mm: Fix a hmm_range_fault() livelock / starvation problem

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()
sinc lru_add_drain_all() requires a short work-item
to be run on all online cpus to complete.

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 by waiting for the folio to be unlocked if the
folio_trylock() fails in do_swap_page().

Rename migration_entry_wait_on_locked() to
softleaf_entry_wait_unlock() and update its documentation to
indicate the new use-case.

Future code improvements might consider moving
the lru_add_drain_all() call in migrate_device_unmap() to be
called *after* all pages have migration entries inserted.
That would eliminate also b) above.

v2:
- Instead of a cond_resched() in hmm_range_fault(),
  eliminate the problem by waiting for the folio to be unlocked
  in do_swap_page() (Alistair Popple, Andrew Morton)
v3:
- Add a stub migration_entry_wait_on_locked() for the
  !CONFIG_MIGRATION case. (Kernel Test Robot)
v4:
- Rename migrate_entry_wait_on_locked() to
  softleaf_entry_wait_on_locked() and update docs (Alistair Popple)
v5:
- Add a WARN_ON_ONCE() for the !CONFIG_MIGRATION
  version of softleaf_entry_wait_on_locked().
- Modify wording around function names in the commit message
  (Andrew Morton)

Suggested-by: Alistair Popple <apopple@nvidia.com>
Fixes: 1afaeb8293 ("mm/migrate: Trylock device page in do_swap_page")
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: linux-mm@kvack.org
Cc: <dri-devel@lists.freedesktop.org>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: <stable@vger.kernel.org> # v6.15+
Reviewed-by: John Hubbard <jhubbard@nvidia.com> #v3
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Link: https://patch.msgid.link/20260210115653.92413-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit a69d1ab971a624c6f112cea61536569d579c3215)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

include/linux/migrate.h

@@ -65,7 +65,7 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list);
 
 int migrate_huge_page_move_mapping(struct address_space *mapping,
 		struct folio *dst, struct folio *src);
-void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
+void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
 		__releases(ptl);
 void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
 int folio_migrate_mapping(struct address_space *mapping,
@@ -97,6 +97,14 @@ static inline int set_movable_ops(const struct movable_operations *ops, enum pag
 	return -ENOSYS;
 }
 
+static inline void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
+	__releases(ptl)
+{
+	WARN_ON_ONCE(1);
+
+	spin_unlock(ptl);
+}
+
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_NUMA_BALANCING

mm/filemap.c

@@ -1379,14 +1379,16 @@ repeat:
 
 #ifdef CONFIG_MIGRATION
 /**
- * migration_entry_wait_on_locked - Wait for a migration entry to be removed
- * @entry: migration swap entry.
+ * softleaf_entry_wait_on_locked - Wait for a migration entry or
+ * device_private entry to be removed.
+ * @entry: migration or device_private swap entry.
  * @ptl: already locked ptl. This function will drop the lock.
  *
- * Wait for a migration entry referencing the given page to be removed. This is
+ * Wait for a migration entry referencing the given page, or device_private
+ * entry referencing a dvice_private page to be unlocked. This is
  * equivalent to folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE) except
  * this can be called without taking a reference on the page. Instead this
- * should be called while holding the ptl for the migration entry referencing
+ * should be called while holding the ptl for @entry referencing
  * the page.
  *
  * Returns after unlocking the ptl.
@@ -1394,7 +1396,7 @@ repeat:
  * This follows the same logic as folio_wait_bit_common() so see the comments
  * there.
  */
-void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
+void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
 	__releases(ptl)
 {
 	struct wait_page_queue wait_page;
@@ -1428,6 +1430,9 @@ void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
 	 * If a migration entry exists for the page the migration path must hold
 	 * a valid reference to the page, and it must take the ptl to remove the
 	 * migration entry. So the page is valid until the ptl is dropped.
+	 * Similarly any path attempting to drop the last reference to a
+	 * device-private page needs to grab the ptl to remove the device-private
+	 * entry.
 	 */
 	spin_unlock(ptl);
 

mm/memory.c

@@ -4763,7 +4763,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 				unlock_page(vmf->page);
 				put_page(vmf->page);
 			} else {
-				pte_unmap_unlock(vmf->pte, vmf->ptl);
+				pte_unmap(vmf->pte);
+				softleaf_entry_wait_on_locked(entry, vmf->ptl);
 			}
 		} else if (softleaf_is_hwpoison(entry)) {
 			ret = VM_FAULT_HWPOISON;

mm/migrate.c

@@ -500,7 +500,7 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 	if (!softleaf_is_migration(entry))
 		goto out;
 
-	migration_entry_wait_on_locked(entry, ptl);
+	softleaf_entry_wait_on_locked(entry, ptl);
 	return;
 out:
 	spin_unlock(ptl);
@@ -532,10 +532,10 @@ void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, p
 		 * If migration entry existed, safe to release vma lock
 		 * here because the pgtable page won't be freed without the
 		 * pgtable lock released.  See comment right above pgtable
-		 * lock release in migration_entry_wait_on_locked().
+		 * lock release in softleaf_entry_wait_on_locked().
 		 */
 		hugetlb_vma_unlock_read(vma);
-		migration_entry_wait_on_locked(entry, ptl);
+		softleaf_entry_wait_on_locked(entry, ptl);
 		return;
 	}
 
@@ -553,7 +553,7 @@ void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd)
 	ptl = pmd_lock(mm, pmd);
 	if (!pmd_is_migration_entry(*pmd))
 		goto unlock;
-	migration_entry_wait_on_locked(softleaf_from_pmd(*pmd), ptl);
+	softleaf_entry_wait_on_locked(softleaf_from_pmd(*pmd), ptl);
 	return;
 unlock:
 	spin_unlock(ptl);

mm/migrate_device.c

@@ -176,7 +176,7 @@ static int migrate_vma_collect_huge_pmd(pmd_t *pmdp, unsigned long start,
 		}
 
 		if (softleaf_is_migration(entry)) {
-			migration_entry_wait_on_locked(entry, ptl);
+			softleaf_entry_wait_on_locked(entry, ptl);
 			spin_unlock(ptl);
 			return -EAGAIN;
 		}