Commit | Line | Data |
---|---|---|
a9282d01 IM |
1 | Coherent Accelerator Interface (CXL) |
2 | ==================================== | |
3 | ||
4 | Introduction | |
5 | ============ | |
6 | ||
7 | The coherent accelerator interface is designed to allow the | |
8 | coherent connection of accelerators (FPGAs and other devices) to a | |
9 | POWER system. These devices need to adhere to the Coherent | |
10 | Accelerator Interface Architecture (CAIA). | |
11 | ||
12 | IBM refers to this as the Coherent Accelerator Processor Interface | |
13 | or CAPI. In the kernel it's referred to by the name CXL to avoid | |
14 | confusion with the ISDN CAPI subsystem. | |
15 | ||
16 | Coherent in this context means that the accelerator and CPUs can | |
17 | both access system memory directly and with the same effective | |
18 | addresses. | |
19 | ||
20 | ||
21 | Hardware overview | |
22 | ================= | |
23 | ||
24 | POWER8 FPGA | |
25 | +----------+ +---------+ | |
26 | | | | | | |
27 | | CPU | | AFU | | |
28 | | | | | | |
29 | | | | | | |
30 | | | | | | |
31 | +----------+ +---------+ | |
32 | | PHB | | | | |
33 | | +------+ | PSL | | |
34 | | | CAPP |<------>| | | |
35 | +---+------+ PCIE +---------+ | |
36 | ||
37 | The POWER8 chip has a Coherently Attached Processor Proxy (CAPP) | |
38 | unit which is part of the PCIe Host Bridge (PHB). This is managed | |
39 | by Linux by calls into OPAL. Linux doesn't directly program the | |
40 | CAPP. | |
41 | ||
42 | The FPGA (or coherently attached device) consists of two parts. | |
43 | The POWER Service Layer (PSL) and the Accelerator Function Unit | |
44 | (AFU). The AFU is used to implement specific functionality behind | |
45 | the PSL. The PSL, among other things, provides memory address | |
46 | translation services to allow each AFU direct access to userspace | |
47 | memory. | |
48 | ||
49 | The AFU is the core part of the accelerator (eg. the compression, | |
50 | crypto etc function). The kernel has no knowledge of the function | |
51 | of the AFU. Only userspace interacts directly with the AFU. | |
52 | ||
53 | The PSL provides the translation and interrupt services that the | |
54 | AFU needs. This is what the kernel interacts with. For example, if | |
55 | the AFU needs to read a particular effective address, it sends | |
56 | that address to the PSL, the PSL then translates it, fetches the | |
57 | data from memory and returns it to the AFU. If the PSL has a | |
58 | translation miss, it interrupts the kernel and the kernel services | |
59 | the fault. The context to which this fault is serviced is based on | |
60 | who owns that acceleration function. | |
61 | ||
62 | ||
63 | AFU Modes | |
64 | ========= | |
65 | ||
66 | There are two programming modes supported by the AFU. Dedicated | |
67 | and AFU directed. AFU may support one or both modes. | |
68 | ||
69 | When using dedicated mode only one MMU context is supported. In | |
70 | this mode, only one userspace process can use the accelerator at | |
71 | time. | |
72 | ||
73 | When using AFU directed mode, up to 16K simultaneous contexts can | |
74 | be supported. This means up to 16K simultaneous userspace | |
75 | applications may use the accelerator (although specific AFUs may | |
76 | support fewer). In this mode, the AFU sends a 16 bit context ID | |
77 | with each of its requests. This tells the PSL which context is | |
78 | associated with each operation. If the PSL can't translate an | |
79 | operation, the ID can also be accessed by the kernel so it can | |
80 | determine the userspace context associated with an operation. | |
81 | ||
82 | ||
83 | MMIO space | |
84 | ========== | |
85 | ||
86 | A portion of the accelerator MMIO space can be directly mapped | |
87 | from the AFU to userspace. Either the whole space can be mapped or | |
88 | just a per context portion. The hardware is self describing, hence | |
89 | the kernel can determine the offset and size of the per context | |
90 | portion. | |
91 | ||
92 | ||
93 | Interrupts | |
94 | ========== | |
95 | ||
96 | AFUs may generate interrupts that are destined for userspace. These | |
97 | are received by the kernel as hardware interrupts and passed onto | |
98 | userspace by a read syscall documented below. | |
99 | ||
100 | Data storage faults and error interrupts are handled by the kernel | |
101 | driver. | |
102 | ||
103 | ||
104 | Work Element Descriptor (WED) | |
105 | ============================= | |
106 | ||
107 | The WED is a 64-bit parameter passed to the AFU when a context is | |
108 | started. Its format is up to the AFU hence the kernel has no | |
109 | knowledge of what it represents. Typically it will be the | |
110 | effective address of a work queue or status block where the AFU | |
111 | and userspace can share control and status information. | |
112 | ||
113 | ||
114 | ||
115 | ||
116 | User API | |
117 | ======== | |
118 | ||
594ff7d0 CL |
119 | 1. AFU character devices |
120 | ||
a9282d01 IM |
121 | For AFUs operating in AFU directed mode, two character device |
122 | files will be created. /dev/cxl/afu0.0m will correspond to a | |
123 | master context and /dev/cxl/afu0.0s will correspond to a slave | |
124 | context. Master contexts have access to the full MMIO space an | |
125 | AFU provides. Slave contexts have access to only the per process | |
126 | MMIO space an AFU provides. | |
127 | ||
128 | For AFUs operating in dedicated process mode, the driver will | |
129 | only create a single character device per AFU called | |
130 | /dev/cxl/afu0.0d. This will have access to the entire MMIO space | |
131 | that the AFU provides (like master contexts in AFU directed). | |
132 | ||
133 | The types described below are defined in include/uapi/misc/cxl.h | |
134 | ||
135 | The following file operations are supported on both slave and | |
136 | master devices. | |
137 | ||
dc12f20b | 138 | A userspace library libcxl is available here: |
aee85fb6 MN |
139 | https://github.com/ibm-capi/libcxl |
140 | This provides a C interface to this kernel API. | |
a9282d01 IM |
141 | |
142 | open | |
143 | ---- | |
144 | ||
145 | Opens the device and allocates a file descriptor to be used with | |
146 | the rest of the API. | |
147 | ||
148 | A dedicated mode AFU only has one context and only allows the | |
149 | device to be opened once. | |
150 | ||
151 | An AFU directed mode AFU can have many contexts, the device can be | |
152 | opened once for each context that is available. | |
153 | ||
154 | When all available contexts are allocated the open call will fail | |
155 | and return -ENOSPC. | |
156 | ||
157 | Note: IRQs need to be allocated for each context, which may limit | |
158 | the number of contexts that can be created, and therefore | |
159 | how many times the device can be opened. The POWER8 CAPP | |
160 | supports 2040 IRQs and 3 are used by the kernel, so 2037 are | |
161 | left. If 1 IRQ is needed per context, then only 2037 | |
162 | contexts can be allocated. If 4 IRQs are needed per context, | |
163 | then only 2037/4 = 509 contexts can be allocated. | |
164 | ||
165 | ||
166 | ioctl | |
167 | ----- | |
168 | ||
169 | CXL_IOCTL_START_WORK: | |
170 | Starts the AFU context and associates it with the current | |
171 | process. Once this ioctl is successfully executed, all memory | |
172 | mapped into this process is accessible to this AFU context | |
173 | using the same effective addresses. No additional calls are | |
174 | required to map/unmap memory. The AFU memory context will be | |
175 | updated as userspace allocates and frees memory. This ioctl | |
176 | returns once the AFU context is started. | |
177 | ||
178 | Takes a pointer to a struct cxl_ioctl_start_work: | |
179 | ||
180 | struct cxl_ioctl_start_work { | |
181 | __u64 flags; | |
182 | __u64 work_element_descriptor; | |
183 | __u64 amr; | |
184 | __s16 num_interrupts; | |
185 | __s16 reserved1; | |
186 | __s32 reserved2; | |
187 | __u64 reserved3; | |
188 | __u64 reserved4; | |
189 | __u64 reserved5; | |
190 | __u64 reserved6; | |
191 | }; | |
192 | ||
193 | flags: | |
194 | Indicates which optional fields in the structure are | |
195 | valid. | |
196 | ||
197 | work_element_descriptor: | |
198 | The Work Element Descriptor (WED) is a 64-bit argument | |
199 | defined by the AFU. Typically this is an effective | |
200 | address pointing to an AFU specific structure | |
201 | describing what work to perform. | |
202 | ||
203 | amr: | |
204 | Authority Mask Register (AMR), same as the powerpc | |
205 | AMR. This field is only used by the kernel when the | |
206 | corresponding CXL_START_WORK_AMR value is specified in | |
207 | flags. If not specified the kernel will use a default | |
208 | value of 0. | |
209 | ||
210 | num_interrupts: | |
211 | Number of userspace interrupts to request. This field | |
212 | is only used by the kernel when the corresponding | |
213 | CXL_START_WORK_NUM_IRQS value is specified in flags. | |
214 | If not specified the minimum number required by the | |
215 | AFU will be allocated. The min and max number can be | |
216 | obtained from sysfs. | |
217 | ||
218 | reserved fields: | |
219 | For ABI padding and future extensions | |
220 | ||
221 | CXL_IOCTL_GET_PROCESS_ELEMENT: | |
222 | Get the current context id, also known as the process element. | |
223 | The value is returned from the kernel as a __u32. | |
224 | ||
225 | ||
226 | mmap | |
227 | ---- | |
228 | ||
229 | An AFU may have an MMIO space to facilitate communication with the | |
230 | AFU. If it does, the MMIO space can be accessed via mmap. The size | |
231 | and contents of this area are specific to the particular AFU. The | |
232 | size can be discovered via sysfs. | |
233 | ||
234 | In AFU directed mode, master contexts are allowed to map all of | |
235 | the MMIO space and slave contexts are allowed to only map the per | |
236 | process MMIO space associated with the context. In dedicated | |
237 | process mode the entire MMIO space can always be mapped. | |
238 | ||
239 | This mmap call must be done after the START_WORK ioctl. | |
240 | ||
241 | Care should be taken when accessing MMIO space. Only 32 and 64-bit | |
242 | accesses are supported by POWER8. Also, the AFU will be designed | |
243 | with a specific endianness, so all MMIO accesses should consider | |
244 | endianness (recommend endian(3) variants like: le64toh(), | |
245 | be64toh() etc). These endian issues equally apply to shared memory | |
246 | queues the WED may describe. | |
247 | ||
248 | ||
249 | read | |
250 | ---- | |
251 | ||
252 | Reads events from the AFU. Blocks if no events are pending | |
253 | (unless O_NONBLOCK is supplied). Returns -EIO in the case of an | |
254 | unrecoverable error or if the card is removed. | |
255 | ||
256 | read() will always return an integral number of events. | |
257 | ||
258 | The buffer passed to read() must be at least 4K bytes. | |
259 | ||
260 | The result of the read will be a buffer of one or more events, | |
261 | each event is of type struct cxl_event, of varying size. | |
262 | ||
263 | struct cxl_event { | |
264 | struct cxl_event_header header; | |
265 | union { | |
266 | struct cxl_event_afu_interrupt irq; | |
267 | struct cxl_event_data_storage fault; | |
268 | struct cxl_event_afu_error afu_error; | |
269 | }; | |
270 | }; | |
271 | ||
272 | The struct cxl_event_header is defined as: | |
273 | ||
274 | struct cxl_event_header { | |
275 | __u16 type; | |
276 | __u16 size; | |
277 | __u16 process_element; | |
278 | __u16 reserved1; | |
279 | }; | |
280 | ||
281 | type: | |
282 | This defines the type of event. The type determines how | |
283 | the rest of the event is structured. These types are | |
284 | described below and defined by enum cxl_event_type. | |
285 | ||
286 | size: | |
287 | This is the size of the event in bytes including the | |
288 | struct cxl_event_header. The start of the next event can | |
289 | be found at this offset from the start of the current | |
290 | event. | |
291 | ||
292 | process_element: | |
293 | Context ID of the event. | |
294 | ||
295 | reserved field: | |
296 | For future extensions and padding. | |
297 | ||
298 | If the event type is CXL_EVENT_AFU_INTERRUPT then the event | |
299 | structure is defined as: | |
300 | ||
301 | struct cxl_event_afu_interrupt { | |
302 | __u16 flags; | |
303 | __u16 irq; /* Raised AFU interrupt number */ | |
304 | __u32 reserved1; | |
305 | }; | |
306 | ||
307 | flags: | |
308 | These flags indicate which optional fields are present | |
309 | in this struct. Currently all fields are mandatory. | |
310 | ||
311 | irq: | |
312 | The IRQ number sent by the AFU. | |
313 | ||
314 | reserved field: | |
315 | For future extensions and padding. | |
316 | ||
317 | If the event type is CXL_EVENT_DATA_STORAGE then the event | |
318 | structure is defined as: | |
319 | ||
320 | struct cxl_event_data_storage { | |
321 | __u16 flags; | |
322 | __u16 reserved1; | |
323 | __u32 reserved2; | |
324 | __u64 addr; | |
325 | __u64 dsisr; | |
326 | __u64 reserved3; | |
327 | }; | |
328 | ||
329 | flags: | |
330 | These flags indicate which optional fields are present in | |
331 | this struct. Currently all fields are mandatory. | |
332 | ||
333 | address: | |
334 | The address that the AFU unsuccessfully attempted to | |
335 | access. Valid accesses will be handled transparently by the | |
336 | kernel but invalid accesses will generate this event. | |
337 | ||
338 | dsisr: | |
339 | This field gives information on the type of fault. It is a | |
340 | copy of the DSISR from the PSL hardware when the address | |
341 | fault occurred. The form of the DSISR is as defined in the | |
342 | CAIA. | |
343 | ||
344 | reserved fields: | |
345 | For future extensions | |
346 | ||
347 | If the event type is CXL_EVENT_AFU_ERROR then the event structure | |
348 | is defined as: | |
349 | ||
350 | struct cxl_event_afu_error { | |
351 | __u16 flags; | |
352 | __u16 reserved1; | |
353 | __u32 reserved2; | |
354 | __u64 error; | |
355 | }; | |
356 | ||
357 | flags: | |
358 | These flags indicate which optional fields are present in | |
359 | this struct. Currently all fields are Mandatory. | |
360 | ||
361 | error: | |
362 | Error status from the AFU. Defined by the AFU. | |
363 | ||
364 | reserved fields: | |
365 | For future extensions and padding | |
366 | ||
594ff7d0 CL |
367 | |
368 | 2. Card character device (powerVM guest only) | |
369 | ||
370 | In a powerVM guest, an extra character device is created for the | |
371 | card. The device is only used to write (flash) a new image on the | |
372 | FPGA accelerator. Once the image is written and verified, the | |
373 | device tree is updated and the card is reset to reload the updated | |
374 | image. | |
375 | ||
376 | open | |
377 | ---- | |
378 | ||
379 | Opens the device and allocates a file descriptor to be used with | |
380 | the rest of the API. The device can only be opened once. | |
381 | ||
382 | ioctl | |
383 | ----- | |
384 | ||
385 | CXL_IOCTL_DOWNLOAD_IMAGE: | |
386 | CXL_IOCTL_VALIDATE_IMAGE: | |
387 | Starts and controls flashing a new FPGA image. Partial | |
388 | reconfiguration is not supported (yet), so the image must contain | |
389 | a copy of the PSL and AFU(s). Since an image can be quite large, | |
390 | the caller may have to iterate, splitting the image in smaller | |
391 | chunks. | |
392 | ||
393 | Takes a pointer to a struct cxl_adapter_image: | |
394 | struct cxl_adapter_image { | |
395 | __u64 flags; | |
396 | __u64 data; | |
397 | __u64 len_data; | |
398 | __u64 len_image; | |
399 | __u64 reserved1; | |
400 | __u64 reserved2; | |
401 | __u64 reserved3; | |
402 | __u64 reserved4; | |
403 | }; | |
404 | ||
405 | flags: | |
406 | These flags indicate which optional fields are present in | |
407 | this struct. Currently all fields are mandatory. | |
408 | ||
409 | data: | |
410 | Pointer to a buffer with part of the image to write to the | |
411 | card. | |
412 | ||
413 | len_data: | |
414 | Size of the buffer pointed to by data. | |
415 | ||
416 | len_image: | |
417 | Full size of the image. | |
418 | ||
419 | ||
a9282d01 IM |
420 | Sysfs Class |
421 | =========== | |
422 | ||
423 | A cxl sysfs class is added under /sys/class/cxl to facilitate | |
424 | enumeration and tuning of the accelerators. Its layout is | |
425 | described in Documentation/ABI/testing/sysfs-class-cxl | |
426 | ||
aee85fb6 | 427 | |
a9282d01 IM |
428 | Udev rules |
429 | ========== | |
430 | ||
431 | The following udev rules could be used to create a symlink to the | |
432 | most logical chardev to use in any programming mode (afuX.Yd for | |
433 | dedicated, afuX.Ys for afu directed), since the API is virtually | |
434 | identical for each: | |
435 | ||
436 | SUBSYSTEM=="cxl", ATTRS{mode}=="dedicated_process", SYMLINK="cxl/%b" | |
437 | SUBSYSTEM=="cxl", ATTRS{mode}=="afu_directed", \ | |
438 | KERNEL=="afu[0-9]*.[0-9]*s", SYMLINK="cxl/%b" |