[Qemu-devel] [PATCH v10 09/14] rdma: new QEMUFileOps hooks

[mrhines@linux.vnet.ibm.com]

From: "Michael R. Hines" <mrhines@us.ibm.com>

These are the prototypes and implementation of new hooks that
RDMA takes advantage of to perform dynamic page registration.

An optional hook is also introduced for a custom function
to be able to override the default save_page function.

Also included are the prototypes and accessor methods used by
arch_init.c which invoke funtions inside savevm.c to call out
to the hooks that may or may not have been overridden
inside of QEMUFileOps.

Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Chegu Vinod <chegu_vinod@hp.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
Tested-by: Michael R. Hines <mrhines@us.ibm.com>
Signed-off-by: Michael R. Hines <mrhines@us.ibm.com>
---
 include/migration/migration.h |   20 ++++++++++++++
 include/migration/qemu-file.h |   29 ++++++++++++++++++++
 savevm.c                      |   59 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 108 insertions(+)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index 110f4ad..d60c64c 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -21,6 +21,7 @@
 #include "qapi/error.h"
 #include "migration/vmstate.h"
 #include "qapi-types.h"
+#include "exec/cpu-common.h"
 
 struct MigrationParams {
     bool blk;
@@ -132,4 +133,23 @@ int migrate_use_xbzrle(void);
 int64_t migrate_xbzrle_cache_size(void);
 
 int64_t xbzrle_cache_resize(int64_t new_size);
+
+void ram_control_before_iterate(QEMUFile *f, uint64_t flags);
+void ram_control_after_iterate(QEMUFile *f, uint64_t flags);
+void ram_control_load_hook(QEMUFile *f, uint64_t flags);
+
+/* Whenever this is found in the data stream, the flags
+ * will be passed to ram_control_load_hook in the incoming-migration
+ * side. This lets before_ram_iterate/after_ram_iterate add
+ * transport-specific sections to the RAM migration data.
+ */
+#define RAM_SAVE_FLAG_HOOK     0x80
+
+#define RAM_SAVE_CONTROL_NOT_SUPP -1000
+#define RAM_SAVE_CONTROL_DELAYED  -2000
+
+size_t ram_control_save_page(QEMUFile *f, ram_addr_t block_offset,
+                             ram_addr_t offset, size_t size,
+                             int *bytes_sent);
+
 #endif
diff --git a/include/migration/qemu-file.h b/include/migration/qemu-file.h
index 37d1604..0f757fb 100644
--- a/include/migration/qemu-file.h
+++ b/include/migration/qemu-file.h
@@ -23,6 +23,7 @@
  */
 #ifndef QEMU_FILE_H
 #define QEMU_FILE_H 1
+#include "exec/cpu-common.h"
 
 /* This function writes a chunk of data to a file at the given position.
  * The pos argument can be ignored if the file is only being used for
@@ -57,12 +58,40 @@ typedef int (QEMUFileGetFD)(void *opaque);
 typedef ssize_t (QEMUFileWritevBufferFunc)(void *opaque, struct iovec *iov,
                                            int iovcnt, int64_t pos);
 
+/*
+ * This function provides hooks around different
+ * stages of RAM migration.
+ */
+typedef int (QEMURamHookFunc)(QEMUFile *f, void *opaque, uint64_t flags);
+
+/*
+ * Constants used by ram_control_* hooks
+ */
+#define RAM_CONTROL_SETUP    0
+#define RAM_CONTROL_ROUND    1
+#define RAM_CONTROL_HOOK     2
+#define RAM_CONTROL_FINISH   3
+
+/*
+ * This function allows override of where the RAM page
+ * is saved (such as RDMA, for example.)
+ */
+typedef size_t (QEMURamSaveFunc)(QEMUFile *f, void *opaque,
+                               ram_addr_t block_offset,
+                               ram_addr_t offset,
+                               size_t size,
+                               int *bytes_sent);
+
 typedef struct QEMUFileOps {
     QEMUFilePutBufferFunc *put_buffer;
     QEMUFileGetBufferFunc *get_buffer;
     QEMUFileCloseFunc *close;
     QEMUFileGetFD *get_fd;
     QEMUFileWritevBufferFunc *writev_buffer;
+    QEMURamHookFunc *before_ram_iterate;
+    QEMURamHookFunc *after_ram_iterate;
+    QEMURamHookFunc *hook_ram_load;
+    QEMURamSaveFunc *save_page;
 } QEMUFileOps;
 
 QEMUFile *qemu_fopen_ops(void *opaque, const QEMUFileOps *ops);
diff --git a/savevm.c b/savevm.c
index ba307b1..d80af02 100644
--- a/savevm.c
+++ b/savevm.c
@@ -615,6 +615,65 @@ void qemu_fflush(QEMUFile *f)
     }
 }
 
+void ram_control_before_iterate(QEMUFile *f, uint64_t flags)
+{
+    int ret = 0;
+
+    if (f->ops->before_ram_iterate) {
+        ret = f->ops->before_ram_iterate(f, f->opaque, flags);
+        if (ret < 0) {
+            qemu_file_set_error(f, ret);
+        }
+    }
+}
+
+void ram_control_after_iterate(QEMUFile *f, uint64_t flags)
+{
+    int ret = 0;
+
+    if (f->ops->after_ram_iterate) {
+        ret = f->ops->after_ram_iterate(f, f->opaque, flags);
+        if (ret < 0) {
+            qemu_file_set_error(f, ret);
+        }
+    }
+}
+
+void ram_control_load_hook(QEMUFile *f, uint64_t flags)
+{
+    int ret = 0;
+
+    if (f->ops->hook_ram_load) {
+        ret = f->ops->hook_ram_load(f, f->opaque, flags);
+        if (ret < 0) {
+            qemu_file_set_error(f, ret);
+        }
+    } else {
+        qemu_file_set_error(f, ret);
+    }
+}
+
+size_t ram_control_save_page(QEMUFile *f, ram_addr_t block_offset,
+                         ram_addr_t offset, size_t size, int *bytes_sent)
+{
+    if (f->ops->save_page) {
+        int ret = f->ops->save_page(f, f->opaque, block_offset,
+                                    offset, size, bytes_sent);
+
+        if (ret != RAM_SAVE_CONTROL_DELAYED) {
+            if (*bytes_sent > 0) {
+                qemu_update_position(f, *bytes_sent);
+            } else if (ret < 0) {
+                qemu_file_set_error(f, ret);
+            }
+        }
+
+        return ret;
+    }
+
+    return RAM_SAVE_CONTROL_NOT_SUPP;
+}
+
 static void qemu_fill_buffer(QEMUFile *f)
 {
     int len;
-- 
1.7.10.4