mm: make vma cache SLAB_TYPESAFE_BY_RCU

To enable SLAB_TYPESAFE_BY_RCU for vma cache we need to ensure that object
reuse before RCU grace period is over will be detected by
lock_vma_under_rcu().

Current checks are sufficient as long as vma is detached before it is
freed.  The only place this is not currently happening is in exit_mmap(). 
Add the missing vma_mark_detached() in exit_mmap().

Another issue which might trick lock_vma_under_rcu() during vma reuse is
vm_area_dup(), which copies the entire content of the vma into a new one,
overriding new vma's vm_refcnt and temporarily making it appear as
attached.  This might trick a racing lock_vma_under_rcu() to operate on a
reused vma if it found the vma before it got reused.  To prevent this
situation, we should ensure that vm_refcnt stays at detached state (0)
when it is copied and advances to attached state only after it is added
into the vma tree.  Introduce vm_area_init_from() which preserves new
vma's vm_refcnt and use it in vm_area_dup().  Since all vmas are in
detached state with no current readers when they are freed,
lock_vma_under_rcu() will not be able to take vm_refcnt after vma got
detached even if vma is reused.

Finally, make vm_area_cachep SLAB_TYPESAFE_BY_RCU.  This will facilitate
vm_area_struct reuse and will minimize the number of call_rcu() calls.

Link: https://lkml.kernel.org/r/20250111042604.3230628-17-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Hugh Dickens <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: kernel test robot <oliver.sang@intel.com>
Cc: Klara Modin <klarasmodin@gmail.com>
Cc: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Mattew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: "Paul E . McKenney" <paulmck@kernel.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Sourav Panda <souravpanda@google.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/mm.h

@@ -258,8 +258,6 @@ void setup_initial_init_mm(void *start_code, void *end_code,
 struct vm_area_struct *vm_area_alloc(struct mm_struct *);
 struct vm_area_struct *vm_area_dup(struct vm_area_struct *);
 void vm_area_free(struct vm_area_struct *);
-/* Use only if VMA has no other users */
-void __vm_area_free(struct vm_area_struct *vma);
 
 #ifndef CONFIG_MMU
 extern struct rb_root nommu_region_tree;

include/linux/mm_types.h

@@ -574,6 +574,12 @@ static inline void *folio_get_private(struct folio *folio)
 
 typedef unsigned long vm_flags_t;
 
+/*
+ * 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;
+
 /*
  * A region containing a mapping of a non-memory backed file under NOMMU
  * conditions.  These are held in a global tree and are pinned by the VMAs that
@@ -677,6 +683,9 @@ struct vma_numab_state {
  *
  * Only explicitly marked struct members may be accessed by RCU readers before
  * getting a stable reference.
+ *
+ * WARNING: when adding new members, please update vm_area_init_from() to copy
+ * them during vm_area_struct content duplication.
  */
 struct vm_area_struct {
 	/* The first cache line has the info for VMA tree walking. */
@@ -687,9 +696,7 @@ struct vm_area_struct {
 			unsigned long vm_start;
 			unsigned long vm_end;
 		};
-#ifdef CONFIG_PER_VMA_LOCK
-		struct rcu_head vm_rcu;	/* Used for deferred freeing. */
-#endif
+		freeptr_t vm_freeptr; /* Pointer used by SLAB_TYPESAFE_BY_RCU */
 	};
 
 	/*

include/linux/slab.h

@@ -234,12 +234,6 @@ enum _slab_flag_bits {
 #define SLAB_NO_OBJ_EXT		__SLAB_FLAG_UNUSED
 #endif
 
-/*
- * 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;
-
 /*
  * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests.
  *

kernel/fork.c

@@ -449,6 +449,42 @@ struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
 	return vma;
 }
 
+static void vm_area_init_from(const struct vm_area_struct *src,
+			      struct vm_area_struct *dest)
+{
+	dest->vm_mm = src->vm_mm;
+	dest->vm_ops = src->vm_ops;
+	dest->vm_start = src->vm_start;
+	dest->vm_end = src->vm_end;
+	dest->anon_vma = src->anon_vma;
+	dest->vm_pgoff = src->vm_pgoff;
+	dest->vm_file = src->vm_file;
+	dest->vm_private_data = src->vm_private_data;
+	vm_flags_init(dest, src->vm_flags);
+	memcpy(&dest->vm_page_prot, &src->vm_page_prot,
+	       sizeof(dest->vm_page_prot));
+	/*
+	 * src->shared.rb may be modified concurrently when called from
+	 * dup_mmap(), but the clone will reinitialize it.
+	 */
+	data_race(memcpy(&dest->shared, &src->shared, sizeof(dest->shared)));
+	memcpy(&dest->vm_userfaultfd_ctx, &src->vm_userfaultfd_ctx,
+	       sizeof(dest->vm_userfaultfd_ctx));
+#ifdef CONFIG_ANON_VMA_NAME
+	dest->anon_name = src->anon_name;
+#endif
+#ifdef CONFIG_SWAP
+	memcpy(&dest->swap_readahead_info, &src->swap_readahead_info,
+	       sizeof(dest->swap_readahead_info));
+#endif
+#ifndef CONFIG_MMU
+	dest->vm_region = src->vm_region;
+#endif
+#ifdef CONFIG_NUMA
+	dest->vm_policy = src->vm_policy;
+#endif
+}
+
 struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 {
 	struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
@@ -458,11 +494,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 
 	ASSERT_EXCLUSIVE_WRITER(orig->vm_flags);
 	ASSERT_EXCLUSIVE_WRITER(orig->vm_file);
-	/*
-	 * orig->shared.rb may be modified concurrently, but the clone
-	 * will be reinitialized.
-	 */
-	data_race(memcpy(new, orig, sizeof(*new)));
+	vm_area_init_from(orig, new);
 	vma_lock_init(new, true);
 	INIT_LIST_HEAD(&new->anon_vma_chain);
 	vma_numab_state_init(new);
@@ -471,7 +503,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
 	return new;
 }
 
-void __vm_area_free(struct vm_area_struct *vma)
+void vm_area_free(struct vm_area_struct *vma)
 {
 	/* The vma should be detached while being destroyed. */
 	vma_assert_detached(vma);
@@ -480,25 +512,6 @@ void __vm_area_free(struct vm_area_struct *vma)
 	kmem_cache_free(vm_area_cachep, vma);
 }
 
-#ifdef CONFIG_PER_VMA_LOCK
-static void vm_area_free_rcu_cb(struct rcu_head *head)
-{
-	struct vm_area_struct *vma = container_of(head, struct vm_area_struct,
-						  vm_rcu);
-
-	__vm_area_free(vma);
-}
-#endif
-
-void vm_area_free(struct vm_area_struct *vma)
-{
-#ifdef CONFIG_PER_VMA_LOCK
-	call_rcu(&vma->vm_rcu, vm_area_free_rcu_cb);
-#else
-	__vm_area_free(vma);
-#endif
-}
-
 static void account_kernel_stack(struct task_struct *tsk, int account)
 {
 	if (IS_ENABLED(CONFIG_VMAP_STACK)) {
@@ -3144,6 +3157,11 @@ void __init mm_cache_init(void)
 
 void __init proc_caches_init(void)
 {
+	struct kmem_cache_args args = {
+		.use_freeptr_offset = true,
+		.freeptr_offset = offsetof(struct vm_area_struct, vm_freeptr),
+	};
+
 	sighand_cachep = kmem_cache_create("sighand_cache",
 			sizeof(struct sighand_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
@@ -3160,8 +3178,9 @@ void __init proc_caches_init(void)
 			sizeof(struct fs_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
 			NULL);
-	vm_area_cachep = KMEM_CACHE(vm_area_struct,
-			SLAB_HWCACHE_ALIGN|SLAB_NO_MERGE|SLAB_PANIC|
+	vm_area_cachep = kmem_cache_create("vm_area_struct",
+			sizeof(struct vm_area_struct), &args,
+			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
 			SLAB_ACCOUNT);
 	mmap_init();
 	nsproxy_cache_init();

mm/mmap.c

@@ -1364,7 +1364,8 @@ void exit_mmap(struct mm_struct *mm)
 	do {
 		if (vma->vm_flags & VM_ACCOUNT)
 			nr_accounted += vma_pages(vma);
-		remove_vma(vma, /* unreachable = */ true);
+		vma_mark_detached(vma);
+		remove_vma(vma);
 		count++;
 		cond_resched();
 		vma = vma_next(&vmi);

mm/vma.c

@@ -406,19 +406,14 @@ static bool can_vma_merge_right(struct vma_merge_struct *vmg,
 /*
  * Close a vm structure and free it.
  */
-void remove_vma(struct vm_area_struct *vma, bool unreachable)
+void remove_vma(struct vm_area_struct *vma)
 {
 	might_sleep();
 	vma_close(vma);
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	mpol_put(vma_policy(vma));
-	if (unreachable) {
-		vma_mark_detached(vma);
-		__vm_area_free(vma);
-	} else {
 	vm_area_free(vma);
-	}
 }
 
 /*
@@ -1201,7 +1196,7 @@ static void vms_complete_munmap_vmas(struct vma_munmap_struct *vms,
 	/* Remove and clean up vmas */
 	mas_set(mas_detach, 0);
 	mas_for_each(mas_detach, vma, ULONG_MAX)
-		remove_vma(vma, /* unreachable = */ false);
+		remove_vma(vma);
 
 	vm_unacct_memory(vms->nr_accounted);
 	validate_mm(mm);

mm/vma.h

@@ -170,7 +170,7 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm,
 		  unsigned long start, size_t len, struct list_head *uf,
 		  bool unlock);
 
-void remove_vma(struct vm_area_struct *vma, bool unreachable);
+void remove_vma(struct vm_area_struct *vma);
 
 void unmap_region(struct ma_state *mas, struct vm_area_struct *vma,
 		struct vm_area_struct *prev, struct vm_area_struct *next);

tools/testing/vma/vma_internal.h

@@ -693,14 +693,9 @@ static inline void mpol_put(struct mempolicy *)
 {
 }
 
-static inline void __vm_area_free(struct vm_area_struct *vma)
-{
-	free(vma);
-}
-
 static inline void vm_area_free(struct vm_area_struct *vma)
 {
-	__vm_area_free(vma);
+	free(vma);
 }
 
 static inline void lru_add_drain(void)