mm/device-public-memory: device memory cache coherent with CPU

Platform with advance system bus (like CAPI or CCIX) allow device memory
to be accessible from CPU in a cache coherent fashion.  Add a new type of
ZONE_DEVICE to represent such memory.  The use case are the same as for
the un-addressable device memory but without all the corners cases.

Link: http://lkml.kernel.org/r/20170817000548.32038-19-jglisse@redhat.com
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Balbir Singh <bsingharora@gmail.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: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mark Hairgrove <mhairgrove@nvidia.com>
Cc: Michal Hocko <mhocko@kernel.org>
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, 41 insertions, 5 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 079eeac0b009..ad0ea1af1f44 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -818,8 +818,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
 #else
 # define HAVE_PTE_SPECIAL 0
 #endif
-struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
-                                pte_t pte)
+struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+                             pte_t pte, bool with_public_device)
 {
         unsigned long pfn = pte_pfn(pte);
 
@@ -830,8 +830,31 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
                         return vma->vm_ops->find_special_page(vma, addr);
                 if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
                         return NULL;
-                if (!is_zero_pfn(pfn))
-                        print_bad_pte(vma, addr, pte, NULL);
+                if (is_zero_pfn(pfn))
+                        return NULL;
+
+                /*
+                 * Device public pages are special pages (they are ZONE_DEVICE
+                 * pages but different from persistent memory). They behave
+                 * allmost like normal pages. The difference is that they are
+                 * not on the lru and thus should never be involve with any-
+                 * thing that involve lru manipulation (mlock, numa balancing,
+                 * ...).
+                 *
+                 * This is why we still want to return NULL for such page from
+                 * vm_normal_page() so that we do not have to special case all
+                 * call site of vm_normal_page().
+                 */
+                if (likely(pfn < highest_memmap_pfn)) {
+                        struct page *page = pfn_to_page(pfn);
+
+                        if (is_device_public_page(page)) {
+                                if (with_public_device)
+                                        return page;
+                                return NULL;
+                        }
+                }
+                print_bad_pte(vma, addr, pte, NULL);
                 return NULL;
         }
 
@@ -1012,6 +1035,19 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
                 get_page(page);
                 page_dup_rmap(page, false);
                 rss[mm_counter(page)]++;
+        } else if (pte_devmap(pte)) {
+                page = pte_page(pte);
+
+                /*
+                 * Cache coherent device memory behave like regular page and
+                 * not like persistent memory page. For more informations see
+                 * MEMORY_DEVICE_CACHE_COHERENT in memory_hotplug.h
+                 */
+                if (is_device_public_page(page)) {
+                        get_page(page);
+                        page_dup_rmap(page, false);
+                        rss[mm_counter(page)]++;
+                }
         }
 
 out_set_pte:
@@ -1267,7 +1303,7 @@ again:
                 if (pte_present(ptent)) {
                         struct page *page;
 
-                        page = vm_normal_page(vma, addr, ptent);
+                        page = _vm_normal_page(vma, addr, ptent, true);
                         if (unlikely(details) && page) {
                                 /*
                                  * unmap_shared_mapping_pages() wants to