linux/fs/kernfs/mount.c

336 lines
8.5 KiB
C
Raw Normal View History

/*
* fs/kernfs/mount.c - kernfs mount implementation
*
* Copyright (c) 2001-3 Patrick Mochel
* Copyright (c) 2007 SUSE Linux Products GmbH
* Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
*
* This file is released under the GPLv2.
*/
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/init.h>
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/namei.h>
cgroup, kernfs: make mountinfo show properly scoped path for cgroup namespaces Patch summary: When showing a cgroupfs entry in mountinfo, show the path of the mount root dentry relative to the reader's cgroup namespace root. Short explanation (courtesy of mkerrisk): If we create a new cgroup namespace, then we want both /proc/self/cgroup and /proc/self/mountinfo to show cgroup paths that are correctly virtualized with respect to the cgroup mount point. Previous to this patch, /proc/self/cgroup shows the right info, but /proc/self/mountinfo does not. Long version: When a uid 0 task which is in freezer cgroup /a/b, unshares a new cgroup namespace, and then mounts a new instance of the freezer cgroup, the new mount will be rooted at /a/b. The root dentry field of the mountinfo entry will show '/a/b'. cat > /tmp/do1 << EOF mount -t cgroup -o freezer freezer /mnt grep freezer /proc/self/mountinfo EOF unshare -Gm bash /tmp/do1 > 330 160 0:34 / /sys/fs/cgroup/freezer rw,nosuid,nodev,noexec,relatime - cgroup cgroup rw,freezer > 355 133 0:34 /a/b /mnt rw,relatime - cgroup freezer rw,freezer The task's freezer cgroup entry in /proc/self/cgroup will simply show '/': grep freezer /proc/self/cgroup 9:freezer:/ If instead the same task simply bind mounts the /a/b cgroup directory, the resulting mountinfo entry will again show /a/b for the dentry root. However in this case the task will find its own cgroup at /mnt/a/b, not at /mnt: mount --bind /sys/fs/cgroup/freezer/a/b /mnt 130 25 0:34 /a/b /mnt rw,nosuid,nodev,noexec,relatime shared:21 - cgroup cgroup rw,freezer In other words, there is no way for the task to know, based on what is in mountinfo, which cgroup directory is its own. Example (by mkerrisk): First, a little script to save some typing and verbiage: echo -e "\t/proc/self/cgroup:\t$(cat /proc/self/cgroup | grep freezer)" cat /proc/self/mountinfo | grep freezer | awk '{print "\tmountinfo:\t\t" $4 "\t" $5}' Create cgroup, place this shell into the cgroup, and look at the state of the /proc files: 2653 2653 # Our shell 14254 # cat(1) /proc/self/cgroup: 10:freezer:/a/b mountinfo: / /sys/fs/cgroup/freezer Create a shell in new cgroup and mount namespaces. The act of creating a new cgroup namespace causes the process's current cgroups directories to become its cgroup root directories. (Here, I'm using my own version of the "unshare" utility, which takes the same options as the util-linux version): Look at the state of the /proc files: /proc/self/cgroup: 10:freezer:/ mountinfo: / /sys/fs/cgroup/freezer The third entry in /proc/self/cgroup (the pathname of the cgroup inside the hierarchy) is correctly virtualized w.r.t. the cgroup namespace, which is rooted at /a/b in the outer namespace. However, the info in /proc/self/mountinfo is not for this cgroup namespace, since we are seeing a duplicate of the mount from the old mount namespace, and the info there does not correspond to the new cgroup namespace. However, trying to create a new mount still doesn't show us the right information in mountinfo: # propagating to other mountns /proc/self/cgroup: 7:freezer:/ mountinfo: /a/b /mnt/freezer The act of creating a new cgroup namespace caused the process's current freezer directory, "/a/b", to become its cgroup freezer root directory. In other words, the pathname directory of the directory within the newly mounted cgroup filesystem should be "/", but mountinfo wrongly shows us "/a/b". The consequence of this is that the process in the cgroup namespace cannot correctly construct the pathname of its cgroup root directory from the information in /proc/PID/mountinfo. With this patch, the dentry root field in mountinfo is shown relative to the reader's cgroup namespace. So the same steps as above: /proc/self/cgroup: 10:freezer:/a/b mountinfo: / /sys/fs/cgroup/freezer /proc/self/cgroup: 10:freezer:/ mountinfo: /../.. /sys/fs/cgroup/freezer /proc/self/cgroup: 10:freezer:/ mountinfo: / /mnt/freezer cgroup.clone_children freezer.parent_freezing freezer.state tasks cgroup.procs freezer.self_freezing notify_on_release 3164 2653 # First shell that placed in this cgroup 3164 # Shell started by 'unshare' 14197 # cat(1) Signed-off-by: Serge Hallyn <serge.hallyn@ubuntu.com> Tested-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2016-05-09 17:59:55 +03:00
#include <linux/seq_file.h>
#include "kernfs-internal.h"
struct kmem_cache *kernfs_node_cache;
static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data)
{
struct kernfs_root *root = kernfs_info(sb)->root;
struct kernfs_syscall_ops *scops = root->syscall_ops;
if (scops && scops->remount_fs)
return scops->remount_fs(root, flags, data);
return 0;
}
static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
{
struct kernfs_root *root = kernfs_root(dentry->d_fsdata);
struct kernfs_syscall_ops *scops = root->syscall_ops;
if (scops && scops->show_options)
return scops->show_options(sf, root);
return 0;
}
cgroup, kernfs: make mountinfo show properly scoped path for cgroup namespaces Patch summary: When showing a cgroupfs entry in mountinfo, show the path of the mount root dentry relative to the reader's cgroup namespace root. Short explanation (courtesy of mkerrisk): If we create a new cgroup namespace, then we want both /proc/self/cgroup and /proc/self/mountinfo to show cgroup paths that are correctly virtualized with respect to the cgroup mount point. Previous to this patch, /proc/self/cgroup shows the right info, but /proc/self/mountinfo does not. Long version: When a uid 0 task which is in freezer cgroup /a/b, unshares a new cgroup namespace, and then mounts a new instance of the freezer cgroup, the new mount will be rooted at /a/b. The root dentry field of the mountinfo entry will show '/a/b'. cat > /tmp/do1 << EOF mount -t cgroup -o freezer freezer /mnt grep freezer /proc/self/mountinfo EOF unshare -Gm bash /tmp/do1 > 330 160 0:34 / /sys/fs/cgroup/freezer rw,nosuid,nodev,noexec,relatime - cgroup cgroup rw,freezer > 355 133 0:34 /a/b /mnt rw,relatime - cgroup freezer rw,freezer The task's freezer cgroup entry in /proc/self/cgroup will simply show '/': grep freezer /proc/self/cgroup 9:freezer:/ If instead the same task simply bind mounts the /a/b cgroup directory, the resulting mountinfo entry will again show /a/b for the dentry root. However in this case the task will find its own cgroup at /mnt/a/b, not at /mnt: mount --bind /sys/fs/cgroup/freezer/a/b /mnt 130 25 0:34 /a/b /mnt rw,nosuid,nodev,noexec,relatime shared:21 - cgroup cgroup rw,freezer In other words, there is no way for the task to know, based on what is in mountinfo, which cgroup directory is its own. Example (by mkerrisk): First, a little script to save some typing and verbiage: echo -e "\t/proc/self/cgroup:\t$(cat /proc/self/cgroup | grep freezer)" cat /proc/self/mountinfo | grep freezer | awk '{print "\tmountinfo:\t\t" $4 "\t" $5}' Create cgroup, place this shell into the cgroup, and look at the state of the /proc files: 2653 2653 # Our shell 14254 # cat(1) /proc/self/cgroup: 10:freezer:/a/b mountinfo: / /sys/fs/cgroup/freezer Create a shell in new cgroup and mount namespaces. The act of creating a new cgroup namespace causes the process's current cgroups directories to become its cgroup root directories. (Here, I'm using my own version of the "unshare" utility, which takes the same options as the util-linux version): Look at the state of the /proc files: /proc/self/cgroup: 10:freezer:/ mountinfo: / /sys/fs/cgroup/freezer The third entry in /proc/self/cgroup (the pathname of the cgroup inside the hierarchy) is correctly virtualized w.r.t. the cgroup namespace, which is rooted at /a/b in the outer namespace. However, the info in /proc/self/mountinfo is not for this cgroup namespace, since we are seeing a duplicate of the mount from the old mount namespace, and the info there does not correspond to the new cgroup namespace. However, trying to create a new mount still doesn't show us the right information in mountinfo: # propagating to other mountns /proc/self/cgroup: 7:freezer:/ mountinfo: /a/b /mnt/freezer The act of creating a new cgroup namespace caused the process's current freezer directory, "/a/b", to become its cgroup freezer root directory. In other words, the pathname directory of the directory within the newly mounted cgroup filesystem should be "/", but mountinfo wrongly shows us "/a/b". The consequence of this is that the process in the cgroup namespace cannot correctly construct the pathname of its cgroup root directory from the information in /proc/PID/mountinfo. With this patch, the dentry root field in mountinfo is shown relative to the reader's cgroup namespace. So the same steps as above: /proc/self/cgroup: 10:freezer:/a/b mountinfo: / /sys/fs/cgroup/freezer /proc/self/cgroup: 10:freezer:/ mountinfo: /../.. /sys/fs/cgroup/freezer /proc/self/cgroup: 10:freezer:/ mountinfo: / /mnt/freezer cgroup.clone_children freezer.parent_freezing freezer.state tasks cgroup.procs freezer.self_freezing notify_on_release 3164 2653 # First shell that placed in this cgroup 3164 # Shell started by 'unshare' 14197 # cat(1) Signed-off-by: Serge Hallyn <serge.hallyn@ubuntu.com> Tested-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2016-05-09 17:59:55 +03:00
static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry)
{
struct kernfs_node *node = dentry->d_fsdata;
struct kernfs_root *root = kernfs_root(node);
struct kernfs_syscall_ops *scops = root->syscall_ops;
if (scops && scops->show_path)
return scops->show_path(sf, node, root);
seq_dentry(sf, dentry, " \t\n\\");
return 0;
cgroup, kernfs: make mountinfo show properly scoped path for cgroup namespaces Patch summary: When showing a cgroupfs entry in mountinfo, show the path of the mount root dentry relative to the reader's cgroup namespace root. Short explanation (courtesy of mkerrisk): If we create a new cgroup namespace, then we want both /proc/self/cgroup and /proc/self/mountinfo to show cgroup paths that are correctly virtualized with respect to the cgroup mount point. Previous to this patch, /proc/self/cgroup shows the right info, but /proc/self/mountinfo does not. Long version: When a uid 0 task which is in freezer cgroup /a/b, unshares a new cgroup namespace, and then mounts a new instance of the freezer cgroup, the new mount will be rooted at /a/b. The root dentry field of the mountinfo entry will show '/a/b'. cat > /tmp/do1 << EOF mount -t cgroup -o freezer freezer /mnt grep freezer /proc/self/mountinfo EOF unshare -Gm bash /tmp/do1 > 330 160 0:34 / /sys/fs/cgroup/freezer rw,nosuid,nodev,noexec,relatime - cgroup cgroup rw,freezer > 355 133 0:34 /a/b /mnt rw,relatime - cgroup freezer rw,freezer The task's freezer cgroup entry in /proc/self/cgroup will simply show '/': grep freezer /proc/self/cgroup 9:freezer:/ If instead the same task simply bind mounts the /a/b cgroup directory, the resulting mountinfo entry will again show /a/b for the dentry root. However in this case the task will find its own cgroup at /mnt/a/b, not at /mnt: mount --bind /sys/fs/cgroup/freezer/a/b /mnt 130 25 0:34 /a/b /mnt rw,nosuid,nodev,noexec,relatime shared:21 - cgroup cgroup rw,freezer In other words, there is no way for the task to know, based on what is in mountinfo, which cgroup directory is its own. Example (by mkerrisk): First, a little script to save some typing and verbiage: echo -e "\t/proc/self/cgroup:\t$(cat /proc/self/cgroup | grep freezer)" cat /proc/self/mountinfo | grep freezer | awk '{print "\tmountinfo:\t\t" $4 "\t" $5}' Create cgroup, place this shell into the cgroup, and look at the state of the /proc files: 2653 2653 # Our shell 14254 # cat(1) /proc/self/cgroup: 10:freezer:/a/b mountinfo: / /sys/fs/cgroup/freezer Create a shell in new cgroup and mount namespaces. The act of creating a new cgroup namespace causes the process's current cgroups directories to become its cgroup root directories. (Here, I'm using my own version of the "unshare" utility, which takes the same options as the util-linux version): Look at the state of the /proc files: /proc/self/cgroup: 10:freezer:/ mountinfo: / /sys/fs/cgroup/freezer The third entry in /proc/self/cgroup (the pathname of the cgroup inside the hierarchy) is correctly virtualized w.r.t. the cgroup namespace, which is rooted at /a/b in the outer namespace. However, the info in /proc/self/mountinfo is not for this cgroup namespace, since we are seeing a duplicate of the mount from the old mount namespace, and the info there does not correspond to the new cgroup namespace. However, trying to create a new mount still doesn't show us the right information in mountinfo: # propagating to other mountns /proc/self/cgroup: 7:freezer:/ mountinfo: /a/b /mnt/freezer The act of creating a new cgroup namespace caused the process's current freezer directory, "/a/b", to become its cgroup freezer root directory. In other words, the pathname directory of the directory within the newly mounted cgroup filesystem should be "/", but mountinfo wrongly shows us "/a/b". The consequence of this is that the process in the cgroup namespace cannot correctly construct the pathname of its cgroup root directory from the information in /proc/PID/mountinfo. With this patch, the dentry root field in mountinfo is shown relative to the reader's cgroup namespace. So the same steps as above: /proc/self/cgroup: 10:freezer:/a/b mountinfo: / /sys/fs/cgroup/freezer /proc/self/cgroup: 10:freezer:/ mountinfo: /../.. /sys/fs/cgroup/freezer /proc/self/cgroup: 10:freezer:/ mountinfo: / /mnt/freezer cgroup.clone_children freezer.parent_freezing freezer.state tasks cgroup.procs freezer.self_freezing notify_on_release 3164 2653 # First shell that placed in this cgroup 3164 # Shell started by 'unshare' 14197 # cat(1) Signed-off-by: Serge Hallyn <serge.hallyn@ubuntu.com> Tested-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2016-05-09 17:59:55 +03:00
}
const struct super_operations kernfs_sops = {
.statfs = simple_statfs,
.drop_inode = generic_delete_inode,
.evict_inode = kernfs_evict_inode,
.remount_fs = kernfs_sop_remount_fs,
.show_options = kernfs_sop_show_options,
cgroup, kernfs: make mountinfo show properly scoped path for cgroup namespaces Patch summary: When showing a cgroupfs entry in mountinfo, show the path of the mount root dentry relative to the reader's cgroup namespace root. Short explanation (courtesy of mkerrisk): If we create a new cgroup namespace, then we want both /proc/self/cgroup and /proc/self/mountinfo to show cgroup paths that are correctly virtualized with respect to the cgroup mount point. Previous to this patch, /proc/self/cgroup shows the right info, but /proc/self/mountinfo does not. Long version: When a uid 0 task which is in freezer cgroup /a/b, unshares a new cgroup namespace, and then mounts a new instance of the freezer cgroup, the new mount will be rooted at /a/b. The root dentry field of the mountinfo entry will show '/a/b'. cat > /tmp/do1 << EOF mount -t cgroup -o freezer freezer /mnt grep freezer /proc/self/mountinfo EOF unshare -Gm bash /tmp/do1 > 330 160 0:34 / /sys/fs/cgroup/freezer rw,nosuid,nodev,noexec,relatime - cgroup cgroup rw,freezer > 355 133 0:34 /a/b /mnt rw,relatime - cgroup freezer rw,freezer The task's freezer cgroup entry in /proc/self/cgroup will simply show '/': grep freezer /proc/self/cgroup 9:freezer:/ If instead the same task simply bind mounts the /a/b cgroup directory, the resulting mountinfo entry will again show /a/b for the dentry root. However in this case the task will find its own cgroup at /mnt/a/b, not at /mnt: mount --bind /sys/fs/cgroup/freezer/a/b /mnt 130 25 0:34 /a/b /mnt rw,nosuid,nodev,noexec,relatime shared:21 - cgroup cgroup rw,freezer In other words, there is no way for the task to know, based on what is in mountinfo, which cgroup directory is its own. Example (by mkerrisk): First, a little script to save some typing and verbiage: echo -e "\t/proc/self/cgroup:\t$(cat /proc/self/cgroup | grep freezer)" cat /proc/self/mountinfo | grep freezer | awk '{print "\tmountinfo:\t\t" $4 "\t" $5}' Create cgroup, place this shell into the cgroup, and look at the state of the /proc files: 2653 2653 # Our shell 14254 # cat(1) /proc/self/cgroup: 10:freezer:/a/b mountinfo: / /sys/fs/cgroup/freezer Create a shell in new cgroup and mount namespaces. The act of creating a new cgroup namespace causes the process's current cgroups directories to become its cgroup root directories. (Here, I'm using my own version of the "unshare" utility, which takes the same options as the util-linux version): Look at the state of the /proc files: /proc/self/cgroup: 10:freezer:/ mountinfo: / /sys/fs/cgroup/freezer The third entry in /proc/self/cgroup (the pathname of the cgroup inside the hierarchy) is correctly virtualized w.r.t. the cgroup namespace, which is rooted at /a/b in the outer namespace. However, the info in /proc/self/mountinfo is not for this cgroup namespace, since we are seeing a duplicate of the mount from the old mount namespace, and the info there does not correspond to the new cgroup namespace. However, trying to create a new mount still doesn't show us the right information in mountinfo: # propagating to other mountns /proc/self/cgroup: 7:freezer:/ mountinfo: /a/b /mnt/freezer The act of creating a new cgroup namespace caused the process's current freezer directory, "/a/b", to become its cgroup freezer root directory. In other words, the pathname directory of the directory within the newly mounted cgroup filesystem should be "/", but mountinfo wrongly shows us "/a/b". The consequence of this is that the process in the cgroup namespace cannot correctly construct the pathname of its cgroup root directory from the information in /proc/PID/mountinfo. With this patch, the dentry root field in mountinfo is shown relative to the reader's cgroup namespace. So the same steps as above: /proc/self/cgroup: 10:freezer:/a/b mountinfo: / /sys/fs/cgroup/freezer /proc/self/cgroup: 10:freezer:/ mountinfo: /../.. /sys/fs/cgroup/freezer /proc/self/cgroup: 10:freezer:/ mountinfo: / /mnt/freezer cgroup.clone_children freezer.parent_freezing freezer.state tasks cgroup.procs freezer.self_freezing notify_on_release 3164 2653 # First shell that placed in this cgroup 3164 # Shell started by 'unshare' 14197 # cat(1) Signed-off-by: Serge Hallyn <serge.hallyn@ubuntu.com> Tested-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Tejun Heo <tj@kernel.org>
2016-05-09 17:59:55 +03:00
.show_path = kernfs_sop_show_path,
};
/**
* kernfs_root_from_sb - determine kernfs_root associated with a super_block
* @sb: the super_block in question
*
* Return the kernfs_root associated with @sb. If @sb is not a kernfs one,
* %NULL is returned.
*/
struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
{
if (sb->s_op == &kernfs_sops)
return kernfs_info(sb)->root;
return NULL;
}
/*
* find the next ancestor in the path down to @child, where @parent was the
* ancestor whose descendant we want to find.
*
* Say the path is /a/b/c/d. @child is d, @parent is NULL. We return the root
* node. If @parent is b, then we return the node for c.
* Passing in d as @parent is not ok.
*/
static struct kernfs_node *find_next_ancestor(struct kernfs_node *child,
struct kernfs_node *parent)
{
if (child == parent) {
pr_crit_once("BUG in find_next_ancestor: called with parent == child");
return NULL;
}
while (child->parent != parent) {
if (!child->parent)
return NULL;
child = child->parent;
}
return child;
}
/**
* kernfs_node_dentry - get a dentry for the given kernfs_node
* @kn: kernfs_node for which a dentry is needed
* @sb: the kernfs super_block
*/
struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
struct super_block *sb)
{
struct dentry *dentry;
struct kernfs_node *knparent = NULL;
BUG_ON(sb->s_op != &kernfs_sops);
dentry = dget(sb->s_root);
/* Check if this is the root kernfs_node */
if (!kn->parent)
return dentry;
knparent = find_next_ancestor(kn, NULL);
if (WARN_ON(!knparent))
return ERR_PTR(-EINVAL);
do {
struct dentry *dtmp;
struct kernfs_node *kntmp;
if (kn == knparent)
return dentry;
kntmp = find_next_ancestor(kn, knparent);
if (WARN_ON(!kntmp))
return ERR_PTR(-EINVAL);
dtmp = lookup_one_len_unlocked(kntmp->name, dentry,
strlen(kntmp->name));
dput(dentry);
if (IS_ERR(dtmp))
return dtmp;
knparent = kntmp;
dentry = dtmp;
} while (true);
}
static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
{
struct kernfs_super_info *info = kernfs_info(sb);
struct inode *inode;
struct dentry *root;
info->sb = sb;
/* Userspace would break if executables or devices appear on sysfs */
sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
sb->s_blocksize = PAGE_SIZE;
sb->s_blocksize_bits = PAGE_SHIFT;
sb->s_magic = magic;
sb->s_op = &kernfs_sops;
sb->s_time_gran = 1;
/* get root inode, initialize and unlock it */
mutex_lock(&kernfs_mutex);
inode = kernfs_get_inode(sb, info->root->kn);
mutex_unlock(&kernfs_mutex);
if (!inode) {
pr_debug("kernfs: could not get root inode\n");
return -ENOMEM;
}
/* instantiate and link root dentry */
root = d_make_root(inode);
if (!root) {
pr_debug("%s: could not get root dentry!\n", __func__);
return -ENOMEM;
}
kernfs_get(info->root->kn);
root->d_fsdata = info->root->kn;
sb->s_root = root;
sb->s_d_op = &kernfs_dops;
return 0;
}
static int kernfs_test_super(struct super_block *sb, void *data)
{
struct kernfs_super_info *sb_info = kernfs_info(sb);
struct kernfs_super_info *info = data;
return sb_info->root == info->root && sb_info->ns == info->ns;
}
static int kernfs_set_super(struct super_block *sb, void *data)
{
int error;
error = set_anon_super(sb, data);
if (!error)
sb->s_fs_info = data;
return error;
}
/**
* kernfs_super_ns - determine the namespace tag of a kernfs super_block
* @sb: super_block of interest
*
* Return the namespace tag associated with kernfs super_block @sb.
*/
const void *kernfs_super_ns(struct super_block *sb)
{
struct kernfs_super_info *info = kernfs_info(sb);
return info->ns;
}
/**
* kernfs_mount_ns - kernfs mount helper
* @fs_type: file_system_type of the fs being mounted
* @flags: mount flags specified for the mount
* @root: kernfs_root of the hierarchy being mounted
* @magic: file system specific magic number
* @new_sb_created: tell the caller if we allocated a new superblock
* @ns: optional namespace tag of the mount
*
* This is to be called from each kernfs user's file_system_type->mount()
* implementation, which should pass through the specified @fs_type and
* @flags, and specify the hierarchy and namespace tag to mount via @root
* and @ns, respectively.
*
* The return value can be passed to the vfs layer verbatim.
*/
struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
struct kernfs_root *root, unsigned long magic,
bool *new_sb_created, const void *ns)
{
struct super_block *sb;
struct kernfs_super_info *info;
int error;
info = kzalloc(sizeof(*info), GFP_KERNEL);
if (!info)
return ERR_PTR(-ENOMEM);
info->root = root;
info->ns = ns;
fs: Add user namespace member to struct super_block Start marking filesystems with a user namespace owner, s_user_ns. In this change this is only used for permission checks of who may mount a filesystem. Ultimately s_user_ns will be used for translating ids and checking capabilities for filesystems mounted from user namespaces. The default policy for setting s_user_ns is implemented in sget(), which arranges for s_user_ns to be set to current_user_ns() and to ensure that the mounter of the filesystem has CAP_SYS_ADMIN in that user_ns. The guts of sget are split out into another function sget_userns(). The function sget_userns calls alloc_super with the specified user namespace or it verifies the existing superblock that was found has the expected user namespace, and fails with EBUSY when it is not. This failing prevents users with the wrong privileges mounting a filesystem. The reason for the split of sget_userns from sget is that in some cases such as mount_ns and kernfs_mount_ns a different policy for permission checking of mounts and setting s_user_ns is necessary, and the existence of sget_userns() allows those policies to be implemented. The helper mount_ns is expected to be used for filesystems such as proc and mqueuefs which present per namespace information. The function mount_ns is modified to call sget_userns instead of sget to ensure the user namespace owner of the namespace whose information is presented by the filesystem is used on the superblock. For sysfs and cgroup the appropriate permission checks are already in place, and kernfs_mount_ns is modified to call sget_userns so that the init_user_ns is the only user namespace used. For the cgroup filesystem cgroup namespace mounts are bind mounts of a subset of the full cgroup filesystem and as such s_user_ns must be the same for all of them as there is only a single superblock. Mounts of sysfs that vary based on the network namespace could in principle change s_user_ns but it keeps the analysis and implementation of kernfs simpler if that is not supported, and at present there appear to be no benefits from supporting a different s_user_ns on any sysfs mount. Getting the details of setting s_user_ns correct has been a long process. Thanks to Pavel Tikhorirorv who spotted a leak in sget_userns. Thanks to Seth Forshee who has kept the work alive. Thanks-to: Seth Forshee <seth.forshee@canonical.com> Thanks-to: Pavel Tikhomirov <ptikhomirov@virtuozzo.com> Acked-by: Seth Forshee <seth.forshee@canonical.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2016-05-24 17:29:01 +03:00
sb = sget_userns(fs_type, kernfs_test_super, kernfs_set_super, flags,
&init_user_ns, info);
if (IS_ERR(sb) || sb->s_fs_info != info)
kfree(info);
if (IS_ERR(sb))
return ERR_CAST(sb);
if (new_sb_created)
*new_sb_created = !sb->s_root;
if (!sb->s_root) {
struct kernfs_super_info *info = kernfs_info(sb);
error = kernfs_fill_super(sb, magic);
if (error) {
deactivate_locked_super(sb);
return ERR_PTR(error);
}
sb->s_flags |= MS_ACTIVE;
mutex_lock(&kernfs_mutex);
list_add(&info->node, &root->supers);
mutex_unlock(&kernfs_mutex);
}
return dget(sb->s_root);
}
/**
* kernfs_kill_sb - kill_sb for kernfs
* @sb: super_block being killed
*
* This can be used directly for file_system_type->kill_sb(). If a kernfs
* user needs extra cleanup, it can implement its own kill_sb() and call
* this function at the end.
*/
void kernfs_kill_sb(struct super_block *sb)
{
struct kernfs_super_info *info = kernfs_info(sb);
struct kernfs_node *root_kn = sb->s_root->d_fsdata;
mutex_lock(&kernfs_mutex);
list_del(&info->node);
mutex_unlock(&kernfs_mutex);
/*
* Remove the superblock from fs_supers/s_instances
* so we can't find it, before freeing kernfs_super_info.
*/
kill_anon_super(sb);
kfree(info);
kernfs_put(root_kn);
}
/**
* kernfs_pin_sb: try to pin the superblock associated with a kernfs_root
* @kernfs_root: the kernfs_root in question
* @ns: the namespace tag
*
* Pin the superblock so the superblock won't be destroyed in subsequent
* operations. This can be used to block ->kill_sb() which may be useful
* for kernfs users which dynamically manage superblocks.
*
* Returns NULL if there's no superblock associated to this kernfs_root, or
* -EINVAL if the superblock is being freed.
*/
struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns)
{
struct kernfs_super_info *info;
struct super_block *sb = NULL;
mutex_lock(&kernfs_mutex);
list_for_each_entry(info, &root->supers, node) {
if (info->ns == ns) {
sb = info->sb;
if (!atomic_inc_not_zero(&info->sb->s_active))
sb = ERR_PTR(-EINVAL);
break;
}
}
mutex_unlock(&kernfs_mutex);
return sb;
}
void __init kernfs_init(void)
{
kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
sizeof(struct kernfs_node),
0, SLAB_PANIC, NULL);
}