[PATCH 06/10] dax: provide an iomap based fault handler

From: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
To: linux-xfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	linux-nvdimm-y27Ovi1pjclAfugRpC6u6w@public.gmane.org
Subject: [PATCH 06/10] dax: provide an iomap based fault handler
Date: Fri,  9 Sep 2016 18:34:40 +0200	[thread overview]
Message-ID: <1473438884-674-7-git-send-email-hch@lst.de> (raw)
In-Reply-To: <1473438884-674-1-git-send-email-hch-jcswGhMUV9g@public.gmane.org>

Very similar to the existing dax_fault function, but instead of using
the get_block callback we rely on the iomap_ops vector from iomap.c.
That also avoids having to do two calls into the file system for write
faults.

Signed-off-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
---
 fs/dax.c              | 113 ++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/iomap.h |   2 +
 2 files changed, 115 insertions(+)

diff --git a/fs/dax.c b/fs/dax.c
index 57ad456..a170a94 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1343,4 +1343,117 @@ iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter,
 	return done;
 }
 EXPORT_SYMBOL_GPL(iomap_dax_rw);
+
+/**
+ * iomap_dax_fault - handle a page fault on a DAX file
+ * @vma: The virtual memory area where the fault occurred
+ * @vmf: The description of the fault
+ * @ops: iomap ops passed from the file system
+ *
+ * When a page fault occurs, filesystems may call this helper in their fault
+ * or mkwrite handler for DAX files. Sssumes the caller has done all the
+ * necessary locking for the page fault to proceed successfully.
+ */
+int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+			struct iomap_ops *ops)
+{
+	struct address_space *mapping = vma->vm_file->f_mapping;
+	struct inode *inode = mapping->host;
+	unsigned long vaddr = (unsigned long)vmf->virtual_address;
+	loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
+	sector_t sector;
+	struct iomap iomap = { 0 };
+	unsigned flags = 0;
+	int error, major = 0;
+	void *entry;
+
+	/*
+	 * Check whether offset isn't beyond end of file now. Caller is supposed
+	 * to hold locks serializing us with truncate / punch hole so this is
+	 * a reliable test.
+	 */
+	if (pos >= i_size_read(inode))
+		return VM_FAULT_SIGBUS;
+
+	entry = grab_mapping_entry(mapping, vmf->pgoff);
+	if (IS_ERR(entry)) {
+		error = PTR_ERR(entry);
+		goto out;
+	}
+
+	if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page)
+		flags |= IOMAP_WRITE;
+
+	/*
+	 * Note that we don't bother to use iomap_apply here: DAX required
+	 * the file system block size to be equal the page size, which means
+	 * that we never have to deal with more than a single extent here.
+	 */
+	error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
+	if (error)
+		goto unlock_entry;
+	if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
+		error = -EIO;		/* fs corruption? */
+		goto unlock_entry;
+	}
+
+	sector = iomap.blkno + (((pos & PAGE_MASK) - iomap.offset) >> 9);
+
+	if (vmf->cow_page) {
+		switch (iomap.type) {
+		case IOMAP_HOLE:
+		case IOMAP_UNWRITTEN:
+			clear_user_highpage(vmf->cow_page, vaddr);
+			break;
+		case IOMAP_MAPPED:
+			error = copy_user_dax(iomap.bdev, sector, PAGE_SIZE,
+					vmf->cow_page, vaddr);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			error = -EIO;
+			break;
+		}
+
+		if (error)
+			goto unlock_entry;
+		if (!radix_tree_exceptional_entry(entry)) {
+			vmf->page = entry;
+			return VM_FAULT_LOCKED;
+		}
+		vmf->entry = entry;
+		return VM_FAULT_DAX_LOCKED;
+	}
+
+	switch (iomap.type) {
+	case IOMAP_MAPPED:
+		if (iomap.flags & IOMAP_F_NEW) {
+			count_vm_event(PGMAJFAULT);
+			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+			major = VM_FAULT_MAJOR;
+		}
+		break;
+	case IOMAP_UNWRITTEN:
+	case IOMAP_HOLE:
+		if (!(vmf->flags & FAULT_FLAG_WRITE))
+			return dax_load_hole(mapping, entry, vmf);
+	default:
+		WARN_ON_ONCE(1);
+		error = -EIO;
+	}
+
+	/* Filesystem should not return unwritten buffers to us! */
+	error = dax_insert_mapping(mapping, iomap.bdev, sector, PAGE_SIZE,
+			&entry, vma, vmf);
+unlock_entry:
+	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
+out:
+	if (error == -ENOMEM)
+		return VM_FAULT_OOM | major;
+	/* -EBUSY is fine, somebody else faulted on the same PTE */
+	if (error < 0 && error != -EBUSY)
+		return VM_FAULT_SIGBUS | major;
+	return VM_FAULT_NOPAGE | major;
+}
+EXPORT_SYMBOL_GPL(iomap_dax_fault);
 #endif /* CONFIG_FS_IOMAP */
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 3d5f785..a4ef953 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -73,6 +73,8 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 		struct iomap_ops *ops);
 int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 		struct iomap_ops *ops);
+int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+			struct iomap_ops *ops);
 int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		loff_t start, loff_t len, struct iomap_ops *ops);
 
-- 
2.1.4
