ext4: Support for synchronous DAX faults

We return IOMAP_F_DIRTY flag from ext4_iomap_begin() when asked to
prepare blocks for writing and the inode has some uncommitted metadata
changes. In the fault handler ext4_dax_fault() we then detect this case
(through VM_FAULT_NEEDDSYNC return value) and call helper
dax_finish_sync_fault() to flush metadata changes and insert page table
entry. Note that this will also dirty corresponding radix tree entry
which is what we want - fsync(2) will still provide data integrity
guarantees for applications not using userspace flushing. And
applications using userspace flushing can avoid calling fsync(2) and
thus avoid the performance overhead.

Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

fs/ext4/file.c

@@ -26,6 +26,7 @@
 #include <linux/quotaops.h>
 #include <linux/pagevec.h>
 #include <linux/uio.h>
+#include <linux/mman.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -295,6 +296,7 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
 	 */
 	bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
 		(vmf->vma->vm_flags & VM_SHARED);
+	pfn_t pfn;
 
 	if (write) {
 		sb_start_pagefault(sb);
@@ -310,9 +312,12 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf,
 	} else {
 		down_read(&EXT4_I(inode)->i_mmap_sem);
 	}
-	result = dax_iomap_fault(vmf, pe_size, NULL, &ext4_iomap_ops);
+	result = dax_iomap_fault(vmf, pe_size, &pfn, &ext4_iomap_ops);
 	if (write) {
 		ext4_journal_stop(handle);
+		/* Handling synchronous page fault? */
+		if (result & VM_FAULT_NEEDDSYNC)
+			result = dax_finish_sync_fault(vmf, pe_size, pfn);
 		up_read(&EXT4_I(inode)->i_mmap_sem);
 		sb_end_pagefault(sb);
 	} else {
@@ -350,6 +355,13 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
+	/*
+	 * 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(file)) && (vma->vm_flags & VM_SYNC))
+		return -EOPNOTSUPP;
+
 	file_accessed(file);
 	if (IS_DAX(file_inode(file))) {
 		vma->vm_ops = &ext4_dax_vm_ops;
@@ -719,6 +731,7 @@ const struct file_operations ext4_file_operations = {
 	.compat_ioctl	= ext4_compat_ioctl,
 #endif
 	.mmap		= ext4_file_mmap,
+	.mmap_supported_flags = MAP_SYNC,
 	.open		= ext4_file_open,
 	.release	= ext4_release_file,
 	.fsync		= ext4_sync_file,

fs/ext4/inode.c

@@ -3394,6 +3394,19 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 }
 
 #ifdef CONFIG_FS_DAX
+static bool ext4_inode_datasync_dirty(struct inode *inode)
+{
+	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+
+	if (journal)
+		return !jbd2_transaction_committed(journal,
+					EXT4_I(inode)->i_datasync_tid);
+	/* Any metadata buffers to write? */
+	if (!list_empty(&inode->i_mapping->private_list))
+		return true;
+	return inode->i_state & I_DIRTY_DATASYNC;
+}
+
 static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 			    unsigned flags, struct iomap *iomap)
 {
@@ -3466,6 +3479,8 @@ retry:
 	}
 
 	iomap->flags = 0;
+	if ((flags & IOMAP_WRITE) && ext4_inode_datasync_dirty(inode))
+		iomap->flags |= IOMAP_F_DIRTY;
 	iomap->bdev = inode->i_sb->s_bdev;
 	iomap->dax_dev = sbi->s_daxdev;
 	iomap->offset = first_block << blkbits;