Re: [PATCH] mm/hmm: Fix a hmm_range_fault() livelock / starvation problem

[Andrew Morton <akpm@linux-foundation.org>]

On Fri, 30 Jan 2026 15:45:29 +0100 Thomas Hellström <thomas.hellstrom@linux.intel.com> wrote:

> If hmm_range_fault() fails a folio_trylock() in do_swap_page,
> trying to acquire the lock of a device-private folio for migration,
> to ram, the function will spin until it succeeds grabbing the lock.
> 
> However, if the process holding the lock is depending on a work
> item to be completed, which is scheduled on the same CPU as the
> spinning hmm_range_fault(), that work item might be starved and
> we end up in a livelock / starvation situation which is never
> resolved.
> 
> This can happen, for example if the process holding the
> device-private folio lock is stuck in
>    migrate_device_unmap()->lru_add_drain_all()
> The lru_add_drain_all() function requires a short work-item
> to be run on all online cpus to complete.

This is pretty bad behavior from lru_add_drain_all().

> A prerequisite for this to happen is:
> a) Both zone device and system memory folios are considered in
>    migrate_device_unmap(), so that there is a reason to call
>    lru_add_drain_all() for a system memory folio while a
>    folio lock is held on a zone device folio.
> b) The zone device folio has an initial mapcount > 1 which causes
>    at least one migration PTE entry insertion to be deferred to
>    try_to_migrate(), which can happen after the call to
>    lru_add_drain_all().
> c) No or voluntary only preemption.
> 
> This all seems pretty unlikely to happen, but indeed is hit by
> the "xe_exec_system_allocator" igt test.
> 
> Resolve this using a cond_resched() after each iteration in
> hmm_range_fault(). Future code improvements might consider moving
> the lru_add_drain_all() call in migrate_device_unmap() out of the
> folio locked region.
> 
> Also, hmm_range_fault() can be a very long-running function
> so a cond_resched() at the end of each iteration can be
> motivated even in the absence of an -EBUSY.
> 
> Fixes: d28c2c9a4877 ("mm/hmm: make full use of walk_page_range()")

Six years ago.

> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -674,6 +674,13 @@ int hmm_range_fault(struct hmm_range *range)
>  			return -EBUSY;
>  		ret = walk_page_range(mm, hmm_vma_walk.last, range->end,
>  				      &hmm_walk_ops, &hmm_vma_walk);
> +		/*
> +		 * Conditionally reschedule to let other work items get
> +		 * a chance to unlock device-private pages whose locks
> +		 * we're spinning on.
> +		 */
> +		cond_resched();
> +
>  		/*
>  		 * When -EBUSY is returned the loop restarts with
>  		 * hmm_vma_walk.last set to an address that has not been stored

If the process which is running hmm_range_fault() has
SCHED_FIFO/SHCED_RR then cond_resched() doesn't work.  An explicit
msleep() would be better?