Merge remote-tracking branch 'remotes/bonzini-gitlab/tags/for-upstream' into staging

Bug fixes

# gpg: Signature made Mon 16 Nov 2020 18:22:51 GMT
# gpg:                using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg:                issuer "pbonzini@redhat.com"
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full]
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>" [full]
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* remotes/bonzini-gitlab/tags/for-upstream:
  memory: Skip dirty tracking for un-migratable memory regions
  target/i386: avoid theoretical leak on MCE injection
  scsi-disk: convert more errno values back to SCSI statuses
  util/vfio-helpers.c: Use ram_block_discard_disable() in qemu_vfio_open_pci()
  kvm/i386: Set proper nested state format for SVM

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

6 files changed, 53 insertions, 11 deletions

diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c
index e859534eaf..90841ad791 100644
--- a/hw/scsi/scsi-disk.c
+++ b/hw/scsi/scsi-disk.c
@@ -461,6 +461,25 @@ static bool scsi_handle_rw_error(SCSIDiskReq *r, int error, bool acct_failed)
             }
             error = scsi_sense_buf_to_errno(r->req.sense, sizeof(r->req.sense));
             break;
+#ifdef CONFIG_LINUX
+            /* These errno mapping are specific to Linux.  For more information:
+             * - scsi_decide_disposition in drivers/scsi/scsi_error.c
+             * - scsi_result_to_blk_status in drivers/scsi/scsi_lib.c
+             * - blk_errors[] in block/blk-core.c
+             */
+        case EBADE:
+            /* DID_NEXUS_FAILURE -> BLK_STS_NEXUS.  */
+            scsi_req_complete(&r->req, RESERVATION_CONFLICT);
+            break;
+        case ENODATA:
+            /* DID_MEDIUM_ERROR -> BLK_STS_MEDIUM.  */
+            scsi_check_condition(r, SENSE_CODE(READ_ERROR));
+            break;
+        case EREMOTEIO:
+            /* DID_TARGET_FAILURE -> BLK_STS_TARGET.  */
+            scsi_req_complete(&r->req, HARDWARE_ERROR);
+            break;
+#endif
         case ENOMEDIUM:
             scsi_check_condition(r, SENSE_CODE(NO_MEDIUM));
             break;
diff --git a/softmmu/memory.c b/softmmu/memory.c
index 71951fe4dc..aa393f1bb0 100644
--- a/softmmu/memory.c
+++ b/softmmu/memory.c
@@ -1806,7 +1806,10 @@ bool memory_region_is_ram_device(MemoryRegion *mr)
 uint8_t memory_region_get_dirty_log_mask(MemoryRegion *mr)
 {
     uint8_t mask = mr->dirty_log_mask;
-    if (global_dirty_log && (mr->ram_block || memory_region_is_iommu(mr))) {
+    RAMBlock *rb = mr->ram_block;
+
+    if (global_dirty_log && ((rb && qemu_ram_is_migratable(rb)) ||
+                             memory_region_is_iommu(mr))) {
         mask |= (1 << DIRTY_MEMORY_MIGRATION);
     }
     return mask;
diff --git a/stubs/ram-block.c b/stubs/ram-block.c
index 73c0a3ee08..108197683b 100644
--- a/stubs/ram-block.c
+++ b/stubs/ram-block.c
@@ -1,6 +1,7 @@
 #include "qemu/osdep.h"
 #include "exec/ramlist.h"
 #include "exec/cpu-common.h"
+#include "exec/memory.h"
 
 void *qemu_ram_get_host_addr(RAMBlock *rb)
 {
@@ -29,3 +30,8 @@ int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque)
 {
     return 0;
 }
+
+int ram_block_discard_disable(bool state)
+{
+    return 0;
+}
diff --git a/target/i386/helper.c b/target/i386/helper.c
index 516ce0cad8..034f46bcc2 100644
--- a/target/i386/helper.c
+++ b/target/i386/helper.c
@@ -908,16 +908,14 @@ static void do_inject_x86_mce(CPUState *cs, run_on_cpu_data data)
             return;
         }
 
-        if (recursive) {
-            need_reset = true;
-            msg = g_strdup_printf("CPU %d: Previous MCE still in progress, "
-                                  "raising triple fault", cs->cpu_index);
-        }
-
         if (!(cenv->cr[4] & CR4_MCE_MASK)) {
             need_reset = true;
             msg = g_strdup_printf("CPU %d: MCE capability is not enabled, "
                                   "raising triple fault", cs->cpu_index);
+        } else if (recursive) {
+            need_reset = true;
+            msg = g_strdup_printf("CPU %d: Previous MCE still in progress, "
+                                  "raising triple fault", cs->cpu_index);
         }
 
         if (need_reset) {
diff --git a/target/i386/kvm.c b/target/i386/kvm.c
index cf46259534..a2934dda02 100644
--- a/target/i386/kvm.c
+++ b/target/i386/kvm.c
@@ -1820,12 +1820,14 @@ int kvm_arch_init_vcpu(CPUState *cs)
 
             env->nested_state = g_malloc0(max_nested_state_len);
             env->nested_state->size = max_nested_state_len;
-            env->nested_state->format = KVM_STATE_NESTED_FORMAT_VMX;
 
             if (cpu_has_vmx(env)) {
-                    vmx_hdr = &env->nested_state->hdr.vmx;
-                    vmx_hdr->vmxon_pa = -1ull;
-                    vmx_hdr->vmcs12_pa = -1ull;
+                env->nested_state->format = KVM_STATE_NESTED_FORMAT_VMX;
+                vmx_hdr = &env->nested_state->hdr.vmx;
+                vmx_hdr->vmxon_pa = -1ull;
+                vmx_hdr->vmcs12_pa = -1ull;
+            } else {
+                env->nested_state->format = KVM_STATE_NESTED_FORMAT_SVM;
             }
         }
     }
diff --git a/util/vfio-helpers.c b/util/vfio-helpers.c
index c469beb061..2bec48e163 100644
--- a/util/vfio-helpers.c
+++ b/util/vfio-helpers.c
@@ -16,6 +16,7 @@
 #include "qapi/error.h"
 #include "exec/ramlist.h"
 #include "exec/cpu-common.h"
+#include "exec/memory.h"
 #include "trace.h"
 #include "qemu/error-report.h"
 #include "standard-headers/linux/pci_regs.h"
@@ -494,8 +495,20 @@ QEMUVFIOState *qemu_vfio_open_pci(const char *device, Error **errp)
     int r;
     QEMUVFIOState *s = g_new0(QEMUVFIOState, 1);
 
+    /*
+     * VFIO may pin all memory inside mappings, resulting it in pinning
+     * all memory inside RAM blocks unconditionally.
+     */
+    r = ram_block_discard_disable(true);
+    if (r) {
+        error_setg_errno(errp, -r, "Cannot set discarding of RAM broken");
+        g_free(s);
+        return NULL;
+    }
+
     r = qemu_vfio_init_pci(s, device, errp);
     if (r) {
+        ram_block_discard_disable(false);
         g_free(s);
         return NULL;
     }
@@ -837,4 +850,5 @@ void qemu_vfio_close(QEMUVFIOState *s)
     close(s->device);
     close(s->group);
     close(s->container);
+    ram_block_discard_disable(false);
 }