migration/multifd: solve zero page causing multiple page faults

Implemented recvbitmap tracking of received pages in multifd.

If the zero page appears for the first time in the recvbitmap, this
page is not checked and set.

If the zero page has already appeared in the recvbitmap, there is no
need to check the data but directly set the data to 0, because it is
unlikely that the zero page will be migrated multiple times.

Signed-off-by: Yuan Liu <yuan1.liu@intel.com>
Reviewed-by: Fabiano Rosas <farosas@suse.de>
Link: https://lore.kernel.org/r/20240401154110.2028453-2-yuan1.liu@intel.com
[peterx: touch up the comment, as the bitmap is used outside postcopy now]
Signed-off-by: Peter Xu <peterx@redhat.com>

6 files changed, 11 insertions, 1 deletions

diff --git a/migration/multifd-zero-page.c b/migration/multifd-zero-page.c
index 1ba38be636..e1b8370f88 100644
--- a/migration/multifd-zero-page.c
+++ b/migration/multifd-zero-page.c
@@ -80,8 +80,10 @@ void multifd_recv_zero_page_process(MultiFDRecvParams *p)
 {
     for (int i = 0; i < p->zero_num; i++) {
         void *page = p->host + p->zero[i];
-        if (!buffer_is_zero(page, p->page_size)) {
+        if (ramblock_recv_bitmap_test_byte_offset(p->block, p->zero[i])) {
             memset(page, 0, p->page_size);
+        } else {
+            ramblock_recv_bitmap_set_offset(p->block, p->zero[i]);
         }
     }
 }
diff --git a/migration/multifd-zlib.c b/migration/multifd-zlib.c
index 99821cd4d5..737a9645d2 100644
--- a/migration/multifd-zlib.c
+++ b/migration/multifd-zlib.c
@@ -284,6 +284,7 @@ static int zlib_recv(MultiFDRecvParams *p, Error **errp)
         int flush = Z_NO_FLUSH;
         unsigned long start = zs->total_out;
 
+        ramblock_recv_bitmap_set_offset(p->block, p->normal[i]);
         if (i == p->normal_num - 1) {
             flush = Z_SYNC_FLUSH;
         }
diff --git a/migration/multifd-zstd.c b/migration/multifd-zstd.c
index 02112255ad..256858df0a 100644
--- a/migration/multifd-zstd.c
+++ b/migration/multifd-zstd.c
@@ -278,6 +278,7 @@ static int zstd_recv(MultiFDRecvParams *p, Error **errp)
     z->in.pos = 0;
 
     for (i = 0; i < p->normal_num; i++) {
+        ramblock_recv_bitmap_set_offset(p->block, p->normal[i]);
         z->out.dst = p->host + p->normal[i];
         z->out.size = p->page_size;
         z->out.pos = 0;
diff --git a/migration/multifd.c b/migration/multifd.c
index 2802afe79d..f317bff077 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -277,6 +277,7 @@ static int nocomp_recv(MultiFDRecvParams *p, Error **errp)
     for (int i = 0; i < p->normal_num; i++) {
         p->iov[i].iov_base = p->host + p->normal[i];
         p->iov[i].iov_len = p->page_size;
+        ramblock_recv_bitmap_set_offset(p->block, p->normal[i]);
     }
     return qio_channel_readv_all(p->c, p->iov, p->normal_num, errp);
 }
diff --git a/migration/ram.c b/migration/ram.c
index daffcd82d4..a975c5af16 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -275,6 +275,10 @@ void ramblock_recv_bitmap_set_range(RAMBlock *rb, void *host_addr,
                       nr);
 }
 
+void ramblock_recv_bitmap_set_offset(RAMBlock *rb, uint64_t byte_offset)
+{
+    set_bit_atomic(byte_offset >> TARGET_PAGE_BITS, rb->receivedmap);
+}
 #define  RAMBLOCK_RECV_BITMAP_ENDING  (0x0123456789abcdefULL)
 
 /*
diff --git a/migration/ram.h b/migration/ram.h
index 08feecaf51..bc0318b834 100644
--- a/migration/ram.h
+++ b/migration/ram.h
@@ -69,6 +69,7 @@ int ramblock_recv_bitmap_test(RAMBlock *rb, void *host_addr);
 bool ramblock_recv_bitmap_test_byte_offset(RAMBlock *rb, uint64_t byte_offset);
 void ramblock_recv_bitmap_set(RAMBlock *rb, void *host_addr);
 void ramblock_recv_bitmap_set_range(RAMBlock *rb, void *host_addr, size_t nr);
+void ramblock_recv_bitmap_set_offset(RAMBlock *rb, uint64_t byte_offset);
 int64_t ramblock_recv_bitmap_send(QEMUFile *file,
                                   const char *block_name);
 bool ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *rb, Error **errp);