Resguardo inicial

linux-7.2.3/tools/testing/selftests/memfd/.gitignore

@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
+fuse_mnt
+fuse_test
+memfd_test
+memfd-test-file

linux-7.2.3/tools/testing/selftests/memfd/Makefile

@@ -0,0 +1,28 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -D_FILE_OFFSET_BITS=64
+CFLAGS += $(KHDR_INCLUDES)
+
+TEST_GEN_PROGS := memfd_test
+TEST_PROGS := run_fuse_test.sh run_hugetlbfs_test.sh
+TEST_GEN_FILES := fuse_test fuse_mnt
+
+VAR_CFLAGS := $(shell pkg-config fuse --cflags 2>/dev/null)
+ifeq ($(VAR_CFLAGS),)
+VAR_CFLAGS := -D_FILE_OFFSET_BITS=64 -I/usr/include/fuse
+endif
+
+VAR_LDLIBS := $(shell pkg-config fuse --libs 2>/dev/null)
+ifeq ($(VAR_LDLIBS),)
+VAR_LDLIBS := -lfuse -pthread
+endif
+
+fuse_mnt.o: CFLAGS += $(VAR_CFLAGS)
+
+include ../lib.mk
+
+$(OUTPUT)/fuse_mnt: LDLIBS += $(VAR_LDLIBS)
+
+$(OUTPUT)/memfd_test: memfd_test.c common.c
+$(OUTPUT)/fuse_test: fuse_test.c common.c
+
+EXTRA_CLEAN = $(OUTPUT)/common.o

linux-7.2.3/tools/testing/selftests/memfd/common.c

@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#define __EXPORTED_HEADERS__
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <linux/fcntl.h>
+#include <linux/memfd.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+
+#include "common.h"
+
+int hugetlbfs_test = 0;
+
+/*
+ * Copied from mlock2-tests.c
+ */
+unsigned long default_huge_page_size(void)
+{
+	unsigned long hps = 0;
+	char *line = NULL;
+	size_t linelen = 0;
+	FILE *f = fopen("/proc/meminfo", "r");
+
+	if (!f)
+		return 0;
+	while (getline(&line, &linelen, f) > 0) {
+		if (sscanf(line, "Hugepagesize:       %lu kB", &hps) == 1) {
+			hps <<= 10;
+			break;
+		}
+	}
+
+	free(line);
+	fclose(f);
+	return hps;
+}
+
+int sys_memfd_create(const char *name, unsigned int flags)
+{
+	if (hugetlbfs_test)
+		flags |= MFD_HUGETLB;
+
+	return syscall(__NR_memfd_create, name, flags);
+}

linux-7.2.3/tools/testing/selftests/memfd/common.h

@@ -0,0 +1,9 @@
+#ifndef COMMON_H_
+#define COMMON_H_
+
+extern int hugetlbfs_test;
+
+unsigned long default_huge_page_size(void);
+int sys_memfd_create(const char *name, unsigned int flags);
+
+#endif

linux-7.2.3/tools/testing/selftests/memfd/config

@@ -0,0 +1 @@
+CONFIG_FUSE_FS=m

linux-7.2.3/tools/testing/selftests/memfd/fuse_mnt.c

@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * memfd test file-system
+ * This file uses FUSE to create a dummy file-system with only one file /memfd.
+ * This file is read-only and takes 1s per read.
+ *
+ * This file-system is used by the memfd test-cases to force the kernel to pin
+ * pages during reads(). Due to the 1s delay of this file-system, this is a
+ * nice way to test race-conditions against get_user_pages() in the kernel.
+ *
+ * We use direct_io==1 to force the kernel to use direct-IO for this
+ * file-system.
+ */
+
+#define FUSE_USE_VERSION 26
+
+#include <fuse.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <unistd.h>
+
+static const char memfd_content[] = "memfd-example-content";
+static const char memfd_path[] = "/memfd";
+
+static int memfd_getattr(const char *path, struct stat *st)
+{
+	memset(st, 0, sizeof(*st));
+
+	if (!strcmp(path, "/")) {
+		st->st_mode = S_IFDIR | 0755;
+		st->st_nlink = 2;
+	} else if (!strcmp(path, memfd_path)) {
+		st->st_mode = S_IFREG | 0444;
+		st->st_nlink = 1;
+		st->st_size = strlen(memfd_content);
+	} else {
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+static int memfd_readdir(const char *path,
+			 void *buf,
+			 fuse_fill_dir_t filler,
+			 off_t offset,
+			 struct fuse_file_info *fi)
+{
+	if (strcmp(path, "/"))
+		return -ENOENT;
+
+	filler(buf, ".", NULL, 0);
+	filler(buf, "..", NULL, 0);
+	filler(buf, memfd_path + 1, NULL, 0);
+
+	return 0;
+}
+
+static int memfd_open(const char *path, struct fuse_file_info *fi)
+{
+	if (strcmp(path, memfd_path))
+		return -ENOENT;
+
+	if ((fi->flags & 3) != O_RDONLY)
+		return -EACCES;
+
+	/* force direct-IO */
+	fi->direct_io = 1;
+
+	return 0;
+}
+
+static int memfd_read(const char *path,
+		      char *buf,
+		      size_t size,
+		      off_t offset,
+		      struct fuse_file_info *fi)
+{
+	size_t len;
+
+	if (strcmp(path, memfd_path) != 0)
+		return -ENOENT;
+
+	sleep(1);
+
+	len = strlen(memfd_content);
+	if (offset < len) {
+		if (offset + size > len)
+			size = len - offset;
+
+		memcpy(buf, memfd_content + offset, size);
+	} else {
+		size = 0;
+	}
+
+	return size;
+}
+
+static struct fuse_operations memfd_ops = {
+	.getattr	= memfd_getattr,
+	.readdir	= memfd_readdir,
+	.open		= memfd_open,
+	.read		= memfd_read,
+};
+
+int main(int argc, char *argv[])
+{
+	return fuse_main(argc, argv, &memfd_ops, NULL);
+}

linux-7.2.3/tools/testing/selftests/memfd/fuse_test.c

@@ -0,0 +1,331 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * memfd GUP test-case
+ * This tests memfd interactions with get_user_pages(). We require the
+ * fuse_mnt.c program to provide a fake direct-IO FUSE mount-point for us. This
+ * file-system delays _all_ reads by 1s and forces direct-IO. This means, any
+ * read() on files in that file-system will pin the receive-buffer pages for at
+ * least 1s via get_user_pages().
+ *
+ * We use this trick to race ADD_SEALS against a write on a memfd object. The
+ * ADD_SEALS must fail if the memfd pages are still pinned. Note that we use
+ * the read() syscall with our memory-mapped memfd object as receive buffer to
+ * force the kernel to write into our memfd object.
+ */
+
+#define _GNU_SOURCE
+#define __EXPORTED_HEADERS__
+
+#include <errno.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <linux/falloc.h>
+#include <fcntl.h>
+#include <linux/memfd.h>
+#include <linux/types.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "common.h"
+
+#define MFD_DEF_SIZE 8192
+#define STACK_SIZE 65536
+
+static size_t mfd_def_size = MFD_DEF_SIZE;
+
+static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags)
+{
+	int r, fd;
+
+	fd = sys_memfd_create(name, flags);
+	if (fd < 0) {
+		printf("memfd_create(\"%s\", %u) failed: %m\n",
+		       name, flags);
+		abort();
+	}
+
+	r = ftruncate(fd, sz);
+	if (r < 0) {
+		printf("ftruncate(%llu) failed: %m\n", (unsigned long long)sz);
+		abort();
+	}
+
+	return fd;
+}
+
+static __u64 mfd_assert_get_seals(int fd)
+{
+	long r;
+
+	r = fcntl(fd, F_GET_SEALS);
+	if (r < 0) {
+		printf("GET_SEALS(%d) failed: %m\n", fd);
+		abort();
+	}
+
+	return r;
+}
+
+static void mfd_assert_has_seals(int fd, __u64 seals)
+{
+	__u64 s;
+
+	s = mfd_assert_get_seals(fd);
+	if (s != seals) {
+		printf("%llu != %llu = GET_SEALS(%d)\n",
+		       (unsigned long long)seals, (unsigned long long)s, fd);
+		abort();
+	}
+}
+
+static void mfd_assert_add_seals(int fd, __u64 seals)
+{
+	long r;
+	__u64 s;
+
+	s = mfd_assert_get_seals(fd);
+	r = fcntl(fd, F_ADD_SEALS, seals);
+	if (r < 0) {
+		printf("ADD_SEALS(%d, %llu -> %llu) failed: %m\n",
+		       fd, (unsigned long long)s, (unsigned long long)seals);
+		abort();
+	}
+}
+
+static int mfd_busy_add_seals(int fd, __u64 seals)
+{
+	long r;
+	__u64 s;
+
+	r = fcntl(fd, F_GET_SEALS);
+	if (r < 0)
+		s = 0;
+	else
+		s = r;
+
+	r = fcntl(fd, F_ADD_SEALS, seals);
+	if (r < 0 && errno != EBUSY) {
+		printf("ADD_SEALS(%d, %llu -> %llu) didn't fail as expected with EBUSY: %m\n",
+		       fd, (unsigned long long)s, (unsigned long long)seals);
+		abort();
+	}
+
+	return r;
+}
+
+static void *mfd_assert_mmap_shared(int fd)
+{
+	void *p;
+
+	p = mmap(NULL,
+		 mfd_def_size,
+		 PROT_READ | PROT_WRITE,
+		 MAP_SHARED,
+		 fd,
+		 0);
+	if (p == MAP_FAILED) {
+		printf("mmap() failed: %m\n");
+		abort();
+	}
+
+	return p;
+}
+
+static void *mfd_assert_mmap_private(int fd)
+{
+	void *p;
+
+	p = mmap(NULL,
+		 mfd_def_size,
+		 PROT_READ | PROT_WRITE,
+		 MAP_PRIVATE,
+		 fd,
+		 0);
+	if (p == MAP_FAILED) {
+		printf("mmap() failed: %m\n");
+		abort();
+	}
+
+	return p;
+}
+
+static int global_mfd = -1;
+static void *global_p = NULL;
+
+static int sealing_thread_fn(void *arg)
+{
+	int r;
+
+	/*
+	 * This thread first waits 200ms so any pending operation in the parent
+	 * is correctly started. After that, it tries to seal @global_mfd as
+	 * SEAL_WRITE. This _must_ fail as the parent thread has a read() into
+	 * that memory mapped object still ongoing.
+	 * We then wait one more second and try sealing again. This time it
+	 * must succeed as there shouldn't be anyone else pinning the pages.
+	 */
+
+	/* wait 200ms for FUSE-request to be active */
+	usleep(200000);
+
+	/* unmount mapping before sealing to avoid i_mmap_writable failures */
+	munmap(global_p, mfd_def_size);
+
+	/* Try sealing the global file; expect EBUSY or success. Current
+	 * kernels will never succeed, but in the future, kernels might
+	 * implement page-replacements or other fancy ways to avoid racing
+	 * writes. */
+	r = mfd_busy_add_seals(global_mfd, F_SEAL_WRITE);
+	if (r >= 0) {
+		printf("HURRAY! This kernel fixed GUP races!\n");
+	} else {
+		/* wait 1s more so the FUSE-request is done */
+		sleep(1);
+
+		/* try sealing the global file again */
+		mfd_assert_add_seals(global_mfd, F_SEAL_WRITE);
+	}
+
+	return 0;
+}
+
+static pid_t spawn_sealing_thread(void)
+{
+	uint8_t *stack;
+	pid_t pid;
+
+	stack = malloc(STACK_SIZE);
+	if (!stack) {
+		printf("malloc(STACK_SIZE) failed: %m\n");
+		abort();
+	}
+
+	pid = clone(sealing_thread_fn,
+		    stack + STACK_SIZE,
+		    SIGCHLD | CLONE_FILES | CLONE_FS | CLONE_VM,
+		    NULL);
+	if (pid < 0) {
+		printf("clone() failed: %m\n");
+		abort();
+	}
+
+	return pid;
+}
+
+static void join_sealing_thread(pid_t pid)
+{
+	waitpid(pid, NULL, 0);
+}
+
+int main(int argc, char **argv)
+{
+	char *zero;
+	int fd, mfd, r;
+	void *p;
+	int was_sealed;
+	pid_t pid;
+
+	if (argc < 2) {
+		printf("error: please pass path to file in fuse_mnt mount-point\n");
+		abort();
+	}
+
+	if (argc >= 3) {
+		if (!strcmp(argv[2], "hugetlbfs")) {
+			unsigned long hpage_size = default_huge_page_size();
+
+			if (!hpage_size) {
+				printf("Unable to determine huge page size\n");
+				abort();
+			}
+
+			hugetlbfs_test = 1;
+			mfd_def_size = hpage_size * 2;
+		} else {
+			printf("Unknown option: %s\n", argv[2]);
+			abort();
+		}
+	}
+
+	zero = calloc(sizeof(*zero), mfd_def_size);
+
+	/* open FUSE memfd file for GUP testing */
+	printf("opening: %s\n", argv[1]);
+	fd = open(argv[1], O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		printf("cannot open(\"%s\"): %m\n", argv[1]);
+		abort();
+	}
+
+	/* create new memfd-object */
+	mfd = mfd_assert_new("kern_memfd_fuse",
+			     mfd_def_size,
+			     MFD_CLOEXEC | MFD_ALLOW_SEALING);
+
+	/* mmap memfd-object for writing */
+	p = mfd_assert_mmap_shared(mfd);
+
+	/* pass mfd+mapping to a separate sealing-thread which tries to seal
+	 * the memfd objects with SEAL_WRITE while we write into it */
+	global_mfd = mfd;
+	global_p = p;
+	pid = spawn_sealing_thread();
+
+	/* Use read() on the FUSE file to read into our memory-mapped memfd
+	 * object. This races the other thread which tries to seal the
+	 * memfd-object.
+	 * If @fd is on the memfd-fake-FUSE-FS, the read() is delayed by 1s.
+	 * This guarantees that the receive-buffer is pinned for 1s until the
+	 * data is written into it. The racing ADD_SEALS should thus fail as
+	 * the pages are still pinned. */
+	r = read(fd, p, mfd_def_size);
+	if (r < 0) {
+		printf("read() failed: %m\n");
+		abort();
+	} else if (!r) {
+		printf("unexpected EOF on read()\n");
+		abort();
+	}
+
+	was_sealed = mfd_assert_get_seals(mfd) & F_SEAL_WRITE;
+
+	/* Wait for sealing-thread to finish and verify that it
+	 * successfully sealed the file after the second try. */
+	join_sealing_thread(pid);
+	mfd_assert_has_seals(mfd, F_SEAL_WRITE);
+
+	/* *IF* the memfd-object was sealed at the time our read() returned,
+	 * then the kernel did a page-replacement or canceled the read() (or
+	 * whatever magic it did..). In that case, the memfd object is still
+	 * all zero.
+	 * In case the memfd-object was *not* sealed, the read() was successful
+	 * and the memfd object must *not* be all zero.
+	 * Note that in real scenarios, there might be a mixture of both, but
+	 * in this test-cases, we have explicit 200ms delays which should be
+	 * enough to avoid any in-flight writes. */
+
+	p = mfd_assert_mmap_private(mfd);
+	if (was_sealed && memcmp(p, zero, mfd_def_size)) {
+		printf("memfd sealed during read() but data not discarded\n");
+		abort();
+	} else if (!was_sealed && !memcmp(p, zero, mfd_def_size)) {
+		printf("memfd sealed after read() but data discarded\n");
+		abort();
+	}
+
+	close(mfd);
+	close(fd);
+
+	printf("fuse: DONE\n");
+	free(zero);
+
+	return 0;
+}

linux-7.2.3/tools/testing/selftests/memfd/run_fuse_test.sh

@@ -0,0 +1,15 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+if test -d "./mnt" ; then
+	fusermount -u ./mnt
+	rmdir ./mnt
+fi
+
+set -e
+
+mkdir mnt
+./fuse_mnt ./mnt
+./fuse_test ./mnt/memfd $@
+fusermount -u ./mnt
+rmdir ./mnt

linux-7.2.3/tools/testing/selftests/memfd/run_hugetlbfs_test.sh

@@ -0,0 +1,68 @@
+#!/bin/bash
+# please run as root
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+#
+# To test memfd_create with hugetlbfs, there needs to be hpages_test
+# huge pages free.  Attempt to allocate enough pages to test.
+#
+hpages_test=8
+
+#
+# Get count of free huge pages from /proc/meminfo
+#
+while read name size unit; do
+        if [ "$name" = "HugePages_Free:" ]; then
+                freepgs=$size
+        fi
+done < /proc/meminfo
+
+#
+# If not enough free huge pages for test, attempt to increase
+#
+if [ -n "$freepgs" ] && [ $freepgs -lt $hpages_test ]; then
+	nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
+	hpages_needed=`expr $hpages_test - $freepgs`
+
+	if [ $UID != 0 ]; then
+		echo "Please run memfd with hugetlbfs test as root"
+		exit $ksft_skip
+	fi
+
+	echo 3 > /proc/sys/vm/drop_caches
+	echo $(( $hpages_needed + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
+	while read name size unit; do
+		if [ "$name" = "HugePages_Free:" ]; then
+			freepgs=$size
+		fi
+	done < /proc/meminfo
+fi
+
+#
+# If still not enough huge pages available, exit.  But, give back any huge
+# pages potentially allocated above.
+#
+if [ $freepgs -lt $hpages_test ]; then
+	# nr_hugepgs non-zero only if we attempted to increase
+	if [ -n "$nr_hugepgs" ]; then
+		echo $nr_hugepgs > /proc/sys/vm/nr_hugepages
+	fi
+	printf "Not enough huge pages available (%d < %d)\n" \
+		$freepgs $needpgs
+	exit $ksft_skip
+fi
+
+#
+# Run the hugetlbfs test
+#
+./memfd_test hugetlbfs
+./run_fuse_test.sh hugetlbfs
+
+#
+# Give back any huge pages allocated for the test
+#
+if [ -n "$nr_hugepgs" ]; then
+	echo $nr_hugepgs > /proc/sys/vm/nr_hugepages
+fi