[PATCH 6/6] dax: update I/O path to do proper PMEM flushing

[Ross Zwisler <ross.zwisler@linux.intel.com>]

Update the DAX I/O path so that all operations that store data (I/O
writes, zeroing blocks, punching holes, etc.) properly synchronize the
stores to media using the PMEM API.  This ensures that the data DAX is
writing is durable on media before the operation completes.

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
---
 fs/dax.c | 55 ++++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 44 insertions(+), 11 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 47c3323..e7595db 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -17,12 +17,14 @@
 #include <linux/atomic.h>
 #include <linux/blkdev.h>
 #include <linux/buffer_head.h>
+#include <linux/dax.h>
 #include <linux/fs.h>
 #include <linux/genhd.h>
 #include <linux/highmem.h>
 #include <linux/memcontrol.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
+#include <linux/pmem.h>
 #include <linux/sched.h>
 #include <linux/uio.h>
 #include <linux/vmstat.h>
@@ -46,10 +48,13 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long size)
 			unsigned pgsz = PAGE_SIZE - offset_in_page(addr);
 			if (pgsz > count)
 				pgsz = count;
-			if (pgsz < PAGE_SIZE)
+		if (pgsz < PAGE_SIZE) {
 				memset(addr, 0, pgsz);
-			else
+				wb_cache_pmem((void __pmem *)addr, pgsz);
+			} else {
 				clear_page(addr);
+				wb_cache_pmem((void __pmem *)addr, PAGE_SIZE);
+			}
 			addr += pgsz;
 			size -= pgsz;
 			count -= pgsz;
@@ -59,6 +64,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long size)
 		}
 	} while (size);
 
+	wmb_pmem();
 	return 0;
 }
 EXPORT_SYMBOL_GPL(dax_clear_blocks);
@@ -70,15 +76,24 @@ static long dax_get_addr(struct buffer_head *bh, void **addr, unsigned blkbits)
 	return bdev_direct_access(bh->b_bdev, sector, addr, &pfn, bh->b_size);
 }
 
+/*
+ * This function's stores and flushes need to be synced to media by a
+ * wmb_pmem() in the caller. We flush the data instead of writing it back
+ * because we don't expect to read this newly zeroed data in the near future.
+ */
 static void dax_new_buf(void *addr, unsigned size, unsigned first, loff_t pos,
 			loff_t end)
 {
 	loff_t final = end - pos + first; /* The final byte of the buffer */
 
-	if (first > 0)
+	if (first > 0) {
 		memset(addr, 0, first);
-	if (final < size)
+		flush_cache_pmem((void __pmem *)addr, first);
+	}
+	if (final < size) {
 		memset(addr + final, 0, size - final);
+		flush_cache_pmem((void __pmem *)addr + final, size - final);
+	}
 }
 
 static bool buffer_written(struct buffer_head *bh)
@@ -108,6 +123,7 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 	loff_t bh_max = start;
 	void *addr;
 	bool hole = false;
+	bool need_wmb = false;
 
 	if (iov_iter_rw(iter) != WRITE)
 		end = min(end, i_size_read(inode));
@@ -145,18 +161,23 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 				retval = dax_get_addr(bh, &addr, blkbits);
 				if (retval < 0)
 					break;
-				if (buffer_unwritten(bh) || buffer_new(bh))
+				if (buffer_unwritten(bh) || buffer_new(bh)) {
 					dax_new_buf(addr, retval, first, pos,
 									end);
+					need_wmb = true;
+				}
 				addr += first;
 				size = retval - first;
 			}
 			max = min(pos + size, end);
 		}
 
-		if (iov_iter_rw(iter) == WRITE)
+		if (iov_iter_rw(iter) == WRITE) {
 			len = copy_from_iter_nocache(addr, max - pos, iter);
-		else if (!hole)
+			if (!iter_is_iovec(iter))
+				wb_cache_pmem((void __pmem *)addr, max - pos);
+			need_wmb = true;
+		} else if (!hole)
 			len = copy_to_iter(addr, max - pos, iter);
 		else
 			len = iov_iter_zero(max - pos, iter);
@@ -168,6 +189,9 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 		addr += len;
 	}
 
+	if (need_wmb)
+		wmb_pmem();
+
 	return (pos == start) ? retval : pos - start;
 }
 
@@ -300,8 +324,11 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 		goto out;
 	}
 
-	if (buffer_unwritten(bh) || buffer_new(bh))
+	if (buffer_unwritten(bh) || buffer_new(bh)) {
 		clear_page(addr);
+		wb_cache_pmem((void __pmem *)addr, PAGE_SIZE);
+		wmb_pmem();
+	}
 
 	error = vm_insert_mixed(vma, vaddr, pfn);
 
@@ -504,7 +531,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	unsigned long pmd_addr = address & PMD_MASK;
 	bool write = flags & FAULT_FLAG_WRITE;
 	long length;
-	void *kaddr;
+	void *kaddr, *paddr;
 	pgoff_t size, pgoff;
 	sector_t block, sector;
 	unsigned long pfn;
@@ -593,8 +620,12 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 
 		if (buffer_unwritten(&bh) || buffer_new(&bh)) {
 			int i;
-			for (i = 0; i < PTRS_PER_PMD; i++)
-				clear_page(kaddr + i * PAGE_SIZE);
+			for (i = 0; i < PTRS_PER_PMD; i++) {
+				paddr = kaddr + i * PAGE_SIZE;
+				clear_page(paddr);
+				wb_cache_pmem((void __pmem *)paddr, PAGE_SIZE);
+			}
+			wmb_pmem();
 			count_vm_event(PGMAJFAULT);
 			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
 			result |= VM_FAULT_MAJOR;
@@ -707,6 +738,8 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
 		if (err < 0)
 			return err;
 		memset(addr + offset, 0, length);
+		flush_cache_pmem((void __pmem *)addr + offset, length);
+		wmb_pmem();
 	}
 
 	return 0;
-- 
2.1.0