Merging upstream version 6.10.4.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 87 insertions, 71 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 374a0d54b0..5f32a196a6 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -517,6 +517,13 @@ static ssize_t thpsize_enabled_store(struct kobject *kobj,
 	} else
 		ret = -EINVAL;
 
+	if (ret > 0) {
+		int err;
+
+		err = start_stop_khugepaged();
+		if (err)
+			ret = err;
+	}
 	return ret;
 }
 
@@ -1659,7 +1666,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 	unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
 	int nid = NUMA_NO_NODE;
 	int target_nid, last_cpupid = (-1 & LAST_CPUPID_MASK);
-	bool migrated = false, writable = false;
+	bool writable = false;
 	int flags = 0;
 
 	vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
@@ -1695,16 +1702,17 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 	if (node_is_toptier(nid))
 		last_cpupid = folio_last_cpupid(folio);
 	target_nid = numa_migrate_prep(folio, vmf, haddr, nid, &flags);
-	if (target_nid == NUMA_NO_NODE) {
-		folio_put(folio);
+	if (target_nid == NUMA_NO_NODE)
+		goto out_map;
+	if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) {
+		flags |= TNF_MIGRATE_FAIL;
 		goto out_map;
 	}
-
+	/* The folio is isolated and isolation code holds a folio reference. */
 	spin_unlock(vmf->ptl);
 	writable = false;
 
-	migrated = migrate_misplaced_folio(folio, vma, target_nid);
-	if (migrated) {
+	if (!migrate_misplaced_folio(folio, vma, target_nid)) {
 		flags |= TNF_MIGRATED;
 		nid = target_nid;
 	} else {
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 774a97e6e2..92ecd59fff 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -416,6 +416,26 @@ static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm)
 	       test_bit(MMF_DISABLE_THP, &mm->flags);
 }
 
+static bool hugepage_pmd_enabled(void)
+{
+	/*
+	 * We cover both the anon and the file-backed case here; file-backed
+	 * hugepages, when configured in, are determined by the global control.
+	 * Anon pmd-sized hugepages are determined by the pmd-size control.
+	 */
+	if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
+	    hugepage_global_enabled())
+		return true;
+	if (test_bit(PMD_ORDER, &huge_anon_orders_always))
+		return true;
+	if (test_bit(PMD_ORDER, &huge_anon_orders_madvise))
+		return true;
+	if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) &&
+	    hugepage_global_enabled())
+		return true;
+	return false;
+}
+
 void __khugepaged_enter(struct mm_struct *mm)
 {
 	struct khugepaged_mm_slot *mm_slot;
@@ -452,7 +472,7 @@ void khugepaged_enter_vma(struct vm_area_struct *vma,
 			  unsigned long vm_flags)
 {
 	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) &&
-	    hugepage_flags_enabled()) {
+	    hugepage_pmd_enabled()) {
 		if (thp_vma_allowable_order(vma, vm_flags, TVA_ENFORCE_SYSFS,
 					    PMD_ORDER))
 			__khugepaged_enter(vma->vm_mm);
@@ -2465,8 +2485,7 @@ breakouterloop_mmap_lock:
 
 static int khugepaged_has_work(void)
 {
-	return !list_empty(&khugepaged_scan.mm_head) &&
-		hugepage_flags_enabled();
+	return !list_empty(&khugepaged_scan.mm_head) && hugepage_pmd_enabled();
 }
 
 static int khugepaged_wait_event(void)
@@ -2539,7 +2558,7 @@ static void khugepaged_wait_work(void)
 		return;
 	}
 
-	if (hugepage_flags_enabled())
+	if (hugepage_pmd_enabled())
 		wait_event_freezable(khugepaged_wait, khugepaged_wait_event());
 }
 
@@ -2570,7 +2589,7 @@ static void set_recommended_min_free_kbytes(void)
 	int nr_zones = 0;
 	unsigned long recommended_min;
 
-	if (!hugepage_flags_enabled()) {
+	if (!hugepage_pmd_enabled()) {
 		calculate_min_free_kbytes();
 		goto update_wmarks;
 	}
@@ -2620,7 +2639,7 @@ int start_stop_khugepaged(void)
 	int err = 0;
 
 	mutex_lock(&khugepaged_mutex);
-	if (hugepage_flags_enabled()) {
+	if (hugepage_pmd_enabled()) {
 		if (!khugepaged_thread)
 			khugepaged_thread = kthread_run(khugepaged, NULL,
 							"khugepaged");
@@ -2646,7 +2665,7 @@ fail:
 void khugepaged_min_free_kbytes_update(void)
 {
 	mutex_lock(&khugepaged_mutex);
-	if (hugepage_flags_enabled() && khugepaged_thread)
+	if (hugepage_pmd_enabled() && khugepaged_thread)
 		set_recommended_min_free_kbytes();
 	mutex_unlock(&khugepaged_mutex);
 }
diff --git a/mm/memory.c b/mm/memory.c
index f81760c938..755ffe082e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5067,8 +5067,6 @@ int numa_migrate_prep(struct folio *folio, struct vm_fault *vmf,
 {
 	struct vm_area_struct *vma = vmf->vma;
 
-	folio_get(folio);
-
 	/* Record the current PID acceesing VMA */
 	vma_set_access_pid_bit(vma);
 
@@ -5205,16 +5203,19 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 	else
 		last_cpupid = folio_last_cpupid(folio);
 	target_nid = numa_migrate_prep(folio, vmf, vmf->address, nid, &flags);
-	if (target_nid == NUMA_NO_NODE) {
-		folio_put(folio);
+	if (target_nid == NUMA_NO_NODE)
+		goto out_map;
+	if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) {
+		flags |= TNF_MIGRATE_FAIL;
 		goto out_map;
 	}
+	/* The folio is isolated and isolation code holds a folio reference. */
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	writable = false;
 	ignore_writable = true;
 
 	/* Migrate to the requested node */
-	if (migrate_misplaced_folio(folio, vma, target_nid)) {
+	if (!migrate_misplaced_folio(folio, vma, target_nid)) {
 		nid = target_nid;
 		flags |= TNF_MIGRATED;
 	} else {
diff --git a/mm/migrate.c b/mm/migrate.c
index a8c6f466e3..9dabeb90f7 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2557,16 +2557,44 @@ static struct folio *alloc_misplaced_dst_folio(struct folio *src,
 	return __folio_alloc_node(gfp, order, nid);
 }
 
-static int numamigrate_isolate_folio(pg_data_t *pgdat, struct folio *folio)
+/*
+ * Prepare for calling migrate_misplaced_folio() by isolating the folio if
+ * permitted. Must be called with the PTL still held.
+ */
+int migrate_misplaced_folio_prepare(struct folio *folio,
+		struct vm_area_struct *vma, int node)
 {
 	int nr_pages = folio_nr_pages(folio);
+	pg_data_t *pgdat = NODE_DATA(node);
+
+	if (folio_is_file_lru(folio)) {
+		/*
+		 * Do not migrate file folios that are mapped in multiple
+		 * processes with execute permissions as they are probably
+		 * shared libraries.
+		 *
+		 * See folio_likely_mapped_shared() on possible imprecision
+		 * when we cannot easily detect if a folio is shared.
+		 */
+		if ((vma->vm_flags & VM_EXEC) &&
+		    folio_likely_mapped_shared(folio))
+			return -EACCES;
+
+		/*
+		 * Do not migrate dirty folios as not all filesystems can move
+		 * dirty folios in MIGRATE_ASYNC mode which is a waste of
+		 * cycles.
+		 */
+		if (folio_test_dirty(folio))
+			return -EAGAIN;
+	}
 
 	/* Avoid migrating to a node that is nearly full */
 	if (!migrate_balanced_pgdat(pgdat, nr_pages)) {
 		int z;
 
 		if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING))
-			return 0;
+			return -EAGAIN;
 		for (z = pgdat->nr_zones - 1; z >= 0; z--) {
 			if (managed_zone(pgdat->node_zones + z))
 				break;
@@ -2577,78 +2605,42 @@ static int numamigrate_isolate_folio(pg_data_t *pgdat, struct folio *folio)
 		 * further.
 		 */
 		if (z < 0)
-			return 0;
+			return -EAGAIN;
 
 		wakeup_kswapd(pgdat->node_zones + z, 0,
 			      folio_order(folio), ZONE_MOVABLE);
-		return 0;
+		return -EAGAIN;
 	}
 
 	if (!folio_isolate_lru(folio))
-		return 0;
+		return -EAGAIN;
 
 	node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio),
 			    nr_pages);
-
-	/*
-	 * Isolating the folio has taken another reference, so the
-	 * caller's reference can be safely dropped without the folio
-	 * disappearing underneath us during migration.
-	 */
-	folio_put(folio);
-	return 1;
+	return 0;
 }
 
 /*
  * Attempt to migrate a misplaced folio to the specified destination
- * node. Caller is expected to have an elevated reference count on
- * the folio that will be dropped by this function before returning.
+ * node. Caller is expected to have isolated the folio by calling
+ * migrate_misplaced_folio_prepare(), which will result in an
+ * elevated reference count on the folio. This function will un-isolate the
+ * folio, dereferencing the folio before returning.
  */
 int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma,
 			    int node)
 {
 	pg_data_t *pgdat = NODE_DATA(node);
-	int isolated;
 	int nr_remaining;
 	unsigned int nr_succeeded;
 	LIST_HEAD(migratepages);
-	int nr_pages = folio_nr_pages(folio);
-
-	/*
-	 * Don't migrate file folios that are mapped in multiple processes
-	 * with execute permissions as they are probably shared libraries.
-	 *
-	 * See folio_likely_mapped_shared() on possible imprecision when we
-	 * cannot easily detect if a folio is shared.
-	 */
-	if (folio_likely_mapped_shared(folio) && folio_is_file_lru(folio) &&
-	    (vma->vm_flags & VM_EXEC))
-		goto out;
-
-	/*
-	 * Also do not migrate dirty folios as not all filesystems can move
-	 * dirty folios in MIGRATE_ASYNC mode which is a waste of cycles.
-	 */
-	if (folio_is_file_lru(folio) && folio_test_dirty(folio))
-		goto out;
-
-	isolated = numamigrate_isolate_folio(pgdat, folio);
-	if (!isolated)
-		goto out;
 
 	list_add(&folio->lru, &migratepages);
 	nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_folio,
 				     NULL, node, MIGRATE_ASYNC,
 				     MR_NUMA_MISPLACED, &nr_succeeded);
-	if (nr_remaining) {
-		if (!list_empty(&migratepages)) {
-			list_del(&folio->lru);
-			node_stat_mod_folio(folio, NR_ISOLATED_ANON +
-					folio_is_file_lru(folio), -nr_pages);
-			folio_putback_lru(folio);
-		}
-		isolated = 0;
-	}
+	if (nr_remaining && !list_empty(&migratepages))
+		putback_movable_pages(&migratepages);
 	if (nr_succeeded) {
 		count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded);
 		if (!node_is_toptier(folio_nid(folio)) && node_is_toptier(node))
@@ -2656,11 +2648,7 @@ int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma,
 					    nr_succeeded);
 	}
 	BUG_ON(!list_empty(&migratepages));
-	return isolated;
-
-out:
-	folio_put(folio);
-	return 0;
+	return nr_remaining ? -EAGAIN : 0;
 }
 #endif /* CONFIG_NUMA_BALANCING */
 #endif /* CONFIG_NUMA */