[RESEND v7 22/29] mm/mincore: report PMD swap-cache residency

[Usama Arif]

mincore_pte_range() reports every page under a huge PMD as resident. That
is wrong for a swapped-out one: mincore() would tell userspace that memory
it will have to fault in is already in core.

A PMD swap entry is only a compact encoding for HPAGE_PMD_NR slots, so
answer from the swap cache instead. One PMD-sized folio covering the range
makes every page resident exactly when that folio is uptodate; an empty
cache makes none of them; and if the folio was split while the entry stayed
in place, fall back to looking up each covered slot as mincore_swap() does
for a PTE swap entry.

Signed-off-by: Usama Arif <usama.arif@xxxxxxxxx>
---
 mm/mincore.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 46 insertions(+), 1 deletion(-)

diff --git a/mm/mincore.c b/mm/mincore.c
index c086836bc4bcc..1846c6f68ae63 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -85,6 +85,48 @@ static unsigned char mincore_swap(swp_entry_t entry, bool shmem)
 	return present;
 }
 
+#ifdef CONFIG_THP_SWAP
+static void mincore_pmd_swap(swp_entry_t entry, unsigned long addr,
+			     unsigned long end, unsigned char *vec)
+{
+	unsigned long haddr = addr & HPAGE_PMD_MASK;
+	unsigned long start = (addr - haddr) >> PAGE_SHIFT;
+	unsigned long nr = (end - addr) >> PAGE_SHIFT;
+	struct folio *folio;
+	enum swap_pmd_cache state;
+	int i;
+
+	state = swap_pmd_cache_lookup(entry, &folio);
+	if (state == SWAP_PMD_CACHE_HUGE) {
+		memset(vec, folio_test_uptodate(folio), nr);
+		folio_put(folio);
+		return;
+	}
+
+	if (state == SWAP_PMD_CACHE_EMPTY) {
+		memset(vec, 0, nr);
+		return;
+	}
+
+	/*
+	 * The PMD swap entry is only a compact encoding for consecutive swap
+	 * slots. If the PMD-sized swapcache folio was split, report residency
+	 * from the individual slots covered by this mincore() range.
+	 */
+	for (i = 0; i < nr; i++)
+		vec[i] = mincore_swap(swp_entry(swp_type(entry),
+						swp_offset(entry) + start + i),
+				      false);
+}
+#else	/* !CONFIG_THP_SWAP */
+static void mincore_pmd_swap(swp_entry_t entry, unsigned long addr,
+			     unsigned long end, unsigned char *vec)
+{
+	/* Nothing produces PMD swap entries without CONFIG_THP_SWAP. */
+	memset(vec, 0, (end - addr) >> PAGE_SHIFT);
+}
+#endif	/* CONFIG_THP_SWAP */
+
 /*
  * Later we can get more picky about what "in core" means precisely.
  * For now, simply check to see if the page is in the page cache,
@@ -171,7 +213,10 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (ptl) {
-		memset(vec, 1, nr);
+		if (pmd_is_swap_entry(*pmd))
+			mincore_pmd_swap(softleaf_from_pmd(*pmd), addr, end, vec);
+		else
+			memset(vec, 1, nr);
 		spin_unlock(ptl);
 		goto out;
 	}
-- 
2.53.0-Meta