[Qemu-devel] [PULL 44/57] Postcopy: Use helpers to map pages during migration

[Juan Quintela <quintela@redhat.com>]

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

In postcopy, the destination guest is running at the same time
as it's receiving pages; as we receive new pages we must put
them into the guests address space atomically to avoid a running
CPU accessing a partially written page.

Use the helpers in postcopy-ram.c to map these pages.

qemu_get_buffer_in_place is used to avoid a copy out of qemu_file
in the case that postcopy is going to do a copy anyway.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
---
 migration/ram.c | 130 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 trace-events    |   1 +
 2 files changed, 130 insertions(+), 1 deletion(-)

diff --git a/migration/ram.c b/migration/ram.c
index d09d5ab..af5f369 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -1932,6 +1932,14 @@ static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
 /* Must be called from within a rcu critical section.
  * Returns a pointer from within the RCU-protected ram_list.
  */
+/*
+ * Read a RAMBlock ID from the stream f, find the host address of the
+ * start of that block and add on 'offset'
+ *
+ * f: Stream to read from
+ * offset: Offset within the block
+ * flags: Page flags (mostly to see if it's a continuation of previous block)
+ */
 static inline void *host_from_stream_offset(QEMUFile *f,
                                             ram_addr_t offset,
                                             int flags)
@@ -2077,11 +2085,126 @@ int ram_postcopy_incoming_init(MigrationIncomingState *mis)
     return postcopy_ram_incoming_init(mis, ram_pages);
 }

+/*
+ * Called in postcopy mode by ram_load().
+ * rcu_read_lock is taken prior to this being called.
+ */
+static int ram_load_postcopy(QEMUFile *f)
+{
+    int flags = 0, ret = 0;
+    bool place_needed = false;
+    bool matching_page_sizes = qemu_host_page_size == TARGET_PAGE_SIZE;
+    MigrationIncomingState *mis = migration_incoming_get_current();
+    /* Temporary page that is later 'placed' */
+    void *postcopy_host_page = postcopy_get_tmp_page(mis);
+
+    while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
+        ram_addr_t addr;
+        void *host = NULL;
+        void *page_buffer = NULL;
+        void *place_source = NULL;
+        uint8_t ch;
+        bool all_zero = false;
+
+        addr = qemu_get_be64(f);
+        flags = addr & ~TARGET_PAGE_MASK;
+        addr &= TARGET_PAGE_MASK;
+
+        trace_ram_load_postcopy_loop((uint64_t)addr, flags);
+        place_needed = false;
+        if (flags & (RAM_SAVE_FLAG_COMPRESS | RAM_SAVE_FLAG_PAGE)) {
+            host = host_from_stream_offset(f, addr, flags);
+            if (!host) {
+                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
+                ret = -EINVAL;
+                break;
+            }
+            page_buffer = host;
+            /*
+             * Postcopy requires that we place whole host pages atomically.
+             * To make it atomic, the data is read into a temporary page
+             * that's moved into place later.
+             * The migration protocol uses,  possibly smaller, target-pages
+             * however the source ensures it always sends all the components
+             * of a host page in order.
+             */
+            page_buffer = postcopy_host_page +
+                          ((uintptr_t)host & ~qemu_host_page_mask);
+            /* If all TP are zero then we can optimise the place */
+            if (!((uintptr_t)host & ~qemu_host_page_mask)) {
+                all_zero = true;
+            }
+
+            /*
+             * If it's the last part of a host page then we place the host
+             * page
+             */
+            place_needed = (((uintptr_t)host + TARGET_PAGE_SIZE) &
+                                     ~qemu_host_page_mask) == 0;
+            place_source = postcopy_host_page;
+        }
+
+        switch (flags & ~RAM_SAVE_FLAG_CONTINUE) {
+        case RAM_SAVE_FLAG_COMPRESS:
+            ch = qemu_get_byte(f);
+            memset(page_buffer, ch, TARGET_PAGE_SIZE);
+            if (ch) {
+                all_zero = false;
+            }
+            break;
+
+        case RAM_SAVE_FLAG_PAGE:
+            all_zero = false;
+            if (!place_needed || !matching_page_sizes) {
+                qemu_get_buffer(f, page_buffer, TARGET_PAGE_SIZE);
+            } else {
+                /* Avoids the qemu_file copy during postcopy, which is
+                 * going to do a copy later; can only do it when we
+                 * do this read in one go (matching page sizes)
+                 */
+                qemu_get_buffer_in_place(f, (uint8_t **)&place_source,
+                                         TARGET_PAGE_SIZE);
+            }
+            break;
+        case RAM_SAVE_FLAG_EOS:
+            /* normal exit */
+            break;
+        default:
+            error_report("Unknown combination of migration flags: %#x"
+                         " (postcopy mode)", flags);
+            ret = -EINVAL;
+        }
+
+        if (place_needed) {
+            /* This gets called at the last target page in the host page */
+            if (all_zero) {
+                ret = postcopy_place_page_zero(mis,
+                                               host + TARGET_PAGE_SIZE -
+                                               qemu_host_page_size);
+            } else {
+                ret = postcopy_place_page(mis, host + TARGET_PAGE_SIZE -
+                                               qemu_host_page_size,
+                                               place_source);
+            }
+        }
+        if (!ret) {
+            ret = qemu_file_get_error(f);
+        }
+    }
+
+    return ret;
+}
+
 static int ram_load(QEMUFile *f, void *opaque, int version_id)
 {
     int flags = 0, ret = 0;
     static uint64_t seq_iter;
     int len = 0;
+    /*
+     * If system is running in postcopy mode, page inserts to host memory must
+     * be atomic
+     */
+    bool postcopy_running = postcopy_state_get() >= POSTCOPY_INCOMING_LISTENING;

     seq_iter++;

@@ -2095,7 +2218,12 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
      * critical section.
      */
     rcu_read_lock();
-    while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
+
+    if (postcopy_running) {
+        ret = ram_load_postcopy(f);
+    }
+
+    while (!postcopy_running && !ret && !(flags & RAM_SAVE_FLAG_EOS)) {
         ram_addr_t addr, total_ram_bytes;
         void *host = NULL;
         uint8_t ch;
diff --git a/trace-events b/trace-events
index c493f5d..ad7afcb 100644
--- a/trace-events
+++ b/trace-events
@@ -1257,6 +1257,7 @@ get_queued_page_not_dirty(const char *block_name, uint64_t tmp_offset, uint64_t
 migration_bitmap_sync_start(void) ""
 migration_bitmap_sync_end(uint64_t dirty_pages) "dirty_pages %" PRIu64""
 migration_throttle(void) ""
+ram_load_postcopy_loop(uint64_t addr, int flags) "@%" PRIx64 " %x"
 ram_postcopy_send_discard_bitmap(void) ""
 ram_save_queue_pages(const char *rbname, size_t start, size_t len) "%s: start: %zx len: %zx"

-- 
2.5.0