ext2: DIO to use iomap

index 26f135e7ffce..dc76147e7b07 100644
@@ -1259,9 +1259,8 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 	inode_dio_wait(inode);
 
 	if (IS_DAX(inode))
-		error = dax_zero_range(inode, newsize,
-				       PAGE_ALIGN(newsize) - newsize, NULL,
-				       &ext2_iomap_ops);
+		error = dax_truncate_page(inode, newsize, NULL,
+					  &ext2_iomap_ops);
 	else
 		error = block_truncate_page(inode->i_mapping,
 				newsize, ext2_get_block);

index 9e1e2add541e..df98f1966a71 100644
@@ -593,6 +593,49 @@ int sync_mapping_buffers(struct address_space *mapping)
 }
 EXPORT_SYMBOL(sync_mapping_buffers);
 
+/**
+ * generic_buffer_fsync - generic buffer fsync implementation
+ * for simple filesystems with no inode lock
+ *
+ * @file:	file to synchronize
+ * @start:	start offset in bytes
+ * @end:	end offset in bytes (inclusive)
+ * @datasync:	only synchronize essential metadata if true
+ *
+ * This is a generic implementation of the fsync method for simple
+ * filesystems which track all non-inode metadata in the buffers list
+ * hanging off the address_space structure.
+ */
+int generic_buffer_fsync(struct file *file, loff_t start, loff_t end,
+			 bool datasync)
+{
+	struct inode *inode = file->f_mapping->host;
+	int err;
+	int ret;
+
+	err = file_write_and_wait_range(file, start, end);
+	if (err)
+		return err;
+
+	ret = sync_mapping_buffers(inode->i_mapping);
+	if (!(inode->i_state & I_DIRTY_ALL))
+		goto out;
+	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+		goto out;
+
+	err = sync_inode_metadata(inode, 1);
+	if (ret == 0)
+		ret = err;
+
+out:
+	/* check and advance again to catch errors after syncing out buffers */
+	err = file_check_and_advance_wb_err(file);
+	if (ret == 0)
+		ret = err;
+	return ret;
+}
+EXPORT_SYMBOL(generic_buffer_fsync);
+
 /*
  * Called when we've recently written block `bblock', and it is known that
  * `bblock' was for a buffer_boundary() buffer.  This means that the block at

index 8f14dca5fed7..3170d0792d52 100644
@@ -211,6 +211,8 @@ int inode_has_buffers(struct inode *);
 void invalidate_inode_buffers(struct inode *);
 int remove_inode_buffers(struct inode *inode);
 int sync_mapping_buffers(struct address_space *mapping);
+int generic_buffer_fsync(struct file *file, loff_t start, loff_t end,
+			 bool datasync);
 void clean_bdev_aliases(struct block_device *bdev, sector_t block,
 			sector_t len);
 static inline void clean_bdev_bh_alias(struct buffer_head *bh)

index 027a7d7037a0..4f2af43f8b0f 100644
@@ -28,6 +28,7 @@
 #include <linux/sched.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
+#include <linux/buffer_head.h>
 
 #include "ext4.h"
 #include "ext4_jbd2.h"

@@ -78,21 +79,13 @@ static int ext4_sync_parent(struct inode *inode)
 	return ret;
 }
 
-static int ext4_fsync_nojournal(struct inode *inode, bool datasync,
-				bool *needs_barrier)
+static int ext4_fsync_nojournal(struct file *file, loff_t start, loff_t end,
+				int datasync, bool *needs_barrier)
 {
-	int ret, err;
-
-	ret = sync_mapping_buffers(inode->i_mapping);
-	if (!(inode->i_state & I_DIRTY_ALL))
-		return ret;
-	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
-		return ret;
-
-	err = sync_inode_metadata(inode, 1);
-	if (!ret)
-		ret = err;
+	struct inode *inode = file->f_inode;
+	int ret;
 
+	ret = generic_buffer_fsync(file, start, end, datasync);
 	if (!ret)
 		ret = ext4_sync_parent(inode);
 	if (test_opt(inode->i_sb, BARRIER))

@@ -148,6 +141,14 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		goto out;
 	}
 
+	if (!sbi->s_journal) {
+		ret = ext4_fsync_nojournal(file, start, end, datasync,
+					   &needs_barrier);
+		if (needs_barrier)
+			goto issue_flush;
+		goto out;
+	}
+
 	ret = file_write_and_wait_range(file, start, end);
 	if (ret)
 		goto out;

@@ -166,13 +167,12 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 *  (they were dirtied by commit).  But that's OK - the blocks are
 	 *  safe in-journal, which is all fsync() needs to ensure.
 	 */
-	if (!sbi->s_journal)
-		ret = ext4_fsync_nojournal(inode, datasync, &needs_barrier);
-	else if (ext4_should_journal_data(inode))
+	if (ext4_should_journal_data(inode))
 		ret = ext4_force_commit(inode->i_sb);
 	else
 		ret = ext4_fsync_journal(inode, datasync, &needs_barrier);
 
+issue_flush:
 	if (needs_barrier) {
 		err = blkdev_issue_flush(inode->i_sb->s_bdev);
 		if (!ret)

index 6b4bebe982ca..7603427fb38f 100644
@@ -25,6 +25,7 @@
 #include <linux/quotaops.h>
 #include <linux/iomap.h>
 #include <linux/uio.h>
+#include <linux/buffer_head.h>
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"

@@ -153,7 +154,9 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	int ret;
 	struct super_block *sb = file->f_mapping->host->i_sb;
 
-	ret = generic_file_fsync(file, start, end, datasync);
+	ret = generic_buffer_fsync(file, start, end, datasync);
+	if (!ret)
+		ret = blkdev_issue_flush(sb->s_bdev);
 	if (ret == -EIO)
 		/* We don't really know where the IO error happened... */
 		ext2_error(sb, __func__,

index cb78d7dcfb95..00168447d48c 100644
@@ -753,6 +753,7 @@ extern unsigned long ext2_count_free (struct buffer_head *, unsigned);
 extern struct inode *ext2_iget (struct super_block *, unsigned long);
 extern int ext2_write_inode (struct inode *, struct writeback_control *);
 extern void ext2_evict_inode(struct inode *);
+void ext2_write_failed(struct address_space *mapping, loff_t to);
 extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int);
 extern int ext2_setattr (struct mnt_idmap *, struct dentry *, struct iattr *);
 extern int ext2_getattr (struct mnt_idmap *, const struct path *,

133 lines not on this page · raw message

91 lines not on this page · raw message

index c85916e9f7db..bdc1f7ed2aba 100644
@@ -340,6 +340,20 @@ enum rw_hint {
 /* can use bio alloc cache */
 #define IOCB_ALLOC_CACHE	(1 << 21)
 
+/* for use in trace events */
+#define TRACE_IOCB_STRINGS \
+	{ IOCB_HIPRI, "HIPRI"	}, \
+	{ IOCB_DSYNC, "DSYNC"	}, \
+	{ IOCB_SYNC, "SYNC"	}, \
+	{ IOCB_NOWAIT, "NOWAIT" }, \
+	{ IOCB_APPEND, "APPEND" }, \
+	{ IOCB_EVENTFD, "EVENTFD"}, \
+	{ IOCB_DIRECT, "DIRECT" }, \
+	{ IOCB_WRITE, "WRITE"	}, \
+	{ IOCB_WAITQ, "WAITQ"	}, \
+	{ IOCB_NOIO, "NOIO"	}, \
+	{ IOCB_ALLOC_CACHE, "ALLOC_CACHE" }
+
 struct kiocb {
 	struct file		*ki_filp;
 	loff_t			ki_pos;

index 704abe0a79cb..c3e8d8cc6792 100644
@@ -29,6 +29,7 @@
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
+#include "trace.h"
 
 #ifdef CONFIG_FS_DAX
 static ssize_t ext2_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)

@@ -170,9 +171,11 @@ static ssize_t ext2_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *inode = file->f_mapping->host;
 	ssize_t ret;
 
+	trace_ext2_dio_read_begin(iocb, to, 0);
 	inode_lock_shared(inode);
 	ret = iomap_dio_rw(iocb, to, &ext2_iomap_ops, NULL, 0, NULL, 0);
 	inode_unlock_shared(inode);
+	trace_ext2_dio_read_end(iocb, to, ret);
 
 	return ret;
 }

@@ -200,6 +203,7 @@ static int ext2_dio_write_end_io(struct kiocb *iocb, ssize_t size,
 		mark_inode_dirty(inode);
 	}
 out:
+	trace_ext2_dio_write_endio(iocb, size, error);
 	return error;
 }
 

@@ -216,7 +220,9 @@ static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	unsigned long blocksize = inode->i_sb->s_blocksize;
 	loff_t offset = iocb->ki_pos;
 	loff_t count = iov_iter_count(from);
+	ssize_t status = 0;
 
+	trace_ext2_dio_write_begin(iocb, from, 0);
 	inode_lock(inode);
 	ret = generic_write_checks(iocb, from);
 	if (ret <= 0)

@@ -244,7 +250,6 @@ static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	/* handle case for partial write and for fallback to buffered write */
 	if (ret >= 0 && iov_iter_count(from)) {
 		loff_t pos, endbyte;
-		ssize_t status;
 		int ret2;
 
 		iocb->ki_flags &= ~IOCB_DIRECT;

@@ -270,6 +275,9 @@ static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 out_unlock:
 	inode_unlock(inode);
+	if (status)
+		trace_ext2_dio_write_buff_end(iocb, from, status);
+	trace_ext2_dio_write_end(iocb, from, ret);
 	return ret;
 }
 

new file mode 100644
index 000000000000..b01cdf6526fd
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "ext2.h"
+#include <linux/uio.h>
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"

94 lines not on this page · raw message

index f771001574d0..36ab1152dbea 100644
@@ -541,7 +541,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		}
 
 		/* for data sync or sync, we need sync completion processing */
-		if (iocb_is_dsync(iocb) && !(dio_flags & IOMAP_DIO_NOSYNC)) {
+		if (iocb_is_dsync(iocb)) {
 			dio->flags |= IOMAP_DIO_NEED_SYNC;
 
 		       /*

index 0f8123504e5e..e2b836c2e119 100644
@@ -377,12 +377,6 @@ struct iomap_dio_ops {
  */
 #define IOMAP_DIO_PARTIAL		(1 << 2)
 
-/*
- * The caller will sync the write if needed; do not sync it within
- * iomap_dio_rw.  Overrides IOMAP_DIO_FORCE_WAIT.
- */
-#define IOMAP_DIO_NOSYNC		(1 << 3)
-
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		unsigned int dio_flags, void *private, size_t done_before);

index 36ab1152dbea..cef28cfd77b7 100644
@@ -130,6 +130,7 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	if (ret > 0)
 		ret += dio->done_before;
 
+	trace_iomap_dio_complete(iocb, dio->error, ret);
 	kfree(dio);
 
 	return ret;

@@ -650,8 +651,10 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	 */
 	dio->wait_for_completion = wait_for_completion;
 	if (!atomic_dec_and_test(&dio->ref)) {
-		if (!wait_for_completion)
+		if (!wait_for_completion) {
+			trace_iomap_dio_rw_queued(inode, iomi.pos, iomi.len);
 			return ERR_PTR(-EIOCBQUEUED);
+		}
 
 		for (;;) {
 			set_current_state(TASK_UNINTERRUPTIBLE);

index da217246b1a9..728d5443daf5 100644
@@ -3,6 +3,7 @@
  * Copyright (c) 2019 Christoph Hellwig
  */
 #include <linux/iomap.h>
+#include <linux/uio.h>
 
 /*
  * We include this last to have the helpers above available for the trace

index f6ea9540d082..9c017af93302 100644
@@ -83,6 +83,7 @@ DEFINE_RANGE_EVENT(iomap_writepage);
 DEFINE_RANGE_EVENT(iomap_release_folio);
 DEFINE_RANGE_EVENT(iomap_invalidate_folio);
 DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail);
+DEFINE_RANGE_EVENT(iomap_dio_rw_queued);
 
 #define IOMAP_TYPE_STRINGS \
 	{ IOMAP_HOLE,		"HOLE" }, \

@@ -183,6 +184,40 @@ TRACE_EVENT(iomap_iter,
 		   (void *)__entry->caller)
 );
 
+TRACE_EVENT(iomap_dio_complete,
+	TP_PROTO(struct kiocb *iocb, int error, ssize_t ret),
+	TP_ARGS(iocb, error, ret),
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(loff_t, isize)
+		__field(loff_t, pos)
+		__field(int,	ki_flags)
+		__field(bool,	aio)
+		__field(int,	error)
+		__field(ssize_t, ret)
+	),
+	TP_fast_assign(
+		__entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev;
+		__entry->ino = file_inode(iocb->ki_filp)->i_ino;
+		__entry->isize = file_inode(iocb->ki_filp)->i_size;
+		__entry->pos = iocb->ki_pos;
+		__entry->ki_flags = iocb->ki_flags;
+		__entry->aio = !is_sync_kiocb(iocb);
+		__entry->error = error;
+		__entry->ret = ret;
+	),
+	TP_printk("dev %d:%d ino 0x%lx size 0x%llx offset 0x%llx flags %s aio %d error %d ret %zd",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->isize,
+		  __entry->pos,
+		  __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS),
+		  __entry->aio,
+		  __entry->error,
+		  __entry->ret)
+);
+
 #endif /* _IOMAP_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH