Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752735AbaAOR1S (ORCPT ); Wed, 15 Jan 2014 12:27:18 -0500 Received: from ducie-dc1.codethink.co.uk ([37.128.190.40]:60928 "EHLO ducie-dc1.codethink.co.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751928AbaAOR1P (ORCPT ); Wed, 15 Jan 2014 12:27:15 -0500 X-Amavis-Alert: BAD HEADER SECTION, Duplicate header field: "References" From: mark.doffman@codethink.co.uk To: ceph-devel@vger.kernel.org Cc: Mark Doffman , sage@inktank.com, netdev@vger.kernel.org, linux-kernel@vger.kernel.org, linux-nfs@vger.kernel.org, rob.taylor@codethink.co.uk Subject: [PATCH v2 1/2] init: Add a new root device option, the Ceph file system Date: Wed, 15 Jan 2014 11:26:28 -0600 Message-Id: X-Mailer: git-send-email 1.8.3.2 In-Reply-To: References: In-Reply-To: References: <1385000024-23463-1-git-send-email-mark.doffman@codethink.co.uk> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Mark Doffman 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 Reviewed-by: Ian Molton --- fs/ceph/Kconfig | 10 +++ fs/ceph/Makefile | 1 + fs/ceph/root.c | 176 +++++++++++++++++++++++++++++++++++++++++ include/linux/ceph/ceph_root.h | 10 +++ include/linux/root_dev.h | 1 + init/do_mounts.c | 32 +++++++- net/ipv4/ipconfig.c | 10 ++- 7 files changed, 237 insertions(+), 3 deletions(-) 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 + . + + 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..1559c19 --- /dev/null +++ b/fs/ceph/root.c @@ -0,0 +1,176 @@ +/* + * Copyright (C) 2012 Codethink Ltd. + * + * This file is released under the GPL v2 + * + * Allow a CephFS filesystem to be mounted as root. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define MAXPATHLEN 1024 + +/* Parameters passed from the kernel command line */ +static char ceph_command_line_params[256] __initdata; + +/* server:path string passed to mount */ +static char ceph_root_device[MAXPATHLEN + 1] __initdata; + +/* Name of directory to mount */ +static char ceph_export_path[MAXPATHLEN + 1] __initdata; + +/* Mount options */ +static char ceph_root_options[256] __initdata; + +/* + * Parse CephFS server and directory information passed on the kernel + * command line. + * + * cephroot=[][,]:[,] + */ +static int __init ceph_root_setup(char *line) +{ + ROOT_DEV = Root_CEPH; + + strlcpy(ceph_command_line_params, line, + sizeof(ceph_command_line_params)); + + return 1; +} + +__setup("cephroot=", ceph_root_setup); + +/* + * ceph_root_append - Concatenates an options or address string + * adding a ',' delimiter if neccessary. + * + * Returns 0 on success -E2BIG if the resulting string is too long. + */ +static int __init ceph_root_append(char *incoming, + char *dest, + const size_t destlen) +{ + int res = 0; + + if (incoming != NULL && *incoming != '\0') { + size_t len = strlen(dest); + + if (len && dest[len - 1] != ',') { + if (strlcat(dest, ",", destlen) > destlen) + res = -E2BIG; + } + + if (strlcat(dest, incoming, destlen) > destlen) + res = -E2BIG; + + } + return res; +} + +/* + * ceph_root_parse_params - Parse out root export path and mount options from + * passed-in string @incoming. + * + * Copy the path into @path. + * + * Returns 0 on success -E2BIG if the resulting options string or device + * string are too long. + */ +static int __init ceph_root_parse_params(char *incoming, char *outpath, + const size_t outpathlen) +{ + int res = -EINVAL; + char *options; + char *path; + + options = strstr(incoming, ":/"); + if (options == NULL) + options = strstr(incoming, "default"); + + if (options != NULL) { + path = strsep(&options, ","); + if (*path != '\0' && strcmp(path, "default") != 0) + strlcpy(outpath, path, outpathlen); + res = ceph_root_append(options, ceph_root_options, + sizeof(ceph_root_options)); + + if (res == 0) { + *path = '\0'; + res = ceph_root_append(incoming, ceph_root_device, + sizeof(ceph_root_device)); + } + } + + return res; +} + +/* + * 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_root_path = NULL; + const size_t tmplen = sizeof(ceph_export_path); + int len; + int res = -E2BIG; + + tmp_root_path = kzalloc(tmplen, GFP_KERNEL); + if (tmp_root_path == NULL) + return -ENOMEM; + + if (root_server_path[0] != '\0') { + if (ceph_root_parse_params(root_server_path, tmp_root_path, + tmplen)) + goto out; + } + + if (ceph_command_line_params[0] != '\0') { + if (ceph_root_parse_params(ceph_command_line_params, + tmp_root_path, 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_root_path, substitute the nodename, then shovel the whole + * mess into ceph_root_device. + */ + len = snprintf(ceph_export_path, sizeof(ceph_export_path), + tmp_root_path, utsname()->nodename); + if (len > (int)sizeof(ceph_export_path)) + goto out; + + len = strlcat(ceph_root_device, ceph_export_path, + sizeof(ceph_root_device)); + 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; + + res = 0; + +out: + kfree(tmp_root_path); + return res; +} 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. + * + * 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 #include +#include + #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 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 */ diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index efa1138..765eea4 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1435,10 +1435,10 @@ static int __init ip_auto_config(void) * missing values. */ if (ic_myaddr == NONE || -#ifdef CONFIG_ROOT_NFS +#if defined(CONFIG_ROOT_NFS) || defined(CONFIG_ROOT_CEPH) (root_server_addr == NONE && ic_servaddr == NONE && - ROOT_DEV == Root_NFS) || + (ROOT_DEV == Root_NFS || ROOT_DEV == Root_CEPH)) || #endif ic_first_dev->next) { #ifdef IPCONFIG_DYNAMIC @@ -1465,6 +1465,12 @@ static int __init ip_auto_config(void) goto try_try_again; } #endif +#ifdef CONFIG_ROOT_CEPH + if (ROOT_DEV == Root_CEPH) { + pr_err("IP-Config: Retrying forever (CEPH root)...\n"); + goto try_try_again; + } +#endif if (--retries) { pr_err("IP-Config: Reopening network devices...\n"); -- 1.8.4 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/