From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
To: Andrew Morton <akpm@linux-foundation.org>
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: [PATCH v2 3/8] mm/rmap: remove unnecessary root lock dance in anon_vma clone, unmap
Date: Tue, 6 Jan 2026 15:04:28 +0000 [thread overview]
Message-ID: <9b5a438237e4ea3b19a986a4f8fddb8848cba54a.1767711638.git.lorenzo.stoakes@oracle.com> (raw)
In-Reply-To: <cover.1767711638.git.lorenzo.stoakes@oracle.com>
The root anon_vma of all anon_vma's linked to a VMA must by definition be
the same - a VMA and all of its descendants/ancestors must exist in the
same CoW chain.
Commit bb4aa39676f7 ("mm: avoid repeated anon_vma lock/unlock sequences in
anon_vma_clone()") introduced paranoid checking of the root anon_vma
remaining the same throughout all AVC's in 2011.
I think 15 years later we can safely assume that this is always the case.
Additionally, since unfaulted VMAs being cloned from or unlinked are
no-op's, we can simply lock the anon_vma's associated with this rather than
doing any specific dance around this.
This removes unnecessary checks and makes it clear that the root anon_vma
is shared between all anon_vma's in a given VMA's anon_vma_chain.
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
---
mm/rmap.c | 51 +++++++++++++++------------------------------------
1 file changed, 15 insertions(+), 36 deletions(-)
diff --git a/mm/rmap.c b/mm/rmap.c
index de2cbe860566..6ac42671bedd 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -232,32 +232,6 @@ int __anon_vma_prepare(struct vm_area_struct *vma)
return -ENOMEM;
}
-/*
- * This is a useful helper function for locking the anon_vma root as
- * we traverse the vma->anon_vma_chain, looping over anon_vma's that
- * have the same vma.
- *
- * Such anon_vma's should have the same root, so you'd expect to see
- * just a single mutex_lock for the whole traversal.
- */
-static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma)
-{
- struct anon_vma *new_root = anon_vma->root;
- if (new_root != root) {
- if (WARN_ON_ONCE(root))
- up_write(&root->rwsem);
- root = new_root;
- down_write(&root->rwsem);
- }
- return root;
-}
-
-static inline void unlock_anon_vma_root(struct anon_vma *root)
-{
- if (root)
- up_write(&root->rwsem);
-}
-
static void check_anon_vma_clone(struct vm_area_struct *dst,
struct vm_area_struct *src)
{
@@ -310,26 +284,28 @@ static void cleanup_partial_anon_vmas(struct vm_area_struct *vma);
int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
{
struct anon_vma_chain *avc, *pavc;
- struct anon_vma *root = NULL;
check_anon_vma_clone(dst, src);
if (!src->anon_vma)
return 0;
+ check_anon_vma_clone(dst, src);
+
+ /* 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;
avc = anon_vma_chain_alloc(GFP_NOWAIT);
if (unlikely(!avc)) {
- unlock_anon_vma_root(root);
- root = NULL;
+ 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;
- root = lock_anon_vma_root(root, anon_vma);
anon_vma_chain_link(dst, avc, anon_vma);
/*
@@ -346,7 +322,8 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
}
if (dst->anon_vma)
dst->anon_vma->num_active_vmas++;
- unlock_anon_vma_root(root);
+
+ anon_vma_unlock_write(src->anon_vma);
return 0;
enomem_failure:
@@ -471,17 +448,19 @@ static void cleanup_partial_anon_vmas(struct vm_area_struct *vma)
void unlink_anon_vmas(struct vm_area_struct *vma)
{
struct anon_vma_chain *avc, *next;
- struct anon_vma *root = NULL;
+ struct anon_vma *active_anon_vma = vma->anon_vma;
/* Always hold mmap lock, read-lock on unmap possibly. */
mmap_assert_locked(vma->vm_mm);
/* Unfaulted is a no-op. */
- if (!vma->anon_vma) {
+ if (!active_anon_vma) {
VM_WARN_ON_ONCE(!list_empty(&vma->anon_vma_chain));
return;
}
+ anon_vma_lock_write(active_anon_vma);
+
/*
* Unlink each anon_vma chained to the VMA. This list is ordered
* from newest to oldest, ensuring the root anon_vma gets freed last.
@@ -489,7 +468,6 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
struct anon_vma *anon_vma = avc->anon_vma;
- root = lock_anon_vma_root(root, anon_vma);
anon_vma_interval_tree_remove(avc, &anon_vma->rb_root);
/*
@@ -505,13 +483,14 @@ void unlink_anon_vmas(struct vm_area_struct *vma)
anon_vma_chain_free(avc);
}
- vma->anon_vma->num_active_vmas--;
+ active_anon_vma->num_active_vmas--;
/*
* vma would still be needed after unlink, and anon_vma will be prepared
* when handle fault.
*/
vma->anon_vma = NULL;
- unlock_anon_vma_root(root);
+ anon_vma_unlock_write(active_anon_vma);
+
/*
* Iterate the list once more, it now only contains empty and unlinked
--
2.52.0
next prev parent reply other threads:[~2026-01-06 15:05 UTC|newest]
Thread overview: 19+ 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
2026-01-06 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
2026-01-06 15:04 ` Lorenzo Stoakes [this message]
2026-01-06 18:42 ` [PATCH v2 3/8] mm/rmap: remove unnecessary root lock dance in anon_vma clone, unmap Liam R. Howlett
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
2026-01-08 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=9b5a438237e4ea3b19a986a4f8fddb8848cba54a.1767711638.git.lorenzo.stoakes@oracle.com \
--to=lorenzo.stoakes@oracle.com \
--cc=Liam.Howlett@oracle.com \
--cc=akpm@linux-foundation.org \
--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=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