[Qemu-devel] [PATCH v2] Add option to mlock qemu and guest memory

[Satoru Moriya]

We have some plans to migrate legacy enterprise systems which require
low latency (10 msec order) to kvm virtualized environment. In our
usecase, the system runs with other untrusted guests and so locking
memory which is used by the system is needed to avoid latency
impacts from other guests' memory activity.

ChangeLog:
v2
 - Change the option name from -mlock to -realtime mlock=on|off
 - Rebase qemu version 1.3.91
 - Update patch description

---
In certain scenario, latency induced by paging is significant and
memory locking is needed. Also, in the scenario with untrusted
guests, latency improvement due to mlock is desired.

This patch introduces a following new option to mlock guest and
qemu memory:

-realtime mlock=on|off

Signed-off-by: Satoru Moriya <address@hidden>
---
 include/sysemu/os-posix.h |  1 +
 include/sysemu/os-win32.h |  1 +
 os-posix.c                |  8 ++++++++
 qemu-options.hx           | 13 +++++++++++++
 vl.c                      | 31 +++++++++++++++++++++++++++++++
 5 files changed, 54 insertions(+)

diff --git a/include/sysemu/os-posix.h b/include/sysemu/os-posix.h
index 7f198e4..2f2ead6 100644
--- a/include/sysemu/os-posix.h
+++ b/include/sysemu/os-posix.h
@@ -31,6 +31,7 @@ void os_set_proc_name(const char *s);
 void os_setup_signal_handling(void);
 void os_daemonize(void);
 void os_setup_post(void);
+void os_mlock(void);
 
 typedef struct timeval qemu_timeval;
 #define qemu_gettimeofday(tp) gettimeofday(tp, NULL)
diff --git a/include/sysemu/os-win32.h b/include/sysemu/os-win32.h
index bf9edeb..a74ca13 100644
--- a/include/sysemu/os-win32.h
+++ b/include/sysemu/os-win32.h
@@ -80,6 +80,7 @@ static inline void os_daemonize(void) {}
 static inline void os_setup_post(void) {}
 void os_set_line_buffering(void);
 static inline void os_set_proc_name(const char *dummy) {}
+static inline void os_mlock(void) {}
 
 #if !defined(EPROTONOSUPPORT)
 # define EPROTONOSUPPORT EINVAL
diff --git a/os-posix.c b/os-posix.c
index 5c64518..1304b0e 100644
--- a/os-posix.c
+++ b/os-posix.c
@@ -363,3 +363,11 @@ bool is_daemonized(void)
 {
     return daemonize;
 }
+
+void os_mlock(void)
+{
+    if (mlockall(MCL_CURRENT | MCL_FUTURE)) {
+        perror("mlockall");
+        exit(1);
+    }
+}
diff --git a/qemu-options.hx b/qemu-options.hx
index 9d7131a..843fcb4 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -2464,6 +2464,19 @@ STEXI
 Do not start CPU at startup (you must type 'c' in the monitor).
 ETEXI
 
+DEF("realtime", HAS_ARG, QEMU_OPTION_realtime,
+    "-realtime [mlock=on|off]\n"
+    "                run qemu with realtime features\n"
+    "                mlock=on|off controls mlock support (default: on)\n",
+    QEMU_ARCH_ALL)
+STEXI
address@hidden -realtime mlock=on|off
address@hidden -realtime
+Run qemu with realtime features.
+mlocking qemu and guest memory can be enabled via @option{mlock=on}
+(enabled by default).
+ETEXI
+
 DEF("gdb", HAS_ARG, QEMU_OPTION_gdb, \
     "-gdb dev        wait for gdb connection on 'dev'\n", QEMU_ARCH_ALL)
 STEXI
diff --git a/vl.c b/vl.c
index 1355f69..c16c8ad 100644
--- a/vl.c
+++ b/vl.c
@@ -491,6 +491,18 @@ static QemuOptsList qemu_object_opts = {
     },
 };
 
+static QemuOptsList qemu_realtime_opts = {
+    .name = "realtime",
+    .head = QTAILQ_HEAD_INITIALIZER(qemu_realtime_opts.head),
+    .desc = {
+        {
+            .name = "mlock",
+            .type = QEMU_OPT_BOOL,
+        },
+        { /* end of list */ }
+    },
+};
+
 const char *qemu_get_vm_name(void)
 {
     return qemu_name;
@@ -1384,6 +1396,17 @@ static void smp_parse(const char *optarg)
         max_cpus = smp_cpus;
 }
 
+static void configure_realtime(QemuOpts *opts)
+{
+    bool is_mlock;
+
+    is_mlock = qemu_opt_get_bool(opts, "mlock", true);
+
+    if (is_mlock) {
+        os_mlock();
+    }
+}
+
 /***********************************************************/
 /* USB devices */
 
@@ -2860,6 +2883,7 @@ int main(int argc, char **argv, char **envp)
     qemu_add_opts(&qemu_sandbox_opts);
     qemu_add_opts(&qemu_add_fd_opts);
     qemu_add_opts(&qemu_object_opts);
+    qemu_add_opts(&qemu_realtime_opts);
 
     runstate_init();
 
@@ -3806,6 +3830,13 @@ int main(int argc, char **argv, char **envp)
                     exit(1);
                 }
                 break;
+            case QEMU_OPTION_realtime:
+                opts = qemu_opts_parse(qemu_find_opts("realtime"), optarg, 0);
+                if (!opts) {
+                    exit(1);
+                }
+                configure_realtime(opts);
+                break;
             default:
                 os_parse_cmd_args(popt->index, optarg);
             }
-- 
1.7.11.7