[PATCH v4 3/3] init: add support to directly boot to a mapped device

[Will Drewry]

This change adds a dm= kernel parameter modeled after the md= parameter
from do_mounts_md.  It allows for simple device-mapper targets to be
configured at boot time for use early in the boot process (as the root
device or otherwise).

The format is as follows:
  dm="name uuid|none ro|rw, table line 1, table line 2, ..."

It relies on the ability to create a device mapper device programmatically and
bind that device to the ioctl-style name/uuid.  In addition, any
/dev/...  devices specified in the target parameters will attempt to be
early-resolved with name_to_dev_t.

v4:
- introduces early device resolving with name_to_dev_t,
- moves to 'ro' and 'rw' from 0 and non-zero for read-only

Signed-off-by: Will Drewry <wad@xxxxxxxxxxxx>
---
 Documentation/device-mapper/boot.txt |   42 ++++
 Documentation/kernel-parameters.txt  |    4 +
 init/Makefile                        |    1 +
 init/do_mounts.c                     |    1 +
 init/do_mounts.h                     |   10 +
 init/do_mounts_dm.c                  |  414 ++++++++++++++++++++++++++++++++++
 6 files changed, 472 insertions(+), 0 deletions(-)
 create mode 100644 Documentation/device-mapper/boot.txt
 create mode 100644 init/do_mounts_dm.c

diff --git a/Documentation/device-mapper/boot.txt b/Documentation/device-mapper/boot.txt
new file mode 100644
index 0000000..76ea6ac
--- /dev/null
+++ b/Documentation/device-mapper/boot.txt
@@ -0,0 +1,42 @@
+Boot time creation of mapped devices
+===================================
+
+It is possible to configure a device mapper device to act as the root
+device for your system in two ways.
+
+The first is to build an initial ramdisk which boots to a minimal
+userspace which configures the device, then pivot_root(8) in to it.
+
+For simple device mapper configurations, it is possible to boot directly
+using the following kernel command line:
+
+dm="<name> <uuid> <ro>,table line 1,...,table line n"
+
+name = the name to associate with the device
+	after boot, udev, if used, will use that name to label
+	the device node.
+uuid = may be 'none' or the UUID desired for the device.
+ro = may be 'ro' or 'rw'.  If 'ro', the device and device table will be
+	marked read-only.
+
+Each table line may be as normal when using the dmsetup tool except for
+two variations:
+1. Any use of commas will be interpreted as a newline
+2. Quotation marks cannot be escaped and cannot be used without
+   terminating the dm= argument.
+
+Unless renamed by udev, the device node created will be dm-0 as the
+first minor number for the device-mapper is used during early creation.
+
+Example
+=======
+
+- Booting to a linear array made up of user-mode linux block devices:
+
+  dm="lroot none 0, 0 4096 linear 98:16 0, 4096 4096 linear 98:32 0" \
+  root=/dev/dm-0
+
+Will boot to a rw dm-linear target of 8192 sectors split across two
+block devices identified by their major:minor numbers.  After boot, udev
+will rename this target to /dev/mapper/lroot (depending on the rules).
+No uuid was assigned.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 1808f11..01d85c9 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -43,6 +43,7 @@ parameter is applicable:
 	AVR32	AVR32 architecture is enabled.
 	AX25	Appropriate AX.25 support is enabled.
 	BLACKFIN Blackfin architecture is enabled.
+	DM	Device mapper support is enabled.
 	DRM	Direct Rendering Management support is enabled.
 	EDD	BIOS Enhanced Disk Drive Services (EDD) is enabled
 	EFI	EFI Partitioning (GPT) is enabled
@@ -655,6 +656,9 @@ and is between 256 and 4096 characters. It is defined in the file
 			Disable PIN 1 of APIC timer
 			Can be useful to work around chipset bugs.
 
+	dm=		[DM] Allows early creation of a device-mapper device.
+			See Documentation/device-mapper/boot.txt.
+
 	dmasound=	[HW,OSS] Sound subsystem buffers
 
 	dma_debug=off	If the kernel is compiled with DMA_API_DEBUG support,
diff --git a/init/Makefile b/init/Makefile
index 0bf677a..1677baa 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -14,6 +14,7 @@ mounts-y			:= do_mounts.o
 mounts-$(CONFIG_BLK_DEV_RAM)	+= do_mounts_rd.o
 mounts-$(CONFIG_BLK_DEV_INITRD)	+= do_mounts_initrd.o
 mounts-$(CONFIG_BLK_DEV_MD)	+= do_mounts_md.o
+mounts-$(CONFIG_BLK_DEV_DM)	+= do_mounts_dm.o
 
 # dependencies on generated files need to be listed explicitly
 $(obj)/version.o: include/generated/compile.h
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 02e3ca4..0848a5b 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -383,6 +383,7 @@ void __init prepare_namespace(void)
 	wait_for_device_probe();
 
 	md_run_setup();
+	dm_run_setup();
 
 	if (saved_root_name[0]) {
 		root_device_name = saved_root_name;
diff --git a/init/do_mounts.h b/init/do_mounts.h
index f5b978a..09d2286 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -74,3 +74,13 @@ void md_run_setup(void);
 static inline void md_run_setup(void) {}
 
 #endif
+
+#ifdef CONFIG_BLK_DEV_DM
+
+void dm_run_setup(void);
+
+#else
+
+static inline void dm_run_setup(void) {}
+
+#endif
diff --git a/init/do_mounts_dm.c b/init/do_mounts_dm.c
new file mode 100644
index 0000000..b342f8f
--- /dev/null
+++ b/init/do_mounts_dm.c
@@ -0,0 +1,414 @@
+/* do_mounts_dm.c
+ * Copyright (C) 2010 The Chromium OS Authors <chromium-os-dev@xxxxxxxxxxxx>
+ *                    All Rights Reserved.
+ * Based on do_mounts_md.c
+ *
+ * This file is released under the GPL.
+ */
+#include <linux/device-mapper.h>
+#include <linux/fs.h>
+#include <linux/string.h>
+
+#include "do_mounts.h"
+
+#define DM_MAX_NAME 32
+#define DM_MAX_UUID 129
+#define DM_NO_UUID "none"
+
+#define DM_MSG_PREFIX "init"
+
+/* Separators used for parsing the dm= argument. */
+#define DM_FIELD_SEP ' '
+#define DM_LINE_SEP ','
+
+/*
+ * When the device-mapper and any targets are compiled into the kernel
+ * (not a module), one target may be created and used as the root device at
+ * boot time with the parameters given with the boot line dm=...
+ * The code for that is here.
+ */
+
+struct dm_setup_target {
+	sector_t begin;
+	sector_t length;
+	char *type;
+	char *params;
+	/* simple singly linked list */
+	struct dm_setup_target *next;
+};
+
+static struct {
+	int minor;
+	int ro;
+	char name[DM_MAX_NAME];
+	char uuid[DM_MAX_UUID];
+	char *targets;
+	struct dm_setup_target *target;
+	int target_count;
+} dm_setup_args __initdata;
+
+static __initdata int dm_early_setup;
+
+static size_t __init get_dm_option(char *str, char **next, char sep)
+{
+	size_t len = 0;
+	char *endp = NULL;
+
+	if (!str)
+		return 0;
+
+	endp = strchr(str, sep);
+	if (!endp) {  /* act like strchrnul */
+		len = strlen(str);
+		endp = str + len;
+	} else {
+		len = endp - str;
+	}
+
+	if (endp == str)
+		return 0;
+
+	if (!next)
+		return len;
+
+	if (*endp == 0) {
+		/* Don't advance past the nul. */
+		*next = endp;
+	} else {
+		*next = endp + 1;
+	}
+	return len;
+}
+
+static int __init dm_setup_args_init(void)
+{
+	dm_setup_args.minor = 0;
+	dm_setup_args.ro = 0;
+	dm_setup_args.target = NULL;
+	dm_setup_args.target_count = 0;
+	return 0;
+}
+
+static int __init dm_setup_cleanup(void)
+{
+	struct dm_setup_target *target = dm_setup_args.target;
+	struct dm_setup_target *old_target = NULL;
+	while (target) {
+		kfree(target->type);
+		kfree(target->params);
+		old_target = target;
+		target = target->next;
+		kfree(old_target);
+		dm_setup_args.target_count--;
+	}
+	BUG_ON(dm_setup_args.target_count);
+	return 0;
+}
+
+static char * __init dm_setup_parse_device_args(char *str)
+{
+	char *next = NULL;
+	size_t len = 0;
+
+	/* Grab the logical name of the device to be exported to udev */
+	len = get_dm_option(str, &next, DM_FIELD_SEP);
+	if (!len) {
+		DMERR("failed to parse device name");
+		goto parse_fail;
+	}
+	len = min(len + 1, sizeof(dm_setup_args.name));
+	strlcpy(dm_setup_args.name, str, len);  /* includes nul */
+	str = skip_spaces(next);
+
+	/* Grab the UUID value or "none" */
+	len = get_dm_option(str, &next, DM_FIELD_SEP);
+	if (!len) {
+		DMERR("failed to parse device uuid");
+		goto parse_fail;
+	}
+	len = min(len + 1, sizeof(dm_setup_args.uuid));
+	strlcpy(dm_setup_args.uuid, str, len);
+	str = skip_spaces(next);
+
+	/* Determine if the table/device will be read onyl or read-write */
+	if (!strncmp("ro,", str, 3)) {
+		dm_setup_args.ro = 1;
+	} else if (!strncmp("rw,", str, 3)) {
+		dm_setup_args.ro = 0;
+	} else {
+		DMERR("failed to parse table mode");
+		goto parse_fail;
+	}
+	str = skip_spaces(str + 3);
+
+	return str;
+
+parse_fail:
+	return NULL;
+}
+
+static void __init dm_substitute_devices(char *str, size_t str_len)
+{
+	char *candidate = str;
+	char *candidate_end = str;
+	char old_char;
+	size_t len = 0;
+	dev_t dev;
+
+	if (str_len < 3)
+		return;
+
+	while (str && *str) {
+		candidate = strchr(str, '/');
+		if (!candidate)
+			break;
+
+		/* Avoid embedded slashes */
+		if (candidate != str && *(candidate - 1) != DM_FIELD_SEP) {
+			str = strchr(candidate, DM_FIELD_SEP);
+			continue;
+		}
+
+		len = get_dm_option(candidate, &candidate_end, DM_FIELD_SEP);
+		str = skip_spaces(candidate_end);
+		if (len < 3)  /* maj:mix min */
+			continue;
+
+		/* Temporarily terminate with a nul */
+		candidate_end--;
+		old_char = *candidate_end;
+		*candidate_end = '\0';
+
+		DMDEBUG("converting candidate device '%s' to dev_t", candidate);
+		/* Use the boot-time specific device naming */
+		dev = name_to_dev_t(candidate);
+		*candidate_end = old_char;
+
+		DMDEBUG(" -> %u", dev);
+		/* No suitable replacement found */
+		if (!dev)
+			continue;
+
+		/* Rewrite the /dev/path as a major:minor */
+		len = snprintf(candidate, len, "%u:%u", MAJOR(dev), MINOR(dev));
+		if (!len) {
+			DMERR("error substituting device major/minor.");
+			break;
+		}
+		candidate += len;
+		/* Pad out with spaces (fixing our nul) */
+		while (candidate < candidate_end)
+			*(candidate++) = DM_FIELD_SEP;
+	}
+}
+
+static int __init dm_setup_parse_targets(char *str)
+{
+	char *next = NULL;
+	size_t len = 0;
+	struct dm_setup_target **target = NULL;
+
+	/* Targets are defined as per the table format but with a
+	 * comma as a newline separator.
+	 */
+	target = &dm_setup_args.target;
+	while (str && *str) {
+		*target = kzalloc(sizeof(struct dm_setup_target), GFP_KERNEL);
+		if (!*target) {
+			DMERR("failed to allocate memory for target %d",
+			      dm_setup_args.target_count);
+			goto parse_fail;
+		}
+		dm_setup_args.target_count++;
+
+		(*target)->begin = simple_strtoull(str, &next, 10);
+		if (!next || *next != DM_FIELD_SEP) {
+			DMERR("failed to parse starting sector for target %d",
+			      dm_setup_args.target_count - 1);
+			goto parse_fail;
+		}
+		str = skip_spaces(next + 1);
+
+		(*target)->length = simple_strtoull(str, &next, 10);
+		if (!next || *next != DM_FIELD_SEP) {
+			DMERR("failed to parse length for target %d",
+			      dm_setup_args.target_count - 1);
+			goto parse_fail;
+		}
+		str = skip_spaces(next + 1);
+
+		len = get_dm_option(str, &next, DM_FIELD_SEP);
+		if (!len ||
+		    !((*target)->type = kstrndup(str, len, GFP_KERNEL))) {
+			DMERR("failed to parse type for target %d",
+			      dm_setup_args.target_count - 1);
+			goto parse_fail;
+		}
+		str = skip_spaces(next);
+
+		len = get_dm_option(str, &next, DM_LINE_SEP);
+		if (!len ||
+		    !((*target)->params = kstrndup(str, len, GFP_KERNEL))) {
+			DMERR("failed to parse params for target %d",
+			      dm_setup_args.target_count - 1);
+			goto parse_fail;
+		}
+		str = skip_spaces(next);
+
+		/* Before moving on, walk through the copied target and
+		 * attempt to replace all /dev/xxx with the major:minor number.
+		 * It may not be possible to resolve them traditionally at
+		 * boot-time.
+		 */
+		dm_substitute_devices((*target)->params, len);
+
+		target = &((*target)->next);
+	}
+	DMDEBUG("parsed %d targets", dm_setup_args.target_count);
+
+	return 0;
+
+parse_fail:
+	return 1;
+}
+
+/*
+ * Parse the command-line parameters given our kernel, but do not
+ * actually try to invoke the DM device now; that is handled by
+ * dm_setup_drive after the low-level disk drivers have initialised.
+ * dm format is as follows:
+ *  dm="name uuid fmode,[table line 1],[table line 2],..."
+ * May be used with root=/dev/dm-0 as it always uses the first dm minor.
+ */
+
+static int __init dm_setup(char *str)
+{
+	dm_setup_args_init();
+
+	str = dm_setup_parse_device_args(str);
+	if (!str) {
+		DMDEBUG("str is NULL");
+		goto parse_fail;
+	}
+
+	/* Target parsing is delayed until we have dynamic memory */
+	dm_setup_args.targets = str;
+
+	printk(KERN_INFO "dm: will configure '%s' on dm-%d\n",
+	       dm_setup_args.name, dm_setup_args.minor);
+
+	dm_early_setup = 1;
+	return 1;
+
+parse_fail:
+	printk(KERN_WARNING "dm: Invalid arguments supplied to dm=.\n");
+	return 0;
+}
+
+
+static void __init dm_setup_drive(void)
+{
+	struct mapped_device *md = NULL;
+	struct dm_table *table = NULL;
+	struct dm_setup_target *target;
+	char *uuid = dm_setup_args.uuid;
+	fmode_t fmode = FMODE_READ;
+
+	/* Finish parsing the targets. */
+	if (dm_setup_parse_targets(dm_setup_args.targets))
+		goto parse_fail;
+
+	if (dm_create(dm_setup_args.minor, &md)) {
+		DMDEBUG("failed to create the device");
+		goto dm_create_fail;
+	}
+	DMDEBUG("created device '%s'", dm_device_name(md));
+
+	/* In addition to flagging the table below, the disk must be
+	 * set explicitly ro/rw.
+	 */
+	set_disk_ro(dm_disk(md), dm_setup_args.ro);
+
+	if (!dm_setup_args.ro)
+		fmode |= FMODE_WRITE;
+	if (dm_table_create(&table, fmode, dm_setup_args.target_count, md)) {
+		DMDEBUG("failed to create the table");
+		goto dm_table_create_fail;
+	}
+
+	target = dm_setup_args.target;
+	while (target) {
+		DMINFO("adding target '%llu %llu %s %s'",
+		       (unsigned long long) target->begin,
+		       (unsigned long long) target->length, target->type,
+		       target->params);
+		if (dm_table_add_target(table, target->type, target->begin,
+					target->length, target->params)) {
+			DMDEBUG("failed to add the target to the table");
+			goto add_target_fail;
+		}
+		target = target->next;
+	}
+
+	if (dm_table_complete(table)) {
+		DMDEBUG("failed to complete the table");
+		goto table_complete_fail;
+	}
+
+	/* Suspend the device so that we can bind it to the table. */
+	if (dm_suspend(md, 0)) {
+		DMDEBUG("failed to suspend the device pre-bind");
+		goto suspend_fail;
+	}
+
+	/* Bind the table to the device. This is the only way to associate
+	 * md->map with the table and set the disk capacity directly.
+	 */
+	if (dm_swap_table(md, table)) {  /* should return NULL. */
+		DMDEBUG("failed to bind the device to the table");
+		goto table_bind_fail;
+	}
+	
+	/* Finally, resume and the device should be ready. */
+	if (dm_resume(md)) {
+		DMDEBUG("failed to resume the device");
+		goto resume_fail;
+	}
+
+	/* Export the dm device via the ioctl interface */
+	if (!strcmp(DM_NO_UUID, dm_setup_args.uuid))
+		uuid = NULL;
+	if (dm_ioctl_export(md, dm_setup_args.name, uuid)) {
+		DMDEBUG("failed to export device with given name and uuid");
+		goto export_fail;
+	}
+	printk(KERN_INFO "dm: dm-%d is ready\n", dm_setup_args.minor);
+
+	dm_setup_cleanup();
+	return;
+
+export_fail:
+resume_fail:
+table_bind_fail:
+suspend_fail:
+table_complete_fail:
+add_target_fail:
+	dm_table_put(table);
+dm_table_create_fail:
+	dm_put(md);
+dm_create_fail:
+	dm_setup_cleanup();
+parse_fail:
+	printk(KERN_WARNING "dm: starting dm-%d (%s) failed\n",
+	       dm_setup_args.minor, dm_setup_args.name);
+}
+
+__setup("dm=", dm_setup);
+
+void __init dm_run_setup(void)
+{
+	if (!dm_early_setup)
+		return;
+	printk(KERN_INFO "dm: attempting early device configuration.\n");
+	dm_setup_drive();
+}
-- 
1.7.0.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/