The patch titled
Subject: mm: make vm_area_struct anon_name field RCU-safe
has been added to the -mm mm-unstable branch. Its filename is
mm-make-vm_area_struct-anon_name-field-rcu-safe.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-make-vm_area_struct-anon_name-field-rcu-safe.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Subject: mm: make vm_area_struct anon_name field RCU-safe
Date: Sun, 21 Jan 2024 23:13:22 -0800
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.
Link: https://lkml.kernel.org/r/20240122071324.2099712-1-surenb@xxxxxxxxxx
Signed-off-by: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Andrei Vagin <avagin@xxxxxxxxxx>
Cc: Andy Shevchenko <andriy.shevchenko@xxxxxxxxxxxxxxx>
Cc: Axel Rasmussen <axelrasmussen@xxxxxxxxxx>
Cc: Ben Wolsieffer <ben.wolsieffer@xxxxxxxxxxx>
Cc: Casey Schaufler <casey@xxxxxxxxxxxxxxxx>
Cc: Christian Brauner <brauner@xxxxxxxxxx>
Cc: Dave Chinner <dchinner@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: David Howells <dhowells@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
Cc: Liam R. Howlett <Liam.Howlett@xxxxxxxxxx>
Cc: Lorenzo Stoakes <lstoakes@xxxxxxxxx>
Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Muhammad Usama Anjum <usama.anjum@xxxxxxxxxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Ryan Roberts <ryan.roberts@xxxxxxx>
Cc: Sidhartha Kumar <sidhartha.kumar@xxxxxxxxxx>
Cc: T.J. Alumbaugh <talumbau@xxxxxxxxxx>
Cc: Vishal Moola (Oracle) <vishal.moola@xxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Xingui Yang <yangxingui@xxxxxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mm_inline.h | 10 +++++++++-
include/linux/mm_types.h | 3 ++-
mm/madvise.c | 30 ++++++++++++++++++++++++++----
3 files changed, 37 insertions(+), 6 deletions(-)
--- a/include/linux/mm_inline.h~mm-make-vm_area_struct-anon_name-field-rcu-safe
+++ a/include/linux/mm_inline.h
@@ -389,7 +389,7 @@ static inline void dup_anon_vma_name(str
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(stru
!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(stru
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)
--- a/include/linux/mm_types.h~mm-make-vm_area_struct-anon_name-field-rcu-safe
+++ a/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;
--- a/mm/madvise.c~mm-make-vm_area_struct-anon_name-field-rcu-safe
+++ a/mm/madvise.c
@@ -88,14 +88,15 @@ void anon_vma_name_free(struct kref *kre
{
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
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
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)
_
Patches currently in -mm which might be from surenb@xxxxxxxxxx are
mm-make-vm_area_struct-anon_name-field-rcu-safe.patch
mm-add-mm_struct-sequence-number-to-detect-write-locks.patch
mm-maps-read-proc-pid-maps-under-rcu.patch
