summary refs log tree commit diff stats
path: root/system
diff options
context:
space:
mode:
Diffstat (limited to 'system')
-rw-r--r--system/memory.c49
-rw-r--r--system/physmem.c65
-rw-r--r--system/qdev-monitor.c10
-rw-r--r--system/rtc.c1
-rw-r--r--system/runstate.c15
5 files changed, 127 insertions, 13 deletions
diff --git a/system/memory.c b/system/memory.c
index a229a79988..49f1cb2c38 100644
--- a/system/memory.c
+++ b/system/memory.c
@@ -1850,6 +1850,11 @@ bool memory_region_is_protected(MemoryRegion *mr)
     return mr->ram && (mr->ram_block->flags & RAM_PROTECTED);
 }
 
+bool memory_region_has_guest_memfd(MemoryRegion *mr)
+{
+    return mr->ram_block && mr->ram_block->guest_memfd >= 0;
+}
+
 uint8_t memory_region_get_dirty_log_mask(MemoryRegion *mr)
 {
     uint8_t mask = mr->dirty_log_mask;
@@ -2914,7 +2919,30 @@ static unsigned int postponed_stop_flags;
 static VMChangeStateEntry *vmstate_change;
 static void memory_global_dirty_log_stop_postponed_run(void);
 
-void memory_global_dirty_log_start(unsigned int flags)
+static bool memory_global_dirty_log_do_start(Error **errp)
+{
+    MemoryListener *listener;
+
+    QTAILQ_FOREACH(listener, &memory_listeners, link) {
+        if (listener->log_global_start) {
+            if (!listener->log_global_start(listener, errp)) {
+                goto err;
+            }
+        }
+    }
+    return true;
+
+err:
+    while ((listener = QTAILQ_PREV(listener, link)) != NULL) {
+        if (listener->log_global_stop) {
+            listener->log_global_stop(listener);
+        }
+    }
+
+    return false;
+}
+
+bool memory_global_dirty_log_start(unsigned int flags, Error **errp)
 {
     unsigned int old_flags;
 
@@ -2928,7 +2956,7 @@ void memory_global_dirty_log_start(unsigned int flags)
 
     flags &= ~global_dirty_tracking;
     if (!flags) {
-        return;
+        return true;
     }
 
     old_flags = global_dirty_tracking;
@@ -2936,11 +2964,17 @@ void memory_global_dirty_log_start(unsigned int flags)
     trace_global_dirty_changed(global_dirty_tracking);
 
     if (!old_flags) {
-        MEMORY_LISTENER_CALL_GLOBAL(log_global_start, Forward);
+        if (!memory_global_dirty_log_do_start(errp)) {
+            global_dirty_tracking &= ~flags;
+            trace_global_dirty_changed(global_dirty_tracking);
+            return false;
+        }
+
         memory_region_transaction_begin();
         memory_region_update_pending = true;
         memory_region_transaction_commit();
     }
+    return true;
 }
 
 static void memory_global_dirty_log_do_stop(unsigned int flags)
@@ -3014,8 +3048,15 @@ static void listener_add_address_space(MemoryListener *listener,
         listener->begin(listener);
     }
     if (global_dirty_tracking) {
+        /*
+         * Currently only VFIO can fail log_global_start(), and it's not
+         * yet allowed to hotplug any PCI device during migration. So this
+         * should never fail when invoked, guard it with error_abort.  If
+         * it can start to fail in the future, we need to be able to fail
+         * the whole listener_add_address_space() and its callers.
+         */
         if (listener->log_global_start) {
-            listener->log_global_start(listener);
+            listener->log_global_start(listener, &error_abort);
         }
     }
 
diff --git a/system/physmem.c b/system/physmem.c
index a4fe3d2bf8..c3d04ca921 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -1808,6 +1808,7 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
     const bool shared = qemu_ram_is_shared(new_block);
     RAMBlock *block;
     RAMBlock *last_block = NULL;
+    bool free_on_error = false;
     ram_addr_t old_ram_size, new_ram_size;
     Error *err = NULL;
 
@@ -1837,6 +1838,26 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
                 return;
             }
             memory_try_enable_merging(new_block->host, new_block->max_length);
+            free_on_error = true;
+        }
+    }
+
+    if (new_block->flags & RAM_GUEST_MEMFD) {
+        assert(kvm_enabled());
+        assert(new_block->guest_memfd < 0);
+
+        if (ram_block_discard_require(true) < 0) {
+            error_setg_errno(errp, errno,
+                             "cannot set up private guest memory: discard currently blocked");
+            error_append_hint(errp, "Are you using assigned devices?\n");
+            goto out_free;
+        }
+
+        new_block->guest_memfd = kvm_create_guest_memfd(new_block->max_length,
+                                                        0, errp);
+        if (new_block->guest_memfd < 0) {
+            qemu_mutex_unlock_ramlist();
+            goto out_free;
         }
     }
 
@@ -1888,6 +1909,13 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
         ram_block_notify_add(new_block->host, new_block->used_length,
                              new_block->max_length);
     }
+    return;
+
+out_free:
+    if (free_on_error) {
+        qemu_anon_ram_free(new_block->host, new_block->max_length);
+        new_block->host = NULL;
+    }
 }
 
 #ifdef CONFIG_POSIX
@@ -1902,7 +1930,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
     /* Just support these ram flags by now. */
     assert((ram_flags & ~(RAM_SHARED | RAM_PMEM | RAM_NORESERVE |
                           RAM_PROTECTED | RAM_NAMED_FILE | RAM_READONLY |
-                          RAM_READONLY_FD)) == 0);
+                          RAM_READONLY_FD | RAM_GUEST_MEMFD)) == 0);
 
     if (xen_enabled()) {
         error_setg(errp, "-mem-path not supported with Xen");
@@ -1939,6 +1967,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
     new_block->used_length = size;
     new_block->max_length = size;
     new_block->flags = ram_flags;
+    new_block->guest_memfd = -1;
     new_block->host = file_ram_alloc(new_block, size, fd, !file_size, offset,
                                      errp);
     if (!new_block->host) {
@@ -2018,7 +2047,7 @@ RAMBlock *qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size,
     int align;
 
     assert((ram_flags & ~(RAM_SHARED | RAM_RESIZEABLE | RAM_PREALLOC |
-                          RAM_NORESERVE)) == 0);
+                          RAM_NORESERVE | RAM_GUEST_MEMFD)) == 0);
     assert(!host ^ (ram_flags & RAM_PREALLOC));
 
     align = qemu_real_host_page_size();
@@ -2033,6 +2062,7 @@ RAMBlock *qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size,
     new_block->max_length = max_size;
     assert(max_size >= size);
     new_block->fd = -1;
+    new_block->guest_memfd = -1;
     new_block->page_size = qemu_real_host_page_size();
     new_block->host = host;
     new_block->flags = ram_flags;
@@ -2055,7 +2085,7 @@ RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
 RAMBlock *qemu_ram_alloc(ram_addr_t size, uint32_t ram_flags,
                          MemoryRegion *mr, Error **errp)
 {
-    assert((ram_flags & ~(RAM_SHARED | RAM_NORESERVE)) == 0);
+    assert((ram_flags & ~(RAM_SHARED | RAM_NORESERVE | RAM_GUEST_MEMFD)) == 0);
     return qemu_ram_alloc_internal(size, size, NULL, NULL, ram_flags, mr, errp);
 }
 
@@ -2083,6 +2113,12 @@ static void reclaim_ramblock(RAMBlock *block)
     } else {
         qemu_anon_ram_free(block->host, block->max_length);
     }
+
+    if (block->guest_memfd >= 0) {
+        close(block->guest_memfd);
+        ram_block_discard_require(false);
+    }
+
     g_free(block);
 }
 
@@ -3685,6 +3721,29 @@ err:
     return ret;
 }
 
+int ram_block_discard_guest_memfd_range(RAMBlock *rb, uint64_t start,
+                                        size_t length)
+{
+    int ret = -1;
+
+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+    ret = fallocate(rb->guest_memfd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+                    start, length);
+
+    if (ret) {
+        ret = -errno;
+        error_report("%s: Failed to fallocate %s:%" PRIx64 " +%zx (%d)",
+                     __func__, rb->idstr, start, length, ret);
+    }
+#else
+    ret = -ENOSYS;
+    error_report("%s: fallocate not available %s:%" PRIx64 " +%zx (%d)",
+                 __func__, rb->idstr, start, length, ret);
+#endif
+
+    return ret;
+}
+
 bool ramblock_is_pmem(RAMBlock *rb)
 {
     return rb->flags & RAM_PMEM;
diff --git a/system/qdev-monitor.c b/system/qdev-monitor.c
index 840177d19f..6af6ef7d66 100644
--- a/system/qdev-monitor.c
+++ b/system/qdev-monitor.c
@@ -660,7 +660,8 @@ DeviceState *qdev_device_add_from_qdict(const QDict *opts,
 
     if (qdev_should_hide_device(opts, from_json, errp)) {
         if (bus && !qbus_is_hotpluggable(bus)) {
-            error_setg(errp, QERR_BUS_NO_HOTPLUG, bus->name);
+            error_setg(errp, "Bus '%s' does not support hotplugging",
+                       bus->name);
         }
         return NULL;
     } else if (*errp) {
@@ -668,7 +669,7 @@ DeviceState *qdev_device_add_from_qdict(const QDict *opts,
     }
 
     if (phase_check(PHASE_MACHINE_READY) && bus && !qbus_is_hotpluggable(bus)) {
-        error_setg(errp, QERR_BUS_NO_HOTPLUG, bus->name);
+        error_setg(errp, "Bus '%s' does not support hotplugging", bus->name);
         return NULL;
     }
 
@@ -910,12 +911,13 @@ void qdev_unplug(DeviceState *dev, Error **errp)
     }
 
     if (dev->parent_bus && !qbus_is_hotpluggable(dev->parent_bus)) {
-        error_setg(errp, QERR_BUS_NO_HOTPLUG, dev->parent_bus->name);
+        error_setg(errp, "Bus '%s' does not support hotplugging",
+                   dev->parent_bus->name);
         return;
     }
 
     if (!dc->hotpluggable) {
-        error_setg(errp, QERR_DEVICE_NO_HOTPLUG,
+        error_setg(errp, "Device '%s' does not support hotplugging",
                    object_get_typename(OBJECT(dev)));
         return;
     }
diff --git a/system/rtc.c b/system/rtc.c
index 4904581abe..dc44576686 100644
--- a/system/rtc.c
+++ b/system/rtc.c
@@ -25,7 +25,6 @@
 #include "qemu/osdep.h"
 #include "qemu/cutils.h"
 #include "qapi/error.h"
-#include "qapi/qmp/qerror.h"
 #include "qemu/error-report.h"
 #include "qemu/option.h"
 #include "qemu/timer.h"
diff --git a/system/runstate.c b/system/runstate.c
index d6ab860eca..cb4905a40f 100644
--- a/system/runstate.c
+++ b/system/runstate.c
@@ -501,7 +501,20 @@ void qemu_system_reset(ShutdownCause reason)
     default:
         qapi_event_send_reset(shutdown_caused_by_guest(reason), reason);
     }
-    cpu_synchronize_all_post_reset();
+
+    /*
+     * Some boards use the machine reset callback to point CPUs to the firmware
+     * entry point.  Assume that this is not the case for boards that support
+     * non-resettable CPUs (currently used only for confidential guests), in
+     * which case cpu_synchronize_all_post_init() is enough because
+     * it does _more_  than cpu_synchronize_all_post_reset().
+     */
+    if (cpus_are_resettable()) {
+        cpu_synchronize_all_post_reset();
+    } else {
+        assert(runstate_check(RUN_STATE_PRELAUNCH));
+    }
+
     vm_set_suspended(false);
 }