[Qemu-devel] [PATCH v5 28/45] postcopy: Incoming initialisation

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

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

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
 arch_init.c                      |  11 ++++
 include/migration/migration.h    |   3 +
 include/migration/postcopy-ram.h |  12 ++++
 migration/migration.c            |   1 +
 migration/postcopy-ram.c         | 119 ++++++++++++++++++++++++++++++++++++++-
 savevm.c                         |   4 ++
 trace-events                     |   2 +
 7 files changed, 151 insertions(+), 1 deletion(-)

diff --git a/arch_init.c b/arch_init.c
index 21e7ebe..d2c4457 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -1363,6 +1363,17 @@ void ram_handle_compressed(void *host, uint8_t ch, uint64_t size)
     }
 }
 
+/*
+ * Allocate data structures etc needed by incoming migration with postcopy-ram
+ * postcopy-ram's similarly names postcopy_ram_incoming_init does the work
+ */
+int ram_postcopy_incoming_init(MigrationIncomingState *mis)
+{
+    size_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS;
+
+    return postcopy_ram_incoming_init(mis, ram_pages);
+}
+
 static int ram_load(QEMUFile *f, void *opaque, int version_id)
 {
     int flags = 0, ret = 0;
diff --git a/include/migration/migration.h b/include/migration/migration.h
index e749f4c..d09561e 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -84,6 +84,8 @@ struct MigrationIncomingState {
 
     PostcopyState postcopy_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;
@@ -206,6 +208,7 @@ int ram_postcopy_send_discard_bitmap(MigrationState *ms);
 /* For incoming postcopy discard */
 int ram_discard_range(MigrationIncomingState *mis, const char *block_name,
                       uint64_t start, uint64_t end);
+int ram_postcopy_incoming_init(MigrationIncomingState *mis);
 
 /**
  * @migrate_add_blocker - prevent migration from proceeding
diff --git a/include/migration/postcopy-ram.h b/include/migration/postcopy-ram.h
index 1fec1c1..305c26b 100644
--- a/include/migration/postcopy-ram.h
+++ b/include/migration/postcopy-ram.h
@@ -19,6 +19,18 @@
 bool postcopy_ram_supported_by_host(void);
 
 /*
+ * 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
+ */
+int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages);
+
+/*
+ * At the end of a migration where postcopy_ram_incoming_init was called.
+ */
+int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis);
+
+/*
  * In 'advise' mode record that a page has been received.
  */
 void postcopy_hook_early_receive(MigrationIncomingState *mis,
diff --git a/migration/migration.c b/migration/migration.c
index 850fe1a..b1ad7b1 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -88,6 +88,7 @@ MigrationIncomingState *migration_incoming_state_new(QEMUFile* f)
 
 void migration_incoming_state_destroy(void)
 {
+    postcopy_pmi_destroy(mis_current);
     loadvm_free_handlers(mis_current);
     g_free(mis_current);
     mis_current = NULL;
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 391e9c6..dbe1892 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -74,7 +74,6 @@ struct PostcopyDiscardState {
 /* the postcopy phase, there is no such guarantee during precopy.  We     */
 /* could boil this down to only holding one bit per-host page, but we lose*/
 /* sanity checking that we really do get whole host-pages from the source.*/
-__attribute__ (( unused )) /* Until later in patch series */
 static void postcopy_pmi_init(MigrationIncomingState *mis, size_t ram_pages)
 {
     unsigned int tpb = qemu_target_page_bits();
@@ -392,6 +391,113 @@ int postcopy_ram_discard_range(MigrationIncomingState *mis, uint8_t *start,
     return 0;
 }
 
+/*
+ * Setup an area of RAM so that it *can* be used for postcopy later; this
+ * must be done right at the start prior to pre-copy.
+ * opaque should be the MIS.
+ */
+static int init_area(const char *block_name, void *host_addr,
+                     ram_addr_t offset, ram_addr_t length, void *opaque)
+{
+    MigrationIncomingState *mis = opaque;
+
+    trace_postcopy_init_area(block_name, host_addr, offset, length);
+
+    /*
+     * We need the whole of RAM to be truly empty for postcopy, so things
+     * like ROMs and any data tables built during init must be zero'd
+     * - we're going to get the copy from the source anyway.
+     * (Precopy will just overwrite this data, so doesn't need the discard)
+     */
+    if (postcopy_ram_discard_range(mis, host_addr, (host_addr + length - 1))) {
+        return -1;
+    }
+
+    /*
+     * We also need the area to be normal 4k pages, not huge pages
+     * (otherwise we can't be sure we can atopically place the
+     * 4k page in later).  THP might come along and map a 2MB page
+     * and when it's partially accessed in precopy it might not break
+     * it down, but leave a 2MB zero'd page.
+     */
+#ifdef MADV_NOHUGEPAGE
+    if (madvise(host_addr, length, MADV_NOHUGEPAGE)) {
+        perror("init_area: NOHUGEPAGE");
+        return -1;
+    }
+#endif
+
+    return 0;
+}
+
+/*
+ * At the end of migration, undo the effects of init_area
+ * opaque should be the MIS.
+ */
+static int cleanup_area(const char *block_name, void *host_addr,
+                        ram_addr_t offset, ram_addr_t length, void *opaque)
+{
+    MigrationIncomingState *mis = opaque;
+    struct uffdio_range range_struct;
+    trace_postcopy_cleanup_area(block_name, host_addr, offset, length);
+
+    /*
+     * We turned off hugepage for the precopy stage with postcopy enabled
+     * we can turn it back on now.
+     */
+#ifdef MADV_HUGEPAGE
+    if (madvise(host_addr, length, MADV_HUGEPAGE)) {
+        perror("cleanup_area: HUGEPAGE");
+        return -1;
+    }
+#endif
+
+    /*
+     * We can also turn off userfault now since we should have all the
+     * pages.   It can be useful to leave it on to debug postcopy
+     * if you're not sure it's always getting every page.
+     */
+    range_struct.start = (uint64_t)(uintptr_t)host_addr;
+    range_struct.len = (uint64_t)length;
+
+    if (ioctl(mis->userfault_fd, UFFDIO_UNREGISTER, &range_struct)) {
+        perror("cleanup_area: userfault unregister");
+
+        return -1;
+    }
+
+    return 0;
+}
+
+/*
+ * 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
+ */
+int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages)
+{
+    postcopy_pmi_init(mis, ram_pages);
+
+    if (qemu_ram_foreach_block(init_area, mis)) {
+        return -1;
+    }
+
+    return 0;
+}
+
+/*
+ * At the end of a migration where postcopy_ram_incoming_init was called.
+ */
+int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
+{
+    /* TODO: Join the fault thread once we're sure it will exit */
+    if (qemu_ram_foreach_block(cleanup_area, mis)) {
+        return -1;
+    }
+
+    return 0;
+}
+
 #else
 /* No target OS support, stubs just fail */
 
@@ -408,6 +514,17 @@ void postcopy_hook_early_receive(MigrationIncomingState *mis,
     /* We don't support postcopy so don't care */
 }
 
+int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages)
+{
+    error_report("postcopy_ram_incoming_init: No OS support");
+    return -1;
+}
+
+int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
+{
+    assert(0);
+}
+
 void postcopy_pmi_destroy(MigrationIncomingState *mis)
 {
     /* Called in normal cleanup path - so it's OK */
diff --git a/savevm.c b/savevm.c
index 2589b8c..6857660 100644
--- a/savevm.c
+++ b/savevm.c
@@ -1186,6 +1186,10 @@ static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis,
         return -1;
     }
 
+    if (ram_postcopy_incoming_init(mis)) {
+        return -1;
+    }
+
     postcopy_state_set(mis, POSTCOPY_INCOMING_ADVISE);
 
     return 0;
diff --git a/trace-events b/trace-events
index f985117..59dea4c 100644
--- a/trace-events
+++ b/trace-events
@@ -1481,6 +1481,8 @@ rdma_start_outgoing_migration_after_rdma_source_init(void) ""
 
 # migration/postcopy-ram.c
 postcopy_discard_send_finish(const char *ramblock, int nwords, int ncmds) "%s mask words sent=%d in %d commands"
+postcopy_cleanup_area(const char *ramblock, void *host_addr, size_t offset, size_t length) "%s: %p offset=%zx length=%zx"
+postcopy_init_area(const char *ramblock, void *host_addr, size_t offset, size_t length) "%s: %p offset=%zx length=%zx"
 
 # kvm-all.c
 kvm_ioctl(int type, void *arg) "type 0x%x, arg %p"
-- 
2.1.0