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>

1 files changed, 64 insertions, 0 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,