[v6,16/71] kernel/fork: Use maple tree for dup_mmap() during forking

Commit Message

Liam R. Howlett Feb. 15, 2022, 2:43 p.m. UTC

From: "Liam R. Howlett" <[e-mail]>

The maple tree was already tracking VMAs in this function by an earlier
commit, but the rbtree iterator was being used to iterate the list.
Change the iterator to use a maple tree native iterator and switch to
the maple tree advanced API to avoid multiple walks of the tree during
insert operations.  Unexport the now-unused vma_store() function.

For performance reasons we bulk allocate the maple tree nodes.  The node
calculations are done internally to the tree and use the VMA count and
assume the worst-case node requirements.  The VM_DONT_COPY flag does
not allow for the most efficient copy method of the tree and so a bulk
loading algorithm is used.

Signed-off-by: Matthew Wilcox (Oracle) <[e-mail]>
Signed-off-by: Liam R. Howlett <[e-mail]>
Acked-by: Vlastimil Babka <[e-mail]>
---
 include/linux/mm.h |  2 --
 kernel/fork.c      | 24 ++++++++++++++++++------
 2 files changed, 18 insertions(+), 8 deletions(-)

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0353e9a902a8..cc6f72c86f3d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2609,8 +2609,6 @@  extern bool arch_has_descending_max_zone_pfns(void);
 /* nommu.c */
 extern atomic_long_t mmap_pages_allocated;
 extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t);
-/* mmap.c */
-void vma_store(struct mm_struct *mm, struct vm_area_struct *vma);
 
 /* interval_tree.c */
 void vma_interval_tree_insert(struct vm_area_struct *node,
diff --git a/kernel/fork.c b/kernel/fork.c
index 51a7971651ef..d7e2e581bdfd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -494,7 +494,9 @@  static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
 	struct rb_node **rb_link, *rb_parent;
 	int retval;
-	unsigned long charge;
+	unsigned long charge = 0;
+	MA_STATE(old_mas, &oldmm->mm_mt, 0, 0);
+	MA_STATE(mas, &mm->mm_mt, 0, 0);
 	LIST_HEAD(uf);
 
 	uprobe_start_dup_mmap();
@@ -528,7 +530,12 @@  static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		goto out;
 
 	prev = NULL;
-	for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
+
+	retval = mas_expected_entries(&mas, oldmm->map_count);
+	if (retval)
+		goto out;
+
+	mas_for_each(&old_mas, mpnt, ULONG_MAX) {
 		struct file *file;
 
 		if (mpnt->vm_flags & VM_DONTCOPY) {
@@ -542,7 +549,7 @@  static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		 */
 		if (fatal_signal_pending(current)) {
 			retval = -EINTR;
-			goto out;
+			goto loop_out;
 		}
 		if (mpnt->vm_flags & VM_ACCOUNT) {
 			unsigned long len = vma_pages(mpnt);
@@ -608,7 +615,9 @@  static __latent_entropy int dup_mmap(struct mm_struct *mm,
 		rb_parent = &tmp->vm_rb;
 
 		/* Link the vma into the MT */
-		vma_store(mm, tmp);
+		mas.index = tmp->vm_start;
+		mas.last = tmp->vm_end - 1;
+		mas_store(&mas, tmp);
 
 		mm->map_count++;
 		if (!(tmp->vm_flags & VM_WIPEONFORK))
@@ -618,10 +627,13 @@  static __latent_entropy int dup_mmap(struct mm_struct *mm,
 			tmp->vm_ops->open(tmp);
 
 		if (retval)
-			goto out;
+			goto loop_out;
+
 	}
 	/* a new mm has just been created */
 	retval = arch_dup_mmap(oldmm, mm);
+loop_out:
+	mas_destroy(&mas);
 out:
 	mmap_write_unlock(mm);
 	flush_tlb_mm(oldmm);
@@ -637,7 +649,7 @@  static __latent_entropy int dup_mmap(struct mm_struct *mm,
 fail_nomem:
 	retval = -ENOMEM;
 	vm_unacct_memory(charge);
-	goto out;
+	goto loop_out;
 }
 
 static inline int mm_alloc_pgd(struct mm_struct *mm)