[Qemu-devel] [PATCH v6 38/47] Postcopy: Use helpers to map pages during migration

["Dr. David Alan Gilbert (git)" <dgilbert@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_less_copy 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>
---
 arch_init.c | 117 +++++++++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 97 insertions(+), 20 deletions(-)

diff --git a/arch_init.c b/arch_init.c
index c96c4c1..0d3e865 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -1476,7 +1476,17 @@ 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
+ * mis: MigrationIncomingState
+ * 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,
+                                            MigrationIncomingState *mis,
                                             ram_addr_t offset,
                                             int flags)
 {
@@ -1489,7 +1499,6 @@ static inline void *host_from_stream_offset(QEMUFile *f,
             error_report("Ack, bad migration stream!");
             return NULL;
         }
-
         return memory_region_get_ram_ptr(block->mr) + offset;
     }
 
@@ -1534,6 +1543,16 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
 {
     int flags = 0, ret = 0;
     static uint64_t seq_iter;
+    /*
+     * System is running in postcopy mode, page inserts to host memory must be
+     * atomic
+     */
+    MigrationIncomingState *mis = migration_incoming_get_current();
+    bool postcopy_running = postcopy_state_get(mis) >=
+                            POSTCOPY_INCOMING_LISTENING;
+    void *postcopy_host_page = NULL;
+    bool postcopy_place_needed = false;
+    bool matching_page_sizes = qemu_host_page_size == TARGET_PAGE_SIZE;
 
     seq_iter++;
 
@@ -1549,13 +1568,57 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
     rcu_read_lock();
     while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
         ram_addr_t addr, total_ram_bytes;
-        void *host;
+        void *host = 0;
+        void *page_buffer = 0;
+        void *postcopy_place_source = 0;
         uint8_t ch;
+        bool all_zero = false;
 
         addr = qemu_get_be64(f);
         flags = addr & ~TARGET_PAGE_MASK;
         addr &= TARGET_PAGE_MASK;
 
+        if (flags & (RAM_SAVE_FLAG_COMPRESS | RAM_SAVE_FLAG_PAGE |
+                     RAM_SAVE_FLAG_XBZRLE)) {
+            host = host_from_stream_offset(f, mis, addr, flags);
+            if (!host) {
+                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
+                ret = -EINVAL;
+                break;
+            }
+            if (!postcopy_running) {
+                page_buffer = host;
+            } else {
+                /*
+                 * 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.
+                 */
+                if (!postcopy_host_page) {
+                    postcopy_host_page = postcopy_get_tmp_page(mis);
+                }
+                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
+                 */
+                postcopy_place_needed = (((uintptr_t)host + TARGET_PAGE_SIZE) &
+                                         ~qemu_host_page_mask) == 0;
+                postcopy_place_source = postcopy_host_page;
+            }
+        } else {
+            postcopy_place_needed = false;
+        }
+
         switch (flags & ~RAM_SAVE_FLAG_CONTINUE) {
         case RAM_SAVE_FLAG_MEM_SIZE:
             /* Synchronize RAM block list */
@@ -1592,30 +1655,36 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
             }
             break;
         case RAM_SAVE_FLAG_COMPRESS:
-            host = host_from_stream_offset(f, addr, flags);
-            if (!host) {
-                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
-                ret = -EINVAL;
-                break;
-            }
             ch = qemu_get_byte(f);
-            ram_handle_compressed(host, ch, TARGET_PAGE_SIZE);
+            if (!postcopy_running) {
+                ram_handle_compressed(host, ch, TARGET_PAGE_SIZE);
+            } else {
+                memset(page_buffer, ch, TARGET_PAGE_SIZE);
+                if (ch) {
+                    all_zero = false;
+                }
+            }
             break;
+
         case 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;
+            all_zero = false;
+            if (!postcopy_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_less_copy(f, (uint8_t **)&postcopy_place_source,
+                                          TARGET_PAGE_SIZE);
             }
-            qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
             break;
+
         case RAM_SAVE_FLAG_XBZRLE:
-            host = host_from_stream_offset(f, addr, flags);
-            if (!host) {
-                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
-                ret = -EINVAL;
-                break;
+            all_zero = false;
+            if (postcopy_running) {
+                error_report("XBZRLE RAM block in postcopy mode @%zx\n", addr);
+                return -EINVAL;
             }
             if (load_xbzrle(f, addr, host) < 0) {
                 error_report("Failed to decompress XBZRLE page at "
@@ -1636,6 +1705,14 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                 ret = -EINVAL;
             }
         }
+
+        if (postcopy_place_needed) {
+            /* This gets called at the last target page in the host page */
+            ret = postcopy_place_page(mis, host + TARGET_PAGE_SIZE -
+                                           qemu_host_page_size,
+                                      postcopy_place_source,
+                                      all_zero);
+        }
         if (!ret) {
             ret = qemu_file_get_error(f);
         }
-- 
2.1.0