Merge tag 'pull-nbd-2023-09-25' of https://repo.or.cz/qemu/ericb into staging

NBD patches through 2023-09-25

- Denis V. Lunev: iotest improvements
- Eric Blake: further work towards 64-bit NBD extensions

# -----BEGIN PGP SIGNATURE-----
#
# iQEzBAABCAAdFiEEccLMIrHEYCkn0vOqp6FrSiUnQ2oFAmUR2MUACgkQp6FrSiUn
# Q2q6jAf+PT65XzMAhgKvu1vIeMSQqyCocNB2MCOzNp+46uB9bNbPPLQSH2EX+t6p
# kQfHyHUl4YMi0EqgCfodiewlaUKeMxP3cPWMGYaYZ16uNMOIYL1boreDAcM25rb5
# P3TV3DAWTWSclUxrkTC2DxAIBPgsPsGG/2daqOMDEdinxlIywCMJDEIHc9gwwd/t
# 7laz9V1cOW9NbQXrM7eTofJKPKIeqZ+w0kvqrf9HBvZl9CqwHADi7xoz9xP+fN+f
# 713ED/hwt0FIlixtIm2/8vu7nn09cu6m9NaKsMOomsYg9Z6wU3ctivViG5NLq3MD
# OOUu51dV8gRRAXAFU5vKb0d93D27zQ==
# =Ik02
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 25 Sep 2023 15:00:21 EDT
# gpg:                using RSA key 71C2CC22B1C4602927D2F3AAA7A16B4A2527436A
# gpg: Good signature from "Eric Blake <eblake@redhat.com>" [full]
# gpg:                 aka "Eric Blake (Free Software Programmer) <ebb9@byu.net>" [full]
# gpg:                 aka "[jpeg image of size 6874]" [full]
# Primary key fingerprint: 71C2 CC22 B1C4 6029 27D2  F3AA A7A1 6B4A 2527 436A

* tag 'pull-nbd-2023-09-25' of https://repo.or.cz/qemu/ericb:
  nbd/server: Refactor handling of command sanity checks
  nbd: Prepare for 64-bit request effect lengths
  nbd: Add types for extended headers
  nbd/client: Pass mode through to nbd_send_request
  nbd: Replace bool structured_reply with mode enum
  iotests: improve 'not run' message for nbd-multiconn test
  iotests: use TEST_IMG_FILE instead of TEST_IMG in _require_large_file

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

12 files changed, 280 insertions, 150 deletions

diff --git a/block/nbd.c b/block/nbd.c
index cc48580df7..4a7f37da1c 100644
--- a/block/nbd.c
+++ b/block/nbd.c
@@ -339,7 +339,7 @@ int coroutine_fn nbd_co_do_establish_connection(BlockDriverState *bs,
          * We have connected, but must fail for other reasons.
          * Send NBD_CMD_DISC as a courtesy to the server.
          */
-        NBDRequest request = { .type = NBD_CMD_DISC };
+        NBDRequest request = { .type = NBD_CMD_DISC, .mode = s->info.mode };
 
         nbd_send_request(s->ioc, &request);
 
@@ -463,7 +463,8 @@ static coroutine_fn int nbd_receive_replies(BDRVNBDState *s, uint64_t cookie)
             nbd_channel_error(s, ret);
             return ret;
         }
-        if (nbd_reply_is_structured(&s->reply) && !s->info.structured_reply) {
+        if (nbd_reply_is_structured(&s->reply) &&
+            s->info.mode < NBD_MODE_STRUCTURED) {
             nbd_channel_error(s, -EINVAL);
             return -EINVAL;
         }
@@ -519,6 +520,7 @@ nbd_co_send_request(BlockDriverState *bs, NBDRequest *request,
 
     qemu_co_mutex_lock(&s->send_mutex);
     request->cookie = INDEX_TO_COOKIE(i);
+    request->mode = s->info.mode;
 
     assert(s->ioc);
 
@@ -608,7 +610,7 @@ static int nbd_parse_offset_hole_payload(BDRVNBDState *s,
 static int nbd_parse_blockstatus_payload(BDRVNBDState *s,
                                          NBDStructuredReplyChunk *chunk,
                                          uint8_t *payload, uint64_t orig_length,
-                                         NBDExtent *extent, Error **errp)
+                                         NBDExtent32 *extent, Error **errp)
 {
     uint32_t context_id;
 
@@ -866,7 +868,7 @@ static coroutine_fn int nbd_co_do_receive_one_chunk(
     }
 
     /* handle structured reply chunk */
-    assert(s->info.structured_reply);
+    assert(s->info.mode >= NBD_MODE_STRUCTURED);
     chunk = &s->reply.structured;
 
     if (chunk->type == NBD_REPLY_TYPE_NONE) {
@@ -1070,7 +1072,8 @@ nbd_co_receive_cmdread_reply(BDRVNBDState *s, uint64_t cookie,
     void *payload = NULL;
     Error *local_err = NULL;
 
-    NBD_FOREACH_REPLY_CHUNK(s, iter, cookie, s->info.structured_reply,
+    NBD_FOREACH_REPLY_CHUNK(s, iter, cookie,
+                            s->info.mode >= NBD_MODE_STRUCTURED,
                             qiov, &reply, &payload)
     {
         int ret;
@@ -1115,7 +1118,7 @@ nbd_co_receive_cmdread_reply(BDRVNBDState *s, uint64_t cookie,
 
 static int coroutine_fn
 nbd_co_receive_blockstatus_reply(BDRVNBDState *s, uint64_t cookie,
-                                 uint64_t length, NBDExtent *extent,
+                                 uint64_t length, NBDExtent32 *extent,
                                  int *request_ret, Error **errp)
 {
     NBDReplyChunkIter iter;
@@ -1302,10 +1305,11 @@ nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int64_t bytes,
     NBDRequest request = {
         .type = NBD_CMD_WRITE_ZEROES,
         .from = offset,
-        .len = bytes,  /* .len is uint32_t actually */
+        .len = bytes,
     };
 
-    assert(bytes <= UINT32_MAX); /* rely on max_pwrite_zeroes */
+    /* rely on max_pwrite_zeroes */
+    assert(bytes <= UINT32_MAX || s->info.mode >= NBD_MODE_EXTENDED);
 
     assert(!(s->info.flags & NBD_FLAG_READ_ONLY));
     if (!(s->info.flags & NBD_FLAG_SEND_WRITE_ZEROES)) {
@@ -1352,10 +1356,11 @@ nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes)
     NBDRequest request = {
         .type = NBD_CMD_TRIM,
         .from = offset,
-        .len = bytes, /* len is uint32_t */
+        .len = bytes,
     };
 
-    assert(bytes <= UINT32_MAX); /* rely on max_pdiscard */
+    /* rely on max_pdiscard */
+    assert(bytes <= UINT32_MAX || s->info.mode >= NBD_MODE_EXTENDED);
 
     assert(!(s->info.flags & NBD_FLAG_READ_ONLY));
     if (!(s->info.flags & NBD_FLAG_SEND_TRIM) || !bytes) {
@@ -1370,15 +1375,14 @@ static int coroutine_fn GRAPH_RDLOCK nbd_client_co_block_status(
         int64_t *pnum, int64_t *map, BlockDriverState **file)
 {
     int ret, request_ret;
-    NBDExtent extent = { 0 };
+    NBDExtent32 extent = { 0 };
     BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
     Error *local_err = NULL;
 
     NBDRequest request = {
         .type = NBD_CMD_BLOCK_STATUS,
         .from = offset,
-        .len = MIN(QEMU_ALIGN_DOWN(INT_MAX, bs->bl.request_alignment),
-                   MIN(bytes, s->info.size - offset)),
+        .len = MIN(bytes, s->info.size - offset),
         .flags = NBD_CMD_FLAG_REQ_ONE,
     };
 
@@ -1388,6 +1392,10 @@ static int coroutine_fn GRAPH_RDLOCK nbd_client_co_block_status(
         *file = bs;
         return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
     }
+    if (s->info.mode < NBD_MODE_EXTENDED) {
+        request.len = MIN(QEMU_ALIGN_DOWN(INT_MAX, bs->bl.request_alignment),
+                          request.len);
+    }
 
     /*
      * Work around the fact that the block layer doesn't do
@@ -1463,7 +1471,7 @@ static void nbd_yank(void *opaque)
 static void nbd_client_close(BlockDriverState *bs)
 {
     BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
-    NBDRequest request = { .type = NBD_CMD_DISC };
+    NBDRequest request = { .type = NBD_CMD_DISC, .mode = s->info.mode };
 
     if (s->ioc) {
         nbd_send_request(s->ioc, &request);
@@ -1952,6 +1960,14 @@ static void nbd_refresh_limits(BlockDriverState *bs, Error **errp)
     bs->bl.max_pwrite_zeroes = max;
     bs->bl.max_transfer = max;
 
+    /*
+     * Assume that if the server supports extended headers, it also
+     * supports unlimited size zero and trim commands.
+     */
+    if (s->info.mode >= NBD_MODE_EXTENDED) {
+        bs->bl.max_pdiscard = bs->bl.max_pwrite_zeroes = 0;
+    }
+
     if (s->info.opt_block &&
         s->info.opt_block > bs->bl.opt_transfer) {
         bs->bl.opt_transfer = s->info.opt_block;
diff --git a/block/trace-events b/block/trace-events
index 6f121b7636..925aa554bb 100644
--- a/block/trace-events
+++ b/block/trace-events
@@ -167,7 +167,7 @@ iscsi_xcopy(void *src_lun, uint64_t src_off, void *dst_lun, uint64_t dst_off, ui
 nbd_parse_blockstatus_compliance(const char *err) "ignoring extra data from non-compliant server: %s"
 nbd_structured_read_compliance(const char *type) "server sent non-compliant unaligned read %s chunk"
 nbd_read_reply_entry_fail(int ret, const char *err) "ret = %d, err: %s"
-nbd_co_request_fail(uint64_t from, uint32_t len, uint64_t handle, uint16_t flags, uint16_t type, const char *name, int ret, const char *err) "Request failed { .from = %" PRIu64", .len = %" PRIu32 ", .handle = %" PRIu64 ", .flags = 0x%" PRIx16 ", .type = %" PRIu16 " (%s) } ret = %d, err: %s"
+nbd_co_request_fail(uint64_t from, uint64_t len, uint64_t handle, uint16_t flags, uint16_t type, const char *name, int ret, const char *err) "Request failed { .from = %" PRIu64", .len = %" PRIu64 ", .handle = %" PRIu64 ", .flags = 0x%" PRIx16 ", .type = %" PRIu16 " (%s) } ret = %d, err: %s"
 nbd_client_handshake(const char *export_name) "export '%s'"
 nbd_client_handshake_success(const char *export_name) "export '%s'"
 nbd_reconnect_attempt(unsigned in_flight) "in_flight %u"
diff --git a/include/block/nbd.h b/include/block/nbd.h
index f672b76173..8a765e78df 100644
--- a/include/block/nbd.h
+++ b/include/block/nbd.h
@@ -60,20 +60,22 @@ typedef enum NBDMode {
     NBD_MODE_EXPORT_NAME,  /* newstyle but only OPT_EXPORT_NAME safe */
     NBD_MODE_SIMPLE,       /* newstyle but only simple replies */
     NBD_MODE_STRUCTURED,   /* newstyle, structured replies enabled */
-    /* TODO add NBD_MODE_EXTENDED */
+    NBD_MODE_EXTENDED,     /* newstyle, extended headers enabled */
 } NBDMode;
 
-/* Transmission phase structs
- *
- * Note: these are _NOT_ the same as the network representation of an NBD
- * request and reply!
+/* Transmission phase structs */
+
+/*
+ * Note: NBDRequest is _NOT_ the same as the network representation of an NBD
+ * request!
  */
 typedef struct NBDRequest {
     uint64_t cookie;
-    uint64_t from;
-    uint32_t len;
+    uint64_t from;  /* Offset touched by the command */
+    uint64_t len;   /* Effect length; 32 bit limit without extended headers */
     uint16_t flags; /* NBD_CMD_FLAG_* */
-    uint16_t type; /* NBD_CMD_* */
+    uint16_t type;  /* NBD_CMD_* */
+    NBDMode mode;   /* Determines which network representation to use */
 } NBDRequest;
 
 typedef struct NBDSimpleReply {
@@ -91,20 +93,36 @@ typedef struct NBDStructuredReplyChunk {
     uint32_t length; /* length of payload */
 } QEMU_PACKED NBDStructuredReplyChunk;
 
+typedef struct NBDExtendedReplyChunk {
+    uint32_t magic;  /* NBD_EXTENDED_REPLY_MAGIC */
+    uint16_t flags;  /* combination of NBD_REPLY_FLAG_* */
+    uint16_t type;   /* NBD_REPLY_TYPE_* */
+    uint64_t cookie; /* request handle */
+    uint64_t offset; /* request offset */
+    uint64_t length; /* length of payload */
+} QEMU_PACKED NBDExtendedReplyChunk;
+
 typedef union NBDReply {
     NBDSimpleReply simple;
     NBDStructuredReplyChunk structured;
+    NBDExtendedReplyChunk extended;
     struct {
         /*
-         * @magic and @cookie fields have the same offset and size both in
-         * simple reply and structured reply chunk, so let them be accessible
-         * without ".simple." or ".structured." specification
+         * @magic and @cookie fields have the same offset and size in all
+         * forms of replies, so let them be accessible without ".simple.",
+         * ".structured.", or ".extended." specifications.
          */
         uint32_t magic;
         uint32_t _skip;
         uint64_t cookie;
-    } QEMU_PACKED;
+    };
 } NBDReply;
+QEMU_BUILD_BUG_ON(offsetof(NBDReply, simple.cookie) !=
+                  offsetof(NBDReply, cookie));
+QEMU_BUILD_BUG_ON(offsetof(NBDReply, structured.cookie) !=
+                  offsetof(NBDReply, cookie));
+QEMU_BUILD_BUG_ON(offsetof(NBDReply, extended.cookie) !=
+                  offsetof(NBDReply, cookie));
 
 /* Header of chunk for NBD_REPLY_TYPE_OFFSET_DATA */
 typedef struct NBDStructuredReadData {
@@ -131,14 +149,34 @@ typedef struct NBDStructuredError {
 typedef struct NBDStructuredMeta {
     /* header's length >= 12 (at least one extent) */
     uint32_t context_id;
-    /* extents follows */
+    /* NBDExtent32 extents[] follows, array length implied by header */
 } QEMU_PACKED NBDStructuredMeta;
 
-/* Extent chunk for NBD_REPLY_TYPE_BLOCK_STATUS */
-typedef struct NBDExtent {
+/* Extent array element for NBD_REPLY_TYPE_BLOCK_STATUS */
+typedef struct NBDExtent32 {
     uint32_t length;
     uint32_t flags; /* NBD_STATE_* */
-} QEMU_PACKED NBDExtent;
+} QEMU_PACKED NBDExtent32;
+
+/* Header of NBD_REPLY_TYPE_BLOCK_STATUS_EXT */
+typedef struct NBDExtendedMeta {
+    /* header's length >= 24 (at least one extent) */
+    uint32_t context_id;
+    uint32_t count; /* header length must be count * 16 + 8 */
+    /* NBDExtent64 extents[count] follows */
+} QEMU_PACKED NBDExtendedMeta;
+
+/* Extent array element for NBD_REPLY_TYPE_BLOCK_STATUS_EXT */
+typedef struct NBDExtent64 {
+    uint64_t length;
+    uint64_t flags; /* NBD_STATE_* */
+} QEMU_PACKED NBDExtent64;
+
+/* Client payload for limiting NBD_CMD_BLOCK_STATUS reply */
+typedef struct NBDBlockStatusPayload {
+    uint64_t effect_length;
+    /* uint32_t ids[] follows, array length implied by header */
+} QEMU_PACKED NBDBlockStatusPayload;
 
 /* Transmission (export) flags: sent from server to client during handshake,
    but describe what will happen during transmission */
@@ -156,20 +194,22 @@ enum {
     NBD_FLAG_SEND_RESIZE_BIT        =  9, /* Send resize */
     NBD_FLAG_SEND_CACHE_BIT         = 10, /* Send CACHE (prefetch) */
     NBD_FLAG_SEND_FAST_ZERO_BIT     = 11, /* FAST_ZERO flag for WRITE_ZEROES */
+    NBD_FLAG_BLOCK_STAT_PAYLOAD_BIT = 12, /* PAYLOAD flag for BLOCK_STATUS */
 };
 
-#define NBD_FLAG_HAS_FLAGS         (1 << NBD_FLAG_HAS_FLAGS_BIT)
-#define NBD_FLAG_READ_ONLY         (1 << NBD_FLAG_READ_ONLY_BIT)
-#define NBD_FLAG_SEND_FLUSH        (1 << NBD_FLAG_SEND_FLUSH_BIT)
-#define NBD_FLAG_SEND_FUA          (1 << NBD_FLAG_SEND_FUA_BIT)
-#define NBD_FLAG_ROTATIONAL        (1 << NBD_FLAG_ROTATIONAL_BIT)
-#define NBD_FLAG_SEND_TRIM         (1 << NBD_FLAG_SEND_TRIM_BIT)
-#define NBD_FLAG_SEND_WRITE_ZEROES (1 << NBD_FLAG_SEND_WRITE_ZEROES_BIT)
-#define NBD_FLAG_SEND_DF           (1 << NBD_FLAG_SEND_DF_BIT)
-#define NBD_FLAG_CAN_MULTI_CONN    (1 << NBD_FLAG_CAN_MULTI_CONN_BIT)
-#define NBD_FLAG_SEND_RESIZE       (1 << NBD_FLAG_SEND_RESIZE_BIT)
-#define NBD_FLAG_SEND_CACHE        (1 << NBD_FLAG_SEND_CACHE_BIT)
-#define NBD_FLAG_SEND_FAST_ZERO    (1 << NBD_FLAG_SEND_FAST_ZERO_BIT)
+#define NBD_FLAG_HAS_FLAGS          (1 << NBD_FLAG_HAS_FLAGS_BIT)
+#define NBD_FLAG_READ_ONLY          (1 << NBD_FLAG_READ_ONLY_BIT)
+#define NBD_FLAG_SEND_FLUSH         (1 << NBD_FLAG_SEND_FLUSH_BIT)
+#define NBD_FLAG_SEND_FUA           (1 << NBD_FLAG_SEND_FUA_BIT)
+#define NBD_FLAG_ROTATIONAL         (1 << NBD_FLAG_ROTATIONAL_BIT)
+#define NBD_FLAG_SEND_TRIM          (1 << NBD_FLAG_SEND_TRIM_BIT)
+#define NBD_FLAG_SEND_WRITE_ZEROES  (1 << NBD_FLAG_SEND_WRITE_ZEROES_BIT)
+#define NBD_FLAG_SEND_DF            (1 << NBD_FLAG_SEND_DF_BIT)
+#define NBD_FLAG_CAN_MULTI_CONN     (1 << NBD_FLAG_CAN_MULTI_CONN_BIT)
+#define NBD_FLAG_SEND_RESIZE        (1 << NBD_FLAG_SEND_RESIZE_BIT)
+#define NBD_FLAG_SEND_CACHE         (1 << NBD_FLAG_SEND_CACHE_BIT)
+#define NBD_FLAG_SEND_FAST_ZERO     (1 << NBD_FLAG_SEND_FAST_ZERO_BIT)
+#define NBD_FLAG_BLOCK_STAT_PAYLOAD (1 << NBD_FLAG_BLOCK_STAT_PAYLOAD_BIT)
 
 /* New-style handshake (global) flags, sent from server to client, and
    control what will happen during handshake phase. */
@@ -192,6 +232,7 @@ enum {
 #define NBD_OPT_STRUCTURED_REPLY  (8)
 #define NBD_OPT_LIST_META_CONTEXT (9)
 #define NBD_OPT_SET_META_CONTEXT  (10)
+#define NBD_OPT_EXTENDED_HEADERS  (11)
 
 /* Option reply types. */
 #define NBD_REP_ERR(value) ((UINT32_C(1) << 31) | (value))
@@ -209,6 +250,8 @@ enum {
 #define NBD_REP_ERR_UNKNOWN         NBD_REP_ERR(6)  /* Export unknown */
 #define NBD_REP_ERR_SHUTDOWN        NBD_REP_ERR(7)  /* Server shutting down */
 #define NBD_REP_ERR_BLOCK_SIZE_REQD NBD_REP_ERR(8)  /* Need INFO_BLOCK_SIZE */
+#define NBD_REP_ERR_TOO_BIG         NBD_REP_ERR(9)  /* Payload size overflow */
+#define NBD_REP_ERR_EXT_HEADER_REQD NBD_REP_ERR(10) /* Need extended headers */
 
 /* Info types, used during NBD_REP_INFO */
 #define NBD_INFO_EXPORT         0
@@ -217,12 +260,14 @@ enum {
 #define NBD_INFO_BLOCK_SIZE     3
 
 /* Request flags, sent from client to server during transmission phase */
-#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 */
-#define NBD_CMD_FLAG_DF         (1 << 2) /* don't fragment structured read */
-#define NBD_CMD_FLAG_REQ_ONE    (1 << 3) /* only one extent in BLOCK_STATUS
-                                          * reply chunk */
-#define NBD_CMD_FLAG_FAST_ZERO  (1 << 4) /* fail if WRITE_ZEROES is not fast */
+#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 */
+#define NBD_CMD_FLAG_DF          (1 << 2) /* don't fragment structured read */
+#define NBD_CMD_FLAG_REQ_ONE     (1 << 3) \
+    /* only one extent in BLOCK_STATUS reply chunk */
+#define NBD_CMD_FLAG_FAST_ZERO   (1 << 4) /* fail if WRITE_ZEROES is not fast */
+#define NBD_CMD_FLAG_PAYLOAD_LEN (1 << 5) \
+    /* length describes payload, not effect; only with ext header */
 
 /* Supported request types */
 enum {
@@ -248,22 +293,31 @@ enum {
  */
 #define NBD_MAX_STRING_SIZE 4096
 
-/* Two types of reply structures */
+/* Two types of request structures, a given client will only use 1 */
+#define NBD_REQUEST_MAGIC           0x25609513
+#define NBD_EXTENDED_REQUEST_MAGIC  0x21e41c71
+
+/*
+ * Three types of reply structures, but what a client expects depends
+ * on NBD_OPT_STRUCTURED_REPLY and NBD_OPT_EXTENDED_HEADERS.
+ */
 #define NBD_SIMPLE_REPLY_MAGIC      0x67446698
 #define NBD_STRUCTURED_REPLY_MAGIC  0x668e33ef
+#define NBD_EXTENDED_REPLY_MAGIC    0x6e8a278c
 
-/* Structured reply flags */
+/* Chunk reply flags (for structured and extended replies) */
 #define NBD_REPLY_FLAG_DONE          (1 << 0) /* This reply-chunk is last */
 
-/* Structured reply types */
+/* Chunk reply types */
 #define NBD_REPLY_ERR(value)         ((1 << 15) | (value))
 
-#define NBD_REPLY_TYPE_NONE          0
-#define NBD_REPLY_TYPE_OFFSET_DATA   1
-#define NBD_REPLY_TYPE_OFFSET_HOLE   2
-#define NBD_REPLY_TYPE_BLOCK_STATUS  5
-#define NBD_REPLY_TYPE_ERROR         NBD_REPLY_ERR(1)
-#define NBD_REPLY_TYPE_ERROR_OFFSET  NBD_REPLY_ERR(2)
+#define NBD_REPLY_TYPE_NONE              0
+#define NBD_REPLY_TYPE_OFFSET_DATA       1
+#define NBD_REPLY_TYPE_OFFSET_HOLE       2
+#define NBD_REPLY_TYPE_BLOCK_STATUS      5
+#define NBD_REPLY_TYPE_BLOCK_STATUS_EXT  6
+#define NBD_REPLY_TYPE_ERROR             NBD_REPLY_ERR(1)
+#define NBD_REPLY_TYPE_ERROR_OFFSET      NBD_REPLY_ERR(2)
 
 /* Extent flags for base:allocation in NBD_REPLY_TYPE_BLOCK_STATUS */
 #define NBD_STATE_HOLE (1 << 0)
@@ -305,7 +359,7 @@ typedef struct NBDExportInfo {
 
     /* In-out fields, set by client before nbd_receive_negotiate() and
      * updated by server results during nbd_receive_negotiate() */
-    bool structured_reply;
+    NBDMode mode; /* input maximum mode tolerated; output actual mode chosen */
     bool base_allocation; /* base:allocation context for NBD_CMD_BLOCK_STATUS */
 
     /* Set by server results during nbd_receive_negotiate() and
diff --git a/nbd/client-connection.c b/nbd/client-connection.c
index 53a6549914..aa0201b710 100644
--- a/nbd/client-connection.c
+++ b/nbd/client-connection.c
@@ -1,5 +1,5 @@
 /*
- * QEMU Block driver for  NBD
+ * QEMU Block driver for NBD
  *
  * Copyright (c) 2021 Virtuozzo International GmbH.
  *
@@ -93,7 +93,7 @@ NBDClientConnection *nbd_client_connection_new(const SocketAddress *saddr,
         .do_negotiation = do_negotiation,
 
         .initial_info.request_sizes = true,
-        .initial_info.structured_reply = true,
+        .initial_info.mode = NBD_MODE_STRUCTURED,
         .initial_info.base_allocation = true,
         .initial_info.x_dirty_bitmap = g_strdup(x_dirty_bitmap),
         .initial_info.name = g_strdup(export_name ?: "")
diff --git a/nbd/client.c b/nbd/client.c
index bd7e200136..cecb0f0437 100644
--- a/nbd/client.c
+++ b/nbd/client.c
@@ -879,7 +879,7 @@ static int nbd_list_meta_contexts(QIOChannel *ioc,
  */
 static int nbd_start_negotiate(QIOChannel *ioc, QCryptoTLSCreds *tlscreds,
                                const char *hostname, QIOChannel **outioc,
-                               bool structured_reply, bool *zeroes,
+                               NBDMode max_mode, bool *zeroes,
                                Error **errp)
 {
     ERRP_GUARD();
@@ -953,7 +953,7 @@ static int nbd_start_negotiate(QIOChannel *ioc, QCryptoTLSCreds *tlscreds,
         if (fixedNewStyle) {
             int result = 0;
 
-            if (structured_reply) {
+            if (max_mode >= NBD_MODE_STRUCTURED) {
                 result = nbd_request_simple_option(ioc,
                                                    NBD_OPT_STRUCTURED_REPLY,
                                                    false, errp);
@@ -1022,20 +1022,19 @@ int nbd_receive_negotiate(QIOChannel *ioc, QCryptoTLSCreds *tlscreds,
     trace_nbd_receive_negotiate_name(info->name);
 
     result = nbd_start_negotiate(ioc, tlscreds, hostname, outioc,
-                                 info->structured_reply, &zeroes, errp);
+                                 info->mode, &zeroes, errp);
     if (result < 0) {
         return result;
     }
 
-    info->structured_reply = false;
+    info->mode = result;
     info->base_allocation = false;
     if (tlscreds && *outioc) {
         ioc = *outioc;
     }
 
-    switch ((NBDMode)result) {
+    switch (info->mode) {
     case NBD_MODE_STRUCTURED:
-        info->structured_reply = true;
         if (base_allocation) {
             result = nbd_negotiate_simple_meta_context(ioc, info, errp);
             if (result < 0) {
@@ -1144,8 +1143,8 @@ int nbd_receive_export_list(QIOChannel *ioc, QCryptoTLSCreds *tlscreds,
     QIOChannel *sioc = NULL;
 
     *info = NULL;
-    result = nbd_start_negotiate(ioc, tlscreds, hostname, &sioc, true,
-                                 NULL, errp);
+    result = nbd_start_negotiate(ioc, tlscreds, hostname, &sioc,
+                                 NBD_MODE_STRUCTURED, NULL, errp);
     if (tlscreds && sioc) {
         ioc = sioc;
     }
@@ -1176,7 +1175,7 @@ int nbd_receive_export_list(QIOChannel *ioc, QCryptoTLSCreds *tlscreds,
             memset(&array[count - 1], 0, sizeof(*array));
             array[count - 1].name = name;
             array[count - 1].description = desc;
-            array[count - 1].structured_reply = result == NBD_MODE_STRUCTURED;
+            array[count - 1].mode = result;
         }
 
         for (i = 0; i < count; i++) {
@@ -1209,6 +1208,7 @@ int nbd_receive_export_list(QIOChannel *ioc, QCryptoTLSCreds *tlscreds,
         /* Lone export name is implied, but we can parse length and flags */
         array = g_new0(NBDExportInfo, 1);
         array->name = g_strdup("");
+        array->mode = NBD_MODE_OLDSTYLE;
         count = 1;
 
         if (nbd_negotiate_finish_oldstyle(ioc, array, errp) < 0) {
@@ -1218,7 +1218,7 @@ int nbd_receive_export_list(QIOChannel *ioc, QCryptoTLSCreds *tlscreds,
         /* Send NBD_CMD_DISC as a courtesy to the server, but ignore all
          * errors now that we have the information we wanted. */
         if (nbd_drop(ioc, 124, NULL) == 0) {
-            NBDRequest request = { .type = NBD_CMD_DISC };
+            NBDRequest request = { .type = NBD_CMD_DISC, .mode = result };
 
             nbd_send_request(ioc, &request);
         }
@@ -1348,6 +1348,8 @@ int nbd_send_request(QIOChannel *ioc, NBDRequest *request)
 {
     uint8_t buf[NBD_REQUEST_SIZE];
 
+    assert(request->mode <= NBD_MODE_STRUCTURED); /* TODO handle extended */
+    assert(request->len <= UINT32_MAX);
     trace_nbd_send_request(request->from, request->len, request->cookie,
                            request->flags, request->type,
                            nbd_cmd_lookup(request->type));
diff --git a/nbd/common.c b/nbd/common.c
index 989fbe54a1..3247c1d618 100644
--- a/nbd/common.c
+++ b/nbd/common.c
@@ -79,6 +79,8 @@ const char *nbd_opt_lookup(uint32_t opt)
         return "list meta context";
     case NBD_OPT_SET_META_CONTEXT:
         return "set meta context";
+    case NBD_OPT_EXTENDED_HEADERS:
+        return "extended headers";
     default:
         return "<unknown>";
     }
@@ -112,6 +114,10 @@ const char *nbd_rep_lookup(uint32_t rep)
         return "server shutting down";
     case NBD_REP_ERR_BLOCK_SIZE_REQD:
         return "block size required";
+    case NBD_REP_ERR_TOO_BIG:
+        return "option payload too big";
+    case NBD_REP_ERR_EXT_HEADER_REQD:
+        return "extended headers required";
     default:
         return "<unknown>";
     }
@@ -170,7 +176,9 @@ const char *nbd_reply_type_lookup(uint16_t type)
     case NBD_REPLY_TYPE_OFFSET_HOLE:
         return "hole";
     case NBD_REPLY_TYPE_BLOCK_STATUS:
-        return "block status";
+        return "block status (32-bit)";
+    case NBD_REPLY_TYPE_BLOCK_STATUS_EXT:
+        return "block status (64-bit)";
     case NBD_REPLY_TYPE_ERROR:
         return "generic error";
     case NBD_REPLY_TYPE_ERROR_OFFSET:
@@ -261,6 +269,8 @@ const char *nbd_mode_lookup(NBDMode mode)
         return "simple headers";
     case NBD_MODE_STRUCTURED:
         return "structured replies";
+    case NBD_MODE_EXTENDED:
+        return "extended headers";
     default:
         return "<unknown>";
     }
diff --git a/nbd/nbd-internal.h b/nbd/nbd-internal.h
index df42fef706..133b1d94b5 100644
--- a/nbd/nbd-internal.h
+++ b/nbd/nbd-internal.h
@@ -1,7 +1,7 @@
 /*
  * NBD Internal Declarations
  *
- * Copyright (C) 2016 Red Hat, Inc.
+ * Copyright Red Hat
  *
  * This work is licensed under the terms of the GNU GPL, version 2 or later.
  * See the COPYING file in the top-level directory.
@@ -44,7 +44,6 @@
 #define NBD_OLDSTYLE_NEGOTIATE_SIZE (8 + 8 + 8 + 4 + 124)
 
 #define NBD_INIT_MAGIC              0x4e42444d41474943LL /* ASCII "NBDMAGIC" */
-#define NBD_REQUEST_MAGIC           0x25609513
 #define NBD_OPTS_MAGIC              0x49484156454F5054LL /* ASCII "IHAVEOPT" */
 #define NBD_CLIENT_MAGIC            0x0000420281861253LL
 #define NBD_REP_MAGIC               0x0003e889045565a9LL
diff --git a/nbd/server.c b/nbd/server.c
index b5f93a20c9..7a6f95071f 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -143,7 +143,7 @@ struct NBDClient {
 
     uint32_t check_align; /* If non-zero, check for aligned client requests */
 
-    bool structured_reply;
+    NBDMode mode;
     NBDExportMetaContexts export_meta;
 
     uint32_t opt; /* Current option being negotiated */
@@ -502,7 +502,7 @@ static int nbd_negotiate_handle_export_name(NBDClient *client, bool no_zeroes,
     }
 
     myflags = client->exp->nbdflags;
-    if (client->structured_reply) {
+    if (client->mode >= NBD_MODE_STRUCTURED) {
         myflags |= NBD_FLAG_SEND_DF;
     }
     trace_nbd_negotiate_new_style_size_flags(client->exp->size, myflags);
@@ -687,7 +687,7 @@ static int nbd_negotiate_handle_info(NBDClient *client, Error **errp)
 
     /* Send NBD_INFO_EXPORT always */
     myflags = exp->nbdflags;
-    if (client->structured_reply) {
+    if (client->mode >= NBD_MODE_STRUCTURED) {
         myflags |= NBD_FLAG_SEND_DF;
     }
     trace_nbd_negotiate_new_style_size_flags(exp->size, myflags);
@@ -985,7 +985,8 @@ static int nbd_negotiate_meta_queries(NBDClient *client,
     size_t i;
     size_t count = 0;
 
-    if (client->opt == NBD_OPT_SET_META_CONTEXT && !client->structured_reply) {
+    if (client->opt == NBD_OPT_SET_META_CONTEXT &&
+        client->mode < NBD_MODE_STRUCTURED) {
         return nbd_opt_invalid(client, errp,
                                "request option '%s' when structured reply "
                                "is not negotiated",
@@ -1122,10 +1123,12 @@ static int nbd_negotiate_options(NBDClient *client, Error **errp)
     if (nbd_read32(client->ioc, &flags, "flags", errp) < 0) {
         return -EIO;
     }
+    client->mode = NBD_MODE_EXPORT_NAME;
     trace_nbd_negotiate_options_flags(flags);
     if (flags & NBD_FLAG_C_FIXED_NEWSTYLE) {
         fixedNewstyle = true;
         flags &= ~NBD_FLAG_C_FIXED_NEWSTYLE;
+        client->mode = NBD_MODE_SIMPLE;
     }
     if (flags & NBD_FLAG_C_NO_ZEROES) {
         no_zeroes = true;
@@ -1162,7 +1165,7 @@ static int nbd_negotiate_options(NBDClient *client, Error **errp)
         client->optlen = length;
 
         if (length > NBD_MAX_BUFFER_SIZE) {
-            error_setg(errp, "len (%" PRIu32" ) is larger than max len (%u)",
+            error_setg(errp, "len (%" PRIu32 ") is larger than max len (%u)",
                        length, NBD_MAX_BUFFER_SIZE);
             return -EINVAL;
         }
@@ -1261,13 +1264,13 @@ static int nbd_negotiate_options(NBDClient *client, Error **errp)
             case NBD_OPT_STRUCTURED_REPLY:
                 if (length) {
                     ret = nbd_reject_length(client, false, errp);
-                } else if (client->structured_reply) {
+                } else if (client->mode >= NBD_MODE_STRUCTURED) {
                     ret = nbd_negotiate_send_rep_err(
                         client, NBD_REP_ERR_INVALID, errp,
                         "structured reply already negotiated");
                 } else {
                     ret = nbd_negotiate_send_rep(client, NBD_REP_ACK, errp);
-                    client->structured_reply = true;
+                    client->mode = NBD_MODE_STRUCTURED;
                 }
                 break;
 
@@ -1434,7 +1437,7 @@ static int coroutine_fn nbd_receive_request(NBDClient *client, NBDRequest *reque
     request->type   = lduw_be_p(buf + 6);
     request->cookie = ldq_be_p(buf + 8);
     request->from   = ldq_be_p(buf + 16);
-    request->len    = ldl_be_p(buf + 24);
+    request->len    = (uint32_t)ldl_be_p(buf + 24); /* widen 32 to 64 bits */
 
     trace_nbd_receive_request(magic, request->flags, request->type,
                               request->from, request->len);
@@ -1884,7 +1887,7 @@ static int coroutine_fn nbd_co_send_simple_reply(NBDClient *client,
                                                  NBDRequest *request,
                                                  uint32_t error,
                                                  void *data,
-                                                 size_t len,
+                                                 uint64_t len,
                                                  Error **errp)
 {
     NBDSimpleReply reply;
@@ -1895,7 +1898,10 @@ static int coroutine_fn nbd_co_send_simple_reply(NBDClient *client,
     };
 
     assert(!len || !nbd_err);
-    assert(!client->structured_reply || request->type != NBD_CMD_READ);
+    assert(len <= NBD_MAX_BUFFER_SIZE);
+    assert(client->mode < NBD_MODE_STRUCTURED ||
+           (client->mode == NBD_MODE_STRUCTURED &&
+            request->type != NBD_CMD_READ));
     trace_nbd_co_send_simple_reply(request->cookie, nbd_err,
                                    nbd_err_lookup(nbd_err), len);
     set_be_simple_reply(&reply, nbd_err, request->cookie);
@@ -1951,7 +1957,7 @@ static int coroutine_fn nbd_co_send_chunk_read(NBDClient *client,
                                                NBDRequest *request,
                                                uint64_t offset,
                                                void *data,
-                                               size_t size,
+                                               uint64_t size,
                                                bool final,
                                                Error **errp)
 {
@@ -1963,7 +1969,7 @@ static int coroutine_fn nbd_co_send_chunk_read(NBDClient *client,
         {.iov_base = data, .iov_len = size}
     };
 
-    assert(size);
+    assert(size && size <= NBD_MAX_BUFFER_SIZE);
     trace_nbd_co_send_chunk_read(request->cookie, offset, data, size);
     set_be_chunk(client, iov, 3, final ? NBD_REPLY_FLAG_DONE : 0,
                  NBD_REPLY_TYPE_OFFSET_DATA, request);
@@ -1971,7 +1977,7 @@ static int coroutine_fn nbd_co_send_chunk_read(NBDClient *client,
 
     return nbd_co_send_iov(client, iov, 3, errp);
 }
-/*ebb*/
+
 static int coroutine_fn nbd_co_send_chunk_error(NBDClient *client,
                                                 NBDRequest *request,
                                                 uint32_t error,
@@ -2006,13 +2012,14 @@ static int coroutine_fn nbd_co_send_sparse_read(NBDClient *client,
                                                 NBDRequest *request,
                                                 uint64_t offset,
                                                 uint8_t *data,
-                                                size_t size,
+                                                uint64_t size,
                                                 Error **errp)
 {
     int ret = 0;
     NBDExport *exp = client->exp;
     size_t progress = 0;
 
+    assert(size <= NBD_MAX_BUFFER_SIZE);
     while (progress < size) {
         int64_t pnum;
         int status = blk_co_block_status_above(exp->common.blk, NULL,
@@ -2067,7 +2074,7 @@ static int coroutine_fn nbd_co_send_sparse_read(NBDClient *client,
 }
 
 typedef struct NBDExtentArray {
-    NBDExtent *extents;
+    NBDExtent32 *extents;
     unsigned int nb_alloc;
     unsigned int count;
     uint64_t total_length;
@@ -2080,7 +2087,7 @@ static NBDExtentArray *nbd_extent_array_new(unsigned int nb_alloc)
     NBDExtentArray *ea = g_new0(NBDExtentArray, 1);
 
     ea->nb_alloc = nb_alloc;
-    ea->extents = g_new(NBDExtent, nb_alloc);
+    ea->extents = g_new(NBDExtent32, nb_alloc);
     ea->can_add = true;
 
     return ea;
@@ -2143,7 +2150,7 @@ static int nbd_extent_array_add(NBDExtentArray *ea,
     }
 
     ea->total_length += length;
-    ea->extents[ea->count] = (NBDExtent) {.length = length, .flags = flags};
+    ea->extents[ea->count] = (NBDExtent32) {.length = length, .flags = flags};
     ea->count++;
 
     return 0;
@@ -2310,11 +2317,16 @@ static int coroutine_fn nbd_co_send_bitmap(NBDClient *client,
  * to the client (although the caller may still need to disconnect after
  * reporting the error).
  */
-static int coroutine_fn nbd_co_receive_request(NBDRequestData *req, NBDRequest *request,
+static int coroutine_fn nbd_co_receive_request(NBDRequestData *req,
+                                               NBDRequest *request,
                                                Error **errp)
 {
     NBDClient *client = req->client;
-    int valid_flags;
+    bool check_length = false;
+    bool check_rofs = false;
+    bool allocate_buffer = false;
+    unsigned payload_len = 0;
+    int valid_flags = NBD_CMD_FLAG_FUA;
     int ret;
 
     g_assert(qemu_in_coroutine());
@@ -2326,60 +2338,94 @@ static int coroutine_fn nbd_co_receive_request(NBDRequestData *req, NBDRequest *
 
     trace_nbd_co_receive_request_decode_type(request->cookie, request->type,
                                              nbd_cmd_lookup(request->type));
-
-    if (request->type != NBD_CMD_WRITE) {
-        /* No payload, we are ready to read the next request.  */
-        req->complete = true;
-    }
-
-    if (request->type == NBD_CMD_DISC) {
+    switch (request->type) {
+    case NBD_CMD_DISC:
         /* Special case: we're going to disconnect without a reply,
          * whether or not flags, from, or len are bogus */
+        req->complete = true;
         return -EIO;
-    }
 
-    if (request->type == NBD_CMD_READ || request->type == NBD_CMD_WRITE ||
-        request->type == NBD_CMD_CACHE)
-    {
-        if (request->len > NBD_MAX_BUFFER_SIZE) {
-            error_setg(errp, "len (%" PRIu32" ) is larger than max len (%u)",
-                       request->len, NBD_MAX_BUFFER_SIZE);
-            return -EINVAL;
+    case NBD_CMD_READ:
+        if (client->mode >= NBD_MODE_STRUCTURED) {
+            valid_flags |= NBD_CMD_FLAG_DF;
         }
+        check_length = true;
+        allocate_buffer = true;
+        break;
 
-        if (request->type != NBD_CMD_CACHE) {
-            req->data = blk_try_blockalign(client->exp->common.blk,
-                                           request->len);
-            if (req->data == NULL) {
-                error_setg(errp, "No memory");
-                return -ENOMEM;
-            }
-        }
+    case NBD_CMD_WRITE:
+        payload_len = request->len;
+        check_length = true;
+        allocate_buffer = true;
+        check_rofs = true;
+        break;
+
+    case NBD_CMD_FLUSH:
+        break;
+
+    case NBD_CMD_TRIM:
+        check_rofs = true;
+        break;
+
+    case NBD_CMD_CACHE:
+        check_length = true;
+        break;
+
+    case NBD_CMD_WRITE_ZEROES:
+        valid_flags |= NBD_CMD_FLAG_NO_HOLE | NBD_CMD_FLAG_FAST_ZERO;
+        check_rofs = true;
+        break;
+
+    case NBD_CMD_BLOCK_STATUS:
+        valid_flags |= NBD_CMD_FLAG_REQ_ONE;
+        break;
+
+    default:
+        /* Unrecognized, will fail later */
+        ;
     }
 
-    if (request->type == NBD_CMD_WRITE) {
-        if (nbd_read(client->ioc, req->data, request->len, "CMD_WRITE data",
-                     errp) < 0)
-        {
+    /* Payload and buffer handling. */
+    if (!payload_len) {
+        req->complete = true;
+    }
+    if (check_length && request->len > NBD_MAX_BUFFER_SIZE) {
+        /* READ, WRITE, CACHE */
+        error_setg(errp, "len (%" PRIu64 ") is larger than max len (%u)",
+                   request->len, NBD_MAX_BUFFER_SIZE);
+        return -EINVAL;
+    }
+    if (allocate_buffer) {
+        /* READ, WRITE */
+        req->data = blk_try_blockalign(client->exp->common.blk,
+                                       request->len);
+        if (req->data == NULL) {
+            error_setg(errp, "No memory");
+            return -ENOMEM;
+        }
+    }
+    if (payload_len) {
+        /* WRITE */
+        assert(req->data);
+        ret = nbd_read(client->ioc, req->data, payload_len,
+                       "CMD_WRITE data", errp);
+        if (ret < 0) {
             return -EIO;
         }
         req->complete = true;
-
         trace_nbd_co_receive_request_payload_received(request->cookie,
-                                                      request->len);
+                                                      payload_len);
     }
 
     /* Sanity checks. */
-    if (client->exp->nbdflags & NBD_FLAG_READ_ONLY &&
-        (request->type == NBD_CMD_WRITE ||
-         request->type == NBD_CMD_WRITE_ZEROES ||
-         request->type == NBD_CMD_TRIM)) {
+    if (client->exp->nbdflags & NBD_FLAG_READ_ONLY && check_rofs) {
+        /* WRITE, TRIM, WRITE_ZEROES */
         error_setg(errp, "Export is read-only");
         return -EROFS;
     }
     if (request->from > client->exp->size ||
         request->len > client->exp->size - request->from) {
-        error_setg(errp, "operation past EOF; From: %" PRIu64 ", Len: %" PRIu32
+        error_setg(errp, "operation past EOF; From: %" PRIu64 ", Len: %" PRIu64
                    ", Size: %" PRIu64, request->from, request->len,
                    client->exp->size);
         return (request->type == NBD_CMD_WRITE ||
@@ -2396,14 +2442,6 @@ static int coroutine_fn nbd_co_receive_request(NBDRequestData *req, NBDRequest *
                                               request->len,
                                               client->check_align);
     }
-    valid_flags = NBD_CMD_FLAG_FUA;
-    if (request->type == NBD_CMD_READ && client->structured_reply) {
-        valid_flags |= NBD_CMD_FLAG_DF;
-    } else if (request->type == NBD_CMD_WRITE_ZEROES) {
-        valid_flags |= NBD_CMD_FLAG_NO_HOLE | NBD_CMD_FLAG_FAST_ZERO;
-    } else if (request->type == NBD_CMD_BLOCK_STATUS) {
-        valid_flags |= NBD_CMD_FLAG_REQ_ONE;
-    }
     if (request->flags & ~valid_flags) {
         error_setg(errp, "unsupported flags for command %s (got 0x%x)",
                    nbd_cmd_lookup(request->type), request->flags);
@@ -2423,7 +2461,7 @@ static coroutine_fn int nbd_send_generic_reply(NBDClient *client,
                                                const char *error_msg,
                                                Error **errp)
 {
-    if (client->structured_reply && ret < 0) {
+    if (client->mode >= NBD_MODE_STRUCTURED && ret < 0) {
         return nbd_co_send_chunk_error(client, request, -ret, error_msg, errp);
     } else {
         return nbd_co_send_simple_reply(client, request, ret < 0 ? -ret : 0,
@@ -2441,6 +2479,7 @@ static coroutine_fn int nbd_do_cmd_read(NBDClient *client, NBDRequest *request,
     NBDExport *exp = client->exp;
 
     assert(request->type == NBD_CMD_READ);
+    assert(request->len <= NBD_MAX_BUFFER_SIZE);
 
     /* XXX: NBD Protocol only documents use of FUA with WRITE */
     if (request->flags & NBD_CMD_FLAG_FUA) {
@@ -2451,8 +2490,8 @@ static coroutine_fn int nbd_do_cmd_read(NBDClient *client, NBDRequest *request,
         }
     }
 
-    if (client->structured_reply && !(request->flags & NBD_CMD_FLAG_DF) &&
-        request->len)
+    if (client->mode >= NBD_MODE_STRUCTURED &&
+        !(request->flags & NBD_CMD_FLAG_DF) && request->len)
     {
         return nbd_co_send_sparse_read(client, request, request->from,
                                        data, request->len, errp);
@@ -2464,7 +2503,7 @@ static coroutine_fn int nbd_do_cmd_read(NBDClient *client, NBDRequest *request,
                                       "reading from file failed", errp);
     }
 
-    if (client->structured_reply) {
+    if (client->mode >= NBD_MODE_STRUCTURED) {
         if (request->len) {
             return nbd_co_send_chunk_read(client, request, request->from, data,
                                           request->len, true, errp);
@@ -2491,6 +2530,7 @@ static coroutine_fn int nbd_do_cmd_cache(NBDClient *client, NBDRequest *request,
     NBDExport *exp = client->exp;
 
     assert(request->type == NBD_CMD_CACHE);
+    assert(request->len <= NBD_MAX_BUFFER_SIZE);
 
     ret = blk_co_preadv(exp->common.blk, request->from, request->len,
                         NULL, BDRV_REQ_COPY_ON_READ | BDRV_REQ_PREFETCH);
@@ -2524,6 +2564,7 @@ static coroutine_fn int nbd_handle_request(NBDClient *client,
         if (request->flags & NBD_CMD_FLAG_FUA) {
             flags |= BDRV_REQ_FUA;
         }
+        assert(request->len <= NBD_MAX_BUFFER_SIZE);
         ret = blk_co_pwrite(exp->common.blk, request->from, request->len, data,
                             flags);
         return nbd_send_generic_reply(client, request, ret,
@@ -2567,6 +2608,7 @@ static coroutine_fn int nbd_handle_request(NBDClient *client,
             return nbd_send_generic_reply(client, request, -EINVAL,
                                           "need non-zero length", errp);
         }
+        assert(request->len <= UINT32_MAX);
         if (client->export_meta.count) {
             bool dont_fragment = request->flags & NBD_CMD_FLAG_REQ_ONE;
             int contexts_remaining = client->export_meta.count;
diff --git a/nbd/trace-events b/nbd/trace-events
index f19a4d0db3..f9dccfcfb4 100644
--- a/nbd/trace-events
+++ b/nbd/trace-events
@@ -31,7 +31,7 @@ nbd_client_loop(void) "Doing NBD loop"
 nbd_client_loop_ret(int ret, const char *error) "NBD loop returned %d: %s"
 nbd_client_clear_queue(void) "Clearing NBD queue"
 nbd_client_clear_socket(void) "Clearing NBD socket"
-nbd_send_request(uint64_t from, uint32_t len, uint64_t cookie, uint16_t flags, uint16_t type, const char *name) "Sending request to server: { .from = %" PRIu64", .len = %" PRIu32 ", .cookie = %" PRIu64 ", .flags = 0x%" PRIx16 ", .type = %" PRIu16 " (%s) }"
+nbd_send_request(uint64_t from, uint64_t len, uint64_t cookie, uint16_t flags, uint16_t type, const char *name) "Sending request to server: { .from = %" PRIu64", .len = %" PRIu64 ", .cookie = %" PRIu64 ", .flags = 0x%" PRIx16 ", .type = %" PRIu16 " (%s) }"
 nbd_receive_simple_reply(int32_t error, const char *errname, uint64_t cookie) "Got simple reply: { .error = %" PRId32 " (%s), cookie = %" PRIu64" }"
 nbd_receive_structured_reply_chunk(uint16_t flags, uint16_t type, const char *name, uint64_t cookie, uint32_t length) "Got structured reply chunk: { flags = 0x%" PRIx16 ", type = %d (%s), cookie = %" PRIu64 ", length = %" PRIu32 " }"
 
@@ -60,18 +60,18 @@ nbd_negotiate_options_check_option(uint32_t option, const char *name) "Checking
 nbd_negotiate_begin(void) "Beginning negotiation"
 nbd_negotiate_new_style_size_flags(uint64_t size, unsigned flags) "advertising size %" PRIu64 " and flags 0x%x"
 nbd_negotiate_success(void) "Negotiation succeeded"
-nbd_receive_request(uint32_t magic, uint16_t flags, uint16_t type, uint64_t from, uint32_t len) "Got request: { magic = 0x%" PRIx32 ", .flags = 0x%" PRIx16 ", .type = 0x%" PRIx16 ", from = %" PRIu64 ", len = %" PRIu32 " }"
+nbd_receive_request(uint32_t magic, uint16_t flags, uint16_t type, uint64_t from, uint64_t len) "Got request: { magic = 0x%" PRIx32 ", .flags = 0x%" PRIx16 ", .type = 0x%" PRIx16 ", from = %" PRIu64 ", len = %" PRIu64 " }"
 nbd_blk_aio_attached(const char *name, void *ctx) "Export %s: Attaching clients to AIO context %p"
 nbd_blk_aio_detach(const char *name, void *ctx) "Export %s: Detaching clients from AIO context %p"
-nbd_co_send_simple_reply(uint64_t cookie, uint32_t error, const char *errname, int len) "Send simple reply: cookie = %" PRIu64 ", error = %" PRIu32 " (%s), len = %d"
+nbd_co_send_simple_reply(uint64_t cookie, uint32_t error, const char *errname, uint64_t len) "Send simple reply: cookie = %" PRIu64 ", error = %" PRIu32 " (%s), len = %" PRIu64
 nbd_co_send_chunk_done(uint64_t cookie) "Send structured reply done: cookie = %" PRIu64
-nbd_co_send_chunk_read(uint64_t cookie, uint64_t offset, void *data, size_t size) "Send structured read data reply: cookie = %" PRIu64 ", offset = %" PRIu64 ", data = %p, len = %zu"
-nbd_co_send_chunk_read_hole(uint64_t cookie, uint64_t offset, size_t size) "Send structured read hole reply: cookie = %" PRIu64 ", offset = %" PRIu64 ", len = %zu"
+nbd_co_send_chunk_read(uint64_t cookie, uint64_t offset, void *data, uint64_t size) "Send structured read data reply: cookie = %" PRIu64 ", offset = %" PRIu64 ", data = %p, len = %" PRIu64
+nbd_co_send_chunk_read_hole(uint64_t cookie, uint64_t offset, uint64_t size) "Send structured read hole reply: cookie = %" PRIu64 ", offset = %" PRIu64 ", len = %" PRIu64
 nbd_co_send_extents(uint64_t cookie, unsigned int extents, uint32_t id, uint64_t length, int last) "Send block status reply: cookie = %" PRIu64 ", extents = %u, context = %d (extents cover %" PRIu64 " bytes, last chunk = %d)"
 nbd_co_send_chunk_error(uint64_t cookie, int err, const char *errname, const char *msg) "Send structured error reply: cookie = %" PRIu64 ", error = %d (%s), msg = '%s'"
 nbd_co_receive_request_decode_type(uint64_t cookie, uint16_t type, const char *name) "Decoding type: cookie = %" PRIu64 ", type = %" PRIu16 " (%s)"
-nbd_co_receive_request_payload_received(uint64_t cookie, uint32_t len) "Payload received: cookie = %" PRIu64 ", len = %" PRIu32
-nbd_co_receive_align_compliance(const char *op, uint64_t from, uint32_t len, uint32_t align) "client sent non-compliant unaligned %s request: from=0x%" PRIx64 ", len=0x%" PRIx32 ", align=0x%" PRIx32
+nbd_co_receive_request_payload_received(uint64_t cookie, uint64_t len) "Payload received: cookie = %" PRIu64 ", len = %" PRIu64
+nbd_co_receive_align_compliance(const char *op, uint64_t from, uint64_t len, uint32_t align) "client sent non-compliant unaligned %s request: from=0x%" PRIx64 ", len=0x%" PRIx64 ", align=0x%" PRIx32
 nbd_trip(void) "Reading request"
 
 # client-connection.c
diff --git a/qemu-nbd.c b/qemu-nbd.c
index 30eeb6f3c7..70aa3c487a 100644
--- a/qemu-nbd.c
+++ b/qemu-nbd.c
@@ -295,7 +295,9 @@ static void *show_parts(void *arg)
 static void *nbd_client_thread(void *arg)
 {
     struct NbdClientOpts *opts = arg;
-    NBDExportInfo info = { .request_sizes = false, .name = g_strdup("") };
+    /* TODO: Revisit this if nbd.ko ever gains support for structured reply */
+    NBDExportInfo info = { .request_sizes = false, .name = g_strdup(""),
+                           .mode = NBD_MODE_SIMPLE };
     QIOChannelSocket *sioc;
     int fd = -1;
     int ret = EXIT_FAILURE;
diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc
index d145f08201..95c12577dd 100644
--- a/tests/qemu-iotests/common.rc
+++ b/tests/qemu-iotests/common.rc
@@ -979,10 +979,15 @@ _require_drivers()
 #
 _require_large_file()
 {
-    if ! truncate --size="$1" "$TEST_IMG"; then
+    if [ -z "$TEST_IMG_FILE" ]; then
+        FILENAME="$TEST_IMG"
+    else
+        FILENAME="$TEST_IMG_FILE"
+    fi
+    if ! truncate --size="$1" "$FILENAME"; then
         _notrun "file system on $TEST_DIR does not support large enough files"
     fi
-    rm "$TEST_IMG"
+    rm "$FILENAME"
 }
 
 # Check that a set of devices is available in the QEMU binary
diff --git a/tests/qemu-iotests/tests/nbd-multiconn b/tests/qemu-iotests/tests/nbd-multiconn
index b121f2e363..478a1eaba2 100755
--- a/tests/qemu-iotests/tests/nbd-multiconn
+++ b/tests/qemu-iotests/tests/nbd-multiconn
@@ -142,4 +142,4 @@ if __name__ == '__main__':
 
         iotests.main(supported_fmts=['qcow2'])
     except ImportError:
-        iotests.notrun('libnbd not installed')
+        iotests.notrun('Python bindings to libnbd are not installed')