iomap: add a flag to bounce buffer direct I/O

Add a new flag that request bounce buffering for direct I/O.  This is
needed to provide the stable pages requirement requested by devices
that need to calculate checksums or parity over the data and allows
file systems to properly work with things like T10 protection
information.  The implementation just calls out to the new bio bounce
buffering helpers to allocate a bounce buffer, which is used for
I/O and to copy to/from it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Tested-by: Anuj Gupta <anuj20.g@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index eca7adda595a3c794d0e5422be1736fc4771c7dc..9c572de0d59604dc8303be7dfb8b9b4e044c6b17 100644 (file)
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -215,7 +215,11 @@ static void __iomap_dio_bio_end_io(struct bio *bio, bool inline_completion)
 {
        struct iomap_dio *dio = bio->bi_private;
 
-       if (dio->flags & IOMAP_DIO_USER_BACKED) {
+       if (dio->flags & IOMAP_DIO_BOUNCE) {
+               bio_iov_iter_unbounce(bio, !!dio->error,
+                               dio->flags & IOMAP_DIO_USER_BACKED);
+               bio_put(bio);
+       } else if (dio->flags & IOMAP_DIO_USER_BACKED) {
                bio_check_pages_dirty(bio);
        } else {
                bio_release_pages(bio, false);
@@ -303,12 +307,16 @@ static ssize_t iomap_dio_bio_iter_one(struct iomap_iter *iter,
                struct iomap_dio *dio, loff_t pos, unsigned int alignment,
                blk_opf_t op)
 {
+       unsigned int nr_vecs;
        struct bio *bio;
        ssize_t ret;
 
-       bio = iomap_dio_alloc_bio(iter, dio,
-                       bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS),
-                       op);
+       if (dio->flags & IOMAP_DIO_BOUNCE)
+               nr_vecs = bio_iov_bounce_nr_vecs(dio->submit.iter, op);
+       else
+               nr_vecs = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS);
+
+       bio = iomap_dio_alloc_bio(iter, dio, nr_vecs, op);
        fscrypt_set_bio_crypt_ctx(bio, iter->inode,
                        pos >> iter->inode->i_blkbits, GFP_KERNEL);
        bio->bi_iter.bi_sector = iomap_sector(&iter->iomap, pos);
@@ -317,7 +325,11 @@ static ssize_t iomap_dio_bio_iter_one(struct iomap_iter *iter,
        bio->bi_private = dio;
        bio->bi_end_io = iomap_dio_bio_end_io;
 
-       ret = bio_iov_iter_get_pages(bio, dio->submit.iter, alignment - 1);
+       if (dio->flags & IOMAP_DIO_BOUNCE)
+               ret = bio_iov_iter_bounce(bio, dio->submit.iter);
+       else
+               ret = bio_iov_iter_get_pages(bio, dio->submit.iter,
+                                            alignment - 1);
        if (unlikely(ret))
                goto out_put_bio;
        ret = bio->bi_iter.bi_size;
@@ -333,7 +345,8 @@ static ssize_t iomap_dio_bio_iter_one(struct iomap_iter *iter,
 
        if (dio->flags & IOMAP_DIO_WRITE)
                task_io_account_write(ret);
-       else if (dio->flags & IOMAP_DIO_USER_BACKED)
+       else if ((dio->flags & IOMAP_DIO_USER_BACKED) &&
+                !(dio->flags & IOMAP_DIO_BOUNCE))
                bio_set_pages_dirty(bio);
 
        /*
@@ -662,7 +675,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
        dio->i_size = i_size_read(inode);
        dio->dops = dops;
        dio->error = 0;
-       dio->flags = 0;
+       dio->flags = dio_flags & (IOMAP_DIO_FSBLOCK_ALIGNED | IOMAP_DIO_BOUNCE);
        dio->done_before = done_before;
 
        dio->submit.iter = iter;
@@ -671,9 +684,6 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
        if (iocb->ki_flags & IOCB_NOWAIT)
                iomi.flags |= IOMAP_NOWAIT;
 
-       if (dio_flags & IOMAP_DIO_FSBLOCK_ALIGNED)
-               dio->flags |= IOMAP_DIO_FSBLOCK_ALIGNED;
-
        if (iov_iter_rw(iter) == READ) {
                if (iomi.pos >= dio->i_size)
                        goto out_free_dio;

diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 520e967cb501d335fd8fc9361cbbeba0042a9a4e..cf152f638665025547719b5c9cdbf6fa113dd284 100644 (file)
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -562,6 +562,15 @@ struct iomap_dio_ops {
  */
 #define IOMAP_DIO_FSBLOCK_ALIGNED      (1 << 3)
 
+/*
+ * Bounce buffer instead of using zero copy access.
+ *
+ * This is needed if the device needs stable data to checksum or generate
+ * parity.  The file system must hook into the I/O submission and offload
+ * completions to user context for reads when this is set.
+ */
+#define IOMAP_DIO_BOUNCE               (1 << 4)
+
 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);