This allows iterating over all levels of the page tables. Recursion continues

to the depth of the lowest supplied callback.

This makes the page walker nearly completely generic and should allow it to
replace some other hand-rolled page table walkers.

Signed-off-by: Matt Mackall <mpm@selenic.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 fs/proc/task_mmu.c |   89 +++++++++++++++++++++++++++++++------------
 1 file changed, 66 insertions(+), 23 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 17d3bcd82b1d634fa5cbbeaf2ada0910f3327aad..0add187b60f21f8098b37289edcf6f506fe7ee27 100644 (file)
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -304,10 +304,35 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
        return 0;
 }
 
+struct mm_walk {
+       int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, void *);
+       int (*pud_entry)(pud_t *, unsigned long, unsigned long, void *);
+       int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, void *);
+       int (*pte_entry)(pte_t *, unsigned long, unsigned long, void *);
+};
+
+static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+                         struct mm_walk *walk, void *private)
+{
+       pte_t *pte;
+       int err;
+
+       for (pte = pte_offset_map(pmd, addr); addr != end;
+            addr += PAGE_SIZE, pte++) {
+               if (pte_none(*pte))
+                       continue;
+               err = walk->pte_entry(pte, addr, addr, private);
+               if (err) {
+                       pte_unmap(pte);
+                       return err;
+               }
+       }
+       pte_unmap(pte);
+       return 0;
+}
+
 static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
-                         int (*action)(pmd_t *, unsigned long,
-                                       unsigned long, void *),
-                         void *private)
+                         struct mm_walk *walk, void *private)
 {
        pmd_t *pmd;
        unsigned long next;
@@ -318,18 +343,22 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
                next = pmd_addr_end(addr, end);
                if (pmd_none_or_clear_bad(pmd))
                        continue;
-               err = action(pmd, addr, next, private);
-               if (err)
-                       return err;
+               if (walk->pmd_entry) {
+                       err = walk->pmd_entry(pmd, addr, next, private);
+                       if (err)
+                               return err;
+               }
+               if (walk->pte_entry) {
+                       err = walk_pte_range(pmd, addr, next, walk, private);
+                       if (err)
+                               return err;
+               }
        }
-
        return 0;
 }
 
 static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
-                         int (*action)(pmd_t *, unsigned long,
-                                       unsigned long, void *),
-                         void *private)
+                         struct mm_walk *walk, void *private)
 {
        pud_t *pud;
        unsigned long next;
@@ -340,11 +369,17 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
                next = pud_addr_end(addr, end);
                if (pud_none_or_clear_bad(pud))
                        continue;
-               err = walk_pmd_range(pud, addr, next, action, private);
-               if (err)
-                       return err;
+               if (walk->pud_entry) {
+                       err = walk->pud_entry(pud, addr, next, private);
+                       if (err)
+                               return err;
+               }
+               if (walk->pmd_entry || walk->pte_entry) {
+                       err = walk_pmd_range(pud, addr, next, walk, private);
+                       if (err)
+                               return err;
+               }
        }
-
        return 0;
 }
 
@@ -361,9 +396,7 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
  */
 static int walk_page_range(struct mm_struct *mm,
                           unsigned long addr, unsigned long end,
-                          int (*action)(pmd_t *, unsigned long,
-                                        unsigned long, void *),
-                          void *private)
+                          struct mm_walk *walk, void *private)
 {
        pgd_t *pgd;
        unsigned long next;
@@ -374,14 +407,22 @@ static int walk_page_range(struct mm_struct *mm,
                next = pgd_addr_end(addr, end);
                if (pgd_none_or_clear_bad(pgd))
                        continue;
-               err = walk_pud_range(pgd, addr, next, action, private);
-               if (err)
-                       return err;
+               if (walk->pgd_entry) {
+                       err = walk->pgd_entry(pgd, addr, next, private);
+                       if (err)
+                               return err;
+               }
+               if (walk->pud_entry || walk->pmd_entry || walk->pte_entry) {
+                       err = walk_pud_range(pgd, addr, next, walk, private);
+                       if (err)
+                               return err;
+               }
        }
-
        return 0;
 }
 
+static struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range };
+
 static int show_smap(struct seq_file *m, void *v)
 {
        struct vm_area_struct *vma = v;
@@ -391,10 +432,12 @@ static int show_smap(struct seq_file *m, void *v)
        mss.vma = vma;
        if (vma->vm_mm && !is_vm_hugetlb_page(vma))
                walk_page_range(vma->vm_mm, vma->vm_start, vma->vm_end,
-                               smaps_pte_range, &mss);
+                               &smaps_walk, &mss);
        return show_map_internal(m, v, &mss);
 }
 
+static struct mm_walk clear_refs_walk = { .pmd_entry = clear_refs_pte_range };
+
 void clear_refs_smap(struct mm_struct *mm)
 {
        struct vm_area_struct *vma;
@@ -403,7 +446,7 @@ void clear_refs_smap(struct mm_struct *mm)
        for (vma = mm->mmap; vma; vma = vma->vm_next)
                if (vma->vm_mm && !is_vm_hugetlb_page(vma))
                        walk_page_range(vma->vm_mm, vma->vm_start, vma->vm_end,
-                                       clear_refs_pte_range, vma);
+                                       &clear_refs_walk, vma);
        flush_tlb_mm(mm);
        up_read(&mm->mmap_sem);
 }