hugetlb: follow_hugetlb_page() for write access

When calling get_user_pages(), a write flag is passed in by the caller to
indicate if write access is required on the faulted-in pages.  Currently,
follow_hugetlb_page() ignores this flag and always faults pages for
read-only access.  This can cause data corruption because a device driver
that calls get_user_pages() with write set will not expect COW faults to
occur on the returned pages.

This patch passes the write flag down to follow_hugetlb_page() and makes
sure hugetlb_fault() is called with the right write_access parameter.

[ezk@cs.sunysb.edu: build fix]
Signed-off-by: Adam Litke <agl@us.ibm.com>
Reviewed-by: Ken Chen <kenchen@google.com>
Cc: David Gibson <hermes@gibson.dropbear.id.au>
Cc: William Lee Irwin III <wli@holomorphy.com>
Cc: Badari Pulavarty <pbadari@us.ibm.com>
Signed-off-by: Erez Zadok <ezk@cs.sunysb.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ea0f50bfbe030dda0ff6d5b1ea22b5f346302279..e22368656b38550f6e16b8252a95202b32d2cb01 100644 (file)
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -19,7 +19,7 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
 int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *);
 int hugetlb_treat_movable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *);
 int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
-int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int);
+int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int, int);
 void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long);
 void __unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long);
 int hugetlb_prefault(struct address_space *, struct vm_area_struct *);
@@ -106,7 +106,7 @@ static inline unsigned long hugetlb_total_pages(void)
        return 0;
 }
 
-#define follow_hugetlb_page(m,v,p,vs,a,b,i)    ({ BUG(); 0; })
+#define follow_hugetlb_page(m,v,p,vs,a,b,i,w)  ({ BUG(); 0; })
 #define follow_huge_addr(mm, addr, write)      ERR_PTR(-EINVAL)
 #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; })
 #define hugetlb_prefault(mapping, vma)         ({ BUG(); 0; })

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8b809ecefa39e4b54f4bfbed8830009a9e260e96..e2c80631d36a29c5c9f93454c6cddebd5d218265 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -868,7 +868,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
                        struct page **pages, struct vm_area_struct **vmas,
-                       unsigned long *position, int *length, int i)
+                       unsigned long *position, int *length, int i,
+                       int write)
 {
        unsigned long pfn_offset;
        unsigned long vaddr = *position;
@@ -890,7 +891,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
                        int ret;
 
                        spin_unlock(&mm->page_table_lock);
-                       ret = hugetlb_fault(mm, vma, vaddr, 0);
+                       ret = hugetlb_fault(mm, vma, vaddr, write);
                        spin_lock(&mm->page_table_lock);
                        if (!(ret & VM_FAULT_ERROR))
                                continue;

diff --git a/mm/memory.c b/mm/memory.c
index 9791e4786843f40438a97910728ec580664d1d4e..7b0403bfc97fb18c0ca08cd275f30149ca31329a 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1036,7 +1036,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
                if (is_vm_hugetlb_page(vma)) {
                        i = follow_hugetlb_page(mm, vma, pages, vmas,
-                                               &start, &len, i);
+                                               &start, &len, i, write);
                        continue;
                }