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. vma_mark_attached() in modified to
include a release fence to ensure all stores to the vma happen before
vm_refcnt gets initialized.

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/20250213224655.1680278-18-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Shivank Garg <shivankg@amd.com>
Link: https://lkml.kernel.org/r/5e19ec93-8307-47c2-bb13-3ddf7150624e@amd.com
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: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
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: Matthew 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>
Cc: Will Deacon <will@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f3b738562e50383be005ea15a1bd1c17ea4f1208..fabd537904fcb9bcf0a699261b556058db63ce3a 100644 (file)
--- a/include/linux/mm.h
+++ b/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;
@@ -890,7 +888,7 @@ static inline void vma_mark_attached(struct vm_area_struct *vma)
 {
        vma_assert_write_locked(vma);
        vma_assert_detached(vma);
-       refcount_set(&vma->vm_refcnt, 1);
+       refcount_set_release(&vma->vm_refcnt, 1);
 }
 
 void vma_mark_detached(struct vm_area_struct *vma);

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index e990d387ec37918c818feee5433468c475fa1129..369f76a8f00cdb96bcb0c61831462e7991ab310c 100644 (file)
--- a/include/linux/mm_types.h
+++ b/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 */
        };
 
        /*

diff --git a/include/linux/slab.h b/include/linux/slab.h
index ad902a2d692b2f83d90d9c39c6fa4bafe09851a2..f8924fd6ea26949c08edb14b47a5415d4c02cd8e 100644 (file)
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -243,12 +243,6 @@ 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.
  *

diff --git a/kernel/fork.c b/kernel/fork.c
index 48a0038f606fcf7f8f831e3f41f8413d2154be1d..364b2d4fd3efa8ffe50921ee6a4b30c425a863f0 100644 (file)
--- a/kernel/fork.c
+++ b/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)) {
@@ -3156,6 +3169,11 @@ 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|
@@ -3172,8 +3190,9 @@ 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();

diff --git a/mm/mmap.c b/mm/mmap.c
index 6401a1d73f4a4415e7b845e69fd95c77c39234d3..15d6cd7cc845f6b7016576635bab48c358232ab8 100644 (file)
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1305,7 +1305,8 @@ 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);

diff --git a/mm/vma.c b/mm/vma.c
index 6fe6e6831aaeb45494b5e7539c75ea15f6f2a9cf..76bec07e30b751d122b8c9e72aed054ae2f140ae 100644 (file)
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -420,19 +420,14 @@ 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);
-       }
+       vm_area_free(vma);
 }
 
 /*
@@ -1218,7 +1213,7 @@ 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);

diff --git a/mm/vma.h b/mm/vma.h
index 55be77ff042f0a0fe224d9866cda7c90842e36f8..7356ca5a22d33286166d813ea4e3fe77f61df608 100644 (file)
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -218,7 +218,7 @@ 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);

diff --git a/tools/include/linux/refcount.h b/tools/include/linux/refcount.h
index 36cb29bc57c2dbfa3168cde5e1d3b15a056f3693..1ace03e1a4f8ba07f8933e95f1f5f8f49292df1b 100644 (file)
--- a/tools/include/linux/refcount.h
+++ b/tools/include/linux/refcount.h
@@ -60,6 +60,11 @@ static inline void refcount_set(refcount_t *r, unsigned int n)
        atomic_set(&r->refs, n);
 }
 
+static inline void refcount_set_release(refcount_t *r, unsigned int n)
+{
+       atomic_set_release(&r->refs, n);
+}
+
 static inline unsigned int refcount_read(const refcount_t *r)
 {
        return atomic_read(&r->refs);

diff --git a/tools/testing/vma/linux/atomic.h b/tools/testing/vma/linux/atomic.h
index 788c597c4fdea7392307de93ff4459453b96179b..683383d0f2bf83c6f3f15302382792e4d081d472 100644 (file)
--- a/tools/testing/vma/linux/atomic.h
+++ b/tools/testing/vma/linux/atomic.h
@@ -7,6 +7,7 @@
 #define atomic_inc(x) uatomic_inc(x)
 #define atomic_read(x) uatomic_read(x)
 #define atomic_set(x, y) uatomic_set(x, y)
+#define atomic_set_release(x, y) uatomic_set(x, y)
 #define U8_MAX UCHAR_MAX
 
 #ifndef atomic_cmpxchg_relaxed

diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index b385170fbb8f0be1e195e073a3a4c6e53ec2bde4..572ab2cea763f50dc7eb04dd8f3c8974874c0971 100644 (file)
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -476,7 +476,7 @@ static inline void vma_mark_attached(struct vm_area_struct *vma)
 {
        vma_assert_write_locked(vma);
        vma_assert_detached(vma);
-       refcount_set(&vma->vm_refcnt, 1);
+       refcount_set_release(&vma->vm_refcnt, 1);
 }
 
 static inline void vma_mark_detached(struct vm_area_struct *vma)
@@ -696,14 +696,9 @@ 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)