diff options
| -rw-r--r-- | fs/Makefile | 2 | ||||
| -rw-r--r-- | fs/mount.h | 24 | ||||
| -rw-r--r-- | fs/namespace.c | 218 | ||||
| -rw-r--r-- | fs/proc/base.c | 114 | ||||
| -rw-r--r-- | fs/proc_namespace.c | 331 | ||||
| -rw-r--r-- | include/linux/mnt_namespace.h | 30 |
6 files changed, 368 insertions, 351 deletions
diff --git a/fs/Makefile b/fs/Makefile index d2c3353..310cfc4 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -19,6 +19,8 @@ else obj-y += no-block.o endif +obj-$(CONFIG_PROC_FS) += proc_namespace.o + obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o obj-y += notify/ obj-$(CONFIG_EPOLL) += eventpoll.o @@ -1,4 +1,14 @@ #include <linux/mount.h> +#include <linux/seq_file.h> +#include <linux/poll.h> + +struct mnt_namespace { + atomic_t count; + struct vfsmount * root; + struct list_head list; + wait_queue_head_t poll; + int event; +}; struct mnt_pcp { int mnt_count; @@ -49,3 +59,17 @@ static inline int mnt_has_parent(struct mount *mnt) } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *, int); + +static inline void get_mnt_ns(struct mnt_namespace *ns) +{ + atomic_inc(&ns->count); +} + +struct proc_mounts { + struct seq_file m; /* must be the first element */ + struct mnt_namespace *ns; + struct path root; + int (*show)(struct seq_file *, struct vfsmount *); +}; + +extern const struct seq_operations mounts_op; diff --git a/fs/namespace.c b/fs/namespace.c index cd63893..21a8261 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -898,10 +898,10 @@ void replace_mount_options(struct super_block *sb, char *options) EXPORT_SYMBOL(replace_mount_options); #ifdef CONFIG_PROC_FS -/* iterator */ +/* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { - struct proc_mounts *p = m->private; + struct proc_mounts *p = container_of(m, struct proc_mounts, m); down_read(&namespace_sem); return seq_list_start(&p->ns->list, *pos); @@ -909,7 +909,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) static void *m_next(struct seq_file *m, void *v, loff_t *pos) { - struct proc_mounts *p = m->private; + struct proc_mounts *p = container_of(m, struct proc_mounts, m); return seq_list_next(v, &p->ns->list, pos); } @@ -919,222 +919,18 @@ static void m_stop(struct seq_file *m, void *v) up_read(&namespace_sem); } -int mnt_had_events(struct proc_mounts *p) -{ - struct mnt_namespace *ns = p->ns; - int res = 0; - - br_read_lock(vfsmount_lock); - if (p->m.poll_event != ns->event) { - p->m.poll_event = ns->event; - res = 1; - } - br_read_unlock(vfsmount_lock); - - return res; -} - -struct proc_fs_info { - int flag; - const char *str; -}; - -static int show_sb_opts(struct seq_file *m, struct super_block *sb) -{ - static const struct proc_fs_info fs_info[] = { - { MS_SYNCHRONOUS, ",sync" }, - { MS_DIRSYNC, ",dirsync" }, - { MS_MANDLOCK, ",mand" }, - { 0, NULL } - }; - const struct proc_fs_info *fs_infop; - - for (fs_infop = fs_info; fs_infop->flag; fs_infop++) { - if (sb->s_flags & fs_infop->flag) - seq_puts(m, fs_infop->str); - } - - return security_sb_show_options(m, sb); -} - -static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt) -{ - static const struct proc_fs_info mnt_info[] = { - { MNT_NOSUID, ",nosuid" }, - { MNT_NODEV, ",nodev" }, - { MNT_NOEXEC, ",noexec" }, - { MNT_NOATIME, ",noatime" }, - { MNT_NODIRATIME, ",nodiratime" }, - { MNT_RELATIME, ",relatime" }, - { 0, NULL } - }; - const struct proc_fs_info *fs_infop; - - for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) { - if (mnt->mnt_flags & fs_infop->flag) - seq_puts(m, fs_infop->str); - } -} - -static void show_type(struct seq_file *m, struct super_block *sb) -{ - mangle(m, sb->s_type->name); - if (sb->s_subtype && sb->s_subtype[0]) { - seq_putc(m, '.'); - mangle(m, sb->s_subtype); - } -} - -static int show_vfsmnt(struct seq_file *m, void *v) +static int m_show(struct seq_file *m, void *v) { + struct proc_mounts *p = container_of(m, struct proc_mounts, m); struct mount *r = list_entry(v, struct mount, mnt_list); - struct vfsmount *mnt = &r->mnt; - int err = 0; - struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; - - if (mnt->mnt_sb->s_op->show_devname) { - err = mnt->mnt_sb->s_op->show_devname(m, mnt); - if (err) - goto out; - } else { - mangle(m, r->mnt_devname ? r->mnt_devname : "none"); - } - seq_putc(m, ' '); - seq_path(m, &mnt_path, " \t\n\\"); - seq_putc(m, ' '); - show_type(m, mnt->mnt_sb); - seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw"); - err = show_sb_opts(m, mnt->mnt_sb); - if (err) - goto out; - show_mnt_opts(m, mnt); - if (mnt->mnt_sb->s_op->show_options) - err = mnt->mnt_sb->s_op->show_options(m, mnt); - seq_puts(m, " 0 0\n"); -out: - return err; + return p->show(m, &r->mnt); } const struct seq_operations mounts_op = { .start = m_start, .next = m_next, .stop = m_stop, - .show = show_vfsmnt -}; - -static int show_mountinfo(struct seq_file *m, void *v) -{ - struct proc_mounts *p = m->private; - struct mount *r = list_entry(v, struct mount, mnt_list); - struct vfsmount *mnt = &r->mnt; - struct super_block *sb = mnt->mnt_sb; - struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; - struct path root = p->root; - int err = 0; - - seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id, - MAJOR(sb->s_dev), MINOR(sb->s_dev)); - if (sb->s_op->show_path) - err = sb->s_op->show_path(m, mnt); - else - seq_dentry(m, mnt->mnt_root, " \t\n\\"); - if (err) - goto out; - seq_putc(m, ' '); - - /* mountpoints outside of chroot jail will give SEQ_SKIP on this */ - err = seq_path_root(m, &mnt_path, &root, " \t\n\\"); - if (err) - goto out; - - seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw"); - show_mnt_opts(m, mnt); - - /* Tagged fields ("foo:X" or "bar") */ - if (IS_MNT_SHARED(r)) - seq_printf(m, " shared:%i", r->mnt_group_id); - if (IS_MNT_SLAVE(r)) { - int master = r->mnt_master->mnt_group_id; - int dom = get_dominating_id(r, &p->root); - seq_printf(m, " master:%i", master); - if (dom && dom != master) - seq_printf(m, " propagate_from:%i", dom); - } - if (IS_MNT_UNBINDABLE(r)) - seq_puts(m, " unbindable"); - - /* Filesystem specific data */ - seq_puts(m, " - "); - show_type(m, sb); - seq_putc(m, ' '); - if (sb->s_op->show_devname) - err = sb->s_op->show_devname(m, mnt); - else - mangle(m, r->mnt_devname ? r->mnt_devname : "none"); - if (err) - goto out; - seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw"); - err = show_sb_opts(m, sb); - if (err) - goto out; - if (sb->s_op->show_options) - err = sb->s_op->show_options(m, mnt); - seq_putc(m, '\n'); -out: - return err; -} - -const struct seq_operations mountinfo_op = { - .start = m_start, - .next = m_next, - .stop = m_stop, - .show = show_mountinfo, -}; - -static int show_vfsstat(struct seq_file *m, void *v) -{ - struct mount *r = list_entry(v, struct mount, mnt_list); - struct vfsmount *mnt = &r->mnt; - struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; - int err = 0; - - /* device */ - if (mnt->mnt_sb->s_op->show_devname) { - seq_puts(m, "device "); - err = mnt->mnt_sb->s_op->show_devname(m, mnt); - } else { - if (r->mnt_devname) { - seq_puts(m, "device "); - mangle(m, r->mnt_devname); - } else - seq_puts(m, "no device"); - } - - /* mount point */ - seq_puts(m, " mounted on "); - seq_path(m, &mnt_path, " \t\n\\"); - seq_putc(m, ' '); - - /* file system type */ - seq_puts(m, "with fstype "); - show_type(m, mnt->mnt_sb); - - /* optional statistics */ - if (mnt->mnt_sb->s_op->show_stats) { - seq_putc(m, ' '); - if (!err) - err = mnt->mnt_sb->s_op->show_stats(m, mnt); - } - - seq_putc(m, '\n'); - return err; -} - -const struct seq_operations mountstats_op = { - .start = m_start, - .next = m_next, - .stop = m_stop, - .show = show_vfsstat, + .show = m_show, }; #endif /* CONFIG_PROC_FS */ diff --git a/fs/proc/base.c b/fs/proc/base.c index 851ba3d..07446b5 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -631,120 +631,6 @@ static const struct inode_operations proc_def_inode_operations = { .setattr = proc_setattr, }; -static int mounts_open_common(struct inode *inode, struct file *file, - const struct seq_operations *op) -{ - struct task_struct *task = get_proc_task(inode); - struct nsproxy *nsp; - struct mnt_namespace *ns = NULL; - struct path root; - struct proc_mounts *p; - int ret = -EINVAL; - - if (task) { - rcu_read_lock(); - nsp = task_nsproxy(task); - if (nsp) { - ns = nsp->mnt_ns; - if (ns) - get_mnt_ns(ns); - } - rcu_read_unlock(); - if (ns && get_task_root(task, &root) == 0) - ret = 0; - put_task_struct(task); - } - - if (!ns) - goto err; - if (ret) - goto err_put_ns; - - ret = -ENOMEM; - p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL); - if (!p) - goto err_put_path; - - file->private_data = &p->m; - ret = seq_open(file, op); - if (ret) - goto err_free; - - p->m.private = p; - p->ns = ns; - p->root = root; - p->m.poll_event = ns->event; - - return 0; - - err_free: - kfree(p); - err_put_path: - path_put(&root); - err_put_ns: - put_mnt_ns(ns); - err: - return ret; -} - -static int mounts_release(struct inode *inode, struct file *file) -{ - struct proc_mounts *p = file->private_data; - path_put(&p->root); - put_mnt_ns(p->ns); - return seq_release(inode, file); -} - -static unsigned mounts_poll(struct file *file, poll_table *wait) -{ - struct proc_mounts *p = file->private_data; - unsigned res = POLLIN | POLLRDNORM; - - poll_wait(file, &p->ns->poll, wait); - if (mnt_had_events(p)) - res |= POLLERR | POLLPRI; - - return res; -} - -static int mounts_open(struct inode *inode, struct file *file) -{ - return mounts_open_common(inode, file, &mounts_op); -} - -static const struct file_operations proc_mounts_operations = { - .open = mounts_open, - .read = seq_read, - .llseek = seq_lseek, - .release = mounts_release, - .poll = mounts_poll, -}; - -static int mountinfo_open(struct inode *inode, struct file *file) -{ - return mounts_open_common(inode, file, &mountinfo_op); -} - -static const struct file_operations proc_mountinfo_operations = { - .open = mountinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = mounts_release, - .poll = mounts_poll, -}; - -static int mountstats_open(struct inode *inode, struct file *file) -{ - return mounts_open_common(inode, file, &mountstats_op); -} - -static const struct file_operations proc_mountstats_operations = { - .open = mountstats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = mounts_release, -}; - #define PROC_BLOCK_SIZE (3*1024) /* 4K page size but our output routines use some slack for overruns */ static ssize_t proc_info_read(struct file * file, char __user * buf, diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c new file mode 100644 index 0000000..9dcd954 --- /dev/null +++ b/fs/proc_namespace.c @@ -0,0 +1,331 @@ +/* + * fs/proc_namespace.c - handling of /proc/<pid>/{mounts,mountinfo,mountstats} + * + * In fact, that's a piece of procfs; it's *almost* isolated from + * the rest of fs/proc, but has rather close relationships with + * fs/namespace.c, thus here instead of fs/proc + * + */ +#include <linux/mnt_namespace.h> +#include <linux/nsproxy.h> +#include <linux/security.h> +#include <linux/fs_struct.h> +#include "proc/internal.h" /* only for get_proc_task() in ->open() */ + +#include "pnode.h" +#include "internal.h" + +static unsigned mounts_poll(struct file *file, poll_table *wait) +{ + struct proc_mounts *p = file->private_data; + struct mnt_namespace *ns = p->ns; + unsigned res = POLLIN | POLLRDNORM; + + poll_wait(file, &p->ns->poll, wait); + + br_read_lock(vfsmount_lock); + if (p->m.poll_event != ns->event) { + p->m.poll_event = ns->event; + res |= POLLERR | POLLPRI; + } + br_read_unlock(vfsmount_lock); + + return res; +} + +struct proc_fs_info { + int flag; + const char *str; +}; + +static int show_sb_opts(struct seq_file *m, struct super_block *sb) +{ + static const struct proc_fs_info fs_info[] = { + { MS_SYNCHRONOUS, ",sync" }, + { MS_DIRSYNC, ",dirsync" }, + { MS_MANDLOCK, ",mand" }, + { 0, NULL } + }; + const struct proc_fs_info *fs_infop; + + for (fs_infop = fs_info; fs_infop->flag; fs_infop++) { + if (sb->s_flags & fs_infop->flag) + seq_puts(m, fs_infop->str); + } + + return security_sb_show_options(m, sb); +} + +static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt) +{ + static const struct proc_fs_info mnt_info[] = { + { MNT_NOSUID, ",nosuid" }, + { MNT_NODEV, ",nodev" }, + { MNT_NOEXEC, ",noexec" }, + { MNT_NOATIME, ",noatime" }, + { MNT_NODIRATIME, ",nodiratime" }, + { MNT_RELATIME, ",relatime" }, + { 0, NULL } + }; + const struct proc_fs_info *fs_infop; + + for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) { + if (mnt->mnt_flags & fs_infop->flag) + seq_puts(m, fs_infop->str); + } +} + +static inline void mangle(struct seq_file *m, const char *s) +{ + seq_escape(m, s, " \t\n\\"); +} + +static void show_type(struct seq_file *m, struct super_block *sb) +{ + mangle(m, sb->s_type->name); + if (sb->s_subtype && sb->s_subtype[0]) { + seq_putc(m, '.'); + mangle(m, sb->s_subtype); + } +} + +static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt) +{ + struct mount *r = real_mount(mnt); + int err = 0; + struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; + + if (mnt->mnt_sb->s_op->show_devname) { + err = mnt->mnt_sb->s_op->show_devname(m, mnt); + if (err) + goto out; + } else { + mangle(m, r->mnt_devname ? r->mnt_devname : "none"); + } + seq_putc(m, ' '); + seq_path(m, &mnt_path, " \t\n\\"); + seq_putc(m, ' '); + show_type(m, mnt->mnt_sb); + seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw"); + err = show_sb_opts(m, mnt->mnt_sb); + if (err) + goto out; + show_mnt_opts(m, mnt); + if (mnt->mnt_sb->s_op->show_options) + err = mnt->mnt_sb->s_op->show_options(m, mnt); + seq_puts(m, " 0 0\n"); +out: + return err; +} + +static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) +{ + struct proc_mounts *p = m->private; + struct mount *r = real_mount(mnt); + struct super_block *sb = mnt->mnt_sb; + struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; + struct path root = p->root; + int err = 0; + + seq_printf(m, "%i %i %u:%u ", r->mnt_id, r->mnt_parent->mnt_id, + MAJOR(sb->s_dev), MINOR(sb->s_dev)); + if (sb->s_op->show_path) + err = sb->s_op->show_path(m, mnt); + else + seq_dentry(m, mnt->mnt_root, " \t\n\\"); + if (err) + goto out; + seq_putc(m, ' '); + + /* mountpoints outside of chroot jail will give SEQ_SKIP on this */ + err = seq_path_root(m, &mnt_path, &root, " \t\n\\"); + if (err) + goto out; + + seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw"); + show_mnt_opts(m, mnt); + + /* Tagged fields ("foo:X" or "bar") */ + if (IS_MNT_SHARED(r)) + seq_printf(m, " shared:%i", r->mnt_group_id); + if (IS_MNT_SLAVE(r)) { + int master = r->mnt_master->mnt_group_id; + int dom = get_dominating_id(r, &p->root); + seq_printf(m, " master:%i", master); + if (dom && dom != master) + seq_printf(m, " propagate_from:%i", dom); + } + if (IS_MNT_UNBINDABLE(r)) + seq_puts(m, " unbindable"); + + /* Filesystem specific data */ + seq_puts(m, " - "); + show_type(m, sb); + seq_putc(m, ' '); + if (sb->s_op->show_devname) + err = sb->s_op->show_devname(m, mnt); + else + mangle(m, r->mnt_devname ? r->mnt_devname : "none"); + if (err) + goto out; + seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw"); + err = show_sb_opts(m, sb); + if (err) + goto out; + if (sb->s_op->show_options) + err = sb->s_op->show_options(m, mnt); + seq_putc(m, '\n'); +out: + return err; +} + +static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt) +{ + struct mount *r = real_mount(mnt); + struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; + int err = 0; + + /* device */ + if (mnt->mnt_sb->s_op->show_devname) { + seq_puts(m, "device "); + err = mnt->mnt_sb->s_op->show_devname(m, mnt); + } else { + if (r->mnt_devname) { + seq_puts(m, "device "); + mangle(m, r->mnt_devname); + } else + seq_puts(m, "no device"); + } + + /* mount point */ + seq_puts(m, " mounted on "); + seq_path(m, &mnt_path, " \t\n\\"); + seq_putc(m, ' '); + + /* file system type */ + seq_puts(m, "with fstype "); + show_type(m, mnt->mnt_sb); + + /* optional statistics */ + if (mnt->mnt_sb->s_op->show_stats) { + seq_putc(m, ' '); + if (!err) + err = mnt->mnt_sb->s_op->show_stats(m, mnt); + } + + seq_putc(m, '\n'); + return err; +} + +static int mounts_open_common(struct inode *inode, struct file *file, + int (*show)(struct seq_file *, struct vfsmount *)) +{ + struct task_struct *task = get_proc_task(inode); + struct nsproxy *nsp; + struct mnt_namespace *ns = NULL; + struct path root; + struct proc_mounts *p; + int ret = -EINVAL; + + if (!task) + goto err; + + rcu_read_lock(); + nsp = task_nsproxy(task); + if (!nsp) { + rcu_read_unlock(); + put_task_struct(task); + goto err; + } + ns = nsp->mnt_ns; + if (!ns) { + rcu_read_unlock(); + put_task_struct(task); + goto err; + } + get_mnt_ns(ns); + rcu_read_unlock(); + task_lock(task); + if (!task->fs) { + task_unlock(task); + put_task_struct(task); + ret = -ENOENT; + goto err_put_ns; + } + get_fs_root(task->fs, &root); + task_unlock(task); + put_task_struct(task); + + ret = -ENOMEM; + p = kmalloc(sizeof(struct proc_mounts), GFP_KERNEL); + if (!p) + goto err_put_path; + + file->private_data = &p->m; + ret = seq_open(file, &mounts_op); + if (ret) + goto err_free; + + p->m.private = p; + p->ns = ns; + p->root = root; + p->m.poll_event = ns->event; + p->show = show; + + return 0; + + err_free: + kfree(p); + err_put_path: + path_put(&root); + err_put_ns: + put_mnt_ns(ns); + err: + return ret; +} + +static int mounts_release(struct inode *inode, struct file *file) +{ + struct proc_mounts *p = file->private_data; + path_put(&p->root); + put_mnt_ns(p->ns); + return seq_release(inode, file); +} + +static int mounts_open(struct inode *inode, struct file *file) +{ + return mounts_open_common(inode, file, show_vfsmnt); +} + +static int mountinfo_open(struct inode *inode, struct file *file) +{ + return mounts_open_common(inode, file, show_mountinfo); +} + +static int mountstats_open(struct inode *inode, struct file *file) +{ + return mounts_open_common(inode, file, show_vfsstat); +} + +const struct file_operations proc_mounts_operations = { + .open = mounts_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mounts_release, + .poll = mounts_poll, +}; + +const struct file_operations proc_mountinfo_operations = { + .open = mountinfo_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mounts_release, + .poll = mounts_poll, +}; + +const struct file_operations proc_mountstats_operations = { + .open = mountstats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mounts_release, +}; diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h index e87ec01..5a8e390 100644 --- a/include/linux/mnt_namespace.h +++ b/include/linux/mnt_namespace.h @@ -2,38 +2,16 @@ #define _NAMESPACE_H_ #ifdef __KERNEL__ -#include <linux/path.h> -#include <linux/seq_file.h> -#include <linux/wait.h> - -struct mnt_namespace { - atomic_t count; - struct vfsmount * root; - struct list_head list; - wait_queue_head_t poll; - int event; -}; - -struct proc_mounts { - struct seq_file m; /* must be the first element */ - struct mnt_namespace *ns; - struct path root; -}; - +struct mnt_namespace; struct fs_struct; extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *, struct fs_struct *); extern void put_mnt_ns(struct mnt_namespace *ns); -static inline void get_mnt_ns(struct mnt_namespace *ns) -{ - atomic_inc(&ns->count); -} -extern const struct seq_operations mounts_op; -extern const struct seq_operations mountinfo_op; -extern const struct seq_operations mountstats_op; -extern int mnt_had_events(struct proc_mounts *); +extern const struct file_operations proc_mounts_operations; +extern const struct file_operations proc_mountinfo_operations; +extern const struct file_operations proc_mountstats_operations; #endif #endif |
