mm: prepare lock_vma_under_rcu() for vma reuse possibility

Once we make vma cache SLAB_TYPESAFE_BY_RCU, it will be possible for a vma
to be reused and attached to another mm after lock_vma_under_rcu() locks
the vma.  lock_vma_under_rcu() should ensure that vma_start_read() is
using the original mm and after locking the vma it should ensure that
vma->vm_mm has not changed from under us.

Link: https://lkml.kernel.org/r/20250213224655.1680278-17-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 aad932c..e3f962d 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -739,10 +739,13 @@ static inline void vma_refcount_put(struct vm_area_struct *vma)
  * Try to read-lock a vma. The function is allowed to occasionally yield false
  * locked result to avoid performance overhead, in which case we fall back to
  * using mmap_lock. The function should never yield false unlocked result.
+ * False locked result is possible if mm_lock_seq overflows or if vma gets
+ * reused and attached to a different mm before we lock it.
  * Returns the vma on success, NULL on failure to lock and EAGAIN if vma got
  * detached.
  */
-static inline struct vm_area_struct *vma_start_read(struct vm_area_struct *vma)
+static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
+                                                   struct vm_area_struct *vma)
 {
        int oldcnt;
 
@@ -753,7 +756,7 @@ static inline struct vm_area_struct *vma_start_read(struct vm_area_struct *vma)
         * we don't rely on for anything - the mm_lock_seq read against which we
         * need ordering is below.
         */
-       if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(vma->vm_mm->mm_lock_seq.sequence))
+       if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(mm->mm_lock_seq.sequence))
                return NULL;
 
        /*
@@ -780,7 +783,7 @@ static inline struct vm_area_struct *vma_start_read(struct vm_area_struct *vma)
         * after it has been unlocked.
         * This pairs with RELEASE semantics in vma_end_write_all().
         */
-       if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&vma->vm_mm->mm_lock_seq))) {
+       if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&mm->mm_lock_seq))) {
                vma_refcount_put(vma);
                return NULL;
        }
@@ -914,7 +917,8 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
 #else /* CONFIG_PER_VMA_LOCK */
 
 static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) {}
-static inline struct vm_area_struct *vma_start_read(struct vm_area_struct *vma)
+static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
+                                                   struct vm_area_struct *vma)
                { return NULL; }
 static inline void vma_end_read(struct vm_area_struct *vma) {}
 static inline void vma_start_write(struct vm_area_struct *vma) {}

diff --git a/mm/memory.c b/mm/memory.c
index 51f2334..39bceed 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6452,7 +6452,7 @@ retry:
        if (!vma)
                goto inval;
 
-       vma = vma_start_read(vma);
+       vma = vma_start_read(mm, vma);
        if (IS_ERR_OR_NULL(vma)) {
                /* Check if the VMA got isolated after we found it */
                if (PTR_ERR(vma) == -EAGAIN) {
@@ -6471,8 +6471,9 @@ retry:
         * fields are accessible for RCU readers.
         */
 
-       /* Check since vm_start/vm_end might change before we lock the VMA */
-       if (unlikely(address < vma->vm_start || address >= vma->vm_end))
+       /* Check if the vma we locked is the right one. */
+       if (unlikely(vma->vm_mm != mm ||
+                    address < vma->vm_start || address >= vma->vm_end))
                goto inval_end_read;
 
        rcu_read_unlock();