linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@linux-foundation.org>
To: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Suren Baghdasaryan <surenb@google.com>,
	"Liam R . Howlett" <Liam.Howlett@oracle.com>,
	Vlastimil Babka <vbabka@suse.cz>,
	Shakeel Butt <shakeel.butt@linux.dev>,
	David Hildenbrand <david@kernel.org>,
	Rik van Riel <riel@surriel.com>, Harry Yoo <harry.yoo@oracle.com>,
	Jann Horn <jannh@google.com>, Mike Rapoport <rppt@kernel.org>,
	Michal Hocko <mhocko@suse.com>, Pedro Falcato <pfalcato@suse.de>,
	Chris Li <chriscli@google.com>,
	Barry Song <v-songbaohua@oppo.com>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 1/8] mm/rmap: improve anon_vma_clone(), unlink_anon_vmas() comments, add asserts
Date: Wed, 14 Jan 2026 13:59:11 -0800	[thread overview]
Message-ID: <20260114135911.ed54bc17bf1e467ad96f5b4f@linux-foundation.org> (raw)
In-Reply-To: <6fb9d6b4-ad39-41de-8db0-aa41a6406378@lucifer.local>

On Wed, 14 Jan 2026 19:02:20 +0000 Lorenzo Stoakes <lorenzo.stoakes@oracle.com> wrote:

> Can you apply the below fix-patch to this to fix up a rather silly
> failure-to-unlock mistake that Suren picked up on?
> 
> Luckily this partial unmap function is unlikely to ever be triggerable in real
> life, AND more to the point - a later patch completely eliminates the locking -
> but to avoid bisection hazard let's fix this.
> 
> Note that there is a conflict at 'mm/rmap: allocate anon_vma_chain objects
> unlocked when possible', please resolve it by just taking that patch and
> dropping _everything_ from this one _including_ the trailing 'if (root) ...'
> code.

No probs. 
mm-rmap-allocate-anon_vma_chain-objects-unlocked-when-possible.patch is
now

--- a/mm/rmap.c~mm-rmap-allocate-anon_vma_chain-objects-unlocked-when-possible
+++ a/mm/rmap.c
@@ -147,14 +147,13 @@ static void anon_vma_chain_free(struct a
 	kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain);
 }
 
-static void anon_vma_chain_link(struct vm_area_struct *vma,
-				struct anon_vma_chain *avc,
-				struct anon_vma *anon_vma)
+static void anon_vma_chain_assign(struct vm_area_struct *vma,
+				  struct anon_vma_chain *avc,
+				  struct anon_vma *anon_vma)
 {
 	avc->vma = vma;
 	avc->anon_vma = anon_vma;
 	list_add(&avc->same_vma, &vma->anon_vma_chain);
-	anon_vma_interval_tree_insert(avc, &anon_vma->rb_root);
 }
 
 /**
@@ -211,7 +210,8 @@ int __anon_vma_prepare(struct vm_area_st
 	spin_lock(&mm->page_table_lock);
 	if (likely(!vma->anon_vma)) {
 		vma->anon_vma = anon_vma;
-		anon_vma_chain_link(vma, avc, anon_vma);
+		anon_vma_chain_assign(vma, avc, anon_vma);
+		anon_vma_interval_tree_insert(avc, &anon_vma->rb_root);
 		anon_vma->num_active_vmas++;
 		allocated = NULL;
 		avc = NULL;
@@ -292,21 +292,31 @@ int anon_vma_clone(struct vm_area_struct
 
 	check_anon_vma_clone(dst, src);
 
-	/* All anon_vma's share the same root. */
+	/*
+	 * Allocate AVCs. We don't need an anon_vma lock for this as we
+	 * are not updating the anon_vma rbtree nor are we changing
+	 * anon_vma statistics.
+	 *
+	 * We hold the exclusive mmap write lock so there's no possibliity of
+	 * the unlinked AVC's being observed yet.
+	 */
+	list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) {
+		avc = anon_vma_chain_alloc(GFP_KERNEL);
+		if (!avc)
+			goto enomem_failure;
+
+		anon_vma_chain_assign(dst, avc, pavc->anon_vma);
+	}
+
+	/*
+	 * Now link the anon_vma's back to the newly inserted AVCs.
+	 * Note that all anon_vma's share the same root.
+	 */
 	anon_vma_lock_write(src->anon_vma);
-	list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
-		struct anon_vma *anon_vma;
+	list_for_each_entry_reverse(avc, &dst->anon_vma_chain, same_vma) {
+		struct anon_vma *anon_vma = avc->anon_vma;
 
-		avc = anon_vma_chain_alloc(GFP_NOWAIT);
-		if (unlikely(!avc)) {
-			anon_vma_unlock_write(src->anon_vma);
-			avc = anon_vma_chain_alloc(GFP_KERNEL);
-			if (!avc)
-				goto enomem_failure;
-			anon_vma_lock_write(src->anon_vma);
-		}
-		anon_vma = pavc->anon_vma;
-		anon_vma_chain_link(dst, avc, anon_vma);
+		anon_vma_interval_tree_insert(avc, &anon_vma->rb_root);
 
 		/*
 		 * Reuse existing anon_vma if it has no vma and only one
@@ -322,7 +332,6 @@ int anon_vma_clone(struct vm_area_struct
 	}
 	if (dst->anon_vma)
 		dst->anon_vma->num_active_vmas++;
-
 	anon_vma_unlock_write(src->anon_vma);
 	return 0;
 
@@ -384,8 +393,10 @@ int anon_vma_fork(struct vm_area_struct
 	get_anon_vma(anon_vma->root);
 	/* Mark this anon_vma as the one where our new (COWed) pages go. */
 	vma->anon_vma = anon_vma;
+	anon_vma_chain_assign(vma, avc, anon_vma);
+	/* Now let rmap see it. */
 	anon_vma_lock_write(anon_vma);
-	anon_vma_chain_link(vma, avc, anon_vma);
+	anon_vma_interval_tree_insert(avc, &anon_vma->rb_root);
 	anon_vma->parent->num_children++;
 	anon_vma_unlock_write(anon_vma);
 
@@ -402,40 +413,18 @@ int anon_vma_fork(struct vm_area_struct
  * In the unfortunate case of anon_vma_clone() failing to allocate memory we
  * have to clean things up.
  *
- * On clone we hold the exclusive mmap write lock, so we can't race
- * unlink_anon_vmas(). Since we're cloning, we know we can't have empty
- * anon_vma's, since existing anon_vma's are what we're cloning from.
- *
- * So this function needs only traverse the anon_vma_chain and free each
- * allocated anon_vma_chain.
+ * Since we allocate anon_vma_chain's before we insert them into the interval
+ * trees, we simply have to free up the AVC's and remove the entries from the
+ * VMA's anon_vma_chain.
  */
 static void cleanup_partial_anon_vmas(struct vm_area_struct *vma)
 {
 	struct anon_vma_chain *avc, *next;
-	struct anon_vma *root = NULL;
-
-	/*
-	 * We exclude everybody else from being able to modify anon_vma's
-	 * underneath us.
-	 */
-	mmap_assert_locked(vma->vm_mm);
 
 	list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
-		struct anon_vma *anon_vma = avc->anon_vma;
-
-		/* All anon_vma's share the same root. */
-		if (!root) {
-			root = anon_vma->root;
-			anon_vma_lock_write(root);
-		}
-
-		anon_vma_interval_tree_remove(avc, &anon_vma->rb_root);
 		list_del(&avc->same_vma);
 		anon_vma_chain_free(avc);
 	}
-
-	if (root)
-		anon_vma_unlock_write(root);
 }
 
 /**
_



  reply	other threads:[~2026-01-14 21:59 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-06 15:04 [PATCH v2 0/8] mm: clean up anon_vma implementation Lorenzo Stoakes
2026-01-06 15:04 ` [PATCH v2 1/8] mm/rmap: improve anon_vma_clone(), unlink_anon_vmas() comments, add asserts Lorenzo Stoakes
2026-01-14 16:14   ` Suren Baghdasaryan
2026-01-14 18:33     ` Lorenzo Stoakes
2026-01-14 18:48       ` Lorenzo Stoakes
2026-01-14 19:02   ` Lorenzo Stoakes
2026-01-14 21:59     ` Andrew Morton [this message]
2026-01-06 15:04 ` [PATCH v2 2/8] mm/rmap: skip unfaulted VMAs on anon_vma clone, unlink Lorenzo Stoakes
2026-01-06 18:34   ` Liam R. Howlett
2026-01-14 16:47     ` Suren Baghdasaryan
2026-01-06 15:04 ` [PATCH v2 3/8] mm/rmap: remove unnecessary root lock dance in anon_vma clone, unmap Lorenzo Stoakes
2026-01-06 18:42   ` Liam R. Howlett
2026-01-14 16:55   ` Suren Baghdasaryan
2026-01-14 17:54     ` Lorenzo Stoakes
2026-01-14 18:01       ` Suren Baghdasaryan
2026-01-14 22:12       ` Andrew Morton
2026-01-06 15:04 ` [PATCH v2 4/8] mm/rmap: remove anon_vma_merge() function Lorenzo Stoakes
2026-01-06 18:42   ` Liam R. Howlett
2026-01-06 15:04 ` [PATCH v2 5/8] mm/rmap: make anon_vma functions internal Lorenzo Stoakes
2026-01-06 18:54   ` Liam R. Howlett
2026-01-06 15:04 ` [PATCH v2 6/8] mm/mmap_lock: add vma_is_attached() helper Lorenzo Stoakes
2026-01-06 18:56   ` Liam R. Howlett
2026-01-06 15:04 ` [PATCH v2 7/8] mm/rmap: allocate anon_vma_chain objects unlocked when possible Lorenzo Stoakes
2026-01-06 19:02   ` Liam R. Howlett
2026-01-08 18:51   ` Lorenzo Stoakes
2026-01-06 15:04 ` [PATCH v2 8/8] mm/rmap: separate out fork-only logic on anon_vma_clone() Lorenzo Stoakes
2026-01-06 19:27   ` Liam R. Howlett
2026-01-08 17:58     ` Lorenzo Stoakes
2026-01-14 17:26     ` Suren Baghdasaryan
2026-01-08 18:52   ` Lorenzo Stoakes

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260114135911.ed54bc17bf1e467ad96f5b4f@linux-foundation.org \
    --to=akpm@linux-foundation.org \
    --cc=Liam.Howlett@oracle.com \
    --cc=chriscli@google.com \
    --cc=david@kernel.org \
    --cc=harry.yoo@oracle.com \
    --cc=jannh@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=mhocko@suse.com \
    --cc=pfalcato@suse.de \
    --cc=riel@surriel.com \
    --cc=rppt@kernel.org \
    --cc=shakeel.butt@linux.dev \
    --cc=surenb@google.com \
    --cc=v-songbaohua@oppo.com \
    --cc=vbabka@suse.cz \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox