migration/rdma: Simplify the function that saves a page
When we sent a page through QEMUFile hooks (RDMA) there are three
posiblities:
- We are not using RDMA. return RAM_SAVE_CONTROL_DELAYED and
control_save_page() returns false to let anything else to proceed.
- There is one error but we are using RDMA. Then we return a negative
value, control_save_page() needs to return true.
- Everything goes well and RDMA start the sent of the page
asynchronously. It returns RAM_SAVE_CONTROL_DELAYED and we need to
return 1 for ram_save_page_legacy.
Clear?
I know, I know, the interface is as bad as it gets. I think that now
it is a bit clearer, but this needs to be done some other way.
Reviewed-by: Leonardo Bras <leobras@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Message-Id: <20230515195709.63843-16-quintela@redhat.com>
diff --git a/migration/qemu-file.c b/migration/qemu-file.c
index 5c43fa3..5e8207d 100644
--- a/migration/qemu-file.c
+++ b/migration/qemu-file.c
@@ -322,14 +322,14 @@
}
}
-size_t ram_control_save_page(QEMUFile *f, ram_addr_t block_offset,
- ram_addr_t offset, size_t size,
- uint64_t *bytes_sent)
+int ram_control_save_page(QEMUFile *f, ram_addr_t block_offset,
+ ram_addr_t offset, size_t size)
{
if (f->hooks && f->hooks->save_page) {
- int ret = f->hooks->save_page(f, block_offset,
- offset, size, bytes_sent);
-
+ int ret = f->hooks->save_page(f, block_offset, offset, size);
+ /*
+ * RAM_SAVE_CONTROL_* are negative values
+ */
if (ret != RAM_SAVE_CONTROL_DELAYED &&
ret != RAM_SAVE_CONTROL_NOT_SUPP) {
if (ret < 0) {
diff --git a/migration/qemu-file.h b/migration/qemu-file.h
index 57b00c8..03e718c 100644
--- a/migration/qemu-file.h
+++ b/migration/qemu-file.h
@@ -49,11 +49,10 @@
* This function allows override of where the RAM page
* is saved (such as RDMA, for example.)
*/
-typedef size_t (QEMURamSaveFunc)(QEMUFile *f,
- ram_addr_t block_offset,
- ram_addr_t offset,
- size_t size,
- uint64_t *bytes_sent);
+typedef int (QEMURamSaveFunc)(QEMUFile *f,
+ ram_addr_t block_offset,
+ ram_addr_t offset,
+ size_t size);
typedef struct QEMUFileHooks {
QEMURamHookFunc *before_ram_iterate;
@@ -142,9 +141,8 @@
#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,
- uint64_t *bytes_sent);
+int ram_control_save_page(QEMUFile *f, ram_addr_t block_offset,
+ ram_addr_t offset, size_t size);
QIOChannel *qemu_file_get_ioc(QEMUFile *file);
#endif
diff --git a/migration/ram.c b/migration/ram.c
index c6238f7..99cff59 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1186,23 +1186,19 @@
static bool control_save_page(PageSearchStatus *pss, RAMBlock *block,
ram_addr_t offset, int *pages)
{
- uint64_t bytes_xmit = 0;
int ret;
- *pages = -1;
ret = ram_control_save_page(pss->pss_channel, block->offset, offset,
- TARGET_PAGE_SIZE, &bytes_xmit);
+ TARGET_PAGE_SIZE);
if (ret == RAM_SAVE_CONTROL_NOT_SUPP) {
return false;
}
- if (bytes_xmit) {
- *pages = 1;
- }
-
if (ret == RAM_SAVE_CONTROL_DELAYED) {
+ *pages = 1;
return true;
}
+ *pages = ret;
return true;
}
diff --git a/migration/rdma.c b/migration/rdma.c
index 9007261..5748c90 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -3240,13 +3240,12 @@
*
* @size : Number of bytes to transfer
*
- * @bytes_sent : User-specificed pointer to indicate how many bytes were
+ * @pages_sent : User-specificed pointer to indicate how many pages were
* sent. Usually, this will not be more than a few bytes of
* the protocol because most transfers are sent asynchronously.
*/
-static size_t qemu_rdma_save_page(QEMUFile *f,
- ram_addr_t block_offset, ram_addr_t offset,
- size_t size, uint64_t *bytes_sent)
+static int qemu_rdma_save_page(QEMUFile *f, ram_addr_t block_offset,
+ ram_addr_t offset, size_t size)
{
QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f));
RDMAContext *rdma;
@@ -3279,18 +3278,6 @@
}
/*
- * We always return 1 bytes because the RDMA
- * protocol is completely asynchronous. We do not yet know
- * whether an identified chunk is zero or not because we're
- * waiting for other pages to potentially be merged with
- * the current chunk. So, we have to call qemu_update_position()
- * later on when the actual write occurs.
- */
- if (bytes_sent) {
- *bytes_sent = 1;
- }
-
- /*
* Drain the Completion Queue if possible, but do not block,
* just poll.
*
