rcu: introduce kfree_rcu()

Many rcu callbacks functions just call kfree() on the base structure.
These functions are trivial, but their size adds up, and furthermore
when they are used in a kernel module, that module must invoke the
high-latency rcu_barrier() function at module-unload time.

The kfree_rcu() function introduced by this commit addresses this issue.
Rather than encoding a function address in the embedded rcu_head
structure, kfree_rcu() instead encodes the offset of the rcu_head
structure within the base structure.  Because the functions are not
allowed in the low-order 4096 bytes of kernel virtual memory, offsets
up to 4095 bytes can be accommodated.  If the offset is larger than
4095 bytes, a compile-time error will be generated in __kfree_rcu().
If this error is triggered, you can either fall back to use of call_rcu()
or rearrange the structure to position the rcu_head structure into the
first 4096 bytes.

Note that the allowable offset might decrease in the future, for example,
to allow something like kmem_cache_free_rcu().

The new kfree_rcu() function can replace code as follows:

	call_rcu(&p->rcu, simple_kfree_callback);

where "simple_kfree_callback()" might be defined as follows:

	void simple_kfree_callback(struct rcu_head *p)
	{
		struct foo *q = container_of(p, struct foo, rcu);

		kfree(q);
	}

with the following:

	kfree_rcu(&p->rcu, rcu);

Note that the "rcu" is the name of a field in the structure being
freed.  The reason for using this rather than passing in a pointer
to the base structure is that the above approach allows better type
checking.

This commit is based on earlier work by Lai Jiangshan and Manfred Spraul:

Lai's V1 patch: http://lkml.org/lkml/2008/9/18/1
Manfred's patch: http://lkml.org/lkml/2009/1/2/115

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: David Howells <dhowells@redhat.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index c7aeacf..99f9aa7 100644 (file)
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -809,4 +809,60 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
+static __always_inline bool __is_kfree_rcu_offset(unsigned long offset)
+{
+       return offset < 4096;
+}
+
+static __always_inline
+void __kfree_rcu(struct rcu_head *head, unsigned long offset)
+{
+       typedef void (*rcu_callback)(struct rcu_head *);
+
+       BUILD_BUG_ON(!__builtin_constant_p(offset));
+
+       /* See the kfree_rcu() header comment. */
+       BUILD_BUG_ON(!__is_kfree_rcu_offset(offset));
+
+       call_rcu(head, (rcu_callback)offset);
+}
+
+extern void kfree(const void *);
+
+static inline void __rcu_reclaim(struct rcu_head *head)
+{
+       unsigned long offset = (unsigned long)head->func;
+
+       if (__is_kfree_rcu_offset(offset))
+               kfree((void *)head - offset);
+       else
+               head->func(head);
+}
+
+/**
+ * kfree_rcu() - kfree an object after a grace period.
+ * @ptr:       pointer to kfree
+ * @rcu_head:  the name of the struct rcu_head within the type of @ptr.
+ *
+ * Many rcu callbacks functions just call kfree() on the base structure.
+ * These functions are trivial, but their size adds up, and furthermore
+ * when they are used in a kernel module, that module must invoke the
+ * high-latency rcu_barrier() function at module-unload time.
+ *
+ * The kfree_rcu() function handles this issue.  Rather than encoding a
+ * function address in the embedded rcu_head structure, kfree_rcu() instead
+ * encodes the offset of the rcu_head structure within the base structure.
+ * Because the functions are not allowed in the low-order 4096 bytes of
+ * kernel virtual memory, offsets up to 4095 bytes can be accommodated.
+ * If the offset is larger than 4095 bytes, a compile-time error will
+ * be generated in __kfree_rcu().  If this error is triggered, you can
+ * either fall back to use of call_rcu() or rearrange the structure to
+ * position the rcu_head structure into the first 4096 bytes.
+ *
+ * Note that the allowable offset might decrease in the future, for example,
+ * to allow something like kmem_cache_free_rcu().
+ */
+#define kfree_rcu(ptr, rcu_head)                                       \
+       __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
+
 #endif /* __LINUX_RCUPDATE_H */

diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 0c343b9..4d60fbc 100644 (file)
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -167,7 +167,7 @@ static void rcu_process_callbacks(struct rcu_ctrlblk *rcp)
                prefetch(next);
                debug_rcu_head_unqueue(list);
                local_bh_disable();
-               list->func(list);
+               __rcu_reclaim(list);
                local_bh_enable();
                list = next;
                RCU_TRACE(cb_count++);

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index b579e4f..2c07adb 100644 (file)
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1206,7 +1206,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
                next = list->next;
                prefetch(next);
                debug_rcu_head_unqueue(list);
-               list->func(list);
+               __rcu_reclaim(list);
                list = next;
                if (++count >= rdp->blimit)
                        break;