Message ID | df2b8a10641ec8a0509f137dcc2db1d3cc6087f1.1570100361.git.mbobrowski@mbobrowski.org |
---|---|
State | Superseded |
Headers | show |
Series | ext4: port direct I/O to iomap infrastructure | expand |
On Thu 03-10-19 21:34:00, Matthew Bobrowski wrote: > This patch introduces a new direct I/O read path that makes use of the > iomap infrastructure. > > The new function ext4_dio_read_iter() is responsible for calling into > the iomap infrastructure via iomap_dio_rw(). If the read operation > being performed on the inode does not pass the preliminary checks > performed within ext4_dio_supported(), then we simply fallback to > buffered I/O in order to fulfil the request. > > Existing direct I/O read buffer_head code has been removed as it's now > redundant. > > Signed-off-by: Matthew Bobrowski <mbobrowski@mbobrowski.org> The patch looks good to me. Just one small nit below. With that fixed, you can add: Reviewed-by: Jan Kara <jack@suse.cz> > + /* > + * Get exclusion from truncate and other inode operations. > + */ > + if (!inode_trylock_shared(inode)) { > + if (iocb->ki_flags & IOCB_NOWAIT) > + return -EAGAIN; > + inode_lock_shared(inode); > + } I've noticed here you actually introduce new trylock pattern - previously we had unconditional inode_lock_shared() in ext4_direct_IO_read(). So the cleanest would be to just use unconditional inode_lock_shared() here and then fixup IOCB_NOWAIT handling (I agree that was missing in the original code) in a separate patch. And the pattern should rather look like: if (iocb->ki_flags & IOCB_NOWAIT) { if (!inode_trylock_shared(inode)) return -EAGAIN; } else { inode_lock_shared(inode); } to avoid two atomical operations instead of one in the fast path. No need to repeat old mistakes when we know better :). Honza
On 10/3/19 5:04 PM, Matthew Bobrowski wrote: > This patch introduces a new direct I/O read path that makes use of the > iomap infrastructure. > > The new function ext4_dio_read_iter() is responsible for calling into > the iomap infrastructure via iomap_dio_rw(). If the read operation > being performed on the inode does not pass the preliminary checks > performed within ext4_dio_supported(), then we simply fallback to > buffered I/O in order to fulfil the request. > > Existing direct I/O read buffer_head code has been removed as it's now > redundant. > > Signed-off-by: Matthew Bobrowski <mbobrowski@mbobrowski.org> > --- > fs/ext4/file.c | 58 +++++++++++++++++++++++++++++++++++++++++++++---- > fs/ext4/inode.c | 32 +-------------------------- > 2 files changed, 55 insertions(+), 35 deletions(-) > > diff --git a/fs/ext4/file.c b/fs/ext4/file.c > index ab75aee3e687..69ac042fb74b 100644 > --- a/fs/ext4/file.c > +++ b/fs/ext4/file.c > @@ -34,6 +34,53 @@ > #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 ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) > +{ > + ssize_t ret; > + struct inode *inode = file_inode(iocb->ki_filp); > + > + /* > + * Get exclusion from truncate and other inode operations. > + */ > + if (!inode_trylock_shared(inode)) { > + if (iocb->ki_flags & IOCB_NOWAIT) > + return -EAGAIN; > + inode_lock_shared(inode); > + } Same comments here. Let's follow as per the discussion here https://patchwork.kernel.org/patch/11141577/ > + > + 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 withiin > + * 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); > + 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) > { > @@ -64,16 +111,19 @@ 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)) > return 0; /* skip atime */ > > -#ifdef CONFIG_FS_DAX > - if (IS_DAX(file_inode(iocb->ki_filp))) > + if (IS_DAX(inode)) > 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 1dace576b8bd..159ffb92f82d 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); > } > > @@ -3855,30 +3852,6 @@ 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; > @@ -3905,10 +3878,7 @@ 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; > } >
On Tue, Oct 08, 2019 at 12:52:07PM +0200, Jan Kara wrote: > On Thu 03-10-19 21:34:00, Matthew Bobrowski wrote: > > This patch introduces a new direct I/O read path that makes use of the > > iomap infrastructure. > > > > The new function ext4_dio_read_iter() is responsible for calling into > > the iomap infrastructure via iomap_dio_rw(). If the read operation > > being performed on the inode does not pass the preliminary checks > > performed within ext4_dio_supported(), then we simply fallback to > > buffered I/O in order to fulfil the request. > > > > Existing direct I/O read buffer_head code has been removed as it's now > > redundant. > > > > Signed-off-by: Matthew Bobrowski <mbobrowski@mbobrowski.org> > > The patch looks good to me. Just one small nit below. With that fixed, you > can add: > > Reviewed-by: Jan Kara <jack@suse.cz> Cool, I'll fix it! > > + /* > > + * Get exclusion from truncate and other inode operations. > > + */ > > + if (!inode_trylock_shared(inode)) { > > + if (iocb->ki_flags & IOCB_NOWAIT) > > + return -EAGAIN; > > + inode_lock_shared(inode); > > + } > > I've noticed here you actually introduce new trylock pattern - previously > we had unconditional inode_lock_shared() in ext4_direct_IO_read(). So the > cleanest would be to just use unconditional inode_lock_shared() here and > then fixup IOCB_NOWAIT handling (I agree that was missing in the original > code) in a separate patch. Right, so I will just have an unconditional call to inode_lock_shared() and in the patch that follows I will fix it up to apply the new pattern. > And the pattern should rather look like: > > if (iocb->ki_flags & IOCB_NOWAIT) { > if (!inode_trylock_shared(inode)) > return -EAGAIN; > } else { > inode_lock_shared(inode); > } > > to avoid two atomical operations instead of one in the fast path. No need > to repeat old mistakes when we know better :). Yes, also agree. --<M>--
diff --git a/fs/ext4/file.c b/fs/ext4/file.c index ab75aee3e687..69ac042fb74b 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -34,6 +34,53 @@ #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 ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + ssize_t ret; + struct inode *inode = file_inode(iocb->ki_filp); + + /* + * Get exclusion from truncate and other inode operations. + */ + if (!inode_trylock_shared(inode)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + 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 withiin + * 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); + 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) { @@ -64,16 +111,19 @@ 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)) return 0; /* skip atime */ -#ifdef CONFIG_FS_DAX - if (IS_DAX(file_inode(iocb->ki_filp))) + if (IS_DAX(inode)) 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 1dace576b8bd..159ffb92f82d 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); } @@ -3855,30 +3852,6 @@ 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; @@ -3905,10 +3878,7 @@ 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; }
This patch introduces a new direct I/O read path that makes use of the iomap infrastructure. The new function ext4_dio_read_iter() is responsible for calling into the iomap infrastructure via iomap_dio_rw(). If the read operation being performed on the inode does not pass the preliminary checks performed within ext4_dio_supported(), then we simply fallback to buffered I/O in order to fulfil the request. Existing direct I/O read buffer_head code has been removed as it's now redundant. Signed-off-by: Matthew Bobrowski <mbobrowski@mbobrowski.org> --- fs/ext4/file.c | 58 +++++++++++++++++++++++++++++++++++++++++++++---- fs/ext4/inode.c | 32 +-------------------------- 2 files changed, 55 insertions(+), 35 deletions(-)