Re: [RFC] mm, page_alloc: reintroduce page allocation stall warning

[David Rientjes <rientjes@google.com>]

On Sat, 21 Mar 2026, David Rientjes wrote:

> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -4706,6 +4706,36 @@ check_retry_cpuset(int cpuset_mems_cookie, struct alloc_context *ac)
>  	return false;
>  }
>  
> +static unsigned long max_alloc_stall_warn_msecs = 10 * 1000L;
> +
> +static void check_alloc_stall_warn(gfp_t gfp_mask, nodemask_t *nodemask,
> +				   unsigned int order, unsigned long alloc_start_time)
> +{
> +	static DEFINE_SPINLOCK(max_alloc_stall_lock);
> +	unsigned long stall_msecs = jiffies_to_msecs(jiffies - alloc_start_time);
> +	unsigned long flags;
> +
> +	if (likely(stall_msecs <= READ_ONCE(max_alloc_stall_warn_msecs)))
> +		return;
> +	if (gfp_mask & __GFP_NOWARN)
> +		return;
> +
> +	spin_lock_irqsave(&max_alloc_stall_lock, flags);
> +	if (stall_msecs > max_alloc_stall_warn_msecs) {
> +		pr_warn("%s: page allocation stall for %lu secs: order:%d, mode:%#x(%pGg) nodemask=%*pbl",
> +			current->comm, stall_msecs / MSEC_PER_SEC, order, gfp_mask, &gfp_mask,
> +			nodemask_pr_args(nodemask));
> +		cpuset_print_current_mems_allowed();
> +		pr_cont("\n");
> +		dump_stack();
> +		warn_alloc_show_mem(gfp_mask, nodemask);
> +
> +		/* Only print future stalls that are more than a second longer */
> +		WRITE_ONCE(max_alloc_stall_warn_msecs, stall_msecs + MSEC_PER_SEC);
> +	}
> +	spin_unlock_irqrestore(&max_alloc_stall_lock, flags);
> +}
> +
>  static inline struct page *
>  __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
>  						struct alloc_context *ac)
> @@ -4726,6 +4756,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
>  	int reserve_flags;
>  	bool compact_first = false;
>  	bool can_retry_reserves = true;
> +	unsigned long alloc_start_time = jiffies;
>  
>  	if (unlikely(nofail)) {
>  		/*
> @@ -4990,6 +5021,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
>  	warn_alloc(gfp_mask, ac->nodemask,
>  			"page allocation failure: order:%u", order);
>  got_pg:
> +	check_alloc_stall_warn(gfp_mask, ac->nodemask, order, alloc_start_time);
>  	return page;
>  }
>  
> 

Another option here if we're concerned about calling 
check_alloc_stall_warn() on every slowpath allocation is to check this 
right after calling into should_reclaim_retry().  We'd normally be looping 
in the page allocator if a single call is taking >10s.  That could output 
multiple stall warnings for a single page allocation, though, so in this 
case we'd probably want to (1) increase the amount of time between one 
warning and another beyond one second and (2) cap the output when some 
time duration is reached like 60 seconds.