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: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20241216192419.2970941-14-surenb@google.com>
Date: Mon, 16 Dec 2024 11:24:16 -0800
From: Suren Baghdasaryan <surenb@...gle.com>
To: akpm@...ux-foundation.org
Cc: peterz@...radead.org, willy@...radead.org, liam.howlett@...cle.com, 
	lorenzo.stoakes@...cle.com, mhocko@...e.com, vbabka@...e.cz, 
	hannes@...xchg.org, mjguzik@...il.com, oliver.sang@...el.com, 
	mgorman@...hsingularity.net, david@...hat.com, peterx@...hat.com, 
	oleg@...hat.com, dave@...olabs.net, paulmck@...nel.org, brauner@...nel.org, 
	dhowells@...hat.com, hdanton@...a.com, hughd@...gle.com, 
	lokeshgidra@...gle.com, minchan@...gle.com, jannh@...gle.com, 
	shakeel.butt@...ux.dev, souravpanda@...gle.com, pasha.tatashin@...een.com, 
	klarasmodin@...il.com, corbet@....net, linux-doc@...r.kernel.org, 
	linux-mm@...ck.org, linux-kernel@...r.kernel.org, kernel-team@...roid.com, 
	surenb@...gle.com
Subject: [PATCH v6 13/16] mm: introduce vma_ensure_detached()

vma_start_read() can temporarily raise vm_refcnt of a write-locked and
detached vma:

// vm_refcnt==1 (attached)
vma_start_write()
    vma->vm_lock_seq = mm->mm_lock_seq

                    vma_start_read()
                       vm_refcnt++; // vm_refcnt==2

vma_mark_detached()
    vm_refcnt--; // vm_refcnt==1

// vma is detached but vm_refcnt!=0 temporarily

                       if (vma->vm_lock_seq == mm->mm_lock_seq)
                           vma_refcount_put()
                               vm_refcnt--; // vm_refcnt==0

This is currently not a problem when freeing the vma because RCU grace
period should pass before kmem_cache_free(vma) gets called and by that
time vma_start_read() should be done and vm_refcnt is 0. However once
we introduce possibility of vma reuse before RCU grace period is over,
this will become a problem (reused vma might be in non-detached state).
Introduce vma_ensure_detached() for the writer to wait for readers until
they exit vma_start_read().

Signed-off-by: Suren Baghdasaryan <surenb@...gle.com>
---
 include/linux/mm.h               |  9 ++++++
 mm/memory.c                      | 55 +++++++++++++++++++++++---------
 tools/testing/vma/vma_internal.h |  8 +++++
 3 files changed, 57 insertions(+), 15 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index b73cf64233a4..361f26dedab1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -863,6 +863,15 @@ static inline bool is_vma_detached(struct vm_area_struct *vma)
 	return refcount_read(&vma->vm_refcnt) == VMA_STATE_DETACHED;
 }
 
+/*
+ * WARNING: to avoid racing with vma_mark_attached(), should be called either
+ * under mmap_write_lock or when the object has been isolated under
+ * mmap_write_lock, ensuring no competing writers.
+ * Should be called after marking vma as detached to wait for possible
+ * readers which temporarily raised vm_refcnt to drop it back and exit.
+ */
+void vma_ensure_detached(struct vm_area_struct *vma);
+
 static inline void vma_mark_attached(struct vm_area_struct *vma)
 {
 	vma_assert_write_locked(vma);
diff --git a/mm/memory.c b/mm/memory.c
index cff132003e24..534e279f98c1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6329,18 +6329,10 @@ struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm,
 #endif
 
 #ifdef CONFIG_PER_VMA_LOCK
-void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq)
+static inline bool __vma_enter_locked(struct vm_area_struct *vma)
 {
-	bool detached;
-
-	/*
-	 * If vma is detached then only vma_mark_attached() can raise the
-	 * vm_refcnt. mmap_write_lock prevents racing with vma_mark_attached().
-	 */
-	if (!refcount_inc_not_zero(&vma->vm_refcnt)) {
-		WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq);
-		return;
-	}
+	if (!refcount_inc_not_zero(&vma->vm_refcnt))
+		return false;
 
 	rwsem_acquire(&vma->vmlock_dep_map, 0, 0, _RET_IP_);
 	/* vma is attached, set the writer present bit */
@@ -6350,6 +6342,22 @@ void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq)
 		   refcount_read(&vma->vm_refcnt) == VMA_STATE_ATTACHED + (VMA_STATE_LOCKED + 1),
 		   TASK_UNINTERRUPTIBLE);
 	lock_acquired(&vma->vmlock_dep_map, _RET_IP_);
+
+	return true;
+}
+
+static inline void __vma_exit_locked(struct vm_area_struct *vma, bool *is_detached)
+{
+	*is_detached = refcount_sub_and_test(VMA_STATE_LOCKED + 1,
+					     &vma->vm_refcnt);
+	rwsem_release(&vma->vmlock_dep_map, _RET_IP_);
+}
+
+void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq)
+{
+	bool locked;
+
+	locked = __vma_enter_locked(vma);
 	/*
 	 * We should use WRITE_ONCE() here because we can have concurrent reads
 	 * from the early lockless pessimistic check in vma_start_read().
@@ -6357,13 +6365,30 @@ void __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq)
 	 * we should use WRITE_ONCE() for cleanliness and to keep KCSAN happy.
 	 */
 	WRITE_ONCE(vma->vm_lock_seq, mm_lock_seq);
-	detached = refcount_sub_and_test(VMA_STATE_LOCKED + 1,
-					 &vma->vm_refcnt);
-	rwsem_release(&vma->vmlock_dep_map, _RET_IP_);
-	VM_BUG_ON_VMA(detached, vma); /* vma should remain attached */
+	if (locked) {
+		bool detached;
+
+		__vma_exit_locked(vma, &detached);
+		/* vma was originally attached and should remain so */
+		VM_BUG_ON_VMA(detached, vma);
+	}
 }
 EXPORT_SYMBOL_GPL(__vma_start_write);
 
+void vma_ensure_detached(struct vm_area_struct *vma)
+{
+	if (is_vma_detached(vma))
+		return;
+
+	if (__vma_enter_locked(vma)) {
+		bool detached;
+
+		/* Wait for temporary readers to drop the vm_refcnt */
+		__vma_exit_locked(vma, &detached);
+		VM_BUG_ON_VMA(!detached, vma);
+	}
+}
+
 /*
  * Lookup and lock a VMA under RCU protection. Returned VMA is guaranteed to be
  * stable and not isolated. If the VMA is not found or is being modified the
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index b55556b16060..ac0a59906fea 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -465,6 +465,14 @@ static inline bool is_vma_detached(struct vm_area_struct *vma)
 	return refcount_read(&vma->vm_refcnt) == VMA_STATE_DETACHED;
 }
 
+static inline void vma_ensure_detached(struct vm_area_struct *vma)
+{
+	if (is_vma_detached(vma))
+		return;
+
+	refcount_set(&vma->vm_refcnt, VMA_STATE_DETACHED);
+}
+
 static inline void vma_assert_write_locked(struct vm_area_struct *);
 static inline void vma_mark_attached(struct vm_area_struct *vma)
 {
-- 
2.47.1.613.gc27f4b7a9f-goog


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ