summaryrefslogtreecommitdiffstats
path: root/kernel/Documentation/virtual/kvm/api.txt
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/Documentation/virtual/kvm/api.txt')
-rw-r--r--kernel/Documentation/virtual/kvm/api.txt145
1 files changed, 120 insertions, 25 deletions
diff --git a/kernel/Documentation/virtual/kvm/api.txt b/kernel/Documentation/virtual/kvm/api.txt
index 9fa2bf8c3..092ee9fba 100644
--- a/kernel/Documentation/virtual/kvm/api.txt
+++ b/kernel/Documentation/virtual/kvm/api.txt
@@ -254,6 +254,11 @@ since the last call to this ioctl. Bit 0 is the first page in the
memory slot. Ensure the entire structure is cleared to avoid padding
issues.
+If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies
+the address space for which you want to return the dirty bitmap.
+They must be less than the value that KVM_CHECK_EXTENSION returns for
+the KVM_CAP_MULTI_ADDRESS_SPACE capability.
+
4.9 KVM_SET_MEMORY_ALIAS
@@ -396,10 +401,9 @@ Capability: basic
Architectures: x86, ppc, mips
Type: vcpu ioctl
Parameters: struct kvm_interrupt (in)
-Returns: 0 on success, -1 on error
+Returns: 0 on success, negative on failure.
-Queues a hardware interrupt vector to be injected. This is only
-useful if in-kernel local APIC or equivalent is not used.
+Queues a hardware interrupt vector to be injected.
/* for KVM_INTERRUPT */
struct kvm_interrupt {
@@ -409,7 +413,14 @@ struct kvm_interrupt {
X86:
-Note 'irq' is an interrupt vector, not an interrupt pin or line.
+Returns: 0 on success,
+ -EEXIST if an interrupt is already enqueued
+ -EINVAL the the irq number is invalid
+ -ENXIO if the PIC is in the kernel
+ -EFAULT if the pointer is invalid
+
+Note 'irq' is an interrupt vector, not an interrupt pin or line. This
+ioctl is useful if the in-kernel PIC is not used.
PPC:
@@ -820,11 +831,21 @@ struct kvm_vcpu_events {
} nmi;
__u32 sipi_vector;
__u32 flags;
+ struct {
+ __u8 smm;
+ __u8 pending;
+ __u8 smm_inside_nmi;
+ __u8 latched_init;
+ } smi;
};
-KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
-interrupt.shadow contains a valid state. Otherwise, this field is undefined.
+Only two fields are defined in the flags field:
+- KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
+ interrupt.shadow contains a valid state.
+
+- KVM_VCPUEVENT_VALID_SMM may be set in the flags field to signal that
+ smi contains a valid state.
4.32 KVM_SET_VCPU_EVENTS
@@ -841,17 +862,20 @@ vcpu.
See KVM_GET_VCPU_EVENTS for the data structure.
Fields that may be modified asynchronously by running VCPUs can be excluded
-from the update. These fields are nmi.pending and sipi_vector. Keep the
-corresponding bits in the flags field cleared to suppress overwriting the
-current in-kernel state. The bits are:
+from the update. These fields are nmi.pending, sipi_vector, smi.smm,
+smi.pending. Keep the corresponding bits in the flags field cleared to
+suppress overwriting the current in-kernel state. The bits are:
KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
+KVM_VCPUEVENT_VALID_SMM - transfer the smi sub-struct.
If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
the flags field to signal that interrupt.shadow contains a valid state and
shall be written into the VCPU.
+KVM_VCPUEVENT_VALID_SMM can only be set if KVM_CAP_X86_SMM is available.
+
4.33 KVM_GET_DEBUGREGS
@@ -911,6 +935,13 @@ slot. When changing an existing slot, it may be moved in the guest
physical memory space, or its flags may be modified. It may not be
resized. Slots may not overlap in guest physical address space.
+If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
+specifies the address space which is being modified. They must be
+less than the value that KVM_CHECK_EXTENSION returns for the
+KVM_CAP_MULTI_ADDRESS_SPACE capability. Slots in separate address spaces
+are unrelated; the restriction on overlapping slots only applies within
+each address space.
+
Memory for the region is taken starting at the address denoted by the
field userspace_addr, which must point at user addressable memory for
the entire memory slot size. Any object may back this memory, including
@@ -959,7 +990,8 @@ documentation when it pops into existence).
4.37 KVM_ENABLE_CAP
Capability: KVM_CAP_ENABLE_CAP, KVM_CAP_ENABLE_CAP_VM
-Architectures: ppc, s390
+Architectures: x86 (only KVM_CAP_ENABLE_CAP_VM),
+ mips (only KVM_CAP_ENABLE_CAP), ppc, s390
Type: vcpu ioctl, vm ioctl (with KVM_CAP_ENABLE_CAP_VM)
Parameters: struct kvm_enable_cap (in)
Returns: 0 on success; -1 on error
@@ -1268,7 +1300,7 @@ The flags bitmap is defined as:
/* the host supports the ePAPR idle hcall
#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
-4.48 KVM_ASSIGN_PCI_DEVICE
+4.48 KVM_ASSIGN_PCI_DEVICE (deprecated)
Capability: none
Architectures: x86
@@ -1318,7 +1350,7 @@ Errors:
have their standard meanings.
-4.49 KVM_DEASSIGN_PCI_DEVICE
+4.49 KVM_DEASSIGN_PCI_DEVICE (deprecated)
Capability: none
Architectures: x86
@@ -1337,7 +1369,7 @@ Errors:
Other error conditions may be defined by individual device types or
have their standard meanings.
-4.50 KVM_ASSIGN_DEV_IRQ
+4.50 KVM_ASSIGN_DEV_IRQ (deprecated)
Capability: KVM_CAP_ASSIGN_DEV_IRQ
Architectures: x86
@@ -1377,7 +1409,7 @@ Errors:
have their standard meanings.
-4.51 KVM_DEASSIGN_DEV_IRQ
+4.51 KVM_DEASSIGN_DEV_IRQ (deprecated)
Capability: KVM_CAP_ASSIGN_DEV_IRQ
Architectures: x86
@@ -1451,7 +1483,7 @@ struct kvm_irq_routing_s390_adapter {
};
-4.53 KVM_ASSIGN_SET_MSIX_NR
+4.53 KVM_ASSIGN_SET_MSIX_NR (deprecated)
Capability: none
Architectures: x86
@@ -1473,7 +1505,7 @@ struct kvm_assigned_msix_nr {
#define KVM_MAX_MSIX_PER_DEV 256
-4.54 KVM_ASSIGN_SET_MSIX_ENTRY
+4.54 KVM_ASSIGN_SET_MSIX_ENTRY (deprecated)
Capability: none
Architectures: x86
@@ -1572,7 +1604,7 @@ provided event instead of triggering an exit.
struct kvm_ioeventfd {
__u64 datamatch;
__u64 addr; /* legal pio/mmio address */
- __u32 len; /* 1, 2, 4, or 8 bytes */
+ __u32 len; /* 0, 1, 2, 4, or 8 bytes */
__s32 fd;
__u32 flags;
__u8 pad[36];
@@ -1595,6 +1627,10 @@ to the registered address is equal to datamatch in struct kvm_ioeventfd.
For virtio-ccw devices, addr contains the subchannel id and datamatch the
virtqueue index.
+With KVM_CAP_IOEVENTFD_ANY_LENGTH, a zero length ioeventfd is allowed, and
+the kernel will ignore the length of guest write and may get a faster vmexit.
+The speedup may only apply to specific architectures, but the ioeventfd will
+work anyway.
4.60 KVM_DIRTY_TLB
@@ -1629,7 +1665,7 @@ should skip processing the bitmap and just invalidate everything. It must
be set to the number of set bits in the bitmap.
-4.61 KVM_ASSIGN_SET_INTX_MASK
+4.61 KVM_ASSIGN_SET_INTX_MASK (deprecated)
Capability: KVM_CAP_PCI_2_3
Architectures: x86
@@ -1748,7 +1784,7 @@ has been called, this interface is completely emulated within the kernel.
To use this to emulate the LINT1 input with KVM_CREATE_IRQCHIP, use the
following algorithm:
- - pause the vpcu
+ - pause the vcpu
- read the local APIC's state (KVM_GET_LAPIC)
- check whether changing LINT1 will queue an NMI (see the LVT entry for LINT1)
- if so, issue KVM_NMI
@@ -2645,7 +2681,7 @@ handled.
4.87 KVM_SET_GUEST_DEBUG
Capability: KVM_CAP_SET_GUEST_DEBUG
-Architectures: x86, s390, ppc
+Architectures: x86, s390, ppc, arm64
Type: vcpu ioctl
Parameters: struct kvm_guest_debug (in)
Returns: 0 on success; -1 on error
@@ -2667,8 +2703,8 @@ when running. Common control bits are:
The top 16 bits of the control field are architecture specific control
flags which can include the following:
- - KVM_GUESTDBG_USE_SW_BP: using software breakpoints [x86]
- - KVM_GUESTDBG_USE_HW_BP: using hardware breakpoints [x86, s390]
+ - KVM_GUESTDBG_USE_SW_BP: using software breakpoints [x86, arm64]
+ - KVM_GUESTDBG_USE_HW_BP: using hardware breakpoints [x86, s390, arm64]
- KVM_GUESTDBG_INJECT_DB: inject DB type exception [x86]
- KVM_GUESTDBG_INJECT_BP: inject BP type exception [x86]
- KVM_GUESTDBG_EXIT_PENDING: trigger an immediate guest exit [s390]
@@ -2683,6 +2719,11 @@ updated to the correct (supplied) values.
The second part of the structure is architecture specific and
typically contains a set of debug registers.
+For arm64 the number of debug registers is implementation defined and
+can be determined by querying the KVM_CAP_GUEST_DEBUG_HW_BPS and
+KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which return a positive number
+indicating the number of supported registers.
+
When debug events exit the main run loop with the reason
KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run
structure containing architecture specific debug information.
@@ -2767,7 +2808,7 @@ Returns: = 0 on success,
< 0 on generic error (e.g. -EFAULT or -ENOMEM),
> 0 if an exception occurred while walking the page tables
-Read or write data from/to the logical (virtual) memory of a VPCU.
+Read or write data from/to the logical (virtual) memory of a VCPU.
Parameters are specified via the following structure:
@@ -2978,6 +3019,16 @@ len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0
and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq),
which is the maximum number of possibly pending cpu-local interrupts.
+4.90 KVM_SMI
+
+Capability: KVM_CAP_X86_SMM
+Architectures: x86
+Type: vcpu ioctl
+Parameters: none
+Returns: 0 on success, -1 on error
+
+Queues an SMI on the thread's vcpu.
+
5. The kvm_run structure
------------------------
@@ -3013,7 +3064,12 @@ an interrupt can be injected now with KVM_INTERRUPT.
The value of the current interrupt flag. Only valid if in-kernel
local APIC is not used.
- __u8 padding2[2];
+ __u16 flags;
+
+More architecture-specific flags detailing state of the VCPU that may
+affect the device's behavior. The only currently defined flag is
+KVM_RUN_X86_SMM, which is valid on x86 machines and is set if the
+VCPU is in system management mode.
/* in (pre_kvm_run), out (post_kvm_run) */
__u64 cr8;
@@ -3070,11 +3126,13 @@ data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
where kvm expects application code to place the data for the next
KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a packed array.
+ /* KVM_EXIT_DEBUG */
struct {
struct kvm_debug_exit_arch arch;
} debug;
-Unused.
+If the exit_reason is KVM_EXIT_DEBUG, then a vcpu is processing a debug event
+for which architecture specific information is returned.
/* KVM_EXIT_MMIO */
struct {
@@ -3236,6 +3294,7 @@ should put the acknowledged interrupt vector into the 'epr' field.
struct {
#define KVM_SYSTEM_EVENT_SHUTDOWN 1
#define KVM_SYSTEM_EVENT_RESET 2
+#define KVM_SYSTEM_EVENT_CRASH 3
__u32 type;
__u64 flags;
} system_event;
@@ -3255,6 +3314,22 @@ Valid values for 'type' are:
KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM.
As with SHUTDOWN, userspace can choose to ignore the request, or
to schedule the reset to occur in the future and may call KVM_RUN again.
+ KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest
+ has requested a crash condition maintenance. Userspace can choose
+ to ignore the request, or to gather VM memory core dump and/or
+ reset/shutdown of the VM.
+
+ /* KVM_EXIT_IOAPIC_EOI */
+ struct {
+ __u8 vector;
+ } eoi;
+
+Indicates that the VCPU's in-kernel local APIC received an EOI for a
+level-triggered IOAPIC interrupt. This exit only triggers when the
+IOAPIC is implemented in userspace (i.e. KVM_CAP_SPLIT_IRQCHIP is enabled);
+the userspace IOAPIC should process the EOI and retrigger the interrupt if
+it is still asserted. Vector is the LAPIC interrupt vector for which the
+EOI was received.
/* Fix the size of the union. */
char padding[256];
@@ -3574,6 +3649,26 @@ struct {
KVM handlers should exit to userspace with rc = -EREMOTE.
+7.5 KVM_CAP_SPLIT_IRQCHIP
+
+Architectures: x86
+Parameters: args[0] - number of routes reserved for userspace IOAPICs
+Returns: 0 on success, -1 on error
+
+Create a local apic for each processor in the kernel. This can be used
+instead of KVM_CREATE_IRQCHIP if the userspace VMM wishes to emulate the
+IOAPIC and PIC (and also the PIT, even though this has to be enabled
+separately).
+
+This capability also enables in kernel routing of interrupt requests;
+when KVM_CAP_SPLIT_IRQCHIP only routes of KVM_IRQ_ROUTING_MSI type are
+used in the IRQ routing table. The first args[0] MSI routes are reserved
+for the IOAPIC pins. Whenever the LAPIC receives an EOI for these routes,
+a KVM_EXIT_IOAPIC_EOI vmexit will be reported to userspace.
+
+Fails if VCPU has already been created, or if the irqchip is already in the
+kernel (i.e. KVM_CREATE_IRQCHIP has already been called).
+
8. Other capabilities.
----------------------