[PATCH 01/15] fork: pass the dst vma to copy_page_range() and its sub-functions.

[JÃrÃme Glisse]

For HMM we will need to resort to the old way of allocating new page
for anonymous memory when that anonymous memory have been migrated
to device memory.

This does not impact any process that do not use HMM through some
device driver. Only process that migrate anonymous memory to device
memory with HMM will have to copy migrated page on fork.

We do not expect this to be a common or advised thing to do so we
resort to the simpler solution of allocating new page. If this kind
of usage turns out to be important we will revisit way to achieve
COW even for remote memory.

Signed-off-by: JÃrÃme Glisse <jglisse@xxxxxxxxxx>
---
 include/linux/mm.h |  5 +++--
 kernel/fork.c      |  2 +-
 mm/memory.c        | 33 +++++++++++++++++++++------------
 3 files changed, 25 insertions(+), 15 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index b5bf210..580fe65 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1124,8 +1124,9 @@ int walk_page_range(unsigned long addr, unsigned long end,
 int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk);
 void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
-int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
-			struct vm_area_struct *vma);
+int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		    struct vm_area_struct *dst_vma,
+		    struct vm_area_struct *vma);
 void unmap_mapping_range(struct address_space *mapping,
 		loff_t const holebegin, loff_t const holelen, int even_cows);
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
diff --git a/kernel/fork.c b/kernel/fork.c
index bf2dcb6..2d32a4b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -497,7 +497,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		rb_parent = &tmp->vm_rb;
 
 		mm->map_count++;
-		retval = copy_page_range(mm, oldmm, mpnt);
+		retval = copy_page_range(mm, oldmm, tmp, mpnt);
 
 		if (tmp->vm_ops && tmp->vm_ops->open)
 			tmp->vm_ops->open(tmp);
diff --git a/mm/memory.c b/mm/memory.c
index d784e35..71b5c35 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -885,8 +885,10 @@ out_set_pte:
 }
 
 static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		   pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma,
-		   unsigned long addr, unsigned long end)
+			  pmd_t *dst_pmd, pmd_t *src_pmd,
+			  struct vm_area_struct *dst_vma,
+			  struct vm_area_struct *vma,
+			  unsigned long addr, unsigned long end)
 {
 	pte_t *orig_src_pte, *orig_dst_pte;
 	pte_t *src_pte, *dst_pte;
@@ -947,9 +949,12 @@ again:
 	return 0;
 }
 
-static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma,
-		unsigned long addr, unsigned long end)
+static inline int copy_pmd_range(struct mm_struct *dst_mm,
+				 struct mm_struct *src_mm,
+				 pud_t *dst_pud, pud_t *src_pud,
+				 struct vm_area_struct *dst_vma,
+				 struct vm_area_struct *vma,
+				 unsigned long addr, unsigned long end)
 {
 	pmd_t *src_pmd, *dst_pmd;
 	unsigned long next;
@@ -974,15 +979,18 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 		if (pmd_none_or_clear_bad(src_pmd))
 			continue;
 		if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
-						vma, addr, next))
+				   dst_vma, vma, addr, next))
 			return -ENOMEM;
 	} while (dst_pmd++, src_pmd++, addr = next, addr != end);
 	return 0;
 }
 
-static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
-		unsigned long addr, unsigned long end)
+static inline int copy_pud_range(struct mm_struct *dst_mm,
+				 struct mm_struct *src_mm,
+				 pgd_t *dst_pgd, pgd_t *src_pgd,
+				 struct vm_area_struct *dst_vma,
+				 struct vm_area_struct *vma,
+				 unsigned long addr, unsigned long end)
 {
 	pud_t *src_pud, *dst_pud;
 	unsigned long next;
@@ -996,14 +1004,15 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
 		if (pud_none_or_clear_bad(src_pud))
 			continue;
 		if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud,
-						vma, addr, next))
+				   dst_vma, vma, addr, next))
 			return -ENOMEM;
 	} while (dst_pud++, src_pud++, addr = next, addr != end);
 	return 0;
 }
 
 int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		struct vm_area_struct *vma)
+		    struct vm_area_struct *dst_vma,
+		    struct vm_area_struct *vma)
 {
 	pgd_t *src_pgd, *dst_pgd;
 	unsigned long next;
@@ -1057,7 +1066,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		if (pgd_none_or_clear_bad(src_pgd))
 			continue;
 		if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
-					    vma, addr, next))) {
+					    dst_vma, vma, addr, next))) {
 			ret = -ENOMEM;
 			break;
 		}
-- 
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/