[Qemu-devel] [PATCH v2 5/6] raw-posix: Implement .bdrv_co_preadv/pwritev

[Kevin Wolf <kwolf@redhat.com>]

The raw-posix block driver actually supports byte-aligned requests now
on non-O_DIRECT images, like it already (and previously incorrectly)
claimed in bs->request_alignment.

For some block drivers this means that a RMW cycle can be avoided when
they write sub-sector metadata e.g. for cluster allocation.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 block/linux-aio.c |  7 ++-----
 block/raw-aio.h   |  3 +--
 block/raw-posix.c | 43 +++++++++++++++++++++++--------------------
 3 files changed, 26 insertions(+), 27 deletions(-)

diff --git a/block/linux-aio.c b/block/linux-aio.c
index 74d9b33..e468960 100644
--- a/block/linux-aio.c
+++ b/block/linux-aio.c
@@ -273,15 +273,12 @@ static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
 }
 
 int coroutine_fn laio_co_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
-                                int64_t sector_num, QEMUIOVector *qiov,
-                                int nb_sectors, int type)
+                                uint64_t offset, QEMUIOVector *qiov, int type)
 {
-    off_t offset = sector_num * BDRV_SECTOR_SIZE;
     int ret;
-
     struct qemu_laiocb laiocb = {
         .co         = qemu_coroutine_self(),
-        .nbytes     = nb_sectors * BDRV_SECTOR_SIZE,
+        .nbytes     = qiov->size,
         .ctx        = s,
         .is_read    = (type == QEMU_AIO_READ),
         .qiov       = qiov,
diff --git a/block/raw-aio.h b/block/raw-aio.h
index 03bbfba..a4cdbbf 100644
--- a/block/raw-aio.h
+++ b/block/raw-aio.h
@@ -40,8 +40,7 @@ typedef struct LinuxAioState LinuxAioState;
 LinuxAioState *laio_init(void);
 void laio_cleanup(LinuxAioState *s);
 int coroutine_fn laio_co_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
-                                int64_t sector_num, QEMUIOVector *qiov,
-                                int nb_sectors, int type);
+                                uint64_t offset, QEMUIOVector *qiov, int type);
 BlockAIOCB *laio_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
         BlockCompletionFunc *cb, void *opaque, int type);
diff --git a/block/raw-posix.c b/block/raw-posix.c
index cb98769..aacf132 100644
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -1325,8 +1325,8 @@ static BlockAIOCB *paio_submit(BlockDriverState *bs, int fd,
     return thread_pool_submit_aio(pool, aio_worker, acb, cb, opaque);
 }
 
-static int coroutine_fn raw_co_rw(BlockDriverState *bs, int64_t sector_num,
-                                  int nb_sectors, QEMUIOVector *qiov, int type)
+static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset,
+                                   uint64_t bytes, QEMUIOVector *qiov, int type)
 {
     BDRVRawState *s = bs->opaque;
 
@@ -1344,26 +1344,28 @@ static int coroutine_fn raw_co_rw(BlockDriverState *bs, int64_t sector_num,
             type |= QEMU_AIO_MISALIGNED;
 #ifdef CONFIG_LINUX_AIO
         } else if (s->use_aio) {
-            return laio_co_submit(bs, s->aio_ctx, s->fd, sector_num, qiov,
-                                  nb_sectors, type);
+            assert(qiov->size == bytes);
+            return laio_co_submit(bs, s->aio_ctx, s->fd, offset, qiov, type);
 #endif
         }
     }
 
-    return paio_submit_co(bs, s->fd, sector_num * BDRV_SECTOR_SIZE, qiov,
-                          nb_sectors * BDRV_SECTOR_SIZE, type);
+    return paio_submit_co(bs, s->fd, offset, qiov, bytes, type);
 }
 
-static int coroutine_fn raw_co_readv(BlockDriverState *bs, int64_t sector_num,
-                                     int nb_sectors, QEMUIOVector *qiov)
+static int coroutine_fn raw_co_preadv(BlockDriverState *bs, uint64_t offset,
+                                      uint64_t bytes, QEMUIOVector *qiov,
+                                      int flags)
 {
-    return raw_co_rw(bs, sector_num, nb_sectors, qiov, QEMU_AIO_READ);
+    return raw_co_prw(bs, offset, bytes, qiov, QEMU_AIO_READ);
 }
 
-static int coroutine_fn raw_co_writev(BlockDriverState *bs, int64_t sector_num,
-                                      int nb_sectors, QEMUIOVector *qiov)
+static int coroutine_fn raw_co_pwritev(BlockDriverState *bs, uint64_t offset,
+                                       uint64_t bytes, QEMUIOVector *qiov,
+                                       int flags)
 {
-    return raw_co_rw(bs, sector_num, nb_sectors, qiov, QEMU_AIO_WRITE);
+    assert(flags == 0);
+    return raw_co_prw(bs, offset, bytes, qiov, QEMU_AIO_WRITE);
 }
 
 static void raw_aio_plug(BlockDriverState *bs)
@@ -1952,8 +1954,8 @@ BlockDriver bdrv_file = {
     .bdrv_co_get_block_status = raw_co_get_block_status,
     .bdrv_co_pwrite_zeroes = raw_co_pwrite_zeroes,
 
-    .bdrv_co_readv          = raw_co_readv,
-    .bdrv_co_writev         = raw_co_writev,
+    .bdrv_co_preadv         = raw_co_preadv,
+    .bdrv_co_pwritev        = raw_co_pwritev,
     .bdrv_aio_flush = raw_aio_flush,
     .bdrv_aio_discard = raw_aio_discard,
     .bdrv_refresh_limits = raw_refresh_limits,
@@ -2400,8 +2402,8 @@ static BlockDriver bdrv_host_device = {
     .create_opts         = &raw_create_opts,
     .bdrv_co_pwrite_zeroes = hdev_co_pwrite_zeroes,
 
-    .bdrv_co_readv          = raw_co_readv,
-    .bdrv_co_writev         = raw_co_writev,
+    .bdrv_co_preadv         = raw_co_preadv,
+    .bdrv_co_pwritev        = raw_co_pwritev,
     .bdrv_aio_flush	= raw_aio_flush,
     .bdrv_aio_discard   = hdev_aio_discard,
     .bdrv_refresh_limits = raw_refresh_limits,
@@ -2530,8 +2532,9 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_create         = hdev_create,
     .create_opts         = &raw_create_opts,
 
-    .bdrv_co_readv          = raw_co_readv,
-    .bdrv_co_writev         = raw_co_writev,
+
+    .bdrv_co_preadv         = raw_co_preadv,
+    .bdrv_co_pwritev        = raw_co_pwritev,
     .bdrv_aio_flush	= raw_aio_flush,
     .bdrv_refresh_limits = raw_refresh_limits,
     .bdrv_io_plug = raw_aio_plug,
@@ -2665,8 +2668,8 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_create        = hdev_create,
     .create_opts        = &raw_create_opts,
 
-    .bdrv_co_readv          = raw_co_readv,
-    .bdrv_co_writev         = raw_co_writev,
+    .bdrv_co_preadv         = raw_co_preadv,
+    .bdrv_co_pwritev        = raw_co_pwritev,
     .bdrv_aio_flush	= raw_aio_flush,
     .bdrv_refresh_limits = raw_refresh_limits,
     .bdrv_io_plug = raw_aio_plug,
-- 
1.8.3.1