forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 23
/
iommu.h
475 lines (440 loc) · 16.1 KB
/
iommu.h
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
* IOMMU user API definitions
*/
#ifndef _UAPI_IOMMU_H
#define _UAPI_IOMMU_H
#include <linux/types.h>
#include <linux/ioctl.h>
/* -------- IOCTLs for IOMMU file descriptor (/dev/iommu) -------- */
#define IOMMU_TYPE (';')
#define IOMMU_BASE 100
/*
* IOMMU_CHECK_EXTENSION - _IO(IOMMU_TYPE, IOMMU_BASE + 0)
*
* Check whether an uAPI extension is supported.
*
* It's unlikely that all planned capabilities in IOMMU fd will be ready
* in one breath. User should check which uAPI extension is supported
* according to its intended usage.
*
* A rough list of possible extensions may include:
*
* - EXT_MAP_TYPE1V2 for vfio type1v2 map semantics;
* - EXT_DMA_NO_SNOOP for no-snoop DMA support;
* - EXT_MAP_NEWTYPE for an enhanced map semantics;
* - EXT_MULTIDEV_GROUP for 1:N iommu group;
* - EXT_IOASID_NESTING for what the name stands;
* - EXT_USER_PAGE_TABLE for user managed page table;
* - EXT_USER_PASID_TABLE for user managed PASID table;
* - EXT_DIRTY_TRACKING for tracking pages dirtied by DMA;
* - ...
*
* Return: 0 if not supported, 1 if supported.
*/
#define EXT_MAP_TYPE1V2 1
#define EXT_DMA_NO_SNOOP 2
#define IOMMU_CHECK_EXTENSION _IO(IOMMU_TYPE, IOMMU_BASE + 0)
/*
* IOMMU_DEVICE_GET_INFO - _IOR(IOMMU_TYPE, IOMMU_BASE + 1,
* struct iommu_device_info)
*
* Check IOMMU capabilities and format information on a bound device.
*
* The device is identified by device cookie (registered when binding
* this device).
*
* @argsz: user filled size of this data.
* @flags: tells userspace which capability info is available
* @dev_cookie: user assinged cookie.
* @pgsize_bitmap: Bitmap of supported page sizes. 1-setting of the
* bit in pgsize_bitmap[63:12] indicates a supported
* page size. Details as below table:
*
* +===============+============+
* | Bit[index] | Page Size |
* +---------------+------------+
* | 12 | 4 KB |
* +---------------+------------+
* | 13 | 8 KB |
* +---------------+------------+
* | 14 | 16 KB |
* +---------------+------------+
* ...
* @addr_width: the address width of supported I/O address spaces.
* @cap_offset: Offset within info struct of first cap
*
* Availability: after device is bound to iommufd
*/
struct iommu_device_info {
__u32 argsz;
__u32 flags;
#define IOMMU_DEVICE_INFO_ENFORCE_SNOOP (1 << 0) /* IOMMU enforced snoop */
#define IOMMU_DEVICE_INFO_PGSIZES (1 << 1) /* supported page sizes */
#define IOMMU_DEVICE_INFO_ADDR_WIDTH (1 << 2) /* addr_wdith field valid */
#define IOMMU_DEVICE_INFO_CAPS (1 << 3) /* info supports cap chain */
__u64 dev_cookie;
__u64 pgsize_bitmap;
__u32 addr_width;
__u32 cap_offset;
};
#define IOMMU_DEVICE_GET_INFO _IO(IOMMU_TYPE, IOMMU_BASE + 1)
/*
* IOMMU_IOASID_ALLOC - _IOWR(IOMMU_TYPE, IOMMU_BASE + 2,
* struct iommu_ioasid_alloc)
*
* Allocate an IOASID.
*
* IOASID is the FD-local software handle representing an I/O address
* space. Each IOASID is associated with a single I/O page table. User
* must call this ioctl to get an IOASID for every I/O address space
* that is intended to be tracked by the kernel.
*
* User needs to specify the attributes of the IOASID and associated
* I/O page table format information according to one or multiple devices
* which will be attached to this IOASID right after. The I/O page table
* is activated in the IOMMU when it's attached by a device. Incompatible
* format between device and IOASID will lead to attaching failure in
* device side.
*
* Currently only one flag (IOMMU_IOASID_ENFORCE_SNOOP) is supported and
* must be always set.
*
* Only one I/O page table type (kernel-managed) is supported, with vfio
* type1v2 mapping semantics.
*
* User should call IOMMU_CHECK_EXTENSION for future extensions.
*
* @argsz: user filled size of this data.
* @flags: additional information for IOASID allocation.
* @type: I/O address space page table type.
* @addr_width: address width of the I/O address space.
*
* Return: allocated ioasid on success, -errno on failure.
*/
struct iommu_ioasid_alloc {
__u32 argsz;
__u32 flags;
#define IOMMU_IOASID_ENFORCE_SNOOP (1 << 0)
__u32 type;
#define IOMMU_IOASID_TYPE_KERNEL_TYPE1V2 1
__u32 addr_width;
};
#define IOMMU_IOASID_ALLOC _IO(IOMMU_TYPE, IOMMU_BASE + 2)
/**
* IOMMU_IOASID_FREE - _IOWR(IOMMU_TYPE, IOMMU_BASE + 3, int)
*
* Free an IOASID.
*
* returns: 0 on success, -errno on failure
*/
#define IOMMU_IOASID_FREE _IO(IOMMU_TYPE, IOMMU_BASE + 3)
#define IOMMU_FAULT_PERM_READ (1 << 0) /* read */
#define IOMMU_FAULT_PERM_WRITE (1 << 1) /* write */
#define IOMMU_FAULT_PERM_EXEC (1 << 2) /* exec */
#define IOMMU_FAULT_PERM_PRIV (1 << 3) /* privileged */
/* Generic fault types, can be expanded IRQ remapping fault */
enum iommu_fault_type {
IOMMU_FAULT_DMA_UNRECOV = 1, /* unrecoverable fault */
IOMMU_FAULT_PAGE_REQ, /* page request fault */
};
enum iommu_fault_reason {
IOMMU_FAULT_REASON_UNKNOWN = 0,
/* Could not access the PASID table (fetch caused external abort) */
IOMMU_FAULT_REASON_PASID_FETCH,
/* PASID entry is invalid or has configuration errors */
IOMMU_FAULT_REASON_BAD_PASID_ENTRY,
/*
* PASID is out of range (e.g. exceeds the maximum PASID
* supported by the IOMMU) or disabled.
*/
IOMMU_FAULT_REASON_PASID_INVALID,
/*
* An external abort occurred fetching (or updating) a translation
* table descriptor
*/
IOMMU_FAULT_REASON_WALK_EABT,
/*
* Could not access the page table entry (Bad address),
* actual translation fault
*/
IOMMU_FAULT_REASON_PTE_FETCH,
/* Protection flag check failed */
IOMMU_FAULT_REASON_PERMISSION,
/* access flag check failed */
IOMMU_FAULT_REASON_ACCESS,
/* Output address of a translation stage caused Address Size fault */
IOMMU_FAULT_REASON_OOR_ADDRESS,
};
/**
* struct iommu_fault_unrecoverable - Unrecoverable fault data
* @reason: reason of the fault, from &enum iommu_fault_reason
* @flags: parameters of this fault (IOMMU_FAULT_UNRECOV_* values)
* @pasid: Process Address Space ID
* @perm: requested permission access using by the incoming transaction
* (IOMMU_FAULT_PERM_* values)
* @addr: offending page address
* @fetch_addr: address that caused a fetch abort, if any
*/
struct iommu_fault_unrecoverable {
__u32 reason;
#define IOMMU_FAULT_UNRECOV_PASID_VALID (1 << 0)
#define IOMMU_FAULT_UNRECOV_ADDR_VALID (1 << 1)
#define IOMMU_FAULT_UNRECOV_FETCH_ADDR_VALID (1 << 2)
__u32 flags;
__u32 pasid;
__u32 perm;
__u64 addr;
__u64 fetch_addr;
};
/**
* struct iommu_fault_page_request - Page Request data
* @flags: encodes whether the corresponding fields are valid and whether this
* is the last page in group (IOMMU_FAULT_PAGE_REQUEST_* values).
* When IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID is set, the page response
* must have the same PASID value as the page request. When it is clear,
* the page response should not have a PASID.
* @pasid: Process Address Space ID
* @grpid: Page Request Group Index
* @perm: requested page permissions (IOMMU_FAULT_PERM_* values)
* @addr: page address
* @private_data: device-specific private information
*/
struct iommu_fault_page_request {
#define IOMMU_FAULT_PAGE_REQUEST_PASID_VALID (1 << 0)
#define IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE (1 << 1)
#define IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA (1 << 2)
#define IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID (1 << 3)
__u32 flags;
__u32 pasid;
__u32 grpid;
__u32 perm;
__u64 addr;
__u64 private_data[2];
};
/**
* struct iommu_fault - Generic fault data
* @type: fault type from &enum iommu_fault_type
* @padding: reserved for future use (should be zero)
* @event: fault event, when @type is %IOMMU_FAULT_DMA_UNRECOV
* @prm: Page Request message, when @type is %IOMMU_FAULT_PAGE_REQ
* @padding2: sets the fault size to allow for future extensions
*/
struct iommu_fault {
__u32 type;
__u32 padding;
union {
struct iommu_fault_unrecoverable event;
struct iommu_fault_page_request prm;
__u8 padding2[56];
};
};
/**
* enum iommu_page_response_code - Return status of fault handlers
* @IOMMU_PAGE_RESP_SUCCESS: Fault has been handled and the page tables
* populated, retry the access. This is "Success" in PCI PRI.
* @IOMMU_PAGE_RESP_FAILURE: General error. Drop all subsequent faults from
* this device if possible. This is "Response Failure" in PCI PRI.
* @IOMMU_PAGE_RESP_INVALID: Could not handle this fault, don't retry the
* access. This is "Invalid Request" in PCI PRI.
*/
enum iommu_page_response_code {
IOMMU_PAGE_RESP_SUCCESS = 0,
IOMMU_PAGE_RESP_INVALID,
IOMMU_PAGE_RESP_FAILURE,
};
/**
* struct iommu_page_response - Generic page response information
* @argsz: User filled size of this data
* @version: API version of this structure
* @flags: encodes whether the corresponding fields are valid
* (IOMMU_FAULT_PAGE_RESPONSE_* values)
* @pasid: Process Address Space ID
* @grpid: Page Request Group Index
* @code: response code from &enum iommu_page_response_code
*/
struct iommu_page_response {
__u32 argsz;
#define IOMMU_PAGE_RESP_VERSION_1 1
__u32 version;
#define IOMMU_PAGE_RESP_PASID_VALID (1 << 0)
__u32 flags;
__u32 pasid;
__u32 grpid;
__u32 code;
};
/* defines the granularity of the invalidation */
enum iommu_inv_granularity {
IOMMU_INV_GRANU_DOMAIN, /* domain-selective invalidation */
IOMMU_INV_GRANU_PASID, /* PASID-selective invalidation */
IOMMU_INV_GRANU_ADDR, /* page-selective invalidation */
IOMMU_INV_GRANU_NR, /* number of invalidation granularities */
};
/**
* struct iommu_inv_addr_info - Address Selective Invalidation Structure
*
* @flags: indicates the granularity of the address-selective invalidation
* - If the PASID bit is set, the @pasid field is populated and the invalidation
* relates to cache entries tagged with this PASID and matching the address
* range.
* - If ARCHID bit is set, @archid is populated and the invalidation relates
* to cache entries tagged with this architecture specific ID and matching
* the address range.
* - Both PASID and ARCHID can be set as they may tag different caches.
* - If neither PASID or ARCHID is set, global addr invalidation applies.
* - The LEAF flag indicates whether only the leaf PTE caching needs to be
* invalidated and other paging structure caches can be preserved.
* @pasid: process address space ID
* @archid: architecture-specific ID
* @addr: first stage/level input address
* @granule_size: page/block size of the mapping in bytes
* @nb_granules: number of contiguous granules to be invalidated
*/
struct iommu_inv_addr_info {
#define IOMMU_INV_ADDR_FLAGS_PASID (1 << 0)
#define IOMMU_INV_ADDR_FLAGS_ARCHID (1 << 1)
#define IOMMU_INV_ADDR_FLAGS_LEAF (1 << 2)
__u32 flags;
__u32 archid;
__u64 pasid;
__u64 addr;
__u64 granule_size;
__u64 nb_granules;
};
/**
* struct iommu_inv_pasid_info - PASID Selective Invalidation Structure
*
* @flags: indicates the granularity of the PASID-selective invalidation
* - If the PASID bit is set, the @pasid field is populated and the invalidation
* relates to cache entries tagged with this PASID and matching the address
* range.
* - If the ARCHID bit is set, the @archid is populated and the invalidation
* relates to cache entries tagged with this architecture specific ID and
* matching the address range.
* - Both PASID and ARCHID can be set as they may tag different caches.
* - At least one of PASID or ARCHID must be set.
* @pasid: process address space ID
* @archid: architecture-specific ID
*/
struct iommu_inv_pasid_info {
#define IOMMU_INV_PASID_FLAGS_PASID (1 << 0)
#define IOMMU_INV_PASID_FLAGS_ARCHID (1 << 1)
__u32 flags;
__u32 archid;
__u64 pasid;
};
/**
* struct iommu_cache_invalidate_info - First level/stage invalidation
* information
* @argsz: User filled size of this data
* @version: API version of this structure
* @cache: bitfield that allows to select which caches to invalidate
* @granularity: defines the lowest granularity used for the invalidation:
* domain > PASID > addr
* @padding: reserved for future use (should be zero)
* @pasid_info: invalidation data when @granularity is %IOMMU_INV_GRANU_PASID
* @addr_info: invalidation data when @granularity is %IOMMU_INV_GRANU_ADDR
*
* Not all the combinations of cache/granularity are valid:
*
* +--------------+---------------+---------------+---------------+
* | type / | DEV_IOTLB | IOTLB | PASID |
* | granularity | | | cache |
* +==============+===============+===============+===============+
* | DOMAIN | N/A | Y | Y |
* +--------------+---------------+---------------+---------------+
* | PASID | Y | Y | Y |
* +--------------+---------------+---------------+---------------+
* | ADDR | Y | Y | N/A |
* +--------------+---------------+---------------+---------------+
*
* Invalidations by %IOMMU_INV_GRANU_DOMAIN don't take any argument other than
* @version and @cache.
*
* If multiple cache types are invalidated simultaneously, they all
* must support the used granularity.
*/
struct iommu_cache_invalidate_info {
__u32 argsz;
#define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1
__u32 version;
/* IOMMU paging structure cache */
#define IOMMU_CACHE_INV_TYPE_IOTLB (1 << 0) /* IOMMU IOTLB */
#define IOMMU_CACHE_INV_TYPE_DEV_IOTLB (1 << 1) /* Device IOTLB */
#define IOMMU_CACHE_INV_TYPE_PASID (1 << 2) /* PASID cache */
#define IOMMU_CACHE_INV_TYPE_NR (3)
__u8 cache;
__u8 granularity;
__u8 padding[6];
union {
struct iommu_inv_pasid_info pasid_info;
struct iommu_inv_addr_info addr_info;
} granu;
};
/**
* struct iommu_gpasid_bind_data_vtd - Intel VT-d specific data on device and guest
* SVA binding.
*
* @flags: VT-d PASID table entry attributes
* @pat: Page attribute table data to compute effective memory type
* @emt: Extended memory type
*
* Only guest vIOMMU selectable and effective options are passed down to
* the host IOMMU.
*/
struct iommu_gpasid_bind_data_vtd {
#define IOMMU_SVA_VTD_GPASID_SRE (1 << 0) /* supervisor request */
#define IOMMU_SVA_VTD_GPASID_EAFE (1 << 1) /* extended access enable */
#define IOMMU_SVA_VTD_GPASID_PCD (1 << 2) /* page-level cache disable */
#define IOMMU_SVA_VTD_GPASID_PWT (1 << 3) /* page-level write through */
#define IOMMU_SVA_VTD_GPASID_EMTE (1 << 4) /* extended mem type enable */
#define IOMMU_SVA_VTD_GPASID_CD (1 << 5) /* PASID-level cache disable */
#define IOMMU_SVA_VTD_GPASID_WPE (1 << 6) /* Write protect enable */
#define IOMMU_SVA_VTD_GPASID_LAST (1 << 7)
__u64 flags;
__u32 pat;
__u32 emt;
};
#define IOMMU_SVA_VTD_GPASID_MTS_MASK (IOMMU_SVA_VTD_GPASID_CD | \
IOMMU_SVA_VTD_GPASID_EMTE | \
IOMMU_SVA_VTD_GPASID_PCD | \
IOMMU_SVA_VTD_GPASID_PWT)
/**
* struct iommu_gpasid_bind_data - Information about device and guest PASID binding
* @argsz: User filled size of this data
* @version: Version of this data structure
* @format: PASID table entry format
* @flags: Additional information on guest bind request
* @gpgd: Guest page directory base of the guest mm to bind
* @hpasid: Process address space ID used for the guest mm in host IOMMU
* @gpasid: Process address space ID used for the guest mm in guest IOMMU
* @addr_width: Guest virtual address width
* @padding: Reserved for future use (should be zero)
* @vtd: Intel VT-d specific data
*
* Guest to host PASID mapping can be an identity or non-identity, where guest
* has its own PASID space. For non-identify mapping, guest to host PASID lookup
* is needed when VM programs guest PASID into an assigned device. VMM may
* trap such PASID programming then request host IOMMU driver to convert guest
* PASID to host PASID based on this bind data.
*/
struct iommu_gpasid_bind_data {
__u32 argsz;
#define IOMMU_GPASID_BIND_VERSION_1 1
__u32 version;
#define IOMMU_PASID_FORMAT_INTEL_VTD 1
#define IOMMU_PASID_FORMAT_LAST 2
__u32 format;
__u32 addr_width;
#define IOMMU_SVA_GPASID_VAL (1 << 0) /* guest PASID valid */
__u64 flags;
__u64 gpgd;
__u64 hpasid;
__u64 gpasid;
__u8 padding[8];
/* Vendor specific data */
union {
struct iommu_gpasid_bind_data_vtd vtd;
} vendor;
};
#endif /* _UAPI_IOMMU_H */