mm: rcu safe VMA freeing

This prepares for page faults handling under VMA lock, looking up VMAs
under protection of an rcu read lock, instead of the usual mmap read lock.

Link: https://lkml.kernel.org/r/20230227173632.3292573-11-surenb@google.com
Signed-off-by: Michel Lespinasse <michel@lespinasse.org>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 651a5c256732fb46e51176ef6fa48f162c3c9f0b..f203e2562e00206fff1806906c72a9676ab7baba 100644 (file)
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -480,9 +480,16 @@ struct anon_vma_name {
 struct vm_area_struct {
        /* The first cache line has the info for VMA tree walking. */
 
-       unsigned long vm_start;         /* Our start address within vm_mm. */
-       unsigned long vm_end;           /* The first byte after our end address
-                                          within vm_mm. */
+       union {
+               struct {
+                       /* VMA covers [vm_start; vm_end) addresses within mm */
+                       unsigned long vm_start;
+                       unsigned long vm_end;
+               };
+#ifdef CONFIG_PER_VMA_LOCK
+               struct rcu_head vm_rcu; /* Used for deferred freeing. */
+#endif
+       };
 
        struct mm_struct *vm_mm;        /* The address space we belong to. */
        pgprot_t vm_page_prot;          /* Access permissions of this VMA. */

diff --git a/kernel/fork.c b/kernel/fork.c
index cea99f003f247c0b84ad5c4817e890c586d0799c..93ec6e14bb65e804f204dc3b2ded458ae94389e0 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -479,12 +479,30 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
        return new;
 }
 
-void vm_area_free(struct vm_area_struct *vma)
+static void __vm_area_free(struct vm_area_struct *vma)
 {
        free_anon_vma_name(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)) {