Message-Id: <1450899560-26708-5-git-send-email-ross.zwisler@linux.intel.com>
Date:	Wed, 23 Dec 2015 12:39:17 -0700
From:	Ross Zwisler <ross.zwisler@...ux.intel.com>
To:	linux-kernel@...r.kernel.org
Cc:	Ross Zwisler <ross.zwisler@...ux.intel.com>,
	"H. Peter Anvin" <hpa@...or.com>,
	"J. Bruce Fields" <bfields@...ldses.org>,
	"Theodore Ts'o" <tytso@....edu>,
	Alexander Viro <viro@...iv.linux.org.uk>,
	Andreas Dilger <adilger.kernel@...ger.ca>,
	Dave Chinner <david@...morbit.com>,
	Ingo Molnar <mingo@...hat.com>, Jan Kara <jack@...e.com>,
	Jeff Layton <jlayton@...chiereds.net>,
	Matthew Wilcox <willy@...ux.intel.com>,
	Thomas Gleixner <tglx@...utronix.de>,
	linux-ext4@...r.kernel.org, linux-fsdevel@...r.kernel.org,
	linux-mm@...ck.org, linux-nvdimm@...ts.01.org, x86@...nel.org,
	xfs@....sgi.com, Andrew Morton <akpm@...ux-foundation.org>,
	Dan Williams <dan.j.williams@...el.com>,
	Matthew Wilcox <matthew.r.wilcox@...el.com>,
	Dave Hansen <dave.hansen@...ux.intel.com>
Subject: [PATCH v6 4/7] dax: add support for fsync/msync

To properly handle fsync/msync in an efficient way DAX needs to track dirty
pages so it is able to flush them durably to media on demand.

The tracking of dirty pages is done via the radix tree in struct
address_space.  This radix tree is already used by the page writeback
infrastructure for tracking dirty pages associated with an open file, and
it already has support for exceptional (non struct page*) entries.  We
build upon these features to add exceptional entries to the radix tree for
DAX dirty PMD or PTE pages at fault time.

Signed-off-by: Ross Zwisler <ross.zwisler@...ux.intel.com>
---
 fs/dax.c            | 196 ++++++++++++++++++++++++++++++++++++++++++++++++++--
 include/linux/dax.h |   2 +
 mm/filemap.c        |   6 ++
 3 files changed, 198 insertions(+), 6 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 82d0bff..050610d 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -24,6 +24,7 @@
 #include <linux/memcontrol.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
+#include <linux/pagevec.h>
 #include <linux/pmem.h>
 #include <linux/sched.h>
 #include <linux/uio.h>
@@ -323,6 +324,176 @@ static int copy_user_bh(struct page *to, struct inode *inode,
 	return 0;
 }
 
+#define NO_SECTOR -1
+
+static int dax_radix_entry(struct address_space *mapping, pgoff_t index,
+		sector_t sector, bool pmd_entry, bool dirty)
+{
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+	int error = 0;
+	void *entry;
+
+	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+
+	spin_lock_irq(&mapping->tree_lock);
+	entry = radix_tree_lookup(page_tree, index);
+
+	if (entry) {
+		if (!pmd_entry || RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD)
+			goto dirty;
+		radix_tree_delete(&mapping->page_tree, index);
+		mapping->nrexceptional--;
+	}
+
+	if (sector == NO_SECTOR) {
+		/*
+		 * This can happen during correct operation if our pfn_mkwrite
+		 * fault raced against a hole punch operation.  If this
+		 * happens the pte that was hole punched will have been
+		 * unmapped and the radix tree entry will have been removed by
+		 * the time we are called, but the call will still happen.  We
+		 * will return all the way up to wp_pfn_shared(), where the
+		 * pte_same() check will fail, eventually causing page fault
+		 * to be retried by the CPU.
+		 */
+		goto unlock;
+	}
+
+	error = radix_tree_insert(page_tree, index,
+			RADIX_DAX_ENTRY(sector, pmd_entry));
+	if (error)
+		goto unlock;
+
+	mapping->nrexceptional++;
+ dirty:
+	if (dirty)
+		radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY);
+ unlock:
+	spin_unlock_irq(&mapping->tree_lock);
+	return error;
+}
+
+static int dax_writeback_one(struct block_device *bdev,
+		struct address_space *mapping, pgoff_t index, void *entry)
+{
+	struct radix_tree_root *page_tree = &mapping->page_tree;
+	int type = RADIX_DAX_TYPE(entry);
+	struct radix_tree_node *node;
+	struct blk_dax_ctl dax;
+	void **slot;
+	int ret = 0;
+
+	spin_lock_irq(&mapping->tree_lock);
+	/*
+	 * Regular page slots are stabilized by the page lock even
+	 * without the tree itself locked.  These unlocked entries
+	 * need verification under the tree lock.
+	 */
+	if (!__radix_tree_lookup(page_tree, index, &node, &slot))
+		goto unlock;
+	if (*slot != entry)
+		goto unlock;
+
+	/* another fsync thread may have already written back this entry */
+	if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
+		goto unlock;
+
+	radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE);
+
+	if (WARN_ON_ONCE(type != RADIX_DAX_PTE && type != RADIX_DAX_PMD)) {
+		ret = -EIO;
+		goto unlock;
+	}
+
+	dax.sector = RADIX_DAX_SECTOR(entry);
+	dax.size = (type == RADIX_DAX_PMD ? PMD_SIZE : PAGE_SIZE);
+	spin_unlock_irq(&mapping->tree_lock);
+
+	/*
+	 * We cannot hold tree_lock while calling dax_map_atomic() because it
+	 * eventually calls cond_resched().
+	 */
+	ret = dax_map_atomic(bdev, &dax);
+	if (ret < 0)
+		return ret;
+
+	if (WARN_ON_ONCE(ret < dax.size)) {
+		ret = -EIO;
+		dax_unmap_atomic(bdev, &dax);
+		return ret;
+	}
+
+	spin_lock_irq(&mapping->tree_lock);
+	/*
+	 * We need to revalidate our radix entry while holding tree_lock
+	 * before we do the writeback.
+	 */
+	if (!__radix_tree_lookup(page_tree, index, &node, &slot))
+		goto unmap;
+	if (*slot != entry)
+		goto unmap;
+
+	wb_cache_pmem(dax.addr, dax.size);
+ unmap:
+	dax_unmap_atomic(bdev, &dax);
+ unlock:
+	spin_unlock_irq(&mapping->tree_lock);
+	return ret;
+}
+
+/*
+ * Flush the mapping to the persistent domain within the byte range of [start,
+ * end]. This is required by data integrity operations to ensure file data is
+ * on persistent storage prior to completion of the operation.
+ */
+int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
+		loff_t end)
+{
+	struct inode *inode = mapping->host;
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	pgoff_t indices[PAGEVEC_SIZE];
+	pgoff_t start_page, end_page;
+	struct pagevec pvec;
+	void *entry;
+	int i, ret = 0;
+
+	if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
+		return -EIO;
+
+	rcu_read_lock();
+	entry = radix_tree_lookup(&mapping->page_tree, start & PMD_MASK);
+	rcu_read_unlock();
+
+	/* see if the start of our range is covered by a PMD entry */
+	if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD)
+		start &= PMD_MASK;
+
+	start_page = start >> PAGE_CACHE_SHIFT;
+	end_page = end >> PAGE_CACHE_SHIFT;
+
+	tag_pages_for_writeback(mapping, start_page, end_page);
+
+	pagevec_init(&pvec, 0);
+	while (1) {
+		pvec.nr = find_get_entries_tag(mapping, start_page,
+				PAGECACHE_TAG_TOWRITE, PAGEVEC_SIZE,
+				pvec.pages, indices);
+
+		if (pvec.nr == 0)
+			break;
+
+		for (i = 0; i < pvec.nr; i++) {
+			ret = dax_writeback_one(bdev, mapping, indices[i],
+					pvec.pages[i]);
+			if (ret < 0)
+				return ret;
+		}
+	}
+	wmb_pmem();
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
+
 static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 			struct vm_area_struct *vma, struct vm_fault *vmf)
 {
@@ -362,6 +533,11 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 	}
 	dax_unmap_atomic(bdev, &dax);
 
+	error = dax_radix_entry(mapping, vmf->pgoff, dax.sector, false,
+			vmf->flags & FAULT_FLAG_WRITE);
+	if (error)
+		goto out;
+
 	error = vm_insert_mixed(vma, vaddr, dax.pfn);
 
  out:
@@ -486,6 +662,7 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		delete_from_page_cache(page);
 		unlock_page(page);
 		page_cache_release(page);
+		page = NULL;
 	}
 
 	/*
@@ -579,7 +756,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	struct block_device *bdev = NULL;
 	pgoff_t size, pgoff;
 	sector_t block;
-	int result = 0;
+	int error, result = 0;
 
 	/* dax pmd mappings require pfn_t_devmap() */
 	if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
@@ -721,6 +898,16 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		}
 		dax_unmap_atomic(bdev, &dax);
 
+		if (write) {
+			error = dax_radix_entry(mapping, pgoff, dax.sector,
+					true, true);
+			if (error) {
+				dax_pmd_dbg(bdev, address,
+						"PMD radix insertion failed");
+				goto fallback;
+			}
+		}
+
 		dev_dbg(part_to_dev(bdev->bd_part),
 				"%s: %s addr: %lx pfn: %lx sect: %llx\n",
 				__func__, current->comm, address,
@@ -779,15 +966,12 @@ EXPORT_SYMBOL_GPL(dax_pmd_fault);
  * dax_pfn_mkwrite - handle first write to DAX page
  * @vma: The virtual memory area where the fault occurred
  * @vmf: The description of the fault
- *
  */
 int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+	struct file *file = vma->vm_file;
 
-	sb_start_pagefault(sb);
-	file_update_time(vma->vm_file);
-	sb_end_pagefault(sb);
+	dax_radix_entry(file->f_mapping, vmf->pgoff, NO_SECTOR, false, true);
 	return VM_FAULT_NOPAGE;
 }
 EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index e9d57f68..8204c3d 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -41,4 +41,6 @@ static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);
 }
+int dax_writeback_mapping_range(struct address_space *mapping, loff_t start,
+		loff_t end);
 #endif
diff --git a/mm/filemap.c b/mm/filemap.c
index 1e215fc..2e7c8d9 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -482,6 +482,12 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 {
 	int err = 0;
 
+	if (dax_mapping(mapping) && mapping->nrexceptional) {
+		err = dax_writeback_mapping_range(mapping, lstart, lend);
+		if (err)
+			return err;
+	}
+
 	if (mapping->nrpages) {
 		err = __filemap_fdatawrite_range(mapping, lstart, lend,
 						 WB_SYNC_ALL);
-- 
2.6.3

--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists