Resguardo inicial

linux-7.2.3/init/.gitignore

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+/utsversion-tmp.h

linux-7.2.3/init/.kunitconfig

@@ -0,0 +1,3 @@
+CONFIG_KUNIT=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_TEST=y

linux-7.2.3/init/Makefile

@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the linux kernel.
+#
+
+ccflags-y := -fno-function-sections -fno-data-sections
+
+obj-y                          := main.o version.o mounts.o
+ifneq ($(CONFIG_BLK_DEV_INITRD),y)
+obj-y                          += noinitramfs.o
+else
+obj-$(CONFIG_BLK_DEV_INITRD)   += initramfs.o
+endif
+obj-$(CONFIG_GENERIC_CALIBRATE_DELAY) += calibrate.o
+obj-$(CONFIG_INITRAMFS_TEST)   += initramfs_test.o
+
+obj-y                          += init_task.o
+
+mounts-y			:= do_mounts.o
+mounts-$(CONFIG_BLK_DEV_RAM)	+= do_mounts_rd.o
+mounts-$(CONFIG_BLK_DEV_INITRD)	+= do_mounts_initrd.o
+
+#
+# UTS_VERSION
+#
+
+smp-flag-$(CONFIG_SMP)			:= SMP
+preempt-flag-$(CONFIG_PREEMPT_BUILD)	:= PREEMPT
+preempt-flag-$(CONFIG_PREEMPT_DYNAMIC)	:= PREEMPT_DYNAMIC
+preempt-flag-$(CONFIG_PREEMPT_RT)	:= PREEMPT_RT
+
+build-version = $(or $(KBUILD_BUILD_VERSION), $(build-version-auto))
+build-timestamp = $(or $(KBUILD_BUILD_TIMESTAMP), $(build-timestamp-auto))
+
+# Maximum length of UTS_VERSION is 64 chars
+filechk_uts_version = \
+	utsver=$$(echo '$(pound)'"$(build-version)" $(smp-flag-y) $(preempt-flag-y) "$(build-timestamp)" | cut -b -64); \
+	echo '$(pound)'define UTS_VERSION \""$${utsver}"\"
+
+#
+# Build version.c with temporary UTS_VERSION
+#
+
+$(obj)/utsversion-tmp.h: FORCE
+	$(call filechk,uts_version)
+
+clean-files += utsversion-tmp.h
+
+$(obj)/version.o: $(obj)/utsversion-tmp.h
+CFLAGS_version.o := -include $(obj)/utsversion-tmp.h
+
+#
+# Build version-timestamp.c with final UTS_VERSION
+#
+
+include/generated/utsversion.h: build-version-auto = $(shell $(srctree)/scripts/build-version)
+include/generated/utsversion.h: build-timestamp-auto = $(shell LC_ALL=C date)
+include/generated/utsversion.h: FORCE
+	$(call filechk,uts_version)
+
+$(obj)/version-timestamp.o: include/generated/utsversion.h
+CFLAGS_version-timestamp.o := -include include/generated/utsversion.h

linux-7.2.3/init/calibrate.c

@@ -0,0 +1,319 @@
+// SPDX-License-Identifier: GPL-2.0
+/* calibrate.c: default delay calibration
+ *
+ * Excised from init/main.c
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/kstrtox.h>
+#include <linux/percpu.h>
+#include <linux/printk.h>
+#include <linux/smp.h>
+#include <linux/stddef.h>
+#include <linux/timex.h>
+
+unsigned long lpj_fine;
+unsigned long preset_lpj;
+
+static int __init lpj_setup(char *str)
+{
+	return kstrtoul(str, 0, &preset_lpj) == 0;
+}
+
+__setup("lpj=", lpj_setup);
+
+#ifdef ARCH_HAS_READ_CURRENT_TIMER
+
+/* This routine uses the read_current_timer() routine and gets the
+ * loops per jiffy directly, instead of guessing it using delay().
+ * Also, this code tries to handle non-maskable asynchronous events
+ * (like SMIs)
+ */
+#define DELAY_CALIBRATION_TICKS			((HZ < 100) ? 1 : (HZ/100))
+#define MAX_DIRECT_CALIBRATION_RETRIES		5
+
+static unsigned long calibrate_delay_direct(void)
+{
+	unsigned long pre_start, start, post_start;
+	unsigned long pre_end, end, post_end;
+	unsigned long start_jiffies;
+	unsigned long timer_rate_min, timer_rate_max;
+	unsigned long good_timer_sum = 0;
+	unsigned long good_timer_count = 0;
+	unsigned long measured_times[MAX_DIRECT_CALIBRATION_RETRIES];
+	int max = -1; /* index of measured_times with max/min values or not set */
+	int min = -1;
+	int i;
+
+	if (read_current_timer(&pre_start) < 0 )
+		return 0;
+
+	/*
+	 * A simple loop like
+	 *	while ( jiffies < start_jiffies+1)
+	 *		start = read_current_timer();
+	 * will not do. As we don't really know whether jiffy switch
+	 * happened first or timer_value was read first. And some asynchronous
+	 * event can happen between these two events introducing errors in lpj.
+	 *
+	 * So, we do
+	 * 1. pre_start <- When we are sure that jiffy switch hasn't happened
+	 * 2. check jiffy switch
+	 * 3. start <- timer value before or after jiffy switch
+	 * 4. post_start <- When we are sure that jiffy switch has happened
+	 *
+	 * Note, we don't know anything about order of 2 and 3.
+	 * Now, by looking at post_start and pre_start difference, we can
+	 * check whether any asynchronous event happened or not
+	 */
+
+	for (i = 0; i < MAX_DIRECT_CALIBRATION_RETRIES; i++) {
+		pre_start = 0;
+		read_current_timer(&start);
+		start_jiffies = jiffies;
+		while (time_before_eq(jiffies, start_jiffies + 1)) {
+			pre_start = start;
+			read_current_timer(&start);
+		}
+		read_current_timer(&post_start);
+
+		pre_end = 0;
+		end = post_start;
+		while (time_before_eq(jiffies, start_jiffies + 1 +
+					       DELAY_CALIBRATION_TICKS)) {
+			pre_end = end;
+			read_current_timer(&end);
+		}
+		read_current_timer(&post_end);
+
+		timer_rate_max = (post_end - pre_start) /
+					DELAY_CALIBRATION_TICKS;
+		timer_rate_min = (pre_end - post_start) /
+					DELAY_CALIBRATION_TICKS;
+
+		/*
+		 * If the upper limit and lower limit of the timer_rate is
+		 * >= 12.5% apart, redo calibration.
+		 */
+		if (start >= post_end)
+			printk(KERN_NOTICE "calibrate_delay_direct() ignoring "
+					"timer_rate as we had a TSC wrap around"
+					" start=%lu >=post_end=%lu\n",
+				start, post_end);
+		if (start < post_end && pre_start != 0 && pre_end != 0 &&
+		    (timer_rate_max - timer_rate_min) < (timer_rate_max >> 3)) {
+			good_timer_count++;
+			good_timer_sum += timer_rate_max;
+			measured_times[i] = timer_rate_max;
+			if (max < 0 || timer_rate_max > measured_times[max])
+				max = i;
+			if (min < 0 || timer_rate_max < measured_times[min])
+				min = i;
+		} else
+			measured_times[i] = 0;
+
+	}
+
+	/*
+	 * Find the maximum & minimum - if they differ too much throw out the
+	 * one with the largest difference from the mean and try again...
+	 */
+	while (good_timer_count > 1) {
+		unsigned long estimate;
+		unsigned long maxdiff;
+
+		/* compute the estimate */
+		estimate = (good_timer_sum/good_timer_count);
+		maxdiff = estimate >> 3;
+
+		/* if range is within 12% let's take it */
+		if ((measured_times[max] - measured_times[min]) < maxdiff)
+			return estimate;
+
+		/* ok - drop the worse value and try again... */
+		good_timer_sum = 0;
+		good_timer_count = 0;
+		if ((measured_times[max] - estimate) <
+				(estimate - measured_times[min])) {
+			printk(KERN_NOTICE "calibrate_delay_direct() dropping "
+					"min bogoMips estimate %d = %lu\n",
+				min, measured_times[min]);
+			measured_times[min] = 0;
+			min = max;
+		} else {
+			printk(KERN_NOTICE "calibrate_delay_direct() dropping "
+					"max bogoMips estimate %d = %lu\n",
+				max, measured_times[max]);
+			measured_times[max] = 0;
+			max = min;
+		}
+
+		for (i = 0; i < MAX_DIRECT_CALIBRATION_RETRIES; i++) {
+			if (measured_times[i] == 0)
+				continue;
+			good_timer_count++;
+			good_timer_sum += measured_times[i];
+			if (measured_times[i] < measured_times[min])
+				min = i;
+			if (measured_times[i] > measured_times[max])
+				max = i;
+		}
+
+	}
+
+	printk(KERN_NOTICE "calibrate_delay_direct() failed to get a good "
+	       "estimate for loops_per_jiffy.\nProbably due to long platform "
+		"interrupts. Consider using \"lpj=\" boot option.\n");
+	return 0;
+}
+#else
+static unsigned long calibrate_delay_direct(void)
+{
+	return 0;
+}
+#endif
+
+/*
+ * This is the number of bits of precision for the loops_per_jiffy.  Each
+ * time we refine our estimate after the first takes 1.5/HZ seconds, so try
+ * to start with a good estimate.
+ * For the boot cpu we can skip the delay calibration and assign it a value
+ * calculated based on the timer frequency.
+ * For the rest of the CPUs we cannot assume that the timer frequency is same as
+ * the cpu frequency, hence do the calibration for those.
+ */
+#define LPS_PREC 8
+
+static unsigned long calibrate_delay_converge(void)
+{
+	/* First stage - slowly accelerate to find initial bounds */
+	unsigned long lpj, lpj_base, ticks, loopadd, loopadd_base, chop_limit;
+	int trials = 0, band = 0, trial_in_band = 0;
+
+	lpj = (1<<12);
+
+	/* wait for "start of" clock tick */
+	ticks = jiffies;
+	while (ticks == jiffies)
+		; /* nothing */
+	/* Go .. */
+	ticks = jiffies;
+	do {
+		if (++trial_in_band == (1<<band)) {
+			++band;
+			trial_in_band = 0;
+		}
+		__delay(lpj * band);
+		trials += band;
+	} while (ticks == jiffies);
+	/*
+	 * We overshot, so retreat to a clear underestimate. Then estimate
+	 * the largest likely undershoot. This defines our chop bounds.
+	 */
+	trials -= band;
+	loopadd_base = lpj * band;
+	lpj_base = lpj * trials;
+
+recalibrate:
+	lpj = lpj_base;
+	loopadd = loopadd_base;
+
+	/*
+	 * Do a binary approximation to get lpj set to
+	 * equal one clock (up to LPS_PREC bits)
+	 */
+	chop_limit = lpj >> LPS_PREC;
+	while (loopadd > chop_limit) {
+		lpj += loopadd;
+		ticks = jiffies;
+		while (ticks == jiffies)
+			; /* nothing */
+		ticks = jiffies;
+		__delay(lpj);
+		if (jiffies != ticks)	/* longer than 1 tick */
+			lpj -= loopadd;
+		loopadd >>= 1;
+	}
+	/*
+	 * If we incremented every single time possible, presume we've
+	 * massively underestimated initially, and retry with a higher
+	 * start, and larger range. (Only seen on x86_64, due to SMIs)
+	 */
+	if (lpj + loopadd * 2 == lpj_base + loopadd_base * 2) {
+		lpj_base = lpj;
+		loopadd_base <<= 2;
+		goto recalibrate;
+	}
+
+	return lpj;
+}
+
+static DEFINE_PER_CPU(unsigned long, cpu_loops_per_jiffy) = { 0 };
+
+/*
+ * Check if cpu calibration delay is already known. For example,
+ * some processors with multi-core sockets may have all cores
+ * with the same calibration delay.
+ *
+ * Architectures should override this function if a faster calibration
+ * method is available.
+ */
+unsigned long __attribute__((weak)) calibrate_delay_is_known(void)
+{
+	return 0;
+}
+
+/*
+ * Indicate the cpu delay calibration is done. This can be used by
+ * architectures to stop accepting delay timer registrations after this point.
+ */
+
+void __attribute__((weak)) calibration_delay_done(void)
+{
+}
+
+void calibrate_delay(void)
+{
+	unsigned long lpj;
+	static bool printed;
+	int this_cpu = smp_processor_id();
+
+	if (per_cpu(cpu_loops_per_jiffy, this_cpu)) {
+		lpj = per_cpu(cpu_loops_per_jiffy, this_cpu);
+		if (!printed)
+			pr_info("Calibrating delay loop (skipped) "
+				"already calibrated this CPU");
+	} else if (preset_lpj) {
+		lpj = preset_lpj;
+		if (!printed)
+			pr_info("Calibrating delay loop (skipped) "
+				"preset value.. ");
+	} else if ((!printed) && lpj_fine) {
+		lpj = lpj_fine;
+		pr_info("Calibrating delay loop (skipped), "
+			"value calculated using timer frequency.. ");
+	} else if ((lpj = calibrate_delay_is_known())) {
+		;
+	} else if ((lpj = calibrate_delay_direct()) != 0) {
+		if (!printed)
+			pr_info("Calibrating delay using timer "
+				"specific routine.. ");
+	} else {
+		if (!printed)
+			pr_info("Calibrating delay loop... ");
+		lpj = calibrate_delay_converge();
+	}
+	per_cpu(cpu_loops_per_jiffy, this_cpu) = lpj;
+	if (!printed)
+		pr_cont("%lu.%02lu BogoMIPS (lpj=%lu)\n",
+			lpj/(500000/HZ),
+			(lpj/(5000/HZ)) % 100, lpj);
+
+	loops_per_jiffy = lpj;
+	printed = true;
+
+	calibration_delay_done();
+}

linux-7.2.3/init/do_mounts.c

@@ -0,0 +1,520 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/ctype.h>
+#include <linux/fd.h>
+#include <linux/tty.h>
+#include <linux/suspend.h>
+#include <linux/root_dev.h>
+#include <linux/security.h>
+#include <linux/delay.h>
+#include <linux/mount.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/initrd.h>
+#include <linux/async.h>
+#include <linux/fs_struct.h>
+#include <linux/slab.h>
+#include <linux/ramfs.h>
+#include <linux/shmem_fs.h>
+#include <linux/ktime.h>
+
+#include <linux/nfs_fs.h>
+#include <linux/nfs_fs_sb.h>
+#include <linux/nfs_mount.h>
+#include <linux/raid/detect.h>
+#include <uapi/linux/mount.h>
+
+#include "do_mounts.h"
+
+int root_mountflags = MS_RDONLY | MS_SILENT;
+static char __initdata saved_root_name[64];
+static int root_wait;
+
+dev_t ROOT_DEV;
+
+static int __init readonly(char *str)
+{
+	if (*str)
+		return 0;
+	root_mountflags |= MS_RDONLY;
+	return 1;
+}
+
+static int __init readwrite(char *str)
+{
+	if (*str)
+		return 0;
+	root_mountflags &= ~MS_RDONLY;
+	return 1;
+}
+
+__setup("ro", readonly);
+__setup("rw", readwrite);
+
+static int __init root_dev_setup(char *line)
+{
+	strscpy(saved_root_name, line, sizeof(saved_root_name));
+	return 1;
+}
+
+__setup("root=", root_dev_setup);
+
+static int __init rootwait_setup(char *str)
+{
+	if (*str)
+		return 0;
+	root_wait = -1;
+	return 1;
+}
+
+__setup("rootwait", rootwait_setup);
+
+static int __init rootwait_timeout_setup(char *str)
+{
+	int sec;
+
+	if (kstrtoint(str, 0, &sec) || sec < 0) {
+		pr_warn("ignoring invalid rootwait value\n");
+		goto ignore;
+	}
+
+	if (check_mul_overflow(sec, MSEC_PER_SEC, &root_wait)) {
+		pr_warn("ignoring excessive rootwait value\n");
+		goto ignore;
+	}
+
+	return 1;
+
+ignore:
+	/* Fallback to indefinite wait */
+	root_wait = -1;
+
+	return 1;
+}
+
+__setup("rootwait=", rootwait_timeout_setup);
+
+static char * __initdata root_mount_data;
+static int __init root_data_setup(char *str)
+{
+	root_mount_data = str;
+	return 1;
+}
+
+static char * __initdata root_fs_names;
+static int __init fs_names_setup(char *str)
+{
+	root_fs_names = str;
+	return 1;
+}
+
+static unsigned int __initdata root_delay;
+static int __init root_delay_setup(char *str)
+{
+	if (kstrtouint(str, 0, &root_delay))
+		return 0;
+	return 1;
+}
+
+__setup("rootflags=", root_data_setup);
+__setup("rootfstype=", fs_names_setup);
+__setup("rootdelay=", root_delay_setup);
+
+/* This can return zero length strings. Caller should check */
+static int __init split_fs_names(char *page, size_t size)
+{
+	int count = 1;
+	char *p = page;
+
+	strscpy(p, root_fs_names, size);
+	while (*p++) {
+		if (p[-1] == ',') {
+			p[-1] = '\0';
+			count++;
+		}
+	}
+
+	return count;
+}
+
+static int __init do_mount_root(const char *name, const char *fs,
+				 const int flags, const void *data)
+{
+	struct super_block *s;
+	char *data_page = NULL;
+	int ret;
+
+	if (data) {
+		/* init_mount() requires a full page as fifth argument */
+		data_page = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		if (!data_page)
+			return -ENOMEM;
+		strscpy_pad(data_page, data, PAGE_SIZE);
+	}
+
+	ret = init_mount(name, "/root", fs, flags, data_page);
+	if (ret)
+		goto out;
+
+	init_chdir("/root");
+	s = current->fs->pwd.dentry->d_sb;
+	ROOT_DEV = s->s_dev;
+	printk(KERN_INFO
+	       "VFS: Mounted root (%s filesystem)%s on device %u:%u.\n",
+	       s->s_type->name,
+	       sb_rdonly(s) ? " readonly" : "",
+	       MAJOR(ROOT_DEV), MINOR(ROOT_DEV));
+
+out:
+	kfree(data_page);
+	return ret;
+}
+
+void __init mount_root_generic(char *name, char *pretty_name, int flags)
+{
+	char *fs_names = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	char *p;
+	char b[BDEVNAME_SIZE];
+	int num_fs, i;
+
+	if (!fs_names)
+		panic("VFS: Unable to mount root fs: not enough memory");
+
+	scnprintf(b, BDEVNAME_SIZE, "unknown-block(%u,%u)",
+		  MAJOR(ROOT_DEV), MINOR(ROOT_DEV));
+	if (root_fs_names)
+		num_fs = split_fs_names(fs_names, PAGE_SIZE);
+	else
+		num_fs = list_bdev_fs_names(fs_names, PAGE_SIZE);
+retry:
+	for (i = 0, p = fs_names; i < num_fs; i++, p += strlen(p)+1) {
+		int err;
+
+		if (!*p)
+			continue;
+		err = do_mount_root(name, p, flags, root_mount_data);
+		switch (err) {
+			case 0:
+				goto out;
+			case -EACCES:
+			case -EINVAL:
+#ifdef CONFIG_BLOCK
+				init_flush_fput();
+#endif
+				continue;
+		}
+	        /*
+		 * Allow the user to distinguish between failed sys_open
+		 * and bad superblock on root device.
+		 * and give them a list of the available devices
+		 */
+		printk("VFS: Cannot open root device \"%s\" or %s: error %d\n",
+				pretty_name, b, err);
+		printk("Please append a correct \"root=\" boot option; here are the available partitions:\n");
+		printk_all_partitions();
+
+		if (root_fs_names)
+			num_fs = list_bdev_fs_names(fs_names, PAGE_SIZE);
+		if (!num_fs)
+			pr_err("Can't find any bdev filesystem to be used for mount!\n");
+		else {
+			pr_err("List of all bdev filesystems:\n");
+			for (i = 0, p = fs_names; i < num_fs; i++, p += strlen(p)+1)
+				pr_err(" %s", p);
+			pr_err("\n");
+		}
+
+		panic("VFS: Unable to mount root fs on %s", b);
+	}
+	if (!(flags & SB_RDONLY)) {
+		flags |= SB_RDONLY;
+		goto retry;
+	}
+
+	printk("List of all partitions:\n");
+	printk_all_partitions();
+	printk("No filesystem could mount root, tried: ");
+	for (i = 0, p = fs_names; i < num_fs; i++, p += strlen(p)+1)
+		printk(" %s", p);
+	printk("\n");
+	panic("VFS: Unable to mount root fs on \"%s\" or %s", pretty_name, b);
+out:
+	kfree(fs_names);
+}
+ 
+#ifdef CONFIG_ROOT_NFS
+
+#define NFSROOT_TIMEOUT_MIN	5
+#define NFSROOT_TIMEOUT_MAX	30
+#define NFSROOT_RETRY_MAX	5
+
+static void __init mount_nfs_root(void)
+{
+	char *root_dev, *root_data;
+	unsigned int timeout;
+	int try;
+
+	if (nfs_root_data(&root_dev, &root_data))
+		goto fail;
+
+	/*
+	 * The server or network may not be ready, so try several
+	 * times.  Stop after a few tries in case the client wants
+	 * to fall back to other boot methods.
+	 */
+	timeout = NFSROOT_TIMEOUT_MIN;
+	for (try = 1; ; try++) {
+		if (!do_mount_root(root_dev, "nfs", root_mountflags, root_data))
+			return;
+		if (try > NFSROOT_RETRY_MAX)
+			break;
+
+		/* Wait, in case the server refused us immediately */
+		ssleep(timeout);
+		timeout <<= 1;
+		if (timeout > NFSROOT_TIMEOUT_MAX)
+			timeout = NFSROOT_TIMEOUT_MAX;
+	}
+fail:
+	pr_err("VFS: Unable to mount root fs via NFS.\n");
+}
+#else
+static inline void mount_nfs_root(void)
+{
+}
+#endif /* CONFIG_ROOT_NFS */
+
+#ifdef CONFIG_CIFS_ROOT
+
+#define CIFSROOT_TIMEOUT_MIN	5
+#define CIFSROOT_TIMEOUT_MAX	30
+#define CIFSROOT_RETRY_MAX	5
+
+static void __init mount_cifs_root(void)
+{
+	char *root_dev, *root_data;
+	unsigned int timeout;
+	int try;
+
+	if (cifs_root_data(&root_dev, &root_data))
+		goto fail;
+
+	timeout = CIFSROOT_TIMEOUT_MIN;
+	for (try = 1; ; try++) {
+		if (!do_mount_root(root_dev, "cifs", root_mountflags,
+				   root_data))
+			return;
+		if (try > CIFSROOT_RETRY_MAX)
+			break;
+
+		ssleep(timeout);
+		timeout <<= 1;
+		if (timeout > CIFSROOT_TIMEOUT_MAX)
+			timeout = CIFSROOT_TIMEOUT_MAX;
+	}
+fail:
+	pr_err("VFS: Unable to mount root fs via SMB.\n");
+}
+#else
+static inline void mount_cifs_root(void)
+{
+}
+#endif /* CONFIG_CIFS_ROOT */
+
+static bool __init fs_is_nodev(char *fstype)
+{
+	struct file_system_type *fs = get_fs_type(fstype);
+	bool ret = false;
+
+	if (fs) {
+		ret = !(fs->fs_flags & FS_REQUIRES_DEV);
+		put_filesystem(fs);
+	}
+
+	return ret;
+}
+
+static int __init mount_nodev_root(char *root_device_name)
+{
+	char *fs_names, *fstype;
+	int err = -EINVAL;
+	int num_fs, i;
+
+	fs_names = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!fs_names)
+		return -EINVAL;
+	num_fs = split_fs_names(fs_names, PAGE_SIZE);
+
+	for (i = 0, fstype = fs_names; i < num_fs;
+	     i++, fstype += strlen(fstype) + 1) {
+		if (!*fstype)
+			continue;
+		if (!fs_is_nodev(fstype))
+			continue;
+		err = do_mount_root(root_device_name, fstype, root_mountflags,
+				    root_mount_data);
+		if (!err)
+			break;
+	}
+
+	kfree(fs_names);
+	return err;
+}
+
+#ifdef CONFIG_BLOCK
+static void __init mount_block_root(char *root_device_name)
+{
+	int err = create_dev("/dev/root", ROOT_DEV);
+
+	if (err < 0)
+		pr_emerg("Failed to create /dev/root: %d\n", err);
+	mount_root_generic("/dev/root", root_device_name, root_mountflags);
+}
+#else
+static inline void mount_block_root(char *root_device_name)
+{
+}
+#endif /* CONFIG_BLOCK */
+
+void __init mount_root(char *root_device_name)
+{
+	switch (ROOT_DEV) {
+	case Root_NFS:
+		mount_nfs_root();
+		break;
+	case Root_CIFS:
+		mount_cifs_root();
+		break;
+	case Root_Generic:
+		mount_root_generic(root_device_name, root_device_name,
+				   root_mountflags);
+		break;
+	case 0:
+		if (root_device_name && root_fs_names &&
+		    mount_nodev_root(root_device_name) == 0)
+			break;
+		fallthrough;
+	default:
+		mount_block_root(root_device_name);
+		break;
+	}
+}
+
+/* wait for any asynchronous scanning to complete */
+static void __init wait_for_root(char *root_device_name)
+{
+	ktime_t end;
+
+	if (ROOT_DEV != 0)
+		return;
+
+	pr_info("Waiting for root device %s...\n", root_device_name);
+
+	end = ktime_add_ms(ktime_get_raw(), root_wait);
+
+	while (!driver_probe_done() ||
+	       early_lookup_bdev(root_device_name, &ROOT_DEV) < 0) {
+		msleep(5);
+		if (root_wait > 0 && ktime_after(ktime_get_raw(), end))
+			break;
+	}
+
+	async_synchronize_full();
+
+}
+
+static dev_t __init parse_root_device(char *root_device_name)
+{
+	int error;
+	dev_t dev;
+
+	if (!strncmp(root_device_name, "mtd", 3) ||
+	    !strncmp(root_device_name, "ubi", 3))
+		return Root_Generic;
+	if (strcmp(root_device_name, "/dev/nfs") == 0)
+		return Root_NFS;
+	if (strcmp(root_device_name, "/dev/cifs") == 0)
+		return Root_CIFS;
+	if (strcmp(root_device_name, "/dev/ram") == 0)
+		return Root_RAM0;
+
+	error = early_lookup_bdev(root_device_name, &dev);
+	if (error) {
+		if (error == -EINVAL && root_wait) {
+			pr_err("Disabling rootwait; root= is invalid.\n");
+			root_wait = 0;
+		}
+		return 0;
+	}
+	return dev;
+}
+
+/*
+ * Prepare the namespace - decide what/where to mount, load ramdisks, etc.
+ */
+void __init prepare_namespace(void)
+{
+	if (root_delay) {
+		printk(KERN_INFO "Waiting %d sec before mounting root device...\n",
+		       root_delay);
+		ssleep(root_delay);
+	}
+
+	/*
+	 * wait for the known devices to complete their probing
+	 *
+	 * Note: this is a potential source of long boot delays.
+	 * For example, it is not atypical to wait 5 seconds here
+	 * for the touchpad of a laptop to initialize.
+	 */
+	wait_for_device_probe();
+
+	md_run_setup();
+
+	if (saved_root_name[0])
+		ROOT_DEV = parse_root_device(saved_root_name);
+
+	initrd_load();
+
+	if (root_wait)
+		wait_for_root(saved_root_name);
+	mount_root(saved_root_name);
+	devtmpfs_mount();
+
+	if (init_pivot_root(".", ".")) {
+		pr_err("VFS: Failed to pivot into new rootfs\n");
+		return;
+	}
+	if (init_umount(".", MNT_DETACH)) {
+		pr_err("VFS: Failed to unmount old rootfs\n");
+		return;
+	}
+	pr_info("VFS: Pivoted into new rootfs\n");
+}
+
+static bool is_tmpfs;
+static int rootfs_init_fs_context(struct fs_context *fc)
+{
+	if (IS_ENABLED(CONFIG_TMPFS) && is_tmpfs)
+		return shmem_init_fs_context(fc);
+
+	return ramfs_init_fs_context(fc);
+}
+
+struct file_system_type rootfs_fs_type = {
+	.name		= "rootfs",
+	.init_fs_context = rootfs_init_fs_context,
+	.kill_sb	= kill_anon_super,
+};
+
+void __init init_rootfs(void)
+{
+	if (IS_ENABLED(CONFIG_TMPFS)) {
+		if (!saved_root_name[0] && !root_fs_names)
+			is_tmpfs = true;
+		else if (root_fs_names && !!strstr(root_fs_names, "tmpfs"))
+			is_tmpfs = true;
+	}
+}

linux-7.2.3/init/do_mounts.h

@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/init.h>
+#include <linux/syscalls.h>
+#include <linux/unistd.h>
+#include <linux/slab.h>
+#include <linux/mount.h>
+#include <linux/major.h>
+#include <linux/root_dev.h>
+#include <linux/init_syscalls.h>
+#include <linux/task_work.h>
+#include <linux/file.h>
+
+void  mount_root_generic(char *name, char *pretty_name, int flags);
+void  mount_root(char *root_device_name);
+extern int root_mountflags;
+
+static inline __init int create_dev(char *name, dev_t dev)
+{
+	init_unlink(name);
+	return init_mknod(name, S_IFBLK | 0600, new_encode_dev(dev));
+}
+
+#ifdef CONFIG_BLK_DEV_RAM
+int __init rd_load_image(void);
+#else
+static inline int rd_load_image(void) { return 0; }
+#endif
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void __init initrd_load(void);
+#else
+static inline void initrd_load(void) { }
+#endif
+
+/* Ensure that async file closing finished to prevent spurious errors. */
+static inline void init_flush_fput(void)
+{
+	flush_delayed_fput();
+	task_work_run();
+}

linux-7.2.3/init/do_mounts_initrd.c

@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/unistd.h>
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/initrd.h>
+
+#include "do_mounts.h"
+
+unsigned long initrd_start, initrd_end;
+int initrd_below_start_ok;
+static int __initdata mount_initrd = 1;
+
+phys_addr_t phys_initrd_start __initdata;
+unsigned long phys_initrd_size __initdata;
+
+static int __init no_initrd(char *str)
+{
+	pr_warn("noinitrd option is deprecated and will be removed soon\n");
+	mount_initrd = 0;
+	return 1;
+}
+
+__setup("noinitrd", no_initrd);
+
+static int __init early_initrdmem(char *p)
+{
+	phys_addr_t start;
+	unsigned long size;
+	char *endp;
+
+	start = memparse(p, &endp);
+	if (*endp == ',') {
+		size = memparse(endp + 1, NULL);
+
+		phys_initrd_start = start;
+		phys_initrd_size = size;
+	}
+	return 0;
+}
+early_param("initrdmem", early_initrdmem);
+
+static int __init early_initrd(char *p)
+{
+	return early_initrdmem(p);
+}
+early_param("initrd", early_initrd);
+
+void __init initrd_load(void)
+{
+	if (mount_initrd) {
+		create_dev("/dev/ram", Root_RAM0);
+		/*
+		 * Load the initrd data into /dev/ram0.
+		 */
+		if (rd_load_image()) {
+			pr_warn("using deprecated initrd support, will be removed in January 2027; "
+				"use initramfs instead or (as a last resort) /sys/firmware/initrd; "
+				"see section \"Workaround\" in "
+				"https://lore.kernel.org/lkml/20251010094047.3111495-1-safinaskar@gmail.com\n");
+		}
+	}
+	init_unlink("/initrd.image");
+}

linux-7.2.3/init/do_mounts_rd.c

@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/minix_fs.h>
+#include <linux/ext2_fs.h>
+#include <linux/romfs_fs.h>
+#include <uapi/linux/cramfs_fs.h>
+#include <linux/initrd.h>
+#include <linux/string.h>
+#include <linux/string_choices.h>
+#include <linux/slab.h>
+
+#include "do_mounts.h"
+#include "../fs/squashfs/squashfs_fs.h"
+
+#include <linux/decompress/generic.h>
+
+static struct file *in_file, *out_file;
+static loff_t in_pos, out_pos;
+
+int __initdata rd_image_start;		/* starting block # of image */
+
+static int __init ramdisk_start_setup(char *str)
+{
+	pr_warn("ramdisk_start= option is deprecated and will be removed soon\n");
+	return kstrtoint(str, 0, &rd_image_start) == 0;
+}
+__setup("ramdisk_start=", ramdisk_start_setup);
+
+static int __init crd_load(decompress_fn deco);
+
+/*
+ * This routine tries to find a RAM disk image to load, and returns the
+ * number of blocks to read for a non-compressed image, 0 if the image
+ * is a compressed image, and -1 if an image with the right magic
+ * numbers could not be found.
+ *
+ * We currently check for the following magic numbers:
+ *	minix
+ *	ext2
+ *	romfs
+ *	cramfs
+ *	squashfs
+ *	gzip
+ *	bzip2
+ *	lzma
+ *	xz
+ *	lzo
+ *	lz4
+ */
+static int __init
+identify_ramdisk_image(struct file *file, loff_t pos,
+		decompress_fn *decompressor)
+{
+	const int size = 512;
+	struct minix_super_block *minixsb;
+	struct romfs_super_block *romfsb;
+	struct cramfs_super *cramfsb;
+	struct squashfs_super_block *squashfsb;
+	int nblocks = -1;
+	unsigned char *buf;
+	const char *compress_name;
+	unsigned long n;
+	int start_block = rd_image_start;
+
+	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	minixsb = (struct minix_super_block *) buf;
+	romfsb = (struct romfs_super_block *) buf;
+	cramfsb = (struct cramfs_super *) buf;
+	squashfsb = (struct squashfs_super_block *) buf;
+	memset(buf, 0xe5, size);
+
+	/*
+	 * Read block 0 to test for compressed kernel
+	 */
+	pos = start_block * BLOCK_SIZE;
+	kernel_read(file, buf, size, &pos);
+
+	*decompressor = decompress_method(buf, size, &compress_name);
+	if (compress_name) {
+		printk(KERN_NOTICE "RAMDISK: %s image found at block %d\n",
+		       compress_name, start_block);
+		if (!*decompressor)
+			printk(KERN_EMERG
+			       "RAMDISK: %s decompressor not configured!\n",
+			       compress_name);
+		nblocks = 0;
+		goto done;
+	}
+
+	/* romfs is at block zero too */
+	if (romfsb->word0 == ROMSB_WORD0 &&
+	    romfsb->word1 == ROMSB_WORD1) {
+		printk(KERN_NOTICE
+		       "RAMDISK: romfs filesystem found at block %d\n",
+		       start_block);
+		nblocks = (ntohl(romfsb->size)+BLOCK_SIZE-1)>>BLOCK_SIZE_BITS;
+		goto done;
+	}
+
+	if (cramfsb->magic == CRAMFS_MAGIC) {
+		printk(KERN_NOTICE
+		       "RAMDISK: cramfs filesystem found at block %d\n",
+		       start_block);
+		nblocks = (cramfsb->size + BLOCK_SIZE - 1) >> BLOCK_SIZE_BITS;
+		goto done;
+	}
+
+	/* squashfs is at block zero too */
+	if (le32_to_cpu(squashfsb->s_magic) == SQUASHFS_MAGIC) {
+		printk(KERN_NOTICE
+		       "RAMDISK: squashfs filesystem found at block %d\n",
+		       start_block);
+		nblocks = (le64_to_cpu(squashfsb->bytes_used) + BLOCK_SIZE - 1)
+			 >> BLOCK_SIZE_BITS;
+		goto done;
+	}
+
+	/*
+	 * Read 512 bytes further to check if cramfs is padded
+	 */
+	pos = start_block * BLOCK_SIZE + 0x200;
+	kernel_read(file, buf, size, &pos);
+
+	if (cramfsb->magic == CRAMFS_MAGIC) {
+		printk(KERN_NOTICE
+		       "RAMDISK: cramfs filesystem found at block %d\n",
+		       start_block);
+		nblocks = (cramfsb->size + BLOCK_SIZE - 1) >> BLOCK_SIZE_BITS;
+		goto done;
+	}
+
+	/*
+	 * Read block 1 to test for minix and ext2 superblock
+	 */
+	pos = (start_block + 1) * BLOCK_SIZE;
+	kernel_read(file, buf, size, &pos);
+
+	/* Try minix */
+	if (minixsb->s_magic == MINIX_SUPER_MAGIC ||
+	    minixsb->s_magic == MINIX_SUPER_MAGIC2) {
+		printk(KERN_NOTICE
+		       "RAMDISK: Minix filesystem found at block %d\n",
+		       start_block);
+		nblocks = minixsb->s_nzones << minixsb->s_log_zone_size;
+		goto done;
+	}
+
+	/* Try ext2 */
+	n = ext2_image_size(buf);
+	if (n) {
+		printk(KERN_NOTICE
+		       "RAMDISK: ext2 filesystem found at block %d\n",
+		       start_block);
+		nblocks = n;
+		goto done;
+	}
+
+	printk(KERN_NOTICE
+	       "RAMDISK: Couldn't find valid RAM disk image starting at %d.\n",
+	       start_block);
+
+done:
+	kfree(buf);
+	return nblocks;
+}
+
+static unsigned long nr_blocks(struct file *file)
+{
+	struct inode *inode = file->f_mapping->host;
+
+	if (!S_ISBLK(inode->i_mode))
+		return 0;
+	return i_size_read(inode) >> 10;
+}
+
+int __init rd_load_image(void)
+{
+	int res = 0;
+	unsigned long rd_blocks, devblocks, nr_disks;
+	int nblocks, i;
+	char *buf = NULL;
+	unsigned short rotate = 0;
+	decompress_fn decompressor = NULL;
+	char rotator[4] = { '|' , '/' , '-' , '\\' };
+
+	out_file = filp_open("/dev/ram", O_RDWR, 0);
+	if (IS_ERR(out_file))
+		goto out;
+
+	in_file = filp_open("/initrd.image", O_RDONLY, 0);
+	if (IS_ERR(in_file))
+		goto noclose_input;
+
+	in_pos = rd_image_start * BLOCK_SIZE;
+	nblocks = identify_ramdisk_image(in_file, in_pos, &decompressor);
+	if (nblocks < 0)
+		goto done;
+
+	if (nblocks == 0) {
+		if (crd_load(decompressor) == 0)
+			goto successful_load;
+		goto done;
+	}
+
+	/*
+	 * NOTE NOTE: nblocks is not actually blocks but
+	 * the number of kibibytes of data to load into a ramdisk.
+	 */
+	rd_blocks = nr_blocks(out_file);
+	if (nblocks > rd_blocks) {
+		printk("RAMDISK: image too big! (%dKiB/%ldKiB)\n",
+		       nblocks, rd_blocks);
+		goto done;
+	}
+
+	/*
+	 * OK, time to copy in the data
+	 */
+	devblocks = nblocks;
+
+	if (devblocks == 0) {
+		printk(KERN_ERR "RAMDISK: could not determine device size\n");
+		goto done;
+	}
+
+	buf = kmalloc(BLOCK_SIZE, GFP_KERNEL);
+	if (!buf) {
+		printk(KERN_ERR "RAMDISK: could not allocate buffer\n");
+		goto done;
+	}
+
+	nr_disks = (nblocks - 1) / devblocks + 1;
+	pr_notice("RAMDISK: Loading %dKiB [%ld disk%s] into ram disk... ",
+		  nblocks, nr_disks, str_plural(nr_disks));
+	for (i = 0; i < nblocks; i++) {
+		if (i && (i % devblocks == 0)) {
+			pr_cont("done disk #1.\n");
+			rotate = 0;
+			fput(in_file);
+			break;
+		}
+		kernel_read(in_file, buf, BLOCK_SIZE, &in_pos);
+		kernel_write(out_file, buf, BLOCK_SIZE, &out_pos);
+		if (!IS_ENABLED(CONFIG_S390) && !(i % 16)) {
+			pr_cont("%c\b", rotator[rotate & 0x3]);
+			rotate++;
+		}
+	}
+	pr_cont("done.\n");
+
+successful_load:
+	res = 1;
+done:
+	fput(in_file);
+noclose_input:
+	fput(out_file);
+out:
+	kfree(buf);
+	init_unlink("/dev/ram");
+	return res;
+}
+
+static int exit_code;
+static int decompress_error;
+
+static long __init compr_fill(void *buf, unsigned long len)
+{
+	long r = kernel_read(in_file, buf, len, &in_pos);
+	if (r < 0)
+		printk(KERN_ERR "RAMDISK: error while reading compressed data");
+	else if (r == 0)
+		printk(KERN_ERR "RAMDISK: EOF while reading compressed data");
+	return r;
+}
+
+static long __init compr_flush(void *window, unsigned long outcnt)
+{
+	long written = kernel_write(out_file, window, outcnt, &out_pos);
+	if (written != outcnt) {
+		if (decompress_error == 0)
+			printk(KERN_ERR
+			       "RAMDISK: incomplete write (%ld != %ld)\n",
+			       written, outcnt);
+		decompress_error = 1;
+		return -1;
+	}
+	return outcnt;
+}
+
+static void __init error(char *x)
+{
+	printk(KERN_ERR "%s\n", x);
+	exit_code = 1;
+	decompress_error = 1;
+}
+
+static int __init crd_load(decompress_fn deco)
+{
+	int result;
+
+	if (!deco) {
+		pr_emerg("Invalid ramdisk decompression routine.  "
+			 "Select appropriate config option.\n");
+		panic("Could not decompress initial ramdisk image.");
+	}
+
+	result = deco(NULL, 0, compr_fill, compr_flush, NULL, NULL, error);
+	if (decompress_error)
+		result = 1;
+	return result;
+}

linux-7.2.3/init/init_task.c

@@ -0,0 +1,277 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init_task.h>
+#include <linux/export.h>
+#include <linux/mqueue.h>
+#include <linux/sched.h>
+#include <linux/sched/sysctl.h>
+#include <linux/sched/rt.h>
+#include <linux/sched/task.h>
+#include <linux/sched/ext.h>
+#include <linux/sched/exec_state.h>
+#include <linux/user_namespace.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/audit.h>
+#include <linux/numa.h>
+#include <linux/scs.h>
+#include <linux/plist.h>
+
+#include <linux/uaccess.h>
+
+static struct signal_struct init_signals = {
+	.nr_threads	= 1,
+	.thread_head	= LIST_HEAD_INIT(init_task.thread_node),
+	.wait_chldexit	= __WAIT_QUEUE_HEAD_INITIALIZER(init_signals.wait_chldexit),
+	.shared_pending	= {
+		.list = LIST_HEAD_INIT(init_signals.shared_pending.list),
+		.signal =  {{0}}
+	},
+	.multiprocess	= HLIST_HEAD_INIT,
+	.rlim		= INIT_RLIMITS,
+#ifdef CONFIG_CGROUPS
+	.cgroup_threadgroup_rwsem	= __RWSEM_INITIALIZER(init_signals.cgroup_threadgroup_rwsem),
+#endif
+	.cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex),
+	.exec_update_lock = __RWSEM_INITIALIZER(init_signals.exec_update_lock),
+#ifdef CONFIG_POSIX_TIMERS
+	.posix_timers		= HLIST_HEAD_INIT,
+	.ignored_posix_timers	= HLIST_HEAD_INIT,
+	.cputimer		= {
+		.cputime_atomic	= INIT_CPUTIME_ATOMIC,
+	},
+#endif
+	INIT_CPU_TIMERS(init_signals)
+	.pids = {
+		[PIDTYPE_PID]	= &init_struct_pid,
+		[PIDTYPE_TGID]	= &init_struct_pid,
+		[PIDTYPE_PGID]	= &init_struct_pid,
+		[PIDTYPE_SID]	= &init_struct_pid,
+	},
+	INIT_PREV_CPUTIME(init_signals)
+};
+
+static struct sighand_struct init_sighand = {
+	.count		= REFCOUNT_INIT(1),
+	.action		= { { { .sa_handler = SIG_DFL, } }, },
+	.siglock	= __SPIN_LOCK_UNLOCKED(init_sighand.siglock),
+	.signalfd_wqh	= __WAIT_QUEUE_HEAD_INITIALIZER(init_sighand.signalfd_wqh),
+};
+
+/* init to 2 - one for init_task, one to ensure it is never freed */
+struct task_exec_state init_task_exec_state = {
+	.count		= REFCOUNT_INIT(2),
+	.dumpable	= TASK_DUMPABLE_OWNER,
+	.user_ns	= &init_user_ns,
+};
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+unsigned long init_shadow_call_stack[SCS_SIZE / sizeof(long)] = {
+	[(SCS_SIZE / sizeof(long)) - 1] = SCS_END_MAGIC
+};
+#endif
+
+/* init to 2 - one for init_task, one to ensure it is never freed */
+static struct group_info init_groups = { .usage = REFCOUNT_INIT(2) };
+
+/*
+ * The initial credentials for the initial task
+ */
+static struct cred init_cred = {
+	.usage			= ATOMIC_INIT(4),
+	.uid			= GLOBAL_ROOT_UID,
+	.gid			= GLOBAL_ROOT_GID,
+	.suid			= GLOBAL_ROOT_UID,
+	.sgid			= GLOBAL_ROOT_GID,
+	.euid			= GLOBAL_ROOT_UID,
+	.egid			= GLOBAL_ROOT_GID,
+	.fsuid			= GLOBAL_ROOT_UID,
+	.fsgid			= GLOBAL_ROOT_GID,
+	.securebits		= SECUREBITS_DEFAULT,
+	.cap_inheritable	= CAP_EMPTY_SET,
+	.cap_permitted		= CAP_FULL_SET,
+	.cap_effective		= CAP_FULL_SET,
+	.cap_bset		= CAP_FULL_SET,
+	.user			= INIT_USER,
+	.user_ns		= &init_user_ns,
+	.group_info		= &init_groups,
+	.ucounts		= &init_ucounts,
+};
+
+/*
+ * Set up the first task table, touch at your own risk!. Base=0,
+ * limit=0x1fffff (=2MB)
+ */
+struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+	.thread_info	= INIT_THREAD_INFO(init_task),
+	.stack_refcount	= REFCOUNT_INIT(1),
+#endif
+	.__state	= 0,
+	.stack		= init_stack,
+	.usage		= REFCOUNT_INIT(2),
+	.flags		= PF_KTHREAD,
+	.prio		= MAX_PRIO - 20,
+	.static_prio	= MAX_PRIO - 20,
+	.normal_prio	= MAX_PRIO - 20,
+	.policy		= SCHED_NORMAL,
+	.cpus_ptr	= &init_task.cpus_mask,
+	.user_cpus_ptr	= NULL,
+	.cpus_mask	= CPU_MASK_ALL,
+	.max_allowed_capacity	= SCHED_CAPACITY_SCALE,
+	.nr_cpus_allowed= NR_CPUS,
+	.mm		= NULL,
+	.active_mm	= &init_mm,
+	.exec_state	= &init_task_exec_state,
+	.restart_block	= {
+		.fn = do_no_restart_syscall,
+	},
+	.se		= {
+		.group_node 	= LIST_HEAD_INIT(init_task.se.group_node),
+	},
+	.rt		= {
+		.run_list	= LIST_HEAD_INIT(init_task.rt.run_list),
+		.time_slice	= RR_TIMESLICE,
+	},
+	.tasks		= LIST_HEAD_INIT(init_task.tasks),
+#ifdef CONFIG_SMP
+	.pushable_tasks	= PLIST_NODE_INIT(init_task.pushable_tasks, MAX_PRIO),
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+	.sched_task_group = &root_task_group,
+#endif
+#ifdef CONFIG_SCHED_CLASS_EXT
+	.scx		= {
+		.dsq_list.node	= LIST_HEAD_INIT(init_task.scx.dsq_list.node),
+		.sticky_cpu	= -1,
+		.holding_cpu	= -1,
+		.runnable_node	= LIST_HEAD_INIT(init_task.scx.runnable_node),
+		.runnable_at	= INITIAL_JIFFIES,
+		.ddsp_dsq_id	= SCX_DSQ_INVALID,
+		.slice		= SCX_SLICE_DFL,
+	},
+#endif
+	.ptraced	= LIST_HEAD_INIT(init_task.ptraced),
+	.ptrace_entry	= LIST_HEAD_INIT(init_task.ptrace_entry),
+	.real_parent	= &init_task,
+	.parent		= &init_task,
+	.children	= LIST_HEAD_INIT(init_task.children),
+	.sibling	= LIST_HEAD_INIT(init_task.sibling),
+	.group_leader	= &init_task,
+	RCU_POINTER_INITIALIZER(real_cred, &init_cred),
+	RCU_POINTER_INITIALIZER(cred, &init_cred),
+	.comm		= INIT_TASK_COMM,
+	.thread		= INIT_THREAD,
+	.fs		= &init_fs,
+	.files		= &init_files,
+#ifdef CONFIG_IO_URING
+	.io_uring	= NULL,
+#endif
+	.signal		= &init_signals,
+	.sighand	= &init_sighand,
+	.nsproxy	= &init_nsproxy,
+	.pending	= {
+		.list = LIST_HEAD_INIT(init_task.pending.list),
+		.signal = {{0}}
+	},
+	.blocked	= {{0}},
+	.alloc_lock	= __SPIN_LOCK_UNLOCKED(init_task.alloc_lock),
+	.journal_info	= NULL,
+	INIT_CPU_TIMERS(init_task)
+	.pi_lock	= __RAW_SPIN_LOCK_UNLOCKED(init_task.pi_lock),
+	.blocked_lock	= __RAW_SPIN_LOCK_UNLOCKED(init_task.blocked_lock),
+	.timer_slack_ns = 50000, /* 50 usec default slack */
+	.thread_pid	= &init_struct_pid,
+	.thread_node	= LIST_HEAD_INIT(init_signals.thread_head),
+#ifdef CONFIG_AUDIT
+	.loginuid	= INVALID_UID,
+	.sessionid	= AUDIT_SID_UNSET,
+#endif
+#ifdef CONFIG_PERF_EVENTS
+	.perf_event_mutex = __MUTEX_INITIALIZER(init_task.perf_event_mutex),
+	.perf_event_list = LIST_HEAD_INIT(init_task.perf_event_list),
+#endif
+#ifdef CONFIG_PREEMPT_RCU
+	.rcu_read_lock_nesting = 0,
+	.rcu_read_unlock_special.s = 0,
+	.rcu_node_entry = LIST_HEAD_INIT(init_task.rcu_node_entry),
+	.rcu_blocked_node = NULL,
+#endif
+#ifdef CONFIG_TASKS_RCU
+	.rcu_tasks_holdout = false,
+	.rcu_tasks_holdout_list = LIST_HEAD_INIT(init_task.rcu_tasks_holdout_list),
+	.rcu_tasks_idle_cpu = -1,
+	.rcu_tasks_exit_list = LIST_HEAD_INIT(init_task.rcu_tasks_exit_list),
+#endif
+#ifdef CONFIG_TASKS_TRACE_RCU
+	.trc_reader_nesting = 0,
+#endif
+#ifdef CONFIG_CPUSETS
+	.mems_allowed_seq = SEQCNT_SPINLOCK_ZERO(init_task.mems_allowed_seq,
+						 &init_task.alloc_lock),
+#endif
+	.blocked_donor = NULL,
+#ifdef CONFIG_RT_MUTEXES
+	.pi_waiters	= RB_ROOT_CACHED,
+	.pi_top_task	= NULL,
+#endif
+	INIT_PREV_CPUTIME(init_task)
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+	.vtime.seqcount	= SEQCNT_ZERO(init_task.vtime_seqcount),
+	.vtime.starttime = 0,
+	.vtime.state	= VTIME_SYS,
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+	.numa_preferred_nid = NUMA_NO_NODE,
+	.numa_group	= NULL,
+	.numa_faults	= NULL,
+#endif
+#ifdef CONFIG_SCHED_CACHE
+	.preferred_llc  = -1,
+	.pref_llc_queued  = 0,
+#endif
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+	.kasan_depth	= 1,
+#endif
+#ifdef CONFIG_KCSAN
+	.kcsan_ctx = {
+		.scoped_accesses	= {LIST_POISON1, NULL},
+	},
+#endif
+#ifdef CONFIG_TRACE_IRQFLAGS
+	.softirqs_enabled = 1,
+#endif
+#ifdef CONFIG_LOCKDEP
+	.lockdep_depth = 0, /* no locks held yet */
+	.curr_chain_key = INITIAL_CHAIN_KEY,
+	.lockdep_recursion = 0,
+#endif
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	.ret_stack		= NULL,
+	.tracing_graph_pause	= ATOMIC_INIT(0),
+#endif
+#if defined(CONFIG_TRACING) && defined(CONFIG_PREEMPTION)
+	.trace_recursion = 0,
+#endif
+#ifdef CONFIG_LIVEPATCH
+	.patch_state	= KLP_TRANSITION_IDLE,
+#endif
+#ifdef CONFIG_SECURITY
+	.security	= NULL,
+#endif
+#ifdef CONFIG_SECCOMP_FILTER
+	.seccomp	= { .filter_count = ATOMIC_INIT(0) },
+#endif
+#ifdef CONFIG_SCHED_MM_CID
+	.mm_cid		= { .cid = MM_CID_UNSET, },
+#endif
+};
+EXPORT_SYMBOL(init_task);
+
+/*
+ * Initial thread structure. Alignment of this is handled by a special
+ * linker map entry.
+ */
+#ifndef CONFIG_THREAD_INFO_IN_TASK
+struct thread_info init_thread_info __init_thread_info = INIT_THREAD_INFO(init_task);
+#endif

linux-7.2.3/init/initramfs.c

@@ -0,0 +1,792 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/async.h>
+#include <linux/delay.h>
+#include <linux/dirent.h>
+#include <linux/export.h>
+#include <linux/fcntl.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/hex.h>
+#include <linux/init.h>
+#include <linux/init_syscalls.h>
+#include <linux/kstrtox.h>
+#include <linux/memblock.h>
+#include <linux/mm.h>
+#include <linux/namei.h>
+#include <linux/overflow.h>
+#include <linux/security.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/syscalls.h>
+#include <linux/types.h>
+#include <linux/umh.h>
+#include <linux/utime.h>
+
+#include <asm/byteorder.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)
+{
+	if (!message)
+		message = x;
+}
+
+#define panic_show_mem(fmt, ...) \
+	({ show_mem(); panic(fmt, ##__VA_ARGS__); })
+
+/* link hash */
+
+#define N_ALIGN(len) ((((len) + 1) & ~3) + 2)
+
+static __initdata struct hash {
+	int ino, minor, major;
+	umode_t mode;
+	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)
+{
+	unsigned long tmp = ino + minor + (major << 3);
+	tmp += tmp >> 5;
+	return tmp & 31;
+}
+
+static char __init *find_link(int major, int minor, int ino,
+			      umode_t mode, char *name)
+{
+	struct hash **p, *q;
+	for (p = head + hash(major, minor, ino); *p; p = &(*p)->next) {
+		if ((*p)->ino != ino)
+			continue;
+		if ((*p)->minor != minor)
+			continue;
+		if ((*p)->major != major)
+			continue;
+		if (((*p)->mode ^ mode) & S_IFMT)
+			continue;
+		return (*p)->name;
+	}
+	q = kmalloc_obj(struct hash);
+	if (!q)
+		panic_show_mem("can't allocate link hash entry");
+	q->major = major;
+	q->minor = minor;
+	q->ino = ino;
+	q->mode = mode;
+	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; hardlink_seen && p < head + 32; p++) {
+		while (*p) {
+			q = *p;
+			*p = q->next;
+			kfree(q);
+		}
+	}
+	hardlink_seen = false;
+}
+
+#ifdef CONFIG_INITRAMFS_PRESERVE_MTIME
+static void __init do_utime(char *filename, time64_t mtime)
+{
+	struct timespec64 t[2] = { { .tv_sec = mtime }, { .tv_sec = mtime } };
+	init_utimes(filename, t);
+}
+
+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;
+	time64_t mtime;
+	char name[];
+};
+
+static void __init dir_add(const char *name, size_t nlen, time64_t mtime)
+{
+	struct dir_entry *de;
+
+	de = kmalloc_flex(*de, name, nlen);
+	if (!de)
+		panic_show_mem("can't allocate dir_entry buffer");
+	INIT_LIST_HEAD(&de->list);
+	strscpy(de->name, name, nlen);
+	de->mtime = mtime;
+	list_add(&de->list, &dir_list);
+}
+
+static void __init dir_utime(void)
+{
+	struct dir_entry *de, *tmp;
+	list_for_each_entry_safe(de, tmp, &dir_list, list) {
+		list_del(&de->list);
+		do_utime(de->name, de->mtime);
+		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 time64_t mtime;
+
+/* cpio header parsing */
+
+static __initdata unsigned long ino, major, minor, nlink;
+static __initdata umode_t mode;
+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 int __init parse_header(char *s)
+{
+	__be32 header[13];
+	int ret;
+
+	ret = hex2bin((u8 *)header, s + 6, sizeof(header));
+	if (ret) {
+		error("damaged header");
+		return ret;
+	}
+
+	ino = be32_to_cpu(header[0]);
+	mode = be32_to_cpu(header[1]);
+	uid = be32_to_cpu(header[2]);
+	gid = be32_to_cpu(header[3]);
+	nlink = be32_to_cpu(header[4]);
+	mtime = be32_to_cpu(header[5]); /* breaks in y2106 */
+	body_len = be32_to_cpu(header[6]);
+	major = be32_to_cpu(header[7]);
+	minor = be32_to_cpu(header[8]);
+	rdev = new_encode_dev(MKDEV(be32_to_cpu(header[9]), be32_to_cpu(header[10])));
+	name_len = be32_to_cpu(header[11]);
+	hdr_csum = be32_to_cpu(header[12]);
+	return 0;
+}
+
+/* Finite-state machine */
+
+static __initdata enum state {
+	Start,
+	Collect,
+	GotHeader,
+	SkipIt,
+	GotName,
+	CopyFile,
+	GotSymlink,
+	Reset
+} state, next_state;
+
+static __initdata char *victim;
+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;
+	byte_count -= n;
+}
+
+static __initdata char *collected;
+static long remains __initdata;
+static __initdata char *collect;
+
+static void __init read_into(char *buf, unsigned size, enum state next)
+{
+	if (byte_count >= size) {
+		collected = victim;
+		eat(size);
+		state = next;
+	} else {
+		collect = collected = buf;
+		remains = size;
+		next_state = next;
+		state = Collect;
+	}
+}
+
+static __initdata char *header_buf, *symlink_buf, *name_buf;
+
+static int __init do_start(void)
+{
+	read_into(header_buf, CPIO_HDRLEN, GotHeader);
+	return 0;
+}
+
+static int __init do_collect(void)
+{
+	unsigned long n = remains;
+	if (byte_count < n)
+		n = byte_count;
+	memcpy(collect, victim, n);
+	eat(n);
+	collect += n;
+	if ((remains -= n) != 0)
+		return 1;
+	state = next_state;
+	return 0;
+}
+
+static int __init do_header(void)
+{
+	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;
+	}
+	if (parse_header(collected))
+		return 1;
+	next_header = this_header + N_ALIGN(name_len) + body_len;
+	next_header = (next_header + 3) & ~3;
+	state = SkipIt;
+	if (name_len <= 0 || name_len > PATH_MAX)
+		return 0;
+	if (S_ISLNK(mode)) {
+		if (body_len > PATH_MAX)
+			return 0;
+		collect = collected = symlink_buf;
+		remains = N_ALIGN(name_len) + body_len;
+		next_state = GotSymlink;
+		state = Collect;
+		return 0;
+	}
+	if (S_ISREG(mode) || !body_len)
+		read_into(name_buf, N_ALIGN(name_len), GotName);
+	return 0;
+}
+
+static int __init do_skip(void)
+{
+	if (this_header + byte_count < next_header) {
+		eat(byte_count);
+		return 1;
+	} else {
+		eat(next_header - this_header);
+		state = next_state;
+		return 0;
+	}
+}
+
+static int __init do_reset(void)
+{
+	while (byte_count && *victim == '\0')
+		eat(1);
+	if (byte_count && (this_header & 3))
+		error("broken padding");
+	return 1;
+}
+
+static void __init clean_path(char *path, umode_t fmode)
+{
+	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);
+	}
+}
+
+static int __init maybe_link(void)
+{
+	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 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;
+	}
+	clean_path(collected, mode);
+	if (S_ISREG(mode)) {
+		int ml = maybe_link();
+		if (ml >= 0) {
+			int openflags = O_WRONLY|O_CREAT|O_LARGEFILE;
+			if (ml != 1)
+				openflags |= O_TRUNC;
+			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)) {
+		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) {
+			init_mknod(collected, mode, rdev);
+			init_chown(collected, uid, gid, 0);
+			init_chmod(collected, mode);
+			do_utime(collected, mtime);
+		}
+	}
+	return 0;
+}
+
+static int __init do_copy(void)
+{
+	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 {
+		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);
+	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;
+	return 0;
+}
+
+static __initdata int (*actions[])(void) = {
+	[Start]		= do_start,
+	[Collect]	= do_collect,
+	[GotHeader]	= do_header,
+	[SkipIt]	= do_skip,
+	[GotName]	= do_name,
+	[CopyFile]	= do_copy,
+	[GotSymlink]	= do_symlink,
+	[Reset]		= do_reset,
+};
+
+static long __init write_buffer(char *buf, unsigned long len)
+{
+	byte_count = len;
+	victim = buf;
+
+	while (!actions[state]())
+		;
+	return len - byte_count;
+}
+
+static long __init flush_buffer(void *bufv, unsigned long len)
+{
+	char *buf = bufv;
+	long written;
+	long origLen = len;
+	if (message)
+		return -1;
+	while ((written = write_buffer(buf, len)) < len && !message) {
+		char c = buf[written];
+		if (c == '0') {
+			buf += written;
+			len -= written;
+			state = Start;
+		} else if (c == 0) {
+			buf += written;
+			len -= written;
+			state = Reset;
+		} else
+			error("junk within compressed archive");
+	}
+	return origLen;
+}
+
+static unsigned long my_inptr __initdata; /* index of next byte to be processed in inbuf */
+
+#include <linux/decompress/generic.h>
+
+/**
+ * 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)
+{
+	long written;
+	decompress_fn decompress;
+	const char *compress_name;
+	struct {
+		char header[CPIO_HDRLEN];
+		char symlink[PATH_MAX + N_ALIGN(PATH_MAX) + 1];
+		char name[N_ALIGN(PATH_MAX)];
+	} *bufs = kmalloc_obj(*bufs);
+
+	if (!bufs)
+		panic_show_mem("can't allocate buffers");
+
+	header_buf = bufs->header;
+	symlink_buf = bufs->symlink;
+	name_buf = bufs->name;
+
+	state = Start;
+	this_header = 0;
+	message = NULL;
+	while (!message && len) {
+		loff_t saved_offset = this_header;
+		if (*buf == '0' && !(this_header & 3)) {
+			state = Start;
+			written = write_buffer(buf, len);
+			buf += written;
+			len -= written;
+			continue;
+		}
+		if (!*buf) {
+			buf++;
+			len--;
+			this_header++;
+			continue;
+		}
+		this_header = 0;
+		decompress = decompress_method(buf, len, &compress_name);
+		pr_debug("Detected %s compressed data\n", compress_name);
+		if (decompress) {
+			int res = decompress(buf, len, NULL, flush_buffer, NULL,
+				   &my_inptr, error);
+			if (res)
+				error("decompressor failed");
+		} else if (compress_name) {
+			pr_err("compression method %s not configured\n",
+			       compress_name);
+			error("decompressor failed");
+		} else
+			error("invalid magic at start of compressed archive");
+		if (state != Reset)
+			error("junk at the end of compressed archive");
+		this_header = saved_offset + my_inptr;
+		buf += my_inptr;
+		len -= my_inptr;
+	}
+	dir_utime();
+	/* free any hardlink state collected without optional TRAILER!!! */
+	free_hash();
+	kfree(bufs);
+	return message;
+}
+
+static int __initdata do_retain_initrd;
+
+static int __init retain_initrd_param(char *str)
+{
+	if (*str)
+		return 0;
+	do_retain_initrd = 1;
+	return 1;
+}
+__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 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)
+{
+	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
+			"initrd");
+}
+
+#ifdef CONFIG_CRASH_RESERVE
+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);
+
+	/*
+	 * 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)
+		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
+static void __init populate_initrd_image(char *err)
+{
+	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;
+
+	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 /* CONFIG_BLK_DEV_RAM */
+
+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_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");
+	else
+		printk(KERN_INFO "Unpacking initramfs...\n");
+
+	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) {
+		/*
+		 * 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);

linux-7.2.3/init/initramfs_internal.h

@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __INITRAMFS_INTERNAL_H__
+#define __INITRAMFS_INTERNAL_H__
+
+char *unpack_to_rootfs(char *buf, unsigned long len);
+#define CPIO_HDRLEN 110
+
+#endif

linux-7.2.3/init/initramfs_test.c

@@ -0,0 +1,585 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <kunit/test.h>
+#include <linux/fcntl.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/init_syscalls.h>
+#include <linux/initrd.h>
+#include <linux/stringify.h>
+#include <linux/timekeeping.h>
+#include "initramfs_internal.h"
+
+struct initramfs_test_cpio {
+	char *magic;
+	unsigned int ino;
+	unsigned int mode;
+	unsigned int uid;
+	unsigned int gid;
+	unsigned int nlink;
+	unsigned int mtime;
+	unsigned int filesize;
+	unsigned int devmajor;
+	unsigned int devminor;
+	unsigned int rdevmajor;
+	unsigned int rdevminor;
+	unsigned int namesize;
+	unsigned int csum;
+	char *fname;
+	char *data;
+};
+
+/* regular newc header format */
+#define CPIO_HDR_FMT "%s%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%08x%s"
+/*
+ * Bogus newc header with "0x" prefixes on the uid, gid, and namesize values.
+ * parse_header()/simple_str[n]toul() accepted this, contrary to the initramfs
+ * specification. hex2bin() now fails.
+ */
+#define CPIO_HDR_OX_INJECT \
+	"%s%08x%08x0x%06x0X%06x%08x%08x%08x%08x%08x%08x%08x0x%06x%08x%s"
+
+static size_t fill_cpio(struct initramfs_test_cpio *cs, size_t csz,
+			bool inject_ox, char *out)
+{
+	int i;
+	size_t off = 0;
+
+	for (i = 0; i < csz; i++) {
+		char *pos = &out[off];
+		struct initramfs_test_cpio *c = &cs[i];
+		size_t thislen;
+
+		/* +1 to account for nulterm */
+		thislen = sprintf(pos,
+			inject_ox ? CPIO_HDR_OX_INJECT : CPIO_HDR_FMT,
+			c->magic, c->ino, c->mode, c->uid, c->gid, c->nlink,
+			c->mtime, c->filesize, c->devmajor, c->devminor,
+			c->rdevmajor, c->rdevminor, c->namesize, c->csum,
+			c->fname) + 1;
+
+		pr_debug("packing (%zu): %.*s\n", thislen, (int)thislen, pos);
+		if (thislen != CPIO_HDRLEN + c->namesize)
+			pr_debug("padded to: %u\n", CPIO_HDRLEN + c->namesize);
+		off += CPIO_HDRLEN + c->namesize;
+		while (off & 3)
+			out[off++] = '\0';
+
+		memcpy(&out[off], c->data, c->filesize);
+		off += c->filesize;
+		while (off & 3)
+			out[off++] = '\0';
+	}
+
+	return off;
+}
+
+static void __init initramfs_test_extract(struct kunit *test)
+{
+	char *err, *cpio_srcbuf;
+	size_t len;
+	struct timespec64 ts_before, ts_after;
+	struct kstat st = {};
+	struct initramfs_test_cpio c[] = { {
+		.magic = "070701",
+		.ino = 1,
+		.mode = S_IFREG | 0777,
+		.uid = 12,
+		.gid = 34,
+		.nlink = 1,
+		.mtime = 56,
+		.filesize = 0,
+		.devmajor = 0,
+		.devminor = 1,
+		.rdevmajor = 0,
+		.rdevminor = 0,
+		.namesize = sizeof("initramfs_test_extract"),
+		.csum = 0,
+		.fname = "initramfs_test_extract",
+	}, {
+		.magic = "070701",
+		.ino = 2,
+		.mode = S_IFDIR | 0777,
+		.nlink = 1,
+		.mtime = 57,
+		.devminor = 1,
+		.namesize = sizeof("initramfs_test_extract_dir"),
+		.fname = "initramfs_test_extract_dir",
+	}, {
+		.magic = "070701",
+		.namesize = sizeof("TRAILER!!!"),
+		.fname = "TRAILER!!!",
+	} };
+
+	/* +3 to cater for any 4-byte end-alignment */
+	cpio_srcbuf = kzalloc(ARRAY_SIZE(c) * (CPIO_HDRLEN + PATH_MAX + 3),
+			      GFP_KERNEL);
+	len = fill_cpio(c, ARRAY_SIZE(c), false, cpio_srcbuf);
+
+	ktime_get_real_ts64(&ts_before);
+	err = unpack_to_rootfs(cpio_srcbuf, len);
+	ktime_get_real_ts64(&ts_after);
+	if (err) {
+		KUNIT_FAIL(test, "unpack failed %s", err);
+		goto out;
+	}
+
+	KUNIT_EXPECT_EQ(test, init_stat(c[0].fname, &st, 0), 0);
+	KUNIT_EXPECT_TRUE(test, S_ISREG(st.mode));
+	KUNIT_EXPECT_TRUE(test, uid_eq(st.uid, KUIDT_INIT(c[0].uid)));
+	KUNIT_EXPECT_TRUE(test, gid_eq(st.gid, KGIDT_INIT(c[0].gid)));
+	KUNIT_EXPECT_EQ(test, st.nlink, 1);
+	if (IS_ENABLED(CONFIG_INITRAMFS_PRESERVE_MTIME)) {
+		KUNIT_EXPECT_EQ(test, st.mtime.tv_sec, c[0].mtime);
+	} else {
+		KUNIT_EXPECT_GE(test, st.mtime.tv_sec, ts_before.tv_sec);
+		KUNIT_EXPECT_LE(test, st.mtime.tv_sec, ts_after.tv_sec);
+	}
+	KUNIT_EXPECT_EQ(test, st.blocks, c[0].filesize);
+
+	KUNIT_EXPECT_EQ(test, init_stat(c[1].fname, &st, 0), 0);
+	KUNIT_EXPECT_TRUE(test, S_ISDIR(st.mode));
+	if (IS_ENABLED(CONFIG_INITRAMFS_PRESERVE_MTIME)) {
+		KUNIT_EXPECT_EQ(test, st.mtime.tv_sec, c[1].mtime);
+	} else {
+		KUNIT_EXPECT_GE(test, st.mtime.tv_sec, ts_before.tv_sec);
+		KUNIT_EXPECT_LE(test, st.mtime.tv_sec, ts_after.tv_sec);
+	}
+
+	KUNIT_EXPECT_EQ(test, init_unlink(c[0].fname), 0);
+	KUNIT_EXPECT_EQ(test, init_rmdir(c[1].fname), 0);
+out:
+	kfree(cpio_srcbuf);
+}
+
+/*
+ * Don't terminate filename. Previously, the cpio filename field was passed
+ * directly to filp_open(collected, O_CREAT|..) without nulterm checks. See
+ * https://lore.kernel.org/linux-fsdevel/20241030035509.20194-2-ddiss@suse.de
+ */
+static void __init initramfs_test_fname_overrun(struct kunit *test)
+{
+	char *err, *cpio_srcbuf;
+	size_t len, suffix_off;
+	struct initramfs_test_cpio c[] = { {
+		.magic = "070701",
+		.ino = 1,
+		.mode = S_IFREG | 0777,
+		.uid = 0,
+		.gid = 0,
+		.nlink = 1,
+		.mtime = 1,
+		.filesize = 0,
+		.devmajor = 0,
+		.devminor = 1,
+		.rdevmajor = 0,
+		.rdevminor = 0,
+		.namesize = sizeof("initramfs_test_fname_overrun"),
+		.csum = 0,
+		.fname = "initramfs_test_fname_overrun",
+	} };
+
+	/*
+	 * poison cpio source buffer, so we can detect overrun. source
+	 * buffer is used by read_into() when hdr or fname
+	 * are already available (e.g. no compression).
+	 */
+	cpio_srcbuf = kmalloc(CPIO_HDRLEN + PATH_MAX + 3, GFP_KERNEL);
+	memset(cpio_srcbuf, 'B', CPIO_HDRLEN + PATH_MAX + 3);
+	/* limit overrun to avoid crashes / filp_open() ENAMETOOLONG */
+	cpio_srcbuf[CPIO_HDRLEN + strlen(c[0].fname) + 20] = '\0';
+
+	len = fill_cpio(c, ARRAY_SIZE(c), false, cpio_srcbuf);
+	/* overwrite trailing fname terminator and padding */
+	suffix_off = len - 1;
+	while (cpio_srcbuf[suffix_off] == '\0') {
+		cpio_srcbuf[suffix_off] = 'P';
+		suffix_off--;
+	}
+
+	err = unpack_to_rootfs(cpio_srcbuf, len);
+	KUNIT_EXPECT_NOT_NULL(test, err);
+
+	kfree(cpio_srcbuf);
+}
+
+static void __init initramfs_test_data(struct kunit *test)
+{
+	char *err, *cpio_srcbuf;
+	size_t len;
+	struct file *file;
+	struct initramfs_test_cpio c[] = { {
+		.magic = "070701",
+		.ino = 1,
+		.mode = S_IFREG | 0777,
+		.uid = 0,
+		.gid = 0,
+		.nlink = 1,
+		.mtime = 1,
+		.filesize = sizeof("ASDF") - 1,
+		.devmajor = 0,
+		.devminor = 1,
+		.rdevmajor = 0,
+		.rdevminor = 0,
+		.namesize = sizeof("initramfs_test_data"),
+		.csum = 0,
+		.fname = "initramfs_test_data",
+		.data = "ASDF",
+	} };
+
+	/* +6 for max name and data 4-byte padding */
+	cpio_srcbuf = kmalloc(CPIO_HDRLEN + c[0].namesize + c[0].filesize + 6,
+			      GFP_KERNEL);
+
+	len = fill_cpio(c, ARRAY_SIZE(c), false, cpio_srcbuf);
+
+	err = unpack_to_rootfs(cpio_srcbuf, len);
+	KUNIT_EXPECT_NULL(test, err);
+
+	file = filp_open(c[0].fname, O_RDONLY, 0);
+	if (IS_ERR(file)) {
+		KUNIT_FAIL(test, "open failed");
+		goto out;
+	}
+
+	/* read back file contents into @cpio_srcbuf and confirm match */
+	len = kernel_read(file, cpio_srcbuf, c[0].filesize, NULL);
+	KUNIT_EXPECT_EQ(test, len, c[0].filesize);
+	KUNIT_EXPECT_MEMEQ(test, cpio_srcbuf, c[0].data, len);
+
+	fput(file);
+	KUNIT_EXPECT_EQ(test, init_unlink(c[0].fname), 0);
+out:
+	kfree(cpio_srcbuf);
+}
+
+static void __init initramfs_test_csum(struct kunit *test)
+{
+	char *err, *cpio_srcbuf;
+	size_t len;
+	struct initramfs_test_cpio c[] = { {
+		/* 070702 magic indicates a valid csum is present */
+		.magic = "070702",
+		.ino = 1,
+		.mode = S_IFREG | 0777,
+		.nlink = 1,
+		.filesize = sizeof("ASDF") - 1,
+		.devminor = 1,
+		.namesize = sizeof("initramfs_test_csum"),
+		.csum = 'A' + 'S' + 'D' + 'F',
+		.fname = "initramfs_test_csum",
+		.data = "ASDF",
+	}, {
+		/* mix csum entry above with no-csum entry below */
+		.magic = "070701",
+		.ino = 2,
+		.mode = S_IFREG | 0777,
+		.nlink = 1,
+		.filesize = sizeof("ASDF") - 1,
+		.devminor = 1,
+		.namesize = sizeof("initramfs_test_csum_not_here"),
+		/* csum ignored */
+		.csum = 5555,
+		.fname = "initramfs_test_csum_not_here",
+		.data = "ASDF",
+	} };
+
+	cpio_srcbuf = kmalloc(8192, GFP_KERNEL);
+
+	len = fill_cpio(c, ARRAY_SIZE(c), false, cpio_srcbuf);
+
+	err = unpack_to_rootfs(cpio_srcbuf, len);
+	KUNIT_EXPECT_NULL(test, err);
+
+	KUNIT_EXPECT_EQ(test, init_unlink(c[0].fname), 0);
+	KUNIT_EXPECT_EQ(test, init_unlink(c[1].fname), 0);
+
+	/* mess up the csum and confirm that unpack fails */
+	c[0].csum--;
+	len = fill_cpio(c, ARRAY_SIZE(c), false, cpio_srcbuf);
+
+	err = unpack_to_rootfs(cpio_srcbuf, len);
+	KUNIT_EXPECT_NOT_NULL(test, err);
+
+	/*
+	 * file (with content) is still retained in case of bad-csum abort.
+	 * Perhaps we should change this.
+	 */
+	KUNIT_EXPECT_EQ(test, init_unlink(c[0].fname), 0);
+	KUNIT_EXPECT_EQ(test, init_unlink(c[1].fname), -ENOENT);
+	kfree(cpio_srcbuf);
+}
+
+/*
+ * hardlink hashtable may leak when the archive omits a trailer:
+ * https://lore.kernel.org/r/20241107002044.16477-10-ddiss@suse.de/
+ */
+static void __init initramfs_test_hardlink(struct kunit *test)
+{
+	char *err, *cpio_srcbuf;
+	size_t len;
+	struct kstat st0 = {}, st1 = {};
+	struct initramfs_test_cpio c[] = { {
+		.magic = "070701",
+		.ino = 1,
+		.mode = S_IFREG | 0777,
+		.nlink = 2,
+		.devminor = 1,
+		.namesize = sizeof("initramfs_test_hardlink"),
+		.fname = "initramfs_test_hardlink",
+	}, {
+		/* hardlink data is present in last archive entry */
+		.magic = "070701",
+		.ino = 1,
+		.mode = S_IFREG | 0777,
+		.nlink = 2,
+		.filesize = sizeof("ASDF") - 1,
+		.devminor = 1,
+		.namesize = sizeof("initramfs_test_hardlink_link"),
+		.fname = "initramfs_test_hardlink_link",
+		.data = "ASDF",
+	} };
+
+	cpio_srcbuf = kmalloc(8192, GFP_KERNEL);
+
+	len = fill_cpio(c, ARRAY_SIZE(c), false, cpio_srcbuf);
+
+	err = unpack_to_rootfs(cpio_srcbuf, len);
+	KUNIT_EXPECT_NULL(test, err);
+
+	KUNIT_EXPECT_EQ(test, init_stat(c[0].fname, &st0, 0), 0);
+	KUNIT_EXPECT_EQ(test, init_stat(c[1].fname, &st1, 0), 0);
+	KUNIT_EXPECT_EQ(test, st0.ino, st1.ino);
+	KUNIT_EXPECT_EQ(test, st0.nlink, 2);
+	KUNIT_EXPECT_EQ(test, st1.nlink, 2);
+
+	KUNIT_EXPECT_EQ(test, init_unlink(c[0].fname), 0);
+	KUNIT_EXPECT_EQ(test, init_unlink(c[1].fname), 0);
+
+	kfree(cpio_srcbuf);
+}
+
+#define INITRAMFS_TEST_MANY_LIMIT 1000
+#define INITRAMFS_TEST_MANY_PATH_MAX (sizeof("initramfs_test_many-") \
+			+ sizeof(__stringify(INITRAMFS_TEST_MANY_LIMIT)))
+static void __init initramfs_test_many(struct kunit *test)
+{
+	char *err, *cpio_srcbuf, *p;
+	size_t len = INITRAMFS_TEST_MANY_LIMIT *
+		     (CPIO_HDRLEN + INITRAMFS_TEST_MANY_PATH_MAX + 3);
+	char thispath[INITRAMFS_TEST_MANY_PATH_MAX];
+	int i;
+
+	p = cpio_srcbuf = kmalloc(len, GFP_KERNEL);
+
+	for (i = 0; i < INITRAMFS_TEST_MANY_LIMIT; i++) {
+		struct initramfs_test_cpio c = {
+			.magic = "070701",
+			.ino = i,
+			.mode = S_IFREG | 0777,
+			.nlink = 1,
+			.devminor = 1,
+			.fname = thispath,
+		};
+
+		c.namesize = 1 + sprintf(thispath, "initramfs_test_many-%d", i);
+		p += fill_cpio(&c, 1, false, p);
+	}
+
+	len = p - cpio_srcbuf;
+	err = unpack_to_rootfs(cpio_srcbuf, len);
+	KUNIT_EXPECT_NULL(test, err);
+
+	for (i = 0; i < INITRAMFS_TEST_MANY_LIMIT; i++) {
+		sprintf(thispath, "initramfs_test_many-%d", i);
+		KUNIT_EXPECT_EQ(test, init_unlink(thispath), 0);
+	}
+
+	kfree(cpio_srcbuf);
+}
+
+/*
+ * An initramfs filename is namesize in length, including the zero-terminator.
+ * A filename can be zero-terminated prior to namesize, with the remainder used
+ * as padding. This can be useful for e.g. alignment of file data segments with
+ * a 4KB filesystem block, allowing for extent sharing (reflinks) between cpio
+ * source and destination. This hack works with both GNU cpio and initramfs, as
+ * long as PATH_MAX isn't exceeded.
+ */
+static void __init initramfs_test_fname_pad(struct kunit *test)
+{
+	char *err;
+	size_t len;
+	struct file *file;
+	char fdata[] = "this file data is aligned at 4K in the archive";
+	struct test_fname_pad {
+		char padded_fname[4096 - CPIO_HDRLEN];
+		char cpio_srcbuf[CPIO_HDRLEN + PATH_MAX + 3 + sizeof(fdata)];
+	} *tbufs = kzalloc_obj(struct test_fname_pad);
+	struct initramfs_test_cpio c[] = { {
+		.magic = "070701",
+		.ino = 1,
+		.mode = S_IFREG | 0777,
+		.uid = 0,
+		.gid = 0,
+		.nlink = 1,
+		.mtime = 1,
+		.filesize = sizeof(fdata),
+		.devmajor = 0,
+		.devminor = 1,
+		.rdevmajor = 0,
+		.rdevminor = 0,
+		/* align file data at 4K archive offset via padded fname */
+		.namesize = 4096 - CPIO_HDRLEN,
+		.csum = 0,
+		.fname = tbufs->padded_fname,
+		.data = fdata,
+	} };
+
+	memcpy(tbufs->padded_fname, "padded_fname", sizeof("padded_fname"));
+	len = fill_cpio(c, ARRAY_SIZE(c), false, tbufs->cpio_srcbuf);
+
+	err = unpack_to_rootfs(tbufs->cpio_srcbuf, len);
+	KUNIT_EXPECT_NULL(test, err);
+
+	file = filp_open(c[0].fname, O_RDONLY, 0);
+	if (IS_ERR(file)) {
+		KUNIT_FAIL(test, "open failed");
+		goto out;
+	}
+
+	/* read back file contents into @cpio_srcbuf and confirm match */
+	len = kernel_read(file, tbufs->cpio_srcbuf, c[0].filesize, NULL);
+	KUNIT_EXPECT_EQ(test, len, c[0].filesize);
+	KUNIT_EXPECT_MEMEQ(test, tbufs->cpio_srcbuf, c[0].data, len);
+
+	fput(file);
+	KUNIT_EXPECT_EQ(test, init_unlink(c[0].fname), 0);
+out:
+	kfree(tbufs);
+}
+
+static void __init initramfs_test_fname_path_max(struct kunit *test)
+{
+	char *err;
+	size_t len;
+	struct kstat st0 = {}, st1 = {};
+	char fdata[] = "this file data will not be unpacked";
+	struct test_fname_path_max {
+		char fname_oversize[PATH_MAX + 1];
+		char fname_ok[PATH_MAX];
+		char cpio_src[(CPIO_HDRLEN + PATH_MAX + 3 + sizeof(fdata)) * 2];
+	} *tbufs = kzalloc_obj(struct test_fname_path_max);
+	struct initramfs_test_cpio c[] = { {
+		.magic = "070701",
+		.ino = 1,
+		.mode = S_IFDIR | 0777,
+		.nlink = 1,
+		.namesize = sizeof(tbufs->fname_oversize),
+		.fname = tbufs->fname_oversize,
+		.filesize = sizeof(fdata),
+		.data = fdata,
+	}, {
+		.magic = "070701",
+		.ino = 2,
+		.mode = S_IFDIR | 0777,
+		.nlink = 1,
+		.namesize = sizeof(tbufs->fname_ok),
+		.fname = tbufs->fname_ok,
+	} };
+
+	memset(tbufs->fname_oversize, '/', sizeof(tbufs->fname_oversize) - 1);
+	memset(tbufs->fname_ok, '/', sizeof(tbufs->fname_ok) - 1);
+	memcpy(tbufs->fname_oversize, "fname_oversize",
+	       sizeof("fname_oversize") - 1);
+	memcpy(tbufs->fname_ok, "fname_ok", sizeof("fname_ok") - 1);
+	len = fill_cpio(c, ARRAY_SIZE(c), false, tbufs->cpio_src);
+
+	/* unpack skips over fname_oversize instead of returning an error */
+	err = unpack_to_rootfs(tbufs->cpio_src, len);
+	KUNIT_EXPECT_NULL(test, err);
+
+	KUNIT_EXPECT_EQ(test, init_stat("fname_oversize", &st0, 0), -ENOENT);
+	KUNIT_EXPECT_EQ(test, init_stat("fname_ok", &st1, 0), 0);
+	KUNIT_EXPECT_EQ(test, init_rmdir("fname_ok"), 0);
+
+	kfree(tbufs);
+}
+
+static void __init initramfs_test_hdr_hex(struct kunit *test)
+{
+	char *err;
+	size_t len;
+	char fdata[] = "this file data will not be unpacked";
+	struct initramfs_test_bufs {
+		char cpio_src[(CPIO_HDRLEN + PATH_MAX + 3 + sizeof(fdata)) * 2];
+	} *tbufs = kzalloc(sizeof(struct initramfs_test_bufs), GFP_KERNEL);
+	struct initramfs_test_cpio c[] = { {
+		.magic = "070701",
+		.ino = 1,
+		.mode = S_IFREG | 0777,
+		.uid = 0x123456,
+		.gid = 0x123457,
+		.nlink = 1,
+		.namesize = sizeof("initramfs_test_hdr_hex_0"),
+		.fname = "initramfs_test_hdr_hex_0",
+		.filesize = sizeof(fdata),
+		.data = fdata,
+	}, {
+		.magic = "070701",
+		.ino = 2,
+		.mode = S_IFDIR | 0777,
+		.uid = 0x000056,
+		.gid = 0x000057,
+		.nlink = 1,
+		.namesize = sizeof("initramfs_test_hdr_hex_1"),
+		.fname = "initramfs_test_hdr_hex_1",
+	} };
+
+	/* inject_ox=true to add "0x" cpio field prefixes */
+	len = fill_cpio(c, ARRAY_SIZE(c), true, tbufs->cpio_src);
+
+	err = unpack_to_rootfs(tbufs->cpio_src, len);
+	KUNIT_EXPECT_NOT_NULL(test, err);
+
+	kfree(tbufs);
+}
+
+/*
+ * The kunit_case/_suite struct cannot be marked as __initdata as this will be
+ * used in debugfs to retrieve results after test has run.
+ */
+static struct kunit_case __refdata initramfs_test_cases[] = {
+	KUNIT_CASE(initramfs_test_extract),
+	KUNIT_CASE(initramfs_test_fname_overrun),
+	KUNIT_CASE(initramfs_test_data),
+	KUNIT_CASE(initramfs_test_csum),
+	KUNIT_CASE(initramfs_test_hardlink),
+	KUNIT_CASE(initramfs_test_many),
+	KUNIT_CASE(initramfs_test_fname_pad),
+	KUNIT_CASE(initramfs_test_fname_path_max),
+	KUNIT_CASE(initramfs_test_hdr_hex),
+	{},
+};
+
+static int __init initramfs_test_init(struct kunit_suite *suite)
+{
+	/*
+	 * unpack_to_rootfs() uses module-static state (victim, byte_count,
+	 * state, ...). The boot-time async do_populate_rootfs() may still be
+	 * running, so wait for it to finish before we call unpack_to_rootfs()
+	 * from the test thread, otherwise the two writers race and crash.
+	 */
+	wait_for_initramfs();
+	return 0;
+}
+
+static struct kunit_suite __refdata initramfs_test_suite = {
+	.name = "initramfs",
+	.suite_init = initramfs_test_init,
+	.test_cases = initramfs_test_cases,
+};
+kunit_test_init_section_suites(&initramfs_test_suite);
+
+MODULE_DESCRIPTION("Initramfs KUnit test suite");
+MODULE_LICENSE("GPL v2");

linux-7.2.3/init/noinitramfs.c

@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * init/noinitramfs.c
+ *
+ * Copyright (C) 2006, NXP Semiconductors, All Rights Reserved
+ * Author: Jean-Paul Saman <jean-paul.saman@nxp.com>
+ */
+#include <linux/init.h>
+#include <linux/stat.h>
+#include <linux/kdev_t.h>
+#include <linux/syscalls.h>
+#include <linux/init_syscalls.h>
+#include <linux/umh.h>
+
+/*
+ * Create a simple rootfs that is similar to the default initramfs
+ */
+static int __init default_rootfs(void)
+{
+	int err;
+
+	usermodehelper_enable();
+	err = init_mkdir("/dev", 0755);
+	if (err < 0)
+		goto out;
+
+	err = init_mknod("/dev/console", S_IFCHR | S_IRUSR | S_IWUSR,
+			new_encode_dev(MKDEV(5, 1)));
+	if (err < 0)
+		goto out;
+
+	err = init_mkdir("/root", 0700);
+	if (err < 0)
+		goto out;
+
+	return 0;
+
+out:
+	printk(KERN_WARNING "Failed to create a rootfs\n");
+	return err;
+}
+rootfs_initcall(default_rootfs);

linux-7.2.3/init/version-timestamp.c

@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <generated/compile.h>
+#include <generated/utsrelease.h>
+#include <linux/proc_ns.h>
+#include <linux/refcount.h>
+#include <linux/uts.h>
+#include <linux/utsname.h>
+
+struct uts_namespace init_uts_ns = {
+	.ns = NS_COMMON_INIT(init_uts_ns),
+	.name = {
+		.sysname	= UTS_SYSNAME,
+		.nodename	= UTS_NODENAME,
+		.release	= UTS_RELEASE,
+		.version	= UTS_VERSION,
+		.machine	= UTS_MACHINE,
+		.domainname	= UTS_DOMAINNAME,
+	},
+	.user_ns = &init_user_ns,
+};
+
+/* FIXED STRINGS! Don't touch! */
+const char linux_banner[] =
+	"Linux version " UTS_RELEASE " (" LINUX_COMPILE_BY "@"
+	LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION "\n";

linux-7.2.3/init/version.c

@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  linux/init/version.c
+ *
+ *  Copyright (C) 1992  Theodore Ts'o
+ *
+ *  May be freely distributed as part of Linux.
+ */
+
+#include <generated/compile.h>
+#include <linux/build-salt.h>
+#include <linux/elfnote-lto.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/printk.h>
+#include <linux/uts.h>
+#include <linux/utsname.h>
+#include <linux/proc_ns.h>
+
+static int __init early_hostname(char *arg)
+{
+	size_t bufsize = sizeof(init_uts_ns.name.nodename);
+	size_t maxlen  = bufsize - 1;
+	ssize_t arglen;
+
+	arglen = strscpy(init_uts_ns.name.nodename, arg, bufsize);
+	if (arglen < 0) {
+		pr_warn("hostname parameter exceeds %zd characters and will be truncated",
+			maxlen);
+	}
+	return 0;
+}
+early_param("hostname", early_hostname);
+
+const char linux_proc_banner[] =
+	"%s version %s"
+	" (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ")"
+	" (" LINUX_COMPILER ") %s\n";
+
+BUILD_SALT;
+BUILD_LTO_INFO;
+
+/*
+ * init_uts_ns and linux_banner contain the build version and timestamp,
+ * which are really fixed at the very last step of build process.
+ * They are compiled with __weak first, and without __weak later.
+ */
+
+struct uts_namespace init_uts_ns __weak;
+const char linux_banner[] __weak;
+
+#include "version-timestamp.c"
+
+EXPORT_SYMBOL_GPL(init_uts_ns);