Add option to mlock qemu and guest memory

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 <satoru.moriya@hds.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-id: 1366382526-26146-1-git-send-email-pbonzini@redhat.com
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

5 files changed, 65 insertions, 0 deletions

diff --git a/include/sysemu/os-posix.h b/include/sysemu/os-posix.h
index 7f198e475c..25d0b2a73f 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);
+int 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 71f5fa0a91..bf8523ada1 100644
--- a/include/sysemu/os-win32.h
+++ b/include/sysemu/os-win32.h
@@ -106,4 +106,9 @@ static inline bool is_daemonized(void)
     return false;
 }
 
+static inline int os_mlock(void)
+{
+    return -ENOSYS;
+}
+
 #endif
diff --git a/os-posix.c b/os-posix.c
index 5c64518902..d39261d849 100644
--- a/os-posix.c
+++ b/os-posix.c
@@ -363,3 +363,15 @@ bool is_daemonized(void)
 {
     return daemonize;
 }
+
+int os_mlock(void)
+{
+    int ret = 0;
+
+    ret = mlockall(MCL_CURRENT | MCL_FUTURE);
+    if (ret < 0) {
+        perror("mlockall");
+    }
+
+    return ret;
+}
diff --git a/qemu-options.hx b/qemu-options.hx
index 5c115d1cf9..e86cc2439d 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -2583,6 +2583,19 @@ 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
+@item -realtime mlock=on|off
+@findex -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 2ef00d893a..6caa5f4272 100644
--- a/vl.c
+++ b/vl.c
@@ -521,6 +521,18 @@ static QemuOptsList qemu_tpmdev_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;
@@ -1420,6 +1432,20 @@ static void smp_parse(const char *optarg)
         max_cpus = smp_cpus;
 }
 
+static void configure_realtime(QemuOpts *opts)
+{
+    bool enable_mlock;
+
+    enable_mlock = qemu_opt_get_bool(opts, "mlock", true);
+
+    if (enable_mlock) {
+        if (os_mlock() < 0) {
+            fprintf(stderr, "qemu: locking memory failed\n");
+            exit(1);
+        }
+    }
+}
+
 /***********************************************************/
 /* USB devices */
 
@@ -2862,6 +2888,7 @@ int main(int argc, char **argv, char **envp)
     qemu_add_opts(&qemu_add_fd_opts);
     qemu_add_opts(&qemu_object_opts);
     qemu_add_opts(&qemu_tpmdev_opts);
+    qemu_add_opts(&qemu_realtime_opts);
 
     runstate_init();
 
@@ -3835,6 +3862,13 @@ 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);
             }