diff mbox

[PATCHv5,22/36] mm, hugetlb: switch hugetlbfs to multi-order radix-tree entries

Message ID 20161129112304.90056-23-kirill.shutemov@linux.intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Kirill A . Shutemov Nov. 29, 2016, 11:22 a.m. UTC
From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>

Currently, hugetlb pages are linked to page cache on the basis of hugepage
offset (derived from vma_hugecache_offset()) for historical reason, which
doesn't match to the generic usage of page cache and requires some routines
to covert page offset <=> hugepage offset in common path. This patch
adjusts code for multi-order radix-tree to avoid the situation.

Main change is on the behavior of page->index for hugetlbfs. Before this
patch, it represented hugepage offset, but with this patch it represents
page offset. So index-related code have to be updated.
Note that hugetlb_fault_mutex_hash() and reservation region handling are
still working with hugepage offset.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
[kirill.shutemov@linux.intel.com: reject fixed]
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 fs/hugetlbfs/inode.c    | 22 ++++++++++------------
 include/linux/pagemap.h | 23 +++--------------------
 mm/filemap.c            | 12 +++++-------
 mm/hugetlb.c            | 19 ++++++-------------
 mm/truncate.c           |  8 ++++----
 5 files changed, 28 insertions(+), 56 deletions(-)

Comments

Hillf Danton Nov. 30, 2016, 9:48 a.m. UTC | #1
On Tuesday, November 29, 2016 7:23 PM Kirill A. Shutemov wrote:
> @@ -607,10 +605,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
>  		}
> 
>  		/* Set numa allocation policy based on index */
> -		hugetlb_set_vma_policy(&pseudo_vma, inode, index);
> +		hugetlb_set_vma_policy(&pseudo_vma, inode, index >> huge_page_order(h));
> 
>  		/* addr is the offset within the file (zero based) */
> -		addr = index * hpage_size;
> +		addr = index << PAGE_SHIFT & ~huge_page_mask(h);
> 
>  		/* mutex taken here, fault path and hole punch */
>  		hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping,

Seems we can't use index in computing hash as long as it isn't in huge page size.

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Kirill A . Shutemov Nov. 30, 2016, 1:15 p.m. UTC | #2
On Wed, Nov 30, 2016 at 05:48:05PM +0800, Hillf Danton wrote:
> On Tuesday, November 29, 2016 7:23 PM Kirill A. Shutemov wrote:
> > @@ -607,10 +605,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
> >  		}
> > 
> >  		/* Set numa allocation policy based on index */
> > -		hugetlb_set_vma_policy(&pseudo_vma, inode, index);
> > +		hugetlb_set_vma_policy(&pseudo_vma, inode, index >> huge_page_order(h));
> > 
> >  		/* addr is the offset within the file (zero based) */
> > -		addr = index * hpage_size;
> > +		addr = index << PAGE_SHIFT & ~huge_page_mask(h);
> > 
> >  		/* mutex taken here, fault path and hole punch */
> >  		hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping,
> 
> Seems we can't use index in computing hash as long as it isn't in huge page size.

Look at changes in hugetlb_fault_mutex_hash(): we shift the index right by
huge_page_order(), before calculating the hash. I don't see a problem
here.
Hillf Danton Dec. 1, 2016, 3:10 a.m. UTC | #3
On Wednesday, November 30, 2016 9:16 PM Kirill A. Shutemov wrote:
> On Wed, Nov 30, 2016 at 05:48:05PM +0800, Hillf Danton wrote:
> > On Tuesday, November 29, 2016 7:23 PM Kirill A. Shutemov wrote:
> > > @@ -607,10 +605,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
> > >  		}
> > >
> > >  		/* Set numa allocation policy based on index */
> > > -		hugetlb_set_vma_policy(&pseudo_vma, inode, index);
> > > +		hugetlb_set_vma_policy(&pseudo_vma, inode, index >> huge_page_order(h));
> > >
> > >  		/* addr is the offset within the file (zero based) */
> > > -		addr = index * hpage_size;
> > > +		addr = index << PAGE_SHIFT & ~huge_page_mask(h);
> > >
> > >  		/* mutex taken here, fault path and hole punch */
> > >  		hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping,
> >
> > Seems we can't use index in computing hash as long as it isn't in huge page size.
> 
> Look at changes in hugetlb_fault_mutex_hash(): we shift the index right by
> huge_page_order(), before calculating the hash. I don't see a problem
> here.
> 
You are right. I missed that critical point.

thanks
Hillf

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 4fb7b10f3a05..45992c839794 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -388,8 +388,8 @@  static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 {
 	struct hstate *h = hstate_inode(inode);
 	struct address_space *mapping = &inode->i_data;
-	const pgoff_t start = lstart >> huge_page_shift(h);
-	const pgoff_t end = lend >> huge_page_shift(h);
+	const pgoff_t start = lstart >> PAGE_SHIFT;
+	const pgoff_t end = lend >> PAGE_SHIFT;
 	struct vm_area_struct pseudo_vma;
 	struct pagevec pvec;
 	pgoff_t next;
@@ -446,8 +446,7 @@  static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 
 				i_mmap_lock_write(mapping);
 				hugetlb_vmdelete_list(&mapping->i_mmap,
-					next * pages_per_huge_page(h),
-					(next + 1) * pages_per_huge_page(h));
+					next, next + 1);
 				i_mmap_unlock_write(mapping);
 			}
 
@@ -466,7 +465,8 @@  static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 			freed++;
 			if (!truncate_op) {
 				if (unlikely(hugetlb_unreserve_pages(inode,
-							next, next + 1, 1)))
+						(next) << huge_page_order(h),
+						(next + 1) << huge_page_order(h), 1)))
 					hugetlb_fix_reserve_counts(inode);
 			}
 
@@ -550,8 +550,6 @@  static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	struct hstate *h = hstate_inode(inode);
 	struct vm_area_struct pseudo_vma;
 	struct mm_struct *mm = current->mm;
-	loff_t hpage_size = huge_page_size(h);
-	unsigned long hpage_shift = huge_page_shift(h);
 	pgoff_t start, index, end;
 	int error;
 	u32 hash;
@@ -567,8 +565,8 @@  static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	 * For this range, start is rounded down and end is rounded up
 	 * as well as being converted to page offsets.
 	 */
-	start = offset >> hpage_shift;
-	end = (offset + len + hpage_size - 1) >> hpage_shift;
+	start = offset >> PAGE_SHIFT;
+	end = (offset + len + huge_page_size(h) - 1) >> PAGE_SHIFT;
 
 	inode_lock(inode);
 
@@ -586,7 +584,7 @@  static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
 	pseudo_vma.vm_file = file;
 
-	for (index = start; index < end; index++) {
+	for (index = start; index < end; index += pages_per_huge_page(h)) {
 		/*
 		 * This is supposed to be the vaddr where the page is being
 		 * faulted in, but we have no vaddr here.
@@ -607,10 +605,10 @@  static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		}
 
 		/* Set numa allocation policy based on index */
-		hugetlb_set_vma_policy(&pseudo_vma, inode, index);
+		hugetlb_set_vma_policy(&pseudo_vma, inode, index >> huge_page_order(h));
 
 		/* addr is the offset within the file (zero based) */
-		addr = index * hpage_size;
+		addr = index << PAGE_SHIFT & ~huge_page_mask(h);
 
 		/* mutex taken here, fault path and hole punch */
 		hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index faa3fa173939..bb0b7022421e 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -398,10 +398,9 @@  static inline struct page *read_mapping_page(struct address_space *mapping,
 }
 
 /*
- * Get index of the page with in radix-tree
- * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE)
+ * Get the offset in PAGE_SIZE.
  */
-static inline pgoff_t page_to_index(struct page *page)
+static inline pgoff_t page_to_pgoff(struct page *page)
 {
 	pgoff_t pgoff;
 
@@ -418,18 +417,6 @@  static inline pgoff_t page_to_index(struct page *page)
 }
 
 /*
- * Get the offset in PAGE_SIZE.
- * (TODO: hugepage should have ->index in PAGE_SIZE)
- */
-static inline pgoff_t page_to_pgoff(struct page *page)
-{
-	if (unlikely(PageHeadHuge(page)))
-		return page->index << compound_order(page);
-
-	return page_to_index(page);
-}
-
-/*
  * Return byte-offset into filesystem object for page.
  */
 static inline loff_t page_offset(struct page *page)
@@ -442,15 +429,11 @@  static inline loff_t page_file_offset(struct page *page)
 	return ((loff_t)page_index(page)) << PAGE_SHIFT;
 }
 
-extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
-				     unsigned long address);
-
 static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
 					unsigned long address)
 {
 	pgoff_t pgoff;
-	if (unlikely(is_vm_hugetlb_page(vma)))
-		return linear_hugepage_index(vma, address);
+
 	pgoff = (address - vma->vm_start) >> PAGE_SHIFT;
 	pgoff += vma->vm_pgoff;
 	return pgoff;
diff --git a/mm/filemap.c b/mm/filemap.c
index 52be2b457208..33974ad1a8ec 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -165,10 +165,7 @@  static void page_cache_tree_delete(struct address_space *mapping,
 {
 	struct radix_tree_node *node;
 	void **slot;
-	int nr;
-
-	/* hugetlb pages are represented by one entry in the radix tree */
-	nr = PageHuge(page) ? 1 : hpage_nr_pages(page);
+	int nr = hpage_nr_pages(page);
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageTail(page), page);
@@ -1420,16 +1417,17 @@  unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
 		}
 
 		/* For multi-order entries, find relevant subpage */
-		if (PageTransHuge(page)) {
+		if (PageCompound(page)) {
 			VM_BUG_ON(index - page->index < 0);
-			VM_BUG_ON(index - page->index >= HPAGE_PMD_NR);
+			VM_BUG_ON(index - page->index >=
+					1 << compound_order(page));
 			page += index - page->index;
 		}
 
 		pages[ret] = page;
 		if (++ret == nr_pages)
 			break;
-		if (!PageTransCompound(page))
+		if (PageHuge(page) || !PageTransCompound(page))
 			continue;
 		for (refs = 0; ret < nr_pages &&
 				(index + 1) % HPAGE_PMD_NR;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3faec05b1875..f359653f31ff 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -622,13 +622,6 @@  static pgoff_t vma_hugecache_offset(struct hstate *h,
 			(vma->vm_pgoff >> huge_page_order(h));
 }
 
-pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
-				     unsigned long address)
-{
-	return vma_hugecache_offset(hstate_vma(vma), vma, address);
-}
-EXPORT_SYMBOL_GPL(linear_hugepage_index);
-
 /*
  * Return the size of the pages allocated when backing a VMA. In the majority
  * cases this will be same size as used by the page table entries.
@@ -3658,7 +3651,7 @@  static struct page *hugetlbfs_pagecache_page(struct hstate *h,
 	pgoff_t idx;
 
 	mapping = vma->vm_file->f_mapping;
-	idx = vma_hugecache_offset(h, vma, address);
+	idx = linear_page_index(vma, address);
 
 	return find_lock_page(mapping, idx);
 }
@@ -3675,7 +3668,7 @@  static bool hugetlbfs_pagecache_present(struct hstate *h,
 	struct page *page;
 
 	mapping = vma->vm_file->f_mapping;
-	idx = vma_hugecache_offset(h, vma, address);
+	idx = linear_page_index(vma, address);
 
 	page = find_get_page(mapping, idx);
 	if (page)
@@ -3730,7 +3723,7 @@  static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 retry:
 	page = find_lock_page(mapping, idx);
 	if (!page) {
-		size = i_size_read(mapping->host) >> huge_page_shift(h);
+		size = i_size_read(mapping->host) >> PAGE_SHIFT;
 		if (idx >= size)
 			goto out;
 		page = alloc_huge_page(vma, address, 0);
@@ -3791,7 +3784,7 @@  static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	ptl = huge_pte_lock(h, mm, ptep);
-	size = i_size_read(mapping->host) >> huge_page_shift(h);
+	size = i_size_read(mapping->host) >> PAGE_SHIFT;
 	if (idx >= size)
 		goto backout;
 
@@ -3839,7 +3832,7 @@  u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
 
 	if (vma->vm_flags & VM_SHARED) {
 		key[0] = (unsigned long) mapping;
-		key[1] = idx;
+		key[1] = idx >> huge_page_order(h);
 	} else {
 		key[0] = (unsigned long) mm;
 		key[1] = address >> huge_page_shift(h);
@@ -3895,7 +3888,7 @@  int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	mapping = vma->vm_file->f_mapping;
-	idx = vma_hugecache_offset(h, vma, address);
+	idx = linear_page_index(vma, address);
 
 	/*
 	 * Serialize hugepage allocation and instantiation, so that we don't
diff --git a/mm/truncate.c b/mm/truncate.c
index 6df4b06a190f..7508c2c7e4ed 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -267,7 +267,7 @@  void truncate_inode_pages_range(struct address_space *mapping,
 
 			if (!trylock_page(page))
 				continue;
-			WARN_ON(page_to_index(page) != index);
+			WARN_ON(page_to_pgoff(page) != index);
 			if (PageWriteback(page)) {
 				unlock_page(page);
 				continue;
@@ -383,7 +383,7 @@  restart:	cond_resched();
 			}
 
 			lock_page(page);
-			WARN_ON(page_to_index(page) != index);
+			WARN_ON(page_to_pgoff(page) != index);
 			wait_on_page_writeback(page);
 
 			if (PageTransHuge(page)) {
@@ -533,7 +533,7 @@  unsigned long invalidate_mapping_pages(struct address_space *mapping,
 			if (!trylock_page(page))
 				continue;
 
-			WARN_ON(page_to_index(page) != index);
+			WARN_ON(page_to_pgoff(page) != index);
 
 			/* Is 'start' or 'end' in the middle of THP ? */
 			if (PageTransHuge(page) &&
@@ -650,7 +650,7 @@  int invalidate_inode_pages2_range(struct address_space *mapping,
 			}
 
 			lock_page(page);
-			WARN_ON(page_to_index(page) != index);
+			WARN_ON(page_to_pgoff(page) != index);
 			if (page->mapping != mapping) {
 				unlock_page(page);
 				continue;