1 .. SPDX-License-Identifier: GPL-2.0 1 .. SPDX-License-Identifier: GPL-2.0
2 2
3 ============================================== 3 ===================================================================
4 The Definitive KVM (Kernel-based Virtual Machi 4 The Definitive KVM (Kernel-based Virtual Machine) API Documentation
5 ============================================== 5 ===================================================================
6 6
7 1. General description 7 1. General description
8 ====================== 8 ======================
9 9
10 The kvm API is a set of ioctls that are issued 10 The kvm API is a set of ioctls that are issued to control various aspects
11 of a virtual machine. The ioctls belong to th 11 of a virtual machine. The ioctls belong to the following classes:
12 12
13 - System ioctls: These query and set global a 13 - System ioctls: These query and set global attributes which affect the
14 whole kvm subsystem. In addition a system 14 whole kvm subsystem. In addition a system ioctl is used to create
15 virtual machines. 15 virtual machines.
16 16
17 - VM ioctls: These query and set attributes t 17 - VM ioctls: These query and set attributes that affect an entire virtual
18 machine, for example memory layout. In add 18 machine, for example memory layout. In addition a VM ioctl is used to
19 create virtual cpus (vcpus) and devices. 19 create virtual cpus (vcpus) and devices.
20 20
21 VM ioctls must be issued from the same proc 21 VM ioctls must be issued from the same process (address space) that was
22 used to create the VM. 22 used to create the VM.
23 23
24 - vcpu ioctls: These query and set attributes 24 - vcpu ioctls: These query and set attributes that control the operation
25 of a single virtual cpu. 25 of a single virtual cpu.
26 26
27 vcpu ioctls should be issued from the same 27 vcpu ioctls should be issued from the same thread that was used to create
28 the vcpu, except for asynchronous vcpu ioct 28 the vcpu, except for asynchronous vcpu ioctl that are marked as such in
29 the documentation. Otherwise, the first io 29 the documentation. Otherwise, the first ioctl after switching threads
30 could see a performance impact. 30 could see a performance impact.
31 31
32 - device ioctls: These query and set attribut 32 - device ioctls: These query and set attributes that control the operation
33 of a single device. 33 of a single device.
34 34
35 device ioctls must be issued from the same 35 device ioctls must be issued from the same process (address space) that
36 was used to create the VM. 36 was used to create the VM.
37 37
38 2. File descriptors 38 2. File descriptors
39 =================== 39 ===================
40 40
41 The kvm API is centered around file descriptor 41 The kvm API is centered around file descriptors. An initial
42 open("/dev/kvm") obtains a handle to the kvm s 42 open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
43 can be used to issue system ioctls. A KVM_CRE 43 can be used to issue system ioctls. A KVM_CREATE_VM ioctl on this
44 handle will create a VM file descriptor which 44 handle will create a VM file descriptor which can be used to issue VM
45 ioctls. A KVM_CREATE_VCPU or KVM_CREATE_DEVIC 45 ioctls. A KVM_CREATE_VCPU or KVM_CREATE_DEVICE ioctl on a VM fd will
46 create a virtual cpu or device and return a fi 46 create a virtual cpu or device and return a file descriptor pointing to
47 the new resource. Finally, ioctls on a vcpu o 47 the new resource. Finally, ioctls on a vcpu or device fd can be used
48 to control the vcpu or device. For vcpus, thi 48 to control the vcpu or device. For vcpus, this includes the important
49 task of actually running guest code. 49 task of actually running guest code.
50 50
51 In general file descriptors can be migrated am 51 In general file descriptors can be migrated among processes by means
52 of fork() and the SCM_RIGHTS facility of unix 52 of fork() and the SCM_RIGHTS facility of unix domain socket. These
53 kinds of tricks are explicitly not supported b 53 kinds of tricks are explicitly not supported by kvm. While they will
54 not cause harm to the host, their actual behav 54 not cause harm to the host, their actual behavior is not guaranteed by
55 the API. See "General description" for detail 55 the API. See "General description" for details on the ioctl usage
56 model that is supported by KVM. 56 model that is supported by KVM.
57 57
58 It is important to note that although VM ioctl 58 It is important to note that although VM ioctls may only be issued from
59 the process that created the VM, a VM's lifecy 59 the process that created the VM, a VM's lifecycle is associated with its
60 file descriptor, not its creator (process). I 60 file descriptor, not its creator (process). In other words, the VM and
61 its resources, *including the associated addre 61 its resources, *including the associated address space*, are not freed
62 until the last reference to the VM's file desc 62 until the last reference to the VM's file descriptor has been released.
63 For example, if fork() is issued after ioctl(K 63 For example, if fork() is issued after ioctl(KVM_CREATE_VM), the VM will
64 not be freed until both the parent (original) 64 not be freed until both the parent (original) process and its child have
65 put their references to the VM's file descript 65 put their references to the VM's file descriptor.
66 66
67 Because a VM's resources are not freed until t 67 Because a VM's resources are not freed until the last reference to its
68 file descriptor is released, creating addition 68 file descriptor is released, creating additional references to a VM
69 via fork(), dup(), etc... without careful cons 69 via fork(), dup(), etc... without careful consideration is strongly
70 discouraged and may have unwanted side effects 70 discouraged and may have unwanted side effects, e.g. memory allocated
71 by and on behalf of the VM's process may not b 71 by and on behalf of the VM's process may not be freed/unaccounted when
72 the VM is shut down. 72 the VM is shut down.
73 73
74 74
75 3. Extensions 75 3. Extensions
76 ============= 76 =============
77 77
78 As of Linux 2.6.22, the KVM ABI has been stabi 78 As of Linux 2.6.22, the KVM ABI has been stabilized: no backward
79 incompatible change are allowed. However, the 79 incompatible change are allowed. However, there is an extension
80 facility that allows backward-compatible exten 80 facility that allows backward-compatible extensions to the API to be
81 queried and used. 81 queried and used.
82 82
83 The extension mechanism is not based on the Li 83 The extension mechanism is not based on the Linux version number.
84 Instead, kvm defines extension identifiers and 84 Instead, kvm defines extension identifiers and a facility to query
85 whether a particular extension identifier is a 85 whether a particular extension identifier is available. If it is, a
86 set of ioctls is available for application use 86 set of ioctls is available for application use.
87 87
88 88
89 4. API description 89 4. API description
90 ================== 90 ==================
91 91
92 This section describes ioctls that can be used 92 This section describes ioctls that can be used to control kvm guests.
93 For each ioctl, the following information is p 93 For each ioctl, the following information is provided along with a
94 description: 94 description:
95 95
96 Capability: 96 Capability:
97 which KVM extension provides this ioctl. 97 which KVM extension provides this ioctl. Can be 'basic',
98 which means that is will be provided by 98 which means that is will be provided by any kernel that supports
99 API version 12 (see section 4.1), a KVM_ 99 API version 12 (see section 4.1), a KVM_CAP_xyz constant, which
100 means availability needs to be checked w 100 means availability needs to be checked with KVM_CHECK_EXTENSION
101 (see section 4.4), or 'none' which means 101 (see section 4.4), or 'none' which means that while not all kernels
102 support this ioctl, there's no capabilit 102 support this ioctl, there's no capability bit to check its
103 availability: for kernels that don't sup 103 availability: for kernels that don't support the ioctl,
104 the ioctl returns -ENOTTY. 104 the ioctl returns -ENOTTY.
105 105
106 Architectures: 106 Architectures:
107 which instruction set architectures prov 107 which instruction set architectures provide this ioctl.
108 x86 includes both i386 and x86_64. 108 x86 includes both i386 and x86_64.
109 109
110 Type: 110 Type:
111 system, vm, or vcpu. 111 system, vm, or vcpu.
112 112
113 Parameters: 113 Parameters:
114 what parameters are accepted by the ioct 114 what parameters are accepted by the ioctl.
115 115
116 Returns: 116 Returns:
117 the return value. General error numbers 117 the return value. General error numbers (EBADF, ENOMEM, EINVAL)
118 are not detailed, but errors with specif 118 are not detailed, but errors with specific meanings are.
119 119
120 120
121 4.1 KVM_GET_API_VERSION 121 4.1 KVM_GET_API_VERSION
122 ----------------------- 122 -----------------------
123 123
124 :Capability: basic 124 :Capability: basic
125 :Architectures: all 125 :Architectures: all
126 :Type: system ioctl 126 :Type: system ioctl
127 :Parameters: none 127 :Parameters: none
128 :Returns: the constant KVM_API_VERSION (=12) 128 :Returns: the constant KVM_API_VERSION (=12)
129 129
130 This identifies the API version as the stable 130 This identifies the API version as the stable kvm API. It is not
131 expected that this number will change. Howeve 131 expected that this number will change. However, Linux 2.6.20 and
132 2.6.21 report earlier versions; these are not 132 2.6.21 report earlier versions; these are not documented and not
133 supported. Applications should refuse to run 133 supported. Applications should refuse to run if KVM_GET_API_VERSION
134 returns a value other than 12. If this check 134 returns a value other than 12. If this check passes, all ioctls
135 described as 'basic' will be available. 135 described as 'basic' will be available.
136 136
137 137
138 4.2 KVM_CREATE_VM 138 4.2 KVM_CREATE_VM
139 ----------------- 139 -----------------
140 140
141 :Capability: basic 141 :Capability: basic
142 :Architectures: all 142 :Architectures: all
143 :Type: system ioctl 143 :Type: system ioctl
144 :Parameters: machine type identifier (KVM_VM_* 144 :Parameters: machine type identifier (KVM_VM_*)
145 :Returns: a VM fd that can be used to control 145 :Returns: a VM fd that can be used to control the new virtual machine.
146 146
147 The new VM has no virtual cpus and no memory. 147 The new VM has no virtual cpus and no memory.
148 You probably want to use 0 as machine type. 148 You probably want to use 0 as machine type.
149 149
150 X86: <<
151 ^^^^ <<
152 <<
153 Supported X86 VM types can be queried via KVM_ <<
154 <<
155 S390: <<
156 ^^^^^ <<
157 <<
158 In order to create user controlled virtual mac 150 In order to create user controlled virtual machines on S390, check
159 KVM_CAP_S390_UCONTROL and use the flag KVM_VM_ 151 KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
160 privileged user (CAP_SYS_ADMIN). 152 privileged user (CAP_SYS_ADMIN).
161 153
162 MIPS: <<
163 ^^^^^ <<
164 <<
165 To use hardware assisted virtualization on MIP <<
166 the default trap & emulate implementation (whi <<
167 memory layout to fit in user mode), check KVM_ <<
168 flag KVM_VM_MIPS_VZ. <<
169 <<
170 ARM64: <<
171 ^^^^^^ <<
172 <<
173 On arm64, the physical address size for a VM ( 154 On arm64, the physical address size for a VM (IPA Size limit) is limited
174 to 40bits by default. The limit can be configu 155 to 40bits by default. The limit can be configured if the host supports the
175 extension KVM_CAP_ARM_VM_IPA_SIZE. When suppor 156 extension KVM_CAP_ARM_VM_IPA_SIZE. When supported, use
176 KVM_VM_TYPE_ARM_IPA_SIZE(IPA_Bits) to set the 157 KVM_VM_TYPE_ARM_IPA_SIZE(IPA_Bits) to set the size in the machine type
177 identifier, where IPA_Bits is the maximum widt 158 identifier, where IPA_Bits is the maximum width of any physical
178 address used by the VM. The IPA_Bits is encode 159 address used by the VM. The IPA_Bits is encoded in bits[7-0] of the
179 machine type identifier. 160 machine type identifier.
180 161
181 e.g, to configure a guest to use 48bit physica 162 e.g, to configure a guest to use 48bit physical address size::
182 163
183 vm_fd = ioctl(dev_fd, KVM_CREATE_VM, KVM_V 164 vm_fd = ioctl(dev_fd, KVM_CREATE_VM, KVM_VM_TYPE_ARM_IPA_SIZE(48));
184 165
185 The requested size (IPA_Bits) must be: 166 The requested size (IPA_Bits) must be:
186 167
187 == ======================================== 168 == =========================================================
188 0 Implies default size, 40bits (for backwa 169 0 Implies default size, 40bits (for backward compatibility)
189 N Implies N bits, where N is a positive in 170 N Implies N bits, where N is a positive integer such that,
190 32 <= N <= Host_IPA_Limit 171 32 <= N <= Host_IPA_Limit
191 == ======================================== 172 == =========================================================
192 173
193 Host_IPA_Limit is the maximum possible value f 174 Host_IPA_Limit is the maximum possible value for IPA_Bits on the host and
194 is dependent on the CPU capability and the ker 175 is dependent on the CPU capability and the kernel configuration. The limit can
195 be retrieved using KVM_CAP_ARM_VM_IPA_SIZE of 176 be retrieved using KVM_CAP_ARM_VM_IPA_SIZE of the KVM_CHECK_EXTENSION
196 ioctl() at run-time. 177 ioctl() at run-time.
197 178
198 Creation of the VM will fail if the requested 179 Creation of the VM will fail if the requested IPA size (whether it is
199 implicit or explicit) is unsupported on the ho 180 implicit or explicit) is unsupported on the host.
200 181
201 Please note that configuring the IPA size does 182 Please note that configuring the IPA size does not affect the capability
202 exposed by the guest CPUs in ID_AA64MMFR0_EL1[ 183 exposed by the guest CPUs in ID_AA64MMFR0_EL1[PARange]. It only affects
203 size of the address translated by the stage2 l 184 size of the address translated by the stage2 level (guest physical to
204 host physical address translations). 185 host physical address translations).
205 186
206 187
207 4.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATUR 188 4.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATURE_INDEX_LIST
208 ---------------------------------------------- 189 ----------------------------------------------------------
209 190
210 :Capability: basic, KVM_CAP_GET_MSR_FEATURES f 191 :Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST
211 :Architectures: x86 192 :Architectures: x86
212 :Type: system ioctl 193 :Type: system ioctl
213 :Parameters: struct kvm_msr_list (in/out) 194 :Parameters: struct kvm_msr_list (in/out)
214 :Returns: 0 on success; -1 on error 195 :Returns: 0 on success; -1 on error
215 196
216 Errors: 197 Errors:
217 198
218 ====== ================================= 199 ====== ============================================================
219 EFAULT the msr index list cannot be read 200 EFAULT the msr index list cannot be read from or written to
220 E2BIG the msr index list is too big to 201 E2BIG the msr index list is too big to fit in the array specified by
221 the user. 202 the user.
222 ====== ================================= 203 ====== ============================================================
223 204
224 :: 205 ::
225 206
226 struct kvm_msr_list { 207 struct kvm_msr_list {
227 __u32 nmsrs; /* number of msrs in entr 208 __u32 nmsrs; /* number of msrs in entries */
228 __u32 indices[0]; 209 __u32 indices[0];
229 }; 210 };
230 211
231 The user fills in the size of the indices arra 212 The user fills in the size of the indices array in nmsrs, and in return
232 kvm adjusts nmsrs to reflect the actual number 213 kvm adjusts nmsrs to reflect the actual number of msrs and fills in the
233 indices array with their numbers. 214 indices array with their numbers.
234 215
235 KVM_GET_MSR_INDEX_LIST returns the guest msrs 216 KVM_GET_MSR_INDEX_LIST returns the guest msrs that are supported. The list
236 varies by kvm version and host processor, but 217 varies by kvm version and host processor, but does not change otherwise.
237 218
238 Note: if kvm indicates supports MCE (KVM_CAP_M 219 Note: if kvm indicates supports MCE (KVM_CAP_MCE), then the MCE bank MSRs are
239 not returned in the MSR list, as different vcp 220 not returned in the MSR list, as different vcpus can have a different number
240 of banks, as set via the KVM_X86_SETUP_MCE ioc 221 of banks, as set via the KVM_X86_SETUP_MCE ioctl.
241 222
242 KVM_GET_MSR_FEATURE_INDEX_LIST returns the lis 223 KVM_GET_MSR_FEATURE_INDEX_LIST returns the list of MSRs that can be passed
243 to the KVM_GET_MSRS system ioctl. This lets u 224 to the KVM_GET_MSRS system ioctl. This lets userspace probe host capabilities
244 and processor features that are exposed via MS 225 and processor features that are exposed via MSRs (e.g., VMX capabilities).
245 This list also varies by kvm version and host 226 This list also varies by kvm version and host processor, but does not change
246 otherwise. 227 otherwise.
247 228
248 229
249 4.4 KVM_CHECK_EXTENSION 230 4.4 KVM_CHECK_EXTENSION
250 ----------------------- 231 -----------------------
251 232
252 :Capability: basic, KVM_CAP_CHECK_EXTENSION_VM 233 :Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl
253 :Architectures: all 234 :Architectures: all
254 :Type: system ioctl, vm ioctl 235 :Type: system ioctl, vm ioctl
255 :Parameters: extension identifier (KVM_CAP_*) 236 :Parameters: extension identifier (KVM_CAP_*)
256 :Returns: 0 if unsupported; 1 (or some other p 237 :Returns: 0 if unsupported; 1 (or some other positive integer) if supported
257 238
258 The API allows the application to query about 239 The API allows the application to query about extensions to the core
259 kvm API. Userspace passes an extension identi 240 kvm API. Userspace passes an extension identifier (an integer) and
260 receives an integer that describes the extensi 241 receives an integer that describes the extension availability.
261 Generally 0 means no and 1 means yes, but some 242 Generally 0 means no and 1 means yes, but some extensions may report
262 additional information in the integer return v 243 additional information in the integer return value.
263 244
264 Based on their initialization different VMs ma 245 Based on their initialization different VMs may have different capabilities.
265 It is thus encouraged to use the vm ioctl to q 246 It is thus encouraged to use the vm ioctl to query for capabilities (available
266 with KVM_CAP_CHECK_EXTENSION_VM on the vm fd) 247 with KVM_CAP_CHECK_EXTENSION_VM on the vm fd)
267 248
268 4.5 KVM_GET_VCPU_MMAP_SIZE 249 4.5 KVM_GET_VCPU_MMAP_SIZE
269 -------------------------- 250 --------------------------
270 251
271 :Capability: basic 252 :Capability: basic
272 :Architectures: all 253 :Architectures: all
273 :Type: system ioctl 254 :Type: system ioctl
274 :Parameters: none 255 :Parameters: none
275 :Returns: size of vcpu mmap area, in bytes 256 :Returns: size of vcpu mmap area, in bytes
276 257
277 The KVM_RUN ioctl (cf.) communicates with user 258 The KVM_RUN ioctl (cf.) communicates with userspace via a shared
278 memory region. This ioctl returns the size of 259 memory region. This ioctl returns the size of that region. See the
279 KVM_RUN documentation for details. 260 KVM_RUN documentation for details.
280 261
281 Besides the size of the KVM_RUN communication 262 Besides the size of the KVM_RUN communication region, other areas of
282 the VCPU file descriptor can be mmap-ed, inclu 263 the VCPU file descriptor can be mmap-ed, including:
283 264
284 - if KVM_CAP_COALESCED_MMIO is available, a pa 265 - if KVM_CAP_COALESCED_MMIO is available, a page at
285 KVM_COALESCED_MMIO_PAGE_OFFSET * PAGE_SIZE; 266 KVM_COALESCED_MMIO_PAGE_OFFSET * PAGE_SIZE; for historical reasons,
286 this page is included in the result of KVM_G 267 this page is included in the result of KVM_GET_VCPU_MMAP_SIZE.
287 KVM_CAP_COALESCED_MMIO is not documented yet 268 KVM_CAP_COALESCED_MMIO is not documented yet.
288 269
289 - if KVM_CAP_DIRTY_LOG_RING is available, a nu 270 - if KVM_CAP_DIRTY_LOG_RING is available, a number of pages at
290 KVM_DIRTY_LOG_PAGE_OFFSET * PAGE_SIZE. For 271 KVM_DIRTY_LOG_PAGE_OFFSET * PAGE_SIZE. For more information on
291 KVM_CAP_DIRTY_LOG_RING, see section 8.3. 272 KVM_CAP_DIRTY_LOG_RING, see section 8.3.
292 273
293 274
294 4.7 KVM_CREATE_VCPU 275 4.7 KVM_CREATE_VCPU
295 ------------------- 276 -------------------
296 277
297 :Capability: basic 278 :Capability: basic
298 :Architectures: all 279 :Architectures: all
299 :Type: vm ioctl 280 :Type: vm ioctl
300 :Parameters: vcpu id (apic id on x86) 281 :Parameters: vcpu id (apic id on x86)
301 :Returns: vcpu fd on success, -1 on error 282 :Returns: vcpu fd on success, -1 on error
302 283
303 This API adds a vcpu to a virtual machine. No 284 This API adds a vcpu to a virtual machine. No more than max_vcpus may be added.
304 The vcpu id is an integer in the range [0, max 285 The vcpu id is an integer in the range [0, max_vcpu_id).
305 286
306 The recommended max_vcpus value can be retriev 287 The recommended max_vcpus value can be retrieved using the KVM_CAP_NR_VCPUS of
307 the KVM_CHECK_EXTENSION ioctl() at run-time. 288 the KVM_CHECK_EXTENSION ioctl() at run-time.
308 The maximum possible value for max_vcpus can b 289 The maximum possible value for max_vcpus can be retrieved using the
309 KVM_CAP_MAX_VCPUS of the KVM_CHECK_EXTENSION i 290 KVM_CAP_MAX_VCPUS of the KVM_CHECK_EXTENSION ioctl() at run-time.
310 291
311 If the KVM_CAP_NR_VCPUS does not exist, you sh 292 If the KVM_CAP_NR_VCPUS does not exist, you should assume that max_vcpus is 4
312 cpus max. 293 cpus max.
313 If the KVM_CAP_MAX_VCPUS does not exist, you s 294 If the KVM_CAP_MAX_VCPUS does not exist, you should assume that max_vcpus is
314 same as the value returned from KVM_CAP_NR_VCP 295 same as the value returned from KVM_CAP_NR_VCPUS.
315 296
316 The maximum possible value for max_vcpu_id can 297 The maximum possible value for max_vcpu_id can be retrieved using the
317 KVM_CAP_MAX_VCPU_ID of the KVM_CHECK_EXTENSION 298 KVM_CAP_MAX_VCPU_ID of the KVM_CHECK_EXTENSION ioctl() at run-time.
318 299
319 If the KVM_CAP_MAX_VCPU_ID does not exist, you 300 If the KVM_CAP_MAX_VCPU_ID does not exist, you should assume that max_vcpu_id
320 is the same as the value returned from KVM_CAP 301 is the same as the value returned from KVM_CAP_MAX_VCPUS.
321 302
322 On powerpc using book3s_hv mode, the vcpus are 303 On powerpc using book3s_hv mode, the vcpus are mapped onto virtual
323 threads in one or more virtual CPU cores. (Th 304 threads in one or more virtual CPU cores. (This is because the
324 hardware requires all the hardware threads in 305 hardware requires all the hardware threads in a CPU core to be in the
325 same partition.) The KVM_CAP_PPC_SMT capabili 306 same partition.) The KVM_CAP_PPC_SMT capability indicates the number
326 of vcpus per virtual core (vcore). The vcore 307 of vcpus per virtual core (vcore). The vcore id is obtained by
327 dividing the vcpu id by the number of vcpus pe 308 dividing the vcpu id by the number of vcpus per vcore. The vcpus in a
328 given vcore will always be in the same physica 309 given vcore will always be in the same physical core as each other
329 (though that might be a different physical cor 310 (though that might be a different physical core from time to time).
330 Userspace can control the threading (SMT) mode 311 Userspace can control the threading (SMT) mode of the guest by its
331 allocation of vcpu ids. For example, if users 312 allocation of vcpu ids. For example, if userspace wants
332 single-threaded guest vcpus, it should make al 313 single-threaded guest vcpus, it should make all vcpu ids be a multiple
333 of the number of vcpus per vcore. 314 of the number of vcpus per vcore.
334 315
335 For virtual cpus that have been created with S 316 For virtual cpus that have been created with S390 user controlled virtual
336 machines, the resulting vcpu fd can be memory 317 machines, the resulting vcpu fd can be memory mapped at page offset
337 KVM_S390_SIE_PAGE_OFFSET in order to obtain a 318 KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of the virtual
338 cpu's hardware control block. 319 cpu's hardware control block.
339 320
340 321
341 4.8 KVM_GET_DIRTY_LOG (vm ioctl) 322 4.8 KVM_GET_DIRTY_LOG (vm ioctl)
342 -------------------------------- 323 --------------------------------
343 324
344 :Capability: basic 325 :Capability: basic
345 :Architectures: all 326 :Architectures: all
346 :Type: vm ioctl 327 :Type: vm ioctl
347 :Parameters: struct kvm_dirty_log (in/out) 328 :Parameters: struct kvm_dirty_log (in/out)
348 :Returns: 0 on success, -1 on error 329 :Returns: 0 on success, -1 on error
349 330
350 :: 331 ::
351 332
352 /* for KVM_GET_DIRTY_LOG */ 333 /* for KVM_GET_DIRTY_LOG */
353 struct kvm_dirty_log { 334 struct kvm_dirty_log {
354 __u32 slot; 335 __u32 slot;
355 __u32 padding; 336 __u32 padding;
356 union { 337 union {
357 void __user *dirty_bitmap; /* 338 void __user *dirty_bitmap; /* one bit per page */
358 __u64 padding; 339 __u64 padding;
359 }; 340 };
360 }; 341 };
361 342
362 Given a memory slot, return a bitmap containin 343 Given a memory slot, return a bitmap containing any pages dirtied
363 since the last call to this ioctl. Bit 0 is t 344 since the last call to this ioctl. Bit 0 is the first page in the
364 memory slot. Ensure the entire structure is c 345 memory slot. Ensure the entire structure is cleared to avoid padding
365 issues. 346 issues.
366 347
367 If KVM_CAP_MULTI_ADDRESS_SPACE is available, b 348 If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of slot field specifies
368 the address space for which you want to return 349 the address space for which you want to return the dirty bitmap. See
369 KVM_SET_USER_MEMORY_REGION for details on the 350 KVM_SET_USER_MEMORY_REGION for details on the usage of slot field.
370 351
371 The bits in the dirty bitmap are cleared befor 352 The bits in the dirty bitmap are cleared before the ioctl returns, unless
372 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is enabled. 353 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is enabled. For more information,
373 see the description of the capability. 354 see the description of the capability.
374 355
375 Note that the Xen shared_info page, if configu !! 356 Note that the Xen shared info page, if configured, shall always be assumed
376 to be dirty. KVM will not explicitly mark it s 357 to be dirty. KVM will not explicitly mark it such.
377 358
378 359
379 4.10 KVM_RUN 360 4.10 KVM_RUN
380 ------------ 361 ------------
381 362
382 :Capability: basic 363 :Capability: basic
383 :Architectures: all 364 :Architectures: all
384 :Type: vcpu ioctl 365 :Type: vcpu ioctl
385 :Parameters: none 366 :Parameters: none
386 :Returns: 0 on success, -1 on error 367 :Returns: 0 on success, -1 on error
387 368
388 Errors: 369 Errors:
389 370
390 ======= ================================= 371 ======= ==============================================================
391 EINTR an unmasked signal is pending 372 EINTR an unmasked signal is pending
392 ENOEXEC the vcpu hasn't been initialized 373 ENOEXEC the vcpu hasn't been initialized or the guest tried to execute
393 instructions from device memory ( 374 instructions from device memory (arm64)
394 ENOSYS data abort outside memslots with 375 ENOSYS data abort outside memslots with no syndrome info and
395 KVM_CAP_ARM_NISV_TO_USER not enab 376 KVM_CAP_ARM_NISV_TO_USER not enabled (arm64)
396 EPERM SVE feature set but not finalized 377 EPERM SVE feature set but not finalized (arm64)
397 ======= ================================= 378 ======= ==============================================================
398 379
399 This ioctl is used to run a guest virtual cpu. 380 This ioctl is used to run a guest virtual cpu. While there are no
400 explicit parameters, there is an implicit para 381 explicit parameters, there is an implicit parameter block that can be
401 obtained by mmap()ing the vcpu fd at offset 0, 382 obtained by mmap()ing the vcpu fd at offset 0, with the size given by
402 KVM_GET_VCPU_MMAP_SIZE. The parameter block i 383 KVM_GET_VCPU_MMAP_SIZE. The parameter block is formatted as a 'struct
403 kvm_run' (see below). 384 kvm_run' (see below).
404 385
405 386
406 4.11 KVM_GET_REGS 387 4.11 KVM_GET_REGS
407 ----------------- 388 -----------------
408 389
409 :Capability: basic 390 :Capability: basic
410 :Architectures: all except arm64 391 :Architectures: all except arm64
411 :Type: vcpu ioctl 392 :Type: vcpu ioctl
412 :Parameters: struct kvm_regs (out) 393 :Parameters: struct kvm_regs (out)
413 :Returns: 0 on success, -1 on error 394 :Returns: 0 on success, -1 on error
414 395
415 Reads the general purpose registers from the v 396 Reads the general purpose registers from the vcpu.
416 397
417 :: 398 ::
418 399
419 /* x86 */ 400 /* x86 */
420 struct kvm_regs { 401 struct kvm_regs {
421 /* out (KVM_GET_REGS) / in (KVM_SET_RE 402 /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
422 __u64 rax, rbx, rcx, rdx; 403 __u64 rax, rbx, rcx, rdx;
423 __u64 rsi, rdi, rsp, rbp; 404 __u64 rsi, rdi, rsp, rbp;
424 __u64 r8, r9, r10, r11; 405 __u64 r8, r9, r10, r11;
425 __u64 r12, r13, r14, r15; 406 __u64 r12, r13, r14, r15;
426 __u64 rip, rflags; 407 __u64 rip, rflags;
427 }; 408 };
428 409
429 /* mips */ 410 /* mips */
430 struct kvm_regs { 411 struct kvm_regs {
431 /* out (KVM_GET_REGS) / in (KVM_SET_RE 412 /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
432 __u64 gpr[32]; 413 __u64 gpr[32];
433 __u64 hi; 414 __u64 hi;
434 __u64 lo; 415 __u64 lo;
435 __u64 pc; 416 __u64 pc;
436 }; 417 };
437 418
438 /* LoongArch */ <<
439 struct kvm_regs { <<
440 /* out (KVM_GET_REGS) / in (KVM_SET_RE <<
441 unsigned long gpr[32]; <<
442 unsigned long pc; <<
443 }; <<
444 <<
445 419
446 4.12 KVM_SET_REGS 420 4.12 KVM_SET_REGS
447 ----------------- 421 -----------------
448 422
449 :Capability: basic 423 :Capability: basic
450 :Architectures: all except arm64 424 :Architectures: all except arm64
451 :Type: vcpu ioctl 425 :Type: vcpu ioctl
452 :Parameters: struct kvm_regs (in) 426 :Parameters: struct kvm_regs (in)
453 :Returns: 0 on success, -1 on error 427 :Returns: 0 on success, -1 on error
454 428
455 Writes the general purpose registers into the 429 Writes the general purpose registers into the vcpu.
456 430
457 See KVM_GET_REGS for the data structure. 431 See KVM_GET_REGS for the data structure.
458 432
459 433
460 4.13 KVM_GET_SREGS 434 4.13 KVM_GET_SREGS
461 ------------------ 435 ------------------
462 436
463 :Capability: basic 437 :Capability: basic
464 :Architectures: x86, ppc 438 :Architectures: x86, ppc
465 :Type: vcpu ioctl 439 :Type: vcpu ioctl
466 :Parameters: struct kvm_sregs (out) 440 :Parameters: struct kvm_sregs (out)
467 :Returns: 0 on success, -1 on error 441 :Returns: 0 on success, -1 on error
468 442
469 Reads special registers from the vcpu. 443 Reads special registers from the vcpu.
470 444
471 :: 445 ::
472 446
473 /* x86 */ 447 /* x86 */
474 struct kvm_sregs { 448 struct kvm_sregs {
475 struct kvm_segment cs, ds, es, fs, gs, 449 struct kvm_segment cs, ds, es, fs, gs, ss;
476 struct kvm_segment tr, ldt; 450 struct kvm_segment tr, ldt;
477 struct kvm_dtable gdt, idt; 451 struct kvm_dtable gdt, idt;
478 __u64 cr0, cr2, cr3, cr4, cr8; 452 __u64 cr0, cr2, cr3, cr4, cr8;
479 __u64 efer; 453 __u64 efer;
480 __u64 apic_base; 454 __u64 apic_base;
481 __u64 interrupt_bitmap[(KVM_NR_INTERRU 455 __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
482 }; 456 };
483 457
484 /* ppc -- see arch/powerpc/include/uapi/asm/ 458 /* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */
485 459
486 interrupt_bitmap is a bitmap of pending extern 460 interrupt_bitmap is a bitmap of pending external interrupts. At most
487 one bit may be set. This interrupt has been a 461 one bit may be set. This interrupt has been acknowledged by the APIC
488 but not yet injected into the cpu core. 462 but not yet injected into the cpu core.
489 463
490 464
491 4.14 KVM_SET_SREGS 465 4.14 KVM_SET_SREGS
492 ------------------ 466 ------------------
493 467
494 :Capability: basic 468 :Capability: basic
495 :Architectures: x86, ppc 469 :Architectures: x86, ppc
496 :Type: vcpu ioctl 470 :Type: vcpu ioctl
497 :Parameters: struct kvm_sregs (in) 471 :Parameters: struct kvm_sregs (in)
498 :Returns: 0 on success, -1 on error 472 :Returns: 0 on success, -1 on error
499 473
500 Writes special registers into the vcpu. See K 474 Writes special registers into the vcpu. See KVM_GET_SREGS for the
501 data structures. 475 data structures.
502 476
503 477
504 4.15 KVM_TRANSLATE 478 4.15 KVM_TRANSLATE
505 ------------------ 479 ------------------
506 480
507 :Capability: basic 481 :Capability: basic
508 :Architectures: x86 482 :Architectures: x86
509 :Type: vcpu ioctl 483 :Type: vcpu ioctl
510 :Parameters: struct kvm_translation (in/out) 484 :Parameters: struct kvm_translation (in/out)
511 :Returns: 0 on success, -1 on error 485 :Returns: 0 on success, -1 on error
512 486
513 Translates a virtual address according to the 487 Translates a virtual address according to the vcpu's current address
514 translation mode. 488 translation mode.
515 489
516 :: 490 ::
517 491
518 struct kvm_translation { 492 struct kvm_translation {
519 /* in */ 493 /* in */
520 __u64 linear_address; 494 __u64 linear_address;
521 495
522 /* out */ 496 /* out */
523 __u64 physical_address; 497 __u64 physical_address;
524 __u8 valid; 498 __u8 valid;
525 __u8 writeable; 499 __u8 writeable;
526 __u8 usermode; 500 __u8 usermode;
527 __u8 pad[5]; 501 __u8 pad[5];
528 }; 502 };
529 503
530 504
531 4.16 KVM_INTERRUPT 505 4.16 KVM_INTERRUPT
532 ------------------ 506 ------------------
533 507
534 :Capability: basic 508 :Capability: basic
535 :Architectures: x86, ppc, mips, riscv, loongar !! 509 :Architectures: x86, ppc, mips, riscv
536 :Type: vcpu ioctl 510 :Type: vcpu ioctl
537 :Parameters: struct kvm_interrupt (in) 511 :Parameters: struct kvm_interrupt (in)
538 :Returns: 0 on success, negative on failure. 512 :Returns: 0 on success, negative on failure.
539 513
540 Queues a hardware interrupt vector to be injec 514 Queues a hardware interrupt vector to be injected.
541 515
542 :: 516 ::
543 517
544 /* for KVM_INTERRUPT */ 518 /* for KVM_INTERRUPT */
545 struct kvm_interrupt { 519 struct kvm_interrupt {
546 /* in */ 520 /* in */
547 __u32 irq; 521 __u32 irq;
548 }; 522 };
549 523
550 X86: 524 X86:
551 ^^^^ 525 ^^^^
552 526
553 :Returns: 527 :Returns:
554 528
555 ========= ============================ 529 ========= ===================================
556 0 on success, 530 0 on success,
557 -EEXIST if an interrupt is already e 531 -EEXIST if an interrupt is already enqueued
558 -EINVAL the irq number is invalid 532 -EINVAL the irq number is invalid
559 -ENXIO if the PIC is in the kernel 533 -ENXIO if the PIC is in the kernel
560 -EFAULT if the pointer is invalid 534 -EFAULT if the pointer is invalid
561 ========= ============================ 535 ========= ===================================
562 536
563 Note 'irq' is an interrupt vector, not an inte 537 Note 'irq' is an interrupt vector, not an interrupt pin or line. This
564 ioctl is useful if the in-kernel PIC is not us 538 ioctl is useful if the in-kernel PIC is not used.
565 539
566 PPC: 540 PPC:
567 ^^^^ 541 ^^^^
568 542
569 Queues an external interrupt to be injected. T !! 543 Queues an external interrupt to be injected. This ioctl is overleaded
570 with 3 different irq values: 544 with 3 different irq values:
571 545
572 a) KVM_INTERRUPT_SET 546 a) KVM_INTERRUPT_SET
573 547
574 This injects an edge type external interrup 548 This injects an edge type external interrupt into the guest once it's ready
575 to receive interrupts. When injected, the i 549 to receive interrupts. When injected, the interrupt is done.
576 550
577 b) KVM_INTERRUPT_UNSET 551 b) KVM_INTERRUPT_UNSET
578 552
579 This unsets any pending interrupt. 553 This unsets any pending interrupt.
580 554
581 Only available with KVM_CAP_PPC_UNSET_IRQ. 555 Only available with KVM_CAP_PPC_UNSET_IRQ.
582 556
583 c) KVM_INTERRUPT_SET_LEVEL 557 c) KVM_INTERRUPT_SET_LEVEL
584 558
585 This injects a level type external interrup 559 This injects a level type external interrupt into the guest context. The
586 interrupt stays pending until a specific io 560 interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET
587 is triggered. 561 is triggered.
588 562
589 Only available with KVM_CAP_PPC_IRQ_LEVEL. 563 Only available with KVM_CAP_PPC_IRQ_LEVEL.
590 564
591 Note that any value for 'irq' other than the o 565 Note that any value for 'irq' other than the ones stated above is invalid
592 and incurs unexpected behavior. 566 and incurs unexpected behavior.
593 567
594 This is an asynchronous vcpu ioctl and can be 568 This is an asynchronous vcpu ioctl and can be invoked from any thread.
595 569
596 MIPS: 570 MIPS:
597 ^^^^^ 571 ^^^^^
598 572
599 Queues an external interrupt to be injected in 573 Queues an external interrupt to be injected into the virtual CPU. A negative
600 interrupt number dequeues the interrupt. 574 interrupt number dequeues the interrupt.
601 575
602 This is an asynchronous vcpu ioctl and can be 576 This is an asynchronous vcpu ioctl and can be invoked from any thread.
603 577
604 RISC-V: 578 RISC-V:
605 ^^^^^^^ 579 ^^^^^^^
606 580
607 Queues an external interrupt to be injected in !! 581 Queues an external interrupt to be injected into the virutal CPU. This ioctl
608 is overloaded with 2 different irq values: 582 is overloaded with 2 different irq values:
609 583
610 a) KVM_INTERRUPT_SET 584 a) KVM_INTERRUPT_SET
611 585
612 This sets external interrupt for a virtual 586 This sets external interrupt for a virtual CPU and it will receive
613 once it is ready. 587 once it is ready.
614 588
615 b) KVM_INTERRUPT_UNSET 589 b) KVM_INTERRUPT_UNSET
616 590
617 This clears pending external interrupt for 591 This clears pending external interrupt for a virtual CPU.
618 592
619 This is an asynchronous vcpu ioctl and can be 593 This is an asynchronous vcpu ioctl and can be invoked from any thread.
620 594
621 LOONGARCH: <<
622 ^^^^^^^^^^ <<
623 595
624 Queues an external interrupt to be injected in !! 596 4.17 KVM_DEBUG_GUEST
625 interrupt number dequeues the interrupt. !! 597 --------------------
626 598
627 This is an asynchronous vcpu ioctl and can be !! 599 :Capability: basic
>> 600 :Architectures: none
>> 601 :Type: vcpu ioctl
>> 602 :Parameters: none)
>> 603 :Returns: -1 on error
>> 604
>> 605 Support for this has been removed. Use KVM_SET_GUEST_DEBUG instead.
628 606
629 607
630 4.18 KVM_GET_MSRS 608 4.18 KVM_GET_MSRS
631 ----------------- 609 -----------------
632 610
633 :Capability: basic (vcpu), KVM_CAP_GET_MSR_FEA 611 :Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system)
634 :Architectures: x86 612 :Architectures: x86
635 :Type: system ioctl, vcpu ioctl 613 :Type: system ioctl, vcpu ioctl
636 :Parameters: struct kvm_msrs (in/out) 614 :Parameters: struct kvm_msrs (in/out)
637 :Returns: number of msrs successfully returned 615 :Returns: number of msrs successfully returned;
638 -1 on error 616 -1 on error
639 617
640 When used as a system ioctl: 618 When used as a system ioctl:
641 Reads the values of MSR-based features that ar 619 Reads the values of MSR-based features that are available for the VM. This
642 is similar to KVM_GET_SUPPORTED_CPUID, but it 620 is similar to KVM_GET_SUPPORTED_CPUID, but it returns MSR indices and values.
643 The list of msr-based features can be obtained 621 The list of msr-based features can be obtained using KVM_GET_MSR_FEATURE_INDEX_LIST
644 in a system ioctl. 622 in a system ioctl.
645 623
646 When used as a vcpu ioctl: 624 When used as a vcpu ioctl:
647 Reads model-specific registers from the vcpu. 625 Reads model-specific registers from the vcpu. Supported msr indices can
648 be obtained using KVM_GET_MSR_INDEX_LIST in a 626 be obtained using KVM_GET_MSR_INDEX_LIST in a system ioctl.
649 627
650 :: 628 ::
651 629
652 struct kvm_msrs { 630 struct kvm_msrs {
653 __u32 nmsrs; /* number of msrs in entr 631 __u32 nmsrs; /* number of msrs in entries */
654 __u32 pad; 632 __u32 pad;
655 633
656 struct kvm_msr_entry entries[0]; 634 struct kvm_msr_entry entries[0];
657 }; 635 };
658 636
659 struct kvm_msr_entry { 637 struct kvm_msr_entry {
660 __u32 index; 638 __u32 index;
661 __u32 reserved; 639 __u32 reserved;
662 __u64 data; 640 __u64 data;
663 }; 641 };
664 642
665 Application code should set the 'nmsrs' member 643 Application code should set the 'nmsrs' member (which indicates the
666 size of the entries array) and the 'index' mem 644 size of the entries array) and the 'index' member of each array entry.
667 kvm will fill in the 'data' member. 645 kvm will fill in the 'data' member.
668 646
669 647
670 4.19 KVM_SET_MSRS 648 4.19 KVM_SET_MSRS
671 ----------------- 649 -----------------
672 650
673 :Capability: basic 651 :Capability: basic
674 :Architectures: x86 652 :Architectures: x86
675 :Type: vcpu ioctl 653 :Type: vcpu ioctl
676 :Parameters: struct kvm_msrs (in) 654 :Parameters: struct kvm_msrs (in)
677 :Returns: number of msrs successfully set (see 655 :Returns: number of msrs successfully set (see below), -1 on error
678 656
679 Writes model-specific registers to the vcpu. 657 Writes model-specific registers to the vcpu. See KVM_GET_MSRS for the
680 data structures. 658 data structures.
681 659
682 Application code should set the 'nmsrs' member 660 Application code should set the 'nmsrs' member (which indicates the
683 size of the entries array), and the 'index' an 661 size of the entries array), and the 'index' and 'data' members of each
684 array entry. 662 array entry.
685 663
686 It tries to set the MSRs in array entries[] on 664 It tries to set the MSRs in array entries[] one by one. If setting an MSR
687 fails, e.g., due to setting reserved bits, the 665 fails, e.g., due to setting reserved bits, the MSR isn't supported/emulated
688 by KVM, etc..., it stops processing the MSR li 666 by KVM, etc..., it stops processing the MSR list and returns the number of
689 MSRs that have been set successfully. 667 MSRs that have been set successfully.
690 668
691 669
692 4.20 KVM_SET_CPUID 670 4.20 KVM_SET_CPUID
693 ------------------ 671 ------------------
694 672
695 :Capability: basic 673 :Capability: basic
696 :Architectures: x86 674 :Architectures: x86
697 :Type: vcpu ioctl 675 :Type: vcpu ioctl
698 :Parameters: struct kvm_cpuid (in) 676 :Parameters: struct kvm_cpuid (in)
699 :Returns: 0 on success, -1 on error 677 :Returns: 0 on success, -1 on error
700 678
701 Defines the vcpu responses to the cpuid instru 679 Defines the vcpu responses to the cpuid instruction. Applications
702 should use the KVM_SET_CPUID2 ioctl if availab 680 should use the KVM_SET_CPUID2 ioctl if available.
703 681
704 Caveat emptor: 682 Caveat emptor:
705 - If this IOCTL fails, KVM gives no guarante 683 - If this IOCTL fails, KVM gives no guarantees that previous valid CPUID
706 configuration (if there is) is not corrupt 684 configuration (if there is) is not corrupted. Userspace can get a copy
707 of the resulting CPUID configuration throu 685 of the resulting CPUID configuration through KVM_GET_CPUID2 in case.
708 - Using KVM_SET_CPUID{,2} after KVM_RUN, i.e 686 - Using KVM_SET_CPUID{,2} after KVM_RUN, i.e. changing the guest vCPU model
709 after running the guest, may cause guest i 687 after running the guest, may cause guest instability.
710 - Using heterogeneous CPUID configurations, 688 - Using heterogeneous CPUID configurations, modulo APIC IDs, topology, etc...
711 may cause guest instability. 689 may cause guest instability.
712 690
713 :: 691 ::
714 692
715 struct kvm_cpuid_entry { 693 struct kvm_cpuid_entry {
716 __u32 function; 694 __u32 function;
717 __u32 eax; 695 __u32 eax;
718 __u32 ebx; 696 __u32 ebx;
719 __u32 ecx; 697 __u32 ecx;
720 __u32 edx; 698 __u32 edx;
721 __u32 padding; 699 __u32 padding;
722 }; 700 };
723 701
724 /* for KVM_SET_CPUID */ 702 /* for KVM_SET_CPUID */
725 struct kvm_cpuid { 703 struct kvm_cpuid {
726 __u32 nent; 704 __u32 nent;
727 __u32 padding; 705 __u32 padding;
728 struct kvm_cpuid_entry entries[0]; 706 struct kvm_cpuid_entry entries[0];
729 }; 707 };
730 708
731 709
732 4.21 KVM_SET_SIGNAL_MASK 710 4.21 KVM_SET_SIGNAL_MASK
733 ------------------------ 711 ------------------------
734 712
735 :Capability: basic 713 :Capability: basic
736 :Architectures: all 714 :Architectures: all
737 :Type: vcpu ioctl 715 :Type: vcpu ioctl
738 :Parameters: struct kvm_signal_mask (in) 716 :Parameters: struct kvm_signal_mask (in)
739 :Returns: 0 on success, -1 on error 717 :Returns: 0 on success, -1 on error
740 718
741 Defines which signals are blocked during execu 719 Defines which signals are blocked during execution of KVM_RUN. This
742 signal mask temporarily overrides the threads 720 signal mask temporarily overrides the threads signal mask. Any
743 unblocked signal received (except SIGKILL and 721 unblocked signal received (except SIGKILL and SIGSTOP, which retain
744 their traditional behaviour) will cause KVM_RU 722 their traditional behaviour) will cause KVM_RUN to return with -EINTR.
745 723
746 Note the signal will only be delivered if not 724 Note the signal will only be delivered if not blocked by the original
747 signal mask. 725 signal mask.
748 726
749 :: 727 ::
750 728
751 /* for KVM_SET_SIGNAL_MASK */ 729 /* for KVM_SET_SIGNAL_MASK */
752 struct kvm_signal_mask { 730 struct kvm_signal_mask {
753 __u32 len; 731 __u32 len;
754 __u8 sigset[0]; 732 __u8 sigset[0];
755 }; 733 };
756 734
757 735
758 4.22 KVM_GET_FPU 736 4.22 KVM_GET_FPU
759 ---------------- 737 ----------------
760 738
761 :Capability: basic 739 :Capability: basic
762 :Architectures: x86, loongarch !! 740 :Architectures: x86
763 :Type: vcpu ioctl 741 :Type: vcpu ioctl
764 :Parameters: struct kvm_fpu (out) 742 :Parameters: struct kvm_fpu (out)
765 :Returns: 0 on success, -1 on error 743 :Returns: 0 on success, -1 on error
766 744
767 Reads the floating point state from the vcpu. 745 Reads the floating point state from the vcpu.
768 746
769 :: 747 ::
770 748
771 /* x86: for KVM_GET_FPU and KVM_SET_FPU */ !! 749 /* for KVM_GET_FPU and KVM_SET_FPU */
772 struct kvm_fpu { 750 struct kvm_fpu {
773 __u8 fpr[8][16]; 751 __u8 fpr[8][16];
774 __u16 fcw; 752 __u16 fcw;
775 __u16 fsw; 753 __u16 fsw;
776 __u8 ftwx; /* in fxsave format */ 754 __u8 ftwx; /* in fxsave format */
777 __u8 pad1; 755 __u8 pad1;
778 __u16 last_opcode; 756 __u16 last_opcode;
779 __u64 last_ip; 757 __u64 last_ip;
780 __u64 last_dp; 758 __u64 last_dp;
781 __u8 xmm[16][16]; 759 __u8 xmm[16][16];
782 __u32 mxcsr; 760 __u32 mxcsr;
783 __u32 pad2; 761 __u32 pad2;
784 }; 762 };
785 763
786 /* LoongArch: for KVM_GET_FPU and KVM_SET_FP <<
787 struct kvm_fpu { <<
788 __u32 fcsr; <<
789 __u64 fcc; <<
790 struct kvm_fpureg { <<
791 __u64 val64[4]; <<
792 }fpr[32]; <<
793 }; <<
794 <<
795 764
796 4.23 KVM_SET_FPU 765 4.23 KVM_SET_FPU
797 ---------------- 766 ----------------
798 767
799 :Capability: basic 768 :Capability: basic
800 :Architectures: x86, loongarch !! 769 :Architectures: x86
801 :Type: vcpu ioctl 770 :Type: vcpu ioctl
802 :Parameters: struct kvm_fpu (in) 771 :Parameters: struct kvm_fpu (in)
803 :Returns: 0 on success, -1 on error 772 :Returns: 0 on success, -1 on error
804 773
805 Writes the floating point state to the vcpu. 774 Writes the floating point state to the vcpu.
806 775
807 :: 776 ::
808 777
809 /* x86: for KVM_GET_FPU and KVM_SET_FPU */ !! 778 /* for KVM_GET_FPU and KVM_SET_FPU */
810 struct kvm_fpu { 779 struct kvm_fpu {
811 __u8 fpr[8][16]; 780 __u8 fpr[8][16];
812 __u16 fcw; 781 __u16 fcw;
813 __u16 fsw; 782 __u16 fsw;
814 __u8 ftwx; /* in fxsave format */ 783 __u8 ftwx; /* in fxsave format */
815 __u8 pad1; 784 __u8 pad1;
816 __u16 last_opcode; 785 __u16 last_opcode;
817 __u64 last_ip; 786 __u64 last_ip;
818 __u64 last_dp; 787 __u64 last_dp;
819 __u8 xmm[16][16]; 788 __u8 xmm[16][16];
820 __u32 mxcsr; 789 __u32 mxcsr;
821 __u32 pad2; 790 __u32 pad2;
822 }; 791 };
823 792
824 /* LoongArch: for KVM_GET_FPU and KVM_SET_FP <<
825 struct kvm_fpu { <<
826 __u32 fcsr; <<
827 __u64 fcc; <<
828 struct kvm_fpureg { <<
829 __u64 val64[4]; <<
830 }fpr[32]; <<
831 }; <<
832 <<
833 793
834 4.24 KVM_CREATE_IRQCHIP 794 4.24 KVM_CREATE_IRQCHIP
835 ----------------------- 795 -----------------------
836 796
837 :Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQ 797 :Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390)
838 :Architectures: x86, arm64, s390 798 :Architectures: x86, arm64, s390
839 :Type: vm ioctl 799 :Type: vm ioctl
840 :Parameters: none 800 :Parameters: none
841 :Returns: 0 on success, -1 on error 801 :Returns: 0 on success, -1 on error
842 802
843 Creates an interrupt controller model in the k 803 Creates an interrupt controller model in the kernel.
844 On x86, creates a virtual ioapic, a virtual PI 804 On x86, creates a virtual ioapic, a virtual PIC (two PICs, nested), and sets up
845 future vcpus to have a local APIC. IRQ routin 805 future vcpus to have a local APIC. IRQ routing for GSIs 0-15 is set to both
846 PIC and IOAPIC; GSI 16-23 only go to the IOAPI 806 PIC and IOAPIC; GSI 16-23 only go to the IOAPIC.
847 On arm64, a GICv2 is created. Any other GIC ve 807 On arm64, a GICv2 is created. Any other GIC versions require the usage of
848 KVM_CREATE_DEVICE, which also supports creatin 808 KVM_CREATE_DEVICE, which also supports creating a GICv2. Using
849 KVM_CREATE_DEVICE is preferred over KVM_CREATE 809 KVM_CREATE_DEVICE is preferred over KVM_CREATE_IRQCHIP for GICv2.
850 On s390, a dummy irq routing table is created. 810 On s390, a dummy irq routing table is created.
851 811
852 Note that on s390 the KVM_CAP_S390_IRQCHIP vm 812 Note that on s390 the KVM_CAP_S390_IRQCHIP vm capability needs to be enabled
853 before KVM_CREATE_IRQCHIP can be used. 813 before KVM_CREATE_IRQCHIP can be used.
854 814
855 815
856 4.25 KVM_IRQ_LINE 816 4.25 KVM_IRQ_LINE
857 ----------------- 817 -----------------
858 818
859 :Capability: KVM_CAP_IRQCHIP 819 :Capability: KVM_CAP_IRQCHIP
860 :Architectures: x86, arm64 820 :Architectures: x86, arm64
861 :Type: vm ioctl 821 :Type: vm ioctl
862 :Parameters: struct kvm_irq_level 822 :Parameters: struct kvm_irq_level
863 :Returns: 0 on success, -1 on error 823 :Returns: 0 on success, -1 on error
864 824
865 Sets the level of a GSI input to the interrupt 825 Sets the level of a GSI input to the interrupt controller model in the kernel.
866 On some architectures it is required that an i 826 On some architectures it is required that an interrupt controller model has
867 been previously created with KVM_CREATE_IRQCHI 827 been previously created with KVM_CREATE_IRQCHIP. Note that edge-triggered
868 interrupts require the level to be set to 1 an 828 interrupts require the level to be set to 1 and then back to 0.
869 829
870 On real hardware, interrupt pins can be active 830 On real hardware, interrupt pins can be active-low or active-high. This
871 does not matter for the level field of struct 831 does not matter for the level field of struct kvm_irq_level: 1 always
872 means active (asserted), 0 means inactive (dea 832 means active (asserted), 0 means inactive (deasserted).
873 833
874 x86 allows the operating system to program the 834 x86 allows the operating system to program the interrupt polarity
875 (active-low/active-high) for level-triggered i 835 (active-low/active-high) for level-triggered interrupts, and KVM used
876 to consider the polarity. However, due to bit 836 to consider the polarity. However, due to bitrot in the handling of
877 active-low interrupts, the above convention is 837 active-low interrupts, the above convention is now valid on x86 too.
878 This is signaled by KVM_CAP_X86_IOAPIC_POLARIT 838 This is signaled by KVM_CAP_X86_IOAPIC_POLARITY_IGNORED. Userspace
879 should not present interrupts to the guest as 839 should not present interrupts to the guest as active-low unless this
880 capability is present (or unless it is not usi 840 capability is present (or unless it is not using the in-kernel irqchip,
881 of course). 841 of course).
882 842
883 843
884 arm64 can signal an interrupt either at the CP 844 arm64 can signal an interrupt either at the CPU level, or at the
885 in-kernel irqchip (GIC), and for in-kernel irq 845 in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to
886 use PPIs designated for specific cpus. The ir 846 use PPIs designated for specific cpus. The irq field is interpreted
887 like this:: 847 like this::
888 848
889 bits: | 31 ... 28 | 27 ... 24 | 23 ... 1 849 bits: | 31 ... 28 | 27 ... 24 | 23 ... 16 | 15 ... 0 |
890 field: | vcpu2_index | irq_type | vcpu_inde 850 field: | vcpu2_index | irq_type | vcpu_index | irq_id |
891 851
892 The irq_type field has the following values: 852 The irq_type field has the following values:
893 853
894 - KVM_ARM_IRQ_TYPE_CPU: !! 854 - irq_type[0]:
895 out-of-kernel GIC: irq_id 0 is 855 out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ
896 - KVM_ARM_IRQ_TYPE_SPI: !! 856 - irq_type[1]:
897 in-kernel GIC: SPI, irq_id betw 857 in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.)
898 (the vcpu_index field is ignore 858 (the vcpu_index field is ignored)
899 - KVM_ARM_IRQ_TYPE_PPI: !! 859 - irq_type[2]:
900 in-kernel GIC: PPI, irq_id betw 860 in-kernel GIC: PPI, irq_id between 16 and 31 (incl.)
901 861
902 (The irq_id field thus corresponds nicely to t 862 (The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs)
903 863
904 In both cases, level is used to assert/deasser 864 In both cases, level is used to assert/deassert the line.
905 865
906 When KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 is supporte 866 When KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 is supported, the target vcpu is
907 identified as (256 * vcpu2_index + vcpu_index) 867 identified as (256 * vcpu2_index + vcpu_index). Otherwise, vcpu2_index
908 must be zero. 868 must be zero.
909 869
910 Note that on arm64, the KVM_CAP_IRQCHIP capabi 870 Note that on arm64, the KVM_CAP_IRQCHIP capability only conditions
911 injection of interrupts for the in-kernel irqc 871 injection of interrupts for the in-kernel irqchip. KVM_IRQ_LINE can always
912 be used for a userspace interrupt controller. 872 be used for a userspace interrupt controller.
913 873
914 :: 874 ::
915 875
916 struct kvm_irq_level { 876 struct kvm_irq_level {
917 union { 877 union {
918 __u32 irq; /* GSI */ 878 __u32 irq; /* GSI */
919 __s32 status; /* not used for 879 __s32 status; /* not used for KVM_IRQ_LEVEL */
920 }; 880 };
921 __u32 level; /* 0 or 1 */ 881 __u32 level; /* 0 or 1 */
922 }; 882 };
923 883
924 884
925 4.26 KVM_GET_IRQCHIP 885 4.26 KVM_GET_IRQCHIP
926 -------------------- 886 --------------------
927 887
928 :Capability: KVM_CAP_IRQCHIP 888 :Capability: KVM_CAP_IRQCHIP
929 :Architectures: x86 889 :Architectures: x86
930 :Type: vm ioctl 890 :Type: vm ioctl
931 :Parameters: struct kvm_irqchip (in/out) 891 :Parameters: struct kvm_irqchip (in/out)
932 :Returns: 0 on success, -1 on error 892 :Returns: 0 on success, -1 on error
933 893
934 Reads the state of a kernel interrupt controll 894 Reads the state of a kernel interrupt controller created with
935 KVM_CREATE_IRQCHIP into a buffer provided by t 895 KVM_CREATE_IRQCHIP into a buffer provided by the caller.
936 896
937 :: 897 ::
938 898
939 struct kvm_irqchip { 899 struct kvm_irqchip {
940 __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 900 __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
941 __u32 pad; 901 __u32 pad;
942 union { 902 union {
943 char dummy[512]; /* reserving 903 char dummy[512]; /* reserving space */
944 struct kvm_pic_state pic; 904 struct kvm_pic_state pic;
945 struct kvm_ioapic_state ioapic 905 struct kvm_ioapic_state ioapic;
946 } chip; 906 } chip;
947 }; 907 };
948 908
949 909
950 4.27 KVM_SET_IRQCHIP 910 4.27 KVM_SET_IRQCHIP
951 -------------------- 911 --------------------
952 912
953 :Capability: KVM_CAP_IRQCHIP 913 :Capability: KVM_CAP_IRQCHIP
954 :Architectures: x86 914 :Architectures: x86
955 :Type: vm ioctl 915 :Type: vm ioctl
956 :Parameters: struct kvm_irqchip (in) 916 :Parameters: struct kvm_irqchip (in)
957 :Returns: 0 on success, -1 on error 917 :Returns: 0 on success, -1 on error
958 918
959 Sets the state of a kernel interrupt controlle 919 Sets the state of a kernel interrupt controller created with
960 KVM_CREATE_IRQCHIP from a buffer provided by t 920 KVM_CREATE_IRQCHIP from a buffer provided by the caller.
961 921
962 :: 922 ::
963 923
964 struct kvm_irqchip { 924 struct kvm_irqchip {
965 __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 925 __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
966 __u32 pad; 926 __u32 pad;
967 union { 927 union {
968 char dummy[512]; /* reserving 928 char dummy[512]; /* reserving space */
969 struct kvm_pic_state pic; 929 struct kvm_pic_state pic;
970 struct kvm_ioapic_state ioapic 930 struct kvm_ioapic_state ioapic;
971 } chip; 931 } chip;
972 }; 932 };
973 933
974 934
975 4.28 KVM_XEN_HVM_CONFIG 935 4.28 KVM_XEN_HVM_CONFIG
976 ----------------------- 936 -----------------------
977 937
978 :Capability: KVM_CAP_XEN_HVM 938 :Capability: KVM_CAP_XEN_HVM
979 :Architectures: x86 939 :Architectures: x86
980 :Type: vm ioctl 940 :Type: vm ioctl
981 :Parameters: struct kvm_xen_hvm_config (in) 941 :Parameters: struct kvm_xen_hvm_config (in)
982 :Returns: 0 on success, -1 on error 942 :Returns: 0 on success, -1 on error
983 943
984 Sets the MSR that the Xen HVM guest uses to in 944 Sets the MSR that the Xen HVM guest uses to initialize its hypercall
985 page, and provides the starting address and si 945 page, and provides the starting address and size of the hypercall
986 blobs in userspace. When the guest writes the 946 blobs in userspace. When the guest writes the MSR, kvm copies one
987 page of a blob (32- or 64-bit, depending on th 947 page of a blob (32- or 64-bit, depending on the vcpu mode) to guest
988 memory. 948 memory.
989 949
990 :: 950 ::
991 951
992 struct kvm_xen_hvm_config { 952 struct kvm_xen_hvm_config {
993 __u32 flags; 953 __u32 flags;
994 __u32 msr; 954 __u32 msr;
995 __u64 blob_addr_32; 955 __u64 blob_addr_32;
996 __u64 blob_addr_64; 956 __u64 blob_addr_64;
997 __u8 blob_size_32; 957 __u8 blob_size_32;
998 __u8 blob_size_64; 958 __u8 blob_size_64;
999 __u8 pad2[30]; 959 __u8 pad2[30];
1000 }; 960 };
1001 961
1002 If certain flags are returned from the KVM_CA 962 If certain flags are returned from the KVM_CAP_XEN_HVM check, they may
1003 be set in the flags field of this ioctl: 963 be set in the flags field of this ioctl:
1004 964
1005 The KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL flag r 965 The KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL flag requests KVM to generate
1006 the contents of the hypercall page automatica 966 the contents of the hypercall page automatically; hypercalls will be
1007 intercepted and passed to userspace through K 967 intercepted and passed to userspace through KVM_EXIT_XEN. In this
1008 case, all of the blob size and address fields !! 968 ase, all of the blob size and address fields must be zero.
1009 969
1010 The KVM_XEN_HVM_CONFIG_EVTCHN_SEND flag indic 970 The KVM_XEN_HVM_CONFIG_EVTCHN_SEND flag indicates to KVM that userspace
1011 will always use the KVM_XEN_HVM_EVTCHN_SEND i 971 will always use the KVM_XEN_HVM_EVTCHN_SEND ioctl to deliver event
1012 channel interrupts rather than manipulating t 972 channel interrupts rather than manipulating the guest's shared_info
1013 structures directly. This, in turn, may allow 973 structures directly. This, in turn, may allow KVM to enable features
1014 such as intercepting the SCHEDOP_poll hyperca 974 such as intercepting the SCHEDOP_poll hypercall to accelerate PV
1015 spinlock operation for the guest. Userspace m 975 spinlock operation for the guest. Userspace may still use the ioctl
1016 to deliver events if it was advertised, even 976 to deliver events if it was advertised, even if userspace does not
1017 send this indication that it will always do s 977 send this indication that it will always do so
1018 978
1019 No other flags are currently valid in the str 979 No other flags are currently valid in the struct kvm_xen_hvm_config.
1020 980
1021 4.29 KVM_GET_CLOCK 981 4.29 KVM_GET_CLOCK
1022 ------------------ 982 ------------------
1023 983
1024 :Capability: KVM_CAP_ADJUST_CLOCK 984 :Capability: KVM_CAP_ADJUST_CLOCK
1025 :Architectures: x86 985 :Architectures: x86
1026 :Type: vm ioctl 986 :Type: vm ioctl
1027 :Parameters: struct kvm_clock_data (out) 987 :Parameters: struct kvm_clock_data (out)
1028 :Returns: 0 on success, -1 on error 988 :Returns: 0 on success, -1 on error
1029 989
1030 Gets the current timestamp of kvmclock as see 990 Gets the current timestamp of kvmclock as seen by the current guest. In
1031 conjunction with KVM_SET_CLOCK, it is used to 991 conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios
1032 such as migration. 992 such as migration.
1033 993
1034 When KVM_CAP_ADJUST_CLOCK is passed to KVM_CH 994 When KVM_CAP_ADJUST_CLOCK is passed to KVM_CHECK_EXTENSION, it returns the
1035 set of bits that KVM can return in struct kvm 995 set of bits that KVM can return in struct kvm_clock_data's flag member.
1036 996
1037 The following flags are defined: 997 The following flags are defined:
1038 998
1039 KVM_CLOCK_TSC_STABLE 999 KVM_CLOCK_TSC_STABLE
1040 If set, the returned value is the exact kvm 1000 If set, the returned value is the exact kvmclock
1041 value seen by all VCPUs at the instant when 1001 value seen by all VCPUs at the instant when KVM_GET_CLOCK was called.
1042 If clear, the returned value is simply CLOC 1002 If clear, the returned value is simply CLOCK_MONOTONIC plus a constant
1043 offset; the offset can be modified with KVM 1003 offset; the offset can be modified with KVM_SET_CLOCK. KVM will try
1044 to make all VCPUs follow this clock, but th 1004 to make all VCPUs follow this clock, but the exact value read by each
1045 VCPU could differ, because the host TSC is 1005 VCPU could differ, because the host TSC is not stable.
1046 1006
1047 KVM_CLOCK_REALTIME 1007 KVM_CLOCK_REALTIME
1048 If set, the `realtime` field in the kvm_clo 1008 If set, the `realtime` field in the kvm_clock_data
1049 structure is populated with the value of th 1009 structure is populated with the value of the host's real time
1050 clocksource at the instant when KVM_GET_CLO 1010 clocksource at the instant when KVM_GET_CLOCK was called. If clear,
1051 the `realtime` field does not contain a val 1011 the `realtime` field does not contain a value.
1052 1012
1053 KVM_CLOCK_HOST_TSC 1013 KVM_CLOCK_HOST_TSC
1054 If set, the `host_tsc` field in the kvm_clo 1014 If set, the `host_tsc` field in the kvm_clock_data
1055 structure is populated with the value of th 1015 structure is populated with the value of the host's timestamp counter (TSC)
1056 at the instant when KVM_GET_CLOCK was calle 1016 at the instant when KVM_GET_CLOCK was called. If clear, the `host_tsc` field
1057 does not contain a value. 1017 does not contain a value.
1058 1018
1059 :: 1019 ::
1060 1020
1061 struct kvm_clock_data { 1021 struct kvm_clock_data {
1062 __u64 clock; /* kvmclock current val 1022 __u64 clock; /* kvmclock current value */
1063 __u32 flags; 1023 __u32 flags;
1064 __u32 pad0; 1024 __u32 pad0;
1065 __u64 realtime; 1025 __u64 realtime;
1066 __u64 host_tsc; 1026 __u64 host_tsc;
1067 __u32 pad[4]; 1027 __u32 pad[4];
1068 }; 1028 };
1069 1029
1070 1030
1071 4.30 KVM_SET_CLOCK 1031 4.30 KVM_SET_CLOCK
1072 ------------------ 1032 ------------------
1073 1033
1074 :Capability: KVM_CAP_ADJUST_CLOCK 1034 :Capability: KVM_CAP_ADJUST_CLOCK
1075 :Architectures: x86 1035 :Architectures: x86
1076 :Type: vm ioctl 1036 :Type: vm ioctl
1077 :Parameters: struct kvm_clock_data (in) 1037 :Parameters: struct kvm_clock_data (in)
1078 :Returns: 0 on success, -1 on error 1038 :Returns: 0 on success, -1 on error
1079 1039
1080 Sets the current timestamp of kvmclock to the 1040 Sets the current timestamp of kvmclock to the value specified in its parameter.
1081 In conjunction with KVM_GET_CLOCK, it is used 1041 In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
1082 such as migration. 1042 such as migration.
1083 1043
1084 The following flags can be passed: 1044 The following flags can be passed:
1085 1045
1086 KVM_CLOCK_REALTIME 1046 KVM_CLOCK_REALTIME
1087 If set, KVM will compare the value of the ` 1047 If set, KVM will compare the value of the `realtime` field
1088 with the value of the host's real time cloc 1048 with the value of the host's real time clocksource at the instant when
1089 KVM_SET_CLOCK was called. The difference in 1049 KVM_SET_CLOCK was called. The difference in elapsed time is added to the final
1090 kvmclock value that will be provided to gue 1050 kvmclock value that will be provided to guests.
1091 1051
1092 Other flags returned by ``KVM_GET_CLOCK`` are 1052 Other flags returned by ``KVM_GET_CLOCK`` are accepted but ignored.
1093 1053
1094 :: 1054 ::
1095 1055
1096 struct kvm_clock_data { 1056 struct kvm_clock_data {
1097 __u64 clock; /* kvmclock current val 1057 __u64 clock; /* kvmclock current value */
1098 __u32 flags; 1058 __u32 flags;
1099 __u32 pad0; 1059 __u32 pad0;
1100 __u64 realtime; 1060 __u64 realtime;
1101 __u64 host_tsc; 1061 __u64 host_tsc;
1102 __u32 pad[4]; 1062 __u32 pad[4];
1103 }; 1063 };
1104 1064
1105 1065
1106 4.31 KVM_GET_VCPU_EVENTS 1066 4.31 KVM_GET_VCPU_EVENTS
1107 ------------------------ 1067 ------------------------
1108 1068
1109 :Capability: KVM_CAP_VCPU_EVENTS 1069 :Capability: KVM_CAP_VCPU_EVENTS
1110 :Extended by: KVM_CAP_INTR_SHADOW 1070 :Extended by: KVM_CAP_INTR_SHADOW
1111 :Architectures: x86, arm64 1071 :Architectures: x86, arm64
1112 :Type: vcpu ioctl 1072 :Type: vcpu ioctl
1113 :Parameters: struct kvm_vcpu_events (out) !! 1073 :Parameters: struct kvm_vcpu_event (out)
1114 :Returns: 0 on success, -1 on error 1074 :Returns: 0 on success, -1 on error
1115 1075
1116 X86: 1076 X86:
1117 ^^^^ 1077 ^^^^
1118 1078
1119 Gets currently pending exceptions, interrupts 1079 Gets currently pending exceptions, interrupts, and NMIs as well as related
1120 states of the vcpu. 1080 states of the vcpu.
1121 1081
1122 :: 1082 ::
1123 1083
1124 struct kvm_vcpu_events { 1084 struct kvm_vcpu_events {
1125 struct { 1085 struct {
1126 __u8 injected; 1086 __u8 injected;
1127 __u8 nr; 1087 __u8 nr;
1128 __u8 has_error_code; 1088 __u8 has_error_code;
1129 __u8 pending; 1089 __u8 pending;
1130 __u32 error_code; 1090 __u32 error_code;
1131 } exception; 1091 } exception;
1132 struct { 1092 struct {
1133 __u8 injected; 1093 __u8 injected;
1134 __u8 nr; 1094 __u8 nr;
1135 __u8 soft; 1095 __u8 soft;
1136 __u8 shadow; 1096 __u8 shadow;
1137 } interrupt; 1097 } interrupt;
1138 struct { 1098 struct {
1139 __u8 injected; 1099 __u8 injected;
1140 __u8 pending; 1100 __u8 pending;
1141 __u8 masked; 1101 __u8 masked;
1142 __u8 pad; 1102 __u8 pad;
1143 } nmi; 1103 } nmi;
1144 __u32 sipi_vector; 1104 __u32 sipi_vector;
1145 __u32 flags; 1105 __u32 flags;
1146 struct { 1106 struct {
1147 __u8 smm; 1107 __u8 smm;
1148 __u8 pending; 1108 __u8 pending;
1149 __u8 smm_inside_nmi; 1109 __u8 smm_inside_nmi;
1150 __u8 latched_init; 1110 __u8 latched_init;
1151 } smi; 1111 } smi;
1152 __u8 reserved[27]; 1112 __u8 reserved[27];
1153 __u8 exception_has_payload; 1113 __u8 exception_has_payload;
1154 __u64 exception_payload; 1114 __u64 exception_payload;
1155 }; 1115 };
1156 1116
1157 The following bits are defined in the flags f 1117 The following bits are defined in the flags field:
1158 1118
1159 - KVM_VCPUEVENT_VALID_SHADOW may be set to si 1119 - KVM_VCPUEVENT_VALID_SHADOW may be set to signal that
1160 interrupt.shadow contains a valid state. 1120 interrupt.shadow contains a valid state.
1161 1121
1162 - KVM_VCPUEVENT_VALID_SMM may be set to signa 1122 - KVM_VCPUEVENT_VALID_SMM may be set to signal that smi contains a
1163 valid state. 1123 valid state.
1164 1124
1165 - KVM_VCPUEVENT_VALID_PAYLOAD may be set to s 1125 - KVM_VCPUEVENT_VALID_PAYLOAD may be set to signal that the
1166 exception_has_payload, exception_payload, a 1126 exception_has_payload, exception_payload, and exception.pending
1167 fields contain a valid state. This bit will 1127 fields contain a valid state. This bit will be set whenever
1168 KVM_CAP_EXCEPTION_PAYLOAD is enabled. 1128 KVM_CAP_EXCEPTION_PAYLOAD is enabled.
1169 1129
1170 - KVM_VCPUEVENT_VALID_TRIPLE_FAULT may be set 1130 - KVM_VCPUEVENT_VALID_TRIPLE_FAULT may be set to signal that the
1171 triple_fault_pending field contains a valid 1131 triple_fault_pending field contains a valid state. This bit will
1172 be set whenever KVM_CAP_X86_TRIPLE_FAULT_EV 1132 be set whenever KVM_CAP_X86_TRIPLE_FAULT_EVENT is enabled.
1173 1133
1174 ARM64: 1134 ARM64:
1175 ^^^^^^ 1135 ^^^^^^
1176 1136
1177 If the guest accesses a device that is being 1137 If the guest accesses a device that is being emulated by the host kernel in
1178 such a way that a real device would generate 1138 such a way that a real device would generate a physical SError, KVM may make
1179 a virtual SError pending for that VCPU. This 1139 a virtual SError pending for that VCPU. This system error interrupt remains
1180 pending until the guest takes the exception b 1140 pending until the guest takes the exception by unmasking PSTATE.A.
1181 1141
1182 Running the VCPU may cause it to take a pendi 1142 Running the VCPU may cause it to take a pending SError, or make an access that
1183 causes an SError to become pending. The event 1143 causes an SError to become pending. The event's description is only valid while
1184 the VPCU is not running. 1144 the VPCU is not running.
1185 1145
1186 This API provides a way to read and write the 1146 This API provides a way to read and write the pending 'event' state that is not
1187 visible to the guest. To save, restore or mig 1147 visible to the guest. To save, restore or migrate a VCPU the struct representing
1188 the state can be read then written using this 1148 the state can be read then written using this GET/SET API, along with the other
1189 guest-visible registers. It is not possible t 1149 guest-visible registers. It is not possible to 'cancel' an SError that has been
1190 made pending. 1150 made pending.
1191 1151
1192 A device being emulated in user-space may als 1152 A device being emulated in user-space may also wish to generate an SError. To do
1193 this the events structure can be populated by 1153 this the events structure can be populated by user-space. The current state
1194 should be read first, to ensure no existing S 1154 should be read first, to ensure no existing SError is pending. If an existing
1195 SError is pending, the architecture's 'Multip 1155 SError is pending, the architecture's 'Multiple SError interrupts' rules should
1196 be followed. (2.5.3 of DDI0587.a "ARM Reliabi 1156 be followed. (2.5.3 of DDI0587.a "ARM Reliability, Availability, and
1197 Serviceability (RAS) Specification"). 1157 Serviceability (RAS) Specification").
1198 1158
1199 SError exceptions always have an ESR value. S 1159 SError exceptions always have an ESR value. Some CPUs have the ability to
1200 specify what the virtual SError's ESR value s 1160 specify what the virtual SError's ESR value should be. These systems will
1201 advertise KVM_CAP_ARM_INJECT_SERROR_ESR. In t 1161 advertise KVM_CAP_ARM_INJECT_SERROR_ESR. In this case exception.has_esr will
1202 always have a non-zero value when read, and t 1162 always have a non-zero value when read, and the agent making an SError pending
1203 should specify the ISS field in the lower 24 1163 should specify the ISS field in the lower 24 bits of exception.serror_esr. If
1204 the system supports KVM_CAP_ARM_INJECT_SERROR 1164 the system supports KVM_CAP_ARM_INJECT_SERROR_ESR, but user-space sets the events
1205 with exception.has_esr as zero, KVM will choo 1165 with exception.has_esr as zero, KVM will choose an ESR.
1206 1166
1207 Specifying exception.has_esr on a system that 1167 Specifying exception.has_esr on a system that does not support it will return
1208 -EINVAL. Setting anything other than the lowe 1168 -EINVAL. Setting anything other than the lower 24bits of exception.serror_esr
1209 will return -EINVAL. 1169 will return -EINVAL.
1210 1170
1211 It is not possible to read back a pending ext 1171 It is not possible to read back a pending external abort (injected via
1212 KVM_SET_VCPU_EVENTS or otherwise) because suc 1172 KVM_SET_VCPU_EVENTS or otherwise) because such an exception is always delivered
1213 directly to the virtual CPU). 1173 directly to the virtual CPU).
1214 1174
1215 :: 1175 ::
1216 1176
1217 struct kvm_vcpu_events { 1177 struct kvm_vcpu_events {
1218 struct { 1178 struct {
1219 __u8 serror_pending; 1179 __u8 serror_pending;
1220 __u8 serror_has_esr; 1180 __u8 serror_has_esr;
1221 __u8 ext_dabt_pending; 1181 __u8 ext_dabt_pending;
1222 /* Align it to 8 bytes */ 1182 /* Align it to 8 bytes */
1223 __u8 pad[5]; 1183 __u8 pad[5];
1224 __u64 serror_esr; 1184 __u64 serror_esr;
1225 } exception; 1185 } exception;
1226 __u32 reserved[12]; 1186 __u32 reserved[12];
1227 }; 1187 };
1228 1188
1229 4.32 KVM_SET_VCPU_EVENTS 1189 4.32 KVM_SET_VCPU_EVENTS
1230 ------------------------ 1190 ------------------------
1231 1191
1232 :Capability: KVM_CAP_VCPU_EVENTS 1192 :Capability: KVM_CAP_VCPU_EVENTS
1233 :Extended by: KVM_CAP_INTR_SHADOW 1193 :Extended by: KVM_CAP_INTR_SHADOW
1234 :Architectures: x86, arm64 1194 :Architectures: x86, arm64
1235 :Type: vcpu ioctl 1195 :Type: vcpu ioctl
1236 :Parameters: struct kvm_vcpu_events (in) !! 1196 :Parameters: struct kvm_vcpu_event (in)
1237 :Returns: 0 on success, -1 on error 1197 :Returns: 0 on success, -1 on error
1238 1198
1239 X86: 1199 X86:
1240 ^^^^ 1200 ^^^^
1241 1201
1242 Set pending exceptions, interrupts, and NMIs 1202 Set pending exceptions, interrupts, and NMIs as well as related states of the
1243 vcpu. 1203 vcpu.
1244 1204
1245 See KVM_GET_VCPU_EVENTS for the data structur 1205 See KVM_GET_VCPU_EVENTS for the data structure.
1246 1206
1247 Fields that may be modified asynchronously by 1207 Fields that may be modified asynchronously by running VCPUs can be excluded
1248 from the update. These fields are nmi.pending 1208 from the update. These fields are nmi.pending, sipi_vector, smi.smm,
1249 smi.pending. Keep the corresponding bits in t 1209 smi.pending. Keep the corresponding bits in the flags field cleared to
1250 suppress overwriting the current in-kernel st 1210 suppress overwriting the current in-kernel state. The bits are:
1251 1211
1252 =============================== ============ 1212 =============================== ==================================
1253 KVM_VCPUEVENT_VALID_NMI_PENDING transfer nmi 1213 KVM_VCPUEVENT_VALID_NMI_PENDING transfer nmi.pending to the kernel
1254 KVM_VCPUEVENT_VALID_SIPI_VECTOR transfer sip 1214 KVM_VCPUEVENT_VALID_SIPI_VECTOR transfer sipi_vector
1255 KVM_VCPUEVENT_VALID_SMM transfer the 1215 KVM_VCPUEVENT_VALID_SMM transfer the smi sub-struct.
1256 =============================== ============ 1216 =============================== ==================================
1257 1217
1258 If KVM_CAP_INTR_SHADOW is available, KVM_VCPU 1218 If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
1259 the flags field to signal that interrupt.shad 1219 the flags field to signal that interrupt.shadow contains a valid state and
1260 shall be written into the VCPU. 1220 shall be written into the VCPU.
1261 1221
1262 KVM_VCPUEVENT_VALID_SMM can only be set if KV 1222 KVM_VCPUEVENT_VALID_SMM can only be set if KVM_CAP_X86_SMM is available.
1263 1223
1264 If KVM_CAP_EXCEPTION_PAYLOAD is enabled, KVM_ 1224 If KVM_CAP_EXCEPTION_PAYLOAD is enabled, KVM_VCPUEVENT_VALID_PAYLOAD
1265 can be set in the flags field to signal that 1225 can be set in the flags field to signal that the
1266 exception_has_payload, exception_payload, and 1226 exception_has_payload, exception_payload, and exception.pending fields
1267 contain a valid state and shall be written in 1227 contain a valid state and shall be written into the VCPU.
1268 1228
1269 If KVM_CAP_X86_TRIPLE_FAULT_EVENT is enabled, 1229 If KVM_CAP_X86_TRIPLE_FAULT_EVENT is enabled, KVM_VCPUEVENT_VALID_TRIPLE_FAULT
1270 can be set in flags field to signal that the 1230 can be set in flags field to signal that the triple_fault field contains
1271 a valid state and shall be written into the V 1231 a valid state and shall be written into the VCPU.
1272 1232
1273 ARM64: 1233 ARM64:
1274 ^^^^^^ 1234 ^^^^^^
1275 1235
1276 User space may need to inject several types o 1236 User space may need to inject several types of events to the guest.
1277 1237
1278 Set the pending SError exception state for th 1238 Set the pending SError exception state for this VCPU. It is not possible to
1279 'cancel' an Serror that has been made pending 1239 'cancel' an Serror that has been made pending.
1280 1240
1281 If the guest performed an access to I/O memor 1241 If the guest performed an access to I/O memory which could not be handled by
1282 userspace, for example because of missing ins 1242 userspace, for example because of missing instruction syndrome decode
1283 information or because there is no device map 1243 information or because there is no device mapped at the accessed IPA, then
1284 userspace can ask the kernel to inject an ext 1244 userspace can ask the kernel to inject an external abort using the address
1285 from the exiting fault on the VCPU. It is a p 1245 from the exiting fault on the VCPU. It is a programming error to set
1286 ext_dabt_pending after an exit which was not 1246 ext_dabt_pending after an exit which was not either KVM_EXIT_MMIO or
1287 KVM_EXIT_ARM_NISV. This feature is only avail 1247 KVM_EXIT_ARM_NISV. This feature is only available if the system supports
1288 KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper 1248 KVM_CAP_ARM_INJECT_EXT_DABT. This is a helper which provides commonality in
1289 how userspace reports accesses for the above 1249 how userspace reports accesses for the above cases to guests, across different
1290 userspace implementations. Nevertheless, user 1250 userspace implementations. Nevertheless, userspace can still emulate all Arm
1291 exceptions by manipulating individual registe 1251 exceptions by manipulating individual registers using the KVM_SET_ONE_REG API.
1292 1252
1293 See KVM_GET_VCPU_EVENTS for the data structur 1253 See KVM_GET_VCPU_EVENTS for the data structure.
1294 1254
1295 1255
1296 4.33 KVM_GET_DEBUGREGS 1256 4.33 KVM_GET_DEBUGREGS
1297 ---------------------- 1257 ----------------------
1298 1258
1299 :Capability: KVM_CAP_DEBUGREGS 1259 :Capability: KVM_CAP_DEBUGREGS
1300 :Architectures: x86 1260 :Architectures: x86
1301 :Type: vm ioctl 1261 :Type: vm ioctl
1302 :Parameters: struct kvm_debugregs (out) 1262 :Parameters: struct kvm_debugregs (out)
1303 :Returns: 0 on success, -1 on error 1263 :Returns: 0 on success, -1 on error
1304 1264
1305 Reads debug registers from the vcpu. 1265 Reads debug registers from the vcpu.
1306 1266
1307 :: 1267 ::
1308 1268
1309 struct kvm_debugregs { 1269 struct kvm_debugregs {
1310 __u64 db[4]; 1270 __u64 db[4];
1311 __u64 dr6; 1271 __u64 dr6;
1312 __u64 dr7; 1272 __u64 dr7;
1313 __u64 flags; 1273 __u64 flags;
1314 __u64 reserved[9]; 1274 __u64 reserved[9];
1315 }; 1275 };
1316 1276
1317 1277
1318 4.34 KVM_SET_DEBUGREGS 1278 4.34 KVM_SET_DEBUGREGS
1319 ---------------------- 1279 ----------------------
1320 1280
1321 :Capability: KVM_CAP_DEBUGREGS 1281 :Capability: KVM_CAP_DEBUGREGS
1322 :Architectures: x86 1282 :Architectures: x86
1323 :Type: vm ioctl 1283 :Type: vm ioctl
1324 :Parameters: struct kvm_debugregs (in) 1284 :Parameters: struct kvm_debugregs (in)
1325 :Returns: 0 on success, -1 on error 1285 :Returns: 0 on success, -1 on error
1326 1286
1327 Writes debug registers into the vcpu. 1287 Writes debug registers into the vcpu.
1328 1288
1329 See KVM_GET_DEBUGREGS for the data structure. 1289 See KVM_GET_DEBUGREGS for the data structure. The flags field is unused
1330 yet and must be cleared on entry. 1290 yet and must be cleared on entry.
1331 1291
1332 1292
1333 4.35 KVM_SET_USER_MEMORY_REGION 1293 4.35 KVM_SET_USER_MEMORY_REGION
1334 ------------------------------- 1294 -------------------------------
1335 1295
1336 :Capability: KVM_CAP_USER_MEMORY 1296 :Capability: KVM_CAP_USER_MEMORY
1337 :Architectures: all 1297 :Architectures: all
1338 :Type: vm ioctl 1298 :Type: vm ioctl
1339 :Parameters: struct kvm_userspace_memory_regi 1299 :Parameters: struct kvm_userspace_memory_region (in)
1340 :Returns: 0 on success, -1 on error 1300 :Returns: 0 on success, -1 on error
1341 1301
1342 :: 1302 ::
1343 1303
1344 struct kvm_userspace_memory_region { 1304 struct kvm_userspace_memory_region {
1345 __u32 slot; 1305 __u32 slot;
1346 __u32 flags; 1306 __u32 flags;
1347 __u64 guest_phys_addr; 1307 __u64 guest_phys_addr;
1348 __u64 memory_size; /* bytes */ 1308 __u64 memory_size; /* bytes */
1349 __u64 userspace_addr; /* start of the 1309 __u64 userspace_addr; /* start of the userspace allocated memory */
1350 }; 1310 };
1351 1311
1352 /* for kvm_userspace_memory_region::flags * 1312 /* for kvm_userspace_memory_region::flags */
1353 #define KVM_MEM_LOG_DIRTY_PAGES (1UL 1313 #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
1354 #define KVM_MEM_READONLY (1UL << 1) 1314 #define KVM_MEM_READONLY (1UL << 1)
1355 1315
1356 This ioctl allows the user to create, modify 1316 This ioctl allows the user to create, modify or delete a guest physical
1357 memory slot. Bits 0-15 of "slot" specify the 1317 memory slot. Bits 0-15 of "slot" specify the slot id and this value
1358 should be less than the maximum number of use 1318 should be less than the maximum number of user memory slots supported per
1359 VM. The maximum allowed slots can be queried 1319 VM. The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS.
1360 Slots may not overlap in guest physical addre 1320 Slots may not overlap in guest physical address space.
1361 1321
1362 If KVM_CAP_MULTI_ADDRESS_SPACE is available, 1322 If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
1363 specifies the address space which is being mo 1323 specifies the address space which is being modified. They must be
1364 less than the value that KVM_CHECK_EXTENSION 1324 less than the value that KVM_CHECK_EXTENSION returns for the
1365 KVM_CAP_MULTI_ADDRESS_SPACE capability. Slot 1325 KVM_CAP_MULTI_ADDRESS_SPACE capability. Slots in separate address spaces
1366 are unrelated; the restriction on overlapping 1326 are unrelated; the restriction on overlapping slots only applies within
1367 each address space. 1327 each address space.
1368 1328
1369 Deleting a slot is done by passing zero for m 1329 Deleting a slot is done by passing zero for memory_size. When changing
1370 an existing slot, it may be moved in the gues 1330 an existing slot, it may be moved in the guest physical memory space,
1371 or its flags may be modified, but it may not 1331 or its flags may be modified, but it may not be resized.
1372 1332
1373 Memory for the region is taken starting at th 1333 Memory for the region is taken starting at the address denoted by the
1374 field userspace_addr, which must point at use 1334 field userspace_addr, which must point at user addressable memory for
1375 the entire memory slot size. Any object may 1335 the entire memory slot size. Any object may back this memory, including
1376 anonymous memory, ordinary files, and hugetlb 1336 anonymous memory, ordinary files, and hugetlbfs.
1377 1337
1378 On architectures that support a form of addre 1338 On architectures that support a form of address tagging, userspace_addr must
1379 be an untagged address. 1339 be an untagged address.
1380 1340
1381 It is recommended that the lower 21 bits of g 1341 It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
1382 be identical. This allows large pages in the 1342 be identical. This allows large pages in the guest to be backed by large
1383 pages in the host. 1343 pages in the host.
1384 1344
1385 The flags field supports two flags: KVM_MEM_L 1345 The flags field supports two flags: KVM_MEM_LOG_DIRTY_PAGES and
1386 KVM_MEM_READONLY. The former can be set to i 1346 KVM_MEM_READONLY. The former can be set to instruct KVM to keep track of
1387 writes to memory within the slot. See KVM_GE 1347 writes to memory within the slot. See KVM_GET_DIRTY_LOG ioctl to know how to
1388 use it. The latter can be set, if KVM_CAP_RE 1348 use it. The latter can be set, if KVM_CAP_READONLY_MEM capability allows it,
1389 to make a new slot read-only. In this case, 1349 to make a new slot read-only. In this case, writes to this memory will be
1390 posted to userspace as KVM_EXIT_MMIO exits. 1350 posted to userspace as KVM_EXIT_MMIO exits.
1391 1351
1392 When the KVM_CAP_SYNC_MMU capability is avail 1352 When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
1393 the memory region are automatically reflected 1353 the memory region are automatically reflected into the guest. For example, an
1394 mmap() that affects the region will be made v 1354 mmap() that affects the region will be made visible immediately. Another
1395 example is madvise(MADV_DROP). 1355 example is madvise(MADV_DROP).
1396 1356
1397 Note: On arm64, a write generated by the page 1357 Note: On arm64, a write generated by the page-table walker (to update
1398 the Access and Dirty flags, for example) neve 1358 the Access and Dirty flags, for example) never results in a
1399 KVM_EXIT_MMIO exit when the slot has the KVM_ 1359 KVM_EXIT_MMIO exit when the slot has the KVM_MEM_READONLY flag. This
1400 is because KVM cannot provide the data that w 1360 is because KVM cannot provide the data that would be written by the
1401 page-table walker, making it impossible to em 1361 page-table walker, making it impossible to emulate the access.
1402 Instead, an abort (data abort if the cause of 1362 Instead, an abort (data abort if the cause of the page-table update
1403 was a load or a store, instruction abort if i 1363 was a load or a store, instruction abort if it was an instruction
1404 fetch) is injected in the guest. 1364 fetch) is injected in the guest.
1405 1365
1406 S390: <<
1407 ^^^^^ <<
1408 <<
1409 Returns -EINVAL if the VM has the KVM_VM_S390 <<
1410 Returns -EINVAL if called on a protected VM. <<
1411 <<
1412 4.36 KVM_SET_TSS_ADDR 1366 4.36 KVM_SET_TSS_ADDR
1413 --------------------- 1367 ---------------------
1414 1368
1415 :Capability: KVM_CAP_SET_TSS_ADDR 1369 :Capability: KVM_CAP_SET_TSS_ADDR
1416 :Architectures: x86 1370 :Architectures: x86
1417 :Type: vm ioctl 1371 :Type: vm ioctl
1418 :Parameters: unsigned long tss_address (in) 1372 :Parameters: unsigned long tss_address (in)
1419 :Returns: 0 on success, -1 on error 1373 :Returns: 0 on success, -1 on error
1420 1374
1421 This ioctl defines the physical address of a 1375 This ioctl defines the physical address of a three-page region in the guest
1422 physical address space. The region must be w 1376 physical address space. The region must be within the first 4GB of the
1423 guest physical address space and must not con 1377 guest physical address space and must not conflict with any memory slot
1424 or any mmio address. The guest may malfuncti 1378 or any mmio address. The guest may malfunction if it accesses this memory
1425 region. 1379 region.
1426 1380
1427 This ioctl is required on Intel-based hosts. 1381 This ioctl is required on Intel-based hosts. This is needed on Intel hardware
1428 because of a quirk in the virtualization impl 1382 because of a quirk in the virtualization implementation (see the internals
1429 documentation when it pops into existence). 1383 documentation when it pops into existence).
1430 1384
1431 1385
1432 4.37 KVM_ENABLE_CAP 1386 4.37 KVM_ENABLE_CAP
1433 ------------------- 1387 -------------------
1434 1388
1435 :Capability: KVM_CAP_ENABLE_CAP 1389 :Capability: KVM_CAP_ENABLE_CAP
1436 :Architectures: mips, ppc, s390, x86, loongar !! 1390 :Architectures: mips, ppc, s390, x86
1437 :Type: vcpu ioctl 1391 :Type: vcpu ioctl
1438 :Parameters: struct kvm_enable_cap (in) 1392 :Parameters: struct kvm_enable_cap (in)
1439 :Returns: 0 on success; -1 on error 1393 :Returns: 0 on success; -1 on error
1440 1394
1441 :Capability: KVM_CAP_ENABLE_CAP_VM 1395 :Capability: KVM_CAP_ENABLE_CAP_VM
1442 :Architectures: all 1396 :Architectures: all
1443 :Type: vm ioctl 1397 :Type: vm ioctl
1444 :Parameters: struct kvm_enable_cap (in) 1398 :Parameters: struct kvm_enable_cap (in)
1445 :Returns: 0 on success; -1 on error 1399 :Returns: 0 on success; -1 on error
1446 1400
1447 .. note:: 1401 .. note::
1448 1402
1449 Not all extensions are enabled by default. 1403 Not all extensions are enabled by default. Using this ioctl the application
1450 can enable an extension, making it availab 1404 can enable an extension, making it available to the guest.
1451 1405
1452 On systems that do not support this ioctl, it 1406 On systems that do not support this ioctl, it always fails. On systems that
1453 do support it, it only works for extensions t 1407 do support it, it only works for extensions that are supported for enablement.
1454 1408
1455 To check if a capability can be enabled, the 1409 To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should
1456 be used. 1410 be used.
1457 1411
1458 :: 1412 ::
1459 1413
1460 struct kvm_enable_cap { 1414 struct kvm_enable_cap {
1461 /* in */ 1415 /* in */
1462 __u32 cap; 1416 __u32 cap;
1463 1417
1464 The capability that is supposed to get enable 1418 The capability that is supposed to get enabled.
1465 1419
1466 :: 1420 ::
1467 1421
1468 __u32 flags; 1422 __u32 flags;
1469 1423
1470 A bitfield indicating future enhancements. Ha 1424 A bitfield indicating future enhancements. Has to be 0 for now.
1471 1425
1472 :: 1426 ::
1473 1427
1474 __u64 args[4]; 1428 __u64 args[4];
1475 1429
1476 Arguments for enabling a feature. If a featur 1430 Arguments for enabling a feature. If a feature needs initial values to
1477 function properly, this is the place to put t 1431 function properly, this is the place to put them.
1478 1432
1479 :: 1433 ::
1480 1434
1481 __u8 pad[64]; 1435 __u8 pad[64];
1482 }; 1436 };
1483 1437
1484 The vcpu ioctl should be used for vcpu-specif 1438 The vcpu ioctl should be used for vcpu-specific capabilities, the vm ioctl
1485 for vm-wide capabilities. 1439 for vm-wide capabilities.
1486 1440
1487 4.38 KVM_GET_MP_STATE 1441 4.38 KVM_GET_MP_STATE
1488 --------------------- 1442 ---------------------
1489 1443
1490 :Capability: KVM_CAP_MP_STATE 1444 :Capability: KVM_CAP_MP_STATE
1491 :Architectures: x86, s390, arm64, riscv, loon !! 1445 :Architectures: x86, s390, arm64, riscv
1492 :Type: vcpu ioctl 1446 :Type: vcpu ioctl
1493 :Parameters: struct kvm_mp_state (out) 1447 :Parameters: struct kvm_mp_state (out)
1494 :Returns: 0 on success; -1 on error 1448 :Returns: 0 on success; -1 on error
1495 1449
1496 :: 1450 ::
1497 1451
1498 struct kvm_mp_state { 1452 struct kvm_mp_state {
1499 __u32 mp_state; 1453 __u32 mp_state;
1500 }; 1454 };
1501 1455
1502 Returns the vcpu's current "multiprocessing s 1456 Returns the vcpu's current "multiprocessing state" (though also valid on
1503 uniprocessor guests). 1457 uniprocessor guests).
1504 1458
1505 Possible values are: 1459 Possible values are:
1506 1460
1507 ========================== ============ 1461 ========================== ===============================================
1508 KVM_MP_STATE_RUNNABLE the vcpu is 1462 KVM_MP_STATE_RUNNABLE the vcpu is currently running
1509 [x86,arm64,r !! 1463 [x86,arm64,riscv]
1510 KVM_MP_STATE_UNINITIALIZED the vcpu is 1464 KVM_MP_STATE_UNINITIALIZED the vcpu is an application processor (AP)
1511 which has no 1465 which has not yet received an INIT signal [x86]
1512 KVM_MP_STATE_INIT_RECEIVED the vcpu has 1466 KVM_MP_STATE_INIT_RECEIVED the vcpu has received an INIT signal, and is
1513 now ready fo 1467 now ready for a SIPI [x86]
1514 KVM_MP_STATE_HALTED the vcpu has 1468 KVM_MP_STATE_HALTED the vcpu has executed a HLT instruction and
1515 is waiting f 1469 is waiting for an interrupt [x86]
1516 KVM_MP_STATE_SIPI_RECEIVED the vcpu has 1470 KVM_MP_STATE_SIPI_RECEIVED the vcpu has just received a SIPI (vector
1517 accessible v 1471 accessible via KVM_GET_VCPU_EVENTS) [x86]
1518 KVM_MP_STATE_STOPPED the vcpu is 1472 KVM_MP_STATE_STOPPED the vcpu is stopped [s390,arm64,riscv]
1519 KVM_MP_STATE_CHECK_STOP the vcpu is 1473 KVM_MP_STATE_CHECK_STOP the vcpu is in a special error state [s390]
1520 KVM_MP_STATE_OPERATING the vcpu is 1474 KVM_MP_STATE_OPERATING the vcpu is operating (running or halted)
1521 [s390] 1475 [s390]
1522 KVM_MP_STATE_LOAD the vcpu is 1476 KVM_MP_STATE_LOAD the vcpu is in a special load/startup state
1523 [s390] 1477 [s390]
1524 KVM_MP_STATE_SUSPENDED the vcpu is 1478 KVM_MP_STATE_SUSPENDED the vcpu is in a suspend state and is waiting
1525 for a wakeup 1479 for a wakeup event [arm64]
1526 ========================== ============ 1480 ========================== ===============================================
1527 1481
1528 On x86, this ioctl is only useful after KVM_C 1482 On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
1529 in-kernel irqchip, the multiprocessing state 1483 in-kernel irqchip, the multiprocessing state must be maintained by userspace on
1530 these architectures. 1484 these architectures.
1531 1485
1532 For arm64: 1486 For arm64:
1533 ^^^^^^^^^^ 1487 ^^^^^^^^^^
1534 1488
1535 If a vCPU is in the KVM_MP_STATE_SUSPENDED st 1489 If a vCPU is in the KVM_MP_STATE_SUSPENDED state, KVM will emulate the
1536 architectural execution of a WFI instruction. 1490 architectural execution of a WFI instruction.
1537 1491
1538 If a wakeup event is recognized, KVM will exi 1492 If a wakeup event is recognized, KVM will exit to userspace with a
1539 KVM_SYSTEM_EVENT exit, where the event type i 1493 KVM_SYSTEM_EVENT exit, where the event type is KVM_SYSTEM_EVENT_WAKEUP. If
1540 userspace wants to honor the wakeup, it must 1494 userspace wants to honor the wakeup, it must set the vCPU's MP state to
1541 KVM_MP_STATE_RUNNABLE. If it does not, KVM wi 1495 KVM_MP_STATE_RUNNABLE. If it does not, KVM will continue to await a wakeup
1542 event in subsequent calls to KVM_RUN. 1496 event in subsequent calls to KVM_RUN.
1543 1497
1544 .. warning:: 1498 .. warning::
1545 1499
1546 If userspace intends to keep the vCPU in 1500 If userspace intends to keep the vCPU in a SUSPENDED state, it is
1547 strongly recommended that userspace take 1501 strongly recommended that userspace take action to suppress the
1548 wakeup event (such as masking an interru 1502 wakeup event (such as masking an interrupt). Otherwise, subsequent
1549 calls to KVM_RUN will immediately exit w 1503 calls to KVM_RUN will immediately exit with a KVM_SYSTEM_EVENT_WAKEUP
1550 event and inadvertently waste CPU cycles 1504 event and inadvertently waste CPU cycles.
1551 1505
1552 Additionally, if userspace takes action 1506 Additionally, if userspace takes action to suppress a wakeup event,
1553 it is strongly recommended that it also 1507 it is strongly recommended that it also restores the vCPU to its
1554 original state when the vCPU is made RUN 1508 original state when the vCPU is made RUNNABLE again. For example,
1555 if userspace masked a pending interrupt 1509 if userspace masked a pending interrupt to suppress the wakeup,
1556 the interrupt should be unmasked before 1510 the interrupt should be unmasked before returning control to the
1557 guest. 1511 guest.
1558 1512
1559 For riscv: 1513 For riscv:
1560 ^^^^^^^^^^ 1514 ^^^^^^^^^^
1561 1515
1562 The only states that are valid are KVM_MP_STA 1516 The only states that are valid are KVM_MP_STATE_STOPPED and
1563 KVM_MP_STATE_RUNNABLE which reflect if the vc 1517 KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not.
1564 1518
1565 On LoongArch, only the KVM_MP_STATE_RUNNABLE <<
1566 whether the vcpu is runnable. <<
1567 <<
1568 4.39 KVM_SET_MP_STATE 1519 4.39 KVM_SET_MP_STATE
1569 --------------------- 1520 ---------------------
1570 1521
1571 :Capability: KVM_CAP_MP_STATE 1522 :Capability: KVM_CAP_MP_STATE
1572 :Architectures: x86, s390, arm64, riscv, loon !! 1523 :Architectures: x86, s390, arm64, riscv
1573 :Type: vcpu ioctl 1524 :Type: vcpu ioctl
1574 :Parameters: struct kvm_mp_state (in) 1525 :Parameters: struct kvm_mp_state (in)
1575 :Returns: 0 on success; -1 on error 1526 :Returns: 0 on success; -1 on error
1576 1527
1577 Sets the vcpu's current "multiprocessing stat 1528 Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
1578 arguments. 1529 arguments.
1579 1530
1580 On x86, this ioctl is only useful after KVM_C 1531 On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
1581 in-kernel irqchip, the multiprocessing state 1532 in-kernel irqchip, the multiprocessing state must be maintained by userspace on
1582 these architectures. 1533 these architectures.
1583 1534
1584 For arm64/riscv: 1535 For arm64/riscv:
1585 ^^^^^^^^^^^^^^^^ 1536 ^^^^^^^^^^^^^^^^
1586 1537
1587 The only states that are valid are KVM_MP_STA 1538 The only states that are valid are KVM_MP_STATE_STOPPED and
1588 KVM_MP_STATE_RUNNABLE which reflect if the vc 1539 KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not.
1589 1540
1590 On LoongArch, only the KVM_MP_STATE_RUNNABLE <<
1591 whether the vcpu is runnable. <<
1592 <<
1593 4.40 KVM_SET_IDENTITY_MAP_ADDR 1541 4.40 KVM_SET_IDENTITY_MAP_ADDR
1594 ------------------------------ 1542 ------------------------------
1595 1543
1596 :Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR 1544 :Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR
1597 :Architectures: x86 1545 :Architectures: x86
1598 :Type: vm ioctl 1546 :Type: vm ioctl
1599 :Parameters: unsigned long identity (in) 1547 :Parameters: unsigned long identity (in)
1600 :Returns: 0 on success, -1 on error 1548 :Returns: 0 on success, -1 on error
1601 1549
1602 This ioctl defines the physical address of a 1550 This ioctl defines the physical address of a one-page region in the guest
1603 physical address space. The region must be w 1551 physical address space. The region must be within the first 4GB of the
1604 guest physical address space and must not con 1552 guest physical address space and must not conflict with any memory slot
1605 or any mmio address. The guest may malfuncti 1553 or any mmio address. The guest may malfunction if it accesses this memory
1606 region. 1554 region.
1607 1555
1608 Setting the address to 0 will result in reset 1556 Setting the address to 0 will result in resetting the address to its default
1609 (0xfffbc000). 1557 (0xfffbc000).
1610 1558
1611 This ioctl is required on Intel-based hosts. 1559 This ioctl is required on Intel-based hosts. This is needed on Intel hardware
1612 because of a quirk in the virtualization impl 1560 because of a quirk in the virtualization implementation (see the internals
1613 documentation when it pops into existence). 1561 documentation when it pops into existence).
1614 1562
1615 Fails if any VCPU has already been created. 1563 Fails if any VCPU has already been created.
1616 1564
1617 4.41 KVM_SET_BOOT_CPU_ID 1565 4.41 KVM_SET_BOOT_CPU_ID
1618 ------------------------ 1566 ------------------------
1619 1567
1620 :Capability: KVM_CAP_SET_BOOT_CPU_ID 1568 :Capability: KVM_CAP_SET_BOOT_CPU_ID
1621 :Architectures: x86 1569 :Architectures: x86
1622 :Type: vm ioctl 1570 :Type: vm ioctl
1623 :Parameters: unsigned long vcpu_id 1571 :Parameters: unsigned long vcpu_id
1624 :Returns: 0 on success, -1 on error 1572 :Returns: 0 on success, -1 on error
1625 1573
1626 Define which vcpu is the Bootstrap Processor 1574 Define which vcpu is the Bootstrap Processor (BSP). Values are the same
1627 as the vcpu id in KVM_CREATE_VCPU. If this i 1575 as the vcpu id in KVM_CREATE_VCPU. If this ioctl is not called, the default
1628 is vcpu 0. This ioctl has to be called before 1576 is vcpu 0. This ioctl has to be called before vcpu creation,
1629 otherwise it will return EBUSY error. 1577 otherwise it will return EBUSY error.
1630 1578
1631 1579
1632 4.42 KVM_GET_XSAVE 1580 4.42 KVM_GET_XSAVE
1633 ------------------ 1581 ------------------
1634 1582
1635 :Capability: KVM_CAP_XSAVE 1583 :Capability: KVM_CAP_XSAVE
1636 :Architectures: x86 1584 :Architectures: x86
1637 :Type: vcpu ioctl 1585 :Type: vcpu ioctl
1638 :Parameters: struct kvm_xsave (out) 1586 :Parameters: struct kvm_xsave (out)
1639 :Returns: 0 on success, -1 on error 1587 :Returns: 0 on success, -1 on error
1640 1588
1641 1589
1642 :: 1590 ::
1643 1591
1644 struct kvm_xsave { 1592 struct kvm_xsave {
1645 __u32 region[1024]; 1593 __u32 region[1024];
1646 __u32 extra[0]; 1594 __u32 extra[0];
1647 }; 1595 };
1648 1596
1649 This ioctl would copy current vcpu's xsave st 1597 This ioctl would copy current vcpu's xsave struct to the userspace.
1650 1598
1651 1599
1652 4.43 KVM_SET_XSAVE 1600 4.43 KVM_SET_XSAVE
1653 ------------------ 1601 ------------------
1654 1602
1655 :Capability: KVM_CAP_XSAVE and KVM_CAP_XSAVE2 1603 :Capability: KVM_CAP_XSAVE and KVM_CAP_XSAVE2
1656 :Architectures: x86 1604 :Architectures: x86
1657 :Type: vcpu ioctl 1605 :Type: vcpu ioctl
1658 :Parameters: struct kvm_xsave (in) 1606 :Parameters: struct kvm_xsave (in)
1659 :Returns: 0 on success, -1 on error 1607 :Returns: 0 on success, -1 on error
1660 1608
1661 :: 1609 ::
1662 1610
1663 1611
1664 struct kvm_xsave { 1612 struct kvm_xsave {
1665 __u32 region[1024]; 1613 __u32 region[1024];
1666 __u32 extra[0]; 1614 __u32 extra[0];
1667 }; 1615 };
1668 1616
1669 This ioctl would copy userspace's xsave struc 1617 This ioctl would copy userspace's xsave struct to the kernel. It copies
1670 as many bytes as are returned by KVM_CHECK_EX 1618 as many bytes as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2),
1671 when invoked on the vm file descriptor. The s 1619 when invoked on the vm file descriptor. The size value returned by
1672 KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) will alwa 1620 KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) will always be at least 4096.
1673 Currently, it is only greater than 4096 if a 1621 Currently, it is only greater than 4096 if a dynamic feature has been
1674 enabled with ``arch_prctl()``, but this may c 1622 enabled with ``arch_prctl()``, but this may change in the future.
1675 1623
1676 The offsets of the state save areas in struct 1624 The offsets of the state save areas in struct kvm_xsave follow the
1677 contents of CPUID leaf 0xD on the host. 1625 contents of CPUID leaf 0xD on the host.
1678 1626
1679 1627
1680 4.44 KVM_GET_XCRS 1628 4.44 KVM_GET_XCRS
1681 ----------------- 1629 -----------------
1682 1630
1683 :Capability: KVM_CAP_XCRS 1631 :Capability: KVM_CAP_XCRS
1684 :Architectures: x86 1632 :Architectures: x86
1685 :Type: vcpu ioctl 1633 :Type: vcpu ioctl
1686 :Parameters: struct kvm_xcrs (out) 1634 :Parameters: struct kvm_xcrs (out)
1687 :Returns: 0 on success, -1 on error 1635 :Returns: 0 on success, -1 on error
1688 1636
1689 :: 1637 ::
1690 1638
1691 struct kvm_xcr { 1639 struct kvm_xcr {
1692 __u32 xcr; 1640 __u32 xcr;
1693 __u32 reserved; 1641 __u32 reserved;
1694 __u64 value; 1642 __u64 value;
1695 }; 1643 };
1696 1644
1697 struct kvm_xcrs { 1645 struct kvm_xcrs {
1698 __u32 nr_xcrs; 1646 __u32 nr_xcrs;
1699 __u32 flags; 1647 __u32 flags;
1700 struct kvm_xcr xcrs[KVM_MAX_XCRS]; 1648 struct kvm_xcr xcrs[KVM_MAX_XCRS];
1701 __u64 padding[16]; 1649 __u64 padding[16];
1702 }; 1650 };
1703 1651
1704 This ioctl would copy current vcpu's xcrs to 1652 This ioctl would copy current vcpu's xcrs to the userspace.
1705 1653
1706 1654
1707 4.45 KVM_SET_XCRS 1655 4.45 KVM_SET_XCRS
1708 ----------------- 1656 -----------------
1709 1657
1710 :Capability: KVM_CAP_XCRS 1658 :Capability: KVM_CAP_XCRS
1711 :Architectures: x86 1659 :Architectures: x86
1712 :Type: vcpu ioctl 1660 :Type: vcpu ioctl
1713 :Parameters: struct kvm_xcrs (in) 1661 :Parameters: struct kvm_xcrs (in)
1714 :Returns: 0 on success, -1 on error 1662 :Returns: 0 on success, -1 on error
1715 1663
1716 :: 1664 ::
1717 1665
1718 struct kvm_xcr { 1666 struct kvm_xcr {
1719 __u32 xcr; 1667 __u32 xcr;
1720 __u32 reserved; 1668 __u32 reserved;
1721 __u64 value; 1669 __u64 value;
1722 }; 1670 };
1723 1671
1724 struct kvm_xcrs { 1672 struct kvm_xcrs {
1725 __u32 nr_xcrs; 1673 __u32 nr_xcrs;
1726 __u32 flags; 1674 __u32 flags;
1727 struct kvm_xcr xcrs[KVM_MAX_XCRS]; 1675 struct kvm_xcr xcrs[KVM_MAX_XCRS];
1728 __u64 padding[16]; 1676 __u64 padding[16];
1729 }; 1677 };
1730 1678
1731 This ioctl would set vcpu's xcr to the value 1679 This ioctl would set vcpu's xcr to the value userspace specified.
1732 1680
1733 1681
1734 4.46 KVM_GET_SUPPORTED_CPUID 1682 4.46 KVM_GET_SUPPORTED_CPUID
1735 ---------------------------- 1683 ----------------------------
1736 1684
1737 :Capability: KVM_CAP_EXT_CPUID 1685 :Capability: KVM_CAP_EXT_CPUID
1738 :Architectures: x86 1686 :Architectures: x86
1739 :Type: system ioctl 1687 :Type: system ioctl
1740 :Parameters: struct kvm_cpuid2 (in/out) 1688 :Parameters: struct kvm_cpuid2 (in/out)
1741 :Returns: 0 on success, -1 on error 1689 :Returns: 0 on success, -1 on error
1742 1690
1743 :: 1691 ::
1744 1692
1745 struct kvm_cpuid2 { 1693 struct kvm_cpuid2 {
1746 __u32 nent; 1694 __u32 nent;
1747 __u32 padding; 1695 __u32 padding;
1748 struct kvm_cpuid_entry2 entries[0]; 1696 struct kvm_cpuid_entry2 entries[0];
1749 }; 1697 };
1750 1698
1751 #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1699 #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
1752 #define KVM_CPUID_FLAG_STATEFUL_FUNC 1700 #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) /* deprecated */
1753 #define KVM_CPUID_FLAG_STATE_READ_NEXT 1701 #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) /* deprecated */
1754 1702
1755 struct kvm_cpuid_entry2 { 1703 struct kvm_cpuid_entry2 {
1756 __u32 function; 1704 __u32 function;
1757 __u32 index; 1705 __u32 index;
1758 __u32 flags; 1706 __u32 flags;
1759 __u32 eax; 1707 __u32 eax;
1760 __u32 ebx; 1708 __u32 ebx;
1761 __u32 ecx; 1709 __u32 ecx;
1762 __u32 edx; 1710 __u32 edx;
1763 __u32 padding[3]; 1711 __u32 padding[3];
1764 }; 1712 };
1765 1713
1766 This ioctl returns x86 cpuid features which a 1714 This ioctl returns x86 cpuid features which are supported by both the
1767 hardware and kvm in its default configuration 1715 hardware and kvm in its default configuration. Userspace can use the
1768 information returned by this ioctl to constru 1716 information returned by this ioctl to construct cpuid information (for
1769 KVM_SET_CPUID2) that is consistent with hardw 1717 KVM_SET_CPUID2) that is consistent with hardware, kernel, and
1770 userspace capabilities, and with user require 1718 userspace capabilities, and with user requirements (for example, the
1771 user may wish to constrain cpuid to emulate o 1719 user may wish to constrain cpuid to emulate older hardware, or for
1772 feature consistency across a cluster). 1720 feature consistency across a cluster).
1773 1721
1774 Dynamically-enabled feature bits need to be r 1722 Dynamically-enabled feature bits need to be requested with
1775 ``arch_prctl()`` before calling this ioctl. F 1723 ``arch_prctl()`` before calling this ioctl. Feature bits that have not
1776 been requested are excluded from the result. 1724 been requested are excluded from the result.
1777 1725
1778 Note that certain capabilities, such as KVM_C 1726 Note that certain capabilities, such as KVM_CAP_X86_DISABLE_EXITS, may
1779 expose cpuid features (e.g. MONITOR) which ar 1727 expose cpuid features (e.g. MONITOR) which are not supported by kvm in
1780 its default configuration. If userspace enabl 1728 its default configuration. If userspace enables such capabilities, it
1781 is responsible for modifying the results of t 1729 is responsible for modifying the results of this ioctl appropriately.
1782 1730
1783 Userspace invokes KVM_GET_SUPPORTED_CPUID by 1731 Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure
1784 with the 'nent' field indicating the number o 1732 with the 'nent' field indicating the number of entries in the variable-size
1785 array 'entries'. If the number of entries is 1733 array 'entries'. If the number of entries is too low to describe the cpu
1786 capabilities, an error (E2BIG) is returned. 1734 capabilities, an error (E2BIG) is returned. If the number is too high,
1787 the 'nent' field is adjusted and an error (EN 1735 the 'nent' field is adjusted and an error (ENOMEM) is returned. If the
1788 number is just right, the 'nent' field is adj 1736 number is just right, the 'nent' field is adjusted to the number of valid
1789 entries in the 'entries' array, which is then 1737 entries in the 'entries' array, which is then filled.
1790 1738
1791 The entries returned are the host cpuid as re 1739 The entries returned are the host cpuid as returned by the cpuid instruction,
1792 with unknown or unsupported features masked o 1740 with unknown or unsupported features masked out. Some features (for example,
1793 x2apic), may not be present in the host cpu, 1741 x2apic), may not be present in the host cpu, but are exposed by kvm if it can
1794 emulate them efficiently. The fields in each 1742 emulate them efficiently. The fields in each entry are defined as follows:
1795 1743
1796 function: 1744 function:
1797 the eax value used to obtain the ent 1745 the eax value used to obtain the entry
1798 1746
1799 index: 1747 index:
1800 the ecx value used to obtain the ent 1748 the ecx value used to obtain the entry (for entries that are
1801 affected by ecx) 1749 affected by ecx)
1802 1750
1803 flags: 1751 flags:
1804 an OR of zero or more of the following: 1752 an OR of zero or more of the following:
1805 1753
1806 KVM_CPUID_FLAG_SIGNIFCANT_INDEX: 1754 KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
1807 if the index field is valid 1755 if the index field is valid
1808 1756
1809 eax, ebx, ecx, edx: 1757 eax, ebx, ecx, edx:
1810 the values returned by the cpuid ins 1758 the values returned by the cpuid instruction for
1811 this function/index combination 1759 this function/index combination
1812 1760
1813 The TSC deadline timer feature (CPUID leaf 1, 1761 The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned
1814 as false, since the feature depends on KVM_CR 1762 as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC
1815 support. Instead it is reported via:: 1763 support. Instead it is reported via::
1816 1764
1817 ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEAD 1765 ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER)
1818 1766
1819 if that returns true and you use KVM_CREATE_I 1767 if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the
1820 feature in userspace, then you can enable the 1768 feature in userspace, then you can enable the feature for KVM_SET_CPUID2.
1821 1769
1822 1770
1823 4.47 KVM_PPC_GET_PVINFO 1771 4.47 KVM_PPC_GET_PVINFO
1824 ----------------------- 1772 -----------------------
1825 1773
1826 :Capability: KVM_CAP_PPC_GET_PVINFO 1774 :Capability: KVM_CAP_PPC_GET_PVINFO
1827 :Architectures: ppc 1775 :Architectures: ppc
1828 :Type: vm ioctl 1776 :Type: vm ioctl
1829 :Parameters: struct kvm_ppc_pvinfo (out) 1777 :Parameters: struct kvm_ppc_pvinfo (out)
1830 :Returns: 0 on success, !0 on error 1778 :Returns: 0 on success, !0 on error
1831 1779
1832 :: 1780 ::
1833 1781
1834 struct kvm_ppc_pvinfo { 1782 struct kvm_ppc_pvinfo {
1835 __u32 flags; 1783 __u32 flags;
1836 __u32 hcall[4]; 1784 __u32 hcall[4];
1837 __u8 pad[108]; 1785 __u8 pad[108];
1838 }; 1786 };
1839 1787
1840 This ioctl fetches PV specific information th 1788 This ioctl fetches PV specific information that need to be passed to the guest
1841 using the device tree or other means from vm 1789 using the device tree or other means from vm context.
1842 1790
1843 The hcall array defines 4 instructions that m 1791 The hcall array defines 4 instructions that make up a hypercall.
1844 1792
1845 If any additional field gets added to this st 1793 If any additional field gets added to this structure later on, a bit for that
1846 additional piece of information will be set i 1794 additional piece of information will be set in the flags bitmap.
1847 1795
1848 The flags bitmap is defined as:: 1796 The flags bitmap is defined as::
1849 1797
1850 /* the host supports the ePAPR idle hcall 1798 /* the host supports the ePAPR idle hcall
1851 #define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1< 1799 #define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
1852 1800
1853 4.52 KVM_SET_GSI_ROUTING 1801 4.52 KVM_SET_GSI_ROUTING
1854 ------------------------ 1802 ------------------------
1855 1803
1856 :Capability: KVM_CAP_IRQ_ROUTING 1804 :Capability: KVM_CAP_IRQ_ROUTING
1857 :Architectures: x86 s390 arm64 1805 :Architectures: x86 s390 arm64
1858 :Type: vm ioctl 1806 :Type: vm ioctl
1859 :Parameters: struct kvm_irq_routing (in) 1807 :Parameters: struct kvm_irq_routing (in)
1860 :Returns: 0 on success, -1 on error 1808 :Returns: 0 on success, -1 on error
1861 1809
1862 Sets the GSI routing table entries, overwriti 1810 Sets the GSI routing table entries, overwriting any previously set entries.
1863 1811
1864 On arm64, GSI routing has the following limit 1812 On arm64, GSI routing has the following limitation:
1865 1813
1866 - GSI routing does not apply to KVM_IRQ_LINE 1814 - GSI routing does not apply to KVM_IRQ_LINE but only to KVM_IRQFD.
1867 1815
1868 :: 1816 ::
1869 1817
1870 struct kvm_irq_routing { 1818 struct kvm_irq_routing {
1871 __u32 nr; 1819 __u32 nr;
1872 __u32 flags; 1820 __u32 flags;
1873 struct kvm_irq_routing_entry entries[ 1821 struct kvm_irq_routing_entry entries[0];
1874 }; 1822 };
1875 1823
1876 No flags are specified so far, the correspond 1824 No flags are specified so far, the corresponding field must be set to zero.
1877 1825
1878 :: 1826 ::
1879 1827
1880 struct kvm_irq_routing_entry { 1828 struct kvm_irq_routing_entry {
1881 __u32 gsi; 1829 __u32 gsi;
1882 __u32 type; 1830 __u32 type;
1883 __u32 flags; 1831 __u32 flags;
1884 __u32 pad; 1832 __u32 pad;
1885 union { 1833 union {
1886 struct kvm_irq_routing_irqchi 1834 struct kvm_irq_routing_irqchip irqchip;
1887 struct kvm_irq_routing_msi ms 1835 struct kvm_irq_routing_msi msi;
1888 struct kvm_irq_routing_s390_a 1836 struct kvm_irq_routing_s390_adapter adapter;
1889 struct kvm_irq_routing_hv_sin 1837 struct kvm_irq_routing_hv_sint hv_sint;
1890 struct kvm_irq_routing_xen_ev 1838 struct kvm_irq_routing_xen_evtchn xen_evtchn;
1891 __u32 pad[8]; 1839 __u32 pad[8];
1892 } u; 1840 } u;
1893 }; 1841 };
1894 1842
1895 /* gsi routing entry types */ 1843 /* gsi routing entry types */
1896 #define KVM_IRQ_ROUTING_IRQCHIP 1 1844 #define KVM_IRQ_ROUTING_IRQCHIP 1
1897 #define KVM_IRQ_ROUTING_MSI 2 1845 #define KVM_IRQ_ROUTING_MSI 2
1898 #define KVM_IRQ_ROUTING_S390_ADAPTER 3 1846 #define KVM_IRQ_ROUTING_S390_ADAPTER 3
1899 #define KVM_IRQ_ROUTING_HV_SINT 4 1847 #define KVM_IRQ_ROUTING_HV_SINT 4
1900 #define KVM_IRQ_ROUTING_XEN_EVTCHN 5 1848 #define KVM_IRQ_ROUTING_XEN_EVTCHN 5
1901 1849
1902 flags: 1850 flags:
1903 1851
1904 - KVM_MSI_VALID_DEVID: used along with KVM_IR 1852 - KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry
1905 type, specifies that the devid field contai 1853 type, specifies that the devid field contains a valid value. The per-VM
1906 KVM_CAP_MSI_DEVID capability advertises the 1854 KVM_CAP_MSI_DEVID capability advertises the requirement to provide
1907 the device ID. If this capability is not a 1855 the device ID. If this capability is not available, userspace should
1908 never set the KVM_MSI_VALID_DEVID flag as t 1856 never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.
1909 - zero otherwise 1857 - zero otherwise
1910 1858
1911 :: 1859 ::
1912 1860
1913 struct kvm_irq_routing_irqchip { 1861 struct kvm_irq_routing_irqchip {
1914 __u32 irqchip; 1862 __u32 irqchip;
1915 __u32 pin; 1863 __u32 pin;
1916 }; 1864 };
1917 1865
1918 struct kvm_irq_routing_msi { 1866 struct kvm_irq_routing_msi {
1919 __u32 address_lo; 1867 __u32 address_lo;
1920 __u32 address_hi; 1868 __u32 address_hi;
1921 __u32 data; 1869 __u32 data;
1922 union { 1870 union {
1923 __u32 pad; 1871 __u32 pad;
1924 __u32 devid; 1872 __u32 devid;
1925 }; 1873 };
1926 }; 1874 };
1927 1875
1928 If KVM_MSI_VALID_DEVID is set, devid contains 1876 If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier
1929 for the device that wrote the MSI message. F 1877 for the device that wrote the MSI message. For PCI, this is usually a
1930 BDF identifier in the lower 16 bits. !! 1878 BFD identifier in the lower 16 bits.
1931 1879
1932 On x86, address_hi is ignored unless the KVM_ 1880 On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
1933 feature of KVM_CAP_X2APIC_API capability is e 1881 feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled,
1934 address_hi bits 31-8 provide bits 31-8 of the 1882 address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of
1935 address_hi must be zero. 1883 address_hi must be zero.
1936 1884
1937 :: 1885 ::
1938 1886
1939 struct kvm_irq_routing_s390_adapter { 1887 struct kvm_irq_routing_s390_adapter {
1940 __u64 ind_addr; 1888 __u64 ind_addr;
1941 __u64 summary_addr; 1889 __u64 summary_addr;
1942 __u64 ind_offset; 1890 __u64 ind_offset;
1943 __u32 summary_offset; 1891 __u32 summary_offset;
1944 __u32 adapter_id; 1892 __u32 adapter_id;
1945 }; 1893 };
1946 1894
1947 struct kvm_irq_routing_hv_sint { 1895 struct kvm_irq_routing_hv_sint {
1948 __u32 vcpu; 1896 __u32 vcpu;
1949 __u32 sint; 1897 __u32 sint;
1950 }; 1898 };
1951 1899
1952 struct kvm_irq_routing_xen_evtchn { 1900 struct kvm_irq_routing_xen_evtchn {
1953 __u32 port; 1901 __u32 port;
1954 __u32 vcpu; 1902 __u32 vcpu;
1955 __u32 priority; 1903 __u32 priority;
1956 }; 1904 };
1957 1905
1958 1906
1959 When KVM_CAP_XEN_HVM includes the KVM_XEN_HVM 1907 When KVM_CAP_XEN_HVM includes the KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL bit
1960 in its indication of supported features, rout 1908 in its indication of supported features, routing to Xen event channels
1961 is supported. Although the priority field is 1909 is supported. Although the priority field is present, only the value
1962 KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL is supported 1910 KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL is supported, which means delivery by
1963 2 level event channels. FIFO event channel su 1911 2 level event channels. FIFO event channel support may be added in
1964 the future. 1912 the future.
1965 1913
1966 1914
1967 4.55 KVM_SET_TSC_KHZ 1915 4.55 KVM_SET_TSC_KHZ
1968 -------------------- 1916 --------------------
1969 1917
1970 :Capability: KVM_CAP_TSC_CONTROL / KVM_CAP_VM 1918 :Capability: KVM_CAP_TSC_CONTROL / KVM_CAP_VM_TSC_CONTROL
1971 :Architectures: x86 1919 :Architectures: x86
1972 :Type: vcpu ioctl / vm ioctl 1920 :Type: vcpu ioctl / vm ioctl
1973 :Parameters: virtual tsc_khz 1921 :Parameters: virtual tsc_khz
1974 :Returns: 0 on success, -1 on error 1922 :Returns: 0 on success, -1 on error
1975 1923
1976 Specifies the tsc frequency for the virtual m 1924 Specifies the tsc frequency for the virtual machine. The unit of the
1977 frequency is KHz. 1925 frequency is KHz.
1978 1926
1979 If the KVM_CAP_VM_TSC_CONTROL capability is a 1927 If the KVM_CAP_VM_TSC_CONTROL capability is advertised, this can also
1980 be used as a vm ioctl to set the initial tsc 1928 be used as a vm ioctl to set the initial tsc frequency of subsequently
1981 created vCPUs. 1929 created vCPUs.
1982 1930
1983 4.56 KVM_GET_TSC_KHZ 1931 4.56 KVM_GET_TSC_KHZ
1984 -------------------- 1932 --------------------
1985 1933
1986 :Capability: KVM_CAP_GET_TSC_KHZ / KVM_CAP_VM 1934 :Capability: KVM_CAP_GET_TSC_KHZ / KVM_CAP_VM_TSC_CONTROL
1987 :Architectures: x86 1935 :Architectures: x86
1988 :Type: vcpu ioctl / vm ioctl 1936 :Type: vcpu ioctl / vm ioctl
1989 :Parameters: none 1937 :Parameters: none
1990 :Returns: virtual tsc-khz on success, negativ 1938 :Returns: virtual tsc-khz on success, negative value on error
1991 1939
1992 Returns the tsc frequency of the guest. The u 1940 Returns the tsc frequency of the guest. The unit of the return value is
1993 KHz. If the host has unstable tsc this ioctl 1941 KHz. If the host has unstable tsc this ioctl returns -EIO instead as an
1994 error. 1942 error.
1995 1943
1996 1944
1997 4.57 KVM_GET_LAPIC 1945 4.57 KVM_GET_LAPIC
1998 ------------------ 1946 ------------------
1999 1947
2000 :Capability: KVM_CAP_IRQCHIP 1948 :Capability: KVM_CAP_IRQCHIP
2001 :Architectures: x86 1949 :Architectures: x86
2002 :Type: vcpu ioctl 1950 :Type: vcpu ioctl
2003 :Parameters: struct kvm_lapic_state (out) 1951 :Parameters: struct kvm_lapic_state (out)
2004 :Returns: 0 on success, -1 on error 1952 :Returns: 0 on success, -1 on error
2005 1953
2006 :: 1954 ::
2007 1955
2008 #define KVM_APIC_REG_SIZE 0x400 1956 #define KVM_APIC_REG_SIZE 0x400
2009 struct kvm_lapic_state { 1957 struct kvm_lapic_state {
2010 char regs[KVM_APIC_REG_SIZE]; 1958 char regs[KVM_APIC_REG_SIZE];
2011 }; 1959 };
2012 1960
2013 Reads the Local APIC registers and copies the 1961 Reads the Local APIC registers and copies them into the input argument. The
2014 data format and layout are the same as docume 1962 data format and layout are the same as documented in the architecture manual.
2015 1963
2016 If KVM_X2APIC_API_USE_32BIT_IDS feature of KV 1964 If KVM_X2APIC_API_USE_32BIT_IDS feature of KVM_CAP_X2APIC_API is
2017 enabled, then the format of APIC_ID register 1965 enabled, then the format of APIC_ID register depends on the APIC mode
2018 (reported by MSR_IA32_APICBASE) of its VCPU. 1966 (reported by MSR_IA32_APICBASE) of its VCPU. x2APIC stores APIC ID in
2019 the APIC_ID register (bytes 32-35). xAPIC on 1967 the APIC_ID register (bytes 32-35). xAPIC only allows an 8-bit APIC ID
2020 which is stored in bits 31-24 of the APIC reg 1968 which is stored in bits 31-24 of the APIC register, or equivalently in
2021 byte 35 of struct kvm_lapic_state's regs fiel 1969 byte 35 of struct kvm_lapic_state's regs field. KVM_GET_LAPIC must then
2022 be called after MSR_IA32_APICBASE has been se 1970 be called after MSR_IA32_APICBASE has been set with KVM_SET_MSR.
2023 1971
2024 If KVM_X2APIC_API_USE_32BIT_IDS feature is di 1972 If KVM_X2APIC_API_USE_32BIT_IDS feature is disabled, struct kvm_lapic_state
2025 always uses xAPIC format. 1973 always uses xAPIC format.
2026 1974
2027 1975
2028 4.58 KVM_SET_LAPIC 1976 4.58 KVM_SET_LAPIC
2029 ------------------ 1977 ------------------
2030 1978
2031 :Capability: KVM_CAP_IRQCHIP 1979 :Capability: KVM_CAP_IRQCHIP
2032 :Architectures: x86 1980 :Architectures: x86
2033 :Type: vcpu ioctl 1981 :Type: vcpu ioctl
2034 :Parameters: struct kvm_lapic_state (in) 1982 :Parameters: struct kvm_lapic_state (in)
2035 :Returns: 0 on success, -1 on error 1983 :Returns: 0 on success, -1 on error
2036 1984
2037 :: 1985 ::
2038 1986
2039 #define KVM_APIC_REG_SIZE 0x400 1987 #define KVM_APIC_REG_SIZE 0x400
2040 struct kvm_lapic_state { 1988 struct kvm_lapic_state {
2041 char regs[KVM_APIC_REG_SIZE]; 1989 char regs[KVM_APIC_REG_SIZE];
2042 }; 1990 };
2043 1991
2044 Copies the input argument into the Local APIC 1992 Copies the input argument into the Local APIC registers. The data format
2045 and layout are the same as documented in the 1993 and layout are the same as documented in the architecture manual.
2046 1994
2047 The format of the APIC ID register (bytes 32- 1995 The format of the APIC ID register (bytes 32-35 of struct kvm_lapic_state's
2048 regs field) depends on the state of the KVM_C 1996 regs field) depends on the state of the KVM_CAP_X2APIC_API capability.
2049 See the note in KVM_GET_LAPIC. 1997 See the note in KVM_GET_LAPIC.
2050 1998
2051 1999
2052 4.59 KVM_IOEVENTFD 2000 4.59 KVM_IOEVENTFD
2053 ------------------ 2001 ------------------
2054 2002
2055 :Capability: KVM_CAP_IOEVENTFD 2003 :Capability: KVM_CAP_IOEVENTFD
2056 :Architectures: all 2004 :Architectures: all
2057 :Type: vm ioctl 2005 :Type: vm ioctl
2058 :Parameters: struct kvm_ioeventfd (in) 2006 :Parameters: struct kvm_ioeventfd (in)
2059 :Returns: 0 on success, !0 on error 2007 :Returns: 0 on success, !0 on error
2060 2008
2061 This ioctl attaches or detaches an ioeventfd 2009 This ioctl attaches or detaches an ioeventfd to a legal pio/mmio address
2062 within the guest. A guest write in the regis 2010 within the guest. A guest write in the registered address will signal the
2063 provided event instead of triggering an exit. 2011 provided event instead of triggering an exit.
2064 2012
2065 :: 2013 ::
2066 2014
2067 struct kvm_ioeventfd { 2015 struct kvm_ioeventfd {
2068 __u64 datamatch; 2016 __u64 datamatch;
2069 __u64 addr; /* legal pio/mmio 2017 __u64 addr; /* legal pio/mmio address */
2070 __u32 len; /* 0, 1, 2, 4, or 2018 __u32 len; /* 0, 1, 2, 4, or 8 bytes */
2071 __s32 fd; 2019 __s32 fd;
2072 __u32 flags; 2020 __u32 flags;
2073 __u8 pad[36]; 2021 __u8 pad[36];
2074 }; 2022 };
2075 2023
2076 For the special case of virtio-ccw devices on 2024 For the special case of virtio-ccw devices on s390, the ioevent is matched
2077 to a subchannel/virtqueue tuple instead. 2025 to a subchannel/virtqueue tuple instead.
2078 2026
2079 The following flags are defined:: 2027 The following flags are defined::
2080 2028
2081 #define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << 2029 #define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
2082 #define KVM_IOEVENTFD_FLAG_PIO (1 << 2030 #define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio)
2083 #define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << 2031 #define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign)
2084 #define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIF 2032 #define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
2085 (1 << kvm_ioeventfd_flag_nr_virtio_cc 2033 (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify)
2086 2034
2087 If datamatch flag is set, the event will be s 2035 If datamatch flag is set, the event will be signaled only if the written value
2088 to the registered address is equal to datamat 2036 to the registered address is equal to datamatch in struct kvm_ioeventfd.
2089 2037
2090 For virtio-ccw devices, addr contains the sub 2038 For virtio-ccw devices, addr contains the subchannel id and datamatch the
2091 virtqueue index. 2039 virtqueue index.
2092 2040
2093 With KVM_CAP_IOEVENTFD_ANY_LENGTH, a zero len 2041 With KVM_CAP_IOEVENTFD_ANY_LENGTH, a zero length ioeventfd is allowed, and
2094 the kernel will ignore the length of guest wr 2042 the kernel will ignore the length of guest write and may get a faster vmexit.
2095 The speedup may only apply to specific archit 2043 The speedup may only apply to specific architectures, but the ioeventfd will
2096 work anyway. 2044 work anyway.
2097 2045
2098 4.60 KVM_DIRTY_TLB 2046 4.60 KVM_DIRTY_TLB
2099 ------------------ 2047 ------------------
2100 2048
2101 :Capability: KVM_CAP_SW_TLB 2049 :Capability: KVM_CAP_SW_TLB
2102 :Architectures: ppc 2050 :Architectures: ppc
2103 :Type: vcpu ioctl 2051 :Type: vcpu ioctl
2104 :Parameters: struct kvm_dirty_tlb (in) 2052 :Parameters: struct kvm_dirty_tlb (in)
2105 :Returns: 0 on success, -1 on error 2053 :Returns: 0 on success, -1 on error
2106 2054
2107 :: 2055 ::
2108 2056
2109 struct kvm_dirty_tlb { 2057 struct kvm_dirty_tlb {
2110 __u64 bitmap; 2058 __u64 bitmap;
2111 __u32 num_dirty; 2059 __u32 num_dirty;
2112 }; 2060 };
2113 2061
2114 This must be called whenever userspace has ch 2062 This must be called whenever userspace has changed an entry in the shared
2115 TLB, prior to calling KVM_RUN on the associat 2063 TLB, prior to calling KVM_RUN on the associated vcpu.
2116 2064
2117 The "bitmap" field is the userspace address o 2065 The "bitmap" field is the userspace address of an array. This array
2118 consists of a number of bits, equal to the to 2066 consists of a number of bits, equal to the total number of TLB entries as
2119 determined by the last successful call to KVM 2067 determined by the last successful call to KVM_CONFIG_TLB, rounded up to the
2120 nearest multiple of 64. 2068 nearest multiple of 64.
2121 2069
2122 Each bit corresponds to one TLB entry, ordere 2070 Each bit corresponds to one TLB entry, ordered the same as in the shared TLB
2123 array. 2071 array.
2124 2072
2125 The array is little-endian: the bit 0 is the 2073 The array is little-endian: the bit 0 is the least significant bit of the
2126 first byte, bit 8 is the least significant bi 2074 first byte, bit 8 is the least significant bit of the second byte, etc.
2127 This avoids any complications with differing 2075 This avoids any complications with differing word sizes.
2128 2076
2129 The "num_dirty" field is a performance hint f 2077 The "num_dirty" field is a performance hint for KVM to determine whether it
2130 should skip processing the bitmap and just in 2078 should skip processing the bitmap and just invalidate everything. It must
2131 be set to the number of set bits in the bitma 2079 be set to the number of set bits in the bitmap.
2132 2080
2133 2081
2134 4.62 KVM_CREATE_SPAPR_TCE 2082 4.62 KVM_CREATE_SPAPR_TCE
2135 ------------------------- 2083 -------------------------
2136 2084
2137 :Capability: KVM_CAP_SPAPR_TCE 2085 :Capability: KVM_CAP_SPAPR_TCE
2138 :Architectures: powerpc 2086 :Architectures: powerpc
2139 :Type: vm ioctl 2087 :Type: vm ioctl
2140 :Parameters: struct kvm_create_spapr_tce (in) 2088 :Parameters: struct kvm_create_spapr_tce (in)
2141 :Returns: file descriptor for manipulating th 2089 :Returns: file descriptor for manipulating the created TCE table
2142 2090
2143 This creates a virtual TCE (translation contr 2091 This creates a virtual TCE (translation control entry) table, which
2144 is an IOMMU for PAPR-style virtual I/O. It i 2092 is an IOMMU for PAPR-style virtual I/O. It is used to translate
2145 logical addresses used in virtual I/O into gu 2093 logical addresses used in virtual I/O into guest physical addresses,
2146 and provides a scatter/gather capability for 2094 and provides a scatter/gather capability for PAPR virtual I/O.
2147 2095
2148 :: 2096 ::
2149 2097
2150 /* for KVM_CAP_SPAPR_TCE */ 2098 /* for KVM_CAP_SPAPR_TCE */
2151 struct kvm_create_spapr_tce { 2099 struct kvm_create_spapr_tce {
2152 __u64 liobn; 2100 __u64 liobn;
2153 __u32 window_size; 2101 __u32 window_size;
2154 }; 2102 };
2155 2103
2156 The liobn field gives the logical IO bus numb 2104 The liobn field gives the logical IO bus number for which to create a
2157 TCE table. The window_size field specifies t 2105 TCE table. The window_size field specifies the size of the DMA window
2158 which this TCE table will translate - the tab 2106 which this TCE table will translate - the table will contain one 64
2159 bit TCE entry for every 4kiB of the DMA windo 2107 bit TCE entry for every 4kiB of the DMA window.
2160 2108
2161 When the guest issues an H_PUT_TCE hcall on a 2109 When the guest issues an H_PUT_TCE hcall on a liobn for which a TCE
2162 table has been created using this ioctl(), th 2110 table has been created using this ioctl(), the kernel will handle it
2163 in real mode, updating the TCE table. H_PUT_ 2111 in real mode, updating the TCE table. H_PUT_TCE calls for other
2164 liobns will cause a vm exit and must be handl 2112 liobns will cause a vm exit and must be handled by userspace.
2165 2113
2166 The return value is a file descriptor which c 2114 The return value is a file descriptor which can be passed to mmap(2)
2167 to map the created TCE table into userspace. 2115 to map the created TCE table into userspace. This lets userspace read
2168 the entries written by kernel-handled H_PUT_T 2116 the entries written by kernel-handled H_PUT_TCE calls, and also lets
2169 userspace update the TCE table directly which 2117 userspace update the TCE table directly which is useful in some
2170 circumstances. 2118 circumstances.
2171 2119
2172 2120
2173 4.63 KVM_ALLOCATE_RMA 2121 4.63 KVM_ALLOCATE_RMA
2174 --------------------- 2122 ---------------------
2175 2123
2176 :Capability: KVM_CAP_PPC_RMA 2124 :Capability: KVM_CAP_PPC_RMA
2177 :Architectures: powerpc 2125 :Architectures: powerpc
2178 :Type: vm ioctl 2126 :Type: vm ioctl
2179 :Parameters: struct kvm_allocate_rma (out) 2127 :Parameters: struct kvm_allocate_rma (out)
2180 :Returns: file descriptor for mapping the all 2128 :Returns: file descriptor for mapping the allocated RMA
2181 2129
2182 This allocates a Real Mode Area (RMA) from th 2130 This allocates a Real Mode Area (RMA) from the pool allocated at boot
2183 time by the kernel. An RMA is a physically-c 2131 time by the kernel. An RMA is a physically-contiguous, aligned region
2184 of memory used on older POWER processors to p 2132 of memory used on older POWER processors to provide the memory which
2185 will be accessed by real-mode (MMU off) acces 2133 will be accessed by real-mode (MMU off) accesses in a KVM guest.
2186 POWER processors support a set of sizes for t 2134 POWER processors support a set of sizes for the RMA that usually
2187 includes 64MB, 128MB, 256MB and some larger p 2135 includes 64MB, 128MB, 256MB and some larger powers of two.
2188 2136
2189 :: 2137 ::
2190 2138
2191 /* for KVM_ALLOCATE_RMA */ 2139 /* for KVM_ALLOCATE_RMA */
2192 struct kvm_allocate_rma { 2140 struct kvm_allocate_rma {
2193 __u64 rma_size; 2141 __u64 rma_size;
2194 }; 2142 };
2195 2143
2196 The return value is a file descriptor which c 2144 The return value is a file descriptor which can be passed to mmap(2)
2197 to map the allocated RMA into userspace. The 2145 to map the allocated RMA into userspace. The mapped area can then be
2198 passed to the KVM_SET_USER_MEMORY_REGION ioct 2146 passed to the KVM_SET_USER_MEMORY_REGION ioctl to establish it as the
2199 RMA for a virtual machine. The size of the R 2147 RMA for a virtual machine. The size of the RMA in bytes (which is
2200 fixed at host kernel boot time) is returned i 2148 fixed at host kernel boot time) is returned in the rma_size field of
2201 the argument structure. 2149 the argument structure.
2202 2150
2203 The KVM_CAP_PPC_RMA capability is 1 or 2 if t 2151 The KVM_CAP_PPC_RMA capability is 1 or 2 if the KVM_ALLOCATE_RMA ioctl
2204 is supported; 2 if the processor requires all 2152 is supported; 2 if the processor requires all virtual machines to have
2205 an RMA, or 1 if the processor can use an RMA 2153 an RMA, or 1 if the processor can use an RMA but doesn't require it,
2206 because it supports the Virtual RMA (VRMA) fa 2154 because it supports the Virtual RMA (VRMA) facility.
2207 2155
2208 2156
2209 4.64 KVM_NMI 2157 4.64 KVM_NMI
2210 ------------ 2158 ------------
2211 2159
2212 :Capability: KVM_CAP_USER_NMI 2160 :Capability: KVM_CAP_USER_NMI
2213 :Architectures: x86 2161 :Architectures: x86
2214 :Type: vcpu ioctl 2162 :Type: vcpu ioctl
2215 :Parameters: none 2163 :Parameters: none
2216 :Returns: 0 on success, -1 on error 2164 :Returns: 0 on success, -1 on error
2217 2165
2218 Queues an NMI on the thread's vcpu. Note thi 2166 Queues an NMI on the thread's vcpu. Note this is well defined only
2219 when KVM_CREATE_IRQCHIP has not been called, 2167 when KVM_CREATE_IRQCHIP has not been called, since this is an interface
2220 between the virtual cpu core and virtual loca 2168 between the virtual cpu core and virtual local APIC. After KVM_CREATE_IRQCHIP
2221 has been called, this interface is completely 2169 has been called, this interface is completely emulated within the kernel.
2222 2170
2223 To use this to emulate the LINT1 input with K 2171 To use this to emulate the LINT1 input with KVM_CREATE_IRQCHIP, use the
2224 following algorithm: 2172 following algorithm:
2225 2173
2226 - pause the vcpu 2174 - pause the vcpu
2227 - read the local APIC's state (KVM_GET_LAPI 2175 - read the local APIC's state (KVM_GET_LAPIC)
2228 - check whether changing LINT1 will queue a 2176 - check whether changing LINT1 will queue an NMI (see the LVT entry for LINT1)
2229 - if so, issue KVM_NMI 2177 - if so, issue KVM_NMI
2230 - resume the vcpu 2178 - resume the vcpu
2231 2179
2232 Some guests configure the LINT1 NMI input to 2180 Some guests configure the LINT1 NMI input to cause a panic, aiding in
2233 debugging. 2181 debugging.
2234 2182
2235 2183
2236 4.65 KVM_S390_UCAS_MAP 2184 4.65 KVM_S390_UCAS_MAP
2237 ---------------------- 2185 ----------------------
2238 2186
2239 :Capability: KVM_CAP_S390_UCONTROL 2187 :Capability: KVM_CAP_S390_UCONTROL
2240 :Architectures: s390 2188 :Architectures: s390
2241 :Type: vcpu ioctl 2189 :Type: vcpu ioctl
2242 :Parameters: struct kvm_s390_ucas_mapping (in 2190 :Parameters: struct kvm_s390_ucas_mapping (in)
2243 :Returns: 0 in case of success 2191 :Returns: 0 in case of success
2244 2192
2245 The parameter is defined like this:: 2193 The parameter is defined like this::
2246 2194
2247 struct kvm_s390_ucas_mapping { 2195 struct kvm_s390_ucas_mapping {
2248 __u64 user_addr; 2196 __u64 user_addr;
2249 __u64 vcpu_addr; 2197 __u64 vcpu_addr;
2250 __u64 length; 2198 __u64 length;
2251 }; 2199 };
2252 2200
2253 This ioctl maps the memory at "user_addr" wit 2201 This ioctl maps the memory at "user_addr" with the length "length" to
2254 the vcpu's address space starting at "vcpu_ad 2202 the vcpu's address space starting at "vcpu_addr". All parameters need to
2255 be aligned by 1 megabyte. 2203 be aligned by 1 megabyte.
2256 2204
2257 2205
2258 4.66 KVM_S390_UCAS_UNMAP 2206 4.66 KVM_S390_UCAS_UNMAP
2259 ------------------------ 2207 ------------------------
2260 2208
2261 :Capability: KVM_CAP_S390_UCONTROL 2209 :Capability: KVM_CAP_S390_UCONTROL
2262 :Architectures: s390 2210 :Architectures: s390
2263 :Type: vcpu ioctl 2211 :Type: vcpu ioctl
2264 :Parameters: struct kvm_s390_ucas_mapping (in 2212 :Parameters: struct kvm_s390_ucas_mapping (in)
2265 :Returns: 0 in case of success 2213 :Returns: 0 in case of success
2266 2214
2267 The parameter is defined like this:: 2215 The parameter is defined like this::
2268 2216
2269 struct kvm_s390_ucas_mapping { 2217 struct kvm_s390_ucas_mapping {
2270 __u64 user_addr; 2218 __u64 user_addr;
2271 __u64 vcpu_addr; 2219 __u64 vcpu_addr;
2272 __u64 length; 2220 __u64 length;
2273 }; 2221 };
2274 2222
2275 This ioctl unmaps the memory in the vcpu's ad 2223 This ioctl unmaps the memory in the vcpu's address space starting at
2276 "vcpu_addr" with the length "length". The fie 2224 "vcpu_addr" with the length "length". The field "user_addr" is ignored.
2277 All parameters need to be aligned by 1 megaby 2225 All parameters need to be aligned by 1 megabyte.
2278 2226
2279 2227
2280 4.67 KVM_S390_VCPU_FAULT 2228 4.67 KVM_S390_VCPU_FAULT
2281 ------------------------ 2229 ------------------------
2282 2230
2283 :Capability: KVM_CAP_S390_UCONTROL 2231 :Capability: KVM_CAP_S390_UCONTROL
2284 :Architectures: s390 2232 :Architectures: s390
2285 :Type: vcpu ioctl 2233 :Type: vcpu ioctl
2286 :Parameters: vcpu absolute address (in) 2234 :Parameters: vcpu absolute address (in)
2287 :Returns: 0 in case of success 2235 :Returns: 0 in case of success
2288 2236
2289 This call creates a page table entry on the v 2237 This call creates a page table entry on the virtual cpu's address space
2290 (for user controlled virtual machines) or the 2238 (for user controlled virtual machines) or the virtual machine's address
2291 space (for regular virtual machines). This on 2239 space (for regular virtual machines). This only works for minor faults,
2292 thus it's recommended to access subject memor 2240 thus it's recommended to access subject memory page via the user page
2293 table upfront. This is useful to handle valid 2241 table upfront. This is useful to handle validity intercepts for user
2294 controlled virtual machines to fault in the v 2242 controlled virtual machines to fault in the virtual cpu's lowcore pages
2295 prior to calling the KVM_RUN ioctl. 2243 prior to calling the KVM_RUN ioctl.
2296 2244
2297 2245
2298 4.68 KVM_SET_ONE_REG 2246 4.68 KVM_SET_ONE_REG
2299 -------------------- 2247 --------------------
2300 2248
2301 :Capability: KVM_CAP_ONE_REG 2249 :Capability: KVM_CAP_ONE_REG
2302 :Architectures: all 2250 :Architectures: all
2303 :Type: vcpu ioctl 2251 :Type: vcpu ioctl
2304 :Parameters: struct kvm_one_reg (in) 2252 :Parameters: struct kvm_one_reg (in)
2305 :Returns: 0 on success, negative value on fai 2253 :Returns: 0 on success, negative value on failure
2306 2254
2307 Errors: 2255 Errors:
2308 2256
2309 ====== ================================== 2257 ====== ============================================================
2310 ENOENT no such register 2258 ENOENT no such register
2311 EINVAL invalid register ID, or no such re 2259 EINVAL invalid register ID, or no such register or used with VMs in
2312 protected virtualization mode on s 2260 protected virtualization mode on s390
2313 EPERM (arm64) register access not allowe 2261 EPERM (arm64) register access not allowed before vcpu finalization
2314 EBUSY (riscv) changing register value no <<
2315 has run at least once <<
2316 ====== ================================== 2262 ====== ============================================================
2317 2263
2318 (These error codes are indicative only: do no 2264 (These error codes are indicative only: do not rely on a specific error
2319 code being returned in a specific situation.) 2265 code being returned in a specific situation.)
2320 2266
2321 :: 2267 ::
2322 2268
2323 struct kvm_one_reg { 2269 struct kvm_one_reg {
2324 __u64 id; 2270 __u64 id;
2325 __u64 addr; 2271 __u64 addr;
2326 }; 2272 };
2327 2273
2328 Using this ioctl, a single vcpu register can 2274 Using this ioctl, a single vcpu register can be set to a specific value
2329 defined by user space with the passed in stru 2275 defined by user space with the passed in struct kvm_one_reg, where id
2330 refers to the register identifier as describe 2276 refers to the register identifier as described below and addr is a pointer
2331 to a variable with the respective size. There 2277 to a variable with the respective size. There can be architecture agnostic
2332 and architecture specific registers. Each hav 2278 and architecture specific registers. Each have their own range of operation
2333 and their own constants and width. To keep tr 2279 and their own constants and width. To keep track of the implemented
2334 registers, find a list below: 2280 registers, find a list below:
2335 2281
2336 ======= =============================== === 2282 ======= =============================== ============
2337 Arch Register Wid 2283 Arch Register Width (bits)
2338 ======= =============================== === 2284 ======= =============================== ============
2339 PPC KVM_REG_PPC_HIOR 64 2285 PPC KVM_REG_PPC_HIOR 64
2340 PPC KVM_REG_PPC_IAC1 64 2286 PPC KVM_REG_PPC_IAC1 64
2341 PPC KVM_REG_PPC_IAC2 64 2287 PPC KVM_REG_PPC_IAC2 64
2342 PPC KVM_REG_PPC_IAC3 64 2288 PPC KVM_REG_PPC_IAC3 64
2343 PPC KVM_REG_PPC_IAC4 64 2289 PPC KVM_REG_PPC_IAC4 64
2344 PPC KVM_REG_PPC_DAC1 64 2290 PPC KVM_REG_PPC_DAC1 64
2345 PPC KVM_REG_PPC_DAC2 64 2291 PPC KVM_REG_PPC_DAC2 64
2346 PPC KVM_REG_PPC_DABR 64 2292 PPC KVM_REG_PPC_DABR 64
2347 PPC KVM_REG_PPC_DSCR 64 2293 PPC KVM_REG_PPC_DSCR 64
2348 PPC KVM_REG_PPC_PURR 64 2294 PPC KVM_REG_PPC_PURR 64
2349 PPC KVM_REG_PPC_SPURR 64 2295 PPC KVM_REG_PPC_SPURR 64
2350 PPC KVM_REG_PPC_DAR 64 2296 PPC KVM_REG_PPC_DAR 64
2351 PPC KVM_REG_PPC_DSISR 32 2297 PPC KVM_REG_PPC_DSISR 32
2352 PPC KVM_REG_PPC_AMR 64 2298 PPC KVM_REG_PPC_AMR 64
2353 PPC KVM_REG_PPC_UAMOR 64 2299 PPC KVM_REG_PPC_UAMOR 64
2354 PPC KVM_REG_PPC_MMCR0 64 2300 PPC KVM_REG_PPC_MMCR0 64
2355 PPC KVM_REG_PPC_MMCR1 64 2301 PPC KVM_REG_PPC_MMCR1 64
2356 PPC KVM_REG_PPC_MMCRA 64 2302 PPC KVM_REG_PPC_MMCRA 64
2357 PPC KVM_REG_PPC_MMCR2 64 2303 PPC KVM_REG_PPC_MMCR2 64
2358 PPC KVM_REG_PPC_MMCRS 64 2304 PPC KVM_REG_PPC_MMCRS 64
2359 PPC KVM_REG_PPC_MMCR3 64 2305 PPC KVM_REG_PPC_MMCR3 64
2360 PPC KVM_REG_PPC_SIAR 64 2306 PPC KVM_REG_PPC_SIAR 64
2361 PPC KVM_REG_PPC_SDAR 64 2307 PPC KVM_REG_PPC_SDAR 64
2362 PPC KVM_REG_PPC_SIER 64 2308 PPC KVM_REG_PPC_SIER 64
2363 PPC KVM_REG_PPC_SIER2 64 2309 PPC KVM_REG_PPC_SIER2 64
2364 PPC KVM_REG_PPC_SIER3 64 2310 PPC KVM_REG_PPC_SIER3 64
2365 PPC KVM_REG_PPC_PMC1 32 2311 PPC KVM_REG_PPC_PMC1 32
2366 PPC KVM_REG_PPC_PMC2 32 2312 PPC KVM_REG_PPC_PMC2 32
2367 PPC KVM_REG_PPC_PMC3 32 2313 PPC KVM_REG_PPC_PMC3 32
2368 PPC KVM_REG_PPC_PMC4 32 2314 PPC KVM_REG_PPC_PMC4 32
2369 PPC KVM_REG_PPC_PMC5 32 2315 PPC KVM_REG_PPC_PMC5 32
2370 PPC KVM_REG_PPC_PMC6 32 2316 PPC KVM_REG_PPC_PMC6 32
2371 PPC KVM_REG_PPC_PMC7 32 2317 PPC KVM_REG_PPC_PMC7 32
2372 PPC KVM_REG_PPC_PMC8 32 2318 PPC KVM_REG_PPC_PMC8 32
2373 PPC KVM_REG_PPC_FPR0 64 2319 PPC KVM_REG_PPC_FPR0 64
2374 ... 2320 ...
2375 PPC KVM_REG_PPC_FPR31 64 2321 PPC KVM_REG_PPC_FPR31 64
2376 PPC KVM_REG_PPC_VR0 128 2322 PPC KVM_REG_PPC_VR0 128
2377 ... 2323 ...
2378 PPC KVM_REG_PPC_VR31 128 2324 PPC KVM_REG_PPC_VR31 128
2379 PPC KVM_REG_PPC_VSR0 128 2325 PPC KVM_REG_PPC_VSR0 128
2380 ... 2326 ...
2381 PPC KVM_REG_PPC_VSR31 128 2327 PPC KVM_REG_PPC_VSR31 128
2382 PPC KVM_REG_PPC_FPSCR 64 2328 PPC KVM_REG_PPC_FPSCR 64
2383 PPC KVM_REG_PPC_VSCR 32 2329 PPC KVM_REG_PPC_VSCR 32
2384 PPC KVM_REG_PPC_VPA_ADDR 64 2330 PPC KVM_REG_PPC_VPA_ADDR 64
2385 PPC KVM_REG_PPC_VPA_SLB 128 2331 PPC KVM_REG_PPC_VPA_SLB 128
2386 PPC KVM_REG_PPC_VPA_DTL 128 2332 PPC KVM_REG_PPC_VPA_DTL 128
2387 PPC KVM_REG_PPC_EPCR 32 2333 PPC KVM_REG_PPC_EPCR 32
2388 PPC KVM_REG_PPC_EPR 32 2334 PPC KVM_REG_PPC_EPR 32
2389 PPC KVM_REG_PPC_TCR 32 2335 PPC KVM_REG_PPC_TCR 32
2390 PPC KVM_REG_PPC_TSR 32 2336 PPC KVM_REG_PPC_TSR 32
2391 PPC KVM_REG_PPC_OR_TSR 32 2337 PPC KVM_REG_PPC_OR_TSR 32
2392 PPC KVM_REG_PPC_CLEAR_TSR 32 2338 PPC KVM_REG_PPC_CLEAR_TSR 32
2393 PPC KVM_REG_PPC_MAS0 32 2339 PPC KVM_REG_PPC_MAS0 32
2394 PPC KVM_REG_PPC_MAS1 32 2340 PPC KVM_REG_PPC_MAS1 32
2395 PPC KVM_REG_PPC_MAS2 64 2341 PPC KVM_REG_PPC_MAS2 64
2396 PPC KVM_REG_PPC_MAS7_3 64 2342 PPC KVM_REG_PPC_MAS7_3 64
2397 PPC KVM_REG_PPC_MAS4 32 2343 PPC KVM_REG_PPC_MAS4 32
2398 PPC KVM_REG_PPC_MAS6 32 2344 PPC KVM_REG_PPC_MAS6 32
2399 PPC KVM_REG_PPC_MMUCFG 32 2345 PPC KVM_REG_PPC_MMUCFG 32
2400 PPC KVM_REG_PPC_TLB0CFG 32 2346 PPC KVM_REG_PPC_TLB0CFG 32
2401 PPC KVM_REG_PPC_TLB1CFG 32 2347 PPC KVM_REG_PPC_TLB1CFG 32
2402 PPC KVM_REG_PPC_TLB2CFG 32 2348 PPC KVM_REG_PPC_TLB2CFG 32
2403 PPC KVM_REG_PPC_TLB3CFG 32 2349 PPC KVM_REG_PPC_TLB3CFG 32
2404 PPC KVM_REG_PPC_TLB0PS 32 2350 PPC KVM_REG_PPC_TLB0PS 32
2405 PPC KVM_REG_PPC_TLB1PS 32 2351 PPC KVM_REG_PPC_TLB1PS 32
2406 PPC KVM_REG_PPC_TLB2PS 32 2352 PPC KVM_REG_PPC_TLB2PS 32
2407 PPC KVM_REG_PPC_TLB3PS 32 2353 PPC KVM_REG_PPC_TLB3PS 32
2408 PPC KVM_REG_PPC_EPTCFG 32 2354 PPC KVM_REG_PPC_EPTCFG 32
2409 PPC KVM_REG_PPC_ICP_STATE 64 2355 PPC KVM_REG_PPC_ICP_STATE 64
2410 PPC KVM_REG_PPC_VP_STATE 128 2356 PPC KVM_REG_PPC_VP_STATE 128
2411 PPC KVM_REG_PPC_TB_OFFSET 64 2357 PPC KVM_REG_PPC_TB_OFFSET 64
2412 PPC KVM_REG_PPC_SPMC1 32 2358 PPC KVM_REG_PPC_SPMC1 32
2413 PPC KVM_REG_PPC_SPMC2 32 2359 PPC KVM_REG_PPC_SPMC2 32
2414 PPC KVM_REG_PPC_IAMR 64 2360 PPC KVM_REG_PPC_IAMR 64
2415 PPC KVM_REG_PPC_TFHAR 64 2361 PPC KVM_REG_PPC_TFHAR 64
2416 PPC KVM_REG_PPC_TFIAR 64 2362 PPC KVM_REG_PPC_TFIAR 64
2417 PPC KVM_REG_PPC_TEXASR 64 2363 PPC KVM_REG_PPC_TEXASR 64
2418 PPC KVM_REG_PPC_FSCR 64 2364 PPC KVM_REG_PPC_FSCR 64
2419 PPC KVM_REG_PPC_PSPB 32 2365 PPC KVM_REG_PPC_PSPB 32
2420 PPC KVM_REG_PPC_EBBHR 64 2366 PPC KVM_REG_PPC_EBBHR 64
2421 PPC KVM_REG_PPC_EBBRR 64 2367 PPC KVM_REG_PPC_EBBRR 64
2422 PPC KVM_REG_PPC_BESCR 64 2368 PPC KVM_REG_PPC_BESCR 64
2423 PPC KVM_REG_PPC_TAR 64 2369 PPC KVM_REG_PPC_TAR 64
2424 PPC KVM_REG_PPC_DPDES 64 2370 PPC KVM_REG_PPC_DPDES 64
2425 PPC KVM_REG_PPC_DAWR 64 2371 PPC KVM_REG_PPC_DAWR 64
2426 PPC KVM_REG_PPC_DAWRX 64 2372 PPC KVM_REG_PPC_DAWRX 64
2427 PPC KVM_REG_PPC_CIABR 64 2373 PPC KVM_REG_PPC_CIABR 64
2428 PPC KVM_REG_PPC_IC 64 2374 PPC KVM_REG_PPC_IC 64
2429 PPC KVM_REG_PPC_VTB 64 2375 PPC KVM_REG_PPC_VTB 64
2430 PPC KVM_REG_PPC_CSIGR 64 2376 PPC KVM_REG_PPC_CSIGR 64
2431 PPC KVM_REG_PPC_TACR 64 2377 PPC KVM_REG_PPC_TACR 64
2432 PPC KVM_REG_PPC_TCSCR 64 2378 PPC KVM_REG_PPC_TCSCR 64
2433 PPC KVM_REG_PPC_PID 64 2379 PPC KVM_REG_PPC_PID 64
2434 PPC KVM_REG_PPC_ACOP 64 2380 PPC KVM_REG_PPC_ACOP 64
2435 PPC KVM_REG_PPC_VRSAVE 32 2381 PPC KVM_REG_PPC_VRSAVE 32
2436 PPC KVM_REG_PPC_LPCR 32 2382 PPC KVM_REG_PPC_LPCR 32
2437 PPC KVM_REG_PPC_LPCR_64 64 2383 PPC KVM_REG_PPC_LPCR_64 64
2438 PPC KVM_REG_PPC_PPR 64 2384 PPC KVM_REG_PPC_PPR 64
2439 PPC KVM_REG_PPC_ARCH_COMPAT 32 2385 PPC KVM_REG_PPC_ARCH_COMPAT 32
2440 PPC KVM_REG_PPC_DABRX 32 2386 PPC KVM_REG_PPC_DABRX 32
2441 PPC KVM_REG_PPC_WORT 64 2387 PPC KVM_REG_PPC_WORT 64
2442 PPC KVM_REG_PPC_SPRG9 64 2388 PPC KVM_REG_PPC_SPRG9 64
2443 PPC KVM_REG_PPC_DBSR 32 2389 PPC KVM_REG_PPC_DBSR 32
2444 PPC KVM_REG_PPC_TIDR 64 2390 PPC KVM_REG_PPC_TIDR 64
2445 PPC KVM_REG_PPC_PSSCR 64 2391 PPC KVM_REG_PPC_PSSCR 64
2446 PPC KVM_REG_PPC_DEC_EXPIRY 64 2392 PPC KVM_REG_PPC_DEC_EXPIRY 64
2447 PPC KVM_REG_PPC_PTCR 64 2393 PPC KVM_REG_PPC_PTCR 64
2448 PPC KVM_REG_PPC_HASHKEYR 64 <<
2449 PPC KVM_REG_PPC_HASHPKEYR 64 <<
2450 PPC KVM_REG_PPC_DAWR1 64 2394 PPC KVM_REG_PPC_DAWR1 64
2451 PPC KVM_REG_PPC_DAWRX1 64 2395 PPC KVM_REG_PPC_DAWRX1 64
2452 PPC KVM_REG_PPC_DEXCR 64 <<
2453 PPC KVM_REG_PPC_TM_GPR0 64 2396 PPC KVM_REG_PPC_TM_GPR0 64
2454 ... 2397 ...
2455 PPC KVM_REG_PPC_TM_GPR31 64 2398 PPC KVM_REG_PPC_TM_GPR31 64
2456 PPC KVM_REG_PPC_TM_VSR0 128 2399 PPC KVM_REG_PPC_TM_VSR0 128
2457 ... 2400 ...
2458 PPC KVM_REG_PPC_TM_VSR63 128 2401 PPC KVM_REG_PPC_TM_VSR63 128
2459 PPC KVM_REG_PPC_TM_CR 64 2402 PPC KVM_REG_PPC_TM_CR 64
2460 PPC KVM_REG_PPC_TM_LR 64 2403 PPC KVM_REG_PPC_TM_LR 64
2461 PPC KVM_REG_PPC_TM_CTR 64 2404 PPC KVM_REG_PPC_TM_CTR 64
2462 PPC KVM_REG_PPC_TM_FPSCR 64 2405 PPC KVM_REG_PPC_TM_FPSCR 64
2463 PPC KVM_REG_PPC_TM_AMR 64 2406 PPC KVM_REG_PPC_TM_AMR 64
2464 PPC KVM_REG_PPC_TM_PPR 64 2407 PPC KVM_REG_PPC_TM_PPR 64
2465 PPC KVM_REG_PPC_TM_VRSAVE 64 2408 PPC KVM_REG_PPC_TM_VRSAVE 64
2466 PPC KVM_REG_PPC_TM_VSCR 32 2409 PPC KVM_REG_PPC_TM_VSCR 32
2467 PPC KVM_REG_PPC_TM_DSCR 64 2410 PPC KVM_REG_PPC_TM_DSCR 64
2468 PPC KVM_REG_PPC_TM_TAR 64 2411 PPC KVM_REG_PPC_TM_TAR 64
2469 PPC KVM_REG_PPC_TM_XER 64 2412 PPC KVM_REG_PPC_TM_XER 64
2470 2413
2471 MIPS KVM_REG_MIPS_R0 64 2414 MIPS KVM_REG_MIPS_R0 64
2472 ... 2415 ...
2473 MIPS KVM_REG_MIPS_R31 64 2416 MIPS KVM_REG_MIPS_R31 64
2474 MIPS KVM_REG_MIPS_HI 64 2417 MIPS KVM_REG_MIPS_HI 64
2475 MIPS KVM_REG_MIPS_LO 64 2418 MIPS KVM_REG_MIPS_LO 64
2476 MIPS KVM_REG_MIPS_PC 64 2419 MIPS KVM_REG_MIPS_PC 64
2477 MIPS KVM_REG_MIPS_CP0_INDEX 32 2420 MIPS KVM_REG_MIPS_CP0_INDEX 32
2478 MIPS KVM_REG_MIPS_CP0_ENTRYLO0 64 2421 MIPS KVM_REG_MIPS_CP0_ENTRYLO0 64
2479 MIPS KVM_REG_MIPS_CP0_ENTRYLO1 64 2422 MIPS KVM_REG_MIPS_CP0_ENTRYLO1 64
2480 MIPS KVM_REG_MIPS_CP0_CONTEXT 64 2423 MIPS KVM_REG_MIPS_CP0_CONTEXT 64
2481 MIPS KVM_REG_MIPS_CP0_CONTEXTCONFIG 32 2424 MIPS KVM_REG_MIPS_CP0_CONTEXTCONFIG 32
2482 MIPS KVM_REG_MIPS_CP0_USERLOCAL 64 2425 MIPS KVM_REG_MIPS_CP0_USERLOCAL 64
2483 MIPS KVM_REG_MIPS_CP0_XCONTEXTCONFIG 64 2426 MIPS KVM_REG_MIPS_CP0_XCONTEXTCONFIG 64
2484 MIPS KVM_REG_MIPS_CP0_PAGEMASK 32 2427 MIPS KVM_REG_MIPS_CP0_PAGEMASK 32
2485 MIPS KVM_REG_MIPS_CP0_PAGEGRAIN 32 2428 MIPS KVM_REG_MIPS_CP0_PAGEGRAIN 32
2486 MIPS KVM_REG_MIPS_CP0_SEGCTL0 64 2429 MIPS KVM_REG_MIPS_CP0_SEGCTL0 64
2487 MIPS KVM_REG_MIPS_CP0_SEGCTL1 64 2430 MIPS KVM_REG_MIPS_CP0_SEGCTL1 64
2488 MIPS KVM_REG_MIPS_CP0_SEGCTL2 64 2431 MIPS KVM_REG_MIPS_CP0_SEGCTL2 64
2489 MIPS KVM_REG_MIPS_CP0_PWBASE 64 2432 MIPS KVM_REG_MIPS_CP0_PWBASE 64
2490 MIPS KVM_REG_MIPS_CP0_PWFIELD 64 2433 MIPS KVM_REG_MIPS_CP0_PWFIELD 64
2491 MIPS KVM_REG_MIPS_CP0_PWSIZE 64 2434 MIPS KVM_REG_MIPS_CP0_PWSIZE 64
2492 MIPS KVM_REG_MIPS_CP0_WIRED 32 2435 MIPS KVM_REG_MIPS_CP0_WIRED 32
2493 MIPS KVM_REG_MIPS_CP0_PWCTL 32 2436 MIPS KVM_REG_MIPS_CP0_PWCTL 32
2494 MIPS KVM_REG_MIPS_CP0_HWRENA 32 2437 MIPS KVM_REG_MIPS_CP0_HWRENA 32
2495 MIPS KVM_REG_MIPS_CP0_BADVADDR 64 2438 MIPS KVM_REG_MIPS_CP0_BADVADDR 64
2496 MIPS KVM_REG_MIPS_CP0_BADINSTR 32 2439 MIPS KVM_REG_MIPS_CP0_BADINSTR 32
2497 MIPS KVM_REG_MIPS_CP0_BADINSTRP 32 2440 MIPS KVM_REG_MIPS_CP0_BADINSTRP 32
2498 MIPS KVM_REG_MIPS_CP0_COUNT 32 2441 MIPS KVM_REG_MIPS_CP0_COUNT 32
2499 MIPS KVM_REG_MIPS_CP0_ENTRYHI 64 2442 MIPS KVM_REG_MIPS_CP0_ENTRYHI 64
2500 MIPS KVM_REG_MIPS_CP0_COMPARE 32 2443 MIPS KVM_REG_MIPS_CP0_COMPARE 32
2501 MIPS KVM_REG_MIPS_CP0_STATUS 32 2444 MIPS KVM_REG_MIPS_CP0_STATUS 32
2502 MIPS KVM_REG_MIPS_CP0_INTCTL 32 2445 MIPS KVM_REG_MIPS_CP0_INTCTL 32
2503 MIPS KVM_REG_MIPS_CP0_CAUSE 32 2446 MIPS KVM_REG_MIPS_CP0_CAUSE 32
2504 MIPS KVM_REG_MIPS_CP0_EPC 64 2447 MIPS KVM_REG_MIPS_CP0_EPC 64
2505 MIPS KVM_REG_MIPS_CP0_PRID 32 2448 MIPS KVM_REG_MIPS_CP0_PRID 32
2506 MIPS KVM_REG_MIPS_CP0_EBASE 64 2449 MIPS KVM_REG_MIPS_CP0_EBASE 64
2507 MIPS KVM_REG_MIPS_CP0_CONFIG 32 2450 MIPS KVM_REG_MIPS_CP0_CONFIG 32
2508 MIPS KVM_REG_MIPS_CP0_CONFIG1 32 2451 MIPS KVM_REG_MIPS_CP0_CONFIG1 32
2509 MIPS KVM_REG_MIPS_CP0_CONFIG2 32 2452 MIPS KVM_REG_MIPS_CP0_CONFIG2 32
2510 MIPS KVM_REG_MIPS_CP0_CONFIG3 32 2453 MIPS KVM_REG_MIPS_CP0_CONFIG3 32
2511 MIPS KVM_REG_MIPS_CP0_CONFIG4 32 2454 MIPS KVM_REG_MIPS_CP0_CONFIG4 32
2512 MIPS KVM_REG_MIPS_CP0_CONFIG5 32 2455 MIPS KVM_REG_MIPS_CP0_CONFIG5 32
2513 MIPS KVM_REG_MIPS_CP0_CONFIG7 32 2456 MIPS KVM_REG_MIPS_CP0_CONFIG7 32
2514 MIPS KVM_REG_MIPS_CP0_XCONTEXT 64 2457 MIPS KVM_REG_MIPS_CP0_XCONTEXT 64
2515 MIPS KVM_REG_MIPS_CP0_ERROREPC 64 2458 MIPS KVM_REG_MIPS_CP0_ERROREPC 64
2516 MIPS KVM_REG_MIPS_CP0_KSCRATCH1 64 2459 MIPS KVM_REG_MIPS_CP0_KSCRATCH1 64
2517 MIPS KVM_REG_MIPS_CP0_KSCRATCH2 64 2460 MIPS KVM_REG_MIPS_CP0_KSCRATCH2 64
2518 MIPS KVM_REG_MIPS_CP0_KSCRATCH3 64 2461 MIPS KVM_REG_MIPS_CP0_KSCRATCH3 64
2519 MIPS KVM_REG_MIPS_CP0_KSCRATCH4 64 2462 MIPS KVM_REG_MIPS_CP0_KSCRATCH4 64
2520 MIPS KVM_REG_MIPS_CP0_KSCRATCH5 64 2463 MIPS KVM_REG_MIPS_CP0_KSCRATCH5 64
2521 MIPS KVM_REG_MIPS_CP0_KSCRATCH6 64 2464 MIPS KVM_REG_MIPS_CP0_KSCRATCH6 64
2522 MIPS KVM_REG_MIPS_CP0_MAAR(0..63) 64 2465 MIPS KVM_REG_MIPS_CP0_MAAR(0..63) 64
2523 MIPS KVM_REG_MIPS_COUNT_CTL 64 2466 MIPS KVM_REG_MIPS_COUNT_CTL 64
2524 MIPS KVM_REG_MIPS_COUNT_RESUME 64 2467 MIPS KVM_REG_MIPS_COUNT_RESUME 64
2525 MIPS KVM_REG_MIPS_COUNT_HZ 64 2468 MIPS KVM_REG_MIPS_COUNT_HZ 64
2526 MIPS KVM_REG_MIPS_FPR_32(0..31) 32 2469 MIPS KVM_REG_MIPS_FPR_32(0..31) 32
2527 MIPS KVM_REG_MIPS_FPR_64(0..31) 64 2470 MIPS KVM_REG_MIPS_FPR_64(0..31) 64
2528 MIPS KVM_REG_MIPS_VEC_128(0..31) 128 2471 MIPS KVM_REG_MIPS_VEC_128(0..31) 128
2529 MIPS KVM_REG_MIPS_FCR_IR 32 2472 MIPS KVM_REG_MIPS_FCR_IR 32
2530 MIPS KVM_REG_MIPS_FCR_CSR 32 2473 MIPS KVM_REG_MIPS_FCR_CSR 32
2531 MIPS KVM_REG_MIPS_MSA_IR 32 2474 MIPS KVM_REG_MIPS_MSA_IR 32
2532 MIPS KVM_REG_MIPS_MSA_CSR 32 2475 MIPS KVM_REG_MIPS_MSA_CSR 32
2533 ======= =============================== === 2476 ======= =============================== ============
2534 2477
2535 ARM registers are mapped using the lower 32 b 2478 ARM registers are mapped using the lower 32 bits. The upper 16 of that
2536 is the register group type, or coprocessor nu 2479 is the register group type, or coprocessor number:
2537 2480
2538 ARM core registers have the following id bit 2481 ARM core registers have the following id bit patterns::
2539 2482
2540 0x4020 0000 0010 <index into the kvm_regs s 2483 0x4020 0000 0010 <index into the kvm_regs struct:16>
2541 2484
2542 ARM 32-bit CP15 registers have the following 2485 ARM 32-bit CP15 registers have the following id bit patterns::
2543 2486
2544 0x4020 0000 000F <zero:1> <crn:4> <crm:4> < 2487 0x4020 0000 000F <zero:1> <crn:4> <crm:4> <opc1:4> <opc2:3>
2545 2488
2546 ARM 64-bit CP15 registers have the following 2489 ARM 64-bit CP15 registers have the following id bit patterns::
2547 2490
2548 0x4030 0000 000F <zero:1> <zero:4> <crm:4> 2491 0x4030 0000 000F <zero:1> <zero:4> <crm:4> <opc1:4> <zero:3>
2549 2492
2550 ARM CCSIDR registers are demultiplexed by CSS 2493 ARM CCSIDR registers are demultiplexed by CSSELR value::
2551 2494
2552 0x4020 0000 0011 00 <csselr:8> 2495 0x4020 0000 0011 00 <csselr:8>
2553 2496
2554 ARM 32-bit VFP control registers have the fol 2497 ARM 32-bit VFP control registers have the following id bit patterns::
2555 2498
2556 0x4020 0000 0012 1 <regno:12> 2499 0x4020 0000 0012 1 <regno:12>
2557 2500
2558 ARM 64-bit FP registers have the following id 2501 ARM 64-bit FP registers have the following id bit patterns::
2559 2502
2560 0x4030 0000 0012 0 <regno:12> 2503 0x4030 0000 0012 0 <regno:12>
2561 2504
2562 ARM firmware pseudo-registers have the follow 2505 ARM firmware pseudo-registers have the following bit pattern::
2563 2506
2564 0x4030 0000 0014 <regno:16> 2507 0x4030 0000 0014 <regno:16>
2565 2508
2566 2509
2567 arm64 registers are mapped using the lower 32 2510 arm64 registers are mapped using the lower 32 bits. The upper 16 of
2568 that is the register group type, or coprocess 2511 that is the register group type, or coprocessor number:
2569 2512
2570 arm64 core/FP-SIMD registers have the followi 2513 arm64 core/FP-SIMD registers have the following id bit patterns. Note
2571 that the size of the access is variable, as t 2514 that the size of the access is variable, as the kvm_regs structure
2572 contains elements ranging from 32 to 128 bits 2515 contains elements ranging from 32 to 128 bits. The index is a 32bit
2573 value in the kvm_regs structure seen as a 32b 2516 value in the kvm_regs structure seen as a 32bit array::
2574 2517
2575 0x60x0 0000 0010 <index into the kvm_regs s 2518 0x60x0 0000 0010 <index into the kvm_regs struct:16>
2576 2519
2577 Specifically: 2520 Specifically:
2578 2521
2579 ======================= ========= ===== ===== 2522 ======================= ========= ===== =======================================
2580 Encoding Register Bits kvm_r 2523 Encoding Register Bits kvm_regs member
2581 ======================= ========= ===== ===== 2524 ======================= ========= ===== =======================================
2582 0x6030 0000 0010 0000 X0 64 regs. 2525 0x6030 0000 0010 0000 X0 64 regs.regs[0]
2583 0x6030 0000 0010 0002 X1 64 regs. 2526 0x6030 0000 0010 0002 X1 64 regs.regs[1]
2584 ... 2527 ...
2585 0x6030 0000 0010 003c X30 64 regs. 2528 0x6030 0000 0010 003c X30 64 regs.regs[30]
2586 0x6030 0000 0010 003e SP 64 regs. 2529 0x6030 0000 0010 003e SP 64 regs.sp
2587 0x6030 0000 0010 0040 PC 64 regs. 2530 0x6030 0000 0010 0040 PC 64 regs.pc
2588 0x6030 0000 0010 0042 PSTATE 64 regs. 2531 0x6030 0000 0010 0042 PSTATE 64 regs.pstate
2589 0x6030 0000 0010 0044 SP_EL1 64 sp_el 2532 0x6030 0000 0010 0044 SP_EL1 64 sp_el1
2590 0x6030 0000 0010 0046 ELR_EL1 64 elr_e 2533 0x6030 0000 0010 0046 ELR_EL1 64 elr_el1
2591 0x6030 0000 0010 0048 SPSR_EL1 64 spsr[ 2534 0x6030 0000 0010 0048 SPSR_EL1 64 spsr[KVM_SPSR_EL1] (alias SPSR_SVC)
2592 0x6030 0000 0010 004a SPSR_ABT 64 spsr[ 2535 0x6030 0000 0010 004a SPSR_ABT 64 spsr[KVM_SPSR_ABT]
2593 0x6030 0000 0010 004c SPSR_UND 64 spsr[ 2536 0x6030 0000 0010 004c SPSR_UND 64 spsr[KVM_SPSR_UND]
2594 0x6030 0000 0010 004e SPSR_IRQ 64 spsr[ 2537 0x6030 0000 0010 004e SPSR_IRQ 64 spsr[KVM_SPSR_IRQ]
2595 0x6030 0000 0010 0050 SPSR_FIQ 64 spsr[ !! 2538 0x6060 0000 0010 0050 SPSR_FIQ 64 spsr[KVM_SPSR_FIQ]
2596 0x6040 0000 0010 0054 V0 128 fp_re 2539 0x6040 0000 0010 0054 V0 128 fp_regs.vregs[0] [1]_
2597 0x6040 0000 0010 0058 V1 128 fp_re 2540 0x6040 0000 0010 0058 V1 128 fp_regs.vregs[1] [1]_
2598 ... 2541 ...
2599 0x6040 0000 0010 00d0 V31 128 fp_re 2542 0x6040 0000 0010 00d0 V31 128 fp_regs.vregs[31] [1]_
2600 0x6020 0000 0010 00d4 FPSR 32 fp_re 2543 0x6020 0000 0010 00d4 FPSR 32 fp_regs.fpsr
2601 0x6020 0000 0010 00d5 FPCR 32 fp_re 2544 0x6020 0000 0010 00d5 FPCR 32 fp_regs.fpcr
2602 ======================= ========= ===== ===== 2545 ======================= ========= ===== =======================================
2603 2546
2604 .. [1] These encodings are not accepted for S 2547 .. [1] These encodings are not accepted for SVE-enabled vcpus. See
2605 KVM_ARM_VCPU_INIT. 2548 KVM_ARM_VCPU_INIT.
2606 2549
2607 The equivalent register content can be 2550 The equivalent register content can be accessed via bits [127:0] of
2608 the corresponding SVE Zn registers ins 2551 the corresponding SVE Zn registers instead for vcpus that have SVE
2609 enabled (see below). 2552 enabled (see below).
2610 2553
2611 arm64 CCSIDR registers are demultiplexed by C 2554 arm64 CCSIDR registers are demultiplexed by CSSELR value::
2612 2555
2613 0x6020 0000 0011 00 <csselr:8> 2556 0x6020 0000 0011 00 <csselr:8>
2614 2557
2615 arm64 system registers have the following id 2558 arm64 system registers have the following id bit patterns::
2616 2559
2617 0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <c 2560 0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
2618 2561
2619 .. warning:: 2562 .. warning::
2620 2563
2621 Two system register IDs do not follow th 2564 Two system register IDs do not follow the specified pattern. These
2622 are KVM_REG_ARM_TIMER_CVAL and KVM_REG_A 2565 are KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT, which map to
2623 system registers CNTV_CVAL_EL0 and CNTVC 2566 system registers CNTV_CVAL_EL0 and CNTVCT_EL0 respectively. These
2624 two had their values accidentally swappe 2567 two had their values accidentally swapped, which means TIMER_CVAL is
2625 derived from the register encoding for C 2568 derived from the register encoding for CNTVCT_EL0 and TIMER_CNT is
2626 derived from the register encoding for C 2569 derived from the register encoding for CNTV_CVAL_EL0. As this is
2627 API, it must remain this way. 2570 API, it must remain this way.
2628 2571
2629 arm64 firmware pseudo-registers have the foll 2572 arm64 firmware pseudo-registers have the following bit pattern::
2630 2573
2631 0x6030 0000 0014 <regno:16> 2574 0x6030 0000 0014 <regno:16>
2632 2575
2633 arm64 SVE registers have the following bit pa 2576 arm64 SVE registers have the following bit patterns::
2634 2577
2635 0x6080 0000 0015 00 <n:5> <slice:5> Zn bi 2578 0x6080 0000 0015 00 <n:5> <slice:5> Zn bits[2048*slice + 2047 : 2048*slice]
2636 0x6050 0000 0015 04 <n:4> <slice:5> Pn bi 2579 0x6050 0000 0015 04 <n:4> <slice:5> Pn bits[256*slice + 255 : 256*slice]
2637 0x6050 0000 0015 060 <slice:5> FFR b 2580 0x6050 0000 0015 060 <slice:5> FFR bits[256*slice + 255 : 256*slice]
2638 0x6060 0000 0015 ffff KVM_R 2581 0x6060 0000 0015 ffff KVM_REG_ARM64_SVE_VLS pseudo-register
2639 2582
2640 Access to register IDs where 2048 * slice >= 2583 Access to register IDs where 2048 * slice >= 128 * max_vq will fail with
2641 ENOENT. max_vq is the vcpu's maximum support 2584 ENOENT. max_vq is the vcpu's maximum supported vector length in 128-bit
2642 quadwords: see [2]_ below. 2585 quadwords: see [2]_ below.
2643 2586
2644 These registers are only accessible on vcpus 2587 These registers are only accessible on vcpus for which SVE is enabled.
2645 See KVM_ARM_VCPU_INIT for details. 2588 See KVM_ARM_VCPU_INIT for details.
2646 2589
2647 In addition, except for KVM_REG_ARM64_SVE_VLS 2590 In addition, except for KVM_REG_ARM64_SVE_VLS, these registers are not
2648 accessible until the vcpu's SVE configuration 2591 accessible until the vcpu's SVE configuration has been finalized
2649 using KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE) 2592 using KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE). See KVM_ARM_VCPU_INIT
2650 and KVM_ARM_VCPU_FINALIZE for more informatio 2593 and KVM_ARM_VCPU_FINALIZE for more information about this procedure.
2651 2594
2652 KVM_REG_ARM64_SVE_VLS is a pseudo-register th 2595 KVM_REG_ARM64_SVE_VLS is a pseudo-register that allows the set of vector
2653 lengths supported by the vcpu to be discovere 2596 lengths supported by the vcpu to be discovered and configured by
2654 userspace. When transferred to or from user 2597 userspace. When transferred to or from user memory via KVM_GET_ONE_REG
2655 or KVM_SET_ONE_REG, the value of this registe 2598 or KVM_SET_ONE_REG, the value of this register is of type
2656 __u64[KVM_ARM64_SVE_VLS_WORDS], and encodes t 2599 __u64[KVM_ARM64_SVE_VLS_WORDS], and encodes the set of vector lengths as
2657 follows:: 2600 follows::
2658 2601
2659 __u64 vector_lengths[KVM_ARM64_SVE_VLS_WORD 2602 __u64 vector_lengths[KVM_ARM64_SVE_VLS_WORDS];
2660 2603
2661 if (vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX && 2604 if (vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX &&
2662 ((vector_lengths[(vq - KVM_ARM64_SVE_VQ 2605 ((vector_lengths[(vq - KVM_ARM64_SVE_VQ_MIN) / 64] >>
2663 ((vq - KVM_ARM64_SVE_VQ_MIN) 2606 ((vq - KVM_ARM64_SVE_VQ_MIN) % 64)) & 1))
2664 /* Vector length vq * 16 bytes suppor 2607 /* Vector length vq * 16 bytes supported */
2665 else 2608 else
2666 /* Vector length vq * 16 bytes not su 2609 /* Vector length vq * 16 bytes not supported */
2667 2610
2668 .. [2] The maximum value vq for which the abo 2611 .. [2] The maximum value vq for which the above condition is true is
2669 max_vq. This is the maximum vector le 2612 max_vq. This is the maximum vector length available to the guest on
2670 this vcpu, and determines which regist 2613 this vcpu, and determines which register slices are visible through
2671 this ioctl interface. 2614 this ioctl interface.
2672 2615
2673 (See Documentation/arch/arm64/sve.rst for an 2616 (See Documentation/arch/arm64/sve.rst for an explanation of the "vq"
2674 nomenclature.) 2617 nomenclature.)
2675 2618
2676 KVM_REG_ARM64_SVE_VLS is only accessible afte 2619 KVM_REG_ARM64_SVE_VLS is only accessible after KVM_ARM_VCPU_INIT.
2677 KVM_ARM_VCPU_INIT initialises it to the best 2620 KVM_ARM_VCPU_INIT initialises it to the best set of vector lengths that
2678 the host supports. 2621 the host supports.
2679 2622
2680 Userspace may subsequently modify it if desir 2623 Userspace may subsequently modify it if desired until the vcpu's SVE
2681 configuration is finalized using KVM_ARM_VCPU 2624 configuration is finalized using KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE).
2682 2625
2683 Apart from simply removing all vector lengths 2626 Apart from simply removing all vector lengths from the host set that
2684 exceed some value, support for arbitrarily ch 2627 exceed some value, support for arbitrarily chosen sets of vector lengths
2685 is hardware-dependent and may not be availabl 2628 is hardware-dependent and may not be available. Attempting to configure
2686 an invalid set of vector lengths via KVM_SET_ 2629 an invalid set of vector lengths via KVM_SET_ONE_REG will fail with
2687 EINVAL. 2630 EINVAL.
2688 2631
2689 After the vcpu's SVE configuration is finaliz 2632 After the vcpu's SVE configuration is finalized, further attempts to
2690 write this register will fail with EPERM. 2633 write this register will fail with EPERM.
2691 2634
2692 arm64 bitmap feature firmware pseudo-register 2635 arm64 bitmap feature firmware pseudo-registers have the following bit pattern::
2693 2636
2694 0x6030 0000 0016 <regno:16> 2637 0x6030 0000 0016 <regno:16>
2695 2638
2696 The bitmap feature firmware registers exposes 2639 The bitmap feature firmware registers exposes the hypercall services that
2697 are available for userspace to configure. The 2640 are available for userspace to configure. The set bits corresponds to the
2698 services that are available for the guests to 2641 services that are available for the guests to access. By default, KVM
2699 sets all the supported bits during VM initial 2642 sets all the supported bits during VM initialization. The userspace can
2700 discover the available services via KVM_GET_O 2643 discover the available services via KVM_GET_ONE_REG, and write back the
2701 bitmap corresponding to the features that it 2644 bitmap corresponding to the features that it wishes guests to see via
2702 KVM_SET_ONE_REG. 2645 KVM_SET_ONE_REG.
2703 2646
2704 Note: These registers are immutable once any 2647 Note: These registers are immutable once any of the vCPUs of the VM has
2705 run at least once. A KVM_SET_ONE_REG in such 2648 run at least once. A KVM_SET_ONE_REG in such a scenario will return
2706 a -EBUSY to userspace. 2649 a -EBUSY to userspace.
2707 2650
2708 (See Documentation/virt/kvm/arm/hypercalls.rs 2651 (See Documentation/virt/kvm/arm/hypercalls.rst for more details.)
2709 2652
2710 2653
2711 MIPS registers are mapped using the lower 32 2654 MIPS registers are mapped using the lower 32 bits. The upper 16 of that is
2712 the register group type: 2655 the register group type:
2713 2656
2714 MIPS core registers (see above) have the foll 2657 MIPS core registers (see above) have the following id bit patterns::
2715 2658
2716 0x7030 0000 0000 <reg:16> 2659 0x7030 0000 0000 <reg:16>
2717 2660
2718 MIPS CP0 registers (see KVM_REG_MIPS_CP0_* ab 2661 MIPS CP0 registers (see KVM_REG_MIPS_CP0_* above) have the following id bit
2719 patterns depending on whether they're 32-bit 2662 patterns depending on whether they're 32-bit or 64-bit registers::
2720 2663
2721 0x7020 0000 0001 00 <reg:5> <sel:3> (32-b 2664 0x7020 0000 0001 00 <reg:5> <sel:3> (32-bit)
2722 0x7030 0000 0001 00 <reg:5> <sel:3> (64-b 2665 0x7030 0000 0001 00 <reg:5> <sel:3> (64-bit)
2723 2666
2724 Note: KVM_REG_MIPS_CP0_ENTRYLO0 and KVM_REG_M 2667 Note: KVM_REG_MIPS_CP0_ENTRYLO0 and KVM_REG_MIPS_CP0_ENTRYLO1 are the MIPS64
2725 versions of the EntryLo registers regardless 2668 versions of the EntryLo registers regardless of the word size of the host
2726 hardware, host kernel, guest, and whether XPA 2669 hardware, host kernel, guest, and whether XPA is present in the guest, i.e.
2727 with the RI and XI bits (if they exist) in bi 2670 with the RI and XI bits (if they exist) in bits 63 and 62 respectively, and
2728 the PFNX field starting at bit 30. 2671 the PFNX field starting at bit 30.
2729 2672
2730 MIPS MAARs (see KVM_REG_MIPS_CP0_MAAR(*) abov 2673 MIPS MAARs (see KVM_REG_MIPS_CP0_MAAR(*) above) have the following id bit
2731 patterns:: 2674 patterns::
2732 2675
2733 0x7030 0000 0001 01 <reg:8> 2676 0x7030 0000 0001 01 <reg:8>
2734 2677
2735 MIPS KVM control registers (see above) have t 2678 MIPS KVM control registers (see above) have the following id bit patterns::
2736 2679
2737 0x7030 0000 0002 <reg:16> 2680 0x7030 0000 0002 <reg:16>
2738 2681
2739 MIPS FPU registers (see KVM_REG_MIPS_FPR_{32, 2682 MIPS FPU registers (see KVM_REG_MIPS_FPR_{32,64}() above) have the following
2740 id bit patterns depending on the size of the 2683 id bit patterns depending on the size of the register being accessed. They are
2741 always accessed according to the current gues 2684 always accessed according to the current guest FPU mode (Status.FR and
2742 Config5.FRE), i.e. as the guest would see the 2685 Config5.FRE), i.e. as the guest would see them, and they become unpredictable
2743 if the guest FPU mode is changed. MIPS SIMD A 2686 if the guest FPU mode is changed. MIPS SIMD Architecture (MSA) vector
2744 registers (see KVM_REG_MIPS_VEC_128() above) 2687 registers (see KVM_REG_MIPS_VEC_128() above) have similar patterns as they
2745 overlap the FPU registers:: 2688 overlap the FPU registers::
2746 2689
2747 0x7020 0000 0003 00 <0:3> <reg:5> (32-bit F 2690 0x7020 0000 0003 00 <0:3> <reg:5> (32-bit FPU registers)
2748 0x7030 0000 0003 00 <0:3> <reg:5> (64-bit F 2691 0x7030 0000 0003 00 <0:3> <reg:5> (64-bit FPU registers)
2749 0x7040 0000 0003 00 <0:3> <reg:5> (128-bit 2692 0x7040 0000 0003 00 <0:3> <reg:5> (128-bit MSA vector registers)
2750 2693
2751 MIPS FPU control registers (see KVM_REG_MIPS_ 2694 MIPS FPU control registers (see KVM_REG_MIPS_FCR_{IR,CSR} above) have the
2752 following id bit patterns:: 2695 following id bit patterns::
2753 2696
2754 0x7020 0000 0003 01 <0:3> <reg:5> 2697 0x7020 0000 0003 01 <0:3> <reg:5>
2755 2698
2756 MIPS MSA control registers (see KVM_REG_MIPS_ 2699 MIPS MSA control registers (see KVM_REG_MIPS_MSA_{IR,CSR} above) have the
2757 following id bit patterns:: 2700 following id bit patterns::
2758 2701
2759 0x7020 0000 0003 02 <0:3> <reg:5> 2702 0x7020 0000 0003 02 <0:3> <reg:5>
2760 2703
2761 RISC-V registers are mapped using the lower 3 2704 RISC-V registers are mapped using the lower 32 bits. The upper 8 bits of
2762 that is the register group type. 2705 that is the register group type.
2763 2706
2764 RISC-V config registers are meant for configu 2707 RISC-V config registers are meant for configuring a Guest VCPU and it has
2765 the following id bit patterns:: 2708 the following id bit patterns::
2766 2709
2767 0x8020 0000 01 <index into the kvm_riscv_co 2710 0x8020 0000 01 <index into the kvm_riscv_config struct:24> (32bit Host)
2768 0x8030 0000 01 <index into the kvm_riscv_co 2711 0x8030 0000 01 <index into the kvm_riscv_config struct:24> (64bit Host)
2769 2712
2770 Following are the RISC-V config registers: 2713 Following are the RISC-V config registers:
2771 2714
2772 ======================= ========= =========== 2715 ======================= ========= =============================================
2773 Encoding Register Description 2716 Encoding Register Description
2774 ======================= ========= =========== 2717 ======================= ========= =============================================
2775 0x80x0 0000 0100 0000 isa ISA feature 2718 0x80x0 0000 0100 0000 isa ISA feature bitmap of Guest VCPU
2776 ======================= ========= =========== 2719 ======================= ========= =============================================
2777 2720
2778 The isa config register can be read anytime b 2721 The isa config register can be read anytime but can only be written before
2779 a Guest VCPU runs. It will have ISA feature b 2722 a Guest VCPU runs. It will have ISA feature bits matching underlying host
2780 set by default. 2723 set by default.
2781 2724
2782 RISC-V core registers represent the general e !! 2725 RISC-V core registers represent the general excution state of a Guest VCPU
2783 and it has the following id bit patterns:: 2726 and it has the following id bit patterns::
2784 2727
2785 0x8020 0000 02 <index into the kvm_riscv_co 2728 0x8020 0000 02 <index into the kvm_riscv_core struct:24> (32bit Host)
2786 0x8030 0000 02 <index into the kvm_riscv_co 2729 0x8030 0000 02 <index into the kvm_riscv_core struct:24> (64bit Host)
2787 2730
2788 Following are the RISC-V core registers: 2731 Following are the RISC-V core registers:
2789 2732
2790 ======================= ========= =========== 2733 ======================= ========= =============================================
2791 Encoding Register Description 2734 Encoding Register Description
2792 ======================= ========= =========== 2735 ======================= ========= =============================================
2793 0x80x0 0000 0200 0000 regs.pc Program cou 2736 0x80x0 0000 0200 0000 regs.pc Program counter
2794 0x80x0 0000 0200 0001 regs.ra Return addr 2737 0x80x0 0000 0200 0001 regs.ra Return address
2795 0x80x0 0000 0200 0002 regs.sp Stack point 2738 0x80x0 0000 0200 0002 regs.sp Stack pointer
2796 0x80x0 0000 0200 0003 regs.gp Global poin 2739 0x80x0 0000 0200 0003 regs.gp Global pointer
2797 0x80x0 0000 0200 0004 regs.tp Task pointe 2740 0x80x0 0000 0200 0004 regs.tp Task pointer
2798 0x80x0 0000 0200 0005 regs.t0 Caller save 2741 0x80x0 0000 0200 0005 regs.t0 Caller saved register 0
2799 0x80x0 0000 0200 0006 regs.t1 Caller save 2742 0x80x0 0000 0200 0006 regs.t1 Caller saved register 1
2800 0x80x0 0000 0200 0007 regs.t2 Caller save 2743 0x80x0 0000 0200 0007 regs.t2 Caller saved register 2
2801 0x80x0 0000 0200 0008 regs.s0 Callee save 2744 0x80x0 0000 0200 0008 regs.s0 Callee saved register 0
2802 0x80x0 0000 0200 0009 regs.s1 Callee save 2745 0x80x0 0000 0200 0009 regs.s1 Callee saved register 1
2803 0x80x0 0000 0200 000a regs.a0 Function ar 2746 0x80x0 0000 0200 000a regs.a0 Function argument (or return value) 0
2804 0x80x0 0000 0200 000b regs.a1 Function ar 2747 0x80x0 0000 0200 000b regs.a1 Function argument (or return value) 1
2805 0x80x0 0000 0200 000c regs.a2 Function ar 2748 0x80x0 0000 0200 000c regs.a2 Function argument 2
2806 0x80x0 0000 0200 000d regs.a3 Function ar 2749 0x80x0 0000 0200 000d regs.a3 Function argument 3
2807 0x80x0 0000 0200 000e regs.a4 Function ar 2750 0x80x0 0000 0200 000e regs.a4 Function argument 4
2808 0x80x0 0000 0200 000f regs.a5 Function ar 2751 0x80x0 0000 0200 000f regs.a5 Function argument 5
2809 0x80x0 0000 0200 0010 regs.a6 Function ar 2752 0x80x0 0000 0200 0010 regs.a6 Function argument 6
2810 0x80x0 0000 0200 0011 regs.a7 Function ar 2753 0x80x0 0000 0200 0011 regs.a7 Function argument 7
2811 0x80x0 0000 0200 0012 regs.s2 Callee save 2754 0x80x0 0000 0200 0012 regs.s2 Callee saved register 2
2812 0x80x0 0000 0200 0013 regs.s3 Callee save 2755 0x80x0 0000 0200 0013 regs.s3 Callee saved register 3
2813 0x80x0 0000 0200 0014 regs.s4 Callee save 2756 0x80x0 0000 0200 0014 regs.s4 Callee saved register 4
2814 0x80x0 0000 0200 0015 regs.s5 Callee save 2757 0x80x0 0000 0200 0015 regs.s5 Callee saved register 5
2815 0x80x0 0000 0200 0016 regs.s6 Callee save 2758 0x80x0 0000 0200 0016 regs.s6 Callee saved register 6
2816 0x80x0 0000 0200 0017 regs.s7 Callee save 2759 0x80x0 0000 0200 0017 regs.s7 Callee saved register 7
2817 0x80x0 0000 0200 0018 regs.s8 Callee save 2760 0x80x0 0000 0200 0018 regs.s8 Callee saved register 8
2818 0x80x0 0000 0200 0019 regs.s9 Callee save 2761 0x80x0 0000 0200 0019 regs.s9 Callee saved register 9
2819 0x80x0 0000 0200 001a regs.s10 Callee save 2762 0x80x0 0000 0200 001a regs.s10 Callee saved register 10
2820 0x80x0 0000 0200 001b regs.s11 Callee save 2763 0x80x0 0000 0200 001b regs.s11 Callee saved register 11
2821 0x80x0 0000 0200 001c regs.t3 Caller save 2764 0x80x0 0000 0200 001c regs.t3 Caller saved register 3
2822 0x80x0 0000 0200 001d regs.t4 Caller save 2765 0x80x0 0000 0200 001d regs.t4 Caller saved register 4
2823 0x80x0 0000 0200 001e regs.t5 Caller save 2766 0x80x0 0000 0200 001e regs.t5 Caller saved register 5
2824 0x80x0 0000 0200 001f regs.t6 Caller save 2767 0x80x0 0000 0200 001f regs.t6 Caller saved register 6
2825 0x80x0 0000 0200 0020 mode Privilege m 2768 0x80x0 0000 0200 0020 mode Privilege mode (1 = S-mode or 0 = U-mode)
2826 ======================= ========= =========== 2769 ======================= ========= =============================================
2827 2770
2828 RISC-V csr registers represent the supervisor 2771 RISC-V csr registers represent the supervisor mode control/status registers
2829 of a Guest VCPU and it has the following id b 2772 of a Guest VCPU and it has the following id bit patterns::
2830 2773
2831 0x8020 0000 03 <index into the kvm_riscv_cs 2774 0x8020 0000 03 <index into the kvm_riscv_csr struct:24> (32bit Host)
2832 0x8030 0000 03 <index into the kvm_riscv_cs 2775 0x8030 0000 03 <index into the kvm_riscv_csr struct:24> (64bit Host)
2833 2776
2834 Following are the RISC-V csr registers: 2777 Following are the RISC-V csr registers:
2835 2778
2836 ======================= ========= =========== 2779 ======================= ========= =============================================
2837 Encoding Register Description 2780 Encoding Register Description
2838 ======================= ========= =========== 2781 ======================= ========= =============================================
2839 0x80x0 0000 0300 0000 sstatus Supervisor 2782 0x80x0 0000 0300 0000 sstatus Supervisor status
2840 0x80x0 0000 0300 0001 sie Supervisor 2783 0x80x0 0000 0300 0001 sie Supervisor interrupt enable
2841 0x80x0 0000 0300 0002 stvec Supervisor 2784 0x80x0 0000 0300 0002 stvec Supervisor trap vector base
2842 0x80x0 0000 0300 0003 sscratch Supervisor 2785 0x80x0 0000 0300 0003 sscratch Supervisor scratch register
2843 0x80x0 0000 0300 0004 sepc Supervisor 2786 0x80x0 0000 0300 0004 sepc Supervisor exception program counter
2844 0x80x0 0000 0300 0005 scause Supervisor 2787 0x80x0 0000 0300 0005 scause Supervisor trap cause
2845 0x80x0 0000 0300 0006 stval Supervisor 2788 0x80x0 0000 0300 0006 stval Supervisor bad address or instruction
2846 0x80x0 0000 0300 0007 sip Supervisor 2789 0x80x0 0000 0300 0007 sip Supervisor interrupt pending
2847 0x80x0 0000 0300 0008 satp Supervisor 2790 0x80x0 0000 0300 0008 satp Supervisor address translation and protection
2848 ======================= ========= =========== 2791 ======================= ========= =============================================
2849 2792
2850 RISC-V timer registers represent the timer st 2793 RISC-V timer registers represent the timer state of a Guest VCPU and it has
2851 the following id bit patterns:: 2794 the following id bit patterns::
2852 2795
2853 0x8030 0000 04 <index into the kvm_riscv_ti 2796 0x8030 0000 04 <index into the kvm_riscv_timer struct:24>
2854 2797
2855 Following are the RISC-V timer registers: 2798 Following are the RISC-V timer registers:
2856 2799
2857 ======================= ========= =========== 2800 ======================= ========= =============================================
2858 Encoding Register Description 2801 Encoding Register Description
2859 ======================= ========= =========== 2802 ======================= ========= =============================================
2860 0x8030 0000 0400 0000 frequency Time base f 2803 0x8030 0000 0400 0000 frequency Time base frequency (read-only)
2861 0x8030 0000 0400 0001 time Time value 2804 0x8030 0000 0400 0001 time Time value visible to Guest
2862 0x8030 0000 0400 0002 compare Time compar 2805 0x8030 0000 0400 0002 compare Time compare programmed by Guest
2863 0x8030 0000 0400 0003 state Time compar 2806 0x8030 0000 0400 0003 state Time compare state (1 = ON or 0 = OFF)
2864 ======================= ========= =========== 2807 ======================= ========= =============================================
2865 2808
2866 RISC-V F-extension registers represent the si 2809 RISC-V F-extension registers represent the single precision floating point
2867 state of a Guest VCPU and it has the followin 2810 state of a Guest VCPU and it has the following id bit patterns::
2868 2811
2869 0x8020 0000 05 <index into the __riscv_f_ex 2812 0x8020 0000 05 <index into the __riscv_f_ext_state struct:24>
2870 2813
2871 Following are the RISC-V F-extension register 2814 Following are the RISC-V F-extension registers:
2872 2815
2873 ======================= ========= =========== 2816 ======================= ========= =============================================
2874 Encoding Register Description 2817 Encoding Register Description
2875 ======================= ========= =========== 2818 ======================= ========= =============================================
2876 0x8020 0000 0500 0000 f[0] Floating po 2819 0x8020 0000 0500 0000 f[0] Floating point register 0
2877 ... 2820 ...
2878 0x8020 0000 0500 001f f[31] Floating po 2821 0x8020 0000 0500 001f f[31] Floating point register 31
2879 0x8020 0000 0500 0020 fcsr Floating po 2822 0x8020 0000 0500 0020 fcsr Floating point control and status register
2880 ======================= ========= =========== 2823 ======================= ========= =============================================
2881 2824
2882 RISC-V D-extension registers represent the do 2825 RISC-V D-extension registers represent the double precision floating point
2883 state of a Guest VCPU and it has the followin 2826 state of a Guest VCPU and it has the following id bit patterns::
2884 2827
2885 0x8020 0000 06 <index into the __riscv_d_ex 2828 0x8020 0000 06 <index into the __riscv_d_ext_state struct:24> (fcsr)
2886 0x8030 0000 06 <index into the __riscv_d_ex 2829 0x8030 0000 06 <index into the __riscv_d_ext_state struct:24> (non-fcsr)
2887 2830
2888 Following are the RISC-V D-extension register 2831 Following are the RISC-V D-extension registers:
2889 2832
2890 ======================= ========= =========== 2833 ======================= ========= =============================================
2891 Encoding Register Description 2834 Encoding Register Description
2892 ======================= ========= =========== 2835 ======================= ========= =============================================
2893 0x8030 0000 0600 0000 f[0] Floating po 2836 0x8030 0000 0600 0000 f[0] Floating point register 0
2894 ... 2837 ...
2895 0x8030 0000 0600 001f f[31] Floating po 2838 0x8030 0000 0600 001f f[31] Floating point register 31
2896 0x8020 0000 0600 0020 fcsr Floating po 2839 0x8020 0000 0600 0020 fcsr Floating point control and status register
2897 ======================= ========= =========== 2840 ======================= ========= =============================================
2898 2841
2899 LoongArch registers are mapped using the lowe <<
2900 that is the register group type. <<
2901 <<
2902 LoongArch csr registers are used to control g <<
2903 cpu, and they have the following id bit patte <<
2904 <<
2905 0x9030 0000 0001 00 <reg:5> <sel:3> (64-b <<
2906 <<
2907 LoongArch KVM control registers are used to i <<
2908 such as set vcpu counter or reset vcpu, and t <<
2909 <<
2910 0x9030 0000 0002 <reg:16> <<
2911 <<
2912 2842
2913 4.69 KVM_GET_ONE_REG 2843 4.69 KVM_GET_ONE_REG
2914 -------------------- 2844 --------------------
2915 2845
2916 :Capability: KVM_CAP_ONE_REG 2846 :Capability: KVM_CAP_ONE_REG
2917 :Architectures: all 2847 :Architectures: all
2918 :Type: vcpu ioctl 2848 :Type: vcpu ioctl
2919 :Parameters: struct kvm_one_reg (in and out) 2849 :Parameters: struct kvm_one_reg (in and out)
2920 :Returns: 0 on success, negative value on fai 2850 :Returns: 0 on success, negative value on failure
2921 2851
2922 Errors include: 2852 Errors include:
2923 2853
2924 ======== ================================== 2854 ======== ============================================================
2925 ENOENT no such register 2855 ENOENT no such register
2926 EINVAL invalid register ID, or no such re 2856 EINVAL invalid register ID, or no such register or used with VMs in
2927 protected virtualization mode on s 2857 protected virtualization mode on s390
2928 EPERM (arm64) register access not allowe 2858 EPERM (arm64) register access not allowed before vcpu finalization
2929 ======== ================================== 2859 ======== ============================================================
2930 2860
2931 (These error codes are indicative only: do no 2861 (These error codes are indicative only: do not rely on a specific error
2932 code being returned in a specific situation.) 2862 code being returned in a specific situation.)
2933 2863
2934 This ioctl allows to receive the value of a s 2864 This ioctl allows to receive the value of a single register implemented
2935 in a vcpu. The register to read is indicated 2865 in a vcpu. The register to read is indicated by the "id" field of the
2936 kvm_one_reg struct passed in. On success, the 2866 kvm_one_reg struct passed in. On success, the register value can be found
2937 at the memory location pointed to by "addr". 2867 at the memory location pointed to by "addr".
2938 2868
2939 The list of registers accessible using this i 2869 The list of registers accessible using this interface is identical to the
2940 list in 4.68. 2870 list in 4.68.
2941 2871
2942 2872
2943 4.70 KVM_KVMCLOCK_CTRL 2873 4.70 KVM_KVMCLOCK_CTRL
2944 ---------------------- 2874 ----------------------
2945 2875
2946 :Capability: KVM_CAP_KVMCLOCK_CTRL 2876 :Capability: KVM_CAP_KVMCLOCK_CTRL
2947 :Architectures: Any that implement pvclocks ( 2877 :Architectures: Any that implement pvclocks (currently x86 only)
2948 :Type: vcpu ioctl 2878 :Type: vcpu ioctl
2949 :Parameters: None 2879 :Parameters: None
2950 :Returns: 0 on success, -1 on error 2880 :Returns: 0 on success, -1 on error
2951 2881
2952 This ioctl sets a flag accessible to the gues 2882 This ioctl sets a flag accessible to the guest indicating that the specified
2953 vCPU has been paused by the host userspace. 2883 vCPU has been paused by the host userspace.
2954 2884
2955 The host will set a flag in the pvclock struc 2885 The host will set a flag in the pvclock structure that is checked from the
2956 soft lockup watchdog. The flag is part of th 2886 soft lockup watchdog. The flag is part of the pvclock structure that is
2957 shared between guest and host, specifically t 2887 shared between guest and host, specifically the second bit of the flags
2958 field of the pvclock_vcpu_time_info structure 2888 field of the pvclock_vcpu_time_info structure. It will be set exclusively by
2959 the host and read/cleared exclusively by the 2889 the host and read/cleared exclusively by the guest. The guest operation of
2960 checking and clearing the flag must be an ato 2890 checking and clearing the flag must be an atomic operation so
2961 load-link/store-conditional, or equivalent mu 2891 load-link/store-conditional, or equivalent must be used. There are two cases
2962 where the guest will clear the flag: when the 2892 where the guest will clear the flag: when the soft lockup watchdog timer resets
2963 itself or when a soft lockup is detected. Th 2893 itself or when a soft lockup is detected. This ioctl can be called any time
2964 after pausing the vcpu, but before it is resu 2894 after pausing the vcpu, but before it is resumed.
2965 2895
2966 2896
2967 4.71 KVM_SIGNAL_MSI 2897 4.71 KVM_SIGNAL_MSI
2968 ------------------- 2898 -------------------
2969 2899
2970 :Capability: KVM_CAP_SIGNAL_MSI 2900 :Capability: KVM_CAP_SIGNAL_MSI
2971 :Architectures: x86 arm64 2901 :Architectures: x86 arm64
2972 :Type: vm ioctl 2902 :Type: vm ioctl
2973 :Parameters: struct kvm_msi (in) 2903 :Parameters: struct kvm_msi (in)
2974 :Returns: >0 on delivery, 0 if guest blocked 2904 :Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error
2975 2905
2976 Directly inject a MSI message. Only valid wit 2906 Directly inject a MSI message. Only valid with in-kernel irqchip that handles
2977 MSI messages. 2907 MSI messages.
2978 2908
2979 :: 2909 ::
2980 2910
2981 struct kvm_msi { 2911 struct kvm_msi {
2982 __u32 address_lo; 2912 __u32 address_lo;
2983 __u32 address_hi; 2913 __u32 address_hi;
2984 __u32 data; 2914 __u32 data;
2985 __u32 flags; 2915 __u32 flags;
2986 __u32 devid; 2916 __u32 devid;
2987 __u8 pad[12]; 2917 __u8 pad[12];
2988 }; 2918 };
2989 2919
2990 flags: 2920 flags:
2991 KVM_MSI_VALID_DEVID: devid contains a valid 2921 KVM_MSI_VALID_DEVID: devid contains a valid value. The per-VM
2992 KVM_CAP_MSI_DEVID capability advertises the 2922 KVM_CAP_MSI_DEVID capability advertises the requirement to provide
2993 the device ID. If this capability is not a 2923 the device ID. If this capability is not available, userspace
2994 should never set the KVM_MSI_VALID_DEVID fl 2924 should never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.
2995 2925
2996 If KVM_MSI_VALID_DEVID is set, devid contains 2926 If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier
2997 for the device that wrote the MSI message. F 2927 for the device that wrote the MSI message. For PCI, this is usually a
2998 BDF identifier in the lower 16 bits. !! 2928 BFD identifier in the lower 16 bits.
2999 2929
3000 On x86, address_hi is ignored unless the KVM_ 2930 On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
3001 feature of KVM_CAP_X2APIC_API capability is e 2931 feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled,
3002 address_hi bits 31-8 provide bits 31-8 of the 2932 address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of
3003 address_hi must be zero. 2933 address_hi must be zero.
3004 2934
3005 2935
3006 4.71 KVM_CREATE_PIT2 2936 4.71 KVM_CREATE_PIT2
3007 -------------------- 2937 --------------------
3008 2938
3009 :Capability: KVM_CAP_PIT2 2939 :Capability: KVM_CAP_PIT2
3010 :Architectures: x86 2940 :Architectures: x86
3011 :Type: vm ioctl 2941 :Type: vm ioctl
3012 :Parameters: struct kvm_pit_config (in) 2942 :Parameters: struct kvm_pit_config (in)
3013 :Returns: 0 on success, -1 on error 2943 :Returns: 0 on success, -1 on error
3014 2944
3015 Creates an in-kernel device model for the i82 2945 Creates an in-kernel device model for the i8254 PIT. This call is only valid
3016 after enabling in-kernel irqchip support via 2946 after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following
3017 parameters have to be passed:: 2947 parameters have to be passed::
3018 2948
3019 struct kvm_pit_config { 2949 struct kvm_pit_config {
3020 __u32 flags; 2950 __u32 flags;
3021 __u32 pad[15]; 2951 __u32 pad[15];
3022 }; 2952 };
3023 2953
3024 Valid flags are:: 2954 Valid flags are::
3025 2955
3026 #define KVM_PIT_SPEAKER_DUMMY 1 /* emul 2956 #define KVM_PIT_SPEAKER_DUMMY 1 /* emulate speaker port stub */
3027 2957
3028 PIT timer interrupts may use a per-VM kernel 2958 PIT timer interrupts may use a per-VM kernel thread for injection. If it
3029 exists, this thread will have a name of the f 2959 exists, this thread will have a name of the following pattern::
3030 2960
3031 kvm-pit/<owner-process-pid> 2961 kvm-pit/<owner-process-pid>
3032 2962
3033 When running a guest with elevated priorities 2963 When running a guest with elevated priorities, the scheduling parameters of
3034 this thread may have to be adjusted according 2964 this thread may have to be adjusted accordingly.
3035 2965
3036 This IOCTL replaces the obsolete KVM_CREATE_P 2966 This IOCTL replaces the obsolete KVM_CREATE_PIT.
3037 2967
3038 2968
3039 4.72 KVM_GET_PIT2 2969 4.72 KVM_GET_PIT2
3040 ----------------- 2970 -----------------
3041 2971
3042 :Capability: KVM_CAP_PIT_STATE2 2972 :Capability: KVM_CAP_PIT_STATE2
3043 :Architectures: x86 2973 :Architectures: x86
3044 :Type: vm ioctl 2974 :Type: vm ioctl
3045 :Parameters: struct kvm_pit_state2 (out) 2975 :Parameters: struct kvm_pit_state2 (out)
3046 :Returns: 0 on success, -1 on error 2976 :Returns: 0 on success, -1 on error
3047 2977
3048 Retrieves the state of the in-kernel PIT mode 2978 Retrieves the state of the in-kernel PIT model. Only valid after
3049 KVM_CREATE_PIT2. The state is returned in the 2979 KVM_CREATE_PIT2. The state is returned in the following structure::
3050 2980
3051 struct kvm_pit_state2 { 2981 struct kvm_pit_state2 {
3052 struct kvm_pit_channel_state channels 2982 struct kvm_pit_channel_state channels[3];
3053 __u32 flags; 2983 __u32 flags;
3054 __u32 reserved[9]; 2984 __u32 reserved[9];
3055 }; 2985 };
3056 2986
3057 Valid flags are:: 2987 Valid flags are::
3058 2988
3059 /* disable PIT in HPET legacy mode */ 2989 /* disable PIT in HPET legacy mode */
3060 #define KVM_PIT_FLAGS_HPET_LEGACY 0x000 2990 #define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001
3061 /* speaker port data bit enabled */ 2991 /* speaker port data bit enabled */
3062 #define KVM_PIT_FLAGS_SPEAKER_DATA_ON 0x000 2992 #define KVM_PIT_FLAGS_SPEAKER_DATA_ON 0x00000002
3063 2993
3064 This IOCTL replaces the obsolete KVM_GET_PIT. 2994 This IOCTL replaces the obsolete KVM_GET_PIT.
3065 2995
3066 2996
3067 4.73 KVM_SET_PIT2 2997 4.73 KVM_SET_PIT2
3068 ----------------- 2998 -----------------
3069 2999
3070 :Capability: KVM_CAP_PIT_STATE2 3000 :Capability: KVM_CAP_PIT_STATE2
3071 :Architectures: x86 3001 :Architectures: x86
3072 :Type: vm ioctl 3002 :Type: vm ioctl
3073 :Parameters: struct kvm_pit_state2 (in) 3003 :Parameters: struct kvm_pit_state2 (in)
3074 :Returns: 0 on success, -1 on error 3004 :Returns: 0 on success, -1 on error
3075 3005
3076 Sets the state of the in-kernel PIT model. On 3006 Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2.
3077 See KVM_GET_PIT2 for details on struct kvm_pi 3007 See KVM_GET_PIT2 for details on struct kvm_pit_state2.
3078 3008
3079 This IOCTL replaces the obsolete KVM_SET_PIT. 3009 This IOCTL replaces the obsolete KVM_SET_PIT.
3080 3010
3081 3011
3082 4.74 KVM_PPC_GET_SMMU_INFO 3012 4.74 KVM_PPC_GET_SMMU_INFO
3083 -------------------------- 3013 --------------------------
3084 3014
3085 :Capability: KVM_CAP_PPC_GET_SMMU_INFO 3015 :Capability: KVM_CAP_PPC_GET_SMMU_INFO
3086 :Architectures: powerpc 3016 :Architectures: powerpc
3087 :Type: vm ioctl 3017 :Type: vm ioctl
3088 :Parameters: None 3018 :Parameters: None
3089 :Returns: 0 on success, -1 on error 3019 :Returns: 0 on success, -1 on error
3090 3020
3091 This populates and returns a structure descri 3021 This populates and returns a structure describing the features of
3092 the "Server" class MMU emulation supported by 3022 the "Server" class MMU emulation supported by KVM.
3093 This can in turn be used by userspace to gene 3023 This can in turn be used by userspace to generate the appropriate
3094 device-tree properties for the guest operatin 3024 device-tree properties for the guest operating system.
3095 3025
3096 The structure contains some global informatio 3026 The structure contains some global information, followed by an
3097 array of supported segment page sizes:: 3027 array of supported segment page sizes::
3098 3028
3099 struct kvm_ppc_smmu_info { 3029 struct kvm_ppc_smmu_info {
3100 __u64 flags; 3030 __u64 flags;
3101 __u32 slb_size; 3031 __u32 slb_size;
3102 __u32 pad; 3032 __u32 pad;
3103 struct kvm_ppc_one_seg_page_size 3033 struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
3104 }; 3034 };
3105 3035
3106 The supported flags are: 3036 The supported flags are:
3107 3037
3108 - KVM_PPC_PAGE_SIZES_REAL: 3038 - KVM_PPC_PAGE_SIZES_REAL:
3109 When that flag is set, guest page siz 3039 When that flag is set, guest page sizes must "fit" the backing
3110 store page sizes. When not set, any p 3040 store page sizes. When not set, any page size in the list can
3111 be used regardless of how they are ba 3041 be used regardless of how they are backed by userspace.
3112 3042
3113 - KVM_PPC_1T_SEGMENTS 3043 - KVM_PPC_1T_SEGMENTS
3114 The emulated MMU supports 1T segments 3044 The emulated MMU supports 1T segments in addition to the
3115 standard 256M ones. 3045 standard 256M ones.
3116 3046
3117 - KVM_PPC_NO_HASH 3047 - KVM_PPC_NO_HASH
3118 This flag indicates that HPT guests a 3048 This flag indicates that HPT guests are not supported by KVM,
3119 thus all guests must use radix MMU mo 3049 thus all guests must use radix MMU mode.
3120 3050
3121 The "slb_size" field indicates how many SLB e 3051 The "slb_size" field indicates how many SLB entries are supported
3122 3052
3123 The "sps" array contains 8 entries indicating 3053 The "sps" array contains 8 entries indicating the supported base
3124 page sizes for a segment in increasing order. 3054 page sizes for a segment in increasing order. Each entry is defined
3125 as follow:: 3055 as follow::
3126 3056
3127 struct kvm_ppc_one_seg_page_size { 3057 struct kvm_ppc_one_seg_page_size {
3128 __u32 page_shift; /* Base page 3058 __u32 page_shift; /* Base page shift of segment (or 0) */
3129 __u32 slb_enc; /* SLB encodi 3059 __u32 slb_enc; /* SLB encoding for BookS */
3130 struct kvm_ppc_one_page_size enc[KVM_ 3060 struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
3131 }; 3061 };
3132 3062
3133 An entry with a "page_shift" of 0 is unused. 3063 An entry with a "page_shift" of 0 is unused. Because the array is
3134 organized in increasing order, a lookup can s !! 3064 organized in increasing order, a lookup can stop when encoutering
3135 such an entry. 3065 such an entry.
3136 3066
3137 The "slb_enc" field provides the encoding to 3067 The "slb_enc" field provides the encoding to use in the SLB for the
3138 page size. The bits are in positions such as 3068 page size. The bits are in positions such as the value can directly
3139 be OR'ed into the "vsid" argument of the slbm 3069 be OR'ed into the "vsid" argument of the slbmte instruction.
3140 3070
3141 The "enc" array is a list which for each of t 3071 The "enc" array is a list which for each of those segment base page
3142 size provides the list of supported actual pa 3072 size provides the list of supported actual page sizes (which can be
3143 only larger or equal to the base page size), 3073 only larger or equal to the base page size), along with the
3144 corresponding encoding in the hash PTE. Simil 3074 corresponding encoding in the hash PTE. Similarly, the array is
3145 8 entries sorted by increasing sizes and an e 3075 8 entries sorted by increasing sizes and an entry with a "0" shift
3146 is an empty entry and a terminator:: 3076 is an empty entry and a terminator::
3147 3077
3148 struct kvm_ppc_one_page_size { 3078 struct kvm_ppc_one_page_size {
3149 __u32 page_shift; /* Page shift 3079 __u32 page_shift; /* Page shift (or 0) */
3150 __u32 pte_enc; /* Encoding i 3080 __u32 pte_enc; /* Encoding in the HPTE (>>12) */
3151 }; 3081 };
3152 3082
3153 The "pte_enc" field provides a value that can 3083 The "pte_enc" field provides a value that can OR'ed into the hash
3154 PTE's RPN field (ie, it needs to be shifted l 3084 PTE's RPN field (ie, it needs to be shifted left by 12 to OR it
3155 into the hash PTE second double word). 3085 into the hash PTE second double word).
3156 3086
3157 4.75 KVM_IRQFD 3087 4.75 KVM_IRQFD
3158 -------------- 3088 --------------
3159 3089
3160 :Capability: KVM_CAP_IRQFD 3090 :Capability: KVM_CAP_IRQFD
3161 :Architectures: x86 s390 arm64 3091 :Architectures: x86 s390 arm64
3162 :Type: vm ioctl 3092 :Type: vm ioctl
3163 :Parameters: struct kvm_irqfd (in) 3093 :Parameters: struct kvm_irqfd (in)
3164 :Returns: 0 on success, -1 on error 3094 :Returns: 0 on success, -1 on error
3165 3095
3166 Allows setting an eventfd to directly trigger 3096 Allows setting an eventfd to directly trigger a guest interrupt.
3167 kvm_irqfd.fd specifies the file descriptor to 3097 kvm_irqfd.fd specifies the file descriptor to use as the eventfd and
3168 kvm_irqfd.gsi specifies the irqchip pin toggl 3098 kvm_irqfd.gsi specifies the irqchip pin toggled by this event. When
3169 an event is triggered on the eventfd, an inte 3099 an event is triggered on the eventfd, an interrupt is injected into
3170 the guest using the specified gsi pin. The i 3100 the guest using the specified gsi pin. The irqfd is removed using
3171 the KVM_IRQFD_FLAG_DEASSIGN flag, specifying 3101 the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd
3172 and kvm_irqfd.gsi. 3102 and kvm_irqfd.gsi.
3173 3103
3174 With KVM_CAP_IRQFD_RESAMPLE, KVM_IRQFD suppor 3104 With KVM_CAP_IRQFD_RESAMPLE, KVM_IRQFD supports a de-assert and notify
3175 mechanism allowing emulation of level-trigger 3105 mechanism allowing emulation of level-triggered, irqfd-based
3176 interrupts. When KVM_IRQFD_FLAG_RESAMPLE is 3106 interrupts. When KVM_IRQFD_FLAG_RESAMPLE is set the user must pass an
3177 additional eventfd in the kvm_irqfd.resamplef 3107 additional eventfd in the kvm_irqfd.resamplefd field. When operating
3178 in resample mode, posting of an interrupt thr 3108 in resample mode, posting of an interrupt through kvm_irq.fd asserts
3179 the specified gsi in the irqchip. When the i 3109 the specified gsi in the irqchip. When the irqchip is resampled, such
3180 as from an EOI, the gsi is de-asserted and th 3110 as from an EOI, the gsi is de-asserted and the user is notified via
3181 kvm_irqfd.resamplefd. It is the user's respo 3111 kvm_irqfd.resamplefd. It is the user's responsibility to re-queue
3182 the interrupt if the device making use of it 3112 the interrupt if the device making use of it still requires service.
3183 Note that closing the resamplefd is not suffi 3113 Note that closing the resamplefd is not sufficient to disable the
3184 irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only n 3114 irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment
3185 and need not be specified with KVM_IRQFD_FLAG 3115 and need not be specified with KVM_IRQFD_FLAG_DEASSIGN.
3186 3116
3187 On arm64, gsi routing being supported, the fo 3117 On arm64, gsi routing being supported, the following can happen:
3188 3118
3189 - in case no routing entry is associated to t 3119 - in case no routing entry is associated to this gsi, injection fails
3190 - in case the gsi is associated to an irqchip 3120 - in case the gsi is associated to an irqchip routing entry,
3191 irqchip.pin + 32 corresponds to the injecte 3121 irqchip.pin + 32 corresponds to the injected SPI ID.
3192 - in case the gsi is associated to an MSI rou 3122 - in case the gsi is associated to an MSI routing entry, the MSI
3193 message and device ID are translated into a 3123 message and device ID are translated into an LPI (support restricted
3194 to GICv3 ITS in-kernel emulation). 3124 to GICv3 ITS in-kernel emulation).
3195 3125
3196 4.76 KVM_PPC_ALLOCATE_HTAB 3126 4.76 KVM_PPC_ALLOCATE_HTAB
3197 -------------------------- 3127 --------------------------
3198 3128
3199 :Capability: KVM_CAP_PPC_ALLOC_HTAB 3129 :Capability: KVM_CAP_PPC_ALLOC_HTAB
3200 :Architectures: powerpc 3130 :Architectures: powerpc
3201 :Type: vm ioctl 3131 :Type: vm ioctl
3202 :Parameters: Pointer to u32 containing hash t 3132 :Parameters: Pointer to u32 containing hash table order (in/out)
3203 :Returns: 0 on success, -1 on error 3133 :Returns: 0 on success, -1 on error
3204 3134
3205 This requests the host kernel to allocate an 3135 This requests the host kernel to allocate an MMU hash table for a
3206 guest using the PAPR paravirtualization inter 3136 guest using the PAPR paravirtualization interface. This only does
3207 anything if the kernel is configured to use t 3137 anything if the kernel is configured to use the Book 3S HV style of
3208 virtualization. Otherwise the capability doe 3138 virtualization. Otherwise the capability doesn't exist and the ioctl
3209 returns an ENOTTY error. The rest of this de 3139 returns an ENOTTY error. The rest of this description assumes Book 3S
3210 HV. 3140 HV.
3211 3141
3212 There must be no vcpus running when this ioct 3142 There must be no vcpus running when this ioctl is called; if there
3213 are, it will do nothing and return an EBUSY e 3143 are, it will do nothing and return an EBUSY error.
3214 3144
3215 The parameter is a pointer to a 32-bit unsign 3145 The parameter is a pointer to a 32-bit unsigned integer variable
3216 containing the order (log base 2) of the desi 3146 containing the order (log base 2) of the desired size of the hash
3217 table, which must be between 18 and 46. On s 3147 table, which must be between 18 and 46. On successful return from the
3218 ioctl, the value will not be changed by the k 3148 ioctl, the value will not be changed by the kernel.
3219 3149
3220 If no hash table has been allocated when any 3150 If no hash table has been allocated when any vcpu is asked to run
3221 (with the KVM_RUN ioctl), the host kernel wil 3151 (with the KVM_RUN ioctl), the host kernel will allocate a
3222 default-sized hash table (16 MB). 3152 default-sized hash table (16 MB).
3223 3153
3224 If this ioctl is called when a hash table has 3154 If this ioctl is called when a hash table has already been allocated,
3225 with a different order from the existing hash 3155 with a different order from the existing hash table, the existing hash
3226 table will be freed and a new one allocated. 3156 table will be freed and a new one allocated. If this is ioctl is
3227 called when a hash table has already been all 3157 called when a hash table has already been allocated of the same order
3228 as specified, the kernel will clear out the e 3158 as specified, the kernel will clear out the existing hash table (zero
3229 all HPTEs). In either case, if the guest is 3159 all HPTEs). In either case, if the guest is using the virtualized
3230 real-mode area (VRMA) facility, the kernel wi 3160 real-mode area (VRMA) facility, the kernel will re-create the VMRA
3231 HPTEs on the next KVM_RUN of any vcpu. 3161 HPTEs on the next KVM_RUN of any vcpu.
3232 3162
3233 4.77 KVM_S390_INTERRUPT 3163 4.77 KVM_S390_INTERRUPT
3234 ----------------------- 3164 -----------------------
3235 3165
3236 :Capability: basic 3166 :Capability: basic
3237 :Architectures: s390 3167 :Architectures: s390
3238 :Type: vm ioctl, vcpu ioctl 3168 :Type: vm ioctl, vcpu ioctl
3239 :Parameters: struct kvm_s390_interrupt (in) 3169 :Parameters: struct kvm_s390_interrupt (in)
3240 :Returns: 0 on success, -1 on error 3170 :Returns: 0 on success, -1 on error
3241 3171
3242 Allows to inject an interrupt to the guest. I 3172 Allows to inject an interrupt to the guest. Interrupts can be floating
3243 (vm ioctl) or per cpu (vcpu ioctl), depending 3173 (vm ioctl) or per cpu (vcpu ioctl), depending on the interrupt type.
3244 3174
3245 Interrupt parameters are passed via kvm_s390_ 3175 Interrupt parameters are passed via kvm_s390_interrupt::
3246 3176
3247 struct kvm_s390_interrupt { 3177 struct kvm_s390_interrupt {
3248 __u32 type; 3178 __u32 type;
3249 __u32 parm; 3179 __u32 parm;
3250 __u64 parm64; 3180 __u64 parm64;
3251 }; 3181 };
3252 3182
3253 type can be one of the following: 3183 type can be one of the following:
3254 3184
3255 KVM_S390_SIGP_STOP (vcpu) 3185 KVM_S390_SIGP_STOP (vcpu)
3256 - sigp stop; optional flags in parm 3186 - sigp stop; optional flags in parm
3257 KVM_S390_PROGRAM_INT (vcpu) 3187 KVM_S390_PROGRAM_INT (vcpu)
3258 - program check; code in parm 3188 - program check; code in parm
3259 KVM_S390_SIGP_SET_PREFIX (vcpu) 3189 KVM_S390_SIGP_SET_PREFIX (vcpu)
3260 - sigp set prefix; prefix address in parm 3190 - sigp set prefix; prefix address in parm
3261 KVM_S390_RESTART (vcpu) 3191 KVM_S390_RESTART (vcpu)
3262 - restart 3192 - restart
3263 KVM_S390_INT_CLOCK_COMP (vcpu) 3193 KVM_S390_INT_CLOCK_COMP (vcpu)
3264 - clock comparator interrupt 3194 - clock comparator interrupt
3265 KVM_S390_INT_CPU_TIMER (vcpu) 3195 KVM_S390_INT_CPU_TIMER (vcpu)
3266 - CPU timer interrupt 3196 - CPU timer interrupt
3267 KVM_S390_INT_VIRTIO (vm) 3197 KVM_S390_INT_VIRTIO (vm)
3268 - virtio external interrupt; external int 3198 - virtio external interrupt; external interrupt
3269 parameters in parm and parm64 3199 parameters in parm and parm64
3270 KVM_S390_INT_SERVICE (vm) 3200 KVM_S390_INT_SERVICE (vm)
3271 - sclp external interrupt; sclp parameter 3201 - sclp external interrupt; sclp parameter in parm
3272 KVM_S390_INT_EMERGENCY (vcpu) 3202 KVM_S390_INT_EMERGENCY (vcpu)
3273 - sigp emergency; source cpu in parm 3203 - sigp emergency; source cpu in parm
3274 KVM_S390_INT_EXTERNAL_CALL (vcpu) 3204 KVM_S390_INT_EXTERNAL_CALL (vcpu)
3275 - sigp external call; source cpu in parm 3205 - sigp external call; source cpu in parm
3276 KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) 3206 KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm)
3277 - compound value to indicate an 3207 - compound value to indicate an
3278 I/O interrupt (ai - adapter interrupt; 3208 I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel);
3279 I/O interruption parameters in parm (su 3209 I/O interruption parameters in parm (subchannel) and parm64 (intparm,
3280 interruption subclass) 3210 interruption subclass)
3281 KVM_S390_MCHK (vm, vcpu) 3211 KVM_S390_MCHK (vm, vcpu)
3282 - machine check interrupt; cr 14 bits in 3212 - machine check interrupt; cr 14 bits in parm, machine check interrupt
3283 code in parm64 (note that machine check 3213 code in parm64 (note that machine checks needing further payload are not
3284 supported by this ioctl) 3214 supported by this ioctl)
3285 3215
3286 This is an asynchronous vcpu ioctl and can be 3216 This is an asynchronous vcpu ioctl and can be invoked from any thread.
3287 3217
3288 4.78 KVM_PPC_GET_HTAB_FD 3218 4.78 KVM_PPC_GET_HTAB_FD
3289 ------------------------ 3219 ------------------------
3290 3220
3291 :Capability: KVM_CAP_PPC_HTAB_FD 3221 :Capability: KVM_CAP_PPC_HTAB_FD
3292 :Architectures: powerpc 3222 :Architectures: powerpc
3293 :Type: vm ioctl 3223 :Type: vm ioctl
3294 :Parameters: Pointer to struct kvm_get_htab_f 3224 :Parameters: Pointer to struct kvm_get_htab_fd (in)
3295 :Returns: file descriptor number (>= 0) on su 3225 :Returns: file descriptor number (>= 0) on success, -1 on error
3296 3226
3297 This returns a file descriptor that can be us 3227 This returns a file descriptor that can be used either to read out the
3298 entries in the guest's hashed page table (HPT 3228 entries in the guest's hashed page table (HPT), or to write entries to
3299 initialize the HPT. The returned fd can only 3229 initialize the HPT. The returned fd can only be written to if the
3300 KVM_GET_HTAB_WRITE bit is set in the flags fi 3230 KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and
3301 can only be read if that bit is clear. The a 3231 can only be read if that bit is clear. The argument struct looks like
3302 this:: 3232 this::
3303 3233
3304 /* For KVM_PPC_GET_HTAB_FD */ 3234 /* For KVM_PPC_GET_HTAB_FD */
3305 struct kvm_get_htab_fd { 3235 struct kvm_get_htab_fd {
3306 __u64 flags; 3236 __u64 flags;
3307 __u64 start_index; 3237 __u64 start_index;
3308 __u64 reserved[2]; 3238 __u64 reserved[2];
3309 }; 3239 };
3310 3240
3311 /* Values for kvm_get_htab_fd.flags */ 3241 /* Values for kvm_get_htab_fd.flags */
3312 #define KVM_GET_HTAB_BOLTED_ONLY ((__u 3242 #define KVM_GET_HTAB_BOLTED_ONLY ((__u64)0x1)
3313 #define KVM_GET_HTAB_WRITE ((__u 3243 #define KVM_GET_HTAB_WRITE ((__u64)0x2)
3314 3244
3315 The 'start_index' field gives the index in th 3245 The 'start_index' field gives the index in the HPT of the entry at
3316 which to start reading. It is ignored when w 3246 which to start reading. It is ignored when writing.
3317 3247
3318 Reads on the fd will initially supply informa 3248 Reads on the fd will initially supply information about all
3319 "interesting" HPT entries. Interesting entri 3249 "interesting" HPT entries. Interesting entries are those with the
3320 bolted bit set, if the KVM_GET_HTAB_BOLTED_ON 3250 bolted bit set, if the KVM_GET_HTAB_BOLTED_ONLY bit is set, otherwise
3321 all entries. When the end of the HPT is reac 3251 all entries. When the end of the HPT is reached, the read() will
3322 return. If read() is called again on the fd, 3252 return. If read() is called again on the fd, it will start again from
3323 the beginning of the HPT, but will only retur 3253 the beginning of the HPT, but will only return HPT entries that have
3324 changed since they were last read. 3254 changed since they were last read.
3325 3255
3326 Data read or written is structured as a heade 3256 Data read or written is structured as a header (8 bytes) followed by a
3327 series of valid HPT entries (16 bytes) each. 3257 series of valid HPT entries (16 bytes) each. The header indicates how
3328 many valid HPT entries there are and how many 3258 many valid HPT entries there are and how many invalid entries follow
3329 the valid entries. The invalid entries are n 3259 the valid entries. The invalid entries are not represented explicitly
3330 in the stream. The header format is:: 3260 in the stream. The header format is::
3331 3261
3332 struct kvm_get_htab_header { 3262 struct kvm_get_htab_header {
3333 __u32 index; 3263 __u32 index;
3334 __u16 n_valid; 3264 __u16 n_valid;
3335 __u16 n_invalid; 3265 __u16 n_invalid;
3336 }; 3266 };
3337 3267
3338 Writes to the fd create HPT entries starting 3268 Writes to the fd create HPT entries starting at the index given in the
3339 header; first 'n_valid' valid entries with co 3269 header; first 'n_valid' valid entries with contents from the data
3340 written, then 'n_invalid' invalid entries, in 3270 written, then 'n_invalid' invalid entries, invalidating any previously
3341 valid entries found. 3271 valid entries found.
3342 3272
3343 4.79 KVM_CREATE_DEVICE 3273 4.79 KVM_CREATE_DEVICE
3344 ---------------------- 3274 ----------------------
3345 3275
3346 :Capability: KVM_CAP_DEVICE_CTRL 3276 :Capability: KVM_CAP_DEVICE_CTRL
3347 :Architectures: all 3277 :Architectures: all
3348 :Type: vm ioctl 3278 :Type: vm ioctl
3349 :Parameters: struct kvm_create_device (in/out 3279 :Parameters: struct kvm_create_device (in/out)
3350 :Returns: 0 on success, -1 on error 3280 :Returns: 0 on success, -1 on error
3351 3281
3352 Errors: 3282 Errors:
3353 3283
3354 ====== =================================== 3284 ====== =======================================================
3355 ENODEV The device type is unknown or unsup 3285 ENODEV The device type is unknown or unsupported
3356 EEXIST Device already created, and this ty 3286 EEXIST Device already created, and this type of device may not
3357 be instantiated multiple times 3287 be instantiated multiple times
3358 ====== =================================== 3288 ====== =======================================================
3359 3289
3360 Other error conditions may be defined by in 3290 Other error conditions may be defined by individual device types or
3361 have their standard meanings. 3291 have their standard meanings.
3362 3292
3363 Creates an emulated device in the kernel. Th 3293 Creates an emulated device in the kernel. The file descriptor returned
3364 in fd can be used with KVM_SET/GET/HAS_DEVICE 3294 in fd can be used with KVM_SET/GET/HAS_DEVICE_ATTR.
3365 3295
3366 If the KVM_CREATE_DEVICE_TEST flag is set, on 3296 If the KVM_CREATE_DEVICE_TEST flag is set, only test whether the
3367 device type is supported (not necessarily whe 3297 device type is supported (not necessarily whether it can be created
3368 in the current vm). 3298 in the current vm).
3369 3299
3370 Individual devices should not define flags. 3300 Individual devices should not define flags. Attributes should be used
3371 for specifying any behavior that is not impli 3301 for specifying any behavior that is not implied by the device type
3372 number. 3302 number.
3373 3303
3374 :: 3304 ::
3375 3305
3376 struct kvm_create_device { 3306 struct kvm_create_device {
3377 __u32 type; /* in: KVM_DEV_TYPE_x 3307 __u32 type; /* in: KVM_DEV_TYPE_xxx */
3378 __u32 fd; /* out: device handle 3308 __u32 fd; /* out: device handle */
3379 __u32 flags; /* in: KVM_CREATE_DEV 3309 __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */
3380 }; 3310 };
3381 3311
3382 4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR 3312 4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR
3383 -------------------------------------------- 3313 --------------------------------------------
3384 3314
3385 :Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ 3315 :Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
3386 KVM_CAP_VCPU_ATTRIBUTES for vcpu 3316 KVM_CAP_VCPU_ATTRIBUTES for vcpu device
3387 KVM_CAP_SYS_ATTRIBUTES for syste 3317 KVM_CAP_SYS_ATTRIBUTES for system (/dev/kvm) device (no set)
3388 :Architectures: x86, arm64, s390 3318 :Architectures: x86, arm64, s390
3389 :Type: device ioctl, vm ioctl, vcpu ioctl 3319 :Type: device ioctl, vm ioctl, vcpu ioctl
3390 :Parameters: struct kvm_device_attr 3320 :Parameters: struct kvm_device_attr
3391 :Returns: 0 on success, -1 on error 3321 :Returns: 0 on success, -1 on error
3392 3322
3393 Errors: 3323 Errors:
3394 3324
3395 ===== =================================== 3325 ===== =============================================================
3396 ENXIO The group or attribute is unknown/u 3326 ENXIO The group or attribute is unknown/unsupported for this device
3397 or hardware support is missing. 3327 or hardware support is missing.
3398 EPERM The attribute cannot (currently) be 3328 EPERM The attribute cannot (currently) be accessed this way
3399 (e.g. read-only attribute, or attri 3329 (e.g. read-only attribute, or attribute that only makes
3400 sense when the device is in a diffe 3330 sense when the device is in a different state)
3401 ===== =================================== 3331 ===== =============================================================
3402 3332
3403 Other error conditions may be defined by in 3333 Other error conditions may be defined by individual device types.
3404 3334
3405 Gets/sets a specified piece of device configu 3335 Gets/sets a specified piece of device configuration and/or state. The
3406 semantics are device-specific. See individua 3336 semantics are device-specific. See individual device documentation in
3407 the "devices" directory. As with ONE_REG, th 3337 the "devices" directory. As with ONE_REG, the size of the data
3408 transferred is defined by the particular attr 3338 transferred is defined by the particular attribute.
3409 3339
3410 :: 3340 ::
3411 3341
3412 struct kvm_device_attr { 3342 struct kvm_device_attr {
3413 __u32 flags; /* no flags c 3343 __u32 flags; /* no flags currently defined */
3414 __u32 group; /* device-def 3344 __u32 group; /* device-defined */
3415 __u64 attr; /* group-defi 3345 __u64 attr; /* group-defined */
3416 __u64 addr; /* userspace 3346 __u64 addr; /* userspace address of attr data */
3417 }; 3347 };
3418 3348
3419 4.81 KVM_HAS_DEVICE_ATTR 3349 4.81 KVM_HAS_DEVICE_ATTR
3420 ------------------------ 3350 ------------------------
3421 3351
3422 :Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ 3352 :Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
3423 KVM_CAP_VCPU_ATTRIBUTES for vcpu 3353 KVM_CAP_VCPU_ATTRIBUTES for vcpu device
3424 KVM_CAP_SYS_ATTRIBUTES for syste 3354 KVM_CAP_SYS_ATTRIBUTES for system (/dev/kvm) device
3425 :Type: device ioctl, vm ioctl, vcpu ioctl 3355 :Type: device ioctl, vm ioctl, vcpu ioctl
3426 :Parameters: struct kvm_device_attr 3356 :Parameters: struct kvm_device_attr
3427 :Returns: 0 on success, -1 on error 3357 :Returns: 0 on success, -1 on error
3428 3358
3429 Errors: 3359 Errors:
3430 3360
3431 ===== =================================== 3361 ===== =============================================================
3432 ENXIO The group or attribute is unknown/u 3362 ENXIO The group or attribute is unknown/unsupported for this device
3433 or hardware support is missing. 3363 or hardware support is missing.
3434 ===== =================================== 3364 ===== =============================================================
3435 3365
3436 Tests whether a device supports a particular 3366 Tests whether a device supports a particular attribute. A successful
3437 return indicates the attribute is implemented 3367 return indicates the attribute is implemented. It does not necessarily
3438 indicate that the attribute can be read or wr 3368 indicate that the attribute can be read or written in the device's
3439 current state. "addr" is ignored. 3369 current state. "addr" is ignored.
3440 3370
3441 .. _KVM_ARM_VCPU_INIT: <<
3442 <<
3443 4.82 KVM_ARM_VCPU_INIT 3371 4.82 KVM_ARM_VCPU_INIT
3444 ---------------------- 3372 ----------------------
3445 3373
3446 :Capability: basic 3374 :Capability: basic
3447 :Architectures: arm64 3375 :Architectures: arm64
3448 :Type: vcpu ioctl 3376 :Type: vcpu ioctl
3449 :Parameters: struct kvm_vcpu_init (in) 3377 :Parameters: struct kvm_vcpu_init (in)
3450 :Returns: 0 on success; -1 on error 3378 :Returns: 0 on success; -1 on error
3451 3379
3452 Errors: 3380 Errors:
3453 3381
3454 ====== ================================ 3382 ====== =================================================================
3455 EINVAL the target is unknown, or the co 3383 EINVAL the target is unknown, or the combination of features is invalid.
3456 ENOENT a features bit specified is unkn 3384 ENOENT a features bit specified is unknown.
3457 ====== ================================ 3385 ====== =================================================================
3458 3386
3459 This tells KVM what type of CPU to present to 3387 This tells KVM what type of CPU to present to the guest, and what
3460 optional features it should have. This will 3388 optional features it should have. This will cause a reset of the cpu
3461 registers to their initial values. If this i 3389 registers to their initial values. If this is not called, KVM_RUN will
3462 return ENOEXEC for that vcpu. 3390 return ENOEXEC for that vcpu.
3463 3391
3464 The initial values are defined as: 3392 The initial values are defined as:
3465 - Processor state: 3393 - Processor state:
3466 * AArch64: EL1h, D, A, I and 3394 * AArch64: EL1h, D, A, I and F bits set. All other bits
3467 are cleared. 3395 are cleared.
3468 * AArch32: SVC, A, I and F bi 3396 * AArch32: SVC, A, I and F bits set. All other bits are
3469 cleared. 3397 cleared.
3470 - General Purpose registers, includin 3398 - General Purpose registers, including PC and SP: set to 0
3471 - FPSIMD/NEON registers: set to 0 3399 - FPSIMD/NEON registers: set to 0
3472 - SVE registers: set to 0 3400 - SVE registers: set to 0
3473 - System registers: Reset to their ar 3401 - System registers: Reset to their architecturally defined
3474 values as for a warm reset to EL1 ( 3402 values as for a warm reset to EL1 (resp. SVC)
3475 3403
3476 Note that because some registers reflect mach 3404 Note that because some registers reflect machine topology, all vcpus
3477 should be created before this ioctl is invoke 3405 should be created before this ioctl is invoked.
3478 3406
3479 Userspace can call this function multiple tim 3407 Userspace can call this function multiple times for a given vcpu, including
3480 after the vcpu has been run. This will reset 3408 after the vcpu has been run. This will reset the vcpu to its initial
3481 state. All calls to this function after the i 3409 state. All calls to this function after the initial call must use the same
3482 target and same set of feature flags, otherwi 3410 target and same set of feature flags, otherwise EINVAL will be returned.
3483 3411
3484 Possible features: 3412 Possible features:
3485 3413
3486 - KVM_ARM_VCPU_POWER_OFF: Starts the 3414 - KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state.
3487 Depends on KVM_CAP_ARM_PSCI. If no 3415 Depends on KVM_CAP_ARM_PSCI. If not set, the CPU will be powered on
3488 and execute guest code when KVM_RUN 3416 and execute guest code when KVM_RUN is called.
3489 - KVM_ARM_VCPU_EL1_32BIT: Starts the 3417 - KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
3490 Depends on KVM_CAP_ARM_EL1_32BIT (a 3418 Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
3491 - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI 3419 - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 (or a future revision
3492 backward compatible with v0.2) for 3420 backward compatible with v0.2) for the CPU.
3493 Depends on KVM_CAP_ARM_PSCI_0_2. 3421 Depends on KVM_CAP_ARM_PSCI_0_2.
3494 - KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 3422 - KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU.
3495 Depends on KVM_CAP_ARM_PMU_V3. 3423 Depends on KVM_CAP_ARM_PMU_V3.
3496 3424
3497 - KVM_ARM_VCPU_PTRAUTH_ADDRESS: Enabl 3425 - KVM_ARM_VCPU_PTRAUTH_ADDRESS: Enables Address Pointer authentication
3498 for arm64 only. 3426 for arm64 only.
3499 Depends on KVM_CAP_ARM_PTRAUTH_ADDR 3427 Depends on KVM_CAP_ARM_PTRAUTH_ADDRESS.
3500 If KVM_CAP_ARM_PTRAUTH_ADDRESS and 3428 If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are
3501 both present, then both KVM_ARM_VCP 3429 both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and
3502 KVM_ARM_VCPU_PTRAUTH_GENERIC must b 3430 KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be
3503 requested. 3431 requested.
3504 3432
3505 - KVM_ARM_VCPU_PTRAUTH_GENERIC: Enabl 3433 - KVM_ARM_VCPU_PTRAUTH_GENERIC: Enables Generic Pointer authentication
3506 for arm64 only. 3434 for arm64 only.
3507 Depends on KVM_CAP_ARM_PTRAUTH_GENE 3435 Depends on KVM_CAP_ARM_PTRAUTH_GENERIC.
3508 If KVM_CAP_ARM_PTRAUTH_ADDRESS and 3436 If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are
3509 both present, then both KVM_ARM_VCP 3437 both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and
3510 KVM_ARM_VCPU_PTRAUTH_GENERIC must b 3438 KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be
3511 requested. 3439 requested.
3512 3440
3513 - KVM_ARM_VCPU_SVE: Enables SVE for t 3441 - KVM_ARM_VCPU_SVE: Enables SVE for the CPU (arm64 only).
3514 Depends on KVM_CAP_ARM_SVE. 3442 Depends on KVM_CAP_ARM_SVE.
3515 Requires KVM_ARM_VCPU_FINALIZE(KVM_ 3443 Requires KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE):
3516 3444
3517 * After KVM_ARM_VCPU_INIT: 3445 * After KVM_ARM_VCPU_INIT:
3518 3446
3519 - KVM_REG_ARM64_SVE_VLS may be 3447 - KVM_REG_ARM64_SVE_VLS may be read using KVM_GET_ONE_REG: the
3520 initial value of this pseudo- 3448 initial value of this pseudo-register indicates the best set of
3521 vector lengths possible for a 3449 vector lengths possible for a vcpu on this host.
3522 3450
3523 * Before KVM_ARM_VCPU_FINALIZE(KVM 3451 * Before KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE):
3524 3452
3525 - KVM_RUN and KVM_GET_REG_LIST 3453 - KVM_RUN and KVM_GET_REG_LIST are not available;
3526 3454
3527 - KVM_GET_ONE_REG and KVM_SET_O 3455 - KVM_GET_ONE_REG and KVM_SET_ONE_REG cannot be used to access
3528 the scalable architectural SV !! 3456 the scalable archietctural SVE registers
3529 KVM_REG_ARM64_SVE_ZREG(), KVM 3457 KVM_REG_ARM64_SVE_ZREG(), KVM_REG_ARM64_SVE_PREG() or
3530 KVM_REG_ARM64_SVE_FFR; 3458 KVM_REG_ARM64_SVE_FFR;
3531 3459
3532 - KVM_REG_ARM64_SVE_VLS may opt 3460 - KVM_REG_ARM64_SVE_VLS may optionally be written using
3533 KVM_SET_ONE_REG, to modify th 3461 KVM_SET_ONE_REG, to modify the set of vector lengths available
3534 for the vcpu. 3462 for the vcpu.
3535 3463
3536 * After KVM_ARM_VCPU_FINALIZE(KVM_ 3464 * After KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE):
3537 3465
3538 - the KVM_REG_ARM64_SVE_VLS pse 3466 - the KVM_REG_ARM64_SVE_VLS pseudo-register is immutable, and can
3539 no longer be written using KV 3467 no longer be written using KVM_SET_ONE_REG.
3540 3468
3541 4.83 KVM_ARM_PREFERRED_TARGET 3469 4.83 KVM_ARM_PREFERRED_TARGET
3542 ----------------------------- 3470 -----------------------------
3543 3471
3544 :Capability: basic 3472 :Capability: basic
3545 :Architectures: arm64 3473 :Architectures: arm64
3546 :Type: vm ioctl 3474 :Type: vm ioctl
3547 :Parameters: struct kvm_vcpu_init (out) 3475 :Parameters: struct kvm_vcpu_init (out)
3548 :Returns: 0 on success; -1 on error 3476 :Returns: 0 on success; -1 on error
3549 3477
3550 Errors: 3478 Errors:
3551 3479
3552 ====== ================================ 3480 ====== ==========================================
3553 ENODEV no preferred target available fo 3481 ENODEV no preferred target available for the host
3554 ====== ================================ 3482 ====== ==========================================
3555 3483
3556 This queries KVM for preferred CPU target typ 3484 This queries KVM for preferred CPU target type which can be emulated
3557 by KVM on underlying host. 3485 by KVM on underlying host.
3558 3486
3559 The ioctl returns struct kvm_vcpu_init instan 3487 The ioctl returns struct kvm_vcpu_init instance containing information
3560 about preferred CPU target type and recommend 3488 about preferred CPU target type and recommended features for it. The
3561 kvm_vcpu_init->features bitmap returned will 3489 kvm_vcpu_init->features bitmap returned will have feature bits set if
3562 the preferred target recommends setting these 3490 the preferred target recommends setting these features, but this is
3563 not mandatory. 3491 not mandatory.
3564 3492
3565 The information returned by this ioctl can be 3493 The information returned by this ioctl can be used to prepare an instance
3566 of struct kvm_vcpu_init for KVM_ARM_VCPU_INIT 3494 of struct kvm_vcpu_init for KVM_ARM_VCPU_INIT ioctl which will result in
3567 VCPU matching underlying host. 3495 VCPU matching underlying host.
3568 3496
3569 3497
3570 4.84 KVM_GET_REG_LIST 3498 4.84 KVM_GET_REG_LIST
3571 --------------------- 3499 ---------------------
3572 3500
3573 :Capability: basic 3501 :Capability: basic
3574 :Architectures: arm64, mips, riscv !! 3502 :Architectures: arm64, mips
3575 :Type: vcpu ioctl 3503 :Type: vcpu ioctl
3576 :Parameters: struct kvm_reg_list (in/out) 3504 :Parameters: struct kvm_reg_list (in/out)
3577 :Returns: 0 on success; -1 on error 3505 :Returns: 0 on success; -1 on error
3578 3506
3579 Errors: 3507 Errors:
3580 3508
3581 ===== ================================ 3509 ===== ==============================================================
3582 E2BIG the reg index list is too big to 3510 E2BIG the reg index list is too big to fit in the array specified by
3583 the user (the number required wi 3511 the user (the number required will be written into n).
3584 ===== ================================ 3512 ===== ==============================================================
3585 3513
3586 :: 3514 ::
3587 3515
3588 struct kvm_reg_list { 3516 struct kvm_reg_list {
3589 __u64 n; /* number of registers in re 3517 __u64 n; /* number of registers in reg[] */
3590 __u64 reg[0]; 3518 __u64 reg[0];
3591 }; 3519 };
3592 3520
3593 This ioctl returns the guest registers that a 3521 This ioctl returns the guest registers that are supported for the
3594 KVM_GET_ONE_REG/KVM_SET_ONE_REG calls. 3522 KVM_GET_ONE_REG/KVM_SET_ONE_REG calls.
3595 3523
3596 3524
3597 4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated) 3525 4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated)
3598 ----------------------------------------- 3526 -----------------------------------------
3599 3527
3600 :Capability: KVM_CAP_ARM_SET_DEVICE_ADDR 3528 :Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
3601 :Architectures: arm64 3529 :Architectures: arm64
3602 :Type: vm ioctl 3530 :Type: vm ioctl
3603 :Parameters: struct kvm_arm_device_address (i 3531 :Parameters: struct kvm_arm_device_address (in)
3604 :Returns: 0 on success, -1 on error 3532 :Returns: 0 on success, -1 on error
3605 3533
3606 Errors: 3534 Errors:
3607 3535
3608 ====== =================================== 3536 ====== ============================================
3609 ENODEV The device id is unknown 3537 ENODEV The device id is unknown
3610 ENXIO Device not supported on current sys 3538 ENXIO Device not supported on current system
3611 EEXIST Address already set 3539 EEXIST Address already set
3612 E2BIG Address outside guest physical addr 3540 E2BIG Address outside guest physical address space
3613 EBUSY Address overlaps with other device 3541 EBUSY Address overlaps with other device range
3614 ====== =================================== 3542 ====== ============================================
3615 3543
3616 :: 3544 ::
3617 3545
3618 struct kvm_arm_device_addr { 3546 struct kvm_arm_device_addr {
3619 __u64 id; 3547 __u64 id;
3620 __u64 addr; 3548 __u64 addr;
3621 }; 3549 };
3622 3550
3623 Specify a device address in the guest's physi 3551 Specify a device address in the guest's physical address space where guests
3624 can access emulated or directly exposed devic 3552 can access emulated or directly exposed devices, which the host kernel needs
3625 to know about. The id field is an architectur 3553 to know about. The id field is an architecture specific identifier for a
3626 specific device. 3554 specific device.
3627 3555
3628 arm64 divides the id field into two parts, a 3556 arm64 divides the id field into two parts, a device id and an
3629 address type id specific to the individual de 3557 address type id specific to the individual device::
3630 3558
3631 bits: | 63 ... 32 | 31 ... 3559 bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 |
3632 field: | 0x00000000 | devic 3560 field: | 0x00000000 | device id | addr type id |
3633 3561
3634 arm64 currently only require this when using 3562 arm64 currently only require this when using the in-kernel GIC
3635 support for the hardware VGIC features, using 3563 support for the hardware VGIC features, using KVM_ARM_DEVICE_VGIC_V2
3636 as the device id. When setting the base addr 3564 as the device id. When setting the base address for the guest's
3637 mapping of the VGIC virtual CPU and distribut 3565 mapping of the VGIC virtual CPU and distributor interface, the ioctl
3638 must be called after calling KVM_CREATE_IRQCH 3566 must be called after calling KVM_CREATE_IRQCHIP, but before calling
3639 KVM_RUN on any of the VCPUs. Calling this io 3567 KVM_RUN on any of the VCPUs. Calling this ioctl twice for any of the
3640 base addresses will return -EEXIST. 3568 base addresses will return -EEXIST.
3641 3569
3642 Note, this IOCTL is deprecated and the more f 3570 Note, this IOCTL is deprecated and the more flexible SET/GET_DEVICE_ATTR API
3643 should be used instead. 3571 should be used instead.
3644 3572
3645 3573
3646 4.86 KVM_PPC_RTAS_DEFINE_TOKEN 3574 4.86 KVM_PPC_RTAS_DEFINE_TOKEN
3647 ------------------------------ 3575 ------------------------------
3648 3576
3649 :Capability: KVM_CAP_PPC_RTAS 3577 :Capability: KVM_CAP_PPC_RTAS
3650 :Architectures: ppc 3578 :Architectures: ppc
3651 :Type: vm ioctl 3579 :Type: vm ioctl
3652 :Parameters: struct kvm_rtas_token_args 3580 :Parameters: struct kvm_rtas_token_args
3653 :Returns: 0 on success, -1 on error 3581 :Returns: 0 on success, -1 on error
3654 3582
3655 Defines a token value for a RTAS (Run Time Ab 3583 Defines a token value for a RTAS (Run Time Abstraction Services)
3656 service in order to allow it to be handled in 3584 service in order to allow it to be handled in the kernel. The
3657 argument struct gives the name of the service 3585 argument struct gives the name of the service, which must be the name
3658 of a service that has a kernel-side implement 3586 of a service that has a kernel-side implementation. If the token
3659 value is non-zero, it will be associated with 3587 value is non-zero, it will be associated with that service, and
3660 subsequent RTAS calls by the guest specifying 3588 subsequent RTAS calls by the guest specifying that token will be
3661 handled by the kernel. If the token value is 3589 handled by the kernel. If the token value is 0, then any token
3662 associated with the service will be forgotten 3590 associated with the service will be forgotten, and subsequent RTAS
3663 calls by the guest for that service will be p 3591 calls by the guest for that service will be passed to userspace to be
3664 handled. 3592 handled.
3665 3593
3666 4.87 KVM_SET_GUEST_DEBUG 3594 4.87 KVM_SET_GUEST_DEBUG
3667 ------------------------ 3595 ------------------------
3668 3596
3669 :Capability: KVM_CAP_SET_GUEST_DEBUG 3597 :Capability: KVM_CAP_SET_GUEST_DEBUG
3670 :Architectures: x86, s390, ppc, arm64 3598 :Architectures: x86, s390, ppc, arm64
3671 :Type: vcpu ioctl 3599 :Type: vcpu ioctl
3672 :Parameters: struct kvm_guest_debug (in) 3600 :Parameters: struct kvm_guest_debug (in)
3673 :Returns: 0 on success; -1 on error 3601 :Returns: 0 on success; -1 on error
3674 3602
3675 :: 3603 ::
3676 3604
3677 struct kvm_guest_debug { 3605 struct kvm_guest_debug {
3678 __u32 control; 3606 __u32 control;
3679 __u32 pad; 3607 __u32 pad;
3680 struct kvm_guest_debug_arch arch; 3608 struct kvm_guest_debug_arch arch;
3681 }; 3609 };
3682 3610
3683 Set up the processor specific debug registers 3611 Set up the processor specific debug registers and configure vcpu for
3684 handling guest debug events. There are two pa 3612 handling guest debug events. There are two parts to the structure, the
3685 first a control bitfield indicates the type o 3613 first a control bitfield indicates the type of debug events to handle
3686 when running. Common control bits are: 3614 when running. Common control bits are:
3687 3615
3688 - KVM_GUESTDBG_ENABLE: guest debuggi 3616 - KVM_GUESTDBG_ENABLE: guest debugging is enabled
3689 - KVM_GUESTDBG_SINGLESTEP: the next run 3617 - KVM_GUESTDBG_SINGLESTEP: the next run should single-step
3690 3618
3691 The top 16 bits of the control field are arch 3619 The top 16 bits of the control field are architecture specific control
3692 flags which can include the following: 3620 flags which can include the following:
3693 3621
3694 - KVM_GUESTDBG_USE_SW_BP: using softwar 3622 - KVM_GUESTDBG_USE_SW_BP: using software breakpoints [x86, arm64]
3695 - KVM_GUESTDBG_USE_HW_BP: using hardwar 3623 - KVM_GUESTDBG_USE_HW_BP: using hardware breakpoints [x86, s390]
3696 - KVM_GUESTDBG_USE_HW: using hardwar 3624 - KVM_GUESTDBG_USE_HW: using hardware debug events [arm64]
3697 - KVM_GUESTDBG_INJECT_DB: inject DB typ 3625 - KVM_GUESTDBG_INJECT_DB: inject DB type exception [x86]
3698 - KVM_GUESTDBG_INJECT_BP: inject BP typ 3626 - KVM_GUESTDBG_INJECT_BP: inject BP type exception [x86]
3699 - KVM_GUESTDBG_EXIT_PENDING: trigger an im 3627 - KVM_GUESTDBG_EXIT_PENDING: trigger an immediate guest exit [s390]
3700 - KVM_GUESTDBG_BLOCKIRQ: avoid injecti 3628 - KVM_GUESTDBG_BLOCKIRQ: avoid injecting interrupts/NMI/SMI [x86]
3701 3629
3702 For example KVM_GUESTDBG_USE_SW_BP indicates 3630 For example KVM_GUESTDBG_USE_SW_BP indicates that software breakpoints
3703 are enabled in memory so we need to ensure br 3631 are enabled in memory so we need to ensure breakpoint exceptions are
3704 correctly trapped and the KVM run loop exits 3632 correctly trapped and the KVM run loop exits at the breakpoint and not
3705 running off into the normal guest vector. For 3633 running off into the normal guest vector. For KVM_GUESTDBG_USE_HW_BP
3706 we need to ensure the guest vCPUs architectur 3634 we need to ensure the guest vCPUs architecture specific registers are
3707 updated to the correct (supplied) values. 3635 updated to the correct (supplied) values.
3708 3636
3709 The second part of the structure is architect 3637 The second part of the structure is architecture specific and
3710 typically contains a set of debug registers. 3638 typically contains a set of debug registers.
3711 3639
3712 For arm64 the number of debug registers is im 3640 For arm64 the number of debug registers is implementation defined and
3713 can be determined by querying the KVM_CAP_GUE 3641 can be determined by querying the KVM_CAP_GUEST_DEBUG_HW_BPS and
3714 KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which 3642 KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which return a positive number
3715 indicating the number of supported registers. 3643 indicating the number of supported registers.
3716 3644
3717 For ppc, the KVM_CAP_PPC_GUEST_DEBUG_SSTEP ca 3645 For ppc, the KVM_CAP_PPC_GUEST_DEBUG_SSTEP capability indicates whether
3718 the single-step debug event (KVM_GUESTDBG_SIN 3646 the single-step debug event (KVM_GUESTDBG_SINGLESTEP) is supported.
3719 3647
3720 Also when supported, KVM_CAP_SET_GUEST_DEBUG2 3648 Also when supported, KVM_CAP_SET_GUEST_DEBUG2 capability indicates the
3721 supported KVM_GUESTDBG_* bits in the control 3649 supported KVM_GUESTDBG_* bits in the control field.
3722 3650
3723 When debug events exit the main run loop with 3651 When debug events exit the main run loop with the reason
3724 KVM_EXIT_DEBUG with the kvm_debug_exit_arch p 3652 KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run
3725 structure containing architecture specific de 3653 structure containing architecture specific debug information.
3726 3654
3727 4.88 KVM_GET_EMULATED_CPUID 3655 4.88 KVM_GET_EMULATED_CPUID
3728 --------------------------- 3656 ---------------------------
3729 3657
3730 :Capability: KVM_CAP_EXT_EMUL_CPUID 3658 :Capability: KVM_CAP_EXT_EMUL_CPUID
3731 :Architectures: x86 3659 :Architectures: x86
3732 :Type: system ioctl 3660 :Type: system ioctl
3733 :Parameters: struct kvm_cpuid2 (in/out) 3661 :Parameters: struct kvm_cpuid2 (in/out)
3734 :Returns: 0 on success, -1 on error 3662 :Returns: 0 on success, -1 on error
3735 3663
3736 :: 3664 ::
3737 3665
3738 struct kvm_cpuid2 { 3666 struct kvm_cpuid2 {
3739 __u32 nent; 3667 __u32 nent;
3740 __u32 flags; 3668 __u32 flags;
3741 struct kvm_cpuid_entry2 entries[0]; 3669 struct kvm_cpuid_entry2 entries[0];
3742 }; 3670 };
3743 3671
3744 The member 'flags' is used for passing flags 3672 The member 'flags' is used for passing flags from userspace.
3745 3673
3746 :: 3674 ::
3747 3675
3748 #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 3676 #define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
3749 #define KVM_CPUID_FLAG_STATEFUL_FUNC 3677 #define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) /* deprecated */
3750 #define KVM_CPUID_FLAG_STATE_READ_NEXT 3678 #define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) /* deprecated */
3751 3679
3752 struct kvm_cpuid_entry2 { 3680 struct kvm_cpuid_entry2 {
3753 __u32 function; 3681 __u32 function;
3754 __u32 index; 3682 __u32 index;
3755 __u32 flags; 3683 __u32 flags;
3756 __u32 eax; 3684 __u32 eax;
3757 __u32 ebx; 3685 __u32 ebx;
3758 __u32 ecx; 3686 __u32 ecx;
3759 __u32 edx; 3687 __u32 edx;
3760 __u32 padding[3]; 3688 __u32 padding[3];
3761 }; 3689 };
3762 3690
3763 This ioctl returns x86 cpuid features which a 3691 This ioctl returns x86 cpuid features which are emulated by
3764 kvm.Userspace can use the information returne 3692 kvm.Userspace can use the information returned by this ioctl to query
3765 which features are emulated by kvm instead of 3693 which features are emulated by kvm instead of being present natively.
3766 3694
3767 Userspace invokes KVM_GET_EMULATED_CPUID by p 3695 Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2
3768 structure with the 'nent' field indicating th 3696 structure with the 'nent' field indicating the number of entries in
3769 the variable-size array 'entries'. If the num 3697 the variable-size array 'entries'. If the number of entries is too low
3770 to describe the cpu capabilities, an error (E 3698 to describe the cpu capabilities, an error (E2BIG) is returned. If the
3771 number is too high, the 'nent' field is adjus 3699 number is too high, the 'nent' field is adjusted and an error (ENOMEM)
3772 is returned. If the number is just right, the 3700 is returned. If the number is just right, the 'nent' field is adjusted
3773 to the number of valid entries in the 'entrie 3701 to the number of valid entries in the 'entries' array, which is then
3774 filled. 3702 filled.
3775 3703
3776 The entries returned are the set CPUID bits o 3704 The entries returned are the set CPUID bits of the respective features
3777 which kvm emulates, as returned by the CPUID 3705 which kvm emulates, as returned by the CPUID instruction, with unknown
3778 or unsupported feature bits cleared. 3706 or unsupported feature bits cleared.
3779 3707
3780 Features like x2apic, for example, may not be 3708 Features like x2apic, for example, may not be present in the host cpu
3781 but are exposed by kvm in KVM_GET_SUPPORTED_C 3709 but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be
3782 emulated efficiently and thus not included he 3710 emulated efficiently and thus not included here.
3783 3711
3784 The fields in each entry are defined as follo 3712 The fields in each entry are defined as follows:
3785 3713
3786 function: 3714 function:
3787 the eax value used to obtain the ent 3715 the eax value used to obtain the entry
3788 index: 3716 index:
3789 the ecx value used to obtain the ent 3717 the ecx value used to obtain the entry (for entries that are
3790 affected by ecx) 3718 affected by ecx)
3791 flags: 3719 flags:
3792 an OR of zero or more of the following: 3720 an OR of zero or more of the following:
3793 3721
3794 KVM_CPUID_FLAG_SIGNIFCANT_INDEX: 3722 KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
3795 if the index field is valid 3723 if the index field is valid
3796 3724
3797 eax, ebx, ecx, edx: 3725 eax, ebx, ecx, edx:
3798 3726
3799 the values returned by the cpuid ins 3727 the values returned by the cpuid instruction for
3800 this function/index combination 3728 this function/index combination
3801 3729
3802 4.89 KVM_S390_MEM_OP 3730 4.89 KVM_S390_MEM_OP
3803 -------------------- 3731 --------------------
3804 3732
3805 :Capability: KVM_CAP_S390_MEM_OP, KVM_CAP_S39 3733 :Capability: KVM_CAP_S390_MEM_OP, KVM_CAP_S390_PROTECTED, KVM_CAP_S390_MEM_OP_EXTENSION
3806 :Architectures: s390 3734 :Architectures: s390
3807 :Type: vm ioctl, vcpu ioctl 3735 :Type: vm ioctl, vcpu ioctl
3808 :Parameters: struct kvm_s390_mem_op (in) 3736 :Parameters: struct kvm_s390_mem_op (in)
3809 :Returns: = 0 on success, 3737 :Returns: = 0 on success,
3810 < 0 on generic error (e.g. -EFAULT 3738 < 0 on generic error (e.g. -EFAULT or -ENOMEM),
3811 16 bit program exception code if th 3739 16 bit program exception code if the access causes such an exception
3812 3740
3813 Read or write data from/to the VM's memory. 3741 Read or write data from/to the VM's memory.
3814 The KVM_CAP_S390_MEM_OP_EXTENSION capability 3742 The KVM_CAP_S390_MEM_OP_EXTENSION capability specifies what functionality is
3815 supported. 3743 supported.
3816 3744
3817 Parameters are specified via the following st 3745 Parameters are specified via the following structure::
3818 3746
3819 struct kvm_s390_mem_op { 3747 struct kvm_s390_mem_op {
3820 __u64 gaddr; /* the guest 3748 __u64 gaddr; /* the guest address */
3821 __u64 flags; /* flags */ 3749 __u64 flags; /* flags */
3822 __u32 size; /* amount of 3750 __u32 size; /* amount of bytes */
3823 __u32 op; /* type of op 3751 __u32 op; /* type of operation */
3824 __u64 buf; /* buffer in 3752 __u64 buf; /* buffer in userspace */
3825 union { 3753 union {
3826 struct { 3754 struct {
3827 __u8 ar; /* th 3755 __u8 ar; /* the access register number */
3828 __u8 key; /* ac 3756 __u8 key; /* access key, ignored if flag unset */
3829 __u8 pad1[6]; /* ig 3757 __u8 pad1[6]; /* ignored */
3830 __u64 old_addr; /* ig 3758 __u64 old_addr; /* ignored if flag unset */
3831 }; 3759 };
3832 __u32 sida_offset; /* offset 3760 __u32 sida_offset; /* offset into the sida */
3833 __u8 reserved[32]; /* ignored 3761 __u8 reserved[32]; /* ignored */
3834 }; 3762 };
3835 }; 3763 };
3836 3764
3837 The start address of the memory region has to 3765 The start address of the memory region has to be specified in the "gaddr"
3838 field, and the length of the region in the "s 3766 field, and the length of the region in the "size" field (which must not
3839 be 0). The maximum value for "size" can be ob 3767 be 0). The maximum value for "size" can be obtained by checking the
3840 KVM_CAP_S390_MEM_OP capability. "buf" is the 3768 KVM_CAP_S390_MEM_OP capability. "buf" is the buffer supplied by the
3841 userspace application where the read data sho 3769 userspace application where the read data should be written to for
3842 a read access, or where the data that should 3770 a read access, or where the data that should be written is stored for
3843 a write access. The "reserved" field is mean 3771 a write access. The "reserved" field is meant for future extensions.
3844 Reserved and unused values are ignored. Futur 3772 Reserved and unused values are ignored. Future extension that add members must
3845 introduce new flags. 3773 introduce new flags.
3846 3774
3847 The type of operation is specified in the "op 3775 The type of operation is specified in the "op" field. Flags modifying
3848 their behavior can be set in the "flags" fiel 3776 their behavior can be set in the "flags" field. Undefined flag bits must
3849 be set to 0. 3777 be set to 0.
3850 3778
3851 Possible operations are: 3779 Possible operations are:
3852 * ``KVM_S390_MEMOP_LOGICAL_READ`` 3780 * ``KVM_S390_MEMOP_LOGICAL_READ``
3853 * ``KVM_S390_MEMOP_LOGICAL_WRITE`` 3781 * ``KVM_S390_MEMOP_LOGICAL_WRITE``
3854 * ``KVM_S390_MEMOP_ABSOLUTE_READ`` 3782 * ``KVM_S390_MEMOP_ABSOLUTE_READ``
3855 * ``KVM_S390_MEMOP_ABSOLUTE_WRITE`` 3783 * ``KVM_S390_MEMOP_ABSOLUTE_WRITE``
3856 * ``KVM_S390_MEMOP_SIDA_READ`` 3784 * ``KVM_S390_MEMOP_SIDA_READ``
3857 * ``KVM_S390_MEMOP_SIDA_WRITE`` 3785 * ``KVM_S390_MEMOP_SIDA_WRITE``
3858 * ``KVM_S390_MEMOP_ABSOLUTE_CMPXCHG`` 3786 * ``KVM_S390_MEMOP_ABSOLUTE_CMPXCHG``
3859 3787
3860 Logical read/write: 3788 Logical read/write:
3861 ^^^^^^^^^^^^^^^^^^^ 3789 ^^^^^^^^^^^^^^^^^^^
3862 3790
3863 Access logical memory, i.e. translate the giv 3791 Access logical memory, i.e. translate the given guest address to an absolute
3864 address given the state of the VCPU and use t 3792 address given the state of the VCPU and use the absolute address as target of
3865 the access. "ar" designates the access regist 3793 the access. "ar" designates the access register number to be used; the valid
3866 range is 0..15. 3794 range is 0..15.
3867 Logical accesses are permitted for the VCPU i 3795 Logical accesses are permitted for the VCPU ioctl only.
3868 Logical accesses are permitted for non-protec 3796 Logical accesses are permitted for non-protected guests only.
3869 3797
3870 Supported flags: 3798 Supported flags:
3871 * ``KVM_S390_MEMOP_F_CHECK_ONLY`` 3799 * ``KVM_S390_MEMOP_F_CHECK_ONLY``
3872 * ``KVM_S390_MEMOP_F_INJECT_EXCEPTION`` 3800 * ``KVM_S390_MEMOP_F_INJECT_EXCEPTION``
3873 * ``KVM_S390_MEMOP_F_SKEY_PROTECTION`` 3801 * ``KVM_S390_MEMOP_F_SKEY_PROTECTION``
3874 3802
3875 The KVM_S390_MEMOP_F_CHECK_ONLY flag can be s 3803 The KVM_S390_MEMOP_F_CHECK_ONLY flag can be set to check whether the
3876 corresponding memory access would cause an ac 3804 corresponding memory access would cause an access exception; however,
3877 no actual access to the data in memory at the 3805 no actual access to the data in memory at the destination is performed.
3878 In this case, "buf" is unused and can be NULL 3806 In this case, "buf" is unused and can be NULL.
3879 3807
3880 In case an access exception occurred during t 3808 In case an access exception occurred during the access (or would occur
3881 in case of KVM_S390_MEMOP_F_CHECK_ONLY), the 3809 in case of KVM_S390_MEMOP_F_CHECK_ONLY), the ioctl returns a positive
3882 error number indicating the type of exception 3810 error number indicating the type of exception. This exception is also
3883 raised directly at the corresponding VCPU if 3811 raised directly at the corresponding VCPU if the flag
3884 KVM_S390_MEMOP_F_INJECT_EXCEPTION is set. 3812 KVM_S390_MEMOP_F_INJECT_EXCEPTION is set.
3885 On protection exceptions, unless specified ot 3813 On protection exceptions, unless specified otherwise, the injected
3886 translation-exception identifier (TEID) indic 3814 translation-exception identifier (TEID) indicates suppression.
3887 3815
3888 If the KVM_S390_MEMOP_F_SKEY_PROTECTION flag 3816 If the KVM_S390_MEMOP_F_SKEY_PROTECTION flag is set, storage key
3889 protection is also in effect and may cause ex 3817 protection is also in effect and may cause exceptions if accesses are
3890 prohibited given the access key designated by 3818 prohibited given the access key designated by "key"; the valid range is 0..15.
3891 KVM_S390_MEMOP_F_SKEY_PROTECTION is available 3819 KVM_S390_MEMOP_F_SKEY_PROTECTION is available if KVM_CAP_S390_MEM_OP_EXTENSION
3892 is > 0. 3820 is > 0.
3893 Since the accessed memory may span multiple p 3821 Since the accessed memory may span multiple pages and those pages might have
3894 different storage keys, it is possible that a 3822 different storage keys, it is possible that a protection exception occurs
3895 after memory has been modified. In this case, 3823 after memory has been modified. In this case, if the exception is injected,
3896 the TEID does not indicate suppression. 3824 the TEID does not indicate suppression.
3897 3825
3898 Absolute read/write: 3826 Absolute read/write:
3899 ^^^^^^^^^^^^^^^^^^^^ 3827 ^^^^^^^^^^^^^^^^^^^^
3900 3828
3901 Access absolute memory. This operation is int 3829 Access absolute memory. This operation is intended to be used with the
3902 KVM_S390_MEMOP_F_SKEY_PROTECTION flag, to all 3830 KVM_S390_MEMOP_F_SKEY_PROTECTION flag, to allow accessing memory and performing
3903 the checks required for storage key protectio 3831 the checks required for storage key protection as one operation (as opposed to
3904 user space getting the storage keys, performi 3832 user space getting the storage keys, performing the checks, and accessing
3905 memory thereafter, which could lead to a dela 3833 memory thereafter, which could lead to a delay between check and access).
3906 Absolute accesses are permitted for the VM io 3834 Absolute accesses are permitted for the VM ioctl if KVM_CAP_S390_MEM_OP_EXTENSION
3907 has the KVM_S390_MEMOP_EXTENSION_CAP_BASE bit 3835 has the KVM_S390_MEMOP_EXTENSION_CAP_BASE bit set.
3908 Currently absolute accesses are not permitted 3836 Currently absolute accesses are not permitted for VCPU ioctls.
3909 Absolute accesses are permitted for non-prote 3837 Absolute accesses are permitted for non-protected guests only.
3910 3838
3911 Supported flags: 3839 Supported flags:
3912 * ``KVM_S390_MEMOP_F_CHECK_ONLY`` 3840 * ``KVM_S390_MEMOP_F_CHECK_ONLY``
3913 * ``KVM_S390_MEMOP_F_SKEY_PROTECTION`` 3841 * ``KVM_S390_MEMOP_F_SKEY_PROTECTION``
3914 3842
3915 The semantics of the flags common with logica 3843 The semantics of the flags common with logical accesses are as for logical
3916 accesses. 3844 accesses.
3917 3845
3918 Absolute cmpxchg: 3846 Absolute cmpxchg:
3919 ^^^^^^^^^^^^^^^^^ 3847 ^^^^^^^^^^^^^^^^^
3920 3848
3921 Perform cmpxchg on absolute guest memory. Int 3849 Perform cmpxchg on absolute guest memory. Intended for use with the
3922 KVM_S390_MEMOP_F_SKEY_PROTECTION flag. 3850 KVM_S390_MEMOP_F_SKEY_PROTECTION flag.
3923 Instead of doing an unconditional write, the 3851 Instead of doing an unconditional write, the access occurs only if the target
3924 location contains the value pointed to by "ol 3852 location contains the value pointed to by "old_addr".
3925 This is performed as an atomic cmpxchg with t 3853 This is performed as an atomic cmpxchg with the length specified by the "size"
3926 parameter. "size" must be a power of two up t 3854 parameter. "size" must be a power of two up to and including 16.
3927 If the exchange did not take place because th 3855 If the exchange did not take place because the target value doesn't match the
3928 old value, the value "old_addr" points to is 3856 old value, the value "old_addr" points to is replaced by the target value.
3929 User space can tell if an exchange took place 3857 User space can tell if an exchange took place by checking if this replacement
3930 occurred. The cmpxchg op is permitted for the 3858 occurred. The cmpxchg op is permitted for the VM ioctl if
3931 KVM_CAP_S390_MEM_OP_EXTENSION has flag KVM_S3 3859 KVM_CAP_S390_MEM_OP_EXTENSION has flag KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG set.
3932 3860
3933 Supported flags: 3861 Supported flags:
3934 * ``KVM_S390_MEMOP_F_SKEY_PROTECTION`` 3862 * ``KVM_S390_MEMOP_F_SKEY_PROTECTION``
3935 3863
3936 SIDA read/write: 3864 SIDA read/write:
3937 ^^^^^^^^^^^^^^^^ 3865 ^^^^^^^^^^^^^^^^
3938 3866
3939 Access the secure instruction data area which 3867 Access the secure instruction data area which contains memory operands necessary
3940 for instruction emulation for protected guest 3868 for instruction emulation for protected guests.
3941 SIDA accesses are available if the KVM_CAP_S3 3869 SIDA accesses are available if the KVM_CAP_S390_PROTECTED capability is available.
3942 SIDA accesses are permitted for the VCPU ioct 3870 SIDA accesses are permitted for the VCPU ioctl only.
3943 SIDA accesses are permitted for protected gue 3871 SIDA accesses are permitted for protected guests only.
3944 3872
3945 No flags are supported. 3873 No flags are supported.
3946 3874
3947 4.90 KVM_S390_GET_SKEYS 3875 4.90 KVM_S390_GET_SKEYS
3948 ----------------------- 3876 -----------------------
3949 3877
3950 :Capability: KVM_CAP_S390_SKEYS 3878 :Capability: KVM_CAP_S390_SKEYS
3951 :Architectures: s390 3879 :Architectures: s390
3952 :Type: vm ioctl 3880 :Type: vm ioctl
3953 :Parameters: struct kvm_s390_skeys 3881 :Parameters: struct kvm_s390_skeys
3954 :Returns: 0 on success, KVM_S390_GET_SKEYS_NO 3882 :Returns: 0 on success, KVM_S390_GET_SKEYS_NONE if guest is not using storage
3955 keys, negative value on error 3883 keys, negative value on error
3956 3884
3957 This ioctl is used to get guest storage key v 3885 This ioctl is used to get guest storage key values on the s390
3958 architecture. The ioctl takes parameters via 3886 architecture. The ioctl takes parameters via the kvm_s390_skeys struct::
3959 3887
3960 struct kvm_s390_skeys { 3888 struct kvm_s390_skeys {
3961 __u64 start_gfn; 3889 __u64 start_gfn;
3962 __u64 count; 3890 __u64 count;
3963 __u64 skeydata_addr; 3891 __u64 skeydata_addr;
3964 __u32 flags; 3892 __u32 flags;
3965 __u32 reserved[9]; 3893 __u32 reserved[9];
3966 }; 3894 };
3967 3895
3968 The start_gfn field is the number of the firs 3896 The start_gfn field is the number of the first guest frame whose storage keys
3969 you want to get. 3897 you want to get.
3970 3898
3971 The count field is the number of consecutive 3899 The count field is the number of consecutive frames (starting from start_gfn)
3972 whose storage keys to get. The count field mu 3900 whose storage keys to get. The count field must be at least 1 and the maximum
3973 allowed value is defined as KVM_S390_SKEYS_MA 3901 allowed value is defined as KVM_S390_SKEYS_MAX. Values outside this range
3974 will cause the ioctl to return -EINVAL. 3902 will cause the ioctl to return -EINVAL.
3975 3903
3976 The skeydata_addr field is the address to a b 3904 The skeydata_addr field is the address to a buffer large enough to hold count
3977 bytes. This buffer will be filled with storag 3905 bytes. This buffer will be filled with storage key data by the ioctl.
3978 3906
3979 4.91 KVM_S390_SET_SKEYS 3907 4.91 KVM_S390_SET_SKEYS
3980 ----------------------- 3908 -----------------------
3981 3909
3982 :Capability: KVM_CAP_S390_SKEYS 3910 :Capability: KVM_CAP_S390_SKEYS
3983 :Architectures: s390 3911 :Architectures: s390
3984 :Type: vm ioctl 3912 :Type: vm ioctl
3985 :Parameters: struct kvm_s390_skeys 3913 :Parameters: struct kvm_s390_skeys
3986 :Returns: 0 on success, negative value on err 3914 :Returns: 0 on success, negative value on error
3987 3915
3988 This ioctl is used to set guest storage key v 3916 This ioctl is used to set guest storage key values on the s390
3989 architecture. The ioctl takes parameters via 3917 architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
3990 See section on KVM_S390_GET_SKEYS for struct 3918 See section on KVM_S390_GET_SKEYS for struct definition.
3991 3919
3992 The start_gfn field is the number of the firs 3920 The start_gfn field is the number of the first guest frame whose storage keys
3993 you want to set. 3921 you want to set.
3994 3922
3995 The count field is the number of consecutive 3923 The count field is the number of consecutive frames (starting from start_gfn)
3996 whose storage keys to get. The count field mu 3924 whose storage keys to get. The count field must be at least 1 and the maximum
3997 allowed value is defined as KVM_S390_SKEYS_MA 3925 allowed value is defined as KVM_S390_SKEYS_MAX. Values outside this range
3998 will cause the ioctl to return -EINVAL. 3926 will cause the ioctl to return -EINVAL.
3999 3927
4000 The skeydata_addr field is the address to a b 3928 The skeydata_addr field is the address to a buffer containing count bytes of
4001 storage keys. Each byte in the buffer will be 3929 storage keys. Each byte in the buffer will be set as the storage key for a
4002 single frame starting at start_gfn for count 3930 single frame starting at start_gfn for count frames.
4003 3931
4004 Note: If any architecturally invalid key valu 3932 Note: If any architecturally invalid key value is found in the given data then
4005 the ioctl will return -EINVAL. 3933 the ioctl will return -EINVAL.
4006 3934
4007 4.92 KVM_S390_IRQ 3935 4.92 KVM_S390_IRQ
4008 ----------------- 3936 -----------------
4009 3937
4010 :Capability: KVM_CAP_S390_INJECT_IRQ 3938 :Capability: KVM_CAP_S390_INJECT_IRQ
4011 :Architectures: s390 3939 :Architectures: s390
4012 :Type: vcpu ioctl 3940 :Type: vcpu ioctl
4013 :Parameters: struct kvm_s390_irq (in) 3941 :Parameters: struct kvm_s390_irq (in)
4014 :Returns: 0 on success, -1 on error 3942 :Returns: 0 on success, -1 on error
4015 3943
4016 Errors: 3944 Errors:
4017 3945
4018 3946
4019 ====== =================================== 3947 ====== =================================================================
4020 EINVAL interrupt type is invalid 3948 EINVAL interrupt type is invalid
4021 type is KVM_S390_SIGP_STOP and flag 3949 type is KVM_S390_SIGP_STOP and flag parameter is invalid value,
4022 type is KVM_S390_INT_EXTERNAL_CALL 3950 type is KVM_S390_INT_EXTERNAL_CALL and code is bigger
4023 than the maximum of VCPUs 3951 than the maximum of VCPUs
4024 EBUSY type is KVM_S390_SIGP_SET_PREFIX an 3952 EBUSY type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped,
4025 type is KVM_S390_SIGP_STOP and a st 3953 type is KVM_S390_SIGP_STOP and a stop irq is already pending,
4026 type is KVM_S390_INT_EXTERNAL_CALL 3954 type is KVM_S390_INT_EXTERNAL_CALL and an external call interrupt
4027 is already pending 3955 is already pending
4028 ====== =================================== 3956 ====== =================================================================
4029 3957
4030 Allows to inject an interrupt to the guest. 3958 Allows to inject an interrupt to the guest.
4031 3959
4032 Using struct kvm_s390_irq as a parameter allo 3960 Using struct kvm_s390_irq as a parameter allows
4033 to inject additional payload which is not 3961 to inject additional payload which is not
4034 possible via KVM_S390_INTERRUPT. 3962 possible via KVM_S390_INTERRUPT.
4035 3963
4036 Interrupt parameters are passed via kvm_s390_ 3964 Interrupt parameters are passed via kvm_s390_irq::
4037 3965
4038 struct kvm_s390_irq { 3966 struct kvm_s390_irq {
4039 __u64 type; 3967 __u64 type;
4040 union { 3968 union {
4041 struct kvm_s390_io_info io; 3969 struct kvm_s390_io_info io;
4042 struct kvm_s390_ext_info ext; 3970 struct kvm_s390_ext_info ext;
4043 struct kvm_s390_pgm_info pgm; 3971 struct kvm_s390_pgm_info pgm;
4044 struct kvm_s390_emerg_info em 3972 struct kvm_s390_emerg_info emerg;
4045 struct kvm_s390_extcall_info 3973 struct kvm_s390_extcall_info extcall;
4046 struct kvm_s390_prefix_info p 3974 struct kvm_s390_prefix_info prefix;
4047 struct kvm_s390_stop_info sto 3975 struct kvm_s390_stop_info stop;
4048 struct kvm_s390_mchk_info mch 3976 struct kvm_s390_mchk_info mchk;
4049 char reserved[64]; 3977 char reserved[64];
4050 } u; 3978 } u;
4051 }; 3979 };
4052 3980
4053 type can be one of the following: 3981 type can be one of the following:
4054 3982
4055 - KVM_S390_SIGP_STOP - sigp stop; parameter i 3983 - KVM_S390_SIGP_STOP - sigp stop; parameter in .stop
4056 - KVM_S390_PROGRAM_INT - program check; param 3984 - KVM_S390_PROGRAM_INT - program check; parameters in .pgm
4057 - KVM_S390_SIGP_SET_PREFIX - sigp set prefix; 3985 - KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix
4058 - KVM_S390_RESTART - restart; no parameters 3986 - KVM_S390_RESTART - restart; no parameters
4059 - KVM_S390_INT_CLOCK_COMP - clock comparator 3987 - KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters
4060 - KVM_S390_INT_CPU_TIMER - CPU timer interrup 3988 - KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters
4061 - KVM_S390_INT_EMERGENCY - sigp emergency; pa 3989 - KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg
4062 - KVM_S390_INT_EXTERNAL_CALL - sigp external 3990 - KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall
4063 - KVM_S390_MCHK - machine check interrupt; pa 3991 - KVM_S390_MCHK - machine check interrupt; parameters in .mchk
4064 3992
4065 This is an asynchronous vcpu ioctl and can be 3993 This is an asynchronous vcpu ioctl and can be invoked from any thread.
4066 3994
4067 4.94 KVM_S390_GET_IRQ_STATE 3995 4.94 KVM_S390_GET_IRQ_STATE
4068 --------------------------- 3996 ---------------------------
4069 3997
4070 :Capability: KVM_CAP_S390_IRQ_STATE 3998 :Capability: KVM_CAP_S390_IRQ_STATE
4071 :Architectures: s390 3999 :Architectures: s390
4072 :Type: vcpu ioctl 4000 :Type: vcpu ioctl
4073 :Parameters: struct kvm_s390_irq_state (out) 4001 :Parameters: struct kvm_s390_irq_state (out)
4074 :Returns: >= number of bytes copied into buff 4002 :Returns: >= number of bytes copied into buffer,
4075 -EINVAL if buffer size is 0, 4003 -EINVAL if buffer size is 0,
4076 -ENOBUFS if buffer size is too smal 4004 -ENOBUFS if buffer size is too small to fit all pending interrupts,
4077 -EFAULT if the buffer address was i 4005 -EFAULT if the buffer address was invalid
4078 4006
4079 This ioctl allows userspace to retrieve the c 4007 This ioctl allows userspace to retrieve the complete state of all currently
4080 pending interrupts in a single buffer. Use ca 4008 pending interrupts in a single buffer. Use cases include migration
4081 and introspection. The parameter structure co 4009 and introspection. The parameter structure contains the address of a
4082 userspace buffer and its length:: 4010 userspace buffer and its length::
4083 4011
4084 struct kvm_s390_irq_state { 4012 struct kvm_s390_irq_state {
4085 __u64 buf; 4013 __u64 buf;
4086 __u32 flags; /* will stay unus 4014 __u32 flags; /* will stay unused for compatibility reasons */
4087 __u32 len; 4015 __u32 len;
4088 __u32 reserved[4]; /* will stay unus 4016 __u32 reserved[4]; /* will stay unused for compatibility reasons */
4089 }; 4017 };
4090 4018
4091 Userspace passes in the above struct and for 4019 Userspace passes in the above struct and for each pending interrupt a
4092 struct kvm_s390_irq is copied to the provided 4020 struct kvm_s390_irq is copied to the provided buffer.
4093 4021
4094 The structure contains a flags and a reserved 4022 The structure contains a flags and a reserved field for future extensions. As
4095 the kernel never checked for flags == 0 and Q 4023 the kernel never checked for flags == 0 and QEMU never pre-zeroed flags and
4096 reserved, these fields can not be used in the 4024 reserved, these fields can not be used in the future without breaking
4097 compatibility. 4025 compatibility.
4098 4026
4099 If -ENOBUFS is returned the buffer provided w 4027 If -ENOBUFS is returned the buffer provided was too small and userspace
4100 may retry with a bigger buffer. 4028 may retry with a bigger buffer.
4101 4029
4102 4.95 KVM_S390_SET_IRQ_STATE 4030 4.95 KVM_S390_SET_IRQ_STATE
4103 --------------------------- 4031 ---------------------------
4104 4032
4105 :Capability: KVM_CAP_S390_IRQ_STATE 4033 :Capability: KVM_CAP_S390_IRQ_STATE
4106 :Architectures: s390 4034 :Architectures: s390
4107 :Type: vcpu ioctl 4035 :Type: vcpu ioctl
4108 :Parameters: struct kvm_s390_irq_state (in) 4036 :Parameters: struct kvm_s390_irq_state (in)
4109 :Returns: 0 on success, 4037 :Returns: 0 on success,
4110 -EFAULT if the buffer address was i 4038 -EFAULT if the buffer address was invalid,
4111 -EINVAL for an invalid buffer lengt 4039 -EINVAL for an invalid buffer length (see below),
4112 -EBUSY if there were already interr 4040 -EBUSY if there were already interrupts pending,
4113 errors occurring when actually inje 4041 errors occurring when actually injecting the
4114 interrupt. See KVM_S390_IRQ. 4042 interrupt. See KVM_S390_IRQ.
4115 4043
4116 This ioctl allows userspace to set the comple 4044 This ioctl allows userspace to set the complete state of all cpu-local
4117 interrupts currently pending for the vcpu. It 4045 interrupts currently pending for the vcpu. It is intended for restoring
4118 interrupt state after a migration. The input 4046 interrupt state after a migration. The input parameter is a userspace buffer
4119 containing a struct kvm_s390_irq_state:: 4047 containing a struct kvm_s390_irq_state::
4120 4048
4121 struct kvm_s390_irq_state { 4049 struct kvm_s390_irq_state {
4122 __u64 buf; 4050 __u64 buf;
4123 __u32 flags; /* will stay unus 4051 __u32 flags; /* will stay unused for compatibility reasons */
4124 __u32 len; 4052 __u32 len;
4125 __u32 reserved[4]; /* will stay unus 4053 __u32 reserved[4]; /* will stay unused for compatibility reasons */
4126 }; 4054 };
4127 4055
4128 The restrictions for flags and reserved apply 4056 The restrictions for flags and reserved apply as well.
4129 (see KVM_S390_GET_IRQ_STATE) 4057 (see KVM_S390_GET_IRQ_STATE)
4130 4058
4131 The userspace memory referenced by buf contai 4059 The userspace memory referenced by buf contains a struct kvm_s390_irq
4132 for each interrupt to be injected into the gu 4060 for each interrupt to be injected into the guest.
4133 If one of the interrupts could not be injecte 4061 If one of the interrupts could not be injected for some reason the
4134 ioctl aborts. 4062 ioctl aborts.
4135 4063
4136 len must be a multiple of sizeof(struct kvm_s 4064 len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0
4137 and it must not exceed (max_vcpus + 32) * siz 4065 and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq),
4138 which is the maximum number of possibly pendi 4066 which is the maximum number of possibly pending cpu-local interrupts.
4139 4067
4140 4.96 KVM_SMI 4068 4.96 KVM_SMI
4141 ------------ 4069 ------------
4142 4070
4143 :Capability: KVM_CAP_X86_SMM 4071 :Capability: KVM_CAP_X86_SMM
4144 :Architectures: x86 4072 :Architectures: x86
4145 :Type: vcpu ioctl 4073 :Type: vcpu ioctl
4146 :Parameters: none 4074 :Parameters: none
4147 :Returns: 0 on success, -1 on error 4075 :Returns: 0 on success, -1 on error
4148 4076
4149 Queues an SMI on the thread's vcpu. 4077 Queues an SMI on the thread's vcpu.
4150 4078
4151 4.97 KVM_X86_SET_MSR_FILTER 4079 4.97 KVM_X86_SET_MSR_FILTER
4152 ---------------------------- 4080 ----------------------------
4153 4081
4154 :Capability: KVM_CAP_X86_MSR_FILTER 4082 :Capability: KVM_CAP_X86_MSR_FILTER
4155 :Architectures: x86 4083 :Architectures: x86
4156 :Type: vm ioctl 4084 :Type: vm ioctl
4157 :Parameters: struct kvm_msr_filter 4085 :Parameters: struct kvm_msr_filter
4158 :Returns: 0 on success, < 0 on error 4086 :Returns: 0 on success, < 0 on error
4159 4087
4160 :: 4088 ::
4161 4089
4162 struct kvm_msr_filter_range { 4090 struct kvm_msr_filter_range {
4163 #define KVM_MSR_FILTER_READ (1 << 0) 4091 #define KVM_MSR_FILTER_READ (1 << 0)
4164 #define KVM_MSR_FILTER_WRITE (1 << 1) 4092 #define KVM_MSR_FILTER_WRITE (1 << 1)
4165 __u32 flags; 4093 __u32 flags;
4166 __u32 nmsrs; /* number of msrs in bit 4094 __u32 nmsrs; /* number of msrs in bitmap */
4167 __u32 base; /* MSR index the bitmap 4095 __u32 base; /* MSR index the bitmap starts at */
4168 __u8 *bitmap; /* a 1 bit allows the o 4096 __u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */
4169 }; 4097 };
4170 4098
4171 #define KVM_MSR_FILTER_MAX_RANGES 16 4099 #define KVM_MSR_FILTER_MAX_RANGES 16
4172 struct kvm_msr_filter { 4100 struct kvm_msr_filter {
4173 #define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 4101 #define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
4174 #define KVM_MSR_FILTER_DEFAULT_DENY (1 << 4102 #define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0)
4175 __u32 flags; 4103 __u32 flags;
4176 struct kvm_msr_filter_range ranges[KV 4104 struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
4177 }; 4105 };
4178 4106
4179 flags values for ``struct kvm_msr_filter_rang 4107 flags values for ``struct kvm_msr_filter_range``:
4180 4108
4181 ``KVM_MSR_FILTER_READ`` 4109 ``KVM_MSR_FILTER_READ``
4182 4110
4183 Filter read accesses to MSRs using the give 4111 Filter read accesses to MSRs using the given bitmap. A 0 in the bitmap
4184 indicates that read accesses should be deni 4112 indicates that read accesses should be denied, while a 1 indicates that
4185 a read for a particular MSR should be allow 4113 a read for a particular MSR should be allowed regardless of the default
4186 filter action. 4114 filter action.
4187 4115
4188 ``KVM_MSR_FILTER_WRITE`` 4116 ``KVM_MSR_FILTER_WRITE``
4189 4117
4190 Filter write accesses to MSRs using the giv 4118 Filter write accesses to MSRs using the given bitmap. A 0 in the bitmap
4191 indicates that write accesses should be den 4119 indicates that write accesses should be denied, while a 1 indicates that
4192 a write for a particular MSR should be allo 4120 a write for a particular MSR should be allowed regardless of the default
4193 filter action. 4121 filter action.
4194 4122
4195 flags values for ``struct kvm_msr_filter``: 4123 flags values for ``struct kvm_msr_filter``:
4196 4124
4197 ``KVM_MSR_FILTER_DEFAULT_ALLOW`` 4125 ``KVM_MSR_FILTER_DEFAULT_ALLOW``
4198 4126
4199 If no filter range matches an MSR index tha 4127 If no filter range matches an MSR index that is getting accessed, KVM will
4200 allow accesses to all MSRs by default. 4128 allow accesses to all MSRs by default.
4201 4129
4202 ``KVM_MSR_FILTER_DEFAULT_DENY`` 4130 ``KVM_MSR_FILTER_DEFAULT_DENY``
4203 4131
4204 If no filter range matches an MSR index tha 4132 If no filter range matches an MSR index that is getting accessed, KVM will
4205 deny accesses to all MSRs by default. 4133 deny accesses to all MSRs by default.
4206 4134
4207 This ioctl allows userspace to define up to 1 4135 This ioctl allows userspace to define up to 16 bitmaps of MSR ranges to deny
4208 guest MSR accesses that would normally be all 4136 guest MSR accesses that would normally be allowed by KVM. If an MSR is not
4209 covered by a specific range, the "default" fi 4137 covered by a specific range, the "default" filtering behavior applies. Each
4210 bitmap range covers MSRs from [base .. base+n 4138 bitmap range covers MSRs from [base .. base+nmsrs).
4211 4139
4212 If an MSR access is denied by userspace, the 4140 If an MSR access is denied by userspace, the resulting KVM behavior depends on
4213 whether or not KVM_CAP_X86_USER_SPACE_MSR's K 4141 whether or not KVM_CAP_X86_USER_SPACE_MSR's KVM_MSR_EXIT_REASON_FILTER is
4214 enabled. If KVM_MSR_EXIT_REASON_FILTER is en 4142 enabled. If KVM_MSR_EXIT_REASON_FILTER is enabled, KVM will exit to userspace
4215 on denied accesses, i.e. userspace effectivel 4143 on denied accesses, i.e. userspace effectively intercepts the MSR access. If
4216 KVM_MSR_EXIT_REASON_FILTER is not enabled, KV 4144 KVM_MSR_EXIT_REASON_FILTER is not enabled, KVM will inject a #GP into the guest
4217 on denied accesses. Note, if an MSR access i !! 4145 on denied accesses.
4218 load/stores during VMX transitions, KVM ignor <<
4219 See the below warning for full details. <<
4220 4146
4221 If an MSR access is allowed by userspace, KVM 4147 If an MSR access is allowed by userspace, KVM will emulate and/or virtualize
4222 the access in accordance with the vCPU model. 4148 the access in accordance with the vCPU model. Note, KVM may still ultimately
4223 inject a #GP if an access is allowed by users 4149 inject a #GP if an access is allowed by userspace, e.g. if KVM doesn't support
4224 the MSR, or to follow architectural behavior 4150 the MSR, or to follow architectural behavior for the MSR.
4225 4151
4226 By default, KVM operates in KVM_MSR_FILTER_DE 4152 By default, KVM operates in KVM_MSR_FILTER_DEFAULT_ALLOW mode with no MSR range
4227 filters. 4153 filters.
4228 4154
4229 Calling this ioctl with an empty set of range 4155 Calling this ioctl with an empty set of ranges (all nmsrs == 0) disables MSR
4230 filtering. In that mode, ``KVM_MSR_FILTER_DEF 4156 filtering. In that mode, ``KVM_MSR_FILTER_DEFAULT_DENY`` is invalid and causes
4231 an error. 4157 an error.
4232 4158
4233 .. warning:: 4159 .. warning::
4234 MSR accesses that are side effects of inst !! 4160 MSR accesses as part of nested VM-Enter/VM-Exit are not filtered.
4235 native) are not filtered as hardware does !! 4161 This includes both writes to individual VMCS fields and reads/writes
4236 RDMSR and WRMSR, and KVM mimics that behav !! 4162 through the MSR lists pointed to by the VMCS.
4237 to avoid pointless divergence from hardwar <<
4238 SYSENTER reads the SYSENTER MSRs, etc. <<
4239 <<
4240 MSRs that are loaded/stored via dedicated <<
4241 part of VM-Enter/VM-Exit emulation. <<
4242 <<
4243 MSRs that are loaded/store via VMX's load/ <<
4244 of VM-Enter/VM-Exit emulation. If an MSR <<
4245 synthesizes a consistency check VM-Exit(EX <<
4246 MSR access is denied on VM-Exit, KVM synth <<
4247 extends Intel's architectural list of MSRs <<
4248 the VM-Enter/VM-Exit MSR list. It is plat <<
4249 to communicate any such restrictions to th <<
4250 4163
4251 x2APIC MSR accesses cannot be filtered (KV 4164 x2APIC MSR accesses cannot be filtered (KVM silently ignores filters that
4252 cover any x2APIC MSRs). 4165 cover any x2APIC MSRs).
4253 4166
4254 Note, invoking this ioctl while a vCPU is run 4167 Note, invoking this ioctl while a vCPU is running is inherently racy. However,
4255 KVM does guarantee that vCPUs will see either 4168 KVM does guarantee that vCPUs will see either the previous filter or the new
4256 filter, e.g. MSRs with identical settings in 4169 filter, e.g. MSRs with identical settings in both the old and new filter will
4257 have deterministic behavior. 4170 have deterministic behavior.
4258 4171
4259 Similarly, if userspace wishes to intercept o 4172 Similarly, if userspace wishes to intercept on denied accesses,
4260 KVM_MSR_EXIT_REASON_FILTER must be enabled be 4173 KVM_MSR_EXIT_REASON_FILTER must be enabled before activating any filters, and
4261 left enabled until after all filters are deac 4174 left enabled until after all filters are deactivated. Failure to do so may
4262 result in KVM injecting a #GP instead of exit 4175 result in KVM injecting a #GP instead of exiting to userspace.
4263 4176
4264 4.98 KVM_CREATE_SPAPR_TCE_64 4177 4.98 KVM_CREATE_SPAPR_TCE_64
4265 ---------------------------- 4178 ----------------------------
4266 4179
4267 :Capability: KVM_CAP_SPAPR_TCE_64 4180 :Capability: KVM_CAP_SPAPR_TCE_64
4268 :Architectures: powerpc 4181 :Architectures: powerpc
4269 :Type: vm ioctl 4182 :Type: vm ioctl
4270 :Parameters: struct kvm_create_spapr_tce_64 ( 4183 :Parameters: struct kvm_create_spapr_tce_64 (in)
4271 :Returns: file descriptor for manipulating th 4184 :Returns: file descriptor for manipulating the created TCE table
4272 4185
4273 This is an extension for KVM_CAP_SPAPR_TCE wh 4186 This is an extension for KVM_CAP_SPAPR_TCE which only supports 32bit
4274 windows, described in 4.62 KVM_CREATE_SPAPR_T 4187 windows, described in 4.62 KVM_CREATE_SPAPR_TCE
4275 4188
4276 This capability uses extended struct in ioctl 4189 This capability uses extended struct in ioctl interface::
4277 4190
4278 /* for KVM_CAP_SPAPR_TCE_64 */ 4191 /* for KVM_CAP_SPAPR_TCE_64 */
4279 struct kvm_create_spapr_tce_64 { 4192 struct kvm_create_spapr_tce_64 {
4280 __u64 liobn; 4193 __u64 liobn;
4281 __u32 page_shift; 4194 __u32 page_shift;
4282 __u32 flags; 4195 __u32 flags;
4283 __u64 offset; /* in pages */ 4196 __u64 offset; /* in pages */
4284 __u64 size; /* in pages */ 4197 __u64 size; /* in pages */
4285 }; 4198 };
4286 4199
4287 The aim of extension is to support an additio 4200 The aim of extension is to support an additional bigger DMA window with
4288 a variable page size. 4201 a variable page size.
4289 KVM_CREATE_SPAPR_TCE_64 receives a 64bit wind 4202 KVM_CREATE_SPAPR_TCE_64 receives a 64bit window size, an IOMMU page shift and
4290 a bus offset of the corresponding DMA window, 4203 a bus offset of the corresponding DMA window, @size and @offset are numbers
4291 of IOMMU pages. 4204 of IOMMU pages.
4292 4205
4293 @flags are not used at the moment. 4206 @flags are not used at the moment.
4294 4207
4295 The rest of functionality is identical to KVM 4208 The rest of functionality is identical to KVM_CREATE_SPAPR_TCE.
4296 4209
4297 4.99 KVM_REINJECT_CONTROL 4210 4.99 KVM_REINJECT_CONTROL
4298 ------------------------- 4211 -------------------------
4299 4212
4300 :Capability: KVM_CAP_REINJECT_CONTROL 4213 :Capability: KVM_CAP_REINJECT_CONTROL
4301 :Architectures: x86 4214 :Architectures: x86
4302 :Type: vm ioctl 4215 :Type: vm ioctl
4303 :Parameters: struct kvm_reinject_control (in) 4216 :Parameters: struct kvm_reinject_control (in)
4304 :Returns: 0 on success, 4217 :Returns: 0 on success,
4305 -EFAULT if struct kvm_reinject_contr 4218 -EFAULT if struct kvm_reinject_control cannot be read,
4306 -ENXIO if KVM_CREATE_PIT or KVM_CREA 4219 -ENXIO if KVM_CREATE_PIT or KVM_CREATE_PIT2 didn't succeed earlier.
4307 4220
4308 i8254 (PIT) has two modes, reinject and !rein 4221 i8254 (PIT) has two modes, reinject and !reinject. The default is reinject,
4309 where KVM queues elapsed i8254 ticks and moni 4222 where KVM queues elapsed i8254 ticks and monitors completion of interrupt from
4310 vector(s) that i8254 injects. Reinject mode 4223 vector(s) that i8254 injects. Reinject mode dequeues a tick and injects its
4311 interrupt whenever there isn't a pending inte 4224 interrupt whenever there isn't a pending interrupt from i8254.
4312 !reinject mode injects an interrupt as soon a 4225 !reinject mode injects an interrupt as soon as a tick arrives.
4313 4226
4314 :: 4227 ::
4315 4228
4316 struct kvm_reinject_control { 4229 struct kvm_reinject_control {
4317 __u8 pit_reinject; 4230 __u8 pit_reinject;
4318 __u8 reserved[31]; 4231 __u8 reserved[31];
4319 }; 4232 };
4320 4233
4321 pit_reinject = 0 (!reinject mode) is recommen 4234 pit_reinject = 0 (!reinject mode) is recommended, unless running an old
4322 operating system that uses the PIT for timing 4235 operating system that uses the PIT for timing (e.g. Linux 2.4.x).
4323 4236
4324 4.100 KVM_PPC_CONFIGURE_V3_MMU 4237 4.100 KVM_PPC_CONFIGURE_V3_MMU
4325 ------------------------------ 4238 ------------------------------
4326 4239
4327 :Capability: KVM_CAP_PPC_MMU_RADIX or KVM_CAP !! 4240 :Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3
4328 :Architectures: ppc 4241 :Architectures: ppc
4329 :Type: vm ioctl 4242 :Type: vm ioctl
4330 :Parameters: struct kvm_ppc_mmuv3_cfg (in) 4243 :Parameters: struct kvm_ppc_mmuv3_cfg (in)
4331 :Returns: 0 on success, 4244 :Returns: 0 on success,
4332 -EFAULT if struct kvm_ppc_mmuv3_cfg 4245 -EFAULT if struct kvm_ppc_mmuv3_cfg cannot be read,
4333 -EINVAL if the configuration is inva 4246 -EINVAL if the configuration is invalid
4334 4247
4335 This ioctl controls whether the guest will us 4248 This ioctl controls whether the guest will use radix or HPT (hashed
4336 page table) translation, and sets the pointer 4249 page table) translation, and sets the pointer to the process table for
4337 the guest. 4250 the guest.
4338 4251
4339 :: 4252 ::
4340 4253
4341 struct kvm_ppc_mmuv3_cfg { 4254 struct kvm_ppc_mmuv3_cfg {
4342 __u64 flags; 4255 __u64 flags;
4343 __u64 process_table; 4256 __u64 process_table;
4344 }; 4257 };
4345 4258
4346 There are two bits that can be set in flags; 4259 There are two bits that can be set in flags; KVM_PPC_MMUV3_RADIX and
4347 KVM_PPC_MMUV3_GTSE. KVM_PPC_MMUV3_RADIX, if 4260 KVM_PPC_MMUV3_GTSE. KVM_PPC_MMUV3_RADIX, if set, configures the guest
4348 to use radix tree translation, and if clear, 4261 to use radix tree translation, and if clear, to use HPT translation.
4349 KVM_PPC_MMUV3_GTSE, if set and if KVM permits 4262 KVM_PPC_MMUV3_GTSE, if set and if KVM permits it, configures the guest
4350 to be able to use the global TLB and SLB inva 4263 to be able to use the global TLB and SLB invalidation instructions;
4351 if clear, the guest may not use these instruc 4264 if clear, the guest may not use these instructions.
4352 4265
4353 The process_table field specifies the address 4266 The process_table field specifies the address and size of the guest
4354 process table, which is in the guest's space. 4267 process table, which is in the guest's space. This field is formatted
4355 as the second doubleword of the partition tab 4268 as the second doubleword of the partition table entry, as defined in
4356 the Power ISA V3.00, Book III section 5.7.6.1 4269 the Power ISA V3.00, Book III section 5.7.6.1.
4357 4270
4358 4.101 KVM_PPC_GET_RMMU_INFO 4271 4.101 KVM_PPC_GET_RMMU_INFO
4359 --------------------------- 4272 ---------------------------
4360 4273
4361 :Capability: KVM_CAP_PPC_MMU_RADIX !! 4274 :Capability: KVM_CAP_PPC_RADIX_MMU
4362 :Architectures: ppc 4275 :Architectures: ppc
4363 :Type: vm ioctl 4276 :Type: vm ioctl
4364 :Parameters: struct kvm_ppc_rmmu_info (out) 4277 :Parameters: struct kvm_ppc_rmmu_info (out)
4365 :Returns: 0 on success, 4278 :Returns: 0 on success,
4366 -EFAULT if struct kvm_ppc_rmmu_info 4279 -EFAULT if struct kvm_ppc_rmmu_info cannot be written,
4367 -EINVAL if no useful information can 4280 -EINVAL if no useful information can be returned
4368 4281
4369 This ioctl returns a structure containing two 4282 This ioctl returns a structure containing two things: (a) a list
4370 containing supported radix tree geometries, a 4283 containing supported radix tree geometries, and (b) a list that maps
4371 page sizes to put in the "AP" (actual page si 4284 page sizes to put in the "AP" (actual page size) field for the tlbie
4372 (TLB invalidate entry) instruction. 4285 (TLB invalidate entry) instruction.
4373 4286
4374 :: 4287 ::
4375 4288
4376 struct kvm_ppc_rmmu_info { 4289 struct kvm_ppc_rmmu_info {
4377 struct kvm_ppc_radix_geom { 4290 struct kvm_ppc_radix_geom {
4378 __u8 page_shift; 4291 __u8 page_shift;
4379 __u8 level_bits[4]; 4292 __u8 level_bits[4];
4380 __u8 pad[3]; 4293 __u8 pad[3];
4381 } geometries[8]; 4294 } geometries[8];
4382 __u32 ap_encodings[8]; 4295 __u32 ap_encodings[8];
4383 }; 4296 };
4384 4297
4385 The geometries[] field gives up to 8 supporte 4298 The geometries[] field gives up to 8 supported geometries for the
4386 radix page table, in terms of the log base 2 4299 radix page table, in terms of the log base 2 of the smallest page
4387 size, and the number of bits indexed at each 4300 size, and the number of bits indexed at each level of the tree, from
4388 the PTE level up to the PGD level in that ord 4301 the PTE level up to the PGD level in that order. Any unused entries
4389 will have 0 in the page_shift field. 4302 will have 0 in the page_shift field.
4390 4303
4391 The ap_encodings gives the supported page siz 4304 The ap_encodings gives the supported page sizes and their AP field
4392 encodings, encoded with the AP value in the t 4305 encodings, encoded with the AP value in the top 3 bits and the log
4393 base 2 of the page size in the bottom 6 bits. 4306 base 2 of the page size in the bottom 6 bits.
4394 4307
4395 4.102 KVM_PPC_RESIZE_HPT_PREPARE 4308 4.102 KVM_PPC_RESIZE_HPT_PREPARE
4396 -------------------------------- 4309 --------------------------------
4397 4310
4398 :Capability: KVM_CAP_SPAPR_RESIZE_HPT 4311 :Capability: KVM_CAP_SPAPR_RESIZE_HPT
4399 :Architectures: powerpc 4312 :Architectures: powerpc
4400 :Type: vm ioctl 4313 :Type: vm ioctl
4401 :Parameters: struct kvm_ppc_resize_hpt (in) 4314 :Parameters: struct kvm_ppc_resize_hpt (in)
4402 :Returns: 0 on successful completion, 4315 :Returns: 0 on successful completion,
4403 >0 if a new HPT is being prepared, t 4316 >0 if a new HPT is being prepared, the value is an estimated
4404 number of milliseconds until prepara 4317 number of milliseconds until preparation is complete,
4405 -EFAULT if struct kvm_reinject_contr 4318 -EFAULT if struct kvm_reinject_control cannot be read,
4406 -EINVAL if the supplied shift or fla 4319 -EINVAL if the supplied shift or flags are invalid,
4407 -ENOMEM if unable to allocate the ne 4320 -ENOMEM if unable to allocate the new HPT,
4408 4321
4409 Used to implement the PAPR extension for runt 4322 Used to implement the PAPR extension for runtime resizing of a guest's
4410 Hashed Page Table (HPT). Specifically this s 4323 Hashed Page Table (HPT). Specifically this starts, stops or monitors
4411 the preparation of a new potential HPT for th 4324 the preparation of a new potential HPT for the guest, essentially
4412 implementing the H_RESIZE_HPT_PREPARE hyperca 4325 implementing the H_RESIZE_HPT_PREPARE hypercall.
4413 4326
4414 :: 4327 ::
4415 4328
4416 struct kvm_ppc_resize_hpt { 4329 struct kvm_ppc_resize_hpt {
4417 __u64 flags; 4330 __u64 flags;
4418 __u32 shift; 4331 __u32 shift;
4419 __u32 pad; 4332 __u32 pad;
4420 }; 4333 };
4421 4334
4422 If called with shift > 0 when there is no pen 4335 If called with shift > 0 when there is no pending HPT for the guest,
4423 this begins preparation of a new pending HPT 4336 this begins preparation of a new pending HPT of size 2^(shift) bytes.
4424 It then returns a positive integer with the e 4337 It then returns a positive integer with the estimated number of
4425 milliseconds until preparation is complete. 4338 milliseconds until preparation is complete.
4426 4339
4427 If called when there is a pending HPT whose s 4340 If called when there is a pending HPT whose size does not match that
4428 requested in the parameters, discards the exi 4341 requested in the parameters, discards the existing pending HPT and
4429 creates a new one as above. 4342 creates a new one as above.
4430 4343
4431 If called when there is a pending HPT of the 4344 If called when there is a pending HPT of the size requested, will:
4432 4345
4433 * If preparation of the pending HPT is alre 4346 * If preparation of the pending HPT is already complete, return 0
4434 * If preparation of the pending HPT has fai 4347 * If preparation of the pending HPT has failed, return an error
4435 code, then discard the pending HPT. 4348 code, then discard the pending HPT.
4436 * If preparation of the pending HPT is stil 4349 * If preparation of the pending HPT is still in progress, return an
4437 estimated number of milliseconds until pr 4350 estimated number of milliseconds until preparation is complete.
4438 4351
4439 If called with shift == 0, discards any curre 4352 If called with shift == 0, discards any currently pending HPT and
4440 returns 0 (i.e. cancels any in-progress prepa 4353 returns 0 (i.e. cancels any in-progress preparation).
4441 4354
4442 flags is reserved for future expansion, curre 4355 flags is reserved for future expansion, currently setting any bits in
4443 flags will result in an -EINVAL. 4356 flags will result in an -EINVAL.
4444 4357
4445 Normally this will be called repeatedly with 4358 Normally this will be called repeatedly with the same parameters until
4446 it returns <= 0. The first call will initiat 4359 it returns <= 0. The first call will initiate preparation, subsequent
4447 ones will monitor preparation until it comple 4360 ones will monitor preparation until it completes or fails.
4448 4361
4449 4.103 KVM_PPC_RESIZE_HPT_COMMIT 4362 4.103 KVM_PPC_RESIZE_HPT_COMMIT
4450 ------------------------------- 4363 -------------------------------
4451 4364
4452 :Capability: KVM_CAP_SPAPR_RESIZE_HPT 4365 :Capability: KVM_CAP_SPAPR_RESIZE_HPT
4453 :Architectures: powerpc 4366 :Architectures: powerpc
4454 :Type: vm ioctl 4367 :Type: vm ioctl
4455 :Parameters: struct kvm_ppc_resize_hpt (in) 4368 :Parameters: struct kvm_ppc_resize_hpt (in)
4456 :Returns: 0 on successful completion, 4369 :Returns: 0 on successful completion,
4457 -EFAULT if struct kvm_reinject_contr 4370 -EFAULT if struct kvm_reinject_control cannot be read,
4458 -EINVAL if the supplied shift or fla 4371 -EINVAL if the supplied shift or flags are invalid,
4459 -ENXIO is there is no pending HPT, o 4372 -ENXIO is there is no pending HPT, or the pending HPT doesn't
4460 have the requested size, 4373 have the requested size,
4461 -EBUSY if the pending HPT is not ful 4374 -EBUSY if the pending HPT is not fully prepared,
4462 -ENOSPC if there was a hash collisio 4375 -ENOSPC if there was a hash collision when moving existing
4463 HPT entries to the new HPT, 4376 HPT entries to the new HPT,
4464 -EIO on other error conditions 4377 -EIO on other error conditions
4465 4378
4466 Used to implement the PAPR extension for runt 4379 Used to implement the PAPR extension for runtime resizing of a guest's
4467 Hashed Page Table (HPT). Specifically this r 4380 Hashed Page Table (HPT). Specifically this requests that the guest be
4468 transferred to working with the new HPT, esse 4381 transferred to working with the new HPT, essentially implementing the
4469 H_RESIZE_HPT_COMMIT hypercall. 4382 H_RESIZE_HPT_COMMIT hypercall.
4470 4383
4471 :: 4384 ::
4472 4385
4473 struct kvm_ppc_resize_hpt { 4386 struct kvm_ppc_resize_hpt {
4474 __u64 flags; 4387 __u64 flags;
4475 __u32 shift; 4388 __u32 shift;
4476 __u32 pad; 4389 __u32 pad;
4477 }; 4390 };
4478 4391
4479 This should only be called after KVM_PPC_RESI 4392 This should only be called after KVM_PPC_RESIZE_HPT_PREPARE has
4480 returned 0 with the same parameters. In othe 4393 returned 0 with the same parameters. In other cases
4481 KVM_PPC_RESIZE_HPT_COMMIT will return an erro 4394 KVM_PPC_RESIZE_HPT_COMMIT will return an error (usually -ENXIO or
4482 -EBUSY, though others may be possible if the 4395 -EBUSY, though others may be possible if the preparation was started,
4483 but failed). 4396 but failed).
4484 4397
4485 This will have undefined effects on the guest 4398 This will have undefined effects on the guest if it has not already
4486 placed itself in a quiescent state where no v 4399 placed itself in a quiescent state where no vcpu will make MMU enabled
4487 memory accesses. 4400 memory accesses.
4488 4401
4489 On successful completion, the pending HPT wil !! 4402 On succsful completion, the pending HPT will become the guest's active
4490 HPT and the previous HPT will be discarded. 4403 HPT and the previous HPT will be discarded.
4491 4404
4492 On failure, the guest will still be operating 4405 On failure, the guest will still be operating on its previous HPT.
4493 4406
4494 4.104 KVM_X86_GET_MCE_CAP_SUPPORTED 4407 4.104 KVM_X86_GET_MCE_CAP_SUPPORTED
4495 ----------------------------------- 4408 -----------------------------------
4496 4409
4497 :Capability: KVM_CAP_MCE 4410 :Capability: KVM_CAP_MCE
4498 :Architectures: x86 4411 :Architectures: x86
4499 :Type: system ioctl 4412 :Type: system ioctl
4500 :Parameters: u64 mce_cap (out) 4413 :Parameters: u64 mce_cap (out)
4501 :Returns: 0 on success, -1 on error 4414 :Returns: 0 on success, -1 on error
4502 4415
4503 Returns supported MCE capabilities. The u64 m 4416 Returns supported MCE capabilities. The u64 mce_cap parameter
4504 has the same format as the MSR_IA32_MCG_CAP r 4417 has the same format as the MSR_IA32_MCG_CAP register. Supported
4505 capabilities will have the corresponding bits 4418 capabilities will have the corresponding bits set.
4506 4419
4507 4.105 KVM_X86_SETUP_MCE 4420 4.105 KVM_X86_SETUP_MCE
4508 ----------------------- 4421 -----------------------
4509 4422
4510 :Capability: KVM_CAP_MCE 4423 :Capability: KVM_CAP_MCE
4511 :Architectures: x86 4424 :Architectures: x86
4512 :Type: vcpu ioctl 4425 :Type: vcpu ioctl
4513 :Parameters: u64 mcg_cap (in) 4426 :Parameters: u64 mcg_cap (in)
4514 :Returns: 0 on success, 4427 :Returns: 0 on success,
4515 -EFAULT if u64 mcg_cap cannot be rea 4428 -EFAULT if u64 mcg_cap cannot be read,
4516 -EINVAL if the requested number of b 4429 -EINVAL if the requested number of banks is invalid,
4517 -EINVAL if requested MCE capability 4430 -EINVAL if requested MCE capability is not supported.
4518 4431
4519 Initializes MCE support for use. The u64 mcg_ 4432 Initializes MCE support for use. The u64 mcg_cap parameter
4520 has the same format as the MSR_IA32_MCG_CAP r 4433 has the same format as the MSR_IA32_MCG_CAP register and
4521 specifies which capabilities should be enable 4434 specifies which capabilities should be enabled. The maximum
4522 supported number of error-reporting banks can 4435 supported number of error-reporting banks can be retrieved when
4523 checking for KVM_CAP_MCE. The supported capab 4436 checking for KVM_CAP_MCE. The supported capabilities can be
4524 retrieved with KVM_X86_GET_MCE_CAP_SUPPORTED. 4437 retrieved with KVM_X86_GET_MCE_CAP_SUPPORTED.
4525 4438
4526 4.106 KVM_X86_SET_MCE 4439 4.106 KVM_X86_SET_MCE
4527 --------------------- 4440 ---------------------
4528 4441
4529 :Capability: KVM_CAP_MCE 4442 :Capability: KVM_CAP_MCE
4530 :Architectures: x86 4443 :Architectures: x86
4531 :Type: vcpu ioctl 4444 :Type: vcpu ioctl
4532 :Parameters: struct kvm_x86_mce (in) 4445 :Parameters: struct kvm_x86_mce (in)
4533 :Returns: 0 on success, 4446 :Returns: 0 on success,
4534 -EFAULT if struct kvm_x86_mce cannot 4447 -EFAULT if struct kvm_x86_mce cannot be read,
4535 -EINVAL if the bank number is invali 4448 -EINVAL if the bank number is invalid,
4536 -EINVAL if VAL bit is not set in sta 4449 -EINVAL if VAL bit is not set in status field.
4537 4450
4538 Inject a machine check error (MCE) into the g 4451 Inject a machine check error (MCE) into the guest. The input
4539 parameter is:: 4452 parameter is::
4540 4453
4541 struct kvm_x86_mce { 4454 struct kvm_x86_mce {
4542 __u64 status; 4455 __u64 status;
4543 __u64 addr; 4456 __u64 addr;
4544 __u64 misc; 4457 __u64 misc;
4545 __u64 mcg_status; 4458 __u64 mcg_status;
4546 __u8 bank; 4459 __u8 bank;
4547 __u8 pad1[7]; 4460 __u8 pad1[7];
4548 __u64 pad2[3]; 4461 __u64 pad2[3];
4549 }; 4462 };
4550 4463
4551 If the MCE being reported is an uncorrected e 4464 If the MCE being reported is an uncorrected error, KVM will
4552 inject it as an MCE exception into the guest. 4465 inject it as an MCE exception into the guest. If the guest
4553 MCG_STATUS register reports that an MCE is in 4466 MCG_STATUS register reports that an MCE is in progress, KVM
4554 causes an KVM_EXIT_SHUTDOWN vmexit. 4467 causes an KVM_EXIT_SHUTDOWN vmexit.
4555 4468
4556 Otherwise, if the MCE is a corrected error, K 4469 Otherwise, if the MCE is a corrected error, KVM will just
4557 store it in the corresponding bank (provided 4470 store it in the corresponding bank (provided this bank is
4558 not holding a previously reported uncorrected 4471 not holding a previously reported uncorrected error).
4559 4472
4560 4.107 KVM_S390_GET_CMMA_BITS 4473 4.107 KVM_S390_GET_CMMA_BITS
4561 ---------------------------- 4474 ----------------------------
4562 4475
4563 :Capability: KVM_CAP_S390_CMMA_MIGRATION 4476 :Capability: KVM_CAP_S390_CMMA_MIGRATION
4564 :Architectures: s390 4477 :Architectures: s390
4565 :Type: vm ioctl 4478 :Type: vm ioctl
4566 :Parameters: struct kvm_s390_cmma_log (in, ou 4479 :Parameters: struct kvm_s390_cmma_log (in, out)
4567 :Returns: 0 on success, a negative value on e 4480 :Returns: 0 on success, a negative value on error
4568 4481
4569 Errors: 4482 Errors:
4570 4483
4571 ====== ================================ 4484 ====== =============================================================
4572 ENOMEM not enough memory can be allocat 4485 ENOMEM not enough memory can be allocated to complete the task
4573 ENXIO if CMMA is not enabled 4486 ENXIO if CMMA is not enabled
4574 EINVAL if KVM_S390_CMMA_PEEK is not set 4487 EINVAL if KVM_S390_CMMA_PEEK is not set but migration mode was not enabled
4575 EINVAL if KVM_S390_CMMA_PEEK is not set 4488 EINVAL if KVM_S390_CMMA_PEEK is not set but dirty tracking has been
4576 disabled (and thus migration mod 4489 disabled (and thus migration mode was automatically disabled)
4577 EFAULT if the userspace address is inva 4490 EFAULT if the userspace address is invalid or if no page table is
4578 present for the addresses (e.g. 4491 present for the addresses (e.g. when using hugepages).
4579 ====== ================================ 4492 ====== =============================================================
4580 4493
4581 This ioctl is used to get the values of the C 4494 This ioctl is used to get the values of the CMMA bits on the s390
4582 architecture. It is meant to be used in two s 4495 architecture. It is meant to be used in two scenarios:
4583 4496
4584 - During live migration to save the CMMA valu 4497 - During live migration to save the CMMA values. Live migration needs
4585 to be enabled via the KVM_REQ_START_MIGRATI 4498 to be enabled via the KVM_REQ_START_MIGRATION VM property.
4586 - To non-destructively peek at the CMMA value 4499 - To non-destructively peek at the CMMA values, with the flag
4587 KVM_S390_CMMA_PEEK set. 4500 KVM_S390_CMMA_PEEK set.
4588 4501
4589 The ioctl takes parameters via the kvm_s390_c 4502 The ioctl takes parameters via the kvm_s390_cmma_log struct. The desired
4590 values are written to a buffer whose location 4503 values are written to a buffer whose location is indicated via the "values"
4591 member in the kvm_s390_cmma_log struct. The 4504 member in the kvm_s390_cmma_log struct. The values in the input struct are
4592 also updated as needed. 4505 also updated as needed.
4593 4506
4594 Each CMMA value takes up one byte. 4507 Each CMMA value takes up one byte.
4595 4508
4596 :: 4509 ::
4597 4510
4598 struct kvm_s390_cmma_log { 4511 struct kvm_s390_cmma_log {
4599 __u64 start_gfn; 4512 __u64 start_gfn;
4600 __u32 count; 4513 __u32 count;
4601 __u32 flags; 4514 __u32 flags;
4602 union { 4515 union {
4603 __u64 remaining; 4516 __u64 remaining;
4604 __u64 mask; 4517 __u64 mask;
4605 }; 4518 };
4606 __u64 values; 4519 __u64 values;
4607 }; 4520 };
4608 4521
4609 start_gfn is the number of the first guest fr 4522 start_gfn is the number of the first guest frame whose CMMA values are
4610 to be retrieved, 4523 to be retrieved,
4611 4524
4612 count is the length of the buffer in bytes, 4525 count is the length of the buffer in bytes,
4613 4526
4614 values points to the buffer where the result 4527 values points to the buffer where the result will be written to.
4615 4528
4616 If count is greater than KVM_S390_SKEYS_MAX, 4529 If count is greater than KVM_S390_SKEYS_MAX, then it is considered to be
4617 KVM_S390_SKEYS_MAX. KVM_S390_SKEYS_MAX is re- 4530 KVM_S390_SKEYS_MAX. KVM_S390_SKEYS_MAX is re-used for consistency with
4618 other ioctls. 4531 other ioctls.
4619 4532
4620 The result is written in the buffer pointed t 4533 The result is written in the buffer pointed to by the field values, and
4621 the values of the input parameter are updated 4534 the values of the input parameter are updated as follows.
4622 4535
4623 Depending on the flags, different actions are 4536 Depending on the flags, different actions are performed. The only
4624 supported flag so far is KVM_S390_CMMA_PEEK. 4537 supported flag so far is KVM_S390_CMMA_PEEK.
4625 4538
4626 The default behaviour if KVM_S390_CMMA_PEEK i 4539 The default behaviour if KVM_S390_CMMA_PEEK is not set is:
4627 start_gfn will indicate the first page frame 4540 start_gfn will indicate the first page frame whose CMMA bits were dirty.
4628 It is not necessarily the same as the one pas 4541 It is not necessarily the same as the one passed as input, as clean pages
4629 are skipped. 4542 are skipped.
4630 4543
4631 count will indicate the number of bytes actua 4544 count will indicate the number of bytes actually written in the buffer.
4632 It can (and very often will) be smaller than 4545 It can (and very often will) be smaller than the input value, since the
4633 buffer is only filled until 16 bytes of clean 4546 buffer is only filled until 16 bytes of clean values are found (which
4634 are then not copied in the buffer). Since a C 4547 are then not copied in the buffer). Since a CMMA migration block needs
4635 the base address and the length, for a total 4548 the base address and the length, for a total of 16 bytes, we will send
4636 back some clean data if there is some dirty d 4549 back some clean data if there is some dirty data afterwards, as long as
4637 the size of the clean data does not exceed th 4550 the size of the clean data does not exceed the size of the header. This
4638 allows to minimize the amount of data to be s 4551 allows to minimize the amount of data to be saved or transferred over
4639 the network at the expense of more roundtrips 4552 the network at the expense of more roundtrips to userspace. The next
4640 invocation of the ioctl will skip over all th 4553 invocation of the ioctl will skip over all the clean values, saving
4641 potentially more than just the 16 bytes we fo 4554 potentially more than just the 16 bytes we found.
4642 4555
4643 If KVM_S390_CMMA_PEEK is set: 4556 If KVM_S390_CMMA_PEEK is set:
4644 the existing storage attributes are read even 4557 the existing storage attributes are read even when not in migration
4645 mode, and no other action is performed; 4558 mode, and no other action is performed;
4646 4559
4647 the output start_gfn will be equal to the inp 4560 the output start_gfn will be equal to the input start_gfn,
4648 4561
4649 the output count will be equal to the input c 4562 the output count will be equal to the input count, except if the end of
4650 memory has been reached. 4563 memory has been reached.
4651 4564
4652 In both cases: 4565 In both cases:
4653 the field "remaining" will indicate the total 4566 the field "remaining" will indicate the total number of dirty CMMA values
4654 still remaining, or 0 if KVM_S390_CMMA_PEEK i 4567 still remaining, or 0 if KVM_S390_CMMA_PEEK is set and migration mode is
4655 not enabled. 4568 not enabled.
4656 4569
4657 mask is unused. 4570 mask is unused.
4658 4571
4659 values points to the userspace buffer where t 4572 values points to the userspace buffer where the result will be stored.
4660 4573
4661 4.108 KVM_S390_SET_CMMA_BITS 4574 4.108 KVM_S390_SET_CMMA_BITS
4662 ---------------------------- 4575 ----------------------------
4663 4576
4664 :Capability: KVM_CAP_S390_CMMA_MIGRATION 4577 :Capability: KVM_CAP_S390_CMMA_MIGRATION
4665 :Architectures: s390 4578 :Architectures: s390
4666 :Type: vm ioctl 4579 :Type: vm ioctl
4667 :Parameters: struct kvm_s390_cmma_log (in) 4580 :Parameters: struct kvm_s390_cmma_log (in)
4668 :Returns: 0 on success, a negative value on e 4581 :Returns: 0 on success, a negative value on error
4669 4582
4670 This ioctl is used to set the values of the C 4583 This ioctl is used to set the values of the CMMA bits on the s390
4671 architecture. It is meant to be used during l 4584 architecture. It is meant to be used during live migration to restore
4672 the CMMA values, but there are no restriction 4585 the CMMA values, but there are no restrictions on its use.
4673 The ioctl takes parameters via the kvm_s390_c 4586 The ioctl takes parameters via the kvm_s390_cmma_values struct.
4674 Each CMMA value takes up one byte. 4587 Each CMMA value takes up one byte.
4675 4588
4676 :: 4589 ::
4677 4590
4678 struct kvm_s390_cmma_log { 4591 struct kvm_s390_cmma_log {
4679 __u64 start_gfn; 4592 __u64 start_gfn;
4680 __u32 count; 4593 __u32 count;
4681 __u32 flags; 4594 __u32 flags;
4682 union { 4595 union {
4683 __u64 remaining; 4596 __u64 remaining;
4684 __u64 mask; 4597 __u64 mask;
4685 }; 4598 };
4686 __u64 values; 4599 __u64 values;
4687 }; 4600 };
4688 4601
4689 start_gfn indicates the starting guest frame 4602 start_gfn indicates the starting guest frame number,
4690 4603
4691 count indicates how many values are to be con 4604 count indicates how many values are to be considered in the buffer,
4692 4605
4693 flags is not used and must be 0. 4606 flags is not used and must be 0.
4694 4607
4695 mask indicates which PGSTE bits are to be con 4608 mask indicates which PGSTE bits are to be considered.
4696 4609
4697 remaining is not used. 4610 remaining is not used.
4698 4611
4699 values points to the buffer in userspace wher 4612 values points to the buffer in userspace where to store the values.
4700 4613
4701 This ioctl can fail with -ENOMEM if not enoug 4614 This ioctl can fail with -ENOMEM if not enough memory can be allocated to
4702 complete the task, with -ENXIO if CMMA is not 4615 complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if
4703 the count field is too large (e.g. more than 4616 the count field is too large (e.g. more than KVM_S390_CMMA_SIZE_MAX) or
4704 if the flags field was not 0, with -EFAULT if 4617 if the flags field was not 0, with -EFAULT if the userspace address is
4705 invalid, if invalid pages are written to (e.g 4618 invalid, if invalid pages are written to (e.g. after the end of memory)
4706 or if no page table is present for the addres 4619 or if no page table is present for the addresses (e.g. when using
4707 hugepages). 4620 hugepages).
4708 4621
4709 4.109 KVM_PPC_GET_CPU_CHAR 4622 4.109 KVM_PPC_GET_CPU_CHAR
4710 -------------------------- 4623 --------------------------
4711 4624
4712 :Capability: KVM_CAP_PPC_GET_CPU_CHAR 4625 :Capability: KVM_CAP_PPC_GET_CPU_CHAR
4713 :Architectures: powerpc 4626 :Architectures: powerpc
4714 :Type: vm ioctl 4627 :Type: vm ioctl
4715 :Parameters: struct kvm_ppc_cpu_char (out) 4628 :Parameters: struct kvm_ppc_cpu_char (out)
4716 :Returns: 0 on successful completion, 4629 :Returns: 0 on successful completion,
4717 -EFAULT if struct kvm_ppc_cpu_char c 4630 -EFAULT if struct kvm_ppc_cpu_char cannot be written
4718 4631
4719 This ioctl gives userspace information about 4632 This ioctl gives userspace information about certain characteristics
4720 of the CPU relating to speculative execution 4633 of the CPU relating to speculative execution of instructions and
4721 possible information leakage resulting from s 4634 possible information leakage resulting from speculative execution (see
4722 CVE-2017-5715, CVE-2017-5753 and CVE-2017-575 4635 CVE-2017-5715, CVE-2017-5753 and CVE-2017-5754). The information is
4723 returned in struct kvm_ppc_cpu_char, which lo 4636 returned in struct kvm_ppc_cpu_char, which looks like this::
4724 4637
4725 struct kvm_ppc_cpu_char { 4638 struct kvm_ppc_cpu_char {
4726 __u64 character; /* ch 4639 __u64 character; /* characteristics of the CPU */
4727 __u64 behaviour; /* re 4640 __u64 behaviour; /* recommended software behaviour */
4728 __u64 character_mask; /* va 4641 __u64 character_mask; /* valid bits in character */
4729 __u64 behaviour_mask; /* va 4642 __u64 behaviour_mask; /* valid bits in behaviour */
4730 }; 4643 };
4731 4644
4732 For extensibility, the character_mask and beh 4645 For extensibility, the character_mask and behaviour_mask fields
4733 indicate which bits of character and behaviou 4646 indicate which bits of character and behaviour have been filled in by
4734 the kernel. If the set of defined bits is ex 4647 the kernel. If the set of defined bits is extended in future then
4735 userspace will be able to tell whether it is 4648 userspace will be able to tell whether it is running on a kernel that
4736 knows about the new bits. 4649 knows about the new bits.
4737 4650
4738 The character field describes attributes of t 4651 The character field describes attributes of the CPU which can help
4739 with preventing inadvertent information discl 4652 with preventing inadvertent information disclosure - specifically,
4740 whether there is an instruction to flash-inva 4653 whether there is an instruction to flash-invalidate the L1 data cache
4741 (ori 30,30,0 or mtspr SPRN_TRIG2,rN), whether 4654 (ori 30,30,0 or mtspr SPRN_TRIG2,rN), whether the L1 data cache is set
4742 to a mode where entries can only be used by t 4655 to a mode where entries can only be used by the thread that created
4743 them, whether the bcctr[l] instruction preven 4656 them, whether the bcctr[l] instruction prevents speculation, and
4744 whether a speculation barrier instruction (or 4657 whether a speculation barrier instruction (ori 31,31,0) is provided.
4745 4658
4746 The behaviour field describes actions that so 4659 The behaviour field describes actions that software should take to
4747 prevent inadvertent information disclosure, a 4660 prevent inadvertent information disclosure, and thus describes which
4748 vulnerabilities the hardware is subject to; s 4661 vulnerabilities the hardware is subject to; specifically whether the
4749 L1 data cache should be flushed when returnin 4662 L1 data cache should be flushed when returning to user mode from the
4750 kernel, and whether a speculation barrier sho 4663 kernel, and whether a speculation barrier should be placed between an
4751 array bounds check and the array access. 4664 array bounds check and the array access.
4752 4665
4753 These fields use the same bit definitions as 4666 These fields use the same bit definitions as the new
4754 H_GET_CPU_CHARACTERISTICS hypercall. 4667 H_GET_CPU_CHARACTERISTICS hypercall.
4755 4668
4756 4.110 KVM_MEMORY_ENCRYPT_OP 4669 4.110 KVM_MEMORY_ENCRYPT_OP
4757 --------------------------- 4670 ---------------------------
4758 4671
4759 :Capability: basic 4672 :Capability: basic
4760 :Architectures: x86 4673 :Architectures: x86
4761 :Type: vm 4674 :Type: vm
4762 :Parameters: an opaque platform specific stru 4675 :Parameters: an opaque platform specific structure (in/out)
4763 :Returns: 0 on success; -1 on error 4676 :Returns: 0 on success; -1 on error
4764 4677
4765 If the platform supports creating encrypted V 4678 If the platform supports creating encrypted VMs then this ioctl can be used
4766 for issuing platform-specific memory encrypti 4679 for issuing platform-specific memory encryption commands to manage those
4767 encrypted VMs. 4680 encrypted VMs.
4768 4681
4769 Currently, this ioctl is used for issuing Sec 4682 Currently, this ioctl is used for issuing Secure Encrypted Virtualization
4770 (SEV) commands on AMD Processors. The SEV com 4683 (SEV) commands on AMD Processors. The SEV commands are defined in
4771 Documentation/virt/kvm/x86/amd-memory-encrypt 4684 Documentation/virt/kvm/x86/amd-memory-encryption.rst.
4772 4685
4773 4.111 KVM_MEMORY_ENCRYPT_REG_REGION 4686 4.111 KVM_MEMORY_ENCRYPT_REG_REGION
4774 ----------------------------------- 4687 -----------------------------------
4775 4688
4776 :Capability: basic 4689 :Capability: basic
4777 :Architectures: x86 4690 :Architectures: x86
4778 :Type: system 4691 :Type: system
4779 :Parameters: struct kvm_enc_region (in) 4692 :Parameters: struct kvm_enc_region (in)
4780 :Returns: 0 on success; -1 on error 4693 :Returns: 0 on success; -1 on error
4781 4694
4782 This ioctl can be used to register a guest me 4695 This ioctl can be used to register a guest memory region which may
4783 contain encrypted data (e.g. guest RAM, SMRAM 4696 contain encrypted data (e.g. guest RAM, SMRAM etc).
4784 4697
4785 It is used in the SEV-enabled guest. When enc 4698 It is used in the SEV-enabled guest. When encryption is enabled, a guest
4786 memory region may contain encrypted data. The 4699 memory region may contain encrypted data. The SEV memory encryption
4787 engine uses a tweak such that two identical p 4700 engine uses a tweak such that two identical plaintext pages, each at
4788 different locations will have differing ciphe 4701 different locations will have differing ciphertexts. So swapping or
4789 moving ciphertext of those pages will not res 4702 moving ciphertext of those pages will not result in plaintext being
4790 swapped. So relocating (or migrating) physica 4703 swapped. So relocating (or migrating) physical backing pages for the SEV
4791 guest will require some additional steps. 4704 guest will require some additional steps.
4792 4705
4793 Note: The current SEV key management spec doe 4706 Note: The current SEV key management spec does not provide commands to
4794 swap or migrate (move) ciphertext pages. Henc 4707 swap or migrate (move) ciphertext pages. Hence, for now we pin the guest
4795 memory region registered with the ioctl. 4708 memory region registered with the ioctl.
4796 4709
4797 4.112 KVM_MEMORY_ENCRYPT_UNREG_REGION 4710 4.112 KVM_MEMORY_ENCRYPT_UNREG_REGION
4798 ------------------------------------- 4711 -------------------------------------
4799 4712
4800 :Capability: basic 4713 :Capability: basic
4801 :Architectures: x86 4714 :Architectures: x86
4802 :Type: system 4715 :Type: system
4803 :Parameters: struct kvm_enc_region (in) 4716 :Parameters: struct kvm_enc_region (in)
4804 :Returns: 0 on success; -1 on error 4717 :Returns: 0 on success; -1 on error
4805 4718
4806 This ioctl can be used to unregister the gues 4719 This ioctl can be used to unregister the guest memory region registered
4807 with KVM_MEMORY_ENCRYPT_REG_REGION ioctl abov 4720 with KVM_MEMORY_ENCRYPT_REG_REGION ioctl above.
4808 4721
4809 4.113 KVM_HYPERV_EVENTFD 4722 4.113 KVM_HYPERV_EVENTFD
4810 ------------------------ 4723 ------------------------
4811 4724
4812 :Capability: KVM_CAP_HYPERV_EVENTFD 4725 :Capability: KVM_CAP_HYPERV_EVENTFD
4813 :Architectures: x86 4726 :Architectures: x86
4814 :Type: vm ioctl 4727 :Type: vm ioctl
4815 :Parameters: struct kvm_hyperv_eventfd (in) 4728 :Parameters: struct kvm_hyperv_eventfd (in)
4816 4729
4817 This ioctl (un)registers an eventfd to receiv 4730 This ioctl (un)registers an eventfd to receive notifications from the guest on
4818 the specified Hyper-V connection id through t 4731 the specified Hyper-V connection id through the SIGNAL_EVENT hypercall, without
4819 causing a user exit. SIGNAL_EVENT hypercall 4732 causing a user exit. SIGNAL_EVENT hypercall with non-zero event flag number
4820 (bits 24-31) still triggers a KVM_EXIT_HYPERV 4733 (bits 24-31) still triggers a KVM_EXIT_HYPERV_HCALL user exit.
4821 4734
4822 :: 4735 ::
4823 4736
4824 struct kvm_hyperv_eventfd { 4737 struct kvm_hyperv_eventfd {
4825 __u32 conn_id; 4738 __u32 conn_id;
4826 __s32 fd; 4739 __s32 fd;
4827 __u32 flags; 4740 __u32 flags;
4828 __u32 padding[3]; 4741 __u32 padding[3];
4829 }; 4742 };
4830 4743
4831 The conn_id field should fit within 24 bits:: 4744 The conn_id field should fit within 24 bits::
4832 4745
4833 #define KVM_HYPERV_CONN_ID_MASK 4746 #define KVM_HYPERV_CONN_ID_MASK 0x00ffffff
4834 4747
4835 The acceptable values for the flags field are 4748 The acceptable values for the flags field are::
4836 4749
4837 #define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 4750 #define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0)
4838 4751
4839 :Returns: 0 on success, 4752 :Returns: 0 on success,
4840 -EINVAL if conn_id or flags is outs 4753 -EINVAL if conn_id or flags is outside the allowed range,
4841 -ENOENT on deassign if the conn_id 4754 -ENOENT on deassign if the conn_id isn't registered,
4842 -EEXIST on assign if the conn_id is 4755 -EEXIST on assign if the conn_id is already registered
4843 4756
4844 4.114 KVM_GET_NESTED_STATE 4757 4.114 KVM_GET_NESTED_STATE
4845 -------------------------- 4758 --------------------------
4846 4759
4847 :Capability: KVM_CAP_NESTED_STATE 4760 :Capability: KVM_CAP_NESTED_STATE
4848 :Architectures: x86 4761 :Architectures: x86
4849 :Type: vcpu ioctl 4762 :Type: vcpu ioctl
4850 :Parameters: struct kvm_nested_state (in/out) 4763 :Parameters: struct kvm_nested_state (in/out)
4851 :Returns: 0 on success, -1 on error 4764 :Returns: 0 on success, -1 on error
4852 4765
4853 Errors: 4766 Errors:
4854 4767
4855 ===== ================================ 4768 ===== =============================================================
4856 E2BIG the total state size exceeds the 4769 E2BIG the total state size exceeds the value of 'size' specified by
4857 the user; the size required will 4770 the user; the size required will be written into size.
4858 ===== ================================ 4771 ===== =============================================================
4859 4772
4860 :: 4773 ::
4861 4774
4862 struct kvm_nested_state { 4775 struct kvm_nested_state {
4863 __u16 flags; 4776 __u16 flags;
4864 __u16 format; 4777 __u16 format;
4865 __u32 size; 4778 __u32 size;
4866 4779
4867 union { 4780 union {
4868 struct kvm_vmx_nested_state_h 4781 struct kvm_vmx_nested_state_hdr vmx;
4869 struct kvm_svm_nested_state_h 4782 struct kvm_svm_nested_state_hdr svm;
4870 4783
4871 /* Pad the header to 128 byte 4784 /* Pad the header to 128 bytes. */
4872 __u8 pad[120]; 4785 __u8 pad[120];
4873 } hdr; 4786 } hdr;
4874 4787
4875 union { 4788 union {
4876 struct kvm_vmx_nested_state_d 4789 struct kvm_vmx_nested_state_data vmx[0];
4877 struct kvm_svm_nested_state_d 4790 struct kvm_svm_nested_state_data svm[0];
4878 } data; 4791 } data;
4879 }; 4792 };
4880 4793
4881 #define KVM_STATE_NESTED_GUEST_MODE 4794 #define KVM_STATE_NESTED_GUEST_MODE 0x00000001
4882 #define KVM_STATE_NESTED_RUN_PENDING 4795 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002
4883 #define KVM_STATE_NESTED_EVMCS 4796 #define KVM_STATE_NESTED_EVMCS 0x00000004
4884 4797
4885 #define KVM_STATE_NESTED_FORMAT_VMX 4798 #define KVM_STATE_NESTED_FORMAT_VMX 0
4886 #define KVM_STATE_NESTED_FORMAT_SVM 4799 #define KVM_STATE_NESTED_FORMAT_SVM 1
4887 4800
4888 #define KVM_STATE_NESTED_VMX_VMCS_SIZE 4801 #define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000
4889 4802
4890 #define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE 4803 #define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE 0x00000001
4891 #define KVM_STATE_NESTED_VMX_SMM_VMXON 4804 #define KVM_STATE_NESTED_VMX_SMM_VMXON 0x00000002
4892 4805
4893 #define KVM_STATE_VMX_PREEMPTION_TIMER_DEAD 4806 #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001
4894 4807
4895 struct kvm_vmx_nested_state_hdr { 4808 struct kvm_vmx_nested_state_hdr {
4896 __u64 vmxon_pa; 4809 __u64 vmxon_pa;
4897 __u64 vmcs12_pa; 4810 __u64 vmcs12_pa;
4898 4811
4899 struct { 4812 struct {
4900 __u16 flags; 4813 __u16 flags;
4901 } smm; 4814 } smm;
4902 4815
4903 __u32 flags; 4816 __u32 flags;
4904 __u64 preemption_timer_deadline; 4817 __u64 preemption_timer_deadline;
4905 }; 4818 };
4906 4819
4907 struct kvm_vmx_nested_state_data { 4820 struct kvm_vmx_nested_state_data {
4908 __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS 4821 __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
4909 __u8 shadow_vmcs12[KVM_STATE_NESTED_V 4822 __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
4910 }; 4823 };
4911 4824
4912 This ioctl copies the vcpu's nested virtualiz 4825 This ioctl copies the vcpu's nested virtualization state from the kernel to
4913 userspace. 4826 userspace.
4914 4827
4915 The maximum size of the state can be retrieve 4828 The maximum size of the state can be retrieved by passing KVM_CAP_NESTED_STATE
4916 to the KVM_CHECK_EXTENSION ioctl(). 4829 to the KVM_CHECK_EXTENSION ioctl().
4917 4830
4918 4.115 KVM_SET_NESTED_STATE 4831 4.115 KVM_SET_NESTED_STATE
4919 -------------------------- 4832 --------------------------
4920 4833
4921 :Capability: KVM_CAP_NESTED_STATE 4834 :Capability: KVM_CAP_NESTED_STATE
4922 :Architectures: x86 4835 :Architectures: x86
4923 :Type: vcpu ioctl 4836 :Type: vcpu ioctl
4924 :Parameters: struct kvm_nested_state (in) 4837 :Parameters: struct kvm_nested_state (in)
4925 :Returns: 0 on success, -1 on error 4838 :Returns: 0 on success, -1 on error
4926 4839
4927 This copies the vcpu's kvm_nested_state struc 4840 This copies the vcpu's kvm_nested_state struct from userspace to the kernel.
4928 For the definition of struct kvm_nested_state 4841 For the definition of struct kvm_nested_state, see KVM_GET_NESTED_STATE.
4929 4842
4930 4.116 KVM_(UN)REGISTER_COALESCED_MMIO 4843 4.116 KVM_(UN)REGISTER_COALESCED_MMIO
4931 ------------------------------------- 4844 -------------------------------------
4932 4845
4933 :Capability: KVM_CAP_COALESCED_MMIO (for coal 4846 :Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio)
4934 KVM_CAP_COALESCED_PIO (for coale 4847 KVM_CAP_COALESCED_PIO (for coalesced pio)
4935 :Architectures: all 4848 :Architectures: all
4936 :Type: vm ioctl 4849 :Type: vm ioctl
4937 :Parameters: struct kvm_coalesced_mmio_zone 4850 :Parameters: struct kvm_coalesced_mmio_zone
4938 :Returns: 0 on success, < 0 on error 4851 :Returns: 0 on success, < 0 on error
4939 4852
4940 Coalesced I/O is a performance optimization t 4853 Coalesced I/O is a performance optimization that defers hardware
4941 register write emulation so that userspace ex 4854 register write emulation so that userspace exits are avoided. It is
4942 typically used to reduce the overhead of emul 4855 typically used to reduce the overhead of emulating frequently accessed
4943 hardware registers. 4856 hardware registers.
4944 4857
4945 When a hardware register is configured for co 4858 When a hardware register is configured for coalesced I/O, write accesses
4946 do not exit to userspace and their value is r 4859 do not exit to userspace and their value is recorded in a ring buffer
4947 that is shared between kernel and userspace. 4860 that is shared between kernel and userspace.
4948 4861
4949 Coalesced I/O is used if one or more write ac 4862 Coalesced I/O is used if one or more write accesses to a hardware
4950 register can be deferred until a read or a wr 4863 register can be deferred until a read or a write to another hardware
4951 register on the same device. This last acces 4864 register on the same device. This last access will cause a vmexit and
4952 userspace will process accesses from the ring 4865 userspace will process accesses from the ring buffer before emulating
4953 it. That will avoid exiting to userspace on r 4866 it. That will avoid exiting to userspace on repeated writes.
4954 4867
4955 Coalesced pio is based on coalesced mmio. The 4868 Coalesced pio is based on coalesced mmio. There is little difference
4956 between coalesced mmio and pio except that co 4869 between coalesced mmio and pio except that coalesced pio records accesses
4957 to I/O ports. 4870 to I/O ports.
4958 4871
4959 4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl) 4872 4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl)
4960 ------------------------------------ 4873 ------------------------------------
4961 4874
4962 :Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 4875 :Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
4963 :Architectures: x86, arm64, mips 4876 :Architectures: x86, arm64, mips
4964 :Type: vm ioctl 4877 :Type: vm ioctl
4965 :Parameters: struct kvm_clear_dirty_log (in) 4878 :Parameters: struct kvm_clear_dirty_log (in)
4966 :Returns: 0 on success, -1 on error 4879 :Returns: 0 on success, -1 on error
4967 4880
4968 :: 4881 ::
4969 4882
4970 /* for KVM_CLEAR_DIRTY_LOG */ 4883 /* for KVM_CLEAR_DIRTY_LOG */
4971 struct kvm_clear_dirty_log { 4884 struct kvm_clear_dirty_log {
4972 __u32 slot; 4885 __u32 slot;
4973 __u32 num_pages; 4886 __u32 num_pages;
4974 __u64 first_page; 4887 __u64 first_page;
4975 union { 4888 union {
4976 void __user *dirty_bitmap; /* 4889 void __user *dirty_bitmap; /* one bit per page */
4977 __u64 padding; 4890 __u64 padding;
4978 }; 4891 };
4979 }; 4892 };
4980 4893
4981 The ioctl clears the dirty status of pages in 4894 The ioctl clears the dirty status of pages in a memory slot, according to
4982 the bitmap that is passed in struct kvm_clear 4895 the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap
4983 field. Bit 0 of the bitmap corresponds to pa 4896 field. Bit 0 of the bitmap corresponds to page "first_page" in the
4984 memory slot, and num_pages is the size in bit 4897 memory slot, and num_pages is the size in bits of the input bitmap.
4985 first_page must be a multiple of 64; num_page 4898 first_page must be a multiple of 64; num_pages must also be a multiple of
4986 64 unless first_page + num_pages is the size 4899 64 unless first_page + num_pages is the size of the memory slot. For each
4987 bit that is set in the input bitmap, the corr 4900 bit that is set in the input bitmap, the corresponding page is marked "clean"
4988 in KVM's dirty bitmap, and dirty tracking is 4901 in KVM's dirty bitmap, and dirty tracking is re-enabled for that page
4989 (for example via write-protection, or by clea 4902 (for example via write-protection, or by clearing the dirty bit in
4990 a page table entry). 4903 a page table entry).
4991 4904
4992 If KVM_CAP_MULTI_ADDRESS_SPACE is available, 4905 If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of slot field specifies
4993 the address space for which you want to clear 4906 the address space for which you want to clear the dirty status. See
4994 KVM_SET_USER_MEMORY_REGION for details on the 4907 KVM_SET_USER_MEMORY_REGION for details on the usage of slot field.
4995 4908
4996 This ioctl is mostly useful when KVM_CAP_MANU 4909 This ioctl is mostly useful when KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
4997 is enabled; for more information, see the des 4910 is enabled; for more information, see the description of the capability.
4998 However, it can always be used as long as KVM 4911 However, it can always be used as long as KVM_CHECK_EXTENSION confirms
4999 that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is pre 4912 that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is present.
5000 4913
5001 4.118 KVM_GET_SUPPORTED_HV_CPUID 4914 4.118 KVM_GET_SUPPORTED_HV_CPUID
5002 -------------------------------- 4915 --------------------------------
5003 4916
5004 :Capability: KVM_CAP_HYPERV_CPUID (vcpu), KVM 4917 :Capability: KVM_CAP_HYPERV_CPUID (vcpu), KVM_CAP_SYS_HYPERV_CPUID (system)
5005 :Architectures: x86 4918 :Architectures: x86
5006 :Type: system ioctl, vcpu ioctl 4919 :Type: system ioctl, vcpu ioctl
5007 :Parameters: struct kvm_cpuid2 (in/out) 4920 :Parameters: struct kvm_cpuid2 (in/out)
5008 :Returns: 0 on success, -1 on error 4921 :Returns: 0 on success, -1 on error
5009 4922
5010 :: 4923 ::
5011 4924
5012 struct kvm_cpuid2 { 4925 struct kvm_cpuid2 {
5013 __u32 nent; 4926 __u32 nent;
5014 __u32 padding; 4927 __u32 padding;
5015 struct kvm_cpuid_entry2 entries[0]; 4928 struct kvm_cpuid_entry2 entries[0];
5016 }; 4929 };
5017 4930
5018 struct kvm_cpuid_entry2 { 4931 struct kvm_cpuid_entry2 {
5019 __u32 function; 4932 __u32 function;
5020 __u32 index; 4933 __u32 index;
5021 __u32 flags; 4934 __u32 flags;
5022 __u32 eax; 4935 __u32 eax;
5023 __u32 ebx; 4936 __u32 ebx;
5024 __u32 ecx; 4937 __u32 ecx;
5025 __u32 edx; 4938 __u32 edx;
5026 __u32 padding[3]; 4939 __u32 padding[3];
5027 }; 4940 };
5028 4941
5029 This ioctl returns x86 cpuid features leaves 4942 This ioctl returns x86 cpuid features leaves related to Hyper-V emulation in
5030 KVM. Userspace can use the information retur 4943 KVM. Userspace can use the information returned by this ioctl to construct
5031 cpuid information presented to guests consumi 4944 cpuid information presented to guests consuming Hyper-V enlightenments (e.g.
5032 Windows or Hyper-V guests). 4945 Windows or Hyper-V guests).
5033 4946
5034 CPUID feature leaves returned by this ioctl a 4947 CPUID feature leaves returned by this ioctl are defined by Hyper-V Top Level
5035 Functional Specification (TLFS). These leaves 4948 Functional Specification (TLFS). These leaves can't be obtained with
5036 KVM_GET_SUPPORTED_CPUID ioctl because some of 4949 KVM_GET_SUPPORTED_CPUID ioctl because some of them intersect with KVM feature
5037 leaves (0x40000000, 0x40000001). 4950 leaves (0x40000000, 0x40000001).
5038 4951
5039 Currently, the following list of CPUID leaves 4952 Currently, the following list of CPUID leaves are returned:
5040 4953
5041 - HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS 4954 - HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS
5042 - HYPERV_CPUID_INTERFACE 4955 - HYPERV_CPUID_INTERFACE
5043 - HYPERV_CPUID_VERSION 4956 - HYPERV_CPUID_VERSION
5044 - HYPERV_CPUID_FEATURES 4957 - HYPERV_CPUID_FEATURES
5045 - HYPERV_CPUID_ENLIGHTMENT_INFO 4958 - HYPERV_CPUID_ENLIGHTMENT_INFO
5046 - HYPERV_CPUID_IMPLEMENT_LIMITS 4959 - HYPERV_CPUID_IMPLEMENT_LIMITS
5047 - HYPERV_CPUID_NESTED_FEATURES 4960 - HYPERV_CPUID_NESTED_FEATURES
5048 - HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIO 4961 - HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS
5049 - HYPERV_CPUID_SYNDBG_INTERFACE 4962 - HYPERV_CPUID_SYNDBG_INTERFACE
5050 - HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES 4963 - HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES
5051 4964
5052 Userspace invokes KVM_GET_SUPPORTED_HV_CPUID 4965 Userspace invokes KVM_GET_SUPPORTED_HV_CPUID by passing a kvm_cpuid2 structure
5053 with the 'nent' field indicating the number o 4966 with the 'nent' field indicating the number of entries in the variable-size
5054 array 'entries'. If the number of entries is 4967 array 'entries'. If the number of entries is too low to describe all Hyper-V
5055 feature leaves, an error (E2BIG) is returned. 4968 feature leaves, an error (E2BIG) is returned. If the number is more or equal
5056 to the number of Hyper-V feature leaves, the 4969 to the number of Hyper-V feature leaves, the 'nent' field is adjusted to the
5057 number of valid entries in the 'entries' arra 4970 number of valid entries in the 'entries' array, which is then filled.
5058 4971
5059 'index' and 'flags' fields in 'struct kvm_cpu 4972 'index' and 'flags' fields in 'struct kvm_cpuid_entry2' are currently reserved,
5060 userspace should not expect to get any partic 4973 userspace should not expect to get any particular value there.
5061 4974
5062 Note, vcpu version of KVM_GET_SUPPORTED_HV_CP 4975 Note, vcpu version of KVM_GET_SUPPORTED_HV_CPUID is currently deprecated. Unlike
5063 system ioctl which exposes all supported feat 4976 system ioctl which exposes all supported feature bits unconditionally, vcpu
5064 version has the following quirks: 4977 version has the following quirks:
5065 4978
5066 - HYPERV_CPUID_NESTED_FEATURES leaf and HV_X6 4979 - HYPERV_CPUID_NESTED_FEATURES leaf and HV_X64_ENLIGHTENED_VMCS_RECOMMENDED
5067 feature bit are only exposed when Enlighten 4980 feature bit are only exposed when Enlightened VMCS was previously enabled
5068 on the corresponding vCPU (KVM_CAP_HYPERV_E 4981 on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS).
5069 - HV_STIMER_DIRECT_MODE_AVAILABLE bit is only 4982 - HV_STIMER_DIRECT_MODE_AVAILABLE bit is only exposed with in-kernel LAPIC.
5070 (presumes KVM_CREATE_IRQCHIP has already be 4983 (presumes KVM_CREATE_IRQCHIP has already been called).
5071 4984
5072 4.119 KVM_ARM_VCPU_FINALIZE 4985 4.119 KVM_ARM_VCPU_FINALIZE
5073 --------------------------- 4986 ---------------------------
5074 4987
5075 :Architectures: arm64 4988 :Architectures: arm64
5076 :Type: vcpu ioctl 4989 :Type: vcpu ioctl
5077 :Parameters: int feature (in) 4990 :Parameters: int feature (in)
5078 :Returns: 0 on success, -1 on error 4991 :Returns: 0 on success, -1 on error
5079 4992
5080 Errors: 4993 Errors:
5081 4994
5082 ====== ================================ 4995 ====== ==============================================================
5083 EPERM feature not enabled, needs confi 4996 EPERM feature not enabled, needs configuration, or already finalized
5084 EINVAL feature unknown or not present 4997 EINVAL feature unknown or not present
5085 ====== ================================ 4998 ====== ==============================================================
5086 4999
5087 Recognised values for feature: 5000 Recognised values for feature:
5088 5001
5089 ===== ================================ 5002 ===== ===========================================
5090 arm64 KVM_ARM_VCPU_SVE (requires KVM_C 5003 arm64 KVM_ARM_VCPU_SVE (requires KVM_CAP_ARM_SVE)
5091 ===== ================================ 5004 ===== ===========================================
5092 5005
5093 Finalizes the configuration of the specified 5006 Finalizes the configuration of the specified vcpu feature.
5094 5007
5095 The vcpu must already have been initialised, 5008 The vcpu must already have been initialised, enabling the affected feature, by
5096 means of a successful KVM_ARM_VCPU_INIT call 5009 means of a successful KVM_ARM_VCPU_INIT call with the appropriate flag set in
5097 features[]. 5010 features[].
5098 5011
5099 For affected vcpu features, this is a mandato 5012 For affected vcpu features, this is a mandatory step that must be performed
5100 before the vcpu is fully usable. 5013 before the vcpu is fully usable.
5101 5014
5102 Between KVM_ARM_VCPU_INIT and KVM_ARM_VCPU_FI 5015 Between KVM_ARM_VCPU_INIT and KVM_ARM_VCPU_FINALIZE, the feature may be
5103 configured by use of ioctls such as KVM_SET_O 5016 configured by use of ioctls such as KVM_SET_ONE_REG. The exact configuration
5104 that should be performed and how to do it are !! 5017 that should be performaned and how to do it are feature-dependent.
5105 5018
5106 Other calls that depend on a particular featu 5019 Other calls that depend on a particular feature being finalized, such as
5107 KVM_RUN, KVM_GET_REG_LIST, KVM_GET_ONE_REG an 5020 KVM_RUN, KVM_GET_REG_LIST, KVM_GET_ONE_REG and KVM_SET_ONE_REG, will fail with
5108 -EPERM unless the feature has already been fi 5021 -EPERM unless the feature has already been finalized by means of a
5109 KVM_ARM_VCPU_FINALIZE call. 5022 KVM_ARM_VCPU_FINALIZE call.
5110 5023
5111 See KVM_ARM_VCPU_INIT for details of vcpu fea 5024 See KVM_ARM_VCPU_INIT for details of vcpu features that require finalization
5112 using this ioctl. 5025 using this ioctl.
5113 5026
5114 4.120 KVM_SET_PMU_EVENT_FILTER 5027 4.120 KVM_SET_PMU_EVENT_FILTER
5115 ------------------------------ 5028 ------------------------------
5116 5029
5117 :Capability: KVM_CAP_PMU_EVENT_FILTER 5030 :Capability: KVM_CAP_PMU_EVENT_FILTER
5118 :Architectures: x86 5031 :Architectures: x86
5119 :Type: vm ioctl 5032 :Type: vm ioctl
5120 :Parameters: struct kvm_pmu_event_filter (in) 5033 :Parameters: struct kvm_pmu_event_filter (in)
5121 :Returns: 0 on success, -1 on error 5034 :Returns: 0 on success, -1 on error
5122 5035
5123 Errors: 5036 Errors:
5124 5037
5125 ====== ================================ 5038 ====== ============================================================
5126 EFAULT args[0] cannot be accessed 5039 EFAULT args[0] cannot be accessed
5127 EINVAL args[0] contains invalid data in 5040 EINVAL args[0] contains invalid data in the filter or filter events
5128 E2BIG nevents is too large 5041 E2BIG nevents is too large
5129 EBUSY not enough memory to allocate th 5042 EBUSY not enough memory to allocate the filter
5130 ====== ================================ 5043 ====== ============================================================
5131 5044
5132 :: 5045 ::
5133 5046
5134 struct kvm_pmu_event_filter { 5047 struct kvm_pmu_event_filter {
5135 __u32 action; 5048 __u32 action;
5136 __u32 nevents; 5049 __u32 nevents;
5137 __u32 fixed_counter_bitmap; 5050 __u32 fixed_counter_bitmap;
5138 __u32 flags; 5051 __u32 flags;
5139 __u32 pad[4]; 5052 __u32 pad[4];
5140 __u64 events[0]; 5053 __u64 events[0];
5141 }; 5054 };
5142 5055
5143 This ioctl restricts the set of PMU events th 5056 This ioctl restricts the set of PMU events the guest can program by limiting
5144 which event select and unit mask combinations 5057 which event select and unit mask combinations are permitted.
5145 5058
5146 The argument holds a list of filter events wh 5059 The argument holds a list of filter events which will be allowed or denied.
5147 5060
5148 Filter events only control general purpose co 5061 Filter events only control general purpose counters; fixed purpose counters
5149 are controlled by the fixed_counter_bitmap. 5062 are controlled by the fixed_counter_bitmap.
5150 5063
5151 Valid values for 'flags':: 5064 Valid values for 'flags'::
5152 5065
5153 ``0`` 5066 ``0``
5154 5067
5155 To use this mode, clear the 'flags' field. 5068 To use this mode, clear the 'flags' field.
5156 5069
5157 In this mode each event will contain an event 5070 In this mode each event will contain an event select + unit mask.
5158 5071
5159 When the guest attempts to program the PMU th 5072 When the guest attempts to program the PMU the guest's event select +
5160 unit mask is compared against the filter even 5073 unit mask is compared against the filter events to determine whether the
5161 guest should have access. 5074 guest should have access.
5162 5075
5163 ``KVM_PMU_EVENT_FLAG_MASKED_EVENTS`` 5076 ``KVM_PMU_EVENT_FLAG_MASKED_EVENTS``
5164 :Capability: KVM_CAP_PMU_EVENT_MASKED_EVENTS 5077 :Capability: KVM_CAP_PMU_EVENT_MASKED_EVENTS
5165 5078
5166 In this mode each filter event will contain a 5079 In this mode each filter event will contain an event select, mask, match, and
5167 exclude value. To encode a masked event use: 5080 exclude value. To encode a masked event use::
5168 5081
5169 KVM_PMU_ENCODE_MASKED_ENTRY() 5082 KVM_PMU_ENCODE_MASKED_ENTRY()
5170 5083
5171 An encoded event will follow this layout:: 5084 An encoded event will follow this layout::
5172 5085
5173 Bits Description 5086 Bits Description
5174 ---- ----------- 5087 ---- -----------
5175 7:0 event select (low bits) 5088 7:0 event select (low bits)
5176 15:8 umask match 5089 15:8 umask match
5177 31:16 unused 5090 31:16 unused
5178 35:32 event select (high bits) 5091 35:32 event select (high bits)
5179 36:54 unused 5092 36:54 unused
5180 55 exclude bit 5093 55 exclude bit
5181 63:56 umask mask 5094 63:56 umask mask
5182 5095
5183 When the guest attempts to program the PMU, t 5096 When the guest attempts to program the PMU, these steps are followed in
5184 determining if the guest should have access: 5097 determining if the guest should have access:
5185 5098
5186 1. Match the event select from the guest aga 5099 1. Match the event select from the guest against the filter events.
5187 2. If a match is found, match the guest's un 5100 2. If a match is found, match the guest's unit mask to the mask and match
5188 values of the included filter events. 5101 values of the included filter events.
5189 I.e. (unit mask & mask) == match && !excl 5102 I.e. (unit mask & mask) == match && !exclude.
5190 3. If a match is found, match the guest's un 5103 3. If a match is found, match the guest's unit mask to the mask and match
5191 values of the excluded filter events. 5104 values of the excluded filter events.
5192 I.e. (unit mask & mask) == match && exclu 5105 I.e. (unit mask & mask) == match && exclude.
5193 4. 5106 4.
5194 a. If an included match is found and an ex 5107 a. If an included match is found and an excluded match is not found, filter
5195 the event. 5108 the event.
5196 b. For everything else, do not filter the 5109 b. For everything else, do not filter the event.
5197 5. 5110 5.
5198 a. If the event is filtered and it's an al 5111 a. If the event is filtered and it's an allow list, allow the guest to
5199 program the event. 5112 program the event.
5200 b. If the event is filtered and it's a den 5113 b. If the event is filtered and it's a deny list, do not allow the guest to
5201 program the event. 5114 program the event.
5202 5115
5203 When setting a new pmu event filter, -EINVAL 5116 When setting a new pmu event filter, -EINVAL will be returned if any of the
5204 unused fields are set or if any of the high b 5117 unused fields are set or if any of the high bits (35:32) in the event
5205 select are set when called on Intel. 5118 select are set when called on Intel.
5206 5119
5207 Valid values for 'action':: 5120 Valid values for 'action'::
5208 5121
5209 #define KVM_PMU_EVENT_ALLOW 0 5122 #define KVM_PMU_EVENT_ALLOW 0
5210 #define KVM_PMU_EVENT_DENY 1 5123 #define KVM_PMU_EVENT_DENY 1
5211 5124
5212 Via this API, KVM userspace can also control <<
5213 counters (if any) by configuring the "action" <<
5214 <<
5215 Specifically, KVM follows the following pseud <<
5216 allow the guest FixCtr[i] to count its pre-de <<
5217 <<
5218 FixCtr[i]_is_allowed = (action == ALLOW) && <<
5219 (action == DENY) && !(bitmap & BIT(i)); <<
5220 FixCtr[i]_is_denied = !FixCtr[i]_is_allowed <<
5221 <<
5222 KVM always consumes fixed_counter_bitmap, it' <<
5223 ensure fixed_counter_bitmap is set correctly, <<
5224 a filter that only affects general purpose co <<
5225 <<
5226 Note, the "events" field also applies to fixe <<
5227 and unit_mask values. "fixed_counter_bitmap" <<
5228 if there is a contradiction between the two. <<
5229 <<
5230 4.121 KVM_PPC_SVM_OFF 5125 4.121 KVM_PPC_SVM_OFF
5231 --------------------- 5126 ---------------------
5232 5127
5233 :Capability: basic 5128 :Capability: basic
5234 :Architectures: powerpc 5129 :Architectures: powerpc
5235 :Type: vm ioctl 5130 :Type: vm ioctl
5236 :Parameters: none 5131 :Parameters: none
5237 :Returns: 0 on successful completion, 5132 :Returns: 0 on successful completion,
5238 5133
5239 Errors: 5134 Errors:
5240 5135
5241 ====== ================================ 5136 ====== ================================================================
5242 EINVAL if ultravisor failed to terminat 5137 EINVAL if ultravisor failed to terminate the secure guest
5243 ENOMEM if hypervisor failed to allocate 5138 ENOMEM if hypervisor failed to allocate new radix page tables for guest
5244 ====== ================================ 5139 ====== ================================================================
5245 5140
5246 This ioctl is used to turn off the secure mod 5141 This ioctl is used to turn off the secure mode of the guest or transition
5247 the guest from secure mode to normal mode. Th 5142 the guest from secure mode to normal mode. This is invoked when the guest
5248 is reset. This has no effect if called for a 5143 is reset. This has no effect if called for a normal guest.
5249 5144
5250 This ioctl issues an ultravisor call to termi 5145 This ioctl issues an ultravisor call to terminate the secure guest,
5251 unpins the VPA pages and releases all the dev 5146 unpins the VPA pages and releases all the device pages that are used to
5252 track the secure pages by hypervisor. 5147 track the secure pages by hypervisor.
5253 5148
5254 4.122 KVM_S390_NORMAL_RESET 5149 4.122 KVM_S390_NORMAL_RESET
5255 --------------------------- 5150 ---------------------------
5256 5151
5257 :Capability: KVM_CAP_S390_VCPU_RESETS 5152 :Capability: KVM_CAP_S390_VCPU_RESETS
5258 :Architectures: s390 5153 :Architectures: s390
5259 :Type: vcpu ioctl 5154 :Type: vcpu ioctl
5260 :Parameters: none 5155 :Parameters: none
5261 :Returns: 0 5156 :Returns: 0
5262 5157
5263 This ioctl resets VCPU registers and control 5158 This ioctl resets VCPU registers and control structures according to
5264 the cpu reset definition in the POP (Principl 5159 the cpu reset definition in the POP (Principles Of Operation).
5265 5160
5266 4.123 KVM_S390_INITIAL_RESET 5161 4.123 KVM_S390_INITIAL_RESET
5267 ---------------------------- 5162 ----------------------------
5268 5163
5269 :Capability: none 5164 :Capability: none
5270 :Architectures: s390 5165 :Architectures: s390
5271 :Type: vcpu ioctl 5166 :Type: vcpu ioctl
5272 :Parameters: none 5167 :Parameters: none
5273 :Returns: 0 5168 :Returns: 0
5274 5169
5275 This ioctl resets VCPU registers and control 5170 This ioctl resets VCPU registers and control structures according to
5276 the initial cpu reset definition in the POP. 5171 the initial cpu reset definition in the POP. However, the cpu is not
5277 put into ESA mode. This reset is a superset o 5172 put into ESA mode. This reset is a superset of the normal reset.
5278 5173
5279 4.124 KVM_S390_CLEAR_RESET 5174 4.124 KVM_S390_CLEAR_RESET
5280 -------------------------- 5175 --------------------------
5281 5176
5282 :Capability: KVM_CAP_S390_VCPU_RESETS 5177 :Capability: KVM_CAP_S390_VCPU_RESETS
5283 :Architectures: s390 5178 :Architectures: s390
5284 :Type: vcpu ioctl 5179 :Type: vcpu ioctl
5285 :Parameters: none 5180 :Parameters: none
5286 :Returns: 0 5181 :Returns: 0
5287 5182
5288 This ioctl resets VCPU registers and control 5183 This ioctl resets VCPU registers and control structures according to
5289 the clear cpu reset definition in the POP. Ho 5184 the clear cpu reset definition in the POP. However, the cpu is not put
5290 into ESA mode. This reset is a superset of th 5185 into ESA mode. This reset is a superset of the initial reset.
5291 5186
5292 5187
5293 4.125 KVM_S390_PV_COMMAND 5188 4.125 KVM_S390_PV_COMMAND
5294 ------------------------- 5189 -------------------------
5295 5190
5296 :Capability: KVM_CAP_S390_PROTECTED 5191 :Capability: KVM_CAP_S390_PROTECTED
5297 :Architectures: s390 5192 :Architectures: s390
5298 :Type: vm ioctl 5193 :Type: vm ioctl
5299 :Parameters: struct kvm_pv_cmd 5194 :Parameters: struct kvm_pv_cmd
5300 :Returns: 0 on success, < 0 on error 5195 :Returns: 0 on success, < 0 on error
5301 5196
5302 :: 5197 ::
5303 5198
5304 struct kvm_pv_cmd { 5199 struct kvm_pv_cmd {
5305 __u32 cmd; /* Command to be exec 5200 __u32 cmd; /* Command to be executed */
5306 __u16 rc; /* Ultravisor return 5201 __u16 rc; /* Ultravisor return code */
5307 __u16 rrc; /* Ultravisor return 5202 __u16 rrc; /* Ultravisor return reason code */
5308 __u64 data; /* Data or address */ 5203 __u64 data; /* Data or address */
5309 __u32 flags; /* flags for future e 5204 __u32 flags; /* flags for future extensions. Must be 0 for now */
5310 __u32 reserved[3]; 5205 __u32 reserved[3];
5311 }; 5206 };
5312 5207
5313 **Ultravisor return codes** 5208 **Ultravisor return codes**
5314 The Ultravisor return (reason) codes are prov 5209 The Ultravisor return (reason) codes are provided by the kernel if a
5315 Ultravisor call has been executed to achieve 5210 Ultravisor call has been executed to achieve the results expected by
5316 the command. Therefore they are independent o 5211 the command. Therefore they are independent of the IOCTL return
5317 code. If KVM changes `rc`, its value will alw 5212 code. If KVM changes `rc`, its value will always be greater than 0
5318 hence setting it to 0 before issuing a PV com 5213 hence setting it to 0 before issuing a PV command is advised to be
5319 able to detect a change of `rc`. 5214 able to detect a change of `rc`.
5320 5215
5321 **cmd values:** 5216 **cmd values:**
5322 5217
5323 KVM_PV_ENABLE 5218 KVM_PV_ENABLE
5324 Allocate memory and register the VM with th 5219 Allocate memory and register the VM with the Ultravisor, thereby
5325 donating memory to the Ultravisor that will 5220 donating memory to the Ultravisor that will become inaccessible to
5326 KVM. All existing CPUs are converted to pro 5221 KVM. All existing CPUs are converted to protected ones. After this
5327 command has succeeded, any CPU added via ho 5222 command has succeeded, any CPU added via hotplug will become
5328 protected during its creation as well. 5223 protected during its creation as well.
5329 5224
5330 Errors: 5225 Errors:
5331 5226
5332 ===== ============================= 5227 ===== =============================
5333 EINTR an unmasked signal is pending 5228 EINTR an unmasked signal is pending
5334 ===== ============================= 5229 ===== =============================
5335 5230
5336 KVM_PV_DISABLE 5231 KVM_PV_DISABLE
5337 Deregister the VM from the Ultravisor and r 5232 Deregister the VM from the Ultravisor and reclaim the memory that had
5338 been donated to the Ultravisor, making it u 5233 been donated to the Ultravisor, making it usable by the kernel again.
5339 All registered VCPUs are converted back to 5234 All registered VCPUs are converted back to non-protected ones. If a
5340 previous protected VM had been prepared for !! 5235 previous protected VM had been prepared for asynchonous teardown with
5341 KVM_PV_ASYNC_CLEANUP_PREPARE and not subseq 5236 KVM_PV_ASYNC_CLEANUP_PREPARE and not subsequently torn down with
5342 KVM_PV_ASYNC_CLEANUP_PERFORM, it will be to 5237 KVM_PV_ASYNC_CLEANUP_PERFORM, it will be torn down in this call
5343 together with the current protected VM. 5238 together with the current protected VM.
5344 5239
5345 KVM_PV_VM_SET_SEC_PARMS 5240 KVM_PV_VM_SET_SEC_PARMS
5346 Pass the image header from VM memory to the 5241 Pass the image header from VM memory to the Ultravisor in
5347 preparation of image unpacking and verifica 5242 preparation of image unpacking and verification.
5348 5243
5349 KVM_PV_VM_UNPACK 5244 KVM_PV_VM_UNPACK
5350 Unpack (protect and decrypt) a page of the 5245 Unpack (protect and decrypt) a page of the encrypted boot image.
5351 5246
5352 KVM_PV_VM_VERIFY 5247 KVM_PV_VM_VERIFY
5353 Verify the integrity of the unpacked image. 5248 Verify the integrity of the unpacked image. Only if this succeeds,
5354 KVM is allowed to start protected VCPUs. 5249 KVM is allowed to start protected VCPUs.
5355 5250
5356 KVM_PV_INFO 5251 KVM_PV_INFO
5357 :Capability: KVM_CAP_S390_PROTECTED_DUMP 5252 :Capability: KVM_CAP_S390_PROTECTED_DUMP
5358 5253
5359 Presents an API that provides Ultravisor re 5254 Presents an API that provides Ultravisor related data to userspace
5360 via subcommands. len_max is the size of the 5255 via subcommands. len_max is the size of the user space buffer,
5361 len_written is KVM's indication of how much 5256 len_written is KVM's indication of how much bytes of that buffer
5362 were actually written to. len_written can b 5257 were actually written to. len_written can be used to determine the
5363 valid fields if more response fields are ad 5258 valid fields if more response fields are added in the future.
5364 5259
5365 :: 5260 ::
5366 5261
5367 enum pv_cmd_info_id { 5262 enum pv_cmd_info_id {
5368 KVM_PV_INFO_VM, 5263 KVM_PV_INFO_VM,
5369 KVM_PV_INFO_DUMP, 5264 KVM_PV_INFO_DUMP,
5370 }; 5265 };
5371 5266
5372 struct kvm_s390_pv_info_header { 5267 struct kvm_s390_pv_info_header {
5373 __u32 id; 5268 __u32 id;
5374 __u32 len_max; 5269 __u32 len_max;
5375 __u32 len_written; 5270 __u32 len_written;
5376 __u32 reserved; 5271 __u32 reserved;
5377 }; 5272 };
5378 5273
5379 struct kvm_s390_pv_info { 5274 struct kvm_s390_pv_info {
5380 struct kvm_s390_pv_info_header header 5275 struct kvm_s390_pv_info_header header;
5381 struct kvm_s390_pv_info_dump dump; 5276 struct kvm_s390_pv_info_dump dump;
5382 struct kvm_s390_pv_info_vm vm; 5277 struct kvm_s390_pv_info_vm vm;
5383 }; 5278 };
5384 5279
5385 **subcommands:** 5280 **subcommands:**
5386 5281
5387 KVM_PV_INFO_VM 5282 KVM_PV_INFO_VM
5388 This subcommand provides basic Ultravisor 5283 This subcommand provides basic Ultravisor information for PV
5389 hosts. These values are likely also expor 5284 hosts. These values are likely also exported as files in the sysfs
5390 firmware UV query interface but they are 5285 firmware UV query interface but they are more easily available to
5391 programs in this API. 5286 programs in this API.
5392 5287
5393 The installed calls and feature_indicatio 5288 The installed calls and feature_indication members provide the
5394 installed UV calls and the UV's other fea 5289 installed UV calls and the UV's other feature indications.
5395 5290
5396 The max_* members provide information abo 5291 The max_* members provide information about the maximum number of PV
5397 vcpus, PV guests and PV guest memory size 5292 vcpus, PV guests and PV guest memory size.
5398 5293
5399 :: 5294 ::
5400 5295
5401 struct kvm_s390_pv_info_vm { 5296 struct kvm_s390_pv_info_vm {
5402 __u64 inst_calls_list[4]; 5297 __u64 inst_calls_list[4];
5403 __u64 max_cpus; 5298 __u64 max_cpus;
5404 __u64 max_guests; 5299 __u64 max_guests;
5405 __u64 max_guest_addr; 5300 __u64 max_guest_addr;
5406 __u64 feature_indication; 5301 __u64 feature_indication;
5407 }; 5302 };
5408 5303
5409 5304
5410 KVM_PV_INFO_DUMP 5305 KVM_PV_INFO_DUMP
5411 This subcommand provides information rela 5306 This subcommand provides information related to dumping PV guests.
5412 5307
5413 :: 5308 ::
5414 5309
5415 struct kvm_s390_pv_info_dump { 5310 struct kvm_s390_pv_info_dump {
5416 __u64 dump_cpu_buffer_len; 5311 __u64 dump_cpu_buffer_len;
5417 __u64 dump_config_mem_buffer_per_1m; 5312 __u64 dump_config_mem_buffer_per_1m;
5418 __u64 dump_config_finalize_len; 5313 __u64 dump_config_finalize_len;
5419 }; 5314 };
5420 5315
5421 KVM_PV_DUMP 5316 KVM_PV_DUMP
5422 :Capability: KVM_CAP_S390_PROTECTED_DUMP 5317 :Capability: KVM_CAP_S390_PROTECTED_DUMP
5423 5318
5424 Presents an API that provides calls which f 5319 Presents an API that provides calls which facilitate dumping a
5425 protected VM. 5320 protected VM.
5426 5321
5427 :: 5322 ::
5428 5323
5429 struct kvm_s390_pv_dmp { 5324 struct kvm_s390_pv_dmp {
5430 __u64 subcmd; 5325 __u64 subcmd;
5431 __u64 buff_addr; 5326 __u64 buff_addr;
5432 __u64 buff_len; 5327 __u64 buff_len;
5433 __u64 gaddr; /* For dump s 5328 __u64 gaddr; /* For dump storage state */
5434 }; 5329 };
5435 5330
5436 **subcommands:** 5331 **subcommands:**
5437 5332
5438 KVM_PV_DUMP_INIT 5333 KVM_PV_DUMP_INIT
5439 Initializes the dump process of a protect 5334 Initializes the dump process of a protected VM. If this call does
5440 not succeed all other subcommands will fa 5335 not succeed all other subcommands will fail with -EINVAL. This
5441 subcommand will return -EINVAL if a dump 5336 subcommand will return -EINVAL if a dump process has not yet been
5442 completed. 5337 completed.
5443 5338
5444 Not all PV vms can be dumped, the owner n 5339 Not all PV vms can be dumped, the owner needs to set `dump
5445 allowed` PCF bit 34 in the SE header to a 5340 allowed` PCF bit 34 in the SE header to allow dumping.
5446 5341
5447 KVM_PV_DUMP_CONFIG_STOR_STATE 5342 KVM_PV_DUMP_CONFIG_STOR_STATE
5448 Stores `buff_len` bytes of tweak compone 5343 Stores `buff_len` bytes of tweak component values starting with
5449 the 1MB block specified by the absolute 5344 the 1MB block specified by the absolute guest address
5450 (`gaddr`). `buff_len` needs to be `conf_ 5345 (`gaddr`). `buff_len` needs to be `conf_dump_storage_state_len`
5451 aligned and at least >= the `conf_dump_s 5346 aligned and at least >= the `conf_dump_storage_state_len` value
5452 provided by the dump uv_info data. buff_ 5347 provided by the dump uv_info data. buff_user might be written to
5453 even if an error rc is returned. For ins 5348 even if an error rc is returned. For instance if we encounter a
5454 fault after writing the first page of da 5349 fault after writing the first page of data.
5455 5350
5456 KVM_PV_DUMP_COMPLETE 5351 KVM_PV_DUMP_COMPLETE
5457 If the subcommand succeeds it completes t 5352 If the subcommand succeeds it completes the dump process and lets
5458 KVM_PV_DUMP_INIT be called again. 5353 KVM_PV_DUMP_INIT be called again.
5459 5354
5460 On success `conf_dump_finalize_len` bytes 5355 On success `conf_dump_finalize_len` bytes of completion data will be
5461 stored to the `buff_addr`. The completion 5356 stored to the `buff_addr`. The completion data contains a key
5462 derivation seed, IV, tweak nonce and encr 5357 derivation seed, IV, tweak nonce and encryption keys as well as an
5463 authentication tag all of which are neede 5358 authentication tag all of which are needed to decrypt the dump at a
5464 later time. 5359 later time.
5465 5360
5466 KVM_PV_ASYNC_CLEANUP_PREPARE 5361 KVM_PV_ASYNC_CLEANUP_PREPARE
5467 :Capability: KVM_CAP_S390_PROTECTED_ASYNC_D 5362 :Capability: KVM_CAP_S390_PROTECTED_ASYNC_DISABLE
5468 5363
5469 Prepare the current protected VM for asynch 5364 Prepare the current protected VM for asynchronous teardown. Most
5470 resources used by the current protected VM 5365 resources used by the current protected VM will be set aside for a
5471 subsequent asynchronous teardown. The curre 5366 subsequent asynchronous teardown. The current protected VM will then
5472 resume execution immediately as non-protect 5367 resume execution immediately as non-protected. There can be at most
5473 one protected VM prepared for asynchronous 5368 one protected VM prepared for asynchronous teardown at any time. If
5474 a protected VM had already been prepared fo 5369 a protected VM had already been prepared for teardown without
5475 subsequently calling KVM_PV_ASYNC_CLEANUP_P 5370 subsequently calling KVM_PV_ASYNC_CLEANUP_PERFORM, this call will
5476 fail. In that case, the userspace process s 5371 fail. In that case, the userspace process should issue a normal
5477 KVM_PV_DISABLE. The resources set aside wit 5372 KVM_PV_DISABLE. The resources set aside with this call will need to
5478 be cleaned up with a subsequent call to KVM 5373 be cleaned up with a subsequent call to KVM_PV_ASYNC_CLEANUP_PERFORM
5479 or KVM_PV_DISABLE, otherwise they will be c 5374 or KVM_PV_DISABLE, otherwise they will be cleaned up when KVM
5480 terminates. KVM_PV_ASYNC_CLEANUP_PREPARE ca 5375 terminates. KVM_PV_ASYNC_CLEANUP_PREPARE can be called again as soon
5481 as cleanup starts, i.e. before KVM_PV_ASYNC 5376 as cleanup starts, i.e. before KVM_PV_ASYNC_CLEANUP_PERFORM finishes.
5482 5377
5483 KVM_PV_ASYNC_CLEANUP_PERFORM 5378 KVM_PV_ASYNC_CLEANUP_PERFORM
5484 :Capability: KVM_CAP_S390_PROTECTED_ASYNC_D 5379 :Capability: KVM_CAP_S390_PROTECTED_ASYNC_DISABLE
5485 5380
5486 Tear down the protected VM previously prepa 5381 Tear down the protected VM previously prepared for teardown with
5487 KVM_PV_ASYNC_CLEANUP_PREPARE. The resources 5382 KVM_PV_ASYNC_CLEANUP_PREPARE. The resources that had been set aside
5488 will be freed during the execution of this 5383 will be freed during the execution of this command. This PV command
5489 should ideally be issued by userspace from 5384 should ideally be issued by userspace from a separate thread. If a
5490 fatal signal is received (or the process te 5385 fatal signal is received (or the process terminates naturally), the
5491 command will terminate immediately without 5386 command will terminate immediately without completing, and the normal
5492 KVM shutdown procedure will take care of cl 5387 KVM shutdown procedure will take care of cleaning up all remaining
5493 protected VMs, including the ones whose tea 5388 protected VMs, including the ones whose teardown was interrupted by
5494 process termination. 5389 process termination.
5495 5390
5496 4.126 KVM_XEN_HVM_SET_ATTR 5391 4.126 KVM_XEN_HVM_SET_ATTR
5497 -------------------------- 5392 --------------------------
5498 5393
5499 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CO 5394 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO
5500 :Architectures: x86 5395 :Architectures: x86
5501 :Type: vm ioctl 5396 :Type: vm ioctl
5502 :Parameters: struct kvm_xen_hvm_attr 5397 :Parameters: struct kvm_xen_hvm_attr
5503 :Returns: 0 on success, < 0 on error 5398 :Returns: 0 on success, < 0 on error
5504 5399
5505 :: 5400 ::
5506 5401
5507 struct kvm_xen_hvm_attr { 5402 struct kvm_xen_hvm_attr {
5508 __u16 type; 5403 __u16 type;
5509 __u16 pad[3]; 5404 __u16 pad[3];
5510 union { 5405 union {
5511 __u8 long_mode; 5406 __u8 long_mode;
5512 __u8 vector; 5407 __u8 vector;
5513 __u8 runstate_update_flag; 5408 __u8 runstate_update_flag;
5514 union { !! 5409 struct {
5515 __u64 gfn; 5410 __u64 gfn;
5516 __u64 hva; <<
5517 } shared_info; 5411 } shared_info;
5518 struct { 5412 struct {
5519 __u32 send_port; 5413 __u32 send_port;
5520 __u32 type; /* EVTCHN 5414 __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */
5521 __u32 flags; 5415 __u32 flags;
5522 union { 5416 union {
5523 struct { 5417 struct {
5524 __u32 5418 __u32 port;
5525 __u32 5419 __u32 vcpu;
5526 __u32 5420 __u32 priority;
5527 } port; 5421 } port;
5528 struct { 5422 struct {
5529 __u32 5423 __u32 port; /* Zero for eventfd */
5530 __s32 5424 __s32 fd;
5531 } eventfd; 5425 } eventfd;
5532 __u32 padding 5426 __u32 padding[4];
5533 } deliver; 5427 } deliver;
5534 } evtchn; 5428 } evtchn;
5535 __u32 xen_version; 5429 __u32 xen_version;
5536 __u64 pad[8]; 5430 __u64 pad[8];
5537 } u; 5431 } u;
5538 }; 5432 };
5539 5433
5540 type values: 5434 type values:
5541 5435
5542 KVM_XEN_ATTR_TYPE_LONG_MODE 5436 KVM_XEN_ATTR_TYPE_LONG_MODE
5543 Sets the ABI mode of the VM to 32-bit or 64 5437 Sets the ABI mode of the VM to 32-bit or 64-bit (long mode). This
5544 determines the layout of the shared_info pa !! 5438 determines the layout of the shared info pages exposed to the VM.
5545 5439
5546 KVM_XEN_ATTR_TYPE_SHARED_INFO 5440 KVM_XEN_ATTR_TYPE_SHARED_INFO
5547 Sets the guest physical frame number at whi !! 5441 Sets the guest physical frame number at which the Xen "shared info"
5548 page resides. Note that although Xen places 5442 page resides. Note that although Xen places vcpu_info for the first
5549 32 vCPUs in the shared_info page, KVM does 5443 32 vCPUs in the shared_info page, KVM does not automatically do so
5550 and instead requires that KVM_XEN_VCPU_ATTR !! 5444 and instead requires that KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO be used
5551 KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA be use !! 5445 explicitly even when the vcpu_info for a given vCPU resides at the
5552 the vcpu_info for a given vCPU resides at t !! 5446 "default" location in the shared_info page. This is because KVM may
5553 in the shared_info page. This is because KV !! 5447 not be aware of the Xen CPU id which is used as the index into the
5554 the Xen CPU id which is used as the index i !! 5448 vcpu_info[] array, so may know the correct default location.
5555 array, so may know the correct default loca <<
5556 5449
5557 Note that the shared_info page may be const !! 5450 Note that the shared info page may be constantly written to by KVM;
5558 it contains the event channel bitmap used t 5451 it contains the event channel bitmap used to deliver interrupts to
5559 a Xen guest, amongst other things. It is ex 5452 a Xen guest, amongst other things. It is exempt from dirty tracking
5560 mechanisms — KVM will not explicitly mark 5453 mechanisms — KVM will not explicitly mark the page as dirty each
5561 time an event channel interrupt is delivere 5454 time an event channel interrupt is delivered to the guest! Thus,
5562 userspace should always assume that the des 5455 userspace should always assume that the designated GFN is dirty if
5563 any vCPU has been running or any event chan 5456 any vCPU has been running or any event channel interrupts can be
5564 routed to the guest. 5457 routed to the guest.
5565 5458
5566 Setting the gfn to KVM_XEN_INVALID_GFN will !! 5459 Setting the gfn to KVM_XEN_INVALID_GFN will disable the shared info
5567 page. 5460 page.
5568 5461
5569 KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA <<
5570 If the KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA f <<
5571 Xen capabilities, then this attribute may b <<
5572 userspace address at which the shared_info <<
5573 will always be fixed in the VMM regardless <<
5574 in guest physical address space. This attri <<
5575 preference to KVM_XEN_ATTR_TYPE_SHARED_INFO <<
5576 unnecessary invalidation of an internal cac <<
5577 re-mapped in guest physcial address space. <<
5578 <<
5579 Setting the hva to zero will disable the sh <<
5580 <<
5581 KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 5462 KVM_XEN_ATTR_TYPE_UPCALL_VECTOR
5582 Sets the exception vector used to deliver X 5463 Sets the exception vector used to deliver Xen event channel upcalls.
5583 This is the HVM-wide vector injected direct 5464 This is the HVM-wide vector injected directly by the hypervisor
5584 (not through the local APIC), typically con 5465 (not through the local APIC), typically configured by a guest via
5585 HVM_PARAM_CALLBACK_IRQ. This can be disable 5466 HVM_PARAM_CALLBACK_IRQ. This can be disabled again (e.g. for guest
5586 SHUTDOWN_soft_reset) by setting it to zero. 5467 SHUTDOWN_soft_reset) by setting it to zero.
5587 5468
5588 KVM_XEN_ATTR_TYPE_EVTCHN 5469 KVM_XEN_ATTR_TYPE_EVTCHN
5589 This attribute is available when the KVM_CA 5470 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
5590 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND 5471 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures
5591 an outbound port number for interception of 5472 an outbound port number for interception of EVTCHNOP_send requests
5592 from the guest. A given sending port number 5473 from the guest. A given sending port number may be directed back to
5593 a specified vCPU (by APIC ID) / port / prio 5474 a specified vCPU (by APIC ID) / port / priority on the guest, or to
5594 trigger events on an eventfd. The vCPU and 5475 trigger events on an eventfd. The vCPU and priority can be changed
5595 by setting KVM_XEN_EVTCHN_UPDATE in a subse !! 5476 by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, but but other
5596 fields cannot change for a given sending po 5477 fields cannot change for a given sending port. A port mapping is
5597 removed by using KVM_XEN_EVTCHN_DEASSIGN in 5478 removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags field. Passing
5598 KVM_XEN_EVTCHN_RESET in the flags field rem 5479 KVM_XEN_EVTCHN_RESET in the flags field removes all interception of
5599 outbound event channels. The values of the 5480 outbound event channels. The values of the flags field are mutually
5600 exclusive and cannot be combined as a bitma 5481 exclusive and cannot be combined as a bitmask.
5601 5482
5602 KVM_XEN_ATTR_TYPE_XEN_VERSION 5483 KVM_XEN_ATTR_TYPE_XEN_VERSION
5603 This attribute is available when the KVM_CA 5484 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
5604 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND 5485 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures
5605 the 32-bit version code returned to the gue 5486 the 32-bit version code returned to the guest when it invokes the
5606 XENVER_version call; typically (XEN_MAJOR < 5487 XENVER_version call; typically (XEN_MAJOR << 16 | XEN_MINOR). PV
5607 Xen guests will often use this to as a dumm 5488 Xen guests will often use this to as a dummy hypercall to trigger
5608 event channel delivery, so responding withi 5489 event channel delivery, so responding within the kernel without
5609 exiting to userspace is beneficial. 5490 exiting to userspace is beneficial.
5610 5491
5611 KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 5492 KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG
5612 This attribute is available when the KVM_CA 5493 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
5613 support for KVM_XEN_HVM_CONFIG_RUNSTATE_UPD 5494 support for KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG. It enables the
5614 XEN_RUNSTATE_UPDATE flag which allows guest 5495 XEN_RUNSTATE_UPDATE flag which allows guest vCPUs to safely read
5615 other vCPUs' vcpu_runstate_info. Xen guests 5496 other vCPUs' vcpu_runstate_info. Xen guests enable this feature via
5616 the VMASST_TYPE_runstate_update_flag of the 5497 the VMASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist
5617 hypercall. 5498 hypercall.
5618 5499
5619 4.127 KVM_XEN_HVM_GET_ATTR 5500 4.127 KVM_XEN_HVM_GET_ATTR
5620 -------------------------- 5501 --------------------------
5621 5502
5622 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CO 5503 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO
5623 :Architectures: x86 5504 :Architectures: x86
5624 :Type: vm ioctl 5505 :Type: vm ioctl
5625 :Parameters: struct kvm_xen_hvm_attr 5506 :Parameters: struct kvm_xen_hvm_attr
5626 :Returns: 0 on success, < 0 on error 5507 :Returns: 0 on success, < 0 on error
5627 5508
5628 Allows Xen VM attributes to be read. For the 5509 Allows Xen VM attributes to be read. For the structure and types,
5629 see KVM_XEN_HVM_SET_ATTR above. The KVM_XEN_A 5510 see KVM_XEN_HVM_SET_ATTR above. The KVM_XEN_ATTR_TYPE_EVTCHN
5630 attribute cannot be read. 5511 attribute cannot be read.
5631 5512
5632 4.128 KVM_XEN_VCPU_SET_ATTR 5513 4.128 KVM_XEN_VCPU_SET_ATTR
5633 --------------------------- 5514 ---------------------------
5634 5515
5635 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CO 5516 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO
5636 :Architectures: x86 5517 :Architectures: x86
5637 :Type: vcpu ioctl 5518 :Type: vcpu ioctl
5638 :Parameters: struct kvm_xen_vcpu_attr 5519 :Parameters: struct kvm_xen_vcpu_attr
5639 :Returns: 0 on success, < 0 on error 5520 :Returns: 0 on success, < 0 on error
5640 5521
5641 :: 5522 ::
5642 5523
5643 struct kvm_xen_vcpu_attr { 5524 struct kvm_xen_vcpu_attr {
5644 __u16 type; 5525 __u16 type;
5645 __u16 pad[3]; 5526 __u16 pad[3];
5646 union { 5527 union {
5647 __u64 gpa; 5528 __u64 gpa;
5648 __u64 pad[4]; 5529 __u64 pad[4];
5649 struct { 5530 struct {
5650 __u64 state; 5531 __u64 state;
5651 __u64 state_entry_tim 5532 __u64 state_entry_time;
5652 __u64 time_running; 5533 __u64 time_running;
5653 __u64 time_runnable; 5534 __u64 time_runnable;
5654 __u64 time_blocked; 5535 __u64 time_blocked;
5655 __u64 time_offline; 5536 __u64 time_offline;
5656 } runstate; 5537 } runstate;
5657 __u32 vcpu_id; 5538 __u32 vcpu_id;
5658 struct { 5539 struct {
5659 __u32 port; 5540 __u32 port;
5660 __u32 priority; 5541 __u32 priority;
5661 __u64 expires_ns; 5542 __u64 expires_ns;
5662 } timer; 5543 } timer;
5663 __u8 vector; 5544 __u8 vector;
5664 } u; 5545 } u;
5665 }; 5546 };
5666 5547
5667 type values: 5548 type values:
5668 5549
5669 KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 5550 KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO
5670 Sets the guest physical address of the vcpu 5551 Sets the guest physical address of the vcpu_info for a given vCPU.
5671 As with the shared_info page for the VM, th 5552 As with the shared_info page for the VM, the corresponding page may be
5672 dirtied at any time if event channel interr 5553 dirtied at any time if event channel interrupt delivery is enabled, so
5673 userspace should always assume that the pag 5554 userspace should always assume that the page is dirty without relying
5674 on dirty logging. Setting the gpa to KVM_XE 5555 on dirty logging. Setting the gpa to KVM_XEN_INVALID_GPA will disable
5675 the vcpu_info. 5556 the vcpu_info.
5676 5557
5677 KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA <<
5678 If the KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA f <<
5679 Xen capabilities, then this attribute may b <<
5680 userspace address of the vcpu_info for a gi <<
5681 only be used when the vcpu_info resides at <<
5682 in the shared_info page. In this case it is <<
5683 userspace address will not change, because <<
5684 an overlay on guest memory and remains at a <<
5685 regardless of where it is mapped in guest p <<
5686 and hence unnecessary invalidation of an in <<
5687 avoided if the guest memory layout is modif <<
5688 If the vcpu_info does not reside at the "de <<
5689 it is not guaranteed to remain at the same <<
5690 hence the aforementioned cache invalidation <<
5691 <<
5692 KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 5558 KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO
5693 Sets the guest physical address of an addit 5559 Sets the guest physical address of an additional pvclock structure
5694 for a given vCPU. This is typically used fo 5560 for a given vCPU. This is typically used for guest vsyscall support.
5695 Setting the gpa to KVM_XEN_INVALID_GPA will 5561 Setting the gpa to KVM_XEN_INVALID_GPA will disable the structure.
5696 5562
5697 KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 5563 KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR
5698 Sets the guest physical address of the vcpu 5564 Sets the guest physical address of the vcpu_runstate_info for a given
5699 vCPU. This is how a Xen guest tracks CPU st 5565 vCPU. This is how a Xen guest tracks CPU state such as steal time.
5700 Setting the gpa to KVM_XEN_INVALID_GPA will 5566 Setting the gpa to KVM_XEN_INVALID_GPA will disable the runstate area.
5701 5567
5702 KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 5568 KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT
5703 Sets the runstate (RUNSTATE_running/_runnab 5569 Sets the runstate (RUNSTATE_running/_runnable/_blocked/_offline) of
5704 the given vCPU from the .u.runstate.state m 5570 the given vCPU from the .u.runstate.state member of the structure.
5705 KVM automatically accounts running and runn 5571 KVM automatically accounts running and runnable time but blocked
5706 and offline states are only entered explici 5572 and offline states are only entered explicitly.
5707 5573
5708 KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 5574 KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA
5709 Sets all fields of the vCPU runstate data f 5575 Sets all fields of the vCPU runstate data from the .u.runstate member
5710 of the structure, including the current run 5576 of the structure, including the current runstate. The state_entry_time
5711 must equal the sum of the other four times. 5577 must equal the sum of the other four times.
5712 5578
5713 KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 5579 KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST
5714 This *adds* the contents of the .u.runstate 5580 This *adds* the contents of the .u.runstate members of the structure
5715 to the corresponding members of the given v 5581 to the corresponding members of the given vCPU's runstate data, thus
5716 permitting atomic adjustments to the runsta 5582 permitting atomic adjustments to the runstate times. The adjustment
5717 to the state_entry_time must equal the sum 5583 to the state_entry_time must equal the sum of the adjustments to the
5718 other four times. The state field must be s 5584 other four times. The state field must be set to -1, or to a valid
5719 runstate value (RUNSTATE_running, RUNSTATE_ 5585 runstate value (RUNSTATE_running, RUNSTATE_runnable, RUNSTATE_blocked
5720 or RUNSTATE_offline) to set the current acc 5586 or RUNSTATE_offline) to set the current accounted state as of the
5721 adjusted state_entry_time. 5587 adjusted state_entry_time.
5722 5588
5723 KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 5589 KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID
5724 This attribute is available when the KVM_CA 5590 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
5725 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND 5591 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the Xen
5726 vCPU ID of the given vCPU, to allow timer-r 5592 vCPU ID of the given vCPU, to allow timer-related VCPU operations to
5727 be intercepted by KVM. 5593 be intercepted by KVM.
5728 5594
5729 KVM_XEN_VCPU_ATTR_TYPE_TIMER 5595 KVM_XEN_VCPU_ATTR_TYPE_TIMER
5730 This attribute is available when the KVM_CA 5596 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
5731 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND 5597 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the
5732 event channel port/priority for the VIRQ_TI 5598 event channel port/priority for the VIRQ_TIMER of the vCPU, as well
5733 as allowing a pending timer to be saved/res 5599 as allowing a pending timer to be saved/restored. Setting the timer
5734 port to zero disables kernel handling of th 5600 port to zero disables kernel handling of the singleshot timer.
5735 5601
5736 KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 5602 KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR
5737 This attribute is available when the KVM_CA 5603 This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
5738 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND 5604 support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the
5739 per-vCPU local APIC upcall vector, configur 5605 per-vCPU local APIC upcall vector, configured by a Xen guest with
5740 the HVMOP_set_evtchn_upcall_vector hypercal 5606 the HVMOP_set_evtchn_upcall_vector hypercall. This is typically
5741 used by Windows guests, and is distinct fro 5607 used by Windows guests, and is distinct from the HVM-wide upcall
5742 vector configured with HVM_PARAM_CALLBACK_I 5608 vector configured with HVM_PARAM_CALLBACK_IRQ. It is disabled by
5743 setting the vector to zero. 5609 setting the vector to zero.
5744 5610
5745 5611
5746 4.129 KVM_XEN_VCPU_GET_ATTR 5612 4.129 KVM_XEN_VCPU_GET_ATTR
5747 --------------------------- 5613 ---------------------------
5748 5614
5749 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CO 5615 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO
5750 :Architectures: x86 5616 :Architectures: x86
5751 :Type: vcpu ioctl 5617 :Type: vcpu ioctl
5752 :Parameters: struct kvm_xen_vcpu_attr 5618 :Parameters: struct kvm_xen_vcpu_attr
5753 :Returns: 0 on success, < 0 on error 5619 :Returns: 0 on success, < 0 on error
5754 5620
5755 Allows Xen vCPU attributes to be read. For th 5621 Allows Xen vCPU attributes to be read. For the structure and types,
5756 see KVM_XEN_VCPU_SET_ATTR above. 5622 see KVM_XEN_VCPU_SET_ATTR above.
5757 5623
5758 The KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST ty 5624 The KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST type may not be used
5759 with the KVM_XEN_VCPU_GET_ATTR ioctl. 5625 with the KVM_XEN_VCPU_GET_ATTR ioctl.
5760 5626
5761 4.130 KVM_ARM_MTE_COPY_TAGS 5627 4.130 KVM_ARM_MTE_COPY_TAGS
5762 --------------------------- 5628 ---------------------------
5763 5629
5764 :Capability: KVM_CAP_ARM_MTE 5630 :Capability: KVM_CAP_ARM_MTE
5765 :Architectures: arm64 5631 :Architectures: arm64
5766 :Type: vm ioctl 5632 :Type: vm ioctl
5767 :Parameters: struct kvm_arm_copy_mte_tags 5633 :Parameters: struct kvm_arm_copy_mte_tags
5768 :Returns: number of bytes copied, < 0 on erro 5634 :Returns: number of bytes copied, < 0 on error (-EINVAL for incorrect
5769 arguments, -EFAULT if memory cannot 5635 arguments, -EFAULT if memory cannot be accessed).
5770 5636
5771 :: 5637 ::
5772 5638
5773 struct kvm_arm_copy_mte_tags { 5639 struct kvm_arm_copy_mte_tags {
5774 __u64 guest_ipa; 5640 __u64 guest_ipa;
5775 __u64 length; 5641 __u64 length;
5776 void __user *addr; 5642 void __user *addr;
5777 __u64 flags; 5643 __u64 flags;
5778 __u64 reserved[2]; 5644 __u64 reserved[2];
5779 }; 5645 };
5780 5646
5781 Copies Memory Tagging Extension (MTE) tags to 5647 Copies Memory Tagging Extension (MTE) tags to/from guest tag memory. The
5782 ``guest_ipa`` and ``length`` fields must be ` 5648 ``guest_ipa`` and ``length`` fields must be ``PAGE_SIZE`` aligned.
5783 ``length`` must not be bigger than 2^31 - PAG 5649 ``length`` must not be bigger than 2^31 - PAGE_SIZE bytes. The ``addr``
5784 field must point to a buffer which the tags w 5650 field must point to a buffer which the tags will be copied to or from.
5785 5651
5786 ``flags`` specifies the direction of copy, ei 5652 ``flags`` specifies the direction of copy, either ``KVM_ARM_TAGS_TO_GUEST`` or
5787 ``KVM_ARM_TAGS_FROM_GUEST``. 5653 ``KVM_ARM_TAGS_FROM_GUEST``.
5788 5654
5789 The size of the buffer to store the tags is ` 5655 The size of the buffer to store the tags is ``(length / 16)`` bytes
5790 (granules in MTE are 16 bytes long). Each byt 5656 (granules in MTE are 16 bytes long). Each byte contains a single tag
5791 value. This matches the format of ``PTRACE_PE 5657 value. This matches the format of ``PTRACE_PEEKMTETAGS`` and
5792 ``PTRACE_POKEMTETAGS``. 5658 ``PTRACE_POKEMTETAGS``.
5793 5659
5794 If an error occurs before any data is copied 5660 If an error occurs before any data is copied then a negative error code is
5795 returned. If some tags have been copied befor 5661 returned. If some tags have been copied before an error occurs then the number
5796 of bytes successfully copied is returned. If 5662 of bytes successfully copied is returned. If the call completes successfully
5797 then ``length`` is returned. 5663 then ``length`` is returned.
5798 5664
5799 4.131 KVM_GET_SREGS2 5665 4.131 KVM_GET_SREGS2
5800 -------------------- 5666 --------------------
5801 5667
5802 :Capability: KVM_CAP_SREGS2 5668 :Capability: KVM_CAP_SREGS2
5803 :Architectures: x86 5669 :Architectures: x86
5804 :Type: vcpu ioctl 5670 :Type: vcpu ioctl
5805 :Parameters: struct kvm_sregs2 (out) 5671 :Parameters: struct kvm_sregs2 (out)
5806 :Returns: 0 on success, -1 on error 5672 :Returns: 0 on success, -1 on error
5807 5673
5808 Reads special registers from the vcpu. 5674 Reads special registers from the vcpu.
5809 This ioctl (when supported) replaces the KVM_ 5675 This ioctl (when supported) replaces the KVM_GET_SREGS.
5810 5676
5811 :: 5677 ::
5812 5678
5813 struct kvm_sregs2 { 5679 struct kvm_sregs2 {
5814 /* out (KVM_GET_SREGS2) / in 5680 /* out (KVM_GET_SREGS2) / in (KVM_SET_SREGS2) */
5815 struct kvm_segment cs, ds, es 5681 struct kvm_segment cs, ds, es, fs, gs, ss;
5816 struct kvm_segment tr, ldt; 5682 struct kvm_segment tr, ldt;
5817 struct kvm_dtable gdt, idt; 5683 struct kvm_dtable gdt, idt;
5818 __u64 cr0, cr2, cr3, cr4, cr8 5684 __u64 cr0, cr2, cr3, cr4, cr8;
5819 __u64 efer; 5685 __u64 efer;
5820 __u64 apic_base; 5686 __u64 apic_base;
5821 __u64 flags; 5687 __u64 flags;
5822 __u64 pdptrs[4]; 5688 __u64 pdptrs[4];
5823 }; 5689 };
5824 5690
5825 flags values for ``kvm_sregs2``: 5691 flags values for ``kvm_sregs2``:
5826 5692
5827 ``KVM_SREGS2_FLAGS_PDPTRS_VALID`` 5693 ``KVM_SREGS2_FLAGS_PDPTRS_VALID``
5828 5694
5829 Indicates that the struct contains valid PD !! 5695 Indicates thats the struct contain valid PDPTR values.
5830 5696
5831 5697
5832 4.132 KVM_SET_SREGS2 5698 4.132 KVM_SET_SREGS2
5833 -------------------- 5699 --------------------
5834 5700
5835 :Capability: KVM_CAP_SREGS2 5701 :Capability: KVM_CAP_SREGS2
5836 :Architectures: x86 5702 :Architectures: x86
5837 :Type: vcpu ioctl 5703 :Type: vcpu ioctl
5838 :Parameters: struct kvm_sregs2 (in) 5704 :Parameters: struct kvm_sregs2 (in)
5839 :Returns: 0 on success, -1 on error 5705 :Returns: 0 on success, -1 on error
5840 5706
5841 Writes special registers into the vcpu. 5707 Writes special registers into the vcpu.
5842 See KVM_GET_SREGS2 for the data structures. 5708 See KVM_GET_SREGS2 for the data structures.
5843 This ioctl (when supported) replaces the KVM_ 5709 This ioctl (when supported) replaces the KVM_SET_SREGS.
5844 5710
5845 4.133 KVM_GET_STATS_FD 5711 4.133 KVM_GET_STATS_FD
5846 ---------------------- 5712 ----------------------
5847 5713
5848 :Capability: KVM_CAP_STATS_BINARY_FD 5714 :Capability: KVM_CAP_STATS_BINARY_FD
5849 :Architectures: all 5715 :Architectures: all
5850 :Type: vm ioctl, vcpu ioctl 5716 :Type: vm ioctl, vcpu ioctl
5851 :Parameters: none 5717 :Parameters: none
5852 :Returns: statistics file descriptor on succe 5718 :Returns: statistics file descriptor on success, < 0 on error
5853 5719
5854 Errors: 5720 Errors:
5855 5721
5856 ====== ================================ 5722 ====== ======================================================
5857 ENOMEM if the fd could not be created d 5723 ENOMEM if the fd could not be created due to lack of memory
5858 EMFILE if the number of opened files ex 5724 EMFILE if the number of opened files exceeds the limit
5859 ====== ================================ 5725 ====== ======================================================
5860 5726
5861 The returned file descriptor can be used to r 5727 The returned file descriptor can be used to read VM/vCPU statistics data in
5862 binary format. The data in the file descripto 5728 binary format. The data in the file descriptor consists of four blocks
5863 organized as follows: 5729 organized as follows:
5864 5730
5865 +-------------+ 5731 +-------------+
5866 | Header | 5732 | Header |
5867 +-------------+ 5733 +-------------+
5868 | id string | 5734 | id string |
5869 +-------------+ 5735 +-------------+
5870 | Descriptors | 5736 | Descriptors |
5871 +-------------+ 5737 +-------------+
5872 | Stats Data | 5738 | Stats Data |
5873 +-------------+ 5739 +-------------+
5874 5740
5875 Apart from the header starting at offset 0, p 5741 Apart from the header starting at offset 0, please be aware that it is
5876 not guaranteed that the four blocks are adjac 5742 not guaranteed that the four blocks are adjacent or in the above order;
5877 the offsets of the id, descriptors and data b 5743 the offsets of the id, descriptors and data blocks are found in the
5878 header. However, all four blocks are aligned 5744 header. However, all four blocks are aligned to 64 bit offsets in the
5879 file and they do not overlap. 5745 file and they do not overlap.
5880 5746
5881 All blocks except the data block are immutabl 5747 All blocks except the data block are immutable. Userspace can read them
5882 only one time after retrieving the file descr 5748 only one time after retrieving the file descriptor, and then use ``pread`` or
5883 ``lseek`` to read the statistics repeatedly. 5749 ``lseek`` to read the statistics repeatedly.
5884 5750
5885 All data is in system endianness. 5751 All data is in system endianness.
5886 5752
5887 The format of the header is as follows:: 5753 The format of the header is as follows::
5888 5754
5889 struct kvm_stats_header { 5755 struct kvm_stats_header {
5890 __u32 flags; 5756 __u32 flags;
5891 __u32 name_size; 5757 __u32 name_size;
5892 __u32 num_desc; 5758 __u32 num_desc;
5893 __u32 id_offset; 5759 __u32 id_offset;
5894 __u32 desc_offset; 5760 __u32 desc_offset;
5895 __u32 data_offset; 5761 __u32 data_offset;
5896 }; 5762 };
5897 5763
5898 The ``flags`` field is not used at the moment 5764 The ``flags`` field is not used at the moment. It is always read as 0.
5899 5765
5900 The ``name_size`` field is the size (in byte) 5766 The ``name_size`` field is the size (in byte) of the statistics name string
5901 (including trailing '\0') which is contained 5767 (including trailing '\0') which is contained in the "id string" block and
5902 appended at the end of every descriptor. 5768 appended at the end of every descriptor.
5903 5769
5904 The ``num_desc`` field is the number of descr 5770 The ``num_desc`` field is the number of descriptors that are included in the
5905 descriptor block. (The actual number of valu 5771 descriptor block. (The actual number of values in the data block may be
5906 larger, since each descriptor may comprise mo 5772 larger, since each descriptor may comprise more than one value).
5907 5773
5908 The ``id_offset`` field is the offset of the 5774 The ``id_offset`` field is the offset of the id string from the start of the
5909 file indicated by the file descriptor. It is 5775 file indicated by the file descriptor. It is a multiple of 8.
5910 5776
5911 The ``desc_offset`` field is the offset of th 5777 The ``desc_offset`` field is the offset of the Descriptors block from the start
5912 of the file indicated by the file descriptor. 5778 of the file indicated by the file descriptor. It is a multiple of 8.
5913 5779
5914 The ``data_offset`` field is the offset of th 5780 The ``data_offset`` field is the offset of the Stats Data block from the start
5915 of the file indicated by the file descriptor. 5781 of the file indicated by the file descriptor. It is a multiple of 8.
5916 5782
5917 The id string block contains a string which i 5783 The id string block contains a string which identifies the file descriptor on
5918 which KVM_GET_STATS_FD was invoked. The size 5784 which KVM_GET_STATS_FD was invoked. The size of the block, including the
5919 trailing ``'\0'``, is indicated by the ``name 5785 trailing ``'\0'``, is indicated by the ``name_size`` field in the header.
5920 5786
5921 The descriptors block is only needed to be re 5787 The descriptors block is only needed to be read once for the lifetime of the
5922 file descriptor contains a sequence of ``stru 5788 file descriptor contains a sequence of ``struct kvm_stats_desc``, each followed
5923 by a string of size ``name_size``. 5789 by a string of size ``name_size``.
5924 :: 5790 ::
5925 5791
5926 #define KVM_STATS_TYPE_SHIFT 5792 #define KVM_STATS_TYPE_SHIFT 0
5927 #define KVM_STATS_TYPE_MASK 5793 #define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT)
5928 #define KVM_STATS_TYPE_CUMULATIVE 5794 #define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT)
5929 #define KVM_STATS_TYPE_INSTANT 5795 #define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT)
5930 #define KVM_STATS_TYPE_PEAK 5796 #define KVM_STATS_TYPE_PEAK (0x2 << KVM_STATS_TYPE_SHIFT)
5931 #define KVM_STATS_TYPE_LINEAR_HIST 5797 #define KVM_STATS_TYPE_LINEAR_HIST (0x3 << KVM_STATS_TYPE_SHIFT)
5932 #define KVM_STATS_TYPE_LOG_HIST 5798 #define KVM_STATS_TYPE_LOG_HIST (0x4 << KVM_STATS_TYPE_SHIFT)
5933 #define KVM_STATS_TYPE_MAX 5799 #define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_LOG_HIST
5934 5800
5935 #define KVM_STATS_UNIT_SHIFT 5801 #define KVM_STATS_UNIT_SHIFT 4
5936 #define KVM_STATS_UNIT_MASK 5802 #define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT)
5937 #define KVM_STATS_UNIT_NONE 5803 #define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT)
5938 #define KVM_STATS_UNIT_BYTES 5804 #define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT)
5939 #define KVM_STATS_UNIT_SECONDS 5805 #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT)
5940 #define KVM_STATS_UNIT_CYCLES 5806 #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT)
5941 #define KVM_STATS_UNIT_BOOLEAN 5807 #define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT)
5942 #define KVM_STATS_UNIT_MAX 5808 #define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_BOOLEAN
5943 5809
5944 #define KVM_STATS_BASE_SHIFT 5810 #define KVM_STATS_BASE_SHIFT 8
5945 #define KVM_STATS_BASE_MASK 5811 #define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT)
5946 #define KVM_STATS_BASE_POW10 5812 #define KVM_STATS_BASE_POW10 (0x0 << KVM_STATS_BASE_SHIFT)
5947 #define KVM_STATS_BASE_POW2 5813 #define KVM_STATS_BASE_POW2 (0x1 << KVM_STATS_BASE_SHIFT)
5948 #define KVM_STATS_BASE_MAX 5814 #define KVM_STATS_BASE_MAX KVM_STATS_BASE_POW2
5949 5815
5950 struct kvm_stats_desc { 5816 struct kvm_stats_desc {
5951 __u32 flags; 5817 __u32 flags;
5952 __s16 exponent; 5818 __s16 exponent;
5953 __u16 size; 5819 __u16 size;
5954 __u32 offset; 5820 __u32 offset;
5955 __u32 bucket_size; 5821 __u32 bucket_size;
5956 char name[]; 5822 char name[];
5957 }; 5823 };
5958 5824
5959 The ``flags`` field contains the type and uni 5825 The ``flags`` field contains the type and unit of the statistics data described
5960 by this descriptor. Its endianness is CPU nat 5826 by this descriptor. Its endianness is CPU native.
5961 The following flags are supported: 5827 The following flags are supported:
5962 5828
5963 Bits 0-3 of ``flags`` encode the type: 5829 Bits 0-3 of ``flags`` encode the type:
5964 5830
5965 * ``KVM_STATS_TYPE_CUMULATIVE`` 5831 * ``KVM_STATS_TYPE_CUMULATIVE``
5966 The statistics reports a cumulative count 5832 The statistics reports a cumulative count. The value of data can only be increased.
5967 Most of the counters used in KVM are of t 5833 Most of the counters used in KVM are of this type.
5968 The corresponding ``size`` field for this 5834 The corresponding ``size`` field for this type is always 1.
5969 All cumulative statistics data are read/w 5835 All cumulative statistics data are read/write.
5970 * ``KVM_STATS_TYPE_INSTANT`` 5836 * ``KVM_STATS_TYPE_INSTANT``
5971 The statistics reports an instantaneous v 5837 The statistics reports an instantaneous value. Its value can be increased or
5972 decreased. This type is usually used as a 5838 decreased. This type is usually used as a measurement of some resources,
5973 like the number of dirty pages, the numbe 5839 like the number of dirty pages, the number of large pages, etc.
5974 All instant statistics are read only. 5840 All instant statistics are read only.
5975 The corresponding ``size`` field for this 5841 The corresponding ``size`` field for this type is always 1.
5976 * ``KVM_STATS_TYPE_PEAK`` 5842 * ``KVM_STATS_TYPE_PEAK``
5977 The statistics data reports a peak value, 5843 The statistics data reports a peak value, for example the maximum number
5978 of items in a hash table bucket, the long 5844 of items in a hash table bucket, the longest time waited and so on.
5979 The value of data can only be increased. 5845 The value of data can only be increased.
5980 The corresponding ``size`` field for this 5846 The corresponding ``size`` field for this type is always 1.
5981 * ``KVM_STATS_TYPE_LINEAR_HIST`` 5847 * ``KVM_STATS_TYPE_LINEAR_HIST``
5982 The statistic is reported as a linear his 5848 The statistic is reported as a linear histogram. The number of
5983 buckets is specified by the ``size`` fiel 5849 buckets is specified by the ``size`` field. The size of buckets is specified
5984 by the ``hist_param`` field. The range of 5850 by the ``hist_param`` field. The range of the Nth bucket (1 <= N < ``size``)
5985 is [``hist_param``*(N-1), ``hist_param``* 5851 is [``hist_param``*(N-1), ``hist_param``*N), while the range of the last
5986 bucket is [``hist_param``*(``size``-1), + 5852 bucket is [``hist_param``*(``size``-1), +INF). (+INF means positive infinity
5987 value.) 5853 value.)
5988 * ``KVM_STATS_TYPE_LOG_HIST`` 5854 * ``KVM_STATS_TYPE_LOG_HIST``
5989 The statistic is reported as a logarithmi 5855 The statistic is reported as a logarithmic histogram. The number of
5990 buckets is specified by the ``size`` fiel 5856 buckets is specified by the ``size`` field. The range of the first bucket is
5991 [0, 1), while the range of the last bucke 5857 [0, 1), while the range of the last bucket is [pow(2, ``size``-2), +INF).
5992 Otherwise, The Nth bucket (1 < N < ``size 5858 Otherwise, The Nth bucket (1 < N < ``size``) covers
5993 [pow(2, N-2), pow(2, N-1)). 5859 [pow(2, N-2), pow(2, N-1)).
5994 5860
5995 Bits 4-7 of ``flags`` encode the unit: 5861 Bits 4-7 of ``flags`` encode the unit:
5996 5862
5997 * ``KVM_STATS_UNIT_NONE`` 5863 * ``KVM_STATS_UNIT_NONE``
5998 There is no unit for the value of statist 5864 There is no unit for the value of statistics data. This usually means that
5999 the value is a simple counter of an event 5865 the value is a simple counter of an event.
6000 * ``KVM_STATS_UNIT_BYTES`` 5866 * ``KVM_STATS_UNIT_BYTES``
6001 It indicates that the statistics data is 5867 It indicates that the statistics data is used to measure memory size, in the
6002 unit of Byte, KiByte, MiByte, GiByte, etc 5868 unit of Byte, KiByte, MiByte, GiByte, etc. The unit of the data is
6003 determined by the ``exponent`` field in t 5869 determined by the ``exponent`` field in the descriptor.
6004 * ``KVM_STATS_UNIT_SECONDS`` 5870 * ``KVM_STATS_UNIT_SECONDS``
6005 It indicates that the statistics data is 5871 It indicates that the statistics data is used to measure time or latency.
6006 * ``KVM_STATS_UNIT_CYCLES`` 5872 * ``KVM_STATS_UNIT_CYCLES``
6007 It indicates that the statistics data is 5873 It indicates that the statistics data is used to measure CPU clock cycles.
6008 * ``KVM_STATS_UNIT_BOOLEAN`` 5874 * ``KVM_STATS_UNIT_BOOLEAN``
6009 It indicates that the statistic will alwa 5875 It indicates that the statistic will always be either 0 or 1. Boolean
6010 statistics of "peak" type will never go b 5876 statistics of "peak" type will never go back from 1 to 0. Boolean
6011 statistics can be linear histograms (with 5877 statistics can be linear histograms (with two buckets) but not logarithmic
6012 histograms. 5878 histograms.
6013 5879
6014 Note that, in the case of histograms, the uni 5880 Note that, in the case of histograms, the unit applies to the bucket
6015 ranges, while the bucket value indicates how 5881 ranges, while the bucket value indicates how many samples fell in the
6016 bucket's range. 5882 bucket's range.
6017 5883
6018 Bits 8-11 of ``flags``, together with ``expon 5884 Bits 8-11 of ``flags``, together with ``exponent``, encode the scale of the
6019 unit: 5885 unit:
6020 5886
6021 * ``KVM_STATS_BASE_POW10`` 5887 * ``KVM_STATS_BASE_POW10``
6022 The scale is based on power of 10. It is 5888 The scale is based on power of 10. It is used for measurement of time and
6023 CPU clock cycles. For example, an expone 5889 CPU clock cycles. For example, an exponent of -9 can be used with
6024 ``KVM_STATS_UNIT_SECONDS`` to express tha 5890 ``KVM_STATS_UNIT_SECONDS`` to express that the unit is nanoseconds.
6025 * ``KVM_STATS_BASE_POW2`` 5891 * ``KVM_STATS_BASE_POW2``
6026 The scale is based on power of 2. It is u 5892 The scale is based on power of 2. It is used for measurement of memory size.
6027 For example, an exponent of 20 can be use 5893 For example, an exponent of 20 can be used with ``KVM_STATS_UNIT_BYTES`` to
6028 express that the unit is MiB. 5894 express that the unit is MiB.
6029 5895
6030 The ``size`` field is the number of values of 5896 The ``size`` field is the number of values of this statistics data. Its
6031 value is usually 1 for most of simple statist 5897 value is usually 1 for most of simple statistics. 1 means it contains an
6032 unsigned 64bit data. 5898 unsigned 64bit data.
6033 5899
6034 The ``offset`` field is the offset from the s 5900 The ``offset`` field is the offset from the start of Data Block to the start of
6035 the corresponding statistics data. 5901 the corresponding statistics data.
6036 5902
6037 The ``bucket_size`` field is used as a parame 5903 The ``bucket_size`` field is used as a parameter for histogram statistics data.
6038 It is only used by linear histogram statistic 5904 It is only used by linear histogram statistics data, specifying the size of a
6039 bucket in the unit expressed by bits 4-11 of 5905 bucket in the unit expressed by bits 4-11 of ``flags`` together with ``exponent``.
6040 5906
6041 The ``name`` field is the name string of the 5907 The ``name`` field is the name string of the statistics data. The name string
6042 starts at the end of ``struct kvm_stats_desc` 5908 starts at the end of ``struct kvm_stats_desc``. The maximum length including
6043 the trailing ``'\0'``, is indicated by ``name 5909 the trailing ``'\0'``, is indicated by ``name_size`` in the header.
6044 5910
6045 The Stats Data block contains an array of 64- 5911 The Stats Data block contains an array of 64-bit values in the same order
6046 as the descriptors in Descriptors block. 5912 as the descriptors in Descriptors block.
6047 5913
6048 4.134 KVM_GET_XSAVE2 5914 4.134 KVM_GET_XSAVE2
6049 -------------------- 5915 --------------------
6050 5916
6051 :Capability: KVM_CAP_XSAVE2 5917 :Capability: KVM_CAP_XSAVE2
6052 :Architectures: x86 5918 :Architectures: x86
6053 :Type: vcpu ioctl 5919 :Type: vcpu ioctl
6054 :Parameters: struct kvm_xsave (out) 5920 :Parameters: struct kvm_xsave (out)
6055 :Returns: 0 on success, -1 on error 5921 :Returns: 0 on success, -1 on error
6056 5922
6057 5923
6058 :: 5924 ::
6059 5925
6060 struct kvm_xsave { 5926 struct kvm_xsave {
6061 __u32 region[1024]; 5927 __u32 region[1024];
6062 __u32 extra[0]; 5928 __u32 extra[0];
6063 }; 5929 };
6064 5930
6065 This ioctl would copy current vcpu's xsave st 5931 This ioctl would copy current vcpu's xsave struct to the userspace. It
6066 copies as many bytes as are returned by KVM_C 5932 copies as many bytes as are returned by KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2)
6067 when invoked on the vm file descriptor. The s 5933 when invoked on the vm file descriptor. The size value returned by
6068 KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) will alwa 5934 KVM_CHECK_EXTENSION(KVM_CAP_XSAVE2) will always be at least 4096.
6069 Currently, it is only greater than 4096 if a 5935 Currently, it is only greater than 4096 if a dynamic feature has been
6070 enabled with ``arch_prctl()``, but this may c 5936 enabled with ``arch_prctl()``, but this may change in the future.
6071 5937
6072 The offsets of the state save areas in struct 5938 The offsets of the state save areas in struct kvm_xsave follow the contents
6073 of CPUID leaf 0xD on the host. 5939 of CPUID leaf 0xD on the host.
6074 5940
6075 4.135 KVM_XEN_HVM_EVTCHN_SEND 5941 4.135 KVM_XEN_HVM_EVTCHN_SEND
6076 ----------------------------- 5942 -----------------------------
6077 5943
6078 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CO 5944 :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND
6079 :Architectures: x86 5945 :Architectures: x86
6080 :Type: vm ioctl 5946 :Type: vm ioctl
6081 :Parameters: struct kvm_irq_routing_xen_evtch 5947 :Parameters: struct kvm_irq_routing_xen_evtchn
6082 :Returns: 0 on success, < 0 on error 5948 :Returns: 0 on success, < 0 on error
6083 5949
6084 5950
6085 :: 5951 ::
6086 5952
6087 struct kvm_irq_routing_xen_evtchn { 5953 struct kvm_irq_routing_xen_evtchn {
6088 __u32 port; 5954 __u32 port;
6089 __u32 vcpu; 5955 __u32 vcpu;
6090 __u32 priority; 5956 __u32 priority;
6091 }; 5957 };
6092 5958
6093 This ioctl injects an event channel interrupt 5959 This ioctl injects an event channel interrupt directly to the guest vCPU.
6094 5960
6095 4.136 KVM_S390_PV_CPU_COMMAND 5961 4.136 KVM_S390_PV_CPU_COMMAND
6096 ----------------------------- 5962 -----------------------------
6097 5963
6098 :Capability: KVM_CAP_S390_PROTECTED_DUMP 5964 :Capability: KVM_CAP_S390_PROTECTED_DUMP
6099 :Architectures: s390 5965 :Architectures: s390
6100 :Type: vcpu ioctl 5966 :Type: vcpu ioctl
6101 :Parameters: none 5967 :Parameters: none
6102 :Returns: 0 on success, < 0 on error 5968 :Returns: 0 on success, < 0 on error
6103 5969
6104 This ioctl closely mirrors `KVM_S390_PV_COMMA 5970 This ioctl closely mirrors `KVM_S390_PV_COMMAND` but handles requests
6105 for vcpus. It re-uses the kvm_s390_pv_dmp str 5971 for vcpus. It re-uses the kvm_s390_pv_dmp struct and hence also shares
6106 the command ids. 5972 the command ids.
6107 5973
6108 **command:** 5974 **command:**
6109 5975
6110 KVM_PV_DUMP 5976 KVM_PV_DUMP
6111 Presents an API that provides calls which f 5977 Presents an API that provides calls which facilitate dumping a vcpu
6112 of a protected VM. 5978 of a protected VM.
6113 5979
6114 **subcommand:** 5980 **subcommand:**
6115 5981
6116 KVM_PV_DUMP_CPU 5982 KVM_PV_DUMP_CPU
6117 Provides encrypted dump data like register 5983 Provides encrypted dump data like register values.
6118 The length of the returned data is provided 5984 The length of the returned data is provided by uv_info.guest_cpu_stor_len.
6119 5985
6120 4.137 KVM_S390_ZPCI_OP 5986 4.137 KVM_S390_ZPCI_OP
6121 ---------------------- 5987 ----------------------
6122 5988
6123 :Capability: KVM_CAP_S390_ZPCI_OP 5989 :Capability: KVM_CAP_S390_ZPCI_OP
6124 :Architectures: s390 5990 :Architectures: s390
6125 :Type: vm ioctl 5991 :Type: vm ioctl
6126 :Parameters: struct kvm_s390_zpci_op (in) 5992 :Parameters: struct kvm_s390_zpci_op (in)
6127 :Returns: 0 on success, <0 on error 5993 :Returns: 0 on success, <0 on error
6128 5994
6129 Used to manage hardware-assisted virtualizati 5995 Used to manage hardware-assisted virtualization features for zPCI devices.
6130 5996
6131 Parameters are specified via the following st 5997 Parameters are specified via the following structure::
6132 5998
6133 struct kvm_s390_zpci_op { 5999 struct kvm_s390_zpci_op {
6134 /* in */ 6000 /* in */
6135 __u32 fh; /* target dev 6001 __u32 fh; /* target device */
6136 __u8 op; /* operation 6002 __u8 op; /* operation to perform */
6137 __u8 pad[3]; 6003 __u8 pad[3];
6138 union { 6004 union {
6139 /* for KVM_S390_ZPCIOP_REG_AE 6005 /* for KVM_S390_ZPCIOP_REG_AEN */
6140 struct { 6006 struct {
6141 __u64 ibv; /* Gu 6007 __u64 ibv; /* Guest addr of interrupt bit vector */
6142 __u64 sb; /* Gu 6008 __u64 sb; /* Guest addr of summary bit */
6143 __u32 flags; 6009 __u32 flags;
6144 __u32 noi; /* Nu 6010 __u32 noi; /* Number of interrupts */
6145 __u8 isc; /* Gu 6011 __u8 isc; /* Guest interrupt subclass */
6146 __u8 sbo; /* Of 6012 __u8 sbo; /* Offset of guest summary bit vector */
6147 __u16 pad; 6013 __u16 pad;
6148 } reg_aen; 6014 } reg_aen;
6149 __u64 reserved[8]; 6015 __u64 reserved[8];
6150 } u; 6016 } u;
6151 }; 6017 };
6152 6018
6153 The type of operation is specified in the "op 6019 The type of operation is specified in the "op" field.
6154 KVM_S390_ZPCIOP_REG_AEN is used to register t 6020 KVM_S390_ZPCIOP_REG_AEN is used to register the VM for adapter event
6155 notification interpretation, which will allow 6021 notification interpretation, which will allow firmware delivery of adapter
6156 events directly to the vm, with KVM providing 6022 events directly to the vm, with KVM providing a backup delivery mechanism;
6157 KVM_S390_ZPCIOP_DEREG_AEN is used to subseque 6023 KVM_S390_ZPCIOP_DEREG_AEN is used to subsequently disable interpretation of
6158 adapter event notifications. 6024 adapter event notifications.
6159 6025
6160 The target zPCI function must also be specifi 6026 The target zPCI function must also be specified via the "fh" field. For the
6161 KVM_S390_ZPCIOP_REG_AEN operation, additional 6027 KVM_S390_ZPCIOP_REG_AEN operation, additional information to establish firmware
6162 delivery must be provided via the "reg_aen" s 6028 delivery must be provided via the "reg_aen" struct.
6163 6029
6164 The "pad" and "reserved" fields may be used f 6030 The "pad" and "reserved" fields may be used for future extensions and should be
6165 set to 0s by userspace. 6031 set to 0s by userspace.
6166 6032
6167 4.138 KVM_ARM_SET_COUNTER_OFFSET 6033 4.138 KVM_ARM_SET_COUNTER_OFFSET
6168 -------------------------------- 6034 --------------------------------
6169 6035
6170 :Capability: KVM_CAP_COUNTER_OFFSET 6036 :Capability: KVM_CAP_COUNTER_OFFSET
6171 :Architectures: arm64 6037 :Architectures: arm64
6172 :Type: vm ioctl 6038 :Type: vm ioctl
6173 :Parameters: struct kvm_arm_counter_offset (i 6039 :Parameters: struct kvm_arm_counter_offset (in)
6174 :Returns: 0 on success, < 0 on error 6040 :Returns: 0 on success, < 0 on error
6175 6041
6176 This capability indicates that userspace is a 6042 This capability indicates that userspace is able to apply a single VM-wide
6177 offset to both the virtual and physical count 6043 offset to both the virtual and physical counters as viewed by the guest
6178 using the KVM_ARM_SET_CNT_OFFSET ioctl and th 6044 using the KVM_ARM_SET_CNT_OFFSET ioctl and the following data structure:
6179 6045
6180 :: 6046 ::
6181 6047
6182 struct kvm_arm_counter_offset { 6048 struct kvm_arm_counter_offset {
6183 __u64 counter_offset; 6049 __u64 counter_offset;
6184 __u64 reserved; 6050 __u64 reserved;
6185 }; 6051 };
6186 6052
6187 The offset describes a number of counter cycl 6053 The offset describes a number of counter cycles that are subtracted from
6188 both virtual and physical counter views (simi 6054 both virtual and physical counter views (similar to the effects of the
6189 CNTVOFF_EL2 and CNTPOFF_EL2 system registers, 6055 CNTVOFF_EL2 and CNTPOFF_EL2 system registers, but only global). The offset
6190 always applies to all vcpus (already created 6056 always applies to all vcpus (already created or created after this ioctl)
6191 for this VM. 6057 for this VM.
6192 6058
6193 It is userspace's responsibility to compute t 6059 It is userspace's responsibility to compute the offset based, for example,
6194 on previous values of the guest counters. 6060 on previous values of the guest counters.
6195 6061
6196 Any value other than 0 for the "reserved" fie 6062 Any value other than 0 for the "reserved" field may result in an error
6197 (-EINVAL) being returned. This ioctl can also 6063 (-EINVAL) being returned. This ioctl can also return -EBUSY if any vcpu
6198 ioctl is issued concurrently. 6064 ioctl is issued concurrently.
6199 6065
6200 Note that using this ioctl results in KVM ign 6066 Note that using this ioctl results in KVM ignoring subsequent userspace
6201 writes to the CNTVCT_EL0 and CNTPCT_EL0 regis 6067 writes to the CNTVCT_EL0 and CNTPCT_EL0 registers using the SET_ONE_REG
6202 interface. No error will be returned, but the 6068 interface. No error will be returned, but the resulting offset will not be
6203 applied. 6069 applied.
6204 6070
6205 .. _KVM_ARM_GET_REG_WRITABLE_MASKS: <<
6206 <<
6207 4.139 KVM_ARM_GET_REG_WRITABLE_MASKS <<
6208 ------------------------------------------- <<
6209 <<
6210 :Capability: KVM_CAP_ARM_SUPPORTED_REG_MASK_R <<
6211 :Architectures: arm64 <<
6212 :Type: vm ioctl <<
6213 :Parameters: struct reg_mask_range (in/out) <<
6214 :Returns: 0 on success, < 0 on error <<
6215 <<
6216 <<
6217 :: <<
6218 <<
6219 #define KVM_ARM_FEATURE_ID_RANGE <<
6220 #define KVM_ARM_FEATURE_ID_RANGE_SIZE <<
6221 <<
6222 struct reg_mask_range { <<
6223 __u64 addr; /* Po <<
6224 __u32 range; /* Re <<
6225 __u32 reserved[13]; <<
6226 }; <<
6227 <<
6228 This ioctl copies the writable masks for a se <<
6229 userspace. <<
6230 <<
6231 The ``addr`` field is a pointer to the destin <<
6232 the writable masks. <<
6233 <<
6234 The ``range`` field indicates the requested r <<
6235 ``KVM_CHECK_EXTENSION`` for the ``KVM_CAP_ARM <<
6236 capability returns the supported ranges, expr <<
6237 flag's bit index represents a possible value <<
6238 All other values are reserved for future use <<
6239 <<
6240 The ``reserved[13]`` array is reserved for fu <<
6241 KVM may return an error. <<
6242 <<
6243 KVM_ARM_FEATURE_ID_RANGE (0) <<
6244 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ <<
6245 <<
6246 The Feature ID range is defined as the AArch6 <<
6247 op0==3, op1=={0, 1, 3}, CRn==0, CRm=={0-7}, o <<
6248 <<
6249 The mask returned array pointed to by ``addr` <<
6250 ``ARM64_FEATURE_ID_RANGE_IDX(op0, op1, crn, c <<
6251 to know what fields can be changed for the sy <<
6252 ``op0, op1, crn, crm, op2``. KVM rejects ID r <<
6253 superset of the features supported by the sys <<
6254 <<
6255 4.140 KVM_SET_USER_MEMORY_REGION2 <<
6256 --------------------------------- <<
6257 <<
6258 :Capability: KVM_CAP_USER_MEMORY2 <<
6259 :Architectures: all <<
6260 :Type: vm ioctl <<
6261 :Parameters: struct kvm_userspace_memory_regi <<
6262 :Returns: 0 on success, -1 on error <<
6263 <<
6264 KVM_SET_USER_MEMORY_REGION2 is an extension t <<
6265 allows mapping guest_memfd memory into a gues <<
6266 KVM_SET_USER_MEMORY_REGION identically. User <<
6267 in flags to have KVM bind the memory region t <<
6268 [guest_memfd_offset, guest_memfd_offset + mem <<
6269 must point at a file created via KVM_CREATE_G <<
6270 the target range must not be bound to any oth <<
6271 bounds checks apply (use common sense). <<
6272 <<
6273 :: <<
6274 <<
6275 struct kvm_userspace_memory_region2 { <<
6276 __u32 slot; <<
6277 __u32 flags; <<
6278 __u64 guest_phys_addr; <<
6279 __u64 memory_size; /* bytes */ <<
6280 __u64 userspace_addr; /* start of the <<
6281 __u64 guest_memfd_offset; <<
6282 __u32 guest_memfd; <<
6283 __u32 pad1; <<
6284 __u64 pad2[14]; <<
6285 }; <<
6286 <<
6287 A KVM_MEM_GUEST_MEMFD region _must_ have a va <<
6288 userspace_addr (shared memory). However, "va <<
6289 means that the address itself must be a legal <<
6290 mapping for userspace_addr is not required to <<
6291 KVM_SET_USER_MEMORY_REGION2, e.g. shared memo <<
6292 on-demand. <<
6293 <<
6294 When mapping a gfn into the guest, KVM select <<
6295 userspace_addr vs. guest_memfd, based on the <<
6296 state. At VM creation time, all memory is sh <<
6297 is '0' for all gfns. Userspace can control w <<
6298 toggling KVM_MEMORY_ATTRIBUTE_PRIVATE via KVM <<
6299 <<
6300 S390: <<
6301 ^^^^^ <<
6302 <<
6303 Returns -EINVAL if the VM has the KVM_VM_S390 <<
6304 Returns -EINVAL if called on a protected VM. <<
6305 <<
6306 4.141 KVM_SET_MEMORY_ATTRIBUTES <<
6307 ------------------------------- <<
6308 <<
6309 :Capability: KVM_CAP_MEMORY_ATTRIBUTES <<
6310 :Architectures: x86 <<
6311 :Type: vm ioctl <<
6312 :Parameters: struct kvm_memory_attributes (in <<
6313 :Returns: 0 on success, <0 on error <<
6314 <<
6315 KVM_SET_MEMORY_ATTRIBUTES allows userspace to <<
6316 of guest physical memory. <<
6317 <<
6318 :: <<
6319 <<
6320 struct kvm_memory_attributes { <<
6321 __u64 address; <<
6322 __u64 size; <<
6323 __u64 attributes; <<
6324 __u64 flags; <<
6325 }; <<
6326 <<
6327 #define KVM_MEMORY_ATTRIBUTE_PRIVATE <<
6328 <<
6329 The address and size must be page aligned. T <<
6330 retrieved via ioctl(KVM_CHECK_EXTENSION) on K <<
6331 executed on a VM, KVM_CAP_MEMORY_ATTRIBUTES p <<
6332 supported by that VM. If executed at system <<
6333 returns all attributes supported by KVM. The <<
6334 time is KVM_MEMORY_ATTRIBUTE_PRIVATE, which m <<
6335 guest private memory. <<
6336 <<
6337 Note, there is no "get" API. Userspace is re <<
6338 the state of a gfn/page as needed. <<
6339 <<
6340 The "flags" field is reserved for future exte <<
6341 <<
6342 4.142 KVM_CREATE_GUEST_MEMFD <<
6343 ---------------------------- <<
6344 <<
6345 :Capability: KVM_CAP_GUEST_MEMFD <<
6346 :Architectures: none <<
6347 :Type: vm ioctl <<
6348 :Parameters: struct kvm_create_guest_memfd(in <<
6349 :Returns: A file descriptor on success, <0 on <<
6350 <<
6351 KVM_CREATE_GUEST_MEMFD creates an anonymous f <<
6352 that refers to it. guest_memfd files are rou <<
6353 via memfd_create(), e.g. guest_memfd files li <<
6354 and are automatically released when the last <<
6355 "regular" memfd_create() files, guest_memfd f <<
6356 virtual machine (see below), cannot be mapped <<
6357 and cannot be resized (guest_memfd files do <<
6358 <<
6359 :: <<
6360 <<
6361 struct kvm_create_guest_memfd { <<
6362 __u64 size; <<
6363 __u64 flags; <<
6364 __u64 reserved[6]; <<
6365 }; <<
6366 <<
6367 Conceptually, the inode backing a guest_memfd <<
6368 i.e. is coupled to the virtual machine as a t <<
6369 file itself, which is bound to a "struct kvm" <<
6370 underlying memory, e.g. effectively provides <<
6371 to host memory. This allows for use cases wh <<
6372 used to manage a single virtual machine, e.g. <<
6373 migration of a virtual machine. <<
6374 <<
6375 KVM currently only supports mapping guest_mem <<
6376 and more specifically via the guest_memfd and <<
6377 "struct kvm_userspace_memory_region2", where <<
6378 into the guest_memfd instance. For a given g <<
6379 most one mapping per page, i.e. binding multi <<
6380 guest_memfd range is not allowed (any number <<
6381 a single guest_memfd file, but the bound rang <<
6382 <<
6383 See KVM_SET_USER_MEMORY_REGION2 for additiona <<
6384 <<
6385 4.143 KVM_PRE_FAULT_MEMORY <<
6386 --------------------------- <<
6387 <<
6388 :Capability: KVM_CAP_PRE_FAULT_MEMORY <<
6389 :Architectures: none <<
6390 :Type: vcpu ioctl <<
6391 :Parameters: struct kvm_pre_fault_memory (in/ <<
6392 :Returns: 0 if at least one page is processed <<
6393 <<
6394 Errors: <<
6395 <<
6396 ========== ================================ <<
6397 EINVAL The specified `gpa` and `size` w <<
6398 page aligned, causes an overflow <<
6399 ENOENT The specified `gpa` is outside d <<
6400 EINTR An unmasked signal is pending an <<
6401 EFAULT The parameter address was invali <<
6402 EOPNOTSUPP Mapping memory for a GPA is unsu <<
6403 hypervisor, and/or for the curre <<
6404 EIO unexpected error conditions (als <<
6405 ========== ================================ <<
6406 <<
6407 :: <<
6408 <<
6409 struct kvm_pre_fault_memory { <<
6410 /* in/out */ <<
6411 __u64 gpa; <<
6412 __u64 size; <<
6413 /* in */ <<
6414 __u64 flags; <<
6415 __u64 padding[5]; <<
6416 }; <<
6417 <<
6418 KVM_PRE_FAULT_MEMORY populates KVM's stage-2 <<
6419 for the current vCPU state. KVM maps memory <<
6420 stage-2 read page fault, e.g. faults in memor <<
6421 CoW. However, KVM does not mark any newly cr <<
6422 <<
6423 In the case of confidential VM types where th <<
6424 private guest memory before the guest is 'fin <<
6425 should only be issued after completing all th <<
6426 guest into a 'finalized' state so that the ab <<
6427 ensured. <<
6428 <<
6429 In some cases, multiple vCPUs might share the <<
6430 case, the ioctl can be called in parallel. <<
6431 <<
6432 When the ioctl returns, the input values are <<
6433 remaining range. If `size` > 0 on return, th <<
6434 the ioctl again with the same `struct kvm_map <<
6435 <<
6436 Shadow page tables cannot support this ioctl <<
6437 are indexed by virtual address or nested gues <<
6438 Calling this ioctl when the guest is using sh <<
6439 example because it is running a nested guest <<
6440 will fail with `EOPNOTSUPP` even if `KVM_CHEC <<
6441 the capability to be present. <<
6442 <<
6443 `flags` must currently be zero. <<
6444 <<
6445 <<
6446 5. The kvm_run structure 6071 5. The kvm_run structure
6447 ======================== 6072 ========================
6448 6073
6449 Application code obtains a pointer to the kvm 6074 Application code obtains a pointer to the kvm_run structure by
6450 mmap()ing a vcpu fd. From that point, applic 6075 mmap()ing a vcpu fd. From that point, application code can control
6451 execution by changing fields in kvm_run prior 6076 execution by changing fields in kvm_run prior to calling the KVM_RUN
6452 ioctl, and obtain information about the reaso 6077 ioctl, and obtain information about the reason KVM_RUN returned by
6453 looking up structure members. 6078 looking up structure members.
6454 6079
6455 :: 6080 ::
6456 6081
6457 struct kvm_run { 6082 struct kvm_run {
6458 /* in */ 6083 /* in */
6459 __u8 request_interrupt_window; 6084 __u8 request_interrupt_window;
6460 6085
6461 Request that KVM_RUN return when it becomes p 6086 Request that KVM_RUN return when it becomes possible to inject external
6462 interrupts into the guest. Useful in conjunc 6087 interrupts into the guest. Useful in conjunction with KVM_INTERRUPT.
6463 6088
6464 :: 6089 ::
6465 6090
6466 __u8 immediate_exit; 6091 __u8 immediate_exit;
6467 6092
6468 This field is polled once when KVM_RUN starts 6093 This field is polled once when KVM_RUN starts; if non-zero, KVM_RUN
6469 exits immediately, returning -EINTR. In the 6094 exits immediately, returning -EINTR. In the common scenario where a
6470 signal is used to "kick" a VCPU out of KVM_RU 6095 signal is used to "kick" a VCPU out of KVM_RUN, this field can be used
6471 to avoid usage of KVM_SET_SIGNAL_MASK, which 6096 to avoid usage of KVM_SET_SIGNAL_MASK, which has worse scalability.
6472 Rather than blocking the signal outside KVM_R 6097 Rather than blocking the signal outside KVM_RUN, userspace can set up
6473 a signal handler that sets run->immediate_exi 6098 a signal handler that sets run->immediate_exit to a non-zero value.
6474 6099
6475 This field is ignored if KVM_CAP_IMMEDIATE_EX 6100 This field is ignored if KVM_CAP_IMMEDIATE_EXIT is not available.
6476 6101
6477 :: 6102 ::
6478 6103
6479 __u8 padding1[6]; 6104 __u8 padding1[6];
6480 6105
6481 /* out */ 6106 /* out */
6482 __u32 exit_reason; 6107 __u32 exit_reason;
6483 6108
6484 When KVM_RUN has returned successfully (retur 6109 When KVM_RUN has returned successfully (return value 0), this informs
6485 application code why KVM_RUN has returned. A 6110 application code why KVM_RUN has returned. Allowable values for this
6486 field are detailed below. 6111 field are detailed below.
6487 6112
6488 :: 6113 ::
6489 6114
6490 __u8 ready_for_interrupt_injection; 6115 __u8 ready_for_interrupt_injection;
6491 6116
6492 If request_interrupt_window has been specifie 6117 If request_interrupt_window has been specified, this field indicates
6493 an interrupt can be injected now with KVM_INT 6118 an interrupt can be injected now with KVM_INTERRUPT.
6494 6119
6495 :: 6120 ::
6496 6121
6497 __u8 if_flag; 6122 __u8 if_flag;
6498 6123
6499 The value of the current interrupt flag. Onl 6124 The value of the current interrupt flag. Only valid if in-kernel
6500 local APIC is not used. 6125 local APIC is not used.
6501 6126
6502 :: 6127 ::
6503 6128
6504 __u16 flags; 6129 __u16 flags;
6505 6130
6506 More architecture-specific flags detailing st 6131 More architecture-specific flags detailing state of the VCPU that may
6507 affect the device's behavior. Current defined 6132 affect the device's behavior. Current defined flags::
6508 6133
6509 /* x86, set if the VCPU is in system manage 6134 /* x86, set if the VCPU is in system management mode */
6510 #define KVM_RUN_X86_SMM (1 << 0) !! 6135 #define KVM_RUN_X86_SMM (1 << 0)
6511 /* x86, set if bus lock detected in VM */ 6136 /* x86, set if bus lock detected in VM */
6512 #define KVM_RUN_X86_BUS_LOCK (1 << 1) !! 6137 #define KVM_RUN_BUS_LOCK (1 << 1)
6513 /* x86, set if the VCPU is executing a nest <<
6514 #define KVM_RUN_X86_GUEST_MODE (1 << 2) <<
6515 <<
6516 /* arm64, set for KVM_EXIT_DEBUG */ 6138 /* arm64, set for KVM_EXIT_DEBUG */
6517 #define KVM_DEBUG_ARCH_HSR_HIGH_VALID (1 < 6139 #define KVM_DEBUG_ARCH_HSR_HIGH_VALID (1 << 0)
6518 6140
6519 :: 6141 ::
6520 6142
6521 /* in (pre_kvm_run), out (post_kvm_ru 6143 /* in (pre_kvm_run), out (post_kvm_run) */
6522 __u64 cr8; 6144 __u64 cr8;
6523 6145
6524 The value of the cr8 register. Only valid if 6146 The value of the cr8 register. Only valid if in-kernel local APIC is
6525 not used. Both input and output. 6147 not used. Both input and output.
6526 6148
6527 :: 6149 ::
6528 6150
6529 __u64 apic_base; 6151 __u64 apic_base;
6530 6152
6531 The value of the APIC BASE msr. Only valid i 6153 The value of the APIC BASE msr. Only valid if in-kernel local
6532 APIC is not used. Both input and output. 6154 APIC is not used. Both input and output.
6533 6155
6534 :: 6156 ::
6535 6157
6536 union { 6158 union {
6537 /* KVM_EXIT_UNKNOWN */ 6159 /* KVM_EXIT_UNKNOWN */
6538 struct { 6160 struct {
6539 __u64 hardware_exit_r 6161 __u64 hardware_exit_reason;
6540 } hw; 6162 } hw;
6541 6163
6542 If exit_reason is KVM_EXIT_UNKNOWN, the vcpu 6164 If exit_reason is KVM_EXIT_UNKNOWN, the vcpu has exited due to unknown
6543 reasons. Further architecture-specific infor 6165 reasons. Further architecture-specific information is available in
6544 hardware_exit_reason. 6166 hardware_exit_reason.
6545 6167
6546 :: 6168 ::
6547 6169
6548 /* KVM_EXIT_FAIL_ENTRY */ 6170 /* KVM_EXIT_FAIL_ENTRY */
6549 struct { 6171 struct {
6550 __u64 hardware_entry_ 6172 __u64 hardware_entry_failure_reason;
6551 __u32 cpu; /* if KVM_ 6173 __u32 cpu; /* if KVM_LAST_CPU */
6552 } fail_entry; 6174 } fail_entry;
6553 6175
6554 If exit_reason is KVM_EXIT_FAIL_ENTRY, the vc 6176 If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due
6555 to unknown reasons. Further architecture-spe 6177 to unknown reasons. Further architecture-specific information is
6556 available in hardware_entry_failure_reason. 6178 available in hardware_entry_failure_reason.
6557 6179
6558 :: 6180 ::
6559 6181
6560 /* KVM_EXIT_EXCEPTION */ 6182 /* KVM_EXIT_EXCEPTION */
6561 struct { 6183 struct {
6562 __u32 exception; 6184 __u32 exception;
6563 __u32 error_code; 6185 __u32 error_code;
6564 } ex; 6186 } ex;
6565 6187
6566 Unused. 6188 Unused.
6567 6189
6568 :: 6190 ::
6569 6191
6570 /* KVM_EXIT_IO */ 6192 /* KVM_EXIT_IO */
6571 struct { 6193 struct {
6572 #define KVM_EXIT_IO_IN 0 6194 #define KVM_EXIT_IO_IN 0
6573 #define KVM_EXIT_IO_OUT 1 6195 #define KVM_EXIT_IO_OUT 1
6574 __u8 direction; 6196 __u8 direction;
6575 __u8 size; /* bytes * 6197 __u8 size; /* bytes */
6576 __u16 port; 6198 __u16 port;
6577 __u32 count; 6199 __u32 count;
6578 __u64 data_offset; /* 6200 __u64 data_offset; /* relative to kvm_run start */
6579 } io; 6201 } io;
6580 6202
6581 If exit_reason is KVM_EXIT_IO, then the vcpu 6203 If exit_reason is KVM_EXIT_IO, then the vcpu has
6582 executed a port I/O instruction which could n 6204 executed a port I/O instruction which could not be satisfied by kvm.
6583 data_offset describes where the data is locat 6205 data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
6584 where kvm expects application code to place t 6206 where kvm expects application code to place the data for the next
6585 KVM_RUN invocation (KVM_EXIT_IO_IN). Data fo 6207 KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a packed array.
6586 6208
6587 :: 6209 ::
6588 6210
6589 /* KVM_EXIT_DEBUG */ 6211 /* KVM_EXIT_DEBUG */
6590 struct { 6212 struct {
6591 struct kvm_debug_exit 6213 struct kvm_debug_exit_arch arch;
6592 } debug; 6214 } debug;
6593 6215
6594 If the exit_reason is KVM_EXIT_DEBUG, then a 6216 If the exit_reason is KVM_EXIT_DEBUG, then a vcpu is processing a debug event
6595 for which architecture specific information i 6217 for which architecture specific information is returned.
6596 6218
6597 :: 6219 ::
6598 6220
6599 /* KVM_EXIT_MMIO */ 6221 /* KVM_EXIT_MMIO */
6600 struct { 6222 struct {
6601 __u64 phys_addr; 6223 __u64 phys_addr;
6602 __u8 data[8]; 6224 __u8 data[8];
6603 __u32 len; 6225 __u32 len;
6604 __u8 is_write; 6226 __u8 is_write;
6605 } mmio; 6227 } mmio;
6606 6228
6607 If exit_reason is KVM_EXIT_MMIO, then the vcp 6229 If exit_reason is KVM_EXIT_MMIO, then the vcpu has
6608 executed a memory-mapped I/O instruction whic 6230 executed a memory-mapped I/O instruction which could not be satisfied
6609 by kvm. The 'data' member contains the writt 6231 by kvm. The 'data' member contains the written data if 'is_write' is
6610 true, and should be filled by application cod 6232 true, and should be filled by application code otherwise.
6611 6233
6612 The 'data' member contains, in its first 'len 6234 The 'data' member contains, in its first 'len' bytes, the value as it would
6613 appear if the VCPU performed a load or store 6235 appear if the VCPU performed a load or store of the appropriate width directly
6614 to the byte array. 6236 to the byte array.
6615 6237
6616 .. note:: 6238 .. note::
6617 6239
6618 For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXI 6240 For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR, KVM_EXIT_XEN,
6619 KVM_EXIT_EPR, KVM_EXIT_X86_RDMSR and KV 6241 KVM_EXIT_EPR, KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR the corresponding
6620 operations are complete (and guest stat 6242 operations are complete (and guest state is consistent) only after userspace
6621 has re-entered the kernel with KVM_RUN. 6243 has re-entered the kernel with KVM_RUN. The kernel side will first finish
6622 incomplete operations and then check fo 6244 incomplete operations and then check for pending signals.
6623 6245
6624 The pending state of the operation is n 6246 The pending state of the operation is not preserved in state which is
6625 visible to userspace, thus userspace sh 6247 visible to userspace, thus userspace should ensure that the operation is
6626 completed before performing a live migr 6248 completed before performing a live migration. Userspace can re-enter the
6627 guest with an unmasked signal pending o 6249 guest with an unmasked signal pending or with the immediate_exit field set
6628 to complete pending operations without 6250 to complete pending operations without allowing any further instructions
6629 to be executed. 6251 to be executed.
6630 6252
6631 :: 6253 ::
6632 6254
6633 /* KVM_EXIT_HYPERCALL */ 6255 /* KVM_EXIT_HYPERCALL */
6634 struct { 6256 struct {
6635 __u64 nr; 6257 __u64 nr;
6636 __u64 args[6]; 6258 __u64 args[6];
6637 __u64 ret; 6259 __u64 ret;
6638 __u64 flags; 6260 __u64 flags;
6639 } hypercall; 6261 } hypercall;
6640 6262
6641 6263
6642 It is strongly recommended that userspace use 6264 It is strongly recommended that userspace use ``KVM_EXIT_IO`` (x86) or
6643 ``KVM_EXIT_MMIO`` (all except s390) to implem 6265 ``KVM_EXIT_MMIO`` (all except s390) to implement functionality that
6644 requires a guest to interact with host usersp !! 6266 requires a guest to interact with host userpace.
6645 6267
6646 .. note:: KVM_EXIT_IO is significantly faster 6268 .. note:: KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO.
6647 6269
6648 For arm64: 6270 For arm64:
6649 ---------- 6271 ----------
6650 6272
6651 SMCCC exits can be enabled depending on the c 6273 SMCCC exits can be enabled depending on the configuration of the SMCCC
6652 filter. See the Documentation/virt/kvm/device 6274 filter. See the Documentation/virt/kvm/devices/vm.rst
6653 ``KVM_ARM_SMCCC_FILTER`` for more details. 6275 ``KVM_ARM_SMCCC_FILTER`` for more details.
6654 6276
6655 ``nr`` contains the function ID of the guest' 6277 ``nr`` contains the function ID of the guest's SMCCC call. Userspace is
6656 expected to use the ``KVM_GET_ONE_REG`` ioctl 6278 expected to use the ``KVM_GET_ONE_REG`` ioctl to retrieve the call
6657 parameters from the vCPU's GPRs. 6279 parameters from the vCPU's GPRs.
6658 6280
6659 Definition of ``flags``: 6281 Definition of ``flags``:
6660 - ``KVM_HYPERCALL_EXIT_SMC``: Indicates that 6282 - ``KVM_HYPERCALL_EXIT_SMC``: Indicates that the guest used the SMC
6661 conduit to initiate the SMCCC call. If thi 6283 conduit to initiate the SMCCC call. If this bit is 0 then the guest
6662 used the HVC conduit for the SMCCC call. 6284 used the HVC conduit for the SMCCC call.
6663 6285
6664 - ``KVM_HYPERCALL_EXIT_16BIT``: Indicates th 6286 - ``KVM_HYPERCALL_EXIT_16BIT``: Indicates that the guest used a 16bit
6665 instruction to initiate the SMCCC call. If 6287 instruction to initiate the SMCCC call. If this bit is 0 then the
6666 guest used a 32bit instruction. An AArch64 6288 guest used a 32bit instruction. An AArch64 guest always has this
6667 bit set to 0. 6289 bit set to 0.
6668 6290
6669 At the point of exit, PC points to the instru 6291 At the point of exit, PC points to the instruction immediately following
6670 the trapping instruction. 6292 the trapping instruction.
6671 6293
6672 :: 6294 ::
6673 6295
6674 /* KVM_EXIT_TPR_ACCESS */ 6296 /* KVM_EXIT_TPR_ACCESS */
6675 struct { 6297 struct {
6676 __u64 rip; 6298 __u64 rip;
6677 __u32 is_write; 6299 __u32 is_write;
6678 __u32 pad; 6300 __u32 pad;
6679 } tpr_access; 6301 } tpr_access;
6680 6302
6681 To be documented (KVM_TPR_ACCESS_REPORTING). 6303 To be documented (KVM_TPR_ACCESS_REPORTING).
6682 6304
6683 :: 6305 ::
6684 6306
6685 /* KVM_EXIT_S390_SIEIC */ 6307 /* KVM_EXIT_S390_SIEIC */
6686 struct { 6308 struct {
6687 __u8 icptcode; 6309 __u8 icptcode;
6688 __u64 mask; /* psw up 6310 __u64 mask; /* psw upper half */
6689 __u64 addr; /* psw lo 6311 __u64 addr; /* psw lower half */
6690 __u16 ipa; 6312 __u16 ipa;
6691 __u32 ipb; 6313 __u32 ipb;
6692 } s390_sieic; 6314 } s390_sieic;
6693 6315
6694 s390 specific. 6316 s390 specific.
6695 6317
6696 :: 6318 ::
6697 6319
6698 /* KVM_EXIT_S390_RESET */ 6320 /* KVM_EXIT_S390_RESET */
6699 #define KVM_S390_RESET_POR 1 6321 #define KVM_S390_RESET_POR 1
6700 #define KVM_S390_RESET_CLEAR 2 6322 #define KVM_S390_RESET_CLEAR 2
6701 #define KVM_S390_RESET_SUBSYSTEM 4 6323 #define KVM_S390_RESET_SUBSYSTEM 4
6702 #define KVM_S390_RESET_CPU_INIT 8 6324 #define KVM_S390_RESET_CPU_INIT 8
6703 #define KVM_S390_RESET_IPL 16 6325 #define KVM_S390_RESET_IPL 16
6704 __u64 s390_reset_flags; 6326 __u64 s390_reset_flags;
6705 6327
6706 s390 specific. 6328 s390 specific.
6707 6329
6708 :: 6330 ::
6709 6331
6710 /* KVM_EXIT_S390_UCONTROL */ 6332 /* KVM_EXIT_S390_UCONTROL */
6711 struct { 6333 struct {
6712 __u64 trans_exc_code; 6334 __u64 trans_exc_code;
6713 __u32 pgm_code; 6335 __u32 pgm_code;
6714 } s390_ucontrol; 6336 } s390_ucontrol;
6715 6337
6716 s390 specific. A page fault has occurred for 6338 s390 specific. A page fault has occurred for a user controlled virtual
6717 machine (KVM_VM_S390_UNCONTROL) on its host p !! 6339 machine (KVM_VM_S390_UNCONTROL) on it's host page table that cannot be
6718 resolved by the kernel. 6340 resolved by the kernel.
6719 The program code and the translation exceptio 6341 The program code and the translation exception code that were placed
6720 in the cpu's lowcore are presented here as de 6342 in the cpu's lowcore are presented here as defined by the z Architecture
6721 Principles of Operation Book in the Chapter f 6343 Principles of Operation Book in the Chapter for Dynamic Address Translation
6722 (DAT) 6344 (DAT)
6723 6345
6724 :: 6346 ::
6725 6347
6726 /* KVM_EXIT_DCR */ 6348 /* KVM_EXIT_DCR */
6727 struct { 6349 struct {
6728 __u32 dcrn; 6350 __u32 dcrn;
6729 __u32 data; 6351 __u32 data;
6730 __u8 is_write; 6352 __u8 is_write;
6731 } dcr; 6353 } dcr;
6732 6354
6733 Deprecated - was used for 440 KVM. 6355 Deprecated - was used for 440 KVM.
6734 6356
6735 :: 6357 ::
6736 6358
6737 /* KVM_EXIT_OSI */ 6359 /* KVM_EXIT_OSI */
6738 struct { 6360 struct {
6739 __u64 gprs[32]; 6361 __u64 gprs[32];
6740 } osi; 6362 } osi;
6741 6363
6742 MOL uses a special hypercall interface it cal 6364 MOL uses a special hypercall interface it calls 'OSI'. To enable it, we catch
6743 hypercalls and exit with this exit struct tha 6365 hypercalls and exit with this exit struct that contains all the guest gprs.
6744 6366
6745 If exit_reason is KVM_EXIT_OSI, then the vcpu 6367 If exit_reason is KVM_EXIT_OSI, then the vcpu has triggered such a hypercall.
6746 Userspace can now handle the hypercall and wh 6368 Userspace can now handle the hypercall and when it's done modify the gprs as
6747 necessary. Upon guest entry all guest GPRs wi 6369 necessary. Upon guest entry all guest GPRs will then be replaced by the values
6748 in this struct. 6370 in this struct.
6749 6371
6750 :: 6372 ::
6751 6373
6752 /* KVM_EXIT_PAPR_HCALL */ 6374 /* KVM_EXIT_PAPR_HCALL */
6753 struct { 6375 struct {
6754 __u64 nr; 6376 __u64 nr;
6755 __u64 ret; 6377 __u64 ret;
6756 __u64 args[9]; 6378 __u64 args[9];
6757 } papr_hcall; 6379 } papr_hcall;
6758 6380
6759 This is used on 64-bit PowerPC when emulating 6381 This is used on 64-bit PowerPC when emulating a pSeries partition,
6760 e.g. with the 'pseries' machine type in qemu. 6382 e.g. with the 'pseries' machine type in qemu. It occurs when the
6761 guest does a hypercall using the 'sc 1' instr 6383 guest does a hypercall using the 'sc 1' instruction. The 'nr' field
6762 contains the hypercall number (from the guest 6384 contains the hypercall number (from the guest R3), and 'args' contains
6763 the arguments (from the guest R4 - R12). Use 6385 the arguments (from the guest R4 - R12). Userspace should put the
6764 return code in 'ret' and any extra returned v 6386 return code in 'ret' and any extra returned values in args[].
6765 The possible hypercalls are defined in the Po 6387 The possible hypercalls are defined in the Power Architecture Platform
6766 Requirements (PAPR) document available from w 6388 Requirements (PAPR) document available from www.power.org (free
6767 developer registration required to access it) 6389 developer registration required to access it).
6768 6390
6769 :: 6391 ::
6770 6392
6771 /* KVM_EXIT_S390_TSCH */ 6393 /* KVM_EXIT_S390_TSCH */
6772 struct { 6394 struct {
6773 __u16 subchannel_id; 6395 __u16 subchannel_id;
6774 __u16 subchannel_nr; 6396 __u16 subchannel_nr;
6775 __u32 io_int_parm; 6397 __u32 io_int_parm;
6776 __u32 io_int_word; 6398 __u32 io_int_word;
6777 __u32 ipb; 6399 __u32 ipb;
6778 __u8 dequeued; 6400 __u8 dequeued;
6779 } s390_tsch; 6401 } s390_tsch;
6780 6402
6781 s390 specific. This exit occurs when KVM_CAP_ 6403 s390 specific. This exit occurs when KVM_CAP_S390_CSS_SUPPORT has been enabled
6782 and TEST SUBCHANNEL was intercepted. If deque 6404 and TEST SUBCHANNEL was intercepted. If dequeued is set, a pending I/O
6783 interrupt for the target subchannel has been 6405 interrupt for the target subchannel has been dequeued and subchannel_id,
6784 subchannel_nr, io_int_parm and io_int_word co 6406 subchannel_nr, io_int_parm and io_int_word contain the parameters for that
6785 interrupt. ipb is needed for instruction para 6407 interrupt. ipb is needed for instruction parameter decoding.
6786 6408
6787 :: 6409 ::
6788 6410
6789 /* KVM_EXIT_EPR */ 6411 /* KVM_EXIT_EPR */
6790 struct { 6412 struct {
6791 __u32 epr; 6413 __u32 epr;
6792 } epr; 6414 } epr;
6793 6415
6794 On FSL BookE PowerPC chips, the interrupt con 6416 On FSL BookE PowerPC chips, the interrupt controller has a fast patch
6795 interrupt acknowledge path to the core. When 6417 interrupt acknowledge path to the core. When the core successfully
6796 delivers an interrupt, it automatically popul 6418 delivers an interrupt, it automatically populates the EPR register with
6797 the interrupt vector number and acknowledges 6419 the interrupt vector number and acknowledges the interrupt inside
6798 the interrupt controller. 6420 the interrupt controller.
6799 6421
6800 In case the interrupt controller lives in use 6422 In case the interrupt controller lives in user space, we need to do
6801 the interrupt acknowledge cycle through it to 6423 the interrupt acknowledge cycle through it to fetch the next to be
6802 delivered interrupt vector using this exit. 6424 delivered interrupt vector using this exit.
6803 6425
6804 It gets triggered whenever both KVM_CAP_PPC_E 6426 It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an
6805 external interrupt has just been delivered in 6427 external interrupt has just been delivered into the guest. User space
6806 should put the acknowledged interrupt vector 6428 should put the acknowledged interrupt vector into the 'epr' field.
6807 6429
6808 :: 6430 ::
6809 6431
6810 /* KVM_EXIT_SYSTEM_EVENT */ 6432 /* KVM_EXIT_SYSTEM_EVENT */
6811 struct { 6433 struct {
6812 #define KVM_SYSTEM_EVENT_SHUTDOWN 1 6434 #define KVM_SYSTEM_EVENT_SHUTDOWN 1
6813 #define KVM_SYSTEM_EVENT_RESET 2 6435 #define KVM_SYSTEM_EVENT_RESET 2
6814 #define KVM_SYSTEM_EVENT_CRASH 3 6436 #define KVM_SYSTEM_EVENT_CRASH 3
6815 #define KVM_SYSTEM_EVENT_WAKEUP 4 6437 #define KVM_SYSTEM_EVENT_WAKEUP 4
6816 #define KVM_SYSTEM_EVENT_SUSPEND 5 6438 #define KVM_SYSTEM_EVENT_SUSPEND 5
6817 #define KVM_SYSTEM_EVENT_SEV_TERM 6 6439 #define KVM_SYSTEM_EVENT_SEV_TERM 6
6818 __u32 type; 6440 __u32 type;
6819 __u32 ndata; 6441 __u32 ndata;
6820 __u64 data[16]; 6442 __u64 data[16];
6821 } system_event; 6443 } system_event;
6822 6444
6823 If exit_reason is KVM_EXIT_SYSTEM_EVENT then 6445 If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered
6824 a system-level event using some architecture 6446 a system-level event using some architecture specific mechanism (hypercall
6825 or some special instruction). In case of ARM6 6447 or some special instruction). In case of ARM64, this is triggered using
6826 HVC instruction based PSCI call from the vcpu 6448 HVC instruction based PSCI call from the vcpu.
6827 6449
6828 The 'type' field describes the system-level e 6450 The 'type' field describes the system-level event type.
6829 Valid values for 'type' are: 6451 Valid values for 'type' are:
6830 6452
6831 - KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has 6453 - KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the
6832 VM. Userspace is not obliged to honour thi 6454 VM. Userspace is not obliged to honour this, and if it does honour
6833 this does not need to destroy the VM synch 6455 this does not need to destroy the VM synchronously (ie it may call
6834 KVM_RUN again before shutdown finally occu 6456 KVM_RUN again before shutdown finally occurs).
6835 - KVM_SYSTEM_EVENT_RESET -- the guest has re 6457 - KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM.
6836 As with SHUTDOWN, userspace can choose to 6458 As with SHUTDOWN, userspace can choose to ignore the request, or
6837 to schedule the reset to occur in the futu 6459 to schedule the reset to occur in the future and may call KVM_RUN again.
6838 - KVM_SYSTEM_EVENT_CRASH -- the guest crash 6460 - KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest
6839 has requested a crash condition maintenanc 6461 has requested a crash condition maintenance. Userspace can choose
6840 to ignore the request, or to gather VM mem 6462 to ignore the request, or to gather VM memory core dump and/or
6841 reset/shutdown of the VM. 6463 reset/shutdown of the VM.
6842 - KVM_SYSTEM_EVENT_SEV_TERM -- an AMD SEV gu 6464 - KVM_SYSTEM_EVENT_SEV_TERM -- an AMD SEV guest requested termination.
6843 The guest physical address of the guest's 6465 The guest physical address of the guest's GHCB is stored in `data[0]`.
6844 - KVM_SYSTEM_EVENT_WAKEUP -- the exiting vCP 6466 - KVM_SYSTEM_EVENT_WAKEUP -- the exiting vCPU is in a suspended state and
6845 KVM has recognized a wakeup event. Userspa 6467 KVM has recognized a wakeup event. Userspace may honor this event by
6846 marking the exiting vCPU as runnable, or d 6468 marking the exiting vCPU as runnable, or deny it and call KVM_RUN again.
6847 - KVM_SYSTEM_EVENT_SUSPEND -- the guest has 6469 - KVM_SYSTEM_EVENT_SUSPEND -- the guest has requested a suspension of
6848 the VM. 6470 the VM.
6849 6471
6850 If KVM_CAP_SYSTEM_EVENT_DATA is present, the 6472 If KVM_CAP_SYSTEM_EVENT_DATA is present, the 'data' field can contain
6851 architecture specific information for the sys 6473 architecture specific information for the system-level event. Only
6852 the first `ndata` items (possibly zero) of th 6474 the first `ndata` items (possibly zero) of the data array are valid.
6853 6475
6854 - for arm64, data[0] is set to KVM_SYSTEM_EV 6476 - for arm64, data[0] is set to KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 if
6855 the guest issued a SYSTEM_RESET2 call acco 6477 the guest issued a SYSTEM_RESET2 call according to v1.1 of the PSCI
6856 specification. 6478 specification.
6857 6479
6858 - for RISC-V, data[0] is set to the value of 6480 - for RISC-V, data[0] is set to the value of the second argument of the
6859 ``sbi_system_reset`` call. 6481 ``sbi_system_reset`` call.
6860 6482
6861 Previous versions of Linux defined a `flags` 6483 Previous versions of Linux defined a `flags` member in this struct. The
6862 field is now aliased to `data[0]`. Userspace 6484 field is now aliased to `data[0]`. Userspace can assume that it is only
6863 written if ndata is greater than 0. 6485 written if ndata is greater than 0.
6864 6486
6865 For arm/arm64: 6487 For arm/arm64:
6866 -------------- 6488 --------------
6867 6489
6868 KVM_SYSTEM_EVENT_SUSPEND exits are enabled wi 6490 KVM_SYSTEM_EVENT_SUSPEND exits are enabled with the
6869 KVM_CAP_ARM_SYSTEM_SUSPEND VM capability. If 6491 KVM_CAP_ARM_SYSTEM_SUSPEND VM capability. If a guest invokes the PSCI
6870 SYSTEM_SUSPEND function, KVM will exit to use 6492 SYSTEM_SUSPEND function, KVM will exit to userspace with this event
6871 type. 6493 type.
6872 6494
6873 It is the sole responsibility of userspace to 6495 It is the sole responsibility of userspace to implement the PSCI
6874 SYSTEM_SUSPEND call according to ARM DEN0022D 6496 SYSTEM_SUSPEND call according to ARM DEN0022D.b 5.19 "SYSTEM_SUSPEND".
6875 KVM does not change the vCPU's state before e 6497 KVM does not change the vCPU's state before exiting to userspace, so
6876 the call parameters are left in-place in the 6498 the call parameters are left in-place in the vCPU registers.
6877 6499
6878 Userspace is _required_ to take action for su 6500 Userspace is _required_ to take action for such an exit. It must
6879 either: 6501 either:
6880 6502
6881 - Honor the guest request to suspend the VM. 6503 - Honor the guest request to suspend the VM. Userspace can request
6882 in-kernel emulation of suspension by setti 6504 in-kernel emulation of suspension by setting the calling vCPU's
6883 state to KVM_MP_STATE_SUSPENDED. Userspace 6505 state to KVM_MP_STATE_SUSPENDED. Userspace must configure the vCPU's
6884 state according to the parameters passed t 6506 state according to the parameters passed to the PSCI function when
6885 the calling vCPU is resumed. See ARM DEN00 6507 the calling vCPU is resumed. See ARM DEN0022D.b 5.19.1 "Intended use"
6886 for details on the function parameters. 6508 for details on the function parameters.
6887 6509
6888 - Deny the guest request to suspend the VM. 6510 - Deny the guest request to suspend the VM. See ARM DEN0022D.b 5.19.2
6889 "Caller responsibilities" for possible ret 6511 "Caller responsibilities" for possible return values.
6890 6512
6891 :: 6513 ::
6892 6514
6893 /* KVM_EXIT_IOAPIC_EOI */ 6515 /* KVM_EXIT_IOAPIC_EOI */
6894 struct { 6516 struct {
6895 __u8 vector; 6517 __u8 vector;
6896 } eoi; 6518 } eoi;
6897 6519
6898 Indicates that the VCPU's in-kernel local API 6520 Indicates that the VCPU's in-kernel local APIC received an EOI for a
6899 level-triggered IOAPIC interrupt. This exit 6521 level-triggered IOAPIC interrupt. This exit only triggers when the
6900 IOAPIC is implemented in userspace (i.e. KVM_ 6522 IOAPIC is implemented in userspace (i.e. KVM_CAP_SPLIT_IRQCHIP is enabled);
6901 the userspace IOAPIC should process the EOI a 6523 the userspace IOAPIC should process the EOI and retrigger the interrupt if
6902 it is still asserted. Vector is the LAPIC in 6524 it is still asserted. Vector is the LAPIC interrupt vector for which the
6903 EOI was received. 6525 EOI was received.
6904 6526
6905 :: 6527 ::
6906 6528
6907 struct kvm_hyperv_exit { 6529 struct kvm_hyperv_exit {
6908 #define KVM_EXIT_HYPERV_SYNIC 1 6530 #define KVM_EXIT_HYPERV_SYNIC 1
6909 #define KVM_EXIT_HYPERV_HCALL 2 6531 #define KVM_EXIT_HYPERV_HCALL 2
6910 #define KVM_EXIT_HYPERV_SYNDBG 3 6532 #define KVM_EXIT_HYPERV_SYNDBG 3
6911 __u32 type; 6533 __u32 type;
6912 __u32 pad1; 6534 __u32 pad1;
6913 union { 6535 union {
6914 struct { 6536 struct {
6915 __u32 6537 __u32 msr;
6916 __u32 6538 __u32 pad2;
6917 __u64 6539 __u64 control;
6918 __u64 6540 __u64 evt_page;
6919 __u64 6541 __u64 msg_page;
6920 } synic; 6542 } synic;
6921 struct { 6543 struct {
6922 __u64 6544 __u64 input;
6923 __u64 6545 __u64 result;
6924 __u64 6546 __u64 params[2];
6925 } hcall; 6547 } hcall;
6926 struct { 6548 struct {
6927 __u32 6549 __u32 msr;
6928 __u32 6550 __u32 pad2;
6929 __u64 6551 __u64 control;
6930 __u64 6552 __u64 status;
6931 __u64 6553 __u64 send_page;
6932 __u64 6554 __u64 recv_page;
6933 __u64 6555 __u64 pending_page;
6934 } syndbg; 6556 } syndbg;
6935 } u; 6557 } u;
6936 }; 6558 };
6937 /* KVM_EXIT_HYPERV */ 6559 /* KVM_EXIT_HYPERV */
6938 struct kvm_hyperv_exit hyperv 6560 struct kvm_hyperv_exit hyperv;
6939 6561
6940 Indicates that the VCPU exits into userspace 6562 Indicates that the VCPU exits into userspace to process some tasks
6941 related to Hyper-V emulation. 6563 related to Hyper-V emulation.
6942 6564
6943 Valid values for 'type' are: 6565 Valid values for 'type' are:
6944 6566
6945 - KVM_EXIT_HYPERV_SYNIC -- synchronou 6567 - KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about
6946 6568
6947 Hyper-V SynIC state change. Notification is u 6569 Hyper-V SynIC state change. Notification is used to remap SynIC
6948 event/message pages and to enable/disable Syn 6570 event/message pages and to enable/disable SynIC messages/events processing
6949 in userspace. 6571 in userspace.
6950 6572
6951 - KVM_EXIT_HYPERV_SYNDBG -- synchrono 6573 - KVM_EXIT_HYPERV_SYNDBG -- synchronously notify user-space about
6952 6574
6953 Hyper-V Synthetic debugger state change. Noti 6575 Hyper-V Synthetic debugger state change. Notification is used to either update
6954 the pending_page location or to send a contro 6576 the pending_page location or to send a control command (send the buffer located
6955 in send_page or recv a buffer to recv_page). 6577 in send_page or recv a buffer to recv_page).
6956 6578
6957 :: 6579 ::
6958 6580
6959 /* KVM_EXIT_ARM_NISV */ 6581 /* KVM_EXIT_ARM_NISV */
6960 struct { 6582 struct {
6961 __u64 esr_iss; 6583 __u64 esr_iss;
6962 __u64 fault_ipa; 6584 __u64 fault_ipa;
6963 } arm_nisv; 6585 } arm_nisv;
6964 6586
6965 Used on arm64 systems. If a guest accesses me 6587 Used on arm64 systems. If a guest accesses memory not in a memslot,
6966 KVM will typically return to userspace and as 6588 KVM will typically return to userspace and ask it to do MMIO emulation on its
6967 behalf. However, for certain classes of instr 6589 behalf. However, for certain classes of instructions, no instruction decode
6968 (direction, length of memory access) is provi 6590 (direction, length of memory access) is provided, and fetching and decoding
6969 the instruction from the VM is overly complic 6591 the instruction from the VM is overly complicated to live in the kernel.
6970 6592
6971 Historically, when this situation occurred, K 6593 Historically, when this situation occurred, KVM would print a warning and kill
6972 the VM. KVM assumed that if the guest accesse 6594 the VM. KVM assumed that if the guest accessed non-memslot memory, it was
6973 trying to do I/O, which just couldn't be emul 6595 trying to do I/O, which just couldn't be emulated, and the warning message was
6974 phrased accordingly. However, what happened m 6596 phrased accordingly. However, what happened more often was that a guest bug
6975 caused access outside the guest memory areas 6597 caused access outside the guest memory areas which should lead to a more
6976 meaningful warning message and an external ab 6598 meaningful warning message and an external abort in the guest, if the access
6977 did not fall within an I/O window. 6599 did not fall within an I/O window.
6978 6600
6979 Userspace implementations can query for KVM_C 6601 Userspace implementations can query for KVM_CAP_ARM_NISV_TO_USER, and enable
6980 this capability at VM creation. Once this is 6602 this capability at VM creation. Once this is done, these types of errors will
6981 instead return to userspace with KVM_EXIT_ARM 6603 instead return to userspace with KVM_EXIT_ARM_NISV, with the valid bits from
6982 the ESR_EL2 in the esr_iss field, and the fau 6604 the ESR_EL2 in the esr_iss field, and the faulting IPA in the fault_ipa field.
6983 Userspace can either fix up the access if it' 6605 Userspace can either fix up the access if it's actually an I/O access by
6984 decoding the instruction from guest memory (i 6606 decoding the instruction from guest memory (if it's very brave) and continue
6985 executing the guest, or it can decide to susp 6607 executing the guest, or it can decide to suspend, dump, or restart the guest.
6986 6608
6987 Note that KVM does not skip the faulting inst 6609 Note that KVM does not skip the faulting instruction as it does for
6988 KVM_EXIT_MMIO, but userspace has to emulate a 6610 KVM_EXIT_MMIO, but userspace has to emulate any change to the processing state
6989 if it decides to decode and emulate the instr 6611 if it decides to decode and emulate the instruction.
6990 6612
6991 This feature isn't available to protected VMs <<
6992 have access to the state that is required to <<
6993 Instead, a data abort exception is directly i <<
6994 Note that although KVM_CAP_ARM_NISV_TO_USER w <<
6995 queried outside of a protected VM context, th <<
6996 exposed if queried on a protected VM file des <<
6997 <<
6998 :: 6613 ::
6999 6614
7000 /* KVM_EXIT_X86_RDMSR / KVM_E 6615 /* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
7001 struct { 6616 struct {
7002 __u8 error; /* user - 6617 __u8 error; /* user -> kernel */
7003 __u8 pad[7]; 6618 __u8 pad[7];
7004 __u32 reason; /* kern 6619 __u32 reason; /* kernel -> user */
7005 __u32 index; /* kerne 6620 __u32 index; /* kernel -> user */
7006 __u64 data; /* kernel 6621 __u64 data; /* kernel <-> user */
7007 } msr; 6622 } msr;
7008 6623
7009 Used on x86 systems. When the VM capability K 6624 Used on x86 systems. When the VM capability KVM_CAP_X86_USER_SPACE_MSR is
7010 enabled, MSR accesses to registers that would 6625 enabled, MSR accesses to registers that would invoke a #GP by KVM kernel code
7011 may instead trigger a KVM_EXIT_X86_RDMSR exit 6626 may instead trigger a KVM_EXIT_X86_RDMSR exit for reads and KVM_EXIT_X86_WRMSR
7012 exit for writes. 6627 exit for writes.
7013 6628
7014 The "reason" field specifies why the MSR inte 6629 The "reason" field specifies why the MSR interception occurred. Userspace will
7015 only receive MSR exits when a particular reas 6630 only receive MSR exits when a particular reason was requested during through
7016 ENABLE_CAP. Currently valid exit reasons are: 6631 ENABLE_CAP. Currently valid exit reasons are:
7017 6632
7018 ============================ ================ 6633 ============================ ========================================
7019 KVM_MSR_EXIT_REASON_UNKNOWN access to MSR th 6634 KVM_MSR_EXIT_REASON_UNKNOWN access to MSR that is unknown to KVM
7020 KVM_MSR_EXIT_REASON_INVAL access to invali 6635 KVM_MSR_EXIT_REASON_INVAL access to invalid MSRs or reserved bits
7021 KVM_MSR_EXIT_REASON_FILTER access blocked b 6636 KVM_MSR_EXIT_REASON_FILTER access blocked by KVM_X86_SET_MSR_FILTER
7022 ============================ ================ 6637 ============================ ========================================
7023 6638
7024 For KVM_EXIT_X86_RDMSR, the "index" field tel 6639 For KVM_EXIT_X86_RDMSR, the "index" field tells userspace which MSR the guest
7025 wants to read. To respond to this request wit 6640 wants to read. To respond to this request with a successful read, userspace
7026 writes the respective data into the "data" fi 6641 writes the respective data into the "data" field and must continue guest
7027 execution to ensure the read data is transfer 6642 execution to ensure the read data is transferred into guest register state.
7028 6643
7029 If the RDMSR request was unsuccessful, usersp 6644 If the RDMSR request was unsuccessful, userspace indicates that with a "1" in
7030 the "error" field. This will inject a #GP int 6645 the "error" field. This will inject a #GP into the guest when the VCPU is
7031 executed again. 6646 executed again.
7032 6647
7033 For KVM_EXIT_X86_WRMSR, the "index" field tel 6648 For KVM_EXIT_X86_WRMSR, the "index" field tells userspace which MSR the guest
7034 wants to write. Once finished processing the 6649 wants to write. Once finished processing the event, userspace must continue
7035 vCPU execution. If the MSR write was unsucces 6650 vCPU execution. If the MSR write was unsuccessful, userspace also sets the
7036 "error" field to "1". 6651 "error" field to "1".
7037 6652
7038 See KVM_X86_SET_MSR_FILTER for details on the 6653 See KVM_X86_SET_MSR_FILTER for details on the interaction with MSR filtering.
7039 6654
7040 :: 6655 ::
7041 6656
7042 6657
7043 struct kvm_xen_exit { 6658 struct kvm_xen_exit {
7044 #define KVM_EXIT_XEN_HCALL 1 6659 #define KVM_EXIT_XEN_HCALL 1
7045 __u32 type; 6660 __u32 type;
7046 union { 6661 union {
7047 struct { 6662 struct {
7048 __u32 6663 __u32 longmode;
7049 __u32 6664 __u32 cpl;
7050 __u64 6665 __u64 input;
7051 __u64 6666 __u64 result;
7052 __u64 6667 __u64 params[6];
7053 } hcall; 6668 } hcall;
7054 } u; 6669 } u;
7055 }; 6670 };
7056 /* KVM_EXIT_XEN */ 6671 /* KVM_EXIT_XEN */
7057 struct kvm_hyperv_exit xen; 6672 struct kvm_hyperv_exit xen;
7058 6673
7059 Indicates that the VCPU exits into userspace 6674 Indicates that the VCPU exits into userspace to process some tasks
7060 related to Xen emulation. 6675 related to Xen emulation.
7061 6676
7062 Valid values for 'type' are: 6677 Valid values for 'type' are:
7063 6678
7064 - KVM_EXIT_XEN_HCALL -- synchronously notif 6679 - KVM_EXIT_XEN_HCALL -- synchronously notify user-space about Xen hypercall.
7065 Userspace is expected to place the hyperc 6680 Userspace is expected to place the hypercall result into the appropriate
7066 field before invoking KVM_RUN again. 6681 field before invoking KVM_RUN again.
7067 6682
7068 :: 6683 ::
7069 6684
7070 /* KVM_EXIT_RISCV_SBI */ 6685 /* KVM_EXIT_RISCV_SBI */
7071 struct { 6686 struct {
7072 unsigned long extensi 6687 unsigned long extension_id;
7073 unsigned long functio 6688 unsigned long function_id;
7074 unsigned long args[6] 6689 unsigned long args[6];
7075 unsigned long ret[2]; 6690 unsigned long ret[2];
7076 } riscv_sbi; 6691 } riscv_sbi;
7077 6692
7078 If exit reason is KVM_EXIT_RISCV_SBI then it 6693 If exit reason is KVM_EXIT_RISCV_SBI then it indicates that the VCPU has
7079 done a SBI call which is not handled by KVM R 6694 done a SBI call which is not handled by KVM RISC-V kernel module. The details
7080 of the SBI call are available in 'riscv_sbi' 6695 of the SBI call are available in 'riscv_sbi' member of kvm_run structure. The
7081 'extension_id' field of 'riscv_sbi' represent 6696 'extension_id' field of 'riscv_sbi' represents SBI extension ID whereas the
7082 'function_id' field represents function ID of 6697 'function_id' field represents function ID of given SBI extension. The 'args'
7083 array field of 'riscv_sbi' represents paramet 6698 array field of 'riscv_sbi' represents parameters for the SBI call and 'ret'
7084 array field represents return values. The use 6699 array field represents return values. The userspace should update the return
7085 values of SBI call before resuming the VCPU. 6700 values of SBI call before resuming the VCPU. For more details on RISC-V SBI
7086 spec refer, https://github.com/riscv/riscv-sb 6701 spec refer, https://github.com/riscv/riscv-sbi-doc.
7087 6702
7088 :: 6703 ::
7089 6704
7090 /* KVM_EXIT_MEMORY_FAULT */ <<
7091 struct { <<
7092 #define KVM_MEMORY_EXIT_FLAG_PRIVATE (1ULL <<
7093 __u64 flags; <<
7094 __u64 gpa; <<
7095 __u64 size; <<
7096 } memory_fault; <<
7097 <<
7098 KVM_EXIT_MEMORY_FAULT indicates the vCPU has <<
7099 could not be resolved by KVM. The 'gpa' and <<
7100 guest physical address range [gpa, gpa + size <<
7101 describes properties of the faulting access t <<
7102 <<
7103 - KVM_MEMORY_EXIT_FLAG_PRIVATE - When set, i <<
7104 on a private memory access. When clear, i <<
7105 shared access. <<
7106 <<
7107 Note! KVM_EXIT_MEMORY_FAULT is unique among <<
7108 accompanies a return code of '-1', not '0'! <<
7109 or EHWPOISON when KVM exits with KVM_EXIT_MEM <<
7110 kvm_run.exit_reason is stale/undefined for al <<
7111 <<
7112 :: <<
7113 <<
7114 /* KVM_EXIT_NOTIFY */ 6705 /* KVM_EXIT_NOTIFY */
7115 struct { 6706 struct {
7116 #define KVM_NOTIFY_CONTEXT_INVALID (1 << 6707 #define KVM_NOTIFY_CONTEXT_INVALID (1 << 0)
7117 __u32 flags; 6708 __u32 flags;
7118 } notify; 6709 } notify;
7119 6710
7120 Used on x86 systems. When the VM capability K 6711 Used on x86 systems. When the VM capability KVM_CAP_X86_NOTIFY_VMEXIT is
7121 enabled, a VM exit generated if no event wind 6712 enabled, a VM exit generated if no event window occurs in VM non-root mode
7122 for a specified amount of time. Once KVM_X86_ 6713 for a specified amount of time. Once KVM_X86_NOTIFY_VMEXIT_USER is set when
7123 enabling the cap, it would exit to userspace 6714 enabling the cap, it would exit to userspace with the exit reason
7124 KVM_EXIT_NOTIFY for further handling. The "fl 6715 KVM_EXIT_NOTIFY for further handling. The "flags" field contains more
7125 detailed info. 6716 detailed info.
7126 6717
7127 The valid value for 'flags' is: 6718 The valid value for 'flags' is:
7128 6719
7129 - KVM_NOTIFY_CONTEXT_INVALID -- the VM cont 6720 - KVM_NOTIFY_CONTEXT_INVALID -- the VM context is corrupted and not valid
7130 in VMCS. It would run into unknown result 6721 in VMCS. It would run into unknown result if resume the target VM.
7131 6722
7132 :: 6723 ::
7133 6724
7134 /* Fix the size of the union. 6725 /* Fix the size of the union. */
7135 char padding[256]; 6726 char padding[256];
7136 }; 6727 };
7137 6728
7138 /* 6729 /*
7139 * shared registers between kvm and u 6730 * shared registers between kvm and userspace.
7140 * kvm_valid_regs specifies the regis 6731 * kvm_valid_regs specifies the register classes set by the host
7141 * kvm_dirty_regs specified the regis 6732 * kvm_dirty_regs specified the register classes dirtied by userspace
7142 * struct kvm_sync_regs is architectu 6733 * struct kvm_sync_regs is architecture specific, as well as the
7143 * bits for kvm_valid_regs and kvm_di 6734 * bits for kvm_valid_regs and kvm_dirty_regs
7144 */ 6735 */
7145 __u64 kvm_valid_regs; 6736 __u64 kvm_valid_regs;
7146 __u64 kvm_dirty_regs; 6737 __u64 kvm_dirty_regs;
7147 union { 6738 union {
7148 struct kvm_sync_regs regs; 6739 struct kvm_sync_regs regs;
7149 char padding[SYNC_REGS_SIZE_B 6740 char padding[SYNC_REGS_SIZE_BYTES];
7150 } s; 6741 } s;
7151 6742
7152 If KVM_CAP_SYNC_REGS is defined, these fields 6743 If KVM_CAP_SYNC_REGS is defined, these fields allow userspace to access
7153 certain guest registers without having to cal 6744 certain guest registers without having to call SET/GET_*REGS. Thus we can
7154 avoid some system call overhead if userspace 6745 avoid some system call overhead if userspace has to handle the exit.
7155 Userspace can query the validity of the struc 6746 Userspace can query the validity of the structure by checking
7156 kvm_valid_regs for specific bits. These bits 6747 kvm_valid_regs for specific bits. These bits are architecture specific
7157 and usually define the validity of a groups o 6748 and usually define the validity of a groups of registers. (e.g. one bit
7158 for general purpose registers) 6749 for general purpose registers)
7159 6750
7160 Please note that the kernel is allowed to use 6751 Please note that the kernel is allowed to use the kvm_run structure as the
7161 primary storage for certain register types. T 6752 primary storage for certain register types. Therefore, the kernel may use the
7162 values in kvm_run even if the corresponding b 6753 values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set.
7163 6754
7164 6755
7165 6. Capabilities that can be enabled on vCPUs 6756 6. Capabilities that can be enabled on vCPUs
7166 ============================================ 6757 ============================================
7167 6758
7168 There are certain capabilities that change th 6759 There are certain capabilities that change the behavior of the virtual CPU or
7169 the virtual machine when enabled. To enable t 6760 the virtual machine when enabled. To enable them, please see section 4.37.
7170 Below you can find a list of capabilities and 6761 Below you can find a list of capabilities and what their effect on the vCPU or
7171 the virtual machine is when enabling them. 6762 the virtual machine is when enabling them.
7172 6763
7173 The following information is provided along w 6764 The following information is provided along with the description:
7174 6765
7175 Architectures: 6766 Architectures:
7176 which instruction set architectures pro 6767 which instruction set architectures provide this ioctl.
7177 x86 includes both i386 and x86_64. 6768 x86 includes both i386 and x86_64.
7178 6769
7179 Target: 6770 Target:
7180 whether this is a per-vcpu or per-vm ca 6771 whether this is a per-vcpu or per-vm capability.
7181 6772
7182 Parameters: 6773 Parameters:
7183 what parameters are accepted by the cap 6774 what parameters are accepted by the capability.
7184 6775
7185 Returns: 6776 Returns:
7186 the return value. General error number 6777 the return value. General error numbers (EBADF, ENOMEM, EINVAL)
7187 are not detailed, but errors with speci 6778 are not detailed, but errors with specific meanings are.
7188 6779
7189 6780
7190 6.1 KVM_CAP_PPC_OSI 6781 6.1 KVM_CAP_PPC_OSI
7191 ------------------- 6782 -------------------
7192 6783
7193 :Architectures: ppc 6784 :Architectures: ppc
7194 :Target: vcpu 6785 :Target: vcpu
7195 :Parameters: none 6786 :Parameters: none
7196 :Returns: 0 on success; -1 on error 6787 :Returns: 0 on success; -1 on error
7197 6788
7198 This capability enables interception of OSI h 6789 This capability enables interception of OSI hypercalls that otherwise would
7199 be treated as normal system calls to be injec 6790 be treated as normal system calls to be injected into the guest. OSI hypercalls
7200 were invented by Mac-on-Linux to have a stand 6791 were invented by Mac-on-Linux to have a standardized communication mechanism
7201 between the guest and the host. 6792 between the guest and the host.
7202 6793
7203 When this capability is enabled, KVM_EXIT_OSI 6794 When this capability is enabled, KVM_EXIT_OSI can occur.
7204 6795
7205 6796
7206 6.2 KVM_CAP_PPC_PAPR 6797 6.2 KVM_CAP_PPC_PAPR
7207 -------------------- 6798 --------------------
7208 6799
7209 :Architectures: ppc 6800 :Architectures: ppc
7210 :Target: vcpu 6801 :Target: vcpu
7211 :Parameters: none 6802 :Parameters: none
7212 :Returns: 0 on success; -1 on error 6803 :Returns: 0 on success; -1 on error
7213 6804
7214 This capability enables interception of PAPR 6805 This capability enables interception of PAPR hypercalls. PAPR hypercalls are
7215 done using the hypercall instruction "sc 1". 6806 done using the hypercall instruction "sc 1".
7216 6807
7217 It also sets the guest privilege level to "su 6808 It also sets the guest privilege level to "supervisor" mode. Usually the guest
7218 runs in "hypervisor" privilege mode with a fe 6809 runs in "hypervisor" privilege mode with a few missing features.
7219 6810
7220 In addition to the above, it changes the sema 6811 In addition to the above, it changes the semantics of SDR1. In this mode, the
7221 HTAB address part of SDR1 contains an HVA ins 6812 HTAB address part of SDR1 contains an HVA instead of a GPA, as PAPR keeps the
7222 HTAB invisible to the guest. 6813 HTAB invisible to the guest.
7223 6814
7224 When this capability is enabled, KVM_EXIT_PAP 6815 When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur.
7225 6816
7226 6817
7227 6.3 KVM_CAP_SW_TLB 6818 6.3 KVM_CAP_SW_TLB
7228 ------------------ 6819 ------------------
7229 6820
7230 :Architectures: ppc 6821 :Architectures: ppc
7231 :Target: vcpu 6822 :Target: vcpu
7232 :Parameters: args[0] is the address of a stru 6823 :Parameters: args[0] is the address of a struct kvm_config_tlb
7233 :Returns: 0 on success; -1 on error 6824 :Returns: 0 on success; -1 on error
7234 6825
7235 :: 6826 ::
7236 6827
7237 struct kvm_config_tlb { 6828 struct kvm_config_tlb {
7238 __u64 params; 6829 __u64 params;
7239 __u64 array; 6830 __u64 array;
7240 __u32 mmu_type; 6831 __u32 mmu_type;
7241 __u32 array_len; 6832 __u32 array_len;
7242 }; 6833 };
7243 6834
7244 Configures the virtual CPU's TLB array, estab 6835 Configures the virtual CPU's TLB array, establishing a shared memory area
7245 between userspace and KVM. The "params" and 6836 between userspace and KVM. The "params" and "array" fields are userspace
7246 addresses of mmu-type-specific data structure 6837 addresses of mmu-type-specific data structures. The "array_len" field is an
7247 safety mechanism, and should be set to the si 6838 safety mechanism, and should be set to the size in bytes of the memory that
7248 userspace has reserved for the array. It mus 6839 userspace has reserved for the array. It must be at least the size dictated
7249 by "mmu_type" and "params". 6840 by "mmu_type" and "params".
7250 6841
7251 While KVM_RUN is active, the shared region is 6842 While KVM_RUN is active, the shared region is under control of KVM. Its
7252 contents are undefined, and any modification 6843 contents are undefined, and any modification by userspace results in
7253 boundedly undefined behavior. 6844 boundedly undefined behavior.
7254 6845
7255 On return from KVM_RUN, the shared region wil 6846 On return from KVM_RUN, the shared region will reflect the current state of
7256 the guest's TLB. If userspace makes any chan 6847 the guest's TLB. If userspace makes any changes, it must call KVM_DIRTY_TLB
7257 to tell KVM which entries have been changed, 6848 to tell KVM which entries have been changed, prior to calling KVM_RUN again
7258 on this vcpu. 6849 on this vcpu.
7259 6850
7260 For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_ 6851 For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
7261 6852
7262 - The "params" field is of type "struct kvm_ 6853 - The "params" field is of type "struct kvm_book3e_206_tlb_params".
7263 - The "array" field points to an array of ty 6854 - The "array" field points to an array of type "struct
7264 kvm_book3e_206_tlb_entry". 6855 kvm_book3e_206_tlb_entry".
7265 - The array consists of all entries in the f 6856 - The array consists of all entries in the first TLB, followed by all
7266 entries in the second TLB. 6857 entries in the second TLB.
7267 - Within a TLB, entries are ordered first by 6858 - Within a TLB, entries are ordered first by increasing set number. Within a
7268 set, entries are ordered by way (increasin 6859 set, entries are ordered by way (increasing ESEL).
7269 - The hash for determining set number in TLB 6860 - The hash for determining set number in TLB0 is: (MAS2 >> 12) & (num_sets - 1)
7270 where "num_sets" is the tlb_sizes[] value 6861 where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value.
7271 - The tsize field of mas1 shall be set to 4K 6862 - The tsize field of mas1 shall be set to 4K on TLB0, even though the
7272 hardware ignores this value for TLB0. 6863 hardware ignores this value for TLB0.
7273 6864
7274 6.4 KVM_CAP_S390_CSS_SUPPORT 6865 6.4 KVM_CAP_S390_CSS_SUPPORT
7275 ---------------------------- 6866 ----------------------------
7276 6867
7277 :Architectures: s390 6868 :Architectures: s390
7278 :Target: vcpu 6869 :Target: vcpu
7279 :Parameters: none 6870 :Parameters: none
7280 :Returns: 0 on success; -1 on error 6871 :Returns: 0 on success; -1 on error
7281 6872
7282 This capability enables support for handling 6873 This capability enables support for handling of channel I/O instructions.
7283 6874
7284 TEST PENDING INTERRUPTION and the interrupt p 6875 TEST PENDING INTERRUPTION and the interrupt portion of TEST SUBCHANNEL are
7285 handled in-kernel, while the other I/O instru 6876 handled in-kernel, while the other I/O instructions are passed to userspace.
7286 6877
7287 When this capability is enabled, KVM_EXIT_S39 6878 When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST
7288 SUBCHANNEL intercepts. 6879 SUBCHANNEL intercepts.
7289 6880
7290 Note that even though this capability is enab 6881 Note that even though this capability is enabled per-vcpu, the complete
7291 virtual machine is affected. 6882 virtual machine is affected.
7292 6883
7293 6.5 KVM_CAP_PPC_EPR 6884 6.5 KVM_CAP_PPC_EPR
7294 ------------------- 6885 -------------------
7295 6886
7296 :Architectures: ppc 6887 :Architectures: ppc
7297 :Target: vcpu 6888 :Target: vcpu
7298 :Parameters: args[0] defines whether the prox 6889 :Parameters: args[0] defines whether the proxy facility is active
7299 :Returns: 0 on success; -1 on error 6890 :Returns: 0 on success; -1 on error
7300 6891
7301 This capability enables or disables the deliv 6892 This capability enables or disables the delivery of interrupts through the
7302 external proxy facility. 6893 external proxy facility.
7303 6894
7304 When enabled (args[0] != 0), every time the g 6895 When enabled (args[0] != 0), every time the guest gets an external interrupt
7305 delivered, it automatically exits into user s 6896 delivered, it automatically exits into user space with a KVM_EXIT_EPR exit
7306 to receive the topmost interrupt vector. 6897 to receive the topmost interrupt vector.
7307 6898
7308 When disabled (args[0] == 0), behavior is as 6899 When disabled (args[0] == 0), behavior is as if this facility is unsupported.
7309 6900
7310 When this capability is enabled, KVM_EXIT_EPR 6901 When this capability is enabled, KVM_EXIT_EPR can occur.
7311 6902
7312 6.6 KVM_CAP_IRQ_MPIC 6903 6.6 KVM_CAP_IRQ_MPIC
7313 -------------------- 6904 --------------------
7314 6905
7315 :Architectures: ppc 6906 :Architectures: ppc
7316 :Parameters: args[0] is the MPIC device fd; 6907 :Parameters: args[0] is the MPIC device fd;
7317 args[1] is the MPIC CPU number f 6908 args[1] is the MPIC CPU number for this vcpu
7318 6909
7319 This capability connects the vcpu to an in-ke 6910 This capability connects the vcpu to an in-kernel MPIC device.
7320 6911
7321 6.7 KVM_CAP_IRQ_XICS 6912 6.7 KVM_CAP_IRQ_XICS
7322 -------------------- 6913 --------------------
7323 6914
7324 :Architectures: ppc 6915 :Architectures: ppc
7325 :Target: vcpu 6916 :Target: vcpu
7326 :Parameters: args[0] is the XICS device fd; 6917 :Parameters: args[0] is the XICS device fd;
7327 args[1] is the XICS CPU number ( 6918 args[1] is the XICS CPU number (server ID) for this vcpu
7328 6919
7329 This capability connects the vcpu to an in-ke 6920 This capability connects the vcpu to an in-kernel XICS device.
7330 6921
7331 6.8 KVM_CAP_S390_IRQCHIP 6922 6.8 KVM_CAP_S390_IRQCHIP
7332 ------------------------ 6923 ------------------------
7333 6924
7334 :Architectures: s390 6925 :Architectures: s390
7335 :Target: vm 6926 :Target: vm
7336 :Parameters: none 6927 :Parameters: none
7337 6928
7338 This capability enables the in-kernel irqchip 6929 This capability enables the in-kernel irqchip for s390. Please refer to
7339 "4.24 KVM_CREATE_IRQCHIP" for details. 6930 "4.24 KVM_CREATE_IRQCHIP" for details.
7340 6931
7341 6.9 KVM_CAP_MIPS_FPU 6932 6.9 KVM_CAP_MIPS_FPU
7342 -------------------- 6933 --------------------
7343 6934
7344 :Architectures: mips 6935 :Architectures: mips
7345 :Target: vcpu 6936 :Target: vcpu
7346 :Parameters: args[0] is reserved for future u 6937 :Parameters: args[0] is reserved for future use (should be 0).
7347 6938
7348 This capability allows the use of the host Fl 6939 This capability allows the use of the host Floating Point Unit by the guest. It
7349 allows the Config1.FP bit to be set to enable 6940 allows the Config1.FP bit to be set to enable the FPU in the guest. Once this is
7350 done the ``KVM_REG_MIPS_FPR_*`` and ``KVM_REG 6941 done the ``KVM_REG_MIPS_FPR_*`` and ``KVM_REG_MIPS_FCR_*`` registers can be
7351 accessed (depending on the current guest FPU 6942 accessed (depending on the current guest FPU register mode), and the Status.FR,
7352 Config5.FRE bits are accessible via the KVM A 6943 Config5.FRE bits are accessible via the KVM API and also from the guest,
7353 depending on them being supported by the FPU. 6944 depending on them being supported by the FPU.
7354 6945
7355 6.10 KVM_CAP_MIPS_MSA 6946 6.10 KVM_CAP_MIPS_MSA
7356 --------------------- 6947 ---------------------
7357 6948
7358 :Architectures: mips 6949 :Architectures: mips
7359 :Target: vcpu 6950 :Target: vcpu
7360 :Parameters: args[0] is reserved for future u 6951 :Parameters: args[0] is reserved for future use (should be 0).
7361 6952
7362 This capability allows the use of the MIPS SI 6953 This capability allows the use of the MIPS SIMD Architecture (MSA) by the guest.
7363 It allows the Config3.MSAP bit to be set to e 6954 It allows the Config3.MSAP bit to be set to enable the use of MSA by the guest.
7364 Once this is done the ``KVM_REG_MIPS_VEC_*`` 6955 Once this is done the ``KVM_REG_MIPS_VEC_*`` and ``KVM_REG_MIPS_MSA_*``
7365 registers can be accessed, and the Config5.MS 6956 registers can be accessed, and the Config5.MSAEn bit is accessible via the
7366 KVM API and also from the guest. 6957 KVM API and also from the guest.
7367 6958
7368 6.74 KVM_CAP_SYNC_REGS 6959 6.74 KVM_CAP_SYNC_REGS
7369 ---------------------- 6960 ----------------------
7370 6961
7371 :Architectures: s390, x86 6962 :Architectures: s390, x86
7372 :Target: s390: always enabled, x86: vcpu 6963 :Target: s390: always enabled, x86: vcpu
7373 :Parameters: none 6964 :Parameters: none
7374 :Returns: x86: KVM_CHECK_EXTENSION returns a 6965 :Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register
7375 sets are supported 6966 sets are supported
7376 (bitfields defined in arch/x86/incl 6967 (bitfields defined in arch/x86/include/uapi/asm/kvm.h).
7377 6968
7378 As described above in the kvm_sync_regs struc 6969 As described above in the kvm_sync_regs struct info in section 5 (kvm_run):
7379 KVM_CAP_SYNC_REGS "allow[s] userspace to acce 6970 KVM_CAP_SYNC_REGS "allow[s] userspace to access certain guest registers
7380 without having to call SET/GET_*REGS". This r 6971 without having to call SET/GET_*REGS". This reduces overhead by eliminating
7381 repeated ioctl calls for setting and/or getti 6972 repeated ioctl calls for setting and/or getting register values. This is
7382 particularly important when userspace is maki 6973 particularly important when userspace is making synchronous guest state
7383 modifications, e.g. when emulating and/or int 6974 modifications, e.g. when emulating and/or intercepting instructions in
7384 userspace. 6975 userspace.
7385 6976
7386 For s390 specifics, please refer to the sourc 6977 For s390 specifics, please refer to the source code.
7387 6978
7388 For x86: 6979 For x86:
7389 6980
7390 - the register sets to be copied out to kvm_r 6981 - the register sets to be copied out to kvm_run are selectable
7391 by userspace (rather that all sets being co 6982 by userspace (rather that all sets being copied out for every exit).
7392 - vcpu_events are available in addition to re 6983 - vcpu_events are available in addition to regs and sregs.
7393 6984
7394 For x86, the 'kvm_valid_regs' field of struct 6985 For x86, the 'kvm_valid_regs' field of struct kvm_run is overloaded to
7395 function as an input bit-array field set by u 6986 function as an input bit-array field set by userspace to indicate the
7396 specific register sets to be copied out on th 6987 specific register sets to be copied out on the next exit.
7397 6988
7398 To indicate when userspace has modified value 6989 To indicate when userspace has modified values that should be copied into
7399 the vCPU, the all architecture bitarray field 6990 the vCPU, the all architecture bitarray field, 'kvm_dirty_regs' must be set.
7400 This is done using the same bitflags as for t 6991 This is done using the same bitflags as for the 'kvm_valid_regs' field.
7401 If the dirty bit is not set, then the registe 6992 If the dirty bit is not set, then the register set values will not be copied
7402 into the vCPU even if they've been modified. 6993 into the vCPU even if they've been modified.
7403 6994
7404 Unused bitfields in the bitarrays must be set 6995 Unused bitfields in the bitarrays must be set to zero.
7405 6996
7406 :: 6997 ::
7407 6998
7408 struct kvm_sync_regs { 6999 struct kvm_sync_regs {
7409 struct kvm_regs regs; 7000 struct kvm_regs regs;
7410 struct kvm_sregs sregs; 7001 struct kvm_sregs sregs;
7411 struct kvm_vcpu_events events; 7002 struct kvm_vcpu_events events;
7412 }; 7003 };
7413 7004
7414 6.75 KVM_CAP_PPC_IRQ_XIVE 7005 6.75 KVM_CAP_PPC_IRQ_XIVE
7415 ------------------------- 7006 -------------------------
7416 7007
7417 :Architectures: ppc 7008 :Architectures: ppc
7418 :Target: vcpu 7009 :Target: vcpu
7419 :Parameters: args[0] is the XIVE device fd; 7010 :Parameters: args[0] is the XIVE device fd;
7420 args[1] is the XIVE CPU number ( 7011 args[1] is the XIVE CPU number (server ID) for this vcpu
7421 7012
7422 This capability connects the vcpu to an in-ke 7013 This capability connects the vcpu to an in-kernel XIVE device.
7423 7014
7424 7. Capabilities that can be enabled on VMs 7015 7. Capabilities that can be enabled on VMs
7425 ========================================== 7016 ==========================================
7426 7017
7427 There are certain capabilities that change th 7018 There are certain capabilities that change the behavior of the virtual
7428 machine when enabled. To enable them, please 7019 machine when enabled. To enable them, please see section 4.37. Below
7429 you can find a list of capabilities and what 7020 you can find a list of capabilities and what their effect on the VM
7430 is when enabling them. 7021 is when enabling them.
7431 7022
7432 The following information is provided along w 7023 The following information is provided along with the description:
7433 7024
7434 Architectures: 7025 Architectures:
7435 which instruction set architectures pro 7026 which instruction set architectures provide this ioctl.
7436 x86 includes both i386 and x86_64. 7027 x86 includes both i386 and x86_64.
7437 7028
7438 Parameters: 7029 Parameters:
7439 what parameters are accepted by the cap 7030 what parameters are accepted by the capability.
7440 7031
7441 Returns: 7032 Returns:
7442 the return value. General error number 7033 the return value. General error numbers (EBADF, ENOMEM, EINVAL)
7443 are not detailed, but errors with speci 7034 are not detailed, but errors with specific meanings are.
7444 7035
7445 7036
7446 7.1 KVM_CAP_PPC_ENABLE_HCALL 7037 7.1 KVM_CAP_PPC_ENABLE_HCALL
7447 ---------------------------- 7038 ----------------------------
7448 7039
7449 :Architectures: ppc 7040 :Architectures: ppc
7450 :Parameters: args[0] is the sPAPR hcall numbe 7041 :Parameters: args[0] is the sPAPR hcall number;
7451 args[1] is 0 to disable, 1 to en 7042 args[1] is 0 to disable, 1 to enable in-kernel handling
7452 7043
7453 This capability controls whether individual s 7044 This capability controls whether individual sPAPR hypercalls (hcalls)
7454 get handled by the kernel or not. Enabling o 7045 get handled by the kernel or not. Enabling or disabling in-kernel
7455 handling of an hcall is effective across the 7046 handling of an hcall is effective across the VM. On creation, an
7456 initial set of hcalls are enabled for in-kern 7047 initial set of hcalls are enabled for in-kernel handling, which
7457 consists of those hcalls for which in-kernel 7048 consists of those hcalls for which in-kernel handlers were implemented
7458 before this capability was implemented. If d 7049 before this capability was implemented. If disabled, the kernel will
7459 not to attempt to handle the hcall, but will 7050 not to attempt to handle the hcall, but will always exit to userspace
7460 to handle it. Note that it may not make sens 7051 to handle it. Note that it may not make sense to enable some and
7461 disable others of a group of related hcalls, 7052 disable others of a group of related hcalls, but KVM does not prevent
7462 userspace from doing that. 7053 userspace from doing that.
7463 7054
7464 If the hcall number specified is not one that 7055 If the hcall number specified is not one that has an in-kernel
7465 implementation, the KVM_ENABLE_CAP ioctl will 7056 implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL
7466 error. 7057 error.
7467 7058
7468 7.2 KVM_CAP_S390_USER_SIGP 7059 7.2 KVM_CAP_S390_USER_SIGP
7469 -------------------------- 7060 --------------------------
7470 7061
7471 :Architectures: s390 7062 :Architectures: s390
7472 :Parameters: none 7063 :Parameters: none
7473 7064
7474 This capability controls which SIGP orders wi 7065 This capability controls which SIGP orders will be handled completely in user
7475 space. With this capability enabled, all fast 7066 space. With this capability enabled, all fast orders will be handled completely
7476 in the kernel: 7067 in the kernel:
7477 7068
7478 - SENSE 7069 - SENSE
7479 - SENSE RUNNING 7070 - SENSE RUNNING
7480 - EXTERNAL CALL 7071 - EXTERNAL CALL
7481 - EMERGENCY SIGNAL 7072 - EMERGENCY SIGNAL
7482 - CONDITIONAL EMERGENCY SIGNAL 7073 - CONDITIONAL EMERGENCY SIGNAL
7483 7074
7484 All other orders will be handled completely i 7075 All other orders will be handled completely in user space.
7485 7076
7486 Only privileged operation exceptions will be 7077 Only privileged operation exceptions will be checked for in the kernel (or even
7487 in the hardware prior to interception). If th 7078 in the hardware prior to interception). If this capability is not enabled, the
7488 old way of handling SIGP orders is used (part 7079 old way of handling SIGP orders is used (partially in kernel and user space).
7489 7080
7490 7.3 KVM_CAP_S390_VECTOR_REGISTERS 7081 7.3 KVM_CAP_S390_VECTOR_REGISTERS
7491 --------------------------------- 7082 ---------------------------------
7492 7083
7493 :Architectures: s390 7084 :Architectures: s390
7494 :Parameters: none 7085 :Parameters: none
7495 :Returns: 0 on success, negative value on err 7086 :Returns: 0 on success, negative value on error
7496 7087
7497 Allows use of the vector registers introduced 7088 Allows use of the vector registers introduced with z13 processor, and
7498 provides for the synchronization between host 7089 provides for the synchronization between host and user space. Will
7499 return -EINVAL if the machine does not suppor 7090 return -EINVAL if the machine does not support vectors.
7500 7091
7501 7.4 KVM_CAP_S390_USER_STSI 7092 7.4 KVM_CAP_S390_USER_STSI
7502 -------------------------- 7093 --------------------------
7503 7094
7504 :Architectures: s390 7095 :Architectures: s390
7505 :Parameters: none 7096 :Parameters: none
7506 7097
7507 This capability allows post-handlers for the 7098 This capability allows post-handlers for the STSI instruction. After
7508 initial handling in the kernel, KVM exits to 7099 initial handling in the kernel, KVM exits to user space with
7509 KVM_EXIT_S390_STSI to allow user space to ins 7100 KVM_EXIT_S390_STSI to allow user space to insert further data.
7510 7101
7511 Before exiting to userspace, kvm handlers sho 7102 Before exiting to userspace, kvm handlers should fill in s390_stsi field of
7512 vcpu->run:: 7103 vcpu->run::
7513 7104
7514 struct { 7105 struct {
7515 __u64 addr; 7106 __u64 addr;
7516 __u8 ar; 7107 __u8 ar;
7517 __u8 reserved; 7108 __u8 reserved;
7518 __u8 fc; 7109 __u8 fc;
7519 __u8 sel1; 7110 __u8 sel1;
7520 __u16 sel2; 7111 __u16 sel2;
7521 } s390_stsi; 7112 } s390_stsi;
7522 7113
7523 @addr - guest address of STSI SYSIB 7114 @addr - guest address of STSI SYSIB
7524 @fc - function code 7115 @fc - function code
7525 @sel1 - selector 1 7116 @sel1 - selector 1
7526 @sel2 - selector 2 7117 @sel2 - selector 2
7527 @ar - access register number 7118 @ar - access register number
7528 7119
7529 KVM handlers should exit to userspace with rc 7120 KVM handlers should exit to userspace with rc = -EREMOTE.
7530 7121
7531 7.5 KVM_CAP_SPLIT_IRQCHIP 7122 7.5 KVM_CAP_SPLIT_IRQCHIP
7532 ------------------------- 7123 -------------------------
7533 7124
7534 :Architectures: x86 7125 :Architectures: x86
7535 :Parameters: args[0] - number of routes reser 7126 :Parameters: args[0] - number of routes reserved for userspace IOAPICs
7536 :Returns: 0 on success, -1 on error 7127 :Returns: 0 on success, -1 on error
7537 7128
7538 Create a local apic for each processor in the 7129 Create a local apic for each processor in the kernel. This can be used
7539 instead of KVM_CREATE_IRQCHIP if the userspac 7130 instead of KVM_CREATE_IRQCHIP if the userspace VMM wishes to emulate the
7540 IOAPIC and PIC (and also the PIT, even though 7131 IOAPIC and PIC (and also the PIT, even though this has to be enabled
7541 separately). 7132 separately).
7542 7133
7543 This capability also enables in kernel routin 7134 This capability also enables in kernel routing of interrupt requests;
7544 when KVM_CAP_SPLIT_IRQCHIP only routes of KVM 7135 when KVM_CAP_SPLIT_IRQCHIP only routes of KVM_IRQ_ROUTING_MSI type are
7545 used in the IRQ routing table. The first arg 7136 used in the IRQ routing table. The first args[0] MSI routes are reserved
7546 for the IOAPIC pins. Whenever the LAPIC rece 7137 for the IOAPIC pins. Whenever the LAPIC receives an EOI for these routes,
7547 a KVM_EXIT_IOAPIC_EOI vmexit will be reported 7138 a KVM_EXIT_IOAPIC_EOI vmexit will be reported to userspace.
7548 7139
7549 Fails if VCPU has already been created, or if 7140 Fails if VCPU has already been created, or if the irqchip is already in the
7550 kernel (i.e. KVM_CREATE_IRQCHIP has already b 7141 kernel (i.e. KVM_CREATE_IRQCHIP has already been called).
7551 7142
7552 7.6 KVM_CAP_S390_RI 7143 7.6 KVM_CAP_S390_RI
7553 ------------------- 7144 -------------------
7554 7145
7555 :Architectures: s390 7146 :Architectures: s390
7556 :Parameters: none 7147 :Parameters: none
7557 7148
7558 Allows use of runtime-instrumentation introdu 7149 Allows use of runtime-instrumentation introduced with zEC12 processor.
7559 Will return -EINVAL if the machine does not s 7150 Will return -EINVAL if the machine does not support runtime-instrumentation.
7560 Will return -EBUSY if a VCPU has already been 7151 Will return -EBUSY if a VCPU has already been created.
7561 7152
7562 7.7 KVM_CAP_X2APIC_API 7153 7.7 KVM_CAP_X2APIC_API
7563 ---------------------- 7154 ----------------------
7564 7155
7565 :Architectures: x86 7156 :Architectures: x86
7566 :Parameters: args[0] - features that should b 7157 :Parameters: args[0] - features that should be enabled
7567 :Returns: 0 on success, -EINVAL when args[0] 7158 :Returns: 0 on success, -EINVAL when args[0] contains invalid features
7568 7159
7569 Valid feature flags in args[0] are:: 7160 Valid feature flags in args[0] are::
7570 7161
7571 #define KVM_X2APIC_API_USE_32BIT_IDS 7162 #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
7572 #define KVM_X2APIC_API_DISABLE_BROADCAST_QU 7163 #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
7573 7164
7574 Enabling KVM_X2APIC_API_USE_32BIT_IDS changes 7165 Enabling KVM_X2APIC_API_USE_32BIT_IDS changes the behavior of
7575 KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_ 7166 KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_LAPIC, and KVM_GET_LAPIC,
7576 allowing the use of 32-bit APIC IDs. See KVM 7167 allowing the use of 32-bit APIC IDs. See KVM_CAP_X2APIC_API in their
7577 respective sections. 7168 respective sections.
7578 7169
7579 KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK must b 7170 KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK must be enabled for x2APIC to work
7580 in logical mode or with more than 255 VCPUs. 7171 in logical mode or with more than 255 VCPUs. Otherwise, KVM treats 0xff
7581 as a broadcast even in x2APIC mode in order t 7172 as a broadcast even in x2APIC mode in order to support physical x2APIC
7582 without interrupt remapping. This is undesir 7173 without interrupt remapping. This is undesirable in logical mode,
7583 where 0xff represents CPUs 0-7 in cluster 0. 7174 where 0xff represents CPUs 0-7 in cluster 0.
7584 7175
7585 7.8 KVM_CAP_S390_USER_INSTR0 7176 7.8 KVM_CAP_S390_USER_INSTR0
7586 ---------------------------- 7177 ----------------------------
7587 7178
7588 :Architectures: s390 7179 :Architectures: s390
7589 :Parameters: none 7180 :Parameters: none
7590 7181
7591 With this capability enabled, all illegal ins 7182 With this capability enabled, all illegal instructions 0x0000 (2 bytes) will
7592 be intercepted and forwarded to user space. U 7183 be intercepted and forwarded to user space. User space can use this
7593 mechanism e.g. to realize 2-byte software bre 7184 mechanism e.g. to realize 2-byte software breakpoints. The kernel will
7594 not inject an operating exception for these i 7185 not inject an operating exception for these instructions, user space has
7595 to take care of that. 7186 to take care of that.
7596 7187
7597 This capability can be enabled dynamically ev 7188 This capability can be enabled dynamically even if VCPUs were already
7598 created and are running. 7189 created and are running.
7599 7190
7600 7.9 KVM_CAP_S390_GS 7191 7.9 KVM_CAP_S390_GS
7601 ------------------- 7192 -------------------
7602 7193
7603 :Architectures: s390 7194 :Architectures: s390
7604 :Parameters: none 7195 :Parameters: none
7605 :Returns: 0 on success; -EINVAL if the machin 7196 :Returns: 0 on success; -EINVAL if the machine does not support
7606 guarded storage; -EBUSY if a VCPU h 7197 guarded storage; -EBUSY if a VCPU has already been created.
7607 7198
7608 Allows use of guarded storage for the KVM gue 7199 Allows use of guarded storage for the KVM guest.
7609 7200
7610 7.10 KVM_CAP_S390_AIS 7201 7.10 KVM_CAP_S390_AIS
7611 --------------------- 7202 ---------------------
7612 7203
7613 :Architectures: s390 7204 :Architectures: s390
7614 :Parameters: none 7205 :Parameters: none
7615 7206
7616 Allow use of adapter-interruption suppression 7207 Allow use of adapter-interruption suppression.
7617 :Returns: 0 on success; -EBUSY if a VCPU has 7208 :Returns: 0 on success; -EBUSY if a VCPU has already been created.
7618 7209
7619 7.11 KVM_CAP_PPC_SMT 7210 7.11 KVM_CAP_PPC_SMT
7620 -------------------- 7211 --------------------
7621 7212
7622 :Architectures: ppc 7213 :Architectures: ppc
7623 :Parameters: vsmt_mode, flags 7214 :Parameters: vsmt_mode, flags
7624 7215
7625 Enabling this capability on a VM provides use 7216 Enabling this capability on a VM provides userspace with a way to set
7626 the desired virtual SMT mode (i.e. the number 7217 the desired virtual SMT mode (i.e. the number of virtual CPUs per
7627 virtual core). The virtual SMT mode, vsmt_mo 7218 virtual core). The virtual SMT mode, vsmt_mode, must be a power of 2
7628 between 1 and 8. On POWER8, vsmt_mode must a 7219 between 1 and 8. On POWER8, vsmt_mode must also be no greater than
7629 the number of threads per subcore for the hos 7220 the number of threads per subcore for the host. Currently flags must
7630 be 0. A successful call to enable this capab 7221 be 0. A successful call to enable this capability will result in
7631 vsmt_mode being returned when the KVM_CAP_PPC 7222 vsmt_mode being returned when the KVM_CAP_PPC_SMT capability is
7632 subsequently queried for the VM. This capabi 7223 subsequently queried for the VM. This capability is only supported by
7633 HV KVM, and can only be set before any VCPUs 7224 HV KVM, and can only be set before any VCPUs have been created.
7634 The KVM_CAP_PPC_SMT_POSSIBLE capability indic 7225 The KVM_CAP_PPC_SMT_POSSIBLE capability indicates which virtual SMT
7635 modes are available. 7226 modes are available.
7636 7227
7637 7.12 KVM_CAP_PPC_FWNMI 7228 7.12 KVM_CAP_PPC_FWNMI
7638 ---------------------- 7229 ----------------------
7639 7230
7640 :Architectures: ppc 7231 :Architectures: ppc
7641 :Parameters: none 7232 :Parameters: none
7642 7233
7643 With this capability a machine check exceptio 7234 With this capability a machine check exception in the guest address
7644 space will cause KVM to exit the guest with N 7235 space will cause KVM to exit the guest with NMI exit reason. This
7645 enables QEMU to build error log and branch to 7236 enables QEMU to build error log and branch to guest kernel registered
7646 machine check handling routine. Without this 7237 machine check handling routine. Without this capability KVM will
7647 branch to guests' 0x200 interrupt vector. 7238 branch to guests' 0x200 interrupt vector.
7648 7239
7649 7.13 KVM_CAP_X86_DISABLE_EXITS 7240 7.13 KVM_CAP_X86_DISABLE_EXITS
7650 ------------------------------ 7241 ------------------------------
7651 7242
7652 :Architectures: x86 7243 :Architectures: x86
7653 :Parameters: args[0] defines which exits are 7244 :Parameters: args[0] defines which exits are disabled
7654 :Returns: 0 on success, -EINVAL when args[0] 7245 :Returns: 0 on success, -EINVAL when args[0] contains invalid exits
7655 7246
7656 Valid bits in args[0] are:: 7247 Valid bits in args[0] are::
7657 7248
7658 #define KVM_X86_DISABLE_EXITS_MWAIT 7249 #define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
7659 #define KVM_X86_DISABLE_EXITS_HLT 7250 #define KVM_X86_DISABLE_EXITS_HLT (1 << 1)
7660 #define KVM_X86_DISABLE_EXITS_PAUSE 7251 #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
7661 #define KVM_X86_DISABLE_EXITS_CSTATE 7252 #define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3)
7662 7253
7663 Enabling this capability on a VM provides use 7254 Enabling this capability on a VM provides userspace with a way to no
7664 longer intercept some instructions for improv 7255 longer intercept some instructions for improved latency in some
7665 workloads, and is suggested when vCPUs are as 7256 workloads, and is suggested when vCPUs are associated to dedicated
7666 physical CPUs. More bits can be added in the 7257 physical CPUs. More bits can be added in the future; userspace can
7667 just pass the KVM_CHECK_EXTENSION result to K 7258 just pass the KVM_CHECK_EXTENSION result to KVM_ENABLE_CAP to disable
7668 all such vmexits. 7259 all such vmexits.
7669 7260
7670 Do not enable KVM_FEATURE_PV_UNHALT if you di 7261 Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
7671 7262
7672 7.14 KVM_CAP_S390_HPAGE_1M 7263 7.14 KVM_CAP_S390_HPAGE_1M
7673 -------------------------- 7264 --------------------------
7674 7265
7675 :Architectures: s390 7266 :Architectures: s390
7676 :Parameters: none 7267 :Parameters: none
7677 :Returns: 0 on success, -EINVAL if hpage modu 7268 :Returns: 0 on success, -EINVAL if hpage module parameter was not set
7678 or cmma is enabled, or the VM has t 7269 or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL
7679 flag set 7270 flag set
7680 7271
7681 With this capability the KVM support for memo 7272 With this capability the KVM support for memory backing with 1m pages
7682 through hugetlbfs can be enabled for a VM. Af 7273 through hugetlbfs can be enabled for a VM. After the capability is
7683 enabled, cmma can't be enabled anymore and pf 7274 enabled, cmma can't be enabled anymore and pfmfi and the storage key
7684 interpretation are disabled. If cmma has alre 7275 interpretation are disabled. If cmma has already been enabled or the
7685 hpage module parameter is not set to 1, -EINV 7276 hpage module parameter is not set to 1, -EINVAL is returned.
7686 7277
7687 While it is generally possible to create a hu 7278 While it is generally possible to create a huge page backed VM without
7688 this capability, the VM will not be able to r 7279 this capability, the VM will not be able to run.
7689 7280
7690 7.15 KVM_CAP_MSR_PLATFORM_INFO 7281 7.15 KVM_CAP_MSR_PLATFORM_INFO
7691 ------------------------------ 7282 ------------------------------
7692 7283
7693 :Architectures: x86 7284 :Architectures: x86
7694 :Parameters: args[0] whether feature should b 7285 :Parameters: args[0] whether feature should be enabled or not
7695 7286
7696 With this capability, a guest may read the MS 7287 With this capability, a guest may read the MSR_PLATFORM_INFO MSR. Otherwise,
7697 a #GP would be raised when the guest tries to 7288 a #GP would be raised when the guest tries to access. Currently, this
7698 capability does not enable write permissions 7289 capability does not enable write permissions of this MSR for the guest.
7699 7290
7700 7.16 KVM_CAP_PPC_NESTED_HV 7291 7.16 KVM_CAP_PPC_NESTED_HV
7701 -------------------------- 7292 --------------------------
7702 7293
7703 :Architectures: ppc 7294 :Architectures: ppc
7704 :Parameters: none 7295 :Parameters: none
7705 :Returns: 0 on success, -EINVAL when the impl 7296 :Returns: 0 on success, -EINVAL when the implementation doesn't support
7706 nested-HV virtualization. 7297 nested-HV virtualization.
7707 7298
7708 HV-KVM on POWER9 and later systems allows for 7299 HV-KVM on POWER9 and later systems allows for "nested-HV"
7709 virtualization, which provides a way for a gu 7300 virtualization, which provides a way for a guest VM to run guests that
7710 can run using the CPU's supervisor mode (priv 7301 can run using the CPU's supervisor mode (privileged non-hypervisor
7711 state). Enabling this capability on a VM dep 7302 state). Enabling this capability on a VM depends on the CPU having
7712 the necessary functionality and on the facili 7303 the necessary functionality and on the facility being enabled with a
7713 kvm-hv module parameter. 7304 kvm-hv module parameter.
7714 7305
7715 7.17 KVM_CAP_EXCEPTION_PAYLOAD 7306 7.17 KVM_CAP_EXCEPTION_PAYLOAD
7716 ------------------------------ 7307 ------------------------------
7717 7308
7718 :Architectures: x86 7309 :Architectures: x86
7719 :Parameters: args[0] whether feature should b 7310 :Parameters: args[0] whether feature should be enabled or not
7720 7311
7721 With this capability enabled, CR2 will not be 7312 With this capability enabled, CR2 will not be modified prior to the
7722 emulated VM-exit when L1 intercepts a #PF exc 7313 emulated VM-exit when L1 intercepts a #PF exception that occurs in
7723 L2. Similarly, for kvm-intel only, DR6 will n 7314 L2. Similarly, for kvm-intel only, DR6 will not be modified prior to
7724 the emulated VM-exit when L1 intercepts a #DB 7315 the emulated VM-exit when L1 intercepts a #DB exception that occurs in
7725 L2. As a result, when KVM_GET_VCPU_EVENTS rep 7316 L2. As a result, when KVM_GET_VCPU_EVENTS reports a pending #PF (or
7726 #DB) exception for L2, exception.has_payload 7317 #DB) exception for L2, exception.has_payload will be set and the
7727 faulting address (or the new DR6 bits*) will 7318 faulting address (or the new DR6 bits*) will be reported in the
7728 exception_payload field. Similarly, when user 7319 exception_payload field. Similarly, when userspace injects a #PF (or
7729 #DB) into L2 using KVM_SET_VCPU_EVENTS, it is 7320 #DB) into L2 using KVM_SET_VCPU_EVENTS, it is expected to set
7730 exception.has_payload and to put the faulting 7321 exception.has_payload and to put the faulting address - or the new DR6
7731 bits\ [#]_ - in the exception_payload field. 7322 bits\ [#]_ - in the exception_payload field.
7732 7323
7733 This capability also enables exception.pendin 7324 This capability also enables exception.pending in struct
7734 kvm_vcpu_events, which allows userspace to di 7325 kvm_vcpu_events, which allows userspace to distinguish between pending
7735 and injected exceptions. 7326 and injected exceptions.
7736 7327
7737 7328
7738 .. [#] For the new DR6 bits, note that bit 16 7329 .. [#] For the new DR6 bits, note that bit 16 is set iff the #DB exception
7739 will clear DR6.RTM. 7330 will clear DR6.RTM.
7740 7331
7741 7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 7332 7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
7742 -------------------------------------- 7333 --------------------------------------
7743 7334
7744 :Architectures: x86, arm64, mips 7335 :Architectures: x86, arm64, mips
7745 :Parameters: args[0] whether feature should b 7336 :Parameters: args[0] whether feature should be enabled or not
7746 7337
7747 Valid flags are:: 7338 Valid flags are::
7748 7339
7749 #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE 7340 #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
7750 #define KVM_DIRTY_LOG_INITIALLY_SET 7341 #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1)
7751 7342
7752 With KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE is s 7343 With KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE is set, KVM_GET_DIRTY_LOG will not
7753 automatically clear and write-protect all pag 7344 automatically clear and write-protect all pages that are returned as dirty.
7754 Rather, userspace will have to do this operat 7345 Rather, userspace will have to do this operation separately using
7755 KVM_CLEAR_DIRTY_LOG. 7346 KVM_CLEAR_DIRTY_LOG.
7756 7347
7757 At the cost of a slightly more complicated op 7348 At the cost of a slightly more complicated operation, this provides better
7758 scalability and responsiveness for two reason 7349 scalability and responsiveness for two reasons. First,
7759 KVM_CLEAR_DIRTY_LOG ioctl can operate on a 64 7350 KVM_CLEAR_DIRTY_LOG ioctl can operate on a 64-page granularity rather
7760 than requiring to sync a full memslot; this e 7351 than requiring to sync a full memslot; this ensures that KVM does not
7761 take spinlocks for an extended period of time 7352 take spinlocks for an extended period of time. Second, in some cases a
7762 large amount of time can pass between a call 7353 large amount of time can pass between a call to KVM_GET_DIRTY_LOG and
7763 userspace actually using the data in the page 7354 userspace actually using the data in the page. Pages can be modified
7764 during this time, which is inefficient for bo 7355 during this time, which is inefficient for both the guest and userspace:
7765 the guest will incur a higher penalty due to 7356 the guest will incur a higher penalty due to write protection faults,
7766 while userspace can see false reports of dirt 7357 while userspace can see false reports of dirty pages. Manual reprotection
7767 helps reducing this time, improving guest per 7358 helps reducing this time, improving guest performance and reducing the
7768 number of dirty log false positives. 7359 number of dirty log false positives.
7769 7360
7770 With KVM_DIRTY_LOG_INITIALLY_SET set, all the 7361 With KVM_DIRTY_LOG_INITIALLY_SET set, all the bits of the dirty bitmap
7771 will be initialized to 1 when created. This 7362 will be initialized to 1 when created. This also improves performance because
7772 dirty logging can be enabled gradually in sma 7363 dirty logging can be enabled gradually in small chunks on the first call
7773 to KVM_CLEAR_DIRTY_LOG. KVM_DIRTY_LOG_INITIA 7364 to KVM_CLEAR_DIRTY_LOG. KVM_DIRTY_LOG_INITIALLY_SET depends on
7774 KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (it is al 7365 KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (it is also only available on
7775 x86 and arm64 for now). 7366 x86 and arm64 for now).
7776 7367
7777 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 was previou 7368 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 was previously available under the name
7778 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT, but the imp 7369 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT, but the implementation had bugs that make
7779 it hard or impossible to use it correctly. T 7370 it hard or impossible to use it correctly. The availability of
7780 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 signals tha 7371 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 signals that those bugs are fixed.
7781 Userspace should not try to use KVM_CAP_MANUA 7372 Userspace should not try to use KVM_CAP_MANUAL_DIRTY_LOG_PROTECT.
7782 7373
7783 7.19 KVM_CAP_PPC_SECURE_GUEST 7374 7.19 KVM_CAP_PPC_SECURE_GUEST
7784 ------------------------------ 7375 ------------------------------
7785 7376
7786 :Architectures: ppc 7377 :Architectures: ppc
7787 7378
7788 This capability indicates that KVM is running 7379 This capability indicates that KVM is running on a host that has
7789 ultravisor firmware and thus can support a se 7380 ultravisor firmware and thus can support a secure guest. On such a
7790 system, a guest can ask the ultravisor to mak 7381 system, a guest can ask the ultravisor to make it a secure guest,
7791 one whose memory is inaccessible to the host 7382 one whose memory is inaccessible to the host except for pages which
7792 are explicitly requested to be shared with th 7383 are explicitly requested to be shared with the host. The ultravisor
7793 notifies KVM when a guest requests to become 7384 notifies KVM when a guest requests to become a secure guest, and KVM
7794 has the opportunity to veto the transition. 7385 has the opportunity to veto the transition.
7795 7386
7796 If present, this capability can be enabled fo 7387 If present, this capability can be enabled for a VM, meaning that KVM
7797 will allow the transition to secure guest mod 7388 will allow the transition to secure guest mode. Otherwise KVM will
7798 veto the transition. 7389 veto the transition.
7799 7390
7800 7.20 KVM_CAP_HALT_POLL 7391 7.20 KVM_CAP_HALT_POLL
7801 ---------------------- 7392 ----------------------
7802 7393
7803 :Architectures: all 7394 :Architectures: all
7804 :Target: VM 7395 :Target: VM
7805 :Parameters: args[0] is the maximum poll time 7396 :Parameters: args[0] is the maximum poll time in nanoseconds
7806 :Returns: 0 on success; -1 on error 7397 :Returns: 0 on success; -1 on error
7807 7398
7808 KVM_CAP_HALT_POLL overrides the kvm.halt_poll 7399 KVM_CAP_HALT_POLL overrides the kvm.halt_poll_ns module parameter to set the
7809 maximum halt-polling time for all vCPUs in th 7400 maximum halt-polling time for all vCPUs in the target VM. This capability can
7810 be invoked at any time and any number of time 7401 be invoked at any time and any number of times to dynamically change the
7811 maximum halt-polling time. 7402 maximum halt-polling time.
7812 7403
7813 See Documentation/virt/kvm/halt-polling.rst f 7404 See Documentation/virt/kvm/halt-polling.rst for more information on halt
7814 polling. 7405 polling.
7815 7406
7816 7.21 KVM_CAP_X86_USER_SPACE_MSR 7407 7.21 KVM_CAP_X86_USER_SPACE_MSR
7817 ------------------------------- 7408 -------------------------------
7818 7409
7819 :Architectures: x86 7410 :Architectures: x86
7820 :Target: VM 7411 :Target: VM
7821 :Parameters: args[0] contains the mask of KVM 7412 :Parameters: args[0] contains the mask of KVM_MSR_EXIT_REASON_* events to report
7822 :Returns: 0 on success; -1 on error 7413 :Returns: 0 on success; -1 on error
7823 7414
7824 This capability allows userspace to intercept 7415 This capability allows userspace to intercept RDMSR and WRMSR instructions if
7825 access to an MSR is denied. By default, KVM 7416 access to an MSR is denied. By default, KVM injects #GP on denied accesses.
7826 7417
7827 When a guest requests to read or write an MSR 7418 When a guest requests to read or write an MSR, KVM may not implement all MSRs
7828 that are relevant to a respective system. It 7419 that are relevant to a respective system. It also does not differentiate by
7829 CPU type. 7420 CPU type.
7830 7421
7831 To allow more fine grained control over MSR h 7422 To allow more fine grained control over MSR handling, userspace may enable
7832 this capability. With it enabled, MSR accesse 7423 this capability. With it enabled, MSR accesses that match the mask specified in
7833 args[0] and would trigger a #GP inside the gu 7424 args[0] and would trigger a #GP inside the guest will instead trigger
7834 KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exi 7425 KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exit notifications. Userspace
7835 can then implement model specific MSR handlin 7426 can then implement model specific MSR handling and/or user notifications
7836 to inform a user that an MSR was not emulated 7427 to inform a user that an MSR was not emulated/virtualized by KVM.
7837 7428
7838 The valid mask flags are: 7429 The valid mask flags are:
7839 7430
7840 ============================ ================ 7431 ============================ ===============================================
7841 KVM_MSR_EXIT_REASON_UNKNOWN intercept access 7432 KVM_MSR_EXIT_REASON_UNKNOWN intercept accesses to unknown (to KVM) MSRs
7842 KVM_MSR_EXIT_REASON_INVAL intercept access 7433 KVM_MSR_EXIT_REASON_INVAL intercept accesses that are architecturally
7843 invalid accordin 7434 invalid according to the vCPU model and/or mode
7844 KVM_MSR_EXIT_REASON_FILTER intercept access 7435 KVM_MSR_EXIT_REASON_FILTER intercept accesses that are denied by userspace
7845 via KVM_X86_SET_ 7436 via KVM_X86_SET_MSR_FILTER
7846 ============================ ================ 7437 ============================ ===============================================
7847 7438
7848 7.22 KVM_CAP_X86_BUS_LOCK_EXIT 7439 7.22 KVM_CAP_X86_BUS_LOCK_EXIT
7849 ------------------------------- 7440 -------------------------------
7850 7441
7851 :Architectures: x86 7442 :Architectures: x86
7852 :Target: VM 7443 :Target: VM
7853 :Parameters: args[0] defines the policy used 7444 :Parameters: args[0] defines the policy used when bus locks detected in guest
7854 :Returns: 0 on success, -EINVAL when args[0] 7445 :Returns: 0 on success, -EINVAL when args[0] contains invalid bits
7855 7446
7856 Valid bits in args[0] are:: 7447 Valid bits in args[0] are::
7857 7448
7858 #define KVM_BUS_LOCK_DETECTION_OFF (1 7449 #define KVM_BUS_LOCK_DETECTION_OFF (1 << 0)
7859 #define KVM_BUS_LOCK_DETECTION_EXIT (1 7450 #define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1)
7860 7451
7861 Enabling this capability on a VM provides use !! 7452 Enabling this capability on a VM provides userspace with a way to select
7862 policy to handle the bus locks detected in gu !! 7453 a policy to handle the bus locks detected in guest. Userspace can obtain
7863 supported modes from the result of KVM_CHECK_ !! 7454 the supported modes from the result of KVM_CHECK_EXTENSION and define it
7864 the KVM_ENABLE_CAP. The supported modes are m !! 7455 through the KVM_ENABLE_CAP.
7865 !! 7456
7866 This capability allows userspace to force VM !! 7457 KVM_BUS_LOCK_DETECTION_OFF and KVM_BUS_LOCK_DETECTION_EXIT are supported
7867 guest, irrespective whether or not the host h !! 7458 currently and mutually exclusive with each other. More bits can be added in
7868 (which triggers an #AC exception that KVM int !! 7459 the future.
7869 intended to mitigate attacks where a maliciou !! 7460
7870 locks to degrade the performance of the whole !! 7461 With KVM_BUS_LOCK_DETECTION_OFF set, bus locks in guest will not cause vm exits
7871 !! 7462 so that no additional actions are needed. This is the default mode.
7872 If KVM_BUS_LOCK_DETECTION_OFF is set, KVM doe !! 7463
7873 exit, although the host kernel's split-lock # !! 7464 With KVM_BUS_LOCK_DETECTION_EXIT set, vm exits happen when bus lock detected
7874 enabled. !! 7465 in VM. KVM just exits to userspace when handling them. Userspace can enforce
7875 !! 7466 its own throttling or other policy based mitigations.
7876 If KVM_BUS_LOCK_DETECTION_EXIT is set, KVM en !! 7467
7877 bus locks in the guest trigger a VM exit, and !! 7468 This capability is aimed to address the thread that VM can exploit bus locks to
7878 such VM exits, e.g. to allow userspace to thr !! 7469 degree the performance of the whole system. Once the userspace enable this
7879 apply some other policy-based mitigation. Whe !! 7470 capability and select the KVM_BUS_LOCK_DETECTION_EXIT mode, KVM will set the
7880 KVM_RUN_X86_BUS_LOCK in vcpu-run->flags, and !! 7471 KVM_RUN_BUS_LOCK flag in vcpu-run->flags field and exit to userspace. Concerning
7881 to KVM_EXIT_X86_BUS_LOCK. !! 7472 the bus lock vm exit can be preempted by a higher priority VM exit, the exit
7882 !! 7473 notifications to userspace can be KVM_EXIT_BUS_LOCK or other reasons.
7883 Note! Detected bus locks may be coincident wi !! 7474 KVM_RUN_BUS_LOCK flag is used to distinguish between them.
7884 KVM_RUN_X86_BUS_LOCK should be checked regard <<
7885 userspace wants to take action on all detecte <<
7886 7475
7887 7.23 KVM_CAP_PPC_DAWR1 7476 7.23 KVM_CAP_PPC_DAWR1
7888 ---------------------- 7477 ----------------------
7889 7478
7890 :Architectures: ppc 7479 :Architectures: ppc
7891 :Parameters: none 7480 :Parameters: none
7892 :Returns: 0 on success, -EINVAL when CPU does 7481 :Returns: 0 on success, -EINVAL when CPU doesn't support 2nd DAWR
7893 7482
7894 This capability can be used to check / enable 7483 This capability can be used to check / enable 2nd DAWR feature provided
7895 by POWER10 processor. 7484 by POWER10 processor.
7896 7485
7897 7486
7898 7.24 KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 7487 7.24 KVM_CAP_VM_COPY_ENC_CONTEXT_FROM
7899 ------------------------------------- 7488 -------------------------------------
7900 7489
7901 Architectures: x86 SEV enabled 7490 Architectures: x86 SEV enabled
7902 Type: vm 7491 Type: vm
7903 Parameters: args[0] is the fd of the source v 7492 Parameters: args[0] is the fd of the source vm
7904 Returns: 0 on success; ENOTTY on error 7493 Returns: 0 on success; ENOTTY on error
7905 7494
7906 This capability enables userspace to copy enc 7495 This capability enables userspace to copy encryption context from the vm
7907 indicated by the fd to the vm this is called 7496 indicated by the fd to the vm this is called on.
7908 7497
7909 This is intended to support in-guest workload 7498 This is intended to support in-guest workloads scheduled by the host. This
7910 allows the in-guest workload to maintain its 7499 allows the in-guest workload to maintain its own NPTs and keeps the two vms
7911 from accidentally clobbering each other with 7500 from accidentally clobbering each other with interrupts and the like (separate
7912 APIC/MSRs/etc). 7501 APIC/MSRs/etc).
7913 7502
7914 7.25 KVM_CAP_SGX_ATTRIBUTE 7503 7.25 KVM_CAP_SGX_ATTRIBUTE
7915 -------------------------- 7504 --------------------------
7916 7505
7917 :Architectures: x86 7506 :Architectures: x86
7918 :Target: VM 7507 :Target: VM
7919 :Parameters: args[0] is a file handle of a SG 7508 :Parameters: args[0] is a file handle of a SGX attribute file in securityfs
7920 :Returns: 0 on success, -EINVAL if the file h 7509 :Returns: 0 on success, -EINVAL if the file handle is invalid or if a requested
7921 attribute is not supported by KVM. 7510 attribute is not supported by KVM.
7922 7511
7923 KVM_CAP_SGX_ATTRIBUTE enables a userspace VMM 7512 KVM_CAP_SGX_ATTRIBUTE enables a userspace VMM to grant a VM access to one or
7924 more privileged enclave attributes. args[0] !! 7513 more priveleged enclave attributes. args[0] must hold a file handle to a valid
7925 SGX attribute file corresponding to an attrib 7514 SGX attribute file corresponding to an attribute that is supported/restricted
7926 by KVM (currently only PROVISIONKEY). 7515 by KVM (currently only PROVISIONKEY).
7927 7516
7928 The SGX subsystem restricts access to a subse 7517 The SGX subsystem restricts access to a subset of enclave attributes to provide
7929 additional security for an uncompromised kern 7518 additional security for an uncompromised kernel, e.g. use of the PROVISIONKEY
7930 is restricted to deter malware from using the 7519 is restricted to deter malware from using the PROVISIONKEY to obtain a stable
7931 system fingerprint. To prevent userspace fro 7520 system fingerprint. To prevent userspace from circumventing such restrictions
7932 by running an enclave in a VM, KVM prevents a 7521 by running an enclave in a VM, KVM prevents access to privileged attributes by
7933 default. 7522 default.
7934 7523
7935 See Documentation/arch/x86/sgx.rst for more d 7524 See Documentation/arch/x86/sgx.rst for more details.
7936 7525
7937 7.26 KVM_CAP_PPC_RPT_INVALIDATE 7526 7.26 KVM_CAP_PPC_RPT_INVALIDATE
7938 ------------------------------- 7527 -------------------------------
7939 7528
7940 :Capability: KVM_CAP_PPC_RPT_INVALIDATE 7529 :Capability: KVM_CAP_PPC_RPT_INVALIDATE
7941 :Architectures: ppc 7530 :Architectures: ppc
7942 :Type: vm 7531 :Type: vm
7943 7532
7944 This capability indicates that the kernel is 7533 This capability indicates that the kernel is capable of handling
7945 H_RPT_INVALIDATE hcall. 7534 H_RPT_INVALIDATE hcall.
7946 7535
7947 In order to enable the use of H_RPT_INVALIDAT 7536 In order to enable the use of H_RPT_INVALIDATE in the guest,
7948 user space might have to advertise it for the 7537 user space might have to advertise it for the guest. For example,
7949 IBM pSeries (sPAPR) guest starts using it if 7538 IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is
7950 present in the "ibm,hypertas-functions" devic 7539 present in the "ibm,hypertas-functions" device-tree property.
7951 7540
7952 This capability is enabled for hypervisors on 7541 This capability is enabled for hypervisors on platforms like POWER9
7953 that support radix MMU. 7542 that support radix MMU.
7954 7543
7955 7.27 KVM_CAP_EXIT_ON_EMULATION_FAILURE 7544 7.27 KVM_CAP_EXIT_ON_EMULATION_FAILURE
7956 -------------------------------------- 7545 --------------------------------------
7957 7546
7958 :Architectures: x86 7547 :Architectures: x86
7959 :Parameters: args[0] whether the feature shou 7548 :Parameters: args[0] whether the feature should be enabled or not
7960 7549
7961 When this capability is enabled, an emulation 7550 When this capability is enabled, an emulation failure will result in an exit
7962 to userspace with KVM_INTERNAL_ERROR (except 7551 to userspace with KVM_INTERNAL_ERROR (except when the emulator was invoked
7963 to handle a VMware backdoor instruction). Fur 7552 to handle a VMware backdoor instruction). Furthermore, KVM will now provide up
7964 to 15 instruction bytes for any exit to users 7553 to 15 instruction bytes for any exit to userspace resulting from an emulation
7965 failure. When these exits to userspace occur 7554 failure. When these exits to userspace occur use the emulation_failure struct
7966 instead of the internal struct. They both ha 7555 instead of the internal struct. They both have the same layout, but the
7967 emulation_failure struct matches the content 7556 emulation_failure struct matches the content better. It also explicitly
7968 defines the 'flags' field which is used to de 7557 defines the 'flags' field which is used to describe the fields in the struct
7969 that are valid (ie: if KVM_INTERNAL_ERROR_EMU 7558 that are valid (ie: if KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES is
7970 set in the 'flags' field then both 'insn_size 7559 set in the 'flags' field then both 'insn_size' and 'insn_bytes' have valid data
7971 in them.) 7560 in them.)
7972 7561
7973 7.28 KVM_CAP_ARM_MTE 7562 7.28 KVM_CAP_ARM_MTE
7974 -------------------- 7563 --------------------
7975 7564
7976 :Architectures: arm64 7565 :Architectures: arm64
7977 :Parameters: none 7566 :Parameters: none
7978 7567
7979 This capability indicates that KVM (and the h 7568 This capability indicates that KVM (and the hardware) supports exposing the
7980 Memory Tagging Extensions (MTE) to the guest. 7569 Memory Tagging Extensions (MTE) to the guest. It must also be enabled by the
7981 VMM before creating any VCPUs to allow the gu 7570 VMM before creating any VCPUs to allow the guest access. Note that MTE is only
7982 available to a guest running in AArch64 mode 7571 available to a guest running in AArch64 mode and enabling this capability will
7983 cause attempts to create AArch32 VCPUs to fai 7572 cause attempts to create AArch32 VCPUs to fail.
7984 7573
7985 When enabled the guest is able to access tags 7574 When enabled the guest is able to access tags associated with any memory given
7986 to the guest. KVM will ensure that the tags a 7575 to the guest. KVM will ensure that the tags are maintained during swap or
7987 hibernation of the host; however the VMM need 7576 hibernation of the host; however the VMM needs to manually save/restore the
7988 tags as appropriate if the VM is migrated. 7577 tags as appropriate if the VM is migrated.
7989 7578
7990 When this capability is enabled all memory in 7579 When this capability is enabled all memory in memslots must be mapped as
7991 ``MAP_ANONYMOUS`` or with a RAM-based file ma 7580 ``MAP_ANONYMOUS`` or with a RAM-based file mapping (``tmpfs``, ``memfd``),
7992 attempts to create a memslot with an invalid 7581 attempts to create a memslot with an invalid mmap will result in an
7993 -EINVAL return. 7582 -EINVAL return.
7994 7583
7995 When enabled the VMM may make use of the ``KV 7584 When enabled the VMM may make use of the ``KVM_ARM_MTE_COPY_TAGS`` ioctl to
7996 perform a bulk copy of tags to/from the guest 7585 perform a bulk copy of tags to/from the guest.
7997 7586
7998 7.29 KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 7587 7.29 KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM
7999 ------------------------------------- 7588 -------------------------------------
8000 7589
8001 :Architectures: x86 SEV enabled !! 7590 Architectures: x86 SEV enabled
8002 :Type: vm !! 7591 Type: vm
8003 :Parameters: args[0] is the fd of the source !! 7592 Parameters: args[0] is the fd of the source vm
8004 :Returns: 0 on success !! 7593 Returns: 0 on success
8005 7594
8006 This capability enables userspace to migrate 7595 This capability enables userspace to migrate the encryption context from the VM
8007 indicated by the fd to the VM this is called 7596 indicated by the fd to the VM this is called on.
8008 7597
8009 This is intended to support intra-host migrat 7598 This is intended to support intra-host migration of VMs between userspace VMMs,
8010 upgrading the VMM process without interruptin 7599 upgrading the VMM process without interrupting the guest.
8011 7600
8012 7.30 KVM_CAP_PPC_AIL_MODE_3 7601 7.30 KVM_CAP_PPC_AIL_MODE_3
8013 ------------------------------- 7602 -------------------------------
8014 7603
8015 :Capability: KVM_CAP_PPC_AIL_MODE_3 7604 :Capability: KVM_CAP_PPC_AIL_MODE_3
8016 :Architectures: ppc 7605 :Architectures: ppc
8017 :Type: vm 7606 :Type: vm
8018 7607
8019 This capability indicates that the kernel sup 7608 This capability indicates that the kernel supports the mode 3 setting for the
8020 "Address Translation Mode on Interrupt" aka " 7609 "Address Translation Mode on Interrupt" aka "Alternate Interrupt Location"
8021 resource that is controlled with the H_SET_MO 7610 resource that is controlled with the H_SET_MODE hypercall.
8022 7611
8023 This capability allows a guest kernel to use 7612 This capability allows a guest kernel to use a better-performance mode for
8024 handling interrupts and system calls. 7613 handling interrupts and system calls.
8025 7614
8026 7.31 KVM_CAP_DISABLE_QUIRKS2 7615 7.31 KVM_CAP_DISABLE_QUIRKS2
8027 ---------------------------- 7616 ----------------------------
8028 7617
8029 :Capability: KVM_CAP_DISABLE_QUIRKS2 7618 :Capability: KVM_CAP_DISABLE_QUIRKS2
8030 :Parameters: args[0] - set of KVM quirks to d 7619 :Parameters: args[0] - set of KVM quirks to disable
8031 :Architectures: x86 7620 :Architectures: x86
8032 :Type: vm 7621 :Type: vm
8033 7622
8034 This capability, if enabled, will cause KVM t 7623 This capability, if enabled, will cause KVM to disable some behavior
8035 quirks. 7624 quirks.
8036 7625
8037 Calling KVM_CHECK_EXTENSION for this capabili 7626 Calling KVM_CHECK_EXTENSION for this capability returns a bitmask of
8038 quirks that can be disabled in KVM. 7627 quirks that can be disabled in KVM.
8039 7628
8040 The argument to KVM_ENABLE_CAP for this capab 7629 The argument to KVM_ENABLE_CAP for this capability is a bitmask of
8041 quirks to disable, and must be a subset of th 7630 quirks to disable, and must be a subset of the bitmask returned by
8042 KVM_CHECK_EXTENSION. 7631 KVM_CHECK_EXTENSION.
8043 7632
8044 The valid bits in cap.args[0] are: 7633 The valid bits in cap.args[0] are:
8045 7634
8046 =================================== ========= 7635 =================================== ============================================
8047 KVM_X86_QUIRK_LINT0_REENABLED By defaul 7636 KVM_X86_QUIRK_LINT0_REENABLED By default, the reset value for the LVT
8048 LINT0 reg 7637 LINT0 register is 0x700 (APIC_MODE_EXTINT).
8049 When this 7638 When this quirk is disabled, the reset value
8050 is 0x1000 7639 is 0x10000 (APIC_LVT_MASKED).
8051 7640
8052 KVM_X86_QUIRK_CD_NW_CLEARED By defaul !! 7641 KVM_X86_QUIRK_CD_NW_CLEARED By default, KVM clears CR0.CD and CR0.NW.
8053 AMD CPUs <<
8054 that runs <<
8055 with cach <<
8056 <<
8057 When this 7642 When this quirk is disabled, KVM does not
8058 change th 7643 change the value of CR0.CD and CR0.NW.
8059 7644
8060 KVM_X86_QUIRK_LAPIC_MMIO_HOLE By defaul 7645 KVM_X86_QUIRK_LAPIC_MMIO_HOLE By default, the MMIO LAPIC interface is
8061 available 7646 available even when configured for x2APIC
8062 mode. Whe 7647 mode. When this quirk is disabled, KVM
8063 disables 7648 disables the MMIO LAPIC interface if the
8064 LAPIC is 7649 LAPIC is in x2APIC mode.
8065 7650
8066 KVM_X86_QUIRK_OUT_7E_INC_RIP By defaul 7651 KVM_X86_QUIRK_OUT_7E_INC_RIP By default, KVM pre-increments %rip before
8067 exiting t 7652 exiting to userspace for an OUT instruction
8068 to port 0 7653 to port 0x7e. When this quirk is disabled,
8069 KVM does 7654 KVM does not pre-increment %rip before
8070 exiting t 7655 exiting to userspace.
8071 7656
8072 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT When this 7657 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT When this quirk is disabled, KVM sets
8073 CPUID.01H 7658 CPUID.01H:ECX[bit 3] (MONITOR/MWAIT) if
8074 IA32_MISC 7659 IA32_MISC_ENABLE[bit 18] (MWAIT) is set.
8075 Additiona 7660 Additionally, when this quirk is disabled,
8076 KVM clear 7661 KVM clears CPUID.01H:ECX[bit 3] if
8077 IA32_MISC 7662 IA32_MISC_ENABLE[bit 18] is cleared.
8078 7663
8079 KVM_X86_QUIRK_FIX_HYPERCALL_INSN By defaul 7664 KVM_X86_QUIRK_FIX_HYPERCALL_INSN By default, KVM rewrites guest
8080 VMMCALL/V 7665 VMMCALL/VMCALL instructions to match the
8081 vendor's 7666 vendor's hypercall instruction for the
8082 system. W 7667 system. When this quirk is disabled, KVM
8083 will no l 7668 will no longer rewrite invalid guest
8084 hypercall 7669 hypercall instructions. Executing the
8085 incorrect 7670 incorrect hypercall instruction will
8086 generate 7671 generate a #UD within the guest.
8087 7672
8088 KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By defaul 7673 KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if
8089 they are 7674 they are intercepted) as NOPs regardless of
8090 whether o 7675 whether or not MONITOR/MWAIT are supported
8091 according 7676 according to guest CPUID. When this quirk
8092 is disabl 7677 is disabled and KVM_X86_DISABLE_EXITS_MWAIT
8093 is not se 7678 is not set (MONITOR/MWAIT are intercepted),
8094 KVM will 7679 KVM will inject a #UD on MONITOR/MWAIT if
8095 they're u 7680 they're unsupported per guest CPUID. Note,
8096 KVM will 7681 KVM will modify MONITOR/MWAIT support in
8097 guest CPU 7682 guest CPUID on writes to MISC_ENABLE if
8098 KVM_X86_Q 7683 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is
8099 disabled. 7684 disabled.
8100 <<
8101 KVM_X86_QUIRK_SLOT_ZAP_ALL By defaul <<
8102 invalidat <<
8103 address s <<
8104 moved. W <<
8105 VM type i <<
8106 ensures t <<
8107 or moved <<
8108 _may_ inv <<
8109 memslot. <<
8110 =================================== ========= 7685 =================================== ============================================
8111 7686
8112 7.32 KVM_CAP_MAX_VCPU_ID 7687 7.32 KVM_CAP_MAX_VCPU_ID
8113 ------------------------ 7688 ------------------------
8114 7689
8115 :Architectures: x86 7690 :Architectures: x86
8116 :Target: VM 7691 :Target: VM
8117 :Parameters: args[0] - maximum APIC ID value 7692 :Parameters: args[0] - maximum APIC ID value set for current VM
8118 :Returns: 0 on success, -EINVAL if args[0] is 7693 :Returns: 0 on success, -EINVAL if args[0] is beyond KVM_MAX_VCPU_IDS
8119 supported in KVM or if it has been 7694 supported in KVM or if it has been set.
8120 7695
8121 This capability allows userspace to specify m 7696 This capability allows userspace to specify maximum possible APIC ID
8122 assigned for current VM session prior to the 7697 assigned for current VM session prior to the creation of vCPUs, saving
8123 memory for data structures indexed by the API 7698 memory for data structures indexed by the APIC ID. Userspace is able
8124 to calculate the limit to APIC ID values from 7699 to calculate the limit to APIC ID values from designated
8125 CPU topology. 7700 CPU topology.
8126 7701
8127 The value can be changed only until KVM_ENABL 7702 The value can be changed only until KVM_ENABLE_CAP is set to a nonzero
8128 value or until a vCPU is created. Upon creat 7703 value or until a vCPU is created. Upon creation of the first vCPU,
8129 if the value was set to zero or KVM_ENABLE_CA 7704 if the value was set to zero or KVM_ENABLE_CAP was not invoked, KVM
8130 uses the return value of KVM_CHECK_EXTENSION( 7705 uses the return value of KVM_CHECK_EXTENSION(KVM_CAP_MAX_VCPU_ID) as
8131 the maximum APIC ID. 7706 the maximum APIC ID.
8132 7707
8133 7.33 KVM_CAP_X86_NOTIFY_VMEXIT 7708 7.33 KVM_CAP_X86_NOTIFY_VMEXIT
8134 ------------------------------ 7709 ------------------------------
8135 7710
8136 :Architectures: x86 7711 :Architectures: x86
8137 :Target: VM 7712 :Target: VM
8138 :Parameters: args[0] is the value of notify w 7713 :Parameters: args[0] is the value of notify window as well as some flags
8139 :Returns: 0 on success, -EINVAL if args[0] co 7714 :Returns: 0 on success, -EINVAL if args[0] contains invalid flags or notify
8140 VM exit is unsupported. 7715 VM exit is unsupported.
8141 7716
8142 Bits 63:32 of args[0] are used for notify win 7717 Bits 63:32 of args[0] are used for notify window.
8143 Bits 31:0 of args[0] are for some flags. Vali 7718 Bits 31:0 of args[0] are for some flags. Valid bits are::
8144 7719
8145 #define KVM_X86_NOTIFY_VMEXIT_ENABLED (1 7720 #define KVM_X86_NOTIFY_VMEXIT_ENABLED (1 << 0)
8146 #define KVM_X86_NOTIFY_VMEXIT_USER (1 7721 #define KVM_X86_NOTIFY_VMEXIT_USER (1 << 1)
8147 7722
8148 This capability allows userspace to configure 7723 This capability allows userspace to configure the notify VM exit on/off
8149 in per-VM scope during VM creation. Notify VM 7724 in per-VM scope during VM creation. Notify VM exit is disabled by default.
8150 When userspace sets KVM_X86_NOTIFY_VMEXIT_ENA 7725 When userspace sets KVM_X86_NOTIFY_VMEXIT_ENABLED bit in args[0], VMM will
8151 enable this feature with the notify window pr 7726 enable this feature with the notify window provided, which will generate
8152 a VM exit if no event window occurs in VM non 7727 a VM exit if no event window occurs in VM non-root mode for a specified of
8153 time (notify window). 7728 time (notify window).
8154 7729
8155 If KVM_X86_NOTIFY_VMEXIT_USER is set in args[ 7730 If KVM_X86_NOTIFY_VMEXIT_USER is set in args[0], upon notify VM exits happen,
8156 KVM would exit to userspace for handling. 7731 KVM would exit to userspace for handling.
8157 7732
8158 This capability is aimed to mitigate the thre 7733 This capability is aimed to mitigate the threat that malicious VMs can
8159 cause CPU stuck (due to event windows don't o 7734 cause CPU stuck (due to event windows don't open up) and make the CPU
8160 unavailable to host or other VMs. 7735 unavailable to host or other VMs.
8161 7736
8162 7.34 KVM_CAP_MEMORY_FAULT_INFO <<
8163 ------------------------------ <<
8164 <<
8165 :Architectures: x86 <<
8166 :Returns: Informational only, -EINVAL on dire <<
8167 <<
8168 The presence of this capability indicates tha <<
8169 kvm_run.memory_fault if KVM cannot resolve a <<
8170 there is a valid memslot but no backing VMA f <<
8171 address. <<
8172 <<
8173 The information in kvm_run.memory_fault is va <<
8174 an error with errno=EFAULT or errno=EHWPOISON <<
8175 to KVM_EXIT_MEMORY_FAULT. <<
8176 <<
8177 Note: Userspaces which attempt to resolve mem <<
8178 KVM_RUN are encouraged to guard against repea <<
8179 error/annotated fault. <<
8180 <<
8181 See KVM_EXIT_MEMORY_FAULT for more informatio <<
8182 <<
8183 7.35 KVM_CAP_X86_APIC_BUS_CYCLES_NS <<
8184 ----------------------------------- <<
8185 <<
8186 :Architectures: x86 <<
8187 :Target: VM <<
8188 :Parameters: args[0] is the desired APIC bus <<
8189 :Returns: 0 on success, -EINVAL if args[0] co <<
8190 frequency or if any vCPUs have been <<
8191 local APIC has not been created usi <<
8192 <<
8193 This capability sets the VM's APIC bus clock <<
8194 virtual APIC when emulating APIC timers. KVM <<
8195 by KVM_CHECK_EXTENSION. <<
8196 <<
8197 Note: Userspace is responsible for correctly <<
8198 core crystal clock frequency, if a non-zero C <<
8199 <<
8200 7.36 KVM_CAP_X86_GUEST_MODE <<
8201 ------------------------------ <<
8202 <<
8203 :Architectures: x86 <<
8204 :Returns: Informational only, -EINVAL on dire <<
8205 <<
8206 The presence of this capability indicates tha <<
8207 KVM_RUN_X86_GUEST_MODE bit in kvm_run.flags t <<
8208 vCPU was executing nested guest code when it <<
8209 <<
8210 KVM exits with the register state of either t <<
8211 depending on which executed at the time of an <<
8212 take care to differentiate between these case <<
8213 <<
8214 8. Other capabilities. 7737 8. Other capabilities.
8215 ====================== 7738 ======================
8216 7739
8217 This section lists capabilities that give inf 7740 This section lists capabilities that give information about other
8218 features of the KVM implementation. 7741 features of the KVM implementation.
8219 7742
8220 8.1 KVM_CAP_PPC_HWRNG 7743 8.1 KVM_CAP_PPC_HWRNG
8221 --------------------- 7744 ---------------------
8222 7745
8223 :Architectures: ppc 7746 :Architectures: ppc
8224 7747
8225 This capability, if KVM_CHECK_EXTENSION indic 7748 This capability, if KVM_CHECK_EXTENSION indicates that it is
8226 available, means that the kernel has an imple 7749 available, means that the kernel has an implementation of the
8227 H_RANDOM hypercall backed by a hardware rando 7750 H_RANDOM hypercall backed by a hardware random-number generator.
8228 If present, the kernel H_RANDOM handler can b 7751 If present, the kernel H_RANDOM handler can be enabled for guest use
8229 with the KVM_CAP_PPC_ENABLE_HCALL capability. 7752 with the KVM_CAP_PPC_ENABLE_HCALL capability.
8230 7753
8231 8.2 KVM_CAP_HYPERV_SYNIC 7754 8.2 KVM_CAP_HYPERV_SYNIC
8232 ------------------------ 7755 ------------------------
8233 7756
8234 :Architectures: x86 7757 :Architectures: x86
8235 7758
8236 This capability, if KVM_CHECK_EXTENSION indic 7759 This capability, if KVM_CHECK_EXTENSION indicates that it is
8237 available, means that the kernel has an imple 7760 available, means that the kernel has an implementation of the
8238 Hyper-V Synthetic interrupt controller(SynIC) 7761 Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is
8239 used to support Windows Hyper-V based guest p 7762 used to support Windows Hyper-V based guest paravirt drivers(VMBus).
8240 7763
8241 In order to use SynIC, it has to be activated 7764 In order to use SynIC, it has to be activated by setting this
8242 capability via KVM_ENABLE_CAP ioctl on the vc 7765 capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this
8243 will disable the use of APIC hardware virtual 7766 will disable the use of APIC hardware virtualization even if supported
8244 by the CPU, as it's incompatible with SynIC a 7767 by the CPU, as it's incompatible with SynIC auto-EOI behavior.
8245 7768
8246 8.3 KVM_CAP_PPC_MMU_RADIX !! 7769 8.3 KVM_CAP_PPC_RADIX_MMU
8247 ------------------------- 7770 -------------------------
8248 7771
8249 :Architectures: ppc 7772 :Architectures: ppc
8250 7773
8251 This capability, if KVM_CHECK_EXTENSION indic 7774 This capability, if KVM_CHECK_EXTENSION indicates that it is
8252 available, means that the kernel can support 7775 available, means that the kernel can support guests using the
8253 radix MMU defined in Power ISA V3.00 (as impl 7776 radix MMU defined in Power ISA V3.00 (as implemented in the POWER9
8254 processor). 7777 processor).
8255 7778
8256 8.4 KVM_CAP_PPC_MMU_HASH_V3 !! 7779 8.4 KVM_CAP_PPC_HASH_MMU_V3
8257 --------------------------- 7780 ---------------------------
8258 7781
8259 :Architectures: ppc 7782 :Architectures: ppc
8260 7783
8261 This capability, if KVM_CHECK_EXTENSION indic 7784 This capability, if KVM_CHECK_EXTENSION indicates that it is
8262 available, means that the kernel can support 7785 available, means that the kernel can support guests using the
8263 hashed page table MMU defined in Power ISA V3 7786 hashed page table MMU defined in Power ISA V3.00 (as implemented in
8264 the POWER9 processor), including in-memory se 7787 the POWER9 processor), including in-memory segment tables.
8265 7788
8266 8.5 KVM_CAP_MIPS_VZ 7789 8.5 KVM_CAP_MIPS_VZ
8267 ------------------- 7790 -------------------
8268 7791
8269 :Architectures: mips 7792 :Architectures: mips
8270 7793
8271 This capability, if KVM_CHECK_EXTENSION on th 7794 This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
8272 it is available, means that full hardware ass 7795 it is available, means that full hardware assisted virtualization capabilities
8273 of the hardware are available for use through 7796 of the hardware are available for use through KVM. An appropriate
8274 KVM_VM_MIPS_* type must be passed to KVM_CREA 7797 KVM_VM_MIPS_* type must be passed to KVM_CREATE_VM to create a VM which
8275 utilises it. 7798 utilises it.
8276 7799
8277 If KVM_CHECK_EXTENSION on a kvm VM handle ind 7800 If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is
8278 available, it means that the VM is using full 7801 available, it means that the VM is using full hardware assisted virtualization
8279 capabilities of the hardware. This is useful 7802 capabilities of the hardware. This is useful to check after creating a VM with
8280 KVM_VM_MIPS_DEFAULT. 7803 KVM_VM_MIPS_DEFAULT.
8281 7804
8282 The value returned by KVM_CHECK_EXTENSION sho 7805 The value returned by KVM_CHECK_EXTENSION should be compared against known
8283 values (see below). All other values are rese 7806 values (see below). All other values are reserved. This is to allow for the
8284 possibility of other hardware assisted virtua 7807 possibility of other hardware assisted virtualization implementations which
8285 may be incompatible with the MIPS VZ ASE. 7808 may be incompatible with the MIPS VZ ASE.
8286 7809
8287 == ========================================= 7810 == ==========================================================================
8288 0 The trap & emulate implementation is in u 7811 0 The trap & emulate implementation is in use to run guest code in user
8289 mode. Guest virtual memory segments are r 7812 mode. Guest virtual memory segments are rearranged to fit the guest in the
8290 user mode address space. 7813 user mode address space.
8291 7814
8292 1 The MIPS VZ ASE is in use, providing full 7815 1 The MIPS VZ ASE is in use, providing full hardware assisted
8293 virtualization, including standard guest 7816 virtualization, including standard guest virtual memory segments.
8294 == ========================================= 7817 == ==========================================================================
8295 7818
8296 8.6 KVM_CAP_MIPS_TE 7819 8.6 KVM_CAP_MIPS_TE
8297 ------------------- 7820 -------------------
8298 7821
8299 :Architectures: mips 7822 :Architectures: mips
8300 7823
8301 This capability, if KVM_CHECK_EXTENSION on th 7824 This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
8302 it is available, means that the trap & emulat 7825 it is available, means that the trap & emulate implementation is available to
8303 run guest code in user mode, even if KVM_CAP_ 7826 run guest code in user mode, even if KVM_CAP_MIPS_VZ indicates that hardware
8304 assisted virtualisation is also available. KV 7827 assisted virtualisation is also available. KVM_VM_MIPS_TE (0) must be passed
8305 to KVM_CREATE_VM to create a VM which utilise 7828 to KVM_CREATE_VM to create a VM which utilises it.
8306 7829
8307 If KVM_CHECK_EXTENSION on a kvm VM handle ind 7830 If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is
8308 available, it means that the VM is using trap 7831 available, it means that the VM is using trap & emulate.
8309 7832
8310 8.7 KVM_CAP_MIPS_64BIT 7833 8.7 KVM_CAP_MIPS_64BIT
8311 ---------------------- 7834 ----------------------
8312 7835
8313 :Architectures: mips 7836 :Architectures: mips
8314 7837
8315 This capability indicates the supported archi 7838 This capability indicates the supported architecture type of the guest, i.e. the
8316 supported register and address width. 7839 supported register and address width.
8317 7840
8318 The values returned when this capability is c 7841 The values returned when this capability is checked by KVM_CHECK_EXTENSION on a
8319 kvm VM handle correspond roughly to the CP0_C 7842 kvm VM handle correspond roughly to the CP0_Config.AT register field, and should
8320 be checked specifically against known values 7843 be checked specifically against known values (see below). All other values are
8321 reserved. 7844 reserved.
8322 7845
8323 == ========================================= 7846 == ========================================================================
8324 0 MIPS32 or microMIPS32. 7847 0 MIPS32 or microMIPS32.
8325 Both registers and addresses are 32-bits 7848 Both registers and addresses are 32-bits wide.
8326 It will only be possible to run 32-bit gu 7849 It will only be possible to run 32-bit guest code.
8327 7850
8328 1 MIPS64 or microMIPS64 with access only to 7851 1 MIPS64 or microMIPS64 with access only to 32-bit compatibility segments.
8329 Registers are 64-bits wide, but addresses 7852 Registers are 64-bits wide, but addresses are 32-bits wide.
8330 64-bit guest code may run but cannot acce 7853 64-bit guest code may run but cannot access MIPS64 memory segments.
8331 It will also be possible to run 32-bit gu 7854 It will also be possible to run 32-bit guest code.
8332 7855
8333 2 MIPS64 or microMIPS64 with access to all 7856 2 MIPS64 or microMIPS64 with access to all address segments.
8334 Both registers and addresses are 64-bits 7857 Both registers and addresses are 64-bits wide.
8335 It will be possible to run 64-bit or 32-b 7858 It will be possible to run 64-bit or 32-bit guest code.
8336 == ========================================= 7859 == ========================================================================
8337 7860
8338 8.9 KVM_CAP_ARM_USER_IRQ 7861 8.9 KVM_CAP_ARM_USER_IRQ
8339 ------------------------ 7862 ------------------------
8340 7863
8341 :Architectures: arm64 7864 :Architectures: arm64
8342 7865
8343 This capability, if KVM_CHECK_EXTENSION indic 7866 This capability, if KVM_CHECK_EXTENSION indicates that it is available, means
8344 that if userspace creates a VM without an in- 7867 that if userspace creates a VM without an in-kernel interrupt controller, it
8345 will be notified of changes to the output lev 7868 will be notified of changes to the output level of in-kernel emulated devices,
8346 which can generate virtual interrupts, presen 7869 which can generate virtual interrupts, presented to the VM.
8347 For such VMs, on every return to userspace, t 7870 For such VMs, on every return to userspace, the kernel
8348 updates the vcpu's run->s.regs.device_irq_lev 7871 updates the vcpu's run->s.regs.device_irq_level field to represent the actual
8349 output level of the device. 7872 output level of the device.
8350 7873
8351 Whenever kvm detects a change in the device o 7874 Whenever kvm detects a change in the device output level, kvm guarantees at
8352 least one return to userspace before running 7875 least one return to userspace before running the VM. This exit could either
8353 be a KVM_EXIT_INTR or any other exit event, l 7876 be a KVM_EXIT_INTR or any other exit event, like KVM_EXIT_MMIO. This way,
8354 userspace can always sample the device output 7877 userspace can always sample the device output level and re-compute the state of
8355 the userspace interrupt controller. Userspac 7878 the userspace interrupt controller. Userspace should always check the state
8356 of run->s.regs.device_irq_level on every kvm 7879 of run->s.regs.device_irq_level on every kvm exit.
8357 The value in run->s.regs.device_irq_level can 7880 The value in run->s.regs.device_irq_level can represent both level and edge
8358 triggered interrupt signals, depending on the 7881 triggered interrupt signals, depending on the device. Edge triggered interrupt
8359 signals will exit to userspace with the bit i 7882 signals will exit to userspace with the bit in run->s.regs.device_irq_level
8360 set exactly once per edge signal. 7883 set exactly once per edge signal.
8361 7884
8362 The field run->s.regs.device_irq_level is ava 7885 The field run->s.regs.device_irq_level is available independent of
8363 run->kvm_valid_regs or run->kvm_dirty_regs bi 7886 run->kvm_valid_regs or run->kvm_dirty_regs bits.
8364 7887
8365 If KVM_CAP_ARM_USER_IRQ is supported, the KVM 7888 If KVM_CAP_ARM_USER_IRQ is supported, the KVM_CHECK_EXTENSION ioctl returns a
8366 number larger than 0 indicating the version o 7889 number larger than 0 indicating the version of this capability is implemented
8367 and thereby which bits in run->s.regs.device_ 7890 and thereby which bits in run->s.regs.device_irq_level can signal values.
8368 7891
8369 Currently the following bits are defined for 7892 Currently the following bits are defined for the device_irq_level bitmap::
8370 7893
8371 KVM_CAP_ARM_USER_IRQ >= 1: 7894 KVM_CAP_ARM_USER_IRQ >= 1:
8372 7895
8373 KVM_ARM_DEV_EL1_VTIMER - EL1 virtual tim 7896 KVM_ARM_DEV_EL1_VTIMER - EL1 virtual timer
8374 KVM_ARM_DEV_EL1_PTIMER - EL1 physical ti 7897 KVM_ARM_DEV_EL1_PTIMER - EL1 physical timer
8375 KVM_ARM_DEV_PMU - ARM PMU overflo 7898 KVM_ARM_DEV_PMU - ARM PMU overflow interrupt signal
8376 7899
8377 Future versions of kvm may implement addition 7900 Future versions of kvm may implement additional events. These will get
8378 indicated by returning a higher number from K 7901 indicated by returning a higher number from KVM_CHECK_EXTENSION and will be
8379 listed above. 7902 listed above.
8380 7903
8381 8.10 KVM_CAP_PPC_SMT_POSSIBLE 7904 8.10 KVM_CAP_PPC_SMT_POSSIBLE
8382 ----------------------------- 7905 -----------------------------
8383 7906
8384 :Architectures: ppc 7907 :Architectures: ppc
8385 7908
8386 Querying this capability returns a bitmap ind 7909 Querying this capability returns a bitmap indicating the possible
8387 virtual SMT modes that can be set using KVM_C 7910 virtual SMT modes that can be set using KVM_CAP_PPC_SMT. If bit N
8388 (counting from the right) is set, then a virt 7911 (counting from the right) is set, then a virtual SMT mode of 2^N is
8389 available. 7912 available.
8390 7913
8391 8.11 KVM_CAP_HYPERV_SYNIC2 7914 8.11 KVM_CAP_HYPERV_SYNIC2
8392 -------------------------- 7915 --------------------------
8393 7916
8394 :Architectures: x86 7917 :Architectures: x86
8395 7918
8396 This capability enables a newer version of Hy 7919 This capability enables a newer version of Hyper-V Synthetic interrupt
8397 controller (SynIC). The only difference with 7920 controller (SynIC). The only difference with KVM_CAP_HYPERV_SYNIC is that KVM
8398 doesn't clear SynIC message and event flags p 7921 doesn't clear SynIC message and event flags pages when they are enabled by
8399 writing to the respective MSRs. 7922 writing to the respective MSRs.
8400 7923
8401 8.12 KVM_CAP_HYPERV_VP_INDEX 7924 8.12 KVM_CAP_HYPERV_VP_INDEX
8402 ---------------------------- 7925 ----------------------------
8403 7926
8404 :Architectures: x86 7927 :Architectures: x86
8405 7928
8406 This capability indicates that userspace can 7929 This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr. Its
8407 value is used to denote the target vcpu for a 7930 value is used to denote the target vcpu for a SynIC interrupt. For
8408 compatibility, KVM initializes this msr to KV !! 7931 compatibilty, KVM initializes this msr to KVM's internal vcpu index. When this
8409 capability is absent, userspace can still que 7932 capability is absent, userspace can still query this msr's value.
8410 7933
8411 8.13 KVM_CAP_S390_AIS_MIGRATION 7934 8.13 KVM_CAP_S390_AIS_MIGRATION
8412 ------------------------------- 7935 -------------------------------
8413 7936
8414 :Architectures: s390 7937 :Architectures: s390
8415 :Parameters: none 7938 :Parameters: none
8416 7939
8417 This capability indicates if the flic device 7940 This capability indicates if the flic device will be able to get/set the
8418 AIS states for migration via the KVM_DEV_FLIC 7941 AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows
8419 to discover this without having to create a f 7942 to discover this without having to create a flic device.
8420 7943
8421 8.14 KVM_CAP_S390_PSW 7944 8.14 KVM_CAP_S390_PSW
8422 --------------------- 7945 ---------------------
8423 7946
8424 :Architectures: s390 7947 :Architectures: s390
8425 7948
8426 This capability indicates that the PSW is exp 7949 This capability indicates that the PSW is exposed via the kvm_run structure.
8427 7950
8428 8.15 KVM_CAP_S390_GMAP 7951 8.15 KVM_CAP_S390_GMAP
8429 ---------------------- 7952 ----------------------
8430 7953
8431 :Architectures: s390 7954 :Architectures: s390
8432 7955
8433 This capability indicates that the user space 7956 This capability indicates that the user space memory used as guest mapping can
8434 be anywhere in the user memory address space, 7957 be anywhere in the user memory address space, as long as the memory slots are
8435 aligned and sized to a segment (1MB) boundary 7958 aligned and sized to a segment (1MB) boundary.
8436 7959
8437 8.16 KVM_CAP_S390_COW 7960 8.16 KVM_CAP_S390_COW
8438 --------------------- 7961 ---------------------
8439 7962
8440 :Architectures: s390 7963 :Architectures: s390
8441 7964
8442 This capability indicates that the user space 7965 This capability indicates that the user space memory used as guest mapping can
8443 use copy-on-write semantics as well as dirty 7966 use copy-on-write semantics as well as dirty pages tracking via read-only page
8444 tables. 7967 tables.
8445 7968
8446 8.17 KVM_CAP_S390_BPB 7969 8.17 KVM_CAP_S390_BPB
8447 --------------------- 7970 ---------------------
8448 7971
8449 :Architectures: s390 7972 :Architectures: s390
8450 7973
8451 This capability indicates that kvm will imple 7974 This capability indicates that kvm will implement the interfaces to handle
8452 reset, migration and nested KVM for branch pr 7975 reset, migration and nested KVM for branch prediction blocking. The stfle
8453 facility 82 should not be provided to the gue 7976 facility 82 should not be provided to the guest without this capability.
8454 7977
8455 8.18 KVM_CAP_HYPERV_TLBFLUSH 7978 8.18 KVM_CAP_HYPERV_TLBFLUSH
8456 ---------------------------- 7979 ----------------------------
8457 7980
8458 :Architectures: x86 7981 :Architectures: x86
8459 7982
8460 This capability indicates that KVM supports p 7983 This capability indicates that KVM supports paravirtualized Hyper-V TLB Flush
8461 hypercalls: 7984 hypercalls:
8462 HvFlushVirtualAddressSpace, HvFlushVirtualAdd 7985 HvFlushVirtualAddressSpace, HvFlushVirtualAddressSpaceEx,
8463 HvFlushVirtualAddressList, HvFlushVirtualAddr 7986 HvFlushVirtualAddressList, HvFlushVirtualAddressListEx.
8464 7987
8465 8.19 KVM_CAP_ARM_INJECT_SERROR_ESR 7988 8.19 KVM_CAP_ARM_INJECT_SERROR_ESR
8466 ---------------------------------- 7989 ----------------------------------
8467 7990
8468 :Architectures: arm64 7991 :Architectures: arm64
8469 7992
8470 This capability indicates that userspace can 7993 This capability indicates that userspace can specify (via the
8471 KVM_SET_VCPU_EVENTS ioctl) the syndrome value 7994 KVM_SET_VCPU_EVENTS ioctl) the syndrome value reported to the guest when it
8472 takes a virtual SError interrupt exception. 7995 takes a virtual SError interrupt exception.
8473 If KVM advertises this capability, userspace 7996 If KVM advertises this capability, userspace can only specify the ISS field for
8474 the ESR syndrome. Other parts of the ESR, suc 7997 the ESR syndrome. Other parts of the ESR, such as the EC are generated by the
8475 CPU when the exception is taken. If this virt 7998 CPU when the exception is taken. If this virtual SError is taken to EL1 using
8476 AArch64, this value will be reported in the I 7999 AArch64, this value will be reported in the ISS field of ESR_ELx.
8477 8000
8478 See KVM_CAP_VCPU_EVENTS for more details. 8001 See KVM_CAP_VCPU_EVENTS for more details.
8479 8002
8480 8.20 KVM_CAP_HYPERV_SEND_IPI 8003 8.20 KVM_CAP_HYPERV_SEND_IPI
8481 ---------------------------- 8004 ----------------------------
8482 8005
8483 :Architectures: x86 8006 :Architectures: x86
8484 8007
8485 This capability indicates that KVM supports p 8008 This capability indicates that KVM supports paravirtualized Hyper-V IPI send
8486 hypercalls: 8009 hypercalls:
8487 HvCallSendSyntheticClusterIpi, HvCallSendSynt 8010 HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.
8488 8011
8489 8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH 8012 8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH
8490 ----------------------------------- 8013 -----------------------------------
8491 8014
8492 :Architectures: x86 8015 :Architectures: x86
8493 8016
8494 This capability indicates that KVM running on 8017 This capability indicates that KVM running on top of Hyper-V hypervisor
8495 enables Direct TLB flush for its guests meani 8018 enables Direct TLB flush for its guests meaning that TLB flush
8496 hypercalls are handled by Level 0 hypervisor 8019 hypercalls are handled by Level 0 hypervisor (Hyper-V) bypassing KVM.
8497 Due to the different ABI for hypercall parame 8020 Due to the different ABI for hypercall parameters between Hyper-V and
8498 KVM, enabling this capability effectively dis 8021 KVM, enabling this capability effectively disables all hypercall
8499 handling by KVM (as some KVM hypercall may be 8022 handling by KVM (as some KVM hypercall may be mistakenly treated as TLB
8500 flush hypercalls by Hyper-V) so userspace sho 8023 flush hypercalls by Hyper-V) so userspace should disable KVM identification
8501 in CPUID and only exposes Hyper-V identificat 8024 in CPUID and only exposes Hyper-V identification. In this case, guest
8502 thinks it's running on Hyper-V and only use H 8025 thinks it's running on Hyper-V and only use Hyper-V hypercalls.
8503 8026
8504 8.22 KVM_CAP_S390_VCPU_RESETS 8027 8.22 KVM_CAP_S390_VCPU_RESETS
8505 ----------------------------- 8028 -----------------------------
8506 8029
8507 :Architectures: s390 8030 :Architectures: s390
8508 8031
8509 This capability indicates that the KVM_S390_N 8032 This capability indicates that the KVM_S390_NORMAL_RESET and
8510 KVM_S390_CLEAR_RESET ioctls are available. 8033 KVM_S390_CLEAR_RESET ioctls are available.
8511 8034
8512 8.23 KVM_CAP_S390_PROTECTED 8035 8.23 KVM_CAP_S390_PROTECTED
8513 --------------------------- 8036 ---------------------------
8514 8037
8515 :Architectures: s390 8038 :Architectures: s390
8516 8039
8517 This capability indicates that the Ultravisor 8040 This capability indicates that the Ultravisor has been initialized and
8518 KVM can therefore start protected VMs. 8041 KVM can therefore start protected VMs.
8519 This capability governs the KVM_S390_PV_COMMA 8042 This capability governs the KVM_S390_PV_COMMAND ioctl and the
8520 KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE 8043 KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected
8521 guests when the state change is invalid. 8044 guests when the state change is invalid.
8522 8045
8523 8.24 KVM_CAP_STEAL_TIME 8046 8.24 KVM_CAP_STEAL_TIME
8524 ----------------------- 8047 -----------------------
8525 8048
8526 :Architectures: arm64, x86 8049 :Architectures: arm64, x86
8527 8050
8528 This capability indicates that KVM supports s 8051 This capability indicates that KVM supports steal time accounting.
8529 When steal time accounting is supported it ma 8052 When steal time accounting is supported it may be enabled with
8530 architecture-specific interfaces. This capab 8053 architecture-specific interfaces. This capability and the architecture-
8531 specific interfaces must be consistent, i.e. 8054 specific interfaces must be consistent, i.e. if one says the feature
8532 is supported, than the other should as well a 8055 is supported, than the other should as well and vice versa. For arm64
8533 see Documentation/virt/kvm/devices/vcpu.rst " 8056 see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL".
8534 For x86 see Documentation/virt/kvm/x86/msr.rs 8057 For x86 see Documentation/virt/kvm/x86/msr.rst "MSR_KVM_STEAL_TIME".
8535 8058
8536 8.25 KVM_CAP_S390_DIAG318 8059 8.25 KVM_CAP_S390_DIAG318
8537 ------------------------- 8060 -------------------------
8538 8061
8539 :Architectures: s390 8062 :Architectures: s390
8540 8063
8541 This capability enables a guest to set inform 8064 This capability enables a guest to set information about its control program
8542 (i.e. guest kernel type and version). The inf 8065 (i.e. guest kernel type and version). The information is helpful during
8543 system/firmware service events, providing add 8066 system/firmware service events, providing additional data about the guest
8544 environments running on the machine. 8067 environments running on the machine.
8545 8068
8546 The information is associated with the DIAGNO 8069 The information is associated with the DIAGNOSE 0x318 instruction, which sets
8547 an 8-byte value consisting of a one-byte Cont 8070 an 8-byte value consisting of a one-byte Control Program Name Code (CPNC) and
8548 a 7-byte Control Program Version Code (CPVC). 8071 a 7-byte Control Program Version Code (CPVC). The CPNC determines what
8549 environment the control program is running in 8072 environment the control program is running in (e.g. Linux, z/VM...), and the
8550 CPVC is used for information specific to OS ( 8073 CPVC is used for information specific to OS (e.g. Linux version, Linux
8551 distribution...) 8074 distribution...)
8552 8075
8553 If this capability is available, then the CPN 8076 If this capability is available, then the CPNC and CPVC can be synchronized
8554 between KVM and userspace via the sync regs m 8077 between KVM and userspace via the sync regs mechanism (KVM_SYNC_DIAG318).
8555 8078
8556 8.26 KVM_CAP_X86_USER_SPACE_MSR 8079 8.26 KVM_CAP_X86_USER_SPACE_MSR
8557 ------------------------------- 8080 -------------------------------
8558 8081
8559 :Architectures: x86 8082 :Architectures: x86
8560 8083
8561 This capability indicates that KVM supports d 8084 This capability indicates that KVM supports deflection of MSR reads and
8562 writes to user space. It can be enabled on a 8085 writes to user space. It can be enabled on a VM level. If enabled, MSR
8563 accesses that would usually trigger a #GP by 8086 accesses that would usually trigger a #GP by KVM into the guest will
8564 instead get bounced to user space through the 8087 instead get bounced to user space through the KVM_EXIT_X86_RDMSR and
8565 KVM_EXIT_X86_WRMSR exit notifications. 8088 KVM_EXIT_X86_WRMSR exit notifications.
8566 8089
8567 8.27 KVM_CAP_X86_MSR_FILTER 8090 8.27 KVM_CAP_X86_MSR_FILTER
8568 --------------------------- 8091 ---------------------------
8569 8092
8570 :Architectures: x86 8093 :Architectures: x86
8571 8094
8572 This capability indicates that KVM supports t 8095 This capability indicates that KVM supports that accesses to user defined MSRs
8573 may be rejected. With this capability exposed 8096 may be rejected. With this capability exposed, KVM exports new VM ioctl
8574 KVM_X86_SET_MSR_FILTER which user space can c 8097 KVM_X86_SET_MSR_FILTER which user space can call to specify bitmaps of MSR
8575 ranges that KVM should deny access to. 8098 ranges that KVM should deny access to.
8576 8099
8577 In combination with KVM_CAP_X86_USER_SPACE_MS 8100 In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to
8578 trap and emulate MSRs that are outside of the 8101 trap and emulate MSRs that are outside of the scope of KVM as well as
8579 limit the attack surface on KVM's MSR emulati 8102 limit the attack surface on KVM's MSR emulation code.
8580 8103
8581 8.28 KVM_CAP_ENFORCE_PV_FEATURE_CPUID 8104 8.28 KVM_CAP_ENFORCE_PV_FEATURE_CPUID
8582 ------------------------------------- 8105 -------------------------------------
8583 8106
8584 Architectures: x86 8107 Architectures: x86
8585 8108
8586 When enabled, KVM will disable paravirtual fe 8109 When enabled, KVM will disable paravirtual features provided to the
8587 guest according to the bits in the KVM_CPUID_ 8110 guest according to the bits in the KVM_CPUID_FEATURES CPUID leaf
8588 (0x40000001). Otherwise, a guest may use the 8111 (0x40000001). Otherwise, a guest may use the paravirtual features
8589 regardless of what has actually been exposed 8112 regardless of what has actually been exposed through the CPUID leaf.
8590 8113
8591 8.29 KVM_CAP_DIRTY_LOG_RING/KVM_CAP_DIRTY_LOG 8114 8.29 KVM_CAP_DIRTY_LOG_RING/KVM_CAP_DIRTY_LOG_RING_ACQ_REL
8592 --------------------------------------------- 8115 ----------------------------------------------------------
8593 8116
8594 :Architectures: x86, arm64 8117 :Architectures: x86, arm64
8595 :Parameters: args[0] - size of the dirty log 8118 :Parameters: args[0] - size of the dirty log ring
8596 8119
8597 KVM is capable of tracking dirty memory using 8120 KVM is capable of tracking dirty memory using ring buffers that are
8598 mmapped into userspace; there is one dirty ri !! 8121 mmaped into userspace; there is one dirty ring per vcpu.
8599 8122
8600 The dirty ring is available to userspace as a 8123 The dirty ring is available to userspace as an array of
8601 ``struct kvm_dirty_gfn``. Each dirty entry i !! 8124 ``struct kvm_dirty_gfn``. Each dirty entry it's defined as::
8602 8125
8603 struct kvm_dirty_gfn { 8126 struct kvm_dirty_gfn {
8604 __u32 flags; 8127 __u32 flags;
8605 __u32 slot; /* as_id | slot_id */ 8128 __u32 slot; /* as_id | slot_id */
8606 __u64 offset; 8129 __u64 offset;
8607 }; 8130 };
8608 8131
8609 The following values are defined for the flag 8132 The following values are defined for the flags field to define the
8610 current state of the entry:: 8133 current state of the entry::
8611 8134
8612 #define KVM_DIRTY_GFN_F_DIRTY BIT 8135 #define KVM_DIRTY_GFN_F_DIRTY BIT(0)
8613 #define KVM_DIRTY_GFN_F_RESET BIT 8136 #define KVM_DIRTY_GFN_F_RESET BIT(1)
8614 #define KVM_DIRTY_GFN_F_MASK 0x3 8137 #define KVM_DIRTY_GFN_F_MASK 0x3
8615 8138
8616 Userspace should call KVM_ENABLE_CAP ioctl ri 8139 Userspace should call KVM_ENABLE_CAP ioctl right after KVM_CREATE_VM
8617 ioctl to enable this capability for the new g 8140 ioctl to enable this capability for the new guest and set the size of
8618 the rings. Enabling the capability is only a 8141 the rings. Enabling the capability is only allowed before creating any
8619 vCPU, and the size of the ring must be a powe 8142 vCPU, and the size of the ring must be a power of two. The larger the
8620 ring buffer, the less likely the ring is full 8143 ring buffer, the less likely the ring is full and the VM is forced to
8621 exit to userspace. The optimal size depends o 8144 exit to userspace. The optimal size depends on the workload, but it is
8622 recommended that it be at least 64 KiB (4096 8145 recommended that it be at least 64 KiB (4096 entries).
8623 8146
8624 Just like for dirty page bitmaps, the buffer 8147 Just like for dirty page bitmaps, the buffer tracks writes to
8625 all user memory regions for which the KVM_MEM 8148 all user memory regions for which the KVM_MEM_LOG_DIRTY_PAGES flag was
8626 set in KVM_SET_USER_MEMORY_REGION. Once a me 8149 set in KVM_SET_USER_MEMORY_REGION. Once a memory region is registered
8627 with the flag set, userspace can start harves 8150 with the flag set, userspace can start harvesting dirty pages from the
8628 ring buffer. 8151 ring buffer.
8629 8152
8630 An entry in the ring buffer can be unused (fl 8153 An entry in the ring buffer can be unused (flag bits ``00``),
8631 dirty (flag bits ``01``) or harvested (flag b 8154 dirty (flag bits ``01``) or harvested (flag bits ``1X``). The
8632 state machine for the entry is as follows:: 8155 state machine for the entry is as follows::
8633 8156
8634 dirtied harvested re 8157 dirtied harvested reset
8635 00 -----------> 01 -------------> 1X --- 8158 00 -----------> 01 -------------> 1X -------+
8636 ^ 8159 ^ |
8637 | 8160 | |
8638 +-------------------------------------- 8161 +------------------------------------------+
8639 8162
8640 To harvest the dirty pages, userspace accesse !! 8163 To harvest the dirty pages, userspace accesses the mmaped ring buffer
8641 to read the dirty GFNs. If the flags has the 8164 to read the dirty GFNs. If the flags has the DIRTY bit set (at this stage
8642 the RESET bit must be cleared), then it means 8165 the RESET bit must be cleared), then it means this GFN is a dirty GFN.
8643 The userspace should harvest this GFN and mar 8166 The userspace should harvest this GFN and mark the flags from state
8644 ``01b`` to ``1Xb`` (bit 0 will be ignored by 8167 ``01b`` to ``1Xb`` (bit 0 will be ignored by KVM, but bit 1 must be set
8645 to show that this GFN is harvested and waitin 8168 to show that this GFN is harvested and waiting for a reset), and move
8646 on to the next GFN. The userspace should con 8169 on to the next GFN. The userspace should continue to do this until the
8647 flags of a GFN have the DIRTY bit cleared, me 8170 flags of a GFN have the DIRTY bit cleared, meaning that it has harvested
8648 all the dirty GFNs that were available. 8171 all the dirty GFNs that were available.
8649 8172
8650 Note that on weakly ordered architectures, us 8173 Note that on weakly ordered architectures, userspace accesses to the
8651 ring buffer (and more specifically the 'flags 8174 ring buffer (and more specifically the 'flags' field) must be ordered,
8652 using load-acquire/store-release accessors wh 8175 using load-acquire/store-release accessors when available, or any
8653 other memory barrier that will ensure this or 8176 other memory barrier that will ensure this ordering.
8654 8177
8655 It's not necessary for userspace to harvest t 8178 It's not necessary for userspace to harvest the all dirty GFNs at once.
8656 However it must collect the dirty GFNs in seq 8179 However it must collect the dirty GFNs in sequence, i.e., the userspace
8657 program cannot skip one dirty GFN to collect 8180 program cannot skip one dirty GFN to collect the one next to it.
8658 8181
8659 After processing one or more entries in the r 8182 After processing one or more entries in the ring buffer, userspace
8660 calls the VM ioctl KVM_RESET_DIRTY_RINGS to n 8183 calls the VM ioctl KVM_RESET_DIRTY_RINGS to notify the kernel about
8661 it, so that the kernel will reprotect those c 8184 it, so that the kernel will reprotect those collected GFNs.
8662 Therefore, the ioctl must be called *before* 8185 Therefore, the ioctl must be called *before* reading the content of
8663 the dirty pages. 8186 the dirty pages.
8664 8187
8665 The dirty ring can get full. When it happens 8188 The dirty ring can get full. When it happens, the KVM_RUN of the
8666 vcpu will return with exit reason KVM_EXIT_DI 8189 vcpu will return with exit reason KVM_EXIT_DIRTY_LOG_FULL.
8667 8190
8668 The dirty ring interface has a major differen 8191 The dirty ring interface has a major difference comparing to the
8669 KVM_GET_DIRTY_LOG interface in that, when rea 8192 KVM_GET_DIRTY_LOG interface in that, when reading the dirty ring from
8670 userspace, it's still possible that the kerne 8193 userspace, it's still possible that the kernel has not yet flushed the
8671 processor's dirty page buffers into the kerne 8194 processor's dirty page buffers into the kernel buffer (with dirty bitmaps, the
8672 flushing is done by the KVM_GET_DIRTY_LOG ioc 8195 flushing is done by the KVM_GET_DIRTY_LOG ioctl). To achieve that, one
8673 needs to kick the vcpu out of KVM_RUN using a 8196 needs to kick the vcpu out of KVM_RUN using a signal. The resulting
8674 vmexit ensures that all dirty GFNs are flushe 8197 vmexit ensures that all dirty GFNs are flushed to the dirty rings.
8675 8198
8676 NOTE: KVM_CAP_DIRTY_LOG_RING_ACQ_REL is the o 8199 NOTE: KVM_CAP_DIRTY_LOG_RING_ACQ_REL is the only capability that
8677 should be exposed by weakly ordered architect 8200 should be exposed by weakly ordered architecture, in order to indicate
8678 the additional memory ordering requirements i 8201 the additional memory ordering requirements imposed on userspace when
8679 reading the state of an entry and mutating it 8202 reading the state of an entry and mutating it from DIRTY to HARVESTED.
8680 Architecture with TSO-like ordering (such as 8203 Architecture with TSO-like ordering (such as x86) are allowed to
8681 expose both KVM_CAP_DIRTY_LOG_RING and KVM_CA 8204 expose both KVM_CAP_DIRTY_LOG_RING and KVM_CAP_DIRTY_LOG_RING_ACQ_REL
8682 to userspace. 8205 to userspace.
8683 8206
8684 After enabling the dirty rings, the userspace 8207 After enabling the dirty rings, the userspace needs to detect the
8685 capability of KVM_CAP_DIRTY_LOG_RING_WITH_BIT 8208 capability of KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP to see whether the
8686 ring structures can be backed by per-slot bit 8209 ring structures can be backed by per-slot bitmaps. With this capability
8687 advertised, it means the architecture can dir 8210 advertised, it means the architecture can dirty guest pages without
8688 vcpu/ring context, so that some of the dirty 8211 vcpu/ring context, so that some of the dirty information will still be
8689 maintained in the bitmap structure. KVM_CAP_D 8212 maintained in the bitmap structure. KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP
8690 can't be enabled if the capability of KVM_CAP 8213 can't be enabled if the capability of KVM_CAP_DIRTY_LOG_RING_ACQ_REL
8691 hasn't been enabled, or any memslot has been 8214 hasn't been enabled, or any memslot has been existing.
8692 8215
8693 Note that the bitmap here is only a backup of 8216 Note that the bitmap here is only a backup of the ring structure. The
8694 use of the ring and bitmap combination is onl 8217 use of the ring and bitmap combination is only beneficial if there is
8695 only a very small amount of memory that is di 8218 only a very small amount of memory that is dirtied out of vcpu/ring
8696 context. Otherwise, the stand-alone per-slot 8219 context. Otherwise, the stand-alone per-slot bitmap mechanism needs to
8697 be considered. 8220 be considered.
8698 8221
8699 To collect dirty bits in the backup bitmap, u 8222 To collect dirty bits in the backup bitmap, userspace can use the same
8700 KVM_GET_DIRTY_LOG ioctl. KVM_CLEAR_DIRTY_LOG 8223 KVM_GET_DIRTY_LOG ioctl. KVM_CLEAR_DIRTY_LOG isn't needed as long as all
8701 the generation of the dirty bits is done in a 8224 the generation of the dirty bits is done in a single pass. Collecting
8702 the dirty bitmap should be the very last thin 8225 the dirty bitmap should be the very last thing that the VMM does before
8703 considering the state as complete. VMM needs 8226 considering the state as complete. VMM needs to ensure that the dirty
8704 state is final and avoid missing dirty pages 8227 state is final and avoid missing dirty pages from another ioctl ordered
8705 after the bitmap collection. 8228 after the bitmap collection.
8706 8229
8707 NOTE: Multiple examples of using the backup b 8230 NOTE: Multiple examples of using the backup bitmap: (1) save vgic/its
8708 tables through command KVM_DEV_ARM_{VGIC_GRP_ 8231 tables through command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} on
8709 KVM device "kvm-arm-vgic-its". (2) restore vg 8232 KVM device "kvm-arm-vgic-its". (2) restore vgic/its tables through
8710 command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_RESTO 8233 command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_RESTORE_TABLES} on KVM device
8711 "kvm-arm-vgic-its". VGICv3 LPI pending status 8234 "kvm-arm-vgic-its". VGICv3 LPI pending status is restored. (3) save
8712 vgic3 pending table through KVM_DEV_ARM_VGIC_ 8235 vgic3 pending table through KVM_DEV_ARM_VGIC_{GRP_CTRL, SAVE_PENDING_TABLES}
8713 command on KVM device "kvm-arm-vgic-v3". 8236 command on KVM device "kvm-arm-vgic-v3".
8714 8237
8715 8.30 KVM_CAP_XEN_HVM 8238 8.30 KVM_CAP_XEN_HVM
8716 -------------------- 8239 --------------------
8717 8240
8718 :Architectures: x86 8241 :Architectures: x86
8719 8242
8720 This capability indicates the features that X 8243 This capability indicates the features that Xen supports for hosting Xen
8721 PVHVM guests. Valid flags are:: 8244 PVHVM guests. Valid flags are::
8722 8245
8723 #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR 8246 #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0)
8724 #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL 8247 #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1)
8725 #define KVM_XEN_HVM_CONFIG_SHARED_INFO 8248 #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2)
8726 #define KVM_XEN_HVM_CONFIG_RUNSTATE 8249 #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3)
8727 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL 8250 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4)
8728 #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND 8251 #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5)
8729 #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_ 8252 #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6)
8730 #define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNST <<
8731 8253
8732 The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag ind 8254 The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG
8733 ioctl is available, for the guest to set its 8255 ioctl is available, for the guest to set its hypercall page.
8734 8256
8735 If KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL is also 8257 If KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL is also set, the same flag may also be
8736 provided in the flags to KVM_XEN_HVM_CONFIG, 8258 provided in the flags to KVM_XEN_HVM_CONFIG, without providing hypercall page
8737 contents, to request that KVM generate hyperc 8259 contents, to request that KVM generate hypercall page content automatically
8738 and also enable interception of guest hyperca 8260 and also enable interception of guest hypercalls with KVM_EXIT_XEN.
8739 8261
8740 The KVM_XEN_HVM_CONFIG_SHARED_INFO flag indic 8262 The KVM_XEN_HVM_CONFIG_SHARED_INFO flag indicates the availability of the
8741 KVM_XEN_HVM_SET_ATTR, KVM_XEN_HVM_GET_ATTR, K 8263 KVM_XEN_HVM_SET_ATTR, KVM_XEN_HVM_GET_ATTR, KVM_XEN_VCPU_SET_ATTR and
8742 KVM_XEN_VCPU_GET_ATTR ioctls, as well as the 8264 KVM_XEN_VCPU_GET_ATTR ioctls, as well as the delivery of exception vectors
8743 for event channel upcalls when the evtchn_upc 8265 for event channel upcalls when the evtchn_upcall_pending field of a vcpu's
8744 vcpu_info is set. 8266 vcpu_info is set.
8745 8267
8746 The KVM_XEN_HVM_CONFIG_RUNSTATE flag indicate 8268 The KVM_XEN_HVM_CONFIG_RUNSTATE flag indicates that the runstate-related
8747 features KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 8269 features KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR/_CURRENT/_DATA/_ADJUST are
8748 supported by the KVM_XEN_VCPU_SET_ATTR/KVM_XE 8270 supported by the KVM_XEN_VCPU_SET_ATTR/KVM_XEN_VCPU_GET_ATTR ioctls.
8749 8271
8750 The KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL flag ind 8272 The KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL flag indicates that IRQ routing entries
8751 of the type KVM_IRQ_ROUTING_XEN_EVTCHN are su 8273 of the type KVM_IRQ_ROUTING_XEN_EVTCHN are supported, with the priority
8752 field set to indicate 2 level event channel d 8274 field set to indicate 2 level event channel delivery.
8753 8275
8754 The KVM_XEN_HVM_CONFIG_EVTCHN_SEND flag indic 8276 The KVM_XEN_HVM_CONFIG_EVTCHN_SEND flag indicates that KVM supports
8755 injecting event channel events directly into 8277 injecting event channel events directly into the guest with the
8756 KVM_XEN_HVM_EVTCHN_SEND ioctl. It also indica 8278 KVM_XEN_HVM_EVTCHN_SEND ioctl. It also indicates support for the
8757 KVM_XEN_ATTR_TYPE_EVTCHN/XEN_VERSION HVM attr 8279 KVM_XEN_ATTR_TYPE_EVTCHN/XEN_VERSION HVM attributes and the
8758 KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID/TIMER/UPCALL_V 8280 KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID/TIMER/UPCALL_VECTOR vCPU attributes.
8759 related to event channel delivery, timers, an 8281 related to event channel delivery, timers, and the XENVER_version
8760 interception. 8282 interception.
8761 8283
8762 The KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG f 8284 The KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG flag indicates that KVM supports
8763 the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG at 8285 the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute in the KVM_XEN_SET_ATTR
8764 and KVM_XEN_GET_ATTR ioctls. This controls wh 8286 and KVM_XEN_GET_ATTR ioctls. This controls whether KVM will set the
8765 XEN_RUNSTATE_UPDATE flag in guest memory mapp 8287 XEN_RUNSTATE_UPDATE flag in guest memory mapped vcpu_runstate_info during
8766 updates of the runstate information. Note tha 8288 updates of the runstate information. Note that versions of KVM which support
8767 the RUNSTATE feature above, but not the RUNST !! 8289 the RUNSTATE feature above, but not thie RUNSTATE_UPDATE_FLAG feature, will
8768 always set the XEN_RUNSTATE_UPDATE flag when 8290 always set the XEN_RUNSTATE_UPDATE flag when updating the guest structure,
8769 which is perhaps counterintuitive. When this 8291 which is perhaps counterintuitive. When this flag is advertised, KVM will
8770 behave more correctly, not using the XEN_RUNS 8292 behave more correctly, not using the XEN_RUNSTATE_UPDATE flag until/unless
8771 specifically enabled (by the guest making the 8293 specifically enabled (by the guest making the hypercall, causing the VMM
8772 to enable the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDA 8294 to enable the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute).
8773 8295
8774 The KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE f <<
8775 clearing the PVCLOCK_TSC_STABLE_BIT flag in X <<
8776 done when the KVM_CAP_XEN_HVM ioctl sets the <<
8777 KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag. <<
8778 <<
8779 8.31 KVM_CAP_PPC_MULTITCE 8296 8.31 KVM_CAP_PPC_MULTITCE
8780 ------------------------- 8297 -------------------------
8781 8298
8782 :Capability: KVM_CAP_PPC_MULTITCE 8299 :Capability: KVM_CAP_PPC_MULTITCE
8783 :Architectures: ppc 8300 :Architectures: ppc
8784 :Type: vm 8301 :Type: vm
8785 8302
8786 This capability means the kernel is capable o 8303 This capability means the kernel is capable of handling hypercalls
8787 H_PUT_TCE_INDIRECT and H_STUFF_TCE without pa 8304 H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
8788 space. This significantly accelerates DMA ope 8305 space. This significantly accelerates DMA operations for PPC KVM guests.
8789 User space should expect that its handlers fo 8306 User space should expect that its handlers for these hypercalls
8790 are not going to be called if user space prev 8307 are not going to be called if user space previously registered LIOBN
8791 in KVM (via KVM_CREATE_SPAPR_TCE or similar c 8308 in KVM (via KVM_CREATE_SPAPR_TCE or similar calls).
8792 8309
8793 In order to enable H_PUT_TCE_INDIRECT and H_S 8310 In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest,
8794 user space might have to advertise it for the 8311 user space might have to advertise it for the guest. For example,
8795 IBM pSeries (sPAPR) guest starts using them i 8312 IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is
8796 present in the "ibm,hypertas-functions" devic 8313 present in the "ibm,hypertas-functions" device-tree property.
8797 8314
8798 The hypercalls mentioned above may or may not 8315 The hypercalls mentioned above may or may not be processed successfully
8799 in the kernel based fast path. If they can no 8316 in the kernel based fast path. If they can not be handled by the kernel,
8800 they will get passed on to user space. So use 8317 they will get passed on to user space. So user space still has to have
8801 an implementation for these despite the in ke 8318 an implementation for these despite the in kernel acceleration.
8802 8319
8803 This capability is always enabled. 8320 This capability is always enabled.
8804 8321
8805 8.32 KVM_CAP_PTP_KVM 8322 8.32 KVM_CAP_PTP_KVM
8806 -------------------- 8323 --------------------
8807 8324
8808 :Architectures: arm64 8325 :Architectures: arm64
8809 8326
8810 This capability indicates that the KVM virtua 8327 This capability indicates that the KVM virtual PTP service is
8811 supported in the host. A VMM can check whethe 8328 supported in the host. A VMM can check whether the service is
8812 available to the guest on migration. 8329 available to the guest on migration.
8813 8330
8814 8.33 KVM_CAP_HYPERV_ENFORCE_CPUID 8331 8.33 KVM_CAP_HYPERV_ENFORCE_CPUID
8815 --------------------------------- 8332 ---------------------------------
8816 8333
8817 Architectures: x86 8334 Architectures: x86
8818 8335
8819 When enabled, KVM will disable emulated Hyper 8336 When enabled, KVM will disable emulated Hyper-V features provided to the
8820 guest according to the bits Hyper-V CPUID fea 8337 guest according to the bits Hyper-V CPUID feature leaves. Otherwise, all
8821 currently implemented Hyper-V features are pr !! 8338 currently implmented Hyper-V features are provided unconditionally when
8822 Hyper-V identification is set in the HYPERV_C 8339 Hyper-V identification is set in the HYPERV_CPUID_INTERFACE (0x40000001)
8823 leaf. 8340 leaf.
8824 8341
8825 8.34 KVM_CAP_EXIT_HYPERCALL 8342 8.34 KVM_CAP_EXIT_HYPERCALL
8826 --------------------------- 8343 ---------------------------
8827 8344
8828 :Capability: KVM_CAP_EXIT_HYPERCALL 8345 :Capability: KVM_CAP_EXIT_HYPERCALL
8829 :Architectures: x86 8346 :Architectures: x86
8830 :Type: vm 8347 :Type: vm
8831 8348
8832 This capability, if enabled, will cause KVM t 8349 This capability, if enabled, will cause KVM to exit to userspace
8833 with KVM_EXIT_HYPERCALL exit reason to proces 8350 with KVM_EXIT_HYPERCALL exit reason to process some hypercalls.
8834 8351
8835 Calling KVM_CHECK_EXTENSION for this capabili 8352 Calling KVM_CHECK_EXTENSION for this capability will return a bitmask
8836 of hypercalls that can be configured to exit 8353 of hypercalls that can be configured to exit to userspace.
8837 Right now, the only such hypercall is KVM_HC_ 8354 Right now, the only such hypercall is KVM_HC_MAP_GPA_RANGE.
8838 8355
8839 The argument to KVM_ENABLE_CAP is also a bitm 8356 The argument to KVM_ENABLE_CAP is also a bitmask, and must be a subset
8840 of the result of KVM_CHECK_EXTENSION. KVM wi 8357 of the result of KVM_CHECK_EXTENSION. KVM will forward to userspace
8841 the hypercalls whose corresponding bit is in 8358 the hypercalls whose corresponding bit is in the argument, and return
8842 ENOSYS for the others. 8359 ENOSYS for the others.
8843 8360
8844 8.35 KVM_CAP_PMU_CAPABILITY 8361 8.35 KVM_CAP_PMU_CAPABILITY
8845 --------------------------- 8362 ---------------------------
8846 8363
8847 :Capability: KVM_CAP_PMU_CAPABILITY 8364 :Capability: KVM_CAP_PMU_CAPABILITY
8848 :Architectures: x86 8365 :Architectures: x86
8849 :Type: vm 8366 :Type: vm
8850 :Parameters: arg[0] is bitmask of PMU virtual 8367 :Parameters: arg[0] is bitmask of PMU virtualization capabilities.
8851 :Returns: 0 on success, -EINVAL when arg[0] c 8368 :Returns: 0 on success, -EINVAL when arg[0] contains invalid bits
8852 8369
8853 This capability alters PMU virtualization in 8370 This capability alters PMU virtualization in KVM.
8854 8371
8855 Calling KVM_CHECK_EXTENSION for this capabili 8372 Calling KVM_CHECK_EXTENSION for this capability returns a bitmask of
8856 PMU virtualization capabilities that can be a 8373 PMU virtualization capabilities that can be adjusted on a VM.
8857 8374
8858 The argument to KVM_ENABLE_CAP is also a bitm 8375 The argument to KVM_ENABLE_CAP is also a bitmask and selects specific
8859 PMU virtualization capabilities to be applied 8376 PMU virtualization capabilities to be applied to the VM. This can
8860 only be invoked on a VM prior to the creation 8377 only be invoked on a VM prior to the creation of VCPUs.
8861 8378
8862 At this time, KVM_PMU_CAP_DISABLE is the only 8379 At this time, KVM_PMU_CAP_DISABLE is the only capability. Setting
8863 this capability will disable PMU virtualizati 8380 this capability will disable PMU virtualization for that VM. Usermode
8864 should adjust CPUID leaf 0xA to reflect that 8381 should adjust CPUID leaf 0xA to reflect that the PMU is disabled.
8865 8382
8866 8.36 KVM_CAP_ARM_SYSTEM_SUSPEND 8383 8.36 KVM_CAP_ARM_SYSTEM_SUSPEND
8867 ------------------------------- 8384 -------------------------------
8868 8385
8869 :Capability: KVM_CAP_ARM_SYSTEM_SUSPEND 8386 :Capability: KVM_CAP_ARM_SYSTEM_SUSPEND
8870 :Architectures: arm64 8387 :Architectures: arm64
8871 :Type: vm 8388 :Type: vm
8872 8389
8873 When enabled, KVM will exit to userspace with 8390 When enabled, KVM will exit to userspace with KVM_EXIT_SYSTEM_EVENT of
8874 type KVM_SYSTEM_EVENT_SUSPEND to process the 8391 type KVM_SYSTEM_EVENT_SUSPEND to process the guest suspend request.
8875 8392
8876 8.37 KVM_CAP_S390_PROTECTED_DUMP 8393 8.37 KVM_CAP_S390_PROTECTED_DUMP
8877 -------------------------------- 8394 --------------------------------
8878 8395
8879 :Capability: KVM_CAP_S390_PROTECTED_DUMP 8396 :Capability: KVM_CAP_S390_PROTECTED_DUMP
8880 :Architectures: s390 8397 :Architectures: s390
8881 :Type: vm 8398 :Type: vm
8882 8399
8883 This capability indicates that KVM and the Ul 8400 This capability indicates that KVM and the Ultravisor support dumping
8884 PV guests. The `KVM_PV_DUMP` command is avail 8401 PV guests. The `KVM_PV_DUMP` command is available for the
8885 `KVM_S390_PV_COMMAND` ioctl and the `KVM_PV_I 8402 `KVM_S390_PV_COMMAND` ioctl and the `KVM_PV_INFO` command provides
8886 dump related UV data. Also the vcpu ioctl `KV 8403 dump related UV data. Also the vcpu ioctl `KVM_S390_PV_CPU_COMMAND` is
8887 available and supports the `KVM_PV_DUMP_CPU` 8404 available and supports the `KVM_PV_DUMP_CPU` subcommand.
8888 8405
8889 8.38 KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 8406 8.38 KVM_CAP_VM_DISABLE_NX_HUGE_PAGES
8890 ------------------------------------- 8407 -------------------------------------
8891 8408
8892 :Capability: KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 8409 :Capability: KVM_CAP_VM_DISABLE_NX_HUGE_PAGES
8893 :Architectures: x86 8410 :Architectures: x86
8894 :Type: vm 8411 :Type: vm
8895 :Parameters: arg[0] must be 0. 8412 :Parameters: arg[0] must be 0.
8896 :Returns: 0 on success, -EPERM if the userspa 8413 :Returns: 0 on success, -EPERM if the userspace process does not
8897 have CAP_SYS_BOOT, -EINVAL if args[ 8414 have CAP_SYS_BOOT, -EINVAL if args[0] is not 0 or any vCPUs have been
8898 created. 8415 created.
8899 8416
8900 This capability disables the NX huge pages mi 8417 This capability disables the NX huge pages mitigation for iTLB MULTIHIT.
8901 8418
8902 The capability has no effect if the nx_huge_p 8419 The capability has no effect if the nx_huge_pages module parameter is not set.
8903 8420
8904 This capability may only be set before any vC 8421 This capability may only be set before any vCPUs are created.
8905 8422
8906 8.39 KVM_CAP_S390_CPU_TOPOLOGY 8423 8.39 KVM_CAP_S390_CPU_TOPOLOGY
8907 ------------------------------ 8424 ------------------------------
8908 8425
8909 :Capability: KVM_CAP_S390_CPU_TOPOLOGY 8426 :Capability: KVM_CAP_S390_CPU_TOPOLOGY
8910 :Architectures: s390 8427 :Architectures: s390
8911 :Type: vm 8428 :Type: vm
8912 8429
8913 This capability indicates that KVM will provi 8430 This capability indicates that KVM will provide the S390 CPU Topology
8914 facility which consist of the interpretation 8431 facility which consist of the interpretation of the PTF instruction for
8915 the function code 2 along with interception a 8432 the function code 2 along with interception and forwarding of both the
8916 PTF instruction with function codes 0 or 1 an 8433 PTF instruction with function codes 0 or 1 and the STSI(15,1,x)
8917 instruction to the userland hypervisor. 8434 instruction to the userland hypervisor.
8918 8435
8919 The stfle facility 11, CPU Topology facility, 8436 The stfle facility 11, CPU Topology facility, should not be indicated
8920 to the guest without this capability. 8437 to the guest without this capability.
8921 8438
8922 When this capability is present, KVM provides 8439 When this capability is present, KVM provides a new attribute group
8923 on vm fd, KVM_S390_VM_CPU_TOPOLOGY. 8440 on vm fd, KVM_S390_VM_CPU_TOPOLOGY.
8924 This new attribute allows to get, set or clea 8441 This new attribute allows to get, set or clear the Modified Change
8925 Topology Report (MTCR) bit of the SCA through 8442 Topology Report (MTCR) bit of the SCA through the kvm_device_attr
8926 structure. 8443 structure.
8927 8444
8928 When getting the Modified Change Topology Rep 8445 When getting the Modified Change Topology Report value, the attr->addr
8929 must point to a byte where the value will be 8446 must point to a byte where the value will be stored or retrieved from.
8930 8447
8931 8.40 KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 8448 8.40 KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
8932 --------------------------------------- 8449 ---------------------------------------
8933 8450
8934 :Capability: KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SI 8451 :Capability: KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
8935 :Architectures: arm64 8452 :Architectures: arm64
8936 :Type: vm 8453 :Type: vm
8937 :Parameters: arg[0] is the new split chunk si 8454 :Parameters: arg[0] is the new split chunk size.
8938 :Returns: 0 on success, -EINVAL if any memslo 8455 :Returns: 0 on success, -EINVAL if any memslot was already created.
8939 8456
8940 This capability sets the chunk size used in E 8457 This capability sets the chunk size used in Eager Page Splitting.
8941 8458
8942 Eager Page Splitting improves the performance 8459 Eager Page Splitting improves the performance of dirty-logging (used
8943 in live migrations) when guest memory is back 8460 in live migrations) when guest memory is backed by huge-pages. It
8944 avoids splitting huge-pages (into PAGE_SIZE p 8461 avoids splitting huge-pages (into PAGE_SIZE pages) on fault, by doing
8945 it eagerly when enabling dirty logging (with 8462 it eagerly when enabling dirty logging (with the
8946 KVM_MEM_LOG_DIRTY_PAGES flag for a memory reg 8463 KVM_MEM_LOG_DIRTY_PAGES flag for a memory region), or when using
8947 KVM_CLEAR_DIRTY_LOG. 8464 KVM_CLEAR_DIRTY_LOG.
8948 8465
8949 The chunk size specifies how many pages to br 8466 The chunk size specifies how many pages to break at a time, using a
8950 single allocation for each chunk. Bigger the 8467 single allocation for each chunk. Bigger the chunk size, more pages
8951 need to be allocated ahead of time. 8468 need to be allocated ahead of time.
8952 8469
8953 The chunk size needs to be a valid block size 8470 The chunk size needs to be a valid block size. The list of acceptable
8954 block sizes is exposed in KVM_CAP_ARM_SUPPORT 8471 block sizes is exposed in KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES as a
8955 64-bit bitmap (each bit describing a block si 8472 64-bit bitmap (each bit describing a block size). The default value is
8956 0, to disable the eager page splitting. 8473 0, to disable the eager page splitting.
8957 <<
8958 8.41 KVM_CAP_VM_TYPES <<
8959 --------------------- <<
8960 <<
8961 :Capability: KVM_CAP_MEMORY_ATTRIBUTES <<
8962 :Architectures: x86 <<
8963 :Type: system ioctl <<
8964 <<
8965 This capability returns a bitmap of support V <<
8966 means the VM type with value @n is supported. <<
8967 <<
8968 #define KVM_X86_DEFAULT_VM 0 <<
8969 #define KVM_X86_SW_PROTECTED_VM 1 <<
8970 #define KVM_X86_SEV_VM 2 <<
8971 #define KVM_X86_SEV_ES_VM 3 <<
8972 <<
8973 Note, KVM_X86_SW_PROTECTED_VM is currently on <<
8974 Do not use KVM_X86_SW_PROTECTED_VM for "real" <<
8975 production. The behavior and effective ABI f <<
8976 unstable. <<
8977 8474
8978 9. Known KVM API problems 8475 9. Known KVM API problems
8979 ========================= 8476 =========================
8980 8477
8981 In some cases, KVM's API has some inconsisten 8478 In some cases, KVM's API has some inconsistencies or common pitfalls
8982 that userspace need to be aware of. This sec 8479 that userspace need to be aware of. This section details some of
8983 these issues. 8480 these issues.
8984 8481
8985 Most of them are architecture specific, so th 8482 Most of them are architecture specific, so the section is split by
8986 architecture. 8483 architecture.
8987 8484
8988 9.1. x86 8485 9.1. x86
8989 -------- 8486 --------
8990 8487
8991 ``KVM_GET_SUPPORTED_CPUID`` issues 8488 ``KVM_GET_SUPPORTED_CPUID`` issues
8992 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 8489 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
8993 8490
8994 In general, ``KVM_GET_SUPPORTED_CPUID`` is de 8491 In general, ``KVM_GET_SUPPORTED_CPUID`` is designed so that it is possible
8995 to take its result and pass it directly to `` 8492 to take its result and pass it directly to ``KVM_SET_CPUID2``. This section
8996 documents some cases in which that requires s 8493 documents some cases in which that requires some care.
8997 8494
8998 Local APIC features 8495 Local APIC features
8999 ~~~~~~~~~~~~~~~~~~~ 8496 ~~~~~~~~~~~~~~~~~~~
9000 8497
9001 CPU[EAX=1]:ECX[21] (X2APIC) is reported by `` 8498 CPU[EAX=1]:ECX[21] (X2APIC) is reported by ``KVM_GET_SUPPORTED_CPUID``,
9002 but it can only be enabled if ``KVM_CREATE_IR 8499 but it can only be enabled if ``KVM_CREATE_IRQCHIP`` or
9003 ``KVM_ENABLE_CAP(KVM_CAP_IRQCHIP_SPLIT)`` are 8500 ``KVM_ENABLE_CAP(KVM_CAP_IRQCHIP_SPLIT)`` are used to enable in-kernel emulation of
9004 the local APIC. 8501 the local APIC.
9005 8502
9006 The same is true for the ``KVM_FEATURE_PV_UNH 8503 The same is true for the ``KVM_FEATURE_PV_UNHALT`` paravirtualized feature.
9007 8504
9008 CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not repo 8505 CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not reported by ``KVM_GET_SUPPORTED_CPUID``.
9009 It can be enabled if ``KVM_CAP_TSC_DEADLINE_T 8506 It can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` is present and the kernel
9010 has enabled in-kernel emulation of the local 8507 has enabled in-kernel emulation of the local APIC.
9011 8508
9012 CPU topology 8509 CPU topology
9013 ~~~~~~~~~~~~ 8510 ~~~~~~~~~~~~
9014 8511
9015 Several CPUID values include topology informa 8512 Several CPUID values include topology information for the host CPU:
9016 0x0b and 0x1f for Intel systems, 0x8000001e f 8513 0x0b and 0x1f for Intel systems, 0x8000001e for AMD systems. Different
9017 versions of KVM return different values for t 8514 versions of KVM return different values for this information and userspace
9018 should not rely on it. Currently they return 8515 should not rely on it. Currently they return all zeroes.
9019 8516
9020 If userspace wishes to set up a guest topolog 8517 If userspace wishes to set up a guest topology, it should be careful that
9021 the values of these three leaves differ for e 8518 the values of these three leaves differ for each CPU. In particular,
9022 the APIC ID is found in EDX for all subleaves 8519 the APIC ID is found in EDX for all subleaves of 0x0b and 0x1f, and in EAX
9023 for 0x8000001e; the latter also encodes the c 8520 for 0x8000001e; the latter also encodes the core id and node id in bits
9024 7:0 of EBX and ECX respectively. 8521 7:0 of EBX and ECX respectively.
9025 8522
9026 Obsolete ioctls and capabilities 8523 Obsolete ioctls and capabilities
9027 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 8524 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
9028 8525
9029 KVM_CAP_DISABLE_QUIRKS does not let userspace 8526 KVM_CAP_DISABLE_QUIRKS does not let userspace know which quirks are actually
9030 available. Use ``KVM_CHECK_EXTENSION(KVM_CAP 8527 available. Use ``KVM_CHECK_EXTENSION(KVM_CAP_DISABLE_QUIRKS2)`` instead if
9031 available. 8528 available.
9032 8529
9033 Ordering of KVM_GET_*/KVM_SET_* ioctls 8530 Ordering of KVM_GET_*/KVM_SET_* ioctls
9034 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 8531 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
9035 8532
9036 TBD 8533 TBD
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.