summaryrefslogtreecommitdiff
path: root/tools/mm
diff options
context:
space:
mode:
Diffstat (limited to 'tools/mm')
-rw-r--r--tools/mm/Makefile4
-rw-r--r--tools/mm/page-types.c26
-rw-r--r--tools/mm/page_owner_sort.c1
-rw-r--r--tools/mm/slabinfo.c14
-rw-r--r--tools/mm/thp_swap_allocator_test.c234
5 files changed, 258 insertions, 21 deletions
diff --git a/tools/mm/Makefile b/tools/mm/Makefile
index 7bb03606b9ea..f5725b5c23aa 100644
--- a/tools/mm/Makefile
+++ b/tools/mm/Makefile
@@ -3,7 +3,7 @@
#
include ../scripts/Makefile.include
-BUILD_TARGETS=page-types slabinfo page_owner_sort
+BUILD_TARGETS=page-types slabinfo page_owner_sort thp_swap_allocator_test
INSTALL_TARGETS = $(BUILD_TARGETS) thpmaps
LIB_DIR = ../lib/api
@@ -23,7 +23,7 @@ $(LIBS):
$(CC) $(CFLAGS) -o $@ $< $(LDFLAGS)
clean:
- $(RM) page-types slabinfo page_owner_sort
+ $(RM) page-types slabinfo page_owner_sort thp_swap_allocator_test
make -C $(LIB_DIR) clean
sbindir ?= /usr/sbin
diff --git a/tools/mm/page-types.c b/tools/mm/page-types.c
index 8d5595b6c59f..d7e5e8902af8 100644
--- a/tools/mm/page-types.c
+++ b/tools/mm/page-types.c
@@ -22,9 +22,10 @@
#include <time.h>
#include <setjmp.h>
#include <signal.h>
+#include <inttypes.h>
#include <sys/types.h>
-#include <sys/errno.h>
-#include <sys/fcntl.h>
+#include <errno.h>
+#include <fcntl.h>
#include <sys/mount.h>
#include <sys/statfs.h>
#include <sys/mman.h>
@@ -71,12 +72,12 @@
/* [32-] kernel hacking assistances */
#define KPF_RESERVED 32
#define KPF_MLOCKED 33
-#define KPF_MAPPEDTODISK 34
+#define KPF_OWNER_2 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_UNCACHED 39 /* unused */
#define KPF_SOFTDIRTY 40
#define KPF_ARCH_2 41
@@ -129,12 +130,11 @@ static const char * const page_flag_names[] = {
[KPF_RESERVED] = "r:reserved",
[KPF_MLOCKED] = "m:mlocked",
- [KPF_MAPPEDTODISK] = "d:mappedtodisk",
+ [KPF_OWNER_2] = "d:owner_2",
[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_ARCH_2] = "H:arch_2",
@@ -392,9 +392,9 @@ static void show_page_range(unsigned long voffset, unsigned long offset,
if (opt_file)
printf("%lx\t", voff);
if (opt_list_cgroup)
- printf("@%llu\t", (unsigned long long)cgroup0);
+ printf("@%" PRIu64 "\t", cgroup0);
if (opt_list_mapcnt)
- printf("%lu\t", mapcnt0);
+ printf("%" PRIu64 "\t", mapcnt0);
printf("%lx\t%lx\t%s\n",
index, count, page_flag_name(flags0));
}
@@ -420,9 +420,9 @@ static void show_page(unsigned long voffset, unsigned long offset,
if (opt_file)
printf("%lx\t", voffset);
if (opt_list_cgroup)
- printf("@%llu\t", (unsigned long long)cgroup);
+ printf("@%" PRIu64 "\t", cgroup);
if (opt_list_mapcnt)
- printf("%lu\t", mapcnt);
+ printf("%" PRIu64 "\t", mapcnt);
printf("%lx\t%s\n", offset, page_flag_name(flags));
}
@@ -472,9 +472,9 @@ static int bit_mask_ok(uint64_t flags)
static uint64_t expand_overloaded_flags(uint64_t flags, uint64_t pme)
{
- /* Anonymous pages overload PG_mappedtodisk */
- if ((flags & BIT(ANON)) && (flags & BIT(MAPPEDTODISK)))
- flags ^= BIT(MAPPEDTODISK) | BIT(ANON_EXCLUSIVE);
+ /* Anonymous pages use PG_owner_2 for anon_exclusive */
+ if ((flags & BIT(ANON)) && (flags & BIT(OWNER_2)))
+ flags ^= BIT(OWNER_2) | BIT(ANON_EXCLUSIVE);
/* SLUB overloads several page flags */
if (flags & BIT(SLAB)) {
diff --git a/tools/mm/page_owner_sort.c b/tools/mm/page_owner_sort.c
index e1f264444342..880e36df0c11 100644
--- a/tools/mm/page_owner_sort.c
+++ b/tools/mm/page_owner_sort.c
@@ -377,6 +377,7 @@ static char *get_comm(char *buf)
if (errno != 0) {
if (debug_on)
fprintf(stderr, "wrong comm in follow buf:\n%s\n", buf);
+ free(comm_str);
return NULL;
}
diff --git a/tools/mm/slabinfo.c b/tools/mm/slabinfo.c
index cfaeaea71042..1433eff99feb 100644
--- a/tools/mm/slabinfo.c
+++ b/tools/mm/slabinfo.c
@@ -21,7 +21,7 @@
#include <regex.h>
#include <errno.h>
-#define MAX_SLABS 500
+#define MAX_SLABS 2000
#define MAX_ALIASES 500
#define MAX_NODES 1024
@@ -1228,6 +1228,8 @@ static void read_slab_dir(void)
continue;
switch (de->d_type) {
case DT_LNK:
+ if (alias - aliasinfo == MAX_ALIASES)
+ fatal("Too many aliases\n");
alias->name = strdup(de->d_name);
count = readlink(de->d_name, buffer, sizeof(buffer)-1);
@@ -1242,6 +1244,8 @@ static void read_slab_dir(void)
alias++;
break;
case DT_DIR:
+ if (slab - slabinfo == MAX_SLABS)
+ fatal("Too many slabs\n");
if (chdir(de->d_name))
fatal("Unable to access slab %s\n", slab->name);
slab->name = strdup(de->d_name);
@@ -1297,7 +1301,9 @@ static void read_slab_dir(void)
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 (chdir(".."))
+ fatal("Unable to chdir from slab ../%s\n",
+ slab->name);
if (slab->name[0] == ':')
alias_targets++;
slab++;
@@ -1310,10 +1316,6 @@ static void read_slab_dir(void)
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)
diff --git a/tools/mm/thp_swap_allocator_test.c b/tools/mm/thp_swap_allocator_test.c
new file mode 100644
index 000000000000..83afc52275a5
--- /dev/null
+++ b/tools/mm/thp_swap_allocator_test.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * thp_swap_allocator_test
+ *
+ * The purpose of this test program is helping check if THP swpout
+ * can correctly get swap slots to swap out as a whole instead of
+ * being split. It randomly releases swap entries through madvise
+ * DONTNEED and swapin/out on two memory areas: a memory area for
+ * 64KB THP and the other area for small folios. The second memory
+ * can be enabled by "-s".
+ * Before running the program, we need to setup a zRAM or similar
+ * swap device by:
+ * echo lzo > /sys/block/zram0/comp_algorithm
+ * echo 64M > /sys/block/zram0/disksize
+ * echo never > /sys/kernel/mm/transparent_hugepage/hugepages-2048kB/enabled
+ * echo always > /sys/kernel/mm/transparent_hugepage/hugepages-64kB/enabled
+ * mkswap /dev/zram0
+ * swapon /dev/zram0
+ * The expected result should be 0% anon swpout fallback ratio w/ or
+ * w/o "-s".
+ *
+ * Author(s): Barry Song <v-songbaohua@oppo.com>
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <linux/mman.h>
+#include <sys/mman.h>
+#include <errno.h>
+#include <time.h>
+
+#define MEMSIZE_MTHP (60 * 1024 * 1024)
+#define MEMSIZE_SMALLFOLIO (4 * 1024 * 1024)
+#define ALIGNMENT_MTHP (64 * 1024)
+#define ALIGNMENT_SMALLFOLIO (4 * 1024)
+#define TOTAL_DONTNEED_MTHP (16 * 1024 * 1024)
+#define TOTAL_DONTNEED_SMALLFOLIO (1 * 1024 * 1024)
+#define MTHP_FOLIO_SIZE (64 * 1024)
+
+#define SWPOUT_PATH \
+ "/sys/kernel/mm/transparent_hugepage/hugepages-64kB/stats/swpout"
+#define SWPOUT_FALLBACK_PATH \
+ "/sys/kernel/mm/transparent_hugepage/hugepages-64kB/stats/swpout_fallback"
+
+static void *aligned_alloc_mem(size_t size, size_t alignment)
+{
+ void *mem = NULL;
+
+ if (posix_memalign(&mem, alignment, size) != 0) {
+ perror("posix_memalign");
+ return NULL;
+ }
+ return mem;
+}
+
+/*
+ * This emulates the behavior of native libc and Java heap,
+ * as well as process exit and munmap. It helps generate mTHP
+ * and ensures that iterations can proceed with mTHP, as we
+ * currently don't support large folios swap-in.
+ */
+static void random_madvise_dontneed(void *mem, size_t mem_size,
+ size_t align_size, size_t total_dontneed_size)
+{
+ size_t num_pages = total_dontneed_size / align_size;
+ size_t i;
+ size_t offset;
+ void *addr;
+
+ for (i = 0; i < num_pages; ++i) {
+ offset = (rand() % (mem_size / align_size)) * align_size;
+ addr = (char *)mem + offset;
+ if (madvise(addr, align_size, MADV_DONTNEED) != 0)
+ perror("madvise dontneed");
+
+ memset(addr, 0x11, align_size);
+ }
+}
+
+static void random_swapin(void *mem, size_t mem_size,
+ size_t align_size, size_t total_swapin_size)
+{
+ size_t num_pages = total_swapin_size / align_size;
+ size_t i;
+ size_t offset;
+ void *addr;
+
+ for (i = 0; i < num_pages; ++i) {
+ offset = (rand() % (mem_size / align_size)) * align_size;
+ addr = (char *)mem + offset;
+ memset(addr, 0x11, align_size);
+ }
+}
+
+static unsigned long read_stat(const char *path)
+{
+ FILE *file;
+ unsigned long value;
+
+ file = fopen(path, "r");
+ if (!file) {
+ perror("fopen");
+ return 0;
+ }
+
+ if (fscanf(file, "%lu", &value) != 1) {
+ perror("fscanf");
+ fclose(file);
+ return 0;
+ }
+
+ fclose(file);
+ return value;
+}
+
+int main(int argc, char *argv[])
+{
+ int use_small_folio = 0, aligned_swapin = 0;
+ void *mem1 = NULL, *mem2 = NULL;
+ int i;
+
+ for (i = 1; i < argc; ++i) {
+ if (strcmp(argv[i], "-s") == 0)
+ use_small_folio = 1;
+ else if (strcmp(argv[i], "-a") == 0)
+ aligned_swapin = 1;
+ }
+
+ mem1 = aligned_alloc_mem(MEMSIZE_MTHP, ALIGNMENT_MTHP);
+ if (mem1 == NULL) {
+ fprintf(stderr, "Failed to allocate large folios memory\n");
+ return EXIT_FAILURE;
+ }
+
+ if (madvise(mem1, MEMSIZE_MTHP, MADV_HUGEPAGE) != 0) {
+ perror("madvise hugepage for mem1");
+ free(mem1);
+ return EXIT_FAILURE;
+ }
+
+ if (use_small_folio) {
+ mem2 = aligned_alloc_mem(MEMSIZE_SMALLFOLIO, ALIGNMENT_MTHP);
+ if (mem2 == NULL) {
+ fprintf(stderr, "Failed to allocate small folios memory\n");
+ free(mem1);
+ return EXIT_FAILURE;
+ }
+
+ if (madvise(mem2, MEMSIZE_SMALLFOLIO, MADV_NOHUGEPAGE) != 0) {
+ perror("madvise nohugepage for mem2");
+ free(mem1);
+ free(mem2);
+ return EXIT_FAILURE;
+ }
+ }
+
+ /* warm-up phase to occupy the swapfile */
+ memset(mem1, 0x11, MEMSIZE_MTHP);
+ madvise(mem1, MEMSIZE_MTHP, MADV_PAGEOUT);
+ if (use_small_folio) {
+ memset(mem2, 0x11, MEMSIZE_SMALLFOLIO);
+ madvise(mem2, MEMSIZE_SMALLFOLIO, MADV_PAGEOUT);
+ }
+
+ /* iterations with newly created mTHP, swap-in, and swap-out */
+ for (i = 0; i < 100; ++i) {
+ unsigned long initial_swpout;
+ unsigned long initial_swpout_fallback;
+ unsigned long final_swpout;
+ unsigned long final_swpout_fallback;
+ unsigned long swpout_inc;
+ unsigned long swpout_fallback_inc;
+ double fallback_percentage;
+
+ initial_swpout = read_stat(SWPOUT_PATH);
+ initial_swpout_fallback = read_stat(SWPOUT_FALLBACK_PATH);
+
+ /*
+ * The following setup creates a 1:1 ratio of mTHP to small folios
+ * since large folio swap-in isn't supported yet. Once we support
+ * mTHP swap-in, we'll likely need to reduce MEMSIZE_MTHP and
+ * increase MEMSIZE_SMALLFOLIO to maintain the ratio.
+ */
+ random_swapin(mem1, MEMSIZE_MTHP,
+ aligned_swapin ? ALIGNMENT_MTHP : ALIGNMENT_SMALLFOLIO,
+ TOTAL_DONTNEED_MTHP);
+ random_madvise_dontneed(mem1, MEMSIZE_MTHP, ALIGNMENT_MTHP,
+ TOTAL_DONTNEED_MTHP);
+
+ if (use_small_folio) {
+ random_swapin(mem2, MEMSIZE_SMALLFOLIO,
+ ALIGNMENT_SMALLFOLIO,
+ TOTAL_DONTNEED_SMALLFOLIO);
+ }
+
+ if (madvise(mem1, MEMSIZE_MTHP, MADV_PAGEOUT) != 0) {
+ perror("madvise pageout for mem1");
+ free(mem1);
+ if (mem2 != NULL)
+ free(mem2);
+ return EXIT_FAILURE;
+ }
+
+ if (use_small_folio) {
+ if (madvise(mem2, MEMSIZE_SMALLFOLIO, MADV_PAGEOUT) != 0) {
+ perror("madvise pageout for mem2");
+ free(mem1);
+ free(mem2);
+ return EXIT_FAILURE;
+ }
+ }
+
+ final_swpout = read_stat(SWPOUT_PATH);
+ final_swpout_fallback = read_stat(SWPOUT_FALLBACK_PATH);
+
+ swpout_inc = final_swpout - initial_swpout;
+ swpout_fallback_inc = final_swpout_fallback - initial_swpout_fallback;
+
+ fallback_percentage = (double)swpout_fallback_inc /
+ (swpout_fallback_inc + swpout_inc) * 100;
+
+ printf("Iteration %d: swpout inc: %lu, swpout fallback inc: %lu, Fallback percentage: %.2f%%\n",
+ i + 1, swpout_inc, swpout_fallback_inc, fallback_percentage);
+ }
+
+ free(mem1);
+ if (mem2 != NULL)
+ free(mem2);
+
+ return EXIT_SUCCESS;
+}
generated by cgit (git 2.34.1) at 2025-07-25 05:59:50 +0000