@@ -3985,6 +3985,194 @@ static vm_fault_t handle_pte_marker(struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
}
+static struct folio *__alloc_swap_folio(struct vm_fault *vmf)
+{
+ struct vm_area_struct *vma = vmf->vma;
+ struct folio *folio;
+ swp_entry_t entry;
+
+ folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma,
+ vmf->address, false);
+ if (!folio)
+ return NULL;
+
+ entry = pte_to_swp_entry(vmf->orig_pte);
+ if (mem_cgroup_swapin_charge_folio(folio, vma->vm_mm,
+ GFP_KERNEL, entry)) {
+ folio_put(folio);
+ return NULL;
+ }
+
+ return folio;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
+{
+ struct swap_info_struct *si = swp_swap_info(entry);
+ pgoff_t offset = swp_offset(entry);
+ int i;
+
+ /*
+ * While allocating a large folio and doing swap_read_folio, which is
+ * the case the being faulted pte doesn't have swapcache. We need to
+ * ensure all PTEs have no cache as well, otherwise, we might go to
+ * swap devices while the content is in swapcache.
+ */
+ for (i = 0; i < max_nr; i++) {
+ if ((si->swap_map[offset + i] & SWAP_HAS_CACHE))
+ return i;
+ }
+
+ return i;
+}
+
+/*
+ * Check if the PTEs within a range are contiguous swap entries
+ * and have consistent swapcache, zeromap.
+ */
+static bool can_swapin_thp(struct vm_fault *vmf, pte_t *ptep, int nr_pages)
+{
+ unsigned long addr;
+ swp_entry_t entry;
+ int idx;
+ pte_t pte;
+
+ addr = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE);
+ idx = (vmf->address - addr) / PAGE_SIZE;
+ pte = ptep_get(ptep);
+
+ if (!pte_same(pte, pte_move_swp_offset(vmf->orig_pte, -idx)))
+ return false;
+ entry = pte_to_swp_entry(pte);
+ if (swap_pte_batch(ptep, nr_pages, pte) != nr_pages)
+ return false;
+
+ /*
+ * swap_read_folio() can't handle the case a large folio is hybridly
+ * from different backends. And they are likely corner cases. Similar
+ * things might be added once zswap support large folios.
+ */
+ if (unlikely(swap_zeromap_batch(entry, nr_pages, NULL) != nr_pages))
+ return false;
+ if (unlikely(non_swapcache_batch(entry, nr_pages) != nr_pages))
+ return false;
+
+ return true;
+}
+
+static inline unsigned long thp_swap_suitable_orders(pgoff_t swp_offset,
+ unsigned long addr,
+ unsigned long orders)
+{
+ int order, nr;
+
+ order = highest_order(orders);
+
+ /*
+ * To swap in a THP with nr pages, we require that its first swap_offset
+ * is aligned with that number, as it was when the THP was swapped out.
+ * This helps filter out most invalid entries.
+ */
+ while (orders) {
+ nr = 1 << order;
+ if ((addr >> PAGE_SHIFT) % nr == swp_offset % nr)
+ break;
+ order = next_order(&orders, order);
+ }
+
+ return orders;
+}
+
+static struct folio *alloc_swap_folio(struct vm_fault *vmf)
+{
+ struct vm_area_struct *vma = vmf->vma;
+ unsigned long orders;
+ struct folio *folio;
+ unsigned long addr;
+ swp_entry_t entry;
+ spinlock_t *ptl;
+ pte_t *pte;
+ gfp_t gfp;
+ int order;
+
+ /*
+ * If uffd is active for the vma we need per-page fault fidelity to
+ * maintain the uffd semantics.
+ */
+ if (unlikely(userfaultfd_armed(vma)))
+ goto fallback;
+
+ /*
+ * A large swapped out folio could be partially or fully in zswap. We
+ * lack handling for such cases, so fallback to swapping in order-0
+ * folio.
+ */
+ if (!zswap_never_enabled())
+ goto fallback;
+
+ entry = pte_to_swp_entry(vmf->orig_pte);
+ /*
+ * Get a list of all the (large) orders below PMD_ORDER that are enabled
+ * and suitable for swapping THP.
+ */
+ orders = thp_vma_allowable_orders(vma, vma->vm_flags,
+ TVA_IN_PF | TVA_ENFORCE_SYSFS, BIT(PMD_ORDER) - 1);
+ orders = thp_vma_suitable_orders(vma, vmf->address, orders);
+ orders = thp_swap_suitable_orders(swp_offset(entry),
+ vmf->address, orders);
+
+ if (!orders)
+ goto fallback;
+
+ pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd,
+ vmf->address & PMD_MASK, &ptl);
+ if (unlikely(!pte))
+ goto fallback;
+
+ /*
+ * For do_swap_page, find the highest order where the aligned range is
+ * completely swap entries with contiguous swap offsets.
+ */
+ order = highest_order(orders);
+ while (orders) {
+ addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
+ if (can_swapin_thp(vmf, pte + pte_index(addr), 1 << order))
+ break;
+ order = next_order(&orders, order);
+ }
+
+ pte_unmap_unlock(pte, ptl);
+
+ /* Try allocating the highest of the remaining orders. */
+ gfp = vma_thp_gfp_mask(vma);
+ while (orders) {
+ addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order);
+ folio = vma_alloc_folio(gfp, order, vma, addr, true);
+ if (folio) {
+ if (!mem_cgroup_swapin_charge_folio(folio, vma->vm_mm,
+ gfp, entry))
+ return folio;
+ folio_put(folio);
+ }
+ order = next_order(&orders, order);
+ }
+
+fallback:
+ return __alloc_swap_folio(vmf);
+}
+#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
+static inline bool can_swapin_thp(struct vm_fault *vmf, pte_t *ptep, int nr_pages)
+{
+ return false;
+}
+
+static struct folio *alloc_swap_folio(struct vm_fault *vmf)
+{
+ return __alloc_swap_folio(vmf);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
/*
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
@@ -4073,34 +4261,34 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
if (!folio) {
if (data_race(si->flags & SWP_SYNCHRONOUS_IO) &&
__swap_count(entry) == 1) {
- /*
- * Prevent parallel swapin from proceeding with
- * the cache flag. Otherwise, another thread may
- * finish swapin first, free the entry, and swapout
- * reusing the same entry. It's undetectable as
- * pte_same() returns true due to entry reuse.
- */
- if (swapcache_prepare(entry, 1)) {
- /* Relax a bit to prevent rapid repeated page faults */
- schedule_timeout_uninterruptible(1);
- goto out;
- }
- need_clear_cache = true;
-
/* skip swapcache */
- folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0,
- vma, vmf->address, false);
+ folio = alloc_swap_folio(vmf);
if (folio) {
__folio_set_locked(folio);
__folio_set_swapbacked(folio);
- if (mem_cgroup_swapin_charge_folio(folio,
- vma->vm_mm, GFP_KERNEL,
- entry)) {
- ret = VM_FAULT_OOM;
+ nr_pages = folio_nr_pages(folio);
+ if (folio_test_large(folio))
+ entry.val = ALIGN_DOWN(entry.val, nr_pages);
+ /*
+ * Prevent parallel swapin from proceeding with
+ * the cache flag. Otherwise, another thread
+ * may finish swapin first, free the entry, and
+ * swapout reusing the same entry. It's
+ * undetectable as pte_same() returns true due
+ * to entry reuse.
+ */
+ if (swapcache_prepare(entry, nr_pages)) {
+ /*
+ * Relax a bit to prevent rapid
+ * repeated page faults.
+ */
+ schedule_timeout_uninterruptible(1);
goto out_page;
}
- mem_cgroup_swapin_uncharge_swap(entry, 1);
+ need_clear_cache = true;
+
+ mem_cgroup_swapin_uncharge_swap(entry, nr_pages);
shadow = get_shadow_from_swap_cache(entry);
if (shadow)
@@ -4206,6 +4394,24 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
goto out_nomap;
}
+ /* allocated large folios for SWP_SYNCHRONOUS_IO */
+ if (folio_test_large(folio) && !folio_test_swapcache(folio)) {
+ unsigned long nr = folio_nr_pages(folio);
+ unsigned long folio_start = ALIGN_DOWN(vmf->address, nr * PAGE_SIZE);
+ unsigned long idx = (vmf->address - folio_start) / PAGE_SIZE;
+ pte_t *folio_ptep = vmf->pte - idx;
+ pte_t folio_pte = ptep_get(folio_ptep);
+
+ if (!pte_same(folio_pte, pte_move_swp_offset(vmf->orig_pte, -idx)) ||
+ swap_pte_batch(folio_ptep, nr, folio_pte) != nr)
+ goto out_nomap;
+
+ page_idx = idx;
+ address = folio_start;
+ ptep = folio_ptep;
+ goto check_folio;
+ }
+
nr_pages = 1;
page_idx = 0;
address = vmf->address;
@@ -4337,11 +4543,12 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
folio_add_lru_vma(folio, vma);
} else if (!folio_test_anon(folio)) {
/*
- * We currently only expect small !anon folios, which are either
- * fully exclusive or fully shared. If we ever get large folios
- * here, we have to be careful.
+ * We currently only expect small !anon folios which are either
+ * fully exclusive or fully shared, or new allocated large
+ * folios which are fully exclusive. If we ever get large
+ * folios within swapcache here, we have to be careful.
*/
- VM_WARN_ON_ONCE(folio_test_large(folio));
+ VM_WARN_ON_ONCE(folio_test_large(folio) && folio_test_swapcache(folio));
VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio);
folio_add_new_anon_rmap(folio, vma, address, rmap_flags);
} else {
@@ -4384,7 +4591,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
out:
/* Clear the swap cache pin for direct swapin after PTL unlock */
if (need_clear_cache)
- swapcache_clear(si, entry, 1);
+ swapcache_clear(si, entry, nr_pages);
if (si)
put_swap_device(si);
return ret;
@@ -4400,7 +4607,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
folio_put(swapcache);
}
if (need_clear_cache)
- swapcache_clear(si, entry, 1);
+ swapcache_clear(si, entry, nr_pages);
if (si)
put_swap_device(si);
return ret;