mm: thp: check pmd migration entry in common path

When THP migration is being used, memory management code needs to handle
pmd migration entries properly.  This patch uses !pmd_present() or
is_swap_pmd() (depending on whether pmd_none() needs separate code or
not) to check pmd migration entries at the places where a pmd entry is
present.

Since pmd-related code uses split_huge_page(), split_huge_pmd(),
pmd_trans_huge(), pmd_trans_unstable(), or
pmd_none_or_trans_huge_or_clear_bad(), this patch:

1. adds pmd migration entry split code in split_huge_pmd(),

2. takes care of pmd migration entries whenever pmd_trans_huge() is present,

3. makes pmd_none_or_trans_huge_or_clear_bad() pmd migration entry aware.

Since split_huge_page() uses split_huge_pmd() and pmd_trans_unstable()
is equivalent to pmd_none_or_trans_huge_or_clear_bad(), we do not change
them.

Until this commit, a pmd entry should be:
1. pointing to a pte page,
2. is_swap_pmd(),
3. pmd_trans_huge(),
4. pmd_devmap(), or
5. pmd_none().

Signed-off-by: Zi Yan <zi.yan@cs.rutgers.edu>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Nellans <dnellans@nvidia.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 59 insertions, 6 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 937f007794dd..b82585eabe85 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -928,6 +928,23 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 
 	ret = -EAGAIN;
 	pmd = *src_pmd;
+
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+	if (unlikely(is_swap_pmd(pmd))) {
+		swp_entry_t entry = pmd_to_swp_entry(pmd);
+
+		VM_BUG_ON(!is_pmd_migration_entry(pmd));
+		if (is_write_migration_entry(entry)) {
+			make_migration_entry_read(&entry);
+			pmd = swp_entry_to_pmd(entry);
+			set_pmd_at(src_mm, addr, src_pmd, pmd);
+		}
+		set_pmd_at(dst_mm, addr, dst_pmd, pmd);
+		ret = 0;
+		goto out_unlock;
+	}
+#endif
+
 	if (unlikely(!pmd_trans_huge(pmd))) {
 		pte_free(dst_mm, pgtable);
 		goto out_unlock;
@@ -1599,6 +1616,12 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	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;
+	}
+
 	page = pmd_page(orig_pmd);
 	/*
 	 * If other processes are mapping this page, we couldn't discard
@@ -1810,6 +1833,25 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	preserve_write = prot_numa && pmd_write(*pmd);
 	ret = 1;
 
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+	if (is_swap_pmd(*pmd)) {
+		swp_entry_t entry = pmd_to_swp_entry(*pmd);
+
+		VM_BUG_ON(!is_pmd_migration_entry(*pmd));
+		if (is_write_migration_entry(entry)) {
+			pmd_t newpmd;
+			/*
+			 * A protection check is difficult so
+			 * just be safe and disable write
+			 */
+			make_migration_entry_read(&entry);
+			newpmd = swp_entry_to_pmd(entry);
+			set_pmd_at(mm, addr, pmd, newpmd);
+		}
+		goto unlock;
+	}
+#endif
+
 	/*
 	 * Avoid trapping faults against the zero page. The read-only
 	 * data is likely to be read-cached on the local CPU and
@@ -1875,7 +1917,8 @@ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
 {
 	spinlock_t *ptl;
 	ptl = pmd_lock(vma->vm_mm, pmd);
-	if (likely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd)))
+	if (likely(is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) ||
+			pmd_devmap(*pmd)))
 		return ptl;
 	spin_unlock(ptl);
 	return NULL;
@@ -1993,14 +2036,15 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	struct page *page;
 	pgtable_t pgtable;
 	pmd_t _pmd;
-	bool young, write, dirty, soft_dirty;
+	bool young, write, dirty, soft_dirty, pmd_migration = false;
 	unsigned long addr;
 	int i;
 
 	VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
 	VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
 	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma);
-	VM_BUG_ON(!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd));
+	VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd)
+				&& !pmd_devmap(*pmd));
 
 	count_vm_event(THP_SPLIT_PMD);
 
@@ -2025,7 +2069,16 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		return __split_huge_zero_page_pmd(vma, haddr, pmd);
 	}
 
-	page = pmd_page(*pmd);
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+	pmd_migration = is_pmd_migration_entry(*pmd);
+	if (pmd_migration) {
+		swp_entry_t entry;
+
+		entry = pmd_to_swp_entry(*pmd);
+		page = pfn_to_page(swp_offset(entry));
+	} else
+#endif
+		page = pmd_page(*pmd);
 	VM_BUG_ON_PAGE(!page_count(page), page);
 	page_ref_add(page, HPAGE_PMD_NR - 1);
 	write = pmd_write(*pmd);
@@ -2044,7 +2097,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		 * transferred to avoid any possibility of altering
 		 * permissions across VMAs.
 		 */
-		if (freeze) {
+		if (freeze || pmd_migration) {
 			swp_entry_t swp_entry;
 			swp_entry = make_migration_entry(page + i, write);
 			entry = swp_entry_to_pte(swp_entry);
@@ -2143,7 +2196,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		page = pmd_page(*pmd);
 		if (PageMlocked(page))
 			clear_page_mlock(page);
-	} else if (!pmd_devmap(*pmd))
+	} else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)))
 		goto out;
 	__split_huge_pmd_locked(vma, pmd, haddr, freeze);
 out: