[10/11] multifd: Zero pages transmission

Commit Message

Juan Quintela Nov. 28, 2022, 10:04 a.m. UTC

This implements the zero page dection and handling.

Signed-off-by: Juan Quintela <[e-mail]>

---

Add comment for offset (dave)
Use local variables for offset/block to have shorter lines
---
 migration/multifd.h |  5 +++++
 migration/multifd.c | 45 +++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 48 insertions(+), 2 deletions(-)

Patch

diff --git a/migration/multifd.h b/migration/multifd.h
index a1b852200d..5931de6f86 100644
--- a/migration/multifd.h
+++ b/migration/multifd.h
@@ -52,6 +52,11 @@  typedef struct {
     uint32_t unused32[1];    /* Reserved for future use */
     uint64_t unused64[3];    /* Reserved for future use */
     char ramblock[256];
+    /*
+     * This array contains the pointers to:
+     *  - normal pages (initial normal_pages entries)
+     *  - zero pages (following zero_pages entries)
+     */
     uint64_t offset[];
 } __attribute__((packed)) MultiFDPacket_t;
 
diff --git a/migration/multifd.c b/migration/multifd.c
index 30cc206190..d3f82dad8a 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -11,6 +11,7 @@ 
  */
 
 #include "qemu/osdep.h"
+#include "qemu/cutils.h"
 #include "qemu/rcu.h"
 #include "exec/target_page.h"
 #include "sysemu/sysemu.h"
@@ -275,6 +276,12 @@  static void multifd_send_fill_packet(MultiFDSendParams *p)
 
         packet->offset[i] = cpu_to_be64(temp);
     }
+    for (i = 0; i < p->zero_num; i++) {
+        /* there are architectures where ram_addr_t is 32 bit */
+        uint64_t temp = p->zero[i];
+
+        packet->offset[p->normal_num + i] = cpu_to_be64(temp);
+    }
 }
 
 static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
@@ -358,6 +365,18 @@  static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
         p->normal[i] = offset;
     }
 
+    for (i = 0; i < p->zero_num; i++) {
+        uint64_t offset = be64_to_cpu(packet->offset[p->normal_num + i]);
+
+        if (offset > (block->used_length - p->page_size)) {
+            error_setg(errp, "multifd: offset too long %" PRIu64
+                       " (max " RAM_ADDR_FMT ")",
+                       offset, block->used_length);
+            return -1;
+        }
+        p->zero[i] = offset;
+    }
+
     return 0;
 }
 
@@ -657,6 +676,12 @@  static void *multifd_send_thread(void *opaque)
 {
     MultiFDSendParams *p = opaque;
     Error *local_err = NULL;
+    /*
+     * older qemu don't understand zero page on multifd channel.  To
+     * have capabilities "false" by default, we need to name it this
+     * way.
+     */
+    bool use_multifd_zero_page = !migrate_use_main_zero_page();
     int ret = 0;
     bool use_zero_copy_send = migrate_use_zero_copy_send();
 
@@ -679,6 +704,7 @@  static void *multifd_send_thread(void *opaque)
         qemu_mutex_lock(&p->mutex);
 
         if (p->pending_job) {
+            RAMBlock *rb = p->pages->block;
             uint64_t packet_num = p->packet_num;
             p->flags = 0;
             if (p->sync_needed) {
@@ -697,8 +723,16 @@  static void *multifd_send_thread(void *opaque)
             }
 
             for (int i = 0; i < p->pages->num; i++) {
-                p->normal[p->normal_num] = p->pages->offset[i];
-                p->normal_num++;
+                uint64_t offset = p->pages->offset[i];
+                if (use_multifd_zero_page &&
+                    buffer_is_zero(rb->host + offset, p->page_size)) {
+                    p->zero[p->zero_num] = offset;
+                    p->zero_num++;
+                    ram_release_page(rb->idstr, offset);
+                } else {
+                    p->normal[p->normal_num] = offset;
+                    p->normal_num++;
+                }
             }
 
             if (p->normal_num) {
@@ -1160,6 +1194,13 @@  static void *multifd_recv_thread(void *opaque)
             }
         }
 
+        for (int i = 0; i < p->zero_num; i++) {
+            void *page = p->host + p->zero[i];
+            if (!buffer_is_zero(page, p->page_size)) {
+                memset(page, 0, p->page_size);
+            }
+        }
+
         if (sync_needed) {
             qemu_sem_post(&multifd_recv_state->sem_sync);
             qemu_sem_wait(&p->sem_sync);