[PATCH v4] initramfs: Support initrd that is bigger than 2GiB

[PATCH v4] initramfs: Support initrd that is bigger than 2GiB

[Yinghai Lu]

When initrd (compressed or not) is used, kernel report data corrupted
with /dev/ram0.

The root cause:
During initramfs checking, if it is initrd, it will be transferred to
/initrd.image with sys_write.
sys_write only support 2G-4K write, so if the initrd ram is more than
that, /initrd.image will not complete at all.

Add local xwrite to loop calling sys_write to workaround the
problem.

Also need to use xwrite in write_buffer() to handle:
image is uncompressed cpio and there is one big file (>2G) in it.
   unpack_to_rootfs ===> write_buffer ===> actions[]/do_copy

At the same time, we don't need to worry about sys_read/sys_write in
do_mounts_rd.c::crd_load. As decompressor will have fill/flush and
local buffer that is smaller than 2G.

Test with uncompressed initrd, and compressed ones with gz, bz2, lzma,xz,
lzop.

-v2: according to HPA, change name to xwrite.
-v3: change xwrite to HPA's version. The normal behavior of xwrite(),
     like fwrite() and write(), is to return the total number of bytes
     written if any bytes are written at all.
-v4: change written tyep to ssize_t according to Geert Uytterhoeven.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: H. Peter Anvin <hpa@zytor.com>

---
 init/initramfs.c |   36 ++++++++++++++++++++++++++++++++----
 1 file changed, 32 insertions(+), 4 deletions(-)

Index: linux-2.6/init/initramfs.c
===================================================================
--- linux-2.6.orig/init/initramfs.c
+++ linux-2.6/init/initramfs.c
@@ -19,6 +19,29 @@
 #include <linux/syscalls.h>
 #include <linux/utime.h>
 
+static ssize_t __init xwrite(int fd, const char *p, size_t count)
+{
+	ssize_t out = 0;
+
+	/* sys_write only can write MAX_RW_COUNT aka 2G-4K bytes at most */
+	while (count) {
+		ssize_t rv = sys_write(fd, p, count);
+
+		if (rv < 0) {
+			if (rv == -EINTR || rv == -EAGAIN)
+				continue;
+			return out ? out : rv;
+		} else if (rv == 0)
+			break;
+
+		p += rv;
+		out += rv;
+		count -= rv;
+	}
+
+	return out;
+}
+
 static __initdata char *message;
 static void __init error(char *x)
 {
@@ -346,7 +369,7 @@ static int __init do_name(void)
 static int __init do_copy(void)
 {
 	if (count >= body_len) {
-		sys_write(wfd, victim, body_len);
+		xwrite(wfd, victim, body_len);
 		sys_close(wfd);
 		do_utime(vcollected, mtime);
 		kfree(vcollected);
@@ -354,7 +377,7 @@ static int __init do_copy(void)
 		state = SkipIt;
 		return 0;
 	} else {
-		sys_write(wfd, victim, count);
+		xwrite(wfd, victim, count);
 		body_len -= count;
 		eat(count);
 		return 1;
@@ -603,8 +626,13 @@ static int __init populate_rootfs(void)
 		fd = sys_open("/initrd.image",
 			      O_WRONLY|O_CREAT, 0700);
 		if (fd >= 0) {
-			sys_write(fd, (char *)initrd_start,
-					initrd_end - initrd_start);
+			ssize_t written = xwrite(fd, (char *)initrd_start,
+						initrd_end - initrd_start);
+
+			if (written != initrd_end - initrd_start)
+				pr_err("/initrd.image: incomplete write (%zd != %ld)\n",
+				       written, initrd_end - initrd_start);
+
 			sys_close(fd);
 			free_initrd();
 		}