About Kernel Documentation Linux Kernel Contact Linux Resources Linux Blog

Documentation / virtual / kvm / api.txt




Custom Search

Based on kernel version 3.16. Page generated on 2014-08-06 21:41 EST.

1	The Definitive KVM (Kernel-based Virtual Machine) API Documentation
2	===================================================================
3	
4	1. General description
5	----------------------
6	
7	The kvm API is a set of ioctls that are issued to control various aspects
8	of a virtual machine.  The ioctls belong to three classes
9	
10	 - System ioctls: These query and set global attributes which affect the
11	   whole kvm subsystem.  In addition a system ioctl is used to create
12	   virtual machines
13	
14	 - VM ioctls: These query and set attributes that affect an entire virtual
15	   machine, for example memory layout.  In addition a VM ioctl is used to
16	   create virtual cpus (vcpus).
17	
18	   Only run VM ioctls from the same process (address space) that was used
19	   to create the VM.
20	
21	 - vcpu ioctls: These query and set attributes that control the operation
22	   of a single virtual cpu.
23	
24	   Only run vcpu ioctls from the same thread that was used to create the
25	   vcpu.
26	
27	
28	2. File descriptors
29	-------------------
30	
31	The kvm API is centered around file descriptors.  An initial
32	open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
33	can be used to issue system ioctls.  A KVM_CREATE_VM ioctl on this
34	handle will create a VM file descriptor which can be used to issue VM
35	ioctls.  A KVM_CREATE_VCPU ioctl on a VM fd will create a virtual cpu
36	and return a file descriptor pointing to it.  Finally, ioctls on a vcpu
37	fd can be used to control the vcpu, including the important task of
38	actually running guest code.
39	
40	In general file descriptors can be migrated among processes by means
41	of fork() and the SCM_RIGHTS facility of unix domain socket.  These
42	kinds of tricks are explicitly not supported by kvm.  While they will
43	not cause harm to the host, their actual behavior is not guaranteed by
44	the API.  The only supported use is one virtual machine per process,
45	and one vcpu per thread.
46	
47	
48	3. Extensions
49	-------------
50	
51	As of Linux 2.6.22, the KVM ABI has been stabilized: no backward
52	incompatible change are allowed.  However, there is an extension
53	facility that allows backward-compatible extensions to the API to be
54	queried and used.
55	
56	The extension mechanism is not based on the Linux version number.
57	Instead, kvm defines extension identifiers and a facility to query
58	whether a particular extension identifier is available.  If it is, a
59	set of ioctls is available for application use.
60	
61	
62	4. API description
63	------------------
64	
65	This section describes ioctls that can be used to control kvm guests.
66	For each ioctl, the following information is provided along with a
67	description:
68	
69	  Capability: which KVM extension provides this ioctl.  Can be 'basic',
70	      which means that is will be provided by any kernel that supports
71	      API version 12 (see section 4.1), or a KVM_CAP_xyz constant, which
72	      means availability needs to be checked with KVM_CHECK_EXTENSION
73	      (see section 4.4).
74	
75	  Architectures: which instruction set architectures provide this ioctl.
76	      x86 includes both i386 and x86_64.
77	
78	  Type: system, vm, or vcpu.
79	
80	  Parameters: what parameters are accepted by the ioctl.
81	
82	  Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
83	      are not detailed, but errors with specific meanings are.
84	
85	
86	4.1 KVM_GET_API_VERSION
87	
88	Capability: basic
89	Architectures: all
90	Type: system ioctl
91	Parameters: none
92	Returns: the constant KVM_API_VERSION (=12)
93	
94	This identifies the API version as the stable kvm API. It is not
95	expected that this number will change.  However, Linux 2.6.20 and
96	2.6.21 report earlier versions; these are not documented and not
97	supported.  Applications should refuse to run if KVM_GET_API_VERSION
98	returns a value other than 12.  If this check passes, all ioctls
99	described as 'basic' will be available.
100	
101	
102	4.2 KVM_CREATE_VM
103	
104	Capability: basic
105	Architectures: all
106	Type: system ioctl
107	Parameters: machine type identifier (KVM_VM_*)
108	Returns: a VM fd that can be used to control the new virtual machine.
109	
110	The new VM has no virtual cpus and no memory.  An mmap() of a VM fd
111	will access the virtual machine's physical address space; offset zero
112	corresponds to guest physical address zero.  Use of mmap() on a VM fd
113	is discouraged if userspace memory allocation (KVM_CAP_USER_MEMORY) is
114	available.
115	You most certainly want to use 0 as machine type.
116	
117	In order to create user controlled virtual machines on S390, check
118	KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
119	privileged user (CAP_SYS_ADMIN).
120	
121	
122	4.3 KVM_GET_MSR_INDEX_LIST
123	
124	Capability: basic
125	Architectures: x86
126	Type: system
127	Parameters: struct kvm_msr_list (in/out)
128	Returns: 0 on success; -1 on error
129	Errors:
130	  E2BIG:     the msr index list is to be to fit in the array specified by
131	             the user.
132	
133	struct kvm_msr_list {
134		__u32 nmsrs; /* number of msrs in entries */
135		__u32 indices[0];
136	};
137	
138	This ioctl returns the guest msrs that are supported.  The list varies
139	by kvm version and host processor, but does not change otherwise.  The
140	user fills in the size of the indices array in nmsrs, and in return
141	kvm adjusts nmsrs to reflect the actual number of msrs and fills in
142	the indices array with their numbers.
143	
144	Note: if kvm indicates supports MCE (KVM_CAP_MCE), then the MCE bank MSRs are
145	not returned in the MSR list, as different vcpus can have a different number
146	of banks, as set via the KVM_X86_SETUP_MCE ioctl.
147	
148	
149	4.4 KVM_CHECK_EXTENSION
150	
151	Capability: basic
152	Architectures: all
153	Type: system ioctl
154	Parameters: extension identifier (KVM_CAP_*)
155	Returns: 0 if unsupported; 1 (or some other positive integer) if supported
156	
157	The API allows the application to query about extensions to the core
158	kvm API.  Userspace passes an extension identifier (an integer) and
159	receives an integer that describes the extension availability.
160	Generally 0 means no and 1 means yes, but some extensions may report
161	additional information in the integer return value.
162	
163	
164	4.5 KVM_GET_VCPU_MMAP_SIZE
165	
166	Capability: basic
167	Architectures: all
168	Type: system ioctl
169	Parameters: none
170	Returns: size of vcpu mmap area, in bytes
171	
172	The KVM_RUN ioctl (cf.) communicates with userspace via a shared
173	memory region.  This ioctl returns the size of that region.  See the
174	KVM_RUN documentation for details.
175	
176	
177	4.6 KVM_SET_MEMORY_REGION
178	
179	Capability: basic
180	Architectures: all
181	Type: vm ioctl
182	Parameters: struct kvm_memory_region (in)
183	Returns: 0 on success, -1 on error
184	
185	This ioctl is obsolete and has been removed.
186	
187	
188	4.7 KVM_CREATE_VCPU
189	
190	Capability: basic
191	Architectures: all
192	Type: vm ioctl
193	Parameters: vcpu id (apic id on x86)
194	Returns: vcpu fd on success, -1 on error
195	
196	This API adds a vcpu to a virtual machine.  The vcpu id is a small integer
197	in the range [0, max_vcpus).
198	
199	The recommended max_vcpus value can be retrieved using the KVM_CAP_NR_VCPUS of
200	the KVM_CHECK_EXTENSION ioctl() at run-time.
201	The maximum possible value for max_vcpus can be retrieved using the
202	KVM_CAP_MAX_VCPUS of the KVM_CHECK_EXTENSION ioctl() at run-time.
203	
204	If the KVM_CAP_NR_VCPUS does not exist, you should assume that max_vcpus is 4
205	cpus max.
206	If the KVM_CAP_MAX_VCPUS does not exist, you should assume that max_vcpus is
207	same as the value returned from KVM_CAP_NR_VCPUS.
208	
209	On powerpc using book3s_hv mode, the vcpus are mapped onto virtual
210	threads in one or more virtual CPU cores.  (This is because the
211	hardware requires all the hardware threads in a CPU core to be in the
212	same partition.)  The KVM_CAP_PPC_SMT capability indicates the number
213	of vcpus per virtual core (vcore).  The vcore id is obtained by
214	dividing the vcpu id by the number of vcpus per vcore.  The vcpus in a
215	given vcore will always be in the same physical core as each other
216	(though that might be a different physical core from time to time).
217	Userspace can control the threading (SMT) mode of the guest by its
218	allocation of vcpu ids.  For example, if userspace wants
219	single-threaded guest vcpus, it should make all vcpu ids be a multiple
220	of the number of vcpus per vcore.
221	
222	For virtual cpus that have been created with S390 user controlled virtual
223	machines, the resulting vcpu fd can be memory mapped at page offset
224	KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of the virtual
225	cpu's hardware control block.
226	
227	
228	4.8 KVM_GET_DIRTY_LOG (vm ioctl)
229	
230	Capability: basic
231	Architectures: x86
232	Type: vm ioctl
233	Parameters: struct kvm_dirty_log (in/out)
234	Returns: 0 on success, -1 on error
235	
236	/* for KVM_GET_DIRTY_LOG */
237	struct kvm_dirty_log {
238		__u32 slot;
239		__u32 padding;
240		union {
241			void __user *dirty_bitmap; /* one bit per page */
242			__u64 padding;
243		};
244	};
245	
246	Given a memory slot, return a bitmap containing any pages dirtied
247	since the last call to this ioctl.  Bit 0 is the first page in the
248	memory slot.  Ensure the entire structure is cleared to avoid padding
249	issues.
250	
251	
252	4.9 KVM_SET_MEMORY_ALIAS
253	
254	Capability: basic
255	Architectures: x86
256	Type: vm ioctl
257	Parameters: struct kvm_memory_alias (in)
258	Returns: 0 (success), -1 (error)
259	
260	This ioctl is obsolete and has been removed.
261	
262	
263	4.10 KVM_RUN
264	
265	Capability: basic
266	Architectures: all
267	Type: vcpu ioctl
268	Parameters: none
269	Returns: 0 on success, -1 on error
270	Errors:
271	  EINTR:     an unmasked signal is pending
272	
273	This ioctl is used to run a guest virtual cpu.  While there are no
274	explicit parameters, there is an implicit parameter block that can be
275	obtained by mmap()ing the vcpu fd at offset 0, with the size given by
276	KVM_GET_VCPU_MMAP_SIZE.  The parameter block is formatted as a 'struct
277	kvm_run' (see below).
278	
279	
280	4.11 KVM_GET_REGS
281	
282	Capability: basic
283	Architectures: all except ARM, arm64
284	Type: vcpu ioctl
285	Parameters: struct kvm_regs (out)
286	Returns: 0 on success, -1 on error
287	
288	Reads the general purpose registers from the vcpu.
289	
290	/* x86 */
291	struct kvm_regs {
292		/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
293		__u64 rax, rbx, rcx, rdx;
294		__u64 rsi, rdi, rsp, rbp;
295		__u64 r8,  r9,  r10, r11;
296		__u64 r12, r13, r14, r15;
297		__u64 rip, rflags;
298	};
299	
300	
301	4.12 KVM_SET_REGS
302	
303	Capability: basic
304	Architectures: all except ARM, arm64
305	Type: vcpu ioctl
306	Parameters: struct kvm_regs (in)
307	Returns: 0 on success, -1 on error
308	
309	Writes the general purpose registers into the vcpu.
310	
311	See KVM_GET_REGS for the data structure.
312	
313	
314	4.13 KVM_GET_SREGS
315	
316	Capability: basic
317	Architectures: x86, ppc
318	Type: vcpu ioctl
319	Parameters: struct kvm_sregs (out)
320	Returns: 0 on success, -1 on error
321	
322	Reads special registers from the vcpu.
323	
324	/* x86 */
325	struct kvm_sregs {
326		struct kvm_segment cs, ds, es, fs, gs, ss;
327		struct kvm_segment tr, ldt;
328		struct kvm_dtable gdt, idt;
329		__u64 cr0, cr2, cr3, cr4, cr8;
330		__u64 efer;
331		__u64 apic_base;
332		__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
333	};
334	
335	/* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */
336	
337	interrupt_bitmap is a bitmap of pending external interrupts.  At most
338	one bit may be set.  This interrupt has been acknowledged by the APIC
339	but not yet injected into the cpu core.
340	
341	
342	4.14 KVM_SET_SREGS
343	
344	Capability: basic
345	Architectures: x86, ppc
346	Type: vcpu ioctl
347	Parameters: struct kvm_sregs (in)
348	Returns: 0 on success, -1 on error
349	
350	Writes special registers into the vcpu.  See KVM_GET_SREGS for the
351	data structures.
352	
353	
354	4.15 KVM_TRANSLATE
355	
356	Capability: basic
357	Architectures: x86
358	Type: vcpu ioctl
359	Parameters: struct kvm_translation (in/out)
360	Returns: 0 on success, -1 on error
361	
362	Translates a virtual address according to the vcpu's current address
363	translation mode.
364	
365	struct kvm_translation {
366		/* in */
367		__u64 linear_address;
368	
369		/* out */
370		__u64 physical_address;
371		__u8  valid;
372		__u8  writeable;
373		__u8  usermode;
374		__u8  pad[5];
375	};
376	
377	
378	4.16 KVM_INTERRUPT
379	
380	Capability: basic
381	Architectures: x86, ppc
382	Type: vcpu ioctl
383	Parameters: struct kvm_interrupt (in)
384	Returns: 0 on success, -1 on error
385	
386	Queues a hardware interrupt vector to be injected.  This is only
387	useful if in-kernel local APIC or equivalent is not used.
388	
389	/* for KVM_INTERRUPT */
390	struct kvm_interrupt {
391		/* in */
392		__u32 irq;
393	};
394	
395	X86:
396	
397	Note 'irq' is an interrupt vector, not an interrupt pin or line.
398	
399	PPC:
400	
401	Queues an external interrupt to be injected. This ioctl is overleaded
402	with 3 different irq values:
403	
404	a) KVM_INTERRUPT_SET
405	
406	  This injects an edge type external interrupt into the guest once it's ready
407	  to receive interrupts. When injected, the interrupt is done.
408	
409	b) KVM_INTERRUPT_UNSET
410	
411	  This unsets any pending interrupt.
412	
413	  Only available with KVM_CAP_PPC_UNSET_IRQ.
414	
415	c) KVM_INTERRUPT_SET_LEVEL
416	
417	  This injects a level type external interrupt into the guest context. The
418	  interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET
419	  is triggered.
420	
421	  Only available with KVM_CAP_PPC_IRQ_LEVEL.
422	
423	Note that any value for 'irq' other than the ones stated above is invalid
424	and incurs unexpected behavior.
425	
426	
427	4.17 KVM_DEBUG_GUEST
428	
429	Capability: basic
430	Architectures: none
431	Type: vcpu ioctl
432	Parameters: none)
433	Returns: -1 on error
434	
435	Support for this has been removed.  Use KVM_SET_GUEST_DEBUG instead.
436	
437	
438	4.18 KVM_GET_MSRS
439	
440	Capability: basic
441	Architectures: x86
442	Type: vcpu ioctl
443	Parameters: struct kvm_msrs (in/out)
444	Returns: 0 on success, -1 on error
445	
446	Reads model-specific registers from the vcpu.  Supported msr indices can
447	be obtained using KVM_GET_MSR_INDEX_LIST.
448	
449	struct kvm_msrs {
450		__u32 nmsrs; /* number of msrs in entries */
451		__u32 pad;
452	
453		struct kvm_msr_entry entries[0];
454	};
455	
456	struct kvm_msr_entry {
457		__u32 index;
458		__u32 reserved;
459		__u64 data;
460	};
461	
462	Application code should set the 'nmsrs' member (which indicates the
463	size of the entries array) and the 'index' member of each array entry.
464	kvm will fill in the 'data' member.
465	
466	
467	4.19 KVM_SET_MSRS
468	
469	Capability: basic
470	Architectures: x86
471	Type: vcpu ioctl
472	Parameters: struct kvm_msrs (in)
473	Returns: 0 on success, -1 on error
474	
475	Writes model-specific registers to the vcpu.  See KVM_GET_MSRS for the
476	data structures.
477	
478	Application code should set the 'nmsrs' member (which indicates the
479	size of the entries array), and the 'index' and 'data' members of each
480	array entry.
481	
482	
483	4.20 KVM_SET_CPUID
484	
485	Capability: basic
486	Architectures: x86
487	Type: vcpu ioctl
488	Parameters: struct kvm_cpuid (in)
489	Returns: 0 on success, -1 on error
490	
491	Defines the vcpu responses to the cpuid instruction.  Applications
492	should use the KVM_SET_CPUID2 ioctl if available.
493	
494	
495	struct kvm_cpuid_entry {
496		__u32 function;
497		__u32 eax;
498		__u32 ebx;
499		__u32 ecx;
500		__u32 edx;
501		__u32 padding;
502	};
503	
504	/* for KVM_SET_CPUID */
505	struct kvm_cpuid {
506		__u32 nent;
507		__u32 padding;
508		struct kvm_cpuid_entry entries[0];
509	};
510	
511	
512	4.21 KVM_SET_SIGNAL_MASK
513	
514	Capability: basic
515	Architectures: x86
516	Type: vcpu ioctl
517	Parameters: struct kvm_signal_mask (in)
518	Returns: 0 on success, -1 on error
519	
520	Defines which signals are blocked during execution of KVM_RUN.  This
521	signal mask temporarily overrides the threads signal mask.  Any
522	unblocked signal received (except SIGKILL and SIGSTOP, which retain
523	their traditional behaviour) will cause KVM_RUN to return with -EINTR.
524	
525	Note the signal will only be delivered if not blocked by the original
526	signal mask.
527	
528	/* for KVM_SET_SIGNAL_MASK */
529	struct kvm_signal_mask {
530		__u32 len;
531		__u8  sigset[0];
532	};
533	
534	
535	4.22 KVM_GET_FPU
536	
537	Capability: basic
538	Architectures: x86
539	Type: vcpu ioctl
540	Parameters: struct kvm_fpu (out)
541	Returns: 0 on success, -1 on error
542	
543	Reads the floating point state from the vcpu.
544	
545	/* for KVM_GET_FPU and KVM_SET_FPU */
546	struct kvm_fpu {
547		__u8  fpr[8][16];
548		__u16 fcw;
549		__u16 fsw;
550		__u8  ftwx;  /* in fxsave format */
551		__u8  pad1;
552		__u16 last_opcode;
553		__u64 last_ip;
554		__u64 last_dp;
555		__u8  xmm[16][16];
556		__u32 mxcsr;
557		__u32 pad2;
558	};
559	
560	
561	4.23 KVM_SET_FPU
562	
563	Capability: basic
564	Architectures: x86
565	Type: vcpu ioctl
566	Parameters: struct kvm_fpu (in)
567	Returns: 0 on success, -1 on error
568	
569	Writes the floating point state to the vcpu.
570	
571	/* for KVM_GET_FPU and KVM_SET_FPU */
572	struct kvm_fpu {
573		__u8  fpr[8][16];
574		__u16 fcw;
575		__u16 fsw;
576		__u8  ftwx;  /* in fxsave format */
577		__u8  pad1;
578		__u16 last_opcode;
579		__u64 last_ip;
580		__u64 last_dp;
581		__u8  xmm[16][16];
582		__u32 mxcsr;
583		__u32 pad2;
584	};
585	
586	
587	4.24 KVM_CREATE_IRQCHIP
588	
589	Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390)
590	Architectures: x86, ia64, ARM, arm64, s390
591	Type: vm ioctl
592	Parameters: none
593	Returns: 0 on success, -1 on error
594	
595	Creates an interrupt controller model in the kernel.  On x86, creates a virtual
596	ioapic, a virtual PIC (two PICs, nested), and sets up future vcpus to have a
597	local APIC.  IRQ routing for GSIs 0-15 is set to both PIC and IOAPIC; GSI 16-23
598	only go to the IOAPIC.  On ia64, a IOSAPIC is created. On ARM/arm64, a GIC is
599	created. On s390, a dummy irq routing table is created.
600	
601	Note that on s390 the KVM_CAP_S390_IRQCHIP vm capability needs to be enabled
602	before KVM_CREATE_IRQCHIP can be used.
603	
604	
605	4.25 KVM_IRQ_LINE
606	
607	Capability: KVM_CAP_IRQCHIP
608	Architectures: x86, ia64, arm, arm64
609	Type: vm ioctl
610	Parameters: struct kvm_irq_level
611	Returns: 0 on success, -1 on error
612	
613	Sets the level of a GSI input to the interrupt controller model in the kernel.
614	On some architectures it is required that an interrupt controller model has
615	been previously created with KVM_CREATE_IRQCHIP.  Note that edge-triggered
616	interrupts require the level to be set to 1 and then back to 0.
617	
618	On real hardware, interrupt pins can be active-low or active-high.  This
619	does not matter for the level field of struct kvm_irq_level: 1 always
620	means active (asserted), 0 means inactive (deasserted).
621	
622	x86 allows the operating system to program the interrupt polarity
623	(active-low/active-high) for level-triggered interrupts, and KVM used
624	to consider the polarity.  However, due to bitrot in the handling of
625	active-low interrupts, the above convention is now valid on x86 too.
626	This is signaled by KVM_CAP_X86_IOAPIC_POLARITY_IGNORED.  Userspace
627	should not present interrupts to the guest as active-low unless this
628	capability is present (or unless it is not using the in-kernel irqchip,
629	of course).
630	
631	
632	ARM/arm64 can signal an interrupt either at the CPU level, or at the
633	in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to
634	use PPIs designated for specific cpus.  The irq field is interpreted
635	like this:
636	
637	  bits:  | 31 ... 24 | 23  ... 16 | 15    ...    0 |
638	  field: | irq_type  | vcpu_index |     irq_id     |
639	
640	The irq_type field has the following values:
641	- irq_type[0]: out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ
642	- irq_type[1]: in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.)
643	               (the vcpu_index field is ignored)
644	- irq_type[2]: in-kernel GIC: PPI, irq_id between 16 and 31 (incl.)
645	
646	(The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs)
647	
648	In both cases, level is used to assert/deassert the line.
649	
650	struct kvm_irq_level {
651		union {
652			__u32 irq;     /* GSI */
653			__s32 status;  /* not used for KVM_IRQ_LEVEL */
654		};
655		__u32 level;           /* 0 or 1 */
656	};
657	
658	
659	4.26 KVM_GET_IRQCHIP
660	
661	Capability: KVM_CAP_IRQCHIP
662	Architectures: x86, ia64
663	Type: vm ioctl
664	Parameters: struct kvm_irqchip (in/out)
665	Returns: 0 on success, -1 on error
666	
667	Reads the state of a kernel interrupt controller created with
668	KVM_CREATE_IRQCHIP into a buffer provided by the caller.
669	
670	struct kvm_irqchip {
671		__u32 chip_id;  /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
672		__u32 pad;
673	        union {
674			char dummy[512];  /* reserving space */
675			struct kvm_pic_state pic;
676			struct kvm_ioapic_state ioapic;
677		} chip;
678	};
679	
680	
681	4.27 KVM_SET_IRQCHIP
682	
683	Capability: KVM_CAP_IRQCHIP
684	Architectures: x86, ia64
685	Type: vm ioctl
686	Parameters: struct kvm_irqchip (in)
687	Returns: 0 on success, -1 on error
688	
689	Sets the state of a kernel interrupt controller created with
690	KVM_CREATE_IRQCHIP from a buffer provided by the caller.
691	
692	struct kvm_irqchip {
693		__u32 chip_id;  /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
694		__u32 pad;
695	        union {
696			char dummy[512];  /* reserving space */
697			struct kvm_pic_state pic;
698			struct kvm_ioapic_state ioapic;
699		} chip;
700	};
701	
702	
703	4.28 KVM_XEN_HVM_CONFIG
704	
705	Capability: KVM_CAP_XEN_HVM
706	Architectures: x86
707	Type: vm ioctl
708	Parameters: struct kvm_xen_hvm_config (in)
709	Returns: 0 on success, -1 on error
710	
711	Sets the MSR that the Xen HVM guest uses to initialize its hypercall
712	page, and provides the starting address and size of the hypercall
713	blobs in userspace.  When the guest writes the MSR, kvm copies one
714	page of a blob (32- or 64-bit, depending on the vcpu mode) to guest
715	memory.
716	
717	struct kvm_xen_hvm_config {
718		__u32 flags;
719		__u32 msr;
720		__u64 blob_addr_32;
721		__u64 blob_addr_64;
722		__u8 blob_size_32;
723		__u8 blob_size_64;
724		__u8 pad2[30];
725	};
726	
727	
728	4.29 KVM_GET_CLOCK
729	
730	Capability: KVM_CAP_ADJUST_CLOCK
731	Architectures: x86
732	Type: vm ioctl
733	Parameters: struct kvm_clock_data (out)
734	Returns: 0 on success, -1 on error
735	
736	Gets the current timestamp of kvmclock as seen by the current guest. In
737	conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios
738	such as migration.
739	
740	struct kvm_clock_data {
741		__u64 clock;  /* kvmclock current value */
742		__u32 flags;
743		__u32 pad[9];
744	};
745	
746	
747	4.30 KVM_SET_CLOCK
748	
749	Capability: KVM_CAP_ADJUST_CLOCK
750	Architectures: x86
751	Type: vm ioctl
752	Parameters: struct kvm_clock_data (in)
753	Returns: 0 on success, -1 on error
754	
755	Sets the current timestamp of kvmclock to the value specified in its parameter.
756	In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
757	such as migration.
758	
759	struct kvm_clock_data {
760		__u64 clock;  /* kvmclock current value */
761		__u32 flags;
762		__u32 pad[9];
763	};
764	
765	
766	4.31 KVM_GET_VCPU_EVENTS
767	
768	Capability: KVM_CAP_VCPU_EVENTS
769	Extended by: KVM_CAP_INTR_SHADOW
770	Architectures: x86
771	Type: vm ioctl
772	Parameters: struct kvm_vcpu_event (out)
773	Returns: 0 on success, -1 on error
774	
775	Gets currently pending exceptions, interrupts, and NMIs as well as related
776	states of the vcpu.
777	
778	struct kvm_vcpu_events {
779		struct {
780			__u8 injected;
781			__u8 nr;
782			__u8 has_error_code;
783			__u8 pad;
784			__u32 error_code;
785		} exception;
786		struct {
787			__u8 injected;
788			__u8 nr;
789			__u8 soft;
790			__u8 shadow;
791		} interrupt;
792		struct {
793			__u8 injected;
794			__u8 pending;
795			__u8 masked;
796			__u8 pad;
797		} nmi;
798		__u32 sipi_vector;
799		__u32 flags;
800	};
801	
802	KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
803	interrupt.shadow contains a valid state. Otherwise, this field is undefined.
804	
805	
806	4.32 KVM_SET_VCPU_EVENTS
807	
808	Capability: KVM_CAP_VCPU_EVENTS
809	Extended by: KVM_CAP_INTR_SHADOW
810	Architectures: x86
811	Type: vm ioctl
812	Parameters: struct kvm_vcpu_event (in)
813	Returns: 0 on success, -1 on error
814	
815	Set pending exceptions, interrupts, and NMIs as well as related states of the
816	vcpu.
817	
818	See KVM_GET_VCPU_EVENTS for the data structure.
819	
820	Fields that may be modified asynchronously by running VCPUs can be excluded
821	from the update. These fields are nmi.pending and sipi_vector. Keep the
822	corresponding bits in the flags field cleared to suppress overwriting the
823	current in-kernel state. The bits are:
824	
825	KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
826	KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
827	
828	If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
829	the flags field to signal that interrupt.shadow contains a valid state and
830	shall be written into the VCPU.
831	
832	
833	4.33 KVM_GET_DEBUGREGS
834	
835	Capability: KVM_CAP_DEBUGREGS
836	Architectures: x86
837	Type: vm ioctl
838	Parameters: struct kvm_debugregs (out)
839	Returns: 0 on success, -1 on error
840	
841	Reads debug registers from the vcpu.
842	
843	struct kvm_debugregs {
844		__u64 db[4];
845		__u64 dr6;
846		__u64 dr7;
847		__u64 flags;
848		__u64 reserved[9];
849	};
850	
851	
852	4.34 KVM_SET_DEBUGREGS
853	
854	Capability: KVM_CAP_DEBUGREGS
855	Architectures: x86
856	Type: vm ioctl
857	Parameters: struct kvm_debugregs (in)
858	Returns: 0 on success, -1 on error
859	
860	Writes debug registers into the vcpu.
861	
862	See KVM_GET_DEBUGREGS for the data structure. The flags field is unused
863	yet and must be cleared on entry.
864	
865	
866	4.35 KVM_SET_USER_MEMORY_REGION
867	
868	Capability: KVM_CAP_USER_MEM
869	Architectures: all
870	Type: vm ioctl
871	Parameters: struct kvm_userspace_memory_region (in)
872	Returns: 0 on success, -1 on error
873	
874	struct kvm_userspace_memory_region {
875		__u32 slot;
876		__u32 flags;
877		__u64 guest_phys_addr;
878		__u64 memory_size; /* bytes */
879		__u64 userspace_addr; /* start of the userspace allocated memory */
880	};
881	
882	/* for kvm_memory_region::flags */
883	#define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
884	#define KVM_MEM_READONLY	(1UL << 1)
885	
886	This ioctl allows the user to create or modify a guest physical memory
887	slot.  When changing an existing slot, it may be moved in the guest
888	physical memory space, or its flags may be modified.  It may not be
889	resized.  Slots may not overlap in guest physical address space.
890	
891	Memory for the region is taken starting at the address denoted by the
892	field userspace_addr, which must point at user addressable memory for
893	the entire memory slot size.  Any object may back this memory, including
894	anonymous memory, ordinary files, and hugetlbfs.
895	
896	It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
897	be identical.  This allows large pages in the guest to be backed by large
898	pages in the host.
899	
900	The flags field supports two flags: KVM_MEM_LOG_DIRTY_PAGES and
901	KVM_MEM_READONLY.  The former can be set to instruct KVM to keep track of
902	writes to memory within the slot.  See KVM_GET_DIRTY_LOG ioctl to know how to
903	use it.  The latter can be set, if KVM_CAP_READONLY_MEM capability allows it,
904	to make a new slot read-only.  In this case, writes to this memory will be
905	posted to userspace as KVM_EXIT_MMIO exits.
906	
907	When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
908	the memory region are automatically reflected into the guest.  For example, an
909	mmap() that affects the region will be made visible immediately.  Another
910	example is madvise(MADV_DROP).
911	
912	It is recommended to use this API instead of the KVM_SET_MEMORY_REGION ioctl.
913	The KVM_SET_MEMORY_REGION does not allow fine grained control over memory
914	allocation and is deprecated.
915	
916	
917	4.36 KVM_SET_TSS_ADDR
918	
919	Capability: KVM_CAP_SET_TSS_ADDR
920	Architectures: x86
921	Type: vm ioctl
922	Parameters: unsigned long tss_address (in)
923	Returns: 0 on success, -1 on error
924	
925	This ioctl defines the physical address of a three-page region in the guest
926	physical address space.  The region must be within the first 4GB of the
927	guest physical address space and must not conflict with any memory slot
928	or any mmio address.  The guest may malfunction if it accesses this memory
929	region.
930	
931	This ioctl is required on Intel-based hosts.  This is needed on Intel hardware
932	because of a quirk in the virtualization implementation (see the internals
933	documentation when it pops into existence).
934	
935	
936	4.37 KVM_ENABLE_CAP
937	
938	Capability: KVM_CAP_ENABLE_CAP, KVM_CAP_ENABLE_CAP_VM
939	Architectures: ppc, s390
940	Type: vcpu ioctl, vm ioctl (with KVM_CAP_ENABLE_CAP_VM)
941	Parameters: struct kvm_enable_cap (in)
942	Returns: 0 on success; -1 on error
943	
944	+Not all extensions are enabled by default. Using this ioctl the application
945	can enable an extension, making it available to the guest.
946	
947	On systems that do not support this ioctl, it always fails. On systems that
948	do support it, it only works for extensions that are supported for enablement.
949	
950	To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should
951	be used.
952	
953	struct kvm_enable_cap {
954	       /* in */
955	       __u32 cap;
956	
957	The capability that is supposed to get enabled.
958	
959	       __u32 flags;
960	
961	A bitfield indicating future enhancements. Has to be 0 for now.
962	
963	       __u64 args[4];
964	
965	Arguments for enabling a feature. If a feature needs initial values to
966	function properly, this is the place to put them.
967	
968	       __u8  pad[64];
969	};
970	
971	The vcpu ioctl should be used for vcpu-specific capabilities, the vm ioctl
972	for vm-wide capabilities.
973	
974	4.38 KVM_GET_MP_STATE
975	
976	Capability: KVM_CAP_MP_STATE
977	Architectures: x86, ia64
978	Type: vcpu ioctl
979	Parameters: struct kvm_mp_state (out)
980	Returns: 0 on success; -1 on error
981	
982	struct kvm_mp_state {
983		__u32 mp_state;
984	};
985	
986	Returns the vcpu's current "multiprocessing state" (though also valid on
987	uniprocessor guests).
988	
989	Possible values are:
990	
991	 - KVM_MP_STATE_RUNNABLE:        the vcpu is currently running
992	 - KVM_MP_STATE_UNINITIALIZED:   the vcpu is an application processor (AP)
993	                                 which has not yet received an INIT signal
994	 - KVM_MP_STATE_INIT_RECEIVED:   the vcpu has received an INIT signal, and is
995	                                 now ready for a SIPI
996	 - KVM_MP_STATE_HALTED:          the vcpu has executed a HLT instruction and
997	                                 is waiting for an interrupt
998	 - KVM_MP_STATE_SIPI_RECEIVED:   the vcpu has just received a SIPI (vector
999	                                 accessible via KVM_GET_VCPU_EVENTS)
1000	
1001	This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
1002	irqchip, the multiprocessing state must be maintained by userspace.
1003	
1004	
1005	4.39 KVM_SET_MP_STATE
1006	
1007	Capability: KVM_CAP_MP_STATE
1008	Architectures: x86, ia64
1009	Type: vcpu ioctl
1010	Parameters: struct kvm_mp_state (in)
1011	Returns: 0 on success; -1 on error
1012	
1013	Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
1014	arguments.
1015	
1016	This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
1017	irqchip, the multiprocessing state must be maintained by userspace.
1018	
1019	
1020	4.40 KVM_SET_IDENTITY_MAP_ADDR
1021	
1022	Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR
1023	Architectures: x86
1024	Type: vm ioctl
1025	Parameters: unsigned long identity (in)
1026	Returns: 0 on success, -1 on error
1027	
1028	This ioctl defines the physical address of a one-page region in the guest
1029	physical address space.  The region must be within the first 4GB of the
1030	guest physical address space and must not conflict with any memory slot
1031	or any mmio address.  The guest may malfunction if it accesses this memory
1032	region.
1033	
1034	This ioctl is required on Intel-based hosts.  This is needed on Intel hardware
1035	because of a quirk in the virtualization implementation (see the internals
1036	documentation when it pops into existence).
1037	
1038	
1039	4.41 KVM_SET_BOOT_CPU_ID
1040	
1041	Capability: KVM_CAP_SET_BOOT_CPU_ID
1042	Architectures: x86, ia64
1043	Type: vm ioctl
1044	Parameters: unsigned long vcpu_id
1045	Returns: 0 on success, -1 on error
1046	
1047	Define which vcpu is the Bootstrap Processor (BSP).  Values are the same
1048	as the vcpu id in KVM_CREATE_VCPU.  If this ioctl is not called, the default
1049	is vcpu 0.
1050	
1051	
1052	4.42 KVM_GET_XSAVE
1053	
1054	Capability: KVM_CAP_XSAVE
1055	Architectures: x86
1056	Type: vcpu ioctl
1057	Parameters: struct kvm_xsave (out)
1058	Returns: 0 on success, -1 on error
1059	
1060	struct kvm_xsave {
1061		__u32 region[1024];
1062	};
1063	
1064	This ioctl would copy current vcpu's xsave struct to the userspace.
1065	
1066	
1067	4.43 KVM_SET_XSAVE
1068	
1069	Capability: KVM_CAP_XSAVE
1070	Architectures: x86
1071	Type: vcpu ioctl
1072	Parameters: struct kvm_xsave (in)
1073	Returns: 0 on success, -1 on error
1074	
1075	struct kvm_xsave {
1076		__u32 region[1024];
1077	};
1078	
1079	This ioctl would copy userspace's xsave struct to the kernel.
1080	
1081	
1082	4.44 KVM_GET_XCRS
1083	
1084	Capability: KVM_CAP_XCRS
1085	Architectures: x86
1086	Type: vcpu ioctl
1087	Parameters: struct kvm_xcrs (out)
1088	Returns: 0 on success, -1 on error
1089	
1090	struct kvm_xcr {
1091		__u32 xcr;
1092		__u32 reserved;
1093		__u64 value;
1094	};
1095	
1096	struct kvm_xcrs {
1097		__u32 nr_xcrs;
1098		__u32 flags;
1099		struct kvm_xcr xcrs[KVM_MAX_XCRS];
1100		__u64 padding[16];
1101	};
1102	
1103	This ioctl would copy current vcpu's xcrs to the userspace.
1104	
1105	
1106	4.45 KVM_SET_XCRS
1107	
1108	Capability: KVM_CAP_XCRS
1109	Architectures: x86
1110	Type: vcpu ioctl
1111	Parameters: struct kvm_xcrs (in)
1112	Returns: 0 on success, -1 on error
1113	
1114	struct kvm_xcr {
1115		__u32 xcr;
1116		__u32 reserved;
1117		__u64 value;
1118	};
1119	
1120	struct kvm_xcrs {
1121		__u32 nr_xcrs;
1122		__u32 flags;
1123		struct kvm_xcr xcrs[KVM_MAX_XCRS];
1124		__u64 padding[16];
1125	};
1126	
1127	This ioctl would set vcpu's xcr to the value userspace specified.
1128	
1129	
1130	4.46 KVM_GET_SUPPORTED_CPUID
1131	
1132	Capability: KVM_CAP_EXT_CPUID
1133	Architectures: x86
1134	Type: system ioctl
1135	Parameters: struct kvm_cpuid2 (in/out)
1136	Returns: 0 on success, -1 on error
1137	
1138	struct kvm_cpuid2 {
1139		__u32 nent;
1140		__u32 padding;
1141		struct kvm_cpuid_entry2 entries[0];
1142	};
1143	
1144	#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
1145	#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
1146	#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
1147	
1148	struct kvm_cpuid_entry2 {
1149		__u32 function;
1150		__u32 index;
1151		__u32 flags;
1152		__u32 eax;
1153		__u32 ebx;
1154		__u32 ecx;
1155		__u32 edx;
1156		__u32 padding[3];
1157	};
1158	
1159	This ioctl returns x86 cpuid features which are supported by both the hardware
1160	and kvm.  Userspace can use the information returned by this ioctl to
1161	construct cpuid information (for KVM_SET_CPUID2) that is consistent with
1162	hardware, kernel, and userspace capabilities, and with user requirements (for
1163	example, the user may wish to constrain cpuid to emulate older hardware,
1164	or for feature consistency across a cluster).
1165	
1166	Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure
1167	with the 'nent' field indicating the number of entries in the variable-size
1168	array 'entries'.  If the number of entries is too low to describe the cpu
1169	capabilities, an error (E2BIG) is returned.  If the number is too high,
1170	the 'nent' field is adjusted and an error (ENOMEM) is returned.  If the
1171	number is just right, the 'nent' field is adjusted to the number of valid
1172	entries in the 'entries' array, which is then filled.
1173	
1174	The entries returned are the host cpuid as returned by the cpuid instruction,
1175	with unknown or unsupported features masked out.  Some features (for example,
1176	x2apic), may not be present in the host cpu, but are exposed by kvm if it can
1177	emulate them efficiently. The fields in each entry are defined as follows:
1178	
1179	  function: the eax value used to obtain the entry
1180	  index: the ecx value used to obtain the entry (for entries that are
1181	         affected by ecx)
1182	  flags: an OR of zero or more of the following:
1183	        KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
1184	           if the index field is valid
1185	        KVM_CPUID_FLAG_STATEFUL_FUNC:
1186	           if cpuid for this function returns different values for successive
1187	           invocations; there will be several entries with the same function,
1188	           all with this flag set
1189	        KVM_CPUID_FLAG_STATE_READ_NEXT:
1190	           for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
1191	           the first entry to be read by a cpu
1192	   eax, ebx, ecx, edx: the values returned by the cpuid instruction for
1193	         this function/index combination
1194	
1195	The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned
1196	as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC
1197	support.  Instead it is reported via
1198	
1199	  ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER)
1200	
1201	if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the
1202	feature in userspace, then you can enable the feature for KVM_SET_CPUID2.
1203	
1204	
1205	4.47 KVM_PPC_GET_PVINFO
1206	
1207	Capability: KVM_CAP_PPC_GET_PVINFO
1208	Architectures: ppc
1209	Type: vm ioctl
1210	Parameters: struct kvm_ppc_pvinfo (out)
1211	Returns: 0 on success, !0 on error
1212	
1213	struct kvm_ppc_pvinfo {
1214		__u32 flags;
1215		__u32 hcall[4];
1216		__u8  pad[108];
1217	};
1218	
1219	This ioctl fetches PV specific information that need to be passed to the guest
1220	using the device tree or other means from vm context.
1221	
1222	The hcall array defines 4 instructions that make up a hypercall.
1223	
1224	If any additional field gets added to this structure later on, a bit for that
1225	additional piece of information will be set in the flags bitmap.
1226	
1227	The flags bitmap is defined as:
1228	
1229	   /* the host supports the ePAPR idle hcall
1230	   #define KVM_PPC_PVINFO_FLAGS_EV_IDLE   (1<<0)
1231	
1232	4.48 KVM_ASSIGN_PCI_DEVICE
1233	
1234	Capability: KVM_CAP_DEVICE_ASSIGNMENT
1235	Architectures: x86 ia64
1236	Type: vm ioctl
1237	Parameters: struct kvm_assigned_pci_dev (in)
1238	Returns: 0 on success, -1 on error
1239	
1240	Assigns a host PCI device to the VM.
1241	
1242	struct kvm_assigned_pci_dev {
1243		__u32 assigned_dev_id;
1244		__u32 busnr;
1245		__u32 devfn;
1246		__u32 flags;
1247		__u32 segnr;
1248		union {
1249			__u32 reserved[11];
1250		};
1251	};
1252	
1253	The PCI device is specified by the triple segnr, busnr, and devfn.
1254	Identification in succeeding service requests is done via assigned_dev_id. The
1255	following flags are specified:
1256	
1257	/* Depends on KVM_CAP_IOMMU */
1258	#define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
1259	/* The following two depend on KVM_CAP_PCI_2_3 */
1260	#define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
1261	#define KVM_DEV_ASSIGN_MASK_INTX	(1 << 2)
1262	
1263	If KVM_DEV_ASSIGN_PCI_2_3 is set, the kernel will manage legacy INTx interrupts
1264	via the PCI-2.3-compliant device-level mask, thus enable IRQ sharing with other
1265	assigned devices or host devices. KVM_DEV_ASSIGN_MASK_INTX specifies the
1266	guest's view on the INTx mask, see KVM_ASSIGN_SET_INTX_MASK for details.
1267	
1268	The KVM_DEV_ASSIGN_ENABLE_IOMMU flag is a mandatory option to ensure
1269	isolation of the device.  Usages not specifying this flag are deprecated.
1270	
1271	Only PCI header type 0 devices with PCI BAR resources are supported by
1272	device assignment.  The user requesting this ioctl must have read/write
1273	access to the PCI sysfs resource files associated with the device.
1274	
1275	
1276	4.49 KVM_DEASSIGN_PCI_DEVICE
1277	
1278	Capability: KVM_CAP_DEVICE_DEASSIGNMENT
1279	Architectures: x86 ia64
1280	Type: vm ioctl
1281	Parameters: struct kvm_assigned_pci_dev (in)
1282	Returns: 0 on success, -1 on error
1283	
1284	Ends PCI device assignment, releasing all associated resources.
1285	
1286	See KVM_CAP_DEVICE_ASSIGNMENT for the data structure. Only assigned_dev_id is
1287	used in kvm_assigned_pci_dev to identify the device.
1288	
1289	
1290	4.50 KVM_ASSIGN_DEV_IRQ
1291	
1292	Capability: KVM_CAP_ASSIGN_DEV_IRQ
1293	Architectures: x86 ia64
1294	Type: vm ioctl
1295	Parameters: struct kvm_assigned_irq (in)
1296	Returns: 0 on success, -1 on error
1297	
1298	Assigns an IRQ to a passed-through device.
1299	
1300	struct kvm_assigned_irq {
1301		__u32 assigned_dev_id;
1302		__u32 host_irq; /* ignored (legacy field) */
1303		__u32 guest_irq;
1304		__u32 flags;
1305		union {
1306			__u32 reserved[12];
1307		};
1308	};
1309	
1310	The following flags are defined:
1311	
1312	#define KVM_DEV_IRQ_HOST_INTX    (1 << 0)
1313	#define KVM_DEV_IRQ_HOST_MSI     (1 << 1)
1314	#define KVM_DEV_IRQ_HOST_MSIX    (1 << 2)
1315	
1316	#define KVM_DEV_IRQ_GUEST_INTX   (1 << 8)
1317	#define KVM_DEV_IRQ_GUEST_MSI    (1 << 9)
1318	#define KVM_DEV_IRQ_GUEST_MSIX   (1 << 10)
1319	
1320	It is not valid to specify multiple types per host or guest IRQ. However, the
1321	IRQ type of host and guest can differ or can even be null.
1322	
1323	
1324	4.51 KVM_DEASSIGN_DEV_IRQ
1325	
1326	Capability: KVM_CAP_ASSIGN_DEV_IRQ
1327	Architectures: x86 ia64
1328	Type: vm ioctl
1329	Parameters: struct kvm_assigned_irq (in)
1330	Returns: 0 on success, -1 on error
1331	
1332	Ends an IRQ assignment to a passed-through device.
1333	
1334	See KVM_ASSIGN_DEV_IRQ for the data structure. The target device is specified
1335	by assigned_dev_id, flags must correspond to the IRQ type specified on
1336	KVM_ASSIGN_DEV_IRQ. Partial deassignment of host or guest IRQ is allowed.
1337	
1338	
1339	4.52 KVM_SET_GSI_ROUTING
1340	
1341	Capability: KVM_CAP_IRQ_ROUTING
1342	Architectures: x86 ia64 s390
1343	Type: vm ioctl
1344	Parameters: struct kvm_irq_routing (in)
1345	Returns: 0 on success, -1 on error
1346	
1347	Sets the GSI routing table entries, overwriting any previously set entries.
1348	
1349	struct kvm_irq_routing {
1350		__u32 nr;
1351		__u32 flags;
1352		struct kvm_irq_routing_entry entries[0];
1353	};
1354	
1355	No flags are specified so far, the corresponding field must be set to zero.
1356	
1357	struct kvm_irq_routing_entry {
1358		__u32 gsi;
1359		__u32 type;
1360		__u32 flags;
1361		__u32 pad;
1362		union {
1363			struct kvm_irq_routing_irqchip irqchip;
1364			struct kvm_irq_routing_msi msi;
1365			struct kvm_irq_routing_s390_adapter adapter;
1366			__u32 pad[8];
1367		} u;
1368	};
1369	
1370	/* gsi routing entry types */
1371	#define KVM_IRQ_ROUTING_IRQCHIP 1
1372	#define KVM_IRQ_ROUTING_MSI 2
1373	#define KVM_IRQ_ROUTING_S390_ADAPTER 3
1374	
1375	No flags are specified so far, the corresponding field must be set to zero.
1376	
1377	struct kvm_irq_routing_irqchip {
1378		__u32 irqchip;
1379		__u32 pin;
1380	};
1381	
1382	struct kvm_irq_routing_msi {
1383		__u32 address_lo;
1384		__u32 address_hi;
1385		__u32 data;
1386		__u32 pad;
1387	};
1388	
1389	struct kvm_irq_routing_s390_adapter {
1390		__u64 ind_addr;
1391		__u64 summary_addr;
1392		__u64 ind_offset;
1393		__u32 summary_offset;
1394		__u32 adapter_id;
1395	};
1396	
1397	
1398	4.53 KVM_ASSIGN_SET_MSIX_NR
1399	
1400	Capability: KVM_CAP_DEVICE_MSIX
1401	Architectures: x86 ia64
1402	Type: vm ioctl
1403	Parameters: struct kvm_assigned_msix_nr (in)
1404	Returns: 0 on success, -1 on error
1405	
1406	Set the number of MSI-X interrupts for an assigned device. The number is
1407	reset again by terminating the MSI-X assignment of the device via
1408	KVM_DEASSIGN_DEV_IRQ. Calling this service more than once at any earlier
1409	point will fail.
1410	
1411	struct kvm_assigned_msix_nr {
1412		__u32 assigned_dev_id;
1413		__u16 entry_nr;
1414		__u16 padding;
1415	};
1416	
1417	#define KVM_MAX_MSIX_PER_DEV		256
1418	
1419	
1420	4.54 KVM_ASSIGN_SET_MSIX_ENTRY
1421	
1422	Capability: KVM_CAP_DEVICE_MSIX
1423	Architectures: x86 ia64
1424	Type: vm ioctl
1425	Parameters: struct kvm_assigned_msix_entry (in)
1426	Returns: 0 on success, -1 on error
1427	
1428	Specifies the routing of an MSI-X assigned device interrupt to a GSI. Setting
1429	the GSI vector to zero means disabling the interrupt.
1430	
1431	struct kvm_assigned_msix_entry {
1432		__u32 assigned_dev_id;
1433		__u32 gsi;
1434		__u16 entry; /* The index of entry in the MSI-X table */
1435		__u16 padding[3];
1436	};
1437	
1438	
1439	4.55 KVM_SET_TSC_KHZ
1440	
1441	Capability: KVM_CAP_TSC_CONTROL
1442	Architectures: x86
1443	Type: vcpu ioctl
1444	Parameters: virtual tsc_khz
1445	Returns: 0 on success, -1 on error
1446	
1447	Specifies the tsc frequency for the virtual machine. The unit of the
1448	frequency is KHz.
1449	
1450	
1451	4.56 KVM_GET_TSC_KHZ
1452	
1453	Capability: KVM_CAP_GET_TSC_KHZ
1454	Architectures: x86
1455	Type: vcpu ioctl
1456	Parameters: none
1457	Returns: virtual tsc-khz on success, negative value on error
1458	
1459	Returns the tsc frequency of the guest. The unit of the return value is
1460	KHz. If the host has unstable tsc this ioctl returns -EIO instead as an
1461	error.
1462	
1463	
1464	4.57 KVM_GET_LAPIC
1465	
1466	Capability: KVM_CAP_IRQCHIP
1467	Architectures: x86
1468	Type: vcpu ioctl
1469	Parameters: struct kvm_lapic_state (out)
1470	Returns: 0 on success, -1 on error
1471	
1472	#define KVM_APIC_REG_SIZE 0x400
1473	struct kvm_lapic_state {
1474		char regs[KVM_APIC_REG_SIZE];
1475	};
1476	
1477	Reads the Local APIC registers and copies them into the input argument.  The
1478	data format and layout are the same as documented in the architecture manual.
1479	
1480	
1481	4.58 KVM_SET_LAPIC
1482	
1483	Capability: KVM_CAP_IRQCHIP
1484	Architectures: x86
1485	Type: vcpu ioctl
1486	Parameters: struct kvm_lapic_state (in)
1487	Returns: 0 on success, -1 on error
1488	
1489	#define KVM_APIC_REG_SIZE 0x400
1490	struct kvm_lapic_state {
1491		char regs[KVM_APIC_REG_SIZE];
1492	};
1493	
1494	Copies the input argument into the Local APIC registers.  The data format
1495	and layout are the same as documented in the architecture manual.
1496	
1497	
1498	4.59 KVM_IOEVENTFD
1499	
1500	Capability: KVM_CAP_IOEVENTFD
1501	Architectures: all
1502	Type: vm ioctl
1503	Parameters: struct kvm_ioeventfd (in)
1504	Returns: 0 on success, !0 on error
1505	
1506	This ioctl attaches or detaches an ioeventfd to a legal pio/mmio address
1507	within the guest.  A guest write in the registered address will signal the
1508	provided event instead of triggering an exit.
1509	
1510	struct kvm_ioeventfd {
1511		__u64 datamatch;
1512		__u64 addr;        /* legal pio/mmio address */
1513		__u32 len;         /* 1, 2, 4, or 8 bytes    */
1514		__s32 fd;
1515		__u32 flags;
1516		__u8  pad[36];
1517	};
1518	
1519	For the special case of virtio-ccw devices on s390, the ioevent is matched
1520	to a subchannel/virtqueue tuple instead.
1521	
1522	The following flags are defined:
1523	
1524	#define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
1525	#define KVM_IOEVENTFD_FLAG_PIO       (1 << kvm_ioeventfd_flag_nr_pio)
1526	#define KVM_IOEVENTFD_FLAG_DEASSIGN  (1 << kvm_ioeventfd_flag_nr_deassign)
1527	#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
1528		(1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify)
1529	
1530	If datamatch flag is set, the event will be signaled only if the written value
1531	to the registered address is equal to datamatch in struct kvm_ioeventfd.
1532	
1533	For virtio-ccw devices, addr contains the subchannel id and datamatch the
1534	virtqueue index.
1535	
1536	
1537	4.60 KVM_DIRTY_TLB
1538	
1539	Capability: KVM_CAP_SW_TLB
1540	Architectures: ppc
1541	Type: vcpu ioctl
1542	Parameters: struct kvm_dirty_tlb (in)
1543	Returns: 0 on success, -1 on error
1544	
1545	struct kvm_dirty_tlb {
1546		__u64 bitmap;
1547		__u32 num_dirty;
1548	};
1549	
1550	This must be called whenever userspace has changed an entry in the shared
1551	TLB, prior to calling KVM_RUN on the associated vcpu.
1552	
1553	The "bitmap" field is the userspace address of an array.  This array
1554	consists of a number of bits, equal to the total number of TLB entries as
1555	determined by the last successful call to KVM_CONFIG_TLB, rounded up to the
1556	nearest multiple of 64.
1557	
1558	Each bit corresponds to one TLB entry, ordered the same as in the shared TLB
1559	array.
1560	
1561	The array is little-endian: the bit 0 is the least significant bit of the
1562	first byte, bit 8 is the least significant bit of the second byte, etc.
1563	This avoids any complications with differing word sizes.
1564	
1565	The "num_dirty" field is a performance hint for KVM to determine whether it
1566	should skip processing the bitmap and just invalidate everything.  It must
1567	be set to the number of set bits in the bitmap.
1568	
1569	
1570	4.61 KVM_ASSIGN_SET_INTX_MASK
1571	
1572	Capability: KVM_CAP_PCI_2_3
1573	Architectures: x86
1574	Type: vm ioctl
1575	Parameters: struct kvm_assigned_pci_dev (in)
1576	Returns: 0 on success, -1 on error
1577	
1578	Allows userspace to mask PCI INTx interrupts from the assigned device.  The
1579	kernel will not deliver INTx interrupts to the guest between setting and
1580	clearing of KVM_ASSIGN_SET_INTX_MASK via this interface.  This enables use of
1581	and emulation of PCI 2.3 INTx disable command register behavior.
1582	
1583	This may be used for both PCI 2.3 devices supporting INTx disable natively and
1584	older devices lacking this support. Userspace is responsible for emulating the
1585	read value of the INTx disable bit in the guest visible PCI command register.
1586	When modifying the INTx disable state, userspace should precede updating the
1587	physical device command register by calling this ioctl to inform the kernel of
1588	the new intended INTx mask state.
1589	
1590	Note that the kernel uses the device INTx disable bit to internally manage the
1591	device interrupt state for PCI 2.3 devices.  Reads of this register may
1592	therefore not match the expected value.  Writes should always use the guest
1593	intended INTx disable value rather than attempting to read-copy-update the
1594	current physical device state.  Races between user and kernel updates to the
1595	INTx disable bit are handled lazily in the kernel.  It's possible the device
1596	may generate unintended interrupts, but they will not be injected into the
1597	guest.
1598	
1599	See KVM_ASSIGN_DEV_IRQ for the data structure.  The target device is specified
1600	by assigned_dev_id.  In the flags field, only KVM_DEV_ASSIGN_MASK_INTX is
1601	evaluated.
1602	
1603	
1604	4.62 KVM_CREATE_SPAPR_TCE
1605	
1606	Capability: KVM_CAP_SPAPR_TCE
1607	Architectures: powerpc
1608	Type: vm ioctl
1609	Parameters: struct kvm_create_spapr_tce (in)
1610	Returns: file descriptor for manipulating the created TCE table
1611	
1612	This creates a virtual TCE (translation control entry) table, which
1613	is an IOMMU for PAPR-style virtual I/O.  It is used to translate
1614	logical addresses used in virtual I/O into guest physical addresses,
1615	and provides a scatter/gather capability for PAPR virtual I/O.
1616	
1617	/* for KVM_CAP_SPAPR_TCE */
1618	struct kvm_create_spapr_tce {
1619		__u64 liobn;
1620		__u32 window_size;
1621	};
1622	
1623	The liobn field gives the logical IO bus number for which to create a
1624	TCE table.  The window_size field specifies the size of the DMA window
1625	which this TCE table will translate - the table will contain one 64
1626	bit TCE entry for every 4kiB of the DMA window.
1627	
1628	When the guest issues an H_PUT_TCE hcall on a liobn for which a TCE
1629	table has been created using this ioctl(), the kernel will handle it
1630	in real mode, updating the TCE table.  H_PUT_TCE calls for other
1631	liobns will cause a vm exit and must be handled by userspace.
1632	
1633	The return value is a file descriptor which can be passed to mmap(2)
1634	to map the created TCE table into userspace.  This lets userspace read
1635	the entries written by kernel-handled H_PUT_TCE calls, and also lets
1636	userspace update the TCE table directly which is useful in some
1637	circumstances.
1638	
1639	
1640	4.63 KVM_ALLOCATE_RMA
1641	
1642	Capability: KVM_CAP_PPC_RMA
1643	Architectures: powerpc
1644	Type: vm ioctl
1645	Parameters: struct kvm_allocate_rma (out)
1646	Returns: file descriptor for mapping the allocated RMA
1647	
1648	This allocates a Real Mode Area (RMA) from the pool allocated at boot
1649	time by the kernel.  An RMA is a physically-contiguous, aligned region
1650	of memory used on older POWER processors to provide the memory which
1651	will be accessed by real-mode (MMU off) accesses in a KVM guest.
1652	POWER processors support a set of sizes for the RMA that usually
1653	includes 64MB, 128MB, 256MB and some larger powers of two.
1654	
1655	/* for KVM_ALLOCATE_RMA */
1656	struct kvm_allocate_rma {
1657		__u64 rma_size;
1658	};
1659	
1660	The return value is a file descriptor which can be passed to mmap(2)
1661	to map the allocated RMA into userspace.  The mapped area can then be
1662	passed to the KVM_SET_USER_MEMORY_REGION ioctl to establish it as the
1663	RMA for a virtual machine.  The size of the RMA in bytes (which is
1664	fixed at host kernel boot time) is returned in the rma_size field of
1665	the argument structure.
1666	
1667	The KVM_CAP_PPC_RMA capability is 1 or 2 if the KVM_ALLOCATE_RMA ioctl
1668	is supported; 2 if the processor requires all virtual machines to have
1669	an RMA, or 1 if the processor can use an RMA but doesn't require it,
1670	because it supports the Virtual RMA (VRMA) facility.
1671	
1672	
1673	4.64 KVM_NMI
1674	
1675	Capability: KVM_CAP_USER_NMI
1676	Architectures: x86
1677	Type: vcpu ioctl
1678	Parameters: none
1679	Returns: 0 on success, -1 on error
1680	
1681	Queues an NMI on the thread's vcpu.  Note this is well defined only
1682	when KVM_CREATE_IRQCHIP has not been called, since this is an interface
1683	between the virtual cpu core and virtual local APIC.  After KVM_CREATE_IRQCHIP
1684	has been called, this interface is completely emulated within the kernel.
1685	
1686	To use this to emulate the LINT1 input with KVM_CREATE_IRQCHIP, use the
1687	following algorithm:
1688	
1689	  - pause the vpcu
1690	  - read the local APIC's state (KVM_GET_LAPIC)
1691	  - check whether changing LINT1 will queue an NMI (see the LVT entry for LINT1)
1692	  - if so, issue KVM_NMI
1693	  - resume the vcpu
1694	
1695	Some guests configure the LINT1 NMI input to cause a panic, aiding in
1696	debugging.
1697	
1698	
1699	4.65 KVM_S390_UCAS_MAP
1700	
1701	Capability: KVM_CAP_S390_UCONTROL
1702	Architectures: s390
1703	Type: vcpu ioctl
1704	Parameters: struct kvm_s390_ucas_mapping (in)
1705	Returns: 0 in case of success
1706	
1707	The parameter is defined like this:
1708		struct kvm_s390_ucas_mapping {
1709			__u64 user_addr;
1710			__u64 vcpu_addr;
1711			__u64 length;
1712		};
1713	
1714	This ioctl maps the memory at "user_addr" with the length "length" to
1715	the vcpu's address space starting at "vcpu_addr". All parameters need to
1716	be aligned by 1 megabyte.
1717	
1718	
1719	4.66 KVM_S390_UCAS_UNMAP
1720	
1721	Capability: KVM_CAP_S390_UCONTROL
1722	Architectures: s390
1723	Type: vcpu ioctl
1724	Parameters: struct kvm_s390_ucas_mapping (in)
1725	Returns: 0 in case of success
1726	
1727	The parameter is defined like this:
1728		struct kvm_s390_ucas_mapping {
1729			__u64 user_addr;
1730			__u64 vcpu_addr;
1731			__u64 length;
1732		};
1733	
1734	This ioctl unmaps the memory in the vcpu's address space starting at
1735	"vcpu_addr" with the length "length". The field "user_addr" is ignored.
1736	All parameters need to be aligned by 1 megabyte.
1737	
1738	
1739	4.67 KVM_S390_VCPU_FAULT
1740	
1741	Capability: KVM_CAP_S390_UCONTROL
1742	Architectures: s390
1743	Type: vcpu ioctl
1744	Parameters: vcpu absolute address (in)
1745	Returns: 0 in case of success
1746	
1747	This call creates a page table entry on the virtual cpu's address space
1748	(for user controlled virtual machines) or the virtual machine's address
1749	space (for regular virtual machines). This only works for minor faults,
1750	thus it's recommended to access subject memory page via the user page
1751	table upfront. This is useful to handle validity intercepts for user
1752	controlled virtual machines to fault in the virtual cpu's lowcore pages
1753	prior to calling the KVM_RUN ioctl.
1754	
1755	
1756	4.68 KVM_SET_ONE_REG
1757	
1758	Capability: KVM_CAP_ONE_REG
1759	Architectures: all
1760	Type: vcpu ioctl
1761	Parameters: struct kvm_one_reg (in)
1762	Returns: 0 on success, negative value on failure
1763	
1764	struct kvm_one_reg {
1765	       __u64 id;
1766	       __u64 addr;
1767	};
1768	
1769	Using this ioctl, a single vcpu register can be set to a specific value
1770	defined by user space with the passed in struct kvm_one_reg, where id
1771	refers to the register identifier as described below and addr is a pointer
1772	to a variable with the respective size. There can be architecture agnostic
1773	and architecture specific registers. Each have their own range of operation
1774	and their own constants and width. To keep track of the implemented
1775	registers, find a list below:
1776	
1777	  Arch  |       Register        | Width (bits)
1778	        |                       |
1779	  PPC   | KVM_REG_PPC_HIOR      | 64
1780	  PPC   | KVM_REG_PPC_IAC1      | 64
1781	  PPC   | KVM_REG_PPC_IAC2      | 64
1782	  PPC   | KVM_REG_PPC_IAC3      | 64
1783	  PPC   | KVM_REG_PPC_IAC4      | 64
1784	  PPC   | KVM_REG_PPC_DAC1      | 64
1785	  PPC   | KVM_REG_PPC_DAC2      | 64
1786	  PPC   | KVM_REG_PPC_DABR      | 64
1787	  PPC   | KVM_REG_PPC_DSCR      | 64
1788	  PPC   | KVM_REG_PPC_PURR      | 64
1789	  PPC   | KVM_REG_PPC_SPURR     | 64
1790	  PPC   | KVM_REG_PPC_DAR       | 64
1791	  PPC   | KVM_REG_PPC_DSISR     | 32
1792	  PPC   | KVM_REG_PPC_AMR       | 64
1793	  PPC   | KVM_REG_PPC_UAMOR     | 64
1794	  PPC   | KVM_REG_PPC_MMCR0     | 64
1795	  PPC   | KVM_REG_PPC_MMCR1     | 64
1796	  PPC   | KVM_REG_PPC_MMCRA     | 64
1797	  PPC   | KVM_REG_PPC_MMCR2     | 64
1798	  PPC   | KVM_REG_PPC_MMCRS     | 64
1799	  PPC   | KVM_REG_PPC_SIAR      | 64
1800	  PPC   | KVM_REG_PPC_SDAR      | 64
1801	  PPC   | KVM_REG_PPC_SIER      | 64
1802	  PPC   | KVM_REG_PPC_PMC1      | 32
1803	  PPC   | KVM_REG_PPC_PMC2      | 32
1804	  PPC   | KVM_REG_PPC_PMC3      | 32
1805	  PPC   | KVM_REG_PPC_PMC4      | 32
1806	  PPC   | KVM_REG_PPC_PMC5      | 32
1807	  PPC   | KVM_REG_PPC_PMC6      | 32
1808	  PPC   | KVM_REG_PPC_PMC7      | 32
1809	  PPC   | KVM_REG_PPC_PMC8      | 32
1810	  PPC   | KVM_REG_PPC_FPR0      | 64
1811	          ...
1812	  PPC   | KVM_REG_PPC_FPR31     | 64
1813	  PPC   | KVM_REG_PPC_VR0       | 128
1814	          ...
1815	  PPC   | KVM_REG_PPC_VR31      | 128
1816	  PPC   | KVM_REG_PPC_VSR0      | 128
1817	          ...
1818	  PPC   | KVM_REG_PPC_VSR31     | 128
1819	  PPC   | KVM_REG_PPC_FPSCR     | 64
1820	  PPC   | KVM_REG_PPC_VSCR      | 32
1821	  PPC   | KVM_REG_PPC_VPA_ADDR  | 64
1822	  PPC   | KVM_REG_PPC_VPA_SLB   | 128
1823	  PPC   | KVM_REG_PPC_VPA_DTL   | 128
1824	  PPC   | KVM_REG_PPC_EPCR	| 32
1825	  PPC   | KVM_REG_PPC_EPR	| 32
1826	  PPC   | KVM_REG_PPC_TCR	| 32
1827	  PPC   | KVM_REG_PPC_TSR	| 32
1828	  PPC   | KVM_REG_PPC_OR_TSR	| 32
1829	  PPC   | KVM_REG_PPC_CLEAR_TSR	| 32
1830	  PPC   | KVM_REG_PPC_MAS0	| 32
1831	  PPC   | KVM_REG_PPC_MAS1	| 32
1832	  PPC   | KVM_REG_PPC_MAS2	| 64
1833	  PPC   | KVM_REG_PPC_MAS7_3	| 64
1834	  PPC   | KVM_REG_PPC_MAS4	| 32
1835	  PPC   | KVM_REG_PPC_MAS6	| 32
1836	  PPC   | KVM_REG_PPC_MMUCFG	| 32
1837	  PPC   | KVM_REG_PPC_TLB0CFG	| 32
1838	  PPC   | KVM_REG_PPC_TLB1CFG	| 32
1839	  PPC   | KVM_REG_PPC_TLB2CFG	| 32
1840	  PPC   | KVM_REG_PPC_TLB3CFG	| 32
1841	  PPC   | KVM_REG_PPC_TLB0PS	| 32
1842	  PPC   | KVM_REG_PPC_TLB1PS	| 32
1843	  PPC   | KVM_REG_PPC_TLB2PS	| 32
1844	  PPC   | KVM_REG_PPC_TLB3PS	| 32
1845	  PPC   | KVM_REG_PPC_EPTCFG	| 32
1846	  PPC   | KVM_REG_PPC_ICP_STATE | 64
1847	  PPC   | KVM_REG_PPC_TB_OFFSET	| 64
1848	  PPC   | KVM_REG_PPC_SPMC1	| 32
1849	  PPC   | KVM_REG_PPC_SPMC2	| 32
1850	  PPC   | KVM_REG_PPC_IAMR	| 64
1851	  PPC   | KVM_REG_PPC_TFHAR	| 64
1852	  PPC   | KVM_REG_PPC_TFIAR	| 64
1853	  PPC   | KVM_REG_PPC_TEXASR	| 64
1854	  PPC   | KVM_REG_PPC_FSCR	| 64
1855	  PPC   | KVM_REG_PPC_PSPB	| 32
1856	  PPC   | KVM_REG_PPC_EBBHR	| 64
1857	  PPC   | KVM_REG_PPC_EBBRR	| 64
1858	  PPC   | KVM_REG_PPC_BESCR	| 64
1859	  PPC   | KVM_REG_PPC_TAR	| 64
1860	  PPC   | KVM_REG_PPC_DPDES	| 64
1861	  PPC   | KVM_REG_PPC_DAWR	| 64
1862	  PPC   | KVM_REG_PPC_DAWRX	| 64
1863	  PPC   | KVM_REG_PPC_CIABR	| 64
1864	  PPC   | KVM_REG_PPC_IC	| 64
1865	  PPC   | KVM_REG_PPC_VTB	| 64
1866	  PPC   | KVM_REG_PPC_CSIGR	| 64
1867	  PPC   | KVM_REG_PPC_TACR	| 64
1868	  PPC   | KVM_REG_PPC_TCSCR	| 64
1869	  PPC   | KVM_REG_PPC_PID	| 64
1870	  PPC   | KVM_REG_PPC_ACOP	| 64
1871	  PPC   | KVM_REG_PPC_VRSAVE	| 32
1872	  PPC   | KVM_REG_PPC_LPCR	| 64
1873	  PPC   | KVM_REG_PPC_PPR	| 64
1874	  PPC   | KVM_REG_PPC_ARCH_COMPAT 32
1875	  PPC   | KVM_REG_PPC_DABRX     | 32
1876	  PPC   | KVM_REG_PPC_WORT      | 64
1877	  PPC   | KVM_REG_PPC_TM_GPR0	| 64
1878	          ...
1879	  PPC   | KVM_REG_PPC_TM_GPR31	| 64
1880	  PPC   | KVM_REG_PPC_TM_VSR0	| 128
1881	          ...
1882	  PPC   | KVM_REG_PPC_TM_VSR63	| 128
1883	  PPC   | KVM_REG_PPC_TM_CR	| 64
1884	  PPC   | KVM_REG_PPC_TM_LR	| 64
1885	  PPC   | KVM_REG_PPC_TM_CTR	| 64
1886	  PPC   | KVM_REG_PPC_TM_FPSCR	| 64
1887	  PPC   | KVM_REG_PPC_TM_AMR	| 64
1888	  PPC   | KVM_REG_PPC_TM_PPR	| 64
1889	  PPC   | KVM_REG_PPC_TM_VRSAVE	| 64
1890	  PPC   | KVM_REG_PPC_TM_VSCR	| 32
1891	  PPC   | KVM_REG_PPC_TM_DSCR	| 64
1892	  PPC   | KVM_REG_PPC_TM_TAR	| 64
1893	
1894	ARM registers are mapped using the lower 32 bits.  The upper 16 of that
1895	is the register group type, or coprocessor number:
1896	
1897	ARM core registers have the following id bit patterns:
1898	  0x4020 0000 0010 <index into the kvm_regs struct:16>
1899	
1900	ARM 32-bit CP15 registers have the following id bit patterns:
1901	  0x4020 0000 000F <zero:1> <crn:4> <crm:4> <opc1:4> <opc2:3>
1902	
1903	ARM 64-bit CP15 registers have the following id bit patterns:
1904	  0x4030 0000 000F <zero:1> <zero:4> <crm:4> <opc1:4> <zero:3>
1905	
1906	ARM CCSIDR registers are demultiplexed by CSSELR value:
1907	  0x4020 0000 0011 00 <csselr:8>
1908	
1909	ARM 32-bit VFP control registers have the following id bit patterns:
1910	  0x4020 0000 0012 1 <regno:12>
1911	
1912	ARM 64-bit FP registers have the following id bit patterns:
1913	  0x4030 0000 0012 0 <regno:12>
1914	
1915	
1916	arm64 registers are mapped using the lower 32 bits. The upper 16 of
1917	that is the register group type, or coprocessor number:
1918	
1919	arm64 core/FP-SIMD registers have the following id bit patterns. Note
1920	that the size of the access is variable, as the kvm_regs structure
1921	contains elements ranging from 32 to 128 bits. The index is a 32bit
1922	value in the kvm_regs structure seen as a 32bit array.
1923	  0x60x0 0000 0010 <index into the kvm_regs struct:16>
1924	
1925	arm64 CCSIDR registers are demultiplexed by CSSELR value:
1926	  0x6020 0000 0011 00 <csselr:8>
1927	
1928	arm64 system registers have the following id bit patterns:
1929	  0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
1930	
1931	4.69 KVM_GET_ONE_REG
1932	
1933	Capability: KVM_CAP_ONE_REG
1934	Architectures: all
1935	Type: vcpu ioctl
1936	Parameters: struct kvm_one_reg (in and out)
1937	Returns: 0 on success, negative value on failure
1938	
1939	This ioctl allows to receive the value of a single register implemented
1940	in a vcpu. The register to read is indicated by the "id" field of the
1941	kvm_one_reg struct passed in. On success, the register value can be found
1942	at the memory location pointed to by "addr".
1943	
1944	The list of registers accessible using this interface is identical to the
1945	list in 4.68.
1946	
1947	
1948	4.70 KVM_KVMCLOCK_CTRL
1949	
1950	Capability: KVM_CAP_KVMCLOCK_CTRL
1951	Architectures: Any that implement pvclocks (currently x86 only)
1952	Type: vcpu ioctl
1953	Parameters: None
1954	Returns: 0 on success, -1 on error
1955	
1956	This signals to the host kernel that the specified guest is being paused by
1957	userspace.  The host will set a flag in the pvclock structure that is checked
1958	from the soft lockup watchdog.  The flag is part of the pvclock structure that
1959	is shared between guest and host, specifically the second bit of the flags
1960	field of the pvclock_vcpu_time_info structure.  It will be set exclusively by
1961	the host and read/cleared exclusively by the guest.  The guest operation of
1962	checking and clearing the flag must an atomic operation so
1963	load-link/store-conditional, or equivalent must be used.  There are two cases
1964	where the guest will clear the flag: when the soft lockup watchdog timer resets
1965	itself or when a soft lockup is detected.  This ioctl can be called any time
1966	after pausing the vcpu, but before it is resumed.
1967	
1968	
1969	4.71 KVM_SIGNAL_MSI
1970	
1971	Capability: KVM_CAP_SIGNAL_MSI
1972	Architectures: x86
1973	Type: vm ioctl
1974	Parameters: struct kvm_msi (in)
1975	Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error
1976	
1977	Directly inject a MSI message. Only valid with in-kernel irqchip that handles
1978	MSI messages.
1979	
1980	struct kvm_msi {
1981		__u32 address_lo;
1982		__u32 address_hi;
1983		__u32 data;
1984		__u32 flags;
1985		__u8  pad[16];
1986	};
1987	
1988	No flags are defined so far. The corresponding field must be 0.
1989	
1990	
1991	4.71 KVM_CREATE_PIT2
1992	
1993	Capability: KVM_CAP_PIT2
1994	Architectures: x86
1995	Type: vm ioctl
1996	Parameters: struct kvm_pit_config (in)
1997	Returns: 0 on success, -1 on error
1998	
1999	Creates an in-kernel device model for the i8254 PIT. This call is only valid
2000	after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following
2001	parameters have to be passed:
2002	
2003	struct kvm_pit_config {
2004		__u32 flags;
2005		__u32 pad[15];
2006	};
2007	
2008	Valid flags are:
2009	
2010	#define KVM_PIT_SPEAKER_DUMMY     1 /* emulate speaker port stub */
2011	
2012	PIT timer interrupts may use a per-VM kernel thread for injection. If it
2013	exists, this thread will have a name of the following pattern:
2014	
2015	kvm-pit/<owner-process-pid>
2016	
2017	When running a guest with elevated priorities, the scheduling parameters of
2018	this thread may have to be adjusted accordingly.
2019	
2020	This IOCTL replaces the obsolete KVM_CREATE_PIT.
2021	
2022	
2023	4.72 KVM_GET_PIT2
2024	
2025	Capability: KVM_CAP_PIT_STATE2
2026	Architectures: x86
2027	Type: vm ioctl
2028	Parameters: struct kvm_pit_state2 (out)
2029	Returns: 0 on success, -1 on error
2030	
2031	Retrieves the state of the in-kernel PIT model. Only valid after
2032	KVM_CREATE_PIT2. The state is returned in the following structure:
2033	
2034	struct kvm_pit_state2 {
2035		struct kvm_pit_channel_state channels[3];
2036		__u32 flags;
2037		__u32 reserved[9];
2038	};
2039	
2040	Valid flags are:
2041	
2042	/* disable PIT in HPET legacy mode */
2043	#define KVM_PIT_FLAGS_HPET_LEGACY  0x00000001
2044	
2045	This IOCTL replaces the obsolete KVM_GET_PIT.
2046	
2047	
2048	4.73 KVM_SET_PIT2
2049	
2050	Capability: KVM_CAP_PIT_STATE2
2051	Architectures: x86
2052	Type: vm ioctl
2053	Parameters: struct kvm_pit_state2 (in)
2054	Returns: 0 on success, -1 on error
2055	
2056	Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2.
2057	See KVM_GET_PIT2 for details on struct kvm_pit_state2.
2058	
2059	This IOCTL replaces the obsolete KVM_SET_PIT.
2060	
2061	
2062	4.74 KVM_PPC_GET_SMMU_INFO
2063	
2064	Capability: KVM_CAP_PPC_GET_SMMU_INFO
2065	Architectures: powerpc
2066	Type: vm ioctl
2067	Parameters: None
2068	Returns: 0 on success, -1 on error
2069	
2070	This populates and returns a structure describing the features of
2071	the "Server" class MMU emulation supported by KVM.
2072	This can in turn be used by userspace to generate the appropriate
2073	device-tree properties for the guest operating system.
2074	
2075	The structure contains some global information, followed by an
2076	array of supported segment page sizes:
2077	
2078	      struct kvm_ppc_smmu_info {
2079		     __u64 flags;
2080		     __u32 slb_size;
2081		     __u32 pad;
2082		     struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
2083	      };
2084	
2085	The supported flags are:
2086	
2087	    - KVM_PPC_PAGE_SIZES_REAL:
2088	        When that flag is set, guest page sizes must "fit" the backing
2089	        store page sizes. When not set, any page size in the list can
2090	        be used regardless of how they are backed by userspace.
2091	
2092	    - KVM_PPC_1T_SEGMENTS
2093	        The emulated MMU supports 1T segments in addition to the
2094	        standard 256M ones.
2095	
2096	The "slb_size" field indicates how many SLB entries are supported
2097	
2098	The "sps" array contains 8 entries indicating the supported base
2099	page sizes for a segment in increasing order. Each entry is defined
2100	as follow:
2101	
2102	   struct kvm_ppc_one_seg_page_size {
2103		__u32 page_shift;	/* Base page shift of segment (or 0) */
2104		__u32 slb_enc;		/* SLB encoding for BookS */
2105		struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
2106	   };
2107	
2108	An entry with a "page_shift" of 0 is unused. Because the array is
2109	organized in increasing order, a lookup can stop when encoutering
2110	such an entry.
2111	
2112	The "slb_enc" field provides the encoding to use in the SLB for the
2113	page size. The bits are in positions such as the value can directly
2114	be OR'ed into the "vsid" argument of the slbmte instruction.
2115	
2116	The "enc" array is a list which for each of those segment base page
2117	size provides the list of supported actual page sizes (which can be
2118	only larger or equal to the base page size), along with the
2119	corresponding encoding in the hash PTE. Similarly, the array is
2120	8 entries sorted by increasing sizes and an entry with a "0" shift
2121	is an empty entry and a terminator:
2122	
2123	   struct kvm_ppc_one_page_size {
2124		__u32 page_shift;	/* Page shift (or 0) */
2125		__u32 pte_enc;		/* Encoding in the HPTE (>>12) */
2126	   };
2127	
2128	The "pte_enc" field provides a value that can OR'ed into the hash
2129	PTE's RPN field (ie, it needs to be shifted left by 12 to OR it
2130	into the hash PTE second double word).
2131	
2132	4.75 KVM_IRQFD
2133	
2134	Capability: KVM_CAP_IRQFD
2135	Architectures: x86 s390
2136	Type: vm ioctl
2137	Parameters: struct kvm_irqfd (in)
2138	Returns: 0 on success, -1 on error
2139	
2140	Allows setting an eventfd to directly trigger a guest interrupt.
2141	kvm_irqfd.fd specifies the file descriptor to use as the eventfd and
2142	kvm_irqfd.gsi specifies the irqchip pin toggled by this event.  When
2143	an event is triggered on the eventfd, an interrupt is injected into
2144	the guest using the specified gsi pin.  The irqfd is removed using
2145	the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd
2146	and kvm_irqfd.gsi.
2147	
2148	With KVM_CAP_IRQFD_RESAMPLE, KVM_IRQFD supports a de-assert and notify
2149	mechanism allowing emulation of level-triggered, irqfd-based
2150	interrupts.  When KVM_IRQFD_FLAG_RESAMPLE is set the user must pass an
2151	additional eventfd in the kvm_irqfd.resamplefd field.  When operating
2152	in resample mode, posting of an interrupt through kvm_irq.fd asserts
2153	the specified gsi in the irqchip.  When the irqchip is resampled, such
2154	as from an EOI, the gsi is de-asserted and the user is notified via
2155	kvm_irqfd.resamplefd.  It is the user's responsibility to re-queue
2156	the interrupt if the device making use of it still requires service.
2157	Note that closing the resamplefd is not sufficient to disable the
2158	irqfd.  The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment
2159	and need not be specified with KVM_IRQFD_FLAG_DEASSIGN.
2160	
2161	4.76 KVM_PPC_ALLOCATE_HTAB
2162	
2163	Capability: KVM_CAP_PPC_ALLOC_HTAB
2164	Architectures: powerpc
2165	Type: vm ioctl
2166	Parameters: Pointer to u32 containing hash table order (in/out)
2167	Returns: 0 on success, -1 on error
2168	
2169	This requests the host kernel to allocate an MMU hash table for a
2170	guest using the PAPR paravirtualization interface.  This only does
2171	anything if the kernel is configured to use the Book 3S HV style of
2172	virtualization.  Otherwise the capability doesn't exist and the ioctl
2173	returns an ENOTTY error.  The rest of this description assumes Book 3S
2174	HV.
2175	
2176	There must be no vcpus running when this ioctl is called; if there
2177	are, it will do nothing and return an EBUSY error.
2178	
2179	The parameter is a pointer to a 32-bit unsigned integer variable
2180	containing the order (log base 2) of the desired size of the hash
2181	table, which must be between 18 and 46.  On successful return from the
2182	ioctl, it will have been updated with the order of the hash table that
2183	was allocated.
2184	
2185	If no hash table has been allocated when any vcpu is asked to run
2186	(with the KVM_RUN ioctl), the host kernel will allocate a
2187	default-sized hash table (16 MB).
2188	
2189	If this ioctl is called when a hash table has already been allocated,
2190	the kernel will clear out the existing hash table (zero all HPTEs) and
2191	return the hash table order in the parameter.  (If the guest is using
2192	the virtualized real-mode area (VRMA) facility, the kernel will
2193	re-create the VMRA HPTEs on the next KVM_RUN of any vcpu.)
2194	
2195	4.77 KVM_S390_INTERRUPT
2196	
2197	Capability: basic
2198	Architectures: s390
2199	Type: vm ioctl, vcpu ioctl
2200	Parameters: struct kvm_s390_interrupt (in)
2201	Returns: 0 on success, -1 on error
2202	
2203	Allows to inject an interrupt to the guest. Interrupts can be floating
2204	(vm ioctl) or per cpu (vcpu ioctl), depending on the interrupt type.
2205	
2206	Interrupt parameters are passed via kvm_s390_interrupt:
2207	
2208	struct kvm_s390_interrupt {
2209		__u32 type;
2210		__u32 parm;
2211		__u64 parm64;
2212	};
2213	
2214	type can be one of the following:
2215	
2216	KVM_S390_SIGP_STOP (vcpu) - sigp restart
2217	KVM_S390_PROGRAM_INT (vcpu) - program check; code in parm
2218	KVM_S390_SIGP_SET_PREFIX (vcpu) - sigp set prefix; prefix address in parm
2219	KVM_S390_RESTART (vcpu) - restart
2220	KVM_S390_INT_CLOCK_COMP (vcpu) - clock comparator interrupt
2221	KVM_S390_INT_CPU_TIMER (vcpu) - CPU timer interrupt
2222	KVM_S390_INT_VIRTIO (vm) - virtio external interrupt; external interrupt
2223				   parameters in parm and parm64
2224	KVM_S390_INT_SERVICE (vm) - sclp external interrupt; sclp parameter in parm
2225	KVM_S390_INT_EMERGENCY (vcpu) - sigp emergency; source cpu in parm
2226	KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm
2227	KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) - compound value to indicate an
2228	    I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel);
2229	    I/O interruption parameters in parm (subchannel) and parm64 (intparm,
2230	    interruption subclass)
2231	KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm,
2232	                           machine check interrupt code in parm64 (note that
2233	                           machine checks needing further payload are not
2234	                           supported by this ioctl)
2235	
2236	Note that the vcpu ioctl is asynchronous to vcpu execution.
2237	
2238	4.78 KVM_PPC_GET_HTAB_FD
2239	
2240	Capability: KVM_CAP_PPC_HTAB_FD
2241	Architectures: powerpc
2242	Type: vm ioctl
2243	Parameters: Pointer to struct kvm_get_htab_fd (in)
2244	Returns: file descriptor number (>= 0) on success, -1 on error
2245	
2246	This returns a file descriptor that can be used either to read out the
2247	entries in the guest's hashed page table (HPT), or to write entries to
2248	initialize the HPT.  The returned fd can only be written to if the
2249	KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and
2250	can only be read if that bit is clear.  The argument struct looks like
2251	this:
2252	
2253	/* For KVM_PPC_GET_HTAB_FD */
2254	struct kvm_get_htab_fd {
2255		__u64	flags;
2256		__u64	start_index;
2257		__u64	reserved[2];
2258	};
2259	
2260	/* Values for kvm_get_htab_fd.flags */
2261	#define KVM_GET_HTAB_BOLTED_ONLY	((__u64)0x1)
2262	#define KVM_GET_HTAB_WRITE		((__u64)0x2)
2263	
2264	The `start_index' field gives the index in the HPT of the entry at
2265	which to start reading.  It is ignored when writing.
2266	
2267	Reads on the fd will initially supply information about all
2268	"interesting" HPT entries.  Interesting entries are those with the
2269	bolted bit set, if the KVM_GET_HTAB_BOLTED_ONLY bit is set, otherwise
2270	all entries.  When the end of the HPT is reached, the read() will
2271	return.  If read() is called again on the fd, it will start again from
2272	the beginning of the HPT, but will only return HPT entries that have
2273	changed since they were last read.
2274	
2275	Data read or written is structured as a header (8 bytes) followed by a
2276	series of valid HPT entries (16 bytes) each.  The header indicates how
2277	many valid HPT entries there are and how many invalid entries follow
2278	the valid entries.  The invalid entries are not represented explicitly
2279	in the stream.  The header format is:
2280	
2281	struct kvm_get_htab_header {
2282		__u32	index;
2283		__u16	n_valid;
2284		__u16	n_invalid;
2285	};
2286	
2287	Writes to the fd create HPT entries starting at the index given in the
2288	header; first `n_valid' valid entries with contents from the data
2289	written, then `n_invalid' invalid entries, invalidating any previously
2290	valid entries found.
2291	
2292	4.79 KVM_CREATE_DEVICE
2293	
2294	Capability: KVM_CAP_DEVICE_CTRL
2295	Type: vm ioctl
2296	Parameters: struct kvm_create_device (in/out)
2297	Returns: 0 on success, -1 on error
2298	Errors:
2299	  ENODEV: The device type is unknown or unsupported
2300	  EEXIST: Device already created, and this type of device may not
2301	          be instantiated multiple times
2302	
2303	  Other error conditions may be defined by individual device types or
2304	  have their standard meanings.
2305	
2306	Creates an emulated device in the kernel.  The file descriptor returned
2307	in fd can be used with KVM_SET/GET/HAS_DEVICE_ATTR.
2308	
2309	If the KVM_CREATE_DEVICE_TEST flag is set, only test whether the
2310	device type is supported (not necessarily whether it can be created
2311	in the current vm).
2312	
2313	Individual devices should not define flags.  Attributes should be used
2314	for specifying any behavior that is not implied by the device type
2315	number.
2316	
2317	struct kvm_create_device {
2318		__u32	type;	/* in: KVM_DEV_TYPE_xxx */
2319		__u32	fd;	/* out: device handle */
2320		__u32	flags;	/* in: KVM_CREATE_DEVICE_xxx */
2321	};
2322	
2323	4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR
2324	
2325	Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device
2326	Type: device ioctl, vm ioctl
2327	Parameters: struct kvm_device_attr
2328	Returns: 0 on success, -1 on error
2329	Errors:
2330	  ENXIO:  The group or attribute is unknown/unsupported for this device
2331	  EPERM:  The attribute cannot (currently) be accessed this way
2332	          (e.g. read-only attribute, or attribute that only makes
2333	          sense when the device is in a different state)
2334	
2335	  Other error conditions may be defined by individual device types.
2336	
2337	Gets/sets a specified piece of device configuration and/or state.  The
2338	semantics are device-specific.  See individual device documentation in
2339	the "devices" directory.  As with ONE_REG, the size of the data
2340	transferred is defined by the particular attribute.
2341	
2342	struct kvm_device_attr {
2343		__u32	flags;		/* no flags currently defined */
2344		__u32	group;		/* device-defined */
2345		__u64	attr;		/* group-defined */
2346		__u64	addr;		/* userspace address of attr data */
2347	};
2348	
2349	4.81 KVM_HAS_DEVICE_ATTR
2350	
2351	Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device
2352	Type: device ioctl, vm ioctl
2353	Parameters: struct kvm_device_attr
2354	Returns: 0 on success, -1 on error
2355	Errors:
2356	  ENXIO:  The group or attribute is unknown/unsupported for this device
2357	
2358	Tests whether a device supports a particular attribute.  A successful
2359	return indicates the attribute is implemented.  It does not necessarily
2360	indicate that the attribute can be read or written in the device's
2361	current state.  "addr" is ignored.
2362	
2363	4.82 KVM_ARM_VCPU_INIT
2364	
2365	Capability: basic
2366	Architectures: arm, arm64
2367	Type: vcpu ioctl
2368	Parameters: struct kvm_vcpu_init (in)
2369	Returns: 0 on success; -1 on error
2370	Errors:
2371	  EINVAL:    the target is unknown, or the combination of features is invalid.
2372	  ENOENT:    a features bit specified is unknown.
2373	
2374	This tells KVM what type of CPU to present to the guest, and what
2375	optional features it should have.  This will cause a reset of the cpu
2376	registers to their initial values.  If this is not called, KVM_RUN will
2377	return ENOEXEC for that vcpu.
2378	
2379	Note that because some registers reflect machine topology, all vcpus
2380	should be created before this ioctl is invoked.
2381	
2382	Possible features:
2383		- KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state.
2384		  Depends on KVM_CAP_ARM_PSCI.
2385		- KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
2386		  Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
2387		- KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 for the CPU.
2388		  Depends on KVM_CAP_ARM_PSCI_0_2.
2389	
2390	
2391	4.83 KVM_ARM_PREFERRED_TARGET
2392	
2393	Capability: basic
2394	Architectures: arm, arm64
2395	Type: vm ioctl
2396	Parameters: struct struct kvm_vcpu_init (out)
2397	Returns: 0 on success; -1 on error
2398	Errors:
2399	  ENODEV:    no preferred target available for the host
2400	
2401	This queries KVM for preferred CPU target type which can be emulated
2402	by KVM on underlying host.
2403	
2404	The ioctl returns struct kvm_vcpu_init instance containing information
2405	about preferred CPU target type and recommended features for it.  The
2406	kvm_vcpu_init->features bitmap returned will have feature bits set if
2407	the preferred target recommends setting these features, but this is
2408	not mandatory.
2409	
2410	The information returned by this ioctl can be used to prepare an instance
2411	of struct kvm_vcpu_init for KVM_ARM_VCPU_INIT ioctl which will result in
2412	in VCPU matching underlying host.
2413	
2414	
2415	4.84 KVM_GET_REG_LIST
2416	
2417	Capability: basic
2418	Architectures: arm, arm64
2419	Type: vcpu ioctl
2420	Parameters: struct kvm_reg_list (in/out)
2421	Returns: 0 on success; -1 on error
2422	Errors:
2423	  E2BIG:     the reg index list is too big to fit in the array specified by
2424	             the user (the number required will be written into n).
2425	
2426	struct kvm_reg_list {
2427		__u64 n; /* number of registers in reg[] */
2428		__u64 reg[0];
2429	};
2430	
2431	This ioctl returns the guest registers that are supported for the
2432	KVM_GET_ONE_REG/KVM_SET_ONE_REG calls.
2433	
2434	
2435	4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated)
2436	
2437	Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
2438	Architectures: arm, arm64
2439	Type: vm ioctl
2440	Parameters: struct kvm_arm_device_address (in)
2441	Returns: 0 on success, -1 on error
2442	Errors:
2443	  ENODEV: The device id is unknown
2444	  ENXIO:  Device not supported on current system
2445	  EEXIST: Address already set
2446	  E2BIG:  Address outside guest physical address space
2447	  EBUSY:  Address overlaps with other device range
2448	
2449	struct kvm_arm_device_addr {
2450		__u64 id;
2451		__u64 addr;
2452	};
2453	
2454	Specify a device address in the guest's physical address space where guests
2455	can access emulated or directly exposed devices, which the host kernel needs
2456	to know about. The id field is an architecture specific identifier for a
2457	specific device.
2458	
2459	ARM/arm64 divides the id field into two parts, a device id and an
2460	address type id specific to the individual device.
2461	
2462	  bits:  | 63        ...       32 | 31    ...    16 | 15    ...    0 |
2463	  field: |        0x00000000      |     device id   |  addr type id  |
2464	
2465	ARM/arm64 currently only require this when using the in-kernel GIC
2466	support for the hardware VGIC features, using KVM_ARM_DEVICE_VGIC_V2
2467	as the device id.  When setting the base address for the guest's
2468	mapping of the VGIC virtual CPU and distributor interface, the ioctl
2469	must be called after calling KVM_CREATE_IRQCHIP, but before calling
2470	KVM_RUN on any of the VCPUs.  Calling this ioctl twice for any of the
2471	base addresses will return -EEXIST.
2472	
2473	Note, this IOCTL is deprecated and the more flexible SET/GET_DEVICE_ATTR API
2474	should be used instead.
2475	
2476	
2477	4.86 KVM_PPC_RTAS_DEFINE_TOKEN
2478	
2479	Capability: KVM_CAP_PPC_RTAS
2480	Architectures: ppc
2481	Type: vm ioctl
2482	Parameters: struct kvm_rtas_token_args
2483	Returns: 0 on success, -1 on error
2484	
2485	Defines a token value for a RTAS (Run Time Abstraction Services)
2486	service in order to allow it to be handled in the kernel.  The
2487	argument struct gives the name of the service, which must be the name
2488	of a service that has a kernel-side implementation.  If the token
2489	value is non-zero, it will be associated with that service, and
2490	subsequent RTAS calls by the guest specifying that token will be
2491	handled by the kernel.  If the token value is 0, then any token
2492	associated with the service will be forgotten, and subsequent RTAS
2493	calls by the guest for that service will be passed to userspace to be
2494	handled.
2495	
2496	
2497	5. The kvm_run structure
2498	------------------------
2499	
2500	Application code obtains a pointer to the kvm_run structure by
2501	mmap()ing a vcpu fd.  From that point, application code can control
2502	execution by changing fields in kvm_run prior to calling the KVM_RUN
2503	ioctl, and obtain information about the reason KVM_RUN returned by
2504	looking up structure members.
2505	
2506	struct kvm_run {
2507		/* in */
2508		__u8 request_interrupt_window;
2509	
2510	Request that KVM_RUN return when it becomes possible to inject external
2511	interrupts into the guest.  Useful in conjunction with KVM_INTERRUPT.
2512	
2513		__u8 padding1[7];
2514	
2515		/* out */
2516		__u32 exit_reason;
2517	
2518	When KVM_RUN has returned successfully (return value 0), this informs
2519	application code why KVM_RUN has returned.  Allowable values for this
2520	field are detailed below.
2521	
2522		__u8 ready_for_interrupt_injection;
2523	
2524	If request_interrupt_window has been specified, this field indicates
2525	an interrupt can be injected now with KVM_INTERRUPT.
2526	
2527		__u8 if_flag;
2528	
2529	The value of the current interrupt flag.  Only valid if in-kernel
2530	local APIC is not used.
2531	
2532		__u8 padding2[2];
2533	
2534		/* in (pre_kvm_run), out (post_kvm_run) */
2535		__u64 cr8;
2536	
2537	The value of the cr8 register.  Only valid if in-kernel local APIC is
2538	not used.  Both input and output.
2539	
2540		__u64 apic_base;
2541	
2542	The value of the APIC BASE msr.  Only valid if in-kernel local
2543	APIC is not used.  Both input and output.
2544	
2545		union {
2546			/* KVM_EXIT_UNKNOWN */
2547			struct {
2548				__u64 hardware_exit_reason;
2549			} hw;
2550	
2551	If exit_reason is KVM_EXIT_UNKNOWN, the vcpu has exited due to unknown
2552	reasons.  Further architecture-specific information is available in
2553	hardware_exit_reason.
2554	
2555			/* KVM_EXIT_FAIL_ENTRY */
2556			struct {
2557				__u64 hardware_entry_failure_reason;
2558			} fail_entry;
2559	
2560	If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due
2561	to unknown reasons.  Further architecture-specific information is
2562	available in hardware_entry_failure_reason.
2563	
2564			/* KVM_EXIT_EXCEPTION */
2565			struct {
2566				__u32 exception;
2567				__u32 error_code;
2568			} ex;
2569	
2570	Unused.
2571	
2572			/* KVM_EXIT_IO */
2573			struct {
2574	#define KVM_EXIT_IO_IN  0
2575	#define KVM_EXIT_IO_OUT 1
2576				__u8 direction;
2577				__u8 size; /* bytes */
2578				__u16 port;
2579				__u32 count;
2580				__u64 data_offset; /* relative to kvm_run start */
2581			} io;
2582	
2583	If exit_reason is KVM_EXIT_IO, then the vcpu has
2584	executed a port I/O instruction which could not be satisfied by kvm.
2585	data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
2586	where kvm expects application code to place the data for the next
2587	KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a packed array.
2588	
2589			struct {
2590				struct kvm_debug_exit_arch arch;
2591			} debug;
2592	
2593	Unused.
2594	
2595			/* KVM_EXIT_MMIO */
2596			struct {
2597				__u64 phys_addr;
2598				__u8  data[8];
2599				__u32 len;
2600				__u8  is_write;
2601			} mmio;
2602	
2603	If exit_reason is KVM_EXIT_MMIO, then the vcpu has
2604	executed a memory-mapped I/O instruction which could not be satisfied
2605	by kvm.  The 'data' member contains the written data if 'is_write' is
2606	true, and should be filled by application code otherwise.
2607	
2608	The 'data' member contains, in its first 'len' bytes, the value as it would
2609	appear if the VCPU performed a load or store of the appropriate width directly
2610	to the byte array.
2611	
2612	NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_DCR,
2613	      KVM_EXIT_PAPR and KVM_EXIT_EPR the corresponding
2614	operations are complete (and guest state is consistent) only after userspace
2615	has re-entered the kernel with KVM_RUN.  The kernel side will first finish
2616	incomplete operations and then check for pending signals.  Userspace
2617	can re-enter the guest with an unmasked signal pending to complete
2618	pending operations.
2619	
2620			/* KVM_EXIT_HYPERCALL */
2621			struct {
2622				__u64 nr;
2623				__u64 args[6];
2624				__u64 ret;
2625				__u32 longmode;
2626				__u32 pad;
2627			} hypercall;
2628	
2629	Unused.  This was once used for 'hypercall to userspace'.  To implement
2630	such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO (all except s390).
2631	Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO.
2632	
2633			/* KVM_EXIT_TPR_ACCESS */
2634			struct {
2635				__u64 rip;
2636				__u32 is_write;
2637				__u32 pad;
2638			} tpr_access;
2639	
2640	To be documented (KVM_TPR_ACCESS_REPORTING).
2641	
2642			/* KVM_EXIT_S390_SIEIC */
2643			struct {
2644				__u8 icptcode;
2645				__u64 mask; /* psw upper half */
2646				__u64 addr; /* psw lower half */
2647				__u16 ipa;
2648				__u32 ipb;
2649			} s390_sieic;
2650	
2651	s390 specific.
2652	
2653			/* KVM_EXIT_S390_RESET */
2654	#define KVM_S390_RESET_POR       1
2655	#define KVM_S390_RESET_CLEAR     2
2656	#define KVM_S390_RESET_SUBSYSTEM 4
2657	#define KVM_S390_RESET_CPU_INIT  8
2658	#define KVM_S390_RESET_IPL       16
2659			__u64 s390_reset_flags;
2660	
2661	s390 specific.
2662	
2663			/* KVM_EXIT_S390_UCONTROL */
2664			struct {
2665				__u64 trans_exc_code;
2666				__u32 pgm_code;
2667			} s390_ucontrol;
2668	
2669	s390 specific. A page fault has occurred for a user controlled virtual
2670	machine (KVM_VM_S390_UNCONTROL) on it's host page table that cannot be
2671	resolved by the kernel.
2672	The program code and the translation exception code that were placed
2673	in the cpu's lowcore are presented here as defined by the z Architecture
2674	Principles of Operation Book in the Chapter for Dynamic Address Translation
2675	(DAT)
2676	
2677			/* KVM_EXIT_DCR */
2678			struct {
2679				__u32 dcrn;
2680				__u32 data;
2681				__u8  is_write;
2682			} dcr;
2683	
2684	powerpc specific.
2685	
2686			/* KVM_EXIT_OSI */
2687			struct {
2688				__u64 gprs[32];
2689			} osi;
2690	
2691	MOL uses a special hypercall interface it calls 'OSI'. To enable it, we catch
2692	hypercalls and exit with this exit struct that contains all the guest gprs.
2693	
2694	If exit_reason is KVM_EXIT_OSI, then the vcpu has triggered such a hypercall.
2695	Userspace can now handle the hypercall and when it's done modify the gprs as
2696	necessary. Upon guest entry all guest GPRs will then be replaced by the values
2697	in this struct.
2698	
2699			/* KVM_EXIT_PAPR_HCALL */
2700			struct {
2701				__u64 nr;
2702				__u64 ret;
2703				__u64 args[9];
2704			} papr_hcall;
2705	
2706	This is used on 64-bit PowerPC when emulating a pSeries partition,
2707	e.g. with the 'pseries' machine type in qemu.  It occurs when the
2708	guest does a hypercall using the 'sc 1' instruction.  The 'nr' field
2709	contains the hypercall number (from the guest R3), and 'args' contains
2710	the arguments (from the guest R4 - R12).  Userspace should put the
2711	return code in 'ret' and any extra returned values in args[].
2712	The possible hypercalls are defined in the Power Architecture Platform
2713	Requirements (PAPR) document available from www.power.org (free
2714	developer registration required to access it).
2715	
2716			/* KVM_EXIT_S390_TSCH */
2717			struct {
2718				__u16 subchannel_id;
2719				__u16 subchannel_nr;
2720				__u32 io_int_parm;
2721				__u32 io_int_word;
2722				__u32 ipb;
2723				__u8 dequeued;
2724			} s390_tsch;
2725	
2726	s390 specific. This exit occurs when KVM_CAP_S390_CSS_SUPPORT has been enabled
2727	and TEST SUBCHANNEL was intercepted. If dequeued is set, a pending I/O
2728	interrupt for the target subchannel has been dequeued and subchannel_id,
2729	subchannel_nr, io_int_parm and io_int_word contain the parameters for that
2730	interrupt. ipb is needed for instruction parameter decoding.
2731	
2732			/* KVM_EXIT_EPR */
2733			struct {
2734				__u32 epr;
2735			} epr;
2736	
2737	On FSL BookE PowerPC chips, the interrupt controller has a fast patch
2738	interrupt acknowledge path to the core. When the core successfully
2739	delivers an interrupt, it automatically populates the EPR register with
2740	the interrupt vector number and acknowledges the interrupt inside
2741	the interrupt controller.
2742	
2743	In case the interrupt controller lives in user space, we need to do
2744	the interrupt acknowledge cycle through it to fetch the next to be
2745	delivered interrupt vector using this exit.
2746	
2747	It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an
2748	external interrupt has just been delivered into the guest. User space
2749	should put the acknowledged interrupt vector into the 'epr' field.
2750	
2751			/* KVM_EXIT_SYSTEM_EVENT */
2752			struct {
2753	#define KVM_SYSTEM_EVENT_SHUTDOWN       1
2754	#define KVM_SYSTEM_EVENT_RESET          2
2755				__u32 type;
2756				__u64 flags;
2757			} system_event;
2758	
2759	If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered
2760	a system-level event using some architecture specific mechanism (hypercall
2761	or some special instruction). In case of ARM/ARM64, this is triggered using
2762	HVC instruction based PSCI call from the vcpu. The 'type' field describes
2763	the system-level event type. The 'flags' field describes architecture
2764	specific flags for the system-level event.
2765	
2766			/* Fix the size of the union. */
2767			char padding[256];
2768		};
2769	
2770		/*
2771		 * shared registers between kvm and userspace.
2772		 * kvm_valid_regs specifies the register classes set by the host
2773		 * kvm_dirty_regs specified the register classes dirtied by userspace
2774		 * struct kvm_sync_regs is architecture specific, as well as the
2775		 * bits for kvm_valid_regs and kvm_dirty_regs
2776		 */
2777		__u64 kvm_valid_regs;
2778		__u64 kvm_dirty_regs;
2779		union {
2780			struct kvm_sync_regs regs;
2781			char padding[1024];
2782		} s;
2783	
2784	If KVM_CAP_SYNC_REGS is defined, these fields allow userspace to access
2785	certain guest registers without having to call SET/GET_*REGS. Thus we can
2786	avoid some system call overhead if userspace has to handle the exit.
2787	Userspace can query the validity of the structure by checking
2788	kvm_valid_regs for specific bits. These bits are architecture specific
2789	and usually define the validity of a groups of registers. (e.g. one bit
2790	 for general purpose registers)
2791	
2792	};
2793	
2794	
2795	4.81 KVM_GET_EMULATED_CPUID
2796	
2797	Capability: KVM_CAP_EXT_EMUL_CPUID
2798	Architectures: x86
2799	Type: system ioctl
2800	Parameters: struct kvm_cpuid2 (in/out)
2801	Returns: 0 on success, -1 on error
2802	
2803	struct kvm_cpuid2 {
2804		__u32 nent;
2805		__u32 flags;
2806		struct kvm_cpuid_entry2 entries[0];
2807	};
2808	
2809	The member 'flags' is used for passing flags from userspace.
2810	
2811	#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
2812	#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
2813	#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
2814	
2815	struct kvm_cpuid_entry2 {
2816		__u32 function;
2817		__u32 index;
2818		__u32 flags;
2819		__u32 eax;
2820		__u32 ebx;
2821		__u32 ecx;
2822		__u32 edx;
2823		__u32 padding[3];
2824	};
2825	
2826	This ioctl returns x86 cpuid features which are emulated by
2827	kvm.Userspace can use the information returned by this ioctl to query
2828	which features are emulated by kvm instead of being present natively.
2829	
2830	Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2
2831	structure with the 'nent' field indicating the number of entries in
2832	the variable-size array 'entries'. If the number of entries is too low
2833	to describe the cpu capabilities, an error (E2BIG) is returned. If the
2834	number is too high, the 'nent' field is adjusted and an error (ENOMEM)
2835	is returned. If the number is just right, the 'nent' field is adjusted
2836	to the number of valid entries in the 'entries' array, which is then
2837	filled.
2838	
2839	The entries returned are the set CPUID bits of the respective features
2840	which kvm emulates, as returned by the CPUID instruction, with unknown
2841	or unsupported feature bits cleared.
2842	
2843	Features like x2apic, for example, may not be present in the host cpu
2844	but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be
2845	emulated efficiently and thus not included here.
2846	
2847	The fields in each entry are defined as follows:
2848	
2849	  function: the eax value used to obtain the entry
2850	  index: the ecx value used to obtain the entry (for entries that are
2851	         affected by ecx)
2852	  flags: an OR of zero or more of the following:
2853	        KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
2854	           if the index field is valid
2855	        KVM_CPUID_FLAG_STATEFUL_FUNC:
2856	           if cpuid for this function returns different values for successive
2857	           invocations; there will be several entries with the same function,
2858	           all with this flag set
2859	        KVM_CPUID_FLAG_STATE_READ_NEXT:
2860	           for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
2861	           the first entry to be read by a cpu
2862	   eax, ebx, ecx, edx: the values returned by the cpuid instruction for
2863	         this function/index combination
2864	
2865	
2866	6. Capabilities that can be enabled
2867	-----------------------------------
2868	
2869	There are certain capabilities that change the behavior of the virtual CPU when
2870	enabled. To enable them, please see section 4.37. Below you can find a list of
2871	capabilities and what their effect on the vCPU is when enabling them.
2872	
2873	The following information is provided along with the description:
2874	
2875	  Architectures: which instruction set architectures provide this ioctl.
2876	      x86 includes both i386 and x86_64.
2877	
2878	  Parameters: what parameters are accepted by the capability.
2879	
2880	  Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
2881	      are not detailed, but errors with specific meanings are.
2882	
2883	
2884	6.1 KVM_CAP_PPC_OSI
2885	
2886	Architectures: ppc
2887	Parameters: none
2888	Returns: 0 on success; -1 on error
2889	
2890	This capability enables interception of OSI hypercalls that otherwise would
2891	be treated as normal system calls to be injected into the guest. OSI hypercalls
2892	were invented by Mac-on-Linux to have a standardized communication mechanism
2893	between the guest and the host.
2894	
2895	When this capability is enabled, KVM_EXIT_OSI can occur.
2896	
2897	
2898	6.2 KVM_CAP_PPC_PAPR
2899	
2900	Architectures: ppc
2901	Parameters: none
2902	Returns: 0 on success; -1 on error
2903	
2904	This capability enables interception of PAPR hypercalls. PAPR hypercalls are
2905	done using the hypercall instruction "sc 1".
2906	
2907	It also sets the guest privilege level to "supervisor" mode. Usually the guest
2908	runs in "hypervisor" privilege mode with a few missing features.
2909	
2910	In addition to the above, it changes the semantics of SDR1. In this mode, the
2911	HTAB address part of SDR1 contains an HVA instead of a GPA, as PAPR keeps the
2912	HTAB invisible to the guest.
2913	
2914	When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur.
2915	
2916	
2917	6.3 KVM_CAP_SW_TLB
2918	
2919	Architectures: ppc
2920	Parameters: args[0] is the address of a struct kvm_config_tlb
2921	Returns: 0 on success; -1 on error
2922	
2923	struct kvm_config_tlb {
2924		__u64 params;
2925		__u64 array;
2926		__u32 mmu_type;
2927		__u32 array_len;
2928	};
2929	
2930	Configures the virtual CPU's TLB array, establishing a shared memory area
2931	between userspace and KVM.  The "params" and "array" fields are userspace
2932	addresses of mmu-type-specific data structures.  The "array_len" field is an
2933	safety mechanism, and should be set to the size in bytes of the memory that
2934	userspace has reserved for the array.  It must be at least the size dictated
2935	by "mmu_type" and "params".
2936	
2937	While KVM_RUN is active, the shared region is under control of KVM.  Its
2938	contents are undefined, and any modification by userspace results in
2939	boundedly undefined behavior.
2940	
2941	On return from KVM_RUN, the shared region will reflect the current state of
2942	the guest's TLB.  If userspace makes any changes, it must call KVM_DIRTY_TLB
2943	to tell KVM which entries have been changed, prior to calling KVM_RUN again
2944	on this vcpu.
2945	
2946	For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
2947	 - The "params" field is of type "struct kvm_book3e_206_tlb_params".
2948	 - The "array" field points to an array of type "struct
2949	   kvm_book3e_206_tlb_entry".
2950	 - The array consists of all entries in the first TLB, followed by all
2951	   entries in the second TLB.
2952	 - Within a TLB, entries are ordered first by increasing set number.  Within a
2953	   set, entries are ordered by way (increasing ESEL).
2954	 - The hash for determining set number in TLB0 is: (MAS2 >> 12) & (num_sets - 1)
2955	   where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value.
2956	 - The tsize field of mas1 shall be set to 4K on TLB0, even though the
2957	   hardware ignores this value for TLB0.
2958	
2959	6.4 KVM_CAP_S390_CSS_SUPPORT
2960	
2961	Architectures: s390
2962	Parameters: none
2963	Returns: 0 on success; -1 on error
2964	
2965	This capability enables support for handling of channel I/O instructions.
2966	
2967	TEST PENDING INTERRUPTION and the interrupt portion of TEST SUBCHANNEL are
2968	handled in-kernel, while the other I/O instructions are passed to userspace.
2969	
2970	When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST
2971	SUBCHANNEL intercepts.
2972	
2973	6.5 KVM_CAP_PPC_EPR
2974	
2975	Architectures: ppc
2976	Parameters: args[0] defines whether the proxy facility is active
2977	Returns: 0 on success; -1 on error
2978	
2979	This capability enables or disables the delivery of interrupts through the
2980	external proxy facility.
2981	
2982	When enabled (args[0] != 0), every time the guest gets an external interrupt
2983	delivered, it automatically exits into user space with a KVM_EXIT_EPR exit
2984	to receive the topmost interrupt vector.
2985	
2986	When disabled (args[0] == 0), behavior is as if this facility is unsupported.
2987	
2988	When this capability is enabled, KVM_EXIT_EPR can occur.
2989	
2990	6.6 KVM_CAP_IRQ_MPIC
2991	
2992	Architectures: ppc
2993	Parameters: args[0] is the MPIC device fd
2994	            args[1] is the MPIC CPU number for this vcpu
2995	
2996	This capability connects the vcpu to an in-kernel MPIC device.
2997	
2998	6.7 KVM_CAP_IRQ_XICS
2999	
3000	Architectures: ppc
3001	Parameters: args[0] is the XICS device fd
3002	            args[1] is the XICS CPU number (server ID) for this vcpu
3003	
3004	This capability connects the vcpu to an in-kernel XICS device.
Hide Line Numbers
About Kernel Documentation Linux Kernel Contact Linux Resources Linux Blog

Information is copyright its respective author. All material is available from the Linux Kernel Source distributed under a GPL License. This page is provided as a free service by mjmwired.net.