Merge branch 'slab/for-6.15/kfree_rcu_tiny' into slab/for-next

Merge the slab feature branch kfree_rcu_tiny for 6.15:

- Move the TINY_RCU kvfree_rcu() implementation from RCU to SLAB
  subsystem and cleanup its integration.

4 files changed, 32 insertions, 54 deletions

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 48e5c03df1dd..23bcf71ffb06 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -1025,12 +1025,6 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 #define RCU_POINTER_INITIALIZER(p, v) \
 		.p = RCU_INITIALIZER(v)
 
-/*
- * Does the specified offset indicate that the corresponding rcu_head
- * structure can be handled by kvfree_rcu()?
- */
-#define __is_kvfree_rcu_offset(offset) ((offset) < 4096)
-
 /**
  * kfree_rcu() - kfree an object after a grace period.
  * @ptr: pointer to kfree for double-argument invocations.
@@ -1041,11 +1035,11 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * 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.
+ * The kfree_rcu() function handles this issue. In order to have a universal
+ * callback function handling different offsets of rcu_head, the callback needs
+ * to determine the starting address of the freed object, which can be a large
+ * kmalloc or vmalloc allocation. To allow simply aligning the pointer down to
+ * page boundary for those, only offsets up to 4095 bytes can be accommodated.
  * If the offset is larger than 4095 bytes, a compile-time error will
  * be generated in kvfree_rcu_arg_2(). If this error is triggered, you can
  * either fall back to use of call_rcu() or rearrange the structure to
@@ -1082,14 +1076,23 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 #define kfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr)
 #define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr)
 
+/*
+ * In mm/slab_common.c, no suitable header to include here.
+ */
+void kvfree_call_rcu(struct rcu_head *head, void *ptr);
+
+/*
+ * The BUILD_BUG_ON() makes sure the rcu_head offset can be handled. See the
+ * comment of kfree_rcu() for details.
+ */
 #define kvfree_rcu_arg_2(ptr, rhf)					\
 do {									\
 	typeof (ptr) ___p = (ptr);					\
 									\
-	if (___p) {									\
-		BUILD_BUG_ON(!__is_kvfree_rcu_offset(offsetof(typeof(*(ptr)), rhf)));	\
-		kvfree_call_rcu(&((___p)->rhf), (void *) (___p));			\
-	}										\
+	if (___p) {							\
+		BUILD_BUG_ON(offsetof(typeof(*(ptr)), rhf) >= 4096);	\
+		kvfree_call_rcu(&((___p)->rhf), (void *) (___p));	\
+	}								\
 } while (0)
 
 #define kvfree_rcu_arg_1(ptr)					\
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index fe42315f667f..f519cd680228 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -90,41 +90,6 @@ static inline void synchronize_rcu_expedited(void)
 	synchronize_rcu();
 }
 
-/*
- * Add one more declaration of kvfree() here. It is
- * not so straight forward to just include <linux/mm.h>
- * where it is defined due to getting many compile
- * errors caused by that include.
- */
-extern void kvfree(const void *addr);
-
-static inline void __kvfree_call_rcu(struct rcu_head *head, void *ptr)
-{
-	if (head) {
-		call_rcu(head, (rcu_callback_t) ((void *) head - ptr));
-		return;
-	}
-
-	// kvfree_rcu(one_arg) call.
-	might_sleep();
-	synchronize_rcu();
-	kvfree(ptr);
-}
-
-static inline void kvfree_rcu_barrier(void)
-{
-	rcu_barrier();
-}
-
-#ifdef CONFIG_KASAN_GENERIC
-void kvfree_call_rcu(struct rcu_head *head, void *ptr);
-#else
-static inline void kvfree_call_rcu(struct rcu_head *head, void *ptr)
-{
-	__kvfree_call_rcu(head, ptr);
-}
-#endif
-
 void rcu_qs(void);
 
 static inline void rcu_softirq_qs(void)
@@ -164,7 +129,6 @@ static inline void rcu_end_inkernel_boot(void) { }
 static inline bool rcu_inkernel_boot_has_ended(void) { return true; }
 static inline bool rcu_is_watching(void) { return true; }
 static inline void rcu_momentary_eqs(void) { }
-static inline void kfree_rcu_scheduler_running(void) { }
 
 /* Avoid RCU read-side critical sections leaking across. */
 static inline void rcu_all_qs(void) { barrier(); }
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 27d86d912781..dbe77b5fe06e 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -34,12 +34,9 @@ static inline void rcu_virt_note_context_switch(void)
 }
 
 void synchronize_rcu_expedited(void);
-void kvfree_call_rcu(struct rcu_head *head, void *ptr);
-void kvfree_rcu_barrier(void);
 
 void rcu_barrier(void);
 void rcu_momentary_eqs(void);
-void kfree_rcu_scheduler_running(void);
 
 struct rcu_gp_oldstate {
 	unsigned long rgos_norm;
diff --git a/include/linux/slab.h b/include/linux/slab.h
index ab05a143d09a..98e07e9e9e58 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -16,6 +16,7 @@
 #include <linux/gfp.h>
 #include <linux/overflow.h>
 #include <linux/types.h>
+#include <linux/rcupdate.h>
 #include <linux/workqueue.h>
 #include <linux/percpu-refcount.h>
 #include <linux/cleanup.h>
@@ -1080,6 +1081,19 @@ extern void kvfree_sensitive(const void *addr, size_t len);
 
 unsigned int kmem_cache_size(struct kmem_cache *s);
 
+#ifndef CONFIG_KVFREE_RCU_BATCHED
+static inline void kvfree_rcu_barrier(void)
+{
+	rcu_barrier();
+}
+
+static inline void kfree_rcu_scheduler_running(void) { }
+#else
+void kvfree_rcu_barrier(void);
+
+void kfree_rcu_scheduler_running(void);
+#endif
+
 /**
  * kmalloc_size_roundup - Report allocation bucket size for the given size
  *