[Qemu-devel] [PULL 23/27] nbd: Implement NBD_CMD_WRITE_ZEROES on server

[Paolo Bonzini <pbonzini@redhat.com>]

From: Eric Blake <eblake@redhat.com>

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 to allow
a hole.

Note that when it comes to requiring full allocation, vs.
permitting optimizations, the NBD spec intentionally picked a
different sense for the flag; the rules in qemu are:
MAY_UNMAP == 0: must write zeroes
MAY_UNMAP == 1: may use holes if reads will see zeroes

while in NBD, the rules are:
FLAG_NO_HOLE == 1: must write zeroes
FLAG_NO_HOLE == 0: may use holes if reads will see zeroes

In all cases, the 'may use holes' scenario is optional (the
server need not use a hole, and must not use a hole if
subsequent reads would not see zeroes).

Signed-off-by: Eric Blake <eblake@redhat.com>
Message-Id: <1476469998-28592-16-git-send-email-eblake@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/block/nbd.h |  8 ++++++--
 nbd/server.c        | 42 ++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 46 insertions(+), 4 deletions(-)

diff --git a/include/block/nbd.h b/include/block/nbd.h
index eea7ef0..3e373f0 100644
--- a/include/block/nbd.h
+++ b/include/block/nbd.h
@@ -71,6 +71,7 @@ typedef struct NBDReply NBDReply;
 #define NBD_FLAG_SEND_FUA       (1 << 3)        /* Send FUA (Force Unit Access) */
 #define NBD_FLAG_ROTATIONAL     (1 << 4)        /* Use elevator algorithm - rotational media */
 #define NBD_FLAG_SEND_TRIM      (1 << 5)        /* Send TRIM (discard) */
+#define NBD_FLAG_SEND_WRITE_ZEROES (1 << 6)     /* Send WRITE_ZEROES */
 
 /* New-style handshake (global) flags, sent from server to client, and
    control what will happen during handshake phase. */
@@ -96,7 +97,8 @@ typedef struct NBDReply NBDReply;
 #define NBD_REP_ERR_SHUTDOWN    NBD_REP_ERR(7)  /* Server shutting down */
 
 /* Request flags, sent from client to server during transmission phase */
-#define NBD_CMD_FLAG_FUA        (1 << 0)
+#define NBD_CMD_FLAG_FUA        (1 << 0) /* 'force unit access' during write */
+#define NBD_CMD_FLAG_NO_HOLE    (1 << 1) /* don't punch hole on zero run */
 
 /* Supported request types */
 enum {
@@ -104,7 +106,9 @@ enum {
     NBD_CMD_WRITE = 1,
     NBD_CMD_DISC = 2,
     NBD_CMD_FLUSH = 3,
-    NBD_CMD_TRIM = 4
+    NBD_CMD_TRIM = 4,
+    /* 5 reserved for failed experiment NBD_CMD_CACHE */
+    NBD_CMD_WRITE_ZEROES = 6,
 };
 
 #define NBD_DEFAULT_PORT	10809
diff --git a/nbd/server.c b/nbd/server.c
index 12e2631..b68534d 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -618,7 +618,8 @@ static coroutine_fn int nbd_negotiate(NBDClientNewData *data)
     char buf[8 + 8 + 8 + 128];
     int rc;
     const uint16_t myflags = (NBD_FLAG_HAS_FLAGS | NBD_FLAG_SEND_TRIM |
-                              NBD_FLAG_SEND_FLUSH | NBD_FLAG_SEND_FUA);
+                              NBD_FLAG_SEND_FLUSH | NBD_FLAG_SEND_FUA |
+                              NBD_FLAG_SEND_WRITE_ZEROES);
     bool oldStyle;
     size_t len;
 
@@ -1148,11 +1149,17 @@ static ssize_t nbd_co_receive_request(NBDRequestData *req,
         rc = request->type == NBD_CMD_WRITE ? -ENOSPC : -EINVAL;
         goto out;
     }
-    if (request->flags & ~NBD_CMD_FLAG_FUA) {
+    if (request->flags & ~(NBD_CMD_FLAG_FUA | NBD_CMD_FLAG_NO_HOLE)) {
         LOG("unsupported flags (got 0x%x)", request->flags);
         rc = -EINVAL;
         goto out;
     }
+    if (request->type != NBD_CMD_WRITE_ZEROES &&
+        (request->flags & NBD_CMD_FLAG_NO_HOLE)) {
+        LOG("unexpected flags (got 0x%x)", request->flags);
+        rc = -EINVAL;
+        goto out;
+    }
 
     rc = 0;
 
@@ -1257,6 +1264,37 @@ static void nbd_trip(void *opaque)
         }
         break;
 
+    case NBD_CMD_WRITE_ZEROES:
+        TRACE("Request type is WRITE_ZEROES");
+
+        if (exp->nbdflags & NBD_FLAG_READ_ONLY) {
+            TRACE("Server is read-only, return error");
+            reply.error = EROFS;
+            goto error_reply;
+        }
+
+        TRACE("Writing to device");
+
+        flags = 0;
+        if (request.flags & NBD_CMD_FLAG_FUA) {
+            flags |= BDRV_REQ_FUA;
+        }
+        if (!(request.flags & NBD_CMD_FLAG_NO_HOLE)) {
+            flags |= BDRV_REQ_MAY_UNMAP;
+        }
+        ret = blk_pwrite_zeroes(exp->blk, request.from + exp->dev_offset,
+                                request.len, flags);
+        if (ret < 0) {
+            LOG("writing to file failed");
+            reply.error = -ret;
+            goto error_reply;
+        }
+
+        if (nbd_co_send_reply(req, &reply, 0) < 0) {
+            goto out;
+        }
+        break;
+
     case NBD_CMD_DISC:
         /* unreachable, thanks to special case in nbd_co_receive_request() */
         abort();
-- 
2.7.4