Functions that use an Error **errp parameter to return errors should
not also report them to the user, because reporting is the caller's
job.  When the caller does, the error is reported twice.  When it
doesn't (because it recovered from the error), there is no error to
report, i.e. the report is bogus.

qemu_rdma_exchange_send() violates this principle: it calls
error_report() via callback qemu_rdma_reg_whole_ram_blocks().  I
elected not to investigate how callers handle the error, i.e. precise
impact is not known.

Clean this up by converting the callback to Error.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
---
 migration/rdma.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/migration/rdma.c b/migration/rdma.c
index 34f05dd541..f1cd659a1f 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -518,7 +518,8 @@ static void network_to_result(RDMARegisterResult *result)
 static int qemu_rdma_exchange_send(RDMAContext *rdma, RDMAControlHeader *head,
                                    uint8_t *data, RDMAControlHeader *resp,
                                    int *resp_idx,
-                                   int (*callback)(RDMAContext *rdma),
+                                   int (*callback)(RDMAContext *rdma,
+                                                   Error **errp),
                                    Error **errp);
 
 static inline uint64_t ram_chunk_index(const uint8_t *start,
@@ -1175,7 +1176,7 @@ static void qemu_rdma_advise_prefetch_mr(struct ibv_pd *pd, uint64_t addr,
 #endif
 }
 
-static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma)
+static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma, Error **errp)
 {
     int i;
     RDMALocalBlocks *local = &rdma->local_ram_blocks;
@@ -1210,16 +1211,16 @@ static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma)
         }
 
         if (!local->block[i].mr) {
-            perror("Failed to register local dest ram block!");
-            break;
+            error_setg_errno(errp, errno,
+                             "Failed to register local dest ram block!");
+            goto err;
         }
         rdma->total_registrations++;
     }
 
-    if (i >= local->nb_blocks) {
-        return 0;
-    }
+    return 0;
 
+err:
     for (i--; i >= 0; i--) {
         ibv_dereg_mr(local->block[i].mr);
         local->block[i].mr = NULL;
@@ -1878,7 +1879,8 @@ static void qemu_rdma_move_header(RDMAContext *rdma, int idx,
 static int qemu_rdma_exchange_send(RDMAContext *rdma, RDMAControlHeader *head,
                                    uint8_t *data, RDMAControlHeader *resp,
                                    int *resp_idx,
-                                   int (*callback)(RDMAContext *rdma),
+                                   int (*callback)(RDMAContext *rdma,
+                                                   Error **errp),
                                    Error **errp)
 {
     int ret;
@@ -1934,9 +1936,8 @@ static int qemu_rdma_exchange_send(RDMAContext *rdma, RDMAControlHeader *head,
     if (resp) {
         if (callback) {
             trace_qemu_rdma_exchange_send_issue_callback();
-            ret = callback(rdma);
+            ret = callback(rdma, errp);
             if (ret < 0) {
-                error_setg(errp, "FIXME temporary error message");
                 return -1;
             }
         }
@@ -3633,10 +3634,9 @@ static int qemu_rdma_registration_handle(QEMUFile *f)
             }
 
             if (rdma->pin_all) {
-                ret = qemu_rdma_reg_whole_ram_blocks(rdma);
+                ret = qemu_rdma_reg_whole_ram_blocks(rdma, &err);
                 if (ret < 0) {
-                    error_report("rdma migration: error dest "
-                                    "registering ram blocks");
+                    error_report_err(err);
                     goto err;
                 }
             }
-- 
2.41.0

On 18/09/2023 22:41, Markus Armbruster wrote:
> Functions that use an Error **errp parameter to return errors should
> not also report them to the user, because reporting is the caller's
> job.  When the caller does, the error is reported twice.  When it
> doesn't (because it recovered from the error), there is no error to
> report, i.e. the report is bogus.
> 
> qemu_rdma_exchange_send() violates this principle: it calls
> error_report() via callback qemu_rdma_reg_whole_ram_blocks().  I
> elected not to investigate how callers handle the error, i.e. precise
> impact is not known.
> 
> Clean this up by converting the callback to Error.
> 
> Signed-off-by: Markus Armbruster<armbru@redhat.com>

Reviewed-by: Li Zhijian <lizhijian@fujitsu.com>