nbd/client: Accept 64-bit block status chunks

Once extended mode is enabled, we need to accept 64-bit status replies
(even for replies that don't exceed a 32-bit length).  It is easier to
normalize narrow replies into wide format so that the rest of our code
only has to handle one width.  Although a server is non-compliant if
it sends a 64-bit reply in compact mode, or a 32-bit reply in extended
mode, it is still easy enough to tolerate these mismatches.

In normal execution, we are only requesting "base:allocation" which
never exceeds 32 bits for flag values. But during testing with
x-dirty-bitmap, we can force qemu to connect to some other context
that might have 64-bit status bit; however, we ignore those upper bits
(other than mapping qemu:allocation-depth into something that
'qemu-img map --output=json' can expose), and since that only affects
testing, we really don't bother with checking whether more than the
two least-significant bits are set.

Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Message-ID: <20230925192229.3186470-22-eblake@redhat.com>

diff --git a/block/nbd.c b/block/nbd.c
index 76461430411d7c22e9f9a6841eeaf751a0b40616..52ebc8b2f535e79c432cfbb69a2c99728ec01ada 100644 (file)
--- a/block/nbd.c
+++ b/block/nbd.c
@@ -615,13 +615,17 @@ 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,
-                                         NBDExtent32 *extent, Error **errp)
+                                         uint8_t *payload, bool wide,
+                                         uint64_t orig_length,
+                                         NBDExtent64 *extent, Error **errp)
 {
     uint32_t context_id;
+    uint32_t count;
+    size_t ext_len = wide ? sizeof(*extent) : sizeof(NBDExtent32);
+    size_t pay_len = sizeof(context_id) + wide * sizeof(count) + ext_len;
 
     /* The server succeeded, so it must have sent [at least] one extent */
-    if (chunk->length < sizeof(context_id) + sizeof(*extent)) {
+    if (chunk->length < pay_len) {
         error_setg(errp, "Protocol error: invalid payload for "
                          "NBD_REPLY_TYPE_BLOCK_STATUS");
         return -EINVAL;
@@ -636,8 +640,15 @@ static int nbd_parse_blockstatus_payload(BDRVNBDState *s,
         return -EINVAL;
     }
 
-    extent->length = payload_advance32(&payload);
-    extent->flags = payload_advance32(&payload);
+    if (wide) {
+        count = payload_advance32(&payload);
+        extent->length = payload_advance64(&payload);
+        extent->flags = payload_advance64(&payload);
+    } else {
+        count = 0;
+        extent->length = payload_advance32(&payload);
+        extent->flags = payload_advance32(&payload);
+    }
 
     if (extent->length == 0) {
         error_setg(errp, "Protocol error: server sent status chunk with "
@@ -658,7 +669,7 @@ static int nbd_parse_blockstatus_payload(BDRVNBDState *s,
      * (always a safe status, even if it loses information).
      */
     if (s->info.min_block && !QEMU_IS_ALIGNED(extent->length,
-                                                   s->info.min_block)) {
+                                              s->info.min_block)) {
         trace_nbd_parse_blockstatus_compliance("extent length is unaligned");
         if (extent->length > s->info.min_block) {
             extent->length = QEMU_ALIGN_DOWN(extent->length,
@@ -672,13 +683,15 @@ static int nbd_parse_blockstatus_payload(BDRVNBDState *s,
     /*
      * We used NBD_CMD_FLAG_REQ_ONE, so the server should not have
      * sent us any more than one extent, nor should it have included
-     * status beyond our request in that extent. However, it's easy
-     * enough to ignore the server's noncompliance without killing the
+     * status beyond our request in that extent. Furthermore, a wide
+     * server should have replied with an accurate count (we left
+     * count at 0 for a narrow server).  However, it's easy enough to
+     * ignore the server's noncompliance without killing the
      * connection; just ignore trailing extents, and clamp things to
      * the length of our request.
      */
-    if (chunk->length > sizeof(context_id) + sizeof(*extent)) {
-        trace_nbd_parse_blockstatus_compliance("more than one extent");
+    if (count != wide || chunk->length > pay_len) {
+        trace_nbd_parse_blockstatus_compliance("unexpected extent count");
     }
     if (extent->length > orig_length) {
         extent->length = orig_length;
@@ -1124,7 +1137,7 @@ 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, NBDExtent32 *extent,
+                                 uint64_t length, NBDExtent64 *extent,
                                  int *request_ret, Error **errp)
 {
     NBDReplyChunkIter iter;
@@ -1137,11 +1150,17 @@ nbd_co_receive_blockstatus_reply(BDRVNBDState *s, uint64_t cookie,
     NBD_FOREACH_REPLY_CHUNK(s, iter, cookie, false, NULL, &reply, &payload) {
         int ret;
         NBDStructuredReplyChunk *chunk = &reply.structured;
+        bool wide;
 
         assert(nbd_reply_is_structured(&reply));
 
         switch (chunk->type) {
+        case NBD_REPLY_TYPE_BLOCK_STATUS_EXT:
         case NBD_REPLY_TYPE_BLOCK_STATUS:
+            wide = chunk->type == NBD_REPLY_TYPE_BLOCK_STATUS_EXT;
+            if ((s->info.mode >= NBD_MODE_EXTENDED) != wide) {
+                trace_nbd_extended_headers_compliance("block_status");
+            }
             if (received) {
                 nbd_channel_error(s, -EINVAL);
                 error_setg(&local_err, "Several BLOCK_STATUS chunks in reply");
@@ -1149,9 +1168,9 @@ nbd_co_receive_blockstatus_reply(BDRVNBDState *s, uint64_t cookie,
             }
             received = true;
 
-            ret = nbd_parse_blockstatus_payload(s, &reply.structured,
-                                                payload, length, extent,
-                                                &local_err);
+            ret = nbd_parse_blockstatus_payload(
+                s, &reply.structured, payload, wide,
+                length, extent, &local_err);
             if (ret < 0) {
                 nbd_channel_error(s, ret);
                 nbd_iter_channel_error(&iter, ret, &local_err);
@@ -1381,7 +1400,7 @@ static int coroutine_fn GRAPH_RDLOCK nbd_client_co_block_status(
         int64_t *pnum, int64_t *map, BlockDriverState **file)
 {
     int ret, request_ret;
-    NBDExtent32 extent = { 0 };
+    NBDExtent64 extent = { 0 };
     BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
     Error *local_err = NULL;
 

diff --git a/block/trace-events b/block/trace-events
index 925aa554bbf8c5bdc64e57a66e101eb7008ab48b..8e789e1f12fe5781868b43b041acbe773c95fbd0 100644 (file)
--- a/block/trace-events
+++ b/block/trace-events
@@ -166,6 +166,7 @@ iscsi_xcopy(void *src_lun, uint64_t src_off, void *dst_lun, uint64_t dst_off, ui
 # nbd.c
 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_extended_headers_compliance(const char *type) "server sent non-compliant %s chunk not matching choice of extended headers"
 nbd_read_reply_entry_fail(int ret, const char *err) "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'"