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

* core support for MemoryRegionCache from myself * rules.mak speedup and cleanups from myself and Marc-Adnré * multiboot command line fix from Vlad * SCSI fixes from myself * small qemu-timer speedup from myself * x86 debugging improvements from Doug * configurable Q35 devices from Chao * x86 5-level paging support from Kirill * x86 SHA_NI support for KVM from Yi Sun * improved kvmclock migration logic from Marcelo * bugfixes and doc fixes from others # gpg: Signature made Thu 22 Dec 2016 15:01:13 GMT # gpg: using RSA key 0xBFFBD25F78C7AE83 # gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" # gpg: aka "Paolo Bonzini <pbonzini@redhat.com>" # 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: (25 commits) x86: implement la57 paging mode target-i386: Fix eflags.TF/#DB handling of syscall/sysret insns kvmclock: reduce kvmclock difference on migration kvm: sync linux headers scsi-disk: fix VERIFY for scsi-block hw/block/pflash_cfi*.c: fix confusing assert fail message multiboot: copy the cmdline verbatim, unescape module strings x86: Fix x86_64 'g' packet response to gdb from 32-bit mode. pc: make pit configurable pc: make sata configurable pc: make smbus configurable target-i386: Add Intel SHA_NI instruction support. block: drop remaining legacy aio functions in comment main-loop: update comment for qemu_mutex_lock/unlock_iothread timer: fix misleading comment in timer.h qemu-timer: check active_timers outside lock/event virtio-scsi: introduce virtio_scsi_acquire/release build-sys: remove libtool left-over rules.mak: add more rules to avoid chaining rules.mak: speedup save-vars load-vars ... Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
2026-07-06 00:20:22 -07:00 · 2016-12-22 19:23:51 +00:00
parent c76904ef2f 6c7c3c21f9
commit a470b33259
45 changed files with 1730 additions and 801 deletions
@@ -82,10 +82,6 @@
 *.d
 !/scripts/qemu-guest-agent/fsfreeze-hook.d
 *.o
-*.lo
-*.la
-*.pc
-.libs
 .sdk
 *.gcda
 *.gcno
@@ -231,12 +231,10 @@ ALL_SUBDIRS=$(TARGET_DIRS) $(patsubst %,pc-bios/%, $(ROMS))

 recurse-all: $(SUBDIR_RULES) $(ROMSUBDIR_RULES)

-$(BUILD_DIR)/version.o: $(SRC_PATH)/version.rc config-host.h | $(BUILD_DIR)/version.lo
+$(BUILD_DIR)/version.o: $(SRC_PATH)/version.rc config-host.h
 	$(call quiet-command,$(WINDRES) -I$(BUILD_DIR) -o $@ $<,"RC","version.o")
-$(BUILD_DIR)/version.lo: $(SRC_PATH)/version.rc config-host.h
-	$(call quiet-command,$(WINDRES) -I$(BUILD_DIR) -o $@ $<,"RC","version.lo")

-Makefile: $(version-obj-y) $(version-lobj-y)
+Makefile: $(version-obj-y)

 ######################################################################
 # Build libraries
@@ -358,10 +356,9 @@ clean:
 	rm -f config.mak op-i386.h opc-i386.h gen-op-i386.h op-arm.h opc-arm.h gen-op-arm.h
 	rm -f qemu-options.def
 	rm -f *.msi
-	find . \( -name '*.l[oa]' -o -name '*.so' -o -name '*.dll' -o -name '*.mo' -o -name '*.[oda]' \) -type f -exec rm {} +
+	find . \( -name '*.so' -o -name '*.dll' -o -name '*.mo' -o -name '*.[oda]' \) -type f -exec rm {} +
 	rm -f $(filter-out %.tlb,$(TOOLS)) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
 	rm -f fsdev/*.pod
-	rm -rf .libs */.libs
 	rm -f qemu-img-cmds.h
 	rm -f ui/shader/*-vert.h ui/shader/*-frag.h
 	@# May not be present in GENERATED_HEADERS
@@ -97,7 +97,6 @@ common-obj-y += disas/
 ######################################################################
 # Resource file for Windows executables
 version-obj-$(CONFIG_WIN32) += $(BUILD_DIR)/version.o
-version-lobj-$(CONFIG_WIN32) += $(BUILD_DIR)/version.lo

 ######################################################################
 # tracing
@@ -76,6 +76,7 @@ $(QEMU_PROG)-simpletrace.stp: $(BUILD_DIR)/trace-events-all
 else
 stap:
 endif
+.PHONY: stap

 all: $(PROGS) stap

@@ -28,8 +28,6 @@ TMPB="qemu-conf"
 TMPC="${TMPDIR1}/${TMPB}.c"
 TMPO="${TMPDIR1}/${TMPB}.o"
 TMPCXX="${TMPDIR1}/${TMPB}.cxx"
-TMPL="${TMPDIR1}/${TMPB}.lo"
-TMPA="${TMPDIR1}/lib${TMPB}.la"
 TMPE="${TMPDIR1}/${TMPB}.exe"
 TMPMO="${TMPDIR1}/${TMPB}.mo"

@@ -707,6 +707,19 @@ static void pflash_cfi01_realize(DeviceState *dev, Error **errp)
    int num_devices;
    Error *local_err = NULL;

+    if (pfl->sector_len == 0) {
+        error_setg(errp, "attribute \"sector-length\" not specified or zero.");
+        return;
+    }
+    if (pfl->nb_blocs == 0) {
+        error_setg(errp, "attribute \"num-blocks\" not specified or zero.");
+        return;
+    }
+    if (pfl->name == NULL) {
+        error_setg(errp, "attribute \"name\" not specified.");
+        return;
+    }
+
    total_len = pfl->sector_len * pfl->nb_blocs;

    /* These are only used to expose the parameters of each device
@@ -600,6 +600,19 @@ static void pflash_cfi02_realize(DeviceState *dev, Error **errp)
    int ret;
    Error *local_err = NULL;

+    if (pfl->sector_len == 0) {
+        error_setg(errp, "attribute \"sector-length\" not specified or zero.");
+        return;
+    }
+    if (pfl->nb_blocs == 0) {
+        error_setg(errp, "attribute \"num-blocks\" not specified or zero.");
+        return;
+    }
+    if (pfl->name == NULL) {
+        error_setg(errp, "attribute \"name\" not specified.");
+        return;
+    }
+
    chip_len = pfl->sector_len * pfl->nb_blocs;
    /* XXX: to be fixed */
 #if 0
@@ -36,6 +36,13 @@ typedef struct KVMClockState {

    uint64_t clock;
    bool clock_valid;
+
+    /* whether machine type supports reliable KVM_GET_CLOCK */
+    bool mach_use_reliable_get_clock;
+
+    /* whether the 'clock' value was obtained in a host with
+     * reliable KVM_GET_CLOCK */
+    bool clock_is_reliable;
 } KVMClockState;

 struct pvclock_vcpu_time_info {
@@ -81,6 +88,60 @@ static uint64_t kvmclock_current_nsec(KVMClockState *s)
    return nsec + time.system_time;
 }

+static void kvm_update_clock(KVMClockState *s)
+{
+    struct kvm_clock_data data;
+    int ret;
+
+    ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data);
+    if (ret < 0) {
+        fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret));
+                abort();
+    }
+    s->clock = data.clock;
+
+    /* If kvm_has_adjust_clock_stable() is false, KVM_GET_CLOCK returns
+     * essentially CLOCK_MONOTONIC plus a guest-specific adjustment.  This
+     * can drift from the TSC-based value that is computed by the guest,
+     * so we need to go through kvmclock_current_nsec().  If
+     * kvm_has_adjust_clock_stable() is true, and the flags contain
+     * KVM_CLOCK_TSC_STABLE, then KVM_GET_CLOCK returns a TSC-based value
+     * and kvmclock_current_nsec() is not necessary.
+     *
+     * Here, however, we need not check KVM_CLOCK_TSC_STABLE.  This is because:
+     *
+     * - if the host has disabled the kvmclock master clock, the guest already
+     *   has protection against time going backwards.  This "safety net" is only
+     *   absent when kvmclock is stable;
+     *
+     * - therefore, we can replace a check like
+     *
+     *       if last KVM_GET_CLOCK was not reliable then
+     *               read from memory
+     *
+     *   with
+     *
+     *       if last KVM_GET_CLOCK was not reliable && masterclock is enabled
+     *               read from memory
+     *
+     * However:
+     *
+     * - if kvm_has_adjust_clock_stable() returns false, the left side is
+     *   always true (KVM_GET_CLOCK is never reliable), and the right side is
+     *   unknown (because we don't have data.flags).  We must assume it's true
+     *   and read from memory.
+     *
+     * - if kvm_has_adjust_clock_stable() returns true, the result of the &&
+     *   is always false (masterclock is enabled iff KVM_GET_CLOCK is reliable)
+     *
+     * So we can just use this instead:
+     *
+     *       if !kvm_has_adjust_clock_stable() then
+     *               read from memory
+     */
+    s->clock_is_reliable = kvm_has_adjust_clock_stable();
+}
+
 static void kvmclock_vm_state_change(void *opaque, int running,
                                     RunState state)
 {
@@ -91,15 +152,21 @@ static void kvmclock_vm_state_change(void *opaque, int running,

    if (running) {
        struct kvm_clock_data data = {};
-        uint64_t time_at_migration = kvmclock_current_nsec(s);
+
+        /*
+         * If the host where s->clock was read did not support reliable
+         * KVM_GET_CLOCK, read kvmclock value from memory.
+         */
+        if (!s->clock_is_reliable) {
+            uint64_t pvclock_via_mem = kvmclock_current_nsec(s);
+            /* We can't rely on the saved clock value, just discard it */
+            if (pvclock_via_mem) {
+                s->clock = pvclock_via_mem;
+            }
+        }

        s->clock_valid = false;

-        /* We can't rely on the migrated clock value, just discard it */
-        if (time_at_migration) {
-            s->clock = time_at_migration;
-        }
-
        data.clock = s->clock;
        ret = kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, &data);
        if (ret < 0) {
@@ -120,8 +187,6 @@ static void kvmclock_vm_state_change(void *opaque, int running,
            }
        }
    } else {
-        struct kvm_clock_data data;
-        int ret;

        if (s->clock_valid) {
            return;
@@ -129,13 +194,7 @@ static void kvmclock_vm_state_change(void *opaque, int running,

        kvm_synchronize_all_tsc();

-        ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data);
-        if (ret < 0) {
-            fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret));
-            abort();
-        }
-        s->clock = data.clock;
-
+        kvm_update_clock(s);
        /*
         * If the VM is stopped, declare the clock state valid to
         * avoid re-reading it on next vmsave (which would return
@@ -149,25 +208,78 @@ static void kvmclock_realize(DeviceState *dev, Error **errp)
 {
    KVMClockState *s = KVM_CLOCK(dev);

+    kvm_update_clock(s);
+
    qemu_add_vm_change_state_handler(kvmclock_vm_state_change, s);
 }

+static bool kvmclock_clock_is_reliable_needed(void *opaque)
+{
+    KVMClockState *s = opaque;
+
+    return s->mach_use_reliable_get_clock;
+}
+
+static const VMStateDescription kvmclock_reliable_get_clock = {
+    .name = "kvmclock/clock_is_reliable",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = kvmclock_clock_is_reliable_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_BOOL(clock_is_reliable, KVMClockState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+/*
+ * When migrating, read the clock just before migration,
+ * so that the guest clock counts during the events
+ * between:
+ *
+ *  * vm_stop()
+ *  *
+ *  * pre_save()
+ *
+ *  This reduces kvmclock difference on migration from 5s
+ *  to 0.1s (when max_downtime == 5s), because sending the
+ *  final pages of memory (which happens between vm_stop()
+ *  and pre_save()) takes max_downtime.
+ */
+static void kvmclock_pre_save(void *opaque)
+{
+    KVMClockState *s = opaque;
+
+    kvm_update_clock(s);
+}
+
 static const VMStateDescription kvmclock_vmsd = {
    .name = "kvmclock",
    .version_id = 1,
    .minimum_version_id = 1,
+    .pre_save = kvmclock_pre_save,
    .fields = (VMStateField[]) {
        VMSTATE_UINT64(clock, KVMClockState),
        VMSTATE_END_OF_LIST()
+    },
+    .subsections = (const VMStateDescription * []) {
+        &kvmclock_reliable_get_clock,
+        NULL
    }
 };

+static Property kvmclock_properties[] = {
+    DEFINE_PROP_BOOL("x-mach-use-reliable-get-clock", KVMClockState,
+                      mach_use_reliable_get_clock, true),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
 static void kvmclock_class_init(ObjectClass *klass, void *data)
 {
    DeviceClass *dc = DEVICE_CLASS(klass);

    dc->realize = kvmclock_realize;
    dc->vmsd = &kvmclock_vmsd;
+    dc->props = kvmclock_properties;
 }

 static const TypeInfo kvmclock_info = {
@@ -109,7 +109,7 @@ static uint32_t mb_add_cmdline(MultibootState *s, const char *cmdline)
    hwaddr p = s->offset_cmdlines;
    char *b = (char *)s->mb_buf + p;

-    get_opt_value(b, strlen(cmdline) + 1, cmdline);
+    memcpy(b, cmdline, strlen(cmdline) + 1);
    s->offset_cmdlines += strlen(b) + 1;
    return s->mb_buf_phys + p;
 }
@@ -287,7 +287,8 @@ int load_multiboot(FWCfgState *fw_cfg,
    mbs.offset_bootloader = mbs.offset_cmdlines + cmdline_len;

    if (initrd_filename) {
-        char *next_initrd, not_last;
+        const char *next_initrd;
+        char not_last, tmpbuf[strlen(initrd_filename) + 1];

        mbs.offset_mods = mbs.mb_buf_size;

@@ -296,25 +297,24 @@ int load_multiboot(FWCfgState *fw_cfg,
            int mb_mod_length;
            uint32_t offs = mbs.mb_buf_size;

-            next_initrd = (char *)get_opt_value(NULL, 0, initrd_filename);
+            next_initrd = get_opt_value(tmpbuf, sizeof(tmpbuf), initrd_filename);
            not_last = *next_initrd;
-            *next_initrd = '\0';
            /* if a space comes after the module filename, treat everything
               after that as parameters */
-            hwaddr c = mb_add_cmdline(&mbs, initrd_filename);
-            if ((next_space = strchr(initrd_filename, ' ')))
+            hwaddr c = mb_add_cmdline(&mbs, tmpbuf);
+            if ((next_space = strchr(tmpbuf, ' ')))
                *next_space = '\0';
-            mb_debug("multiboot loading module: %s\n", initrd_filename);
-            mb_mod_length = get_image_size(initrd_filename);
+            mb_debug("multiboot loading module: %s\n", tmpbuf);
+            mb_mod_length = get_image_size(tmpbuf);
            if (mb_mod_length < 0) {
-                fprintf(stderr, "Failed to open file '%s'\n", initrd_filename);
+                fprintf(stderr, "Failed to open file '%s'\n", tmpbuf);
                exit(1);
            }

            mbs.mb_buf_size = TARGET_PAGE_ALIGN(mb_mod_length + mbs.mb_buf_size);
            mbs.mb_buf = g_realloc(mbs.mb_buf, mbs.mb_buf_size);

-            load_image(initrd_filename, (unsigned char *)mbs.mb_buf + offs);
+            load_image(tmpbuf, (unsigned char *)mbs.mb_buf + offs);
            mb_add_mod(&mbs, mbs.mb_buf_phys + offs,
                       mbs.mb_buf_phys + offs + mb_mod_length, c);

@@ -400,13 +400,13 @@ static void pc_cmos_init_late(void *opaque)
    int i, trans;

    val = 0;
-    if (ide_get_geometry(arg->idebus[0], 0,
-                         &cylinders, &heads, &sectors) >= 0) {
+    if (arg->idebus[0] && ide_get_geometry(arg->idebus[0], 0,
+                                           &cylinders, &heads, &sectors) >= 0) {
        cmos_init_hd(s, 0x19, 0x1b, cylinders, heads, sectors);
        val |= 0xf0;
    }
-    if (ide_get_geometry(arg->idebus[0], 1,
-                         &cylinders, &heads, &sectors) >= 0) {
+    if (arg->idebus[0] && ide_get_geometry(arg->idebus[0], 1,
+                                           &cylinders, &heads, &sectors) >= 0) {
        cmos_init_hd(s, 0x1a, 0x24, cylinders, heads, sectors);
        val |= 0x0f;
    }
@@ -418,7 +418,8 @@ static void pc_cmos_init_late(void *opaque)
           geometry.  It is always such that: 1 <= sects <= 63, 1
           <= heads <= 16, 1 <= cylinders <= 16383. The BIOS
           geometry can be different if a translation is done. */
-        if (ide_get_geometry(arg->idebus[i / 2], i % 2,
+        if (arg->idebus[i / 2] &&
+            ide_get_geometry(arg->idebus[i / 2], i % 2,
                             &cylinders, &heads, &sectors) >= 0) {
            trans = ide_get_bios_chs_trans(arg->idebus[i / 2], i % 2) - 1;
            assert((trans & ~3) == 0);
@@ -1535,6 +1536,7 @@ void pc_basic_device_init(ISABus *isa_bus, qemu_irq *gsi,
                          ISADevice **rtc_state,
                          bool create_fdctrl,
                          bool no_vmport,
+                          bool has_pit,
                          uint32_t hpet_irqs)
 {
    int i;
@@ -1588,7 +1590,7 @@ void pc_basic_device_init(ISABus *isa_bus, qemu_irq *gsi,

    qemu_register_boot_set(pc_boot_set, *rtc_state);

-    if (!xen_enabled()) {
+    if (!xen_enabled() && has_pit) {
        if (kvm_pit_in_kernel()) {
            pit = kvm_pit_init(isa_bus, 0x40);
        } else {
@@ -2158,6 +2160,48 @@ static void pc_machine_set_nvdimm(Object *obj, bool value, Error **errp)
    pcms->acpi_nvdimm_state.is_enabled = value;
 }

+static bool pc_machine_get_smbus(Object *obj, Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+
+    return pcms->smbus;
+}
+
+static void pc_machine_set_smbus(Object *obj, bool value, Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+
+    pcms->smbus = value;
+}
+
+static bool pc_machine_get_sata(Object *obj, Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+
+    return pcms->sata;
+}
+
+static void pc_machine_set_sata(Object *obj, bool value, Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+
+    pcms->sata = value;
+}
+
+static bool pc_machine_get_pit(Object *obj, Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+
+    return pcms->pit;
+}
+
+static void pc_machine_set_pit(Object *obj, bool value, Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+
+    pcms->pit = value;
+}
+
 static void pc_machine_initfn(Object *obj)
 {
    PCMachineState *pcms = PC_MACHINE(obj);
@@ -2169,6 +2213,9 @@ static void pc_machine_initfn(Object *obj)
    pcms->acpi_nvdimm_state.is_enabled = false;
    /* acpi build is enabled by default if machine supports it */
    pcms->acpi_build_enabled = PC_MACHINE_GET_CLASS(pcms)->has_acpi_build;
+    pcms->smbus = true;
+    pcms->sata = true;
+    pcms->pit = true;
 }

 static void pc_machine_reset(void)
@@ -2329,6 +2376,15 @@ static void pc_machine_class_init(ObjectClass *oc, void *data)

    object_class_property_add_bool(oc, PC_MACHINE_NVDIMM,
        pc_machine_get_nvdimm, pc_machine_set_nvdimm, &error_abort);
+
+    object_class_property_add_bool(oc, PC_MACHINE_SMBUS,
+        pc_machine_get_smbus, pc_machine_set_smbus, &error_abort);
+
+    object_class_property_add_bool(oc, PC_MACHINE_SATA,
+        pc_machine_get_sata, pc_machine_set_sata, &error_abort);
+
+    object_class_property_add_bool(oc, PC_MACHINE_PIT,
+        pc_machine_get_pit, pc_machine_set_pit, &error_abort);
 }

 static const TypeInfo pc_machine_info = {
@@ -235,7 +235,7 @@ static void pc_init1(MachineState *machine,

    /* init basic PC hardware */
    pc_basic_device_init(isa_bus, pcms->gsi, &rtc_state, true,
-                         (pcms->vmport != ON_OFF_AUTO_ON), 0x4);
+                         (pcms->vmport != ON_OFF_AUTO_ON), pcms->pit, 0x4);

    pc_nic_init(isa_bus, pci_bus);

@@ -227,32 +227,39 @@ static void pc_q35_init(MachineState *machine)

    /* init basic PC hardware */
    pc_basic_device_init(isa_bus, pcms->gsi, &rtc_state, !mc->no_floppy,
-                         (pcms->vmport != ON_OFF_AUTO_ON), 0xff0104);
+                         (pcms->vmport != ON_OFF_AUTO_ON), pcms->pit,
+                         0xff0104);

    /* connect pm stuff to lpc */
    ich9_lpc_pm_init(lpc, pc_machine_is_smm_enabled(pcms));

-    /* ahci and SATA device, for q35 1 ahci controller is built-in */
-    ahci = pci_create_simple_multifunction(host_bus,
-                                           PCI_DEVFN(ICH9_SATA1_DEV,
-                                                     ICH9_SATA1_FUNC),
-                                           true, "ich9-ahci");
-    idebus[0] = qdev_get_child_bus(&ahci->qdev, "ide.0");
-    idebus[1] = qdev_get_child_bus(&ahci->qdev, "ide.1");
-    g_assert(MAX_SATA_PORTS == ICH_AHCI(ahci)->ahci.ports);
-    ide_drive_get(hd, ICH_AHCI(ahci)->ahci.ports);
-    ahci_ide_create_devs(ahci, hd);
+    if (pcms->sata) {
+        /* ahci and SATA device, for q35 1 ahci controller is built-in */
+        ahci = pci_create_simple_multifunction(host_bus,
+                                               PCI_DEVFN(ICH9_SATA1_DEV,
+                                                         ICH9_SATA1_FUNC),
+                                               true, "ich9-ahci");
+        idebus[0] = qdev_get_child_bus(&ahci->qdev, "ide.0");
+        idebus[1] = qdev_get_child_bus(&ahci->qdev, "ide.1");
+        g_assert(MAX_SATA_PORTS == ICH_AHCI(ahci)->ahci.ports);
+        ide_drive_get(hd, ICH_AHCI(ahci)->ahci.ports);
+        ahci_ide_create_devs(ahci, hd);
+    } else {
+        idebus[0] = idebus[1] = NULL;
+    }

    if (machine_usb(machine)) {
        /* Should we create 6 UHCI according to ich9 spec? */
        ehci_create_ich9_with_companions(host_bus, 0x1d);
    }

-    /* TODO: Populate SPD eeprom data.  */
-    smbus_eeprom_init(ich9_smb_init(host_bus,
-                                    PCI_DEVFN(ICH9_SMB_DEV, ICH9_SMB_FUNC),
-                                    0xb100),
-                      8, NULL, 0);
+    if (pcms->smbus) {
+        /* TODO: Populate SPD eeprom data.  */
+        smbus_eeprom_init(ich9_smb_init(host_bus,
+                                        PCI_DEVFN(ICH9_SMB_DEV, ICH9_SMB_FUNC),
+                                        0xb100),
+                          8, NULL, 0);
+    }

    pc_cmos_init(pcms, idebus[0], idebus[1], rtc_state);

@@ -2157,6 +2157,13 @@ static int32_t scsi_disk_dma_command(SCSIRequest *req, uint8_t *buf)
        DPRINTF("Write %s(sector %" PRId64 ", count %u)\n",
                (command & 0xe) == 0xe ? "And Verify " : "",
                r->req.cmd.lba, len);
+    case VERIFY_10:
+    case VERIFY_12:
+    case VERIFY_16:
+        /* We get here only for BYTCHK == 0x01 and only for scsi-block.
+         * As far as DMA is concerned, we can treat it the same as a write;
+         * scsi_block_do_sgio will send VERIFY commands.
+         */
        if (r->req.cmd.buf[1] & 0xe0) {
            goto illegal_request;
        }
@@ -2712,7 +2719,7 @@ static bool scsi_block_is_passthrough(SCSIDiskState *s, uint8_t *buf)
    case WRITE_VERIFY_16:
        /* MMC writing cannot be done via DMA helpers, because it sometimes
         * involves writing beyond the maximum LBA or to negative LBA (lead-in).
-         * We might use scsi_disk_dma_reqops as long as no writing commands are
+         * We might use scsi_block_dma_reqops as long as no writing commands are
         * seen, but performance usually isn't paramount on optical media.  So,
         * just make scsi-block operate the same as scsi-generic for them.
         */
@@ -420,6 +420,20 @@ static void virtio_scsi_handle_ctrl_req(VirtIOSCSI *s, VirtIOSCSIReq *req)
    }
 }

+static inline void virtio_scsi_acquire(VirtIOSCSI *s)
+{
+    if (s->ctx) {
+        aio_context_acquire(s->ctx);
+    }
+}
+
+static inline void virtio_scsi_release(VirtIOSCSI *s)
+{
+    if (s->ctx) {
+        aio_context_release(s->ctx);
+    }
+}
+
 void virtio_scsi_handle_ctrl_vq(VirtIOSCSI *s, VirtQueue *vq)
 {
    VirtIOSCSIReq *req;
@@ -691,10 +705,7 @@ void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev,
        return;
    }

-    if (s->dataplane_started) {
-        assert(s->ctx);
-        aio_context_acquire(s->ctx);
-    }
+    virtio_scsi_acquire(s);

    req = virtio_scsi_pop_req(s, vs->event_vq);
    if (!req) {
@@ -730,9 +741,7 @@ void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev,
    }
    virtio_scsi_complete_req(req);
 out:
-    if (s->dataplane_started) {
-        aio_context_release(s->ctx);
-    }
+    virtio_scsi_release(s);
 }

 void virtio_scsi_handle_event_vq(VirtIOSCSI *s, VirtQueue *vq)
@@ -778,9 +787,9 @@ static void virtio_scsi_hotplug(HotplugHandler *hotplug_dev, DeviceState *dev,
        if (blk_op_is_blocked(sd->conf.blk, BLOCK_OP_TYPE_DATAPLANE, errp)) {
            return;
        }
-        aio_context_acquire(s->ctx);
+        virtio_scsi_acquire(s);
        blk_set_aio_context(sd->conf.blk, s->ctx);
-        aio_context_release(s->ctx);
+        virtio_scsi_release(s);

    }

@@ -428,6 +428,14 @@ static void i6300esb_realize(PCIDevice *dev, Error **errp)
    /* qemu_register_coalesced_mmio (addr, 0x10); ? */
 }

+static void i6300esb_exit(PCIDevice *dev)
+{
+    I6300State *d = WATCHDOG_I6300ESB_DEVICE(dev);
+
+    timer_del(d->timer);
+    timer_free(d->timer);
+}
+
 static WatchdogTimerModel model = {
    .wdt_name = "i6300esb",
    .wdt_description = "Intel 6300ESB",
@@ -441,6 +449,7 @@ static void i6300esb_class_init(ObjectClass *klass, void *data)
    k->config_read = i6300esb_config_read;
    k->config_write = i6300esb_config_write;
    k->realize = i6300esb_realize;
+    k->exit = i6300esb_exit;
    k->vendor_id = PCI_VENDOR_ID_INTEL;
    k->device_id = PCI_DEVICE_ID_INTEL_ESB_9;
    k->class_id = PCI_CLASS_SYSTEM_OTHER;
@@ -195,8 +195,8 @@ QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque);
 * aio_notify: Force processing of pending events.
 *
 * Similar to signaling a condition variable, aio_notify forces
- * aio_wait to exit, so that the next call will re-examine pending events.
- * The caller of aio_notify will usually call aio_wait again very soon,
+ * aio_poll to exit, so that the next call will re-examine pending events.
+ * The caller of aio_notify will usually call aio_poll again very soon,
 * or go through another iteration of the GLib main loop.  Hence, aio_notify
 * also has the side effect of recalculating the sets of file descriptors
 * that the main loop waits for.
@@ -186,6 +186,29 @@ void address_space_stl(AddressSpace *as, hwaddr addr, uint32_t val,
                            MemTxAttrs attrs, MemTxResult *result);
 void address_space_stq(AddressSpace *as, hwaddr addr, uint64_t val,
                            MemTxAttrs attrs, MemTxResult *result);
+
+uint32_t lduw_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint32_t ldl_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint64_t ldq_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+void stl_phys_notdirty_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stw_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stl_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stq_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val);
+
+uint32_t address_space_lduw_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint32_t address_space_ldl_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint64_t address_space_ldq_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stl_notdirty_cached(MemoryRegionCache *cache, hwaddr addr,
+                            uint32_t val, MemTxAttrs attrs, MemTxResult *result);
+void address_space_stw_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stl_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stq_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
 #endif

 /* page related stuff */
@@ -94,21 +94,6 @@ bool cpu_physical_memory_is_io(hwaddr phys_addr);
 */
 void qemu_flush_coalesced_mmio_buffer(void);

-uint32_t ldub_phys(AddressSpace *as, hwaddr addr);
-uint32_t lduw_le_phys(AddressSpace *as, hwaddr addr);
-uint32_t lduw_be_phys(AddressSpace *as, hwaddr addr);
-uint32_t ldl_le_phys(AddressSpace *as, hwaddr addr);
-uint32_t ldl_be_phys(AddressSpace *as, hwaddr addr);
-uint64_t ldq_le_phys(AddressSpace *as, hwaddr addr);
-uint64_t ldq_be_phys(AddressSpace *as, hwaddr addr);
-void stb_phys(AddressSpace *as, hwaddr addr, uint32_t val);
-void stw_le_phys(AddressSpace *as, hwaddr addr, uint32_t val);
-void stw_be_phys(AddressSpace *as, hwaddr addr, uint32_t val);
-void stl_le_phys(AddressSpace *as, hwaddr addr, uint32_t val);
-void stl_be_phys(AddressSpace *as, hwaddr addr, uint32_t val);
-void stq_le_phys(AddressSpace *as, hwaddr addr, uint64_t val);
-void stq_be_phys(AddressSpace *as, hwaddr addr, uint64_t val);
-
 void cpu_physical_memory_write_rom(AddressSpace *as, hwaddr addr,
                                   const uint8_t *buf, int len);
 void cpu_flush_icache_range(hwaddr start, int len);
@@ -1404,6 +1404,140 @@ void address_space_stq_le(AddressSpace *as, hwaddr addr, uint64_t val,
 void address_space_stq_be(AddressSpace *as, hwaddr addr, uint64_t val,
                            MemTxAttrs attrs, MemTxResult *result);

+uint32_t ldub_phys(AddressSpace *as, hwaddr addr);
+uint32_t lduw_le_phys(AddressSpace *as, hwaddr addr);
+uint32_t lduw_be_phys(AddressSpace *as, hwaddr addr);
+uint32_t ldl_le_phys(AddressSpace *as, hwaddr addr);
+uint32_t ldl_be_phys(AddressSpace *as, hwaddr addr);
+uint64_t ldq_le_phys(AddressSpace *as, hwaddr addr);
+uint64_t ldq_be_phys(AddressSpace *as, hwaddr addr);
+void stb_phys(AddressSpace *as, hwaddr addr, uint32_t val);
+void stw_le_phys(AddressSpace *as, hwaddr addr, uint32_t val);
+void stw_be_phys(AddressSpace *as, hwaddr addr, uint32_t val);
+void stl_le_phys(AddressSpace *as, hwaddr addr, uint32_t val);
+void stl_be_phys(AddressSpace *as, hwaddr addr, uint32_t val);
+void stq_le_phys(AddressSpace *as, hwaddr addr, uint64_t val);
+void stq_be_phys(AddressSpace *as, hwaddr addr, uint64_t val);
+
+struct MemoryRegionCache {
+    hwaddr xlat;
+    void *ptr;
+    hwaddr len;
+    MemoryRegion *mr;
+    bool is_write;
+};
+
+/* address_space_cache_init: prepare for repeated access to a physical
+ * memory region
+ *
+ * @cache: #MemoryRegionCache to be filled
+ * @as: #AddressSpace to be accessed
+ * @addr: address within that address space
+ * @len: length of buffer
+ * @is_write: indicates the transfer direction
+ *
+ * Will only work with RAM, and may map a subset of the requested range by
+ * returning a value that is less than @len.  On failure, return a negative
+ * errno value.
+ *
+ * Because it only works with RAM, this function can be used for
+ * read-modify-write operations.  In this case, is_write should be %true.
+ *
+ * Note that addresses passed to the address_space_*_cached functions
+ * are relative to @addr.
+ */
+int64_t address_space_cache_init(MemoryRegionCache *cache,
+                                 AddressSpace *as,
+                                 hwaddr addr,
+                                 hwaddr len,
+                                 bool is_write);
+
+/**
+ * address_space_cache_invalidate: complete a write to a #MemoryRegionCache
+ *
+ * @cache: The #MemoryRegionCache to operate on.
+ * @addr: The first physical address that was written, relative to the
+ * address that was passed to @address_space_cache_init.
+ * @access_len: The number of bytes that were written starting at @addr.
+ */
+void address_space_cache_invalidate(MemoryRegionCache *cache,
+                                    hwaddr addr,
+                                    hwaddr access_len);
+
+/**
+ * address_space_cache_destroy: free a #MemoryRegionCache
+ *
+ * @cache: The #MemoryRegionCache whose memory should be released.
+ */
+void address_space_cache_destroy(MemoryRegionCache *cache);
+
+/* address_space_ld*_cached: load from a cached #MemoryRegion
+ * address_space_st*_cached: store into a cached #MemoryRegion
+ *
+ * These functions perform a load or store of the byte, word,
+ * longword or quad to the specified address.  The address is
+ * a physical address in the AddressSpace, but it must lie within
+ * a #MemoryRegion that was mapped with address_space_cache_init.
+ *
+ * The _le suffixed functions treat the data as little endian;
+ * _be indicates big endian; no suffix indicates "same endianness
+ * as guest CPU".
+ *
+ * The "guest CPU endianness" accessors are deprecated for use outside
+ * target-* code; devices should be CPU-agnostic and use either the LE
+ * or the BE accessors.
+ *
+ * @cache: previously initialized #MemoryRegionCache to be accessed
+ * @addr: address within the address space
+ * @val: data value, for stores
+ * @attrs: memory transaction attributes
+ * @result: location to write the success/failure of the transaction;
+ *   if NULL, this information is discarded
+ */
+uint32_t address_space_ldub_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint32_t address_space_lduw_le_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint32_t address_space_lduw_be_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint32_t address_space_ldl_le_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint32_t address_space_ldl_be_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint64_t address_space_ldq_le_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+uint64_t address_space_ldq_be_cached(MemoryRegionCache *cache, hwaddr addr,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stb_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stw_le_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stw_be_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stl_le_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stl_be_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stq_le_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+void address_space_stq_be_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val,
+                            MemTxAttrs attrs, MemTxResult *result);
+
+uint32_t ldub_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint32_t lduw_le_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint32_t lduw_be_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint32_t ldl_le_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint32_t ldl_be_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint64_t ldq_le_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+uint64_t ldq_be_phys_cached(MemoryRegionCache *cache, hwaddr addr);
+void stb_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stw_le_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stw_be_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stl_le_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stl_be_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint32_t val);
+void stq_le_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val);
+void stq_be_phys_cached(MemoryRegionCache *cache, hwaddr addr, uint64_t val);
+
 /* address_space_translate: translate an address range into an address space
 * into a MemoryRegion and an address range into that section.  Should be
 * called from an RCU critical section, to avoid that the last reference
@@ -1529,6 +1663,38 @@ MemTxResult address_space_read(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
    return result;
 }

+/**
+ * address_space_read_cached: read from a cached RAM region
+ *
+ * @cache: Cached region to be addressed
+ * @addr: address relative to the base of the RAM region
+ * @buf: buffer with the data transferred
+ * @len: length of the data transferred
+ */
+static inline void
+address_space_read_cached(MemoryRegionCache *cache, hwaddr addr,
+                          void *buf, int len)
+{
+    assert(addr < cache->len && len <= cache->len - addr);
+    memcpy(buf, cache->ptr + addr, len);
+}
+
+/**
+ * address_space_write_cached: write to a cached RAM region
+ *
+ * @cache: Cached region to be addressed
+ * @addr: address relative to the base of the RAM region
+ * @buf: buffer with the data transferred
+ * @len: length of the data transferred
+ */
+static inline void
+address_space_write_cached(MemoryRegionCache *cache, hwaddr addr,
+                           void *buf, int len)
+{
+    assert(addr < cache->len && len <= cache->len - addr);
+    memcpy(cache->ptr + addr, buf, len);
+}
+
 #endif

 #endif
--- a/Show More
+++ b/Show More