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>

2 files changed, 29 insertions, 3 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 4d7bb98f4134..4f93a6d10a47 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -846,7 +846,23 @@ static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	barrier();
 #endif
-	if (pmd_none(pmdval) || pmd_trans_huge(pmdval))
+	/*
+	 * !pmd_present() checks for pmd migration entries
+	 *
+	 * The complete check uses is_pmd_migration_entry() in linux/swapops.h
+	 * But using that requires moving current function and pmd_trans_unstable()
+	 * to linux/swapops.h to resovle dependency, which is too much code move.
+	 *
+	 * !pmd_present() is equivalent to is_pmd_migration_entry() currently,
+	 * because !pmd_present() pages can only be under migration not swapped
+	 * out.
+	 *
+	 * pmd_none() is preseved for future condition checks on pmd migration
+	 * entries and not confusing with this function name, although it is
+	 * redundant with !pmd_present().
+	 */
+	if (pmd_none(pmdval) || pmd_trans_huge(pmdval) ||
+		(IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION) && !pmd_present(pmdval)))
 		return 1;
 	if (unlikely(pmd_bad(pmdval))) {
 		pmd_clear_bad(pmd);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index d8f35a0865dc..14bc21c2ee7f 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -147,7 +147,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 #define split_huge_pmd(__vma, __pmd, __address)				\
 	do {								\
 		pmd_t *____pmd = (__pmd);				\
-		if (pmd_trans_huge(*____pmd)				\
+		if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd)	\
 					|| pmd_devmap(*____pmd))	\
 			__split_huge_pmd(__vma, __pmd, __address,	\
 						false, NULL);		\
@@ -178,12 +178,18 @@ extern spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd,
 		struct vm_area_struct *vma);
 extern spinlock_t *__pud_trans_huge_lock(pud_t *pud,
 		struct vm_area_struct *vma);
+
+static inline int is_swap_pmd(pmd_t pmd)
+{
+	return !pmd_none(pmd) && !pmd_present(pmd);
+}
+
 /* mmap_sem must be held on entry */
 static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
 		struct vm_area_struct *vma)
 {
 	VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
-	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd))
+	if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd))
 		return __pmd_trans_huge_lock(pmd, vma);
 	else
 		return NULL;
@@ -299,6 +305,10 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
 					 long adjust_next)
 {
 }
+static inline int is_swap_pmd(pmd_t pmd)
+{
+	return 0;
+}
 static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
 		struct vm_area_struct *vma)
 {