Re: [PATCH v4 2/2] mm/vmalloc: fix vmalloc_dump_obj cross-zone VA lookup

[Uladzislau Rezki <urezki@gmail.com>]

On Mon, Sep 28, 2026 at 04:15:55PM +0800, Ye Liu wrote:
> From: Ye Liu <liuye@kylinos.cn>
> 
> vmalloc_dump_obj() searches only one vmap node (addr_to_node(addr)),
> but a vmalloc allocation may span multiple vmap zones.  The VA is
> stored in only one node's rb-tree (addr_to_node(va_start)), so an
> object pointer in a different zone than va_start maps to a different
> node and the search misses.  This affects any allocation larger than
> vmap_zone_size (64 KiB) on multi-CPU systems.
> 
> Extract find_vmap_area_lock() from find_vmap_area() to share the
> cross-node iteration logic.  The helper supports both spin_lock and
> spin_trylock, the latter for atomic dump contexts (OOM, KASAN, RCU).
> 
> Signed-off-by: Ye Liu <liuye@kylinos.cn>
> ---
>  mm/vmalloc.c | 108 ++++++++++++++++++++++++++++++++++++-----------------------
>  1 file changed, 66 insertions(+), 42 deletions(-)
> 
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index df42d8a6f058..4f4d7453962f 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -2517,67 +2517,94 @@ static void free_unmap_vmap_area(struct vmap_area *va)
>  	free_vmap_area_noflush(va);
>  }
>  
> -struct vmap_area *find_vmap_area(unsigned long addr)
> +static inline int next_vmap_node_id(int i)
> +{
> +	return (i + nr_vmap_nodes - 1) % nr_vmap_nodes;
> +}
> +
> +enum vmap_lock_mode {
> +	VMAP_LOCK,
> +	VMAP_TRYLOCK,
> +};
> +
> +/*
> + * Search for a vmap_area at @addr across all vmap nodes.  An
> + * addr_to_node_id(addr) converts an address to a node index where
> + * a VA is located. If VA spans several zones and passed addr is not
> + * the same as va->va_start, what is not common, we may need to scan
> + * extra nodes. See an example:
> + *
> + *      <----va---->
> + * -|-----|-----|-----|-----|-
> + *     1     2     0     1
> + *
> + * VA resides in node 1 whereas it spans 1, 2 an 0. If passed addr
> + * is within 2 or 0 nodes we should do extra work.
> + *
> + * Returns the VA with @locked_vn->busy.lock held; the caller must
> + * release it. If @mode is VMAP_TRYLOCK, nodes that cannot be locked
> + * are skipped.
> + */
> +static struct vmap_area *
> +find_vmap_area_lock(unsigned long addr, struct vmap_node **locked_vn,
> +		enum vmap_lock_mode mode)
>  {
>  	struct vmap_node *vn;
>  	struct vmap_area *va;
>  	int i, j;
>  
> +	*locked_vn = NULL;
> +
>  	if (unlikely(!vmap_initialized))
>  		return NULL;
>  
> -	/*
> -	 * An addr_to_node_id(addr) converts an address to a node index
> -	 * where a VA is located. If VA spans several zones and passed
> -	 * addr is not the same as va->va_start, what is not common, we
> -	 * may need to scan extra nodes. See an example:
> -	 *
> -	 *      <----va---->
> -	 * -|-----|-----|-----|-----|-
> -	 *     1     2     0     1
> -	 *
> -	 * VA resides in node 1 whereas it spans 1, 2 an 0. If passed
> -	 * addr is within 2 or 0 nodes we should do extra work.
> -	 */
>  	i = j = addr_to_node_id(addr);
>  	do {
>  		vn = &vmap_nodes[i];
>  
> -		spin_lock(&vn->busy.lock);
> -		va = __find_vmap_area(addr, &vn->busy.root);
> -		spin_unlock(&vn->busy.lock);
> +		if (mode == VMAP_LOCK) {
> +			spin_lock(&vn->busy.lock);
> +		} else {
> +			if (!spin_trylock(&vn->busy.lock))
> +				continue;
> +		}
>  
> -		if (va)
> +		va = __find_vmap_area(addr, &vn->busy.root);
> +		if (va) {
> +			*locked_vn = vn;
>  			return va;
> -	} while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j);
> +		}
> +
> +		spin_unlock(&vn->busy.lock);
> +	} while ((i = next_vmap_node_id(i)) != j);
>  
>  	return NULL;
>  }
>  
> -static struct vmap_area *find_unlink_vmap_area(unsigned long addr)
> +struct vmap_area *find_vmap_area(unsigned long addr)
>  {
>  	struct vmap_node *vn;
>  	struct vmap_area *va;
> -	int i, j;
> -
> -	/*
> -	 * Check the comment in the find_vmap_area() about the loop.
> -	 */
> -	i = j = addr_to_node_id(addr);
> -	do {
> -		vn = &vmap_nodes[i];
>  
> -		spin_lock(&vn->busy.lock);
> -		va = __find_vmap_area(addr, &vn->busy.root);
> -		if (va)
> -			unlink_va(va, &vn->busy.root);
> +	va = find_vmap_area_lock(addr, &vn, VMAP_LOCK);
> +	if (va)
>  		spin_unlock(&vn->busy.lock);
>  
> -		if (va)
> -			return va;
> -	} while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j);
> +	return va;
> +}
>  
> -	return NULL;
> +static struct vmap_area *find_unlink_vmap_area(unsigned long addr)
> +{
> +	struct vmap_node *vn;
> +	struct vmap_area *va;
> +
> +	va = find_vmap_area_lock(addr, &vn, VMAP_LOCK);
> +	if (va) {
> +		unlink_va(va, &vn->busy.root);
> +		spin_unlock(&vn->busy.lock);
> +	}
> +
> +	return va;
>  }
>  
>  /*** Per cpu kva allocator ***/
> @@ -5278,14 +5305,11 @@ bool vmalloc_dump_obj(void *object)
>  	unsigned long nr_pages;
>  
>  	addr = PAGE_ALIGN_DOWN((unsigned long) object);
> -	vn = addr_to_node(addr);
> -
> -	if (!spin_trylock(&vn->busy.lock))
> -		return false;
>  
> -	va = __find_vmap_area(addr, &vn->busy.root);
> +	va = find_vmap_area_lock(addr, &vn, VMAP_TRYLOCK);
>  	if (!va || !va->vm) {
> -		spin_unlock(&vn->busy.lock);
> +		if (va)
> +			spin_unlock(&vn->busy.lock);
>  		return false;
>  	}
>  
> 
> -- 
> 2.25.1
> 
LGTM:

Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>

--
Uladzislau Rezki

_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv