mm: directly use __mlock_vma_pages_range() in find_extend_vma()

In find_extend_vma(), we don't need mlock_vma_pages_range() to verify
the vma type - we know we're working with a stack.  So, we can call
directly into __mlock_vma_pages_range(), and remove the last
make_pages_present() call site.

Note that we don't use mm_populate() here, so we can't release the
mmap_sem while allocating new stack pages.  This is deemed acceptable,
because the stack vmas grow by a bounded number of pages at a time, and
these are anon pages so we don't have to read from disk to populate
them.

Signed-off-by: Michel Lespinasse <walken@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Tested-by: Andy Lutomirski <luto@amacapital.net>
Cc: Greg Ungerer <gregungerer@westnet.com.au>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8332f30..0c34d34 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1035,7 +1035,6 @@ static inline int fixup_user_fault(struct task_struct *tsk,
 }
 #endif
 
-extern int make_pages_present(unsigned long addr, unsigned long end);
 extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
                void *buf, int len, int write);

diff --git a/mm/internal.h b/mm/internal.h
index 9ba2110..1c0c4cc 100644 (file)
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -162,8 +162,8 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
                struct vm_area_struct *prev, struct rb_node *rb_parent);
 
 #ifdef CONFIG_MMU
-extern long mlock_vma_pages_range(struct vm_area_struct *vma,
-                       unsigned long start, unsigned long end);
+extern long __mlock_vma_pages_range(struct vm_area_struct *vma,
+               unsigned long start, unsigned long end, int *nonblocking);
 extern void munlock_vma_pages_range(struct vm_area_struct *vma,
                        unsigned long start, unsigned long end);
 static inline void munlock_vma_pages_all(struct vm_area_struct *vma)

diff --git a/mm/memory.c b/mm/memory.c
index 0abd070..7837cea 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3824,30 +3824,6 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-int make_pages_present(unsigned long addr, unsigned long end)
-{
-       int ret, len, write;
-       struct vm_area_struct * vma;
-
-       vma = find_vma(current->mm, addr);
-       if (!vma)
-               return -ENOMEM;
-       /*
-        * We want to touch writable mappings with a write fault in order
-        * to break COW, except for shared mappings because these don't COW
-        * and we would not want to dirty them for nothing.
-        */
-       write = (vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE;
-       BUG_ON(addr >= end);
-       BUG_ON(end > vma->vm_end);
-       len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE;
-       ret = get_user_pages(current, current->mm, addr,
-                       len, write, 0, NULL, NULL);
-       if (ret < 0)
-               return ret;
-       return ret == len ? 0 : -EFAULT;
-}
-
 #if !defined(__HAVE_ARCH_GATE_AREA)
 
 #if defined(AT_SYSINFO_EHDR)

diff --git a/mm/mlock.c b/mm/mlock.c
index a296a49..569400a 100644 (file)
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -155,9 +155,8 @@ void munlock_vma_page(struct page *page)
  *
  * vma->vm_mm->mmap_sem must be held for at least read.
  */
-static long __mlock_vma_pages_range(struct vm_area_struct *vma,
-                                   unsigned long start, unsigned long end,
-                                   int *nonblocking)
+long __mlock_vma_pages_range(struct vm_area_struct *vma,
+               unsigned long start, unsigned long end, int *nonblocking)
 {
        struct mm_struct *mm = vma->vm_mm;
        unsigned long addr = start;
@@ -202,56 +201,6 @@ static int __mlock_posix_error_return(long retval)
        return retval;
 }
 
-/**
- * mlock_vma_pages_range() - mlock pages in specified vma range.
- * @vma - the vma containing the specfied address range
- * @start - starting address in @vma to mlock
- * @end   - end address [+1] in @vma to mlock
- *
- * For mmap()/mremap()/expansion of mlocked vma.
- *
- * return 0 on success for "normal" vmas.
- *
- * return number of pages [> 0] to be removed from locked_vm on success
- * of "special" vmas.
- */
-long mlock_vma_pages_range(struct vm_area_struct *vma,
-                       unsigned long start, unsigned long end)
-{
-       int nr_pages = (end - start) / PAGE_SIZE;
-       BUG_ON(!(vma->vm_flags & VM_LOCKED));
-
-       /*
-        * filter unlockable vmas
-        */
-       if (vma->vm_flags & (VM_IO | VM_PFNMAP))
-               goto no_mlock;
-
-       if (!((vma->vm_flags & VM_DONTEXPAND) ||
-                       is_vm_hugetlb_page(vma) ||
-                       vma == get_gate_vma(current->mm))) {
-
-               __mlock_vma_pages_range(vma, start, end, NULL);
-
-               /* Hide errors from mmap() and other callers */
-               return 0;
-       }
-
-       /*
-        * User mapped kernel pages or huge pages:
-        * make these pages present to populate the ptes, but
-        * fall thru' to reset VM_LOCKED--no need to unlock, and
-        * return nr_pages so these don't get counted against task's
-        * locked limit.  huge pages are already counted against
-        * locked vm limit.
-        */
-       make_pages_present(start, end);
-
-no_mlock:
-       vma->vm_flags &= ~VM_LOCKED;    /* and don't come back! */
-       return nr_pages;                /* error or pages NOT mlocked */
-}
-
 /*
  * munlock_vma_pages_range() - munlock all pages in the vma range.'
  * @vma - vma containing range to be munlock()ed.
@@ -303,7 +252,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
  *
  * Filters out "special" vmas -- VM_LOCKED never gets set for these, and
  * munlock is a no-op.  However, for some special vmas, we go ahead and
- * populate the ptes via make_pages_present().
+ * populate the ptes.
  *
  * For vmas that pass the filters, merge/split as appropriate.
  */

diff --git a/mm/mmap.c b/mm/mmap.c
index d6bc39e..8826c77 100644 (file)
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2204,9 +2204,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
                return vma;
        if (!prev || expand_stack(prev, addr))
                return NULL;
-       if (prev->vm_flags & VM_LOCKED) {
-               mlock_vma_pages_range(prev, addr, prev->vm_end);
-       }
+       if (prev->vm_flags & VM_LOCKED)
+               __mlock_vma_pages_range(prev, addr, prev->vm_end, NULL);
        return prev;
 }
 #else
@@ -2232,9 +2231,8 @@ find_extend_vma(struct mm_struct * mm, unsigned long addr)
        start = vma->vm_start;
        if (expand_stack(vma, addr))
                return NULL;
-       if (vma->vm_flags & VM_LOCKED) {
-               mlock_vma_pages_range(vma, addr, start);
-       }
+       if (vma->vm_flags & VM_LOCKED)
+               __mlock_vma_pages_range(vma, addr, start, NULL);
        return vma;
 }
 #endif