xfs, dax: fix the page fault/allocation mess

cover

---
 fs/dax.c    | 36 ++++++++++++++++--------------------
 mm/memory.c | 11 +++++++++--
 2 files changed, 25 insertions(+), 22 deletions(-)
index 7ae6df7..400fe95 100644
@@ -569,26 +569,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
 		goto fallback;
 
-	if (buffer_unwritten(&bh) || buffer_new(&bh)) {
-		int i;
-		for (i = 0; i < PTRS_PER_PMD; i++)
-			clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
-		wmb_pmem();
-		count_vm_event(PGMAJFAULT);
-		mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
-		result |= VM_FAULT_MAJOR;
-	}
-
-	/*
-	 * If we allocated new storage, make sure no process has any
-	 * zero pages covering this hole
-	 */
-	if (buffer_new(&bh)) {
-		i_mmap_unlock_write(mapping);
-		unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0);
-		i_mmap_lock_write(mapping);
-	}
-
 	/*
 	 * If a truncate happened while we were allocating blocks, we may
 	 * leave blocks allocated to the file that are beyond EOF.  We can't

@@ -603,6 +583,13 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if ((pgoff | PG_PMD_COLOUR) >= size)
 		goto fallback;
 
+	/*
+	 * If we allocated new storage, make sure no process has any
+	 * zero pages covering this hole
+	 */
+	if (buffer_new(&bh))
+		unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0);
+
 	if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
 		spinlock_t *ptl;
 		pmd_t entry;

@@ -633,6 +620,15 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
 			goto fallback;
 
+		if (buffer_unwritten(&bh) || buffer_new(&bh)) {
+			int i;
+			for (i = 0; i < PTRS_PER_PMD; i++)
+				clear_page(kaddr + i * PAGE_SIZE);
+			count_vm_event(PGMAJFAULT);
+			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+			result |= VM_FAULT_MAJOR;
+		}
+
 		result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write);
 	}
 

index 9cb2747..5ec066f 100644
@@ -2426,10 +2426,17 @@ void unmap_mapping_range(struct address_space *mapping,
 	if (details.last_index < details.first_index)
 		details.last_index = ULONG_MAX;
 
-	i_mmap_lock_write(mapping);
+
+	/*
+	 * DAX already holds i_mmap_lock to serialise file truncate vs
+	 * page fault and page fault vs page fault.
+	 */
+	if (!IS_DAX(mapping->host))
+		i_mmap_lock_write(mapping);
 	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
 		unmap_mapping_range_tree(&mapping->i_mmap, &details);
-	i_mmap_unlock_write(mapping);
+	if (!IS_DAX(mapping->host))
+		i_mmap_unlock_write(mapping);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 

2.5.0

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
        # apt-get install sparse
        make ARCH=x86_64 allmodconfig
        make C=1 CF=-D__CHECK_ENDIAN__
>> fs/dax.c:626:50: sparse: incorrect type in argument 1 (different address spaces)
 > 626					clear_page(kaddr + i * PAGE_SIZE);
---
 fs/dax.c    | 36 ++++++++++++++++--------------------
 mm/memory.c | 11 +++++++++--
 2 files changed, 25 insertions(+), 22 deletions(-)
index 7ae6df7..400fe95 100644

@@ -569,26 +569,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
 		goto fallback;
 
-	if (buffer_unwritten(&bh) || buffer_new(&bh)) {
-		int i;
-		for (i = 0; i < PTRS_PER_PMD; i++)
-			clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
-		wmb_pmem();

@@ -633,6 +620,15 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
 			goto fallback;
 
+		if (buffer_unwritten(&bh) || buffer_new(&bh)) {

+			int i;
+			for (i = 0; i < PTRS_PER_PMD; i++)
+				clear_page(kaddr + i * PAGE_SIZE);
+			count_vm_event(PGMAJFAULT);
+			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+			result |= VM_FAULT_MAJOR;
+		}
+
 		result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write);
 	}

---
 fs/dax.c    | 36 ++++++++++++++++--------------------
 mm/memory.c | 11 +++++++++--
 2 files changed, 25 insertions(+), 22 deletions(-)
index 7ae6df7..400fe95 100644

@@ -569,26 +569,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
 		goto fallback;
 
-	if (buffer_unwritten(&bh) || buffer_new(&bh)) {
-		int i;
-		for (i = 0; i < PTRS_PER_PMD; i++)
-			clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
-		wmb_pmem();

@@ -633,6 +620,15 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
 			goto fallback;
 

+		if (buffer_unwritten(&bh) || buffer_new(&bh)) {
+			int i;
+			for (i = 0; i < PTRS_PER_PMD; i++)
+				clear_page(kaddr + i * PAGE_SIZE);
+			count_vm_event(PGMAJFAULT);
+			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+			result |= VM_FAULT_MAJOR;
+		}
+
 		result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write);
 	}

---
 arch/x86/include/asm/pmem.h |    7 +------
 fs/dax.c                    |    4 +---
 2 files changed, 2 insertions(+), 9 deletions(-)
index d8ce3ec816ab..1544fabcd7f9 100644
@@ -132,12 +132,7 @@ static inline void arch_clear_pmem(void __pmem *addr, size_t size)
 {
 	void *vaddr = (void __force *)addr;
 
-	/* TODO: implement the zeroing via non-temporal writes */
-	if (size == PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0)
-		clear_page(vaddr);
-	else
-		memset(vaddr, 0, size);
-
+	memset(vaddr, 0, size);
 	__arch_wb_cache_pmem(vaddr, size);
 }
 

index b36d6d2e7f87..3faff9227135 100644
@@ -625,9 +625,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 			goto fallback;
 
 		if (buffer_unwritten(&bh) || buffer_new(&bh)) {
-			int i;
-			for (i = 0; i < PTRS_PER_PMD; i++)
-				clear_page(kaddr + i * PAGE_SIZE);
+			clear_pmem(kaddr, HPAGE_SIZE);
 			count_vm_event(PGMAJFAULT);
 			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
 			result |= VM_FAULT_MAJOR;

---
 arch/x86/include/asm/pmem.h |    7 +------
 fs/dax.c                    |    4 +---
 2 files changed, 2 insertions(+), 9 deletions(-)
index d8ce3ec816ab..1544fabcd7f9 100644
@@ -132,12 +132,7 @@ static inline void arch_clear_pmem(void __pmem *addr, size_t size)
 {
 	void *vaddr = (void __force *)addr;
 
-	/* TODO: implement the zeroing via non-temporal writes */
-	if (size == PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0)
-		clear_page(vaddr);
-	else
-		memset(vaddr, 0, size);
-
+	memset(vaddr, 0, size);
 	__arch_wb_cache_pmem(vaddr, size);
 }
 

index b36d6d2e7f87..3faff9227135 100644

@@ -625,9 +625,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 			goto fallback;
 
 		if (buffer_unwritten(&bh) || buffer_new(&bh)) {
-			int i;
-			for (i = 0; i < PTRS_PER_PMD; i++)
-				clear_page(kaddr + i * PAGE_SIZE);
+			clear_pmem(kaddr, HPAGE_SIZE);
 			count_vm_event(PGMAJFAULT);
 			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
 			result |= VM_FAULT_MAJOR;

---
 fs/dax.c    | 36 ++++++++++++++++--------------------
 mm/memory.c | 11 +++++++++--
 2 files changed, 25 insertions(+), 22 deletions(-)
index 7ae6df7..400fe95 100644

@@ -569,26 +569,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
 		goto fallback;
 
-	if (buffer_unwritten(&bh) || buffer_new(&bh)) {
-		int i;
-		for (i = 0; i < PTRS_PER_PMD; i++)
-			clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
-		wmb_pmem();

@@ -633,6 +620,15 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
 			goto fallback;
 

+		if (buffer_unwritten(&bh) || buffer_new(&bh)) {
+			int i;
+			for (i = 0; i < PTRS_PER_PMD; i++)
+				clear_page(kaddr + i * PAGE_SIZE);
+			count_vm_event(PGMAJFAULT);
+			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+			result |= VM_FAULT_MAJOR;
+		}
+
 		result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write);
 	}

Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/dax.c    | 33 ++++++++++++++++-----------------
 mm/memory.c | 11 +++--------
 2 files changed, 19 insertions(+), 25 deletions(-)
index 400fe95..3994a2b 100644
@@ -285,6 +285,7 @@ static int copy_user_bh(struct page *to, struct buffer_head *bh,
 static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 			struct vm_area_struct *vma, struct vm_fault *vmf)
 {
+	struct address_space *mapping = inode->i_mapping;
 	sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
 	unsigned long vaddr = (unsigned long)vmf->virtual_address;
 	void __pmem *addr;

@@ -292,6 +293,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 	pgoff_t size;
 	int error;
 
+	i_mmap_lock_read(mapping);
+
 	/*
 	 * Check truncate didn't happen while we were allocating a block.
 	 * If it did, this block may or may not be still allocated to the

@@ -321,6 +324,8 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 	error = vm_insert_mixed(vma, vaddr, pfn);
 
  out:
+	i_mmap_unlock_read(mapping);
+
 	return error;
 }
 

@@ -382,17 +387,15 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			 * from a read fault and we've raced with a truncate
 			 */
 			error = -EIO;
-			goto unlock;
+			goto unlock_page;
 		}
-	} else {
-		i_mmap_lock_write(mapping);
 	}
 
 	error = get_block(inode, block, &bh, 0);
 	if (!error && (bh.b_size < PAGE_SIZE))
 		error = -EIO;		/* fs corruption? */
 	if (error)
-		goto unlock;
+		goto unlock_page;
 
 	if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) {
 		if (vmf->flags & FAULT_FLAG_WRITE) {

@@ -403,9 +406,8 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			if (!error && (bh.b_size < PAGE_SIZE))
 				error = -EIO;
 			if (error)
-				goto unlock;
+				goto unlock_page;
 		} else {
-			i_mmap_unlock_write(mapping);
 			return dax_load_hole(mapping, page, vmf);
 		}
 	}

@@ -417,15 +419,17 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		else
 			clear_user_highpage(new_page, vaddr);
 		if (error)
-			goto unlock;
+			goto unlock_page;
 		vmf->page = page;
 		if (!page) {
+			i_mmap_lock_read(mapping);
 			/* Check we didn't race with truncate */
 			size = (i_size_read(inode) + PAGE_SIZE - 1) >>
 								PAGE_SHIFT;
 			if (vmf->pgoff >= size) {
+				i_mmap_unlock_read(mapping);
 				error = -EIO;
-				goto unlock;
+				goto out;
 			}
 		}
 		return VM_FAULT_LOCKED;

@@ -461,8 +465,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
 	}
 
-	if (!page)
-		i_mmap_unlock_write(mapping);
  out:
 	if (error == -ENOMEM)
 		return VM_FAULT_OOM | major;

@@ -471,14 +473,11 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		return VM_FAULT_SIGBUS | major;
 	return VM_FAULT_NOPAGE | major;
 
- unlock:
+ unlock_page:
 	if (page) {
 		unlock_page(page);
 		page_cache_release(page);
-	} else {
-		i_mmap_unlock_write(mapping);
 	}
-
 	goto out;
 }
 EXPORT_SYMBOL(__dax_fault);

@@ -556,10 +555,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);
 
 	bh.b_size = PMD_SIZE;
-	i_mmap_lock_write(mapping);
 	length = get_block(inode, block, &bh, write);
 	if (length)
 		return VM_FAULT_SIGBUS;
+	i_mmap_lock_read(mapping);
 
 	/*
 	 * If the filesystem isn't willing to tell us the length of a hole,

@@ -633,11 +632,11 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	}
 
  out:
+	i_mmap_unlock_read(mapping);
+
 	if (buffer_unwritten(&bh))
 		complete_unwritten(&bh, !(result & VM_FAULT_ERROR));
 
-	i_mmap_unlock_write(mapping);
-
 	return result;
 
  fallback:

index 5ec066f..deb679c 100644
@@ -2427,16 +2427,11 @@ void unmap_mapping_range(struct address_space *mapping,
 		details.last_index = ULONG_MAX;
 
 
-	/*
-	 * DAX already holds i_mmap_lock to serialise file truncate vs
-	 * page fault and page fault vs page fault.
-	 */
-	if (!IS_DAX(mapping->host))
-		i_mmap_lock_write(mapping);
+	/* DAX uses i_mmap_lock to serialise file truncate vs page fault */
+	i_mmap_lock_write(mapping);
 	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
 		unmap_mapping_range_tree(&mapping->i_mmap, &details);
-	if (!IS_DAX(mapping->host))
-		i_mmap_unlock_write(mapping);
+	i_mmap_unlock_write(mapping);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 

2.5.0
xfs_get_blocks_alloc: [...] offset 0x7ffffffffffff000 count 4096
xfs_gbmap_direct:     [...] offset 0x7ffffffffffff000 count 4096
---
 fs/xfs/xfs_aops.c | 50 ++++++++++++++++++++++++++++++++++++++++++++------
 fs/xfs/xfs_aops.h |  2 ++
 fs/xfs/xfs_file.c |  6 +++---
 3 files changed, 49 insertions(+), 9 deletions(-)
index 50ab287..e747d6a 100644
@@ -1250,13 +1250,28 @@ xfs_vm_releasepage(
  * the DIO. There is only going to be one reference to the ioend and its life
  * cycle is constrained by the DIO completion code. hence we don't need
  * reference counting here.
+ *
+ * Note that for DIO, an IO to the highest supported file block offset (i.e.
+ * 2^63 - 1FSB bytes) will result in the offset + count overflowing a signed 64
+ * bit variable. Hence if we see this overflow, we have to assume that the IO is
+ * extending the file size. We won't know for sure until IO completion is run
+ * and the actual max write offset is communicated to the IO completion
+ * routine.
+ *
+ * For DAX page faults, we are preparing to never see unwritten extents here,
+ * nor should we ever extend the inode size. Hence we will soon have nothing to
+ * do here for this case, ensuring we don't have to provide an IO completion
+ * callback to free an ioend that we don't actually need for a fault into the
+ * page at offset (2^63 - 1FSB) bytes.
  */
+
 static void
 xfs_map_direct(
 	struct inode		*inode,
 	struct buffer_head	*bh_result,
 	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset)
+	xfs_off_t		offset,
+	bool			dax_fault)
 {
 	struct xfs_ioend	*ioend;
 	xfs_off_t		size = bh_result->b_size;

@@ -1269,6 +1284,16 @@ xfs_map_direct(
 
 	trace_xfs_gbmap_direct(XFS_I(inode), offset, size, type, imap);
 
+	/* XXX: preparation for removing unwritten extents in DAX */
+#if 0
+	if (dax_fault) {
+		ASSERT(type == XFS_IO_OVERWRITE);
+		trace_xfs_gbmap_direct_none(XFS_I(inode), offset, size, type,
+					    imap);
+		return;
+	}
+#endif
+
 	if (bh_result->b_private) {
 		ioend = bh_result->b_private;
 		ASSERT(ioend->io_size > 0);

@@ -1283,7 +1308,8 @@ xfs_map_direct(
 					      ioend->io_size, ioend->io_type,
 					      imap);
 	} else if (type == XFS_IO_UNWRITTEN ||
-		   offset + size > i_size_read(inode)) {
+		   offset + size > i_size_read(inode) ||
+		   offset + size < 0) {
 		ioend = xfs_alloc_ioend(inode, type);
 		ioend->io_offset = offset;
 		ioend->io_size = size;

@@ -1345,7 +1371,8 @@ __xfs_get_blocks(
 	sector_t		iblock,
 	struct buffer_head	*bh_result,
 	int			create,
-	bool			direct)
+	bool			direct,
+	bool			dax_fault)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;

@@ -1458,7 +1485,8 @@ __xfs_get_blocks(
 			set_buffer_unwritten(bh_result);
 		/* direct IO needs special help */
 		if (create && direct)
-			xfs_map_direct(inode, bh_result, &imap, offset);
+			xfs_map_direct(inode, bh_result, &imap, offset,
+				       dax_fault);
 	}
 
 	/*

@@ -1505,7 +1533,7 @@ xfs_get_blocks(
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	return __xfs_get_blocks(inode, iblock, bh_result, create, false);
+	return __xfs_get_blocks(inode, iblock, bh_result, create, false, false);
 }
 
 int

@@ -1515,7 +1543,17 @@ xfs_get_blocks_direct(
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	return __xfs_get_blocks(inode, iblock, bh_result, create, true);
+	return __xfs_get_blocks(inode, iblock, bh_result, create, true, false);
+}
+
+int
+xfs_get_blocks_dax_fault(
+	struct inode		*inode,
+	sector_t		iblock,
+	struct buffer_head	*bh_result,
+	int			create)
+{
+	return __xfs_get_blocks(inode, iblock, bh_result, create, true, true);
 }
 
 static void

index 86afd1a..d39ba25 100644
@@ -58,6 +58,8 @@ int	xfs_get_blocks(struct inode *inode, sector_t offset,
 		       struct buffer_head *map_bh, int create);
 int	xfs_get_blocks_direct(struct inode *inode, sector_t offset,
 			      struct buffer_head *map_bh, int create);
+int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
+			         struct buffer_head *map_bh, int create);
 void	xfs_end_io_dax_write(struct buffer_head *bh, int uptodate);
 
 extern void xfs_count_page_state(struct page *, int *, int *);

index e78feb4..27abe1c 100644
@@ -1503,7 +1503,7 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_direct,
+		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault,
 				    xfs_end_io_dax_write);
 	} else {
 		ret = __block_page_mkwrite(vma, vmf, xfs_get_blocks);

@@ -1538,7 +1538,7 @@ xfs_filemap_fault(
 		 * changes to xfs_get_blocks_direct() to map unwritten extent
 		 * ioend for conversion on read-only mappings.
 		 */
-		ret = __dax_fault(vma, vmf, xfs_get_blocks_direct, NULL);
+		ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
 	} else
 		ret = filemap_fault(vma, vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);

@@ -1565,7 +1565,7 @@ xfs_filemap_pmd_fault(
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vma->vm_file);
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_direct,
+	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
 				    xfs_end_io_dax_write);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	sb_end_pagefault(inode->i_sb);

2.5.0

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/libxfs/xfs_alloc.c | 10 +++++++++-
 fs/xfs/libxfs/xfs_alloc.h |  8 +++++---
 fs/xfs/libxfs/xfs_bmap.c  | 25 +++++++++++++++++++++++--
 fs/xfs/libxfs/xfs_bmap.h  | 13 +++++++++++--
 fs/xfs/xfs_bmap_util.c    | 36 ++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_mount.h        |  3 +++
 6 files changed, 87 insertions(+), 8 deletions(-)
index ffad7f2..4cffc17 100644
@@ -2503,7 +2503,7 @@ xfs_alloc_vextent(
 		 * Try near allocation first, then anywhere-in-ag after
 		 * the first a.g. fails.
 		 */
-		if ((args->userdata  == XFS_ALLOC_INITIAL_USER_DATA) &&
+		if ((args->userdata & XFS_ALLOC_INITIAL_USER_DATA) &&
 		    (mp->m_flags & XFS_MOUNT_32BITINODES)) {
 			args->fsbno = XFS_AGB_TO_FSB(mp,
 					((mp->m_agfrotor / rotorstep) %

@@ -2634,6 +2634,14 @@ xfs_alloc_vextent(
 		XFS_AG_CHECK_DADDR(mp, XFS_FSB_TO_DADDR(mp, args->fsbno),
 			args->len);
 #endif
+
+		/* Zero the extent if we were asked to do so */
+		if (args->userdata & XFS_ALLOC_USERDATA_ZERO) {
+			error = xfs_zero_extent(args->ip, args->fsbno, args->len);
+			if (error)
+				goto error0;
+		}
+
 	}
 	xfs_perag_put(args->pag);
 	return 0;

index ca1c816..0ecde4d 100644
@@ -101,6 +101,7 @@ typedef struct xfs_alloc_arg {
 	struct xfs_mount *mp;		/* file system mount point */
 	struct xfs_buf	*agbp;		/* buffer for a.g. freelist header */
 	struct xfs_perag *pag;		/* per-ag struct for this agno */
+	struct xfs_inode *ip;		/* for userdata zeroing method */
 	xfs_fsblock_t	fsbno;		/* file system block number */
 	xfs_agnumber_t	agno;		/* allocation group number */
 	xfs_agblock_t	agbno;		/* allocation group-relative block # */

@@ -120,15 +121,16 @@ typedef struct xfs_alloc_arg {
 	char		wasdel;		/* set if allocation was prev delayed */
 	char		wasfromfl;	/* set if allocation is from freelist */
 	char		isfl;		/* set if is freelist blocks - !acctg */
-	char		userdata;	/* set if this is user data */
+	char		userdata;	/* mask defining userdata treatment */
 	xfs_fsblock_t	firstblock;	/* io first block allocated */
 } xfs_alloc_arg_t;
 
 /*
  * Defines for userdata
  */
-#define XFS_ALLOC_USERDATA		1	/* allocation is for user data*/
-#define XFS_ALLOC_INITIAL_USER_DATA	2	/* special case start of file */
+#define XFS_ALLOC_USERDATA		(1 << 0)/* allocation is for user data*/
+#define XFS_ALLOC_INITIAL_USER_DATA	(1 << 1)/* special case start of file */
+#define XFS_ALLOC_USERDATA_ZERO		(1 << 2)/* zero extent on allocation */
 
 xfs_extlen_t xfs_alloc_longest_free_extent(struct xfs_mount *mp,
 		struct xfs_perag *pag, xfs_extlen_t need);

index 8e2010d..8f607ed 100644
@@ -3800,8 +3800,13 @@ xfs_bmap_btalloc(
 	args.wasdel = ap->wasdel;
 	args.isfl = 0;
 	args.userdata = ap->userdata;
-	if ((error = xfs_alloc_vextent(&args)))
+	if (ap->userdata & XFS_ALLOC_USERDATA_ZERO)
+		args.ip = ap->ip;
+
+	error = xfs_alloc_vextent(&args);
+	if (error)
 		return error;
+
 	if (tryagain && args.fsbno == NULLFSBLOCK) {
 		/*
 		 * Exact allocation failed. Now try with alignment

@@ -4300,11 +4305,14 @@ xfs_bmapi_allocate(
 
 	/*
 	 * Indicate if this is the first user data in the file, or just any
-	 * user data.
+	 * user data. And if it is userdata, indicate whether it needs to
+	 * be initialised to zero during allocation.
 	 */
 	if (!(bma->flags & XFS_BMAPI_METADATA)) {
 		bma->userdata = (bma->offset == 0) ?
 			XFS_ALLOC_INITIAL_USER_DATA : XFS_ALLOC_USERDATA;
+		if (bma->flags & XFS_BMAPI_ZERO)
+			bma->userdata |= XFS_ALLOC_USERDATA_ZERO;
 	}
 
 	bma->minlen = (bma->flags & XFS_BMAPI_CONTIG) ? bma->length : 1;

@@ -4419,6 +4427,17 @@ xfs_bmapi_convert_unwritten(
 	mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN)
 				? XFS_EXT_NORM : XFS_EXT_UNWRITTEN;
 
+	/*
+	 * Before insertion into the bmbt, zero the range being converted
+	 * if required.
+	 */
+	if (flags & XFS_BMAPI_ZERO) {
+		error = xfs_zero_extent(bma->ip, mval->br_startblock,
+					mval->br_blockcount);
+		if (error)
+			return error;
+	}
+
 	error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, &bma->idx,
 			&bma->cur, mval, bma->firstblock, bma->flist,
 			&tmp_logflags);

@@ -4511,6 +4530,8 @@ xfs_bmapi_write(
 	ASSERT(len > 0);
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	ASSERT((flags & (XFS_BMAPI_METADATA | XFS_BMAPI_ZERO)) !=
+			(XFS_BMAPI_METADATA | XFS_BMAPI_ZERO));
 
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&

index 6aaa0c1..a160f8a 100644
@@ -52,9 +52,9 @@ struct xfs_bmalloca {
 	xfs_extlen_t		minleft; /* amount must be left after alloc */
 	bool			eof;	/* set if allocating past last extent */
 	bool			wasdel;	/* replacing a delayed allocation */
-	bool			userdata;/* set if is user data */
 	bool			aeof;	/* allocated space at eof */
 	bool			conv;	/* overwriting unwritten extents */
+	char			userdata;/* userdata mask */
 	int			flags;
 };
 

@@ -109,6 +109,14 @@ typedef	struct xfs_bmap_free
  */
 #define XFS_BMAPI_CONVERT	0x040
 
+/*
+ * allocate zeroed extents - this requires all newly allocated user data extents
+ * to be initialised to zero. It will be ignored if XFS_BMAPI_METADATA is set.
+ * Use in conjunction with XFS_BMAPI_CONVERT to convert unwritten extents found
+ * during the allocation range to zeroed written extents.
+ */
+#define XFS_BMAPI_ZERO		0x080
+
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
 	{ XFS_BMAPI_METADATA,	"METADATA" }, \

@@ -116,7 +124,8 @@ typedef	struct xfs_bmap_free
 	{ XFS_BMAPI_PREALLOC,	"PREALLOC" }, \
 	{ XFS_BMAPI_IGSTATE,	"IGSTATE" }, \
 	{ XFS_BMAPI_CONTIG,	"CONTIG" }, \
-	{ XFS_BMAPI_CONVERT,	"CONVERT" }
+	{ XFS_BMAPI_CONVERT,	"CONVERT" }, \
+	{ XFS_BMAPI_ZERO,	"ZERO" }
 
 
 static inline int xfs_bmapi_aflag(int w)

index 3bf4ad0..3f59698 100644
@@ -57,6 +57,35 @@ xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
 }
 
 /*
+ * Routine to zero an extent on disk allocated to the specific inode.
+ *
+ * The VFS functions take a linearised filesystem block offset, so we have to
+ * convert the sparse xfs fsb to the right format first.
+ * VFS types are real funky, too.
+ */
+int
+xfs_zero_extent(
+	struct xfs_inode *ip,
+	xfs_fsblock_t	start_fsb,
+	xfs_off_t	count_fsb)
+{
+	struct xfs_mount *mp = ip->i_mount;
+	xfs_daddr_t	sector = xfs_fsb_to_db(ip, start_fsb);
+	sector_t	block = XFS_BB_TO_FSBT(mp, sector);
+	ssize_t		size = XFS_FSB_TO_B(mp, count_fsb);
+
+	if (IS_DAX(VFS_I(ip)))
+		return dax_clear_blocks(VFS_I(ip), block, size);
+
+	/*
+	 * let the block layer decide on the fastest method of
+	 * implementing the zeroing.
+	 */
+	return sb_issue_zeroout(mp->m_super, block, count_fsb, GFP_NOFS);
+
+}
+
+/*
  * Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi
  * caller.  Frees all the extents that need freeing, which must be done
  * last due to locking considerations.  We never free any extents in

@@ -229,6 +258,13 @@ xfs_bmap_rtalloc(
 		xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
 			ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
 					XFS_TRANS_DQ_RTBCOUNT, (long) ralen);
+
+		/* Zero the extent if we were asked to do so */
+		if (ap->userdata & XFS_ALLOC_USERDATA_ZERO) {
+			error = xfs_zero_extent(ap->ip, ap->blkno, ap->length);
+			if (error)
+				return error;
+		}
 	} else {
 		ap->length = 0;
 	}

index 7999e91..404bfa5 100644
@@ -336,4 +336,7 @@ extern int	xfs_dev_is_read_only(struct xfs_mount *, char *);
 
 extern void	xfs_set_low_space_thresholds(struct xfs_mount *);
 
+int	xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb,
+			xfs_off_t count_fsb);
+
 #endif	/* __XFS_MOUNT_H__ */

2.5.0
---
 fs/dax.c           |  5 +++++
 fs/xfs/xfs_aops.c  | 13 +++++++++----
 fs/xfs/xfs_iomap.c | 17 ++++++++++++++++-
 3 files changed, 30 insertions(+), 5 deletions(-)
index 3994a2b..b36d6d2 100644
@@ -29,6 +29,11 @@
 #include <linux/uio.h>
 #include <linux/vmstat.h>
 
+/*
+ * dax_clear_blocks() is called from within transaction context from XFS,
+ * and hence this means the stack from this point must follow GFP_NOFS
+ * semantics for all operations.
+ */
 int dax_clear_blocks(struct inode *inode, sector_t block, long size)
 {
 	struct block_device *bdev = inode->i_sb->s_bdev;

index e747d6a..df3dabd 100644
@@ -1284,15 +1284,12 @@ xfs_map_direct(
 
 	trace_xfs_gbmap_direct(XFS_I(inode), offset, size, type, imap);
 
-	/* XXX: preparation for removing unwritten extents in DAX */
-#if 0
 	if (dax_fault) {
 		ASSERT(type == XFS_IO_OVERWRITE);
 		trace_xfs_gbmap_direct_none(XFS_I(inode), offset, size, type,
 					    imap);
 		return;
 	}
-#endif
 
 	if (bh_result->b_private) {
 		ioend = bh_result->b_private;

@@ -1420,10 +1417,12 @@ __xfs_get_blocks(
 	if (error)
 		goto out_unlock;
 
+	/* for DAX, we convert unwritten extents directly */
 	if (create &&
 	    (!nimaps ||
 	     (imap.br_startblock == HOLESTARTBLOCK ||
-	      imap.br_startblock == DELAYSTARTBLOCK))) {
+	      imap.br_startblock == DELAYSTARTBLOCK) ||
+	     (IS_DAX(inode) && ISUNWRITTEN(&imap)))) {
 		if (direct || xfs_get_extsz_hint(ip)) {
 			/*
 			 * Drop the ilock in preparation for starting the block

@@ -1468,6 +1467,12 @@ __xfs_get_blocks(
 		goto out_unlock;
 	}
 
+	if (IS_DAX(inode) && create) {
+		ASSERT(!ISUNWRITTEN(&imap));
+		/* zeroing is not needed at a higher layer */
+		new = 0;
+	}
+
 	/* trim mapping down to size requested */
 	if (direct || size > (1 << inode->i_blkbits))
 		xfs_map_trim_size(inode, iblock, bh_result,

index 1f86033..8b2b4a9 100644
@@ -131,6 +131,7 @@ xfs_iomap_write_direct(
 	uint		qblocks, resblks, resrtextents;
 	int		committed;
 	int		error;
+	int		bmapi_flags = XFS_BMAPI_PREALLOC;
 
 	error = xfs_qm_dqattach(ip, 0);
 	if (error)

@@ -196,13 +197,26 @@ xfs_iomap_write_direct(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	/*
+	 * For DAX, we do not allocate unwritten extents, but instead we zero
+	 * the block before we commit the transaction.  Ideally we'd like to do
+	 * this outside the transaction context, but if we commit and then crash
+	 * we may not have zeroed the blocks and this will be exposed on
+	 * recovery of the allocation. Hence we must zero before commit.
+	 * Further, if we are mapping unwritten extents here, we need to zero
+	 * and convert them to written so that we don't need an unwritten extent
+	 * callback for DAX.
+	 */
+	if (IS_DAX(VFS_I(ip)))
+		bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
+
+	/*
 	 * From this point onwards we overwrite the imap pointer that the
 	 * caller gave to us.
 	 */
 	xfs_bmap_init(&free_list, &firstfsb);
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-				XFS_BMAPI_PREALLOC, &firstfsb, 0,
+				bmapi_flags, &firstfsb, 0,
 				imap, &nimaps, &free_list);
 	if (error)
 		goto out_bmap_cancel;

@@ -213,6 +227,7 @@ xfs_iomap_write_direct(
 	error = xfs_bmap_finish(&tp, &free_list, &committed);
 	if (error)
 		goto out_bmap_cancel;
+
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_unlock;

2.5.0

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_aops.c | 39 ---------------------------------------
 fs/xfs/xfs_aops.h |  1 -
 fs/xfs/xfs_file.c |  5 ++---
 3 files changed, 2 insertions(+), 43 deletions(-)
index df3dabd..69c2dbc 100644
@@ -1657,45 +1657,6 @@ xfs_end_io_direct_write(
 	__xfs_end_io_direct_write(inode, ioend, offset, size);
 }
 
-/*
- * For DAX we need a mapping buffer callback for unwritten extent conversion
- * when page faults allocate blocks and then zero them. Note that in this
- * case the mapping indicated by the ioend may extend beyond EOF. We most
- * definitely do not want to extend EOF here, so we trim back the ioend size to
- * EOF.
- */
-#ifdef CONFIG_FS_DAX
-void
-xfs_end_io_dax_write(
-	struct buffer_head	*bh,
-	int			uptodate)
-{
-	struct xfs_ioend	*ioend = bh->b_private;
-	struct inode		*inode = ioend->io_inode;
-	ssize_t			size = ioend->io_size;
-
-	ASSERT(IS_DAX(ioend->io_inode));
-
-	/* if there was an error zeroing, then don't convert it */
-	if (!uptodate)
-		ioend->io_error = -EIO;
-
-	/*
-	 * Trim update to EOF, so we don't extend EOF during unwritten extent
-	 * conversion of partial EOF blocks.
-	 */
-	spin_lock(&XFS_I(inode)->i_flags_lock);
-	if (ioend->io_offset + size > i_size_read(inode))
-		size = i_size_read(inode) - ioend->io_offset;
-	spin_unlock(&XFS_I(inode)->i_flags_lock);
-
-	__xfs_end_io_direct_write(inode, ioend, ioend->io_offset, size);
-
-}
-#else
-void xfs_end_io_dax_write(struct buffer_head *bh, int uptodate) { }
-#endif
-
 static inline ssize_t
 xfs_vm_do_dio(
 	struct inode		*inode,

index d39ba25..f6ffc9a 100644
@@ -60,7 +60,6 @@ int	xfs_get_blocks_direct(struct inode *inode, sector_t offset,
 			      struct buffer_head *map_bh, int create);
 int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
 			         struct buffer_head *map_bh, int create);
-void	xfs_end_io_dax_write(struct buffer_head *bh, int uptodate);
 
 extern void xfs_count_page_state(struct page *, int *, int *);
 

index 27abe1c..9c8eef7 100644
@@ -1503,8 +1503,7 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault,
-				    xfs_end_io_dax_write);
+		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
 	} else {
 		ret = __block_page_mkwrite(vma, vmf, xfs_get_blocks);
 		ret = block_page_mkwrite_return(ret);

@@ -1566,7 +1565,7 @@ xfs_filemap_pmd_fault(
 	file_update_time(vma->vm_file);
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
-				    xfs_end_io_dax_write);
+			      NULL);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	sb_end_pagefault(inode->i_sb);
 

2.5.0
---
 fs/xfs/xfs_file.c  | 35 +++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_trace.h |  1 +
 2 files changed, 36 insertions(+)
index 9c8eef7..f429662 100644
@@ -1572,11 +1572,46 @@ xfs_filemap_pmd_fault(
 	return ret;
 }
 
+/*
+ * pfn_mkwrite was originally inteneded to ensure we capture time stamp
+ * updates on write faults. In reality, it's need to serialise against
+ * truncate similar to page_mkwrite. Hence we open-code dax_pfn_mkwrite()
+ * here and cycle the XFS_MMAPLOCK_SHARED to ensure we serialise the fault
+ * barrier in place.
+ */
+static int
+xfs_filemap_pfn_mkwrite(
+	struct vm_area_struct	*vma,
+	struct vm_fault		*vmf)
+{
+
+	struct inode		*inode = file_inode(vma->vm_file);
+	struct xfs_inode	*ip = XFS_I(inode);
+	int			ret = VM_FAULT_NOPAGE;
+	loff_t			size;
+
+	trace_xfs_filemap_pfn_mkwrite(ip);
+
+	sb_start_pagefault(inode->i_sb);
+	file_update_time(vma->vm_file);
+
+	/* check if the faulting page hasn't raced with truncate */
+	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size)
+		ret = VM_FAULT_SIGBUS;
+	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+	sb_end_pagefault(inode->i_sb);
+	return ret;
+
+}
+
 static const struct vm_operations_struct xfs_file_vm_ops = {
 	.fault		= xfs_filemap_fault,
 	.pmd_fault	= xfs_filemap_pmd_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= xfs_filemap_page_mkwrite,
+	.pfn_mkwrite	= xfs_filemap_pfn_mkwrite,
 };
 
 STATIC int

index 5ed36b1..c53beda 100644
@@ -689,6 +689,7 @@ DEFINE_INODE_EVENT(xfs_inode_free_eofblocks_invalid);
 DEFINE_INODE_EVENT(xfs_filemap_fault);
 DEFINE_INODE_EVENT(xfs_filemap_pmd_fault);
 DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite);
+DEFINE_INODE_EVENT(xfs_filemap_pfn_mkwrite);
 
 DECLARE_EVENT_CLASS(xfs_iref_class,
 	TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip),

2.5.0

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
	# diff -u tests/generic/274.out /root/xfstests/results//generic/274.out.bad
	--- tests/generic/274.out	2015-08-24 11:05:41.490926305 -0600
	+++ /root/xfstests/results//generic/274.out.bad	2015-10-01 13:53:50.498354091 -0600
	@@ -2,4 +2,5 @@
	 ------------------------------
	 preallocation test
	 ------------------------------
	-done
	+failed to write to test file
	+(see /root/xfstests/results//generic/274.full for details)
	# diff -u tests/generic/274.out /root/xfstests/results//generic/274.out.bad
	--- tests/generic/274.out	2015-08-24 11:05:41.490926305 -0600
	+++ /root/xfstests/results//generic/274.out.bad	2015-10-01 13:53:50.498354091 -0600
	@@ -2,4 +2,5 @@
	 ------------------------------
	 preallocation test
	 ------------------------------
	-done
	+failed to write to test file
	+(see /root/xfstests/results//generic/274.full for details)
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs

xfs, dax: fix the page fault/allocation mess

Dave Chinner

Dave Chinner

kbuild test robot

Ross Zwisler

Williams, Dan J

Ross Zwisler

Dave Chinner

Ross Zwisler

Dave Chinner

Dave Chinner

Dave Chinner

Dave Chinner

Dave Chinner

Dave Chinner

Ross Zwisler

Dave Chinner