diff mbox series

[v2,3/4] migration/rdma: destination: create the return patch after the first accept

Message ID 20210525080552.28259-3-lizhijian@cn.fujitsu.com (mailing list archive)
State New, archived
Headers show
Series [v2,1/4] migration/rdma: cleanup rmda in rdma_start_incoming_migration error path | expand

Commit Message

Li Zhijian May 25, 2021, 8:05 a.m. UTC
destination side:
$ build/qemu-system-x86_64 -enable-kvm -netdev tap,id=hn0,script=/etc/qemu-ifup,downscript=/etc/qemu-ifdown -device e1000,netdev=hn0,mac=50:52:54:00:11:22 -boot c -drive if=none,file=./Fedora-rdma-server-migration.qcow2,id=drive-virtio-disk0 -device virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 -m 2048 -smp 2 -device piix3-usb-uhci -device usb-tablet -monitor stdio -vga qxl -spice streaming-video=filter,port=5902,disable-ticketing -incoming rdma:192.168.1.10:8888
(qemu) migrate_set_capability postcopy-ram on
(qemu)
dest_init RDMA Device opened: kernel name rocep1s0f0 uverbs device name uverbs0, infiniband_verbs class device path /sys/class/infiniband_verbs/uverbs0, infiniband class device path /sys/class/infiniband/rocep1s0f0, transport: (2) Ethernet
Segmentation fault (core dumped)

 (gdb) bt
 #0  qemu_rdma_accept (rdma=0x0) at ../migration/rdma.c:3272
 #1  rdma_accept_incoming_migration (opaque=0x0) at     ../migration/rdma.c:3986
 #2  0x0000563c9e51f02a in aio_dispatch_handler
     (ctx=ctx@entry=0x563ca0606010, node=0x563ca12b2150) at ../util/aio-posix.c:329
 #3  0x0000563c9e51f752 in aio_dispatch_handlers (ctx=0x563ca0606010) at      ../util/aio-posix.c:372
 #4  aio_dispatch (ctx=0x563ca0606010) at ../util/aio-posix.c:382
 #5  0x0000563c9e4f4d9e in aio_ctx_dispatch (source=<optimized out>,      callback=<optimized out>, user_data=<optimized out>)    at ../util/async.c:306
 #6  0x00007fe96ef3fa9f in g_main_context_dispatch () at      /lib64/libglib-2.0.so.0
 #7  0x0000563c9e4ffeb8 in glib_pollfds_poll () at     ../util/main-loop.c:231
 #8  os_host_main_loop_wait (timeout=12188789) at     ../util/main-loop.c:254
 #9  main_loop_wait (nonblocking=nonblocking@entry=0) at     ../util/main-loop.c:530
 #10 0x0000563c9e3c7211 in qemu_main_loop () at     ../softmmu/runstate.c:725
 #11 0x0000563c9dfd46fe in main (argc=<optimized out>, argv=<optimized     out>, envp=<optimized out>) at ../softmmu/main.c:50

The rdma return path will not be created when qemu incoming is starting
since migrate_copy() is false at that moment, then a  NULL return path
rdma was referenced if the user enabled postcopy later.

Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
---
V2: alloc memory for host_port
---
 migration/rdma.c | 32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

Comments

Dr. David Alan Gilbert May 25, 2021, 9:40 a.m. UTC | #1
* Li Zhijian (lizhijian@cn.fujitsu.com) wrote:
> destination side:
> $ build/qemu-system-x86_64 -enable-kvm -netdev tap,id=hn0,script=/etc/qemu-ifup,downscript=/etc/qemu-ifdown -device e1000,netdev=hn0,mac=50:52:54:00:11:22 -boot c -drive if=none,file=./Fedora-rdma-server-migration.qcow2,id=drive-virtio-disk0 -device virtio-blk-pci,bus=pci.0,addr=0x4,drive=drive-virtio-disk0,id=virtio-disk0 -m 2048 -smp 2 -device piix3-usb-uhci -device usb-tablet -monitor stdio -vga qxl -spice streaming-video=filter,port=5902,disable-ticketing -incoming rdma:192.168.1.10:8888
> (qemu) migrate_set_capability postcopy-ram on
> (qemu)
> dest_init RDMA Device opened: kernel name rocep1s0f0 uverbs device name uverbs0, infiniband_verbs class device path /sys/class/infiniband_verbs/uverbs0, infiniband class device path /sys/class/infiniband/rocep1s0f0, transport: (2) Ethernet
> Segmentation fault (core dumped)
> 
>  (gdb) bt
>  #0  qemu_rdma_accept (rdma=0x0) at ../migration/rdma.c:3272
>  #1  rdma_accept_incoming_migration (opaque=0x0) at     ../migration/rdma.c:3986
>  #2  0x0000563c9e51f02a in aio_dispatch_handler
>      (ctx=ctx@entry=0x563ca0606010, node=0x563ca12b2150) at ../util/aio-posix.c:329
>  #3  0x0000563c9e51f752 in aio_dispatch_handlers (ctx=0x563ca0606010) at      ../util/aio-posix.c:372
>  #4  aio_dispatch (ctx=0x563ca0606010) at ../util/aio-posix.c:382
>  #5  0x0000563c9e4f4d9e in aio_ctx_dispatch (source=<optimized out>,      callback=<optimized out>, user_data=<optimized out>)    at ../util/async.c:306
>  #6  0x00007fe96ef3fa9f in g_main_context_dispatch () at      /lib64/libglib-2.0.so.0
>  #7  0x0000563c9e4ffeb8 in glib_pollfds_poll () at     ../util/main-loop.c:231
>  #8  os_host_main_loop_wait (timeout=12188789) at     ../util/main-loop.c:254
>  #9  main_loop_wait (nonblocking=nonblocking@entry=0) at     ../util/main-loop.c:530
>  #10 0x0000563c9e3c7211 in qemu_main_loop () at     ../softmmu/runstate.c:725
>  #11 0x0000563c9dfd46fe in main (argc=<optimized out>, argv=<optimized     out>, envp=<optimized out>) at ../softmmu/main.c:50
> 
> The rdma return path will not be created when qemu incoming is starting
> since migrate_copy() is false at that moment, then a  NULL return path
> rdma was referenced if the user enabled postcopy later.
> 
> Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>

Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>

> ---
> V2: alloc memory for host_port
> ---
>  migration/rdma.c | 32 +++++++++++++++++++++-----------
>  1 file changed, 21 insertions(+), 11 deletions(-)
> 
> diff --git a/migration/rdma.c b/migration/rdma.c
> index 651534e8255..d829d08d076 100644
> --- a/migration/rdma.c
> +++ b/migration/rdma.c
> @@ -316,6 +316,7 @@ typedef struct RDMALocalBlocks {
>  typedef struct RDMAContext {
>      char *host;
>      int port;
> +    char *host_port;
>  
>      RDMAWorkRequestData wr_data[RDMA_WRID_MAX];
>  
> @@ -2392,7 +2393,9 @@ static void qemu_rdma_cleanup(RDMAContext *rdma)
>          rdma->channel = NULL;
>      }
>      g_free(rdma->host);
> +    g_free(rdma->host_port);
>      rdma->host = NULL;
> +    rdma->host_port = NULL;
>  }
>  
>  
> @@ -2648,6 +2651,7 @@ static void *qemu_rdma_data_init(const char *host_port, Error **errp)
>          if (!inet_parse(addr, host_port, NULL)) {
>              rdma->port = atoi(addr->port);
>              rdma->host = g_strdup(addr->host);
> +            rdma->host_port = g_strdup(host_port);
>          } else {
>              ERROR(errp, "bad RDMA migration address '%s'", host_port);
>              g_free(rdma);
> @@ -3276,6 +3280,7 @@ static int qemu_rdma_accept(RDMAContext *rdma)
>                                              .private_data = &cap,
>                                              .private_data_len = sizeof(cap),
>                                           };
> +    RDMAContext *rdma_return_path = NULL;
>      struct rdma_cm_event *cm_event;
>      struct ibv_context *verbs;
>      int ret = -EINVAL;
> @@ -3291,6 +3296,20 @@ static int qemu_rdma_accept(RDMAContext *rdma)
>          goto err_rdma_dest_wait;
>      }
>  
> +    /*
> +     * initialize the RDMAContext for return path for postcopy after first
> +     * connection request reached.
> +     */
> +    if (migrate_postcopy() && !rdma->is_return_path) {
> +        rdma_return_path = qemu_rdma_data_init(rdma->host_port, NULL);
> +        if (rdma_return_path == NULL) {
> +            rdma_ack_cm_event(cm_event);
> +            goto err_rdma_dest_wait;
> +        }
> +
> +        qemu_rdma_return_path_dest_init(rdma_return_path, rdma);
> +    }
> +
>      memcpy(&cap, cm_event->param.conn.private_data, sizeof(cap));
>  
>      network_to_caps(&cap);
> @@ -3406,6 +3425,7 @@ static int qemu_rdma_accept(RDMAContext *rdma)
>  err_rdma_dest_wait:
>      rdma->error_state = ret;
>      qemu_rdma_cleanup(rdma);
> +    g_free(rdma_return_path);
>      return ret;
>  }
>  
> @@ -4048,17 +4068,6 @@ void rdma_start_incoming_migration(const char *host_port, Error **errp)
>  
>      trace_rdma_start_incoming_migration_after_rdma_listen();
>  
> -    /* initialize the RDMAContext for return path */
> -    if (migrate_postcopy()) {
> -        rdma_return_path = qemu_rdma_data_init(host_port, &local_err);
> -
> -        if (rdma_return_path == NULL) {
> -            goto cleanup_rdma;
> -        }
> -
> -        qemu_rdma_return_path_dest_init(rdma_return_path, rdma);
> -    }
> -
>      qemu_set_fd_handler(rdma->channel->fd, rdma_accept_incoming_migration,
>                          NULL, (void *)(intptr_t)rdma);
>      return;
> @@ -4069,6 +4078,7 @@ err:
>      error_propagate(errp, local_err);
>      if (rdma) {
>          g_free(rdma->host);
> +        g_free(rdma->host_port);
>      }
>      g_free(rdma);
>      g_free(rdma_return_path);
> -- 
> 2.30.2
> 
> 
>
diff mbox series

Patch

diff --git a/migration/rdma.c b/migration/rdma.c
index 651534e8255..d829d08d076 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -316,6 +316,7 @@  typedef struct RDMALocalBlocks {
 typedef struct RDMAContext {
     char *host;
     int port;
+    char *host_port;
 
     RDMAWorkRequestData wr_data[RDMA_WRID_MAX];
 
@@ -2392,7 +2393,9 @@  static void qemu_rdma_cleanup(RDMAContext *rdma)
         rdma->channel = NULL;
     }
     g_free(rdma->host);
+    g_free(rdma->host_port);
     rdma->host = NULL;
+    rdma->host_port = NULL;
 }
 
 
@@ -2648,6 +2651,7 @@  static void *qemu_rdma_data_init(const char *host_port, Error **errp)
         if (!inet_parse(addr, host_port, NULL)) {
             rdma->port = atoi(addr->port);
             rdma->host = g_strdup(addr->host);
+            rdma->host_port = g_strdup(host_port);
         } else {
             ERROR(errp, "bad RDMA migration address '%s'", host_port);
             g_free(rdma);
@@ -3276,6 +3280,7 @@  static int qemu_rdma_accept(RDMAContext *rdma)
                                             .private_data = &cap,
                                             .private_data_len = sizeof(cap),
                                          };
+    RDMAContext *rdma_return_path = NULL;
     struct rdma_cm_event *cm_event;
     struct ibv_context *verbs;
     int ret = -EINVAL;
@@ -3291,6 +3296,20 @@  static int qemu_rdma_accept(RDMAContext *rdma)
         goto err_rdma_dest_wait;
     }
 
+    /*
+     * initialize the RDMAContext for return path for postcopy after first
+     * connection request reached.
+     */
+    if (migrate_postcopy() && !rdma->is_return_path) {
+        rdma_return_path = qemu_rdma_data_init(rdma->host_port, NULL);
+        if (rdma_return_path == NULL) {
+            rdma_ack_cm_event(cm_event);
+            goto err_rdma_dest_wait;
+        }
+
+        qemu_rdma_return_path_dest_init(rdma_return_path, rdma);
+    }
+
     memcpy(&cap, cm_event->param.conn.private_data, sizeof(cap));
 
     network_to_caps(&cap);
@@ -3406,6 +3425,7 @@  static int qemu_rdma_accept(RDMAContext *rdma)
 err_rdma_dest_wait:
     rdma->error_state = ret;
     qemu_rdma_cleanup(rdma);
+    g_free(rdma_return_path);
     return ret;
 }
 
@@ -4048,17 +4068,6 @@  void rdma_start_incoming_migration(const char *host_port, Error **errp)
 
     trace_rdma_start_incoming_migration_after_rdma_listen();
 
-    /* initialize the RDMAContext for return path */
-    if (migrate_postcopy()) {
-        rdma_return_path = qemu_rdma_data_init(host_port, &local_err);
-
-        if (rdma_return_path == NULL) {
-            goto cleanup_rdma;
-        }
-
-        qemu_rdma_return_path_dest_init(rdma_return_path, rdma);
-    }
-
     qemu_set_fd_handler(rdma->channel->fd, rdma_accept_incoming_migration,
                         NULL, (void *)(intptr_t)rdma);
     return;
@@ -4069,6 +4078,7 @@  err:
     error_propagate(errp, local_err);
     if (rdma) {
         g_free(rdma->host);
+        g_free(rdma->host_port);
     }
     g_free(rdma);
     g_free(rdma_return_path);