summaryrefslogtreecommitdiff
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/include/uapi/asm-generic/mman-common.h3
-rw-r--r--tools/mm/page_owner_sort.c1
-rw-r--r--tools/mm/slabinfo.c10
-rw-r--r--tools/testing/radix-tree/maple.c22
-rw-r--r--tools/testing/selftests/damon/_debugfs_common.sh7
-rw-r--r--tools/testing/selftests/damon/access_memory_even.c2
-rwxr-xr-xtools/testing/selftests/damon/debugfs_duplicate_context_creation.sh2
-rw-r--r--tools/testing/selftests/damon/huge_count_read_write.c4
-rw-r--r--tools/testing/selftests/mm/.gitignore4
-rw-r--r--tools/testing/selftests/mm/Makefile3
-rw-r--r--tools/testing/selftests/mm/guard-pages.c1243
-rw-r--r--tools/testing/selftests/mm/hugetlb_fault_after_madv.c48
-rwxr-xr-xtools/testing/selftests/mm/run_vmtests.sh10
-rw-r--r--tools/testing/selftests/mm/virtual_address_range.c4
-rw-r--r--tools/testing/shared/shared.mk1
-rw-r--r--tools/testing/vma/vma.c2
-rw-r--r--tools/testing/vma/vma_internal.h115
17 files changed, 1456 insertions, 25 deletions
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 6ce1f1ceb432..1ea2c4c33b86 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -79,6 +79,9 @@
#define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */
+#define MADV_GUARD_INSTALL 102 /* fatal signal on access to range */
+#define MADV_GUARD_REMOVE 103 /* unguard range */
+
/* compatibility flags */
#define MAP_FILE 0
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 04e9e6ba86ea..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);
@@ -1312,10 +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/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c
index 551ae6898c1d..bc30050227fd 100644
--- a/tools/testing/radix-tree/maple.c
+++ b/tools/testing/radix-tree/maple.c
@@ -462,6 +462,28 @@ static noinline void __init check_new_node(struct maple_tree *mt)
MT_BUG_ON(mt, mas_allocated(&mas) != 10 + MAPLE_ALLOC_SLOTS - 1);
mas_destroy(&mas);
+ mas.node = MA_ERROR(-ENOMEM);
+ mas_node_count(&mas, MAPLE_ALLOC_SLOTS + 1); /* Request */
+ mas_nomem(&mas, GFP_KERNEL); /* Fill request */
+ MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1);
+ mas.node = MA_ERROR(-ENOMEM);
+ mas_node_count(&mas, MAPLE_ALLOC_SLOTS * 2 + 2); /* Request */
+ mas_nomem(&mas, GFP_KERNEL); /* Fill request */
+ mas.status = ma_start;
+ MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS * 2 + 2);
+ mas_destroy(&mas);
+
+ mas.node = MA_ERROR(-ENOMEM);
+ mas_node_count(&mas, MAPLE_ALLOC_SLOTS * 2 + 1); /* Request */
+ mas_nomem(&mas, GFP_KERNEL); /* Fill request */
+ MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS * 2 + 1);
+ mas.node = MA_ERROR(-ENOMEM);
+ mas_node_count(&mas, MAPLE_ALLOC_SLOTS * 3 + 2); /* Request */
+ mas_nomem(&mas, GFP_KERNEL); /* Fill request */
+ mas.status = ma_start;
+ MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS * 3 + 2);
+ mas_destroy(&mas);
+
mtree_unlock(mt);
}
diff --git a/tools/testing/selftests/damon/_debugfs_common.sh b/tools/testing/selftests/damon/_debugfs_common.sh
index aa995516870b..54d45791b0d9 100644
--- a/tools/testing/selftests/damon/_debugfs_common.sh
+++ b/tools/testing/selftests/damon/_debugfs_common.sh
@@ -8,7 +8,12 @@ test_write_result() {
expect_reason=$4
expected=$5
- echo "$content" > "$file"
+ if [ "$expected" = "0" ]
+ then
+ echo "$content" > "$file"
+ else
+ echo "$content" > "$file" 2> /dev/null
+ fi
if [ $? -ne "$expected" ]
then
echo "writing $content to $file doesn't return $expected"
diff --git a/tools/testing/selftests/damon/access_memory_even.c b/tools/testing/selftests/damon/access_memory_even.c
index 3be121487432..a9f4e9aaf3a9 100644
--- a/tools/testing/selftests/damon/access_memory_even.c
+++ b/tools/testing/selftests/damon/access_memory_even.c
@@ -14,10 +14,8 @@
int main(int argc, char *argv[])
{
char **regions;
- clock_t start_clock;
int nr_regions;
int sz_region;
- int access_time_ms;
int i;
if (argc != 3) {
diff --git a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh b/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh
index 4a76e37ef16b..bd6c22d96ead 100755
--- a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh
+++ b/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh
@@ -12,7 +12,7 @@ then
exit 1
fi
-if echo foo > "$DBGFS/mk_contexts"
+if echo foo > "$DBGFS/mk_contexts" 2> /dev/null
then
echo "duplicate context creation success"
exit 1
diff --git a/tools/testing/selftests/damon/huge_count_read_write.c b/tools/testing/selftests/damon/huge_count_read_write.c
index a6fe0689f88d..53e69a669668 100644
--- a/tools/testing/selftests/damon/huge_count_read_write.c
+++ b/tools/testing/selftests/damon/huge_count_read_write.c
@@ -18,7 +18,7 @@
void write_read_with_huge_count(char *file)
{
int filedesc = open(file, O_RDWR);
- char buf[25];
+ char buf[256];
int ret;
printf("%s %s\n", __func__, file);
@@ -28,9 +28,7 @@ void write_read_with_huge_count(char *file)
}
write(filedesc, "", 0xfffffffful);
- perror("after write: ");
ret = read(filedesc, buf, 0xfffffffful);
- perror("after read: ");
close(filedesc);
}
diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore
index da030b43e43b..8f01f4da1c0d 100644
--- a/tools/testing/selftests/mm/.gitignore
+++ b/tools/testing/selftests/mm/.gitignore
@@ -51,3 +51,7 @@ hugetlb_madv_vs_map
mseal_test
seal_elf
droppable
+hugetlb_dio
+pkey_sighandler_tests_32
+pkey_sighandler_tests_64
+guard-pages
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 321e63955272..3de23ea4663f 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -90,6 +90,7 @@ TEST_GEN_FILES += hugetlb_fault_after_madv
TEST_GEN_FILES += hugetlb_madv_vs_map
TEST_GEN_FILES += hugetlb_dio
TEST_GEN_FILES += droppable
+TEST_GEN_FILES += guard-pages
ifneq ($(ARCH),arm64)
TEST_GEN_FILES += soft-dirty
@@ -126,7 +127,9 @@ endif
ifneq (,$(filter $(ARCH),arm64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64 s390))
TEST_GEN_FILES += va_high_addr_switch
+ifneq ($(ARCH),riscv64)
TEST_GEN_FILES += virtual_address_range
+endif
TEST_GEN_FILES += write_to_hugetlbfs
endif
diff --git a/tools/testing/selftests/mm/guard-pages.c b/tools/testing/selftests/mm/guard-pages.c
new file mode 100644
index 000000000000..7cdf815d0d63
--- /dev/null
+++ b/tools/testing/selftests/mm/guard-pages.c
@@ -0,0 +1,1243 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#define _GNU_SOURCE
+#include "../kselftest_harness.h"
+#include <asm-generic/mman.h> /* Force the import of the tools version. */
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/userfaultfd.h>
+#include <setjmp.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/syscall.h>
+#include <sys/uio.h>
+#include <unistd.h>
+
+/*
+ * Ignore the checkpatch warning, as per the C99 standard, section 7.14.1.1:
+ *
+ * "If the signal occurs other than as the result of calling the abort or raise
+ * function, the behavior is undefined if the signal handler refers to any
+ * object with static storage duration other than by assigning a value to an
+ * object declared as volatile sig_atomic_t"
+ */
+static volatile sig_atomic_t signal_jump_set;
+static sigjmp_buf signal_jmp_buf;
+
+/*
+ * Ignore the checkpatch warning, we must read from x but don't want to do
+ * anything with it in order to trigger a read page fault. We therefore must use
+ * volatile to stop the compiler from optimising this away.
+ */
+#define FORCE_READ(x) (*(volatile typeof(x) *)x)
+
+static int userfaultfd(int flags)
+{
+ return syscall(SYS_userfaultfd, flags);
+}
+
+static void handle_fatal(int c)
+{
+ if (!signal_jump_set)
+ return;
+
+ siglongjmp(signal_jmp_buf, c);
+}
+
+static int pidfd_open(pid_t pid, unsigned int flags)
+{
+ return syscall(SYS_pidfd_open, pid, flags);
+}
+
+/*
+ * Enable our signal catcher and try to read/write the specified buffer. The
+ * return value indicates whether the read/write succeeds without a fatal
+ * signal.
+ */
+static bool try_access_buf(char *ptr, bool write)
+{
+ bool failed;
+
+ /* Tell signal handler to jump back here on fatal signal. */
+ signal_jump_set = true;
+ /* If a fatal signal arose, we will jump back here and failed is set. */
+ failed = sigsetjmp(signal_jmp_buf, 0) != 0;
+
+ if (!failed) {
+ if (write)
+ *ptr = 'x';
+ else
+ FORCE_READ(ptr);
+ }
+
+ signal_jump_set = false;
+ return !failed;
+}
+
+/* Try and read from a buffer, return true if no fatal signal. */
+static bool try_read_buf(char *ptr)
+{
+ return try_access_buf(ptr, false);
+}
+
+/* Try and write to a buffer, return true if no fatal signal. */
+static bool try_write_buf(char *ptr)
+{
+ return try_access_buf(ptr, true);
+}
+
+/*
+ * Try and BOTH read from AND write to a buffer, return true if BOTH operations
+ * succeed.
+ */
+static bool try_read_write_buf(char *ptr)
+{
+ return try_read_buf(ptr) && try_write_buf(ptr);
+}
+
+FIXTURE(guard_pages)
+{
+ unsigned long page_size;
+};
+
+FIXTURE_SETUP(guard_pages)
+{
+ struct sigaction act = {
+ .sa_handler = &handle_fatal,
+ .sa_flags = SA_NODEFER,
+ };
+
+ sigemptyset(&act.sa_mask);
+ if (sigaction(SIGSEGV, &act, NULL))
+ ksft_exit_fail_perror("sigaction");
+
+ self->page_size = (unsigned long)sysconf(_SC_PAGESIZE);
+};
+
+FIXTURE_TEARDOWN(guard_pages)
+{
+ struct sigaction act = {
+ .sa_handler = SIG_DFL,
+ .sa_flags = SA_NODEFER,
+ };
+
+ sigemptyset(&act.sa_mask);
+ sigaction(SIGSEGV, &act, NULL);
+}
+
+TEST_F(guard_pages, basic)
+{
+ const unsigned long NUM_PAGES = 10;
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ int i;
+
+ ptr = mmap(NULL, NUM_PAGES * page_size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANON, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Trivially assert we can touch the first page. */
+ ASSERT_TRUE(try_read_write_buf(ptr));
+
+ ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0);
+
+ /* Establish that 1st page SIGSEGV's. */
+ ASSERT_FALSE(try_read_write_buf(ptr));
+
+ /* Ensure we can touch everything else.*/
+ for (i = 1; i < NUM_PAGES; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_TRUE(try_read_write_buf(curr));
+ }
+
+ /* Establish a guard page at the end of the mapping. */
+ ASSERT_EQ(madvise(&ptr[(NUM_PAGES - 1) * page_size], page_size,
+ MADV_GUARD_INSTALL), 0);
+
+ /* Check that both guard pages result in SIGSEGV. */
+ ASSERT_FALSE(try_read_write_buf(ptr));
+ ASSERT_FALSE(try_read_write_buf(&ptr[(NUM_PAGES - 1) * page_size]));
+
+ /* Remove the first guard page. */
+ ASSERT_FALSE(madvise(ptr, page_size, MADV_GUARD_REMOVE));
+
+ /* Make sure we can touch it. */
+ ASSERT_TRUE(try_read_write_buf(ptr));
+
+ /* Remove the last guard page. */
+ ASSERT_FALSE(madvise(&ptr[(NUM_PAGES - 1) * page_size], page_size,
+ MADV_GUARD_REMOVE));
+
+ /* Make sure we can touch it. */
+ ASSERT_TRUE(try_read_write_buf(&ptr[(NUM_PAGES - 1) * page_size]));
+
+ /*
+ * Test setting a _range_ of pages, namely the first 3. The first of
+ * these be faulted in, so this also tests that we can install guard
+ * pages over backed pages.
+ */
+ ASSERT_EQ(madvise(ptr, 3 * page_size, MADV_GUARD_INSTALL), 0);
+
+ /* Make sure they are all guard pages. */
+ for (i = 0; i < 3; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ /* Make sure the rest are not. */
+ for (i = 3; i < NUM_PAGES; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_TRUE(try_read_write_buf(curr));
+ }
+
+ /* Remove guard pages. */
+ ASSERT_EQ(madvise(ptr, NUM_PAGES * page_size, MADV_GUARD_REMOVE), 0);
+
+ /* Now make sure we can touch everything. */
+ for (i = 0; i < NUM_PAGES; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_TRUE(try_read_write_buf(curr));
+ }
+
+ /*
+ * Now remove all guard pages, make sure we don't remove existing
+ * entries.
+ */
+ ASSERT_EQ(madvise(ptr, NUM_PAGES * page_size, MADV_GUARD_REMOVE), 0);
+
+ for (i = 0; i < NUM_PAGES * page_size; i += page_size) {
+ char chr = ptr[i];
+
+ ASSERT_EQ(chr, 'x');
+ }
+
+ ASSERT_EQ(munmap(ptr, NUM_PAGES * page_size), 0);
+}
+
+/* Assert that operations applied across multiple VMAs work as expected. */
+TEST_F(guard_pages, multi_vma)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr_region, *ptr, *ptr1, *ptr2, *ptr3;
+ int i;
+
+ /* Reserve a 100 page region over which we can install VMAs. */
+ ptr_region = mmap(NULL, 100 * page_size, PROT_NONE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr_region, MAP_FAILED);
+
+ /* Place a VMA of 10 pages size at the start of the region. */
+ ptr1 = mmap(ptr_region, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr1, MAP_FAILED);
+
+ /* Place a VMA of 5 pages size 50 pages into the region. */
+ ptr2 = mmap(&ptr_region[50 * page_size], 5 * page_size,
+ PROT_READ | PROT_WRITE,
+ MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr2, MAP_FAILED);
+
+ /* Place a VMA of 20 pages size at the end of the region. */
+ ptr3 = mmap(&ptr_region[80 * page_size], 20 * page_size,
+ PROT_READ | PROT_WRITE,
+ MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr3, MAP_FAILED);
+
+ /* Unmap gaps. */
+ ASSERT_EQ(munmap(&ptr_region[10 * page_size], 40 * page_size), 0);
+ ASSERT_EQ(munmap(&ptr_region[55 * page_size], 25 * page_size), 0);
+
+ /*
+ * We end up with VMAs like this:
+ *
+ * 0 10 .. 50 55 .. 80 100
+ * [---] [---] [---]
+ */
+
+ /*
+ * Now mark the whole range as guard pages and make sure all VMAs are as
+ * such.
+ */
+
+ /*
+ * madvise() is certifiable and lets you perform operations over gaps,
+ * everything works, but it indicates an error and errno is set to
+ * -ENOMEM. Also if anything runs out of memory it is set to
+ * -ENOMEM. You are meant to guess which is which.
+ */
+ ASSERT_EQ(madvise(ptr_region, 100 * page_size, MADV_GUARD_INSTALL), -1);
+ ASSERT_EQ(errno, ENOMEM);
+
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr1[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ for (i = 0; i < 5; i++) {
+ char *curr = &ptr2[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ for (i = 0; i < 20; i++) {
+ char *curr = &ptr3[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ /* Now remove guar pages over range and assert the opposite. */
+
+ ASSERT_EQ(madvise(ptr_region, 100 * page_size, MADV_GUARD_REMOVE), -1);
+ ASSERT_EQ(errno, ENOMEM);
+
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr1[i * page_size];
+
+ ASSERT_TRUE(try_read_write_buf(curr));
+ }
+
+ for (i = 0; i < 5; i++) {
+ char *curr = &ptr2[i * page_size];
+
+ ASSERT_TRUE(try_read_write_buf(curr));
+ }
+
+ for (i = 0; i < 20; i++) {
+ char *curr = &ptr3[i * page_size];
+
+ ASSERT_TRUE(try_read_write_buf(curr));
+ }
+
+ /* Now map incompatible VMAs in the gaps. */
+ ptr = mmap(&ptr_region[10 * page_size], 40 * page_size,
+ PROT_READ | PROT_WRITE | PROT_EXEC,
+ MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+ ptr = mmap(&ptr_region[55 * page_size], 25 * page_size,
+ PROT_READ | PROT_WRITE | PROT_EXEC,
+ MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /*
+ * We end up with VMAs like this:
+ *
+ * 0 10 .. 50 55 .. 80 100
+ * [---][xxxx][---][xxxx][---]
+ *
+ * Where 'x' signifies VMAs that cannot be merged with those adjacent to
+ * them.
+ */
+
+ /* Multiple VMAs adjacent to one another should result in no error. */
+ ASSERT_EQ(madvise(ptr_region, 100 * page_size, MADV_GUARD_INSTALL), 0);
+ for (i = 0; i < 100; i++) {
+ char *curr = &ptr_region[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+ ASSERT_EQ(madvise(ptr_region, 100 * page_size, MADV_GUARD_REMOVE), 0);
+ for (i = 0; i < 100; i++) {
+ char *curr = &ptr_region[i * page_size];
+
+ ASSERT_TRUE(try_read_write_buf(curr));
+ }
+
+ /* Cleanup. */
+ ASSERT_EQ(munmap(ptr_region, 100 * page_size), 0);
+}
+
+/*
+ * Assert that batched operations performed using process_madvise() work as
+ * expected.
+ */
+TEST_F(guard_pages, process_madvise)
+{
+ const unsigned long page_size = self->page_size;
+ pid_t pid = getpid();
+ int pidfd = pidfd_open(pid, 0);
+ char *ptr_region, *ptr1, *ptr2, *ptr3;
+ ssize_t count;
+ struct iovec vec[6];
+
+ ASSERT_NE(pidfd, -1);
+
+ /* Reserve region to map over. */
+ ptr_region = mmap(NULL, 100 * page_size, PROT_NONE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr_region, MAP_FAILED);
+
+ /*
+ * 10 pages offset 1 page into reserve region. We MAP_POPULATE so we
+ * overwrite existing entries and test this code path against
+ * overwriting existing entries.
+ */
+ ptr1 = mmap(&ptr_region[page_size], 10 * page_size,
+ PROT_READ | PROT_WRITE,
+ MAP_FIXED | MAP_ANON | MAP_PRIVATE | MAP_POPULATE, -1, 0);
+ ASSERT_NE(ptr1, MAP_FAILED);
+ /* We want guard markers at start/end of each VMA. */
+ vec[0].iov_base = ptr1;
+ vec[0].iov_len = page_size;
+ vec[1].iov_base = &ptr1[9 * page_size];
+ vec[1].iov_len = page_size;
+
+ /* 5 pages offset 50 pages into reserve region. */
+ ptr2 = mmap(&ptr_region[50 * page_size], 5 * page_size,
+ PROT_READ | PROT_WRITE,
+ MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr2, MAP_FAILED);
+ vec[2].iov_base = ptr2;
+ vec[2].iov_len = page_size;
+ vec[3].iov_base = &ptr2[4 * page_size];
+ vec[3].iov_len = page_size;
+
+ /* 20 pages offset 79 pages into reserve region. */
+ ptr3 = mmap(&ptr_region[79 * page_size], 20 * page_size,
+ PROT_READ | PROT_WRITE,
+ MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr3, MAP_FAILED);
+ vec[4].iov_base = ptr3;
+ vec[4].iov_len = page_size;
+ vec[5].iov_base = &ptr3[19 * page_size];
+ vec[5].iov_len = page_size;
+
+ /* Free surrounding VMAs. */
+ ASSERT_EQ(munmap(ptr_region, page_size), 0);
+ ASSERT_EQ(munmap(&ptr_region[11 * page_size], 39 * page_size), 0);
+ ASSERT_EQ(munmap(&ptr_region[55 * page_size], 24 * page_size), 0);
+ ASSERT_EQ(munmap(&ptr_region[99 * page_size], page_size), 0);
+
+ /* Now guard in one step. */
+ count = process_madvise(pidfd, vec, 6, MADV_GUARD_INSTALL, 0);
+
+ /* OK we don't have permission to do this, skip. */
+ if (count == -1 && errno == EPERM)
+ ksft_exit_skip("No process_madvise() permissions, try running as root.\n");
+
+ /* Returns the number of bytes advised. */
+ ASSERT_EQ(count, 6 * page_size);
+
+ /* Now make sure the guarding was applied. */
+
+ ASSERT_FALSE(try_read_write_buf(ptr1));
+ ASSERT_FALSE(try_read_write_buf(&ptr1[9 * page_size]));
+
+ ASSERT_FALSE(try_read_write_buf(ptr2));
+ ASSERT_FALSE(try_read_write_buf(&ptr2[4 * page_size]));
+
+ ASSERT_FALSE(try_read_write_buf(ptr3));
+ ASSERT_FALSE(try_read_write_buf(&ptr3[19 * page_size]));
+
+ /* Now do the same with unguard... */
+ count = process_madvise(pidfd, vec, 6, MADV_GUARD_REMOVE, 0);
+
+ /* ...and everything should now succeed. */
+
+ ASSERT_TRUE(try_read_write_buf(ptr1));
+ ASSERT_TRUE(try_read_write_buf(&ptr1[9 * page_size]));
+
+ ASSERT_TRUE(try_read_write_buf(ptr2));
+ ASSERT_TRUE(try_read_write_buf(&ptr2[4 * page_size]));
+
+ ASSERT_TRUE(try_read_write_buf(ptr3));
+ ASSERT_TRUE(try_read_write_buf(&ptr3[19 * page_size]));
+
+ /* Cleanup. */
+ ASSERT_EQ(munmap(ptr1, 10 * page_size), 0);
+ ASSERT_EQ(munmap(ptr2, 5 * page_size), 0);
+ ASSERT_EQ(munmap(ptr3, 20 * page_size), 0);
+ close(pidfd);
+}
+
+/* Assert that unmapping ranges does not leave guard markers behind. */
+TEST_F(guard_pages, munmap)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr, *ptr_new1, *ptr_new2;
+
+ ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Guard first and last pages. */
+ ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0);
+ ASSERT_EQ(madvise(&ptr[9 * page_size], page_size, MADV_GUARD_INSTALL), 0);
+
+ /* Assert that they are guarded. */
+ ASSERT_FALSE(try_read_write_buf(ptr));
+ ASSERT_FALSE(try_read_write_buf(&ptr[9 * page_size]));
+
+ /* Unmap them. */
+ ASSERT_EQ(munmap(ptr, page_size), 0);
+ ASSERT_EQ(munmap(&ptr[9 * page_size], page_size), 0);
+
+ /* Map over them.*/
+ ptr_new1 = mmap(ptr, page_size, PROT_READ | PROT_WRITE,
+ MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr_new1, MAP_FAILED);
+ ptr_new2 = mmap(&ptr[9 * page_size], page_size, PROT_READ | PROT_WRITE,
+ MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr_new2, MAP_FAILED);
+
+ /* Assert that they are now not guarded. */
+ ASSERT_TRUE(try_read_write_buf(ptr_new1));
+ ASSERT_TRUE(try_read_write_buf(ptr_new2));
+
+ /* Cleanup. */
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/* Assert that mprotect() operations have no bearing on guard markers. */
+TEST_F(guard_pages, mprotect)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ int i;
+
+ ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Guard the middle of the range. */
+ ASSERT_EQ(madvise(&ptr[5 * page_size], 2 * page_size,
+ MADV_GUARD_INSTALL), 0);
+
+ /* Assert that it is indeed guarded. */
+ ASSERT_FALSE(try_read_write_buf(&ptr[5 * page_size]));
+ ASSERT_FALSE(try_read_write_buf(&ptr[6 * page_size]));
+
+ /* Now make these pages read-only. */
+ ASSERT_EQ(mprotect(&ptr[5 * page_size], 2 * page_size, PROT_READ), 0);
+
+ /* Make sure the range is still guarded. */
+ ASSERT_FALSE(try_read_buf(&ptr[5 * page_size]));
+ ASSERT_FALSE(try_read_buf(&ptr[6 * page_size]));
+
+ /* Make sure we can guard again without issue.*/
+ ASSERT_EQ(madvise(&ptr[5 * page_size], 2 * page_size,
+ MADV_GUARD_INSTALL), 0);
+
+ /* Make sure the range is, yet again, still guarded. */
+ ASSERT_FALSE(try_read_buf(&ptr[5 * page_size]));
+ ASSERT_FALSE(try_read_buf(&ptr[6 * page_size]));
+
+ /* Now unguard the whole range. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0);
+
+ /* Make sure the whole range is readable. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_TRUE(try_read_buf(curr));
+ }
+
+ /* Cleanup. */
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/* Split and merge VMAs and make sure guard pages still behave. */
+TEST_F(guard_pages, split_merge)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr, *ptr_new;
+ int i;
+
+ ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Guard the whole range. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0);
+
+ /* Make sure the whole range is guarded. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ /* Now unmap some pages in the range so we split. */
+ ASSERT_EQ(munmap(&ptr[2 * page_size], page_size), 0);
+ ASSERT_EQ(munmap(&ptr[5 * page_size], page_size), 0);
+ ASSERT_EQ(munmap(&ptr[8 * page_size], page_size), 0);
+
+ /* Make sure the remaining ranges are guarded post-split. */
+ for (i = 0; i < 2; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+ for (i = 2; i < 5; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+ for (i = 6; i < 8; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+ for (i = 9; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ /* Now map them again - the unmap will have cleared the guards. */
+ ptr_new = mmap(&ptr[2 * page_size], page_size, PROT_READ | PROT_WRITE,
+ MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr_new, MAP_FAILED);
+ ptr_new = mmap(&ptr[5 * page_size], page_size, PROT_READ | PROT_WRITE,
+ MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr_new, MAP_FAILED);
+ ptr_new = mmap(&ptr[8 * page_size], page_size, PROT_READ | PROT_WRITE,
+ MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr_new, MAP_FAILED);
+
+ /* Now make sure guard pages are established. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+ bool result = try_read_write_buf(curr);
+ bool expect_true = i == 2 || i == 5 || i == 8;
+
+ ASSERT_TRUE(expect_true ? result : !result);
+ }
+
+ /* Now guard everything again. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0);
+
+ /* Make sure the whole range is guarded. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ /* Now split the range into three. */
+ ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ), 0);
+ ASSERT_EQ(mprotect(&ptr[7 * page_size], 3 * page_size, PROT_READ), 0);
+
+ /* Make sure the whole range is guarded for read. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_buf(curr));
+ }
+
+ /* Now reset protection bits so we merge the whole thing. */
+ ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ | PROT_WRITE), 0);
+ ASSERT_EQ(mprotect(&ptr[7 * page_size], 3 * page_size,
+ PROT_READ | PROT_WRITE), 0);
+
+ /* Make sure the whole range is still guarded. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ /* Split range into 3 again... */
+ ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ), 0);
+ ASSERT_EQ(mprotect(&ptr[7 * page_size], 3 * page_size, PROT_READ), 0);
+
+ /* ...and unguard the whole range. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0);
+
+ /* Make sure the whole range is remedied for read. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_TRUE(try_read_buf(curr));
+ }
+
+ /* Merge them again. */
+ ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ | PROT_WRITE), 0);
+ ASSERT_EQ(mprotect(&ptr[7 * page_size], 3 * page_size,
+ PROT_READ | PROT_WRITE), 0);
+
+ /* Now ensure the merged range is remedied for read/write. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_TRUE(try_read_write_buf(curr));
+ }
+
+ /* Cleanup. */
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/* Assert that MADV_DONTNEED does not remove guard markers. */
+TEST_F(guard_pages, dontneed)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ int i;
+
+ ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Back the whole range. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ *curr = 'y';
+ }
+
+ /* Guard every other page. */
+ for (i = 0; i < 10; i += 2) {
+ char *curr = &ptr[i * page_size];
+ int res = madvise(curr, page_size, MADV_GUARD_INSTALL);
+
+ ASSERT_EQ(res, 0);
+ }
+
+ /* Indicate that we don't need any of the range. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_DONTNEED), 0);
+
+ /* Check to ensure guard markers are still in place. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+ bool result = try_read_buf(curr);
+
+ if (i % 2 == 0) {
+ ASSERT_FALSE(result);
+ } else {
+ ASSERT_TRUE(result);
+ /* Make sure we really did get reset to zero page. */
+ ASSERT_EQ(*curr, '\0');
+ }
+
+ /* Now write... */
+ result = try_write_buf(&ptr[i * page_size]);
+
+ /* ...and make sure same result. */
+ ASSERT_TRUE(i % 2 != 0 ? result : !result);
+ }
+
+ /* Cleanup. */
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/* Assert that mlock()'ed pages work correctly with guard markers. */
+TEST_F(guard_pages, mlock)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ int i;
+
+ ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Populate. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ *curr = 'y';
+ }
+
+ /* Lock. */
+ ASSERT_EQ(mlock(ptr, 10 * page_size), 0);
+
+ /* Now try to guard, should fail with EINVAL. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), -1);
+ ASSERT_EQ(errno, EINVAL);
+
+ /* OK unlock. */
+ ASSERT_EQ(munlock(ptr, 10 * page_size), 0);
+
+ /* Guard first half of range, should now succeed. */
+ ASSERT_EQ(madvise(ptr, 5 * page_size, MADV_GUARD_INSTALL), 0);
+
+ /* Make sure guard works. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+ bool result = try_read_write_buf(curr);
+
+ if (i < 5) {
+ ASSERT_FALSE(result);
+ } else {
+ ASSERT_TRUE(result);
+ ASSERT_EQ(*curr, 'x');
+ }
+ }
+
+ /*
+ * Now lock the latter part of the range. We can't lock the guard pages,
+ * as this would result in the pages being populated and the guarding
+ * would cause this to error out.
+ */
+ ASSERT_EQ(mlock(&ptr[5 * page_size], 5 * page_size), 0);
+
+ /*
+ * Now remove guard pages, we permit mlock()'d ranges to have guard
+ * pages removed as it is a non-destructive operation.
+ */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0);
+
+ /* Now check that no guard pages remain. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_TRUE(try_read_write_buf(curr));
+ }
+
+ /* Cleanup. */
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/*
+ * Assert that moving, extending and shrinking memory via mremap() retains
+ * guard markers where possible.
+ *
+ * - Moving a mapping alone should retain markers as they are.
+ */
+TEST_F(guard_pages, mremap_move)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr, *ptr_new;
+
+ /* Map 5 pages. */
+ ptr = mmap(NULL, 5 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Place guard markers at both ends of the 5 page span. */
+ ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0);
+ ASSERT_EQ(madvise(&ptr[4 * page_size], page_size, MADV_GUARD_INSTALL), 0);
+
+ /* Make sure the guard pages are in effect. */
+ ASSERT_FALSE(try_read_write_buf(ptr));
+ ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size]));
+
+ /* Map a new region we will move this range into. Doing this ensures
+ * that we have reserved a range to map into.
+ */
+ ptr_new = mmap(NULL, 5 * page_size, PROT_NONE, MAP_ANON | MAP_PRIVATE,
+ -1, 0);
+ ASSERT_NE(ptr_new, MAP_FAILED);
+
+ ASSERT_EQ(mremap(ptr, 5 * page_size, 5 * page_size,
+ MREMAP_MAYMOVE | MREMAP_FIXED, ptr_new), ptr_new);
+
+ /* Make sure the guard markers are retained. */
+ ASSERT_FALSE(try_read_write_buf(ptr_new));
+ ASSERT_FALSE(try_read_write_buf(&ptr_new[4 * page_size]));
+
+ /*
+ * Clean up - we only need reference the new pointer as we overwrote the
+ * PROT_NONE range and moved the existing one.
+ */
+ munmap(ptr_new, 5 * page_size);
+}
+
+/*
+ * Assert that moving, extending and shrinking memory via mremap() retains
+ * guard markers where possible.
+ *
+ * Expanding should retain guard pages, only now in different position. The user
+ * will have to remove guard pages manually to fix up (they'd have to do the
+ * same if it were a PROT_NONE mapping).
+ */
+TEST_F(guard_pages, mremap_expand)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr, *ptr_new;
+
+ /* Map 10 pages... */
+ ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+ /* ...But unmap the last 5 so we can ensure we can expand into them. */
+ ASSERT_EQ(munmap(&ptr[5 * page_size], 5 * page_size), 0);
+
+ /* Place guard markers at both ends of the 5 page span. */
+ ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0);
+ ASSERT_EQ(madvise(&ptr[4 * page_size], page_size, MADV_GUARD_INSTALL), 0);
+
+ /* Make sure the guarding is in effect. */
+ ASSERT_FALSE(try_read_write_buf(ptr));
+ ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size]));
+
+ /* Now expand to 10 pages. */
+ ptr = mremap(ptr, 5 * page_size, 10 * page_size, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /*
+ * Make sure the guard markers are retained in their original positions.
+ */
+ ASSERT_FALSE(try_read_write_buf(ptr));
+ ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size]));
+
+ /* Reserve a region which we can move to and expand into. */
+ ptr_new = mmap(NULL, 20 * page_size, PROT_NONE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr_new, MAP_FAILED);
+
+ /* Now move and expand into it. */
+ ptr = mremap(ptr, 10 * page_size, 20 * page_size,
+ MREMAP_MAYMOVE | MREMAP_FIXED, ptr_new);
+ ASSERT_EQ(ptr, ptr_new);
+
+ /*
+ * Again, make sure the guard markers are retained in their original positions.
+ */
+ ASSERT_FALSE(try_read_write_buf(ptr));
+ ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size]));
+
+ /*
+ * A real user would have to remove guard markers, but would reasonably
+ * expect all characteristics of the mapping to be retained, including
+ * guard markers.
+ */
+
+ /* Cleanup. */
+ munmap(ptr, 20 * page_size);
+}
+/*
+ * Assert that moving, extending and shrinking memory via mremap() retains
+ * guard markers where possible.
+ *
+ * Shrinking will result in markers that are shrunk over being removed. Again,
+ * if the user were using a PROT_NONE mapping they'd have to manually fix this
+ * up also so this is OK.
+ */
+TEST_F(guard_pages, mremap_shrink)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ int i;
+
+ /* Map 5 pages. */
+ ptr = mmap(NULL, 5 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Place guard markers at both ends of the 5 page span. */
+ ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0);
+ ASSERT_EQ(madvise(&ptr[4 * page_size], page_size, MADV_GUARD_INSTALL), 0);
+
+ /* Make sure the guarding is in effect. */
+ ASSERT_FALSE(try_read_write_buf(ptr));
+ ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size]));
+
+ /* Now shrink to 3 pages. */
+ ptr = mremap(ptr, 5 * page_size, 3 * page_size, MREMAP_MAYMOVE);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* We expect the guard marker at the start to be retained... */
+ ASSERT_FALSE(try_read_write_buf(ptr));
+
+ /* ...But remaining pages will not have guard markers. */
+ for (i = 1; i < 3; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_TRUE(try_read_write_buf(curr));
+ }
+
+ /*
+ * As with expansion, a real user would have to remove guard pages and
+ * fixup. But you'd have to do similar manual things with PROT_NONE
+ * mappings too.
+ */
+
+ /*
+ * If we expand back to the original size, the end marker will, of
+ * course, no longer be present.
+ */
+ ptr = mremap(ptr, 3 * page_size, 5 * page_size, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Again, we expect the guard marker at the start to be retained... */
+ ASSERT_FALSE(try_read_write_buf(ptr));
+
+ /* ...But remaining pages will not have guard markers. */
+ for (i = 1; i < 5; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_TRUE(try_read_write_buf(curr));
+ }
+
+ /* Cleanup. */
+ munmap(ptr, 5 * page_size);
+}
+
+/*
+ * Assert that forking a process with VMAs that do not have VM_WIPEONFORK set
+ * retain guard pages.
+ */
+TEST_F(guard_pages, fork)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ pid_t pid;
+ int i;
+
+ /* Map 10 pages. */
+ ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Establish guard apges in the first 5 pages. */
+ ASSERT_EQ(madvise(ptr, 5 * page_size, MADV_GUARD_INSTALL), 0);
+
+ pid = fork();
+ ASSERT_NE(pid, -1);
+ if (!pid) {
+ /* This is the child process now. */
+
+ /* Assert that the guarding is in effect. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+ bool result = try_read_write_buf(curr);
+
+ ASSERT_TRUE(i >= 5 ? result : !result);
+ }
+
+ /* Now unguard the range.*/
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0);
+
+ exit(0);
+ }
+
+ /* Parent process. */
+
+ /* Parent simply waits on child. */
+ waitpid(pid, NULL, 0);
+
+ /* Child unguard does not impact parent page table state. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+ bool result = try_read_write_buf(curr);
+
+ ASSERT_TRUE(i >= 5 ? result : !result);
+ }
+
+ /* Cleanup. */
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/*
+ * Assert that forking a process with VMAs that do have VM_WIPEONFORK set
+ * behave as expected.
+ */
+TEST_F(guard_pages, fork_wipeonfork)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ pid_t pid;
+ int i;
+
+ /* Map 10 pages. */
+ ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Mark wipe on fork. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_WIPEONFORK), 0);
+
+ /* Guard the first 5 pages. */
+ ASSERT_EQ(madvise(ptr, 5 * page_size, MADV_GUARD_INSTALL), 0);
+
+ pid = fork();
+ ASSERT_NE(pid, -1);
+ if (!pid) {
+ /* This is the child process now. */
+
+ /* Guard will have been wiped. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_TRUE(try_read_write_buf(curr));
+ }
+
+ exit(0);
+ }
+
+ /* Parent process. */
+
+ waitpid(pid, NULL, 0);
+
+ /* Guard markers should be in effect.*/
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+ bool result = try_read_write_buf(curr);
+
+ ASSERT_TRUE(i >= 5 ? result : !result);
+ }
+
+ /* Cleanup. */
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/* Ensure that MADV_FREE retains guard entries as expected. */
+TEST_F(guard_pages, lazyfree)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ int i;
+
+ /* Map 10 pages. */
+ ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Guard range. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0);
+
+ /* Ensure guarded. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ /* Lazyfree range. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_FREE), 0);
+
+ /* This should leave the guard markers in place. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ /* Cleanup. */
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/* Ensure that MADV_POPULATE_READ, MADV_POPULATE_WRITE behave as expected. */
+TEST_F(guard_pages, populate)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+
+ /* Map 10 pages. */
+ ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Guard range. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0);
+
+ /* Populate read should error out... */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_POPULATE_READ), -1);
+ ASSERT_EQ(errno, EFAULT);
+
+ /* ...as should populate write. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_POPULATE_WRITE), -1);
+ ASSERT_EQ(errno, EFAULT);
+
+ /* Cleanup. */
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/* Ensure that MADV_COLD, MADV_PAGEOUT do not remove guard markers. */
+TEST_F(guard_pages, cold_pageout)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ int i;
+
+ /* Map 10 pages. */
+ ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Guard range. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0);
+
+ /* Ensured guarded. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ /* Now mark cold. This should have no impact on guard markers. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_COLD), 0);
+
+ /* Should remain guarded. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ /* OK, now page out. This should equally, have no effect on markers. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_PAGEOUT), 0);
+
+ /* Should remain guarded. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ /* Cleanup. */
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/* Ensure that guard pages do not break userfaultd. */
+TEST_F(guard_pages, uffd)
+{
+ const unsigned long page_size = self->page_size;
+ int uffd;
+ char *ptr;
+ int i;
+ struct uffdio_api api = {
+ .api = UFFD_API,
+ .features = 0,
+ };
+ struct uffdio_register reg;
+ struct uffdio_range range;
+
+ /* Set up uffd. */
+ uffd = userfaultfd(0);
+ if (uffd == -1 && errno == EPERM)
+ ksft_exit_skip("No userfaultfd permissions, try running as root.\n");
+ ASSERT_NE(uffd, -1);
+
+ ASSERT_EQ(ioctl(uffd, UFFDIO_API, &api), 0);
+
+ /* Map 10 pages. */
+ ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANON | MAP_PRIVATE, -1, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Register the range with uffd. */
+ range.start = (unsigned long)ptr;
+ range.len = 10 * page_size;
+ reg.range = range;
+ reg.mode = UFFDIO_REGISTER_MODE_MISSING;
+ ASSERT_EQ(ioctl(uffd, UFFDIO_REGISTER, &reg), 0);
+
+ /* Guard the range. This should not trigger the uffd. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0);
+
+ /* The guarding should behave as usual with no uffd intervention. */
+ for (i = 0; i < 10; i++) {
+ char *curr = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_read_write_buf(curr));
+ }
+
+ /* Cleanup. */
+ ASSERT_EQ(ioctl(uffd, UFFDIO_UNREGISTER, &range), 0);
+ close(uffd);
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/mm/hugetlb_fault_after_madv.c b/tools/testing/selftests/mm/hugetlb_fault_after_madv.c
index 73b81c632366..e2640529dbb2 100644
--- a/tools/testing/selftests/mm/hugetlb_fault_after_madv.c
+++ b/tools/testing/selftests/mm/hugetlb_fault_after_madv.c
@@ -5,20 +5,36 @@
#include <sys/mman.h>
#include <sys/types.h>
#include <unistd.h>
+#include <setjmp.h>
+#include <signal.h>
#include "vm_util.h"
#include "../kselftest.h"
-#define MMAP_SIZE (1 << 21)
#define INLOOP_ITER 100
-char *huge_ptr;
+static char *huge_ptr;
+static size_t huge_page_size;
+
+static sigjmp_buf sigbuf;
+static bool sigbus_triggered;
+
+static void signal_handler(int signal)
+{
+ if (signal == SIGBUS) {
+ sigbus_triggered = true;
+ siglongjmp(sigbuf, 1);
+ }
+}
/* Touch the memory while it is being madvised() */
void *touch(void *unused)
{
char *ptr = (char *)huge_ptr;
+ if (sigsetjmp(sigbuf, 1))
+ return NULL;
+
for (int i = 0; i < INLOOP_ITER; i++)
ptr[0] = '.';
@@ -30,7 +46,7 @@ void *madv(void *unused)
usleep(rand() % 10);
for (int i = 0; i < INLOOP_ITER; i++)
- madvise(huge_ptr, MMAP_SIZE, MADV_DONTNEED);
+ madvise(huge_ptr, huge_page_size, MADV_DONTNEED);
return NULL;
}
@@ -44,9 +60,23 @@ int main(void)
* interactions
*/
int max = 10000;
+ int err;
+
+ ksft_print_header();
+ ksft_set_plan(1);
srand(getpid());
+ if (signal(SIGBUS, signal_handler) == SIG_ERR)
+ ksft_exit_skip("Could not register signal handler.");
+
+ huge_page_size = default_huge_page_size();
+ if (!huge_page_size)
+ ksft_exit_skip("Could not detect default hugetlb page size.");
+
+ ksft_print_msg("[INFO] detected default hugetlb page size: %zu KiB\n",
+ huge_page_size / 1024);
+
free_hugepages = get_free_hugepages();
if (free_hugepages != 1) {
ksft_exit_skip("This test needs one and only one page to execute. Got %lu\n",
@@ -54,7 +84,7 @@ int main(void)
}
while (max--) {
- huge_ptr = mmap(NULL, MMAP_SIZE, PROT_READ | PROT_WRITE,
+ huge_ptr = mmap(NULL, huge_page_size, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB,
-1, 0);
@@ -66,8 +96,14 @@ int main(void)
pthread_join(thread1, NULL);
pthread_join(thread2, NULL);
- munmap(huge_ptr, MMAP_SIZE);
+ munmap(huge_ptr, huge_page_size);
}
- return KSFT_PASS;
+ ksft_test_result(!sigbus_triggered, "SIGBUS behavior\n");
+
+ err = ksft_get_fail_cnt();
+ if (err)
+ ksft_exit_fail_msg("%d out of %d tests failed\n",
+ err, ksft_test_num());
+ ksft_exit_pass();
}
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index 2c5394584af4..2fc290d9430c 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -349,10 +349,12 @@ if [ $VADDR64 -ne 0 ]; then
# allows high virtual address allocation requests independent
# of platform's physical memory.
- prev_policy=$(cat /proc/sys/vm/overcommit_memory)
- echo 1 > /proc/sys/vm/overcommit_memory
- CATEGORY="hugevm" run_test ./virtual_address_range
- echo $prev_policy > /proc/sys/vm/overcommit_memory
+ if [ -x ./virtual_address_range ]; then
+ prev_policy=$(cat /proc/sys/vm/overcommit_memory)
+ echo 1 > /proc/sys/vm/overcommit_memory
+ CATEGORY="hugevm" run_test ./virtual_address_range
+ echo $prev_policy > /proc/sys/vm/overcommit_memory
+ fi
# va high address boundary switch test
ARCH_ARM64="arm64"
diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c
index 4e4c1e311247..2a2b69e91950 100644
--- a/tools/testing/selftests/mm/virtual_address_range.c
+++ b/tools/testing/selftests/mm/virtual_address_range.c
@@ -64,7 +64,7 @@
#define NR_CHUNKS_HIGH NR_CHUNKS_384TB
#endif
-static char *hind_addr(void)
+static char *hint_addr(void)
{
int bits = HIGH_ADDR_SHIFT + rand() % (63 - HIGH_ADDR_SHIFT);
@@ -185,7 +185,7 @@ int main(int argc, char *argv[])
}
for (i = 0; i < NR_CHUNKS_HIGH; i++) {
- hint = hind_addr();
+ hint = hint_addr();
hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
diff --git a/tools/testing/shared/shared.mk b/tools/testing/shared/shared.mk
index a6bc51d0b0bf..923ee2492256 100644
--- a/tools/testing/shared/shared.mk
+++ b/tools/testing/shared/shared.mk
@@ -69,6 +69,7 @@ generated/bit-length.h: FORCE
@if ! grep -qws CONFIG_$(LONG_BIT)BIT generated/bit-length.h; then \
echo "Generating $@"; \
echo "#define CONFIG_$(LONG_BIT)BIT 1" > $@; \
+ echo "#define CONFIG_PHYS_ADDR_T_$(LONG_BIT)BIT 1" >> $@; \
fi
FORCE: ;
diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c
index b33b47342d41..8fab5e13c7c3 100644
--- a/tools/testing/vma/vma.c
+++ b/tools/testing/vma/vma.c
@@ -4,6 +4,8 @@
#include <stdio.h>
#include <stdlib.h>
+#include "generated/bit-length.h"
+
#include "maple-shared.h"
#include "vma_internal.h"
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index c5b9da034511..e76ff579e1fd 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -44,7 +44,9 @@
#define VM_LOCKED 0x00002000
#define VM_IO 0x00004000
#define VM_DONTEXPAND 0x00040000
+#define VM_LOCKONFAULT 0x00080000
#define VM_ACCOUNT 0x00100000
+#define VM_NORESERVE 0x00200000
#define VM_MIXEDMAP 0x10000000
#define VM_STACK VM_GROWSDOWN
#define VM_SHADOW_STACK VM_NONE
@@ -53,6 +55,14 @@
#define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC)
#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
+/* This mask represents all the VMA flag bits used by mlock */
+#define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT)
+
+#ifdef CONFIG_64BIT
+/* VM is sealed, in vm_flags */
+#define VM_SEALED _BITUL(63)
+#endif
+
#define FIRST_USER_ADDRESS 0UL
#define USER_PGTABLES_CEILING 0UL
@@ -698,8 +708,9 @@ static inline void tlb_finish_mmu(struct mmu_gather *)
{
}
-static inline void get_file(struct file *)
+static inline struct file *get_file(struct file *f)
{
+ return f;
}
static inline int vma_dup_policy(struct vm_area_struct *, struct vm_area_struct *)
@@ -920,4 +931,106 @@ static inline bool signal_pending(void *)
return false;
}
+static inline bool is_file_hugepages(struct file *)
+{
+ return false;
+}
+
+static inline int security_vm_enough_memory_mm(struct mm_struct *, long)
+{
+ return true;
+}
+
+static inline bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long)
+{
+ return true;
+}
+
+static inline void vm_flags_init(struct vm_area_struct *vma,
+ vm_flags_t flags)
+{
+ vma->__vm_flags = flags;
+}
+
+static inline void vm_flags_set(struct vm_area_struct *vma,
+ vm_flags_t flags)
+{
+ vma_start_write(vma);
+ vma->__vm_flags |= flags;
+}
+
+static inline void vm_flags_clear(struct vm_area_struct *vma,
+ vm_flags_t flags)
+{
+ vma_start_write(vma);
+ vma->__vm_flags &= ~flags;
+}
+
+static inline int call_mmap(struct file *, struct vm_area_struct *)
+{
+ return 0;
+}
+
+static inline int shmem_zero_setup(struct vm_area_struct *)
+{
+ return 0;
+}
+
+static inline void vma_set_anonymous(struct vm_area_struct *vma)
+{
+ vma->vm_ops = NULL;
+}
+
+static inline void ksm_add_vma(struct vm_area_struct *)
+{
+}
+
+static inline void perf_event_mmap(struct vm_area_struct *)
+{
+}
+
+static inline bool vma_is_dax(struct vm_area_struct *)
+{
+ return false;
+}
+
+static inline struct vm_area_struct *get_gate_vma(struct mm_struct *)
+{
+ return NULL;
+}
+
+bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot);
+
+/* Update vma->vm_page_prot to reflect vma->vm_flags. */
+static inline void vma_set_page_prot(struct vm_area_struct *vma)
+{
+ unsigned long vm_flags = vma->vm_flags;
+ pgprot_t vm_page_prot;
+
+ /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */
+ vm_page_prot = pgprot_modify(vma->vm_page_prot, vm_get_page_prot(vm_flags));
+
+ if (vma_wants_writenotify(vma, vm_page_prot)) {
+ vm_flags &= ~VM_SHARED;
+ /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */
+ vm_page_prot = pgprot_modify(vm_page_prot, vm_get_page_prot(vm_flags));
+ }
+ /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */
+ WRITE_ONCE(vma->vm_page_prot, vm_page_prot);
+}
+
+static inline bool arch_validate_flags(unsigned long)
+{
+ return true;
+}
+
+static inline void vma_close(struct vm_area_struct *)
+{
+}
+
+static inline int mmap_file(struct file *, struct vm_area_struct *)
+{
+ return 0;
+}
+
#endif /* __MM_VMA_INTERNAL_H */
generated by cgit v1.2.3-70-g09d2 (git 2.48.1) at 2025-05-20 11:32:27 +0000