initramfs: Expose retained initrd as sysfs file

When the kernel command line option "retain_initrd" is set, we do not
free the initrd memory. However, we also don't expose it to anyone for
consumption. That leaves us in a weird situation where the only user of
this feature is ppc64 and arm64 specific kexec tooling.

To make it more generally useful, this patch adds a kobject to the
firmware object that contains the initrd context when "retain_initrd"
is set. That way, we can access the initrd any time after boot from
user space and for example hand it into kexec as --initrd parameter
if we want to reboot the same initrd. Or inspect it directly locally.

With this patch applied, there is a new /sys/firmware/initrd file when
the kernel was booted with an initrd and "retain_initrd" command line
option is set.
Signed-off-by: Alexander Graf <graf@amazon.com>
Tested-by: Bagas Sanjaya <bagasdotme@gmail.com>
Link: https://lore.kernel.org/r/20231207235654.16622-1-graf@amazon.comSigned-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Documentation/ABI/testing/sysfs-firmware-initrd

+What:		/sys/firmware/initrd
+Date:		December 2023
+Contact:	Alexander Graf <graf@amazon.com>
+Description:
+		When the kernel was booted with an initrd and the
+		"retain_initrd" option is set on the kernel command
+		line, /sys/firmware/initrd contains the contents of the
+		initrd that the kernel was booted with.

Documentation/admin-guide/kernel-parameters.txt

@@ -2438,7 +2438,7 @@
 			between unregistering the boot console and initializing
 			the real console.
 
-	keepinitrd	[HW,ARM]
+	keepinitrd	[HW,ARM] See retain_initrd.
 
 	kernelcore=	[KNL,X86,IA-64,PPC]
 			Format: nn[KMGTPE] | nn% | "mirror"
@@ -5580,7 +5580,8 @@
 			Useful for devices that are detected asynchronously
 			(e.g. USB and MMC devices).
 
-	retain_initrd	[RAM] Keep initrd memory after extraction
+	retain_initrd	[RAM] Keep initrd memory after extraction. After boot, it will
+			be accessible via /sys/firmware/initrd.
 
 	retbleed=	[X86] Control mitigation of RETBleed (Arbitrary
 			Speculative Code Execution with Return Instructions)

init/initramfs.c

@@ -574,6 +574,16 @@ extern unsigned long __initramfs_size;
 #include <linux/initrd.h>
 #include <linux/kexec.h>
 
+static ssize_t raw_read(struct file *file, struct kobject *kobj,
+			struct bin_attribute *attr, char *buf,
+			loff_t pos, size_t count)
+{
+	memcpy(buf, attr->private + pos, count);
+	return count;
+}
+
+static BIN_ATTR(initrd, 0440, raw_read, NULL, 0);
+
 void __init reserve_initrd_mem(void)
 {
 	phys_addr_t start;
@@ -715,8 +725,14 @@ static void __init do_populate_rootfs(void *unused, async_cookie_t cookie)
 	 * 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())
+	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;