1 files changed, 391 insertions, 227 deletions

diff --git a/init/initramfs.c b/init/initramfs.c
index a67ef9dbda9d..6ddbfb17fb8f 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -1,14 +1,7 @@
-/*
- * Many of the syscalls used in this file expect some of the arguments
- * to be __user pointers not __kernel pointers.  To limit the sparse
- * noise, turn off sparse checking for this file.
- */
-#ifdef __CHECKER__
-#undef __CHECKER__
-#warning "Sparse checking disabled for this file"
-#endif
-
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/init.h>
+#include <linux/async.h>
+#include <linux/export.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -18,6 +11,52 @@
 #include <linux/dirent.h>
 #include <linux/syscalls.h>
 #include <linux/utime.h>
+#include <linux/file.h>
+#include <linux/kstrtox.h>
+#include <linux/memblock.h>
+#include <linux/mm.h>
+#include <linux/namei.h>
+#include <linux/init_syscalls.h>
+#include <linux/umh.h>
+#include <linux/security.h>
+#include <linux/overflow.h>
+
+#include "do_mounts.h"
+#include "initramfs_internal.h"
+
+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 = kernel_write(file, p, count, pos);
+
+		if (rv < 0) {
+			if (rv == -EINTR || rv == -EAGAIN)
+				continue;
+			return out ? out : rv;
+		} 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;
+	}
+
+	return out;
+}
 
 static __initdata char *message;
 static void __init error(char *x)
@@ -26,6 +65,9 @@ static void __init error(char *x)
 		message = x;
 }
 
+#define panic_show_mem(fmt, ...) \
+	({ show_mem(); panic(fmt, ##__VA_ARGS__); })
+
 /* link hash */
 
 #define N_ALIGN(len) ((((len) + 1) & ~3) + 2)
@@ -36,6 +78,7 @@ static __initdata struct hash {
 	struct hash *next;
 	char name[N_ALIGN(PATH_MAX)];
 } *head[32];
+static __initdata bool hardlink_seen;
 
 static inline int hash(int major, int minor, int ino)
 {
@@ -61,55 +104,60 @@ 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;
 	q->mode = mode;
-	strcpy(q->name, name);
+	strscpy(q->name, name);
 	q->next = NULL;
 	*p = q;
+	hardlink_seen = true;
 	return NULL;
 }
 
 static void __init free_hash(void)
 {
 	struct hash **p, *q;
-	for (p = head; p < head + 32; p++) {
+	for (p = head; hardlink_seen && p < head + 32; p++) {
 		while (*p) {
 			q = *p;
 			*p = q->next;
 			kfree(q);
 		}
 	}
+	hardlink_seen = false;
 }
 
-static long __init do_utime(char *filename, time_t mtime)
+#ifdef CONFIG_INITRAMFS_PRESERVE_MTIME
+static void __init do_utime(char *filename, time64_t mtime)
 {
-	struct timespec 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;
-	time_t mtime;
+	time64_t mtime;
+	char name[];
 };
 
-static void __init dir_add(const char *name, time_t mtime)
+static void __init dir_add(const char *name, size_t nlen, time64_t mtime)
 {
-	struct dir_entry *de = kmalloc(sizeof(struct dir_entry), GFP_KERNEL);
+	struct dir_entry *de;
+
+	de = kmalloc(struct_size(de, name, 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);
 }
@@ -120,12 +168,17 @@ 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, size_t nlen, time64_t mtime) {}
+static void __init dir_utime(void) {}
+#endif
 
-static __initdata time_t mtime;
+static __initdata time64_t mtime;
 
 /* cpio header parsing */
 
@@ -135,29 +188,28 @@ 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];
-	char buf[9];
+	unsigned long parsed[13];
 	int i;
 
-	buf[8] = '\0';
-	for (i = 0, s += 6; i < 12; i++, s += 8) {
-		memcpy(buf, s, 8);
-		parsed[i] = simple_strtoul(buf, NULL, 16);
-	}
+	for (i = 0, s += 6; i < 13; i++, s += 8)
+		parsed[i] = simple_strntoul(s, NULL, 16, 8);
+
 	ino = parsed[0];
 	mode = parsed[1];
 	uid = parsed[2];
 	gid = parsed[3];
 	nlink = parsed[4];
-	mtime = parsed[5];
+	mtime = parsed[5]; /* breaks in y2106 */
 	body_len = parsed[6];
 	major = parsed[7];
 	minor = parsed[8];
 	rdev = new_encode_dev(MKDEV(parsed[9], parsed[10]));
 	name_len = parsed[11];
+	hdr_csum = parsed[12];
 }
 
 /* FSM */
@@ -174,24 +226,23 @@ static __initdata enum state {
 } state, next_state;
 
 static __initdata char *victim;
-static __initdata unsigned count;
+static unsigned long byte_count __initdata;
 static __initdata loff_t this_header, next_header;
 
 static inline void __init eat(unsigned n)
 {
 	victim += n;
 	this_header += n;
-	count -= n;
+	byte_count -= n;
 }
 
-static __initdata char *vcollected;
 static __initdata char *collected;
-static __initdata int remains;
+static long remains __initdata;
 static __initdata char *collect;
 
 static void __init read_into(char *buf, unsigned size, enum state next)
 {
-	if (count >= size) {
+	if (byte_count >= size) {
 		collected = victim;
 		eat(size);
 		state = next;
@@ -207,15 +258,15 @@ static __initdata char *header_buf, *symlink_buf, *name_buf;
 
 static int __init do_start(void)
 {
-	read_into(header_buf, 110, GotHeader);
+	read_into(header_buf, CPIO_HDRLEN, GotHeader);
 	return 0;
 }
 
 static int __init do_collect(void)
 {
-	unsigned n = remains;
-	if (count < n)
-		n = count;
+	unsigned long n = remains;
+	if (byte_count < n)
+		n = byte_count;
 	memcpy(collect, victim, n);
 	eat(n);
 	collect += n;
@@ -227,12 +278,15 @@ 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);
@@ -257,8 +311,8 @@ static int __init do_header(void)
 
 static int __init do_skip(void)
 {
-	if (this_header + count < next_header) {
-		eat(count);
+	if (this_header + byte_count < next_header) {
+		eat(byte_count);
 		return 1;
 	} else {
 		eat(next_header - this_header);
@@ -269,41 +323,54 @@ static int __init do_skip(void)
 
 static int __init do_reset(void)
 {
-	while(count && *victim == '\0')
+	while (byte_count && *victim == '\0')
 		eat(1);
-	if (count && (this_header & 3))
+	if (byte_count && (this_header & 3))
 		error("broken padding");
 	return 1;
 }
 
-static int __init maybe_link(void)
+static void __init clean_path(char *path, umode_t fmode)
 {
-	if (nlink >= 2) {
-		char *old = find_link(major, minor, ino, mode, collected);
-		if (old)
-			return (sys_link(old, collected) < 0) ? -1 : 1;
+	struct kstat st;
+
+	if (!init_stat(path, &st, AT_SYMLINK_NOFOLLOW) &&
+	    (st.mode ^ fmode) & S_IFMT) {
+		if (S_ISDIR(st.mode))
+			init_rmdir(path);
+		else
+			init_unlink(path);
 	}
-	return 0;
 }
 
-static void __init clean_path(char *path, umode_t mode)
+static int __init maybe_link(void)
 {
-	struct stat st;
-
-	if (!sys_newlstat(path, &st) && (st.st_mode^mode) & S_IFMT) {
-		if (S_ISDIR(st.st_mode))
-			sys_rmdir(path);
-		else
-			sys_unlink(path);
+	if (nlink >= 2) {
+		char *old = find_link(major, minor, ino, mode, collected);
+		if (old) {
+			clean_path(collected, 0);
+			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)
 {
 	state = SkipIt;
 	next_state = Reset;
+
+	/* name_len > 0 && name_len <= PATH_MAX checked in do_header */
+	if (collected[name_len - 1] != '\0') {
+		pr_err("initramfs name without nulterm: %.*s\n",
+		       (int)name_len, collected);
+		error("malformed archive");
+		return 1;
+	}
+
 	if (strcmp(collected, "TRAILER!!!") == 0) {
 		free_hash();
 		return 0;
@@ -312,31 +379,32 @@ static int __init do_name(void)
 	if (S_ISREG(mode)) {
 		int ml = maybe_link();
 		if (ml >= 0) {
-			int openflags = O_WRONLY|O_CREAT;
+			int openflags = O_WRONLY|O_CREAT|O_LARGEFILE;
 			if (ml != 1)
 				openflags |= O_TRUNC;
-			wfd = sys_open(collected, openflags, mode);
-
-			if (wfd >= 0) {
-				sys_fchown(wfd, uid, gid);
-				sys_fchmod(wfd, mode);
-				if (body_len)
-					sys_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)) {
-		sys_mkdir(collected, mode);
-		sys_chown(collected, uid, gid);
-		sys_chmod(collected, mode);
-		dir_add(collected, mtime);
+		init_mkdir(collected, mode);
+		init_chown(collected, uid, gid, 0);
+		init_chmod(collected, mode);
+		dir_add(collected, name_len, mtime);
 	} else if (S_ISBLK(mode) || S_ISCHR(mode) ||
 		   S_ISFIFO(mode) || S_ISSOCK(mode)) {
 		if (maybe_link() == 0) {
-			sys_mknod(collected, mode, rdev);
-			sys_chown(collected, uid, gid);
-			sys_chmod(collected, mode);
+			init_mknod(collected, mode, rdev);
+			init_chown(collected, uid, gid, 0);
+			init_chmod(collected, mode);
 			do_utime(collected, mtime);
 		}
 	}
@@ -345,28 +413,38 @@ static int __init do_name(void)
 
 static int __init do_copy(void)
 {
-	if (count >= body_len) {
-		sys_write(wfd, victim, body_len);
-		sys_close(wfd);
-		do_utime(vcollected, mtime);
-		kfree(vcollected);
+	if (byte_count >= body_len) {
+		if (xwrite(wfile, victim, body_len, &wfile_pos) != body_len)
+			error("write error");
+
+		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 {
-		sys_write(wfd, victim, count);
-		body_len -= count;
-		eat(count);
+		if (xwrite(wfile, victim, byte_count, &wfile_pos) != byte_count)
+			error("write error");
+		body_len -= byte_count;
+		eat(byte_count);
 		return 1;
 	}
 }
 
 static int __init do_symlink(void)
 {
+	if (collected[name_len - 1] != '\0') {
+		pr_err("initramfs symlink without nulterm: %.*s\n",
+		       (int)name_len, collected);
+		error("malformed archive");
+		return 1;
+	}
 	collected[N_ALIGN(name_len) + body_len] = '\0';
 	clean_path(collected, 0);
-	sys_symlink(collected + N_ALIGN(name_len), collected);
-	sys_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;
@@ -384,21 +462,21 @@ static __initdata int (*actions[])(void) = {
 	[Reset]		= do_reset,
 };
 
-static int __init write_buffer(char *buf, unsigned len)
+static long __init write_buffer(char *buf, unsigned long len)
 {
-	count = len;
+	byte_count = len;
 	victim = buf;
 
 	while (!actions[state]())
 		;
-	return len - count;
+	return len - byte_count;
 }
 
-static int __init flush_buffer(void *bufv, unsigned len)
+static long __init flush_buffer(void *bufv, unsigned long len)
 {
-	char *buf = (char *) bufv;
-	int written;
-	int origLen = len;
+	char *buf = bufv;
+	long written;
+	long origLen = len;
 	if (message)
 		return -1;
 	while ((written = write_buffer(buf, len)) < len && !message) {
@@ -412,28 +490,41 @@ static int __init flush_buffer(void *bufv, unsigned len)
 			len -= written;
 			state = Reset;
 		} else
-			error("junk in compressed archive");
+			error("junk within compressed archive");
 	}
 	return origLen;
 }
 
-static unsigned 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>
 
-static char * __init unpack_to_rootfs(char *buf, unsigned len)
+/**
+ * unpack_to_rootfs - decompress and extract an initramfs archive
+ * @buf: input initramfs archive to extract
+ * @len: length of initramfs data to process
+ *
+ * Returns: NULL for success or an error message string
+ *
+ * This symbol shouldn't be used externally. It's available for unit tests.
+ */
+char * __init unpack_to_rootfs(char *buf, unsigned long len)
 {
-	int written, res;
+	long written;
 	decompress_fn decompress;
 	const char *compress_name;
-	static __initdata char msg_buf[64];
+	struct {
+		char header[CPIO_HDRLEN];
+		char symlink[PATH_MAX + N_ALIGN(PATH_MAX) + 1];
+		char name[N_ALIGN(PATH_MAX)];
+	} *bufs = kmalloc(sizeof(*bufs), GFP_KERNEL);
 
-	header_buf = kmalloc(110, GFP_KERNEL);
-	symlink_buf = kmalloc(PATH_MAX + N_ALIGN(PATH_MAX) + 1, GFP_KERNEL);
-	name_buf = kmalloc(N_ALIGN(PATH_MAX), GFP_KERNEL);
+	if (!bufs)
+		panic_show_mem("can't allocate buffers");
 
-	if (!header_buf || !symlink_buf || !name_buf)
-		panic("can't allocate buffers");
+	header_buf = bufs->header;
+	symlink_buf = bufs->symlink;
+	name_buf = bufs->name;
 
 	state = Start;
 	this_header = 0;
@@ -455,30 +546,28 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len)
 		}
 		this_header = 0;
 		decompress = decompress_method(buf, len, &compress_name);
+		pr_debug("Detected %s compressed data\n", compress_name);
 		if (decompress) {
-			res = decompress(buf, len, NULL, flush_buffer, NULL,
+			int res = decompress(buf, len, NULL, flush_buffer, NULL,
 				   &my_inptr, error);
 			if (res)
 				error("decompressor failed");
 		} else if (compress_name) {
-			if (!message) {
-				snprintf(msg_buf, sizeof msg_buf,
-					 "compression method %s not configured",
-					 compress_name);
-				message = msg_buf;
-			}
+			pr_err("compression method %s not configured\n",
+			       compress_name);
+			error("decompressor failed");
 		} else
-			error("junk in compressed archive");
+			error("invalid magic at start of compressed archive");
 		if (state != Reset)
-			error("junk in compressed archive");
+			error("junk at the end of compressed archive");
 		this_header = saved_offset + my_inptr;
 		buf += my_inptr;
 		len -= my_inptr;
 	}
 	dir_utime();
-	kfree(name_buf);
-	kfree(symlink_buf);
-	kfree(header_buf);
+	/* free any hardlink state collected without optional TRAILER!!! */
+	free_hash();
+	kfree(bufs);
 	return message;
 }
 
@@ -493,135 +582,210 @@ static int __init retain_initrd_param(char *str)
 }
 __setup("retain_initrd", retain_initrd_param);
 
+#ifdef CONFIG_ARCH_HAS_KEEPINITRD
+static int __init keepinitrd_setup(char *__unused)
+{
+	do_retain_initrd = 1;
+	return 1;
+}
+__setup("keepinitrd", keepinitrd_setup);
+#endif
+
+static bool __initdata initramfs_async = true;
+static int __init initramfs_async_setup(char *str)
+{
+	return kstrtobool(str, &initramfs_async) == 0;
+}
+__setup("initramfs_async=", initramfs_async_setup);
+
 extern char __initramfs_start[];
 extern unsigned long __initramfs_size;
 #include <linux/initrd.h>
 #include <linux/kexec.h>
 
-static void __init free_initrd(void)
+static BIN_ATTR(initrd, 0440, sysfs_bin_attr_simple_read, NULL, 0);
+
+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((void *)aligned_start, aligned_end - aligned_start);
+#endif
+
+	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
+			"initrd");
+}
+
+#ifdef CONFIG_CRASH_RESERVE
+static bool __init kexec_free_initrd(void)
 {
-#ifdef CONFIG_KEXEC
 	unsigned long crashk_start = (unsigned long)__va(crashk_res.start);
 	unsigned long crashk_end   = (unsigned long)__va(crashk_res.end);
-#endif
-	if (do_retain_initrd)
-		goto skip;
 
-#ifdef CONFIG_KEXEC
 	/*
 	 * If the initrd region is overlapped with crashkernel reserved region,
 	 * free only memory that is not part of crashkernel region.
 	 */
-	if (initrd_start < crashk_end && initrd_end > crashk_start) {
-		/*
-		 * Initialize initrd memory region since the kexec boot does
-		 * not do.
-		 */
-		memset((void *)initrd_start, 0, initrd_end - initrd_start);
-		if (initrd_start < crashk_start)
-			free_initrd_mem(initrd_start, crashk_start);
-		if (initrd_end > crashk_end)
-			free_initrd_mem(crashk_end, initrd_end);
-	} else
-#endif
-		free_initrd_mem(initrd_start, initrd_end);
-skip:
-	initrd_start = 0;
-	initrd_end = 0;
+	if (initrd_start >= crashk_end || initrd_end <= crashk_start)
+		return false;
+
+	/*
+	 * Initialize initrd memory region since the kexec boot does not do.
+	 */
+	memset((void *)initrd_start, 0, initrd_end - initrd_start);
+	if (initrd_start < crashk_start)
+		free_initrd_mem(initrd_start, crashk_start);
+	if (initrd_end > crashk_end)
+		free_initrd_mem(crashk_end, initrd_end);
+	return true;
+}
+#else
+static inline bool kexec_free_initrd(void)
+{
+	return false;
 }
+#endif /* CONFIG_KEXEC_CORE */
 
 #ifdef CONFIG_BLK_DEV_RAM
-#define BUF_SIZE 1024
-static void __init clean_rootfs(void)
+static void __init populate_initrd_image(char *err)
 {
-	int fd;
-	void *buf;
-	struct linux_dirent64 *dirp;
-	int num;
-
-	fd = sys_open("/", O_RDONLY, 0);
-	WARN_ON(fd < 0);
-	if (fd < 0)
-		return;
-	buf = kzalloc(BUF_SIZE, GFP_KERNEL);
-	WARN_ON(!buf);
-	if (!buf) {
-		sys_close(fd);
+	ssize_t written;
+	struct file *file;
+	loff_t pos = 0;
+
+	printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n",
+			err);
+	file = filp_open("/initrd.image", O_WRONLY|O_CREAT|O_LARGEFILE, 0700);
+	if (IS_ERR(file))
 		return;
-	}
-
-	dirp = buf;
-	num = sys_getdents64(fd, dirp, BUF_SIZE);
-	while (num > 0) {
-		while (num > 0) {
-			struct stat st;
-			int ret;
-
-			ret = sys_newlstat(dirp->d_name, &st);
-			WARN_ON_ONCE(ret);
-			if (!ret) {
-				if (S_ISDIR(st.st_mode))
-					sys_rmdir(dirp->d_name);
-				else
-					sys_unlink(dirp->d_name);
-			}
-
-			num -= dirp->d_reclen;
-			dirp = (void *)dirp + dirp->d_reclen;
-		}
-		dirp = buf;
-		memset(buf, 0, BUF_SIZE);
-		num = sys_getdents64(fd, dirp, BUF_SIZE);
-	}
 
-	sys_close(fd);
-	kfree(buf);
+	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);
+	fput(file);
 }
-#endif
+#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(err);	/* Failed to decompress INTERNAL initramfs */
-	if (initrd_start) {
-#ifdef CONFIG_BLK_DEV_RAM
-		int fd;
+		panic_show_mem("%s", err); /* Failed to decompress INTERNAL initramfs */
+
+	if (!initrd_start || IS_ENABLED(CONFIG_INITRAMFS_FORCE))
+		goto done;
+
+	if (IS_ENABLED(CONFIG_BLK_DEV_RAM))
 		printk(KERN_INFO "Trying to unpack rootfs image as initramfs...\n");
-		err = unpack_to_rootfs((char *)initrd_start,
-			initrd_end - initrd_start);
-		if (!err) {
-			free_initrd();
-			goto done;
-		} else {
-			clean_rootfs();
-			unpack_to_rootfs(__initramfs_start, __initramfs_size);
-		}
-		printk(KERN_INFO "rootfs image is not initramfs (%s)"
-				"; looks like an initrd\n", err);
-		fd = sys_open("/initrd.image",
-			      O_WRONLY|O_CREAT, 0700);
-		if (fd >= 0) {
-			sys_write(fd, (char *)initrd_start,
-					initrd_end - initrd_start);
-			sys_close(fd);
-			free_initrd();
-		}
-	done:
-#else
+	else
 		printk(KERN_INFO "Unpacking initramfs...\n");
-		err = unpack_to_rootfs((char *)initrd_start,
-			initrd_end - initrd_start);
-		if (err)
-			printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err);
-		free_initrd();
+
+	err = unpack_to_rootfs((char *)initrd_start, initrd_end - initrd_start);
+	if (err) {
+#ifdef CONFIG_BLK_DEV_RAM
+		populate_initrd_image(err);
+#else
+		printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err);
 #endif
+	}
+
+done:
+	security_initramfs_populated();
+
+	/*
+	 * If the initrd region is overlapped with crashkernel reserved region,
+	 * free only memory that is not part of crashkernel region.
+	 */
+	if (!do_retain_initrd && initrd_start && !kexec_free_initrd()) {
+		free_initrd_mem(initrd_start, initrd_end);
+	} else if (do_retain_initrd && initrd_start) {
+		bin_attr_initrd.size = initrd_end - initrd_start;
+		bin_attr_initrd.private = (void *)initrd_start;
+		if (sysfs_create_bin_file(firmware_kobj, &bin_attr_initrd))
+			pr_err("Failed to create initrd sysfs file");
+	}
+	initrd_start = 0;
+	initrd_end = 0;
+
+	init_flush_fput();
+}
+
+static ASYNC_DOMAIN_EXCLUSIVE(initramfs_domain);
+static async_cookie_t initramfs_cookie;
+
+void wait_for_initramfs(void)
+{
+	if (!initramfs_cookie) {
 		/*
-		 * Try loading default modules from initramfs.  This gives
-		 * us a chance to load before device_initcalls.
+		 * 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.
 		 */
-		load_default_modules();
+		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);