[PATCH 3/3] migration: Pre-fault memory before starting background snasphot

[Andrey Gruzdev]

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().

Signed-off-by: Andrey Gruzdev <andrey.gruzdev@virtuozzo.com>
---
 migration/migration.c |  6 +++++
 migration/ram.c       | 51 +++++++++++++++++++++++++++++++++++++++++++
 migration/ram.h       |  1 +
 3 files changed, 58 insertions(+)

diff --git a/migration/migration.c b/migration/migration.c
index 656d6249a6..496e88cbda 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -3872,6 +3872,12 @@ 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.
+     */
+    ram_write_tracking_prepare();
+
     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 52537f14ac..825eb80030 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1560,6 +1560,57 @@ out:
     return ret;
 }
 
+/*
+ * 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 TARGET_PAGE_SIZE.
+ *
+ * @bs: RAM block to populate
+ */
+volatile int ram_block_populate_pages__tmp;
+static void ram_block_populate_pages(RAMBlock *bs)
+{
+    ram_addr_t offset = 0;
+    int tmp = 0;
+
+    for (char *ptr = (char *) bs->host; offset < bs->used_length;
+            ptr += TARGET_PAGE_SIZE, offset += TARGET_PAGE_SIZE) {
+        /* Try to do it without memory writes */
+        tmp += *(volatile int *) ptr;
+    }
+    /* Create dependency on 'extern volatile int' to avoid optimizing out */
+    ram_block_populate_pages__tmp += 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
  *
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);
 
-- 
2.25.1