[Qemu-devel] [PATCH 4/5] nbd: Rely on block layer to break up large requests

[Eric Blake <eblake@redhat.com>]

Now that the block layer will honor max_transfer, we can simplify
our code to rely on that guarantee.

The readv code can call directly into nbd-client, just as the
writev code has done since commit 52a4650.

Interestingly enough, while qemu-io 'w 0 40m' splits into a 32M
and 8M transaction, 'w -z 0 40m' splits into two 16M and an 8M,
because the block layer caps the bounce buffer for writing zeroes
at 16M.  When we later introduce support for NBD_CMD_WRITE_ZEROES,
we can get a full 32M zero write (or larger, if the client and
server negotiate that write zeroes can use a larger size than
ordinary writes).

Signed-off-by: Eric Blake <eblake@redhat.com>
---
 block/nbd-client.c | 51 ++++++++-------------------------------------------
 block/nbd.c        | 12 +++---------
 2 files changed, 11 insertions(+), 52 deletions(-)

diff --git a/block/nbd-client.c b/block/nbd-client.c
index 420bce8..9f023f8 100644
--- a/block/nbd-client.c
+++ b/block/nbd-client.c
@@ -217,15 +217,15 @@ static void nbd_coroutine_end(NbdClientSession *s,
     }
 }

-static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,
-                          int nb_sectors, QEMUIOVector *qiov,
-                          int offset)
+int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
+                        int nb_sectors, QEMUIOVector *qiov)
 {
     NbdClientSession *client = nbd_get_client_session(bs);
     struct nbd_request request = { .type = NBD_CMD_READ };
     struct nbd_reply reply;
     ssize_t ret;

+    assert(nb_sectors <= NBD_MAX_SECTORS);
     request.from = sector_num * 512;
     request.len = nb_sectors * 512;

@@ -234,16 +234,15 @@ static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,
     if (ret < 0) {
         reply.error = -ret;
     } else {
-        nbd_co_receive_reply(client, &request, &reply, qiov, offset);
+        nbd_co_receive_reply(client, &request, &reply, qiov, 0);
     }
     nbd_coroutine_end(client, &request);
     return -reply.error;

 }

-static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
-                           int nb_sectors, QEMUIOVector *qiov,
-                           int offset, int flags)
+int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
+                         int nb_sectors, QEMUIOVector *qiov, int flags)
 {
     NbdClientSession *client = nbd_get_client_session(bs);
     struct nbd_request request = { .type = NBD_CMD_WRITE };
@@ -255,11 +254,12 @@ static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
         request.type |= NBD_CMD_FLAG_FUA;
     }

+    assert(nb_sectors <= NBD_MAX_SECTORS);
     request.from = sector_num * 512;
     request.len = nb_sectors * 512;

     nbd_coroutine_start(client, &request);
-    ret = nbd_co_send_request(bs, &request, qiov, offset);
+    ret = nbd_co_send_request(bs, &request, qiov, 0);
     if (ret < 0) {
         reply.error = -ret;
     } else {
@@ -269,41 +269,6 @@ static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
     return -reply.error;
 }

-int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
-                        int nb_sectors, QEMUIOVector *qiov)
-{
-    int offset = 0;
-    int ret;
-    while (nb_sectors > NBD_MAX_SECTORS) {
-        ret = nbd_co_readv_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset);
-        if (ret < 0) {
-            return ret;
-        }
-        offset += NBD_MAX_SECTORS * 512;
-        sector_num += NBD_MAX_SECTORS;
-        nb_sectors -= NBD_MAX_SECTORS;
-    }
-    return nbd_co_readv_1(bs, sector_num, nb_sectors, qiov, offset);
-}
-
-int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
-                         int nb_sectors, QEMUIOVector *qiov, int flags)
-{
-    int offset = 0;
-    int ret;
-    while (nb_sectors > NBD_MAX_SECTORS) {
-        ret = nbd_co_writev_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset,
-                              flags);
-        if (ret < 0) {
-            return ret;
-        }
-        offset += NBD_MAX_SECTORS * 512;
-        sector_num += NBD_MAX_SECTORS;
-        nb_sectors -= NBD_MAX_SECTORS;
-    }
-    return nbd_co_writev_1(bs, sector_num, nb_sectors, qiov, offset, flags);
-}
-
 int nbd_client_co_flush(BlockDriverState *bs)
 {
     NbdClientSession *client = nbd_get_client_session(bs);
diff --git a/block/nbd.c b/block/nbd.c
index 08e5b67..8a13078 100644
--- a/block/nbd.c
+++ b/block/nbd.c
@@ -349,12 +349,6 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
     return ret;
 }

-static int nbd_co_readv(BlockDriverState *bs, int64_t sector_num,
-                        int nb_sectors, QEMUIOVector *qiov)
-{
-    return nbd_client_co_readv(bs, sector_num, nb_sectors, qiov);
-}
-
 static int nbd_co_flush(BlockDriverState *bs)
 {
     return nbd_client_co_flush(bs);
@@ -450,7 +444,7 @@ static BlockDriver bdrv_nbd = {
     .instance_size              = sizeof(BDRVNBDState),
     .bdrv_parse_filename        = nbd_parse_filename,
     .bdrv_file_open             = nbd_open,
-    .bdrv_co_readv              = nbd_co_readv,
+    .bdrv_co_readv              = nbd_client_co_readv,
     .bdrv_co_writev_flags       = nbd_client_co_writev,
     .bdrv_close                 = nbd_close,
     .bdrv_co_flush_to_os        = nbd_co_flush,
@@ -468,7 +462,7 @@ static BlockDriver bdrv_nbd_tcp = {
     .instance_size              = sizeof(BDRVNBDState),
     .bdrv_parse_filename        = nbd_parse_filename,
     .bdrv_file_open             = nbd_open,
-    .bdrv_co_readv              = nbd_co_readv,
+    .bdrv_co_readv              = nbd_client_co_readv,
     .bdrv_co_writev_flags       = nbd_client_co_writev,
     .bdrv_close                 = nbd_close,
     .bdrv_co_flush_to_os        = nbd_co_flush,
@@ -486,7 +480,7 @@ static BlockDriver bdrv_nbd_unix = {
     .instance_size              = sizeof(BDRVNBDState),
     .bdrv_parse_filename        = nbd_parse_filename,
     .bdrv_file_open             = nbd_open,
-    .bdrv_co_readv              = nbd_co_readv,
+    .bdrv_co_readv              = nbd_client_co_readv,
     .bdrv_co_writev_flags       = nbd_client_co_writev,
     .bdrv_close                 = nbd_close,
     .bdrv_co_flush_to_os        = nbd_co_flush,
-- 
2.5.5