[PATCH] mm: ptd_alloc take ptlock

Second step in pushing down the page_table_lock.  Remove the temporary
bridging hack from __pud_alloc, __pmd_alloc, __pte_alloc: expect callers not
to hold page_table_lock, whether it's on init_mm or a user mm; take
page_table_lock internally to check if a racing task already allocated.

Convert their callers from common code.  But avoid coming back to change them
again later: instead of moving the spin_lock(&mm->page_table_lock) down,
switch over to new macros pte_alloc_map_lock and pte_unmap_unlock, which
encapsulate the mapping+locking and unlocking+unmapping together, and in the
end may use alternatives to the mm page_table_lock itself.

These callers all hold mmap_sem (some exclusively, some not), so at no level
can a page table be whipped away from beneath them; and pte_alloc uses the
"atomic" pmd_present to test whether it needs to allocate.  It appears that on
all arches we can safely descend without page_table_lock.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 18 insertions, 30 deletions

diff --git a/mm/fremap.c b/mm/fremap.c
index 49719a35769a..d862be3bc3e3 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -63,23 +63,20 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma,
         pud_t *pud;
         pgd_t *pgd;
         pte_t pte_val;
+        spinlock_t *ptl;
 
         BUG_ON(vma->vm_flags & VM_RESERVED);
 
         pgd = pgd_offset(mm, addr);
-        spin_lock(&mm->page_table_lock);
-        
         pud = pud_alloc(mm, pgd, addr);
         if (!pud)
-                goto err_unlock;
-
+                goto out;
         pmd = pmd_alloc(mm, pud, addr);
         if (!pmd)
-                goto err_unlock;
-
-        pte = pte_alloc_map(mm, pmd, addr);
+                goto out;
+        pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
         if (!pte)
-                goto err_unlock;
+                goto out;
 
         /*
          * This page may have been truncated. Tell the
@@ -89,10 +86,10 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma,
         inode = vma->vm_file->f_mapping->host;
         size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
         if (!page->mapping || page->index >= size)
-                goto err_unlock;
+                goto unlock;
         err = -ENOMEM;
         if (page_mapcount(page) > INT_MAX/2)
-                goto err_unlock;
+                goto unlock;
 
         if (pte_none(*pte) || !zap_pte(mm, vma, addr, pte))
                 inc_mm_counter(mm, file_rss);
@@ -101,17 +98,15 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma,
         set_pte_at(mm, addr, pte, mk_pte(page, prot));
         page_add_file_rmap(page);
         pte_val = *pte;
-        pte_unmap(pte);
         update_mmu_cache(vma, addr, pte_val);
-
         err = 0;
-err_unlock:
-        spin_unlock(&mm->page_table_lock);
+unlock:
+        pte_unmap_unlock(pte, ptl);
+out:
         return err;
 }
 EXPORT_SYMBOL(install_page);
 
-
 /*
  * Install a file pte to a given virtual memory address, release any
  * previously existing mapping.
@@ -125,23 +120,20 @@ int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
         pud_t *pud;
         pgd_t *pgd;
         pte_t pte_val;
+        spinlock_t *ptl;
 
         BUG_ON(vma->vm_flags & VM_RESERVED);
 
         pgd = pgd_offset(mm, addr);
-        spin_lock(&mm->page_table_lock);
-        
         pud = pud_alloc(mm, pgd, addr);
         if (!pud)
-                goto err_unlock;
-
+                goto out;
         pmd = pmd_alloc(mm, pud, addr);
         if (!pmd)
-                goto err_unlock;
-
-        pte = pte_alloc_map(mm, pmd, addr);
+                goto out;
+        pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
         if (!pte)
-                goto err_unlock;
+                goto out;
 
         if (!pte_none(*pte) && zap_pte(mm, vma, addr, pte)) {
                 update_hiwater_rss(mm);
@@ -150,17 +142,13 @@ int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 
         set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff));
         pte_val = *pte;
-        pte_unmap(pte);
         update_mmu_cache(vma, addr, pte_val);
-        spin_unlock(&mm->page_table_lock);
-        return 0;
-
-err_unlock:
-        spin_unlock(&mm->page_table_lock);
+        pte_unmap_unlock(pte, ptl);
+        err = 0;
+out:
         return err;
 }
 
-
 /***
  * sys_remap_file_pages - remap arbitrary pages of a shared backing store
  *                        file within an existing vma.