 |
index : litmus-rt.git | |
| The LITMUS^RT kernel. | Bjoern Brandenburg |
| aboutsummaryrefslogtreecommitdiffstats |
| author | Bjoern Brandenburg <bbb@mpi-sws.org> | 2014-04-30 12:35:11 -0400 |
|---|---|---|
| committer | Bjoern Brandenburg <bbb@mpi-sws.org> | 2015-09-07 16:47:32 -0400 |
| commit | 0ce2d95d10bc7ecab7fcf1e4bb5d9942625f91e7 (patch) | |
| tree | 39a9e408fd4fe55129b791ef591fff5cef1ce0f2 /net/x25/x25_link.c | |
| parent | 2971daf071d2c0a35986f16bfed7e661e7e88f92 (diff) | |
54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91
630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685
885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931
1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639
1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968
2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113
2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187
2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613
2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659
2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810
2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883
2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934
3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050
3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123
/*
* Generic process-grouping system.
*
* Based originally on the cpuset system, extracted by Paul Menage
* Copyright (C) 2006 Google, Inc
*
* Copyright notices from the original cpuset code:
* --------------------------------------------------
* Copyright (C) 2003 BULL SA.
* Copyright (C) 2004-2006 Silicon Graphics, Inc.
*
* Portions derived from Patrick Mochel's sysfs code.
* sysfs is Copyright (c) 2001-3 Patrick Mochel
*
* 2003-10-10 Written by Simon Derr.
* 2003-10-22 Updates by Stephen Hemminger.
* 2004 May-July Rework by Paul Jackson.
* ---------------------------------------------------
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file COPYING in the main directory of the Linux
* distribution for more details.
*/
#include <linux/cgroup.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/backing-dev.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/magic.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/sort.h>
#include <linux/kmod.h>
#include <linux/delayacct.h>
#include <linux/cgroupstats.h>
#include <linux/hash.h>
#include <linux/namei.h>
#include <asm/atomic.h>
static DEFINE_MUTEX(cgroup_mutex);
/* Generate an array of cgroup subsystem pointers */
#define SUBSYS(_x) &_x ## _subsys,
static struct cgroup_subsys *subsys[] = {
#include <linux/cgroup_subsys.h>
};
/*
* A cgroupfs_root represents the root of a cgroup hierarchy,
* and may be associated with a superblock to form an active
* hierarchy
*/
struct cgroupfs_root {
struct super_block *sb;
/*
* The bitmask of subsystems intended to be attached to this
* hierarchy
*/
unsigned long subsys_bits;
/* The bitmask of subsystems currently attached to this hierarchy */
unsigned long actual_subsys_bits;
/* A list running through the attached subsystems */
struct list_head subsys_list;
/* The root cgroup for this hierarchy */
struct cgroup top_cgroup;
/* Tracks how many cgroups are currently defined in hierarchy.*/
int number_of_cgroups;
/* A list running through the mounted hierarchies */
struct list_head root_list;
/* Hierarchy-specific flags */
unsigned long flags;
/* The path to use for release notifications. */
char release_agent_path[PATH_MAX];
};
/*
* The "rootnode" hierarchy is the "dummy hierarchy", reserved for the
* subsystems that are otherwise unattached - it never has more than a
* single cgroup, and all tasks are part of that cgroup.
*/
static struct cgroupfs_root rootnode;
/* The list of hierarchy roots */
static LIST_HEAD(roots);
static int root_count;
/* dummytop is a shorthand for the dummy hierarchy's top cgroup */
#define dummytop (&rootnode.top_cgroup)
/* This flag indicates whether tasks in the fork and exit paths should
* check for fork/exit handlers to call. This avoids us having to do
* extra work in the fork/exit path if none of the subsystems need to
* be called.
*/
static int need_forkexit_callback __read_mostly;
static int need_mm_owner_callback __read_mostly;
/* convenient tests for these bits */
inline int cgroup_is_removed(const struct cgroup *cgrp)
{
return test_bit(CGRP_REMOVED, &cgrp->flags);
}
/* bits in struct cgroupfs_root flags field */
enum {
ROOT_NOPREFIX, /* mounted subsystems have no named prefix */
};
static int cgroup_is_releasable(const struct cgroup *cgrp)
{
const int bits =
(1 << CGRP_RELEASABLE) |
(1 << CGRP_NOTIFY_ON_RELEASE);
return (cgrp->flags & bits) == bits;
}
static int notify_on_release(const struct cgroup *cgrp)
{
return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
}
/*
* for_each_subsys() allows you to iterate on each subsystem attached to
* an active hierarchy
*/
#define for_each_subsys(_root, _ss) \
list_for_each_entry(_ss, &_root->subsys_list, sibling)
/* for_each_root() allows you to iterate across the active hierarchies */
#define for_each_root(_root) \
list_for_each_entry(_root, &roots, root_list)
/* the list of cgroups eligible for automatic release. Protected by
* release_list_lock */
static LIST_HEAD(release_list);
static DEFINE_SPINLOCK(release_list_lock);
static void cgroup_release_agent(struct work_struct *work);
static DECLARE_WORK(release_agent_work, cgroup_release_agent);
static void check_for_release(struct cgroup *cgrp);
/* Link structure for associating css_set objects with cgroups */
struct cg_cgroup_link {
/*
* List running through cg_cgroup_links associated with a
* cgroup, anchored on cgroup->css_sets
*/
struct list_head cgrp_link_list;
/*
* List running through cg_cgroup_links pointing at a
* single css_set object, anchored on css_set->cg_links
*/
struct list_head cg_link_list;
struct css_set *cg;
};
/* The default css_set - used by init and its children prior to any
* hierarchies being mounted. It contains a pointer to the root state
* for each subsystem. Also used to anchor the list of css_sets. Not
* reference-counted, to improve performance when child cgroups
* haven't been created.
*/
static struct css_set init_css_set;
static struct cg_cgroup_link init_css_set_link;
/* css_set_lock protects the list of css_set objects, and the
* chain of tasks off each css_set. Nests outside task->alloc_lock
* due to cgroup_iter_start() */
static DEFINE_RWLOCK(css_set_lock);
static int css_set_count;
/* hash table for cgroup groups. This improves the performance to
* find an existing css_set */
#define CSS_SET_HASH_BITS 7
#define CSS_SET_TABLE_SIZE (1 << CSS_SET_HASH_BITS)
static struct hlist_head css_set_table[CSS_SET_TABLE_SIZE];
static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
{
int i;
int index;
unsigned long tmp = 0UL;
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++)
tmp += (unsigned long)css[i];
tmp = (tmp >> 16) ^ tmp;
index = hash_long(tmp, CSS_SET_HASH_BITS);
return &css_set_table[index];
}
/* We don't maintain the lists running through each css_set to its
* task until after the first call to cgroup_iter_start(). This
* reduces the fork()/exit() overhead for people who have cgroups
* compiled into their kernel but not actually in use */
static int use_task_css_set_links __read_mostly;
/* When we create or destroy a css_set, the operation simply
* takes/releases a reference count on all the cgroups referenced
* by subsystems in this css_set. This can end up multiple-counting
* some cgroups, but that's OK - the ref-count is just a
* busy/not-busy indicator; ensuring that we only count each cgroup
* once would require taking a global lock to ensure that no
* subsystems moved between hierarchies while we were doing so.
*
* Possible TODO: decide at boot time based on the number of
* registered subsystems and the number of CPUs or NUMA nodes whether
* it's better for performance to ref-count every subsystem, or to
* take a global lock and only add one ref count to each hierarchy.
*/
/*
* unlink a css_set from the list and free it
*/
static void unlink_css_set(struct css_set *cg)
{
struct cg_cgroup_link *link;
struct cg_cgroup_link *saved_link;
write_lock(&css_set_lock);
hlist_del(&cg->hlist);
css_set_count--;
list_for_each_entry_safe(link, saved_link, &cg->cg_links,
cg_link_list) {
list_del(&link->cg_link_list);
list_del(&link->cgrp_link_list);
kfree(link);
}
write_unlock(&css_set_lock);
}
static void __release_css_set(struct kref *k, int taskexit)
{
int i;
struct css_set *cg = container_of(k, struct css_set, ref);
unlink_css_set(cg);
rcu_read_lock();
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
struct cgroup *cgrp = cg->subsys[i]->cgroup;
if (atomic_dec_and_test(&cgrp->count) &&
notify_on_release(cgrp)) {
if (taskexit)
set_bit(CGRP_RELEASABLE, &cgrp->flags);
check_for_release(cgrp);
}
}
rcu_read_unlock();
kfree(cg);
}
static void release_css_set(struct kref *k)
{
__release_css_set(k, 0);
}
static void release_css_set_taskexit(struct kref *k)
{
__release_css_set(k, 1);
}
/*
* refcounted get/put for css_set objects
*/
static inline void get_css_set(struct css_set *cg)
{
kref_get(&cg->ref);
}
static inline void put_css_set(struct css_set *cg)
{
kref_put(&cg->ref, release_css_set);
}
static inline void put_css_set_taskexit(struct css_set *cg)
{
kref_put(&cg->ref, release_css_set_taskexit);
}
/*
* find_existing_css_set() is a helper for
* find_css_set(), and checks to see whether an existing
* css_set is suitable.
*
* oldcg: the cgroup group that we're using before the cgroup
* transition
*
* cgrp: the cgroup that we're moving into
*
* template: location in which to build the desired set of subsystem
* state objects for the new cgroup group
*/
static struct css_set *find_existing_css_set(
struct css_set *oldcg,
struct cgroup *cgrp,
struct cgroup_subsys_state *template[])
{
int i;
struct cgroupfs_root *root = cgrp->root;
struct hlist_head *hhead;
struct hlist_node *node;
struct css_set *cg;
/* Built the set of subsystem state objects that we want to
* see in the new css_set */
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
if (root->subsys_bits & (1UL << i)) {
/* Subsystem is in this hierarchy. So we want
* the subsystem state from the new
* cgroup */
template[i] = cgrp->subsys[i];
} else {
/* Subsystem is not in this hierarchy, so we
* don't want to change the subsystem state */
template[i] = oldcg->subsys[i];
}
}
hhead = css_set_hash(template);
hlist_for_each_entry(cg, node, hhead, hlist) {
if (!memcmp(template, cg->subsys, sizeof(cg->subsys))) {
/* All subsystems matched */
return cg;
}
}
/* No existing cgroup group matched */
return NULL;
}
static void free_cg_links(struct list_head *tmp)
{
struct cg_cgroup_link *link;
struct cg_cgroup_link *saved_link;
list_for_each_entry_safe(link, saved_link, tmp, cgrp_link_list) {
list_del(&link->cgrp_link_list);
kfree(link);
}
}
/*
* allocate_cg_links() allocates "count" cg_cgroup_link structures
* and chains them on tmp through their cgrp_link_list fields. Returns 0 on
* success or a negative error
*/
static int allocate_cg_links(int count, struct list_head *tmp)
{
struct cg_cgroup_link *link;
int i;
INIT_LIST_HEAD(tmp);
for (i = 0; i < count; i++) {
link = kmalloc(sizeof(*link), GFP_KERNEL);
if (!link) {
free_cg_links(tmp);
return -ENOMEM;
}
list_add(&link->cgrp_link_list, tmp);
}
return 0;
}
/*
* find_css_set() takes an existing cgroup group and a
* cgroup object, and returns a css_set object that's
* equivalent to the old group, but with the given cgroup
* substituted into the appropriate hierarchy. Must be called with
* cgroup_mutex held
*/
static struct css_set *find_css_set(
struct css_set *oldcg, struct cgroup *cgrp)
{
struct css_set *res;
struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];
int i;
struct list_head tmp_cg_links;
struct cg_cgroup_link *link;
struct hlist_head *hhead;
/* First see if we already have a cgroup group that matches
* the desired set */
read_lock(&css_set_lock);
res = find_existing_css_set(oldcg, cgrp, template);
if (res)
get_css_set(res);
read_unlock(&css_set_lock);
if (res)
return res;
res = kmalloc(sizeof(*res), GFP_KERNEL);
if (!res)
return NULL;
/* Allocate all the cg_cgroup_link objects that we'll need */
if (allocate_cg_links(root_count, &tmp_cg_links) < 0) {
kfree(res);
return NULL;
}
kref_init(&res->ref);
INIT_LIST_HEAD(&res->cg_links);
INIT_LIST_HEAD(&res->tasks);
INIT_HLIST_NODE(&res->hlist);
/* Copy the set of subsystem state objects generated in
* find_existing_css_set() */
memcpy(res->subsys, template, sizeof(res->subsys));
write_lock(&css_set_lock);
/* Add reference counts and links from the new css_set. */
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
struct cgroup *cgrp = res->subsys[i]->cgroup;
struct cgroup_subsys *ss = subsys[i];
atomic_inc(&cgrp->count);
/*
* We want to add a link once per cgroup, so we
* only do it for the first subsystem in each
* hierarchy
*/
if (ss->root->subsys_list.next == &ss->sibling) {
BUG_ON(list_empty(&tmp_cg_links));
link = list_entry(tmp_cg_links.next,
struct cg_cgroup_link,
cgrp_link_list);
list_del(&link->cgrp_link_list);
list_add(&link->cgrp_link_list, &cgrp->css_sets);
link->cg = res;
list_add(&link->cg_link_list, &res->cg_links);
}
}
if (list_empty(&rootnode.subsys_list)) {
link = list_entry(tmp_cg_links.next,
struct cg_cgroup_link,
cgrp_link_list);
list_del(&link->cgrp_link_list);
list_add(&link->cgrp_link_list, &dummytop->css_sets);
link->cg = res;
list_add(&link->cg_link_list, &res->cg_links);
}
BUG_ON(!list_empty(&tmp_cg_links));
css_set_count++;
/* Add this cgroup group to the hash table */
hhead = css_set_hash(res->subsys);
hlist_add_head(&res->hlist, hhead);
write_unlock(&css_set_lock);
return res;
}
/*
* There is one global cgroup mutex. We also require taking
* task_lock() when dereferencing a task's cgroup subsys pointers.
* See "The task_lock() exception", at the end of this comment.
*
* A task must hold cgroup_mutex to modify cgroups.
*
* Any task can increment and decrement the count field without lock.
* So in general, code holding cgroup_mutex can't rely on the count
* field not changing. However, if the count goes to zero, then only
* cgroup_attach_task() can increment it again. Because a count of zero
* means that no tasks are currently attached, therefore there is no
* way a task attached to that cgroup can fork (the other way to
* increment the count). So code holding cgroup_mutex can safely
* assume that if the count is zero, it will stay zero. Similarly, if
* a task holds cgroup_mutex on a cgroup with zero count, it
* knows that the cgroup won't be removed, as cgroup_rmdir()
* needs that mutex.
*
* The fork and exit callbacks cgroup_fork() and cgroup_exit(), don't
* (usually) take cgroup_mutex. These are the two most performance
* critical pieces of code here. The exception occurs on cgroup_exit(),
* when a task in a notify_on_release cgroup exits. Then cgroup_mutex
* is taken, and if the cgroup count is zero, a usermode call made
* to the release agent with the name of the cgroup (path relative to
* the root of cgroup file system) as the argument.
*
* A cgroup can only be deleted if both its 'count' of using tasks
* is zero, and its list of 'children' cgroups is empty. Since all
* tasks in the system use _some_ cgroup, and since there is always at
* least one task in the system (init, pid == 1), therefore, top_cgroup
* always has either children cgroups and/or using tasks. So we don't
* need a special hack to ensure that top_cgroup cannot be deleted.
*
* The task_lock() exception
*
* The need for this exception arises from the action of
* cgroup_attach_task(), which overwrites one tasks cgroup pointer with
* another. It does so using cgroup_mutex, however there are
* several performance critical places that need to reference
* task->cgroup without the expense of grabbing a system global
* mutex. Therefore except as noted below, when dereferencing or, as
* in cgroup_attach_task(), modifying a task'ss cgroup pointer we use
* task_lock(), which acts on a spinlock (task->alloc_lock) already in
* the task_struct routinely used for such matters.
*
* P.S. One more locking exception. RCU is used to guard the
* update of a tasks cgroup pointer by cgroup_attach_task()
*/
/**
* cgroup_lock - lock out any changes to cgroup structures
*
*/
void cgroup_lock(void)
{
mutex_lock(&cgroup_mutex);
}
/**
* cgroup_unlock - release lock on cgroup changes
*
* Undo the lock taken in a previous cgroup_lock() call.
*/
void cgroup_unlock(void)
{
mutex_unlock(&cgroup_mutex);
}
/*
* A couple of forward declarations required, due to cyclic reference loop:
* cgroup_mkdir -> cgroup_create -> cgroup_populate_dir ->
* cgroup_add_file -> cgroup_create_file -> cgroup_dir_inode_operations
* -> cgroup_mkdir.
*/
static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode);
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp);
static struct inode_operations cgroup_dir_inode_operations;
static struct file_operations proc_cgroupstats_operations;
static struct backing_dev_info cgroup_backing_dev_info = {
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
{
struct inode *inode = new_inode(sb);
if (inode) {
inode->i_mode = mode;
inode->i_uid = current->fsuid;
inode->i_gid = current->fsgid;
inode->i_blocks = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
}
return inode;
}
/*
* Call subsys's pre_destroy handler.
* This is called before css refcnt check.
*/
static void cgroup_call_pre_destroy(struct cgroup *cgrp)
{
struct cgroup_subsys *ss;
for_each_subsys(cgrp->root, ss)
if (ss->pre_destroy && cgrp->subsys[ss->subsys_id])
ss->pre_destroy(ss, cgrp);
return;
}
static void cgroup_diput(struct dentry *dentry, struct inode *inode)
{
/* is dentry a directory ? if so, kfree() associated cgroup */
if (S_ISDIR(inode->i_mode)) {
struct cgroup *cgrp = dentry->d_fsdata;
struct cgroup_subsys *ss;
BUG_ON(!(cgroup_is_removed(cgrp)));
/* It's possible for external users to be holding css
* reference counts on a cgroup; css_put() needs to
* be able to access the cgroup after decrementing
* the reference count in order to know if it needs to
* queue the cgroup to be handled by the release
* agent */
synchronize_rcu();
mutex_lock(&cgroup_mutex);
/*
* Release the subsystem state objects.
*/
for_each_subsys(cgrp->root, ss) {
if (cgrp->subsys[ss->subsys_id])
ss->destroy(ss, cgrp);
}
cgrp->root->number_of_cgroups--;
mutex_unlock(&cgroup_mutex);
/* Drop the active superblock reference that we took when we
* created the cgroup */
deactivate_super(cgrp->root->sb);
kfree(cgrp);
}
iput(inode);
}
static void remove_dir(struct dentry *d)
{
struct dentry *parent = dget(d->d_parent);
d_delete(d);
simple_rmdir(parent->d_inode, d);
dput(parent);
}
static void cgroup_clear_directory(struct dentry *dentry)
{
struct list_head *node;
BUG_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
spin_lock(&dcache_lock);
node = dentry->d_subdirs.next;
while (node != &dentry->d_subdirs) {
struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
list_del_init(node);
if (d->d_inode) {
/* This should never be called on a cgroup
* directory with child cgroups */
BUG_ON(d->d_inode->i_mode & S_IFDIR);
d = dget_locked(d);
spin_unlock(&dcache_lock);
d_delete(d);
simple_unlink(dentry->d_inode, d);
dput(d);
spin_lock(&dcache_lock);
}
node = dentry->d_subdirs.next;
}
spin_unlock(&dcache_lock);
}
/*
* NOTE : the dentry must have been dget()'ed
*/
static void cgroup_d_remove_dir(struct dentry *dentry)
{
cgroup_clear_directory(dentry);
spin_lock(&dcache_lock);
list_del_init(&dentry->d_u.d_child);
spin_unlock(&dcache_lock);
remove_dir(dentry);
}
static int rebind_subsystems(struct cgroupfs_root *root,
unsigned long final_bits)
{
unsigned long added_bits, removed_bits;
struct cgroup *cgrp = &root->top_cgroup;
int i;
removed_bits = root->actual_subsys_bits & ~final_bits;
added_bits = final_bits & ~root->actual_subsys_bits;
/* Check that any added subsystems are currently free */
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
unsigned long bit = 1UL << i;
struct cgroup_subsys *ss = subsys[i];
if (!(bit & added_bits))
continue;
if (ss->root != &rootnode) {
/* Subsystem isn't free */
return -EBUSY;
}
}
/* Currently we don't handle adding/removing subsystems when
* any child cgroups exist. This is theoretically supportable
* but involves complex error handling, so it's being left until
* later */
if (!list_empty(&cgrp->children))
return -EBUSY;
/* Process each subsystem */
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
struct cgroup_subsys *ss = subsys[i];
unsigned long bit = 1UL << i;
if (bit & added_bits) {
/* We're binding this subsystem to this hierarchy */
BUG_ON(cgrp->subsys[i]);
BUG_ON(!dummytop->subsys[i]);
BUG_ON(dummytop->subsys[i]->cgroup != dummytop);
cgrp->subsys[i] = dummytop->subsys[i];
cgrp->subsys[i]->cgroup = cgrp;
list_add(&ss->sibling, &root->subsys_list);
rcu_assign_pointer(ss->root, root);
if (ss->bind)
ss->bind(ss, cgrp);
} else if (bit & removed_bits) {
/* We're removing this subsystem */
BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]);
BUG_ON(cgrp->subsys[i]->cgroup != cgrp);
if (ss->bind)
ss->bind(ss, dummytop);
dummytop->subsys[i]->cgroup = dummytop;
cgrp->subsys[i] = NULL;
rcu_assign_pointer(subsys[i]->root, &rootnode);
list_del(&ss->sibling);
} else if (bit & final_bits) {
/* Subsystem state should already exist */
BUG_ON(!cgrp->subsys[i]);
} else {
/* Subsystem state shouldn't exist */
BUG_ON(cgrp->subsys[i]);
}
}
root->subsys_bits = root->actual_subsys_bits = final_bits;
synchronize_rcu();
return 0;
}
static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
struct cgroupfs_root *root = vfs->mnt_sb->s_fs_info;
struct cgroup_subsys *ss;
mutex_lock(&cgroup_mutex);
for_each_subsys(root, ss)
seq_printf(seq, ",%s", ss->name);
if (test_bit(ROOT_NOPREFIX, &root->flags))
seq_puts(seq, ",noprefix");
if (strlen(root->release_agent_path))
seq_printf(seq, ",release_agent=%s", root->release_agent_path);
mutex_unlock(&cgroup_mutex);
return 0;
}
struct cgroup_sb_opts {
unsigned long subsys_bits;
unsigned long flags;
char *release_agent;
};
/* Convert a hierarchy specifier into a bitmask of subsystems and
* flags. */
static int parse_cgroupfs_options(char *data,
struct cgroup_sb_opts *opts)
{
char *token, *o = data ?: "all";
opts->subsys_bits = 0;
opts->flags = 0;
opts->release_agent = NULL;
while ((token = strsep(&o, ",")) != NULL) {
if (!*token)
return -EINVAL;
if (!strcmp(token, "all")) {
/* Add all non-disabled subsystems */
int i;
opts->subsys_bits = 0;
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
struct cgroup_subsys *ss = subsys[i];
if (!ss->disabled)
opts->subsys_bits |= 1ul << i;
}
} else if (!strcmp(token, "noprefix")) {
set_bit(ROOT_NOPREFIX, &opts->flags);
} else if (!strncmp(token, "release_agent=", 14)) {
/* Specifying two release agents is forbidden */
if (opts->release_agent)
return -EINVAL;
opts->release_agent = kzalloc(PATH_MAX, GFP_KERNEL);
if (!opts->release_agent)
return -ENOMEM;
strncpy(opts->release_agent, token + 14, PATH_MAX - 1);
opts->release_agent[PATH_MAX - 1] = 0;
} else {
struct cgroup_subsys *ss;
int i;
for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
ss = subsys[i];
if (!strcmp(token, ss->name)) {
if (!ss->disabled)
set_bit(i, &opts->subsys_bits);
break;
}
}
if (i == CGROUP_SUBSYS_COUNT)
return -ENOENT;
}
}
/* We can't have an empty hierarchy */
if (!opts->subsys_bits)
return -EINVAL;
return 0;
}
static int cgroup_remount(struct super_block *sb, int *flags, char *data)
{
int ret = 0;
struct cgroupfs_root *root = sb->s_fs_info;
struct cgroup *cgrp = &root->top_cgroup;
struct cgroup_sb_opts opts;
mutex_lock(&cgrp->dentry->d_inode->i_mutex);
mutex_lock(&cgroup_mutex);
/* See what subsystems are wanted */
ret = parse_cgroupfs_options(data, &opts);
if (ret)
goto out_unlock;
/* Don't allow flags to change at remount */
if (opts.flags != root->flags) {
ret = -EINVAL;
goto out_unlock;
}
ret = rebind_subsystems(root, opts.subsys_bits);
/* (re)populate subsystem files */
if (!ret)
cgroup_populate_dir(cgrp);
if (opts.release_agent)
strcpy(root->release_agent_path, opts.release_agent);
out_unlock:
if (opts.release_agent)
kfree(opts.release_agent);
mutex_unlock(&cgroup_mutex);
mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
return ret;
}
static struct super_operations cgroup_ops = {
.statfs = simple_statfs,
.drop_inode = generic_delete_inode,
.show_options = cgroup_show_options,
.remount_fs = cgroup_remount,
};
static void init_cgroup_root(struct cgroupfs_root *root)
{
struct cgroup *cgrp = &root->top_cgroup;
INIT_LIST_HEAD(&root->subsys_list);
INIT_LIST_HEAD(&root->root_list);
root->number_of_cgroups = 1;
cgrp->root = root;
cgrp->top_cgroup = cgrp;
INIT_LIST_HEAD(&cgrp->sibling);
INIT_LIST_HEAD(&cgrp->children);
INIT_LIST_HEAD(&cgrp->css_sets);
INIT_LIST_HEAD(&cgrp->release_list);
}
static int cgroup_test_super(struct super_block *sb, void *data)
{
struct cgroupfs_root *new = data;
struct cgroupfs_root *root = sb->s_fs_info;
/* First check subsystems */
if (new->subsys_bits != root->subsys_bits)
return 0;
/* Next check flags */
if (new->flags != root->flags)
return 0;
return 1;
}
static int cgroup_set_super(struct super_block *sb, void *data)
{
int ret;
struct cgroupfs_root *root = data;
ret = set_anon_super(sb, NULL);
if (ret)
return ret;
sb->s_fs_info = root;
root->sb = sb;
sb->s_blocksize = PAGE_CACHE_SIZE;
sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
sb->s_magic = CGROUP_SUPER_MAGIC;
sb->s_op = &cgroup_ops;
return 0;
}
static int cgroup_get_rootdir(struct super_block *sb)
{
struct inode *inode =
cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb);
struct dentry *dentry;
if (!inode)
return -ENOMEM;
inode->i_fop = &simple_dir_operations;
inode->i_op = &cgroup_dir_inode_operations;
/* directories start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
dentry = d_alloc_root(inode);
if (!dentry) {
iput(inode);
return -ENOMEM;
}
sb->s_root = dentry;
return 0;
}
static int cgroup_get_sb(struct file_system_type *fs_type,
int flags, const char *unused_dev_name,
void *data, struct vfsmount *mnt)
{
struct cgroup_sb_opts opts;
int ret = 0;
struct super_block *sb;
struct cgroupfs_root *root;
struct list_head tmp_cg_links;
/* First find the desired set of subsystems */
ret = parse_cgroupfs_options(data, &opts);
if (ret) {
if (opts.release_agent)
kfree(opts.release_agent);
return ret;
}
root = kzalloc(sizeof(*root), GFP_KERNEL);
if (!root) {
if (opts.release_agent)
kfree(opts.release_agent);
return -ENOMEM;
}
init_cgroup_root(root);
root->subsys_bits = opts.subsys_bits;
root->flags = opts.flags;
if (opts.release_agent) {
strcpy(root->release_agent_path, opts.release_agent);
kfree(opts.release_agent);
}
sb = sget(fs_type, cgroup_test_super, cgroup_set_super, root);
if (IS_ERR(sb)) {
kfree(root);
return PTR_ERR(sb);
}
if (sb->s_fs_info != root) {
/* Reusing an existing superblock */
BUG_ON(sb->s_root == NULL);
kfree(root);
root = NULL;
} else {
/* New superblock */
struct cgroup *cgrp = &root->top_cgroup;
struct inode *inode;
int i;
BUG_ON(sb->s_root != NULL);
ret = cgroup_get_rootdir(sb);
if (ret)
goto drop_new_super;
inode = sb->s_root->d_inode;
mutex_lock(&inode->i_mutex);
mutex_lock(&cgroup_mutex);
/*
* We're accessing css_set_count without locking
* css_set_lock here, but that's OK - it can only be
* increased by someone holding cgroup_lock, and
* that's us. The worst that can happen is that we
* have some link structures left over
*/
ret = allocate_cg_links(css_set_count, &tmp_cg_links);
if (ret) {
mutex_unlock(&cgroup_mutex);
mutex_unlock(&inode->i_mutex);
goto drop_new_super;
}
ret = rebind_subsystems(root, root->subsys_bits);
if (ret == -EBUSY) {
mutex_unlock(&cgroup_mutex);
mutex_unlock(&inode->i_mutex);
goto drop_new_super;
}
/* EBUSY should be the only error here */
BUG_ON(ret);
list_add(&root->root_list, &roots);
root_count++;
sb->s_root->d_fsdata = &root->top_cgroup;
root->top_cgroup.dentry = sb->s_root;
/* Link the top cgroup in this hierarchy into all
* the css_set objects */
write_lock(&css_set_lock);
for (i = 0; i < CSS_SET_TABLE_SIZE; i++) {
struct hlist_head *hhead = &css_set_table[i];
struct hlist_node *node;
struct css_set *cg;
hlist_for_each_entry(cg, node, hhead, hlist) {
struct cg_cgroup_link *link;
BUG_ON(list_empty(&tmp_cg_links));
link = list_entry(tmp_cg_links.next,
struct cg_cgroup_link,
cgrp_link_list);
list_del(&link->cgrp_link_list);
link->cg = cg;
list_add(&link->cgrp_link_list,
&root->top_cgroup.css_sets);
list_add(&link->cg_link_list, &cg->cg_links);
}
}
write_unlock(&css_set_lock);
free_cg_links(&tmp_cg_links);
BUG_ON(!list_empty(&cgrp->sibling));
BUG_ON(!list_empty(&cgrp->children));
BUG_ON(root->number_of_cgroups != 1);
cgroup_populate_dir(cgrp);
mutex_unlock(&inode->i_mutex);
mutex_unlock(&cgroup_mutex);
}
return simple_set_mnt(mnt, sb);
drop_new_super:
up_write(&sb->s_umount);
deactivate_super(sb);
free_cg_links(&tmp_cg_links);
return ret;
}
static void cgroup_kill_sb(struct super_block *sb) {
struct cgroupfs_root *root = sb->s_fs_info;
struct cgroup *cgrp = &root->top_cgroup;
int ret;
struct cg_cgroup_link *link;
struct cg_cgroup_link *saved_link;
BUG_ON(!root);
BUG_ON(root->number_of_cgroups != 1);
BUG_ON(!list_empty(&cgrp->children));
BUG_ON(!list_empty(&cgrp->sibling));
mutex_lock(&cgroup_mutex);
/* Rebind all subsystems back to the default hierarchy */
ret = rebind_subsystems(root, 0);
/* Shouldn't be able to fail ... */
BUG_ON(ret);
/*
* Release all the links from css_sets to this hierarchy's
* root cgroup
*/
write_lock(&css_set_lock);
list_for_each_entry_safe(link, saved_link, &cgrp->css_sets,
cgrp_link_list) {
list_del(&link->cg_link_list);
list_del(&link->cgrp_link_list);
kfree(link);
}
write_unlock(&css_set_lock);
if (!list_empty(&root->root_list)) {
list_del(&root->root_list);
root_count--;
}
mutex_unlock(&cgroup_mutex);
kfree(root);
kill_litter_super(sb);
}
static struct file_system_type cgroup_fs_type = {
.name = "cgroup",
.get_sb = cgroup_get_sb,
.kill_sb = cgroup_kill_sb,
};
static inline struct cgroup *__d_cgrp(struct dentry *dentry)
{
return dentry->d_fsdata;
}
static inline struct cftype *__d_cft(struct dentry *dentry)
{
return dentry->d_fsdata;
}
/**
* cgroup_path - generate the path of a cgroup
* @cgrp: the cgroup in question
* @buf: the buffer to write the path into
* @buflen: the length of the buffer
*
* Called with cgroup_mutex held. Writes path of cgroup into buf.
* Returns 0 on success, -errno on error.
*/
int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
{
char *start;
if (cgrp == dummytop) {
/*