[PATCH -V5 13/21] swap: Support PMD swap mapping in madvise_free()

[Huang Ying]

When madvise_free() found a PMD swap mapping, if only part of the huge
swap cluster is operated on, the PMD swap mapping will be split and
fallback to PTE swap mapping processing.  Otherwise, if all huge swap
cluster is operated on, free_swap_and_cache() will be called to
decrease the PMD swap mapping count and probably free the swap space
and the THP in swap cache too.

Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Shaohua Li <shli@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Zi Yan <zi.yan@xxxxxxxxxxxxxx>
Cc: Daniel Jordan <daniel.m.jordan@xxxxxxxxxx>
---
 mm/huge_memory.c | 54 +++++++++++++++++++++++++++++++++++++++---------------
 mm/madvise.c     |  2 +-
 2 files changed, 40 insertions(+), 16 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4b7ee510a9fe..656e760d19e2 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1844,6 +1844,15 @@ int do_huge_pmd_swap_page(struct vm_fault *vmf, pmd_t orig_pmd)
 }
 #endif
 
+static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd)
+{
+	pgtable_t pgtable;
+
+	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
+	pte_free(mm, pgtable);
+	mm_dec_nr_ptes(mm);
+}
+
 /*
  * Return true if we do MADV_FREE successfully on entire pmd page.
  * Otherwise, return false.
@@ -1864,15 +1873,39 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		goto out_unlocked;
 
 	orig_pmd = *pmd;
-	if (is_huge_zero_pmd(orig_pmd))
-		goto out;
-
 	if (unlikely(!pmd_present(orig_pmd))) {
-		VM_BUG_ON(thp_migration_supported() &&
-				  !is_pmd_migration_entry(orig_pmd));
-		goto out;
+		swp_entry_t entry = pmd_to_swp_entry(orig_pmd);
+
+		if (is_migration_entry(entry)) {
+			VM_BUG_ON(!thp_migration_supported());
+			goto out;
+		} else if (IS_ENABLED(CONFIG_THP_SWAP) &&
+			   !non_swap_entry(entry)) {
+			/*
+			 * If part of THP is discarded, split the PMD
+			 * swap mapping and operate on the PTEs
+			 */
+			if (next - addr != HPAGE_PMD_SIZE) {
+				unsigned long haddr = addr & HPAGE_PMD_MASK;
+
+				__split_huge_swap_pmd(vma, haddr, pmd);
+				goto out;
+			}
+			free_swap_and_cache(entry, HPAGE_PMD_NR);
+			pmd_clear(pmd);
+			zap_deposited_table(mm, pmd);
+			if (current->mm == mm)
+				sync_mm_rss(mm);
+			add_mm_counter(mm, MM_SWAPENTS, -HPAGE_PMD_NR);
+			ret = true;
+			goto out;
+		} else
+			VM_BUG_ON(1);
 	}
 
+	if (is_huge_zero_pmd(orig_pmd))
+		goto out;
+
 	page = pmd_page(orig_pmd);
 	/*
 	 * If other processes are mapping this page, we couldn't discard
@@ -1918,15 +1951,6 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	return ret;
 }
 
-static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd)
-{
-	pgtable_t pgtable;
-
-	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
-	pte_free(mm, pgtable);
-	mm_dec_nr_ptes(mm);
-}
-
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 pmd_t *pmd, unsigned long addr)
 {
diff --git a/mm/madvise.c b/mm/madvise.c
index 50282ba862e2..20101ff125d0 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -321,7 +321,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 	unsigned long next;
 
 	next = pmd_addr_end(addr, end);
-	if (pmd_trans_huge(*pmd))
+	if (pmd_trans_huge(*pmd) || is_swap_pmd(*pmd))
 		if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next))
 			goto next;
 
-- 
2.16.4