linux-kernel - [RFC 1/3] mm: make vm_area_struct anon

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240115183837.205694-2-surenb@google.com>
Date: Mon, 15 Jan 2024 10:38:34 -0800
From: Suren Baghdasaryan <surenb@...gle.com>
To: akpm@...ux-foundation.org
Cc: viro@...iv.linux.org.uk, brauner@...nel.org, jack@...e.cz, 
	dchinner@...hat.com, casey@...aufler-ca.com, ben.wolsieffer@...ring.com, 
	paulmck@...nel.org, david@...hat.com, avagin@...gle.com, 
	usama.anjum@...labora.com, peterx@...hat.com, hughd@...gle.com, 
	ryan.roberts@....com, wangkefeng.wang@...wei.com, Liam.Howlett@...cle.com, 
	yuzhao@...gle.com, axelrasmussen@...gle.com, lstoakes@...il.com, 
	talumbau@...gle.com, willy@...radead.org, vbabka@...e.cz, 
	mgorman@...hsingularity.net, jhubbard@...dia.com, vishal.moola@...il.com, 
	mathieu.desnoyers@...icios.com, dhowells@...hat.com, jgg@...pe.ca, 
	sidhartha.kumar@...cle.com, andriy.shevchenko@...ux.intel.com, 
	yangxingui@...wei.com, keescook@...omium.org, linux-kernel@...r.kernel.org, 
	linux-fsdevel@...r.kernel.org, linux-mm@...ck.org, kernel-team@...roid.com, 
	surenb@...gle.com
Subject: [RFC 1/3] mm: make vm_area_struct anon_name field RCU-safe

For lockless /proc/pid/maps reading we have to ensure all the fields
used when generating the output are RCU-safe. The only pointer fields
in vm_area_struct which are used to generate that file's output are
vm_file and anon_name. vm_file is RCU-safe but anon_name is not. Make
anon_name RCU-safe as well.

Signed-off-by: Suren Baghdasaryan <surenb@...gle.com>
---
 include/linux/mm_inline.h | 10 +++++++++-
 include/linux/mm_types.h  |  3 ++-
 mm/madvise.c              | 30 ++++++++++++++++++++++++++----
 3 files changed, 37 insertions(+), 6 deletions(-)

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index f4fe593c1400..bbdb0ca857f1 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -389,7 +389,7 @@ static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma,
 	struct anon_vma_name *anon_name = anon_vma_name(orig_vma);
 
 	if (anon_name)
-		new_vma->anon_name = anon_vma_name_reuse(anon_name);
+		rcu_assign_pointer(new_vma->anon_name, anon_vma_name_reuse(anon_name));
 }
 
 static inline void free_anon_vma_name(struct vm_area_struct *vma)
@@ -411,6 +411,8 @@ static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,
 		!strcmp(anon_name1->name, anon_name2->name);
 }
 
+struct anon_vma_name *anon_vma_name_get_rcu(struct vm_area_struct *vma);
+
 #else /* CONFIG_ANON_VMA_NAME */
 static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {}
 static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {}
@@ -424,6 +426,12 @@ static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,
 	return true;
 }
 
+static inline
+struct anon_vma_name *anon_vma_name_get_rcu(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+
 #endif  /* CONFIG_ANON_VMA_NAME */
 
 static inline void init_tlb_flush_pending(struct mm_struct *mm)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index b2d3a88a34d1..1f0a30c00795 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -545,6 +545,7 @@ struct vm_userfaultfd_ctx {};
 
 struct anon_vma_name {
 	struct kref kref;
+	struct rcu_head rcu;
 	/* The name needs to be at the end because it is dynamically sized. */
 	char name[];
 };
@@ -699,7 +700,7 @@ struct vm_area_struct {
 	 * terminated string containing the name given to the vma, or NULL if
 	 * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
 	 */
-	struct anon_vma_name *anon_name;
+	struct anon_vma_name __rcu *anon_name;
 #endif
 #ifdef CONFIG_SWAP
 	atomic_long_t swap_readahead_info;
diff --git a/mm/madvise.c b/mm/madvise.c
index 912155a94ed5..0f222d464254 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -88,14 +88,15 @@ void anon_vma_name_free(struct kref *kref)
 {
 	struct anon_vma_name *anon_name =
 			container_of(kref, struct anon_vma_name, kref);
-	kfree(anon_name);
+	kfree_rcu(anon_name, rcu);
 }
 
 struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma)
 {
 	mmap_assert_locked(vma->vm_mm);
 
-	return vma->anon_name;
+	return rcu_dereference_protected(vma->anon_name,
+		rwsem_is_locked(&vma->vm_mm->mmap_lock));
 }
 
 /* mmap_lock should be write-locked */
@@ -105,7 +106,7 @@ static int replace_anon_vma_name(struct vm_area_struct *vma,
 	struct anon_vma_name *orig_name = anon_vma_name(vma);
 
 	if (!anon_name) {
-		vma->anon_name = NULL;
+		rcu_assign_pointer(vma->anon_name, NULL);
 		anon_vma_name_put(orig_name);
 		return 0;
 	}
@@ -113,11 +114,32 @@ static int replace_anon_vma_name(struct vm_area_struct *vma,
 	if (anon_vma_name_eq(orig_name, anon_name))
 		return 0;
 
-	vma->anon_name = anon_vma_name_reuse(anon_name);
+	rcu_assign_pointer(vma->anon_name, anon_vma_name_reuse(anon_name));
 	anon_vma_name_put(orig_name);
 
 	return 0;
 }
+
+/*
+ * Returned anon_vma_name is stable due to elevated refcount but not guaranteed
+ * to be assigned to the original VMA after the call.
+ */
+struct anon_vma_name *anon_vma_name_get_rcu(struct vm_area_struct *vma)
+{
+	struct anon_vma_name __rcu *anon_name;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	anon_name = rcu_dereference(vma->anon_name);
+	if (!anon_name)
+		return NULL;
+
+	if (unlikely(!kref_get_unless_zero(&anon_name->kref)))
+		return NULL;
+
+	return anon_name;
+}
+
 #else /* CONFIG_ANON_VMA_NAME */
 static int replace_anon_vma_name(struct vm_area_struct *vma,
 				 struct anon_vma_name *anon_name)
-- 
2.43.0.381.gb435a96ce8-goog