1 files changed, 43 insertions, 80 deletions

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 309e26c9dddb..299aee4b7b0b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -44,23 +44,10 @@
 #include <linux/falloc.h>
 #include <linux/pagevec.h>
 #include <linux/backing-dev.h>
+#include <linux/mman.h>
 
 static const struct vm_operations_struct xfs_file_vm_ops;
 
-/*
- * Clear the specified ranges to zero through either the pagecache or DAX.
- * Holes and unwritten extents will be left as-is as they already are zeroed.
- */
-int
-xfs_zero_range(
-	struct xfs_inode	*ip,
-	xfs_off_t		pos,
-	xfs_off_t		count,
-	bool			*did_zero)
-{
-	return iomap_zero_range(VFS_I(ip), pos, count, did_zero, &xfs_iomap_ops);
-}
-
 int
 xfs_update_prealloc_flags(
 	struct xfs_inode	*ip,
@@ -121,7 +108,7 @@ xfs_dir_fsync(
 
 	if (!lsn)
 		return 0;
-	return _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, NULL);
+	return xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, NULL);
 }
 
 STATIC int
@@ -181,7 +168,7 @@ xfs_file_fsync(
 	}
 
 	if (lsn) {
-		error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
+		error = xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
 		ip->i_itemp->ili_fsync_fields = 0;
 	}
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
@@ -237,11 +224,13 @@ xfs_file_dax_read(
 	if (!count)
 		return 0; /* skip atime */
 
-	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
 			return -EAGAIN;
+	} else {
 		xfs_ilock(ip, XFS_IOLOCK_SHARED);
 	}
+
 	ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops);
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
@@ -259,9 +248,10 @@ xfs_file_buffered_aio_read(
 
 	trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos);
 
-	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
 			return -EAGAIN;
+	} else {
 		xfs_ilock(ip, XFS_IOLOCK_SHARED);
 	}
 	ret = generic_file_read_iter(iocb, to);
@@ -297,31 +287,6 @@ xfs_file_read_iter(
 }
 
 /*
- * Zero any on disk space between the current EOF and the new, larger EOF.
- *
- * This handles the normal case of zeroing the remainder of the last block in
- * the file and the unusual case of zeroing blocks out beyond the size of the
- * file.  This second case only happens with fixed size extents and when the
- * system crashes before the inode size was updated but after blocks were
- * allocated.
- *
- * Expects the iolock to be held exclusive, and will take the ilock internally.
- */
-int					/* error (positive) */
-xfs_zero_eof(
-	struct xfs_inode	*ip,
-	xfs_off_t		offset,		/* starting I/O offset */
-	xfs_fsize_t		isize,		/* current inode size */
-	bool			*did_zeroing)
-{
-	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
-	ASSERT(offset > isize);
-
-	trace_xfs_zero_eof(ip, isize, offset - isize);
-	return xfs_zero_range(ip, isize, offset - isize, did_zeroing);
-}
-
-/*
  * Common pre-write limit and setup checks.
  *
  * Called with the iolocked held either shared and exclusive according to
@@ -340,6 +305,7 @@ xfs_file_aio_write_checks(
 	ssize_t			error = 0;
 	size_t			count = iov_iter_count(from);
 	bool			drained_dio = false;
+	loff_t			isize;
 
 restart:
 	error = generic_write_checks(iocb, from);
@@ -376,7 +342,8 @@ restart:
 	 * and hence be able to correctly determine if we need to run zeroing.
 	 */
 	spin_lock(&ip->i_flags_lock);
-	if (iocb->ki_pos > i_size_read(inode)) {
+	isize = i_size_read(inode);
+	if (iocb->ki_pos > isize) {
 		spin_unlock(&ip->i_flags_lock);
 		if (!drained_dio) {
 			if (*iolock == XFS_IOLOCK_SHARED) {
@@ -397,7 +364,10 @@ restart:
 			drained_dio = true;
 			goto restart;
 		}
-		error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), NULL);
+	
+		trace_xfs_zero_eof(ip, isize, iocb->ki_pos - isize);
+		error = iomap_zero_range(inode, isize, iocb->ki_pos - isize,
+				NULL, &xfs_iomap_ops);
 		if (error)
 			return error;
 	} else
@@ -552,9 +522,10 @@ xfs_file_dio_aio_write(
 		iolock = XFS_IOLOCK_SHARED;
 	}
 
-	if (!xfs_ilock_nowait(ip, iolock)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!xfs_ilock_nowait(ip, iolock))
 			return -EAGAIN;
+	} else {
 		xfs_ilock(ip, iolock);
 	}
 
@@ -606,9 +577,10 @@ xfs_file_dax_write(
 	size_t			count;
 	loff_t			pos;
 
-	if (!xfs_ilock_nowait(ip, iolock)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!xfs_ilock_nowait(ip, iolock))
 			return -EAGAIN;
+	} else {
 		xfs_ilock(ip, iolock);
 	}
 
@@ -764,7 +736,7 @@ xfs_file_fallocate(
 	enum xfs_prealloc_flags	flags = 0;
 	uint			iolock = XFS_IOLOCK_EXCL;
 	loff_t			new_size = 0;
-	bool			do_file_insert = 0;
+	bool			do_file_insert = false;
 
 	if (!S_ISREG(inode->i_mode))
 		return -EINVAL;
@@ -825,7 +797,7 @@ xfs_file_fallocate(
 			error = -EINVAL;
 			goto out_unlock;
 		}
-		do_file_insert = 1;
+		do_file_insert = true;
 	} else {
 		flags |= XFS_PREALLOC_SET;
 
@@ -979,7 +951,7 @@ xfs_file_readdir(
 	 * point we can change the ->readdir prototype to include the
 	 * buffer size.  For now we use the current glibc buffer size.
 	 */
-	bufsize = (size_t)min_t(loff_t, 32768, ip->i_d.di_size);
+	bufsize = (size_t)min_t(loff_t, XFS_READDIR_BUFSIZE, ip->i_d.di_size);
 
 	return xfs_readdir(NULL, ip, ctx, bufsize);
 }
@@ -1040,7 +1012,11 @@ __xfs_filemap_fault(
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	if (IS_DAX(inode)) {
-		ret = dax_iomap_fault(vmf, pe_size, &xfs_iomap_ops);
+		pfn_t pfn;
+
+		ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL, &xfs_iomap_ops);
+		if (ret & VM_FAULT_NEEDDSYNC)
+			ret = dax_finish_sync_fault(vmf, pe_size, pfn);
 	} else {
 		if (write_fault)
 			ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops);
@@ -1085,37 +1061,16 @@ xfs_filemap_page_mkwrite(
 }
 
 /*
- * 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 cycle the XFS_MMAPLOCK_SHARED
- * to ensure we serialise the fault barrier in place.
+ * pfn_mkwrite was originally intended to ensure we capture time stamp updates
+ * on write faults. In reality, it needs to serialise against truncate and
+ * prepare memory for writing so handle is as standard write fault.
  */
 static int
 xfs_filemap_pfn_mkwrite(
 	struct vm_fault		*vmf)
 {
 
-	struct inode		*inode = file_inode(vmf->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(vmf->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;
-	else if (IS_DAX(inode))
-		ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
-	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
-	sb_end_pagefault(inode->i_sb);
-	return ret;
-
+	return __xfs_filemap_fault(vmf, PE_SIZE_PTE, true);
 }
 
 static const struct vm_operations_struct xfs_file_vm_ops = {
@@ -1131,6 +1086,13 @@ xfs_file_mmap(
 	struct file	*filp,
 	struct vm_area_struct *vma)
 {
+	/*
+	 * We don't support synchronous mappings for non-DAX files. At least
+	 * until someone comes with a sensible use case.
+	 */
+	if (!IS_DAX(file_inode(filp)) && (vma->vm_flags & VM_SYNC))
+		return -EOPNOTSUPP;
+
 	file_accessed(filp);
 	vma->vm_ops = &xfs_file_vm_ops;
 	if (IS_DAX(file_inode(filp)))
@@ -1149,6 +1111,7 @@ const struct file_operations xfs_file_operations = {
 	.compat_ioctl	= xfs_file_compat_ioctl,
 #endif
 	.mmap		= xfs_file_mmap,
+	.mmap_supported_flags = MAP_SYNC,
 	.open		= xfs_file_open,
 	.release	= xfs_file_release,
 	.fsync		= xfs_file_fsync,