diff --git a/libvirt.spec b/libvirt.spec
index ae416c261abac2cb535bada4ce3a1ba2dc43877e..c6e8d083a96d83e8f111f6d8c97f8f61c1fd323d 100644
--- a/libvirt.spec
+++ b/libvirt.spec
@@ -101,7 +101,7 @@
 Summary: Library providing a simple virtualization API
 Name: libvirt
 Version: 6.2.0
-Release: 65
+Release: 66
 License: LGPLv2+
 URL: https://libvirt.org/
 
@@ -535,6 +535,7 @@ Patch0422: libvirt-add-get-tmm-memory-info-API-and-libvirtd-RPC.patch
 Patch0423: virsh-add-tmm-main-command-word.patch
 Patch0424: qemu-avoid-deadlock-in-qemuDomainObjStopWorker.patch
 Patch0425: remote-fix-double-free-of-migration-params-on-error.patch
+Patch0426: qemu-enable-overcommit_memory-while-start-cvm.patch
 
 Requires: libvirt-daemon = %{version}-%{release}
 Requires: libvirt-daemon-config-network = %{version}-%{release}
@@ -2271,6 +2272,9 @@ exit 0
 
 
 %changelog
+* Thu July 1 2024 Jiabo Feng <tujipei@huawei.com> - 6.2.0-66
+- qemu: enable overcommit_memory while start cvm
+
 * Thu Jun 13 2024 Jiabo Feng <fengjiabo1@huawei.com> - 6.2.0-65
 - remote: fix double free of migration params on error
 - qemu: avoid deadlock in qemuDomainObjStopWorker We are dropping the only reference here so that the event loop thread is going to be exited synchronously. In order to avoid deadlocks we need to unlock the VM so that any handler being called can finish execution and thus even loop thread be finished too.
diff --git a/qemu-enable-overcommit_memory-while-start-cvm.patch b/qemu-enable-overcommit_memory-while-start-cvm.patch
new file mode 100644
index 0000000000000000000000000000000000000000..2c32a0aba4da25174a7a325e3f85e348af1b1e87
--- /dev/null
+++ b/qemu-enable-overcommit_memory-while-start-cvm.patch
@@ -0,0 +1,36 @@
+From 90b6a01fe7433e7d5ee3fc2e5eac334e2905fed9 Mon Sep 17 00:00:00 2001
+From: ikarosYuuki <tujipei@huawei.com>
+Date: Tue, 9 Jul 2024 22:03:05 +0800
+Subject: [PATCH] qemu: enable overcommit_memory while start cvm In case of
+ asymmetric memory numa, starting cvm with huge memory might be prevented by
+ host kernel because of non-secure memory smaller than secure memory in the
+ same numa. Ensuring the normal launch of cvm, libvirt need to enable
+ overcommit_memory feature by writing the 1 to overcommit_memory system file.
+
+Signed-off-by: ikarosYuuki <tujipei@huawei.com>
+---
+ src/qemu/qemu_driver.c | 8 ++++++++
+ 1 file changed, 8 insertions(+)
+
+diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c
+index 1e3f63a39a..823ffbc673 100644
+--- a/src/qemu/qemu_driver.c
++++ b/src/qemu/qemu_driver.c
+@@ -7424,6 +7424,14 @@ qemuDomainObjStart(virConnectPtr conn,
+         }
+     }
+ 
++    if (vm->def->cvm) {
++        if (virFileWriteStr("/proc/sys/vm/overcommit_memory", "1", 0)) {
++            virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
++                           _("Failed to enable overcommit_memory"));
++            return -1;
++        }
++    }
++
+     ret = qemuProcessStart(conn, driver, vm, NULL, asyncJob,
+                            NULL, -1, NULL, NULL,
+                            VIR_NETDEV_VPORT_PROFILE_OP_CREATE, start_flags);
+-- 
+2.31.1.windows.1
+