[v5,07/12] ext4: introduce direct I/O read using iomap infrastructure
diff mbox series

Message ID 280de880787dc7c064c309efb685f95d4ff732a9.1571647179.git.mbobrowski@mbobrowski.org
State Superseded
Headers show
Series
  • ext4: port direct I/O to iomap infrastructure
Related show

Commit Message

Matthew Bobrowski Oct. 21, 2019, 9:18 a.m. UTC
This patch introduces a new direct I/O read path which makes use of
the iomap infrastructure.

The new function ext4_do_read_iter() is responsible for calling into
the iomap infrastructure via iomap_dio_rw(). If the read operation
performed on the inode is not supported, which is checked via
ext4_dio_supported(), then we simply fallback and complete the I/O
using buffered I/O.

Existing direct I/O read code path has been removed, as it is no
longer required.

Signed-off-by: Matthew Bobrowski <mbobrowski@mbobrowski.org>
---
 fs/ext4/file.c  | 46 +++++++++++++++++++++++++++++++++++++++++++++-
 fs/ext4/inode.c | 32 +-------------------------------
 2 files changed, 46 insertions(+), 32 deletions(-)

Comments

Jan Kara Oct. 21, 2019, 1:41 p.m. UTC | #1
On Mon 21-10-19 20:18:37, Matthew Bobrowski wrote:
> This patch introduces a new direct I/O read path which makes use of
> the iomap infrastructure.
> 
> The new function ext4_do_read_iter() is responsible for calling into
> the iomap infrastructure via iomap_dio_rw(). If the read operation
> performed on the inode is not supported, which is checked via
> ext4_dio_supported(), then we simply fallback and complete the I/O
> using buffered I/O.
> 
> Existing direct I/O read code path has been removed, as it is no
> longer required.
> 
> Signed-off-by: Matthew Bobrowski <mbobrowski@mbobrowski.org>

Looks good to me. You can add:

Reviewed-by: Jan Kara <jack@suse.cz>

BTW, I think I gave you my Reviewed-by tag for this patch also last time
and this patch didn't change since then. You can just include the tag in
your posting in that case.

								Honza

> ---
>  fs/ext4/file.c  | 46 +++++++++++++++++++++++++++++++++++++++++++++-
>  fs/ext4/inode.c | 32 +-------------------------------
>  2 files changed, 46 insertions(+), 32 deletions(-)
> 
> diff --git a/fs/ext4/file.c b/fs/ext4/file.c
> index ab75aee3e687..6ea7e00e0204 100644
> --- a/fs/ext4/file.c
> +++ b/fs/ext4/file.c
> @@ -34,6 +34,46 @@
>  #include "xattr.h"
>  #include "acl.h"
>  
> +static bool ext4_dio_supported(struct inode *inode)
> +{
> +	if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode))
> +		return false;
> +	if (fsverity_active(inode))
> +		return false;
> +	if (ext4_should_journal_data(inode))
> +		return false;
> +	if (ext4_has_inline_data(inode))
> +		return false;
> +	return true;
> +}
> +
> +static int ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
> +{
> +	ssize_t ret;
> +	struct inode *inode = file_inode(iocb->ki_filp);
> +
> +	inode_lock_shared(inode);
> +	if (!ext4_dio_supported(inode)) {
> +		inode_unlock_shared(inode);
> +		/*
> +		 * Fallback to buffered I/O if the operation being performed on
> +		 * the inode is not supported by direct I/O. The IOCB_DIRECT
> +		 * flag needs to be cleared here in order to ensure that the
> +		 * direct I/O path within generic_file_read_iter() is not
> +		 * taken.
> +		 */
> +		iocb->ki_flags &= ~IOCB_DIRECT;
> +		return generic_file_read_iter(iocb, to);
> +	}
> +
> +	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL,
> +			   is_sync_kiocb(iocb));
> +	inode_unlock_shared(inode);
> +
> +	file_accessed(iocb->ki_filp);
> +	return ret;
> +}
> +
>  #ifdef CONFIG_FS_DAX
>  static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
>  {
> @@ -64,7 +104,9 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
>  
>  static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
>  {
> -	if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
> +	struct inode *inode = file_inode(iocb->ki_filp);
> +
> +	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
>  		return -EIO;
>  
>  	if (!iov_iter_count(to))
> @@ -74,6 +116,8 @@ static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
>  	if (IS_DAX(file_inode(iocb->ki_filp)))
>  		return ext4_dax_read_iter(iocb, to);
>  #endif
> +	if (iocb->ki_flags & IOCB_DIRECT)
> +		return ext4_dio_read_iter(iocb, to);
>  	return generic_file_read_iter(iocb, to);
>  }
>  
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index ebeedbf3900f..03a9e2b85e46 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -863,9 +863,6 @@ int ext4_dio_get_block(struct inode *inode, sector_t iblock,
>  {
>  	/* We don't expect handle for direct IO */
>  	WARN_ON_ONCE(ext4_journal_current_handle());
> -
> -	if (!create)
> -		return _ext4_get_block(inode, iblock, bh, 0);
>  	return ext4_get_block_trans(inode, iblock, bh, EXT4_GET_BLOCKS_CREATE);
>  }
>  
> @@ -3865,30 +3862,6 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
>  	return ret;
>  }
>  
> -static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
> -{
> -	struct address_space *mapping = iocb->ki_filp->f_mapping;
> -	struct inode *inode = mapping->host;
> -	size_t count = iov_iter_count(iter);
> -	ssize_t ret;
> -
> -	/*
> -	 * Shared inode_lock is enough for us - it protects against concurrent
> -	 * writes & truncates and since we take care of writing back page cache,
> -	 * we are protected against page writeback as well.
> -	 */
> -	inode_lock_shared(inode);
> -	ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
> -					   iocb->ki_pos + count - 1);
> -	if (ret)
> -		goto out_unlock;
> -	ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
> -				   iter, ext4_dio_get_block, NULL, NULL, 0);
> -out_unlock:
> -	inode_unlock_shared(inode);
> -	return ret;
> -}
> -
>  static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>  {
>  	struct file *file = iocb->ki_filp;
> @@ -3915,10 +3888,7 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>  		return 0;
>  
>  	trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
> -	if (iov_iter_rw(iter) == READ)
> -		ret = ext4_direct_IO_read(iocb, iter);
> -	else
> -		ret = ext4_direct_IO_write(iocb, iter);
> +	ret = ext4_direct_IO_write(iocb, iter);
>  	trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
>  	return ret;
>  }
> -- 
> 2.20.1
> 
> --<M>--
Matthew Bobrowski Oct. 22, 2019, 1:58 a.m. UTC | #2
On Mon, Oct 21, 2019 at 03:41:31PM +0200, Jan Kara wrote:
> On Mon 21-10-19 20:18:37, Matthew Bobrowski wrote:
> > This patch introduces a new direct I/O read path which makes use of
> > the iomap infrastructure.
> > 
> > The new function ext4_do_read_iter() is responsible for calling into
> > the iomap infrastructure via iomap_dio_rw(). If the read operation
> > performed on the inode is not supported, which is checked via
> > ext4_dio_supported(), then we simply fallback and complete the I/O
> > using buffered I/O.
> > 
> > Existing direct I/O read code path has been removed, as it is no
> > longer required.
> > 
> > Signed-off-by: Matthew Bobrowski <mbobrowski@mbobrowski.org>
> 
> Looks good to me. You can add:
> 
> Reviewed-by: Jan Kara <jack@suse.cz>
> 
> BTW, I think I gave you my Reviewed-by tag for this patch also last time
> and this patch didn't change since then. You can just include the tag in
> your posting in that case.

The lock pattern was dropped here, so I thought I'd just have you
review it again to be sure that you didn't object. But anyway, thank
you!

--<M>--
Ritesh Harjani Oct. 23, 2019, 6:40 a.m. UTC | #3
On 10/21/19 2:48 PM, Matthew Bobrowski wrote:
> This patch introduces a new direct I/O read path which makes use of
> the iomap infrastructure.
> 
> The new function ext4_do_read_iter() is responsible for calling into
> the iomap infrastructure via iomap_dio_rw(). If the read operation
> performed on the inode is not supported, which is checked via
> ext4_dio_supported(), then we simply fallback and complete the I/O
> using buffered I/O.
> 
> Existing direct I/O read code path has been removed, as it is no
> longer required.
> 
> Signed-off-by: Matthew Bobrowski <mbobrowski@mbobrowski.org>


Patch looks good to me. You may add:

Reviewed-by: Ritesh Harjani <riteshh@linux.ibm.com>


> ---
>   fs/ext4/file.c  | 46 +++++++++++++++++++++++++++++++++++++++++++++-
>   fs/ext4/inode.c | 32 +-------------------------------
>   2 files changed, 46 insertions(+), 32 deletions(-)
> 
> diff --git a/fs/ext4/file.c b/fs/ext4/file.c
> index ab75aee3e687..6ea7e00e0204 100644
> --- a/fs/ext4/file.c
> +++ b/fs/ext4/file.c
> @@ -34,6 +34,46 @@
>   #include "xattr.h"
>   #include "acl.h"
>   
> +static bool ext4_dio_supported(struct inode *inode)
> +{
> +	if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode))
> +		return false;
> +	if (fsverity_active(inode))
> +		return false;
> +	if (ext4_should_journal_data(inode))
> +		return false;
> +	if (ext4_has_inline_data(inode))
> +		return false;
> +	return true;
> +}
> +
> +static int ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
> +{
> +	ssize_t ret;
> +	struct inode *inode = file_inode(iocb->ki_filp);
> +
> +	inode_lock_shared(inode);
> +	if (!ext4_dio_supported(inode)) {
> +		inode_unlock_shared(inode);
> +		/*
> +		 * Fallback to buffered I/O if the operation being performed on
> +		 * the inode is not supported by direct I/O. The IOCB_DIRECT
> +		 * flag needs to be cleared here in order to ensure that the
> +		 * direct I/O path within generic_file_read_iter() is not
> +		 * taken.
> +		 */
> +		iocb->ki_flags &= ~IOCB_DIRECT;
> +		return generic_file_read_iter(iocb, to);
> +	}
> +
> +	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL,
> +			   is_sync_kiocb(iocb));
> +	inode_unlock_shared(inode);
> +
> +	file_accessed(iocb->ki_filp);
> +	return ret;
> +}
> +
>   #ifdef CONFIG_FS_DAX
>   static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
>   {
> @@ -64,7 +104,9 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
>   
>   static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
>   {
> -	if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
> +	struct inode *inode = file_inode(iocb->ki_filp);
> +
> +	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
>   		return -EIO;
>   
>   	if (!iov_iter_count(to))
> @@ -74,6 +116,8 @@ static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
>   	if (IS_DAX(file_inode(iocb->ki_filp)))
>   		return ext4_dax_read_iter(iocb, to);
>   #endif
> +	if (iocb->ki_flags & IOCB_DIRECT)
> +		return ext4_dio_read_iter(iocb, to);
>   	return generic_file_read_iter(iocb, to);
>   }
>   
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index ebeedbf3900f..03a9e2b85e46 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -863,9 +863,6 @@ int ext4_dio_get_block(struct inode *inode, sector_t iblock,
>   {
>   	/* We don't expect handle for direct IO */
>   	WARN_ON_ONCE(ext4_journal_current_handle());
> -
> -	if (!create)
> -		return _ext4_get_block(inode, iblock, bh, 0);
>   	return ext4_get_block_trans(inode, iblock, bh, EXT4_GET_BLOCKS_CREATE);
>   }
>   
> @@ -3865,30 +3862,6 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
>   	return ret;
>   }
>   
> -static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
> -{
> -	struct address_space *mapping = iocb->ki_filp->f_mapping;
> -	struct inode *inode = mapping->host;
> -	size_t count = iov_iter_count(iter);
> -	ssize_t ret;
> -
> -	/*
> -	 * Shared inode_lock is enough for us - it protects against concurrent
> -	 * writes & truncates and since we take care of writing back page cache,
> -	 * we are protected against page writeback as well.
> -	 */
> -	inode_lock_shared(inode);
> -	ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
> -					   iocb->ki_pos + count - 1);
> -	if (ret)
> -		goto out_unlock;
> -	ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
> -				   iter, ext4_dio_get_block, NULL, NULL, 0);
> -out_unlock:
> -	inode_unlock_shared(inode);
> -	return ret;
> -}
> -
>   static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>   {
>   	struct file *file = iocb->ki_filp;
> @@ -3915,10 +3888,7 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
>   		return 0;
>   
>   	trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
> -	if (iov_iter_rw(iter) == READ)
> -		ret = ext4_direct_IO_read(iocb, iter);
> -	else
> -		ret = ext4_direct_IO_write(iocb, iter);
> +	ret = ext4_direct_IO_write(iocb, iter);
>   	trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
>   	return ret;
>   }
>

Patch
diff mbox series

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index ab75aee3e687..6ea7e00e0204 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -34,6 +34,46 @@ 
 #include "xattr.h"
 #include "acl.h"
 
+static bool ext4_dio_supported(struct inode *inode)
+{
+	if (IS_ENABLED(CONFIG_FS_ENCRYPTION) && IS_ENCRYPTED(inode))
+		return false;
+	if (fsverity_active(inode))
+		return false;
+	if (ext4_should_journal_data(inode))
+		return false;
+	if (ext4_has_inline_data(inode))
+		return false;
+	return true;
+}
+
+static int ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	ssize_t ret;
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	inode_lock_shared(inode);
+	if (!ext4_dio_supported(inode)) {
+		inode_unlock_shared(inode);
+		/*
+		 * Fallback to buffered I/O if the operation being performed on
+		 * the inode is not supported by direct I/O. The IOCB_DIRECT
+		 * flag needs to be cleared here in order to ensure that the
+		 * direct I/O path within generic_file_read_iter() is not
+		 * taken.
+		 */
+		iocb->ki_flags &= ~IOCB_DIRECT;
+		return generic_file_read_iter(iocb, to);
+	}
+
+	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL,
+			   is_sync_kiocb(iocb));
+	inode_unlock_shared(inode);
+
+	file_accessed(iocb->ki_filp);
+	return ret;
+}
+
 #ifdef CONFIG_FS_DAX
 static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
@@ -64,7 +104,9 @@  static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
 	if (!iov_iter_count(to))
@@ -74,6 +116,8 @@  static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	if (IS_DAX(file_inode(iocb->ki_filp)))
 		return ext4_dax_read_iter(iocb, to);
 #endif
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return ext4_dio_read_iter(iocb, to);
 	return generic_file_read_iter(iocb, to);
 }
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ebeedbf3900f..03a9e2b85e46 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -863,9 +863,6 @@  int ext4_dio_get_block(struct inode *inode, sector_t iblock,
 {
 	/* We don't expect handle for direct IO */
 	WARN_ON_ONCE(ext4_journal_current_handle());
-
-	if (!create)
-		return _ext4_get_block(inode, iblock, bh, 0);
 	return ext4_get_block_trans(inode, iblock, bh, EXT4_GET_BLOCKS_CREATE);
 }
 
@@ -3865,30 +3862,6 @@  static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
 	return ret;
 }
 
-static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
-{
-	struct address_space *mapping = iocb->ki_filp->f_mapping;
-	struct inode *inode = mapping->host;
-	size_t count = iov_iter_count(iter);
-	ssize_t ret;
-
-	/*
-	 * Shared inode_lock is enough for us - it protects against concurrent
-	 * writes & truncates and since we take care of writing back page cache,
-	 * we are protected against page writeback as well.
-	 */
-	inode_lock_shared(inode);
-	ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
-					   iocb->ki_pos + count - 1);
-	if (ret)
-		goto out_unlock;
-	ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
-				   iter, ext4_dio_get_block, NULL, NULL, 0);
-out_unlock:
-	inode_unlock_shared(inode);
-	return ret;
-}
-
 static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
@@ -3915,10 +3888,7 @@  static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		return 0;
 
 	trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
-	if (iov_iter_rw(iter) == READ)
-		ret = ext4_direct_IO_read(iocb, iter);
-	else
-		ret = ext4_direct_IO_write(iocb, iter);
+	ret = ext4_direct_IO_write(iocb, iter);
 	trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
 	return ret;
 }