migration: run pending/iterate callbacks out of big lock

[qemu.git] / exec.c

diff --git a/exec.c b/exec.c
index 78bae1c7acb984606221b531c2b2777f1fe1998f..46a283071a2e908bd9f3aa77af7d2c2694909246 100644 (file)
--- a/exec.c
+++ b/exec.c
@@ -57,7 +57,7 @@
 int phys_ram_fd;
 static int in_migration;
 
-RAMList ram_list = { .blocks = QLIST_HEAD_INITIALIZER(ram_list.blocks) };
+RAMList ram_list = { .blocks = QTAILQ_HEAD_INITIALIZER(ram_list.blocks) };
 
 static MemoryRegion *system_memory;
 static MemoryRegion *system_io;
@@ -78,7 +78,7 @@ DEFINE_TLS(CPUArchState *,cpu_single_env);
 /* 0 = Do not count executed instructions.
    1 = Precise instruction counting.
    2 = Adaptive rate instruction counting.  */
-int use_icount = 0;
+int use_icount;
 
 #if !defined(CONFIG_USER_ONLY)
 
@@ -213,6 +213,7 @@ bool memory_region_is_unassigned(MemoryRegion *mr)
 void cpu_exec_init_all(void)
 {
 #if !defined(CONFIG_USER_ONLY)
+    qemu_mutex_init(&ram_list.mutex);
     memory_map_init();
     io_mem_init();
 #endif
@@ -246,24 +247,25 @@ static const VMStateDescription vmstate_cpu_common = {
 };
 #endif
 
-CPUArchState *qemu_get_cpu(int cpu)
+CPUState *qemu_get_cpu(int index)
 {
     CPUArchState *env = first_cpu;
+    CPUState *cpu = NULL;
 
     while (env) {
-        if (env->cpu_index == cpu)
+        cpu = ENV_GET_CPU(env);
+        if (cpu->cpu_index == index) {
             break;
+        }
         env = env->next_cpu;
     }
 
-    return env;
+    return cpu;
 }
 
 void cpu_exec_init(CPUArchState *env)
 {
-#ifndef CONFIG_USER_ONLY
     CPUState *cpu = ENV_GET_CPU(env);
-#endif
     CPUArchState **penv;
     int cpu_index;
 
@@ -277,8 +279,8 @@ void cpu_exec_init(CPUArchState *env)
         penv = &(*penv)->next_cpu;
         cpu_index++;
     }
-    env->cpu_index = cpu_index;
-    env->numa_node = 0;
+    cpu->cpu_index = cpu_index;
+    cpu->numa_node = 0;
     QTAILQ_INIT(&env->breakpoints);
     QTAILQ_INIT(&env->watchpoints);
 #ifndef CONFIG_USER_ONLY
@@ -490,8 +492,10 @@ void cpu_reset_interrupt(CPUArchState *env, int mask)
 
 void cpu_exit(CPUArchState *env)
 {
-    env->exit_request = 1;
-    cpu_unlink_tb(env);
+    CPUState *cpu = ENV_GET_CPU(env);
+
+    cpu->exit_request = 1;
+    cpu->tcg_exit_req = 1;
 }
 
 void cpu_abort(CPUArchState *env, const char *fmt, ...)
@@ -530,7 +534,6 @@ CPUArchState *cpu_copy(CPUArchState *env)
 {
     CPUArchState *new_env = cpu_init(env->cpu_model_str);
     CPUArchState *next_cpu = new_env->next_cpu;
-    int cpu_index = new_env->cpu_index;
 #if defined(TARGET_HAS_ICE)
     CPUBreakpoint *bp;
     CPUWatchpoint *wp;
@@ -538,9 +541,8 @@ CPUArchState *cpu_copy(CPUArchState *env)
 
     memcpy(new_env, env, sizeof(CPUArchState));
 
-    /* Preserve chaining and index. */
+    /* Preserve chaining. */
     new_env->next_cpu = next_cpu;
-    new_env->cpu_index = cpu_index;
 
     /* Clone all break/watchpoints.
        Note: Once we support ptrace with hw-debug register access, make sure
@@ -801,6 +803,16 @@ void qemu_flush_coalesced_mmio_buffer(void)
         kvm_flush_coalesced_mmio_buffer();
 }
 
+void qemu_mutex_lock_ramlist(void)
+{
+    qemu_mutex_lock(&ram_list.mutex);
+}
+
+void qemu_mutex_unlock_ramlist(void)
+{
+    qemu_mutex_unlock(&ram_list.mutex);
+}
+
 #if defined(__linux__) && !defined(TARGET_S390X)
 
 #include <sys/vfs.h>
@@ -853,18 +865,16 @@ static void *file_ram_alloc(RAMBlock *block,
         return NULL;
     }
 
-    if (asprintf(&filename, "%s/qemu_back_mem.XXXXXX", path) == -1) {
-        return NULL;
-    }
+    filename = g_strdup_printf("%s/qemu_back_mem.XXXXXX", path);
 
     fd = mkstemp(filename);
     if (fd < 0) {
         perror("unable to create backing store for hugepages");
-        free(filename);
+        g_free(filename);
         return NULL;
     }
     unlink(filename);
-    free(filename);
+    g_free(filename);
 
     memory = (memory+hpagesize-1) & ~(hpagesize-1);
 
@@ -902,15 +912,15 @@ static ram_addr_t find_ram_offset(ram_addr_t size)
     RAMBlock *block, *next_block;
     ram_addr_t offset = RAM_ADDR_MAX, mingap = RAM_ADDR_MAX;
 
-    if (QLIST_EMPTY(&ram_list.blocks))
+    if (QTAILQ_EMPTY(&ram_list.blocks))
         return 0;
 
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
         ram_addr_t end, next = RAM_ADDR_MAX;
 
         end = block->offset + block->length;
 
-        QLIST_FOREACH(next_block, &ram_list.blocks, next) {
+        QTAILQ_FOREACH(next_block, &ram_list.blocks, next) {
             if (next_block->offset >= end) {
                 next = MIN(next, next_block->offset);
             }
@@ -935,7 +945,7 @@ ram_addr_t last_ram_offset(void)
     RAMBlock *block;
     ram_addr_t last = 0;
 
-    QLIST_FOREACH(block, &ram_list.blocks, next)
+    QTAILQ_FOREACH(block, &ram_list.blocks, next)
         last = MAX(last, block->offset + block->length);
 
     return last;
@@ -964,7 +974,7 @@ void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev)
     RAMBlock *new_block, *block;
 
     new_block = NULL;
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
         if (block->offset == addr) {
             new_block = block;
             break;
@@ -982,13 +992,16 @@ void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev)
     }
     pstrcat(new_block->idstr, sizeof(new_block->idstr), name);
 
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    /* This assumes the iothread lock is taken here too.  */
+    qemu_mutex_lock_ramlist();
+    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
         if (block != new_block && !strcmp(block->idstr, new_block->idstr)) {
             fprintf(stderr, "RAMBlock \"%s\" already registered, abort!\n",
                     new_block->idstr);
             abort();
         }
     }
+    qemu_mutex_unlock_ramlist();
 }
 
 static int memory_try_enable_merging(void *addr, size_t len)
@@ -1007,11 +1020,13 @@ static int memory_try_enable_merging(void *addr, size_t len)
 ram_addr_t qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
                                    MemoryRegion *mr)
 {
-    RAMBlock *new_block;
+    RAMBlock *block, *new_block;
 
     size = TARGET_PAGE_ALIGN(size);
     new_block = g_malloc0(sizeof(*new_block));
 
+    /* This assumes the iothread lock is taken here too.  */
+    qemu_mutex_lock_ramlist();
     new_block->mr = mr;
     new_block->offset = find_ram_offset(size);
     if (host) {
@@ -1043,9 +1058,22 @@ ram_addr_t qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
     }
     new_block->length = size;
 
-    QLIST_INSERT_HEAD(&ram_list.blocks, new_block, next);
+    /* Keep the list sorted from biggest to smallest block.  */
+    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
+        if (block->length < new_block->length) {
+            break;
+        }
+    }
+    if (block) {
+        QTAILQ_INSERT_BEFORE(block, new_block, next);
+    } else {
+        QTAILQ_INSERT_TAIL(&ram_list.blocks, new_block, next);
+    }
     ram_list.mru_block = NULL;
 
+    ram_list.version++;
+    qemu_mutex_unlock_ramlist();
+
     ram_list.phys_dirty = g_realloc(ram_list.phys_dirty,
                                        last_ram_offset() >> TARGET_PAGE_BITS);
     memset(ram_list.phys_dirty + (new_block->offset >> TARGET_PAGE_BITS),
@@ -1070,24 +1098,31 @@ void qemu_ram_free_from_ptr(ram_addr_t addr)
 {
     RAMBlock *block;
 
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    /* This assumes the iothread lock is taken here too.  */
+    qemu_mutex_lock_ramlist();
+    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
         if (addr == block->offset) {
-            QLIST_REMOVE(block, next);
+            QTAILQ_REMOVE(&ram_list.blocks, block, next);
             ram_list.mru_block = NULL;
+            ram_list.version++;
             g_free(block);
-            return;
+            break;
         }
     }
+    qemu_mutex_unlock_ramlist();
 }
 
 void qemu_ram_free(ram_addr_t addr)
 {
     RAMBlock *block;
 
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    /* This assumes the iothread lock is taken here too.  */
+    qemu_mutex_lock_ramlist();
+    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
         if (addr == block->offset) {
-            QLIST_REMOVE(block, next);
+            QTAILQ_REMOVE(&ram_list.blocks, block, next);
             ram_list.mru_block = NULL;
+            ram_list.version++;
             if (block->flags & RAM_PREALLOC_MASK) {
                 ;
             } else if (mem_path) {
@@ -1113,9 +1148,10 @@ void qemu_ram_free(ram_addr_t addr)
 #endif
             }
             g_free(block);
-            return;
+            break;
         }
     }
+    qemu_mutex_unlock_ramlist();
 
 }
 
@@ -1127,7 +1163,7 @@ void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
     int flags;
     void *area, *vaddr;
 
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
         offset = addr - block->offset;
         if (offset < block->length) {
             vaddr = block->host + offset;
@@ -1193,11 +1229,12 @@ void *qemu_get_ram_ptr(ram_addr_t addr)
 {
     RAMBlock *block;
 
+    /* The list is protected by the iothread lock here.  */
     block = ram_list.mru_block;
     if (block && addr - block->offset < block->length) {
         goto found;
     }
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
         if (addr - block->offset < block->length) {
             goto found;
         }
@@ -1232,7 +1269,8 @@ static void *qemu_safe_ram_ptr(ram_addr_t addr)
 {
     RAMBlock *block;
 
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    /* The list is protected by the iothread lock here.  */
+    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
         if (addr - block->offset < block->length) {
             if (xen_enabled()) {
                 /* We need to check if the requested address is in the RAM
@@ -1268,7 +1306,7 @@ static void *qemu_ram_ptr_length(ram_addr_t addr, ram_addr_t *size)
     } else {
         RAMBlock *block;
 
-        QLIST_FOREACH(block, &ram_list.blocks, next) {
+        QTAILQ_FOREACH(block, &ram_list.blocks, next) {
             if (addr - block->offset < block->length) {
                 if (addr - block->offset + *size > block->length)
                     *size = block->length - addr + block->offset;
@@ -1296,7 +1334,7 @@ int qemu_ram_addr_from_host(void *ptr, ram_addr_t *ram_addr)
         return 0;
     }
 
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
         /* This case append when the block is not mapped. */
         if (block->host == NULL) {
             continue;