migration: Pre-fault memory before starting background snasphot

This commit solves the issue with userfault_fd WP feature that
background snapshot is based on. For any never poluated or discarded
memory page, the UFFDIO_WRITEPROTECT ioctl() would skip updating
PTE for that page, thereby loosing WP setting for it.

So we need to pre-fault pages for each RAM block to be protected
before making a userfault_fd wr-protect ioctl().

Fixes: 278e2f551a095b234de74dca9c214d5502a1f72c (migration: support
  UFFD write fault processing in ram_save_iterate())
Signed-off-by: Andrey Gruzdev <andrey.gruzdev@virtuozzo.com>
Reported-by: David Hildenbrand <david@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210401092226.102804-4-andrey.gruzdev@virtuozzo.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
dgilbert:
  Bodged ifdef __linux__ on ram_write_tracking_prepare, should really
      go in a stub

3 files changed, 58 insertions, 0 deletions

diff --git a/migration/migration.c b/migration/migration.c
index be4729e7c8..8ca034136b 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -3827,6 +3827,14 @@ static void *bg_migration_thread(void *opaque)
 
     update_iteration_initial_status(s);
 
+    /*
+     * Prepare for tracking memory writes with UFFD-WP - populate
+     * RAM pages before protecting.
+     */
+#ifdef __linux__
+    ram_write_tracking_prepare();
+#endif
+
     qemu_savevm_state_header(s->to_dst_file);
     qemu_savevm_state_setup(s->to_dst_file);
 
diff --git a/migration/ram.c b/migration/ram.c
index 40e78952ad..7e2bc0fdd3 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1561,6 +1561,55 @@ out:
 }
 
 /*
+ * ram_block_populate_pages: populate memory in the RAM block by reading
+ *   an integer from the beginning of each page.
+ *
+ * Since it's solely used for userfault_fd WP feature, here we just
+ *   hardcode page size to qemu_real_host_page_size.
+ *
+ * @bs: RAM block to populate
+ */
+static void ram_block_populate_pages(RAMBlock *bs)
+{
+    char *ptr = (char *) bs->host;
+
+    for (ram_addr_t offset = 0; offset < bs->used_length;
+            offset += qemu_real_host_page_size) {
+        char tmp = *(ptr + offset);
+
+        /* Don't optimize the read out */
+        asm volatile("" : "+r" (tmp));
+    }
+}
+
+/*
+ * ram_write_tracking_prepare: prepare for UFFD-WP memory tracking
+ */
+void ram_write_tracking_prepare(void)
+{
+    RAMBlock *bs;
+
+    RCU_READ_LOCK_GUARD();
+
+    RAMBLOCK_FOREACH_NOT_IGNORED(bs) {
+        /* Nothing to do with read-only and MMIO-writable regions */
+        if (bs->mr->readonly || bs->mr->rom_device) {
+            continue;
+        }
+
+        /*
+         * Populate pages of the RAM block before enabling userfault_fd
+         * write protection.
+         *
+         * This stage is required since ioctl(UFFDIO_WRITEPROTECT) with
+         * UFFDIO_WRITEPROTECT_MODE_WP mode setting would silently skip
+         * pages with pte_none() entries in page table.
+         */
+        ram_block_populate_pages(bs);
+    }
+}
+
+/*
  * ram_write_tracking_start: start UFFD-WP memory tracking
  *
  * Returns 0 for success or negative value in case of error
diff --git a/migration/ram.h b/migration/ram.h
index 6378bb3ebc..4833e9fd5b 100644
--- a/migration/ram.h
+++ b/migration/ram.h
@@ -82,6 +82,7 @@ void colo_incoming_start_dirty_log(void);
 /* Background snapshot */
 bool ram_write_tracking_available(void);
 bool ram_write_tracking_compatible(void);
+void ram_write_tracking_prepare(void);
 int ram_write_tracking_start(void);
 void ram_write_tracking_stop(void);