btrfs: split btrfs_direct_IO to read and write part (d8f3e735) · Commits · 戴 / test

fs/btrfs/ctree.h

+3 −0

Original line number	Diff line number	Diff line
		@@ -28,6 +28,7 @@
		#include <linux/dynamic_debug.h>
		#include <linux/refcount.h>
		#include <linux/crc32c.h>
		#include <linux/iomap.h>
		#include "extent-io-tree.h"
		#include "extent_io.h"
		#include "extent_map.h"
		@@ -2934,6 +2935,8 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
		u64 end, int uptodate);
		extern const struct dentry_operations btrfs_dentry_operations;
		ssize_t btrfs_direct_IO(struct kiocb iocb, struct iov_iter iter);
		extern const struct iomap_ops btrfs_dio_iomap_ops;
		extern const struct iomap_dio_ops btrfs_dops;

		/* ioctl.c */
		long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);

fs/btrfs/file.c

+78 −10

Original line number	Diff line number	Diff line
		@@ -1809,21 +1809,61 @@ again:
		return num_written ? num_written : ret;
		}

		static ssize_t __btrfs_direct_write(struct kiocb iocb, struct iov_iter from)
		static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
		const struct iov_iter *iter, loff_t offset)
		{
		const unsigned int blocksize_mask = fs_info->sectorsize - 1;

		if (offset & blocksize_mask)
		return -EINVAL;

		if (iov_iter_alignment(iter) & blocksize_mask)
		return -EINVAL;

		return 0;
		}

		static ssize_t btrfs_direct_write(struct kiocb iocb, struct iov_iter from)
		{
		struct file *file = iocb->ki_filp;
		struct inode *inode = file_inode(file);
		loff_t pos;
		ssize_t written;
		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
		loff_t pos = iocb->ki_pos;
		ssize_t written = 0;
		ssize_t written_buffered;
		loff_t endbyte;
		int err;
		size_t count = 0;
		bool relock = false;

		if (check_direct_IO(fs_info, from, pos))
		goto buffered;

		written = btrfs_direct_IO(iocb, from);
		count = iov_iter_count(from);
		/*
		* If the write DIO is beyond the EOF, we need update the isize, but it
		* is protected by i_mutex. So we can not unlock the i_mutex at this
		* case.
		*/
		if (pos + count <= inode->i_size) {
		inode_unlock(inode);
		relock = true;
		} else if (iocb->ki_flags & IOCB_NOWAIT) {
		return -EAGAIN;
		}

		down_read(&BTRFS_I(inode)->dio_sem);
		written = iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dops,
		is_sync_kiocb(iocb));
		up_read(&BTRFS_I(inode)->dio_sem);

		if (relock)
		inode_lock(inode);

		if (written < 0 \|\| !iov_iter_count(from))
		return written;

		buffered:
		pos = iocb->ki_pos;
		written_buffered = btrfs_buffered_write(iocb, from);
		if (written_buffered < 0) {
		@@ -1962,7 +2002,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
		atomic_inc(&BTRFS_I(inode)->sync_writers);

		if (iocb->ki_flags & IOCB_DIRECT) {
		num_written = __btrfs_direct_write(iocb, from);
		num_written = btrfs_direct_write(iocb, from);
		} else {
		num_written = btrfs_buffered_write(iocb, from);
		if (num_written > 0)
		@@ -3476,16 +3516,44 @@ static int btrfs_file_open(struct inode inode, struct file filp)
		return generic_file_open(inode, filp);
		}

		static ssize_t btrfs_file_read_iter(struct kiocb iocb, struct iov_iter to)
		static int check_direct_read(struct btrfs_fs_info *fs_info,
		const struct iov_iter *iter, loff_t offset)
		{
		ssize_t ret = 0;
		int ret;
		int i, seg;

		if (iocb->ki_flags & IOCB_DIRECT) {
		ret = check_direct_IO(fs_info, iter, offset);
		if (ret < 0)
		return ret;

		for (seg = 0; seg < iter->nr_segs; seg++)
		for (i = seg + 1; i < iter->nr_segs; i++)
		if (iter->iov[seg].iov_base == iter->iov[i].iov_base)
		return -EINVAL;
		return 0;
		}

		static ssize_t btrfs_direct_read(struct kiocb iocb, struct iov_iter to)
		{
		struct inode *inode = file_inode(iocb->ki_filp);
		ssize_t ret;

		if (check_direct_read(btrfs_sb(inode->i_sb), to, iocb->ki_pos))
		return 0;

		inode_lock_shared(inode);
		ret = btrfs_direct_IO(iocb, to);
		ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dops,
		is_sync_kiocb(iocb));
		inode_unlock_shared(inode);
		return ret;
		}

		static ssize_t btrfs_file_read_iter(struct kiocb iocb, struct iov_iter to)
		{
		ssize_t ret = 0;

		if (iocb->ki_flags & IOCB_DIRECT) {
		ret = btrfs_direct_read(iocb, to);
		if (ret < 0)
		return ret;
		}

fs/btrfs/inode.c

+2 −80

Original line number	Diff line number	Diff line
		@@ -29,7 +29,6 @@
		#include <linux/swap.h>
		#include <linux/migrate.h>
		#include <linux/sched/mm.h>
		#include <linux/iomap.h>
		#include <asm/unaligned.h>
		#include "misc.h"
		#include "ctree.h"
		@@ -7759,92 +7758,15 @@ out_err:
		return BLK_QC_T_NONE;
		}

		static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
		const struct iov_iter *iter, loff_t offset)
		{
		int seg;
		int i;
		unsigned int blocksize_mask = fs_info->sectorsize - 1;
		ssize_t retval = -EINVAL;

		if (offset & blocksize_mask)
		goto out;

		if (iov_iter_alignment(iter) & blocksize_mask)
		goto out;

		/* If this is a write we don't need to check anymore */
		if (iov_iter_rw(iter) != READ \|\| !iter_is_iovec(iter))
		return 0;
		/*
		* Check to make sure we don't have duplicate iov_base's in this
		* iovec, if so return EINVAL, otherwise we'll get csum errors
		* when reading back.
		*/
		for (seg = 0; seg < iter->nr_segs; seg++) {
		for (i = seg + 1; i < iter->nr_segs; i++) {
		if (iter->iov[seg].iov_base == iter->iov[i].iov_base)
		goto out;
		}
		}
		retval = 0;
		out:
		return retval;
		}

		static const struct iomap_ops btrfs_dio_iomap_ops = {
		const struct iomap_ops btrfs_dio_iomap_ops = {
		.iomap_begin = btrfs_dio_iomap_begin,
		.iomap_end = btrfs_dio_iomap_end,
		};

		static const struct iomap_dio_ops btrfs_dops = {
		const struct iomap_dio_ops btrfs_dops = {
		.submit_io = btrfs_submit_direct,
		};

		ssize_t btrfs_direct_IO(struct kiocb iocb, struct iov_iter iter)
		{
		struct file *file = iocb->ki_filp;
		struct inode *inode = file->f_mapping->host;
		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
		struct extent_changeset *data_reserved = NULL;
		loff_t offset = iocb->ki_pos;
		size_t count = 0;
		bool relock = false;
		ssize_t ret;

		if (check_direct_IO(fs_info, iter, offset))
		return 0;

		count = iov_iter_count(iter);
		if (iov_iter_rw(iter) == WRITE) {
		/*
		* If the write DIO is beyond the EOF, we need update
		* the isize, but it is protected by i_mutex. So we can
		* not unlock the i_mutex at this case.
		*/
		if (offset + count <= inode->i_size) {
		inode_unlock(inode);
		relock = true;
		} else if (iocb->ki_flags & IOCB_NOWAIT) {
		ret = -EAGAIN;
		goto out;
		}
		down_read(&BTRFS_I(inode)->dio_sem);
		}

		ret = iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dops,
		is_sync_kiocb(iocb));

		if (iov_iter_rw(iter) == WRITE) {
		up_read(&BTRFS_I(inode)->dio_sem);
		}
		out:
		if (relock)
		inode_lock(inode);
		extent_changeset_free(data_reserved);
		return ret;
		}

		#define BTRFS_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC)

		static int btrfs_fiemap(struct inode inode, struct fiemap_extent_info fieinfo,

Admin message