mm, x86: get_user_pages() for dax mappings

[linux-beck.git] / mm / huge_memory.c

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 82bed2bec3ed8afdf787d78b0ad14f7b70df6cb1..b2db98136af9d574646ef3f25d3cf1d462c174c1 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -23,6 +23,7 @@
 #include <linux/freezer.h>
 #include <linux/pfn_t.h>
 #include <linux/mman.h>
+#include <linux/memremap.h>
 #include <linux/pagemap.h>
 #include <linux/debugfs.h>
 #include <linux/migrate.h>
@@ -974,6 +975,63 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
        return VM_FAULT_NOPAGE;
 }
 
+static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
+               pmd_t *pmd)
+{
+       pmd_t _pmd;
+
+       /*
+        * We should set the dirty bit only for FOLL_WRITE but for now
+        * the dirty bit in the pmd is meaningless.  And if the dirty
+        * bit will become meaningful and we'll only set it with
+        * FOLL_WRITE, an atomic set_bit will be required on the pmd to
+        * set the young bit, instead of the current set_pmd_at.
+        */
+       _pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
+       if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
+                               pmd, _pmd,  1))
+               update_mmu_cache_pmd(vma, addr, pmd);
+}
+
+struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
+               pmd_t *pmd, int flags)
+{
+       unsigned long pfn = pmd_pfn(*pmd);
+       struct mm_struct *mm = vma->vm_mm;
+       struct dev_pagemap *pgmap;
+       struct page *page;
+
+       assert_spin_locked(pmd_lockptr(mm, pmd));
+
+       if (flags & FOLL_WRITE && !pmd_write(*pmd))
+               return NULL;
+
+       if (pmd_present(*pmd) && pmd_devmap(*pmd))
+               /* pass */;
+       else
+               return NULL;
+
+       if (flags & FOLL_TOUCH)
+               touch_pmd(vma, addr, pmd);
+
+       /*
+        * device mapped pages can only be returned if the
+        * caller will manage the page reference count.
+        */
+       if (!(flags & FOLL_GET))
+               return ERR_PTR(-EEXIST);
+
+       pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
+       pgmap = get_dev_pagemap(pfn, NULL);
+       if (!pgmap)
+               return ERR_PTR(-EFAULT);
+       page = pfn_to_page(pfn);
+       get_page(page);
+       put_dev_pagemap(pgmap);
+
+       return page;
+}
+
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
                  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
                  struct vm_area_struct *vma)
@@ -1331,21 +1389,8 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 
        page = pmd_page(*pmd);
        VM_BUG_ON_PAGE(!PageHead(page), page);
-       if (flags & FOLL_TOUCH) {
-               pmd_t _pmd;
-               /*
-                * We should set the dirty bit only for FOLL_WRITE but
-                * for now the dirty bit in the pmd is meaningless.
-                * And if the dirty bit will become meaningful and
-                * we'll only set it with FOLL_WRITE, an atomic
-                * set_bit will be required on the pmd to set the
-                * young bit, instead of the current set_pmd_at.
-                */
-               _pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
-               if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK,
-                                         pmd, _pmd,  1))
-                       update_mmu_cache_pmd(vma, addr, pmd);
-       }
+       if (flags & FOLL_TOUCH)
+               touch_pmd(vma, addr, pmd);
        if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
                /*
                 * We don't mlock() pte-mapped THPs. This way we can avoid