overcommit: introduce mem-lock=on-fault

Locking the memory without MCL_ONFAULT instantly prefaults any mmaped
anonymous memory with a write-fault, which introduces a lot of extra
overhead in terms of memory usage when all you want to do is to prevent
kcompactd from migrating and compacting QEMU pages. Add an option to
only lock pages lazily as they're faulted by the process by using
MCL_ONFAULT if asked.

Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Daniil Tatianin <d-tatianin@yandex-team.ru>
Link: https://lore.kernel.org/r/20250212143920.1269754-5-d-tatianin@yandex-team.ru
Signed-off-by: Peter Xu <peterx@redhat.com>

1 files changed, 27 insertions, 7 deletions

diff --git a/system/vl.c b/system/vl.c
index 2895824c1a..3c0fa2ff64 100644
--- a/system/vl.c
+++ b/system/vl.c
@@ -351,7 +351,7 @@ static QemuOptsList qemu_overcommit_opts = {
     .desc = {
         {
             .name = "mem-lock",
-            .type = QEMU_OPT_BOOL,
+            .type = QEMU_OPT_STRING,
         },
         {
             .name = "cpu-pm",
@@ -797,7 +797,7 @@ static QemuOptsList qemu_run_with_opts = {
 static void realtime_init(void)
 {
     if (should_mlock(mlock_state)) {
-        if (os_mlock(false) < 0) {
+        if (os_mlock(is_mlock_on_fault(mlock_state)) < 0) {
             error_report("locking memory failed");
             exit(1);
         }
@@ -1878,7 +1878,7 @@ static void object_option_parse(const char *str)
 static void overcommit_parse(const char *str)
 {
     QemuOpts *opts;
-    bool enable_mlock;
+    const char *mem_lock_opt;
 
     opts = qemu_opts_parse_noisily(qemu_find_opts("overcommit"),
                                    str, false);
@@ -1886,11 +1886,31 @@ static void overcommit_parse(const char *str)
         exit(1);
     }
 
-    enable_mlock = qemu_opt_get_bool(opts, "mem-lock",
-                                     should_mlock(mlock_state));
-    mlock_state = enable_mlock ? MLOCK_ON : MLOCK_OFF;
-
     enable_cpu_pm = qemu_opt_get_bool(opts, "cpu-pm", enable_cpu_pm);
+
+    mem_lock_opt = qemu_opt_get(opts, "mem-lock");
+    if (!mem_lock_opt) {
+        return;
+    }
+
+    if (strcmp(mem_lock_opt, "on") == 0) {
+        mlock_state = MLOCK_ON;
+        return;
+    }
+
+    if (strcmp(mem_lock_opt, "off") == 0) {
+        mlock_state = MLOCK_OFF;
+        return;
+    }
+
+    if (strcmp(mem_lock_opt, "on-fault") == 0) {
+        mlock_state = MLOCK_ON_FAULT;
+        return;
+    }
+
+    error_report("parameter 'mem-lock' expects one of "
+                 "'on', 'off', 'on-fault'");
+    exit(1);
 }
 
 /*