Re: [PATCH 1/4] init: Add a new root device option, the Ceph filesystem

[Sage Weil]

[adding linux-fsdevel]

Hi Mark!

There was a question on this thread earlier about whether it makes sense 
to support this in-kernel or make users build an initrd.  This looks 
pretty simple to me and is certainly easier for users, so (with some 
adjustments) I'm happy with it, but I think the folks on 
linux-fsdevel may have a more informed opinion than do.

See below for a few comments...

On Wed, 20 Nov 2013, mark.doffman@xxxxxxxxxxxxxxx wrote:
> From: Mark Doffman <mark.doffman@xxxxxxxxxxxxxxx>
> 
> Analogous to NFS add a new root device option, the ability
> to boot using the Ceph networked file system as the root fs.
> 
> This patch adds a new root device option '/dev/ceph' that
> uses a ceph networked file system. File system parameters
> are passed using a new kernel parameter: 'cephroot'.
> 
> The 'cephroot' parameters are very similar to 'nfsroot'.
> 
> Signed-off-by: Mark Doffman <mark.doffman@xxxxxxxxxxxxxxx>
> Reviewed-by: Ian Molton <ian.molton@xxxxxxxxxxxxxxx>
> ---
>  fs/ceph/Kconfig                |  10 +++
>  fs/ceph/Makefile               |   1 +
>  fs/ceph/root.c                 | 163 +++++++++++++++++++++++++++++++++++++++++
>  include/linux/ceph/ceph_root.h |  10 +++
>  include/linux/root_dev.h       |   1 +
>  init/do_mounts.c               |  32 +++++++-
>  6 files changed, 216 insertions(+), 1 deletion(-)
>  create mode 100644 fs/ceph/root.c
>  create mode 100644 include/linux/ceph/ceph_root.h
> 
> diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
> index ac9a2ef..325e83d 100644
> --- a/fs/ceph/Kconfig
> +++ b/fs/ceph/Kconfig
> @@ -25,3 +25,13 @@ config CEPH_FSCACHE
>  	  caching support for Ceph clients using FS-Cache
>  
>  endif
> +
> +config ROOT_CEPH
> +	bool "Root file system on Ceph FS"
> +	depends on CEPH_FS=y && IP_PNP
> +	help
> +	  If you want your system to mount its root file system via CEPH,
> +	  choose Y here.  For details, read
> +	  <file:Documentation/filesystems/ceph/cephroot.txt>.
> +
> +	  If unsure say N.
> diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile
> index 32e3010..af2dcbf 100644
> --- a/fs/ceph/Makefile
> +++ b/fs/ceph/Makefile
> @@ -10,3 +10,4 @@ ceph-y := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
>  	debugfs.o
>  
>  ceph-$(CONFIG_CEPH_FSCACHE) += cache.o
> +ceph-$(CONFIG_ROOT_CEPH) += root.o
> diff --git a/fs/ceph/root.c b/fs/ceph/root.c
> new file mode 100644
> index 0000000..bff67fb
> --- /dev/null
> +++ b/fs/ceph/root.c
> @@ -0,0 +1,163 @@
> +/*
> + * Copyright (C) 2012 Codethink Ltd. <mark.doffman@xxxxxxxxxxxxxxx>
> + *
> + * This file is released under the GPL v2
> + *
> + * Allow a CephFS filesystem to be mounted as root.
> + */
> +
> +#include <linux/kernel.h>
> +#include <linux/types.h>
> +#include <linux/string.h>
> +#include <linux/init.h>
> +#include <linux/slab.h>
> +#include <linux/utsname.h>
> +#include <linux/root_dev.h>
> +#include <linux/in.h>
> +#include <net/ipconfig.h>
> +#include <linux/ceph/ceph_root.h>
> +
> +/* linux/net/ipv4/ipconfig.c: trims ip addr off front of name, too. */
> +extern __be32 root_nfs_parse_addr(char *name); /*__init*/
> +
> +#define MAXPATHLEN 1024
> +
> +/* Parameters passed from the kernel command line */
> +static char ceph_root_params[256] __initdata;
> +
> +/* Address of CEPH server */
> +static __be32 servaddr __initdata = htonl(INADDR_NONE);

IPv4 only?

> +
> +/* Name of directory to mount */
> +static char ceph_export_path[MAXPATHLEN + 1] __initdata;
> +
> +/* Text-based mount options */
> +static char ceph_root_options[256] __initdata;
> +
> +/* server:path string passed to mount */
> +static char ceph_root_device[MAXPATHLEN + 1] __initdata;
> +
> +/* Address of CEPH server */
> +static __be32 root_ceph_server_addr = htonl(INADDR_NONE);
> +
> +/*
> + * Parse out root export path and mount options from
> + * passed-in string @incoming.
> + *
> + * Copy the export path into @exppath.
> + *
> + * Returns 0 on success -E2BIG if the resulting options string is too long.
> + */
> +static int __init root_ceph_parse_options(char *incoming, char *exppath,
> +						const size_t exppathlen)
> +{
> +	char *p;
> +	int res = 0;
> +
> +	/*
> +	 * Set the remote path
> +	 */
> +	p = strsep(&incoming, ",");
> +	if (*p != '\0' && strcmp(p, "default") != 0)
> +		strlcpy(exppath, p, exppathlen);
> +
> +	/*
> +	 * @incoming now points to the rest of the string; if it
> +	 * contains something, append it to our root options buffer
> +	 */
> +	if (incoming != NULL && *incoming != '\0') {
> +		size_t len = strlen(ceph_root_options);
> +		size_t destlen = sizeof(ceph_root_options);
> +
> +		if (len && ceph_root_options[len - 1] != ',') {
> +			if (strlcat(ceph_root_options, ",", destlen) > destlen)
> +				res = -E2BIG;
> +		}
> +
> +		if (strlcat(ceph_root_options, incoming, destlen) > destlen)
> +			res = -E2BIG;
> +
> +	}
> +	return res;
> +}
> +
> +/*
> + *  Parse CephFS server and directory information passed on the kernel
> + *  command line.
> + *
> + *  cephroot=[<server-ip>:]<root-dir>[,<cephfs-options>]
> + */

I think we would be better off using the parsing code in fs/ceph/super.c, 
which handles both IPv4 and IPv6, and more importantly lets you provide a 
list of monitors.  Providing only a single server IP makes it a single 
point of failure during mount (though of course if/when we connect we will 
discover the current set of mons).

Attaching the options at the end doesn't appeal to me cosmetically, but I 
can see how it's useful to have it all in a single string that DHCP can 
provide.

sage


> +static int __init ceph_root_setup(char *line)
> +{
> +	ROOT_DEV = Root_CEPH;
> +
> +	strlcpy(ceph_root_params, line, sizeof(ceph_root_params));
> +
> +	/*
> +	 * Note: root_nfs_parse_addr() removes the server-ip from
> +	 * ceph_root_params, if it exists.
> +	 */
> +	root_ceph_server_addr = root_nfs_parse_addr(ceph_root_params);
> +
> +	return 1;
> +}
> +
> +__setup("cephroot=", ceph_root_setup);
> +
> +/*
> + * ceph_root_data - Return mount device and data for CEPHROOT mount.
> + *
> + * @root_device: OUT: Address of string containing CEPHROOT device.
> + * @root_data: OUT: Address of string containing CEPHROOT mount options.
> + *
> + * Returns: 0 and sets @root_device and @root_data if successful.
> + *          error code if unsuccessful.
> + */
> +int __init ceph_root_data(char **root_device, char **root_data)
> +{
> +	char *tmp = NULL;
> +	const size_t tmplen = sizeof(ceph_export_path);
> +	int len;
> +	int ret = -E2BIG;
> +
> +	servaddr = root_ceph_server_addr;
> +	if (servaddr == htonl(INADDR_NONE))
> +		return -ENOENT;
> +
> +	tmp = kzalloc(tmplen, GFP_KERNEL);
> +	if (tmp == NULL)
> +		return -ENOMEM;
> +
> +	if (ceph_root_params[0] != '\0') {
> +		if (root_ceph_parse_options(ceph_root_params, tmp, tmplen))
> +			goto out;
> +	}
> +
> +	/*
> +	 * Set up ceph_root_device. This looks like: server:/path
> +	 *
> +	 * At this point, utsname()->nodename contains our local
> +	 * IP address or hostname, set by ipconfig.  If "%s" exists
> +	 * in tmp, substitute the nodename, then shovel the whole
> +	 * mess into ceph_root_device.
> +	 */
> +	len = snprintf(ceph_export_path, sizeof(ceph_export_path),
> +				tmp, utsname()->nodename);
> +	if (len > (int)sizeof(ceph_export_path))
> +		goto out;
> +	len = snprintf(ceph_root_device, sizeof(ceph_root_device),
> +				"%pI4:%s", &servaddr, ceph_export_path);
> +	if (len > (int)sizeof(ceph_root_device))
> +		goto out;
> +
> +	pr_debug("Root-CEPH: Root device: %s\n", ceph_root_device);
> +	pr_debug("Root-CEPH: Root options: %s\n", ceph_root_options);
> +	*root_device = ceph_root_device;
> +	*root_data = ceph_root_options;
> +
> +	ret = 0;
> +
> +out:
> +	kfree(tmp);
> +	return ret;
> +}
> diff --git a/include/linux/ceph/ceph_root.h b/include/linux/ceph/ceph_root.h
> new file mode 100644
> index 0000000..e6bae63
> --- /dev/null
> +++ b/include/linux/ceph/ceph_root.h
> @@ -0,0 +1,10 @@
> +/*
> + * Copyright (C) 2012 Codethink Ltd. <mark.doffman@xxxxxxxxxxxxxxx>
> + *
> + * This file is released under the GPL v2
> + *
> + * ceph_root.h
> + */
> +
> +/* linux/fs/ceph/root.c */
> +extern int ceph_root_data(char **root_device, char **root_data); /*__init*/
> diff --git a/include/linux/root_dev.h b/include/linux/root_dev.h
> index ed241aa..af6b182 100644
> --- a/include/linux/root_dev.h
> +++ b/include/linux/root_dev.h
> @@ -16,6 +16,7 @@ enum {
>  	Root_SDA2 = MKDEV(SCSI_DISK0_MAJOR, 2),
>  	Root_HDC1 = MKDEV(IDE1_MAJOR, 1),
>  	Root_SR0 = MKDEV(SCSI_CDROM_MAJOR, 0),
> +	Root_CEPH = MKDEV(UNNAMED_MAJOR, 254),
>  };
>  
>  extern dev_t ROOT_DEV;
> diff --git a/init/do_mounts.c b/init/do_mounts.c
> index 8e5addc..d075020 100644
> --- a/init/do_mounts.c
> +++ b/init/do_mounts.c
> @@ -33,6 +33,8 @@
>  #include <linux/nfs_fs_sb.h>
>  #include <linux/nfs_mount.h>
>  
> +#include <linux/ceph/ceph_root.h>
> +
>  #include "do_mounts.h"
>  
>  int __initdata rd_doload;	/* 1 = load RAM disk, 0 = don't load */
> @@ -199,6 +201,7 @@ done:
>   *	   a partition with a known unique id.
>   *	8) <major>:<minor> major and minor number of the device separated by
>   *	   a colon.
> + *	9) /dev/ceph represents Root_CEPH
>   *
>   *	If name doesn't have fall into the categories above, we return (0,0).
>   *	block_class is used to check if something is a disk name. If the disk
> @@ -245,7 +248,9 @@ dev_t name_to_dev_t(char *name)
>  	res = Root_RAM0;
>  	if (strcmp(name, "ram") == 0)
>  		goto done;
> -
> +	res = Root_CEPH;
> +	if (strcmp(name, "ceph") == 0)
> +		goto done;
>  	if (strlen(name) > 31)
>  		goto fail;
>  	strcpy(s, name);
> @@ -473,6 +478,22 @@ static int __init mount_nfs_root(void)
>  }
>  #endif
>  
> +#ifdef CONFIG_ROOT_CEPH
> +static int __init mount_ceph_root(void)
> +{
> +	char *root_dev, *root_data;
> +
> +	if (ceph_root_data(&root_dev, &root_data))
> +		return 0;
> +
> +	if (do_mount_root(root_dev, "ceph",
> +				root_mountflags, root_data))
> +		return 0;
> +
> +	return 1;
> +}
> +#endif
> +
>  #if defined(CONFIG_BLK_DEV_RAM) || defined(CONFIG_BLK_DEV_FD)
>  void __init change_floppy(char *fmt, ...)
>  {
> @@ -514,6 +535,15 @@ void __init mount_root(void)
>  		ROOT_DEV = Root_FD0;
>  	}
>  #endif
> +#ifdef CONFIG_ROOT_CEPH
> +	if (ROOT_DEV == Root_CEPH) {
> +		if (mount_ceph_root())
> +			return;
> +
> +		printk(KERN_ERR "VFS: Unable to mount root fs via CephFS, trying floppy.\n");
> +		ROOT_DEV = Root_FD0;
> +	}
> +#endif
>  #ifdef CONFIG_BLK_DEV_FD
>  	if (MAJOR(ROOT_DEV) == FLOPPY_MAJOR) {
>  		/* rd_doload is 2 for a dual initrd/ramload setup */
> -- 
> 1.8.4
> 
> --
> To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 
> 
--
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/