summaryrefslogtreecommitdiff
path: root/drivers/cxl/mem.c
blob: aa8f843fcca14e902ae4fc8274ebf83862ef80a2 (plain)
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
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright(c) 2020 Intel Corporation. All rights reserved. */
#include <uapi/linux/cxl_mem.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/cdev.h>
#include <linux/idr.h>
#include <linux/pci.h>
#include <linux/io.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include "pci.h"
#include "cxl.h"

/**
 * DOC: cxl mem
 *
 * This implements a CXL memory device ("type-3") as it is defined by the
 * Compute Express Link specification.
 *
 * The driver has several responsibilities, mainly:
 *  - Create the memX device and register on the CXL bus.
 *  - Enumerate device's register interface and map them.
 *  - Probe the device attributes to establish sysfs interface.
 *  - Provide an IOCTL interface to userspace to communicate with the device for
 *    things like firmware update.
 *  - Support management of interleave sets.
 *  - Handle and manage error conditions.
 */

/*
 * An entire PCI topology full of devices should be enough for any
 * config
 */
#define CXL_MEM_MAX_DEVS 65536

#define cxl_doorbell_busy(cxlm)                                                \
	(readl((cxlm)->mbox_regs + CXLDEV_MBOX_CTRL_OFFSET) &                  \
	 CXLDEV_MBOX_CTRL_DOORBELL)

/* CXL 2.0 - 8.2.8.4 */
#define CXL_MAILBOX_TIMEOUT_MS (2 * HZ)

enum opcode {
	CXL_MBOX_OP_INVALID		= 0x0000,
	CXL_MBOX_OP_IDENTIFY		= 0x4000,
	CXL_MBOX_OP_MAX			= 0x10000
};

/**
 * struct mbox_cmd - A command to be submitted to hardware.
 * @opcode: (input) The command set and command submitted to hardware.
 * @payload_in: (input) Pointer to the input payload.
 * @payload_out: (output) Pointer to the output payload. Must be allocated by
 *		 the caller.
 * @size_in: (input) Number of bytes to load from @payload_in.
 * @size_out: (input) Max number of bytes loaded into @payload_out.
 *            (output) Number of bytes generated by the device. For fixed size
 *            outputs commands this is always expected to be deterministic. For
 *            variable sized output commands, it tells the exact number of bytes
 *            written.
 * @return_code: (output) Error code returned from hardware.
 *
 * This is the primary mechanism used to send commands to the hardware.
 * All the fields except @payload_* correspond exactly to the fields described in
 * Command Register section of the CXL 2.0 8.2.8.4.5. @payload_in and
 * @payload_out are written to, and read from the Command Payload Registers
 * defined in CXL 2.0 8.2.8.4.8.
 */
struct mbox_cmd {
	u16 opcode;
	void *payload_in;
	void *payload_out;
	size_t size_in;
	size_t size_out;
	u16 return_code;
#define CXL_MBOX_SUCCESS 0
};

/**
 * struct cxl_memdev - CXL bus object representing a Type-3 Memory Device
 * @dev: driver core device object
 * @cdev: char dev core object for ioctl operations
 * @cxlm: pointer to the parent device driver data
 * @ops_active: active user of @cxlm in ops handlers
 * @ops_dead: completion when all @cxlm ops users have exited
 * @id: id number of this memdev instance.
 */
struct cxl_memdev {
	struct device dev;
	struct cdev cdev;
	struct cxl_mem *cxlm;
	struct percpu_ref ops_active;
	struct completion ops_dead;
	int id;
};

static int cxl_mem_major;
static DEFINE_IDA(cxl_memdev_ida);

/**
 * struct cxl_mem_command - Driver representation of a memory device command
 * @info: Command information as it exists for the UAPI
 * @opcode: The actual bits used for the mailbox protocol
 *
 * The cxl_mem_command is the driver's internal representation of commands that
 * are supported by the driver. Some of these commands may not be supported by
 * the hardware. The driver will use @info to validate the fields passed in by
 * the user then submit the @opcode to the hardware.
 *
 * See struct cxl_command_info.
 */
struct cxl_mem_command {
	struct cxl_command_info info;
	enum opcode opcode;
};

#define CXL_CMD(_id, sin, sout)                                                \
	[CXL_MEM_COMMAND_ID_##_id] = {                                         \
	.info =	{                                                              \
			.id = CXL_MEM_COMMAND_ID_##_id,                        \
			.size_in = sin,                                        \
			.size_out = sout,                                      \
		},                                                             \
	.opcode = CXL_MBOX_OP_##_id,                                           \
	}

/*
 * This table defines the supported mailbox commands for the driver. This table
 * is made up of a UAPI structure. Non-negative values as parameters in the
 * table will be validated against the user's input. For example, if size_in is
 * 0, and the user passed in 1, it is an error.
 */
static struct cxl_mem_command mem_commands[] = {
	CXL_CMD(IDENTIFY, 0, 0x43),
};

#define cxl_for_each_cmd(cmd)                                                  \
	for ((cmd) = &mem_commands[0];                                         \
	     ((cmd) - mem_commands) < ARRAY_SIZE(mem_commands); (cmd)++)

#define cxl_cmd_count ARRAY_SIZE(mem_commands)

static int cxl_mem_wait_for_doorbell(struct cxl_mem *cxlm)
{
	const unsigned long start = jiffies;
	unsigned long end = start;

	while (cxl_doorbell_busy(cxlm)) {
		end = jiffies;

		if (time_after(end, start + CXL_MAILBOX_TIMEOUT_MS)) {
			/* Check again in case preempted before timeout test */
			if (!cxl_doorbell_busy(cxlm))
				break;
			return -ETIMEDOUT;
		}
		cpu_relax();
	}

	dev_dbg(&cxlm->pdev->dev, "Doorbell wait took %dms",
		jiffies_to_msecs(end) - jiffies_to_msecs(start));
	return 0;
}

static void cxl_mem_mbox_timeout(struct cxl_mem *cxlm,
				 struct mbox_cmd *mbox_cmd)
{
	struct device *dev = &cxlm->pdev->dev;

	dev_dbg(dev, "Mailbox command (opcode: %#x size: %zub) timed out\n",
		mbox_cmd->opcode, mbox_cmd->size_in);
}

/**
 * __cxl_mem_mbox_send_cmd() - Execute a mailbox command
 * @cxlm: The CXL memory device to communicate with.
 * @mbox_cmd: Command to send to the memory device.
 *
 * Context: Any context. Expects mbox_mutex to be held.
 * Return: -ETIMEDOUT if timeout occurred waiting for completion. 0 on success.
 *         Caller should check the return code in @mbox_cmd to make sure it
 *         succeeded.
 *
 * This is a generic form of the CXL mailbox send command thus only using the
 * registers defined by the mailbox capability ID - CXL 2.0 8.2.8.4. Memory
 * devices, and perhaps other types of CXL devices may have further information
 * available upon error conditions. Driver facilities wishing to send mailbox
 * commands should use the wrapper command.
 *
 * The CXL spec allows for up to two mailboxes. The intention is for the primary
 * mailbox to be OS controlled and the secondary mailbox to be used by system
 * firmware. This allows the OS and firmware to communicate with the device and
 * not need to coordinate with each other. The driver only uses the primary
 * mailbox.
 */
static int __cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm,
				   struct mbox_cmd *mbox_cmd)
{
	void __iomem *payload = cxlm->mbox_regs + CXLDEV_MBOX_PAYLOAD_OFFSET;
	u64 cmd_reg, status_reg;
	size_t out_len;
	int rc;

	lockdep_assert_held(&cxlm->mbox_mutex);

	/*
	 * Here are the steps from 8.2.8.4 of the CXL 2.0 spec.
	 *   1. Caller reads MB Control Register to verify doorbell is clear
	 *   2. Caller writes Command Register
	 *   3. Caller writes Command Payload Registers if input payload is non-empty
	 *   4. Caller writes MB Control Register to set doorbell
	 *   5. Caller either polls for doorbell to be clear or waits for interrupt if configured
	 *   6. Caller reads MB Status Register to fetch Return code
	 *   7. If command successful, Caller reads Command Register to get Payload Length
	 *   8. If output payload is non-empty, host reads Command Payload Registers
	 *
	 * Hardware is free to do whatever it wants before the doorbell is rung,
	 * and isn't allowed to change anything after it clears the doorbell. As
	 * such, steps 2 and 3 can happen in any order, and steps 6, 7, 8 can
	 * also happen in any order (though some orders might not make sense).
	 */

	/* #1 */
	if (cxl_doorbell_busy(cxlm)) {
		dev_err_ratelimited(&cxlm->pdev->dev,
				    "Mailbox re-busy after acquiring\n");
		return -EBUSY;
	}

	cmd_reg = FIELD_PREP(CXLDEV_MBOX_CMD_COMMAND_OPCODE_MASK,
			     mbox_cmd->opcode);
	if (mbox_cmd->size_in) {
		if (WARN_ON(!mbox_cmd->payload_in))
			return -EINVAL;

		cmd_reg |= FIELD_PREP(CXLDEV_MBOX_CMD_PAYLOAD_LENGTH_MASK,
				      mbox_cmd->size_in);
		memcpy_toio(payload, mbox_cmd->payload_in, mbox_cmd->size_in);
	}

	/* #2, #3 */
	writeq(cmd_reg, cxlm->mbox_regs + CXLDEV_MBOX_CMD_OFFSET);

	/* #4 */
	dev_dbg(&cxlm->pdev->dev, "Sending command\n");
	writel(CXLDEV_MBOX_CTRL_DOORBELL,
	       cxlm->mbox_regs + CXLDEV_MBOX_CTRL_OFFSET);

	/* #5 */
	rc = cxl_mem_wait_for_doorbell(cxlm);
	if (rc == -ETIMEDOUT) {
		cxl_mem_mbox_timeout(cxlm, mbox_cmd);
		return rc;
	}

	/* #6 */
	status_reg = readq(cxlm->mbox_regs + CXLDEV_MBOX_STATUS_OFFSET);
	mbox_cmd->return_code =
		FIELD_GET(CXLDEV_MBOX_STATUS_RET_CODE_MASK, status_reg);

	if (mbox_cmd->return_code != 0) {
		dev_dbg(&cxlm->pdev->dev, "Mailbox operation had an error\n");
		return 0;
	}

	/* #7 */
	cmd_reg = readq(cxlm->mbox_regs + CXLDEV_MBOX_CMD_OFFSET);
	out_len = FIELD_GET(CXLDEV_MBOX_CMD_PAYLOAD_LENGTH_MASK, cmd_reg);

	/* #8 */
	if (out_len && mbox_cmd->payload_out) {
		/*
		 * Sanitize the copy. If hardware misbehaves, out_len per the
		 * spec can actually be greater than the max allowed size (21
		 * bits available but spec defined 1M max). The caller also may
		 * have requested less data than the hardware supplied even
		 * within spec.
		 */
		size_t n = min3(mbox_cmd->size_out, cxlm->payload_size, out_len);

		memcpy_fromio(mbox_cmd->payload_out, payload, n);
		mbox_cmd->size_out = n;
	} else {
		mbox_cmd->size_out = 0;
	}

	return 0;
}

/**
 * cxl_mem_mbox_get() - Acquire exclusive access to the mailbox.
 * @cxlm: The memory device to gain access to.
 *
 * Context: Any context. Takes the mbox_mutex.
 * Return: 0 if exclusive access was acquired.
 */
static int cxl_mem_mbox_get(struct cxl_mem *cxlm)
{
	struct device *dev = &cxlm->pdev->dev;
	u64 md_status;
	int rc;

	mutex_lock_io(&cxlm->mbox_mutex);

	/*
	 * XXX: There is some amount of ambiguity in the 2.0 version of the spec
	 * around the mailbox interface ready (8.2.8.5.1.1).  The purpose of the
	 * bit is to allow firmware running on the device to notify the driver
	 * that it's ready to receive commands. It is unclear if the bit needs
	 * to be read for each transaction mailbox, ie. the firmware can switch
	 * it on and off as needed. Second, there is no defined timeout for
	 * mailbox ready, like there is for the doorbell interface.
	 *
	 * Assumptions:
	 * 1. The firmware might toggle the Mailbox Interface Ready bit, check
	 *    it for every command.
	 *
	 * 2. If the doorbell is clear, the firmware should have first set the
	 *    Mailbox Interface Ready bit. Therefore, waiting for the doorbell
	 *    to be ready is sufficient.
	 */
	rc = cxl_mem_wait_for_doorbell(cxlm);
	if (rc) {
		dev_warn(dev, "Mailbox interface not ready\n");
		goto out;
	}

	md_status = readq(cxlm->memdev_regs + CXLMDEV_STATUS_OFFSET);
	if (!(md_status & CXLMDEV_MBOX_IF_READY && CXLMDEV_READY(md_status))) {
		dev_err(dev, "mbox: reported doorbell ready, but not mbox ready\n");
		rc = -EBUSY;
		goto out;
	}

	/*
	 * Hardware shouldn't allow a ready status but also have failure bits
	 * set. Spit out an error, this should be a bug report
	 */
	rc = -EFAULT;
	if (md_status & CXLMDEV_DEV_FATAL) {
		dev_err(dev, "mbox: reported ready, but fatal\n");
		goto out;
	}
	if (md_status & CXLMDEV_FW_HALT) {
		dev_err(dev, "mbox: reported ready, but halted\n");
		goto out;
	}
	if (CXLMDEV_RESET_NEEDED(md_status)) {
		dev_err(dev, "mbox: reported ready, but reset needed\n");
		goto out;
	}

	/* with lock held */
	return 0;

out:
	mutex_unlock(&cxlm->mbox_mutex);
	return rc;
}

/**
 * cxl_mem_mbox_put() - Release exclusive access to the mailbox.
 * @cxlm: The CXL memory device to communicate with.
 *
 * Context: Any context. Expects mbox_mutex to be held.
 */
static void cxl_mem_mbox_put(struct cxl_mem *cxlm)
{
	mutex_unlock(&cxlm->mbox_mutex);
}

/**
 * handle_mailbox_cmd_from_user() - Dispatch a mailbox command for userspace.
 * @cxlm: The CXL memory device to communicate with.
 * @cmd: The validated command.
 * @in_payload: Pointer to userspace's input payload.
 * @out_payload: Pointer to userspace's output payload.
 * @size_out: (Input) Max payload size to copy out.
 *            (Output) Payload size hardware generated.
 * @retval: Hardware generated return code from the operation.
 *
 * Return:
 *  * %0	- Mailbox transaction succeeded. This implies the mailbox
 *		  protocol completed successfully not that the operation itself
 *		  was successful.
 *  * %-ENOMEM  - Couldn't allocate a bounce buffer.
 *  * %-EFAULT	- Something happened with copy_to/from_user.
 *  * %-EINTR	- Mailbox acquisition interrupted.
 *  * %-EXXX	- Transaction level failures.
 *
 * Creates the appropriate mailbox command and dispatches it on behalf of a
 * userspace request. The input and output payloads are copied between
 * userspace.
 *
 * See cxl_send_cmd().
 */
static int handle_mailbox_cmd_from_user(struct cxl_mem *cxlm,
					const struct cxl_mem_command *cmd,
					u64 in_payload, u64 out_payload,
					s32 *size_out, u32 *retval)
{
	struct device *dev = &cxlm->pdev->dev;
	struct mbox_cmd mbox_cmd = {
		.opcode = cmd->opcode,
		.size_in = cmd->info.size_in,
		.size_out = cmd->info.size_out,
	};
	int rc;

	if (cmd->info.size_out) {
		mbox_cmd.payload_out = kvzalloc(cmd->info.size_out, GFP_KERNEL);
		if (!mbox_cmd.payload_out)
			return -ENOMEM;
	}

	if (cmd->info.size_in) {
		mbox_cmd.payload_in = vmemdup_user(u64_to_user_ptr(in_payload),
						   cmd->info.size_in);
		if (IS_ERR(mbox_cmd.payload_in))
			return PTR_ERR(mbox_cmd.payload_in);
	}

	rc = cxl_mem_mbox_get(cxlm);
	if (rc)
		goto out;

	dev_dbg(dev,
		"Submitting %s command for user\n"
		"\topcode: %x\n"
		"\tsize: %ub\n",
		cxl_command_names[cmd->info.id].name, mbox_cmd.opcode,
		cmd->info.size_in);

	rc = __cxl_mem_mbox_send_cmd(cxlm, &mbox_cmd);
	cxl_mem_mbox_put(cxlm);
	if (rc)
		goto out;

	/*
	 * @size_out contains the max size that's allowed to be written back out
	 * to userspace. While the payload may have written more output than
	 * this it will have to be ignored.
	 */
	if (mbox_cmd.size_out) {
		dev_WARN_ONCE(dev, mbox_cmd.size_out > *size_out,
			      "Invalid return size\n");
		if (copy_to_user(u64_to_user_ptr(out_payload),
				 mbox_cmd.payload_out, mbox_cmd.size_out)) {
			rc = -EFAULT;
			goto out;
		}
	}

	*size_out = mbox_cmd.size_out;
	*retval = mbox_cmd.return_code;

out:
	kvfree(mbox_cmd.payload_in);
	kvfree(mbox_cmd.payload_out);
	return rc;
}

/**
 * cxl_validate_cmd_from_user() - Check fields for CXL_MEM_SEND_COMMAND.
 * @cxlm: &struct cxl_mem device whose mailbox will be used.
 * @send_cmd: &struct cxl_send_command copied in from userspace.
 * @out_cmd: Sanitized and populated &struct cxl_mem_command.
 *
 * Return:
 *  * %0	- @out_cmd is ready to send.
 *  * %-ENOTTY	- Invalid command specified.
 *  * %-EINVAL	- Reserved fields or invalid values were used.
 *  * %-ENOMEM	- Input or output buffer wasn't sized properly.
 *
 * The result of this command is a fully validated command in @out_cmd that is
 * safe to send to the hardware.
 *
 * See handle_mailbox_cmd_from_user()
 */
static int cxl_validate_cmd_from_user(struct cxl_mem *cxlm,
				      const struct cxl_send_command *send_cmd,
				      struct cxl_mem_command *out_cmd)
{
	const struct cxl_command_info *info;
	struct cxl_mem_command *c;

	if (send_cmd->id == 0 || send_cmd->id >= CXL_MEM_COMMAND_ID_MAX)
		return -ENOTTY;

	/*
	 * The user can never specify an input payload larger than what hardware
	 * supports, but output can be arbitrarily large (simply write out as
	 * much data as the hardware provides).
	 */
	if (send_cmd->in.size > cxlm->payload_size)
		return -EINVAL;

	if (send_cmd->flags & ~CXL_MEM_COMMAND_FLAG_MASK)
		return -EINVAL;

	if (send_cmd->rsvd)
		return -EINVAL;

	if (send_cmd->in.rsvd || send_cmd->out.rsvd)
		return -EINVAL;

	/* Convert user's command into the internal representation */
	c = &mem_commands[send_cmd->id];
	info = &c->info;

	/* Check the input buffer is the expected size */
	if (info->size_in >= 0 && info->size_in != send_cmd->in.size)
		return -ENOMEM;

	/* Check the output buffer is at least large enough */
	if (info->size_out >= 0 && send_cmd->out.size < info->size_out)
		return -ENOMEM;

	memcpy(out_cmd, c, sizeof(*c));
	out_cmd->info.size_in = send_cmd->in.size;
	/*
	 * XXX: out_cmd->info.size_out will be controlled by the driver, and the
	 * specified number of bytes @send_cmd->out.size will be copied back out
	 * to userspace.
	 */

	return 0;
}

static int cxl_query_cmd(struct cxl_memdev *cxlmd,
			 struct cxl_mem_query_commands __user *q)
{
	struct device *dev = &cxlmd->dev;
	struct cxl_mem_command *cmd;
	u32 n_commands;
	int j = 0;

	dev_dbg(dev, "Query IOCTL\n");

	if (get_user(n_commands, &q->n_commands))
		return -EFAULT;

	/* returns the total number if 0 elements are requested. */
	if (n_commands == 0)
		return put_user(cxl_cmd_count, &q->n_commands);

	/*
	 * otherwise, return max(n_commands, total commands) cxl_command_info
	 * structures.
	 */
	cxl_for_each_cmd(cmd) {
		const struct cxl_command_info *info = &cmd->info;

		if (copy_to_user(&q->commands[j++], info, sizeof(*info)))
			return -EFAULT;

		if (j == n_commands)
			break;
	}

	return 0;
}

static int cxl_send_cmd(struct cxl_memdev *cxlmd,
			struct cxl_send_command __user *s)
{
	struct cxl_mem *cxlm = cxlmd->cxlm;
	struct device *dev = &cxlmd->dev;
	struct cxl_send_command send;
	struct cxl_mem_command c;
	int rc;

	dev_dbg(dev, "Send IOCTL\n");

	if (copy_from_user(&send, s, sizeof(send)))
		return -EFAULT;

	rc = cxl_validate_cmd_from_user(cxlmd->cxlm, &send, &c);
	if (rc)
		return rc;

	/* Prepare to handle a full payload for variable sized output */
	if (c.info.size_out < 0)
		c.info.size_out = cxlm->payload_size;

	rc = handle_mailbox_cmd_from_user(cxlm, &c, send.in.payload,
					  send.out.payload, &send.out.size,
					  &send.retval);
	if (rc)
		return rc;

	return copy_to_user(s, &send, sizeof(send));
}

static long __cxl_memdev_ioctl(struct cxl_memdev *cxlmd, unsigned int cmd,
			       unsigned long arg)
{
	switch (cmd) {
	case CXL_MEM_QUERY_COMMANDS:
		return cxl_query_cmd(cxlmd, (void __user *)arg);
	case CXL_MEM_SEND_COMMAND:
		return cxl_send_cmd(cxlmd, (void __user *)arg);
	default:
		return -ENOTTY;
	}
}

static long cxl_memdev_ioctl(struct file *file, unsigned int cmd,
			     unsigned long arg)
{
	struct cxl_memdev *cxlmd;
	struct inode *inode;
	int rc = -ENOTTY;

	inode = file_inode(file);
	cxlmd = container_of(inode->i_cdev, typeof(*cxlmd), cdev);

	if (!percpu_ref_tryget_live(&cxlmd->ops_active))
		return -ENXIO;

	rc = __cxl_memdev_ioctl(cxlmd, cmd, arg);

	percpu_ref_put(&cxlmd->ops_active);

	return rc;
}

static const struct file_operations cxl_memdev_fops = {
	.owner = THIS_MODULE,
	.unlocked_ioctl = cxl_memdev_ioctl,
	.compat_ioctl = compat_ptr_ioctl,
	.llseek = noop_llseek,
};

/**
 * cxl_mem_mbox_send_cmd() - Send a mailbox command to a memory device.
 * @cxlm: The CXL memory device to communicate with.
 * @opcode: Opcode for the mailbox command.
 * @in: The input payload for the mailbox command.
 * @in_size: The length of the input payload
 * @out: Caller allocated buffer for the output.
 * @out_size: Expected size of output.
 *
 * Context: Any context. Will acquire and release mbox_mutex.
 * Return:
 *  * %>=0	- Number of bytes returned in @out.
 *  * %-E2BIG	- Payload is too large for hardware.
 *  * %-EBUSY	- Couldn't acquire exclusive mailbox access.
 *  * %-EFAULT	- Hardware error occurred.
 *  * %-ENXIO	- Command completed, but device reported an error.
 *  * %-EIO	- Unexpected output size.
 *
 * Mailbox commands may execute successfully yet the device itself reported an
 * error. While this distinction can be useful for commands from userspace, the
 * kernel will only be able to use results when both are successful. It's
 * expected that all callers of this function know exactly the size of the data
 * they will consume from the hardware.
 *
 * See __cxl_mem_mbox_send_cmd()
 */
static int cxl_mem_mbox_send_cmd(struct cxl_mem *cxlm, u16 opcode,
				 void *in, size_t in_size,
				 void *out, size_t out_size)
{
	struct mbox_cmd mbox_cmd = {
		.opcode = opcode,
		.payload_in = in,
		.size_in = in_size,
		.size_out = out_size,
		.payload_out = out,
	};
	int rc;

	if (out_size > cxlm->payload_size)
		return -E2BIG;

	rc = cxl_mem_mbox_get(cxlm);
	if (rc)
		return rc;

	rc = __cxl_mem_mbox_send_cmd(cxlm, &mbox_cmd);
	cxl_mem_mbox_put(cxlm);
	if (rc)
		return rc;

	/* TODO: Map return code to proper kernel style errno */
	if (mbox_cmd.return_code != CXL_MBOX_SUCCESS)
		return -ENXIO;

	if (mbox_cmd.size_out != out_size)
		return -EIO;

	return 0;
}

/**
 * cxl_mem_setup_regs() - Setup necessary MMIO.
 * @cxlm: The CXL memory device to communicate with.
 *
 * Return: 0 if all necessary registers mapped.
 *
 * A memory device is required by spec to implement a certain set of MMIO
 * regions. The purpose of this function is to enumerate and map those
 * registers.
 */
static int cxl_mem_setup_regs(struct cxl_mem *cxlm)
{
	struct device *dev = &cxlm->pdev->dev;
	int cap, cap_count;
	u64 cap_array;

	cap_array = readq(cxlm->regs + CXLDEV_CAP_ARRAY_OFFSET);
	if (FIELD_GET(CXLDEV_CAP_ARRAY_ID_MASK, cap_array) !=
	    CXLDEV_CAP_ARRAY_CAP_ID)
		return -ENODEV;

	cap_count = FIELD_GET(CXLDEV_CAP_ARRAY_COUNT_MASK, cap_array);

	for (cap = 1; cap <= cap_count; cap++) {
		void __iomem *register_block;
		u32 offset;
		u16 cap_id;

		cap_id = FIELD_GET(CXLDEV_CAP_HDR_CAP_ID_MASK,
				   readl(cxlm->regs + cap * 0x10));
		offset = readl(cxlm->regs + cap * 0x10 + 0x4);
		register_block = cxlm->regs + offset;

		switch (cap_id) {
		case CXLDEV_CAP_CAP_ID_DEVICE_STATUS:
			dev_dbg(dev, "found Status capability (0x%x)\n", offset);
			cxlm->status_regs = register_block;
			break;
		case CXLDEV_CAP_CAP_ID_PRIMARY_MAILBOX:
			dev_dbg(dev, "found Mailbox capability (0x%x)\n", offset);
			cxlm->mbox_regs = register_block;
			break;
		case CXLDEV_CAP_CAP_ID_SECONDARY_MAILBOX:
			dev_dbg(dev, "found Secondary Mailbox capability (0x%x)\n", offset);
			break;
		case CXLDEV_CAP_CAP_ID_MEMDEV:
			dev_dbg(dev, "found Memory Device capability (0x%x)\n", offset);
			cxlm->memdev_regs = register_block;
			break;
		default:
			dev_dbg(dev, "Unknown cap ID: %d (0x%x)\n", cap_id, offset);
			break;
		}
	}

	if (!cxlm->status_regs || !cxlm->mbox_regs || !cxlm->memdev_regs) {
		dev_err(dev, "registers not found: %s%s%s\n",
			!cxlm->status_regs ? "status " : "",
			!cxlm->mbox_regs ? "mbox " : "",
			!cxlm->memdev_regs ? "memdev" : "");
		return -ENXIO;
	}

	return 0;
}

static int cxl_mem_setup_mailbox(struct cxl_mem *cxlm)
{
	const int cap = readl(cxlm->mbox_regs + CXLDEV_MBOX_CAPS_OFFSET);

	cxlm->payload_size =
		1 << FIELD_GET(CXLDEV_MBOX_CAP_PAYLOAD_SIZE_MASK, cap);

	/*
	 * CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register
	 *
	 * If the size is too small, mandatory commands will not work and so
	 * there's no point in going forward. If the size is too large, there's
	 * no harm is soft limiting it.
	 */
	cxlm->payload_size = min_t(size_t, cxlm->payload_size, SZ_1M);
	if (cxlm->payload_size < 256) {
		dev_err(&cxlm->pdev->dev, "Mailbox is too small (%zub)",
			cxlm->payload_size);
		return -ENXIO;
	}

	dev_dbg(&cxlm->pdev->dev, "Mailbox payload sized %zu",
		cxlm->payload_size);

	return 0;
}

static struct cxl_mem *cxl_mem_create(struct pci_dev *pdev, u32 reg_lo,
				      u32 reg_hi)
{
	struct device *dev = &pdev->dev;
	struct cxl_mem *cxlm;
	void __iomem *regs;
	u64 offset;
	u8 bar;
	int rc;

	cxlm = devm_kzalloc(&pdev->dev, sizeof(*cxlm), GFP_KERNEL);
	if (!cxlm) {
		dev_err(dev, "No memory available\n");
		return NULL;
	}

	offset = ((u64)reg_hi << 32) | FIELD_GET(CXL_REGLOC_ADDR_MASK, reg_lo);
	bar = FIELD_GET(CXL_REGLOC_BIR_MASK, reg_lo);

	/* Basic sanity check that BAR is big enough */
	if (pci_resource_len(pdev, bar) < offset) {
		dev_err(dev, "BAR%d: %pr: too small (offset: %#llx)\n", bar,
			&pdev->resource[bar], (unsigned long long)offset);
		return NULL;
	}

	rc = pcim_iomap_regions(pdev, BIT(bar), pci_name(pdev));
	if (rc) {
		dev_err(dev, "failed to map registers\n");
		return NULL;
	}
	regs = pcim_iomap_table(pdev)[bar];

	mutex_init(&cxlm->mbox_mutex);
	cxlm->pdev = pdev;
	cxlm->regs = regs + offset;

	dev_dbg(dev, "Mapped CXL Memory Device resource\n");
	return cxlm;
}

static int cxl_mem_dvsec(struct pci_dev *pdev, int dvsec)
{
	int pos;

	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DVSEC);
	if (!pos)
		return 0;

	while (pos) {
		u16 vendor, id;

		pci_read_config_word(pdev, pos + PCI_DVSEC_HEADER1, &vendor);
		pci_read_config_word(pdev, pos + PCI_DVSEC_HEADER2, &id);
		if (vendor == PCI_DVSEC_VENDOR_ID_CXL && dvsec == id)
			return pos;

		pos = pci_find_next_ext_capability(pdev, pos,
						   PCI_EXT_CAP_ID_DVSEC);
	}

	return 0;
}

static struct cxl_memdev *to_cxl_memdev(struct device *dev)
{
	return container_of(dev, struct cxl_memdev, dev);
}

static void cxl_memdev_release(struct device *dev)
{
	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);

	percpu_ref_exit(&cxlmd->ops_active);
	ida_free(&cxl_memdev_ida, cxlmd->id);
	kfree(cxlmd);
}

static char *cxl_memdev_devnode(struct device *dev, umode_t *mode, kuid_t *uid,
				kgid_t *gid)
{
	return kasprintf(GFP_KERNEL, "cxl/%s", dev_name(dev));
}

static ssize_t firmware_version_show(struct device *dev,
				     struct device_attribute *attr, char *buf)
{
	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
	struct cxl_mem *cxlm = cxlmd->cxlm;

	return sprintf(buf, "%.16s\n", cxlm->firmware_version);
}
static DEVICE_ATTR_RO(firmware_version);

static ssize_t payload_max_show(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
	struct cxl_mem *cxlm = cxlmd->cxlm;

	return sprintf(buf, "%zu\n", cxlm->payload_size);
}
static DEVICE_ATTR_RO(payload_max);

static ssize_t ram_size_show(struct device *dev, struct device_attribute *attr,
			     char *buf)
{
	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
	struct cxl_mem *cxlm = cxlmd->cxlm;
	unsigned long long len = range_len(&cxlm->ram_range);

	return sprintf(buf, "%#llx\n", len);
}

static struct device_attribute dev_attr_ram_size =
	__ATTR(size, 0444, ram_size_show, NULL);

static ssize_t pmem_size_show(struct device *dev, struct device_attribute *attr,
			      char *buf)
{
	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
	struct cxl_mem *cxlm = cxlmd->cxlm;
	unsigned long long len = range_len(&cxlm->pmem_range);

	return sprintf(buf, "%#llx\n", len);
}

static struct device_attribute dev_attr_pmem_size =
	__ATTR(size, 0444, pmem_size_show, NULL);

static struct attribute *cxl_memdev_attributes[] = {
	&dev_attr_firmware_version.attr,
	&dev_attr_payload_max.attr,
	NULL,
};

static struct attribute *cxl_memdev_pmem_attributes[] = {
	&dev_attr_pmem_size.attr,
	NULL,
};

static struct attribute *cxl_memdev_ram_attributes[] = {
	&dev_attr_ram_size.attr,
	NULL,
};

static struct attribute_group cxl_memdev_attribute_group = {
	.attrs = cxl_memdev_attributes,
};

static struct attribute_group cxl_memdev_ram_attribute_group = {
	.name = "ram",
	.attrs = cxl_memdev_ram_attributes,
};

static struct attribute_group cxl_memdev_pmem_attribute_group = {
	.name = "pmem",
	.attrs = cxl_memdev_pmem_attributes,
};

static const struct attribute_group *cxl_memdev_attribute_groups[] = {
	&cxl_memdev_attribute_group,
	&cxl_memdev_ram_attribute_group,
	&cxl_memdev_pmem_attribute_group,
	NULL,
};

static const struct device_type cxl_memdev_type = {
	.name = "cxl_memdev",
	.release = cxl_memdev_release,
	.devnode = cxl_memdev_devnode,
	.groups = cxl_memdev_attribute_groups,
};

static void cxlmdev_unregister(void *_cxlmd)
{
	struct cxl_memdev *cxlmd = _cxlmd;
	struct device *dev = &cxlmd->dev;

	percpu_ref_kill(&cxlmd->ops_active);
	cdev_device_del(&cxlmd->cdev, dev);
	wait_for_completion(&cxlmd->ops_dead);
	cxlmd->cxlm = NULL;
	put_device(dev);
}

static void cxlmdev_ops_active_release(struct percpu_ref *ref)
{
	struct cxl_memdev *cxlmd =
		container_of(ref, typeof(*cxlmd), ops_active);

	complete(&cxlmd->ops_dead);
}

static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
{
	struct pci_dev *pdev = cxlm->pdev;
	struct cxl_memdev *cxlmd;
	struct device *dev;
	struct cdev *cdev;
	int rc;

	cxlmd = kzalloc(sizeof(*cxlmd), GFP_KERNEL);
	if (!cxlmd)
		return -ENOMEM;
	init_completion(&cxlmd->ops_dead);

	/*
	 * @cxlm is deallocated when the driver unbinds so operations
	 * that are using it need to hold a live reference.
	 */
	cxlmd->cxlm = cxlm;
	rc = percpu_ref_init(&cxlmd->ops_active, cxlmdev_ops_active_release, 0,
			     GFP_KERNEL);
	if (rc)
		goto err_ref;

	rc = ida_alloc_range(&cxl_memdev_ida, 0, CXL_MEM_MAX_DEVS, GFP_KERNEL);
	if (rc < 0)
		goto err_id;
	cxlmd->id = rc;

	dev = &cxlmd->dev;
	device_initialize(dev);
	dev->parent = &pdev->dev;
	dev->bus = &cxl_bus_type;
	dev->devt = MKDEV(cxl_mem_major, cxlmd->id);
	dev->type = &cxl_memdev_type;
	dev_set_name(dev, "mem%d", cxlmd->id);

	cdev = &cxlmd->cdev;
	cdev_init(cdev, &cxl_memdev_fops);

	rc = cdev_device_add(cdev, dev);
	if (rc)
		goto err_add;

	return devm_add_action_or_reset(dev->parent, cxlmdev_unregister, cxlmd);

err_add:
	ida_free(&cxl_memdev_ida, cxlmd->id);
err_id:
	/*
	 * Theoretically userspace could have already entered the fops,
	 * so flush ops_active.
	 */
	percpu_ref_kill(&cxlmd->ops_active);
	wait_for_completion(&cxlmd->ops_dead);
	percpu_ref_exit(&cxlmd->ops_active);
err_ref:
	kfree(cxlmd);

	return rc;
}

/**
 * cxl_mem_identify() - Send the IDENTIFY command to the device.
 * @cxlm: The device to identify.
 *
 * Return: 0 if identify was executed successfully.
 *
 * This will dispatch the identify command to the device and on success populate
 * structures to be exported to sysfs.
 */
static int cxl_mem_identify(struct cxl_mem *cxlm)
{
	struct cxl_mbox_identify {
		char fw_revision[0x10];
		__le64 total_capacity;
		__le64 volatile_capacity;
		__le64 persistent_capacity;
		__le64 partition_align;
		__le16 info_event_log_size;
		__le16 warning_event_log_size;
		__le16 failure_event_log_size;
		__le16 fatal_event_log_size;
		__le32 lsa_size;
		u8 poison_list_max_mer[3];
		__le16 inject_poison_limit;
		u8 poison_caps;
		u8 qos_telemetry_caps;
	} __packed id;
	int rc;

	rc = cxl_mem_mbox_send_cmd(cxlm, CXL_MBOX_OP_IDENTIFY, NULL, 0, &id,
				   sizeof(id));
	if (rc < 0)
		return rc;

	/*
	 * TODO: enumerate DPA map, as 'ram' and 'pmem' do not alias.
	 * For now, only the capacity is exported in sysfs
	 */
	cxlm->ram_range.start = 0;
	cxlm->ram_range.end = le64_to_cpu(id.volatile_capacity) - 1;

	cxlm->pmem_range.start = 0;
	cxlm->pmem_range.end = le64_to_cpu(id.persistent_capacity) - 1;

	memcpy(cxlm->firmware_version, id.fw_revision, sizeof(id.fw_revision));

	return 0;
}

static int cxl_mem_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
	struct device *dev = &pdev->dev;
	struct cxl_mem *cxlm = NULL;
	u32 regloc_size, regblocks;
	int rc, regloc, i;

	rc = pcim_enable_device(pdev);
	if (rc)
		return rc;

	regloc = cxl_mem_dvsec(pdev, PCI_DVSEC_ID_CXL_REGLOC_OFFSET);
	if (!regloc) {
		dev_err(dev, "register location dvsec not found\n");
		return -ENXIO;
	}

	/* Get the size of the Register Locator DVSEC */
	pci_read_config_dword(pdev, regloc + PCI_DVSEC_HEADER1, &regloc_size);
	regloc_size = FIELD_GET(PCI_DVSEC_HEADER1_LENGTH_MASK, regloc_size);

	regloc += PCI_DVSEC_ID_CXL_REGLOC_BLOCK1_OFFSET;
	regblocks = (regloc_size - PCI_DVSEC_ID_CXL_REGLOC_BLOCK1_OFFSET) / 8;

	for (i = 0; i < regblocks; i++, regloc += 8) {
		u32 reg_lo, reg_hi;
		u8 reg_type;

		/* "register low and high" contain other bits */
		pci_read_config_dword(pdev, regloc, &reg_lo);
		pci_read_config_dword(pdev, regloc + 4, &reg_hi);

		reg_type = FIELD_GET(CXL_REGLOC_RBI_MASK, reg_lo);

		if (reg_type == CXL_REGLOC_RBI_MEMDEV) {
			cxlm = cxl_mem_create(pdev, reg_lo, reg_hi);
			break;
		}
	}

	if (!cxlm)
		return -ENODEV;

	rc = cxl_mem_setup_regs(cxlm);
	if (rc)
		return rc;

	rc = cxl_mem_setup_mailbox(cxlm);
	if (rc)
		return rc;

	rc = cxl_mem_identify(cxlm);
	if (rc)
		return rc;

	return cxl_mem_add_memdev(cxlm);
}

static const struct pci_device_id cxl_mem_pci_tbl[] = {
	/* PCI class code for CXL.mem Type-3 Devices */
	{ PCI_DEVICE_CLASS((PCI_CLASS_MEMORY_CXL << 8 | CXL_MEMORY_PROGIF), ~0)},
	{ /* terminate list */ },
};
MODULE_DEVICE_TABLE(pci, cxl_mem_pci_tbl);

static struct pci_driver cxl_mem_driver = {
	.name			= KBUILD_MODNAME,
	.id_table		= cxl_mem_pci_tbl,
	.probe			= cxl_mem_probe,
	.driver	= {
		.probe_type	= PROBE_PREFER_ASYNCHRONOUS,
	},
};

static __init int cxl_mem_init(void)
{
	dev_t devt;
	int rc;

	rc = alloc_chrdev_region(&devt, 0, CXL_MEM_MAX_DEVS, "cxl");
	if (rc)
		return rc;

	cxl_mem_major = MAJOR(devt);

	rc = pci_register_driver(&cxl_mem_driver);
	if (rc) {
		unregister_chrdev_region(MKDEV(cxl_mem_major, 0),
					 CXL_MEM_MAX_DEVS);
		return rc;
	}

	return 0;
}

static __exit void cxl_mem_exit(void)
{
	pci_unregister_driver(&cxl_mem_driver);
	unregister_chrdev_region(MKDEV(cxl_mem_major, 0), CXL_MEM_MAX_DEVS);
}

MODULE_LICENSE("GPL v2");
module_init(cxl_mem_init);
module_exit(cxl_mem_exit);
MODULE_IMPORT_NS(CXL);