diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index f2ce5cd45a2ca984473cb40c26ada71e7591bb04..946ccb260be2449368ba54561a39d6f6fcd54923 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -45,6 +45,7 @@
 #include "qemu/guest-random.h"
 #include "sysemu/hw_accel.h"
 #include "kvm-cpus.h"
+#include "sysemu/dirtylimit.h"
 
 #include "hw/boards.h"
 
@@ -493,6 +494,7 @@ int kvm_init_vcpu(CPUState *cpu, Error **errp)
     cpu->kvm_state = s;
     cpu->vcpu_dirty = true;
     cpu->dirty_pages = 0;
+    cpu->throttle_us_per_full = 0;
 
     mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
     if (mmap_size < 0) {
@@ -773,17 +775,20 @@ static uint32_t kvm_dirty_ring_reap_one(KVMState *s, CPUState *cpu)
 }
 
 /* Must be with slots_lock held */
-static uint64_t kvm_dirty_ring_reap_locked(KVMState *s)
+static uint64_t kvm_dirty_ring_reap_locked(KVMState *s, CPUState* cpu)
 {
     int ret;
-    CPUState *cpu;
     uint64_t total = 0;
     int64_t stamp;
 
     stamp = get_clock();
 
-    CPU_FOREACH(cpu) {
-        total += kvm_dirty_ring_reap_one(s, cpu);
+    if (cpu) {
+        total = kvm_dirty_ring_reap_one(s, cpu);
+    } else {
+        CPU_FOREACH(cpu) {
+            total += kvm_dirty_ring_reap_one(s, cpu);
+        }
     }
 
     if (total) {
@@ -804,7 +809,7 @@ static uint64_t kvm_dirty_ring_reap_locked(KVMState *s)
  * Currently for simplicity, we must hold BQL before calling this.  We can
  * consider to drop the BQL if we're clear with all the race conditions.
  */
-static uint64_t kvm_dirty_ring_reap(KVMState *s)
+static uint64_t kvm_dirty_ring_reap(KVMState *s, CPUState *cpu)
 {
     uint64_t total;
 
@@ -824,7 +829,7 @@ static uint64_t kvm_dirty_ring_reap(KVMState *s)
      *     reset below.
      */
     kvm_slots_lock();
-    total = kvm_dirty_ring_reap_locked(s);
+    total = kvm_dirty_ring_reap_locked(s, cpu);
     kvm_slots_unlock();
 
     return total;
@@ -871,7 +876,7 @@ static void kvm_dirty_ring_flush(void)
      * vcpus out in a synchronous way.
      */
     kvm_cpu_synchronize_kick_all();
-    kvm_dirty_ring_reap(kvm_state);
+    kvm_dirty_ring_reap(kvm_state, NULL);
     trace_kvm_dirty_ring_flush(1);
 }
 
@@ -1415,7 +1420,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
                  * Not easy.  Let's cross the fingers until it's fixed.
                  */
                 if (kvm_state->kvm_dirty_ring_size) {
-                    kvm_dirty_ring_reap_locked(kvm_state);
+                    kvm_dirty_ring_reap_locked(kvm_state, NULL);
                 } else {
                     kvm_slot_get_dirty_log(kvm_state, mem);
                 }
@@ -1483,11 +1488,16 @@ static void *kvm_dirty_ring_reaper_thread(void *data)
          */
         sleep(1);
 
+        /* keep sleeping so that dirtylimit not be interfered by reaper */
+        if (dirtylimit_in_service()) {
+            continue;
+        }
+
         trace_kvm_dirty_ring_reaper("wakeup");
         r->reaper_state = KVM_DIRTY_RING_REAPER_REAPING;
 
         qemu_mutex_lock_iothread();
-        kvm_dirty_ring_reap(s);
+        kvm_dirty_ring_reap(s, NULL);
         qemu_mutex_unlock_iothread();
 
         r->reaper_iteration++;
@@ -2329,6 +2339,11 @@ bool kvm_dirty_ring_enabled(void)
     return kvm_state->kvm_dirty_ring_size ? true : false;
 }
 
+uint32_t kvm_dirty_ring_size(void)
+{
+    return kvm_state->kvm_dirty_ring_size;
+}
+
 static int kvm_init(MachineState *ms)
 {
     MachineClass *mc = MACHINE_GET_CLASS(ms);
@@ -2957,8 +2972,19 @@ int kvm_cpu_exec(CPUState *cpu)
              */
             trace_kvm_dirty_ring_full(cpu->cpu_index);
             qemu_mutex_lock_iothread();
-            kvm_dirty_ring_reap(kvm_state);
+            /*
+             * We throttle vCPU by making it sleep once it exit from kernel
+             * due to dirty ring full. In the dirtylimit scenario, reaping
+             * all vCPUs after a single vCPU dirty ring get full result in
+             * the miss of sleep, so just reap the ring-fulled vCPU.
+             */
+            if (dirtylimit_in_service()) {
+                kvm_dirty_ring_reap(kvm_state, cpu);
+            } else {
+                kvm_dirty_ring_reap(kvm_state, NULL);
+            }
             qemu_mutex_unlock_iothread();
+            dirtylimit_vcpu_execute(cpu);
             ret = 0;
             break;
         case KVM_EXIT_SYSTEM_EVENT:
diff --git a/accel/stubs/kvm-stub.c b/accel/stubs/kvm-stub.c
index 5319573e0032a336612a822cb15a60ec113c9785..1128cb2928a0aa375b2f474665b99f2fc5ad7665 100644
--- a/accel/stubs/kvm-stub.c
+++ b/accel/stubs/kvm-stub.c
@@ -152,4 +152,9 @@ bool kvm_dirty_ring_enabled(void)
 {
     return false;
 }
+
+uint32_t kvm_dirty_ring_size(void)
+{
+    return 0;
+}
 #endif
diff --git a/cpus-common.c b/cpus-common.c
index 6e73d3e58dac6b6f4e117d56f5020d8496f17439..31c6415f37c64ef62d4e9a9d41be6b0263e5716e 100644
--- a/cpus-common.c
+++ b/cpus-common.c
@@ -73,6 +73,12 @@ static int cpu_get_free_index(void)
 }
 
 CPUTailQ cpus = QTAILQ_HEAD_INITIALIZER(cpus);
+static unsigned int cpu_list_generation_id;
+
+unsigned int cpu_list_generation_id_get(void)
+{
+    return cpu_list_generation_id;
+}
 
 void cpu_list_add(CPUState *cpu)
 {
@@ -84,6 +90,7 @@ void cpu_list_add(CPUState *cpu)
         assert(!cpu_index_auto_assigned);
     }
     QTAILQ_INSERT_TAIL_RCU(&cpus, cpu, node);
+    cpu_list_generation_id++;
 }
 
 void cpu_list_remove(CPUState *cpu)
@@ -96,6 +103,7 @@ void cpu_list_remove(CPUState *cpu)
 
     QTAILQ_REMOVE_RCU(&cpus, cpu, node);
     cpu->cpu_index = UNASSIGNED_CPU_INDEX;
+    cpu_list_generation_id++;
 }
 
 CPUState *qemu_get_cpu(int index)
diff --git a/hmp-commands-info.hx b/hmp-commands-info.hx
index 407a1da800cfc19376dc48e1941de9346462e7f7..5dd3001af09ead0966391cc36b7b2fb2e4389e3d 100644
--- a/hmp-commands-info.hx
+++ b/hmp-commands-info.hx
@@ -863,6 +863,19 @@ SRST
     Display the vcpu dirty rate information.
 ERST
 
+    {
+        .name       = "vcpu_dirty_limit",
+        .args_type  = "",
+        .params     = "",
+        .help       = "show dirty page limit information of all vCPU",
+        .cmd        = hmp_info_vcpu_dirty_limit,
+    },
+
+SRST
+  ``info vcpu_dirty_limit``
+    Display the vcpu dirty page limit information.
+ERST
+
 #if defined(TARGET_I386)
     {
         .name       = "sgx",
diff --git a/hmp-commands.hx b/hmp-commands.hx
index 70a9136ac2935b0cb2b2f132266196b5df6cd556..5bedee2d49547acfcda639f7cb6fe8636d643e76 100644
--- a/hmp-commands.hx
+++ b/hmp-commands.hx
@@ -1744,3 +1744,35 @@ ERST
                       "\n\t\t\t -b to specify dirty bitmap as method of calculation)",
         .cmd        = hmp_calc_dirty_rate,
     },
+
+SRST
+``set_vcpu_dirty_limit``
+  Set dirty page rate limit on virtual CPU, the information about all the
+  virtual CPU dirty limit status can be observed with ``info vcpu_dirty_limit``
+  command.
+ERST
+
+    {
+        .name       = "set_vcpu_dirty_limit",
+        .args_type  = "dirty_rate:l,cpu_index:l?",
+        .params     = "dirty_rate [cpu_index]",
+        .help       = "set dirty page rate limit, use cpu_index to set limit"
+                      "\n\t\t\t\t\t on a specified virtual cpu",
+        .cmd        = hmp_set_vcpu_dirty_limit,
+    },
+
+SRST
+``cancel_vcpu_dirty_limit``
+  Cancel dirty page rate limit on virtual CPU, the information about all the
+  virtual CPU dirty limit status can be observed with ``info vcpu_dirty_limit``
+  command.
+ERST
+
+    {
+        .name       = "cancel_vcpu_dirty_limit",
+        .args_type  = "cpu_index:l?",
+        .params     = "[cpu_index]",
+        .help       = "cancel dirty page rate limit, use cpu_index to cancel"
+                      "\n\t\t\t\t\t limit on a specified virtual cpu",
+        .cmd        = hmp_cancel_vcpu_dirty_limit,
+    },
diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h
index 039d422bf4cb40d4bfd5f37296c0b4e3f699f248..cdee668f20da88e3c4ccb1b9574b4ec22f10e13b 100644
--- a/include/exec/cpu-common.h
+++ b/include/exec/cpu-common.h
@@ -11,6 +11,7 @@
 void qemu_init_cpu_list(void);
 void cpu_list_lock(void);
 void cpu_list_unlock(void);
+unsigned int cpu_list_generation_id_get(void);
 
 void tcg_flush_softmmu_tlb(CPUState *cs);
 
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 3e84d62e40d0672ea63f3e9dcf83392f86c84330..4326d74b95d7249178edb606d58fd78d472e3c30 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -69,7 +69,10 @@ static inline void fuzz_dma_read_cb(size_t addr,
 /* Dirty tracking enabled because measuring dirty rate */
 #define GLOBAL_DIRTY_DIRTY_RATE (1U << 1)
 
-#define GLOBAL_DIRTY_MASK  (0x3)
+/* Dirty tracking enabled because dirty limit */
+#define GLOBAL_DIRTY_LIMIT      (1U << 2)
+
+#define GLOBAL_DIRTY_MASK  (0x7)
 
 extern unsigned int global_dirty_tracking;
 
diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h
index e948e81f1a972898790f52ce274398fe591e1d55..9631c1e2f6da55ce44eddb2165c9c55ac7504632 100644
--- a/include/hw/core/cpu.h
+++ b/include/hw/core/cpu.h
@@ -411,6 +411,12 @@ struct CPUState {
      */
     bool throttle_thread_scheduled;
 
+    /*
+     * Sleep throttle_us_per_full microseconds once dirty ring is full
+     * if dirty page rate limit is enabled.
+     */
+    int64_t throttle_us_per_full;
+
     bool ignore_memory_transaction_failures;
 
     struct hax_vcpu_state *hax_vcpu;
diff --git a/include/monitor/hmp.h b/include/monitor/hmp.h
index 96d014826ada85ab9e9e743c5a7bffbcf50ab750..478820e54fe3023192003636ee651c8b2afa6211 100644
--- a/include/monitor/hmp.h
+++ b/include/monitor/hmp.h
@@ -131,6 +131,9 @@ void hmp_replay_delete_break(Monitor *mon, const QDict *qdict);
 void hmp_replay_seek(Monitor *mon, const QDict *qdict);
 void hmp_info_dirty_rate(Monitor *mon, const QDict *qdict);
 void hmp_calc_dirty_rate(Monitor *mon, const QDict *qdict);
+void hmp_set_vcpu_dirty_limit(Monitor *mon, const QDict *qdict);
+void hmp_cancel_vcpu_dirty_limit(Monitor *mon, const QDict *qdict);
+void hmp_info_vcpu_dirty_limit(Monitor *mon, const QDict *qdict);
 void hmp_human_readable_text_helper(Monitor *mon,
                                     HumanReadableText *(*qmp_handler)(Error **));
 
diff --git a/include/sysemu/dirtylimit.h b/include/sysemu/dirtylimit.h
new file mode 100644
index 0000000000000000000000000000000000000000..8d2c1f3a6b9c66a3a3827623ed14686ad0a4f8af
--- /dev/null
+++ b/include/sysemu/dirtylimit.h
@@ -0,0 +1,37 @@
+/*
+ * Dirty page rate limit common functions
+ *
+ * Copyright (c) 2022 CHINA TELECOM CO.,LTD.
+ *
+ * Authors:
+ *  Hyman Huang(黄勇) <huangy81@chinatelecom.cn>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#ifndef QEMU_DIRTYRLIMIT_H
+#define QEMU_DIRTYRLIMIT_H
+
+#define DIRTYLIMIT_CALC_TIME_MS         1000    /* 1000ms */
+
+int64_t vcpu_dirty_rate_get(int cpu_index);
+void vcpu_dirty_rate_stat_start(void);
+void vcpu_dirty_rate_stat_stop(void);
+void vcpu_dirty_rate_stat_initialize(void);
+void vcpu_dirty_rate_stat_finalize(void);
+
+void dirtylimit_state_lock(void);
+void dirtylimit_state_unlock(void);
+void dirtylimit_state_initialize(void);
+void dirtylimit_state_finalize(void);
+bool dirtylimit_in_service(void);
+bool dirtylimit_vcpu_index_valid(int cpu_index);
+void dirtylimit_process(void);
+void dirtylimit_change(bool start);
+void dirtylimit_set_vcpu(int cpu_index,
+                         uint64_t quota,
+                         bool enable);
+void dirtylimit_set_all(uint64_t quota,
+                        bool enable);
+void dirtylimit_vcpu_execute(CPUState *cpu);
+#endif
diff --git a/include/sysemu/dirtyrate.h b/include/sysemu/dirtyrate.h
new file mode 100644
index 0000000000000000000000000000000000000000..4d3b9a4902211a1f8d475054fc244dddae009bcf
--- /dev/null
+++ b/include/sysemu/dirtyrate.h
@@ -0,0 +1,28 @@
+/*
+ * dirty page rate helper functions
+ *
+ * Copyright (c) 2022 CHINA TELECOM CO.,LTD.
+ *
+ * Authors:
+ *  Hyman Huang(黄勇) <huangy81@chinatelecom.cn>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_DIRTYRATE_H
+#define QEMU_DIRTYRATE_H
+
+typedef struct VcpuStat {
+    int nvcpu; /* number of vcpu */
+    DirtyRateVcpu *rates; /* array of dirty rate for each vcpu */
+} VcpuStat;
+
+int64_t vcpu_calculate_dirtyrate(int64_t calc_time_ms,
+                                 VcpuStat *stat,
+                                 unsigned int flag,
+                                 bool one_shot);
+
+void global_dirty_log_change(unsigned int flag,
+                             bool start);
+#endif
diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h
index 2623775c27e436619b287191ba2d7c1ee8e17a02..19c5c8402ada0cd6688488d8235c1a06739a3136 100644
--- a/include/sysemu/kvm.h
+++ b/include/sysemu/kvm.h
@@ -549,4 +549,6 @@ bool kvm_cpu_check_are_resettable(void);
 bool kvm_arch_cpu_check_are_resettable(void);
 
 bool kvm_dirty_ring_enabled(void);
+
+uint32_t kvm_dirty_ring_size(void);
 #endif
diff --git a/migration/dirtyrate.c b/migration/dirtyrate.c
index 8043bc794681d2f841bcdb996fc23fa466875d61..c449095fc31776acea96c737d5a499f3ea635656 100644
--- a/migration/dirtyrate.c
+++ b/migration/dirtyrate.c
@@ -46,7 +46,7 @@ static struct DirtyRateStat DirtyStat;
 static DirtyRateMeasureMode dirtyrate_mode =
                 DIRTY_RATE_MEASURE_MODE_PAGE_SAMPLING;
 
-static int64_t set_sample_page_period(int64_t msec, int64_t initial_time)
+static int64_t dirty_stat_wait(int64_t msec, int64_t initial_time)
 {
     int64_t current_time;
 
@@ -60,6 +60,132 @@ static int64_t set_sample_page_period(int64_t msec, int64_t initial_time)
     return msec;
 }
 
+static inline void record_dirtypages(DirtyPageRecord *dirty_pages,
+                                     CPUState *cpu, bool start)
+{
+    if (start) {
+        dirty_pages[cpu->cpu_index].start_pages = cpu->dirty_pages;
+    } else {
+        dirty_pages[cpu->cpu_index].end_pages = cpu->dirty_pages;
+    }
+}
+
+static int64_t do_calculate_dirtyrate(DirtyPageRecord dirty_pages,
+                                      int64_t calc_time_ms)
+{
+    uint64_t memory_size_MB;
+    uint64_t increased_dirty_pages =
+        dirty_pages.end_pages - dirty_pages.start_pages;
+
+    memory_size_MB = (increased_dirty_pages * TARGET_PAGE_SIZE) >> 20;
+
+    return memory_size_MB * 1000 / calc_time_ms;
+}
+
+void global_dirty_log_change(unsigned int flag, bool start)
+{
+    qemu_mutex_lock_iothread();
+    if (start) {
+        memory_global_dirty_log_start(flag);
+    } else {
+        memory_global_dirty_log_stop(flag);
+    }
+    qemu_mutex_unlock_iothread();
+}
+
+/*
+ * global_dirty_log_sync
+ * 1. sync dirty log from kvm
+ * 2. stop dirty tracking if needed.
+ */
+static void global_dirty_log_sync(unsigned int flag, bool one_shot)
+{
+    qemu_mutex_lock_iothread();
+    memory_global_dirty_log_sync();
+    if (one_shot) {
+        memory_global_dirty_log_stop(flag);
+    }
+    qemu_mutex_unlock_iothread();
+}
+
+static DirtyPageRecord *vcpu_dirty_stat_alloc(VcpuStat *stat)
+{
+    CPUState *cpu;
+    DirtyPageRecord *records;
+    int nvcpu = 0;
+
+    CPU_FOREACH(cpu) {
+        nvcpu++;
+    }
+
+    stat->nvcpu = nvcpu;
+    stat->rates = g_malloc0(sizeof(DirtyRateVcpu) * nvcpu);
+
+    records = g_malloc0(sizeof(DirtyPageRecord) * nvcpu);
+
+    return records;
+}
+
+static void vcpu_dirty_stat_collect(VcpuStat *stat,
+                                    DirtyPageRecord *records,
+                                    bool start)
+{
+    CPUState *cpu;
+
+    CPU_FOREACH(cpu) {
+        record_dirtypages(records, cpu, start);
+    }
+}
+
+int64_t vcpu_calculate_dirtyrate(int64_t calc_time_ms,
+                                 VcpuStat *stat,
+                                 unsigned int flag,
+                                 bool one_shot)
+{
+    DirtyPageRecord *records;
+    int64_t init_time_ms;
+    int64_t duration;
+    int64_t dirtyrate;
+    int i = 0;
+    unsigned int gen_id;
+
+retry:
+    init_time_ms = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+
+    cpu_list_lock();
+    gen_id = cpu_list_generation_id_get();
+    records = vcpu_dirty_stat_alloc(stat);
+    vcpu_dirty_stat_collect(stat, records, true);
+    cpu_list_unlock();
+
+    duration = dirty_stat_wait(calc_time_ms, init_time_ms);
+
+    global_dirty_log_sync(flag, one_shot);
+
+    cpu_list_lock();
+    if (gen_id != cpu_list_generation_id_get()) {
+        g_free(records);
+        g_free(stat->rates);
+        cpu_list_unlock();
+        goto retry;
+    }
+    vcpu_dirty_stat_collect(stat, records, false);
+    cpu_list_unlock();
+
+    for (i = 0; i < stat->nvcpu; i++) {
+        dirtyrate = do_calculate_dirtyrate(records[i], duration);
+
+        stat->rates[i].id = i;
+        stat->rates[i].dirty_rate = dirtyrate;
+
+        trace_dirtyrate_do_calculate_vcpu(i, dirtyrate);
+    }
+
+    g_free(records);
+
+    return duration;
+}
+
 static bool is_sample_period_valid(int64_t sec)
 {
     if (sec < MIN_FETCH_DIRTYRATE_TIME_SEC ||
@@ -396,44 +522,6 @@ static bool compare_page_hash_info(struct RamblockDirtyInfo *info,
     return true;
 }
 
-static inline void record_dirtypages(DirtyPageRecord *dirty_pages,
-                                     CPUState *cpu, bool start)
-{
-    if (start) {
-        dirty_pages[cpu->cpu_index].start_pages = cpu->dirty_pages;
-    } else {
-        dirty_pages[cpu->cpu_index].end_pages = cpu->dirty_pages;
-    }
-}
-
-static void dirtyrate_global_dirty_log_start(void)
-{
-    qemu_mutex_lock_iothread();
-    memory_global_dirty_log_start(GLOBAL_DIRTY_DIRTY_RATE);
-    qemu_mutex_unlock_iothread();
-}
-
-static void dirtyrate_global_dirty_log_stop(void)
-{
-    qemu_mutex_lock_iothread();
-    memory_global_dirty_log_sync();
-    memory_global_dirty_log_stop(GLOBAL_DIRTY_DIRTY_RATE);
-    qemu_mutex_unlock_iothread();
-}
-
-static int64_t do_calculate_dirtyrate_vcpu(DirtyPageRecord dirty_pages)
-{
-    uint64_t memory_size_MB;
-    int64_t time_s;
-    uint64_t increased_dirty_pages =
-        dirty_pages.end_pages - dirty_pages.start_pages;
-
-    memory_size_MB = (increased_dirty_pages * TARGET_PAGE_SIZE) >> 20;
-    time_s = DirtyStat.calc_time;
-
-    return memory_size_MB / time_s;
-}
-
 static inline void record_dirtypages_bitmap(DirtyPageRecord *dirty_pages,
                                             bool start)
 {
@@ -444,11 +532,6 @@ static inline void record_dirtypages_bitmap(DirtyPageRecord *dirty_pages,
     }
 }
 
-static void do_calculate_dirtyrate_bitmap(DirtyPageRecord dirty_pages)
-{
-    DirtyStat.dirty_rate = do_calculate_dirtyrate_vcpu(dirty_pages);
-}
-
 static inline void dirtyrate_manual_reset_protect(void)
 {
     RAMBlock *block = NULL;
@@ -492,71 +575,49 @@ static void calculate_dirtyrate_dirty_bitmap(struct DirtyRateConfig config)
     DirtyStat.start_time = start_time / 1000;
 
     msec = config.sample_period_seconds * 1000;
-    msec = set_sample_page_period(msec, start_time);
+    msec = dirty_stat_wait(msec, start_time);
     DirtyStat.calc_time = msec / 1000;
 
     /*
-     * dirtyrate_global_dirty_log_stop do two things.
+     * do two things.
      * 1. fetch dirty bitmap from kvm
      * 2. stop dirty tracking
      */
-    dirtyrate_global_dirty_log_stop();
+    global_dirty_log_sync(GLOBAL_DIRTY_DIRTY_RATE, true);
 
     record_dirtypages_bitmap(&dirty_pages, false);
 
-    do_calculate_dirtyrate_bitmap(dirty_pages);
+    DirtyStat.dirty_rate = do_calculate_dirtyrate(dirty_pages, msec);
 }
 
 static void calculate_dirtyrate_dirty_ring(struct DirtyRateConfig config)
 {
-    CPUState *cpu;
-    int64_t msec = 0;
-    int64_t start_time;
+    int64_t duration;
     uint64_t dirtyrate = 0;
     uint64_t dirtyrate_sum = 0;
-    DirtyPageRecord *dirty_pages;
-    int nvcpu = 0;
     int i = 0;
 
-    CPU_FOREACH(cpu) {
-        nvcpu++;
-    }
-
-    dirty_pages = g_new(DirtyPageRecord, nvcpu);
-
-    DirtyStat.dirty_ring.nvcpu = nvcpu;
-    DirtyStat.dirty_ring.rates = g_new(DirtyRateVcpu, nvcpu);
-
-    dirtyrate_global_dirty_log_start();
-
-    CPU_FOREACH(cpu) {
-        record_dirtypages(dirty_pages, cpu, true);
-    }
-
-    start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
-    DirtyStat.start_time = start_time / 1000;
+    /* start log sync */
+    global_dirty_log_change(GLOBAL_DIRTY_DIRTY_RATE, true);
 
-    msec = config.sample_period_seconds * 1000;
-    msec = set_sample_page_period(msec, start_time);
-    DirtyStat.calc_time = msec / 1000;
+    DirtyStat.start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME) / 1000;
 
-    dirtyrate_global_dirty_log_stop();
+    /* calculate vcpu dirtyrate */
+    duration = vcpu_calculate_dirtyrate(config.sample_period_seconds * 1000,
+                                        &DirtyStat.dirty_ring,
+                                        GLOBAL_DIRTY_DIRTY_RATE,
+                                        true);
 
-    CPU_FOREACH(cpu) {
-        record_dirtypages(dirty_pages, cpu, false);
-    }
+    DirtyStat.calc_time = duration / 1000;
 
+    /* calculate vm dirtyrate */
     for (i = 0; i < DirtyStat.dirty_ring.nvcpu; i++) {
-        dirtyrate = do_calculate_dirtyrate_vcpu(dirty_pages[i]);
-        trace_dirtyrate_do_calculate_vcpu(i, dirtyrate);
-
-        DirtyStat.dirty_ring.rates[i].id = i;
+        dirtyrate = DirtyStat.dirty_ring.rates[i].dirty_rate;
         DirtyStat.dirty_ring.rates[i].dirty_rate = dirtyrate;
         dirtyrate_sum += dirtyrate;
     }
 
     DirtyStat.dirty_rate = dirtyrate_sum;
-    g_free(dirty_pages);
 }
 
 static void calculate_dirtyrate_sample_vm(struct DirtyRateConfig config)
@@ -574,7 +635,7 @@ static void calculate_dirtyrate_sample_vm(struct DirtyRateConfig config)
     rcu_read_unlock();
 
     msec = config.sample_period_seconds * 1000;
-    msec = set_sample_page_period(msec, initial_time);
+    msec = dirty_stat_wait(msec, initial_time);
     DirtyStat.start_time = initial_time / 1000;
     DirtyStat.calc_time = msec / 1000;
 
diff --git a/migration/dirtyrate.h b/migration/dirtyrate.h
index 69d4c5b8655f5fa6ae7bd31a97e46e05cf260d27..594a5c0bb64c296bd294ed37949e095ddf9209cd 100644
--- a/migration/dirtyrate.h
+++ b/migration/dirtyrate.h
@@ -13,6 +13,8 @@
 #ifndef QEMU_MIGRATION_DIRTYRATE_H
 #define QEMU_MIGRATION_DIRTYRATE_H
 
+#include "sysemu/dirtyrate.h"
+
 /*
  * Sample 512 pages per GB as default.
  */
@@ -65,11 +67,6 @@ typedef struct SampleVMStat {
     uint64_t total_block_mem_MB; /* size of total sampled pages in MB */
 } SampleVMStat;
 
-typedef struct VcpuStat {
-    int nvcpu; /* number of vcpu */
-    DirtyRateVcpu *rates; /* array of dirty rate for each vcpu */
-} VcpuStat;
-
 /*
  * Store calculation statistics for each measure.
  */
diff --git a/qapi/migration.json b/qapi/migration.json
index d4ebc5f02848b87bc5f5803820df6f13ad6f0e4b..6b3b86386093a51e89f280645d4dd288da2919d5 100644
--- a/qapi/migration.json
+++ b/qapi/migration.json
@@ -1874,6 +1874,86 @@
 ##
 { 'command': 'query-dirty-rate', 'returns': 'DirtyRateInfo' }
 
+##
+# @DirtyLimitInfo:
+#
+# Dirty page rate limit information of a virtual CPU.
+#
+# @cpu-index: index of a virtual CPU.
+#
+# @limit-rate: upper limit of dirty page rate (MB/s) for a virtual
+#              CPU, 0 means unlimited.
+#
+# @current-rate: current dirty page rate (MB/s) for a virtual CPU.
+#
+# Since: 7.1
+#
+##
+{ 'struct': 'DirtyLimitInfo',
+  'data': { 'cpu-index': 'int',
+            'limit-rate': 'uint64',
+            'current-rate': 'uint64' } }
+
+##
+# @set-vcpu-dirty-limit:
+#
+# Set the upper limit of dirty page rate for virtual CPUs.
+#
+# Requires KVM with accelerator property "dirty-ring-size" set.
+# A virtual CPU's dirty page rate is a measure of its memory load.
+# To observe dirty page rates, use @calc-dirty-rate.
+#
+# @cpu-index: index of a virtual CPU, default is all.
+#
+# @dirty-rate: upper limit of dirty page rate (MB/s) for virtual CPUs.
+#
+# Since: 7.1
+#
+# Example:
+#   {"execute": "set-vcpu-dirty-limit"}
+#    "arguments": { "dirty-rate": 200,
+#                   "cpu-index": 1 } }
+#
+##
+{ 'command': 'set-vcpu-dirty-limit',
+  'data': { '*cpu-index': 'int',
+            'dirty-rate': 'uint64' } }
+
+##
+# @cancel-vcpu-dirty-limit:
+#
+# Cancel the upper limit of dirty page rate for virtual CPUs.
+#
+# Cancel the dirty page limit for the vCPU which has been set with
+# set-vcpu-dirty-limit command. Note that this command requires
+# support from dirty ring, same as the "set-vcpu-dirty-limit".
+#
+# @cpu-index: index of a virtual CPU, default is all.
+#
+# Since: 7.1
+#
+# Example:
+#   {"execute": "cancel-vcpu-dirty-limit"}
+#    "arguments": { "cpu-index": 1 } }
+#
+##
+{ 'command': 'cancel-vcpu-dirty-limit',
+  'data': { '*cpu-index': 'int'} }
+
+##
+# @query-vcpu-dirty-limit:
+#
+# Returns information about virtual CPU dirty page rate limits, if any.
+#
+# Since: 7.1
+#
+# Example:
+#   {"execute": "query-vcpu-dirty-limit"}
+#
+##
+{ 'command': 'query-vcpu-dirty-limit',
+  'returns': [ 'DirtyLimitInfo' ] }
+
 ##
 # @snapshot-save:
 #
diff --git a/softmmu/dirtylimit.c b/softmmu/dirtylimit.c
new file mode 100644
index 0000000000000000000000000000000000000000..8d98cb7f2c1c5735410a42ec4dc820df5f370a34
--- /dev/null
+++ b/softmmu/dirtylimit.c
@@ -0,0 +1,601 @@
+/*
+ * Dirty page rate limit implementation code
+ *
+ * Copyright (c) 2022 CHINA TELECOM CO.,LTD.
+ *
+ * Authors:
+ *  Hyman Huang(黄勇) <huangy81@chinatelecom.cn>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/main-loop.h"
+#include "qapi/qapi-commands-migration.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/error.h"
+#include "sysemu/dirtyrate.h"
+#include "sysemu/dirtylimit.h"
+#include "monitor/hmp.h"
+#include "monitor/monitor.h"
+#include "exec/memory.h"
+#include "hw/boards.h"
+#include "sysemu/kvm.h"
+#include "trace.h"
+
+/*
+ * Dirtylimit stop working if dirty page rate error
+ * value less than DIRTYLIMIT_TOLERANCE_RANGE
+ */
+#define DIRTYLIMIT_TOLERANCE_RANGE  25  /* MB/s */
+/*
+ * Plus or minus vcpu sleep time linearly if dirty
+ * page rate error value percentage over
+ * DIRTYLIMIT_LINEAR_ADJUSTMENT_PCT.
+ * Otherwise, plus or minus a fixed vcpu sleep time.
+ */
+#define DIRTYLIMIT_LINEAR_ADJUSTMENT_PCT     50
+/*
+ * Max vcpu sleep time percentage during a cycle
+ * composed of dirty ring full and sleep time.
+ */
+#define DIRTYLIMIT_THROTTLE_PCT_MAX 99
+
+struct {
+    VcpuStat stat;
+    bool running;
+    QemuThread thread;
+} *vcpu_dirty_rate_stat;
+
+typedef struct VcpuDirtyLimitState {
+    int cpu_index;
+    bool enabled;
+    /*
+     * Quota dirty page rate, unit is MB/s
+     * zero if not enabled.
+     */
+    uint64_t quota;
+} VcpuDirtyLimitState;
+
+struct {
+    VcpuDirtyLimitState *states;
+    /* Max cpus number configured by user */
+    int max_cpus;
+    /* Number of vcpu under dirtylimit */
+    int limited_nvcpu;
+} *dirtylimit_state;
+
+/* protect dirtylimit_state */
+static QemuMutex dirtylimit_mutex;
+
+/* dirtylimit thread quit if dirtylimit_quit is true */
+static bool dirtylimit_quit;
+
+static void vcpu_dirty_rate_stat_collect(void)
+{
+    VcpuStat stat;
+    int i = 0;
+
+    /* calculate vcpu dirtyrate */
+    vcpu_calculate_dirtyrate(DIRTYLIMIT_CALC_TIME_MS,
+                             &stat,
+                             GLOBAL_DIRTY_LIMIT,
+                             false);
+
+    for (i = 0; i < stat.nvcpu; i++) {
+        vcpu_dirty_rate_stat->stat.rates[i].id = i;
+        vcpu_dirty_rate_stat->stat.rates[i].dirty_rate =
+            stat.rates[i].dirty_rate;
+    }
+
+    free(stat.rates);
+}
+
+static void *vcpu_dirty_rate_stat_thread(void *opaque)
+{
+    rcu_register_thread();
+
+    /* start log sync */
+    global_dirty_log_change(GLOBAL_DIRTY_LIMIT, true);
+
+    while (qatomic_read(&vcpu_dirty_rate_stat->running)) {
+        vcpu_dirty_rate_stat_collect();
+        if (dirtylimit_in_service()) {
+            dirtylimit_process();
+        }
+    }
+
+    /* stop log sync */
+    global_dirty_log_change(GLOBAL_DIRTY_LIMIT, false);
+
+    rcu_unregister_thread();
+    return NULL;
+}
+
+int64_t vcpu_dirty_rate_get(int cpu_index)
+{
+    DirtyRateVcpu *rates = vcpu_dirty_rate_stat->stat.rates;
+    return qatomic_read_i64(&rates[cpu_index].dirty_rate);
+}
+
+void vcpu_dirty_rate_stat_start(void)
+{
+    if (qatomic_read(&vcpu_dirty_rate_stat->running)) {
+        return;
+    }
+
+    qatomic_set(&vcpu_dirty_rate_stat->running, 1);
+    qemu_thread_create(&vcpu_dirty_rate_stat->thread,
+                       "dirtyrate-stat",
+                       vcpu_dirty_rate_stat_thread,
+                       NULL,
+                       QEMU_THREAD_JOINABLE);
+}
+
+void vcpu_dirty_rate_stat_stop(void)
+{
+    qatomic_set(&vcpu_dirty_rate_stat->running, 0);
+    dirtylimit_state_unlock();
+    qemu_mutex_unlock_iothread();
+    qemu_thread_join(&vcpu_dirty_rate_stat->thread);
+    qemu_mutex_lock_iothread();
+    dirtylimit_state_lock();
+}
+
+void vcpu_dirty_rate_stat_initialize(void)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+    int max_cpus = ms->smp.max_cpus;
+
+    vcpu_dirty_rate_stat =
+        g_malloc0(sizeof(*vcpu_dirty_rate_stat));
+
+    vcpu_dirty_rate_stat->stat.nvcpu = max_cpus;
+    vcpu_dirty_rate_stat->stat.rates =
+        g_malloc0(sizeof(DirtyRateVcpu) * max_cpus);
+
+    vcpu_dirty_rate_stat->running = false;
+}
+
+void vcpu_dirty_rate_stat_finalize(void)
+{
+    free(vcpu_dirty_rate_stat->stat.rates);
+    vcpu_dirty_rate_stat->stat.rates = NULL;
+
+    free(vcpu_dirty_rate_stat);
+    vcpu_dirty_rate_stat = NULL;
+}
+
+void dirtylimit_state_lock(void)
+{
+    qemu_mutex_lock(&dirtylimit_mutex);
+}
+
+void dirtylimit_state_unlock(void)
+{
+    qemu_mutex_unlock(&dirtylimit_mutex);
+}
+
+static void
+__attribute__((__constructor__)) dirtylimit_mutex_init(void)
+{
+    qemu_mutex_init(&dirtylimit_mutex);
+}
+
+static inline VcpuDirtyLimitState *dirtylimit_vcpu_get_state(int cpu_index)
+{
+    return &dirtylimit_state->states[cpu_index];
+}
+
+void dirtylimit_state_initialize(void)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+    int max_cpus = ms->smp.max_cpus;
+    int i;
+
+    dirtylimit_state = g_malloc0(sizeof(*dirtylimit_state));
+
+    dirtylimit_state->states =
+            g_malloc0(sizeof(VcpuDirtyLimitState) * max_cpus);
+
+    for (i = 0; i < max_cpus; i++) {
+        dirtylimit_state->states[i].cpu_index = i;
+    }
+
+    dirtylimit_state->max_cpus = max_cpus;
+    trace_dirtylimit_state_initialize(max_cpus);
+}
+
+void dirtylimit_state_finalize(void)
+{
+    free(dirtylimit_state->states);
+    dirtylimit_state->states = NULL;
+
+    free(dirtylimit_state);
+    dirtylimit_state = NULL;
+
+    trace_dirtylimit_state_finalize();
+}
+
+bool dirtylimit_in_service(void)
+{
+    return !!dirtylimit_state;
+}
+
+bool dirtylimit_vcpu_index_valid(int cpu_index)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+
+    return !(cpu_index < 0 ||
+             cpu_index >= ms->smp.max_cpus);
+}
+
+static inline int64_t dirtylimit_dirty_ring_full_time(uint64_t dirtyrate)
+{
+    static uint64_t max_dirtyrate;
+    uint32_t dirty_ring_size = kvm_dirty_ring_size();
+    uint64_t dirty_ring_size_meory_MB =
+        dirty_ring_size * TARGET_PAGE_SIZE >> 20;
+
+    if (max_dirtyrate < dirtyrate) {
+        max_dirtyrate = dirtyrate;
+    }
+
+    return dirty_ring_size_meory_MB * 1000000 / max_dirtyrate;
+}
+
+static inline bool dirtylimit_done(uint64_t quota,
+                                   uint64_t current)
+{
+    uint64_t min, max;
+
+    min = MIN(quota, current);
+    max = MAX(quota, current);
+
+    return ((max - min) <= DIRTYLIMIT_TOLERANCE_RANGE) ? true : false;
+}
+
+static inline bool
+dirtylimit_need_linear_adjustment(uint64_t quota,
+                                  uint64_t current)
+{
+    uint64_t min, max;
+
+    min = MIN(quota, current);
+    max = MAX(quota, current);
+
+    return ((max - min) * 100 / max) > DIRTYLIMIT_LINEAR_ADJUSTMENT_PCT;
+}
+
+static void dirtylimit_set_throttle(CPUState *cpu,
+                                    uint64_t quota,
+                                    uint64_t current)
+{
+    int64_t ring_full_time_us = 0;
+    uint64_t sleep_pct = 0;
+    uint64_t throttle_us = 0;
+
+    if (current == 0) {
+        cpu->throttle_us_per_full = 0;
+        return;
+    }
+
+    ring_full_time_us = dirtylimit_dirty_ring_full_time(current);
+
+    if (dirtylimit_need_linear_adjustment(quota, current)) {
+        if (quota < current) {
+            sleep_pct = (current - quota) * 100 / current;
+            throttle_us =
+                ring_full_time_us * sleep_pct / (double)(100 - sleep_pct);
+            cpu->throttle_us_per_full += throttle_us;
+        } else {
+            sleep_pct = (quota - current) * 100 / quota;
+            throttle_us =
+                ring_full_time_us * sleep_pct / (double)(100 - sleep_pct);
+            cpu->throttle_us_per_full -= throttle_us;
+        }
+
+        trace_dirtylimit_throttle_pct(cpu->cpu_index,
+                                      sleep_pct,
+                                      throttle_us);
+    } else {
+        if (quota < current) {
+            cpu->throttle_us_per_full += ring_full_time_us / 10;
+        } else {
+            cpu->throttle_us_per_full -= ring_full_time_us / 10;
+        }
+    }
+
+    /*
+     * TODO: in the big kvm_dirty_ring_size case (eg: 65536, or other scenario),
+     *       current dirty page rate may never reach the quota, we should stop
+     *       increasing sleep time?
+     */
+    cpu->throttle_us_per_full = MIN(cpu->throttle_us_per_full,
+        ring_full_time_us * DIRTYLIMIT_THROTTLE_PCT_MAX);
+
+    cpu->throttle_us_per_full = MAX(cpu->throttle_us_per_full, 0);
+}
+
+static void dirtylimit_adjust_throttle(CPUState *cpu)
+{
+    uint64_t quota = 0;
+    uint64_t current = 0;
+    int cpu_index = cpu->cpu_index;
+
+    quota = dirtylimit_vcpu_get_state(cpu_index)->quota;
+    current = vcpu_dirty_rate_get(cpu_index);
+
+    if (!dirtylimit_done(quota, current)) {
+        dirtylimit_set_throttle(cpu, quota, current);
+    }
+
+    return;
+}
+
+void dirtylimit_process(void)
+{
+    CPUState *cpu;
+
+    if (!qatomic_read(&dirtylimit_quit)) {
+        dirtylimit_state_lock();
+
+        if (!dirtylimit_in_service()) {
+            dirtylimit_state_unlock();
+            return;
+        }
+
+        CPU_FOREACH(cpu) {
+            if (!dirtylimit_vcpu_get_state(cpu->cpu_index)->enabled) {
+                continue;
+            }
+            dirtylimit_adjust_throttle(cpu);
+        }
+        dirtylimit_state_unlock();
+    }
+}
+
+void dirtylimit_change(bool start)
+{
+    if (start) {
+        qatomic_set(&dirtylimit_quit, 0);
+    } else {
+        qatomic_set(&dirtylimit_quit, 1);
+    }
+}
+
+void dirtylimit_set_vcpu(int cpu_index,
+                         uint64_t quota,
+                         bool enable)
+{
+    trace_dirtylimit_set_vcpu(cpu_index, quota);
+
+    if (enable) {
+        dirtylimit_state->states[cpu_index].quota = quota;
+        if (!dirtylimit_vcpu_get_state(cpu_index)->enabled) {
+            dirtylimit_state->limited_nvcpu++;
+        }
+    } else {
+        dirtylimit_state->states[cpu_index].quota = 0;
+        if (dirtylimit_state->states[cpu_index].enabled) {
+            dirtylimit_state->limited_nvcpu--;
+        }
+    }
+
+    dirtylimit_state->states[cpu_index].enabled = enable;
+}
+
+void dirtylimit_set_all(uint64_t quota,
+                        bool enable)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+    int max_cpus = ms->smp.max_cpus;
+    int i;
+
+    for (i = 0; i < max_cpus; i++) {
+        dirtylimit_set_vcpu(i, quota, enable);
+    }
+}
+
+void dirtylimit_vcpu_execute(CPUState *cpu)
+{
+    if (dirtylimit_in_service() &&
+        dirtylimit_vcpu_get_state(cpu->cpu_index)->enabled &&
+        cpu->throttle_us_per_full) {
+        trace_dirtylimit_vcpu_execute(cpu->cpu_index,
+                cpu->throttle_us_per_full);
+        usleep(cpu->throttle_us_per_full);
+    }
+}
+
+static void dirtylimit_init(void)
+{
+    dirtylimit_state_initialize();
+    dirtylimit_change(true);
+    vcpu_dirty_rate_stat_initialize();
+    vcpu_dirty_rate_stat_start();
+}
+
+static void dirtylimit_cleanup(void)
+{
+    vcpu_dirty_rate_stat_stop();
+    vcpu_dirty_rate_stat_finalize();
+    dirtylimit_change(false);
+    dirtylimit_state_finalize();
+}
+
+void qmp_cancel_vcpu_dirty_limit(bool has_cpu_index,
+                                 int64_t cpu_index,
+                                 Error **errp)
+{
+    if (!kvm_enabled() || !kvm_dirty_ring_enabled()) {
+        return;
+    }
+
+    if (has_cpu_index && !dirtylimit_vcpu_index_valid(cpu_index)) {
+        error_setg(errp, "incorrect cpu index specified");
+        return;
+    }
+
+    if (!dirtylimit_in_service()) {
+        return;
+    }
+
+    dirtylimit_state_lock();
+
+    if (has_cpu_index) {
+        dirtylimit_set_vcpu(cpu_index, 0, false);
+    } else {
+        dirtylimit_set_all(0, false);
+    }
+
+    if (!dirtylimit_state->limited_nvcpu) {
+        dirtylimit_cleanup();
+    }
+
+    dirtylimit_state_unlock();
+}
+
+void hmp_cancel_vcpu_dirty_limit(Monitor *mon, const QDict *qdict)
+{
+    int64_t cpu_index = qdict_get_try_int(qdict, "cpu_index", -1);
+    Error *err = NULL;
+
+    qmp_cancel_vcpu_dirty_limit(!!(cpu_index != -1), cpu_index, &err);
+    if (err) {
+        hmp_handle_error(mon, err);
+        return;
+    }
+
+    monitor_printf(mon, "[Please use 'info vcpu_dirty_limit' to query "
+                   "dirty limit for virtual CPU]\n");
+}
+
+void qmp_set_vcpu_dirty_limit(bool has_cpu_index,
+                              int64_t cpu_index,
+                              uint64_t dirty_rate,
+                              Error **errp)
+{
+    if (!kvm_enabled() || !kvm_dirty_ring_enabled()) {
+        error_setg(errp, "dirty page limit feature requires KVM with"
+                   " accelerator property 'dirty-ring-size' set'");
+        return;
+    }
+
+    if (has_cpu_index && !dirtylimit_vcpu_index_valid(cpu_index)) {
+        error_setg(errp, "incorrect cpu index specified");
+        return;
+    }
+
+    if (!dirty_rate) {
+        qmp_cancel_vcpu_dirty_limit(has_cpu_index, cpu_index, errp);
+        return;
+    }
+
+    dirtylimit_state_lock();
+
+    if (!dirtylimit_in_service()) {
+        dirtylimit_init();
+    }
+
+    if (has_cpu_index) {
+        dirtylimit_set_vcpu(cpu_index, dirty_rate, true);
+    } else {
+        dirtylimit_set_all(dirty_rate, true);
+    }
+
+    dirtylimit_state_unlock();
+}
+
+void hmp_set_vcpu_dirty_limit(Monitor *mon, const QDict *qdict)
+{
+    int64_t dirty_rate = qdict_get_int(qdict, "dirty_rate");
+    int64_t cpu_index = qdict_get_try_int(qdict, "cpu_index", -1);
+    Error *err = NULL;
+
+    qmp_set_vcpu_dirty_limit(!!(cpu_index != -1), cpu_index, dirty_rate, &err);
+    if (err) {
+        hmp_handle_error(mon, err);
+        return;
+    }
+
+    monitor_printf(mon, "[Please use 'info vcpu_dirty_limit' to query "
+                   "dirty limit for virtual CPU]\n");
+}
+
+static struct DirtyLimitInfo *dirtylimit_query_vcpu(int cpu_index)
+{
+    DirtyLimitInfo *info = NULL;
+
+    info = g_malloc0(sizeof(*info));
+    info->cpu_index = cpu_index;
+    info->limit_rate = dirtylimit_vcpu_get_state(cpu_index)->quota;
+    info->current_rate = vcpu_dirty_rate_get(cpu_index);
+
+    return info;
+}
+
+static struct DirtyLimitInfoList *dirtylimit_query_all(void)
+{
+    int i, index;
+    DirtyLimitInfo *info = NULL;
+    DirtyLimitInfoList *head = NULL, **tail = &head;
+
+    dirtylimit_state_lock();
+
+    if (!dirtylimit_in_service()) {
+        dirtylimit_state_unlock();
+        return NULL;
+    }
+
+    for (i = 0; i < dirtylimit_state->max_cpus; i++) {
+        index = dirtylimit_state->states[i].cpu_index;
+        if (dirtylimit_vcpu_get_state(index)->enabled) {
+            info = dirtylimit_query_vcpu(index);
+            QAPI_LIST_APPEND(tail, info);
+        }
+    }
+
+    dirtylimit_state_unlock();
+
+    return head;
+}
+
+struct DirtyLimitInfoList *qmp_query_vcpu_dirty_limit(Error **errp)
+{
+    if (!dirtylimit_in_service()) {
+        return NULL;
+    }
+
+    return dirtylimit_query_all();
+}
+
+void hmp_info_vcpu_dirty_limit(Monitor *mon, const QDict *qdict)
+{
+    DirtyLimitInfoList *limit, *head, *info = NULL;
+    Error *err = NULL;
+
+    if (!dirtylimit_in_service()) {
+        monitor_printf(mon, "Dirty page limit not enabled!\n");
+        return;
+    }
+
+    info = qmp_query_vcpu_dirty_limit(&err);
+    if (err) {
+        hmp_handle_error(mon, err);
+        return;
+    }
+
+    head = info;
+    for (limit = head; limit != NULL; limit = limit->next) {
+        monitor_printf(mon, "vcpu[%"PRIi64"], limit rate %"PRIi64 " (MB/s),"
+                            " current rate %"PRIi64 " (MB/s)\n",
+                            limit->value->cpu_index,
+                            limit->value->limit_rate,
+                            limit->value->current_rate);
+    }
+
+    g_free(info);
+}
diff --git a/softmmu/meson.build b/softmmu/meson.build
index d8e03018abf5e711079516b0fb48d5c8fa9f5cb1..95029a5db21ae0cc209356f1a76ed32eb7bb558d 100644
--- a/softmmu/meson.build
+++ b/softmmu/meson.build
@@ -15,6 +15,7 @@ specific_ss.add(when: 'CONFIG_SOFTMMU', if_true: [files(
   'vl.c',
   'cpu-timers.c',
   'runstate-action.c',
+  'dirtylimit.c',
 )])
 
 specific_ss.add(when: ['CONFIG_SOFTMMU', 'CONFIG_TCG'], if_true: [files(
diff --git a/softmmu/trace-events b/softmmu/trace-events
index 9c88887b3c643e10cef84c312296a6a92b457a12..22606dc27b3107f8459d2268cf83b9436fa786d8 100644
--- a/softmmu/trace-events
+++ b/softmmu/trace-events
@@ -31,3 +31,10 @@ runstate_set(int current_state, const char *current_state_str, int new_state, co
 system_wakeup_request(int reason) "reason=%d"
 qemu_system_shutdown_request(int reason) "reason=%d"
 qemu_system_powerdown_request(void) ""
+
+#dirtylimit.c
+dirtylimit_state_initialize(int max_cpus) "dirtylimit state initialize: max cpus %d"
+dirtylimit_state_finalize(void)
+dirtylimit_throttle_pct(int cpu_index, uint64_t pct, int64_t time_us) "CPU[%d] throttle percent: %" PRIu64 ", throttle adjust time %"PRIi64 " us"
+dirtylimit_set_vcpu(int cpu_index, uint64_t quota) "CPU[%d] set dirty page rate limit %"PRIu64
+dirtylimit_vcpu_execute(int cpu_index, int64_t sleep_time_us) "CPU[%d] sleep %"PRIi64 " us"
diff --git a/tests/qtest/migration-helpers.c b/tests/qtest/migration-helpers.c
index 4ee26014b78322df9a04ad7be2c368726b9f19d8..1e594f9cb1c65c0a5573ed1ae98e66f68db79851 100644
--- a/tests/qtest/migration-helpers.c
+++ b/tests/qtest/migration-helpers.c
@@ -75,6 +75,28 @@ QDict *wait_command(QTestState *who, const char *command, ...)
     return ret;
 }
 
+/*
+ * Execute the qmp command only
+ */
+QDict *qmp_command(QTestState *who, const char *command, ...)
+{
+    va_list ap;
+    QDict *resp, *ret;
+
+    va_start(ap, command);
+    resp = qtest_vqmp(who, command, ap);
+    va_end(ap);
+
+    g_assert(!qdict_haskey(resp, "error"));
+    g_assert(qdict_haskey(resp, "return"));
+
+    ret = qdict_get_qdict(resp, "return");
+    qobject_ref(ret);
+    qobject_unref(resp);
+
+    return ret;
+}
+
 /*
  * Send QMP command "migrate".
  * Arguments are built from @fmt... (formatted like
diff --git a/tests/qtest/migration-helpers.h b/tests/qtest/migration-helpers.h
index d63bba9630f9572fe4f33a4f606474d7ee63224c..9bc809fb7505dd3322b38949828339c22a2d57b1 100644
--- a/tests/qtest/migration-helpers.h
+++ b/tests/qtest/migration-helpers.h
@@ -22,6 +22,8 @@ QDict *wait_command_fd(QTestState *who, int fd, const char *command, ...);
 GCC_FMT_ATTR(2, 3)
 QDict *wait_command(QTestState *who, const char *command, ...);
 
+QDict *qmp_command(QTestState *who, const char *command, ...);
+
 GCC_FMT_ATTR(3, 4)
 void migrate_qmp(QTestState *who, const char *uri, const char *fmt, ...);
 
diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c
index 7b42f6fd909bfbcd3ae8c6051bcaaff9016bed53..8fad247f6cd7d2f1259e692f9753d35591a48db7 100644
--- a/tests/qtest/migration-test.c
+++ b/tests/qtest/migration-test.c
@@ -23,6 +23,7 @@
 #include "qapi/qapi-visit-sockets.h"
 #include "qapi/qobject-input-visitor.h"
 #include "qapi/qobject-output-visitor.h"
+#include "qapi/qmp/qlist.h"
 
 #include "migration-helpers.h"
 #include "tests/migration/migration-test.h"
@@ -42,6 +43,12 @@ static bool uffd_feature_thread_id;
 /* A downtime where the test really should converge */
 #define CONVERGE_DOWNTIME 1000
 
+/*
+ * Dirtylimit stop working if dirty page rate error
+ * value less than DIRTYLIMIT_TOLERANCE_RANGE
+ */
+#define DIRTYLIMIT_TOLERANCE_RANGE  25  /* MB/s */
+
 #if defined(__linux__)
 #include <sys/syscall.h>
 #include <sys/vfs.h>
@@ -1394,6 +1401,253 @@ static void test_multifd_tcp_cancel(void)
     test_migrate_end(from, to2, true);
 }
 
+static void calc_dirty_rate(QTestState *who, uint64_t calc_time)
+{
+    qobject_unref(qmp_command(who,
+                  "{ 'execute': 'calc-dirty-rate',"
+                  "'arguments': { "
+                  "'calc-time': %ld,"
+                  "'mode': 'dirty-ring' }}",
+                  calc_time));
+}
+
+static QDict *query_dirty_rate(QTestState *who)
+{
+    return qmp_command(who, "{ 'execute': 'query-dirty-rate' }");
+}
+
+static void dirtylimit_set_all(QTestState *who, uint64_t dirtyrate)
+{
+    qobject_unref(qmp_command(who,
+                  "{ 'execute': 'set-vcpu-dirty-limit',"
+                  "'arguments': { "
+                  "'dirty-rate': %ld } }",
+                  dirtyrate));
+}
+
+static void cancel_vcpu_dirty_limit(QTestState *who)
+{
+    qobject_unref(qmp_command(who,
+                  "{ 'execute': 'cancel-vcpu-dirty-limit' }"));
+}
+
+static QDict *query_vcpu_dirty_limit(QTestState *who)
+{
+    QDict *rsp;
+
+    rsp = qtest_qmp(who, "{ 'execute': 'query-vcpu-dirty-limit' }");
+    g_assert(!qdict_haskey(rsp, "error"));
+    g_assert(qdict_haskey(rsp, "return"));
+
+    return rsp;
+}
+
+static bool calc_dirtyrate_ready(QTestState *who)
+{
+    QDict *rsp_return;
+    gchar *status;
+
+    rsp_return = query_dirty_rate(who);
+    g_assert(rsp_return);
+
+    status = g_strdup(qdict_get_str(rsp_return, "status"));
+    g_assert(status);
+
+    return g_strcmp0(status, "measuring");
+}
+
+static void wait_for_calc_dirtyrate_complete(QTestState *who,
+                                             int64_t time_s)
+{
+    int max_try_count = 10000;
+    usleep(time_s * 1000000);
+
+    while (!calc_dirtyrate_ready(who) && max_try_count--) {
+        usleep(1000);
+    }
+
+    /*
+     * Set the timeout with 10 s(max_try_count * 1000us),
+     * if dirtyrate measurement not complete, fail test.
+     */
+    g_assert_cmpint(max_try_count, !=, 0);
+}
+
+static int64_t get_dirty_rate(QTestState *who)
+{
+    QDict *rsp_return;
+    gchar *status;
+    QList *rates;
+    const QListEntry *entry;
+    QDict *rate;
+    int64_t dirtyrate;
+
+    rsp_return = query_dirty_rate(who);
+    g_assert(rsp_return);
+
+    status = g_strdup(qdict_get_str(rsp_return, "status"));
+    g_assert(status);
+    g_assert_cmpstr(status, ==, "measured");
+
+    rates = qdict_get_qlist(rsp_return, "vcpu-dirty-rate");
+    g_assert(rates && !qlist_empty(rates));
+
+    entry = qlist_first(rates);
+    g_assert(entry);
+
+    rate = qobject_to(QDict, qlist_entry_obj(entry));
+    g_assert(rate);
+
+    dirtyrate = qdict_get_try_int(rate, "dirty-rate", -1);
+
+    qobject_unref(rsp_return);
+    return dirtyrate;
+}
+
+static int64_t get_limit_rate(QTestState *who)
+{
+    QDict *rsp_return;
+    QList *rates;
+    const QListEntry *entry;
+    QDict *rate;
+    int64_t dirtyrate;
+
+    rsp_return = query_vcpu_dirty_limit(who);
+    g_assert(rsp_return);
+
+    rates = qdict_get_qlist(rsp_return, "return");
+    g_assert(rates && !qlist_empty(rates));
+
+    entry = qlist_first(rates);
+    g_assert(entry);
+
+    rate = qobject_to(QDict, qlist_entry_obj(entry));
+    g_assert(rate);
+
+    dirtyrate = qdict_get_try_int(rate, "limit-rate", -1);
+
+    qobject_unref(rsp_return);
+    return dirtyrate;
+}
+
+static QTestState *dirtylimit_start_vm(void)
+{
+    QTestState *vm = NULL;
+    g_autofree gchar *cmd = NULL;
+    const char *arch = qtest_get_arch();
+    g_autofree char *bootpath = NULL;
+
+    assert((strcmp(arch, "x86_64") == 0));
+    bootpath = g_strdup_printf("%s/bootsect", tmpfs);
+    assert(sizeof(x86_bootsect) == 512);
+    init_bootfile(bootpath, x86_bootsect, sizeof(x86_bootsect));
+
+    cmd = g_strdup_printf("-accel kvm,dirty-ring-size=4096 "
+                          "-name dirtylimit-test,debug-threads=on "
+                          "-m 150M -smp 1 "
+                          "-serial file:%s/vm_serial "
+                          "-drive file=%s,format=raw ",
+                          tmpfs, bootpath);
+
+    vm = qtest_init(cmd);
+    return vm;
+}
+
+static void dirtylimit_stop_vm(QTestState *vm)
+{
+    qtest_quit(vm);
+    cleanup("bootsect");
+    cleanup("vm_serial");
+}
+
+static void test_vcpu_dirty_limit(void)
+{
+    QTestState *vm;
+    int64_t origin_rate;
+    int64_t quota_rate;
+    int64_t rate ;
+    int max_try_count = 20;
+    int hit = 0;
+
+    /* Start vm for vcpu dirtylimit test */
+    vm = dirtylimit_start_vm();
+
+    /* Wait for the first serial output from the vm*/
+    wait_for_serial("vm_serial");
+
+    /* Do dirtyrate measurement with calc time equals 1s */
+    calc_dirty_rate(vm, 1);
+
+    /* Sleep calc time and wait for calc dirtyrate complete */
+    wait_for_calc_dirtyrate_complete(vm, 1);
+
+    /* Query original dirty page rate */
+    origin_rate = get_dirty_rate(vm);
+
+    /* VM booted from bootsect should dirty memory steadily */
+    assert(origin_rate != 0);
+
+    /* Setup quota dirty page rate at half of origin */
+    quota_rate = origin_rate / 2;
+
+    /* Set dirtylimit */
+    dirtylimit_set_all(vm, quota_rate);
+
+    /*
+     * Check if set-vcpu-dirty-limit and query-vcpu-dirty-limit
+     * works literally
+     */
+    g_assert_cmpint(quota_rate, ==, get_limit_rate(vm));
+
+    /* Sleep a bit to check if it take effect */
+    usleep(2000000);
+
+    /*
+     * Check if dirtylimit take effect realistically, set the
+     * timeout with 20 s(max_try_count * 1s), if dirtylimit
+     * doesn't take effect, fail test.
+     */
+    while (--max_try_count) {
+        calc_dirty_rate(vm, 1);
+        wait_for_calc_dirtyrate_complete(vm, 1);
+        rate = get_dirty_rate(vm);
+
+        /*
+         * Assume hitting if current rate is less
+         * than quota rate (within accepting error)
+         */
+        if (rate < (quota_rate + DIRTYLIMIT_TOLERANCE_RANGE)) {
+            hit = 1;
+            break;
+        }
+    }
+
+    g_assert_cmpint(hit, ==, 1);
+
+    hit = 0;
+    max_try_count = 20;
+
+    /* Check if dirtylimit cancellation take effect */
+    cancel_vcpu_dirty_limit(vm);
+    while (--max_try_count) {
+        calc_dirty_rate(vm, 1);
+        wait_for_calc_dirtyrate_complete(vm, 1);
+        rate = get_dirty_rate(vm);
+
+        /*
+         * Assume dirtylimit be canceled if current rate is
+         * greater than quota rate (within accepting error)
+         */
+        if (rate > (quota_rate + DIRTYLIMIT_TOLERANCE_RANGE)) {
+            hit = 1;
+            break;
+        }
+    }
+
+    g_assert_cmpint(hit, ==, 1);
+    dirtylimit_stop_vm(vm);
+}
+
 static bool kvm_dirty_ring_supported(void)
 {
 #if defined(__linux__) && defined(HOST_X86_64)
@@ -1483,6 +1737,8 @@ int main(int argc, char **argv)
     if (kvm_dirty_ring_supported()) {
         qtest_add_func("/migration/dirty_ring",
                        test_precopy_unix_dirty_ring);
+        qtest_add_func("/migration/vcpu_dirty_limit",
+                       test_vcpu_dirty_limit);
     }
 
     ret = g_test_run();
diff --git a/tests/qtest/qmp-cmd-test.c b/tests/qtest/qmp-cmd-test.c
index 7f103ea3fd2ac5c9fd0b6ebb91ce4b66bac31a41..4b216a0435db47ee2e5d46efff289826b5435d22 100644
--- a/tests/qtest/qmp-cmd-test.c
+++ b/tests/qtest/qmp-cmd-test.c
@@ -110,6 +110,8 @@ static bool query_is_ignored(const char *cmd)
         "query-sev-capabilities",
         "query-sgx",
         "query-sgx-capabilities",
+        /* Success depends on enabling dirty page rate limit */
+        "query-vcpu-dirty-limit",
         NULL
     };
     int i;