mm/swap：swap cache 稳定大分配 — 大对象直接入 swap cache 减少页表/分配开销

+static struct folio *__swap_cache_alloc(struct swap_cluster_info *ci,
+					swp_entry_t targ_entry, gfp_t gfp,
+					unsigned int order, struct vm_fault *vmf,
+					struct mempolicy *mpol, pgoff_t ilx)
+{
+	int err;
+	swp_entry_t entry;
+	struct folio *folio;
+	void *shadow = NULL;
+	unsigned long address, nr_pages = 1UL << order;
+	struct vm_area_struct *vma = vmf ? vmf->vma : NULL;
+
+	VM_WARN_ON_ONCE(nr_pages > SWAPFILE_CLUSTER);
+	entry.val = round_down(targ_entry.val, nr_pages);
+
+	/* Check if the slot and range are available, skip allocation if not */
+	spin_lock(&ci->lock);
+	err = __swap_cache_add_check(ci, targ_entry, nr_pages, NULL);
+	spin_unlock(&ci->lock);
+	if (unlikely(err))
+		return ERR_PTR(err);
+
+	/*
+	 * Limit THP gfp. The limitation is a no-op for typical
+	 * GFP_HIGHUSER_MOVABLE but matters for shmem.
+	 */
+	if (order)
+		gfp = thp_shmem_limit_gfp_mask(vma_thp_gfp_mask(vma), gfp);
+
+	if (mpol || !vmf) {
+		folio = folio_alloc_mpol(gfp, order, mpol, ilx, numa_node_id());
+	} else {
+		address = round_down(vmf->address, PAGE_SIZE << order);
+		folio = vma_alloc_folio(gfp, order, vmf->vma, address);
+	}
+	if (unlikely(!folio))
+		return ERR_PTR(-ENOMEM);
+
+	/* Double check the range is still not in conflict */
+	spin_lock(&ci->lock);
+	err = __swap_cache_add_check(ci, targ_entry, nr_pages, &shadow);
+	if (unlikely(err)) {
+		spin_unlock(&ci->lock);
+		folio_put(folio);
+		return ERR_PTR(err);
+	}
+
+	__folio_set_locked(folio);
+	__folio_set_swapbacked(folio);
+	__swap_cache_do_add_folio(ci, folio, entry);
+	spin_unlock(&ci->lock);
+

+	do {
+		ret = __swap_cache_alloc(ci, targ_entry, gfp, order,
+					 vmf, mpol, ilx);
+		if (!IS_ERR(ret))
+			break;
+		err = PTR_ERR(ret);
+		if (!order || (err && err != -EBUSY && err != -ENOMEM))
+			break;
+		count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK);
+		order = next_order(&orders, order);
+	} while (orders);