[Qemu-devel] [PULL 07/22] migration: Add an ability to ignore shared RAM blocks

[Dr. David Alan Gilbert (git)]

From: Yury Kotov <address@hidden>

If ignore-shared capability is set then skip shared RAMBlocks during the
RAM migration.
Also, move qemu_ram_foreach_migratable_block (and rename) to the
migration code, because it requires access to the migration capabilities.

Signed-off-by: Yury Kotov <address@hidden>
Message-Id: <address@hidden>
Reviewed-by: Dr. David Alan Gilbert <address@hidden>
Signed-off-by: Dr. David Alan Gilbert <address@hidden>
---
 exec.c                    |  19 -------
 include/exec/cpu-common.h |   1 -
 migration/migration.h     |   4 +-
 migration/postcopy-ram.c  |  12 ++---
 migration/ram.c           | 110 +++++++++++++++++++++++++++++---------
 migration/rdma.c          |   2 +-
 6 files changed, 94 insertions(+), 54 deletions(-)

diff --git a/exec.c b/exec.c
index bf71462929..1d4f3784d6 100644
--- a/exec.c
+++ b/exec.c
@@ -3985,25 +3985,6 @@ int qemu_ram_foreach_block(RAMBlockIterFunc func, void 
*opaque)
     return ret;
 }
 
-int qemu_ram_foreach_migratable_block(RAMBlockIterFunc func, void *opaque)
-{
-    RAMBlock *block;
-    int ret = 0;
-
-    rcu_read_lock();
-    RAMBLOCK_FOREACH(block) {
-        if (!qemu_ram_is_migratable(block)) {
-            continue;
-        }
-        ret = func(block, opaque);
-        if (ret) {
-            break;
-        }
-    }
-    rcu_read_unlock();
-    return ret;
-}
-
 /*
  * Unmap pages of memory from start to start+length such that
  * they a) read as 0, b) Trigger whatever fault mechanism
diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h
index 9cd1f94bc5..cef8b88a2a 100644
--- a/include/exec/cpu-common.h
+++ b/include/exec/cpu-common.h
@@ -122,7 +122,6 @@ extern struct MemoryRegion io_mem_notdirty;
 typedef int (RAMBlockIterFunc)(RAMBlock *rb, void *opaque);
 
 int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque);
-int qemu_ram_foreach_migratable_block(RAMBlockIterFunc func, void *opaque);
 int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length);
 
 #endif
diff --git a/migration/migration.h b/migration/migration.h
index 443051adb0..81c261941d 100644
--- a/migration/migration.h
+++ b/migration/migration.h
@@ -306,8 +306,10 @@ void migrate_send_rp_resume_ack(MigrationIncomingState 
*mis, uint32_t value);
 void dirty_bitmap_mig_before_vm_start(void);
 void init_dirty_bitmap_incoming_migration(void);
 
+int foreach_not_ignored_block(RAMBlockIterFunc func, void *opaque);
+
 #define qemu_ram_foreach_block \
-  #warning "Use qemu_ram_foreach_block_migratable in migration code"
+  #warning "Use foreach_not_ignored_block in migration code"
 
 void migration_make_urgent_request(void);
 void migration_consume_urgent_request(void);
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index b098816221..e2aa57a701 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -374,7 +374,7 @@ bool postcopy_ram_supported_by_host(MigrationIncomingState 
*mis)
     }
 
     /* We don't support postcopy with shared RAM yet */
-    if (qemu_ram_foreach_migratable_block(test_ramblock_postcopiable, NULL)) {
+    if (foreach_not_ignored_block(test_ramblock_postcopiable, NULL)) {
         goto out;
     }
 
@@ -508,7 +508,7 @@ static int cleanup_range(RAMBlock *rb, void *opaque)
  */
 int postcopy_ram_incoming_init(MigrationIncomingState *mis)
 {
-    if (qemu_ram_foreach_migratable_block(init_range, NULL)) {
+    if (foreach_not_ignored_block(init_range, NULL)) {
         return -1;
     }
 
@@ -550,7 +550,7 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState 
*mis)
             return -1;
         }
 
-        if (qemu_ram_foreach_migratable_block(cleanup_range, mis)) {
+        if (foreach_not_ignored_block(cleanup_range, mis)) {
             return -1;
         }
 
@@ -617,7 +617,7 @@ static int nhp_range(RAMBlock *rb, void *opaque)
  */
 int postcopy_ram_prepare_discard(MigrationIncomingState *mis)
 {
-    if (qemu_ram_foreach_migratable_block(nhp_range, mis)) {
+    if (foreach_not_ignored_block(nhp_range, mis)) {
         return -1;
     }
 
@@ -628,7 +628,7 @@ int postcopy_ram_prepare_discard(MigrationIncomingState 
*mis)
 
 /*
  * Mark the given area of RAM as requiring notification to unwritten areas
- * Used as a  callback on qemu_ram_foreach_migratable_block.
+ * Used as a  callback on foreach_not_ignored_block.
  *   host_addr: Base of area to mark
  *   offset: Offset in the whole ram arena
  *   length: Length of the section
@@ -1122,7 +1122,7 @@ int postcopy_ram_enable_notify(MigrationIncomingState 
*mis)
     mis->have_fault_thread = true;
 
     /* Mark so that we get notified of accesses to unwritten areas */
-    if (qemu_ram_foreach_migratable_block(ram_block_enable_notify, mis)) {
+    if (foreach_not_ignored_block(ram_block_enable_notify, mis)) {
         error_report("ram_block_enable_notify failed");
         return -1;
     }
diff --git a/migration/ram.c b/migration/ram.c
index 59191c1ed2..01315edd66 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -159,18 +159,44 @@ out:
     return ret;
 }
 
+static bool ramblock_is_ignored(RAMBlock *block)
+{
+    return !qemu_ram_is_migratable(block) ||
+           (migrate_ignore_shared() && qemu_ram_is_shared(block));
+}
+
 /* Should be holding either ram_list.mutex, or the RCU lock. */
+#define RAMBLOCK_FOREACH_NOT_IGNORED(block)            \
+    INTERNAL_RAMBLOCK_FOREACH(block)                   \
+        if (ramblock_is_ignored(block)) {} else
+
 #define RAMBLOCK_FOREACH_MIGRATABLE(block)             \
     INTERNAL_RAMBLOCK_FOREACH(block)                   \
         if (!qemu_ram_is_migratable(block)) {} else
 
 #undef RAMBLOCK_FOREACH
 
+int foreach_not_ignored_block(RAMBlockIterFunc func, void *opaque)
+{
+    RAMBlock *block;
+    int ret = 0;
+
+    rcu_read_lock();
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
+        ret = func(block, opaque);
+        if (ret) {
+            break;
+        }
+    }
+    rcu_read_unlock();
+    return ret;
+}
+
 static void ramblock_recv_map_init(void)
 {
     RAMBlock *rb;
 
-    RAMBLOCK_FOREACH_MIGRATABLE(rb) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(rb) {
         assert(!rb->receivedmap);
         rb->receivedmap = bitmap_new(rb->max_length >> 
qemu_target_page_bits());
     }
@@ -1545,7 +1571,7 @@ unsigned long migration_bitmap_find_dirty(RAMState *rs, 
RAMBlock *rb,
     unsigned long *bitmap = rb->bmap;
     unsigned long next;
 
-    if (!qemu_ram_is_migratable(rb)) {
+    if (ramblock_is_ignored(rb)) {
         return size;
     }
 
@@ -1594,7 +1620,7 @@ uint64_t ram_pagesize_summary(void)
     RAMBlock *block;
     uint64_t summary = 0;
 
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         summary |= block->page_size;
     }
 
@@ -1664,7 +1690,7 @@ static void migration_bitmap_sync(RAMState *rs)
 
     qemu_mutex_lock(&rs->bitmap_mutex);
     rcu_read_lock();
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         migration_bitmap_sync_range(rs, block, 0, block->used_length);
     }
     ram_counters.remaining = ram_bytes_remaining();
@@ -2388,7 +2414,7 @@ static int ram_save_host_page(RAMState *rs, 
PageSearchStatus *pss,
     size_t pagesize_bits =
         qemu_ram_pagesize(pss->block) >> TARGET_PAGE_BITS;
 
-    if (!qemu_ram_is_migratable(pss->block)) {
+    if (ramblock_is_ignored(pss->block)) {
         error_report("block %s should not be migrated !", pss->block->idstr);
         return 0;
     }
@@ -2486,19 +2512,30 @@ void acct_update_position(QEMUFile *f, size_t size, 
bool zero)
     }
 }
 
-uint64_t ram_bytes_total(void)
+static uint64_t ram_bytes_total_common(bool count_ignored)
 {
     RAMBlock *block;
     uint64_t total = 0;
 
     rcu_read_lock();
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
-        total += block->used_length;
+    if (count_ignored) {
+        RAMBLOCK_FOREACH_MIGRATABLE(block) {
+            total += block->used_length;
+        }
+    } else {
+        RAMBLOCK_FOREACH_NOT_IGNORED(block) {
+            total += block->used_length;
+        }
     }
     rcu_read_unlock();
     return total;
 }
 
+uint64_t ram_bytes_total(void)
+{
+    return ram_bytes_total_common(false);
+}
+
 static void xbzrle_load_setup(void)
 {
     XBZRLE.decoded_buf = g_malloc(TARGET_PAGE_SIZE);
@@ -2547,7 +2584,7 @@ static void ram_save_cleanup(void *opaque)
      */
     memory_global_dirty_log_stop();
 
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         g_free(block->bmap);
         block->bmap = NULL;
         g_free(block->unsentmap);
@@ -2610,7 +2647,7 @@ void ram_postcopy_migrated_memory_release(MigrationState 
*ms)
 {
     struct RAMBlock *block;
 
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         unsigned long *bitmap = block->bmap;
         unsigned long range = block->used_length >> TARGET_PAGE_BITS;
         unsigned long run_start = find_next_zero_bit(bitmap, range, 0);
@@ -2688,7 +2725,7 @@ static int postcopy_each_ram_send_discard(MigrationState 
*ms)
     struct RAMBlock *block;
     int ret;
 
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         PostcopyDiscardState *pds =
             postcopy_discard_send_init(ms, block->idstr);
 
@@ -2896,7 +2933,7 @@ int ram_postcopy_send_discard_bitmap(MigrationState *ms)
     rs->last_sent_block = NULL;
     rs->last_page = 0;
 
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         unsigned long pages = block->used_length >> TARGET_PAGE_BITS;
         unsigned long *bitmap = block->bmap;
         unsigned long *unsentmap = block->unsentmap;
@@ -3062,7 +3099,7 @@ static void ram_list_init_bitmaps(void)
 
     /* Skip setting bitmap if there is no RAM */
     if (ram_bytes_total()) {
-        RAMBLOCK_FOREACH_MIGRATABLE(block) {
+        RAMBLOCK_FOREACH_NOT_IGNORED(block) {
             pages = block->max_length >> TARGET_PAGE_BITS;
             block->bmap = bitmap_new(pages);
             bitmap_set(block->bmap, 0, pages);
@@ -3117,7 +3154,7 @@ static void ram_state_resume_prepare(RAMState *rs, 
QEMUFile *out)
      * about dirty page logging as well.
      */
 
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         pages += bitmap_count_one(block->bmap,
                                   block->used_length >> TARGET_PAGE_BITS);
     }
@@ -3176,7 +3213,7 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
 
     rcu_read_lock();
 
-    qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE);
+    qemu_put_be64(f, ram_bytes_total_common(true) | RAM_SAVE_FLAG_MEM_SIZE);
 
     RAMBLOCK_FOREACH_MIGRATABLE(block) {
         qemu_put_byte(f, strlen(block->idstr));
@@ -3185,6 +3222,10 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
         if (migrate_postcopy_ram() && block->page_size != qemu_host_page_size) 
{
             qemu_put_be64(f, block->page_size);
         }
+        if (migrate_ignore_shared()) {
+            qemu_put_be64(f, block->mr->addr);
+            qemu_put_byte(f, ramblock_is_ignored(block) ? 1 : 0);
+        }
     }
 
     rcu_read_unlock();
@@ -3443,7 +3484,7 @@ static inline RAMBlock *ram_block_from_stream(QEMUFile 
*f, int flags)
         return NULL;
     }
 
-    if (!qemu_ram_is_migratable(block)) {
+    if (ramblock_is_ignored(block)) {
         error_report("block %s should not be migrated !", id);
         return NULL;
     }
@@ -3698,7 +3739,7 @@ int colo_init_ram_cache(void)
     RAMBlock *block;
 
     rcu_read_lock();
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         block->colo_cache = qemu_anon_ram_alloc(block->used_length,
                                                 NULL,
                                                 false);
@@ -3719,7 +3760,7 @@ int colo_init_ram_cache(void)
     if (ram_bytes_total()) {
         RAMBlock *block;
 
-        RAMBLOCK_FOREACH_MIGRATABLE(block) {
+        RAMBLOCK_FOREACH_NOT_IGNORED(block) {
             unsigned long pages = block->max_length >> TARGET_PAGE_BITS;
 
             block->bmap = bitmap_new(pages);
@@ -3734,7 +3775,7 @@ int colo_init_ram_cache(void)
 
 out_locked:
 
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         if (block->colo_cache) {
             qemu_anon_ram_free(block->colo_cache, block->used_length);
             block->colo_cache = NULL;
@@ -3751,14 +3792,14 @@ void colo_release_ram_cache(void)
     RAMBlock *block;
 
     memory_global_dirty_log_stop();
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         g_free(block->bmap);
         block->bmap = NULL;
     }
 
     rcu_read_lock();
 
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         if (block->colo_cache) {
             qemu_anon_ram_free(block->colo_cache, block->used_length);
             block->colo_cache = NULL;
@@ -3794,7 +3835,7 @@ static int ram_load_cleanup(void *opaque)
 {
     RAMBlock *rb;
 
-    RAMBLOCK_FOREACH_MIGRATABLE(rb) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(rb) {
         if (ramblock_is_pmem(rb)) {
             pmem_persist(rb->host, rb->used_length);
         }
@@ -3803,7 +3844,7 @@ static int ram_load_cleanup(void *opaque)
     xbzrle_load_cleanup();
     compress_threads_load_cleanup();
 
-    RAMBLOCK_FOREACH_MIGRATABLE(rb) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(rb) {
         g_free(rb->receivedmap);
         rb->receivedmap = NULL;
     }
@@ -4003,7 +4044,7 @@ static void colo_flush_ram_cache(void)
 
     memory_global_dirty_log_sync();
     rcu_read_lock();
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         migration_bitmap_sync_range(ram_state, block, 0, block->used_length);
     }
     rcu_read_unlock();
@@ -4146,6 +4187,23 @@ static int ram_load(QEMUFile *f, void *opaque, int 
version_id)
                             ret = -EINVAL;
                         }
                     }
+                    if (migrate_ignore_shared()) {
+                        hwaddr addr = qemu_get_be64(f);
+                        bool ignored = qemu_get_byte(f);
+                        if (ignored != ramblock_is_ignored(block)) {
+                            error_report("RAM block %s should %s be migrated",
+                                         id, ignored ? "" : "not");
+                            ret = -EINVAL;
+                        }
+                        if (ramblock_is_ignored(block) &&
+                            block->mr->addr != addr) {
+                            error_report("Mismatched GPAs for block %s "
+                                         "%" PRId64 "!= %" PRId64,
+                                         id, (uint64_t)addr,
+                                         (uint64_t)block->mr->addr);
+                            ret = -EINVAL;
+                        }
+                    }
                     ram_control_load_hook(f, RAM_CONTROL_BLOCK_REG,
                                           block->idstr);
                 } else {
@@ -4216,7 +4274,7 @@ static int ram_load(QEMUFile *f, void *opaque, int 
version_id)
 static bool ram_has_postcopy(void *opaque)
 {
     RAMBlock *rb;
-    RAMBLOCK_FOREACH_MIGRATABLE(rb) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(rb) {
         if (ramblock_is_pmem(rb)) {
             info_report("Block: %s, host: %p is a nvdimm memory, postcopy"
                          "is not supported now!", rb->idstr, rb->host);
@@ -4236,7 +4294,7 @@ static int ram_dirty_bitmap_sync_all(MigrationState *s, 
RAMState *rs)
 
     trace_ram_dirty_bitmap_sync_start();
 
-    RAMBLOCK_FOREACH_MIGRATABLE(block) {
+    RAMBLOCK_FOREACH_NOT_IGNORED(block) {
         qemu_savevm_send_recv_bitmap(file, block->idstr);
         trace_ram_dirty_bitmap_request(block->idstr);
         ramblock_count++;
diff --git a/migration/rdma.c b/migration/rdma.c
index b0115e4de5..63c118af09 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -644,7 +644,7 @@ static int qemu_rdma_init_ram_blocks(RDMAContext *rdma)
 
     assert(rdma->blockmap == NULL);
     memset(local, 0, sizeof *local);
-    qemu_ram_foreach_migratable_block(qemu_rdma_init_one_block, rdma);
+    foreach_not_ignored_block(qemu_rdma_init_one_block, rdma);
     trace_qemu_rdma_init_ram_blocks(local->nb_blocks);
     rdma->dest_blocks = g_new0(RDMADestBlock,
                                rdma->local_ram_blocks.nb_blocks);
-- 
2.20.1