") == 0)
+ return;
+
+ if (!highest_node) {
+ printf("\n%s: No NUMA information available.\n", s->name);
+ return;
+ }
+
+ if (skip_zero && !s->slabs)
+ return;
+
+ if (!line) {
+ printf("\n%-21s:", mode ? "NUMA nodes" : "Slab");
+ for(node = 0; node <= highest_node; node++)
+ printf(" %4d", node);
+ printf("\n----------------------");
+ for(node = 0; node <= highest_node; node++)
+ printf("-----");
+ printf("\n");
+ }
+ printf("%-21s ", mode ? "All slabs" : s->name);
+ for(node = 0; node <= highest_node; node++) {
+ char b[20];
+
+ store_size(b, s->numa[node]);
+ printf(" %4s", b);
+ }
+ printf("\n");
+ if (mode) {
+ printf("%-21s ", "Partial slabs");
+ for(node = 0; node <= highest_node; node++) {
+ char b[20];
+
+ store_size(b, s->numa_partial[node]);
+ printf(" %4s", b);
+ }
+ printf("\n");
+ }
+ line++;
+}
+
+static void show_tracking(struct slabinfo *s)
+{
+ printf("\n%s: Kernel object allocation\n", s->name);
+ printf("-----------------------------------------------------------------------\n");
+ if (read_slab_obj(s, "alloc_calls"))
+ printf("%s", buffer);
+ else
+ printf("No Data\n");
+
+ printf("\n%s: Kernel object freeing\n", s->name);
+ printf("------------------------------------------------------------------------\n");
+ if (read_slab_obj(s, "free_calls"))
+ printf("%s", buffer);
+ else
+ printf("No Data\n");
+
+}
+
+static void ops(struct slabinfo *s)
+{
+ if (strcmp(s->name, "*") == 0)
+ return;
+
+ if (read_slab_obj(s, "ops")) {
+ printf("\n%s: kmem_cache operations\n", s->name);
+ printf("--------------------------------------------\n");
+ printf("%s", buffer);
+ } else
+ printf("\n%s has no kmem_cache operations\n", s->name);
+}
+
+static const char *onoff(int x)
+{
+ if (x)
+ return "On ";
+ return "Off";
+}
+
+static void slab_stats(struct slabinfo *s)
+{
+ unsigned long total_alloc;
+ unsigned long total_free;
+ unsigned long total;
+
+ if (!s->alloc_slab)
+ return;
+
+ total_alloc = s->alloc_fastpath + s->alloc_slowpath;
+ total_free = s->free_fastpath + s->free_slowpath;
+
+ if (!total_alloc)
+ return;
+
+ printf("\n");
+ printf("Slab Perf Counter Alloc Free %%Al %%Fr\n");
+ printf("--------------------------------------------------\n");
+ printf("Fastpath %8lu %8lu %3lu %3lu\n",
+ s->alloc_fastpath, s->free_fastpath,
+ s->alloc_fastpath * 100 / total_alloc,
+ total_free ? s->free_fastpath * 100 / total_free : 0);
+ printf("Slowpath %8lu %8lu %3lu %3lu\n",
+ total_alloc - s->alloc_fastpath, s->free_slowpath,
+ (total_alloc - s->alloc_fastpath) * 100 / total_alloc,
+ total_free ? s->free_slowpath * 100 / total_free : 0);
+ printf("Page Alloc %8lu %8lu %3lu %3lu\n",
+ s->alloc_slab, s->free_slab,
+ s->alloc_slab * 100 / total_alloc,
+ total_free ? s->free_slab * 100 / total_free : 0);
+ printf("Add partial %8lu %8lu %3lu %3lu\n",
+ s->deactivate_to_head + s->deactivate_to_tail,
+ s->free_add_partial,
+ (s->deactivate_to_head + s->deactivate_to_tail) * 100 / total_alloc,
+ total_free ? s->free_add_partial * 100 / total_free : 0);
+ printf("Remove partial %8lu %8lu %3lu %3lu\n",
+ s->alloc_from_partial, s->free_remove_partial,
+ s->alloc_from_partial * 100 / total_alloc,
+ total_free ? s->free_remove_partial * 100 / total_free : 0);
+
+ printf("Cpu partial list %8lu %8lu %3lu %3lu\n",
+ s->cpu_partial_alloc, s->cpu_partial_free,
+ s->cpu_partial_alloc * 100 / total_alloc,
+ total_free ? s->cpu_partial_free * 100 / total_free : 0);
+
+ printf("RemoteObj/SlabFrozen %8lu %8lu %3lu %3lu\n",
+ s->deactivate_remote_frees, s->free_frozen,
+ s->deactivate_remote_frees * 100 / total_alloc,
+ total_free ? s->free_frozen * 100 / total_free : 0);
+
+ printf("Total %8lu %8lu\n\n", total_alloc, total_free);
+
+ if (s->cpuslab_flush)
+ printf("Flushes %8lu\n", s->cpuslab_flush);
+
+ total = s->deactivate_full + s->deactivate_empty +
+ s->deactivate_to_head + s->deactivate_to_tail + s->deactivate_bypass;
+
+ if (total) {
+ printf("\nSlab Deactivation Ocurrences %%\n");
+ printf("-------------------------------------------------\n");
+ printf("Slab full %7lu %3lu%%\n",
+ s->deactivate_full, (s->deactivate_full * 100) / total);
+ printf("Slab empty %7lu %3lu%%\n",
+ s->deactivate_empty, (s->deactivate_empty * 100) / total);
+ printf("Moved to head of partial list %7lu %3lu%%\n",
+ s->deactivate_to_head, (s->deactivate_to_head * 100) / total);
+ printf("Moved to tail of partial list %7lu %3lu%%\n",
+ s->deactivate_to_tail, (s->deactivate_to_tail * 100) / total);
+ printf("Deactivation bypass %7lu %3lu%%\n",
+ s->deactivate_bypass, (s->deactivate_bypass * 100) / total);
+ printf("Refilled from foreign frees %7lu %3lu%%\n",
+ s->alloc_refill, (s->alloc_refill * 100) / total);
+ printf("Node mismatch %7lu %3lu%%\n",
+ s->alloc_node_mismatch, (s->alloc_node_mismatch * 100) / total);
+ }
+
+ if (s->cmpxchg_double_fail || s->cmpxchg_double_cpu_fail)
+ printf("\nCmpxchg_double Looping\n------------------------\n");
+ printf("Locked Cmpxchg Double redos %lu\nUnlocked Cmpxchg Double redos %lu\n",
+ s->cmpxchg_double_fail, s->cmpxchg_double_cpu_fail);
+}
+
+static void report(struct slabinfo *s)
+{
+ if (strcmp(s->name, "*") == 0)
+ return;
+
+ printf("\nSlabcache: %-20s Aliases: %2d Order : %2d Objects: %lu\n",
+ s->name, s->aliases, s->order, s->objects);
+ if (s->hwcache_align)
+ printf("** Hardware cacheline aligned\n");
+ if (s->cache_dma)
+ printf("** Memory is allocated in a special DMA zone\n");
+ if (s->destroy_by_rcu)
+ printf("** Slabs are destroyed via RCU\n");
+ if (s->reclaim_account)
+ printf("** Reclaim accounting active\n");
+
+ printf("\nSizes (bytes) Slabs Debug Memory\n");
+ printf("------------------------------------------------------------------------\n");
+ printf("Object : %7d Total : %7ld Sanity Checks : %s Total: %7ld\n",
+ s->object_size, s->slabs, onoff(s->sanity_checks),
+ s->slabs * (page_size << s->order));
+ printf("SlabObj: %7d Full : %7ld Redzoning : %s Used : %7ld\n",
+ s->slab_size, s->slabs - s->partial - s->cpu_slabs,
+ onoff(s->red_zone), s->objects * s->object_size);
+ printf("SlabSiz: %7d Partial: %7ld Poisoning : %s Loss : %7ld\n",
+ page_size << s->order, s->partial, onoff(s->poison),
+ s->slabs * (page_size << s->order) - s->objects * s->object_size);
+ printf("Loss : %7d CpuSlab: %7d Tracking : %s Lalig: %7ld\n",
+ s->slab_size - s->object_size, s->cpu_slabs, onoff(s->store_user),
+ (s->slab_size - s->object_size) * s->objects);
+ printf("Align : %7d Objects: %7d Tracing : %s Lpadd: %7ld\n",
+ s->align, s->objs_per_slab, onoff(s->trace),
+ ((page_size << s->order) - s->objs_per_slab * s->slab_size) *
+ s->slabs);
+
+ ops(s);
+ show_tracking(s);
+ slab_numa(s, 1);
+ slab_stats(s);
+}
+
+static void slabcache(struct slabinfo *s)
+{
+ char size_str[20];
+ char dist_str[40];
+ char flags[20];
+ char *p = flags;
+
+ if (strcmp(s->name, "*") == 0)
+ return;
+
+ if (actual_slabs == 1) {
+ report(s);
+ return;
+ }
+
+ if (skip_zero && !show_empty && !s->slabs)
+ return;
+
+ if (show_empty && s->slabs)
+ return;
+
+ store_size(size_str, slab_size(s));
+ snprintf(dist_str, 40, "%lu/%lu/%d", s->slabs - s->cpu_slabs,
+ s->partial, s->cpu_slabs);
+
+ if (!line++)
+ first_line();
+
+ if (s->aliases)
+ *p++ = '*';
+ if (s->cache_dma)
+ *p++ = 'd';
+ if (s->hwcache_align)
+ *p++ = 'A';
+ if (s->poison)
+ *p++ = 'P';
+ if (s->reclaim_account)
+ *p++ = 'a';
+ if (s->red_zone)
+ *p++ = 'Z';
+ if (s->sanity_checks)
+ *p++ = 'F';
+ if (s->store_user)
+ *p++ = 'U';
+ if (s->trace)
+ *p++ = 'T';
+
+ *p = 0;
+ if (show_activity) {
+ unsigned long total_alloc;
+ unsigned long total_free;
+
+ total_alloc = s->alloc_fastpath + s->alloc_slowpath;
+ total_free = s->free_fastpath + s->free_slowpath;
+
+ printf("%-21s %8ld %10ld %10ld %3ld %3ld %5ld %1d %4ld %4ld\n",
+ s->name, s->objects,
+ total_alloc, total_free,
+ total_alloc ? (s->alloc_fastpath * 100 / total_alloc) : 0,
+ total_free ? (s->free_fastpath * 100 / total_free) : 0,
+ s->order_fallback, s->order, s->cmpxchg_double_fail,
+ s->cmpxchg_double_cpu_fail);
+ }
+ else
+ printf("%-21s %8ld %7d %8s %14s %4d %1d %3ld %3ld %s\n",
+ s->name, s->objects, s->object_size, size_str, dist_str,
+ s->objs_per_slab, s->order,
+ s->slabs ? (s->partial * 100) / s->slabs : 100,
+ s->slabs ? (s->objects * s->object_size * 100) /
+ (s->slabs * (page_size << s->order)) : 100,
+ flags);
+}
+
+/*
+ * Analyze debug options. Return false if something is amiss.
+ */
+static int debug_opt_scan(char *opt)
+{
+ if (!opt || !opt[0] || strcmp(opt, "-") == 0)
+ return 1;
+
+ if (strcasecmp(opt, "a") == 0) {
+ sanity = 1;
+ poison = 1;
+ redzone = 1;
+ tracking = 1;
+ return 1;
+ }
+
+ for ( ; *opt; opt++)
+ switch (*opt) {
+ case 'F' : case 'f':
+ if (sanity)
+ return 0;
+ sanity = 1;
+ break;
+ case 'P' : case 'p':
+ if (poison)
+ return 0;
+ poison = 1;
+ break;
+
+ case 'Z' : case 'z':
+ if (redzone)
+ return 0;
+ redzone = 1;
+ break;
+
+ case 'U' : case 'u':
+ if (tracking)
+ return 0;
+ tracking = 1;
+ break;
+
+ case 'T' : case 't':
+ if (tracing)
+ return 0;
+ tracing = 1;
+ break;
+ default:
+ return 0;
+ }
+ return 1;
+}
+
+static int slab_empty(struct slabinfo *s)
+{
+ if (s->objects > 0)
+ return 0;
+
+ /*
+ * We may still have slabs even if there are no objects. Shrinking will
+ * remove them.
+ */
+ if (s->slabs != 0)
+ set_obj(s, "shrink", 1);
+
+ return 1;
+}
+
+static void slab_debug(struct slabinfo *s)
+{
+ if (strcmp(s->name, "*") == 0)
+ return;
+
+ if (sanity && !s->sanity_checks) {
+ set_obj(s, "sanity", 1);
+ }
+ if (!sanity && s->sanity_checks) {
+ if (slab_empty(s))
+ set_obj(s, "sanity", 0);
+ else
+ fprintf(stderr, "%s not empty cannot disable sanity checks\n", s->name);
+ }
+ if (redzone && !s->red_zone) {
+ if (slab_empty(s))
+ set_obj(s, "red_zone", 1);
+ else
+ fprintf(stderr, "%s not empty cannot enable redzoning\n", s->name);
+ }
+ if (!redzone && s->red_zone) {
+ if (slab_empty(s))
+ set_obj(s, "red_zone", 0);
+ else
+ fprintf(stderr, "%s not empty cannot disable redzoning\n", s->name);
+ }
+ if (poison && !s->poison) {
+ if (slab_empty(s))
+ set_obj(s, "poison", 1);
+ else
+ fprintf(stderr, "%s not empty cannot enable poisoning\n", s->name);
+ }
+ if (!poison && s->poison) {
+ if (slab_empty(s))
+ set_obj(s, "poison", 0);
+ else
+ fprintf(stderr, "%s not empty cannot disable poisoning\n", s->name);
+ }
+ if (tracking && !s->store_user) {
+ if (slab_empty(s))
+ set_obj(s, "store_user", 1);
+ else
+ fprintf(stderr, "%s not empty cannot enable tracking\n", s->name);
+ }
+ if (!tracking && s->store_user) {
+ if (slab_empty(s))
+ set_obj(s, "store_user", 0);
+ else
+ fprintf(stderr, "%s not empty cannot disable tracking\n", s->name);
+ }
+ if (tracing && !s->trace) {
+ if (slabs == 1)
+ set_obj(s, "trace", 1);
+ else
+ fprintf(stderr, "%s can only enable trace for one slab at a time\n", s->name);
+ }
+ if (!tracing && s->trace)
+ set_obj(s, "trace", 1);
+}
+
+static void totals(void)
+{
+ struct slabinfo *s;
+
+ int used_slabs = 0;
+ char b1[20], b2[20], b3[20], b4[20];
+ unsigned long long max = 1ULL << 63;
+
+ /* Object size */
+ unsigned long long min_objsize = max, max_objsize = 0, avg_objsize;
+
+ /* Number of partial slabs in a slabcache */
+ unsigned long long min_partial = max, max_partial = 0,
+ avg_partial, total_partial = 0;
+
+ /* Number of slabs in a slab cache */
+ unsigned long long min_slabs = max, max_slabs = 0,
+ avg_slabs, total_slabs = 0;
+
+ /* Size of the whole slab */
+ unsigned long long min_size = max, max_size = 0,
+ avg_size, total_size = 0;
+
+ /* Bytes used for object storage in a slab */
+ unsigned long long min_used = max, max_used = 0,
+ avg_used, total_used = 0;
+
+ /* Waste: Bytes used for alignment and padding */
+ unsigned long long min_waste = max, max_waste = 0,
+ avg_waste, total_waste = 0;
+ /* Number of objects in a slab */
+ unsigned long long min_objects = max, max_objects = 0,
+ avg_objects, total_objects = 0;
+ /* Waste per object */
+ unsigned long long min_objwaste = max,
+ max_objwaste = 0, avg_objwaste,
+ total_objwaste = 0;
+
+ /* Memory per object */
+ unsigned long long min_memobj = max,
+ max_memobj = 0, avg_memobj,
+ total_objsize = 0;
+
+ /* Percentage of partial slabs per slab */
+ unsigned long min_ppart = 100, max_ppart = 0,
+ avg_ppart, total_ppart = 0;
+
+ /* Number of objects in partial slabs */
+ unsigned long min_partobj = max, max_partobj = 0,
+ avg_partobj, total_partobj = 0;
+
+ /* Percentage of partial objects of all objects in a slab */
+ unsigned long min_ppartobj = 100, max_ppartobj = 0,
+ avg_ppartobj, total_ppartobj = 0;
+
+
+ for (s = slabinfo; s < slabinfo + slabs; s++) {
+ unsigned long long size;
+ unsigned long used;
+ unsigned long long wasted;
+ unsigned long long objwaste;
+ unsigned long percentage_partial_slabs;
+ unsigned long percentage_partial_objs;
+
+ if (!s->slabs || !s->objects)
+ continue;
+
+ used_slabs++;
+
+ size = slab_size(s);
+ used = s->objects * s->object_size;
+ wasted = size - used;
+ objwaste = s->slab_size - s->object_size;
+
+ percentage_partial_slabs = s->partial * 100 / s->slabs;
+ if (percentage_partial_slabs > 100)
+ percentage_partial_slabs = 100;
+
+ percentage_partial_objs = s->objects_partial * 100
+ / s->objects;
+
+ if (percentage_partial_objs > 100)
+ percentage_partial_objs = 100;
+
+ if (s->object_size < min_objsize)
+ min_objsize = s->object_size;
+ if (s->partial < min_partial)
+ min_partial = s->partial;
+ if (s->slabs < min_slabs)
+ min_slabs = s->slabs;
+ if (size < min_size)
+ min_size = size;
+ if (wasted < min_waste)
+ min_waste = wasted;
+ if (objwaste < min_objwaste)
+ min_objwaste = objwaste;
+ if (s->objects < min_objects)
+ min_objects = s->objects;
+ if (used < min_used)
+ min_used = used;
+ if (s->objects_partial < min_partobj)
+ min_partobj = s->objects_partial;
+ if (percentage_partial_slabs < min_ppart)
+ min_ppart = percentage_partial_slabs;
+ if (percentage_partial_objs < min_ppartobj)
+ min_ppartobj = percentage_partial_objs;
+ if (s->slab_size < min_memobj)
+ min_memobj = s->slab_size;
+
+ if (s->object_size > max_objsize)
+ max_objsize = s->object_size;
+ if (s->partial > max_partial)
+ max_partial = s->partial;
+ if (s->slabs > max_slabs)
+ max_slabs = s->slabs;
+ if (size > max_size)
+ max_size = size;
+ if (wasted > max_waste)
+ max_waste = wasted;
+ if (objwaste > max_objwaste)
+ max_objwaste = objwaste;
+ if (s->objects > max_objects)
+ max_objects = s->objects;
+ if (used > max_used)
+ max_used = used;
+ if (s->objects_partial > max_partobj)
+ max_partobj = s->objects_partial;
+ if (percentage_partial_slabs > max_ppart)
+ max_ppart = percentage_partial_slabs;
+ if (percentage_partial_objs > max_ppartobj)
+ max_ppartobj = percentage_partial_objs;
+ if (s->slab_size > max_memobj)
+ max_memobj = s->slab_size;
+
+ total_partial += s->partial;
+ total_slabs += s->slabs;
+ total_size += size;
+ total_waste += wasted;
+
+ total_objects += s->objects;
+ total_used += used;
+ total_partobj += s->objects_partial;
+ total_ppart += percentage_partial_slabs;
+ total_ppartobj += percentage_partial_objs;
+
+ total_objwaste += s->objects * objwaste;
+ total_objsize += s->objects * s->slab_size;
+ }
+
+ if (!total_objects) {
+ printf("No objects\n");
+ return;
+ }
+ if (!used_slabs) {
+ printf("No slabs\n");
+ return;
+ }
+
+ /* Per slab averages */
+ avg_partial = total_partial / used_slabs;
+ avg_slabs = total_slabs / used_slabs;
+ avg_size = total_size / used_slabs;
+ avg_waste = total_waste / used_slabs;
+
+ avg_objects = total_objects / used_slabs;
+ avg_used = total_used / used_slabs;
+ avg_partobj = total_partobj / used_slabs;
+ avg_ppart = total_ppart / used_slabs;
+ avg_ppartobj = total_ppartobj / used_slabs;
+
+ /* Per object object sizes */
+ avg_objsize = total_used / total_objects;
+ avg_objwaste = total_objwaste / total_objects;
+ avg_partobj = total_partobj * 100 / total_objects;
+ avg_memobj = total_objsize / total_objects;
+
+ printf("Slabcache Totals\n");
+ printf("----------------\n");
+ printf("Slabcaches : %3d Aliases : %3d->%-3d Active: %3d\n",
+ slabs, aliases, alias_targets, used_slabs);
+
+ store_size(b1, total_size);store_size(b2, total_waste);
+ store_size(b3, total_waste * 100 / total_used);
+ printf("Memory used: %6s # Loss : %6s MRatio:%6s%%\n", b1, b2, b3);
+
+ store_size(b1, total_objects);store_size(b2, total_partobj);
+ store_size(b3, total_partobj * 100 / total_objects);
+ printf("# Objects : %6s # PartObj: %6s ORatio:%6s%%\n", b1, b2, b3);
+
+ printf("\n");
+ printf("Per Cache Average Min Max Total\n");
+ printf("---------------------------------------------------------\n");
+
+ store_size(b1, avg_objects);store_size(b2, min_objects);
+ store_size(b3, max_objects);store_size(b4, total_objects);
+ printf("#Objects %10s %10s %10s %10s\n",
+ b1, b2, b3, b4);
+
+ store_size(b1, avg_slabs);store_size(b2, min_slabs);
+ store_size(b3, max_slabs);store_size(b4, total_slabs);
+ printf("#Slabs %10s %10s %10s %10s\n",
+ b1, b2, b3, b4);
+
+ store_size(b1, avg_partial);store_size(b2, min_partial);
+ store_size(b3, max_partial);store_size(b4, total_partial);
+ printf("#PartSlab %10s %10s %10s %10s\n",
+ b1, b2, b3, b4);
+ store_size(b1, avg_ppart);store_size(b2, min_ppart);
+ store_size(b3, max_ppart);
+ store_size(b4, total_partial * 100 / total_slabs);
+ printf("%%PartSlab%10s%% %10s%% %10s%% %10s%%\n",
+ b1, b2, b3, b4);
+
+ store_size(b1, avg_partobj);store_size(b2, min_partobj);
+ store_size(b3, max_partobj);
+ store_size(b4, total_partobj);
+ printf("PartObjs %10s %10s %10s %10s\n",
+ b1, b2, b3, b4);
+
+ store_size(b1, avg_ppartobj);store_size(b2, min_ppartobj);
+ store_size(b3, max_ppartobj);
+ store_size(b4, total_partobj * 100 / total_objects);
+ printf("%% PartObj%10s%% %10s%% %10s%% %10s%%\n",
+ b1, b2, b3, b4);
+
+ store_size(b1, avg_size);store_size(b2, min_size);
+ store_size(b3, max_size);store_size(b4, total_size);
+ printf("Memory %10s %10s %10s %10s\n",
+ b1, b2, b3, b4);
+
+ store_size(b1, avg_used);store_size(b2, min_used);
+ store_size(b3, max_used);store_size(b4, total_used);
+ printf("Used %10s %10s %10s %10s\n",
+ b1, b2, b3, b4);
+
+ store_size(b1, avg_waste);store_size(b2, min_waste);
+ store_size(b3, max_waste);store_size(b4, total_waste);
+ printf("Loss %10s %10s %10s %10s\n",
+ b1, b2, b3, b4);
+
+ printf("\n");
+ printf("Per Object Average Min Max\n");
+ printf("---------------------------------------------\n");
+
+ store_size(b1, avg_memobj);store_size(b2, min_memobj);
+ store_size(b3, max_memobj);
+ printf("Memory %10s %10s %10s\n",
+ b1, b2, b3);
+ store_size(b1, avg_objsize);store_size(b2, min_objsize);
+ store_size(b3, max_objsize);
+ printf("User %10s %10s %10s\n",
+ b1, b2, b3);
+
+ store_size(b1, avg_objwaste);store_size(b2, min_objwaste);
+ store_size(b3, max_objwaste);
+ printf("Loss %10s %10s %10s\n",
+ b1, b2, b3);
+}
+
+static void sort_slabs(void)
+{
+ struct slabinfo *s1,*s2;
+
+ for (s1 = slabinfo; s1 < slabinfo + slabs; s1++) {
+ for (s2 = s1 + 1; s2 < slabinfo + slabs; s2++) {
+ int result;
+
+ if (sort_size)
+ result = slab_size(s1) < slab_size(s2);
+ else if (sort_active)
+ result = slab_activity(s1) < slab_activity(s2);
+ else
+ result = strcasecmp(s1->name, s2->name);
+
+ if (show_inverted)
+ result = -result;
+
+ if (result > 0) {
+ struct slabinfo t;
+
+ memcpy(&t, s1, sizeof(struct slabinfo));
+ memcpy(s1, s2, sizeof(struct slabinfo));
+ memcpy(s2, &t, sizeof(struct slabinfo));
+ }
+ }
+ }
+}
+
+static void sort_aliases(void)
+{
+ struct aliasinfo *a1,*a2;
+
+ for (a1 = aliasinfo; a1 < aliasinfo + aliases; a1++) {
+ for (a2 = a1 + 1; a2 < aliasinfo + aliases; a2++) {
+ char *n1, *n2;
+
+ n1 = a1->name;
+ n2 = a2->name;
+ if (show_alias && !show_inverted) {
+ n1 = a1->ref;
+ n2 = a2->ref;
+ }
+ if (strcasecmp(n1, n2) > 0) {
+ struct aliasinfo t;
+
+ memcpy(&t, a1, sizeof(struct aliasinfo));
+ memcpy(a1, a2, sizeof(struct aliasinfo));
+ memcpy(a2, &t, sizeof(struct aliasinfo));
+ }
+ }
+ }
+}
+
+static void link_slabs(void)
+{
+ struct aliasinfo *a;
+ struct slabinfo *s;
+
+ for (a = aliasinfo; a < aliasinfo + aliases; a++) {
+
+ for (s = slabinfo; s < slabinfo + slabs; s++)
+ if (strcmp(a->ref, s->name) == 0) {
+ a->slab = s;
+ s->refs++;
+ break;
+ }
+ if (s == slabinfo + slabs)
+ fatal("Unresolved alias %s\n", a->ref);
+ }
+}
+
+static void alias(void)
+{
+ struct aliasinfo *a;
+ char *active = NULL;
+
+ sort_aliases();
+ link_slabs();
+
+ for(a = aliasinfo; a < aliasinfo + aliases; a++) {
+
+ if (!show_single_ref && a->slab->refs == 1)
+ continue;
+
+ if (!show_inverted) {
+ if (active) {
+ if (strcmp(a->slab->name, active) == 0) {
+ printf(" %s", a->name);
+ continue;
+ }
+ }
+ printf("\n%-12s <- %s", a->slab->name, a->name);
+ active = a->slab->name;
+ }
+ else
+ printf("%-20s -> %s\n", a->name, a->slab->name);
+ }
+ if (active)
+ printf("\n");
+}
+
+
+static void rename_slabs(void)
+{
+ struct slabinfo *s;
+ struct aliasinfo *a;
+
+ for (s = slabinfo; s < slabinfo + slabs; s++) {
+ if (*s->name != ':')
+ continue;
+
+ if (s->refs > 1 && !show_first_alias)
+ continue;
+
+ a = find_one_alias(s);
+
+ if (a)
+ s->name = a->name;
+ else {
+ s->name = "*";
+ actual_slabs--;
+ }
+ }
+}
+
+static int slab_mismatch(char *slab)
+{
+ return regexec(&pattern, slab, 0, NULL, 0);
+}
+
+static void read_slab_dir(void)
+{
+ DIR *dir;
+ struct dirent *de;
+ struct slabinfo *slab = slabinfo;
+ struct aliasinfo *alias = aliasinfo;
+ char *p;
+ char *t;
+ int count;
+
+ if (chdir("/sys/kernel/slab") && chdir("/sys/slab"))
+ fatal("SYSFS support for SLUB not active\n");
+
+ dir = opendir(".");
+ while ((de = readdir(dir))) {
+ if (de->d_name[0] == '.' ||
+ (de->d_name[0] != ':' && slab_mismatch(de->d_name)))
+ continue;
+ switch (de->d_type) {
+ case DT_LNK:
+ alias->name = strdup(de->d_name);
+ count = readlink(de->d_name, buffer, sizeof(buffer)-1);
+
+ if (count < 0)
+ fatal("Cannot read symlink %s\n", de->d_name);
+
+ buffer[count] = 0;
+ p = buffer + count;
+ while (p > buffer && p[-1] != '/')
+ p--;
+ alias->ref = strdup(p);
+ alias++;
+ break;
+ case DT_DIR:
+ if (chdir(de->d_name))
+ fatal("Unable to access slab %s\n", slab->name);
+ slab->name = strdup(de->d_name);
+ slab->alias = 0;
+ slab->refs = 0;
+ slab->aliases = get_obj("aliases");
+ slab->align = get_obj("align");
+ slab->cache_dma = get_obj("cache_dma");
+ slab->cpu_slabs = get_obj("cpu_slabs");
+ slab->destroy_by_rcu = get_obj("destroy_by_rcu");
+ slab->hwcache_align = get_obj("hwcache_align");
+ slab->object_size = get_obj("object_size");
+ slab->objects = get_obj("objects");
+ slab->objects_partial = get_obj("objects_partial");
+ slab->objects_total = get_obj("objects_total");
+ slab->objs_per_slab = get_obj("objs_per_slab");
+ slab->order = get_obj("order");
+ slab->partial = get_obj("partial");
+ slab->partial = get_obj_and_str("partial", &t);
+ decode_numa_list(slab->numa_partial, t);
+ free(t);
+ slab->poison = get_obj("poison");
+ slab->reclaim_account = get_obj("reclaim_account");
+ slab->red_zone = get_obj("red_zone");
+ slab->sanity_checks = get_obj("sanity_checks");
+ slab->slab_size = get_obj("slab_size");
+ slab->slabs = get_obj_and_str("slabs", &t);
+ decode_numa_list(slab->numa, t);
+ free(t);
+ slab->store_user = get_obj("store_user");
+ slab->trace = get_obj("trace");
+ slab->alloc_fastpath = get_obj("alloc_fastpath");
+ slab->alloc_slowpath = get_obj("alloc_slowpath");
+ slab->free_fastpath = get_obj("free_fastpath");
+ slab->free_slowpath = get_obj("free_slowpath");
+ slab->free_frozen= get_obj("free_frozen");
+ slab->free_add_partial = get_obj("free_add_partial");
+ slab->free_remove_partial = get_obj("free_remove_partial");
+ slab->alloc_from_partial = get_obj("alloc_from_partial");
+ slab->alloc_slab = get_obj("alloc_slab");
+ slab->alloc_refill = get_obj("alloc_refill");
+ slab->free_slab = get_obj("free_slab");
+ slab->cpuslab_flush = get_obj("cpuslab_flush");
+ slab->deactivate_full = get_obj("deactivate_full");
+ slab->deactivate_empty = get_obj("deactivate_empty");
+ slab->deactivate_to_head = get_obj("deactivate_to_head");
+ slab->deactivate_to_tail = get_obj("deactivate_to_tail");
+ slab->deactivate_remote_frees = get_obj("deactivate_remote_frees");
+ slab->order_fallback = get_obj("order_fallback");
+ slab->cmpxchg_double_cpu_fail = get_obj("cmpxchg_double_cpu_fail");
+ slab->cmpxchg_double_fail = get_obj("cmpxchg_double_fail");
+ slab->cpu_partial_alloc = get_obj("cpu_partial_alloc");
+ slab->cpu_partial_free = get_obj("cpu_partial_free");
+ slab->alloc_node_mismatch = get_obj("alloc_node_mismatch");
+ slab->deactivate_bypass = get_obj("deactivate_bypass");
+ chdir("..");
+ if (slab->name[0] == ':')
+ alias_targets++;
+ slab++;
+ break;
+ default :
+ fatal("Unknown file type %lx\n", de->d_type);
+ }
+ }
+ closedir(dir);
+ slabs = slab - slabinfo;
+ actual_slabs = slabs;
+ aliases = alias - aliasinfo;
+ if (slabs > MAX_SLABS)
+ fatal("Too many slabs\n");
+ if (aliases > MAX_ALIASES)
+ fatal("Too many aliases\n");
+}
+
+static void output_slabs(void)
+{
+ struct slabinfo *slab;
+
+ for (slab = slabinfo; slab < slabinfo + slabs; slab++) {
+
+ if (slab->alias)
+ continue;
+
+
+ if (show_numa)
+ slab_numa(slab, 0);
+ else if (show_track)
+ show_tracking(slab);
+ else if (validate)
+ slab_validate(slab);
+ else if (shrink)
+ slab_shrink(slab);
+ else if (set_debug)
+ slab_debug(slab);
+ else if (show_ops)
+ ops(slab);
+ else if (show_slab)
+ slabcache(slab);
+ else if (show_report)
+ report(slab);
+ }
+}
+
+struct option opts[] = {
+ { "aliases", 0, NULL, 'a' },
+ { "activity", 0, NULL, 'A' },
+ { "debug", 2, NULL, 'd' },
+ { "display-activity", 0, NULL, 'D' },
+ { "empty", 0, NULL, 'e' },
+ { "first-alias", 0, NULL, 'f' },
+ { "help", 0, NULL, 'h' },
+ { "inverted", 0, NULL, 'i'},
+ { "numa", 0, NULL, 'n' },
+ { "ops", 0, NULL, 'o' },
+ { "report", 0, NULL, 'r' },
+ { "shrink", 0, NULL, 's' },
+ { "slabs", 0, NULL, 'l' },
+ { "track", 0, NULL, 't'},
+ { "validate", 0, NULL, 'v' },
+ { "zero", 0, NULL, 'z' },
+ { "1ref", 0, NULL, '1'},
+ { NULL, 0, NULL, 0 }
+};
+
+int main(int argc, char *argv[])
+{
+ int c;
+ int err;
+ char *pattern_source;
+
+ page_size = getpagesize();
+
+ while ((c = getopt_long(argc, argv, "aAd::Defhil1noprstvzTS",
+ opts, NULL)) != -1)
+ switch (c) {
+ case '1':
+ show_single_ref = 1;
+ break;
+ case 'a':
+ show_alias = 1;
+ break;
+ case 'A':
+ sort_active = 1;
+ break;
+ case 'd':
+ set_debug = 1;
+ if (!debug_opt_scan(optarg))
+ fatal("Invalid debug option '%s'\n", optarg);
+ break;
+ case 'D':
+ show_activity = 1;
+ break;
+ case 'e':
+ show_empty = 1;
+ break;
+ case 'f':
+ show_first_alias = 1;
+ break;
+ case 'h':
+ usage();
+ return 0;
+ case 'i':
+ show_inverted = 1;
+ break;
+ case 'n':
+ show_numa = 1;
+ break;
+ case 'o':
+ show_ops = 1;
+ break;
+ case 'r':
+ show_report = 1;
+ break;
+ case 's':
+ shrink = 1;
+ break;
+ case 'l':
+ show_slab = 1;
+ break;
+ case 't':
+ show_track = 1;
+ break;
+ case 'v':
+ validate = 1;
+ break;
+ case 'z':
+ skip_zero = 0;
+ break;
+ case 'T':
+ show_totals = 1;
+ break;
+ case 'S':
+ sort_size = 1;
+ break;
+
+ default:
+ fatal("%s: Invalid option '%c'\n", argv[0], optopt);
+
+ }
+
+ if (!show_slab && !show_alias && !show_track && !show_report
+ && !validate && !shrink && !set_debug && !show_ops)
+ show_slab = 1;
+
+ if (argc > optind)
+ pattern_source = argv[optind];
+ else
+ pattern_source = ".*";
+
+ err = regcomp(&pattern, pattern_source, REG_ICASE|REG_NOSUB);
+ if (err)
+ fatal("%s: Invalid pattern '%s' code %d\n",
+ argv[0], pattern_source, err);
+ read_slab_dir();
+ if (show_alias)
+ alias();
+ else
+ if (show_totals)
+ totals();
+ else {
+ link_slabs();
+ rename_slabs();
+ sort_slabs();
+ output_slabs();
+ }
+ return 0;
+}