rcu, slab: use a regular callback function for kvfree_rcu

RCU has been special-casing callback function pointers that are integers
lower than 4096 as offsets of rcu_head for kvfree() instead. The tree
RCU implementation no longer does that as the batched kvfree_rcu() is
not a simple call_rcu(). The tiny RCU still does, and the plan is also
to make tree RCU use call_rcu() for SLUB_TINY configurations.

Instead of teaching tree RCU again to special case the offsets, let's
remove the special casing completely. Since there's no SLOB anymore, it
is possible to create a callback function that can take a pointer to a
middle of slab object with unknown offset and determine the object's
pointer before freeing it, so implement that as kvfree_rcu_cb().

Large kmalloc and vmalloc allocations are handled simply by aligning
down to page size. For that we retain the requirement that the offset is
smaller than 4096. But we can remove __is_kvfree_rcu_offset() completely
and instead just opencode the condition in the BUILD_BUG_ON() check.

Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>

1 files changed, 46 insertions, 0 deletions

diff --git a/mm/slub.c b/mm/slub.c
index 1f50129dcfb3..e8273f286569 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -19,6 +19,7 @@
 #include <linux/bitops.h>
 #include <linux/slab.h>
 #include "slab.h"
+#include <linux/vmalloc.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/kasan.h>
@@ -4728,6 +4729,51 @@ static void free_large_kmalloc(struct folio *folio, void *object)
 	folio_put(folio);
 }
 
+/*
+ * Given an rcu_head embedded within an object obtained from kvmalloc at an
+ * offset < 4k, free the object in question.
+ */
+void kvfree_rcu_cb(struct rcu_head *head)
+{
+	void *obj = head;
+	struct folio *folio;
+	struct slab *slab;
+	struct kmem_cache *s;
+	void *slab_addr;
+
+	if (is_vmalloc_addr(obj)) {
+		obj = (void *) PAGE_ALIGN_DOWN((unsigned long)obj);
+		vfree(obj);
+		return;
+	}
+
+	folio = virt_to_folio(obj);
+	if (!folio_test_slab(folio)) {
+		/*
+		 * rcu_head offset can be only less than page size so no need to
+		 * consider folio order
+		 */
+		obj = (void *) PAGE_ALIGN_DOWN((unsigned long)obj);
+		free_large_kmalloc(folio, obj);
+		return;
+	}
+
+	slab = folio_slab(folio);
+	s = slab->slab_cache;
+	slab_addr = folio_address(folio);
+
+	if (is_kfence_address(obj)) {
+		obj = kfence_object_start(obj);
+	} else {
+		unsigned int idx = __obj_to_index(s, slab_addr, obj);
+
+		obj = slab_addr + s->size * idx;
+		obj = fixup_red_left(s, obj);
+	}
+
+	slab_free(s, slab, obj, _RET_IP_);
+}
+
 /**
  * kfree - free previously allocated memory
  * @object: pointer returned by kmalloc() or kmem_cache_alloc()