[PATCH 11/28] kernel/fork: Convert dup_mmap to use maple tree

From: "Liam R. Howlett" <Liam.Howlett@Oracle.com>
To: maple-tree@lists.infradead.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Cc: Andrew Morton <akpm@google.com>, Song Liu <songliubraving@fb.com>,
	Davidlohr Bueso <dave@stgolabs.net>,
	"Paul E . McKenney" <paulmck@kernel.org>,
	Matthew Wilcox <willy@infradead.org>,
	Jerome Glisse <jglisse@redhat.com>,
	David Rientjes <rientjes@google.com>,
	Axel Rasmussen <axelrasmussen@google.com>,
	Suren Baghdasaryan <surenb@google.com>,
	Vlastimil Babka <vbabka@suse.cz>
Subject: [PATCH 11/28] kernel/fork: Convert dup_mmap to use maple tree
Date: Thu, 10 Dec 2020 12:03:45 -0500	[thread overview]
Message-ID: <20201210170402.3468568-12-Liam.Howlett@Oracle.com> (raw)
In-Reply-To: <20201210170402.3468568-1-Liam.Howlett@Oracle.com>

Use the maple tree iterator to duplicate the mm_struct trees.

Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
---
 include/linux/sched/mm.h |  3 +++
 kernel/fork.c            | 22 +++++++++++++++++-----
 2 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index d5ece7a9a403f..919e2e44b764e 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -8,6 +8,7 @@
 #include <linux/mm_types.h>
 #include <linux/gfp.h>
 #include <linux/sync_core.h>
+#include <linux/maple_tree.h>
 
 /*
  * Routines for handling mm_structs
@@ -67,11 +68,13 @@ static inline void mmdrop(struct mm_struct *mm)
  */
 static inline void mmget(struct mm_struct *mm)
 {
+	mt_set_in_rcu(&mm->mm_mt);
 	atomic_inc(&mm->mm_users);
 }
 
 static inline bool mmget_not_zero(struct mm_struct *mm)
 {
+	mt_set_in_rcu(&mm->mm_mt);
 	return atomic_inc_not_zero(&mm->mm_users);
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 23e166d037980..62eba2679216b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -472,7 +472,9 @@ 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();
@@ -506,7 +508,12 @@ 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_entry_count(&mas, oldmm->map_count);
+	if (retval)
+		goto fail_nomem;
+
+	mas_for_each(&old_mas, mpnt, ULONG_MAX) {
 		struct file *file;
 
 		if (mpnt->vm_flags & VM_DONTCOPY) {
@@ -520,7 +527,7 @@ 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);
@@ -589,7 +596,9 @@ 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))
@@ -599,14 +608,16 @@ 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:
 out:
 	mmap_write_unlock(mm);
 	flush_tlb_mm(oldmm);
 	mmap_write_unlock(oldmm);
+	mas_destroy(&mas);
 	dup_userfaultfd_complete(&uf);
 fail_uprobe_end:
 	uprobe_end_dup_mmap();
@@ -1076,6 +1087,7 @@ static inline void __mmput(struct mm_struct *mm)
 {
 	VM_BUG_ON(atomic_read(&mm->mm_users));
 
+	mt_clear_in_rcu(&mm->mm_mt);
 	uprobe_clear_state(mm);
 	exit_aio(mm);
 	ksm_exit(mm);
-- 
2.28.0

