linux-kernel - Re: [PATCH v3 4/8] mm/vma: add+use vma lockdep acquire/release defines

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] [day] [month] [year] [list]
Message-ID: <CAJuCfpFLXtMnO32ffUw91917n22FqFhBRO46BzfOpUe7v_xjPA@mail.gmail.com>
Date: Thu, 22 Jan 2026 11:25:52 -0800
From: Suren Baghdasaryan <surenb@...gle.com>
To: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>, David Hildenbrand <david@...nel.org>, 
	"Liam R . Howlett" <Liam.Howlett@...cle.com>, Vlastimil Babka <vbabka@...e.cz>, 
	Mike Rapoport <rppt@...nel.org>, Michal Hocko <mhocko@...e.com>, Shakeel Butt <shakeel.butt@...ux.dev>, 
	Jann Horn <jannh@...gle.com>, linux-mm@...ck.org, linux-kernel@...r.kernel.org, 
	linux-rt-devel@...ts.linux.dev, Peter Zijlstra <peterz@...radead.org>, 
	Ingo Molnar <mingo@...hat.com>, Will Deacon <will@...nel.org>, Boqun Feng <boqun.feng@...il.com>, 
	Waiman Long <longman@...hat.com>, Sebastian Andrzej Siewior <bigeasy@...utronix.de>, 
	Clark Williams <clrkwllms@...nel.org>, Steven Rostedt <rostedt@...dmis.org>
Subject: Re: [PATCH v3 4/8] mm/vma: add+use vma lockdep acquire/release defines

On Thu, Jan 22, 2026 at 4:50 AM Lorenzo Stoakes
<lorenzo.stoakes@...cle.com> wrote:
>
> The code is littered with inscrutable and duplicative lockdep incantations,
> replace these with defines which explain what is going on and add
> commentary to explain what we're doing.
>
> If lockdep is disabled these become no-ops. We must use defines so _RET_IP_
> remains meaningful.
>
> These are self-documenting and aid readability of the code.
>
> Additionally, instead of using the confusing rwsem_*() form for something
> that is emphatically not an rwsem, we instead explicitly use
> lock_[acquired, release]_shared/exclusive() lockdep invocations since we
> are doing something rather custom here and these make more sense to use.
>
> No functional change intended.
>
> Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>

Reviewed-by: Suren Baghdasaryan <surenb@...gle.com>

> ---
>  include/linux/mmap_lock.h | 35 ++++++++++++++++++++++++++++++++---
>  mm/mmap_lock.c            | 10 +++++-----
>  2 files changed, 37 insertions(+), 8 deletions(-)
>
> diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
> index 0b3614aadbb4..da63b1be6ec0 100644
> --- a/include/linux/mmap_lock.h
> +++ b/include/linux/mmap_lock.h
> @@ -78,6 +78,36 @@ static inline void mmap_assert_write_locked(const struct mm_struct *mm)
>
>  #ifdef CONFIG_PER_VMA_LOCK
>
> +/*
> + * VMA locks do not behave like most ordinary locks found in the kernel, so we
> + * cannot quite have full lockdep tracking in the way we would ideally prefer.
> + *
> + * Read locks act as shared locks which exclude an exclusive lock being
> + * taken. We therefore mark these accordingly on read lock acquire/release.
> + *
> + * Write locks are acquired exclusively per-VMA, but released in a shared
> + * fashion, that is upon vma_end_write_all(), we update the mmap's seqcount such
> + * that write lock is de-acquired.
> + *
> + * We therefore cannot track write locks per-VMA, nor do we try. Mitigating this
> + * is the fact that, of course, we do lockdep-track the mmap lock rwsem.
> + *
> + * We do, however, want to indicate that during either acquisition of a VMA
> + * write lock or detachment of a VMA that we require the lock held be exclusive,
> + * so we utilise lockdep to do so.
> + */
> +#define __vma_lockdep_acquire_read(vma) \
> +       lock_acquire_shared(&vma->vmlock_dep_map, 0, 1, NULL, _RET_IP_)
> +#define __vma_lockdep_release_read(vma) \
> +       lock_release(&vma->vmlock_dep_map, _RET_IP_)
> +#define __vma_lockdep_acquire_exclusive(vma) \
> +       lock_acquire_exclusive(&vma->vmlock_dep_map, 0, 0, NULL, _RET_IP_)
> +#define __vma_lockdep_release_exclusive(vma) \
> +       lock_release(&vma->vmlock_dep_map, _RET_IP_)
> +/* Only meaningful if CONFIG_LOCK_STAT is defined. */
> +#define __vma_lockdep_stat_mark_acquired(vma) \
> +       lock_acquired(&vma->vmlock_dep_map, _RET_IP_)
> +
>  static inline void mm_lock_seqcount_init(struct mm_struct *mm)
>  {
>         seqcount_init(&mm->mm_lock_seq);
> @@ -176,8 +206,7 @@ static inline void vma_refcount_put(struct vm_area_struct *vma)
>         int refcnt;
>         bool detached;
>
> -       rwsem_release(&vma->vmlock_dep_map, _RET_IP_);
> -
> +       __vma_lockdep_release_read(vma);
>         detached = __vma_refcount_put(vma, &refcnt);
>         /*
>          * __vma_enter_locked() may be sleeping waiting for readers to drop
> @@ -203,7 +232,7 @@ static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int
>                                                               VM_REFCNT_LIMIT)))
>                 return false;
>
> -       rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_);
> +       __vma_lockdep_acquire_read(vma);
>         return true;
>  }
>
> diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c
> index ebacb57e5f16..9563bfb051f4 100644
> --- a/mm/mmap_lock.c
> +++ b/mm/mmap_lock.c
> @@ -72,7 +72,7 @@ static inline int __vma_enter_locked(struct vm_area_struct *vma,
>         if (!refcount_add_not_zero(VM_REFCNT_EXCLUDE_READERS_FLAG, &vma->vm_refcnt))
>                 return 0;
>
> -       rwsem_acquire(&vma->vmlock_dep_map, 0, 0, _RET_IP_);
> +       __vma_lockdep_acquire_exclusive(vma);
>         err = rcuwait_wait_event(&vma->vm_mm->vma_writer_wait,
>                    refcount_read(&vma->vm_refcnt) == tgt_refcnt,
>                    state);
> @@ -85,10 +85,10 @@ static inline int __vma_enter_locked(struct vm_area_struct *vma,
>                         WARN_ON_ONCE(!detaching);
>                         err = 0;
>                 }
> -               rwsem_release(&vma->vmlock_dep_map, _RET_IP_);
> +               __vma_lockdep_release_exclusive(vma);
>                 return err;
>         }
> -       lock_acquired(&vma->vmlock_dep_map, _RET_IP_);
> +       __vma_lockdep_stat_mark_acquired(vma);
>
>         return 1;
>  }
> @@ -97,7 +97,7 @@ static inline void __vma_exit_locked(struct vm_area_struct *vma, bool *detached)
>  {
>         *detached = refcount_sub_and_test(VM_REFCNT_EXCLUDE_READERS_FLAG,
>                                           &vma->vm_refcnt);
> -       rwsem_release(&vma->vmlock_dep_map, _RET_IP_);
> +       __vma_lockdep_release_exclusive(vma);
>  }
>
>  int __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq,
> @@ -199,7 +199,7 @@ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
>                 goto err;
>         }
>
> -       rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_);
> +       __vma_lockdep_acquire_read(vma);
>
>         if (unlikely(vma->vm_mm != mm))
>                 goto err_unstable;
> --
> 2.52.0
>