1 files changed, 198 insertions, 124 deletions

diff --git a/init/initramfs.c b/init/initramfs.c
index 8ec1be4d7d51..2f5bfb7d7652 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/init.h>
+#include <linux/async.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -11,14 +12,23 @@
 #include <linux/utime.h>
 #include <linux/file.h>
 #include <linux/memblock.h>
+#include <linux/mm.h>
+#include <linux/namei.h>
+#include <linux/init_syscalls.h>
+#include <linux/task_work.h>
+#include <linux/umh.h>
 
-static ssize_t __init xwrite(int fd, const char *p, size_t count)
+static __initdata bool csum_present;
+static __initdata u32 io_csum;
+
+static ssize_t __init xwrite(struct file *file, const unsigned char *p,
+		size_t count, loff_t *pos)
 {
 	ssize_t out = 0;
 
 	/* sys_write only can write MAX_RW_COUNT aka 2G-4K bytes at most */
 	while (count) {
-		ssize_t rv = ksys_write(fd, p, count);
+		ssize_t rv = kernel_write(file, p, count, pos);
 
 		if (rv < 0) {
 			if (rv == -EINTR || rv == -EAGAIN)
@@ -27,6 +37,13 @@ static ssize_t __init xwrite(int fd, const char *p, size_t count)
 		} else if (rv == 0)
 			break;
 
+		if (csum_present) {
+			ssize_t i;
+
+			for (i = 0; i < rv; i++)
+				io_csum += p[i];
+		}
+
 		p += rv;
 		out += rv;
 		count -= rv;
@@ -42,6 +59,16 @@ static void __init error(char *x)
 		message = x;
 }
 
+static void panic_show_mem(const char *fmt, ...)
+{
+	va_list args;
+
+	show_mem(0, NULL);
+	va_start(args, fmt);
+	panic(fmt, args);
+	va_end(args);
+}
+
 /* link hash */
 
 #define N_ALIGN(len) ((((len) + 1) & ~3) + 2)
@@ -77,7 +104,7 @@ static char __init *find_link(int major, int minor, int ino,
 	}
 	q = kmalloc(sizeof(struct hash), GFP_KERNEL);
 	if (!q)
-		panic("can't allocate link hash entry");
+		panic_show_mem("can't allocate link hash entry");
 	q->major = major;
 	q->minor = minor;
 	q->ino = ino;
@@ -100,32 +127,36 @@ static void __init free_hash(void)
 	}
 }
 
-static long __init do_utime(char *filename, time64_t mtime)
+#ifdef CONFIG_INITRAMFS_PRESERVE_MTIME
+static void __init do_utime(char *filename, time64_t mtime)
 {
-	struct timespec64 t[2];
-
-	t[0].tv_sec = mtime;
-	t[0].tv_nsec = 0;
-	t[1].tv_sec = mtime;
-	t[1].tv_nsec = 0;
+	struct timespec64 t[2] = { { .tv_sec = mtime }, { .tv_sec = mtime } };
+	init_utimes(filename, t);
+}
 
-	return do_utimes(AT_FDCWD, filename, t, AT_SYMLINK_NOFOLLOW);
+static void __init do_utime_path(const struct path *path, time64_t mtime)
+{
+	struct timespec64 t[2] = { { .tv_sec = mtime }, { .tv_sec = mtime } };
+	vfs_utimes(path, t);
 }
 
 static __initdata LIST_HEAD(dir_list);
 struct dir_entry {
 	struct list_head list;
-	char *name;
 	time64_t mtime;
+	char name[];
 };
 
 static void __init dir_add(const char *name, time64_t mtime)
 {
-	struct dir_entry *de = kmalloc(sizeof(struct dir_entry), GFP_KERNEL);
+	size_t nlen = strlen(name) + 1;
+	struct dir_entry *de;
+
+	de = kmalloc(sizeof(struct dir_entry) + nlen, GFP_KERNEL);
 	if (!de)
-		panic("can't allocate dir_entry buffer");
+		panic_show_mem("can't allocate dir_entry buffer");
 	INIT_LIST_HEAD(&de->list);
-	de->name = kstrdup(name, GFP_KERNEL);
+	strscpy(de->name, name, nlen);
 	de->mtime = mtime;
 	list_add(&de->list, &dir_list);
 }
@@ -136,10 +167,15 @@ static void __init dir_utime(void)
 	list_for_each_entry_safe(de, tmp, &dir_list, list) {
 		list_del(&de->list);
 		do_utime(de->name, de->mtime);
-		kfree(de->name);
 		kfree(de);
 	}
 }
+#else
+static void __init do_utime(char *filename, time64_t mtime) {}
+static void __init do_utime_path(const struct path *path, time64_t mtime) {}
+static void __init dir_add(const char *name, time64_t mtime) {}
+static void __init dir_utime(void) {}
+#endif
 
 static __initdata time64_t mtime;
 
@@ -151,15 +187,16 @@ static __initdata unsigned long body_len, name_len;
 static __initdata uid_t uid;
 static __initdata gid_t gid;
 static __initdata unsigned rdev;
+static __initdata u32 hdr_csum;
 
 static void __init parse_header(char *s)
 {
-	unsigned long parsed[12];
+	unsigned long parsed[13];
 	char buf[9];
 	int i;
 
 	buf[8] = '\0';
-	for (i = 0, s += 6; i < 12; i++, s += 8) {
+	for (i = 0, s += 6; i < 13; i++, s += 8) {
 		memcpy(buf, s, 8);
 		parsed[i] = simple_strtoul(buf, NULL, 16);
 	}
@@ -174,6 +211,7 @@ static void __init parse_header(char *s)
 	minor = parsed[8];
 	rdev = new_encode_dev(MKDEV(parsed[9], parsed[10]));
 	name_len = parsed[11];
+	hdr_csum = parsed[12];
 }
 
 /* FSM */
@@ -200,7 +238,6 @@ static inline void __init eat(unsigned n)
 	byte_count -= n;
 }
 
-static __initdata char *vcollected;
 static __initdata char *collected;
 static long remains __initdata;
 static __initdata char *collect;
@@ -243,12 +280,15 @@ static int __init do_collect(void)
 
 static int __init do_header(void)
 {
-	if (memcmp(collected, "070707", 6)==0) {
-		error("incorrect cpio method used: use -H newc option");
-		return 1;
-	}
-	if (memcmp(collected, "070701", 6)) {
-		error("no cpio magic");
+	if (!memcmp(collected, "070701", 6)) {
+		csum_present = false;
+	} else if (!memcmp(collected, "070702", 6)) {
+		csum_present = true;
+	} else {
+		if (memcmp(collected, "070707", 6) == 0)
+			error("incorrect cpio method used: use -H newc option");
+		else
+			error("no cpio magic");
 		return 1;
 	}
 	parse_header(collected);
@@ -296,11 +336,12 @@ static void __init clean_path(char *path, umode_t fmode)
 {
 	struct kstat st;
 
-	if (!vfs_lstat(path, &st) && (st.mode ^ fmode) & S_IFMT) {
+	if (!init_stat(path, &st, AT_SYMLINK_NOFOLLOW) &&
+	    (st.mode ^ fmode) & S_IFMT) {
 		if (S_ISDIR(st.mode))
-			ksys_rmdir(path);
+			init_rmdir(path);
 		else
-			ksys_unlink(path);
+			init_unlink(path);
 	}
 }
 
@@ -310,13 +351,14 @@ static int __init maybe_link(void)
 		char *old = find_link(major, minor, ino, mode, collected);
 		if (old) {
 			clean_path(collected, 0);
-			return (ksys_link(old, collected) < 0) ? -1 : 1;
+			return (init_link(old, collected) < 0) ? -1 : 1;
 		}
 	}
 	return 0;
 }
 
-static __initdata int wfd;
+static __initdata struct file *wfile;
+static __initdata loff_t wfile_pos;
 
 static int __init do_name(void)
 {
@@ -333,28 +375,29 @@ static int __init do_name(void)
 			int openflags = O_WRONLY|O_CREAT;
 			if (ml != 1)
 				openflags |= O_TRUNC;
-			wfd = ksys_open(collected, openflags, mode);
-
-			if (wfd >= 0) {
-				ksys_fchown(wfd, uid, gid);
-				ksys_fchmod(wfd, mode);
-				if (body_len)
-					ksys_ftruncate(wfd, body_len);
-				vcollected = kstrdup(collected, GFP_KERNEL);
-				state = CopyFile;
-			}
+			wfile = filp_open(collected, openflags, mode);
+			if (IS_ERR(wfile))
+				return 0;
+			wfile_pos = 0;
+			io_csum = 0;
+
+			vfs_fchown(wfile, uid, gid);
+			vfs_fchmod(wfile, mode);
+			if (body_len)
+				vfs_truncate(&wfile->f_path, body_len);
+			state = CopyFile;
 		}
 	} else if (S_ISDIR(mode)) {
-		ksys_mkdir(collected, mode);
-		ksys_chown(collected, uid, gid);
-		ksys_chmod(collected, mode);
+		init_mkdir(collected, mode);
+		init_chown(collected, uid, gid, 0);
+		init_chmod(collected, mode);
 		dir_add(collected, mtime);
 	} else if (S_ISBLK(mode) || S_ISCHR(mode) ||
 		   S_ISFIFO(mode) || S_ISSOCK(mode)) {
 		if (maybe_link() == 0) {
-			ksys_mknod(collected, mode, rdev);
-			ksys_chown(collected, uid, gid);
-			ksys_chmod(collected, mode);
+			init_mknod(collected, mode, rdev);
+			init_chown(collected, uid, gid, 0);
+			init_chmod(collected, mode);
 			do_utime(collected, mtime);
 		}
 	}
@@ -364,16 +407,18 @@ static int __init do_name(void)
 static int __init do_copy(void)
 {
 	if (byte_count >= body_len) {
-		if (xwrite(wfd, victim, body_len) != body_len)
+		if (xwrite(wfile, victim, body_len, &wfile_pos) != body_len)
 			error("write error");
-		ksys_close(wfd);
-		do_utime(vcollected, mtime);
-		kfree(vcollected);
+
+		do_utime_path(&wfile->f_path, mtime);
+		fput(wfile);
+		if (csum_present && io_csum != hdr_csum)
+			error("bad data checksum");
 		eat(body_len);
 		state = SkipIt;
 		return 0;
 	} else {
-		if (xwrite(wfd, victim, byte_count) != byte_count)
+		if (xwrite(wfile, victim, byte_count, &wfile_pos) != byte_count)
 			error("write error");
 		body_len -= byte_count;
 		eat(byte_count);
@@ -385,8 +430,8 @@ static int __init do_symlink(void)
 {
 	collected[N_ALIGN(name_len) + body_len] = '\0';
 	clean_path(collected, 0);
-	ksys_symlink(collected + N_ALIGN(name_len), collected);
-	ksys_lchown(collected, uid, gid);
+	init_symlink(collected + N_ALIGN(name_len), collected);
+	init_chown(collected, uid, gid, AT_SYMLINK_NOFOLLOW);
 	do_utime(collected, mtime);
 	state = SkipIt;
 	next_state = Reset;
@@ -437,7 +482,7 @@ static long __init flush_buffer(void *bufv, unsigned long len)
 	return origLen;
 }
 
-static unsigned long my_inptr; /* index of next byte to be processed in inbuf */
+static unsigned long my_inptr __initdata; /* index of next byte to be processed in inbuf */
 
 #include <linux/decompress/generic.h>
 
@@ -453,7 +498,7 @@ static char * __init unpack_to_rootfs(char *buf, unsigned long len)
 	name_buf = kmalloc(N_ALIGN(PATH_MAX), GFP_KERNEL);
 
 	if (!header_buf || !symlink_buf || !name_buf)
-		panic("can't allocate buffers");
+		panic_show_mem("can't allocate buffers");
 
 	state = Start;
 	this_header = 0;
@@ -523,18 +568,71 @@ static int __init keepinitrd_setup(char *__unused)
 __setup("keepinitrd", keepinitrd_setup);
 #endif
 
+static bool __initdata initramfs_async = true;
+static int __init initramfs_async_setup(char *str)
+{
+	strtobool(str, &initramfs_async);
+	return 1;
+}
+__setup("initramfs_async=", initramfs_async_setup);
+
 extern char __initramfs_start[];
 extern unsigned long __initramfs_size;
 #include <linux/initrd.h>
 #include <linux/kexec.h>
 
-void __weak free_initrd_mem(unsigned long start, unsigned long end)
+void __init reserve_initrd_mem(void)
+{
+	phys_addr_t start;
+	unsigned long size;
+
+	/* Ignore the virtul address computed during device tree parsing */
+	initrd_start = initrd_end = 0;
+
+	if (!phys_initrd_size)
+		return;
+	/*
+	 * Round the memory region to page boundaries as per free_initrd_mem()
+	 * This allows us to detect whether the pages overlapping the initrd
+	 * are in use, but more importantly, reserves the entire set of pages
+	 * as we don't want these pages allocated for other purposes.
+	 */
+	start = round_down(phys_initrd_start, PAGE_SIZE);
+	size = phys_initrd_size + (phys_initrd_start - start);
+	size = round_up(size, PAGE_SIZE);
+
+	if (!memblock_is_region_memory(start, size)) {
+		pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region",
+		       (u64)start, size);
+		goto disable;
+	}
+
+	if (memblock_is_region_reserved(start, size)) {
+		pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region\n",
+		       (u64)start, size);
+		goto disable;
+	}
+
+	memblock_reserve(start, size);
+	/* Now convert initrd to virtual addresses */
+	initrd_start = (unsigned long)__va(phys_initrd_start);
+	initrd_end = initrd_start + phys_initrd_size;
+	initrd_below_start_ok = 1;
+
+	return;
+disable:
+	pr_cont(" - disabling initrd\n");
+	initrd_start = 0;
+	initrd_end = 0;
+}
+
+void __weak __init free_initrd_mem(unsigned long start, unsigned long end)
 {
 #ifdef CONFIG_ARCH_KEEP_MEMBLOCK
 	unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE);
 	unsigned long aligned_end = ALIGN(end, PAGE_SIZE);
 
-	memblock_free(__pa(aligned_start), aligned_end - aligned_start);
+	memblock_free((void *)aligned_start, aligned_end - aligned_start);
 #endif
 
 	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
@@ -542,7 +640,7 @@ void __weak free_initrd_mem(unsigned long start, unsigned long end)
 }
 
 #ifdef CONFIG_KEXEC_CORE
-static bool kexec_free_initrd(void)
+static bool __init kexec_free_initrd(void)
 {
 	unsigned long crashk_start = (unsigned long)__va(crashk_res.start);
 	unsigned long crashk_end   = (unsigned long)__va(crashk_res.end);
@@ -572,91 +670,35 @@ static inline bool kexec_free_initrd(void)
 #endif /* CONFIG_KEXEC_CORE */
 
 #ifdef CONFIG_BLK_DEV_RAM
-#define BUF_SIZE 1024
-static void __init clean_rootfs(void)
-{
-	int fd;
-	void *buf;
-	struct linux_dirent64 *dirp;
-	int num;
-
-	fd = ksys_open("/", O_RDONLY, 0);
-	WARN_ON(fd < 0);
-	if (fd < 0)
-		return;
-	buf = kzalloc(BUF_SIZE, GFP_KERNEL);
-	WARN_ON(!buf);
-	if (!buf) {
-		ksys_close(fd);
-		return;
-	}
-
-	dirp = buf;
-	num = ksys_getdents64(fd, dirp, BUF_SIZE);
-	while (num > 0) {
-		while (num > 0) {
-			struct kstat st;
-			int ret;
-
-			ret = vfs_lstat(dirp->d_name, &st);
-			WARN_ON_ONCE(ret);
-			if (!ret) {
-				if (S_ISDIR(st.mode))
-					ksys_rmdir(dirp->d_name);
-				else
-					ksys_unlink(dirp->d_name);
-			}
-
-			num -= dirp->d_reclen;
-			dirp = (void *)dirp + dirp->d_reclen;
-		}
-		dirp = buf;
-		memset(buf, 0, BUF_SIZE);
-		num = ksys_getdents64(fd, dirp, BUF_SIZE);
-	}
-
-	ksys_close(fd);
-	kfree(buf);
-}
-#else
-static inline void clean_rootfs(void)
-{
-}
-#endif /* CONFIG_BLK_DEV_RAM */
-
-#ifdef CONFIG_BLK_DEV_RAM
 static void __init populate_initrd_image(char *err)
 {
 	ssize_t written;
-	int fd;
+	struct file *file;
+	loff_t pos = 0;
 
 	unpack_to_rootfs(__initramfs_start, __initramfs_size);
 
 	printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n",
 			err);
-	fd = ksys_open("/initrd.image", O_WRONLY | O_CREAT, 0700);
-	if (fd < 0)
+	file = filp_open("/initrd.image", O_WRONLY | O_CREAT, 0700);
+	if (IS_ERR(file))
 		return;
 
-	written = xwrite(fd, (char *)initrd_start, initrd_end - initrd_start);
+	written = xwrite(file, (char *)initrd_start, initrd_end - initrd_start,
+			&pos);
 	if (written != initrd_end - initrd_start)
 		pr_err("/initrd.image: incomplete write (%zd != %ld)\n",
 		       written, initrd_end - initrd_start);
-	ksys_close(fd);
-}
-#else
-static void __init populate_initrd_image(char *err)
-{
-	printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err);
+	fput(file);
 }
 #endif /* CONFIG_BLK_DEV_RAM */
 
-static int __init populate_rootfs(void)
+static void __init do_populate_rootfs(void *unused, async_cookie_t cookie)
 {
 	/* Load the built in initramfs */
 	char *err = unpack_to_rootfs(__initramfs_start, __initramfs_size);
 	if (err)
-		panic("%s", err); /* Failed to decompress INTERNAL initramfs */
+		panic_show_mem("%s", err); /* Failed to decompress INTERNAL initramfs */
 
 	if (!initrd_start || IS_ENABLED(CONFIG_INITRAMFS_FORCE))
 		goto done;
@@ -668,8 +710,11 @@ static int __init populate_rootfs(void)
 
 	err = unpack_to_rootfs((char *)initrd_start, initrd_end - initrd_start);
 	if (err) {
-		clean_rootfs();
+#ifdef CONFIG_BLK_DEV_RAM
 		populate_initrd_image(err);
+#else
+		printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err);
+#endif
 	}
 
 done:
@@ -683,6 +728,35 @@ done:
 	initrd_end = 0;
 
 	flush_delayed_fput();
+	task_work_run();
+}
+
+static ASYNC_DOMAIN_EXCLUSIVE(initramfs_domain);
+static async_cookie_t initramfs_cookie;
+
+void wait_for_initramfs(void)
+{
+	if (!initramfs_cookie) {
+		/*
+		 * Something before rootfs_initcall wants to access
+		 * the filesystem/initramfs. Probably a bug. Make a
+		 * note, avoid deadlocking the machine, and let the
+		 * caller's access fail as it used to.
+		 */
+		pr_warn_once("wait_for_initramfs() called before rootfs_initcalls\n");
+		return;
+	}
+	async_synchronize_cookie_domain(initramfs_cookie + 1, &initramfs_domain);
+}
+EXPORT_SYMBOL_GPL(wait_for_initramfs);
+
+static int __init populate_rootfs(void)
+{
+	initramfs_cookie = async_schedule_domain(do_populate_rootfs, NULL,
+						 &initramfs_domain);
+	usermodehelper_enable();
+	if (!initramfs_async)
+		wait_for_initramfs();
 	return 0;
 }
 rootfs_initcall(populate_rootfs);