Merge patch series "fs,mm: add kmem_cache_create_rcu()"

Christian Brauner <brauner@kernel.org> says:

When a kmem cache is created with SLAB_TYPESAFE_BY_RCU the free pointer
must be located outside of the object because we don't know what part of
the memory can safely be overwritten as it may be needed to prevent
object recycling.

That has the consequence that SLAB_TYPESAFE_BY_RCU may end up adding a
new cacheline. This is the case for e.g., struct file. After having it
shrunk down by 40 bytes and having it fit in three cachelines we still
have SLAB_TYPESAFE_BY_RCU adding a fourth cacheline because it needs to
accommodate the free pointer.

Add a new kmem_cache_create_rcu() function that allows the caller to
specify an offset where the free pointer is supposed to be placed.

Before this series cat /proc/slabinfo:

filp                1198   1248    256   32    2 : tunables    0    0    0 : slabdata     39     39      0
                                   ^^^

After this series cat /proc/slabinfo:

filp                1323   1323    192   21    1 : tunables    0    0    0 : slabdata     63     63      0
                                   ^^^
* patches from https://lore.kernel.org/r/20240828-work-kmem_cache-rcu-v3-0-5460bc1f09f6@kernel.org:
  fs: use kmem_cache_create_rcu()
  mm: add kmem_cache_create_rcu()
  mm: remove unused root_cache argument

Link: https://lore.kernel.org/r/20240828-work-kmem_cache-rcu-v3-0-5460bc1f09f6@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 13 insertions, 7 deletions

diff --git a/mm/slub.c b/mm/slub.c
index c9d8a2497fd6..9aa5da1e8e27 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -466,12 +466,6 @@ static struct workqueue_struct *flushwq;
  *******************************************************************/
 
 /*
- * freeptr_t represents a SLUB freelist pointer, which might be encoded
- * and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled.
- */
-typedef struct { unsigned long v; } freeptr_t;
-
-/*
  * Returns freelist pointer (ptr). With hardening, this is obfuscated
  * with an XOR of the address where the pointer is held and a per-cache
  * random number.
@@ -3921,6 +3915,9 @@ static void *__slab_alloc_node(struct kmem_cache *s,
 /*
  * If the object has been wiped upon free, make sure it's fully initialized by
  * zeroing out freelist pointer.
+ *
+ * Note that we also wipe custom freelist pointers specified via
+ * s->rcu_freeptr_offset.
  */
 static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
 						   void *obj)
@@ -5144,6 +5141,12 @@ static void set_cpu_partial(struct kmem_cache *s)
 #endif
 }
 
+/* Was a valid freeptr offset requested? */
+static inline bool has_freeptr_offset(const struct kmem_cache *s)
+{
+	return s->rcu_freeptr_offset != UINT_MAX;
+}
+
 /*
  * calculate_sizes() determines the order and the distribution of data within
  * a slab object.
@@ -5189,7 +5192,8 @@ static int calculate_sizes(struct kmem_cache *s)
 	 */
 	s->inuse = size;
 
-	if ((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) || s->ctor ||
+	if (((flags & SLAB_TYPESAFE_BY_RCU) && !has_freeptr_offset(s)) ||
+	    (flags & SLAB_POISON) || s->ctor ||
 	    ((flags & SLAB_RED_ZONE) &&
 	     (s->object_size < sizeof(void *) || slub_debug_orig_size(s)))) {
 		/*
@@ -5210,6 +5214,8 @@ static int calculate_sizes(struct kmem_cache *s)
 		 */
 		s->offset = size;
 		size += sizeof(void *);
+	} else if ((flags & SLAB_TYPESAFE_BY_RCU) && has_freeptr_offset(s)) {
+		s->offset = s->rcu_freeptr_offset;
 	} else {
 		/*
 		 * Store freelist pointer near middle of object to keep