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, 20 insertions, 2 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 33d651deeae2..76fd199aaae2 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -234,6 +234,16 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
                         return page;
                 return no_page_table(vma, flags);
         }
+retry:
+        if (!pmd_present(*pmd)) {
+                if (likely(!(flags & FOLL_MIGRATION)))
+                        return no_page_table(vma, flags);
+                VM_BUG_ON(thp_migration_supported() &&
+                                  !is_pmd_migration_entry(*pmd));
+                if (is_pmd_migration_entry(*pmd))
+                        pmd_migration_entry_wait(mm, pmd);
+                goto retry;
+        }
         if (pmd_devmap(*pmd)) {
                 ptl = pmd_lock(mm, pmd);
                 page = follow_devmap_pmd(vma, address, pmd, flags);
@@ -247,7 +257,15 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
         if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
                 return no_page_table(vma, flags);
 
+retry_locked:
         ptl = pmd_lock(mm, pmd);
+        if (unlikely(!pmd_present(*pmd))) {
+                spin_unlock(ptl);
+                if (likely(!(flags & FOLL_MIGRATION)))
+                        return no_page_table(vma, flags);
+                pmd_migration_entry_wait(mm, pmd);
+                goto retry_locked;
+        }
         if (unlikely(!pmd_trans_huge(*pmd))) {
                 spin_unlock(ptl);
                 return follow_page_pte(vma, address, pmd, flags);
@@ -424,7 +442,7 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
         pud = pud_offset(p4d, address);
         BUG_ON(pud_none(*pud));
         pmd = pmd_offset(pud, address);
-        if (pmd_none(*pmd))
+        if (!pmd_present(*pmd))
                 return -EFAULT;
         VM_BUG_ON(pmd_trans_huge(*pmd));
         pte = pte_offset_map(pmd, address);
@@ -1534,7 +1552,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
                 pmd_t pmd = READ_ONCE(*pmdp);
 
                 next = pmd_addr_end(addr, end);
-                if (pmd_none(pmd))
+                if (!pmd_present(pmd))
                         return 0;
 
                 if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) {