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

* microvm docs and fixes (Sergio, Liam)
* New processor features for Intel errata (myself, Pawan)
* Kconfig fixes (myself, Thomas)
* Revert mc146818rtc change (myself)
* Deprecate scsi-disk (myself)
* RTC fix (myself, Marcelo)

# gpg: Signature made Tue 19 Nov 2019 09:03:49 GMT
# gpg:                using RSA key BFFBD25F78C7AE83
# 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/tags/for-upstream:
  mc146818rtc: fix timer interrupt reinjection again
  Revert "mc146818rtc: fix timer interrupt reinjection"
  scsi: deprecate scsi-disk
  hw/i386: Move save_tsc_khz from PCMachineClass to X86MachineClass
  docs/microvm.rst: add instructions for shutting down the guest
  docs/microvm.rst: fix alignment in "Limitations"
  vfio: vfio-pci requires EDID
  hw/i386: Fix compiler warning when CONFIG_IDE_ISA is disabled
  target/i386: Export TAA_NO bit to guests
  target/i386: add PSCHANGE_NO bit for the ARCH_CAPABILITIES MSR
  microvm: fix memory leak in microvm_fix_kernel_cmdline
  scripts: Detect git worktrees for get_maintainer.pl --git

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

docs/microvm.rst

@@ -33,9 +33,9 @@ Limitations
 
 Currently, microvm does *not* support the following features:
 
- - PCI-only devices.
- - Hotplug of any kind.
- - Live migration across QEMU versions.
+- PCI-only devices.
+- Hotplug of any kind.
+- Live migration across QEMU versions.
 
 
 Using the microvm machine type
@@ -106,3 +106,24 @@ disabled::
      -device virtio-blk-device,drive=test \
      -netdev tap,id=tap0,script=no,downscript=no \
      -device virtio-net-device,netdev=tap0
+
+
+Triggering a guest-initiated shut down
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+As the microvm machine type includes just a small set of system
+devices, some x86 mechanisms for rebooting or shutting down the
+system, like sending a key sequence to the keyboard or writing to an
+ACPI register, doesn't have any effect in the VM.
+
+The recommended way to trigger a guest-initiated shut down is by
+generating a ``triple-fault``, which will cause the VM to initiate a
+reboot. Additionally, if the ``-no-reboot`` argument is present in the
+command line, QEMU will detect this event and terminate its own
+execution gracefully.
+
+Linux does support this mechanism, but by default will only be used
+after other options have been tried and failed, causing the reboot to
+be delayed by a small number of seconds. It's possible to instruct it
+to try the triple-fault mechanism first, by adding ``reboot=t`` to the
+kernel's command line.

hw/i386/microvm.c

@@ -331,6 +331,8 @@ static void microvm_fix_kernel_cmdline(MachineState *machine)
 
     fw_cfg_modify_i32(x86ms->fw_cfg, FW_CFG_CMDLINE_SIZE, strlen(cmdline) + 1);
     fw_cfg_modify_string(x86ms->fw_cfg, FW_CFG_CMDLINE_DATA, cmdline);
+
+    g_free(cmdline);
 }
 
 static void microvm_machine_state_init(MachineState *machine)

hw/i386/pc.c

@@ -2195,7 +2195,6 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)
     /* BIOS ACPI tables: 128K. Other BIOS datastructures: less than 4K reported
      * to be used at the moment, 32K should be enough for a while.  */
     pcmc->acpi_data_size = 0x20000 + 0x8000;
-    pcmc->save_tsc_khz = true;
     pcmc->linuxboot_dma_enabled = true;
     pcmc->pvh_enabled = true;
     assert(!mc->get_hotplug_handler);

hw/i386/pc_piix.c

@@ -78,7 +78,6 @@ static void pc_init1(MachineState *machine,
     X86MachineState *x86ms = X86_MACHINE(machine);
     MemoryRegion *system_memory = get_system_memory();
     MemoryRegion *system_io = get_system_io();
-    int i;
     PCIBus *pci_bus;
     ISABus *isa_bus;
     PCII440FXState *i440fx_state;
@@ -253,7 +252,8 @@ static void pc_init1(MachineState *machine,
     }
 #ifdef CONFIG_IDE_ISA
 else {
-        for(i = 0; i < MAX_IDE_BUS; i++) {
+        int i;
+        for (i = 0; i < MAX_IDE_BUS; i++) {
             ISADevice *dev;
             char busname[] = "ide.0";
             dev = isa_ide_init(isa_bus, ide_iobase[i], ide_iobase2[i],
@@ -567,10 +567,10 @@ DEFINE_I440FX_MACHINE(v2_6, "pc-i440fx-2.6", NULL,
 
 static void pc_i440fx_2_5_machine_options(MachineClass *m)
 {
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+    X86MachineClass *x86mc = X86_MACHINE_CLASS(m);
 
     pc_i440fx_2_6_machine_options(m);
-    pcmc->save_tsc_khz = false;
+    x86mc->save_tsc_khz = false;
     m->legacy_fw_cfg_order = 1;
     compat_props_add(m->compat_props, hw_compat_2_5, hw_compat_2_5_len);
     compat_props_add(m->compat_props, pc_compat_2_5, pc_compat_2_5_len);

hw/i386/pc_q35.c

@@ -508,10 +508,10 @@ DEFINE_Q35_MACHINE(v2_6, "pc-q35-2.6", NULL,
 
 static void pc_q35_2_5_machine_options(MachineClass *m)
 {
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
+    X86MachineClass *x86mc = X86_MACHINE_CLASS(m);
 
     pc_q35_2_6_machine_options(m);
-    pcmc->save_tsc_khz = false;
+    x86mc->save_tsc_khz = false;
     m->legacy_fw_cfg_order = 1;
     compat_props_add(m->compat_props, hw_compat_2_5, hw_compat_2_5_len);
     compat_props_add(m->compat_props, pc_compat_2_5, pc_compat_2_5_len);

hw/i386/x86.c

@@ -763,6 +763,7 @@ static void x86_machine_class_init(ObjectClass *oc, void *data)
     mc->get_default_cpu_node_id = x86_get_default_cpu_node_id;
     mc->possible_cpu_arch_ids = x86_possible_cpu_arch_ids;
     x86mc->compat_apic_id_mode = false;
+    x86mc->save_tsc_khz = true;
     nc->nmi_monitor_handler = x86_nmi;
 
     object_class_property_add(oc, X86_MACHINE_MAX_RAM_BELOW_4G, "size",

hw/rtc/mc146818rtc.c

@@ -168,12 +168,13 @@ static uint32_t rtc_periodic_clock_ticks(RTCState *s)
  * is just due to period adjustment.
  */
 static void
-periodic_timer_update(RTCState *s, int64_t current_time, uint32_t old_period)
+periodic_timer_update(RTCState *s, int64_t current_time, uint32_t old_period, bool period_change)
 {
     uint32_t period;
     int64_t cur_clock, next_irq_clock, lost_clock = 0;
 
     period = rtc_periodic_clock_ticks(s);
+    s->period = period;
 
     if (!period) {
         s->irq_coalesced = 0;
@@ -189,7 +190,7 @@ periodic_timer_update(RTCState *s, int64_t current_time, uint32_t old_period)
      * if the periodic timer's update is due to period re-configuration,
      * we should count the clock since last interrupt.
      */
-    if (old_period) {
+    if (old_period && period_change) {
         int64_t last_periodic_clock, next_periodic_clock;
 
         next_periodic_clock = muldiv64(s->next_periodic_time,
@@ -197,42 +198,41 @@ periodic_timer_update(RTCState *s, int64_t current_time, uint32_t old_period)
         last_periodic_clock = next_periodic_clock - old_period;
         lost_clock = cur_clock - last_periodic_clock;
         assert(lost_clock >= 0);
+    }
 
+    /*
+     * s->irq_coalesced can change for two reasons:
+     *
+     * a) if one or more periodic timer interrupts have been lost,
+     *    lost_clock will be more that a period.
+     *
+     * b) when the period may be reconfigured, we expect the OS to
+     *    treat delayed tick as the new period.  So, when switching
+     *    from a shorter to a longer period, scale down the missing,
+     *    because the OS will treat past delayed ticks as longer
+     *    (leftovers are put back into lost_clock).  When switching
+     *    to a shorter period, scale up the missing ticks since the
+     *    OS handler will treat past delayed ticks as shorter.
+     */
+    if (s->lost_tick_policy == LOST_TICK_POLICY_SLEW) {
+        uint32_t old_irq_coalesced = s->irq_coalesced;
+
+        lost_clock += old_irq_coalesced * old_period;
+        s->irq_coalesced = lost_clock / s->period;
+        lost_clock %= s->period;
+        if (old_irq_coalesced != s->irq_coalesced ||
+            old_period != s->period) {
+            DPRINTF_C("cmos: coalesced irqs scaled from %d to %d, "
+                      "period scaled from %d to %d\n", old_irq_coalesced,
+                      s->irq_coalesced, old_period, s->period);
+            rtc_coalesced_timer_update(s);
+        }
+    } else {
         /*
-         * s->irq_coalesced can change for two reasons:
-         *
-         * a) if one or more periodic timer interrupts have been lost,
-         *    lost_clock will be more that a period.
-         *
-         * b) when the period may be reconfigured, we expect the OS to
-         *    treat delayed tick as the new period.  So, when switching
-         *    from a shorter to a longer period, scale down the missing,
-         *    because the OS will treat past delayed ticks as longer
-         *    (leftovers are put back into lost_clock).  When switching
-         *    to a shorter period, scale up the missing ticks since the
-         *    OS handler will treat past delayed ticks as shorter.
+         * no way to compensate the interrupt if LOST_TICK_POLICY_SLEW
+         * is not used, we should make the time progress anyway.
          */
-        if (s->lost_tick_policy == LOST_TICK_POLICY_SLEW) {
-            uint32_t old_irq_coalesced = s->irq_coalesced;
-
-            s->period = period;
-            lost_clock += old_irq_coalesced * old_period;
-            s->irq_coalesced = lost_clock / s->period;
-            lost_clock %= s->period;
-            if (old_irq_coalesced != s->irq_coalesced ||
-                old_period != s->period) {
-                DPRINTF_C("cmos: coalesced irqs scaled from %d to %d, "
-                          "period scaled from %d to %d\n", old_irq_coalesced,
-                          s->irq_coalesced, old_period, s->period);
-                rtc_coalesced_timer_update(s);
-            }
-        } else {
-            /*
-             * no way to compensate the interrupt if LOST_TICK_POLICY_SLEW
-             * is not used, we should make the time progress anyway.
-             */
-            lost_clock = MIN(lost_clock, period);
-        }
+        lost_clock = MIN(lost_clock, period);
     }
 
     assert(lost_clock >= 0 && lost_clock <= period);
@@ -246,7 +246,7 @@ static void rtc_periodic_timer(void *opaque)
 {
     RTCState *s = opaque;
 
-    periodic_timer_update(s, s->next_periodic_time, 0);
+    periodic_timer_update(s, s->next_periodic_time, s->period, false);
     s->cmos_data[RTC_REG_C] |= REG_C_PF;
     if (s->cmos_data[RTC_REG_B] & REG_B_PIE) {
         s->cmos_data[RTC_REG_C] |= REG_C_IRQF;
@@ -512,7 +512,7 @@ static void cmos_ioport_write(void *opaque, hwaddr addr,
 
             if (update_periodic_timer) {
                 periodic_timer_update(s, qemu_clock_get_ns(rtc_clock),
-                                      old_period);
+                                      old_period, true);
             }
 
             check_update_timer(s);
@@ -551,7 +551,7 @@ static void cmos_ioport_write(void *opaque, hwaddr addr,
 
             if (update_periodic_timer) {
                 periodic_timer_update(s, qemu_clock_get_ns(rtc_clock),
-                                      old_period);
+                                      old_period, true);
             }
 
             check_update_timer(s);
@@ -795,6 +795,7 @@ static int rtc_post_load(void *opaque, int version_id)
         s->offset = 0;
         check_update_timer(s);
     }
+    s->period = rtc_periodic_clock_ticks(s);
 
     /* The periodic timer is deterministic in record/replay mode,
      * so there is no need to update it after loading the vmstate.
@@ -804,7 +805,7 @@ static int rtc_post_load(void *opaque, int version_id)
         uint64_t now = qemu_clock_get_ns(rtc_clock);
         if (now < s->next_periodic_time ||
             now > (s->next_periodic_time + get_max_clock_jump())) {
-            periodic_timer_update(s, qemu_clock_get_ns(rtc_clock), 0);
+            periodic_timer_update(s, qemu_clock_get_ns(rtc_clock), s->period, false);
         }
     }
 

hw/scsi/scsi-bus.c

@@ -254,8 +254,18 @@ SCSIDevice *scsi_bus_legacy_add_drive(SCSIBus *bus, BlockBackend *blk,
     char *name;
     DeviceState *dev;
     Error *err = NULL;
+    DriveInfo *dinfo;
 
-    driver = blk_is_sg(blk) ? "scsi-generic" : "scsi-disk";
+    if (blk_is_sg(blk)) {
+        driver = "scsi-generic";
+    } else {
+        dinfo = blk_legacy_dinfo(blk);
+        if (dinfo && dinfo->media_cd) {
+            driver = "scsi-cd";
+        } else {
+            driver = "scsi-hd";
+        }
+    }
     dev = qdev_create(&bus->qbus, driver);
     name = g_strdup_printf("legacy[%d]", unit);
     object_property_add_child(OBJECT(bus), name, OBJECT(dev), NULL);

hw/scsi/scsi-disk.c

@@ -2481,6 +2481,9 @@ static void scsi_disk_realize(SCSIDevice *dev, Error **errp)
     DriveInfo *dinfo;
     Error *local_err = NULL;
 
+    warn_report("'scsi-disk' is deprecated, "
+                "please use 'scsi-hd' or 'scsi-cd' instead");
+
     if (!dev->conf.blk) {
         scsi_realize(dev, &local_err);
         assert(local_err);

include/hw/i386/pc.h

@@ -116,8 +116,6 @@ typedef struct PCMachineClass {
     bool enforce_aligned_dimm;
     bool broken_reserved_end;
 
-    /* TSC rate migration: */
-    bool save_tsc_khz;
     /* generate legacy CPU hotplug AML */
     bool legacy_cpu_hotplug;
 

include/hw/i386/x86.h

@@ -30,6 +30,8 @@ typedef struct {
 
     /*< public >*/
 
+    /* TSC rate migration: */
+    bool save_tsc_khz;
     /* Enables contiguous-apic-ID mode */
     bool compat_apic_id_mode;
 } X86MachineClass;

qemu-deprecated.texi

@@ -259,6 +259,11 @@ their usecases.
 The 'ide-drive' device is deprecated. Users should use 'ide-hd' or
 'ide-cd' as appropriate to get an IDE hard disk or CD-ROM as needed.
 
+@subsection scsi-disk (since 4.2)
+
+The 'scsi-disk' device is deprecated. Users should use 'scsi-hd' or
+'scsi-cd' as appropriate to get a SCSI hard disk or CD-ROM as needed.
+
 @section System emulator machines
 
 @subsection pc-0.12, pc-0.13, pc-0.14 and pc-0.15 (since 4.0)

scripts/get_maintainer.pl

@@ -81,7 +81,7 @@ my %VCS_cmds;
 
 my %VCS_cmds_git = (
     "execute_cmd" => \&git_execute_cmd,
-    "available" => '(which("git") ne "") && (-d ".git")',
+    "available" => '(which("git") ne "") && (-e ".git")',
     "find_signers_cmd" =>
 	"git log --no-color --follow --since=\$email_git_since " .
 	    '--format="GitCommit: %H%n' .

target/i386/cpu.c

@@ -1204,8 +1204,8 @@ static FeatureWordInfo feature_word_info[FEATURE_WORDS] = {
         .type = MSR_FEATURE_WORD,
         .feat_names = {
             "rdctl-no", "ibrs-all", "rsba", "skip-l1dfl-vmentry",
-            "ssb-no", "mds-no", NULL, NULL,
-            NULL, NULL, NULL, NULL,
+            "ssb-no", "mds-no", "pschange-mc-no", NULL,
+            "taa-no", NULL, NULL, NULL,
             NULL, NULL, NULL, NULL,
             NULL, NULL, NULL, NULL,
             NULL, NULL, NULL, NULL,

target/i386/machine.c

@@ -988,8 +988,8 @@ static bool tsc_khz_needed(void *opaque)
     X86CPU *cpu = opaque;
     CPUX86State *env = &cpu->env;
     MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine());
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(mc);
-    return env->tsc_khz && pcmc->save_tsc_khz;
+    X86MachineClass *x86mc = X86_MACHINE_CLASS(mc);
+    return env->tsc_khz && x86mc->save_tsc_khz;
 }
 
 static const VMStateDescription vmstate_tsc_khz = {

tests/qemu-iotests/051.pc.out

@@ -167,7 +167,8 @@ QEMU X.Y.Z monitor - type 'help' for more information
 
 Testing: -drive if=none,id=disk -device lsi53c895a -device scsi-disk,drive=disk
 QEMU X.Y.Z monitor - type 'help' for more information
-(qemu) QEMU_PROG: -device scsi-disk,drive=disk: Device needs media, but drive is empty
+(qemu) QEMU_PROG: -device scsi-disk,drive=disk: warning: 'scsi-disk' is deprecated, please use 'scsi-hd' or 'scsi-cd' instead
+QEMU_PROG: -device scsi-disk,drive=disk: Device needs media, but drive is empty
 
 Testing: -drive if=none,id=disk -device lsi53c895a -device scsi-hd,drive=disk
 QEMU X.Y.Z monitor - type 'help' for more information
@@ -238,7 +239,8 @@ QEMU X.Y.Z monitor - type 'help' for more information
 
 Testing: -drive file=TEST_DIR/t.qcow2,if=none,id=disk,readonly=on -device lsi53c895a -device scsi-disk,drive=disk
 QEMU X.Y.Z monitor - type 'help' for more information
-(qemu) quit
+(qemu) QEMU_PROG: -device scsi-disk,drive=disk: warning: 'scsi-disk' is deprecated, please use 'scsi-hd' or 'scsi-cd' instead
+quit
 
 Testing: -drive file=TEST_DIR/t.qcow2,if=none,id=disk,readonly=on -device lsi53c895a -device scsi-hd,drive=disk
 QEMU X.Y.Z monitor - type 'help' for more information