linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Suren Baghdasaryan <surenb@google.com>
To: akpm@linux-foundation.org
Cc: Liam.Howlett@oracle.com, lorenzo.stoakes@oracle.com,
	david@redhat.com,  vbabka@suse.cz, peterx@redhat.com,
	jannh@google.com, hannes@cmpxchg.org,  mhocko@kernel.org,
	paulmck@kernel.org, shuah@kernel.org, adobriyan@gmail.com,
	 brauner@kernel.org, josef@toxicpanda.com, yebin10@huawei.com,
	 linux@weissschuh.net, willy@infradead.org, osalvador@suse.de,
	 andrii@kernel.org, ryan.roberts@arm.com,
	christophe.leroy@csgroup.eu,  tjmercier@google.com,
	kaleshsingh@google.com, linux-kernel@vger.kernel.org,
	 linux-fsdevel@vger.kernel.org, linux-mm@kvack.org,
	 linux-kselftest@vger.kernel.org, surenb@google.com
Subject: [PATCH v4 7/7] mm/maps: execute PROCMAP_QUERY ioctl under per-vma locks
Date: Wed,  4 Jun 2025 16:11:51 -0700	[thread overview]
Message-ID: <20250604231151.799834-8-surenb@google.com> (raw)
In-Reply-To: <20250604231151.799834-1-surenb@google.com>

Utilize per-vma locks to stabilize vma after lookup without taking
mmap_lock during PROCMAP_QUERY ioctl execution. While we might take
mmap_lock for reading during contention, we do that momentarily only
to lock the vma.
This change is designed to reduce mmap_lock contention and prevent
PROCMAP_QUERY ioctl calls from blocking address space updates.

Signed-off-by: Suren Baghdasaryan <surenb@google.com>
---
 fs/proc/task_mmu.c | 56 ++++++++++++++++++++++++++++++++++++----------
 1 file changed, 44 insertions(+), 12 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 36d883c4f394..93ba35a84975 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -550,28 +550,60 @@ static int pid_maps_open(struct inode *inode, struct file *file)
 		PROCMAP_QUERY_VMA_FLAGS				\
 )
 
-static int query_vma_setup(struct mm_struct *mm)
+#ifdef CONFIG_PER_VMA_LOCK
+
+static int query_vma_setup(struct proc_maps_private *priv)
 {
-	return mmap_read_lock_killable(mm);
+	rcu_read_lock();
+	priv->locked_vma = NULL;
+	priv->mmap_locked = false;
+
+	return 0;
 }
 
-static void query_vma_teardown(struct mm_struct *mm, struct vm_area_struct *vma)
+static void query_vma_teardown(struct proc_maps_private *priv)
 {
-	mmap_read_unlock(mm);
+	unlock_vma(priv);
+	rcu_read_unlock();
+}
+
+static struct vm_area_struct *query_vma_find_by_addr(struct proc_maps_private *priv,
+						     unsigned long addr)
+{
+	vma_iter_init(&priv->iter, priv->mm, addr);
+	return get_next_vma(priv, addr);
+}
+
+#else /* CONFIG_PER_VMA_LOCK */
+
+static int query_vma_setup(struct proc_maps_private *priv)
+{
+	return mmap_read_lock_killable(priv->mm);
+}
+
+static void query_vma_teardown(struct proc_maps_private *priv)
+{
+	mmap_read_unlock(priv->mm);
 }
 
-static struct vm_area_struct *query_vma_find_by_addr(struct mm_struct *mm, unsigned long addr)
+static struct vm_area_struct *query_vma_find_by_addr(struct proc_maps_private *priv,
+						     unsigned long addr)
 {
-	return find_vma(mm, addr);
+	return find_vma(priv->mm, addr);
 }
 
-static struct vm_area_struct *query_matching_vma(struct mm_struct *mm,
+#endif  /* CONFIG_PER_VMA_LOCK */
+
+static struct vm_area_struct *query_matching_vma(struct proc_maps_private *priv,
 						 unsigned long addr, u32 flags)
 {
 	struct vm_area_struct *vma;
 
 next_vma:
-	vma = query_vma_find_by_addr(mm, addr);
+	vma = query_vma_find_by_addr(priv, addr);
+	if (IS_ERR(vma))
+		return vma;
+
 	if (!vma)
 		goto no_vma;
 
@@ -647,13 +679,13 @@ static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg)
 	if (!mm || !mmget_not_zero(mm))
 		return -ESRCH;
 
-	err = query_vma_setup(mm);
+	err = query_vma_setup(priv);
 	if (err) {
 		mmput(mm);
 		return err;
 	}
 
-	vma = query_matching_vma(mm, karg.query_addr, karg.query_flags);
+	vma = query_matching_vma(priv, karg.query_addr, karg.query_flags);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		vma = NULL;
@@ -738,7 +770,7 @@ static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg)
 	}
 
 	/* unlock vma or mmap_lock, and put mm_struct before copying data to user */
-	query_vma_teardown(mm, vma);
+	query_vma_teardown(priv);
 	mmput(mm);
 
 	if (karg.vma_name_size && copy_to_user(u64_to_user_ptr(karg.vma_name_addr),
@@ -758,7 +790,7 @@ static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg)
 	return 0;
 
 out:
-	query_vma_teardown(mm, vma);
+	query_vma_teardown(priv);
 	mmput(mm);
 	kfree(name_buf);
 	return err;
-- 
2.49.0.1266.g31b7d2e469-goog



  parent reply	other threads:[~2025-06-04 23:12 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-04 23:11 [PATCH v4 0/7] use per-vma locks for /proc/pid/maps reads and PROCMAP_QUERY Suren Baghdasaryan
2025-06-04 23:11 ` [PATCH v4 1/7] selftests/proc: add /proc/pid/maps tearing from vma split test Suren Baghdasaryan
2025-06-04 23:11 ` [PATCH v4 2/7] selftests/proc: extend /proc/pid/maps tearing test to include vma resizing Suren Baghdasaryan
2025-06-04 23:11 ` [PATCH v4 3/7] selftests/proc: extend /proc/pid/maps tearing test to include vma remapping Suren Baghdasaryan
2025-06-04 23:11 ` [PATCH v4 4/7] selftests/proc: test PROCMAP_QUERY ioctl while vma is concurrently modified Suren Baghdasaryan
2025-06-04 23:11 ` [PATCH v4 5/7] selftests/proc: add verbose more for tests to facilitate debugging Suren Baghdasaryan
2025-06-04 23:11 ` [PATCH v4 6/7] mm/maps: read proc/pid/maps under per-vma lock Suren Baghdasaryan
2025-06-07 17:43   ` Lorenzo Stoakes
2025-06-08  1:41     ` Suren Baghdasaryan
2025-06-10 17:43       ` Lorenzo Stoakes
2025-06-11  0:16         ` Suren Baghdasaryan
2025-06-11 10:24           ` Lorenzo Stoakes
2025-06-11 15:12             ` Suren Baghdasaryan
2025-06-10  7:50   ` kernel test robot
2025-06-10 14:02     ` Suren Baghdasaryan
2025-06-04 23:11 ` Suren Baghdasaryan [this message]
2025-06-13 20:36   ` [PATCH v4 7/7] mm/maps: execute PROCMAP_QUERY ioctl under per-vma locks Andrii Nakryiko
2025-06-13 15:01 ` [PATCH v4 0/7] use per-vma locks for /proc/pid/maps reads and PROCMAP_QUERY Lorenzo Stoakes
2025-06-13 19:11   ` Suren Baghdasaryan
2025-06-13 19:26     ` 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=20250604231151.799834-8-surenb@google.com \
    --to=surenb@google.com \
    --cc=Liam.Howlett@oracle.com \
    --cc=adobriyan@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=andrii@kernel.org \
    --cc=brauner@kernel.org \
    --cc=christophe.leroy@csgroup.eu \
    --cc=david@redhat.com \
    --cc=hannes@cmpxchg.org \
    --cc=jannh@google.com \
    --cc=josef@toxicpanda.com \
    --cc=kaleshsingh@google.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux@weissschuh.net \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=mhocko@kernel.org \
    --cc=osalvador@suse.de \
    --cc=paulmck@kernel.org \
    --cc=peterx@redhat.com \
    --cc=ryan.roberts@arm.com \
    --cc=shuah@kernel.org \
    --cc=tjmercier@google.com \
    --cc=vbabka@suse.cz \
    --cc=willy@infradead.org \
    --cc=yebin10@huawei.com \
    /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;
as well as URLs for NNTP newsgroup(s).