Re: [PATCH 5/5] mm/vmalloc.c: return explicit error value in alloc_vmap_area()

[Baoquan He <bhe@redhat.com>]

On 04/16/25 at 04:28pm, Uladzislau Rezki wrote:
> On Tue, Apr 15, 2025 at 10:39:52AM +0800, Baoquan He wrote:
> > In codes of alloc_vmap_area(), it returns the upper bound 'vend' to
> > indicate if the allocation is successful or failed. That is not very clear.
> > 
> > Here change to return explicit error values and check them to judge if
> > allocation is successful.
> > 
> > IS_ERR_VALUE already uses unlikely() internally
> > 
> > Signed-off-by: Baoquan He <bhe@redhat.com>
> > ---
> >  mm/vmalloc.c | 34 +++++++++++++++++-----------------
> >  1 file changed, 17 insertions(+), 17 deletions(-)
> > 
> > diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> > index 3f38a232663b..5b21cd09b2b4 100644
> > --- a/mm/vmalloc.c
> > +++ b/mm/vmalloc.c
> > @@ -1715,7 +1715,7 @@ va_clip(struct rb_root *root, struct list_head *head,
> >  			 */
> >  			lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT);
> >  			if (!lva)
> > -				return -1;
> > +				return -ENOMEM;
> >  		}
> >  
> >  		/*
> > @@ -1729,7 +1729,7 @@ va_clip(struct rb_root *root, struct list_head *head,
> >  		 */
> >  		va->va_start = nva_start_addr + size;
> >  	} else {
> > -		return -1;
> > +		return -EINVAL;
> >  	}
> >  
> >  	if (type != FL_FIT_TYPE) {
> > @@ -1758,19 +1758,19 @@ va_alloc(struct vmap_area *va,
> >  
> >  	/* Check the "vend" restriction. */
> >  	if (nva_start_addr + size > vend)
> > -		return vend;
> > +		return -ERANGE;
> >  
> >  	/* Update the free vmap_area. */
> >  	ret = va_clip(root, head, va, nva_start_addr, size);
> > -	if (WARN_ON_ONCE(ret))
> > -		return vend;
> >
> Not clear why you remove this WARN_ON by this patch. It should be
> a separate patch or just keep it as is. The warning here can mean
> that something is really wrong, especially if NOTHING_FIT. So we
> definitely want the warning.

I remember one time someone reported that the slab allocation failure
triggered this warning which is confusing to them. But yes, it should be
discussed in a separate post or thread, not appropriate to remove it
silently. I will add it back in v2.

> 
> > +	if (ret)
> > +		return ret;
> >  
> >  	return nva_start_addr;
> >  }
> >  
> >  /*
> >   * Returns a start address of the newly allocated area, if success.
> > - * Otherwise a vend is returned that indicates failure.
> > + * Otherwise an error value is returned that indicates failure.
> >   */
> >  static __always_inline unsigned long
> >  __alloc_vmap_area(struct rb_root *root, struct list_head *head,
> > @@ -1795,14 +1795,13 @@ __alloc_vmap_area(struct rb_root *root, struct list_head *head,
> >  
> >  	va = find_vmap_lowest_match(root, size, align, vstart, adjust_search_size);
> >  	if (unlikely(!va))
> > -		return vend;
> > +		return -ENOENT;
> >  
> >  	nva_start_addr = va_alloc(va, root, head, size, align, vstart, vend);
> > -	if (nva_start_addr == vend)
> > -		return vend;
> >  
> >  #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK
> > -	find_vmap_lowest_match_check(root, head, size, align);
> > +	if (!IS_ERR_VALUE(nva_start_addr))
> >
> Just keep it as it was. No need to check if addr is valid or not.

This is to keep consistent with the old code. Before this patch, if
va_alloc() return vend, it returns directly, no
find_vmap_lowest_match_check() invocation is done. I tried to keep the
behaviour unchanged. That code is for debugging, both is fine to me.

> 
> > +		find_vmap_lowest_match_check(root, head, size, align);
> >  #endif
> >  
> >  	return nva_start_addr;
> > @@ -1932,7 +1931,7 @@ node_alloc(unsigned long size, unsigned long align,
> >  	struct vmap_area *va;
> >  
> >  	*vn_id = 0;
> > -	*addr = vend;
> > +	*addr = -EINVAL;
> >  
> >  	/*
> >  	 * Fallback to a global heap if not vmalloc or there
> > @@ -2012,20 +2011,20 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
> >  	}
> >  
> >  retry:
> > -	if (addr == vend) {
> > +	if (IS_ERR_VALUE(addr)) {
> >  		preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node);
> >  		addr = __alloc_vmap_area(&free_vmap_area_root, &free_vmap_area_list,
> >  			size, align, vstart, vend);
> >  		spin_unlock(&free_vmap_area_lock);
> >  	}
> >  
> > -	trace_alloc_vmap_area(addr, size, align, vstart, vend, addr == vend);
> > +	trace_alloc_vmap_area(addr, size, align, vstart, vend, IS_ERR_VALUE(addr));
> >  
> >  	/*
> > -	 * If an allocation fails, the "vend" address is
> > +	 * If an allocation fails, the error value is
> >  	 * returned. Therefore trigger the overflow path.
> >  	 */
> > -	if (unlikely(addr == vend))
> > +	if (IS_ERR_VALUE(addr))
> >  		goto overflow;
> >  
> >  	va->va_start = addr;
> > @@ -4753,9 +4752,10 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
> >  
> >  		ret = va_clip(&free_vmap_area_root,
> >  			&free_vmap_area_list, va, start, size);
> > -		if (WARN_ON_ONCE(unlikely(ret)))
> > -			/* It is a BUG(), but trigger recovery instead. */
> Keep the comment.

OK, will add it back.

> 
> > +		if ((unlikely(ret))) {
> > +			WARN_ONCE(1, "%s error: errno (%d)\n", __func__, ret);
> >  			goto recovery;
> > +		}
> >
> 
> --
> Uladzislau Rezki
>