summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorBen Blum <bblum@andrew.cmu.edu>2010-03-10 15:22:09 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2010-03-12 15:52:36 -0800
commite6a1105ba08b265023dd71a4174fb4a29ebc7083 (patch)
treec171a012df4364b0feac5d6f1bf8c354164ab0f9
parentaae8aab40367036931608fdaf9e2dc568b516f19 (diff)
downloadlinux-e6a1105ba08b265023dd71a4174fb4a29ebc7083.tar.bz2
cgroups: subsystem module loading interface
Add interface between cgroups subsystem management and module loading This patch implements rudimentary module-loading support for cgroups - namely, a cgroup_load_subsys (similar to cgroup_init_subsys) for use as a module initcall, and a struct module pointer in struct cgroup_subsys. Several functions that might be wanted by modules have had EXPORT_SYMBOL added to them, but it's unclear exactly which functions want it and which won't. Signed-off-by: Ben Blum <bblum@andrew.cmu.edu> Acked-by: Li Zefan <lizf@cn.fujitsu.com> Cc: Paul Menage <menage@google.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--Documentation/cgroups/cgroups.txt4
-rw-r--r--include/linux/cgroup.h4
-rw-r--r--kernel/cgroup.c150
3 files changed, 153 insertions, 5 deletions
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index d45082653e3d..ae8a037a761e 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -488,6 +488,10 @@ Each subsystem should:
- add an entry in linux/cgroup_subsys.h
- define a cgroup_subsys object called <name>_subsys
+If a subsystem can be compiled as a module, it should also have in its
+module initcall a call to cgroup_load_subsys(&its_subsys_struct). It
+should also set its_subsys.module = THIS_MODULE in its .c file.
+
Each subsystem may export the following methods. The only mandatory
methods are create/destroy. Any others that are null are presumed to
be successful no-ops.
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 28319a9fe569..402ce477c47e 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -37,6 +37,7 @@ extern void cgroup_post_fork(struct task_struct *p);
extern void cgroup_exit(struct task_struct *p, int run_callbacks);
extern int cgroupstats_build(struct cgroupstats *stats,
struct dentry *dentry);
+extern int cgroup_load_subsys(struct cgroup_subsys *ss);
extern const struct file_operations proc_cgroup_operations;
@@ -486,6 +487,9 @@ struct cgroup_subsys {
/* used when use_id == true */
struct idr idr;
spinlock_t id_lock;
+
+ /* should be defined only by modular subsystems */
+ struct module *module;
};
#define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c92fb9549358..2cae38e64c59 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -44,6 +44,7 @@
#include <linux/string.h>
#include <linux/sort.h>
#include <linux/kmod.h>
+#include <linux/module.h>
#include <linux/delayacct.h>
#include <linux/cgroupstats.h>
#include <linux/hash.h>
@@ -254,7 +255,8 @@ struct cg_cgroup_link {
static struct css_set init_css_set;
static struct cg_cgroup_link init_css_set_link;
-static int cgroup_subsys_init_idr(struct cgroup_subsys *ss);
+static int cgroup_init_idr(struct cgroup_subsys *ss,
+ struct cgroup_subsys_state *css);
/* css_set_lock protects the list of css_set objects, and the
* chain of tasks off each css_set. Nests outside task->alloc_lock
@@ -2125,6 +2127,7 @@ int cgroup_add_file(struct cgroup *cgrp,
error = PTR_ERR(dentry);
return error;
}
+EXPORT_SYMBOL_GPL(cgroup_add_file);
int cgroup_add_files(struct cgroup *cgrp,
struct cgroup_subsys *subsys,
@@ -2139,6 +2142,7 @@ int cgroup_add_files(struct cgroup *cgrp,
}
return 0;
}
+EXPORT_SYMBOL_GPL(cgroup_add_files);
/**
* cgroup_task_count - count the number of tasks in a cgroup.
@@ -3292,7 +3296,144 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
mutex_init(&ss->hierarchy_mutex);
lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
ss->active = 1;
+
+ /* this function shouldn't be used with modular subsystems, since they
+ * need to register a subsys_id, among other things */
+ BUG_ON(ss->module);
+}
+
+/**
+ * cgroup_load_subsys: load and register a modular subsystem at runtime
+ * @ss: the subsystem to load
+ *
+ * This function should be called in a modular subsystem's initcall. If the
+ * subsytem is built as a module, it will be assigned a new subsys_id and set
+ * up for use. If the subsystem is built-in anyway, work is delegated to the
+ * simpler cgroup_init_subsys.
+ */
+int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
+{
+ int i;
+ struct cgroup_subsys_state *css;
+
+ /* check name and function validity */
+ if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN ||
+ ss->create == NULL || ss->destroy == NULL)
+ return -EINVAL;
+
+ /*
+ * we don't support callbacks in modular subsystems. this check is
+ * before the ss->module check for consistency; a subsystem that could
+ * be a module should still have no callbacks even if the user isn't
+ * compiling it as one.
+ */
+ if (ss->fork || ss->exit)
+ return -EINVAL;
+
+ /*
+ * an optionally modular subsystem is built-in: we want to do nothing,
+ * since cgroup_init_subsys will have already taken care of it.
+ */
+ if (ss->module == NULL) {
+ /* a few sanity checks */
+ BUG_ON(ss->subsys_id >= CGROUP_BUILTIN_SUBSYS_COUNT);
+ BUG_ON(subsys[ss->subsys_id] != ss);
+ return 0;
+ }
+
+ /*
+ * need to register a subsys id before anything else - for example,
+ * init_cgroup_css needs it.
+ */
+ mutex_lock(&cgroup_mutex);
+ /* find the first empty slot in the array */
+ for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) {
+ if (subsys[i] == NULL)
+ break;
+ }
+ if (i == CGROUP_SUBSYS_COUNT) {
+ /* maximum number of subsystems already registered! */
+ mutex_unlock(&cgroup_mutex);
+ return -EBUSY;
+ }
+ /* assign ourselves the subsys_id */
+ ss->subsys_id = i;
+ subsys[i] = ss;
+
+ /*
+ * no ss->create seems to need anything important in the ss struct, so
+ * this can happen first (i.e. before the rootnode attachment).
+ */
+ css = ss->create(ss, dummytop);
+ if (IS_ERR(css)) {
+ /* failure case - need to deassign the subsys[] slot. */
+ subsys[i] = NULL;
+ mutex_unlock(&cgroup_mutex);
+ return PTR_ERR(css);
+ }
+
+ list_add(&ss->sibling, &rootnode.subsys_list);
+ ss->root = &rootnode;
+
+ /* our new subsystem will be attached to the dummy hierarchy. */
+ init_cgroup_css(css, ss, dummytop);
+ /* init_idr must be after init_cgroup_css because it sets css->id. */
+ if (ss->use_id) {
+ int ret = cgroup_init_idr(ss, css);
+ if (ret) {
+ dummytop->subsys[ss->subsys_id] = NULL;
+ ss->destroy(ss, dummytop);
+ subsys[i] = NULL;
+ mutex_unlock(&cgroup_mutex);
+ return ret;
+ }
+ }
+
+ /*
+ * Now we need to entangle the css into the existing css_sets. unlike
+ * in cgroup_init_subsys, there are now multiple css_sets, so each one
+ * will need a new pointer to it; done by iterating the css_set_table.
+ * furthermore, modifying the existing css_sets will corrupt the hash
+ * table state, so each changed css_set will need its hash recomputed.
+ * this is all done under the css_set_lock.
+ */
+ write_lock(&css_set_lock);
+ for (i = 0; i < CSS_SET_TABLE_SIZE; i++) {
+ struct css_set *cg;
+ struct hlist_node *node, *tmp;
+ struct hlist_head *bucket = &css_set_table[i], *new_bucket;
+
+ hlist_for_each_entry_safe(cg, node, tmp, bucket, hlist) {
+ /* skip entries that we already rehashed */
+ if (cg->subsys[ss->subsys_id])
+ continue;
+ /* remove existing entry */
+ hlist_del(&cg->hlist);
+ /* set new value */
+ cg->subsys[ss->subsys_id] = css;
+ /* recompute hash and restore entry */
+ new_bucket = css_set_hash(cg->subsys);
+ hlist_add_head(&cg->hlist, new_bucket);
+ }
+ }
+ write_unlock(&css_set_lock);
+
+ mutex_init(&ss->hierarchy_mutex);
+ lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
+ ss->active = 1;
+
+ /*
+ * pin the subsystem's module so it doesn't go away. this shouldn't
+ * fail, since the module's initcall calls us.
+ * TODO: with module unloading, move this elsewhere
+ */
+ BUG_ON(!try_module_get(ss->module));
+
+ /* success! */
+ mutex_unlock(&cgroup_mutex);
+ return 0;
}
+EXPORT_SYMBOL_GPL(cgroup_load_subsys);
/**
* cgroup_init_early - cgroup initialization at system boot
@@ -3364,7 +3505,7 @@ int __init cgroup_init(void)
if (!ss->early_init)
cgroup_init_subsys(ss);
if (ss->use_id)
- cgroup_subsys_init_idr(ss);
+ cgroup_init_idr(ss, init_css_set.subsys[ss->subsys_id]);
}
/* Add init_css_set to the hash table */
@@ -4033,15 +4174,14 @@ err_out:
}
-static int __init cgroup_subsys_init_idr(struct cgroup_subsys *ss)
+static int __init_or_module cgroup_init_idr(struct cgroup_subsys *ss,
+ struct cgroup_subsys_state *rootcss)
{
struct css_id *newid;
- struct cgroup_subsys_state *rootcss;
spin_lock_init(&ss->id_lock);
idr_init(&ss->idr);
- rootcss = init_css_set.subsys[ss->subsys_id];
newid = get_new_cssid(ss, 0);
if (IS_ERR(newid))
return PTR_ERR(newid);