On 8/5/25 1:15 AM, Suren Baghdasaryan wrote:
> Utilize per-vma locks to stabilize vma after lookup without taking
> mmap_lock during PROCMAP_QUERY ioctl execution. If vma lock is
> contended, we fall back to mmap_lock but take it only momentarily
> to lock the vma and release the mmap_lock. In a very unlikely case
> of vm_refcnt overflow, this fall back path will fail and ioctl is
> done under mmap_lock protection.
>
> This change is designed to reduce mmap_lock contention and prevent
> PROCMAP_QUERY ioctl calls from blocking address space updates.
>
> Signed-off-by: Suren Baghdasaryan <[email protected]>
> ---
> fs/proc/task_mmu.c | 81 +++++++++++++++++++++++++++++++++++++---------
> 1 file changed, 65 insertions(+), 16 deletions(-)
>
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index 843577aa7a32..1d06ecdbef6f 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -517,28 +517,78 @@ static int pid_maps_open(struct inode *inode, struct
> file *file)
> PROCMAP_QUERY_VMA_FLAGS \
> )
>
> -static int query_vma_setup(struct mm_struct *mm)
> +#ifdef CONFIG_PER_VMA_LOCK
> +
> +static int query_vma_setup(struct proc_maps_locking_ctx *lock_ctx)
> {
> - return mmap_read_lock_killable(mm);
> + lock_ctx->locked_vma = NULL;
> + lock_ctx->mmap_locked = false;
> +
> + return 0;
> }
>
> -static void query_vma_teardown(struct mm_struct *mm, struct vm_area_struct
> *vma)
> +static void query_vma_teardown(struct proc_maps_locking_ctx *lock_ctx)
> {
> - mmap_read_unlock(mm);
> + if (lock_ctx->mmap_locked)
> + mmap_read_unlock(lock_ctx->mm);
> + else
> + unlock_vma(lock_ctx);
> }
>
> -static struct vm_area_struct *query_vma_find_by_addr(struct mm_struct *mm,
> unsigned long addr)
> +static struct vm_area_struct *query_vma_find_by_addr(struct
> proc_maps_locking_ctx *lock_ctx,
> + unsigned long addr)
> {
> - return find_vma(mm, addr);
> + struct vm_area_struct *vma;
> + struct vma_iterator vmi;
>
Hm I think we can reach here with lock_ctx->mmap_locked being true via
"goto next_vma" in query_matching_vma(). In that case we should just
"return find_vma()" and doing the below is wrong, no?
> + unlock_vma(lock_ctx);
> + rcu_read_lock();
> + vma_iter_init(&vmi, lock_ctx->mm, addr);
> + vma = lock_next_vma(lock_ctx->mm, &vmi, addr);
> + rcu_read_unlock();
> +
> + if (!IS_ERR_OR_NULL(vma)) {
> + lock_ctx->locked_vma = vma;
> + } else if (PTR_ERR(vma) == -EAGAIN) {
> + /* Fallback to mmap_lock on vma->vm_refcnt overflow */
> + mmap_read_lock(lock_ctx->mm);
> + vma = find_vma(lock_ctx->mm, addr);
> + lock_ctx->mmap_locked = true;
> + }
> +
> + return vma;
> }
>
