[PATCH v11 4/9] fs, block: copy_file_range for def_blk_ops for direct block device

From: Nitesh Shetty
Date: Mon May 22 2023 - 07:16:49 EST


For direct block device opened with O_DIRECT, use copy_file_range to
issue device copy offload, and fallback to generic_copy_file_range incase
device copy offload capability is absent.
Modify checks to allow bdevs to use copy_file_range.

Suggested-by: Ming Lei <ming.lei@xxxxxxxxxx>
Signed-off-by: Anuj Gupta <anuj20.g@xxxxxxxxxxx>
Signed-off-by: Nitesh Shetty <nj.shetty@xxxxxxxxxxx>
---
block/blk-lib.c | 23 +++++++++++++++++++++++
block/fops.c | 20 ++++++++++++++++++++
fs/read_write.c | 11 +++++++++--
include/linux/blkdev.h | 3 +++
mm/filemap.c | 11 ++++++++---
5 files changed, 63 insertions(+), 5 deletions(-)

diff --git a/block/blk-lib.c b/block/blk-lib.c
index ba32545eb8d5..7d6ef85692a6 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -523,6 +523,29 @@ int blkdev_issue_copy(struct block_device *bdev_in, loff_t pos_in,
}
EXPORT_SYMBOL_GPL(blkdev_issue_copy);

+/* Returns the length of bytes copied */
+int blkdev_copy_offload(struct block_device *bdev_in, loff_t pos_in,
+ struct block_device *bdev_out, loff_t pos_out, size_t len,
+ gfp_t gfp_mask)
+{
+ struct request_queue *in_q = bdev_get_queue(bdev_in);
+ struct request_queue *out_q = bdev_get_queue(bdev_out);
+ int ret = 0;
+
+ if (blkdev_copy_sanity_check(bdev_in, pos_in, bdev_out, pos_out, len))
+ return 0;
+
+ if (blk_queue_copy(in_q) && blk_queue_copy(out_q)) {
+ ret = __blkdev_copy_offload(bdev_in, pos_in, bdev_out, pos_out,
+ len, NULL, NULL, gfp_mask);
+ if (ret < 0)
+ return 0;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(blkdev_copy_offload);
+
static int __blkdev_issue_write_zeroes(struct block_device *bdev,
sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
struct bio **biop, unsigned flags)
diff --git a/block/fops.c b/block/fops.c
index ab750e8a040f..df8985675ed1 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -614,6 +614,25 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
return ret;
}

+static ssize_t blkdev_copy_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ size_t len, unsigned int flags)
+{
+ struct block_device *in_bdev = I_BDEV(bdev_file_inode(file_in));
+ struct block_device *out_bdev = I_BDEV(bdev_file_inode(file_out));
+ int comp_len = 0;
+
+ if ((file_in->f_iocb_flags & IOCB_DIRECT) &&
+ (file_out->f_iocb_flags & IOCB_DIRECT))
+ comp_len = blkdev_copy_offload(in_bdev, pos_in, out_bdev,
+ pos_out, len, GFP_KERNEL);
+ if (comp_len != len)
+ comp_len = generic_copy_file_range(file_in, pos_in + comp_len,
+ file_out, pos_out + comp_len, len - comp_len, flags);
+
+ return comp_len;
+}
+
#define BLKDEV_FALLOC_FL_SUPPORTED \
(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \
FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE)
@@ -697,6 +716,7 @@ const struct file_operations def_blk_fops = {
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = blkdev_fallocate,
+ .copy_file_range = blkdev_copy_file_range,
};

static __init int blkdev_init(void)
diff --git a/fs/read_write.c b/fs/read_write.c
index a21ba3be7dbe..47e848fcfd42 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -20,6 +20,7 @@
#include <linux/compat.h>
#include <linux/mount.h>
#include <linux/fs.h>
+#include <linux/blkdev.h>
#include "internal.h"

#include <linux/uaccess.h>
@@ -1447,7 +1448,11 @@ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
return -EOVERFLOW;

/* Shorten the copy to EOF */
- size_in = i_size_read(inode_in);
+ if (S_ISBLK(inode_in->i_mode))
+ size_in = bdev_nr_bytes(I_BDEV(file_in->f_mapping->host));
+ else
+ size_in = i_size_read(inode_in);
+
if (pos_in >= size_in)
count = 0;
else
@@ -1708,7 +1713,9 @@ int generic_file_rw_checks(struct file *file_in, struct file *file_out)
/* Don't copy dirs, pipes, sockets... */
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
return -EISDIR;
- if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+
+ if ((!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) &&
+ (!S_ISBLK(inode_in->i_mode) || !S_ISBLK(inode_out->i_mode)))
return -EINVAL;

if (!(file_in->f_mode & FMODE_READ) ||
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a95c26faa8b6..a9bb7e3a8c79 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1054,6 +1054,9 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
int blkdev_issue_copy(struct block_device *bdev_in, loff_t pos_in,
struct block_device *bdev_out, loff_t pos_out, size_t len,
cio_iodone_t end_io, void *private, gfp_t gfp_mask);
+int blkdev_copy_offload(struct block_device *bdev_in, loff_t pos_in,
+ struct block_device *bdev_out, loff_t pos_out, size_t len,
+ gfp_t gfp_mask);
struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
gfp_t gfp_mask);
void bio_map_kern_endio(struct bio *bio);
diff --git a/mm/filemap.c b/mm/filemap.c
index 570bc8c3db87..289f0c8229ec 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -48,6 +48,7 @@
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include "internal.h"
+#include <linux/blkdev.h>

#define CREATE_TRACE_POINTS
#include <trace/events/filemap.h>
@@ -2855,7 +2856,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
{
struct folio_batch fbatch;
struct kiocb iocb;
- size_t total_spliced = 0, used, npages;
+ size_t total_spliced = 0, used, npages, size_in;
loff_t isize, end_offset;
bool writably_mapped;
int i, error = 0;
@@ -2863,6 +2864,10 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
init_sync_kiocb(&iocb, in);
iocb.ki_pos = *ppos;

+ if (S_ISBLK(file_inode(in)->i_mode))
+ size_in = bdev_nr_bytes(I_BDEV(in->f_mapping->host));
+ else
+ size_in = i_size_read(file_inode(in));
/* Work out how much data we can actually add into the pipe */
used = pipe_occupancy(pipe->head, pipe->tail);
npages = max_t(ssize_t, pipe->max_usage - used, 0);
@@ -2873,7 +2878,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
do {
cond_resched();

- if (*ppos >= i_size_read(file_inode(in)))
+ if (*ppos >= size_in)
break;

iocb.ki_pos = *ppos;
@@ -2889,7 +2894,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
* part of the page is not copied back to userspace (unless
* another truncate extends the file - this is desired though).
*/
- isize = i_size_read(file_inode(in));
+ isize = size_in;
if (unlikely(*ppos >= isize))
break;
end_offset = min_t(loff_t, isize, *ppos + len);
--
2.35.1.500.gb896f729e2