Re: [PATCH 1/2] mm: limit the scope of vma_start_read()

[Lorenzo Stoakes <lorenzo.stoakes@oracle.com>]

One small nit, or maybe just _my_ personal preference :P could you use a
cover letter for these? As I find the 2/2 replying to the 1/2 thing a bit
weird.

Possibly a 'Lorenzo' thing though ;)

On Wed, Jul 30, 2025 at 06:34:03PM -0700, Suren Baghdasaryan wrote:
> Limit the scope of vma_start_read() as it is used only as a helper for
> higher-level locking functions implemented inside mmap_lock.c and we are
> about to introduce more complex RCU rules for this function.
> The change is pure code refactoring and has no functional changes.
>
> Suggested-by: Vlastimil Babka <vbabka@suse.cz>
> Signed-off-by: Suren Baghdasaryan <surenb@google.com>

I've checked this carefully, compiles locally + all fine with no
perceivable delta other than move so:

Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>

> ---
>  include/linux/mmap_lock.h | 85 ---------------------------------------
>  mm/mmap_lock.c            | 85 +++++++++++++++++++++++++++++++++++++++
>  2 files changed, 85 insertions(+), 85 deletions(-)
>
> diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
> index 11a078de9150..2c9fffa58714 100644
> --- a/include/linux/mmap_lock.h
> +++ b/include/linux/mmap_lock.h
> @@ -147,91 +147,6 @@ static inline void vma_refcount_put(struct vm_area_struct *vma)
>  	}
>  }
>
> -/*
> - * Try to read-lock a vma. The function is allowed to occasionally yield false
> - * locked result to avoid performance overhead, in which case we fall back to
> - * using mmap_lock. The function should never yield false unlocked result.
> - * False locked result is possible if mm_lock_seq overflows or if vma gets
> - * reused and attached to a different mm before we lock it.
> - * Returns the vma on success, NULL on failure to lock and EAGAIN if vma got
> - * detached.
> - *
> - * WARNING! The vma passed to this function cannot be used if the function
> - * fails to lock it because in certain cases RCU lock is dropped and then
> - * reacquired. Once RCU lock is dropped the vma can be concurently freed.
> - */
> -static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
> -						    struct vm_area_struct *vma)
> -{
> -	int oldcnt;
> -
> -	/*
> -	 * Check before locking. A race might cause false locked result.
> -	 * We can use READ_ONCE() for the mm_lock_seq here, and don't need
> -	 * ACQUIRE semantics, because this is just a lockless check whose result
> -	 * we don't rely on for anything - the mm_lock_seq read against which we
> -	 * need ordering is below.
> -	 */
> -	if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(mm->mm_lock_seq.sequence))
> -		return NULL;
> -
> -	/*
> -	 * If VMA_LOCK_OFFSET is set, __refcount_inc_not_zero_limited_acquire()
> -	 * will fail because VMA_REF_LIMIT is less than VMA_LOCK_OFFSET.
> -	 * Acquire fence is required here to avoid reordering against later
> -	 * vm_lock_seq check and checks inside lock_vma_under_rcu().
> -	 */
> -	if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt,
> -							      VMA_REF_LIMIT))) {
> -		/* return EAGAIN if vma got detached from under us */
> -		return oldcnt ? NULL : ERR_PTR(-EAGAIN);
> -	}
> -
> -	rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_);
> -
> -	/*
> -	 * If vma got attached to another mm from under us, that mm is not
> -	 * stable and can be freed in the narrow window after vma->vm_refcnt
> -	 * is dropped and before rcuwait_wake_up(mm) is called. Grab it before
> -	 * releasing vma->vm_refcnt.
> -	 */
> -	if (unlikely(vma->vm_mm != mm)) {
> -		/* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */
> -		struct mm_struct *other_mm = vma->vm_mm;
> -
> -		/*
> -		 * __mmdrop() is a heavy operation and we don't need RCU
> -		 * protection here. Release RCU lock during these operations.
> -		 * We reinstate the RCU read lock as the caller expects it to
> -		 * be held when this function returns even on error.
> -		 */
> -		rcu_read_unlock();
> -		mmgrab(other_mm);
> -		vma_refcount_put(vma);
> -		mmdrop(other_mm);
> -		rcu_read_lock();
> -		return NULL;
> -	}
> -
> -	/*
> -	 * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result.
> -	 * False unlocked result is impossible because we modify and check
> -	 * vma->vm_lock_seq under vma->vm_refcnt protection and mm->mm_lock_seq
> -	 * modification invalidates all existing locks.
> -	 *
> -	 * We must use ACQUIRE semantics for the mm_lock_seq so that if we are
> -	 * racing with vma_end_write_all(), we only start reading from the VMA
> -	 * after it has been unlocked.
> -	 * This pairs with RELEASE semantics in vma_end_write_all().
> -	 */
> -	if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&mm->mm_lock_seq))) {
> -		vma_refcount_put(vma);
> -		return NULL;
> -	}
> -
> -	return vma;
> -}
> -
>  /*
>   * Use only while holding mmap read lock which guarantees that locking will not
>   * fail (nobody can concurrently write-lock the vma). vma_start_read() should
> diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c
> index b006cec8e6fe..10826f347a9f 100644
> --- a/mm/mmap_lock.c
> +++ b/mm/mmap_lock.c
> @@ -127,6 +127,91 @@ void vma_mark_detached(struct vm_area_struct *vma)
>  	}
>  }
>
> +/*
> + * Try to read-lock a vma. The function is allowed to occasionally yield false
> + * locked result to avoid performance overhead, in which case we fall back to
> + * using mmap_lock. The function should never yield false unlocked result.
> + * False locked result is possible if mm_lock_seq overflows or if vma gets
> + * reused and attached to a different mm before we lock it.
> + * Returns the vma on success, NULL on failure to lock and EAGAIN if vma got
> + * detached.
> + *
> + * WARNING! The vma passed to this function cannot be used if the function
> + * fails to lock it because in certain cases RCU lock is dropped and then
> + * reacquired. Once RCU lock is dropped the vma can be concurently freed.
> + */
> +static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
> +						    struct vm_area_struct *vma)
> +{
> +	int oldcnt;
> +
> +	/*
> +	 * Check before locking. A race might cause false locked result.
> +	 * We can use READ_ONCE() for the mm_lock_seq here, and don't need
> +	 * ACQUIRE semantics, because this is just a lockless check whose result
> +	 * we don't rely on for anything - the mm_lock_seq read against which we
> +	 * need ordering is below.
> +	 */
> +	if (READ_ONCE(vma->vm_lock_seq) == READ_ONCE(mm->mm_lock_seq.sequence))
> +		return NULL;
> +
> +	/*
> +	 * If VMA_LOCK_OFFSET is set, __refcount_inc_not_zero_limited_acquire()
> +	 * will fail because VMA_REF_LIMIT is less than VMA_LOCK_OFFSET.
> +	 * Acquire fence is required here to avoid reordering against later
> +	 * vm_lock_seq check and checks inside lock_vma_under_rcu().
> +	 */
> +	if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt,
> +							      VMA_REF_LIMIT))) {
> +		/* return EAGAIN if vma got detached from under us */
> +		return oldcnt ? NULL : ERR_PTR(-EAGAIN);
> +	}
> +
> +	rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_);
> +
> +	/*
> +	 * If vma got attached to another mm from under us, that mm is not
> +	 * stable and can be freed in the narrow window after vma->vm_refcnt
> +	 * is dropped and before rcuwait_wake_up(mm) is called. Grab it before
> +	 * releasing vma->vm_refcnt.
> +	 */
> +	if (unlikely(vma->vm_mm != mm)) {
> +		/* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */
> +		struct mm_struct *other_mm = vma->vm_mm;
> +
> +		/*
> +		 * __mmdrop() is a heavy operation and we don't need RCU
> +		 * protection here. Release RCU lock during these operations.
> +		 * We reinstate the RCU read lock as the caller expects it to
> +		 * be held when this function returns even on error.
> +		 */
> +		rcu_read_unlock();
> +		mmgrab(other_mm);
> +		vma_refcount_put(vma);
> +		mmdrop(other_mm);
> +		rcu_read_lock();
> +		return NULL;
> +	}
> +
> +	/*
> +	 * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result.
> +	 * False unlocked result is impossible because we modify and check
> +	 * vma->vm_lock_seq under vma->vm_refcnt protection and mm->mm_lock_seq
> +	 * modification invalidates all existing locks.
> +	 *
> +	 * We must use ACQUIRE semantics for the mm_lock_seq so that if we are
> +	 * racing with vma_end_write_all(), we only start reading from the VMA
> +	 * after it has been unlocked.
> +	 * This pairs with RELEASE semantics in vma_end_write_all().
> +	 */
> +	if (unlikely(vma->vm_lock_seq == raw_read_seqcount(&mm->mm_lock_seq))) {
> +		vma_refcount_put(vma);
> +		return NULL;
> +	}
> +
> +	return 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
> --
> 2.50.1.552.g942d659e1b-goog
>