mm: swap: free_swap_and_cache_nr() as batched free_swap_and_cache()

Now that we no longer have a convenient flag in the cluster to determine
if a folio is large, free_swap_and_cache() will take a reference and lock
a large folio much more often, which could lead to contention and (e.g.)
failure to split large folios, etc.

Let's solve that problem by batch freeing swap and cache with a new
function, free_swap_and_cache_nr(), to free a contiguous range of swap
entries together.  This allows us to first drop a reference to each swap
slot before we try to release the cache folio.  This means we only try to
release the folio once, only taking the reference and lock once - much
better than the previous 512 times for the 2M THP case.

Contiguous swap entries are gathered in zap_pte_range() and
madvise_free_pte_range() in a similar way to how present ptes are already
gathered in zap_pte_range().

While we are at it, let's simplify by converting the return type of both
functions to void.  The return value was used only by zap_pte_range() to
print a bad pte, and was ignored by everyone else, so the extra reporting
wasn't exactly guaranteed.  We will still get the warning with most of the
information from get_swap_device().  With the batch version, we wouldn't
know which pte was bad anyway so could print the wrong one.

[ryan.roberts@arm.com: fix a build warning on parisc]
  Link: https://lkml.kernel.org/r/20240409111840.3173122-1-ryan.roberts@arm.com
Link: https://lkml.kernel.org/r/20240408183946.2991168-3-ryan.roberts@arm.com
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Gao Xiang <xiang@kernel.org>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

4 files changed, 158 insertions, 28 deletions

diff --git a/mm/internal.h b/mm/internal.h
index d567381b12cc..d34df04b11f6 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -11,6 +11,8 @@
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
 #include <linux/tracepoint-defs.h>
 
 struct folio_batch;
@@ -189,6 +191,68 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 
 	return min(ptep - start_ptep, max_nr);
 }
+
+/**
+ * pte_next_swp_offset - Increment the swap entry offset field of a swap pte.
+ * @pte: The initial pte state; is_swap_pte(pte) must be true and
+ *	 non_swap_entry() must be false.
+ *
+ * Increments the swap offset, while maintaining all other fields, including
+ * swap type, and any swp pte bits. The resulting pte is returned.
+ */
+static inline pte_t pte_next_swp_offset(pte_t pte)
+{
+	swp_entry_t entry = pte_to_swp_entry(pte);
+	pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry),
+						   (swp_offset(entry) + 1)));
+
+	if (pte_swp_soft_dirty(pte))
+		new = pte_swp_mksoft_dirty(new);
+	if (pte_swp_exclusive(pte))
+		new = pte_swp_mkexclusive(new);
+	if (pte_swp_uffd_wp(pte))
+		new = pte_swp_mkuffd_wp(new);
+
+	return new;
+}
+
+/**
+ * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries
+ * @start_ptep: Page table pointer for the first entry.
+ * @max_nr: The maximum number of table entries to consider.
+ * @pte: Page table entry for the first entry.
+ *
+ * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs
+ * containing swap entries all with consecutive offsets and targeting the same
+ * swap type, all with matching swp pte bits.
+ *
+ * max_nr must be at least one and must be limited by the caller so scanning
+ * cannot exceed a single page table.
+ *
+ * Return: the number of table entries in the batch.
+ */
+static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte)
+{
+	pte_t expected_pte = pte_next_swp_offset(pte);
+	const pte_t *end_ptep = start_ptep + max_nr;
+	pte_t *ptep = start_ptep + 1;
+
+	VM_WARN_ON(max_nr < 1);
+	VM_WARN_ON(!is_swap_pte(pte));
+	VM_WARN_ON(non_swap_entry(pte_to_swp_entry(pte)));
+
+	while (ptep < end_ptep) {
+		pte = ptep_get(ptep);
+
+		if (!pte_same(pte, expected_pte))
+			break;
+
+		expected_pte = pte_next_swp_offset(expected_pte);
+		ptep++;
+	}
+
+	return ptep - start_ptep;
+}
 #endif /* CONFIG_MMU */
 
 void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio,
diff --git a/mm/madvise.c b/mm/madvise.c
index 1f77a51baaac..5011ecb24344 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -628,6 +628,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 	struct folio *folio;
 	int nr_swap = 0;
 	unsigned long next;
+	int nr, max_nr;
 
 	next = pmd_addr_end(addr, end);
 	if (pmd_trans_huge(*pmd))
@@ -640,7 +641,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 		return 0;
 	flush_tlb_batched_pending(mm);
 	arch_enter_lazy_mmu_mode();
-	for (; addr != end; pte++, addr += PAGE_SIZE) {
+	for (; addr != end; pte += nr, addr += PAGE_SIZE * nr) {
+		nr = 1;
 		ptent = ptep_get(pte);
 
 		if (pte_none(ptent))
@@ -655,9 +657,11 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 
 			entry = pte_to_swp_entry(ptent);
 			if (!non_swap_entry(entry)) {
-				nr_swap--;
-				free_swap_and_cache(entry);
-				pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
+				max_nr = (end - addr) / PAGE_SIZE;
+				nr = swap_pte_batch(pte, max_nr, ptent);
+				nr_swap -= nr;
+				free_swap_and_cache_nr(entry, nr);
+				clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm);
 			} else if (is_hwpoison_entry(entry) ||
 				   is_poisoned_swp_entry(entry)) {
 				pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
diff --git a/mm/memory.c b/mm/memory.c
index 694e18837cd8..7880400370c8 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1637,12 +1637,13 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				folio_remove_rmap_pte(folio, page, vma);
 			folio_put(folio);
 		} else if (!non_swap_entry(entry)) {
-			/* Genuine swap entry, hence a private anon page */
+			max_nr = (end - addr) / PAGE_SIZE;
+			nr = swap_pte_batch(pte, max_nr, ptent);
+			/* Genuine swap entries, hence a private anon pages */
 			if (!should_zap_cows(details))
 				continue;
-			rss[MM_SWAPENTS]--;
-			if (unlikely(!free_swap_and_cache(entry)))
-				print_bad_pte(vma, addr, ptent, NULL);
+			rss[MM_SWAPENTS] -= nr;
+			free_swap_and_cache_nr(entry, nr);
 		} else if (is_migration_entry(entry)) {
 			folio = pfn_swap_entry_folio(entry);
 			if (!should_zap_folio(details, folio))
@@ -1665,8 +1666,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			pr_alert("unrecognized swap entry 0x%lx\n", entry.val);
 			WARN_ON_ONCE(1);
 		}
-		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
-		zap_install_uffd_wp_if_needed(vma, addr, pte, 1, details, ptent);
+		clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm);
+		zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent);
 	} while (pte += nr, addr += PAGE_SIZE * nr, addr != end);
 
 	add_mm_rss_vec(mm, rss);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 1ded6d1dcab4..20c45757f2b2 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -130,7 +130,11 @@ static inline unsigned char swap_count(unsigned char ent)
 /* Reclaim the swap entry if swap is getting full*/
 #define TTRS_FULL		0x4
 
-/* returns 1 if swap entry is freed */
+/*
+ * returns number of pages in the folio that backs the swap entry. If positive,
+ * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no
+ * folio was associated with the swap entry.
+ */
 static int __try_to_reclaim_swap(struct swap_info_struct *si,
 				 unsigned long offset, unsigned long flags)
 {
@@ -155,6 +159,7 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si,
 			ret = folio_free_swap(folio);
 		folio_unlock(folio);
 	}
+	ret = ret ? folio_nr_pages(folio) : -folio_nr_pages(folio);
 	folio_put(folio);
 	return ret;
 }
@@ -895,7 +900,7 @@ checks:
 		swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY);
 		spin_lock(&si->lock);
 		/* entry was freed successfully, try to use this again */
-		if (swap_was_freed)
+		if (swap_was_freed > 0)
 			goto checks;
 		goto scan; /* check next one */
 	}
@@ -1572,32 +1577,88 @@ bool folio_free_swap(struct folio *folio)
 	return true;
 }
 
-/*
- * Free the swap entry like above, but also try to
- * free the page cache entry if it is the last user.
+/**
+ * free_swap_and_cache_nr() - Release reference on range of swap entries and
+ *                            reclaim their cache if no more references remain.
+ * @entry: First entry of range.
+ * @nr: Number of entries in range.
+ *
+ * For each swap entry in the contiguous range, release a reference. If any swap
+ * entries become free, try to reclaim their underlying folios, if present. The
+ * offset range is defined by [entry.offset, entry.offset + nr).
  */
-int free_swap_and_cache(swp_entry_t entry)
+void free_swap_and_cache_nr(swp_entry_t entry, int nr)
 {
-	struct swap_info_struct *p;
+	const unsigned long start_offset = swp_offset(entry);
+	const unsigned long end_offset = start_offset + nr;
+	unsigned int type = swp_type(entry);
+	struct swap_info_struct *si;
+	bool any_only_cache = false;
+	unsigned long offset;
 	unsigned char count;
 
 	if (non_swap_entry(entry))
-		return 1;
+		return;
 
-	p = get_swap_device(entry);
-	if (p) {
-		if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) {
-			put_swap_device(p);
-			return 0;
+	si = get_swap_device(entry);
+	if (!si)
+		return;
+
+	if (WARN_ON(end_offset > si->max))
+		goto out;
+
+	/*
+	 * First free all entries in the range.
+	 */
+	for (offset = start_offset; offset < end_offset; offset++) {
+		if (data_race(si->swap_map[offset])) {
+			count = __swap_entry_free(si, swp_entry(type, offset));
+			if (count == SWAP_HAS_CACHE)
+				any_only_cache = true;
+		} else {
+			WARN_ON_ONCE(1);
 		}
+	}
+
+	/*
+	 * Short-circuit the below loop if none of the entries had their
+	 * reference drop to zero.
+	 */
+	if (!any_only_cache)
+		goto out;
 
-		count = __swap_entry_free(p, entry);
-		if (count == SWAP_HAS_CACHE)
-			__try_to_reclaim_swap(p, swp_offset(entry),
+	/*
+	 * Now go back over the range trying to reclaim the swap cache. This is
+	 * more efficient for large folios because we will only try to reclaim
+	 * the swap once per folio in the common case. If we do
+	 * __swap_entry_free() and __try_to_reclaim_swap() in the same loop, the
+	 * latter will get a reference and lock the folio for every individual
+	 * page but will only succeed once the swap slot for every subpage is
+	 * zero.
+	 */
+	for (offset = start_offset; offset < end_offset; offset += nr) {
+		nr = 1;
+		if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) {
+			/*
+			 * Folios are always naturally aligned in swap so
+			 * advance forward to the next boundary. Zero means no
+			 * folio was found for the swap entry, so advance by 1
+			 * in this case. Negative value means folio was found
+			 * but could not be reclaimed. Here we can still advance
+			 * to the next boundary.
+			 */
+			nr = __try_to_reclaim_swap(si, offset,
 					      TTRS_UNMAPPED | TTRS_FULL);
-		put_swap_device(p);
+			if (nr == 0)
+				nr = 1;
+			else if (nr < 0)
+				nr = -nr;
+			nr = ALIGN(offset + 1, nr) - offset;
+		}
 	}
-	return p != NULL;
+
+out:
+	put_swap_device(si);
 }
 
 #ifdef CONFIG_HIBERNATION