[Qemu-devel] [PATCH v4 32/47] postcopy: ram_enable_notify to switch on userfault

[Dr. David Alan Gilbert (git)]

From: "Dr. David Alan Gilbert" <address@hidden>

Signed-off-by: Dr. David Alan Gilbert <address@hidden>
---
 include/migration/migration.h    |  2 ++
 include/migration/postcopy-ram.h |  6 +++++
 postcopy-ram.c                   | 49 +++++++++++++++++++++++++++++++++++++++-
 savevm.c                         |  9 ++++++++
 4 files changed, 65 insertions(+), 1 deletion(-)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index be63c89..b01cc17 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -87,6 +87,8 @@ struct MigrationIncomingState {
         POSTCOPY_RAM_INCOMING_END
     } postcopy_ram_state;
 
+    /* For the kernel to send us notifications */
+    int            userfault_fd;
     QEMUFile *return_path;
     QemuMutex      rp_mutex;    /* We send replies from multiple threads */
     PostcopyPMI    postcopy_pmi;
diff --git a/include/migration/postcopy-ram.h b/include/migration/postcopy-ram.h
index 8f237a2..413b670 100644
--- a/include/migration/postcopy-ram.h
+++ b/include/migration/postcopy-ram.h
@@ -19,6 +19,12 @@
 int postcopy_ram_hosttest(void);
 
 /*
+ * Make all of RAM sensitive to accesses to areas that haven't yet been written
+ * and wire up anything necessary to deal with it.
+ */
+int postcopy_ram_enable_notify(MigrationIncomingState *mis);
+
+/*
  * Initialise postcopy-ram, setting the RAM to a state where we can go into
  * postcopy later; must be called prior to any precopy.
  * called from arch_init's similarly named ram_postcopy_incoming_init
diff --git a/postcopy-ram.c b/postcopy-ram.c
index 8eccf26..925ac77 100644
--- a/postcopy-ram.c
+++ b/postcopy-ram.c
@@ -485,9 +485,51 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState 
*mis)
     return 0;
 }
 
+/*
+ * Mark the given area of RAM as requiring notification to unwritten areas
+ * Used as a  callback on qemu_ram_foreach_block.
+ *   host_addr: Base of area to mark
+ *   offset: Offset in the whole ram arena
+ *   length: Length of the section
+ *   opaque: Unused
+ * Returns 0 on success
+ */
+static int postcopy_ram_sensitise_area(const char *block_name, void *host_addr,
+                                       ram_addr_t offset, ram_addr_t length,
+                                       void *opaque)
+{
+    MigrationIncomingState *mis = opaque;
+    uint64_t tokern[2];
+
+    if (madvise(host_addr, length, MADV_USERFAULT)) {
+        perror("postcopy_ram_sensitise_area madvise");
+        return -1;
+    }
+
+    /* Now tell our userfault_fd that it's responsible for this area */
+    tokern[0] = (uint64_t)(uintptr_t)host_addr | 1; /* 1 means register area */
+    tokern[1] = (uint64_t)(uintptr_t)host_addr + length;
+    if (write(mis->userfault_fd, tokern, 16) != 16) {
+        perror("postcopy_ram_sensitise_area write");
+        madvise(host_addr, length, MADV_NOUSERFAULT);
+        return -1;
+    }
+
+    return 0;
+}
+
+int postcopy_ram_enable_notify(MigrationIncomingState *mis)
+{
+    /* Mark so that we get notified of accesses to unwritten areas */
+    if (qemu_ram_foreach_block(postcopy_ram_sensitise_area, mis)) {
+        return -1;
+    }
+
+    return 0;
+}
+
 #else
 /* No target OS support, stubs just fail */
-
 int postcopy_ram_hosttest(void)
 {
     error_report("postcopy_ram_hosttest: No OS support");
@@ -528,6 +570,11 @@ int postcopy_ram_discard_range(MigrationIncomingState 
*mis, uint8_t *start,
 {
     assert(0);
 }
+
+int postcopy_ram_enable_notify(MigrationIncomingState *mis)
+{
+    assert(0);
+}
 #endif
 
 /* ------------------------------------------------------------------------- */
diff --git a/savevm.c b/savevm.c
index 54bdb26..859c96f 100644
--- a/savevm.c
+++ b/savevm.c
@@ -1304,6 +1304,15 @@ static int 
loadvm_postcopy_ram_handle_listen(MigrationIncomingState *mis)
 
     mis->postcopy_ram_state = POSTCOPY_RAM_INCOMING_LISTENING;
 
+    /*
+     * Sensitise RAM - can now generate requests for blocks that don't exist
+     * However, at this point the CPU shouldn't be running, and the IO
+     * shouldn't be doing anything yet so don't actually expect requests
+     */
+    if (postcopy_ram_enable_notify(mis)) {
+        return -1;
+    }
+
     /* TODO start up the postcopy listening thread */
     return 0;
 }
-- 
1.9.3