[PULL v2 11/14] os: add an ability to lock memory on_fault

[Peter Xu <peterx@redhat.com>]

From: Daniil Tatianin <d-tatianin@yandex-team.ru>

This will be used in the following commits to make it possible to only
lock memory on fault instead of right away.

Signed-off-by: Daniil Tatianin <d-tatianin@yandex-team.ru>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Link: https://lore.kernel.org/r/20250212143920.1269754-2-d-tatianin@yandex-team.ru
[peterx: fail os_mlock(on_fault=1) when not supported]
[peterx: use G_GNUC_UNUSED instead of "(void)on_fault", per Dan]
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 meson.build               |  6 ++++++
 include/system/os-posix.h |  2 +-
 include/system/os-win32.h |  2 +-
 migration/postcopy-ram.c  |  2 +-
 os-posix.c                | 15 +++++++++++++--
 system/vl.c               |  2 +-
 6 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/meson.build b/meson.build
index 18cf9e2913..59953cbe6b 100644
--- a/meson.build
+++ b/meson.build
@@ -2885,6 +2885,12 @@ config_host_data.set('HAVE_MLOCKALL', cc.links(gnu_source_prefix + '''
     return mlockall(MCL_FUTURE);
   }'''))
 
+config_host_data.set('HAVE_MLOCK_ONFAULT', cc.links(gnu_source_prefix + '''
+  #include <sys/mman.h>
+  int main(void) {
+      return mlockall(MCL_FUTURE | MCL_ONFAULT);
+  }'''))
+
 have_l2tpv3 = false
 if get_option('l2tpv3').allowed() and have_system
   have_l2tpv3 = cc.has_type('struct mmsghdr',
diff --git a/include/system/os-posix.h b/include/system/os-posix.h
index b881ac6c6f..ce5b3bccf8 100644
--- a/include/system/os-posix.h
+++ b/include/system/os-posix.h
@@ -53,7 +53,7 @@ bool os_set_runas(const char *user_id);
 void os_set_chroot(const char *path);
 void os_setup_limits(void);
 void os_setup_post(void);
-int os_mlock(void);
+int os_mlock(bool on_fault);
 
 /**
  * qemu_alloc_stack:
diff --git a/include/system/os-win32.h b/include/system/os-win32.h
index b82a5d3ad9..bc623061d8 100644
--- a/include/system/os-win32.h
+++ b/include/system/os-win32.h
@@ -123,7 +123,7 @@ static inline bool is_daemonized(void)
     return false;
 }
 
-static inline int os_mlock(void)
+static inline int os_mlock(bool on_fault G_GNUC_UNUSED)
 {
     return -ENOSYS;
 }
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index 6a6da6ba7f..fc4d8a10df 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -652,7 +652,7 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis)
     }
 
     if (enable_mlock) {
-        if (os_mlock() < 0) {
+        if (os_mlock(false) < 0) {
             error_report("mlock: %s", strerror(errno));
             /*
              * It doesn't feel right to fail at this point, we have a valid
diff --git a/os-posix.c b/os-posix.c
index 9cce55ff2f..52925c23d3 100644
--- a/os-posix.c
+++ b/os-posix.c
@@ -327,18 +327,29 @@ void os_set_line_buffering(void)
     setvbuf(stdout, NULL, _IOLBF, 0);
 }
 
-int os_mlock(void)
+int os_mlock(bool on_fault)
 {
 #ifdef HAVE_MLOCKALL
     int ret = 0;
+    int flags = MCL_CURRENT | MCL_FUTURE;
 
-    ret = mlockall(MCL_CURRENT | MCL_FUTURE);
+    if (on_fault) {
+#ifdef HAVE_MLOCK_ONFAULT
+        flags |= MCL_ONFAULT;
+#else
+        error_report("mlockall: on_fault not supported");
+        return -EINVAL;
+#endif
+    }
+
+    ret = mlockall(flags);
     if (ret < 0) {
         error_report("mlockall: %s", strerror(errno));
     }
 
     return ret;
 #else
+    (void)on_fault;
     return -ENOSYS;
 #endif
 }
diff --git a/system/vl.c b/system/vl.c
index 9c6942c6cf..e94fc7ea35 100644
--- a/system/vl.c
+++ b/system/vl.c
@@ -797,7 +797,7 @@ static QemuOptsList qemu_run_with_opts = {
 static void realtime_init(void)
 {
     if (enable_mlock) {
-        if (os_mlock() < 0) {
+        if (os_mlock(false) < 0) {
             error_report("locking memory failed");
             exit(1);
         }
-- 
2.47.0