[RFC PATCH v3 03/10] allow preallocated kmem_cache instances in modules

[Al Viro]

	We need to make sure that instance in a module will get to
slab_kmem_cache_release() before the module data gets freed.  That's only
a problem on sysfs setups - otherwise it'll definitely be finished before
kmem_cache_destroy() returns.

	Note that modules themselves have sysfs-exposed attributes,
so a similar problem already exists there.  That's dealt with by
having mod_sysfs_teardown() wait for refcount of module->mkobj.kobj
reaching zero.  Let's make use of that - have static-duration-in-module
kmem_cache instances grab a reference to that kobject upon setup and
drop it in the end of slab_kmem_cache_release().

	Let setup helpers store the kobject to be pinned in
kmem_cache_args->owner (for preallocated; if somebody manually sets it
for non-preallocated case, it'll be ignored).  That would be
&THIS_MODULE->mkobj.kobj for a module and NULL in built-in.

	If sysfs is enabled and we are dealing with preallocated instance,
let create_cache() grab and stash that reference in kmem_cache->owner
and let slab_kmem_cache_release() drop it instead of freeing kmem_cache
instance.

	Preallocated kmem_cache instances in modules are forcibly made
non-mergable - any subsequent alias could outlive the module (and module's
.data) by arbitrary long time.  If you really want your (modular) cache
to be mergable, just have it dynamically allocated.

Signed-off-by: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
---
 include/linux/slab-static.h | 11 +++++++----
 include/linux/slab.h        |  1 +
 mm/slab.h                   |  1 +
 mm/slab_common.c            | 19 +++++++++++++++++--
 4 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/include/linux/slab-static.h b/include/linux/slab-static.h
index 007fc0bd4e8c..16d1564b4a4b 100644
--- a/include/linux/slab-static.h
+++ b/include/linux/slab-static.h
@@ -5,18 +5,21 @@
 #include <linux/init.h>
 #include <generated/kmem_cache_size.h>
 
-#ifdef MODULE
-#error "can't use that in modules"
-#endif
-
 /* same size and alignment as struct kmem_cache: */
 struct kmem_cache_opaque {
 	unsigned char opaque[KMEM_CACHE_SIZE];
 } __aligned(KMEM_CACHE_ALIGN);
 
+#ifdef MODULE
+#define THIS_MODULE_KOBJ &THIS_MODULE->mkobj.kobj
+#else
+#define THIS_MODULE_KOBJ NULL
+#endif
+
 #define __KMEM_CACHE_SETUP(cache, name, size, flags, ...)	\
 		__kmem_cache_create_args((name), (size),	\
 			&(struct kmem_cache_args) {		\
+				.owner = THIS_MODULE_KOBJ,	\
 				.preallocated = (cache),	\
 				__VA_ARGS__}, (flags))
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index ec68aabf98df..c95ad771ece2 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -382,6 +382,7 @@ struct kmem_cache_args {
 	 */
 	unsigned int sheaf_capacity;
 	struct kmem_cache *preallocated;
+	struct kobject *owner;
 };
 
 struct kmem_cache *__kmem_cache_create_args(const char *name,
diff --git a/mm/slab.h b/mm/slab.h
index bf2f87acf5e3..8b1db0d03226 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -219,6 +219,7 @@ struct kmem_cache {
 	struct list_head list;		/* List of slab caches */
 #ifdef CONFIG_SYSFS
 	struct kobject kobj;		/* For sysfs */
+	struct kobject *owner;		/* keep that pinned while alive */
 #endif
 #ifdef CONFIG_SLAB_FREELIST_HARDENED
 	unsigned long random;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 5b6aaa96d68d..1717c79d92be 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -255,6 +255,12 @@ static struct kmem_cache *create_cache(const char *name,
 			kmem_cache_free(kmem_cache, s);
 		return ERR_PTR(err);
 	}
+#ifdef CONFIG_SYSFS
+	if (flags & SLAB_PREALLOCATED) {
+		s->owner = args->owner;
+		kobject_get(s->owner);
+	}
+#endif
 	s->refcount = 1;
 	list_add(&s->list, &slab_caches);
 	return s;
@@ -366,8 +372,11 @@ struct kmem_cache *__kmem_cache_create_args(const char *name,
 		    object_size - args->usersize < args->useroffset))
 		args->usersize = args->useroffset = 0;
 
-	if (args->preallocated)
+	if (args->preallocated) {
 		flags |= SLAB_PREALLOCATED;
+		if (args->owner)
+			flags |= SLAB_NO_MERGE;
+	}
 
 	s = __kmem_cache_alias(name, object_size, flags, args);
 	if (s)
@@ -524,7 +533,13 @@ void slab_kmem_cache_release(struct kmem_cache *s)
 {
 	__kmem_cache_release(s);
 	kfree_const(s->name);
-	kmem_cache_free(kmem_cache, s);
+	if (!(s->flags & SLAB_PREALLOCATED)) {
+		kmem_cache_free(kmem_cache, s);
+		return;
+	}
+#ifdef CONFIG_SYSFS
+	kobject_put(s->owner);
+#endif
 }
 
 void kmem_cache_destroy(struct kmem_cache *s)
-- 
2.47.3