Merge remote-tracking branch 'remotes/dgilbert/tags/pull-migration-20191011a' into staging

Migration pull 2019-10-11

Mostly cleanups and minor fixes

[Note I'm seeing a hang on the aarch64 hosted x86-64 tcg migration
test in xbzrle; but I'm seeing that on current head as well]

# gpg: Signature made Fri 11 Oct 2019 20:14:31 BST
# gpg:                using RSA key 45F5C71B4A0CB7FB977A9FA90516331EBC5BFDE7
# gpg: Good signature from "Dr. David Alan Gilbert (RH2) <dgilbert@redhat.com>" [full]
# Primary key fingerprint: 45F5 C71B 4A0C B7FB 977A  9FA9 0516 331E BC5B FDE7

* remotes/dgilbert/tags/pull-migration-20191011a: (21 commits)
  migration: Support gtree migration
  migration/multifd: pages->used would be cleared when attach to multifd_send_state
  migration/multifd: initialize packet->magic/version once at setup stage
  migration/multifd: use pages->allocated instead of the static max
  migration/multifd: fix a typo in comment of multifd_recv_unfill_packet()
  migration/postcopy: check PostcopyState before setting to POSTCOPY_INCOMING_RUNNING
  migration/postcopy: rename postcopy_ram_enable_notify to postcopy_ram_incoming_setup
  migration/postcopy: postpone setting PostcopyState to END
  migration/postcopy: mis->have_listen_thread check will never be touched
  migration: report SaveStateEntry id and name on failure
  migration: pass in_postcopy instead of check state again
  migration/postcopy: fix typo in mark_postcopy_blocktime_begin's comment
  migration/postcopy: map large zero page in postcopy_ram_incoming_setup()
  migration/postcopy: allocate tmp_page in setup stage
  migration: Don't try and recover return path in non-postcopy
  rcu: Use automatic rc_read unlock in core memory/exec code
  migration: Use automatic rcu_read unlock in rdma.c
  migration: Use automatic rcu_read unlock in ram.c
  migration: Fix missing rcu_read_unlock
  rcu: Add automatically released rcu_read_lock variants
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 131 insertions, 73 deletions

diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index e96e621de5..ad158bb247 100644
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -193,30 +193,29 @@ static inline bool cpu_physical_memory_get_dirty(ram_addr_t start,
     end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
     page = start >> TARGET_PAGE_BITS;
 
-    rcu_read_lock();
-
-    blocks = atomic_rcu_read(&ram_list.dirty_memory[client]);
+    WITH_RCU_READ_LOCK_GUARD() {
+        blocks = atomic_rcu_read(&ram_list.dirty_memory[client]);
+
+        idx = page / DIRTY_MEMORY_BLOCK_SIZE;
+        offset = page % DIRTY_MEMORY_BLOCK_SIZE;
+        base = page - offset;
+        while (page < end) {
+            unsigned long next = MIN(end, base + DIRTY_MEMORY_BLOCK_SIZE);
+            unsigned long num = next - base;
+            unsigned long found = find_next_bit(blocks->blocks[idx],
+                                                num, offset);
+            if (found < num) {
+                dirty = true;
+                break;
+            }
 
-    idx = page / DIRTY_MEMORY_BLOCK_SIZE;
-    offset = page % DIRTY_MEMORY_BLOCK_SIZE;
-    base = page - offset;
-    while (page < end) {
-        unsigned long next = MIN(end, base + DIRTY_MEMORY_BLOCK_SIZE);
-        unsigned long num = next - base;
-        unsigned long found = find_next_bit(blocks->blocks[idx], num, offset);
-        if (found < num) {
-            dirty = true;
-            break;
+            page = next;
+            idx++;
+            offset = 0;
+            base += DIRTY_MEMORY_BLOCK_SIZE;
         }
-
-        page = next;
-        idx++;
-        offset = 0;
-        base += DIRTY_MEMORY_BLOCK_SIZE;
     }
 
-    rcu_read_unlock();
-
     return dirty;
 }
 
@@ -234,7 +233,7 @@ static inline bool cpu_physical_memory_all_dirty(ram_addr_t start,
     end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
     page = start >> TARGET_PAGE_BITS;
 
-    rcu_read_lock();
+    RCU_READ_LOCK_GUARD();
 
     blocks = atomic_rcu_read(&ram_list.dirty_memory[client]);
 
@@ -256,8 +255,6 @@ static inline bool cpu_physical_memory_all_dirty(ram_addr_t start,
         base += DIRTY_MEMORY_BLOCK_SIZE;
     }
 
-    rcu_read_unlock();
-
     return dirty;
 }
 
@@ -309,13 +306,11 @@ static inline void cpu_physical_memory_set_dirty_flag(ram_addr_t addr,
     idx = page / DIRTY_MEMORY_BLOCK_SIZE;
     offset = page % DIRTY_MEMORY_BLOCK_SIZE;
 
-    rcu_read_lock();
+    RCU_READ_LOCK_GUARD();
 
     blocks = atomic_rcu_read(&ram_list.dirty_memory[client]);
 
     set_bit_atomic(offset, blocks->blocks[idx]);
-
-    rcu_read_unlock();
 }
 
 static inline void cpu_physical_memory_set_dirty_range(ram_addr_t start,
@@ -334,39 +329,37 @@ static inline void cpu_physical_memory_set_dirty_range(ram_addr_t start,
     end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
     page = start >> TARGET_PAGE_BITS;
 
-    rcu_read_lock();
+    WITH_RCU_READ_LOCK_GUARD() {
+        for (i = 0; i < DIRTY_MEMORY_NUM; i++) {
+            blocks[i] = atomic_rcu_read(&ram_list.dirty_memory[i]);
+        }
 
-    for (i = 0; i < DIRTY_MEMORY_NUM; i++) {
-        blocks[i] = atomic_rcu_read(&ram_list.dirty_memory[i]);
-    }
+        idx = page / DIRTY_MEMORY_BLOCK_SIZE;
+        offset = page % DIRTY_MEMORY_BLOCK_SIZE;
+        base = page - offset;
+        while (page < end) {
+            unsigned long next = MIN(end, base + DIRTY_MEMORY_BLOCK_SIZE);
 
-    idx = page / DIRTY_MEMORY_BLOCK_SIZE;
-    offset = page % DIRTY_MEMORY_BLOCK_SIZE;
-    base = page - offset;
-    while (page < end) {
-        unsigned long next = MIN(end, base + DIRTY_MEMORY_BLOCK_SIZE);
+            if (likely(mask & (1 << DIRTY_MEMORY_MIGRATION))) {
+                bitmap_set_atomic(blocks[DIRTY_MEMORY_MIGRATION]->blocks[idx],
+                                  offset, next - page);
+            }
+            if (unlikely(mask & (1 << DIRTY_MEMORY_VGA))) {
+                bitmap_set_atomic(blocks[DIRTY_MEMORY_VGA]->blocks[idx],
+                                  offset, next - page);
+            }
+            if (unlikely(mask & (1 << DIRTY_MEMORY_CODE))) {
+                bitmap_set_atomic(blocks[DIRTY_MEMORY_CODE]->blocks[idx],
+                                  offset, next - page);
+            }
 
-        if (likely(mask & (1 << DIRTY_MEMORY_MIGRATION))) {
-            bitmap_set_atomic(blocks[DIRTY_MEMORY_MIGRATION]->blocks[idx],
-                              offset, next - page);
+            page = next;
+            idx++;
+            offset = 0;
+            base += DIRTY_MEMORY_BLOCK_SIZE;
         }
-        if (unlikely(mask & (1 << DIRTY_MEMORY_VGA))) {
-            bitmap_set_atomic(blocks[DIRTY_MEMORY_VGA]->blocks[idx],
-                              offset, next - page);
-        }
-        if (unlikely(mask & (1 << DIRTY_MEMORY_CODE))) {
-            bitmap_set_atomic(blocks[DIRTY_MEMORY_CODE]->blocks[idx],
-                              offset, next - page);
-        }
-
-        page = next;
-        idx++;
-        offset = 0;
-        base += DIRTY_MEMORY_BLOCK_SIZE;
     }
 
-    rcu_read_unlock();
-
     xen_hvm_modified_memory(start, length);
 }
 
@@ -396,36 +389,35 @@ static inline void cpu_physical_memory_set_dirty_lebitmap(unsigned long *bitmap,
         offset = BIT_WORD((start >> TARGET_PAGE_BITS) %
                           DIRTY_MEMORY_BLOCK_SIZE);
 
-        rcu_read_lock();
+        WITH_RCU_READ_LOCK_GUARD() {
+            for (i = 0; i < DIRTY_MEMORY_NUM; i++) {
+                blocks[i] = atomic_rcu_read(&ram_list.dirty_memory[i])->blocks;
+            }
 
-        for (i = 0; i < DIRTY_MEMORY_NUM; i++) {
-            blocks[i] = atomic_rcu_read(&ram_list.dirty_memory[i])->blocks;
-        }
+            for (k = 0; k < nr; k++) {
+                if (bitmap[k]) {
+                    unsigned long temp = leul_to_cpu(bitmap[k]);
 
-        for (k = 0; k < nr; k++) {
-            if (bitmap[k]) {
-                unsigned long temp = leul_to_cpu(bitmap[k]);
+                    atomic_or(&blocks[DIRTY_MEMORY_VGA][idx][offset], temp);
 
-                atomic_or(&blocks[DIRTY_MEMORY_VGA][idx][offset], temp);
+                    if (global_dirty_log) {
+                        atomic_or(&blocks[DIRTY_MEMORY_MIGRATION][idx][offset],
+                                  temp);
+                    }
 
-                if (global_dirty_log) {
-                    atomic_or(&blocks[DIRTY_MEMORY_MIGRATION][idx][offset],
-                              temp);
+                    if (tcg_enabled()) {
+                        atomic_or(&blocks[DIRTY_MEMORY_CODE][idx][offset],
+                                  temp);
+                    }
                 }
 
-                if (tcg_enabled()) {
-                    atomic_or(&blocks[DIRTY_MEMORY_CODE][idx][offset], temp);
+                if (++offset >= BITS_TO_LONGS(DIRTY_MEMORY_BLOCK_SIZE)) {
+                    offset = 0;
+                    idx++;
                 }
             }
-
-            if (++offset >= BITS_TO_LONGS(DIRTY_MEMORY_BLOCK_SIZE)) {
-                offset = 0;
-                idx++;
-            }
         }
 
-        rcu_read_unlock();
-
         xen_hvm_modified_memory(start, pages << TARGET_PAGE_BITS);
     } else {
         uint8_t clients = tcg_enabled() ? DIRTY_CLIENTS_ALL : DIRTY_CLIENTS_NOCODE;
diff --git a/include/migration/misc.h b/include/migration/misc.h
index b9d8e787af..d2762257aa 100644
--- a/include/migration/misc.h
+++ b/include/migration/misc.h
@@ -60,6 +60,7 @@ void migration_object_init(void);
 void migration_shutdown(void);
 void qemu_start_incoming_migration(const char *uri, Error **errp);
 bool migration_is_idle(void);
+bool migration_is_active(MigrationState *);
 void add_migration_state_change_notifier(Notifier *notify);
 void remove_migration_state_change_notifier(Notifier *notify);
 bool migration_in_setup(MigrationState *);
diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h
index 1fbfd099dd..b9ee563aa4 100644
--- a/include/migration/vmstate.h
+++ b/include/migration/vmstate.h
@@ -224,6 +224,7 @@ extern const VMStateInfo vmstate_info_unused_buffer;
 extern const VMStateInfo vmstate_info_tmp;
 extern const VMStateInfo vmstate_info_bitmap;
 extern const VMStateInfo vmstate_info_qtailq;
+extern const VMStateInfo vmstate_info_gtree;
 
 #define type_check_2darray(t1,t2,n,m) ((t1(*)[n][m])0 - (t2*)0)
 /*
@@ -754,6 +755,45 @@ extern const VMStateInfo vmstate_info_qtailq;
     .start        = offsetof(_type, _next),                              \
 }
 
+/*
+ * For migrating a GTree whose key is a pointer to _key_type and the
+ * value, a pointer to _val_type
+ * The target tree must have been properly initialized
+ * _vmsd: Start address of the 2 element array containing the data vmsd
+ *        and the key vmsd, in that order
+ * _key_type: type of the key
+ * _val_type: type of the value
+ */
+#define VMSTATE_GTREE_V(_field, _state, _version, _vmsd,                       \
+                        _key_type, _val_type)                                  \
+{                                                                              \
+    .name         = (stringify(_field)),                                       \
+    .version_id   = (_version),                                                \
+    .vmsd         = (_vmsd),                                                   \
+    .info         = &vmstate_info_gtree,                                       \
+    .start        = sizeof(_key_type),                                         \
+    .size         = sizeof(_val_type),                                         \
+    .offset       = offsetof(_state, _field),                                  \
+}
+
+/*
+ * For migrating a GTree with direct key and the value a pointer
+ * to _val_type
+ * The target tree must have been properly initialized
+ * _vmsd: data vmsd
+ * _val_type: type of the value
+ */
+#define VMSTATE_GTREE_DIRECT_KEY_V(_field, _state, _version, _vmsd, _val_type) \
+{                                                                              \
+    .name         = (stringify(_field)),                                       \
+    .version_id   = (_version),                                                \
+    .vmsd         = (_vmsd),                                                   \
+    .info         = &vmstate_info_gtree,                                       \
+    .start        = 0,                                                         \
+    .size         = sizeof(_val_type),                                         \
+    .offset       = offsetof(_state, _field),                                  \
+}
+
 /* _f : field name
    _f_n : num of elements field_name
    _n : num of elements
diff --git a/include/qemu/rcu.h b/include/qemu/rcu.h
index 22876d1428..9c82683e37 100644
--- a/include/qemu/rcu.h
+++ b/include/qemu/rcu.h
@@ -154,6 +154,31 @@ extern void call_rcu1(struct rcu_head *head, RCUCBFunc *func);
       }),                                                                \
       (RCUCBFunc *)g_free);
 
+typedef void RCUReadAuto;
+static inline RCUReadAuto *rcu_read_auto_lock(void)
+{
+    rcu_read_lock();
+    /* Anything non-NULL causes the cleanup function to be called */
+    return (void *)(uintptr_t)0x1;
+}
+
+static inline void rcu_read_auto_unlock(RCUReadAuto *r)
+{
+    rcu_read_unlock();
+}
+
+G_DEFINE_AUTOPTR_CLEANUP_FUNC(RCUReadAuto, rcu_read_auto_unlock)
+
+#define WITH_RCU_READ_LOCK_GUARD() \
+    WITH_RCU_READ_LOCK_GUARD_(_rcu_read_auto##__COUNTER__)
+
+#define WITH_RCU_READ_LOCK_GUARD_(var) \
+    for (g_autoptr(RCUReadAuto) var = rcu_read_auto_lock(); \
+        (var); rcu_read_auto_unlock(var), (var) = NULL)
+
+#define RCU_READ_LOCK_GUARD() \
+    g_autoptr(RCUReadAuto) _rcu_read_auto __attribute__((unused)) = rcu_read_auto_lock()
+
 #ifdef __cplusplus
 }
 #endif