mm/migrate: support un-addressable ZONE_DEVICE page in migration

Allow to unmap and restore special swap entry of un-addressable
ZONE_DEVICE memory.

Link: http://lkml.kernel.org/r/20170817000548.32038-17-jglisse@redhat.com
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Nellans <dnellans@nvidia.com>
Cc: Evgeny Baskakov <ebaskakov@nvidia.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Mark Hairgrove <mhairgrove@nvidia.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Sherry Cheung <SCheung@nvidia.com>
Cc: Subhash Gutti <sgutti@nvidia.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Bob Liu <liubo95@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 26 insertions, 0 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index 7dc9c02f7106..0618cd85b862 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -63,6 +63,7 @@
 #include <linux/hugetlb.h>
 #include <linux/backing-dev.h>
 #include <linux/page_idle.h>
+#include <linux/memremap.h>
 
 #include <asm/tlbflush.h>
 
@@ -1346,6 +1347,10 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
         if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
                 return true;
 
+        if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) &&
+            is_zone_device_page(page) && !is_device_private_page(page))
+                return true;
+
         if (flags & TTU_SPLIT_HUGE_PMD) {
                 split_huge_pmd_address(vma, address,
                                 flags & TTU_SPLIT_FREEZE, page);
@@ -1403,6 +1408,27 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
                 address = pvmw.address;
 
 
+                if (IS_ENABLED(CONFIG_MIGRATION) &&
+                    (flags & TTU_MIGRATION) &&
+                    is_zone_device_page(page)) {
+                        swp_entry_t entry;
+                        pte_t swp_pte;
+
+                        pteval = ptep_get_and_clear(mm, pvmw.address, pvmw.pte);
+
+                        /*
+                         * Store the pfn of the page in a special migration
+                         * pte. do_swap_page() will wait until the migration
+                         * pte is removed and then restart fault handling.
+                         */
+                        entry = make_migration_entry(page, 0);
+                        swp_pte = swp_entry_to_pte(entry);
+                        if (pte_soft_dirty(pteval))
+                                swp_pte = pte_swp_mksoft_dirty(swp_pte);
+                        set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
+                        goto discard;
+                }
+
                 if (!(flags & TTU_IGNORE_ACCESS)) {
                         if (ptep_clear_flush_young_notify(vma, address,
                                                 pvmw.pte)) {