Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream-smm' into staging
This series implements KVM support for SMM, and lets you enable/disable
it through the "smm" property of x86 machine types.
# gpg: Signature made Mon Jul 6 17:41:05 2015 BST using RSA key ID 78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg: aka "Paolo Bonzini <pbonzini@redhat.com>"
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg: It is not certain that the signature belongs to the owner.
# 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-smm:
pc: add SMM property
ich9: add smm_enabled field and arguments
pc_piix: rename kvm_enabled to smm_enabled
target-i386: register a separate KVM address space including SMRAM regions
kvm-all: kvm_irqchip_create is not expected to fail
kvm-all: add support for multiple address spaces
kvm-all: make KVM's memory listener more generic
kvm-all: move internal types to kvm_int.h
kvm-all: remove useless typedef
kvm-all: put kvm_mem_flags to more work
target-i386: add support for SMBASE MSR and SMIs
piix4/ich9: do not raise SMI on ACPI enable/disable commands
linux-headers: Update to 4.2-rc1
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
diff --git a/hw/acpi/ich9.c b/hw/acpi/ich9.c
index 8a64ffb..f4dc7a8 100644
--- a/hw/acpi/ich9.c
+++ b/hw/acpi/ich9.c
@@ -192,7 +192,7 @@
acpi_pm_tmr_reset(&pm->acpi_regs);
acpi_gpe_reset(&pm->acpi_regs);
- if (kvm_enabled()) {
+ if (!pm->smm_enabled) {
/* Mark SMM as already inited to prevent SMM from running. KVM does not
* support SMM mode. */
pm->smi_en |= ICH9_PMIO_SMI_EN_APMC_EN;
@@ -209,7 +209,7 @@
acpi_pm1_evt_power_down(&pm->acpi_regs);
}
-void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm,
+void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm, bool smm_enabled,
qemu_irq sci_irq)
{
memory_region_init(&pm->io, OBJECT(lpc_pci), "ich9-pm", ICH9_PMIO_SIZE);
@@ -231,6 +231,7 @@
"acpi-smi", 8);
memory_region_add_subregion(&pm->io, ICH9_PMIO_SMI_EN, &pm->io_smi);
+ pm->smm_enabled = smm_enabled;
pm->irq = sci_irq;
qemu_register_reset(pm_reset, pm);
pm->powerdown_notifier.notify = pm_powerdown_req;
diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c
index 3bd1d5a..2cd2fee 100644
--- a/hw/acpi/piix4.c
+++ b/hw/acpi/piix4.c
@@ -72,7 +72,7 @@
qemu_irq irq;
qemu_irq smi_irq;
- int kvm_enabled;
+ int smm_enabled;
Notifier machine_ready;
Notifier powerdown_notifier;
@@ -112,6 +112,9 @@
/* ACPI specs 3.0, 4.7.2.5 */
acpi_pm1_cnt_update(&s->ar, val == ACPI_ENABLE, val == ACPI_DISABLE);
+ if (val == ACPI_ENABLE || val == ACPI_DISABLE) {
+ return;
+ }
if (d->config[0x5b] & (1 << 1)) {
if (s->smi_irq) {
@@ -319,7 +322,7 @@
pci_conf[0x40] = 0x01; /* PM io base read only bit */
pci_conf[0x80] = 0;
- if (s->kvm_enabled) {
+ if (!s->smm_enabled) {
/* Mark SMM as already inited (until KVM supports SMM). */
pci_conf[0x5B] = 0x02;
}
@@ -450,7 +453,7 @@
/* APM */
apm_init(dev, &s->apm, apm_ctrl_changed, s);
- if (s->kvm_enabled) {
+ if (!s->smm_enabled) {
/* Mark SMM as already inited to prevent SMM from running. KVM does not
* support SMM mode. */
pci_conf[0x5B] = 0x02;
@@ -501,7 +504,7 @@
I2CBus *piix4_pm_init(PCIBus *bus, int devfn, uint32_t smb_io_base,
qemu_irq sci_irq, qemu_irq smi_irq,
- int kvm_enabled, DeviceState **piix4_pm)
+ int smm_enabled, DeviceState **piix4_pm)
{
DeviceState *dev;
PIIX4PMState *s;
@@ -515,7 +518,7 @@
s = PIIX4_PM(dev);
s->irq = sci_irq;
s->smi_irq = smi_irq;
- s->kvm_enabled = kvm_enabled;
+ s->smm_enabled = smm_enabled;
if (xen_enabled()) {
s->use_acpi_pci_hotplug = false;
}
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index a66416d..7959b44 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1768,6 +1768,48 @@
visit_type_OnOffAuto(v, &pcms->vmport, name, errp);
}
+bool pc_machine_is_smm_enabled(PCMachineState *pcms)
+{
+ bool smm_available = false;
+
+ if (pcms->smm == ON_OFF_AUTO_OFF) {
+ return false;
+ }
+
+ if (tcg_enabled() || qtest_enabled()) {
+ smm_available = true;
+ } else if (kvm_enabled()) {
+ smm_available = kvm_has_smm();
+ }
+
+ if (smm_available) {
+ return true;
+ }
+
+ if (pcms->smm == ON_OFF_AUTO_ON) {
+ error_report("System Management Mode not supported by this hypervisor.");
+ exit(1);
+ }
+ return false;
+}
+
+static void pc_machine_get_smm(Object *obj, Visitor *v, void *opaque,
+ const char *name, Error **errp)
+{
+ PCMachineState *pcms = PC_MACHINE(obj);
+ OnOffAuto smm = pcms->smm;
+
+ visit_type_OnOffAuto(v, &smm, name, errp);
+}
+
+static void pc_machine_set_smm(Object *obj, Visitor *v, void *opaque,
+ const char *name, Error **errp)
+{
+ PCMachineState *pcms = PC_MACHINE(obj);
+
+ visit_type_OnOffAuto(v, &pcms->smm, name, errp);
+}
+
static bool pc_machine_get_aligned_dimm(Object *obj, Error **errp)
{
PCMachineState *pcms = PC_MACHINE(obj);
@@ -1792,6 +1834,15 @@
"Maximum ram below the 4G boundary (32bit boundary)",
NULL);
+ pcms->smm = ON_OFF_AUTO_AUTO;
+ object_property_add(obj, PC_MACHINE_SMM, "OnOffAuto",
+ pc_machine_get_smm,
+ pc_machine_set_smm,
+ NULL, NULL, NULL);
+ object_property_set_description(obj, PC_MACHINE_SMM,
+ "Enable SMM (pc & q35)",
+ NULL);
+
pcms->vmport = ON_OFF_AUTO_AUTO;
object_property_add(obj, PC_MACHINE_VMPORT, "OnOffAuto",
pc_machine_get_vmport,
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index e142f75..56cdcb9 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -287,7 +287,8 @@
/* TODO: Populate SPD eeprom data. */
smbus = piix4_pm_init(pci_bus, piix3_devfn + 3, 0xb100,
gsi[9], smi_irq,
- kvm_enabled(), &piix4_pm);
+ pc_machine_is_smm_enabled(pc_machine),
+ &piix4_pm);
smbus_eeprom_init(smbus, 8, NULL, 0);
object_property_add_link(OBJECT(machine), PC_MACHINE_ACPI_DEVICE_PROP,
@@ -306,7 +307,11 @@
static void pc_compat_2_3(MachineState *machine)
{
+ PCMachineState *pcms = PC_MACHINE(machine);
savevm_skip_section_footers();
+ if (kvm_enabled()) {
+ pcms->smm = ON_OFF_AUTO_OFF;
+ }
}
static void pc_compat_2_2(MachineState *machine)
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 082cd93..8aa3a67 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -253,7 +253,7 @@
(pc_machine->vmport != ON_OFF_AUTO_ON), 0xff0104);
/* connect pm stuff to lpc */
- ich9_lpc_pm_init(lpc);
+ ich9_lpc_pm_init(lpc, pc_machine_is_smm_enabled(pc_machine));
/* ahci and SATA device, for q35 1 ahci controller is built-in */
ahci = pci_create_simple_multifunction(host_bus,
@@ -290,7 +290,11 @@
static void pc_compat_2_3(MachineState *machine)
{
+ PCMachineState *pcms = PC_MACHINE(machine);
savevm_skip_section_footers();
+ if (kvm_enabled()) {
+ pcms->smm = ON_OFF_AUTO_OFF;
+ }
}
static void pc_compat_2_2(MachineState *machine)
diff --git a/hw/isa/lpc_ich9.c b/hw/isa/lpc_ich9.c
index b3e0b1f..bd655b8 100644
--- a/hw/isa/lpc_ich9.c
+++ b/hw/isa/lpc_ich9.c
@@ -357,11 +357,13 @@
}
}
-void ich9_lpc_pm_init(PCIDevice *lpc_pci)
+void ich9_lpc_pm_init(PCIDevice *lpc_pci, bool smm_enabled)
{
ICH9LPCState *lpc = ICH9_LPC_DEVICE(lpc_pci);
+ qemu_irq sci_irq;
- ich9_pm_init(lpc_pci, &lpc->pm, qemu_allocate_irq(ich9_set_sci, lpc, 0));
+ sci_irq = qemu_allocate_irq(ich9_set_sci, lpc, 0);
+ ich9_pm_init(lpc_pci, &lpc->pm, smm_enabled, sci_irq);
ich9_lpc_reset(&lpc->d.qdev);
}
@@ -375,6 +377,9 @@
acpi_pm1_cnt_update(&lpc->pm.acpi_regs,
val == ICH9_APM_ACPI_ENABLE,
val == ICH9_APM_ACPI_DISABLE);
+ if (val == ICH9_APM_ACPI_ENABLE || val == ICH9_APM_ACPI_DISABLE) {
+ return;
+ }
/* SMI_EN = PMBASE + 30. SMI control and enable register */
if (lpc->pm.smi_en & ICH9_PMIO_SMI_EN_APMC_EN) {
diff --git a/include/hw/acpi/ich9.h b/include/hw/acpi/ich9.h
index 77cc65c..ac24bbe 100644
--- a/include/hw/acpi/ich9.h
+++ b/include/hw/acpi/ich9.h
@@ -54,10 +54,11 @@
uint8_t disable_s3;
uint8_t disable_s4;
uint8_t s4_val;
+ uint8_t smm_enabled;
} ICH9LPCPMRegs;
void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm,
- qemu_irq sci_irq);
+ bool smm_enabled, qemu_irq sci_irq);
void ich9_pm_iospace_update(ICH9LPCPMRegs *pm, uint32_t pm_io_base);
extern const VMStateDescription vmstate_ich9_pm;
diff --git a/include/hw/i386/ich9.h b/include/hw/i386/ich9.h
index a2cc15c..b317a48 100644
--- a/include/hw/i386/ich9.h
+++ b/include/hw/i386/ich9.h
@@ -17,7 +17,7 @@
void ich9_lpc_set_irq(void *opaque, int irq_num, int level);
int ich9_lpc_map_irq(PCIDevice *pci_dev, int intx);
PCIINTxRoute ich9_route_intx_pin_to_irq(void *opaque, int pirq_pin);
-void ich9_lpc_pm_init(PCIDevice *pci_lpc);
+void ich9_lpc_pm_init(PCIDevice *pci_lpc, bool smm_enabled);
I2CBus *ich9_smb_init(PCIBus *bus, int devfn, uint32_t smb_io_base);
#define ICH9_CC_SIZE (16 * 1024) /* 16KB */
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 328c8f7..786a1d5 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -37,6 +37,7 @@
uint64_t max_ram_below_4g;
OnOffAuto vmport;
+ OnOffAuto smm;
bool enforce_aligned_dimm;
};
@@ -44,6 +45,7 @@
#define PC_MACHINE_MEMHP_REGION_SIZE "hotplug-memory-region-size"
#define PC_MACHINE_MAX_RAM_BELOW_4G "max-ram-below-4g"
#define PC_MACHINE_VMPORT "vmport"
+#define PC_MACHINE_SMM "smm"
#define PC_MACHINE_ENFORCE_ALIGNED_DIMM "enforce-aligned-dimm"
/**
@@ -155,6 +157,7 @@
/* pc.c */
extern int fd_bootchk;
+bool pc_machine_is_smm_enabled(PCMachineState *pcms);
void pc_register_ferr_irq(qemu_irq irq);
void pc_acpi_smi_interrupt(void *opaque, int irq, int level);
@@ -214,7 +217,7 @@
I2CBus *piix4_pm_init(PCIBus *bus, int devfn, uint32_t smb_io_base,
qemu_irq sci_irq, qemu_irq smi_irq,
- int kvm_enabled, DeviceState **piix4_pm);
+ int smm_enabled, DeviceState **piix4_pm);
void piix4_smbus_register_device(SMBusDevice *dev, uint8_t addr);
/* hpet.c */
diff --git a/include/standard-headers/linux/input.h b/include/standard-headers/linux/input.h
index b94d365..a459dd2 100644
--- a/include/standard-headers/linux/input.h
+++ b/include/standard-headers/linux/input.h
@@ -367,7 +367,8 @@
#define KEY_MSDOS 151
#define KEY_COFFEE 152 /* AL Terminal Lock/Screensaver */
#define KEY_SCREENLOCK KEY_COFFEE
-#define KEY_DIRECTION 153
+#define KEY_ROTATE_DISPLAY 153 /* Display orientation for e.g. tablets */
+#define KEY_DIRECTION KEY_ROTATE_DISPLAY
#define KEY_CYCLEWINDOWS 154
#define KEY_MAIL 155
#define KEY_BOOKMARKS 156 /* AC Bookmarks */
@@ -700,6 +701,10 @@
#define KEY_NUMERIC_9 0x209
#define KEY_NUMERIC_STAR 0x20a
#define KEY_NUMERIC_POUND 0x20b
+#define KEY_NUMERIC_A 0x20c /* Phone key A - HUT Telephony 0xb9 */
+#define KEY_NUMERIC_B 0x20d
+#define KEY_NUMERIC_C 0x20e
+#define KEY_NUMERIC_D 0x20f
#define KEY_CAMERA_FOCUS 0x210
#define KEY_WPS_BUTTON 0x211 /* WiFi Protected Setup key */
@@ -971,7 +976,8 @@
*/
#define MT_TOOL_FINGER 0
#define MT_TOOL_PEN 1
-#define MT_TOOL_MAX 1
+#define MT_TOOL_PALM 2
+#define MT_TOOL_MAX 2
/*
* Values describing the status of a force-feedback effect
diff --git a/include/standard-headers/linux/virtio_balloon.h b/include/standard-headers/linux/virtio_balloon.h
index 88ada1d..2e2a6dc 100644
--- a/include/standard-headers/linux/virtio_balloon.h
+++ b/include/standard-headers/linux/virtio_balloon.h
@@ -26,6 +26,7 @@
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE. */
#include "standard-headers/linux/types.h"
+#include "standard-headers/linux/virtio_types.h"
#include "standard-headers/linux/virtio_ids.h"
#include "standard-headers/linux/virtio_config.h"
diff --git a/include/standard-headers/linux/virtio_gpu.h b/include/standard-headers/linux/virtio_gpu.h
index cfcfb46..72ef815 100644
--- a/include/standard-headers/linux/virtio_gpu.h
+++ b/include/standard-headers/linux/virtio_gpu.h
@@ -38,6 +38,8 @@
#ifndef VIRTIO_GPU_HW_H
#define VIRTIO_GPU_HW_H
+#include "standard-headers/linux/types.h"
+
enum virtio_gpu_ctrl_type {
VIRTIO_GPU_UNDEFINED = 0,
diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h
new file mode 100644
index 0000000..888557a
--- /dev/null
+++ b/include/sysemu/kvm_int.h
@@ -0,0 +1,39 @@
+/*
+ * Internal definitions for a target's KVM support
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_KVM_INT_H
+#define QEMU_KVM_INT_H
+
+#include "sysemu/sysemu.h"
+#include "sysemu/accel.h"
+#include "sysemu/kvm.h"
+
+typedef struct KVMSlot
+{
+ hwaddr start_addr;
+ ram_addr_t memory_size;
+ void *ram;
+ int slot;
+ int flags;
+} KVMSlot;
+
+typedef struct KVMMemoryListener {
+ MemoryListener listener;
+ KVMSlot *slots;
+ int as_id;
+} KVMMemoryListener;
+
+#define TYPE_KVM_ACCEL ACCEL_CLASS_NAME("kvm")
+
+#define KVM_STATE(obj) \
+ OBJECT_CHECK(KVMState, (obj), TYPE_KVM_ACCEL)
+
+void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
+ AddressSpace *as, int as_id);
+
+#endif
diff --git a/kvm-all.c b/kvm-all.c
index df57da0..edff01c 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -24,13 +24,11 @@
#include "qemu/atomic.h"
#include "qemu/option.h"
#include "qemu/config-file.h"
-#include "sysemu/sysemu.h"
-#include "sysemu/accel.h"
#include "hw/hw.h"
#include "hw/pci/msi.h"
#include "hw/s390x/adapter.h"
#include "exec/gdbstub.h"
-#include "sysemu/kvm.h"
+#include "sysemu/kvm_int.h"
#include "qemu/bswap.h"
#include "exec/memory.h"
#include "exec/ram_addr.h"
@@ -60,22 +58,10 @@
#define KVM_MSI_HASHTAB_SIZE 256
-typedef struct KVMSlot
-{
- hwaddr start_addr;
- ram_addr_t memory_size;
- void *ram;
- int slot;
- int flags;
-} KVMSlot;
-
-typedef struct kvm_dirty_log KVMDirtyLog;
-
struct KVMState
{
AccelState parent_obj;
- KVMSlot *slots;
int nr_slots;
int fd;
int vmfd;
@@ -106,13 +92,9 @@
QTAILQ_HEAD(msi_hashtab, KVMMSIRoute) msi_hashtab[KVM_MSI_HASHTAB_SIZE];
bool direct_msi;
#endif
+ KVMMemoryListener memory_listener;
};
-#define TYPE_KVM_ACCEL ACCEL_CLASS_NAME("kvm")
-
-#define KVM_STATE(obj) \
- OBJECT_CHECK(KVMState, (obj), TYPE_KVM_ACCEL)
-
KVMState *kvm_state;
bool kvm_kernel_irqchip;
bool kvm_async_interrupts_allowed;
@@ -133,13 +115,14 @@
KVM_CAP_LAST_INFO
};
-static KVMSlot *kvm_get_free_slot(KVMState *s)
+static KVMSlot *kvm_get_free_slot(KVMMemoryListener *kml)
{
+ KVMState *s = kvm_state;
int i;
for (i = 0; i < s->nr_slots; i++) {
- if (s->slots[i].memory_size == 0) {
- return &s->slots[i];
+ if (kml->slots[i].memory_size == 0) {
+ return &kml->slots[i];
}
}
@@ -148,12 +131,14 @@
bool kvm_has_free_slot(MachineState *ms)
{
- return kvm_get_free_slot(KVM_STATE(ms->accelerator));
+ KVMState *s = KVM_STATE(ms->accelerator);
+
+ return kvm_get_free_slot(&s->memory_listener);
}
-static KVMSlot *kvm_alloc_slot(KVMState *s)
+static KVMSlot *kvm_alloc_slot(KVMMemoryListener *kml)
{
- KVMSlot *slot = kvm_get_free_slot(s);
+ KVMSlot *slot = kvm_get_free_slot(kml);
if (slot) {
return slot;
@@ -163,14 +148,15 @@
abort();
}
-static KVMSlot *kvm_lookup_matching_slot(KVMState *s,
+static KVMSlot *kvm_lookup_matching_slot(KVMMemoryListener *kml,
hwaddr start_addr,
hwaddr end_addr)
{
+ KVMState *s = kvm_state;
int i;
for (i = 0; i < s->nr_slots; i++) {
- KVMSlot *mem = &s->slots[i];
+ KVMSlot *mem = &kml->slots[i];
if (start_addr == mem->start_addr &&
end_addr == mem->start_addr + mem->memory_size) {
@@ -184,15 +170,16 @@
/*
* Find overlapping slot with lowest start address
*/
-static KVMSlot *kvm_lookup_overlapping_slot(KVMState *s,
+static KVMSlot *kvm_lookup_overlapping_slot(KVMMemoryListener *kml,
hwaddr start_addr,
hwaddr end_addr)
{
+ KVMState *s = kvm_state;
KVMSlot *found = NULL;
int i;
for (i = 0; i < s->nr_slots; i++) {
- KVMSlot *mem = &s->slots[i];
+ KVMSlot *mem = &kml->slots[i];
if (mem->memory_size == 0 ||
(found && found->start_addr < mem->start_addr)) {
@@ -211,10 +198,11 @@
int kvm_physical_memory_addr_from_host(KVMState *s, void *ram,
hwaddr *phys_addr)
{
+ KVMMemoryListener *kml = &s->memory_listener;
int i;
for (i = 0; i < s->nr_slots; i++) {
- KVMSlot *mem = &s->slots[i];
+ KVMSlot *mem = &kml->slots[i];
if (ram >= mem->ram && ram < mem->ram + mem->memory_size) {
*phys_addr = mem->start_addr + (ram - mem->ram);
@@ -225,11 +213,12 @@
return 0;
}
-static int kvm_set_user_memory_region(KVMState *s, KVMSlot *slot)
+static int kvm_set_user_memory_region(KVMMemoryListener *kml, KVMSlot *slot)
{
+ KVMState *s = kvm_state;
struct kvm_userspace_memory_region mem;
- mem.slot = slot->slot;
+ mem.slot = slot->slot | (kml->as_id << 16);
mem.guest_phys_addr = slot->start_addr;
mem.userspace_addr = (unsigned long)slot->ram;
mem.flags = slot->flags;
@@ -291,45 +280,47 @@
* dirty pages logging control
*/
-static int kvm_mem_flags(KVMState *s, bool log_dirty, bool readonly)
+static int kvm_mem_flags(MemoryRegion *mr)
{
+ bool readonly = mr->readonly || memory_region_is_romd(mr);
int flags = 0;
- flags = log_dirty ? KVM_MEM_LOG_DIRTY_PAGES : 0;
+
+ if (memory_region_get_dirty_log_mask(mr) != 0) {
+ flags |= KVM_MEM_LOG_DIRTY_PAGES;
+ }
if (readonly && kvm_readonly_mem_allowed) {
flags |= KVM_MEM_READONLY;
}
return flags;
}
-static int kvm_slot_dirty_pages_log_change(KVMSlot *mem, bool log_dirty)
+static int kvm_slot_update_flags(KVMMemoryListener *kml, KVMSlot *mem,
+ MemoryRegion *mr)
{
- KVMState *s = kvm_state;
- int flags, mask = KVM_MEM_LOG_DIRTY_PAGES;
int old_flags;
old_flags = mem->flags;
-
- flags = (mem->flags & ~mask) | kvm_mem_flags(s, log_dirty, false);
- mem->flags = flags;
+ mem->flags = kvm_mem_flags(mr);
/* If nothing changed effectively, no need to issue ioctl */
- if (flags == old_flags) {
+ if (mem->flags == old_flags) {
return 0;
}
- return kvm_set_user_memory_region(s, mem);
+ return kvm_set_user_memory_region(kml, mem);
}
-static int kvm_dirty_pages_log_change(hwaddr phys_addr,
- ram_addr_t size, bool log_dirty)
+static int kvm_section_update_flags(KVMMemoryListener *kml,
+ MemoryRegionSection *section)
{
- KVMState *s = kvm_state;
- KVMSlot *mem = kvm_lookup_matching_slot(s, phys_addr, phys_addr + size);
+ hwaddr phys_addr = section->offset_within_address_space;
+ ram_addr_t size = int128_get64(section->size);
+ KVMSlot *mem = kvm_lookup_matching_slot(kml, phys_addr, phys_addr + size);
if (mem == NULL) {
return 0;
} else {
- return kvm_slot_dirty_pages_log_change(mem, log_dirty);
+ return kvm_slot_update_flags(kml, mem, section->mr);
}
}
@@ -337,14 +328,14 @@
MemoryRegionSection *section,
int old, int new)
{
+ KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);
int r;
if (old != 0) {
return;
}
- r = kvm_dirty_pages_log_change(section->offset_within_address_space,
- int128_get64(section->size), true);
+ r = kvm_section_update_flags(kml, section);
if (r < 0) {
abort();
}
@@ -354,14 +345,14 @@
MemoryRegionSection *section,
int old, int new)
{
+ KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);
int r;
if (new != 0) {
return;
}
- r = kvm_dirty_pages_log_change(section->offset_within_address_space,
- int128_get64(section->size), false);
+ r = kvm_section_update_flags(kml, section);
if (r < 0) {
abort();
}
@@ -389,11 +380,12 @@
* @start_add: start of logged region.
* @end_addr: end of logged region.
*/
-static int kvm_physical_sync_dirty_bitmap(MemoryRegionSection *section)
+static int kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml,
+ MemoryRegionSection *section)
{
KVMState *s = kvm_state;
unsigned long size, allocated_size = 0;
- KVMDirtyLog d = {};
+ struct kvm_dirty_log d = {};
KVMSlot *mem;
int ret = 0;
hwaddr start_addr = section->offset_within_address_space;
@@ -401,7 +393,7 @@
d.dirty_bitmap = NULL;
while (start_addr < end_addr) {
- mem = kvm_lookup_overlapping_slot(s, start_addr, end_addr);
+ mem = kvm_lookup_overlapping_slot(kml, start_addr, end_addr);
if (mem == NULL) {
break;
}
@@ -428,8 +420,7 @@
allocated_size = size;
memset(d.dirty_bitmap, 0, allocated_size);
- d.slot = mem->slot;
-
+ d.slot = mem->slot | (kml->as_id << 16);
if (kvm_vm_ioctl(s, KVM_GET_DIRTY_LOG, &d) == -1) {
DPRINTF("ioctl failed %d\n", errno);
ret = -1;
@@ -632,15 +623,14 @@
return NULL;
}
-static void kvm_set_phys_mem(MemoryRegionSection *section, bool add)
+static void kvm_set_phys_mem(KVMMemoryListener *kml,
+ MemoryRegionSection *section, bool add)
{
KVMState *s = kvm_state;
KVMSlot *mem, old;
int err;
MemoryRegion *mr = section->mr;
- bool log_dirty = memory_region_get_dirty_log_mask(mr) != 0;
bool writeable = !mr->readonly && !mr->rom_device;
- bool readonly_flag = mr->readonly || memory_region_is_romd(mr);
hwaddr start_addr = section->offset_within_address_space;
ram_addr_t size = int128_get64(section->size);
void *ram = NULL;
@@ -674,7 +664,7 @@
ram = memory_region_get_ram_ptr(mr) + section->offset_within_region + delta;
while (1) {
- mem = kvm_lookup_overlapping_slot(s, start_addr, start_addr + size);
+ mem = kvm_lookup_overlapping_slot(kml, start_addr, start_addr + size);
if (!mem) {
break;
}
@@ -684,19 +674,19 @@
(ram - start_addr == mem->ram - mem->start_addr)) {
/* The new slot fits into the existing one and comes with
* identical parameters - update flags and done. */
- kvm_slot_dirty_pages_log_change(mem, log_dirty);
+ kvm_slot_update_flags(kml, mem, mr);
return;
}
old = *mem;
if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
- kvm_physical_sync_dirty_bitmap(section);
+ kvm_physical_sync_dirty_bitmap(kml, section);
}
/* unregister the overlapping slot */
mem->memory_size = 0;
- err = kvm_set_user_memory_region(s, mem);
+ err = kvm_set_user_memory_region(kml, mem);
if (err) {
fprintf(stderr, "%s: error unregistering overlapping slot: %s\n",
__func__, strerror(-err));
@@ -713,13 +703,13 @@
* - and actually require a recent KVM version. */
if (s->broken_set_mem_region &&
old.start_addr == start_addr && old.memory_size < size && add) {
- mem = kvm_alloc_slot(s);
+ mem = kvm_alloc_slot(kml);
mem->memory_size = old.memory_size;
mem->start_addr = old.start_addr;
mem->ram = old.ram;
- mem->flags = kvm_mem_flags(s, log_dirty, readonly_flag);
+ mem->flags = kvm_mem_flags(mr);
- err = kvm_set_user_memory_region(s, mem);
+ err = kvm_set_user_memory_region(kml, mem);
if (err) {
fprintf(stderr, "%s: error updating slot: %s\n", __func__,
strerror(-err));
@@ -734,13 +724,13 @@
/* register prefix slot */
if (old.start_addr < start_addr) {
- mem = kvm_alloc_slot(s);
+ mem = kvm_alloc_slot(kml);
mem->memory_size = start_addr - old.start_addr;
mem->start_addr = old.start_addr;
mem->ram = old.ram;
- mem->flags = kvm_mem_flags(s, log_dirty, readonly_flag);
+ mem->flags = kvm_mem_flags(mr);
- err = kvm_set_user_memory_region(s, mem);
+ err = kvm_set_user_memory_region(kml, mem);
if (err) {
fprintf(stderr, "%s: error registering prefix slot: %s\n",
__func__, strerror(-err));
@@ -757,14 +747,14 @@
if (old.start_addr + old.memory_size > start_addr + size) {
ram_addr_t size_delta;
- mem = kvm_alloc_slot(s);
+ mem = kvm_alloc_slot(kml);
mem->start_addr = start_addr + size;
size_delta = mem->start_addr - old.start_addr;
mem->memory_size = old.memory_size - size_delta;
mem->ram = old.ram + size_delta;
- mem->flags = kvm_mem_flags(s, log_dirty, readonly_flag);
+ mem->flags = kvm_mem_flags(mr);
- err = kvm_set_user_memory_region(s, mem);
+ err = kvm_set_user_memory_region(kml, mem);
if (err) {
fprintf(stderr, "%s: error registering suffix slot: %s\n",
__func__, strerror(-err));
@@ -780,13 +770,13 @@
if (!add) {
return;
}
- mem = kvm_alloc_slot(s);
+ mem = kvm_alloc_slot(kml);
mem->memory_size = size;
mem->start_addr = start_addr;
mem->ram = ram;
- mem->flags = kvm_mem_flags(s, log_dirty, readonly_flag);
+ mem->flags = kvm_mem_flags(mr);
- err = kvm_set_user_memory_region(s, mem);
+ err = kvm_set_user_memory_region(kml, mem);
if (err) {
fprintf(stderr, "%s: error registering slot: %s\n", __func__,
strerror(-err));
@@ -797,23 +787,28 @@
static void kvm_region_add(MemoryListener *listener,
MemoryRegionSection *section)
{
+ KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);
+
memory_region_ref(section->mr);
- kvm_set_phys_mem(section, true);
+ kvm_set_phys_mem(kml, section, true);
}
static void kvm_region_del(MemoryListener *listener,
MemoryRegionSection *section)
{
- kvm_set_phys_mem(section, false);
+ KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);
+
+ kvm_set_phys_mem(kml, section, false);
memory_region_unref(section->mr);
}
static void kvm_log_sync(MemoryListener *listener,
MemoryRegionSection *section)
{
+ KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);
int r;
- r = kvm_physical_sync_dirty_bitmap(section);
+ r = kvm_physical_sync_dirty_bitmap(kml, section);
if (r < 0) {
abort();
}
@@ -888,18 +883,27 @@
}
}
-static MemoryListener kvm_memory_listener = {
- .region_add = kvm_region_add,
- .region_del = kvm_region_del,
- .log_start = kvm_log_start,
- .log_stop = kvm_log_stop,
- .log_sync = kvm_log_sync,
- .eventfd_add = kvm_mem_ioeventfd_add,
- .eventfd_del = kvm_mem_ioeventfd_del,
- .coalesced_mmio_add = kvm_coalesce_mmio_region,
- .coalesced_mmio_del = kvm_uncoalesce_mmio_region,
- .priority = 10,
-};
+void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
+ AddressSpace *as, int as_id)
+{
+ int i;
+
+ kml->slots = g_malloc0(s->nr_slots * sizeof(KVMSlot));
+ kml->as_id = as_id;
+
+ for (i = 0; i < s->nr_slots; i++) {
+ kml->slots[i].slot = i;
+ }
+
+ kml->listener.region_add = kvm_region_add;
+ kml->listener.region_del = kvm_region_del;
+ kml->listener.log_start = kvm_log_start;
+ kml->listener.log_stop = kvm_log_stop;
+ kml->listener.log_sync = kvm_log_sync;
+ kml->listener.priority = 10;
+
+ memory_listener_register(&kml->listener, as);
+}
static MemoryListener kvm_io_listener = {
.eventfd_add = kvm_io_ioeventfd_add,
@@ -1341,27 +1345,31 @@
false);
}
-static int kvm_irqchip_create(MachineState *machine, KVMState *s)
+static void kvm_irqchip_create(MachineState *machine, KVMState *s)
{
int ret;
- if (!machine_kernel_irqchip_allowed(machine) ||
- (!kvm_check_extension(s, KVM_CAP_IRQCHIP) &&
- (kvm_vm_enable_cap(s, KVM_CAP_S390_IRQCHIP, 0) < 0))) {
- return 0;
+ if (kvm_check_extension(s, KVM_CAP_IRQCHIP)) {
+ ;
+ } else if (kvm_check_extension(s, KVM_CAP_S390_IRQCHIP)) {
+ ret = kvm_vm_enable_cap(s, KVM_CAP_S390_IRQCHIP, 0);
+ if (ret < 0) {
+ fprintf(stderr, "Enable kernel irqchip failed: %s\n", strerror(-ret));
+ exit(1);
+ }
+ } else {
+ return;
}
/* First probe and see if there's a arch-specific hook to create the
* in-kernel irqchip for us */
ret = kvm_arch_irqchip_create(s);
- if (ret < 0) {
- return ret;
- } else if (ret == 0) {
+ if (ret == 0) {
ret = kvm_vm_ioctl(s, KVM_CREATE_IRQCHIP);
- if (ret < 0) {
- fprintf(stderr, "Create kernel irqchip failed\n");
- return ret;
- }
+ }
+ if (ret < 0) {
+ fprintf(stderr, "Create kernel irqchip failed: %s\n", strerror(-ret));
+ exit(1);
}
kvm_kernel_irqchip = true;
@@ -1372,8 +1380,6 @@
kvm_halt_in_kernel_allowed = true;
kvm_init_irq_routing(s);
-
- return 0;
}
/* Find number of supported CPUs using the recommended
@@ -1410,7 +1416,7 @@
KVMState *s;
const KVMCapabilityInfo *missing_cap;
int ret;
- int i, type = 0;
+ int type = 0;
const char *kvm_type;
s = KVM_STATE(ms->accelerator);
@@ -1459,12 +1465,6 @@
s->nr_slots = 32;
}
- s->slots = g_malloc0(s->nr_slots * sizeof(KVMSlot));
-
- for (i = 0; i < s->nr_slots; i++) {
- s->slots[i].slot = i;
- }
-
/* check the vcpu limits */
soft_vcpus_limit = kvm_recommended_vcpus(s);
hard_vcpus_limit = kvm_max_vcpus(s);
@@ -1596,14 +1596,21 @@
goto err;
}
- ret = kvm_irqchip_create(ms, s);
- if (ret < 0) {
- goto err;
+ if (machine_kernel_irqchip_allowed(ms)) {
+ kvm_irqchip_create(ms, s);
}
kvm_state = s;
- memory_listener_register(&kvm_memory_listener, &address_space_memory);
- memory_listener_register(&kvm_io_listener, &address_space_io);
+
+ s->memory_listener.listener.eventfd_add = kvm_mem_ioeventfd_add;
+ s->memory_listener.listener.eventfd_del = kvm_mem_ioeventfd_del;
+ s->memory_listener.listener.coalesced_mmio_add = kvm_coalesce_mmio_region;
+ s->memory_listener.listener.coalesced_mmio_del = kvm_uncoalesce_mmio_region;
+
+ kvm_memory_listener_register(s, &s->memory_listener,
+ &address_space_memory, 0);
+ memory_listener_register(&kvm_io_listener,
+ &address_space_io);
s->many_ioeventfds = kvm_check_many_ioeventfds();
@@ -1619,7 +1626,7 @@
if (s->fd != -1) {
close(s->fd);
}
- g_free(s->slots);
+ g_free(s->memory_listener.slots);
return ret;
}
diff --git a/linux-headers/asm-x86/hyperv.h b/linux-headers/asm-x86/hyperv.h
index ce6068d..8fba544 100644
--- a/linux-headers/asm-x86/hyperv.h
+++ b/linux-headers/asm-x86/hyperv.h
@@ -199,6 +199,17 @@
#define HV_X64_MSR_STIMER3_CONFIG 0x400000B6
#define HV_X64_MSR_STIMER3_COUNT 0x400000B7
+/* Hyper-V guest crash notification MSR's */
+#define HV_X64_MSR_CRASH_P0 0x40000100
+#define HV_X64_MSR_CRASH_P1 0x40000101
+#define HV_X64_MSR_CRASH_P2 0x40000102
+#define HV_X64_MSR_CRASH_P3 0x40000103
+#define HV_X64_MSR_CRASH_P4 0x40000104
+#define HV_X64_MSR_CRASH_CTL 0x40000105
+#define HV_X64_MSR_CRASH_CTL_NOTIFY (1ULL << 63)
+#define HV_X64_MSR_CRASH_PARAMS \
+ (1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0))
+
#define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001
#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12
#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \
diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index fad9e5c..3bac873 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -897,7 +897,7 @@
*
* KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
* the irqfd to operate in resampling mode for level triggered interrupt
- * emlation. See Documentation/virtual/kvm/api.txt.
+ * emulation. See Documentation/virtual/kvm/api.txt.
*/
#define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index 0508d0b..aa276bc 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -36,6 +36,8 @@
/* Two-stage IOMMU */
#define VFIO_TYPE1_NESTING_IOMMU 6 /* Implies v2 */
+#define VFIO_SPAPR_TCE_v2_IOMMU 7
+
/*
* The IOCTL interface is designed for extensibility by embedding the
* structure length (argsz) and flags into structures passed between
@@ -443,6 +445,23 @@
/* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
/*
+ * The SPAPR TCE DDW info struct provides the information about
+ * the details of Dynamic DMA window capability.
+ *
+ * @pgsizes contains a page size bitmask, 4K/64K/16M are supported.
+ * @max_dynamic_windows_supported tells the maximum number of windows
+ * which the platform can create.
+ * @levels tells the maximum number of levels in multi-level IOMMU tables;
+ * this allows splitting a table into smaller chunks which reduces
+ * the amount of physically contiguous memory required for the table.
+ */
+struct vfio_iommu_spapr_tce_ddw_info {
+ __u64 pgsizes; /* Bitmap of supported page sizes */
+ __u32 max_dynamic_windows_supported;
+ __u32 levels;
+};
+
+/*
* The SPAPR TCE info struct provides the information about the PCI bus
* address ranges available for DMA, these values are programmed into
* the hardware so the guest has to know that information.
@@ -452,14 +471,17 @@
* addresses too so the window works as a filter rather than an offset
* for IOVA addresses.
*
- * A flag will need to be added if other page sizes are supported,
- * so as defined here, it is always 4k.
+ * Flags supported:
+ * - VFIO_IOMMU_SPAPR_INFO_DDW: informs the userspace that dynamic DMA windows
+ * (DDW) support is present. @ddw is only supported when DDW is present.
*/
struct vfio_iommu_spapr_tce_info {
__u32 argsz;
- __u32 flags; /* reserved for future use */
+ __u32 flags;
+#define VFIO_IOMMU_SPAPR_INFO_DDW (1 << 0) /* DDW supported */
__u32 dma32_window_start; /* 32 bit window start (bytes) */
__u32 dma32_window_size; /* 32 bit window size (bytes) */
+ struct vfio_iommu_spapr_tce_ddw_info ddw;
};
#define VFIO_IOMMU_SPAPR_TCE_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
@@ -470,12 +492,23 @@
* - unfreeze IO/DMA for frozen PE;
* - read PE state;
* - reset PE;
- * - configure PE.
+ * - configure PE;
+ * - inject EEH error.
*/
+struct vfio_eeh_pe_err {
+ __u32 type;
+ __u32 func;
+ __u64 addr;
+ __u64 mask;
+};
+
struct vfio_eeh_pe_op {
__u32 argsz;
__u32 flags;
__u32 op;
+ union {
+ struct vfio_eeh_pe_err err;
+ };
};
#define VFIO_EEH_PE_DISABLE 0 /* Disable EEH functionality */
@@ -492,9 +525,70 @@
#define VFIO_EEH_PE_RESET_HOT 6 /* Assert hot reset */
#define VFIO_EEH_PE_RESET_FUNDAMENTAL 7 /* Assert fundamental reset */
#define VFIO_EEH_PE_CONFIGURE 8 /* PE configuration */
+#define VFIO_EEH_PE_INJECT_ERR 9 /* Inject EEH error */
#define VFIO_EEH_PE_OP _IO(VFIO_TYPE, VFIO_BASE + 21)
+/**
+ * VFIO_IOMMU_SPAPR_REGISTER_MEMORY - _IOW(VFIO_TYPE, VFIO_BASE + 17, struct vfio_iommu_spapr_register_memory)
+ *
+ * Registers user space memory where DMA is allowed. It pins
+ * user pages and does the locked memory accounting so
+ * subsequent VFIO_IOMMU_MAP_DMA/VFIO_IOMMU_UNMAP_DMA calls
+ * get faster.
+ */
+struct vfio_iommu_spapr_register_memory {
+ __u32 argsz;
+ __u32 flags;
+ __u64 vaddr; /* Process virtual address */
+ __u64 size; /* Size of mapping (bytes) */
+};
+#define VFIO_IOMMU_SPAPR_REGISTER_MEMORY _IO(VFIO_TYPE, VFIO_BASE + 17)
+
+/**
+ * VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY - _IOW(VFIO_TYPE, VFIO_BASE + 18, struct vfio_iommu_spapr_register_memory)
+ *
+ * Unregisters user space memory registered with
+ * VFIO_IOMMU_SPAPR_REGISTER_MEMORY.
+ * Uses vfio_iommu_spapr_register_memory for parameters.
+ */
+#define VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY _IO(VFIO_TYPE, VFIO_BASE + 18)
+
+/**
+ * VFIO_IOMMU_SPAPR_TCE_CREATE - _IOWR(VFIO_TYPE, VFIO_BASE + 19, struct vfio_iommu_spapr_tce_create)
+ *
+ * Creates an additional TCE table and programs it (sets a new DMA window)
+ * to every IOMMU group in the container. It receives page shift, window
+ * size and number of levels in the TCE table being created.
+ *
+ * It allocates and returns an offset on a PCI bus of the new DMA window.
+ */
+struct vfio_iommu_spapr_tce_create {
+ __u32 argsz;
+ __u32 flags;
+ /* in */
+ __u32 page_shift;
+ __u64 window_size;
+ __u32 levels;
+ /* out */
+ __u64 start_addr;
+};
+#define VFIO_IOMMU_SPAPR_TCE_CREATE _IO(VFIO_TYPE, VFIO_BASE + 19)
+
+/**
+ * VFIO_IOMMU_SPAPR_TCE_REMOVE - _IOW(VFIO_TYPE, VFIO_BASE + 20, struct vfio_iommu_spapr_tce_remove)
+ *
+ * Unprograms a TCE table from all groups in the container and destroys it.
+ * It receives a PCI bus offset as a window id.
+ */
+struct vfio_iommu_spapr_tce_remove {
+ __u32 argsz;
+ __u32 flags;
+ /* in */
+ __u64 start_addr;
+};
+#define VFIO_IOMMU_SPAPR_TCE_REMOVE _IO(VFIO_TYPE, VFIO_BASE + 20)
+
/* ***************************************************************** */
#endif /* VFIO_H */
diff --git a/linux-headers/linux/virtio_pci.h b/linux-headers/linux/virtio_pci.h
deleted file mode 100644
index 92624e5..0000000
--- a/linux-headers/linux/virtio_pci.h
+++ /dev/null
@@ -1,192 +0,0 @@
-/*
- * Virtio PCI driver
- *
- * This module allows virtio devices to be used over a virtual PCI device.
- * This can be used with QEMU based VMMs like KVM or Xen.
- *
- * Copyright IBM Corp. 2007
- *
- * Authors:
- * Anthony Liguori <aliguori@us.ibm.com>
- *
- * This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of IBM nor the names of its contributors
- * may be used to endorse or promote products derived from this software
- * without specific prior written permission.
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- */
-
-#ifndef _LINUX_VIRTIO_PCI_H
-#define _LINUX_VIRTIO_PCI_H
-
-#include <linux/types.h>
-
-#ifndef VIRTIO_PCI_NO_LEGACY
-
-/* A 32-bit r/o bitmask of the features supported by the host */
-#define VIRTIO_PCI_HOST_FEATURES 0
-
-/* A 32-bit r/w bitmask of features activated by the guest */
-#define VIRTIO_PCI_GUEST_FEATURES 4
-
-/* A 32-bit r/w PFN for the currently selected queue */
-#define VIRTIO_PCI_QUEUE_PFN 8
-
-/* A 16-bit r/o queue size for the currently selected queue */
-#define VIRTIO_PCI_QUEUE_NUM 12
-
-/* A 16-bit r/w queue selector */
-#define VIRTIO_PCI_QUEUE_SEL 14
-
-/* A 16-bit r/w queue notifier */
-#define VIRTIO_PCI_QUEUE_NOTIFY 16
-
-/* An 8-bit device status register. */
-#define VIRTIO_PCI_STATUS 18
-
-/* An 8-bit r/o interrupt status register. Reading the value will return the
- * current contents of the ISR and will also clear it. This is effectively
- * a read-and-acknowledge. */
-#define VIRTIO_PCI_ISR 19
-
-/* MSI-X registers: only enabled if MSI-X is enabled. */
-/* A 16-bit vector for configuration changes. */
-#define VIRTIO_MSI_CONFIG_VECTOR 20
-/* A 16-bit vector for selected queue notifications. */
-#define VIRTIO_MSI_QUEUE_VECTOR 22
-
-/* The remaining space is defined by each driver as the per-driver
- * configuration space */
-#define VIRTIO_PCI_CONFIG_OFF(msix_enabled) ((msix_enabled) ? 24 : 20)
-/* Deprecated: please use VIRTIO_PCI_CONFIG_OFF instead */
-#define VIRTIO_PCI_CONFIG(dev) VIRTIO_PCI_CONFIG_OFF((dev)->msix_enabled)
-
-/* Virtio ABI version, this must match exactly */
-#define VIRTIO_PCI_ABI_VERSION 0
-
-/* How many bits to shift physical queue address written to QUEUE_PFN.
- * 12 is historical, and due to x86 page size. */
-#define VIRTIO_PCI_QUEUE_ADDR_SHIFT 12
-
-/* The alignment to use between consumer and producer parts of vring.
- * x86 pagesize again. */
-#define VIRTIO_PCI_VRING_ALIGN 4096
-
-#endif /* VIRTIO_PCI_NO_LEGACY */
-
-/* The bit of the ISR which indicates a device configuration change. */
-#define VIRTIO_PCI_ISR_CONFIG 0x2
-/* Vector value used to disable MSI for queue */
-#define VIRTIO_MSI_NO_VECTOR 0xffff
-
-#ifndef VIRTIO_PCI_NO_MODERN
-
-/* IDs for different capabilities. Must all exist. */
-
-/* Common configuration */
-#define VIRTIO_PCI_CAP_COMMON_CFG 1
-/* Notifications */
-#define VIRTIO_PCI_CAP_NOTIFY_CFG 2
-/* ISR access */
-#define VIRTIO_PCI_CAP_ISR_CFG 3
-/* Device specific confiuration */
-#define VIRTIO_PCI_CAP_DEVICE_CFG 4
-
-/* This is the PCI capability header: */
-struct virtio_pci_cap {
- __u8 cap_vndr; /* Generic PCI field: PCI_CAP_ID_VNDR */
- __u8 cap_next; /* Generic PCI field: next ptr. */
- __u8 cap_len; /* Generic PCI field: capability length */
- __u8 cfg_type; /* Identifies the structure. */
- __u8 bar; /* Where to find it. */
- __u8 padding[3]; /* Pad to full dword. */
- __le32 offset; /* Offset within bar. */
- __le32 length; /* Length of the structure, in bytes. */
-};
-
-struct virtio_pci_notify_cap {
- struct virtio_pci_cap cap;
- __le32 notify_off_multiplier; /* Multiplier for queue_notify_off. */
-};
-
-/* Fields in VIRTIO_PCI_CAP_COMMON_CFG: */
-struct virtio_pci_common_cfg {
- /* About the whole device. */
- __le32 device_feature_select; /* read-write */
- __le32 device_feature; /* read-only */
- __le32 guest_feature_select; /* read-write */
- __le32 guest_feature; /* read-write */
- __le16 msix_config; /* read-write */
- __le16 num_queues; /* read-only */
- __u8 device_status; /* read-write */
- __u8 config_generation; /* read-only */
-
- /* About a specific virtqueue. */
- __le16 queue_select; /* read-write */
- __le16 queue_size; /* read-write, power of 2. */
- __le16 queue_msix_vector; /* read-write */
- __le16 queue_enable; /* read-write */
- __le16 queue_notify_off; /* read-only */
- __le32 queue_desc_lo; /* read-write */
- __le32 queue_desc_hi; /* read-write */
- __le32 queue_avail_lo; /* read-write */
- __le32 queue_avail_hi; /* read-write */
- __le32 queue_used_lo; /* read-write */
- __le32 queue_used_hi; /* read-write */
-};
-
-/* Macro versions of offsets for the Old Timers! */
-#define VIRTIO_PCI_CAP_VNDR 0
-#define VIRTIO_PCI_CAP_NEXT 1
-#define VIRTIO_PCI_CAP_LEN 2
-#define VIRTIO_PCI_CAP_CFG_TYPE 3
-#define VIRTIO_PCI_CAP_BAR 4
-#define VIRTIO_PCI_CAP_OFFSET 8
-#define VIRTIO_PCI_CAP_LENGTH 12
-
-#define VIRTIO_PCI_NOTIFY_CAP_MULT 16
-
-
-#define VIRTIO_PCI_COMMON_DFSELECT 0
-#define VIRTIO_PCI_COMMON_DF 4
-#define VIRTIO_PCI_COMMON_GFSELECT 8
-#define VIRTIO_PCI_COMMON_GF 12
-#define VIRTIO_PCI_COMMON_MSIX 16
-#define VIRTIO_PCI_COMMON_NUMQ 18
-#define VIRTIO_PCI_COMMON_STATUS 20
-#define VIRTIO_PCI_COMMON_CFGGENERATION 21
-#define VIRTIO_PCI_COMMON_Q_SELECT 22
-#define VIRTIO_PCI_COMMON_Q_SIZE 24
-#define VIRTIO_PCI_COMMON_Q_MSIX 26
-#define VIRTIO_PCI_COMMON_Q_ENABLE 28
-#define VIRTIO_PCI_COMMON_Q_NOFF 30
-#define VIRTIO_PCI_COMMON_Q_DESCLO 32
-#define VIRTIO_PCI_COMMON_Q_DESCHI 36
-#define VIRTIO_PCI_COMMON_Q_AVAILLO 40
-#define VIRTIO_PCI_COMMON_Q_AVAILHI 44
-#define VIRTIO_PCI_COMMON_Q_USEDLO 48
-#define VIRTIO_PCI_COMMON_Q_USEDHI 52
-
-#endif /* VIRTIO_PCI_NO_MODERN */
-
-#endif
diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index 603aaf0..ac39291 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -314,6 +314,7 @@
#define MSR_P6_PERFCTR0 0xc1
+#define MSR_IA32_SMBASE 0x9e
#define MSR_MTRRcap 0xfe
#define MSR_MTRRcap_VCNT 8
#define MSR_MTRRcap_FIXRANGE_SUPPORT (1 << 8)
diff --git a/target-i386/kvm-stub.c b/target-i386/kvm-stub.c
index 2b9e801..6fefd65 100644
--- a/target-i386/kvm-stub.c
+++ b/target-i386/kvm-stub.c
@@ -18,6 +18,11 @@
}
#ifndef __OPTIMIZE__
+bool kvm_has_smm(void)
+{
+ return 1;
+}
+
/* This function is only called inside conditionals which we
* rely on the compiler to optimize out when CONFIG_KVM is not
* defined.
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 6426600..9038bf7 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -22,7 +22,7 @@
#include "qemu-common.h"
#include "sysemu/sysemu.h"
-#include "sysemu/kvm.h"
+#include "sysemu/kvm_int.h"
#include "kvm_i386.h"
#include "cpu.h"
#include "exec/gdbstub.h"
@@ -73,6 +73,7 @@
static bool has_msr_async_pf_en;
static bool has_msr_pv_eoi_en;
static bool has_msr_misc_enable;
+static bool has_msr_smbase;
static bool has_msr_bndcfgs;
static bool has_msr_kvm_steal_time;
static int lm_capable_kernel;
@@ -85,6 +86,11 @@
static bool has_msr_architectural_pmu;
static uint32_t num_architectural_pmu_counters;
+bool kvm_has_smm(void)
+{
+ return kvm_check_extension(kvm_state, KVM_CAP_X86_SMM);
+}
+
bool kvm_allows_irq0_override(void)
{
return !kvm_irqchip_in_kernel() || kvm_has_gsi_routing();
@@ -819,6 +825,10 @@
has_msr_tsc_deadline = true;
continue;
}
+ if (kvm_msr_list->indices[i] == MSR_IA32_SMBASE) {
+ has_msr_smbase = true;
+ continue;
+ }
if (kvm_msr_list->indices[i] == MSR_IA32_MISC_ENABLE) {
has_msr_misc_enable = true;
continue;
@@ -840,6 +850,40 @@
return ret;
}
+static Notifier smram_machine_done;
+static KVMMemoryListener smram_listener;
+static AddressSpace smram_address_space;
+static MemoryRegion smram_as_root;
+static MemoryRegion smram_as_mem;
+
+static void register_smram_listener(Notifier *n, void *unused)
+{
+ MemoryRegion *smram =
+ (MemoryRegion *) object_resolve_path("/machine/smram", NULL);
+
+ /* Outer container... */
+ memory_region_init(&smram_as_root, OBJECT(kvm_state), "mem-container-smram", ~0ull);
+ memory_region_set_enabled(&smram_as_root, true);
+
+ /* ... with two regions inside: normal system memory with low
+ * priority, and...
+ */
+ memory_region_init_alias(&smram_as_mem, OBJECT(kvm_state), "mem-smram",
+ get_system_memory(), 0, ~0ull);
+ memory_region_add_subregion_overlap(&smram_as_root, 0, &smram_as_mem, 0);
+ memory_region_set_enabled(&smram_as_mem, true);
+
+ if (smram) {
+ /* ... SMRAM with higher priority */
+ memory_region_add_subregion_overlap(&smram_as_root, 0, smram, 10);
+ memory_region_set_enabled(smram, true);
+ }
+
+ address_space_init(&smram_address_space, &smram_as_root, "KVM-SMRAM");
+ kvm_memory_listener_register(kvm_state, &smram_listener,
+ &smram_address_space, 1);
+}
+
int kvm_arch_init(MachineState *ms, KVMState *s)
{
uint64_t identity_base = 0xfffbc000;
@@ -898,6 +942,11 @@
return ret;
}
}
+
+ if (kvm_check_extension(s, KVM_CAP_X86_SMM)) {
+ smram_machine_done.notify = register_smram_listener;
+ qemu_add_machine_init_done_notifier(&smram_machine_done);
+ }
return 0;
}
@@ -1245,6 +1294,9 @@
kvm_msr_entry_set(&msrs[n++], MSR_IA32_MISC_ENABLE,
env->msr_ia32_misc_enable);
}
+ if (has_msr_smbase) {
+ kvm_msr_entry_set(&msrs[n++], MSR_IA32_SMBASE, env->smbase);
+ }
if (has_msr_bndcfgs) {
kvm_msr_entry_set(&msrs[n++], MSR_IA32_BNDCFGS, env->msr_bndcfgs);
}
@@ -1606,6 +1658,9 @@
if (has_msr_misc_enable) {
msrs[n++].index = MSR_IA32_MISC_ENABLE;
}
+ if (has_msr_smbase) {
+ msrs[n++].index = MSR_IA32_SMBASE;
+ }
if (has_msr_feature_control) {
msrs[n++].index = MSR_IA32_FEATURE_CONTROL;
}
@@ -1760,6 +1815,9 @@
case MSR_IA32_MISC_ENABLE:
env->msr_ia32_misc_enable = msrs[i].data;
break;
+ case MSR_IA32_SMBASE:
+ env->smbase = msrs[i].data;
+ break;
case MSR_IA32_FEATURE_CONTROL:
env->msr_ia32_feature_control = msrs[i].data;
break;
@@ -1923,6 +1981,7 @@
static int kvm_put_vcpu_events(X86CPU *cpu, int level)
{
+ CPUState *cs = CPU(cpu);
CPUX86State *env = &cpu->env;
struct kvm_vcpu_events events = {};
@@ -1947,6 +2006,24 @@
events.sipi_vector = env->sipi_vector;
+ if (has_msr_smbase) {
+ events.smi.smm = !!(env->hflags & HF_SMM_MASK);
+ events.smi.smm_inside_nmi = !!(env->hflags2 & HF2_SMM_INSIDE_NMI_MASK);
+ if (kvm_irqchip_in_kernel()) {
+ /* As soon as these are moved to the kernel, remove them
+ * from cs->interrupt_request.
+ */
+ events.smi.pending = cs->interrupt_request & CPU_INTERRUPT_SMI;
+ events.smi.latched_init = cs->interrupt_request & CPU_INTERRUPT_INIT;
+ cs->interrupt_request &= ~(CPU_INTERRUPT_INIT | CPU_INTERRUPT_SMI);
+ } else {
+ /* Keep these in cs->interrupt_request. */
+ events.smi.pending = 0;
+ events.smi.latched_init = 0;
+ }
+ events.flags |= KVM_VCPUEVENT_VALID_SMM;
+ }
+
events.flags = 0;
if (level >= KVM_PUT_RESET_STATE) {
events.flags |=
@@ -1966,6 +2043,7 @@
return 0;
}
+ memset(&events, 0, sizeof(events));
ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_VCPU_EVENTS, &events);
if (ret < 0) {
return ret;
@@ -1987,6 +2065,29 @@
env->hflags2 &= ~HF2_NMI_MASK;
}
+ if (events.flags & KVM_VCPUEVENT_VALID_SMM) {
+ if (events.smi.smm) {
+ env->hflags |= HF_SMM_MASK;
+ } else {
+ env->hflags &= ~HF_SMM_MASK;
+ }
+ if (events.smi.pending) {
+ cpu_interrupt(CPU(cpu), CPU_INTERRUPT_SMI);
+ } else {
+ cpu_reset_interrupt(CPU(cpu), CPU_INTERRUPT_SMI);
+ }
+ if (events.smi.smm_inside_nmi) {
+ env->hflags2 |= HF2_SMM_INSIDE_NMI_MASK;
+ } else {
+ env->hflags2 &= ~HF2_SMM_INSIDE_NMI_MASK;
+ }
+ if (events.smi.latched_init) {
+ cpu_interrupt(CPU(cpu), CPU_INTERRUPT_INIT);
+ } else {
+ cpu_reset_interrupt(CPU(cpu), CPU_INTERRUPT_INIT);
+ }
+ }
+
env->sipi_vector = events.sipi_vector;
return 0;
@@ -2190,16 +2291,28 @@
int ret;
/* Inject NMI */
- if (cpu->interrupt_request & CPU_INTERRUPT_NMI) {
- qemu_mutex_lock_iothread();
- cpu->interrupt_request &= ~CPU_INTERRUPT_NMI;
- qemu_mutex_unlock_iothread();
-
- DPRINTF("injected NMI\n");
- ret = kvm_vcpu_ioctl(cpu, KVM_NMI);
- if (ret < 0) {
- fprintf(stderr, "KVM: injection failed, NMI lost (%s)\n",
- strerror(-ret));
+ if (cpu->interrupt_request & (CPU_INTERRUPT_NMI | CPU_INTERRUPT_SMI)) {
+ if (cpu->interrupt_request & CPU_INTERRUPT_NMI) {
+ qemu_mutex_lock_iothread();
+ cpu->interrupt_request &= ~CPU_INTERRUPT_NMI;
+ qemu_mutex_unlock_iothread();
+ DPRINTF("injected NMI\n");
+ ret = kvm_vcpu_ioctl(cpu, KVM_NMI);
+ if (ret < 0) {
+ fprintf(stderr, "KVM: injection failed, NMI lost (%s)\n",
+ strerror(-ret));
+ }
+ }
+ if (cpu->interrupt_request & CPU_INTERRUPT_SMI) {
+ qemu_mutex_lock_iothread();
+ cpu->interrupt_request &= ~CPU_INTERRUPT_SMI;
+ qemu_mutex_unlock_iothread();
+ DPRINTF("injected SMI\n");
+ ret = kvm_vcpu_ioctl(cpu, KVM_SMI);
+ if (ret < 0) {
+ fprintf(stderr, "KVM: injection failed, SMI lost (%s)\n",
+ strerror(-ret));
+ }
}
}
@@ -2212,7 +2325,13 @@
* pending TPR access reports.
*/
if (cpu->interrupt_request & (CPU_INTERRUPT_INIT | CPU_INTERRUPT_TPR)) {
- cpu->exit_request = 1;
+ if ((cpu->interrupt_request & CPU_INTERRUPT_INIT) &&
+ !(env->hflags & HF_SMM_MASK)) {
+ cpu->exit_request = 1;
+ }
+ if (cpu->interrupt_request & CPU_INTERRUPT_TPR) {
+ cpu->exit_request = 1;
+ }
}
if (!kvm_irqchip_in_kernel()) {
@@ -2260,6 +2379,11 @@
X86CPU *x86_cpu = X86_CPU(cpu);
CPUX86State *env = &x86_cpu->env;
+ if (run->flags & KVM_RUN_X86_SMM) {
+ env->hflags |= HF_SMM_MASK;
+ } else {
+ env->hflags &= HF_SMM_MASK;
+ }
if (run->if_flag) {
env->eflags |= IF_MASK;
} else {
@@ -2307,7 +2431,8 @@
}
}
- if (cs->interrupt_request & CPU_INTERRUPT_INIT) {
+ if ((cs->interrupt_request & CPU_INTERRUPT_INIT) &&
+ !(env->hflags & HF_SMM_MASK)) {
kvm_cpu_synchronize_state(cs);
do_cpu_init(cpu);
}
diff --git a/target-i386/kvm_i386.h b/target-i386/kvm_i386.h
index cac30fd..e557e94 100644
--- a/target-i386/kvm_i386.h
+++ b/target-i386/kvm_i386.h
@@ -14,6 +14,7 @@
#include "sysemu/kvm.h"
bool kvm_allows_irq0_override(void);
+bool kvm_has_smm(void);
void kvm_arch_reset_vcpu(X86CPU *cs);
void kvm_arch_do_init_vcpu(X86CPU *cs);
