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>

2 files changed, 38 insertions, 3 deletions

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index a3fc8150b047..75096025fe52 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -708,6 +708,35 @@ static inline void pte_clear_not_present_full(struct mm_struct *mm,
 }
 #endif
 
+#ifndef clear_not_present_full_ptes
+/**
+ * clear_not_present_full_ptes - Clear multiple not present PTEs which are
+ *				 consecutive in the pgtable.
+ * @mm: Address space the ptes represent.
+ * @addr: Address of the first pte.
+ * @ptep: Page table pointer for the first entry.
+ * @nr: Number of entries to clear.
+ * @full: Whether we are clearing a full mm.
+ *
+ * May be overridden by the architecture; otherwise, implemented as a simple
+ * loop over pte_clear_not_present_full().
+ *
+ * Context: The caller holds the page table lock.  The PTEs are all not present.
+ * The PTEs are all in the same PMD.
+ */
+static inline void clear_not_present_full_ptes(struct mm_struct *mm,
+		unsigned long addr, pte_t *ptep, unsigned int nr, int full)
+{
+	for (;;) {
+		pte_clear_not_present_full(mm, addr, ptep, full);
+		if (--nr == 0)
+			break;
+		ptep++;
+		addr += PAGE_SIZE;
+	}
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
 extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
 			      unsigned long address,
diff --git a/include/linux/swap.h b/include/linux/swap.h
index a803de0ac24f..2d8f2b950ddf 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -468,7 +468,7 @@ extern int swap_duplicate(swp_entry_t);
 extern int swapcache_prepare(swp_entry_t);
 extern void swap_free(swp_entry_t);
 extern void swapcache_free_entries(swp_entry_t *entries, int n);
-extern int free_swap_and_cache(swp_entry_t);
+extern void free_swap_and_cache_nr(swp_entry_t entry, int nr);
 int swap_type_of(dev_t device, sector_t offset);
 int find_first_swap(dev_t *device);
 extern unsigned int count_swap_pages(int, int);
@@ -517,8 +517,9 @@ static inline void put_swap_device(struct swap_info_struct *si)
 #define free_pages_and_swap_cache(pages, nr) \
 	release_pages((pages), (nr));
 
-/* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */
-#define free_swap_and_cache(e) is_pfn_swap_entry(e)
+static inline void free_swap_and_cache_nr(swp_entry_t entry, int nr)
+{
+}
 
 static inline void free_swap_cache(struct folio *folio)
 {
@@ -586,6 +587,11 @@ static inline int add_swap_extent(struct swap_info_struct *sis,
 }
 #endif /* CONFIG_SWAP */
 
+static inline void free_swap_and_cache(swp_entry_t entry)
+{
+	free_swap_and_cache_nr(entry, 1);
+}
+
 #ifdef CONFIG_MEMCG
 static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
 {