The patch titled
cgroups: subsystem module loading interface
has been added to the -mm tree. Its filename is
cgroups-subsystem-module-loading-interface.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: cgroups: subsystem module loading interface
From: Ben Blum <bblum@xxxxxxxxxxxxxx>
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@xxxxxxxxxxxxxx>
Acked-by: Li Zefan <lizf@xxxxxxxxxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Lai Jiangshan <laijs@xxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/cgroups/cgroups.txt | 4
include/linux/cgroup.h | 4
kernel/cgroup.c | 128 ++++++++++++++++++++++++++++
3 files changed, 136 insertions(+)
diff -puN Documentation/cgroups/cgroups.txt~cgroups-subsystem-module-loading-interface Documentation/cgroups/cgroups.txt
--- a/Documentation/cgroups/cgroups.txt~cgroups-subsystem-module-loading-interface
+++ a/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 -puN include/linux/cgroup.h~cgroups-subsystem-module-loading-interface include/linux/cgroup.h
--- a/include/linux/cgroup.h~cgroups-subsystem-module-loading-interface
+++ a/include/linux/cgroup.h
@@ -36,6 +36,7 @@ extern void cgroup_post_fork(struct task
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;
@@ -485,6 +486,9 @@ 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 -puN kernel/cgroup.c~cgroups-subsystem-module-loading-interface kernel/cgroup.c
--- a/kernel/cgroup.c~cgroups-subsystem-module-loading-interface
+++ a/kernel/cgroup.c
@@ -43,6 +43,7 @@
#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>
@@ -2110,6 +2111,7 @@ 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,
@@ -2124,6 +2126,7 @@ 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.
@@ -3274,7 +3277,132 @@ static void __init cgroup_init_subsys(st
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);
+ /*
+ * 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
_
Patches currently in -mm which might be from bblum@xxxxxxxxxxxxxx are
cgroups-fix-2632-regression-causing-bug_on-in-cgroup_diput.patch
cgroups-revamp-subsys-array.patch
cgroups-subsystem-module-loading-interface.patch
cgroups-subsystem-module-unloading.patch
cgroups-net_cls-as-module.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
