*/
#include <linux/cgroup.h>
+#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/smp_lock.h>
#include <linux/pid_namespace.h>
#include <linux/idr.h>
+#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
#include <asm/atomic.h>
*/
static int need_forkexit_callback __read_mostly;
+#ifdef CONFIG_PROVE_LOCKING
+int cgroup_lock_is_held(void)
+{
+ return lockdep_is_held(&cgroup_mutex);
+}
+#else /* #ifdef CONFIG_PROVE_LOCKING */
+int cgroup_lock_is_held(void)
+{
+ return mutex_is_locked(&cgroup_mutex);
+}
+#endif /* #else #ifdef CONFIG_PROVE_LOCKING */
+
+EXPORT_SYMBOL_GPL(cgroup_lock_is_held);
+
/* convenient tests for these bits */
inline int cgroup_is_removed(const struct cgroup *cgrp)
{
return &css_set_table[index];
}
+static void free_css_set_rcu(struct rcu_head *obj)
+{
+ struct css_set *cg = container_of(obj, struct css_set, rcu_head);
+ kfree(cg);
+}
+
/* 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
}
write_unlock(&css_set_lock);
- kfree(cg);
+ call_rcu(&cg->rcu_head, free_css_set_rcu);
}
/*
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp);
static const struct inode_operations cgroup_dir_inode_operations;
-static struct file_operations proc_cgroupstats_operations;
+static const struct file_operations proc_cgroupstats_operations;
static struct backing_dev_info cgroup_backing_dev_info = {
.name = "cgroup",
*/
deactivate_super(cgrp->root->sb);
+ /*
+ * if we're getting rid of the cgroup, refcount should ensure
+ * that there are no pidlists left.
+ */
+ BUG_ON(!list_empty(&cgrp->pidlists));
+
call_rcu(&cgrp->rcu_head, free_cgroup_rcu);
}
iput(inode);
INIT_LIST_HEAD(&cgrp->children);
INIT_LIST_HEAD(&cgrp->css_sets);
INIT_LIST_HEAD(&cgrp->release_list);
- init_rwsem(&cgrp->pids_mutex);
+ INIT_LIST_HEAD(&cgrp->pidlists);
+ mutex_init(&cgrp->pidlist_mutex);
}
static void init_cgroup_root(struct cgroupfs_root *root)
for_each_subsys(root, ss) {
if (ss->can_attach) {
- retval = ss->can_attach(ss, cgrp, tsk);
+ retval = ss->can_attach(ss, cgrp, tsk, false);
if (retval)
return retval;
}
for_each_subsys(root, ss) {
if (ss->attach)
- ss->attach(ss, cgrp, oldcgrp, tsk);
+ ss->attach(ss, cgrp, oldcgrp, tsk, false);
}
set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
synchronize_rcu();
return ret;
}
-/* The various types of files and directories in a cgroup file system */
-enum cgroup_filetype {
- FILE_ROOT,
- FILE_DIR,
- FILE_TASKLIST,
- FILE_NOTIFY_ON_RELEASE,
- FILE_RELEASE_AGENT,
-};
-
/**
* cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
* @cgrp: the cgroup to be checked for liveness
return -EFAULT;
buffer[nbytes] = 0; /* nul-terminate */
- strstrip(buffer);
if (cft->write_u64) {
- u64 val = simple_strtoull(buffer, &end, 0);
+ u64 val = simple_strtoull(strstrip(buffer), &end, 0);
if (*end)
return -EINVAL;
retval = cft->write_u64(cgrp, cft, val);
} else {
- s64 val = simple_strtoll(buffer, &end, 0);
+ s64 val = simple_strtoll(strstrip(buffer), &end, 0);
if (*end)
return -EINVAL;
retval = cft->write_s64(cgrp, cft, val);
}
buffer[nbytes] = 0; /* nul-terminate */
- strstrip(buffer);
- retval = cft->write_string(cgrp, cft, buffer);
+ retval = cft->write_string(cgrp, cft, strstrip(buffer));
if (!retval)
retval = nbytes;
out:
return single_release(inode, file);
}
-static struct file_operations cgroup_seqfile_operations = {
+static const struct file_operations cgroup_seqfile_operations = {
.read = seq_read,
.write = cgroup_file_write,
.llseek = seq_lseek,
return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
}
-static struct file_operations cgroup_file_operations = {
+static const struct file_operations cgroup_file_operations = {
.read = cgroup_file_read,
.write = cgroup_file_write,
.llseek = generic_file_llseek,
}
/*
- * Stuff for reading the 'tasks' file.
+ * Stuff for reading the 'tasks'/'procs' files.
*
* Reading this file can return large amounts of data if a cgroup has
* *lots* of attached tasks. So it may need several calls to read(),
*/
/*
- * Load into 'pidarray' up to 'npids' of the tasks using cgroup
- * 'cgrp'. Return actual number of pids loaded. No need to
- * task_lock(p) when reading out p->cgroup, since we're in an RCU
- * read section, so the css_set can't go away, and is
- * immutable after creation.
+ * The following two functions "fix" the issue where there are more pids
+ * than kmalloc will give memory for; in such cases, we use vmalloc/vfree.
+ * TODO: replace with a kernel-wide solution to this problem
+ */
+#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
+static void *pidlist_allocate(int count)
+{
+ if (PIDLIST_TOO_LARGE(count))
+ return vmalloc(count * sizeof(pid_t));
+ else
+ return kmalloc(count * sizeof(pid_t), GFP_KERNEL);
+}
+static void pidlist_free(void *p)
+{
+ if (is_vmalloc_addr(p))
+ vfree(p);
+ else
+ kfree(p);
+}
+static void *pidlist_resize(void *p, int newcount)
+{
+ void *newlist;
+ /* note: if new alloc fails, old p will still be valid either way */
+ if (is_vmalloc_addr(p)) {
+ newlist = vmalloc(newcount * sizeof(pid_t));
+ if (!newlist)
+ return NULL;
+ memcpy(newlist, p, newcount * sizeof(pid_t));
+ vfree(p);
+ } else {
+ newlist = krealloc(p, newcount * sizeof(pid_t), GFP_KERNEL);
+ }
+ return newlist;
+}
+
+/*
+ * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries
+ * If the new stripped list is sufficiently smaller and there's enough memory
+ * to allocate a new buffer, will let go of the unneeded memory. Returns the
+ * number of unique elements.
+ */
+/* is the size difference enough that we should re-allocate the array? */
+#define PIDLIST_REALLOC_DIFFERENCE(old, new) ((old) - PAGE_SIZE >= (new))
+static int pidlist_uniq(pid_t **p, int length)
+{
+ int src, dest = 1;
+ pid_t *list = *p;
+ pid_t *newlist;
+
+ /*
+ * we presume the 0th element is unique, so i starts at 1. trivial
+ * edge cases first; no work needs to be done for either
+ */
+ if (length == 0 || length == 1)
+ return length;
+ /* src and dest walk down the list; dest counts unique elements */
+ for (src = 1; src < length; src++) {
+ /* find next unique element */
+ while (list[src] == list[src-1]) {
+ src++;
+ if (src == length)
+ goto after;
+ }
+ /* dest always points to where the next unique element goes */
+ list[dest] = list[src];
+ dest++;
+ }
+after:
+ /*
+ * if the length difference is large enough, we want to allocate a
+ * smaller buffer to save memory. if this fails due to out of memory,
+ * we'll just stay with what we've got.
+ */
+ if (PIDLIST_REALLOC_DIFFERENCE(length, dest)) {
+ newlist = pidlist_resize(list, dest);
+ if (newlist)
+ *p = newlist;
+ }
+ return dest;
+}
+
+static int cmppid(const void *a, const void *b)
+{
+ return *(pid_t *)a - *(pid_t *)b;
+}
+
+/*
+ * find the appropriate pidlist for our purpose (given procs vs tasks)
+ * returns with the lock on that pidlist already held, and takes care
+ * of the use count, or returns NULL with no locks held if we're out of
+ * memory.
+ */
+static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
+ enum cgroup_filetype type)
+{
+ struct cgroup_pidlist *l;
+ /* don't need task_nsproxy() if we're looking at ourself */
+ struct pid_namespace *ns = get_pid_ns(current->nsproxy->pid_ns);
+ /*
+ * We can't drop the pidlist_mutex before taking the l->mutex in case
+ * the last ref-holder is trying to remove l from the list at the same
+ * time. Holding the pidlist_mutex precludes somebody taking whichever
+ * list we find out from under us - compare release_pid_array().
+ */
+ mutex_lock(&cgrp->pidlist_mutex);
+ list_for_each_entry(l, &cgrp->pidlists, links) {
+ if (l->key.type == type && l->key.ns == ns) {
+ /* found a matching list - drop the extra refcount */
+ put_pid_ns(ns);
+ /* make sure l doesn't vanish out from under us */
+ down_write(&l->mutex);
+ mutex_unlock(&cgrp->pidlist_mutex);
+ return l;
+ }
+ }
+ /* entry not found; create a new one */
+ l = kmalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
+ if (!l) {
+ mutex_unlock(&cgrp->pidlist_mutex);
+ put_pid_ns(ns);
+ return l;
+ }
+ init_rwsem(&l->mutex);
+ down_write(&l->mutex);
+ l->key.type = type;
+ l->key.ns = ns;
+ l->use_count = 0; /* don't increment here */
+ l->list = NULL;
+ l->owner = cgrp;
+ list_add(&l->links, &cgrp->pidlists);
+ mutex_unlock(&cgrp->pidlist_mutex);
+ return l;
+}
+
+/*
+ * Load a cgroup's pidarray with either procs' tgids or tasks' pids
*/
-static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp)
+static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
+ struct cgroup_pidlist **lp)
{
- int n = 0, pid;
+ pid_t *array;
+ int length;
+ int pid, n = 0; /* used for populating the array */
struct cgroup_iter it;
struct task_struct *tsk;
+ struct cgroup_pidlist *l;
+
+ /*
+ * If cgroup gets more users after we read count, we won't have
+ * enough space - tough. This race is indistinguishable to the
+ * caller from the case that the additional cgroup users didn't
+ * show up until sometime later on.
+ */
+ length = cgroup_task_count(cgrp);
+ array = pidlist_allocate(length);
+ if (!array)
+ return -ENOMEM;
+ /* now, populate the array */
cgroup_iter_start(cgrp, &it);
while ((tsk = cgroup_iter_next(cgrp, &it))) {
- if (unlikely(n == npids))
+ if (unlikely(n == length))
break;
- pid = task_pid_vnr(tsk);
- if (pid > 0)
- pidarray[n++] = pid;
+ /* get tgid or pid for procs or tasks file respectively */
+ if (type == CGROUP_FILE_PROCS)
+ pid = task_tgid_vnr(tsk);
+ else
+ pid = task_pid_vnr(tsk);
+ if (pid > 0) /* make sure to only use valid results */
+ array[n++] = pid;
}
cgroup_iter_end(cgrp, &it);
- return n;
+ length = n;
+ /* now sort & (if procs) strip out duplicates */
+ sort(array, length, sizeof(pid_t), cmppid, NULL);
+ if (type == CGROUP_FILE_PROCS)
+ length = pidlist_uniq(&array, length);
+ l = cgroup_pidlist_find(cgrp, type);
+ if (!l) {
+ pidlist_free(array);
+ return -ENOMEM;
+ }
+ /* store array, freeing old if necessary - lock already held */
+ pidlist_free(l->list);
+ l->list = array;
+ l->length = length;
+ l->use_count++;
+ up_write(&l->mutex);
+ *lp = l;
+ return 0;
}
/**
return ret;
}
-static int cmppid(const void *a, const void *b)
-{
- return *(pid_t *)a - *(pid_t *)b;
-}
-
/*
- * seq_file methods for the "tasks" file. The seq_file position is the
+ * seq_file methods for the tasks/procs files. The seq_file position is the
* next pid to display; the seq_file iterator is a pointer to the pid
- * in the cgroup->tasks_pids array.
+ * in the cgroup->l->list array.
*/
-static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
+static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
{
/*
* Initially we receive a position value that corresponds to
* after a seek to the start). Use a binary-search to find the
* next pid to display, if any
*/
- struct cgroup *cgrp = s->private;
+ struct cgroup_pidlist *l = s->private;
int index = 0, pid = *pos;
int *iter;
- down_read(&cgrp->pids_mutex);
+ down_read(&l->mutex);
if (pid) {
- int end = cgrp->pids_length;
+ int end = l->length;
while (index < end) {
int mid = (index + end) / 2;
- if (cgrp->tasks_pids[mid] == pid) {
+ if (l->list[mid] == pid) {
index = mid;
break;
- } else if (cgrp->tasks_pids[mid] <= pid)
+ } else if (l->list[mid] <= pid)
index = mid + 1;
else
end = mid;
}
}
/* If we're off the end of the array, we're done */
- if (index >= cgrp->pids_length)
+ if (index >= l->length)
return NULL;
/* Update the abstract position to be the actual pid that we found */
- iter = cgrp->tasks_pids + index;
+ iter = l->list + index;
*pos = *iter;
return iter;
}
-static void cgroup_tasks_stop(struct seq_file *s, void *v)
+static void cgroup_pidlist_stop(struct seq_file *s, void *v)
{
- struct cgroup *cgrp = s->private;
- up_read(&cgrp->pids_mutex);
+ struct cgroup_pidlist *l = s->private;
+ up_read(&l->mutex);
}
-static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
+static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
{
- struct cgroup *cgrp = s->private;
- int *p = v;
- int *end = cgrp->tasks_pids + cgrp->pids_length;
-
+ struct cgroup_pidlist *l = s->private;
+ pid_t *p = v;
+ pid_t *end = l->list + l->length;
/*
* Advance to the next pid in the array. If this goes off the
* end, we're done
}
}
-static int cgroup_tasks_show(struct seq_file *s, void *v)
+static int cgroup_pidlist_show(struct seq_file *s, void *v)
{
return seq_printf(s, "%d\n", *(int *)v);
}
-static const struct seq_operations cgroup_tasks_seq_operations = {
- .start = cgroup_tasks_start,
- .stop = cgroup_tasks_stop,
- .next = cgroup_tasks_next,
- .show = cgroup_tasks_show,
+/*
+ * seq_operations functions for iterating on pidlists through seq_file -
+ * independent of whether it's tasks or procs
+ */
+static const struct seq_operations cgroup_pidlist_seq_operations = {
+ .start = cgroup_pidlist_start,
+ .stop = cgroup_pidlist_stop,
+ .next = cgroup_pidlist_next,
+ .show = cgroup_pidlist_show,
};
-static void release_cgroup_pid_array(struct cgroup *cgrp)
+static void cgroup_release_pid_array(struct cgroup_pidlist *l)
{
- down_write(&cgrp->pids_mutex);
- BUG_ON(!cgrp->pids_use_count);
- if (!--cgrp->pids_use_count) {
- kfree(cgrp->tasks_pids);
- cgrp->tasks_pids = NULL;
- cgrp->pids_length = 0;
+ /*
+ * the case where we're the last user of this particular pidlist will
+ * have us remove it from the cgroup's list, which entails taking the
+ * mutex. since in pidlist_find the pidlist->lock depends on cgroup->
+ * pidlist_mutex, we have to take pidlist_mutex first.
+ */
+ mutex_lock(&l->owner->pidlist_mutex);
+ down_write(&l->mutex);
+ BUG_ON(!l->use_count);
+ if (!--l->use_count) {
+ /* we're the last user if refcount is 0; remove and free */
+ list_del(&l->links);
+ mutex_unlock(&l->owner->pidlist_mutex);
+ pidlist_free(l->list);
+ put_pid_ns(l->key.ns);
+ up_write(&l->mutex);
+ kfree(l);
+ return;
}
- up_write(&cgrp->pids_mutex);
+ mutex_unlock(&l->owner->pidlist_mutex);
+ up_write(&l->mutex);
}
-static int cgroup_tasks_release(struct inode *inode, struct file *file)
+static int cgroup_pidlist_release(struct inode *inode, struct file *file)
{
- struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
-
+ struct cgroup_pidlist *l;
if (!(file->f_mode & FMODE_READ))
return 0;
-
- release_cgroup_pid_array(cgrp);
+ /*
+ * the seq_file will only be initialized if the file was opened for
+ * reading; hence we check if it's not null only in that case.
+ */
+ l = ((struct seq_file *)file->private_data)->private;
+ cgroup_release_pid_array(l);
return seq_release(inode, file);
}
-static struct file_operations cgroup_tasks_operations = {
+static const struct file_operations cgroup_pidlist_operations = {
.read = seq_read,
.llseek = seq_lseek,
.write = cgroup_file_write,
- .release = cgroup_tasks_release,
+ .release = cgroup_pidlist_release,
};
/*
- * Handle an open on 'tasks' file. Prepare an array containing the
- * process id's of tasks currently attached to the cgroup being opened.
+ * The following functions handle opens on a file that displays a pidlist
+ * (tasks or procs). Prepare an array of the process/thread IDs of whoever's
+ * in the cgroup.
*/
-
-static int cgroup_tasks_open(struct inode *unused, struct file *file)
+/* helper function for the two below it */
+static int cgroup_pidlist_open(struct file *file, enum cgroup_filetype type)
{
struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
- pid_t *pidarray;
- int npids;
+ struct cgroup_pidlist *l;
int retval;
/* Nothing to do for write-only files */
if (!(file->f_mode & FMODE_READ))
return 0;
- /*
- * If cgroup gets more users after we read count, we won't have
- * enough space - tough. This race is indistinguishable to the
- * caller from the case that the additional cgroup users didn't
- * show up until sometime later on.
- */
- npids = cgroup_task_count(cgrp);
- pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
- if (!pidarray)
- return -ENOMEM;
- npids = pid_array_load(pidarray, npids, cgrp);
- sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);
-
- /*
- * Store the array in the cgroup, freeing the old
- * array if necessary
- */
- down_write(&cgrp->pids_mutex);
- kfree(cgrp->tasks_pids);
- cgrp->tasks_pids = pidarray;
- cgrp->pids_length = npids;
- cgrp->pids_use_count++;
- up_write(&cgrp->pids_mutex);
-
- file->f_op = &cgroup_tasks_operations;
+ /* have the array populated */
+ retval = pidlist_array_load(cgrp, type, &l);
+ if (retval)
+ return retval;
+ /* configure file information */
+ file->f_op = &cgroup_pidlist_operations;
- retval = seq_open(file, &cgroup_tasks_seq_operations);
+ retval = seq_open(file, &cgroup_pidlist_seq_operations);
if (retval) {
- release_cgroup_pid_array(cgrp);
+ cgroup_release_pid_array(l);
return retval;
}
- ((struct seq_file *)file->private_data)->private = cgrp;
+ ((struct seq_file *)file->private_data)->private = l;
return 0;
}
+static int cgroup_tasks_open(struct inode *unused, struct file *file)
+{
+ return cgroup_pidlist_open(file, CGROUP_FILE_TASKS);
+}
+static int cgroup_procs_open(struct inode *unused, struct file *file)
+{
+ return cgroup_pidlist_open(file, CGROUP_FILE_PROCS);
+}
static u64 cgroup_read_notify_on_release(struct cgroup *cgrp,
struct cftype *cft)
/*
* for the common functions, 'private' gives the type of file
*/
+/* for hysterical raisins, we can't put this on the older files */
+#define CGROUP_FILE_GENERIC_PREFIX "cgroup."
static struct cftype files[] = {
{
.name = "tasks",
.open = cgroup_tasks_open,
.write_u64 = cgroup_tasks_write,
- .release = cgroup_tasks_release,
- .private = FILE_TASKLIST,
+ .release = cgroup_pidlist_release,
.mode = S_IRUGO | S_IWUSR,
},
-
+ {
+ .name = CGROUP_FILE_GENERIC_PREFIX "procs",
+ .open = cgroup_procs_open,
+ /* .write_u64 = cgroup_procs_write, TODO */
+ .release = cgroup_pidlist_release,
+ .mode = S_IRUGO,
+ },
{
.name = "notify_on_release",
.read_u64 = cgroup_read_notify_on_release,
.write_u64 = cgroup_write_notify_on_release,
- .private = FILE_NOTIFY_ON_RELEASE,
},
};
.read_seq_string = cgroup_release_agent_show,
.write_string = cgroup_release_agent_write,
.max_write_len = PATH_MAX,
- .private = FILE_RELEASE_AGENT,
};
static int cgroup_populate_dir(struct cgroup *cgrp)
for_each_subsys(root, ss) {
struct cgroup_subsys_state *css = ss->create(ss, cgrp);
+
if (IS_ERR(css)) {
err = PTR_ERR(css);
goto err_destroy;
}
init_cgroup_css(css, ss, cgrp);
- if (ss->use_id)
- if (alloc_css_id(ss, parent, cgrp))
+ if (ss->use_id) {
+ err = alloc_css_id(ss, parent, cgrp);
+ if (err)
goto err_destroy;
+ }
/* At error, ->destroy() callback has to free assigned ID. */
}
return single_open(file, proc_cgroup_show, pid);
}
-struct file_operations proc_cgroup_operations = {
+const struct file_operations proc_cgroup_operations = {
.open = cgroup_open,
.read = seq_read,
.llseek = seq_lseek,
return single_open(file, proc_cgroupstats_show, NULL);
}
-static struct file_operations proc_cgroupstats_operations = {
+static const struct file_operations proc_cgroupstats_operations = {
.open = cgroupstats_open,
.read = seq_read,
.llseek = seq_lseek,
void __css_put(struct cgroup_subsys_state *css)
{
struct cgroup *cgrp = css->cgroup;
+ int val;
rcu_read_lock();
- if (atomic_dec_return(&css->refcnt) == 1) {
+ val = atomic_dec_return(&css->refcnt);
+ if (val == 1) {
if (notify_on_release(cgrp)) {
set_bit(CGRP_RELEASABLE, &cgrp->flags);
check_for_release(cgrp);
cgroup_wakeup_rmdir_waiter(cgrp);
}
rcu_read_unlock();
+ WARN_ON_ONCE(val < 1);
}
/*
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff