[Qemu-devel] [PATCH 3/5] Vectored block device API

[Avi Kivity]

Most devices that are capable of DMA are also capable of scatter-gather.
With the memory mapping API, this means that the device code needs to be
able to access discontiguous host memory regions.

For block devices, this translates to vectored I/O.  This patch implements
an aynchronous vectored interface for the qemu block devices.  At the moment
all I/O is bounced and submitted through the non-vectored API; in the future
we will convert block devices to natively support vectored I/O wherever
possible.

Signed-off-by: Avi Kivity <address@hidden>
---
 block.c |   92 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 block.h |    7 +++++
 2 files changed, 99 insertions(+), 0 deletions(-)

diff --git a/block.c b/block.c
index 3250327..4b2e34b 100644
--- a/block.c
+++ b/block.c
@@ -1246,6 +1246,93 @@ char *bdrv_snapshot_dump(char *buf, int buf_size, 
QEMUSnapshotInfo *sn)
 /**************************************************************/
 /* async I/Os */
 
+typedef struct VectorTranslationState {
+    struct iovec *iov;
+    int niov;
+    uint8_t *bounce;
+    int is_write;
+    BlockDriverAIOCB *aiocb;
+    BlockDriverAIOCB *this_aiocb;
+} VectorTranslationState;
+
+static void flatten_iovec(VectorTranslationState *s)
+{
+    uint8_t *p = s->bounce;
+    int i;
+
+    for (i = 0; i < s->niov; ++i) {
+        memcpy(p, s->iov[i].iov_base, s->iov[i].iov_len);
+        p += s->iov[i].iov_len;
+    }
+}
+
+static void unflatten_iovec(VectorTranslationState *s)
+{
+    uint8_t *p = s->bounce;
+    int i;
+
+    for (i = 0; i < s->niov; ++i) {
+        memcpy(s->iov[i].iov_base, p, s->iov[i].iov_len);
+        p += s->iov[i].iov_len;
+    }
+}
+
+static void bdrv_aio_rw_vector_cb(void *opaque, int ret)
+{
+    VectorTranslationState *s = opaque;
+
+    if (!s->is_write) {
+        unflatten_iovec(s);
+    }
+    qemu_free(s->bounce);
+    s->this_aiocb->cb(s->this_aiocb->opaque, ret);
+    qemu_aio_release(s->this_aiocb);
+}
+
+static BlockDriverAIOCB *bdrv_aio_rw_vector(BlockDriverState *bs,
+                                            int64_t sector_num,
+                                            struct iovec *iov, int niov,
+                                            int nb_sectors,
+                                            BlockDriverCompletionFunc *cb,
+                                            void *opaque,
+                                            int is_write)
+
+{
+    VectorTranslationState *s = qemu_mallocz(sizeof(*s));
+    BlockDriverAIOCB *aiocb = qemu_aio_get(bs, cb, opaque);
+
+    s->this_aiocb = aiocb;
+    s->iov = iov;
+    s->niov = niov;
+    s->bounce = qemu_memalign(512, nb_sectors * 512);
+    s->is_write = is_write;
+    if (is_write) {
+        flatten_iovec(s);
+        s->aiocb = bdrv_aio_write(bs, sector_num, s->bounce, nb_sectors,
+                                  bdrv_aio_rw_vector_cb, s);
+    } else {
+        s->aiocb = bdrv_aio_read(bs, sector_num, s->bounce, nb_sectors,
+                                 bdrv_aio_rw_vector_cb, s);
+    }
+    return aiocb;
+}
+
+BlockDriverAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
+                                 struct iovec *iov, int niov, int nb_sectors,
+                                 BlockDriverCompletionFunc *cb, void *opaque)
+{
+    return bdrv_aio_rw_vector(bs, sector_num, iov, niov, nb_sectors,
+                              cb, opaque, 0);
+}
+
+BlockDriverAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
+                                  struct iovec *iov, int niov, int nb_sectors,
+                                  BlockDriverCompletionFunc *cb, void *opaque)
+{
+    return bdrv_aio_rw_vector(bs, sector_num, iov, niov, nb_sectors,
+                              cb, opaque, 1);
+}
+
 BlockDriverAIOCB *bdrv_aio_read(BlockDriverState *bs, int64_t sector_num,
                                 uint8_t *buf, int nb_sectors,
                                 BlockDriverCompletionFunc *cb, void *opaque)
@@ -1294,6 +1381,11 @@ void bdrv_aio_cancel(BlockDriverAIOCB *acb)
 {
     BlockDriver *drv = acb->bs->drv;
 
+    if (acb->cb == bdrv_aio_rw_vector_cb) {
+        VectorTranslationState *s = acb->opaque;
+        acb = s->aiocb;
+    }
+
     drv->bdrv_aio_cancel(acb);
 }
 
diff --git a/block.h b/block.h
index c3314a1..0391704 100644
--- a/block.h
+++ b/block.h
@@ -85,6 +85,13 @@ int bdrv_commit(BlockDriverState *bs);
 typedef struct BlockDriverAIOCB BlockDriverAIOCB;
 typedef void BlockDriverCompletionFunc(void *opaque, int ret);
 
+BlockDriverAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
+                                 struct iovec *iov, int niov, int nb_sectors,
+                                 BlockDriverCompletionFunc *cb, void *opaque);
+BlockDriverAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
+                                  struct iovec *iov, int niov, int nb_sectors,
+                                  BlockDriverCompletionFunc *cb, void *opaque);
+
 BlockDriverAIOCB *bdrv_aio_read(BlockDriverState *bs, int64_t sector_num,
                                 uint8_t *buf, int nb_sectors,
                                 BlockDriverCompletionFunc *cb, void *opaque);
-- 
1.6.0.6