[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>

fs/exec.c

@@ -309,40 +309,36 @@ void install_arg_page(struct vm_area_struct *vma,
 	pud_t * pud;
 	pmd_t * pmd;
 	pte_t * pte;
+	spinlock_t *ptl;
 
 	if (unlikely(anon_vma_prepare(vma)))
-		goto out_sig;
+		goto out;
 
 	flush_dcache_page(page);
 	pgd = pgd_offset(mm, address);
-
-	spin_lock(&mm->page_table_lock);
 	pud = pud_alloc(mm, pgd, address);
 	if (!pud)
 		goto out;
 	pmd = pmd_alloc(mm, pud, address);
 	if (!pmd)
 		goto out;
-	pte = pte_alloc_map(mm, pmd, address);
+	pte = pte_alloc_map_lock(mm, pmd, address, &ptl);
 	if (!pte)
 		goto out;
 	if (!pte_none(*pte)) {
-		pte_unmap(pte);
+		pte_unmap_unlock(pte, ptl);
 		goto out;
 	}
 	inc_mm_counter(mm, anon_rss);
 	lru_cache_add_active(page);
 	set_pte_at(mm, address, pte, pte_mkdirty(pte_mkwrite(mk_pte(
 					page, vma->vm_page_prot))));
 	page_add_anon_rmap(page, vma, address);
-	pte_unmap(pte);
-	spin_unlock(&mm->page_table_lock);
+	pte_unmap_unlock(pte, ptl);
 
 	/* no need for flush_tlb */
 	return;
 out:
-	spin_unlock(&mm->page_table_lock);
-out_sig:
 	__free_page(page);
 	force_sig(SIGKILL, current);
 }

include/linux/mm.h

@@ -779,10 +779,28 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 }
 #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */
 
+#define pte_offset_map_lock(mm, pmd, address, ptlp)	\
+({							\
+	spinlock_t *__ptl = &(mm)->page_table_lock;	\
+	pte_t *__pte = pte_offset_map(pmd, address);	\
+	*(ptlp) = __ptl;				\
+	spin_lock(__ptl);				\
+	__pte;						\
+})
+
+#define pte_unmap_unlock(pte, ptl)	do {		\
+	spin_unlock(ptl);				\
+	pte_unmap(pte);					\
+} while (0)
+
 #define pte_alloc_map(mm, pmd, address)			\
 	((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
 		NULL: pte_offset_map(pmd, address))
 
+#define pte_alloc_map_lock(mm, pmd, address, ptlp)	\
+	((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
+		NULL: pte_offset_map_lock(mm, pmd, address, ptlp))
+
 #define pte_alloc_kernel(pmd, address)			\
 	((unlikely(!pmd_present(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
 		NULL: pte_offset_kernel(pmd, address))

kernel/fork.c

@@ -255,7 +255,6 @@ static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		/*
 		 * Link in the new vma and copy the page table entries.
 		 */
-		spin_lock(&mm->page_table_lock);
 		*pprev = tmp;
 		pprev = &tmp->vm_next;
 
@@ -265,7 +264,6 @@ static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 
 		mm->map_count++;
 		retval = copy_page_range(mm, oldmm, tmp);
-		spin_unlock(&mm->page_table_lock);
 
 		if (tmp->vm_ops && tmp->vm_ops->open)
 			tmp->vm_ops->open(tmp);

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.

mm/hugetlb.c

@@ -277,19 +277,23 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	unsigned long addr;
 
 	for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
+		src_pte = huge_pte_offset(src, addr);
+		if (!src_pte)
+			continue;
 		dst_pte = huge_pte_alloc(dst, addr);
 		if (!dst_pte)
 			goto nomem;
+		spin_lock(&dst->page_table_lock);
 		spin_lock(&src->page_table_lock);
-		src_pte = huge_pte_offset(src, addr);
-		if (src_pte && !pte_none(*src_pte)) {
+		if (!pte_none(*src_pte)) {
 			entry = *src_pte;
 			ptepage = pte_page(entry);
 			get_page(ptepage);
 			add_mm_counter(dst, file_rss, HPAGE_SIZE / PAGE_SIZE);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 		}
 		spin_unlock(&src->page_table_lock);
+		spin_unlock(&dst->page_table_lock);
 	}
 	return 0;
 
@@ -354,7 +358,6 @@ int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
 
 	hugetlb_prefault_arch_hook(mm);
 
-	spin_lock(&mm->page_table_lock);
 	for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
 		unsigned long idx;
 		pte_t *pte = huge_pte_alloc(mm, addr);
@@ -389,11 +392,12 @@ int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
 				goto out;
 			}
 		}
+		spin_lock(&mm->page_table_lock);
 		add_mm_counter(mm, file_rss, HPAGE_SIZE / PAGE_SIZE);
 		set_huge_pte_at(mm, addr, pte, make_huge_pte(vma, page));
+		spin_unlock(&mm->page_table_lock);
 	}
 out:
-	spin_unlock(&mm->page_table_lock);
 	return ret;
 }