[Qemu-devel] [PATCH v8 34/54] postcopy: ram_enable_notify to switch on userfault

["Dr. David Alan Gilbert (git)" <dgilbert@redhat.com>]

From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>

Mark the area of RAM as 'userfault'
Start up a fault-thread to handle any userfaults we might receive
from it (to be filled in later)

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Juan Quintela <quintela@redhat.com>
---
 include/migration/migration.h    |  3 ++
 include/migration/postcopy-ram.h |  6 ++++
 migration/postcopy-ram.c         | 68 ++++++++++++++++++++++++++++++++++++++++
 migration/savevm.c               |  9 ++++++
 4 files changed, 86 insertions(+)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index 321ad1e..aecf284 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -86,6 +86,9 @@ struct MigrationIncomingState {
      */
     QemuEvent main_thread_load_event;
 
+    QemuThread     fault_thread;
+    QemuSemaphore  fault_thread_sem;
+
     /* For the kernel to send us notifications */
     int       userfault_fd;
     QEMUFile *to_src_file;
diff --git a/include/migration/postcopy-ram.h b/include/migration/postcopy-ram.h
index 9d98f7a..9d037ff 100644
--- a/include/migration/postcopy-ram.h
+++ b/include/migration/postcopy-ram.h
@@ -17,6 +17,12 @@
 bool postcopy_ram_supported_by_host(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 ram.c's similarly named ram_postcopy_incoming_init
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 15ac820..e89a99e 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -275,6 +275,69 @@ 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: MigrationIncomingState pointer
+ * Returns 0 on success
+ */
+static int ram_block_enable_notify(const char *block_name, void *host_addr,
+                                   ram_addr_t offset, ram_addr_t length,
+                                   void *opaque)
+{
+    MigrationIncomingState *mis = opaque;
+    struct uffdio_register reg_struct;
+
+    reg_struct.range.start = (uintptr_t)host_addr;
+    reg_struct.range.len = length;
+    reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
+
+    /* Now tell our userfault_fd that it's responsible for this area */
+    if (ioctl(mis->userfault_fd, UFFDIO_REGISTER, &reg_struct)) {
+        error_report("%s userfault register: %s", __func__, strerror(errno));
+        return -1;
+    }
+
+    return 0;
+}
+
+/*
+ * Handle faults detected by the USERFAULT markings
+ */
+static void *postcopy_ram_fault_thread(void *opaque)
+{
+    MigrationIncomingState *mis = opaque;
+
+    fprintf(stderr, "postcopy_ram_fault_thread\n");
+    /* TODO: In later patch */
+    qemu_sem_post(&mis->fault_thread_sem);
+    while (1) {
+        /* TODO: In later patch */
+    }
+
+    return NULL;
+}
+
+int postcopy_ram_enable_notify(MigrationIncomingState *mis)
+{
+    /* Create the fault handler thread and wait for it to be ready */
+    qemu_sem_init(&mis->fault_thread_sem, 0);
+    qemu_thread_create(&mis->fault_thread, "postcopy/fault",
+                       postcopy_ram_fault_thread, mis, QEMU_THREAD_JOINABLE);
+    qemu_sem_wait(&mis->fault_thread_sem);
+    qemu_sem_destroy(&mis->fault_thread_sem);
+
+    /* Mark so that we get notified of accesses to unwritten areas */
+    if (qemu_ram_foreach_block(ram_block_enable_notify, mis)) {
+        return -1;
+    }
+
+    return 0;
+}
+
 #else
 /* No target OS support, stubs just fail */
 bool postcopy_ram_supported_by_host(void)
@@ -299,6 +362,11 @@ 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/migration/savevm.c b/migration/savevm.c
index 11bf172..4072912 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -1379,6 +1379,15 @@ static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis)
         return -1;
     }
 
+    /*
+     * 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;
 }
-- 
2.5.0