Implement a filesystem context concept to be used during superblock creation for mount and superblock reconfiguration for remount. The mounting procedure then becomes: (1) Allocate new fs_context context. (2) Configure the context. (3) Create superblock. (4) Mount the superblock any number of times. (5) Destroy the context. Rather than calling fs_type->mount(), an fs_context struct is created and fs_type->init_fs_context() is called to set it up. fs_type->fs_context_size says how much space should be allocated for the config context. The fs_context struct is placed at the beginning and any extra space is for the filesystem's use. A set of operations has to be set by ->init_fs_context() to provide freeing, duplication, option parsing, binary data parsing, validation, mounting and superblock filling. Legacy filesystems are supported by the provision of a set of legacy fs_context operations that build up a list of mount options and then invoke fs_type->mount() from within the fs_context ->get_tree() operation. This allows all filesystems to be accessed using fs_context. It should be noted that, whilst this patch adds a lot of lines of code, there is quite a bit of duplication with existing code that can be eliminated should all filesystems be converted over. Signed-off-by: David Howells <dhowells@xxxxxxxxxx> --- fs/Makefile | 3 fs/fs_context.c | 501 ++++++++++++++++++++++++++++++++++++++++++++ fs/internal.h | 2 fs/libfs.c | 18 +- fs/namespace.c | 399 ++++++++++++++++++++++++++--------- fs/super.c | 158 ++++++++++++-- include/linux/fs.h | 17 + include/linux/fs_context.h | 12 + include/linux/mount.h | 2 9 files changed, 992 insertions(+), 120 deletions(-) create mode 100644 fs/fs_context.c diff --git a/fs/Makefile b/fs/Makefile index 7bbaca9c67b1..ffe728cc15e1 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -11,7 +11,8 @@ obj-y := open.o read_write.o file_table.o super.o \ attr.o bad_inode.o file.o filesystems.o namespace.o \ seq_file.o xattr.o libfs.o fs-writeback.o \ pnode.o splice.o sync.o utimes.o \ - stack.o fs_struct.o statfs.o fs_pin.o nsfs.o + stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \ + fs_context.o ifeq ($(CONFIG_BLOCK),y) obj-y += buffer.o block_dev.o direct-io.o mpage.o diff --git a/fs/fs_context.c b/fs/fs_context.c new file mode 100644 index 000000000000..98ba65d49b21 --- /dev/null +++ b/fs/fs_context.c @@ -0,0 +1,501 @@ +/* Provide a way to create a superblock configuration context within the kernel + * that allows a superblock to be set up prior to mounting. + * + * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@xxxxxxxxxx) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/fs_context.h> +#include <linux/fs.h> +#include <linux/mount.h> +#include <linux/nsproxy.h> +#include <linux/slab.h> +#include <linux/magic.h> +#include <linux/security.h> +#include <linux/parser.h> +#include <linux/mnt_namespace.h> +#include <linux/pid_namespace.h> +#include <linux/user_namespace.h> +#include <net/net_namespace.h> +#include "mount.h" + +struct legacy_fs_context { + struct fs_context fc; + char *legacy_data; /* Data page for legacy filesystems */ + char *secdata; + unsigned int data_usage; +}; + +static const struct fs_context_operations legacy_fs_context_ops; + +static const match_table_t common_set_mount_options = { + { MS_DIRSYNC, "dirsync" }, + { MS_I_VERSION, "iversion" }, + { MS_LAZYTIME, "lazytime" }, + { MS_MANDLOCK, "mand" }, + { MS_POSIXACL, "posixacl" }, + { MS_RDONLY, "ro" }, + { MS_REC, "rec" }, + { MS_SYNCHRONOUS, "sync" }, + { MS_VERBOSE, "verbose" }, + { }, +}; + +static const match_table_t common_clear_mount_options = { + { MS_LAZYTIME, "nolazytime" }, + { MS_MANDLOCK, "nomand" }, + { MS_RDONLY, "rw" }, + { MS_SILENT, "silent" }, + { MS_SYNCHRONOUS, "async" }, + { }, +}; + +static const match_table_t forbidden_mount_options = { + { MS_BIND, "bind" }, + { MS_MOVE, "move" }, + { MS_PRIVATE, "private" }, + { MS_REMOUNT, "remount" }, + { MS_SHARED, "shared" }, + { MS_SLAVE, "slave" }, + { MS_UNBINDABLE, "unbindable" }, + { MS_NOATIME, "noatime" }, + { MS_RELATIME, "relatime" }, + { MS_RELATIME, "norelatime" }, + { MS_STRICTATIME, "strictatime" }, + { MS_STRICTATIME, "nostrictatime" }, + { MS_NODIRATIME, "nodiratime" }, + { MS_NODEV, "dev" }, + { MS_NODEV, "nodev" }, + { MS_NOEXEC, "exec" }, + { MS_NOEXEC, "noexec" }, + { MS_NOSUID, "suid" }, + { MS_NOSUID, "nosuid" }, + { }, +}; + +/* + * Check for a common mount option. + */ +static int vfs_parse_ms_mount_option(struct fs_context *fc, char *data) +{ + substring_t args[MAX_OPT_ARGS]; + unsigned int token; + + token = match_token(data, common_set_mount_options, args); + if (token) { + fc->sb_flags |= token; + return 1; + } + + token = match_token(data, common_clear_mount_options, args); + if (token) { + fc->sb_flags &= ~token; + return 1; + } + + token = match_token(data, forbidden_mount_options, args); + if (token) + return invalf("VFS: Mount option, not superblock option"); + + return 0; +} + +/** + * vfs_parse_mount_option - Add a single mount option to a superblock config + * @fc: The filesystem context to modify + * @p: The option to apply. + * + * A single mount option in string form is applied to the filesystem context + * being set up. Certain standard options (for example "ro") are translated + * into flag bits without going to the filesystem. The active security module + * is allowed to observe and poach options. Any other options are passed over + * to the filesystem to parse. + * + * This may be called multiple times for a context. + * + * Returns 0 on success and a negative error code on failure. In the event of + * failure, supplementary error information may have been set. + */ +int vfs_parse_mount_option(struct fs_context *fc, char *p) +{ + int ret; + + ret = vfs_parse_ms_mount_option(fc, p); + if (ret < 0) + return ret; + if (ret == 1) + return 0; + + ret = security_fs_context_parse_option(fc, p); + if (ret < 0) + return ret; + if (ret == 1) + return 0; + + if (fc->ops->parse_option) + return fc->ops->parse_option(fc, p); + + return invalf("VFS: FS takes no options"); +} +EXPORT_SYMBOL(vfs_parse_mount_option); + +/** + * generic_monolithic_mount_data - Parse key[=val][,key[=val]]* mount data + * @mc: The superblock configuration to fill in. + * @data: The data to parse + * + * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be + * called from the ->monolithic_mount_data() fs_context operation. + * + * Returns 0 on success or the error returned by the ->parse_option() fs_context + * operation on failure. + */ +int generic_monolithic_mount_data(struct fs_context *ctx, void *data) +{ + char *options = data, *p; + int ret; + + if (!options) + return 0; + + while ((p = strsep(&options, ",")) != NULL) { + if (*p) { + ret = vfs_parse_mount_option(ctx, p); + if (ret < 0) + return ret; + } + } + + return 0; +} +EXPORT_SYMBOL(generic_monolithic_mount_data); + +/** + * vfs_new_fs_context - Create a filesystem context. + * @fs_type: The filesystem type. + * @src_sb: A superblock from which this one derives (or NULL) + * @sb_flags: Superblock flags and op flags (such as MS_REMOUNT) + * @purpose: The purpose that this configuration shall be used for. + * + * Open a filesystem and create a mount context. The mount context is + * initialised with the supplied flags and, if a submount/automount from + * another superblock (@src_sb), may have parameters such as namespaces copied + * across from that superblock. + */ +struct fs_context *vfs_new_fs_context(struct file_system_type *fs_type, + struct super_block *src_sb, + unsigned int sb_flags, + enum fs_context_purpose purpose) +{ + struct fs_context *fc; + size_t fc_size = fs_type->fs_context_size; + int ret; + + BUG_ON(fs_type->init_fs_context && fc_size < sizeof(*fc)); + + if (!fs_type->init_fs_context) + fc_size = sizeof(struct legacy_fs_context); + + fc = kzalloc(fc_size, GFP_KERNEL); + if (!fc) + return ERR_PTR(-ENOMEM); + + fc->purpose = purpose; + fc->sb_flags = sb_flags; + fc->fs_type = get_filesystem(fs_type); + fc->cred = get_current_cred(); + + switch (purpose) { + case FS_CONTEXT_FOR_NEW: + fc->user_ns = get_user_ns(fc->cred->user_ns); + fc->net_ns = get_net(current->nsproxy->net_ns); + break; + case FS_CONTEXT_FOR_SUBMOUNT: + fc->user_ns = get_user_ns(src_sb->s_user_ns); + fc->net_ns = get_net(current->nsproxy->net_ns); + break; + case FS_CONTEXT_FOR_REMOUNT: + /* We don't pin any namespaces as the superblock's + * subscriptions cannot be changed at this point. + */ + break; + } + + + /* TODO: Make all filesystems support this unconditionally */ + if (fc->fs_type->init_fs_context) { + ret = fc->fs_type->init_fs_context(fc, src_sb); + if (ret < 0) + goto err_fc; + } else { + fc->ops = &legacy_fs_context_ops; + } + + /* Do the security check last because ->init_fs_context may change the + * namespace subscriptions. + */ + ret = security_fs_context_alloc(fc, src_sb); + if (ret < 0) + goto err_fc; + + return fc; + +err_fc: + put_fs_context(fc); + return ERR_PTR(ret); +} +EXPORT_SYMBOL(vfs_new_fs_context); + +/** + * vfs_sb_reconfig - Create a filesystem context for remount/reconfiguration + * @mnt: The mountpoint to open + * @sb_flags: Superblock flags and op flags (such as MS_REMOUNT) + * + * Open a mounted filesystem and create a filesystem context such that a + * remount can be effected. + */ +struct fs_context *vfs_sb_reconfig(struct vfsmount *mnt, + unsigned int sb_flags) +{ + return vfs_new_fs_context(mnt->mnt_sb->s_type, mnt->mnt_sb, + sb_flags, FS_CONTEXT_FOR_REMOUNT); +} + +/** + * vfs_dup_fc_config: Duplicate a filesytem context. + * @src_fc: The context to copy. + */ +struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc) +{ + struct fs_context *fc; + size_t fc_size; + int ret; + + if (!src_fc->ops->dup) + return ERR_PTR(-ENOTSUPP); + + fc_size = src_fc->fs_type->fs_context_size; + if (!src_fc->fs_type->init_fs_context) + fc_size = sizeof(struct legacy_fs_context); + + fc = kmemdup(src_fc, src_fc->fs_type->fs_context_size, GFP_KERNEL); + if (!fc) + return ERR_PTR(-ENOMEM); + + fc->device = NULL; + fc->security = NULL; + get_filesystem(fc->fs_type); + get_net(fc->net_ns); + get_user_ns(fc->user_ns); + get_cred(fc->cred); + + /* Can't call put until we've called ->dup */ + ret = fc->ops->dup(fc, src_fc); + if (ret < 0) + goto err_fc; + + ret = security_fs_context_dup(fc, src_fc); + if (ret < 0) + goto err_fc; + return fc; + +err_fc: + put_fs_context(fc); + return ERR_PTR(ret); +} +EXPORT_SYMBOL(vfs_dup_fs_context); + +/** + * put_fs_context - Dispose of a superblock configuration context. + * @sc: The context to dispose of. + */ +void put_fs_context(struct fs_context *fc) +{ + struct super_block *sb; + + if (fc->root) { + sb = fc->root->d_sb; + dput(fc->root); + fc->root = NULL; + deactivate_super(sb); + } + + if (fc->ops && fc->ops->free) + fc->ops->free(fc); + + security_fs_context_free(fc); + if (fc->net_ns) + put_net(fc->net_ns); + put_user_ns(fc->user_ns); + if (fc->cred) + put_cred(fc->cred); + kfree(fc->subtype); + put_filesystem(fc->fs_type); + kfree(fc->device); + kfree(fc); +} +EXPORT_SYMBOL(put_fs_context); + +/* + * Free the config for a filesystem that doesn't support fs_context. + */ +static void legacy_fs_context_free(struct fs_context *fc) +{ + struct legacy_fs_context *ctx = container_of(fc, struct legacy_fs_context, fc); + + free_secdata(ctx->secdata); + kfree(ctx->legacy_data); +} + +/* + * Duplicate a legacy config. + */ +static int legacy_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) +{ + struct legacy_fs_context *ctx = container_of(fc, struct legacy_fs_context, fc); + struct legacy_fs_context *src_ctx = container_of(src_fc, struct legacy_fs_context, fc); + + ctx->legacy_data = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!ctx->legacy_data) + return -ENOMEM; + memcpy(ctx->legacy_data, src_ctx->legacy_data, sizeof(PAGE_SIZE)); + return 0; +} + +/* + * Add an option to a legacy config. We build up a comma-separated list of + * options. + */ +static int legacy_parse_option(struct fs_context *fc, char *p) +{ + struct legacy_fs_context *ctx = container_of(fc, struct legacy_fs_context, fc); + unsigned int usage = ctx->data_usage; + size_t len = strlen(p); + + if (len > PAGE_SIZE - 2 - usage) + return invalf("VFS: Insufficient data buffer space"); + if (memchr(p, ',', len) != NULL) + return invalf("VFS: Options cannot contain commas"); + if (!ctx->legacy_data) { + ctx->legacy_data = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!ctx->legacy_data) + return -ENOMEM; + } + + ctx->legacy_data[usage++] = ','; + memcpy(ctx->legacy_data + usage, p, len); + usage += len; + ctx->legacy_data[usage] = '\0'; + ctx->data_usage = usage; + return 0; +} + +/* + * Add monolithic mount data. + */ +static int legacy_monolithic_mount_data(struct fs_context *fc, void *data) +{ + struct legacy_fs_context *ctx = container_of(fc, struct legacy_fs_context, fc); + + if (ctx->data_usage != 0) + return invalf("VFS: Can't mix monolithic and individual options"); + if (!data) + return 0; + if (!ctx->legacy_data) { + ctx->legacy_data = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!ctx->legacy_data) + return -ENOMEM; + } + + memcpy(ctx->legacy_data, data, PAGE_SIZE); + ctx->data_usage = PAGE_SIZE; + return 0; +} + +/* + * Use the legacy mount validation step to strip out and process security + * config options. + */ +static int legacy_validate(struct fs_context *fc) +{ + struct legacy_fs_context *ctx = container_of(fc, struct legacy_fs_context, fc); + + if (!ctx->legacy_data || ctx->fc.fs_type->fs_flags & FS_BINARY_MOUNTDATA) + return 0; + + ctx->secdata = alloc_secdata(); + if (!ctx->secdata) + return -ENOMEM; + + return security_sb_copy_data(ctx->legacy_data, ctx->secdata); +} + +/* + * Determine the superblock subtype. + */ +static int legacy_set_subtype(struct fs_context *fc) +{ + const char *subtype = strchr(fc->fs_type->name, '.'); + + if (subtype) { + subtype++; + if (!subtype[0]) + return -EINVAL; + } else { + subtype = ""; + } + + fc->subtype = kstrdup(subtype, GFP_KERNEL); + if (!fc->subtype) + return -ENOMEM; + return 0; +} + +/* + * Get a mountable root with the legacy mount command. + */ +static int legacy_get_tree(struct fs_context *fc) +{ + struct legacy_fs_context *ctx = container_of(fc, struct legacy_fs_context, fc); + struct super_block *sb; + struct dentry *root; + int ret; + + root = ctx->fc.fs_type->mount(ctx->fc.fs_type, ctx->fc.sb_flags, + ctx->fc.device, ctx->legacy_data); + if (IS_ERR(root)) + return PTR_ERR(root); + + sb = root->d_sb; + BUG_ON(!sb); + + if ((ctx->fc.fs_type->fs_flags & FS_HAS_SUBTYPE) && + !fc->subtype) { + ret = legacy_set_subtype(fc); + if (ret < 0) + goto err_sb; + } + + ctx->fc.root = root; + return 0; + +err_sb: + dput(root); + deactivate_locked_super(sb); + return ret; +} + +static const struct fs_context_operations legacy_fs_context_ops = { + .free = legacy_fs_context_free, + .dup = legacy_fs_context_dup, + .parse_option = legacy_parse_option, + .monolithic_mount_data = legacy_monolithic_mount_data, + .validate = legacy_validate, + .get_tree = legacy_get_tree, +}; diff --git a/fs/internal.h b/fs/internal.h index 9676fe11c093..08d7816f8686 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -87,7 +87,7 @@ extern struct file *get_empty_filp(void); /* * super.c */ -extern int do_remount_sb(struct super_block *, int, void *, int); +extern int do_remount_sb(struct super_block *, int, void *, int, struct fs_context *); extern bool trylock_super(struct super_block *sb); extern struct dentry *mount_fs(struct file_system_type *, int, const char *, void *); diff --git a/fs/libfs.c b/fs/libfs.c index 32c159ed33dd..21d1e6231707 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -9,6 +9,7 @@ #include <linux/slab.h> #include <linux/cred.h> #include <linux/mount.h> +#include <linux/fs_context.h> #include <linux/vfs.h> #include <linux/quotaops.h> #include <linux/mutex.h> @@ -574,13 +575,28 @@ static DEFINE_SPINLOCK(pin_fs_lock); int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count) { + struct fs_context *fc; struct vfsmount *mnt = NULL; + int ret; + spin_lock(&pin_fs_lock); if (unlikely(!*mount)) { spin_unlock(&pin_fs_lock); - mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); + + fc = vfs_new_fs_context(type, NULL, SB_KERNMOUNT, + FS_CONTEXT_FOR_NEW); + if (IS_ERR(fc)) + return PTR_ERR(fc); + + ret = vfs_get_tree(fc); + if (ret < 0) + return ret; + + mnt = vfs_kern_mount_fc(fc); + put_fs_context(fc); if (IS_ERR(mnt)) return PTR_ERR(mnt); + spin_lock(&pin_fs_lock); if (!*mount) *mount = mnt; diff --git a/fs/namespace.c b/fs/namespace.c index 9a7dbf7b716f..cd44283dee99 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -25,7 +25,9 @@ #include <linux/magic.h> #include <linux/bootmem.h> #include <linux/task_work.h> +#include <linux/file.h> #include <linux/sched/task.h> +#include <linux/fs_context.h> #include "pnode.h" #include "internal.h" @@ -957,55 +959,6 @@ static struct mount *skip_mnt_tree(struct mount *p) return p; } -struct vfsmount * -vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) -{ - struct mount *mnt; - struct dentry *root; - - if (!type) - return ERR_PTR(-ENODEV); - - mnt = alloc_vfsmnt(name); - if (!mnt) - return ERR_PTR(-ENOMEM); - - if (flags & SB_KERNMOUNT) - mnt->mnt.mnt_flags = MNT_INTERNAL; - - root = mount_fs(type, flags, name, data); - if (IS_ERR(root)) { - mnt_free_id(mnt); - free_vfsmnt(mnt); - return ERR_CAST(root); - } - - mnt->mnt.mnt_root = root; - mnt->mnt.mnt_sb = root->d_sb; - mnt->mnt_mountpoint = mnt->mnt.mnt_root; - mnt->mnt_parent = mnt; - lock_mount_hash(); - list_add_tail(&mnt->mnt_instance, &root->d_sb->s_mounts); - unlock_mount_hash(); - return &mnt->mnt; -} -EXPORT_SYMBOL_GPL(vfs_kern_mount); - -struct vfsmount * -vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, - const char *name, void *data) -{ - /* Until it is worked out how to pass the user namespace - * through from the parent mount to the submount don't support - * unprivileged mounts with submounts. - */ - if (mountpoint->d_sb->s_user_ns != &init_user_ns) - return ERR_PTR(-EPERM); - - return vfs_kern_mount(type, SB_SUBMOUNT, name, data); -} -EXPORT_SYMBOL_GPL(vfs_submount); - static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { @@ -1593,7 +1546,7 @@ static int do_umount(struct mount *mnt, int flags) return -EPERM; down_write(&sb->s_umount); if (!(sb->s_flags & SB_RDONLY)) - retval = do_remount_sb(sb, SB_RDONLY, NULL, 0); + retval = do_remount_sb(sb, SB_RDONLY, NULL, 0, NULL); up_write(&sb->s_umount); return retval; } @@ -2133,7 +2086,7 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) static int flags_to_propagation_type(int flags) { - int type = flags & ~(MS_REC | SB_SILENT); + int type = flags & ~(MS_REC | MS_SILENT); /* Fail if any non-propagation flags are set */ if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) @@ -2276,6 +2229,20 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags) } /* + * Parse the monolithic page of mount data given to sys_mount(). + */ +static int parse_monolithic_mount_data(struct fs_context *fc, void *data) +{ + int (*monolithic_mount_data)(struct fs_context *, void *); + + monolithic_mount_data = fc->ops->monolithic_mount_data; + if (!monolithic_mount_data) + monolithic_mount_data = generic_monolithic_mount_data; + + return monolithic_mount_data(fc, data); +} + +/* * change filesystem flags. dir should be a physical root of filesystem. * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. @@ -2283,9 +2250,11 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags) static int do_remount(struct path *path, int flags, int mnt_flags, void *data) { + struct fs_context *fc = NULL; int err; struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); + struct file_system_type *type = sb->s_type; if (!check_mnt(mnt)) return -EINVAL; @@ -2320,9 +2289,25 @@ static int do_remount(struct path *path, int flags, int mnt_flags, return -EPERM; } - err = security_sb_remount(sb, data); - if (err) - return err; + if (type->init_fs_context) { + fc = vfs_sb_reconfig(path->mnt, flags); + if (IS_ERR(fc)) + return PTR_ERR(fc); + + err = parse_monolithic_mount_data(fc, data); + if (err < 0) + goto err_fc; + + if (fc->ops->validate) { + err = fc->ops->validate(fc); + if (err < 0) + goto err_fc; + } + } else { + err = security_sb_remount(sb, data); + if (err) + return err; + } down_write(&sb->s_umount); if (flags & MS_BIND) @@ -2330,7 +2315,7 @@ static int do_remount(struct path *path, int flags, int mnt_flags, else if (!capable(CAP_SYS_ADMIN)) err = -EPERM; else - err = do_remount_sb(sb, flags, data, 0); + err = do_remount_sb(sb, flags, data, 0, fc); if (!err) { lock_mount_hash(); mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; @@ -2339,6 +2324,9 @@ static int do_remount(struct path *path, int flags, int mnt_flags, unlock_mount_hash(); } up_write(&sb->s_umount); +err_fc: + if (fc) + put_fs_context(fc); return err; } @@ -2422,29 +2410,6 @@ static int do_move_mount(struct path *path, const char *old_name) return err; } -static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype) -{ - int err; - const char *subtype = strchr(fstype, '.'); - if (subtype) { - subtype++; - err = -EINVAL; - if (!subtype[0]) - goto err; - } else - subtype = ""; - - mnt->mnt_sb->s_subtype = kstrdup(subtype, GFP_KERNEL); - err = -ENOMEM; - if (!mnt->mnt_sb->s_subtype) - goto err; - return mnt; - - err: - mntput(mnt); - return ERR_PTR(err); -} - /* * add a mount into a namespace's mount tree */ @@ -2492,40 +2457,91 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags) static bool mount_too_revealing(struct vfsmount *mnt, int *new_mnt_flags); /* - * create a new mount for userspace and request it to be added into the - * namespace's tree + * Create a new mount using a superblock configuration and request it + * be added to the namespace tree. */ -static int do_new_mount(struct path *path, const char *fstype, int flags, - int mnt_flags, const char *name, void *data) +static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint, + unsigned int mnt_flags) { - struct file_system_type *type; struct vfsmount *mnt; - int err; - - if (!fstype) - return -EINVAL; - - type = get_fs_type(fstype); - if (!type) - return -ENODEV; + int ret; - mnt = vfs_kern_mount(type, flags, name, data); - if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) && - !mnt->mnt_sb->s_subtype) - mnt = fs_set_subtype(mnt, fstype); + ret = security_sb_mountpoint(fc, mountpoint); + if (ret < 0) + return ret;; - put_filesystem(type); + mnt = vfs_kern_mount_fc(fc); if (IS_ERR(mnt)) return PTR_ERR(mnt); + ret = -EPERM; if (mount_too_revealing(mnt, &mnt_flags)) { - mntput(mnt); - return -EPERM; + errorf("VFS: Mount too revealing"); + goto err_mnt; } - err = do_add_mount(real_mount(mnt), path, mnt_flags); + ret = do_add_mount(real_mount(mnt), mountpoint, mnt_flags); + if (ret < 0) { + errorf("VFS: Failed to add mount"); + goto err_mnt; + } + return ret; + +err_mnt: + mntput(mnt); + return ret; +} + +/* + * create a new mount for userspace and request it to be added into the + * namespace's tree + */ +static int do_new_mount(struct path *mountpoint, const char *fstype, + int ms_flags, int mnt_flags, const char *name, + void *data) +{ + struct file_system_type *fs_type; + struct fs_context *fc; + int err = -EINVAL; + + if (!fstype) + goto err; + + err = -ENODEV; + fs_type = get_fs_type(fstype); + if (!fs_type) + goto err; + + fc = vfs_new_fs_context(fs_type, NULL, ms_flags, FS_CONTEXT_FOR_NEW); + put_filesystem(fs_type); + if (IS_ERR(fc)) { + err = PTR_ERR(fc); + goto err; + } + + err = -ENOMEM; + fc->device = kstrdup(name, GFP_KERNEL); + if (!fc->device) + goto err_fc; + + err = parse_monolithic_mount_data(fc, data); + if (err < 0) + goto err_fc; + + err = vfs_get_tree(fc); + if (err < 0) + goto err_fc; + + err = do_new_mount_fc(fc, mountpoint, mnt_flags); if (err) - mntput(mnt); + goto err_fc; + + put_fs_context(fc); + return 0; + +err_fc: + put_fs_context(fc); +err: return err; } @@ -3058,6 +3074,172 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, return ret; } +/** + * vfs_get_tree - Get the mountable root + * @sc: The superblock configuration context. + * + * The filesystem is invoked to get or create a superblock which can then later + * be used for mounting. The filesystem places a pointer to the root to be + * used for mounting in @fc->root. + */ +int vfs_get_tree(struct fs_context *fc) +{ + struct super_block *sb; + int ret; + + if (fc->root) + return -EBUSY; + + if (fc->ops->validate) { + ret = fc->ops->validate(fc); + if (ret < 0) + return ret; + } + + /* The filesystem may transfer preallocated resources from the + * configuration context to the superblock, thereby rendering the + * config unusable for another attempt at creation if this one fails. + */ + if (fc->degraded) + return invalf("VFS: The config is degraded"); + + /* Get the mountable root in fc->root, with a ref on the root and a ref + * on the superblock. + */ + ret = fc->ops->get_tree(fc); + if (ret < 0) + return ret; + + BUG_ON(!fc->root); + sb = fc->root->d_sb; + WARN_ON(!sb->s_bdi); + + ret = security_sb_get_tree(fc); + if (ret < 0) + goto err_sb; + + ret = -ENOMEM; + if (fc->subtype && !sb->s_subtype) { + sb->s_subtype = kstrdup(fc->subtype, GFP_KERNEL); + if (!sb->s_subtype) + goto err_sb; + } + + sb->s_flags |= MS_BORN; + + /* Filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE + * but s_maxbytes was an unsigned long long for many releases. Throw + * this warning for a little while to try and catch filesystems that + * violate this rule. + */ + WARN(sb->s_maxbytes < 0, + "%s set sb->s_maxbytes to negative value (%lld)\n", + fc->fs_type->name, sb->s_maxbytes); + + up_write(&sb->s_umount); + return 0; + +err_sb: + dput(fc->root); + fc->root = NULL; + deactivate_locked_super(sb); + return ret; +} +EXPORT_SYMBOL(vfs_get_tree); + +/** + * vfs_kern_mount_fc - Create a mount for a configured superblock + * sc: The configuration context with the superblock attached + * + * Create a mount to an already configured superblock. If necessary, the + * caller should invoke vfs_create_super() before calling this. + */ +struct vfsmount *vfs_kern_mount_fc(struct fs_context *fc) +{ + struct mount *mnt; + + if (!fc->root) + return ERR_PTR(invalf("VFS: Root must be obtained before mount")); + + mnt = alloc_vfsmnt(fc->device ?: "none"); + if (!mnt) + return ERR_PTR(-ENOMEM); + + if (fc->sb_flags & SB_KERNMOUNT) + mnt->mnt.mnt_flags = MNT_INTERNAL; + + atomic_inc(&fc->root->d_sb->s_active); + mnt->mnt.mnt_sb = fc->root->d_sb; + mnt->mnt.mnt_root = dget(fc->root); + mnt->mnt_mountpoint = mnt->mnt.mnt_root; + mnt->mnt_parent = mnt; + + lock_mount_hash(); + list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts); + unlock_mount_hash(); + return &mnt->mnt; +} +EXPORT_SYMBOL_GPL(vfs_kern_mount_fc); + +struct vfsmount *vfs_kern_mount(struct file_system_type *type, + int flags, const char *name, void *data) +{ + struct fs_context *fc; + struct vfsmount *mnt; + int ret; + + if (!type) + return ERR_PTR(-EINVAL); + + fc = vfs_new_fs_context(type, NULL, flags, FS_CONTEXT_FOR_NEW); + if (IS_ERR(fc)) + return ERR_CAST(fc); + + if (name) { + ret = -ENOMEM; + fc->device = kstrdup(name, GFP_KERNEL); + if (!fc->device) + goto err_fc; + } + + ret = parse_monolithic_mount_data(fc, data); + if (ret < 0) + goto err_fc; + + ret = vfs_get_tree(fc); + if (ret < 0) + goto err_fc; + + mnt = vfs_kern_mount_fc(fc); + if (IS_ERR(mnt)) { + ret = PTR_ERR(mnt); + goto err_fc; + } + + put_fs_context(fc); + return mnt; + +err_fc: + put_fs_context(fc); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(vfs_kern_mount); + +struct vfsmount * +vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, + const char *name, void *data) +{ + /* Until it is worked out how to pass the user namespace + * through from the parent mount to the submount don't support + * unprivileged mounts with submounts. + */ + if (mountpoint->d_sb->s_user_ns != &init_user_ns) + return ERR_PTR(-EPERM); + + return vfs_kern_mount(type, MS_SUBMOUNT, name, data); +} +EXPORT_SYMBOL_GPL(vfs_submount); + /* * Return true if path is reachable from root * @@ -3299,6 +3481,23 @@ struct vfsmount *kern_mount_data(struct file_system_type *type, void *data) } EXPORT_SYMBOL_GPL(kern_mount_data); +struct vfsmount *kern_mount_data_fc(struct fs_context *fc) +{ + struct vfsmount *mnt; + + fc->sb_flags = SB_KERNMOUNT; + mnt = vfs_kern_mount_fc(fc); + if (!IS_ERR(mnt)) { + /* + * it is a longterm mount, don't release mnt until + * we unmount before file sys is unregistered + */ + real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL; + } + return mnt; +} +EXPORT_SYMBOL_GPL(kern_mount_data_fc); + void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ diff --git a/fs/super.c b/fs/super.c index e55911d31821..8ef5222d6932 100644 --- a/fs/super.c +++ b/fs/super.c @@ -34,6 +34,7 @@ #include <linux/fsnotify.h> #include <linux/lockdep.h> #include <linux/user_namespace.h> +#include <linux/fs_context.h> #include "internal.h" @@ -173,16 +174,13 @@ static void destroy_super(struct super_block *s) } /** - * alloc_super - create new superblock - * @type: filesystem type superblock should belong to - * @flags: the mount flags - * @user_ns: User namespace for the super_block + * alloc_super - Create new superblock + * @sc: The filesystem configuration context * * Allocates and initializes a new &struct super_block. alloc_super() * returns a pointer new superblock or %NULL if allocation had failed. */ -static struct super_block *alloc_super(struct file_system_type *type, int flags, - struct user_namespace *user_ns) +static struct super_block *alloc_super(struct fs_context *fc) { struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER); static const struct super_operations default_op; @@ -192,7 +190,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, return NULL; INIT_LIST_HEAD(&s->s_mounts); - s->s_user_ns = get_user_ns(user_ns); + s->s_user_ns = get_user_ns(fc->user_ns); if (security_sb_alloc(s)) goto fail; @@ -200,12 +198,12 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, for (i = 0; i < SB_FREEZE_LEVELS; i++) { if (__percpu_init_rwsem(&s->s_writers.rw_sem[i], sb_writers_name[i], - &type->s_writers_key[i])) + &fc->fs_type->s_writers_key[i])) goto fail; } init_waitqueue_head(&s->s_writers.wait_unfrozen); s->s_bdi = &noop_backing_dev_info; - s->s_flags = flags; + s->s_flags = fc->sb_flags; if (s->s_user_ns != &init_user_ns) s->s_iflags |= SB_I_NODEV; INIT_HLIST_NODE(&s->s_instances); @@ -222,7 +220,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, goto fail; init_rwsem(&s->s_umount); - lockdep_set_class(&s->s_umount, &type->s_umount_key); + lockdep_set_class(&s->s_umount, &fc->fs_type->s_umount_key); /* * sget() can have s_umount recursion. * @@ -242,7 +240,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, s->s_count = 1; atomic_set(&s->s_active, 1); mutex_init(&s->s_vfs_rename_mutex); - lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key); + lockdep_set_class(&s->s_vfs_rename_mutex, &fc->fs_type->s_vfs_rename_key); mutex_init(&s->s_dquot.dqio_mutex); s->s_maxbytes = MAX_NON_LFS; s->s_op = &default_op; @@ -455,6 +453,79 @@ void generic_shutdown_super(struct super_block *sb) EXPORT_SYMBOL(generic_shutdown_super); /** + * sget_fc - Find or create a superblock + * @fc: Configuration context. + * @test: comparison callback + * @set: setup callback + */ +struct super_block *sget_fc(struct fs_context *fc, + int (*test)(struct super_block *, struct fs_context *), + int (*set)(struct super_block *, struct fs_context *)) +{ + struct super_block *s = NULL; + struct super_block *old; + int err; + + if (!(fc->sb_flags & MS_KERNMOUNT) && + fc->purpose != FS_CONTEXT_FOR_SUBMOUNT) { + if (!(fc->fs_type->fs_flags & FS_USERNS_MOUNT) && + !capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + else if (!ns_capable(fc->user_ns, CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + } + +retry: + spin_lock(&sb_lock); + if (test) { + hlist_for_each_entry(old, &fc->fs_type->fs_supers, s_instances) { + if (!test(old, fc)) + continue; + if (fc->user_ns != old->s_user_ns) { + spin_unlock(&sb_lock); + if (s) { + up_write(&s->s_umount); + destroy_super(s); + } + return ERR_PTR(-EBUSY); + } + if (!grab_super(old)) + goto retry; + if (s) { + up_write(&s->s_umount); + destroy_super(s); + s = NULL; + } + return old; + } + } + if (!s) { + spin_unlock(&sb_lock); + s = alloc_super(fc); + if (!s) + return ERR_PTR(-ENOMEM); + goto retry; + } + + err = set(s, fc); + if (err) { + spin_unlock(&sb_lock); + up_write(&s->s_umount); + destroy_super(s); + return ERR_PTR(err); + } + s->s_type = fc->fs_type; + strlcpy(s->s_id, s->s_type->name, sizeof(s->s_id)); + list_add_tail(&s->s_list, &super_blocks); + hlist_add_head(&s->s_instances, &s->s_type->fs_supers); + spin_unlock(&sb_lock); + get_filesystem(s->s_type); + register_shrinker(&s->s_shrink); + return s; +} +EXPORT_SYMBOL(sget_fc); + +/** * sget_userns - find or create a superblock * @type: filesystem type superblock should belong to * @test: comparison callback @@ -503,7 +574,14 @@ struct super_block *sget_userns(struct file_system_type *type, } if (!s) { spin_unlock(&sb_lock); - s = alloc_super(type, (flags & ~SB_SUBMOUNT), user_ns); + { + struct fs_context fc = { + .fs_type = type, + .sb_flags = flags & ~SB_SUBMOUNT, + .user_ns = user_ns, + }; + s = alloc_super(&fc); + } if (!s) return ERR_PTR(-ENOMEM); goto retry; @@ -805,10 +883,13 @@ struct super_block *user_get_super(dev_t dev) * @flags: MS_* flags translated into SB_* flags * @data: the rest of options * @force: whether or not to force the change + * @fc: the superblock config for filesystems that support it + * (NULL if called from emergency or umount) * * Alters the mount options of a mounted file system. */ -int do_remount_sb(struct super_block *sb, int flags, void *data, int force) +int do_remount_sb(struct super_block *sb, int flags, void *data, int force, + struct fs_context *fc) { int retval; int remount_ro; @@ -850,8 +931,14 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) } } - if (sb->s_op->remount_fs) { - retval = sb->s_op->remount_fs(sb, &flags, data); + if (sb->s_op->remount_fs_fc || + sb->s_op->remount_fs) { + if (sb->s_op->remount_fs_fc) { + retval = sb->s_op->remount_fs_fc(sb, fc); + flags = fc->sb_flags; + } else { + retval = sb->s_op->remount_fs(sb, &flags, data); + } if (retval) { if (!force) goto cancel_readonly; @@ -898,7 +985,7 @@ static void do_emergency_remount(struct work_struct *work) /* * What lock protects sb->s_flags?? */ - do_remount_sb(sb, SB_RDONLY, NULL, 1); + do_remount_sb(sb, SB_RDONLY, NULL, 1, NULL); } up_write(&sb->s_umount); spin_lock(&sb_lock); @@ -1048,6 +1135,43 @@ struct dentry *mount_ns(struct file_system_type *fs_type, EXPORT_SYMBOL(mount_ns); +int mount_ns_fc(struct fs_context *fc, + int (*fill_super)(struct super_block *sb, struct fs_context *fc), + void *ns) +{ + struct super_block *sb; + + /* Don't allow mounting unless the caller has CAP_SYS_ADMIN + * over the namespace. + */ + if (!(fc->sb_flags & SB_KERNMOUNT) && + !ns_capable(fc->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + sb = sget_userns(fc->fs_type, ns_test_super, ns_set_super, + fc->sb_flags, fc->user_ns, ns); + if (IS_ERR(sb)) + return PTR_ERR(sb); + + if (!sb->s_root) { + int err; + err = fill_super(sb, fc); + if (err) { + deactivate_locked_super(sb); + return err; + } + + sb->s_flags |= SB_ACTIVE; + } + + if (!fc->root) { + fc->root = sb->s_root; + dget(sb->s_root); + } + return 0; +} +EXPORT_SYMBOL(mount_ns_fc); + #ifdef CONFIG_BLOCK static int set_bdev_super(struct super_block *s, void *data) { @@ -1196,7 +1320,7 @@ struct dentry *mount_single(struct file_system_type *fs_type, } s->s_flags |= SB_ACTIVE; } else { - do_remount_sb(s, flags, data, 0); + do_remount_sb(s, flags, data, 0, NULL); } return dget(s->s_root); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 3138da4491da..9fd6555122da 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -54,6 +54,7 @@ struct workqueue_struct; struct iov_iter; struct fscrypt_info; struct fscrypt_operations; +struct fs_context; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -701,6 +702,11 @@ static inline void inode_unlock(struct inode *inode) up_write(&inode->i_rwsem); } +static inline int inode_lock_killable(struct inode *inode) +{ + return down_write_killable(&inode->i_rwsem); +} + static inline void inode_lock_shared(struct inode *inode) { down_read(&inode->i_rwsem); @@ -1814,6 +1820,7 @@ struct super_operations { int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); + int (*remount_fs_fc) (struct super_block *, struct fs_context *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); @@ -2048,8 +2055,10 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ + unsigned short fs_context_size; /* Size of superblock config context to allocate */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); + int (*init_fs_context)(struct fs_context *, struct super_block *); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; @@ -2067,6 +2076,10 @@ struct file_system_type { #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) +extern int mount_ns_fc(struct fs_context *fc, + int (*fill_super)(struct super_block *sb, + struct fs_context *fc), + void *ns); extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags, void *data, void *ns, struct user_namespace *user_ns, int (*fill_super)(struct super_block *, void *, int)); @@ -2089,6 +2102,9 @@ void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); int get_anon_bdev(dev_t *); void free_anon_bdev(dev_t); +struct super_block *sget_fc(struct fs_context *fc, + int (*test)(struct super_block *, struct fs_context *), + int (*set)(struct super_block *, struct fs_context *)); struct super_block *sget_userns(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), @@ -2133,6 +2149,7 @@ extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data); #define kern_mount(type) kern_mount_data(type, NULL) +extern struct vfsmount *kern_mount_data_fc(struct fs_context *); extern void kern_unmount(struct vfsmount *mnt); extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 429c40be2c9e..d29fb7b287fd 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -69,4 +69,16 @@ struct fs_context_operations { int (*get_tree)(struct fs_context *fc); }; +extern struct fs_context *vfs_new_fs_context(struct file_system_type *fs_type, + struct super_block *src_sb, + unsigned int ms_flags, + enum fs_context_purpose purpose); +extern struct fs_context *vfs_sb_reconfig(struct vfsmount *mnt, + unsigned int ms_flags); +extern struct fs_context *vfs_dup_fs_context(struct fs_context *src); +extern int vfs_parse_mount_option(struct fs_context *fc, char *data); +extern int generic_monolithic_mount_data(struct fs_context *fc, void *data); +extern int vfs_get_tree(struct fs_context *fc); +extern void put_fs_context(struct fs_context *fc); + #endif /* _LINUX_FS_CONTEXT_H */ diff --git a/include/linux/mount.h b/include/linux/mount.h index 8e0352af06b7..c990906ccced 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -20,6 +20,7 @@ struct super_block; struct vfsmount; struct dentry; struct mnt_namespace; +struct fs_context; #define MNT_NOSUID 0x01 #define MNT_NODEV 0x02 @@ -90,6 +91,7 @@ struct file_system_type; extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data); +extern struct vfsmount *vfs_kern_mount_fc(struct fs_context *fc); extern struct vfsmount *vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, const char *name, void *data);