[Qemu-devel] [PATCH v3 42/44] nbd: Implement NBD_CMD_WRITE_ZEROES on client

[Eric Blake]

Upstream NBD protocol recently added the ability to efficiently
write zeroes without having to send the zeroes over the wire,
along with a flag to control whether the client wants a hole.

The generic block code takes care of falling back to the obvious
write of lots of zeroes if we return -ENOTSUP because the server
does not have WRITE_ZEROES.

Signed-off-by: Eric Blake <address@hidden>

---
v3: rebase, tell block layer about our support
---
 block/nbd-client.h |  2 ++
 block/nbd-client.c | 34 ++++++++++++++++++++++++++++++++++
 block/nbd.c        | 24 ++++++++++++++++++++++++
 3 files changed, 60 insertions(+)

diff --git a/block/nbd-client.h b/block/nbd-client.h
index 0867147..07630ab 100644
--- a/block/nbd-client.h
+++ b/block/nbd-client.h
@@ -46,6 +46,8 @@ void nbd_client_close(BlockDriverState *bs);
 int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num,
                           int nb_sectors);
 int nbd_client_co_flush(BlockDriverState *bs);
+int nbd_client_co_write_zeroes(BlockDriverState *bs, int64_t sector_num,
+                               int nb_sectors, int *flags);
 int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
                          int nb_sectors, QEMUIOVector *qiov, int *flags);
 int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
diff --git a/block/nbd-client.c b/block/nbd-client.c
index f20219b..2b6ac27 100644
--- a/block/nbd-client.c
+++ b/block/nbd-client.c
@@ -291,6 +291,40 @@ int nbd_client_co_readv(BlockDriverState *bs, int64_t 
sector_num,
     return nbd_co_readv_1(bs, sector_num, nb_sectors, qiov, offset);
 }

+int nbd_client_co_write_zeroes(BlockDriverState *bs, int64_t sector_num,
+                               int nb_sectors, int *flags)
+{
+    ssize_t ret;
+    NbdClientSession *client = nbd_get_client_session(bs);
+    struct nbd_request request = { .type = NBD_CMD_WRITE_ZEROES };
+    struct nbd_reply reply;
+
+    if (!(client->info.flags & NBD_FLAG_SEND_WRITE_ZEROES)) {
+        return -ENOTSUP;
+    }
+
+    if ((*flags & BDRV_REQ_FUA) && (client->info.flags & NBD_FLAG_SEND_FUA)) {
+        *flags &= ~BDRV_REQ_FUA;
+        request.flags |= NBD_CMD_FLAG_FUA;
+    }
+    if (!(*flags & BDRV_REQ_MAY_UNMAP)) {
+        request.flags |= NBD_CMD_FLAG_NO_HOLE;
+    }
+
+    request.from = sector_num * 512;
+    request.len = nb_sectors * 512;
+
+    nbd_coroutine_start(client, &request);
+    ret = nbd_co_send_request(bs, &request, NULL, 0);
+    if (ret < 0) {
+        reply.error = -ret;
+    } else {
+        nbd_co_receive_reply(client, &request, &reply, NULL, 0);
+    }
+    nbd_coroutine_end(client, &request);
+    return -reply.error;
+}
+
 int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
                          int nb_sectors, QEMUIOVector *qiov, int *flags)
 {
diff --git a/block/nbd.c b/block/nbd.c
index 34db83e..5172039 100644
--- a/block/nbd.c
+++ b/block/nbd.c
@@ -355,6 +355,26 @@ static int nbd_co_readv(BlockDriverState *bs, int64_t 
sector_num,
     return nbd_client_co_readv(bs, sector_num, nb_sectors, qiov);
 }

+static int nbd_co_write_zeroes(BlockDriverState *bs, int64_t sector_num,
+                               int nb_sectors, BdrvRequestFlags orig_flags)
+{
+    int flags = orig_flags;
+    int ret;
+
+    ret = nbd_client_co_write_zeroes(bs, sector_num, nb_sectors, &flags);
+    if (ret < 0) {
+        return ret;
+    }
+
+    /* The flag wasn't sent to the server, so we need to emulate it with an
+     * explicit flush */
+    if (flags & BDRV_REQ_FUA) {
+        ret = nbd_client_co_flush(bs);
+    }
+
+    return ret;
+}
+
 static int nbd_co_writev_flags(BlockDriverState *bs, int64_t sector_num,
                                int nb_sectors, QEMUIOVector *qiov, int flags)
 {
@@ -388,6 +408,7 @@ static int nbd_co_flush(BlockDriverState *bs)
 static void nbd_refresh_limits(BlockDriverState *bs, Error **errp)
 {
     bs->bl.max_discard = UINT32_MAX >> BDRV_SECTOR_BITS;
+    bs->bl.max_write_zeroes = UINT32_MAX >> BDRV_SECTOR_BITS;
     bs->bl.max_transfer_length = UINT32_MAX >> BDRV_SECTOR_BITS;
 }

@@ -476,6 +497,7 @@ static BlockDriver bdrv_nbd = {
     .bdrv_parse_filename        = nbd_parse_filename,
     .bdrv_file_open             = nbd_open,
     .bdrv_co_readv              = nbd_co_readv,
+    .bdrv_co_write_zeroes       = nbd_co_write_zeroes,
     .bdrv_co_writev             = nbd_co_writev,
     .bdrv_co_writev_flags       = nbd_co_writev_flags,
     .supported_write_flags      = BDRV_REQ_FUA,
@@ -496,6 +518,7 @@ static BlockDriver bdrv_nbd_tcp = {
     .bdrv_parse_filename        = nbd_parse_filename,
     .bdrv_file_open             = nbd_open,
     .bdrv_co_readv              = nbd_co_readv,
+    .bdrv_co_write_zeroes       = nbd_co_write_zeroes,
     .bdrv_co_writev             = nbd_co_writev,
     .bdrv_co_writev_flags       = nbd_co_writev_flags,
     .supported_write_flags      = BDRV_REQ_FUA,
@@ -516,6 +539,7 @@ static BlockDriver bdrv_nbd_unix = {
     .bdrv_parse_filename        = nbd_parse_filename,
     .bdrv_file_open             = nbd_open,
     .bdrv_co_readv              = nbd_co_readv,
+    .bdrv_co_write_zeroes       = nbd_co_write_zeroes,
     .bdrv_co_writev             = nbd_co_writev,
     .bdrv_co_writev_flags       = nbd_co_writev_flags,
     .supported_write_flags      = BDRV_REQ_FUA,
-- 
2.5.5