diff mbox series

[PULL,01/34] migration: prevent migration when VM has poisoned memory

Message ID 20240208030528.368214-2-peterx@redhat.com
State New
Headers show
Series [PULL,01/34] migration: prevent migration when VM has poisoned memory | expand

Commit Message

Peter Xu Feb. 8, 2024, 3:04 a.m. UTC 
From: William Roche <william.roche@oracle.com>

A memory page poisoned from the hypervisor level is no longer readable.
The migration of a VM will crash Qemu when it tries to read the
memory address space and stumbles on the poisoned page with a similar
stack trace:

Program terminated with signal SIGBUS, Bus error.
#0  _mm256_loadu_si256
#1  buffer_zero_avx2
#2  select_accel_fn
#3  buffer_is_zero
#4  save_zero_page
#5  ram_save_target_page_legacy
#6  ram_save_host_page
#7  ram_find_and_save_block
#8  ram_save_iterate
#9  qemu_savevm_state_iterate
#10 migration_iteration_run
#11 migration_thread
#12 qemu_thread_start

To avoid this VM crash during the migration, prevent the migration
when a known hardware poison exists on the VM.

Signed-off-by: William Roche <william.roche@oracle.com>
Link: https://lore.kernel.org/r/20240130190640.139364-2-william.roche@oracle.com
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 include/sysemu/kvm.h   |  6 ++++++
 accel/kvm/kvm-all.c    | 10 ++++++++++
 accel/stubs/kvm-stub.c |  5 +++++
 migration/migration.c  |  7 +++++++
 4 files changed, 28 insertions(+)
diff mbox series

Patch

diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h
index d614878164..fad9a7e8ff 100644
--- a/include/sysemu/kvm.h
+++ b/include/sysemu/kvm.h
@@ -538,4 +538,10 @@  bool kvm_arch_cpu_check_are_resettable(void);
 bool kvm_dirty_ring_enabled(void);
 
 uint32_t kvm_dirty_ring_size(void);
+
+/**
+ * kvm_hwpoisoned_mem - indicate if there is any hwpoisoned page
+ * reported for the VM.
+ */
+bool kvm_hwpoisoned_mem(void);
 #endif
diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 49e755ec4a..a8cecd040e 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -1119,6 +1119,11 @@  int kvm_vm_check_extension(KVMState *s, unsigned int extension)
     return ret;
 }
 
+/*
+ * We track the poisoned pages to be able to:
+ * - replace them on VM reset
+ * - block a migration for a VM with a poisoned page
+ */
 typedef struct HWPoisonPage {
     ram_addr_t ram_addr;
     QLIST_ENTRY(HWPoisonPage) list;
@@ -1152,6 +1157,11 @@  void kvm_hwpoison_page_add(ram_addr_t ram_addr)
     QLIST_INSERT_HEAD(&hwpoison_page_list, page, list);
 }
 
+bool kvm_hwpoisoned_mem(void)
+{
+    return !QLIST_EMPTY(&hwpoison_page_list);
+}
+
 static uint32_t adjust_ioeventfd_endianness(uint32_t val, uint32_t size)
 {
 #if HOST_BIG_ENDIAN != TARGET_BIG_ENDIAN
diff --git a/accel/stubs/kvm-stub.c b/accel/stubs/kvm-stub.c
index 1b37d9a302..ca38172884 100644
--- a/accel/stubs/kvm-stub.c
+++ b/accel/stubs/kvm-stub.c
@@ -124,3 +124,8 @@  uint32_t kvm_dirty_ring_size(void)
 {
     return 0;
 }
+
+bool kvm_hwpoisoned_mem(void)
+{
+    return false;
+}
diff --git a/migration/migration.c b/migration/migration.c
index d5f705ceef..b574e66f7b 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -67,6 +67,7 @@ 
 #include "options.h"
 #include "sysemu/dirtylimit.h"
 #include "qemu/sockets.h"
+#include "sysemu/kvm.h"
 
 static NotifierList migration_state_notifiers =
     NOTIFIER_LIST_INITIALIZER(migration_state_notifiers);
@@ -1906,6 +1907,12 @@  static bool migrate_prepare(MigrationState *s, bool blk, bool blk_inc,
         return false;
     }
 
+    if (kvm_hwpoisoned_mem()) {
+        error_setg(errp, "Can't migrate this vm with hardware poisoned memory, "
+                   "please reboot the vm and try again");
+        return false;
+    }
+
     if (migration_is_blocked(errp)) {
         return false;
     }