From: Chuanhua Han <hanchuanhua@xxxxxxxx>
In an embedded system like Android, more than half of anonymous memory is
actually stored in swap devices such as zRAM. For instance, when an app
is switched to the background, most of its memory might be swapped out.
Currently, we have mTHP features, but unfortunately, without support
for large folio swap-ins, once those large folios are swapped out,
we lose them immediately because mTHP is a one-way ticket.
This patch introduces mTHP swap-in support. For now, we limit mTHP
swap-ins to contiguous swaps that were likely swapped out from mTHP as
a whole.
Additionally, the current implementation only covers the SWAP_SYNCHRONOUS
case. This is the simplest and most common use case, benefiting millions
of Android phones and similar devices with minimal implementation
cost. In this straightforward scenario, large folios are always exclusive,
eliminating the need to handle complex rmap and swapcache issues.
It offers several benefits:
1. Enables bidirectional mTHP swapping, allowing retrieval of mTHP after
swap-out and swap-in.
2. Eliminates fragmentation in swap slots and supports successful
THP_SWPOUT without fragmentation.
3. Enables zRAM/zsmalloc to compress and decompress mTHP, reducing CPU usage
and enhancing compression ratios significantly.
Deploying this on millions of actual products, we haven't observed any
noticeable increase in memory footprint for 64KiB mTHP based on CONT-PTE
on ARM64.
Signed-off-by: Chuanhua Han <hanchuanhua@xxxxxxxx>
Co-developed-by: Barry Song <v-songbaohua@xxxxxxxx>
Signed-off-by: Barry Song <v-songbaohua@xxxxxxxx>
---
mm/memory.c | 211 ++++++++++++++++++++++++++++++++++++++++++++++------
1 file changed, 188 insertions(+), 23 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index 833d2cad6eb2..14048e9285d4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3986,6 +3986,152 @@ static vm_fault_t handle_pte_marker(struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
}
+/*
+ * check a range of PTEs are completely swap entries with
+ * contiguous swap offsets and the same SWAP_HAS_CACHE.
+ * ptep must be first one in the range
+ */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static bool can_swapin_thp(struct vm_fault *vmf, pte_t *ptep, int nr_pages)
+{
+ struct swap_info_struct *si;
+ unsigned long addr;
+ swp_entry_t entry;
+ pgoff_t offset;
+ char has_cache;
+ int idx, i;
+ 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);
+ offset = swp_offset(entry);
+ if (swap_pte_batch(ptep, nr_pages, pte) != nr_pages)
+ return false;
+
+ si = swp_swap_info(entry);
+ has_cache = si->swap_map[offset] & SWAP_HAS_CACHE;
+ for (i = 1; i < nr_pages; i++) {
+ /*
+ * while allocating a large folio and doing swap_read_folio for the
+ * SWP_SYNCHRONOUS_IO path, 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
+ */
+ if ((si->swap_map[offset + i] & SWAP_HAS_CACHE) != has_cache)
+ 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 its first swap_offset
+ * is aligned with nr. This can 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;
+}
+#else
+static inline bool can_swapin_thp(struct vm_fault *vmf, pte_t *ptep, int nr_pages)
+{
+ return false;
+}
+#endif
+
+static struct folio *alloc_swap_folio(struct vm_fault *vmf)
+{
+ struct vm_area_struct *vma = vmf->vma;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ 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)
+ return folio;
+ order = next_order(&orders, order);
+ }
+
+fallback:
+#endif
+ return vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address, false);
+}
+
+
/*
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
@@ -4074,35 +4220,37 @@ 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)) {
- /* 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);
page = &folio->page;
if (folio) {
__folio_set_locked(folio);
__folio_set_swapbacked(folio);
+ 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_nr(entry, nr_pages)) {
+ /* Relax a bit to prevent rapid repeated page faults */
+ schedule_timeout_uninterruptible(1);
+ goto out_page;
+ }
+ need_clear_cache = true;
+
if (mem_cgroup_swapin_charge_folio(folio,
vma->vm_mm, GFP_KERNEL,
entry)) {
ret = VM_FAULT_OOM;
goto out_page;
}
- mem_cgroup_swapin_uncharge_swap(entry);
+ mem_cgroup_swapin_uncharge_swap_nr(entry, nr_pages);
shadow = get_shadow_from_swap_cache(entry);
if (shadow)
@@ -4209,6 +4357,22 @@ 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;
+
+ if (!can_swapin_thp(vmf, folio_ptep, 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;
@@ -4340,11 +4504,12 @@ 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 {
@@ -4387,7 +4552,7 @@ 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);
+ swapcache_clear_nr(si, entry, nr_pages);
if (si)
put_swap_device(si);
return ret;
@@ -4403,7 +4568,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
folio_put(swapcache);
}
if (need_clear_cache)
- swapcache_clear(si, entry);
+ swapcache_clear_nr(si, entry, nr_pages);
if (si)
put_swap_device(si);
return ret;
--
2.34.1
