Re: RFC: Cleanup / small fixes to hugetlb fault handling

['David Gibson']

On Wed, Oct 26, 2005 at 05:16:39PM -0700, Chen, Kenneth W wrote:
> David Gibson wrote on Wednesday, October 26, 2005 5:05 PM
> > On Wed, Oct 26, 2005 at 11:44:52AM -0700, Chen, Kenneth W wrote:
> > > David Gibson wrote on Tuesday, October 25, 2005 7:49 PM
> > > > +int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
> > > > +		  unsigned long address, int write_access)
> > > > +{
> > > > +	pte_t *ptep;
> > > > +	pte_t entry;
> > > > +
> > > > +	ptep = huge_pte_alloc(mm, address);
> > > > +	if (! ptep)
> > > > +		/* OOM */
> > > > +		return VM_FAULT_SIGBUS;
> > > > +
> > > > +	entry = *ptep;
> > > > +
> > > > +	if (pte_none(entry))
> > > > +		return hugetlb_no_page(mm, vma, address, ptep);
> > > > +
> > > > +	/* we could get here if another thread instantiated the pte
> > > > +	 * before the test above */
> > > > +
> > > > +	return VM_FAULT_SIGBUS;
> > > >  }
> > > 
> > > Are you sure about the last return?  Looks like a typo to me, if *ptep
> > > is present, it should return VM_FAULT_MINOR.
> > 
> > Oops, yes, thinko.  Corrected patch shortly.
> 
> While you at it, I think it would be preferable that the first return be
> VM_FAULT_OOM, your thoughts?

Ok, here's the revised patch with this change, and the others
mentioned elsewhere.

RFC: Cleanup / small fixes to hugetlb fault handling

This patch makes some slight tweaks / cleanups to the fault handling
path for huge pages in -mm.  My main motivation is to make it simpler
to fit COW in, but along the way it addresses a few minor problems
with the existing code:

- The check against i_size was duplicated: once in
  find_lock_huge_page() and again in hugetlb_fault() after taking the
  page_table_lock.  We only really need the locked one, so remove the
  other.

- find_lock_huge_page() isn't a great name, since it does extra things
  not analagous to find_lock_page().  Rename it
  find_or_alloc_huge_page() which is closer to the mark.

Signed-off-by: David Gibson <david@xxxxxxxxxxxxxxxxxxxxx>

Index: working-2.6/mm/hugetlb.c
===================================================================
--- working-2.6.orig/mm/hugetlb.c	2005-10-27 16:34:20.000000000 +1000
+++ working-2.6/mm/hugetlb.c	2005-10-27 16:34:55.000000000 +1000
@@ -336,30 +336,24 @@
 	flush_tlb_range(vma, start, end);
 }
 
-static struct page *find_lock_huge_page(struct address_space *mapping,
-			unsigned long idx)
+static struct page *find_or_alloc_huge_page(struct address_space *mapping,
+					    unsigned long idx)
 {
 	struct page *page;
 	int err;
-	struct inode *inode = mapping->host;
-	unsigned long size;
 
 retry:
 	page = find_lock_page(mapping, idx);
 	if (page)
-		goto out;
-
-	/* Check to make sure the mapping hasn't been truncated */
-	size = i_size_read(inode) >> HPAGE_SHIFT;
-	if (idx >= size)
-		goto out;
+		return page;
 
 	if (hugetlb_get_quota(mapping))
-		goto out;
+		return NULL;
+
 	page = alloc_huge_page();
 	if (!page) {
 		hugetlb_put_quota(mapping);
-		goto out;
+		return NULL;
 	}
 
 	err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
@@ -370,50 +364,49 @@
 			goto retry;
 		page = NULL;
 	}
-out:
+
 	return page;
 }
 
-int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
-			unsigned long address, int write_access)
+int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
+		    unsigned long address, pte_t *ptep)
 {
-	int ret = VM_FAULT_SIGBUS;
+	int ret;
 	unsigned long idx;
 	unsigned long size;
-	pte_t *pte;
 	struct page *page;
 	struct address_space *mapping;
 
-	pte = huge_pte_alloc(mm, address);
-	if (!pte)
-		goto out;
-
 	mapping = vma->vm_file->f_mapping;
 	idx = ((address - vma->vm_start) >> HPAGE_SHIFT)
 		+ (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
 
-	/*
-	 * Use page lock to guard against racing truncation
-	 * before we get page_table_lock.
-	 */
-	page = find_lock_huge_page(mapping, idx);
+	/* This returns a locked page, which keeps us safe in the
+	 * event of a race with truncate() */
+	page = find_or_alloc_huge_page(mapping, idx);
 	if (!page)
-		goto out;
+		return VM_FAULT_SIGBUS;
 
 	spin_lock(&mm->page_table_lock);
+
+	ret = VM_FAULT_SIGBUS;
+
 	size = i_size_read(mapping->host) >> HPAGE_SHIFT;
 	if (idx >= size)
 		goto backout;
 
 	ret = VM_FAULT_MINOR;
-	if (!pte_none(*pte))
+
+	if (!pte_none(*ptep))
+		/* oops, someone instantiated this PTE before us */
 		goto backout;
 
 	add_mm_counter(mm, file_rss, HPAGE_SIZE / PAGE_SIZE);
-	set_huge_pte_at(mm, address, pte, make_huge_pte(vma, page));
+	set_huge_pte_at(mm, address, ptep, make_huge_pte(vma, page));
+
 	spin_unlock(&mm->page_table_lock);
 	unlock_page(page);
-out:
+
 	return ret;
 
 backout:
@@ -421,7 +414,29 @@
 	hugetlb_put_quota(mapping);
 	unlock_page(page);
 	put_page(page);
-	goto out;
+
+	return ret;
+}
+
+int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+		  unsigned long address, int write_access)
+{
+	pte_t *ptep;
+	pte_t entry;
+
+	ptep = huge_pte_alloc(mm, address);
+	if (! ptep)
+		return VM_FAULT_OOM;
+
+	entry = *ptep;
+
+	if (pte_none(entry))
+		return hugetlb_no_page(mm, vma, address, ptep);
+
+	/* we could get here if another thread instantiated the pte
+	 * before the test above */
+
+	return VM_FAULT_MINOR;
 }
 
 int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,


-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/people/dgibson
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/