aboutsummaryrefslogtreecommitdiffstats
path: root/arch/cris/arch-v10/kernel/head.S
blob: b260a8833903b89cb48dc77df0b660a649dd35a6 (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
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Head of the kernel - alter with care
 *
 * Copyright (C) 2000, 2001, 2010 Axis Communications AB
 *
 */

#include <linux/init.h>

#define ASSEMBLER_MACROS_ONLY
/* The IO_* macros use the ## token concatenation operator, so
   -traditional must not be used when assembling this file.  */
#include <arch/sv_addr_ag.h>

#define CRAMFS_MAGIC 0x28cd3d45
#define RAM_INIT_MAGIC 0x56902387
#define COMMAND_LINE_MAGIC 0x87109563

#define START_ETHERNET_CLOCK IO_STATE(R_NETWORK_GEN_CONFIG, enable, on) |\
                             IO_STATE(R_NETWORK_GEN_CONFIG, phy, mii_clk)

	;; exported symbols

	.globl	etrax_irv
	.globl	romfs_start
	.globl	romfs_length
	.globl	romfs_in_flash
	.globl  swapper_pg_dir

	__HEAD

	;; This is the entry point of the kernel. We are in supervisor mode.
	;; 0x00000000 if Flash, 0x40004000 if DRAM
	;; since etrax actually starts at address 2 when booting from flash, we
	;; put a nop (2 bytes) here first so we dont accidentally skip the di
	;;
	;; NOTICE! The registers r8 and r9 are used as parameters carrying
	;; information from the decompressor (if the kernel was compressed).
	;; They should not be used in the code below until read.

	nop
	di

	;; First setup the kseg_c mapping from where the kernel is linked
	;; to 0x40000000 (where the actual DRAM resides) otherwise
	;; we cannot do very much! See arch/cris/README.mm
	;;
	;; Notice that since we're potentially running at 0x00 or 0x40 right now,
	;; we will get a fault as soon as we enable the MMU if we dont
	;; temporarily map those segments linearily.
	;;
	;; Due to a bug in Etrax-100 LX version 1 we need to map the memory
	;; slightly different.  The bug is that you can't remap bit 31 of
	;; an address.  Though we can check the version register for
	;; whether the bug is present, some constants would then have to
	;; be variables, so we don't.  The drawback is that you can "only" map
	;; 1G per process with CONFIG_CRIS_LOW_MAP.

#ifdef CONFIG_CRIS_LOW_MAP
	; kseg mappings, temporary map of 0xc0->0x40
	move.d	  IO_FIELD (R_MMU_KBASE_HI, base_c, 4)		\
		| IO_FIELD (R_MMU_KBASE_HI, base_b, 0xb)	\
		| IO_FIELD (R_MMU_KBASE_HI, base_9, 9)		\
		| IO_FIELD (R_MMU_KBASE_HI, base_8, 8), $r0
	move.d	$r0, [R_MMU_KBASE_HI]

	; temporary map of 0x40->0x40 and 0x60->0x40
	move.d	  IO_FIELD (R_MMU_KBASE_LO, base_6, 4)		\
		| IO_FIELD (R_MMU_KBASE_LO, base_4, 4), $r0
	move.d	$r0, [R_MMU_KBASE_LO]

	; mmu enable, segs e,c,b,a,6,5,4,0 segment mapped
	move.d	  IO_STATE (R_MMU_CONFIG, mmu_enable, enable)	\
		| IO_STATE (R_MMU_CONFIG, inv_excp, enable)	\
		| IO_STATE (R_MMU_CONFIG, acc_excp, enable)	\
		| IO_STATE (R_MMU_CONFIG, we_excp, enable)	\
		| IO_STATE (R_MMU_CONFIG, seg_f, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_e, seg)		\
		| IO_STATE (R_MMU_CONFIG, seg_d, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_c, seg)		\
		| IO_STATE (R_MMU_CONFIG, seg_b, seg)		\
		| IO_STATE (R_MMU_CONFIG, seg_a, seg)		\
		| IO_STATE (R_MMU_CONFIG, seg_9, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_8, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_7, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_6, seg)		\
		| IO_STATE (R_MMU_CONFIG, seg_5, seg)		\
		| IO_STATE (R_MMU_CONFIG, seg_4, seg)		\
		| IO_STATE (R_MMU_CONFIG, seg_3, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_2, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_1, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_0, seg), $r0
	move.d	$r0, [R_MMU_CONFIG]
#else
	; kseg mappings
	move.d	  IO_FIELD (R_MMU_KBASE_HI, base_e, 8)		\
		| IO_FIELD (R_MMU_KBASE_HI, base_c, 4)		\
		| IO_FIELD (R_MMU_KBASE_HI, base_b, 0xb), $r0
	move.d	$r0, [R_MMU_KBASE_HI]

	; temporary map of 0x40->0x40 and 0x00->0x00
	move.d	  IO_FIELD (R_MMU_KBASE_LO, base_4, 4), $r0
	move.d	$r0, [R_MMU_KBASE_LO]

	; mmu enable, segs f,e,c,b,4,0 segment mapped
	move.d	  IO_STATE (R_MMU_CONFIG, mmu_enable, enable)	\
		| IO_STATE (R_MMU_CONFIG, inv_excp, enable)	\
		| IO_STATE (R_MMU_CONFIG, acc_excp, enable)	\
		| IO_STATE (R_MMU_CONFIG, we_excp, enable)	\
		| IO_STATE (R_MMU_CONFIG, seg_f, seg)		\
		| IO_STATE (R_MMU_CONFIG, seg_e, seg)		\
		| IO_STATE (R_MMU_CONFIG, seg_d, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_c, seg)		\
		| IO_STATE (R_MMU_CONFIG, seg_b, seg)		\
		| IO_STATE (R_MMU_CONFIG, seg_a, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_9, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_8, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_7, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_6, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_5, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_4, seg)		\
		| IO_STATE (R_MMU_CONFIG, seg_3, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_2, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_1, page)		\
		| IO_STATE (R_MMU_CONFIG, seg_0, seg), $r0
	move.d	$r0, [R_MMU_CONFIG]
#endif

	;; Now we need to sort out the segments and their locations in RAM or
	;; Flash. The image in the Flash (or in DRAM) consists of 3 pieces:
	;; 1) kernel text, 2) kernel data, 3) ROM filesystem image
	;; But the linker has linked the kernel to expect this layout in
	;; DRAM memory:
	;; 1) kernel text, 2) kernel data, 3) kernel BSS
	;; (the location of the ROM filesystem is determined by the krom driver)
	;; If we boot this from Flash, we want to keep the ROM filesystem in
	;; the flash, we want to copy the text and need to copy the data to DRAM.
	;; But if we boot from DRAM, we need to move the ROMFS image
	;; from its position after kernel data, to after kernel BSS, BEFORE the
	;; kernel starts using the BSS area (since its "overlayed" with the ROMFS)
	;;
	;; In both cases, we start in un-cached mode, and need to jump into a
	;; cached PC after we're done fiddling around with the segments.
	;;
	;; arch/etrax100/etrax100.ld sets some symbols that define the start
	;; and end of each segment.

	;; Check if we start from DRAM or FLASH by testing PC

	move.d	$pc,$r0
	and.d	0x7fffffff,$r0	; get rid of the non-cache bit
	cmp.d	0x10000,$r0	; arbitrary... just something above this code
	blo	_inflash0
	nop

	jump	_inram		; enter cached ram

	;; Jumpgate for branches.
_inflash0:
	jump	_inflash

	;; Put this in a suitable section where we can reclaim storage
	;; after init.
	__INIT
_inflash:
#ifdef CONFIG_ETRAX_ETHERNET
	;; Start MII clock to make sure it is running when tranceiver is reset
	move.d START_ETHERNET_CLOCK, $r0
	move.d $r0, [R_NETWORK_GEN_CONFIG]
#endif

	;; Set up waitstates etc according to kernel configuration.
	move.d   CONFIG_ETRAX_DEF_R_WAITSTATES, $r0
	move.d   $r0, [R_WAITSTATES]

	move.d   CONFIG_ETRAX_DEF_R_BUS_CONFIG, $r0
	move.d   $r0, [R_BUS_CONFIG]

	;; We need to initialze DRAM registers before we start using the DRAM

	cmp.d	RAM_INIT_MAGIC, $r8	; Already initialized?
	beq	_dram_init_finished
	nop

#include "../lib/dram_init.S"

_dram_init_finished:
	;; Copy text+data to DRAM
	;; This is fragile - the calculation of r4 as the image size depends
	;; on that the labels below actually are the first and last positions
	;; in the linker-script.
	;;
	;; Then the locating of the cramfs image depends on the aforementioned
	;; image being located in the flash at 0. This is most often not true,
	;; thus the following does not work (normally there is a rescue-block
	;; between the physical start of the flash and the flash-image start,
	;; and when run with compression, the kernel is actually unpacked to
	;; DRAM and we never get here in the first place :))

	moveq	0, $r0			; source
	move.d	text_start, $r1		; destination
	move.d	__vmlinux_end, $r2	; end destination
	move.d	$r2, $r4
	sub.d	$r1, $r4		; r4=__vmlinux_end in flash, used below
1:	move.w	[$r0+], $r3
	move.w	$r3, [$r1+]
	cmp.d	$r2, $r1
	blo	1b
	nop

	;; We keep the cramfs in the flash.
	;; There might be none, but that does not matter because
	;; we don't do anything than read some bytes here.

	moveq	0, $r0
	move.d	$r0, [romfs_length] ; default if there is no cramfs

	move.d  [$r4], $r0	; cramfs_super.magic
	cmp.d	CRAMFS_MAGIC, $r0
	bne	1f
	nop
	move.d	[$r4 + 4], $r0	; cramfs_super.size
	move.d	$r0, [romfs_length]
#ifdef CONFIG_CRIS_LOW_MAP
	add.d   0x50000000, $r4	; add flash start in virtual memory (cached)
#else
	add.d   0xf0000000, $r4	; add flash start in virtual memory (cached)
#endif
	move.d	$r4, [romfs_start]
1:
	moveq	1, $r0
	move.d	$r0, [romfs_in_flash]

	jump	_start_it	; enter code, cached this time

_inram:
	;; Move the ROM fs to after BSS end. This assumes that the cramfs
	;; second longword contains the length of the cramfs

	moveq	0, $r0
	move.d	$r0, [romfs_length] ; default if there is no cramfs

	;; The kernel could have been unpacked to DRAM by the loader, but
	;; the cramfs image could still be in the Flash directly after the
	;; compressed kernel image. The loader passes the address of the
	;; byte succeeding the last compressed byte in the flash in the
	;; register r9 when starting the kernel. Check if r9 points to a
	;; decent cramfs image!
	;; (Notice that if this is not booted from the loader, r9 will be
	;;  garbage but we do sanity checks on it, the chance that it points
	;;  to a cramfs magic is small.. )

	cmp.d	0x0ffffff8, $r9
	bhs	_no_romfs_in_flash	; r9 points outside the flash area
	nop
	move.d	[$r9], $r0	; cramfs_super.magic
	cmp.d	CRAMFS_MAGIC, $r0
	bne	_no_romfs_in_flash
	nop
	move.d	[$r9+4], $r0	; cramfs_super.length
	move.d	$r0, [romfs_length]
#ifdef CONFIG_CRIS_LOW_MAP
	add.d   0x50000000, $r9	; add flash start in virtual memory (cached)
#else
	add.d   0xf0000000, $r9	; add flash start in virtual memory (cached)
#endif
	move.d	$r9, [romfs_start]

	moveq	1, $r0
	move.d	$r0, [romfs_in_flash]

	jump	_start_it	; enter code, cached this time

_no_romfs_in_flash:

	;; Check if there is a cramfs (magic value).
	;; Notice that we check for cramfs magic value - which is
	;; the "rom fs" we'll possibly use in 2.4 if not JFFS (which does
	;; not need this mechanism anyway)

	move.d	__init_end, $r0; the image will be after the end of init
	move.d	[$r0], $r1	; cramfs assumes same endian on host/target
	cmp.d	CRAMFS_MAGIC, $r1; magic value in cramfs superblock
	bne	2f
	nop

	;; Ok. What is its size ?

	move.d	[$r0 + 4], $r2	; cramfs_super.size (again, no need to swapwb)

	;; We want to copy it to the end of the BSS

	move.d	_end, $r1

	;; Remember values so cramfs and setup can find this info

	move.d	$r1, [romfs_start]	; new romfs location
	move.d	$r2, [romfs_length]

	;; We need to copy it backwards, since they can be overlapping

	add.d	$r2, $r0
	add.d	$r2, $r1

	;; Go ahead. Make my loop.

	lsrq	1, $r2		; size is in bytes, we copy words

1:	move.w	[$r0=$r0-2],$r3
	move.w	$r3,[$r1=$r1-2]
	subq	1, $r2
	bne	1b
	nop

2:
	;; Dont worry that the BSS is tainted. It will be cleared later.

	moveq	0, $r0
	move.d	$r0, [romfs_in_flash]

	jump	_start_it	; better skip the additional cramfs check below

_start_it:

	;; Check if kernel command line is supplied
	cmp.d	COMMAND_LINE_MAGIC, $r10
	bne	no_command_line
	nop

	move.d	256, $r13
	move.d  cris_command_line, $r10
	or.d	0x80000000, $r11 ; Make it virtual
1:
	move.b  [$r11+], $r12
	move.b  $r12, [$r10+]
	subq	1, $r13
	bne	1b
	nop

no_command_line:

	;; the kernel stack is overlayed with the task structure for each
	;; task. thus the initial kernel stack is in the same page as the
	;; init_task (but starts in the top of the page, size 8192)
	move.d	init_thread_union + 8192, $sp
	move.d	ibr_start,$r0	; this symbol is set by the linker script 
	move	$r0,$ibr
	move.d	$r0,[etrax_irv]	; set the interrupt base register and pointer

	;; Clear BSS region, from _bss_start to _end

	move.d	__bss_start, $r0
	move.d	_end, $r1
1:	clear.d	[$r0+]
	cmp.d	$r1, $r0
	blo	1b
	nop

	;; Etrax product HW genconfig setup

	moveq	0,$r0

	;; Select or disable serial port 2
#ifdef CONFIG_ETRAX_SERIAL_PORT2
	or.d	  IO_STATE (R_GEN_CONFIG, ser2, select),$r0
#else
	or.d	  IO_STATE (R_GEN_CONFIG, ser2, disable),$r0
#endif

	;; Init interfaces (disable them).
	or.d	  IO_STATE (R_GEN_CONFIG, scsi0, disable) \
		| IO_STATE (R_GEN_CONFIG, ata, disable) \
		| IO_STATE (R_GEN_CONFIG, par0, disable) \
		| IO_STATE (R_GEN_CONFIG, mio, disable) \
		| IO_STATE (R_GEN_CONFIG, scsi1, disable) \
		| IO_STATE (R_GEN_CONFIG, scsi0w, disable) \
		| IO_STATE (R_GEN_CONFIG, par1, disable) \
		| IO_STATE (R_GEN_CONFIG, ser3, disable) \
		| IO_STATE (R_GEN_CONFIG, mio_w, disable) \
		| IO_STATE (R_GEN_CONFIG, usb1, disable) \
		| IO_STATE (R_GEN_CONFIG, usb2, disable) \
		| IO_STATE (R_GEN_CONFIG, par_w, disable),$r0

	;; Init DMA channel muxing (set to unused clients).
	or.d	  IO_STATE (R_GEN_CONFIG, dma2, ata)	\
		| IO_STATE (R_GEN_CONFIG, dma3, ata) \
		| IO_STATE (R_GEN_CONFIG, dma4, scsi1) \
		| IO_STATE (R_GEN_CONFIG, dma5, scsi1) \
		| IO_STATE (R_GEN_CONFIG, dma6, unused) \
		| IO_STATE (R_GEN_CONFIG, dma7, unused) \
		| IO_STATE (R_GEN_CONFIG, dma8, usb) \
		| IO_STATE (R_GEN_CONFIG, dma9, usb),$r0


	move.d	$r0,[genconfig_shadow] ; init a shadow register of R_GEN_CONFIG

	move.d	$r0,[R_GEN_CONFIG]

#if 0
	moveq	4,$r0
	move.b	$r0,[R_DMA_CH6_CMD]	; reset (ser0 dma out)
	move.b	$r0,[R_DMA_CH7_CMD]	; reset (ser0 dma in)
1:	move.b	[R_DMA_CH6_CMD],$r0	; wait for reset cycle to finish
	and.b	7,$r0
	cmp.b	4,$r0
	beq	1b
	nop
1:	move.b	[R_DMA_CH7_CMD],$r0	; wait for reset cycle to finish
	and.b	7,$r0
	cmp.b	4,$r0
	beq	1b
	nop
#endif

	moveq	IO_STATE (R_DMA_CH8_CMD, cmd, reset),$r0
	move.b	$r0,[R_DMA_CH8_CMD]	; reset (ser1 dma out)
	move.b	$r0,[R_DMA_CH9_CMD]	; reset (ser1 dma in)
1:	move.b	[R_DMA_CH8_CMD],$r0	; wait for reset cycle to finish
	andq	IO_MASK (R_DMA_CH8_CMD, cmd),$r0
	cmpq	IO_STATE (R_DMA_CH8_CMD, cmd, reset),$r0
	beq	1b
	nop
1:	move.b	[R_DMA_CH9_CMD],$r0	; wait for reset cycle to finish
	andq	IO_MASK (R_DMA_CH9_CMD, cmd),$r0
	cmpq	IO_STATE (R_DMA_CH9_CMD, cmd, reset),$r0
	beq	1b
	nop

	;; setup port PA and PB default initial directions and data
	;; including their shadow registers

	move.b	CONFIG_ETRAX_DEF_R_PORT_PA_DIR,$r0
	move.b	$r0,[port_pa_dir_shadow]
	move.b	$r0,[R_PORT_PA_DIR]
	move.b	CONFIG_ETRAX_DEF_R_PORT_PA_DATA,$r0
	move.b	$r0,[port_pa_data_shadow]
	move.b	$r0,[R_PORT_PA_DATA]

	move.b	CONFIG_ETRAX_DEF_R_PORT_PB_CONFIG,$r0
	move.b	$r0,[port_pb_config_shadow]
	move.b	$r0,[R_PORT_PB_CONFIG]
	move.b	CONFIG_ETRAX_DEF_R_PORT_PB_DIR,$r0
	move.b	$r0,[port_pb_dir_shadow]
	move.b	$r0,[R_PORT_PB_DIR]
	move.b	CONFIG_ETRAX_DEF_R_PORT_PB_DATA,$r0
	move.b	$r0,[port_pb_data_shadow]
	move.b	$r0,[R_PORT_PB_DATA]

	moveq   0, $r0
	move.d  $r0,[port_pb_i2c_shadow]
	move.d  $r0, [R_PORT_PB_I2C]

	moveq	0,$r0
	move.d	$r0,[port_g_data_shadow]
	move.d	$r0,[R_PORT_G_DATA]

	;; setup the serial port 0 at 115200 baud for debug purposes

	moveq	  IO_STATE (R_SERIAL0_XOFF, tx_stop, enable)		\
		| IO_STATE (R_SERIAL0_XOFF, auto_xoff, disable)		\
		| IO_FIELD (R_SERIAL0_XOFF, xoff_char, 0),$r0
	move.d	$r0,[R_SERIAL0_XOFF]

	; 115.2kbaud for both transmit and receive
	move.b	  IO_STATE (R_SERIAL0_BAUD, tr_baud, c115k2Hz)		\
		| IO_STATE (R_SERIAL0_BAUD, rec_baud, c115k2Hz),$r0
	move.b	$r0,[R_SERIAL0_BAUD]

	; Set up and enable the serial0 receiver.
	move.b	  IO_STATE (R_SERIAL0_REC_CTRL, dma_err, stop)		\
		| IO_STATE (R_SERIAL0_REC_CTRL, rec_enable, enable)	\
		| IO_STATE (R_SERIAL0_REC_CTRL, rts_, active)		\
		| IO_STATE (R_SERIAL0_REC_CTRL, sampling, middle)	\
		| IO_STATE (R_SERIAL0_REC_CTRL, rec_stick_par, normal)	\
		| IO_STATE (R_SERIAL0_REC_CTRL, rec_par, even)		\
		| IO_STATE (R_SERIAL0_REC_CTRL, rec_par_en, disable)	\
		| IO_STATE (R_SERIAL0_REC_CTRL, rec_bitnr, rec_8bit),$r0
	move.b	$r0,[R_SERIAL0_REC_CTRL]

	; Set up and enable the serial0 transmitter.
	move.b	  IO_FIELD (R_SERIAL0_TR_CTRL, txd, 0)			\
		| IO_STATE (R_SERIAL0_TR_CTRL, tr_enable, enable)	\
		| IO_STATE (R_SERIAL0_TR_CTRL, auto_cts, disabled)	\
		| IO_STATE (R_SERIAL0_TR_CTRL, stop_bits, one_bit)	\
		| IO_STATE (R_SERIAL0_TR_CTRL, tr_stick_par, normal)	\
		| IO_STATE (R_SERIAL0_TR_CTRL, tr_par, even)		\
		| IO_STATE (R_SERIAL0_TR_CTRL, tr_par_en, disable)	\
		| IO_STATE (R_SERIAL0_TR_CTRL, tr_bitnr, tr_8bit),$r0
	move.b	$r0,[R_SERIAL0_TR_CTRL]

	;; setup the serial port 1 at 115200 baud for debug purposes

	moveq	  IO_STATE (R_SERIAL1_XOFF, tx_stop, enable)		\
		| IO_STATE (R_SERIAL1_XOFF, auto_xoff, disable)		\
		| IO_FIELD (R_SERIAL1_XOFF, xoff_char, 0),$r0
	move.d	$r0,[R_SERIAL1_XOFF]

	; 115.2kbaud for both transmit and receive
	move.b	  IO_STATE (R_SERIAL1_BAUD, tr_baud, c115k2Hz)		\
		| IO_STATE (R_SERIAL1_BAUD, rec_baud, c115k2Hz),$r0
	move.b	$r0,[R_SERIAL1_BAUD]

	; Set up and enable the serial1 receiver.
	move.b	  IO_STATE (R_SERIAL1_REC_CTRL, dma_err, stop)		\
		| IO_STATE (R_SERIAL1_REC_CTRL, rec_enable, enable)	\
		| IO_STATE (R_SERIAL1_REC_CTRL, rts_, active)		\
		| IO_STATE (R_SERIAL1_REC_CTRL, sampling, middle)	\
		| IO_STATE (R_SERIAL1_REC_CTRL, rec_stick_par, normal)	\
		| IO_STATE (R_SERIAL1_REC_CTRL, rec_par, even)		\
		| IO_STATE (R_SERIAL1_REC_CTRL, rec_par_en, disable)	\
		| IO_STATE (R_SERIAL1_REC_CTRL, rec_bitnr, rec_8bit),$r0
	move.b	$r0,[R_SERIAL1_REC_CTRL]

	; Set up and enable the serial1 transmitter.
	move.b	  IO_FIELD (R_SERIAL1_TR_CTRL, txd, 0)			\
		| IO_STATE (R_SERIAL1_TR_CTRL, tr_enable, enable)	\
		| IO_STATE (R_SERIAL1_TR_CTRL, auto_cts, disabled)	\
		| IO_STATE (R_SERIAL1_TR_CTRL, stop_bits, one_bit)	\
		| IO_STATE (R_SERIAL1_TR_CTRL, tr_stick_par, normal)	\
		| IO_STATE (R_SERIAL1_TR_CTRL, tr_par, even)		\
		| IO_STATE (R_SERIAL1_TR_CTRL, tr_par_en, disable)	\
		| IO_STATE (R_SERIAL1_TR_CTRL, tr_bitnr, tr_8bit),$r0
	move.b	$r0,[R_SERIAL1_TR_CTRL]

#ifdef CONFIG_ETRAX_SERIAL_PORT2
	;; setup the serial port 2 at 115200 baud for debug purposes

	moveq	  IO_STATE (R_SERIAL2_XOFF, tx_stop, enable)		\
		| IO_STATE (R_SERIAL2_XOFF, auto_xoff, disable)		\
		| IO_FIELD (R_SERIAL2_XOFF, xoff_char, 0),$r0
	move.d	$r0,[R_SERIAL2_XOFF]

	; 115.2kbaud for both transmit and receive
	move.b	  IO_STATE (R_SERIAL2_BAUD, tr_baud, c115k2Hz)		\
		| IO_STATE (R_SERIAL2_BAUD, rec_baud, c115k2Hz),$r0
	move.b	$r0,[R_SERIAL2_BAUD]

	; Set up and enable the serial2 receiver.
	move.b	  IO_STATE (R_SERIAL2_REC_CTRL, dma_err, stop)		\
		| IO_STATE (R_SERIAL2_REC_CTRL, rec_enable, enable)	\
		| IO_STATE (R_SERIAL2_REC_CTRL, rts_, active)		\
		| IO_STATE (R_SERIAL2_REC_CTRL, sampling, middle)	\
		| IO_STATE (R_SERIAL2_REC_CTRL, rec_stick_par, normal)	\
		| IO_STATE (R_SERIAL2_REC_CTRL, rec_par, even)		\
		| IO_STATE (R_SERIAL2_REC_CTRL, rec_par_en, disable)	\
		| IO_STATE (R_SERIAL2_REC_CTRL, rec_bitnr, rec_8bit),$r0
	move.b	$r0,[R_SERIAL2_REC_CTRL]

	; Set up and enable the serial2 transmitter.
	move.b	  IO_FIELD (R_SERIAL2_TR_CTRL, txd, 0)			\
		| IO_STATE (R_SERIAL2_TR_CTRL, tr_enable, enable)	\
		| IO_STATE (R_SERIAL2_TR_CTRL, auto_cts, disabled)	\
		| IO_STATE (R_SERIAL2_TR_CTRL, stop_bits, one_bit)	\
		| IO_STATE (R_SERIAL2_TR_CTRL, tr_stick_par, normal)	\
		| IO_STATE (R_SERIAL2_TR_CTRL, tr_par, even)		\
		| IO_STATE (R_SERIAL2_TR_CTRL, tr_par_en, disable)	\
		| IO_STATE (R_SERIAL2_TR_CTRL, tr_bitnr, tr_8bit),$r0
	move.b	$r0,[R_SERIAL2_TR_CTRL]
#endif

#ifdef CONFIG_ETRAX_SERIAL_PORT3
	;; setup the serial port 3 at 115200 baud for debug purposes

	moveq	  IO_STATE (R_SERIAL3_XOFF, tx_stop, enable)		\
		| IO_STATE (R_SERIAL3_XOFF, auto_xoff, disable)		\
		| IO_FIELD (R_SERIAL3_XOFF, xoff_char, 0),$r0
	move.d	$r0,[R_SERIAL3_XOFF]

	; 115.2kbaud for both transmit and receive
	move.b	  IO_STATE (R_SERIAL3_BAUD, tr_baud, c115k2Hz)		\
		| IO_STATE (R_SERIAL3_BAUD, rec_baud, c115k2Hz),$r0
	move.b	$r0,[R_SERIAL3_BAUD]

	; Set up and enable the serial3 receiver.
	move.b	  IO_STATE (R_SERIAL3_REC_CTRL, dma_err, stop)		\
		| IO_STATE (R_SERIAL3_REC_CTRL, rec_enable, enable)	\
		| IO_STATE (R_SERIAL3_REC_CTRL, rts_, active)		\
		| IO_STATE (R_SERIAL3_REC_CTRL, sampling, middle)	\
		| IO_STATE (R_SERIAL3_REC_CTRL, rec_stick_par, normal)	\
		| IO_STATE (R_SERIAL3_REC_CTRL, rec_par, even)		\
		| IO_STATE (R_SERIAL3_REC_CTRL, rec_par_en, disable)	\
		| IO_STATE (R_SERIAL3_REC_CTRL, rec_bitnr, rec_8bit),$r0
	move.b	$r0,[R_SERIAL3_REC_CTRL]

	; Set up and enable the serial3 transmitter.
	move.b	  IO_FIELD (R_SERIAL3_TR_CTRL, txd, 0)			\
		| IO_STATE (R_SERIAL3_TR_CTRL, tr_enable, enable)	\
		| IO_STATE (R_SERIAL3_TR_CTRL, auto_cts, disabled)	\
		| IO_STATE (R_SERIAL3_TR_CTRL, stop_bits, one_bit)	\
		| IO_STATE (R_SERIAL3_TR_CTRL, tr_stick_par, normal)	\
		| IO_STATE (R_SERIAL3_TR_CTRL, tr_par, even)		\
		| IO_STATE (R_SERIAL3_TR_CTRL, tr_par_en, disable)	\
		| IO_STATE (R_SERIAL3_TR_CTRL, tr_bitnr, tr_8bit),$r0
	move.b	$r0,[R_SERIAL3_TR_CTRL]
#endif

	jump	start_kernel	; jump into the C-function start_kernel in init/main.c

	.data
etrax_irv:
	.dword	0
romfs_start:
	.dword	0
romfs_length:
	.dword	0
romfs_in_flash:
	.dword	0

	;; put some special pages at the beginning of the kernel aligned
	;; to page boundaries - the kernel cannot start until after this

#ifdef CONFIG_CRIS_LOW_MAP
swapper_pg_dir = 0x60002000
#else
swapper_pg_dir = 0xc0002000
#endif

	.section ".init.data", "aw"
#include "../lib/hw_settings.S"
href='#n2159'>2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262
/*
 * Copyright © 2012 Intel Corporation
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the "Software"),
 * to deal in the Software without restriction, including without limitation
 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
 * and/or sell copies of the Software, and to permit persons to whom the
 * Software is furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice (including the next
 * paragraph) shall be included in all copies or substantial portions of the
 * Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 *
 * Authors:
 *    Eugeni Dodonov <eugeni.dodonov@intel.com>
 *
 */

#include <linux/cpufreq.h>
#include <drm/drm_plane_helper.h>
#include "i915_drv.h"
#include "intel_drv.h"
#include "../../../platform/x86/intel_ips.h"
#include <linux/module.h>
#include <drm/drm_atomic_helper.h>

/**
 * DOC: RC6
 *
 * RC6 is a special power stage which allows the GPU to enter an very
 * low-voltage mode when idle, using down to 0V while at this stage.  This
 * stage is entered automatically when the GPU is idle when RC6 support is
 * enabled, and as soon as new workload arises GPU wakes up automatically as well.
 *
 * There are different RC6 modes available in Intel GPU, which differentiate
 * among each other with the latency required to enter and leave RC6 and
 * voltage consumed by the GPU in different states.
 *
 * The combination of the following flags define which states GPU is allowed
 * to enter, while RC6 is the normal RC6 state, RC6p is the deep RC6, and
 * RC6pp is deepest RC6. Their support by hardware varies according to the
 * GPU, BIOS, chipset and platform. RC6 is usually the safest one and the one
 * which brings the most power savings; deeper states save more power, but
 * require higher latency to switch to and wake up.
 */
#define INTEL_RC6_ENABLE			(1<<0)
#define INTEL_RC6p_ENABLE			(1<<1)
#define INTEL_RC6pp_ENABLE			(1<<2)

static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
{
	/* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl,cfl */
	I915_WRITE(CHICKEN_PAR1_1,
		   I915_READ(CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP);

	/*
	 * Display WA#0390: skl,bxt,kbl,glk
	 *
	 * Must match Sampler, Pixel Back End, and Media
	 * (0xE194 bit 8, 0x7014 bit 13, 0x4DDC bits 27 and 31).
	 *
	 * Including bits outside the page in the hash would
	 * require 2 (or 4?) MiB alignment of resources. Just
	 * assume the defaul hashing mode which only uses bits
	 * within the page.
	 */
	I915_WRITE(CHICKEN_PAR1_1,
		   I915_READ(CHICKEN_PAR1_1) & ~SKL_RC_HASH_OUTSIDE);

	I915_WRITE(GEN8_CONFIG0,
		   I915_READ(GEN8_CONFIG0) | GEN9_DEFAULT_FIXES);

	/* WaEnableChickenDCPR:skl,bxt,kbl,glk,cfl */
	I915_WRITE(GEN8_CHICKEN_DCPR_1,
		   I915_READ(GEN8_CHICKEN_DCPR_1) | MASK_WAKEMEM);

	/* WaFbcTurnOffFbcWatermark:skl,bxt,kbl,cfl */
	/* WaFbcWakeMemOn:skl,bxt,kbl,glk,cfl */
	I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) |
		   DISP_FBC_WM_DIS |
		   DISP_FBC_MEMORY_WAKE);

	/* WaFbcHighMemBwCorruptionAvoidance:skl,bxt,kbl,cfl */
	I915_WRITE(ILK_DPFC_CHICKEN, I915_READ(ILK_DPFC_CHICKEN) |
		   ILK_DPFC_DISABLE_DUMMY0);

	if (IS_SKYLAKE(dev_priv)) {
		/* WaDisableDopClockGating */
		I915_WRITE(GEN7_MISCCPCTL, I915_READ(GEN7_MISCCPCTL)
			   & ~GEN7_DOP_CLOCK_GATE_ENABLE);
	}
}

static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
{
	gen9_init_clock_gating(dev_priv);

	/* WaDisableSDEUnitClockGating:bxt */
	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);

	/*
	 * FIXME:
	 * GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ applies on 3x6 GT SKUs only.
	 */
	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
		   GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ);

	/*
	 * Wa: Backlight PWM may stop in the asserted state, causing backlight
	 * to stay fully on.
	 */
	I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) |
		   PWM1_GATING_DIS | PWM2_GATING_DIS);
}

static void glk_init_clock_gating(struct drm_i915_private *dev_priv)
{
	gen9_init_clock_gating(dev_priv);

	/*
	 * WaDisablePWMClockGating:glk
	 * Backlight PWM may stop in the asserted state, causing backlight
	 * to stay fully on.
	 */
	I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) |
		   PWM1_GATING_DIS | PWM2_GATING_DIS);

	/* WaDDIIOTimeout:glk */
	if (IS_GLK_REVID(dev_priv, 0, GLK_REVID_A1)) {
		u32 val = I915_READ(CHICKEN_MISC_2);
		val &= ~(GLK_CL0_PWR_DOWN |
			 GLK_CL1_PWR_DOWN |
			 GLK_CL2_PWR_DOWN);
		I915_WRITE(CHICKEN_MISC_2, val);
	}

}

static void i915_pineview_get_mem_freq(struct drm_i915_private *dev_priv)
{
	u32 tmp;

	tmp = I915_READ(CLKCFG);

	switch (tmp & CLKCFG_FSB_MASK) {
	case CLKCFG_FSB_533:
		dev_priv->fsb_freq = 533; /* 133*4 */
		break;
	case CLKCFG_FSB_800:
		dev_priv->fsb_freq = 800; /* 200*4 */
		break;
	case CLKCFG_FSB_667:
		dev_priv->fsb_freq =  667; /* 167*4 */
		break;
	case CLKCFG_FSB_400:
		dev_priv->fsb_freq = 400; /* 100*4 */
		break;
	}

	switch (tmp & CLKCFG_MEM_MASK) {
	case CLKCFG_MEM_533:
		dev_priv->mem_freq = 533;
		break;
	case CLKCFG_MEM_667:
		dev_priv->mem_freq = 667;
		break;
	case CLKCFG_MEM_800:
		dev_priv->mem_freq = 800;
		break;
	}

	/* detect pineview DDR3 setting */
	tmp = I915_READ(CSHRDDR3CTL);
	dev_priv->is_ddr3 = (tmp & CSHRDDR3CTL_DDR3) ? 1 : 0;
}

static void i915_ironlake_get_mem_freq(struct drm_i915_private *dev_priv)
{
	u16 ddrpll, csipll;

	ddrpll = I915_READ16(DDRMPLL1);
	csipll = I915_READ16(CSIPLL0);

	switch (ddrpll & 0xff) {
	case 0xc:
		dev_priv->mem_freq = 800;
		break;
	case 0x10:
		dev_priv->mem_freq = 1066;
		break;
	case 0x14:
		dev_priv->mem_freq = 1333;
		break;
	case 0x18:
		dev_priv->mem_freq = 1600;
		break;
	default:
		DRM_DEBUG_DRIVER("unknown memory frequency 0x%02x\n",
				 ddrpll & 0xff);
		dev_priv->mem_freq = 0;
		break;
	}

	dev_priv->ips.r_t = dev_priv->mem_freq;

	switch (csipll & 0x3ff) {
	case 0x00c:
		dev_priv->fsb_freq = 3200;
		break;
	case 0x00e:
		dev_priv->fsb_freq = 3733;
		break;
	case 0x010:
		dev_priv->fsb_freq = 4266;
		break;
	case 0x012:
		dev_priv->fsb_freq = 4800;
		break;
	case 0x014:
		dev_priv->fsb_freq = 5333;
		break;
	case 0x016:
		dev_priv->fsb_freq = 5866;
		break;
	case 0x018:
		dev_priv->fsb_freq = 6400;
		break;
	default:
		DRM_DEBUG_DRIVER("unknown fsb frequency 0x%04x\n",
				 csipll & 0x3ff);
		dev_priv->fsb_freq = 0;
		break;
	}

	if (dev_priv->fsb_freq == 3200) {
		dev_priv->ips.c_m = 0;
	} else if (dev_priv->fsb_freq > 3200 && dev_priv->fsb_freq <= 4800) {
		dev_priv->ips.c_m = 1;
	} else {
		dev_priv->ips.c_m = 2;
	}
}

static const struct cxsr_latency cxsr_latency_table[] = {
	{1, 0, 800, 400, 3382, 33382, 3983, 33983},    /* DDR2-400 SC */
	{1, 0, 800, 667, 3354, 33354, 3807, 33807},    /* DDR2-667 SC */
	{1, 0, 800, 800, 3347, 33347, 3763, 33763},    /* DDR2-800 SC */
	{1, 1, 800, 667, 6420, 36420, 6873, 36873},    /* DDR3-667 SC */
	{1, 1, 800, 800, 5902, 35902, 6318, 36318},    /* DDR3-800 SC */

	{1, 0, 667, 400, 3400, 33400, 4021, 34021},    /* DDR2-400 SC */
	{1, 0, 667, 667, 3372, 33372, 3845, 33845},    /* DDR2-667 SC */
	{1, 0, 667, 800, 3386, 33386, 3822, 33822},    /* DDR2-800 SC */
	{1, 1, 667, 667, 6438, 36438, 6911, 36911},    /* DDR3-667 SC */
	{1, 1, 667, 800, 5941, 35941, 6377, 36377},    /* DDR3-800 SC */

	{1, 0, 400, 400, 3472, 33472, 4173, 34173},    /* DDR2-400 SC */
	{1, 0, 400, 667, 3443, 33443, 3996, 33996},    /* DDR2-667 SC */
	{1, 0, 400, 800, 3430, 33430, 3946, 33946},    /* DDR2-800 SC */
	{1, 1, 400, 667, 6509, 36509, 7062, 37062},    /* DDR3-667 SC */
	{1, 1, 400, 800, 5985, 35985, 6501, 36501},    /* DDR3-800 SC */

	{0, 0, 800, 400, 3438, 33438, 4065, 34065},    /* DDR2-400 SC */
	{0, 0, 800, 667, 3410, 33410, 3889, 33889},    /* DDR2-667 SC */
	{0, 0, 800, 800, 3403, 33403, 3845, 33845},    /* DDR2-800 SC */
	{0, 1, 800, 667, 6476, 36476, 6955, 36955},    /* DDR3-667 SC */
	{0, 1, 800, 800, 5958, 35958, 6400, 36400},    /* DDR3-800 SC */

	{0, 0, 667, 400, 3456, 33456, 4103, 34106},    /* DDR2-400 SC */
	{0, 0, 667, 667, 3428, 33428, 3927, 33927},    /* DDR2-667 SC */
	{0, 0, 667, 800, 3443, 33443, 3905, 33905},    /* DDR2-800 SC */
	{0, 1, 667, 667, 6494, 36494, 6993, 36993},    /* DDR3-667 SC */
	{0, 1, 667, 800, 5998, 35998, 6460, 36460},    /* DDR3-800 SC */

	{0, 0, 400, 400, 3528, 33528, 4255, 34255},    /* DDR2-400 SC */
	{0, 0, 400, 667, 3500, 33500, 4079, 34079},    /* DDR2-667 SC */
	{0, 0, 400, 800, 3487, 33487, 4029, 34029},    /* DDR2-800 SC */
	{0, 1, 400, 667, 6566, 36566, 7145, 37145},    /* DDR3-667 SC */
	{0, 1, 400, 800, 6042, 36042, 6584, 36584},    /* DDR3-800 SC */
};

static const struct cxsr_latency *intel_get_cxsr_latency(bool is_desktop,
							 bool is_ddr3,
							 int fsb,
							 int mem)
{
	const struct cxsr_latency *latency;
	int i;

	if (fsb == 0 || mem == 0)
		return NULL;

	for (i = 0; i < ARRAY_SIZE(cxsr_latency_table); i++) {
		latency = &cxsr_latency_table[i];
		if (is_desktop == latency->is_desktop &&
		    is_ddr3 == latency->is_ddr3 &&
		    fsb == latency->fsb_freq && mem == latency->mem_freq)
			return latency;
	}

	DRM_DEBUG_KMS("Unknown FSB/MEM found, disable CxSR\n");

	return NULL;
}

static void chv_set_memory_dvfs(struct drm_i915_private *dev_priv, bool enable)
{
	u32 val;

	mutex_lock(&dev_priv->rps.hw_lock);

	val = vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2);
	if (enable)
		val &= ~FORCE_DDR_HIGH_FREQ;
	else
		val |= FORCE_DDR_HIGH_FREQ;
	val &= ~FORCE_DDR_LOW_FREQ;
	val |= FORCE_DDR_FREQ_REQ_ACK;
	vlv_punit_write(dev_priv, PUNIT_REG_DDR_SETUP2, val);

	if (wait_for((vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2) &
		      FORCE_DDR_FREQ_REQ_ACK) == 0, 3))
		DRM_ERROR("timed out waiting for Punit DDR DVFS request\n");

	mutex_unlock(&dev_priv->rps.hw_lock);
}

static void chv_set_memory_pm5(struct drm_i915_private *dev_priv, bool enable)
{
	u32 val;

	mutex_lock(&dev_priv->rps.hw_lock);

	val = vlv_punit_read(dev_priv, PUNIT_REG_DSPFREQ);
	if (enable)
		val |= DSP_MAXFIFO_PM5_ENABLE;
	else
		val &= ~DSP_MAXFIFO_PM5_ENABLE;
	vlv_punit_write(dev_priv, PUNIT_REG_DSPFREQ, val);

	mutex_unlock(&dev_priv->rps.hw_lock);
}

#define FW_WM(value, plane) \
	(((value) << DSPFW_ ## plane ## _SHIFT) & DSPFW_ ## plane ## _MASK)

static bool _intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable)
{
	bool was_enabled;
	u32 val;

	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
		was_enabled = I915_READ(FW_BLC_SELF_VLV) & FW_CSPWRDWNEN;
		I915_WRITE(FW_BLC_SELF_VLV, enable ? FW_CSPWRDWNEN : 0);
		POSTING_READ(FW_BLC_SELF_VLV);
	} else if (IS_G4X(dev_priv) || IS_I965GM(dev_priv)) {
		was_enabled = I915_READ(FW_BLC_SELF) & FW_BLC_SELF_EN;
		I915_WRITE(FW_BLC_SELF, enable ? FW_BLC_SELF_EN : 0);
		POSTING_READ(FW_BLC_SELF);
	} else if (IS_PINEVIEW(dev_priv)) {
		val = I915_READ(DSPFW3);
		was_enabled = val & PINEVIEW_SELF_REFRESH_EN;
		if (enable)
			val |= PINEVIEW_SELF_REFRESH_EN;
		else
			val &= ~PINEVIEW_SELF_REFRESH_EN;
		I915_WRITE(DSPFW3, val);
		POSTING_READ(DSPFW3);
	} else if (IS_I945G(dev_priv) || IS_I945GM(dev_priv)) {
		was_enabled = I915_READ(FW_BLC_SELF) & FW_BLC_SELF_EN;
		val = enable ? _MASKED_BIT_ENABLE(FW_BLC_SELF_EN) :
			       _MASKED_BIT_DISABLE(FW_BLC_SELF_EN);
		I915_WRITE(FW_BLC_SELF, val);
		POSTING_READ(FW_BLC_SELF);
	} else if (IS_I915GM(dev_priv)) {
		/*
		 * FIXME can't find a bit like this for 915G, and
		 * and yet it does have the related watermark in
		 * FW_BLC_SELF. What's going on?
		 */
		was_enabled = I915_READ(INSTPM) & INSTPM_SELF_EN;
		val = enable ? _MASKED_BIT_ENABLE(INSTPM_SELF_EN) :
			       _MASKED_BIT_DISABLE(INSTPM_SELF_EN);
		I915_WRITE(INSTPM, val);
		POSTING_READ(INSTPM);
	} else {
		return false;
	}

	trace_intel_memory_cxsr(dev_priv, was_enabled, enable);

	DRM_DEBUG_KMS("memory self-refresh is %s (was %s)\n",
		      enableddisabled(enable),
		      enableddisabled(was_enabled));

	return was_enabled;
}

/**
 * intel_set_memory_cxsr - Configure CxSR state
 * @dev_priv: i915 device
 * @enable: Allow vs. disallow CxSR
 *
 * Allow or disallow the system to enter a special CxSR
 * (C-state self refresh) state. What typically happens in CxSR mode
 * is that several display FIFOs may get combined into a single larger
 * FIFO for a particular plane (so called max FIFO mode) to allow the
 * system to defer memory fetches longer, and the memory will enter
 * self refresh.
 *
 * Note that enabling CxSR does not guarantee that the system enter
 * this special mode, nor does it guarantee that the system stays
 * in that mode once entered. So this just allows/disallows the system
 * to autonomously utilize the CxSR mode. Other factors such as core
 * C-states will affect when/if the system actually enters/exits the
 * CxSR mode.
 *
 * Note that on VLV/CHV this actually only controls the max FIFO mode,
 * and the system is free to enter/exit memory self refresh at any time
 * even when the use of CxSR has been disallowed.
 *
 * While the system is actually in the CxSR/max FIFO mode, some plane
 * control registers will not get latched on vblank. Thus in order to
 * guarantee the system will respond to changes in the plane registers
 * we must always disallow CxSR prior to making changes to those registers.
 * Unfortunately the system will re-evaluate the CxSR conditions at
 * frame start which happens after vblank start (which is when the plane
 * registers would get latched), so we can't proceed with the plane update
 * during the same frame where we disallowed CxSR.
 *
 * Certain platforms also have a deeper HPLL SR mode. Fortunately the
 * HPLL SR mode depends on CxSR itself, so we don't have to hand hold
 * the hardware w.r.t. HPLL SR when writing to plane registers.
 * Disallowing just CxSR is sufficient.
 */
bool intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable)
{
	bool ret;

	mutex_lock(&dev_priv->wm.wm_mutex);
	ret = _intel_set_memory_cxsr(dev_priv, enable);
	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
		dev_priv->wm.vlv.cxsr = enable;
	else if (IS_G4X(dev_priv))
		dev_priv->wm.g4x.cxsr = enable;
	mutex_unlock(&dev_priv->wm.wm_mutex);

	return ret;
}

/*
 * Latency for FIFO fetches is dependent on several factors:
 *   - memory configuration (speed, channels)
 *   - chipset
 *   - current MCH state
 * It can be fairly high in some situations, so here we assume a fairly
 * pessimal value.  It's a tradeoff between extra memory fetches (if we
 * set this value too high, the FIFO will fetch frequently to stay full)
 * and power consumption (set it too low to save power and we might see
 * FIFO underruns and display "flicker").
 *
 * A value of 5us seems to be a good balance; safe for very low end
 * platforms but not overly aggressive on lower latency configs.
 */
static const int pessimal_latency_ns = 5000;

#define VLV_FIFO_START(dsparb, dsparb2, lo_shift, hi_shift) \
	((((dsparb) >> (lo_shift)) & 0xff) | ((((dsparb2) >> (hi_shift)) & 0x1) << 8))

static void vlv_get_fifo_size(struct intel_crtc_state *crtc_state)
{
	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
	struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state;
	enum pipe pipe = crtc->pipe;
	int sprite0_start, sprite1_start;

	switch (pipe) {
		uint32_t dsparb, dsparb2, dsparb3;
	case PIPE_A:
		dsparb = I915_READ(DSPARB);
		dsparb2 = I915_READ(DSPARB2);
		sprite0_start = VLV_FIFO_START(dsparb, dsparb2, 0, 0);
		sprite1_start = VLV_FIFO_START(dsparb, dsparb2, 8, 4);
		break;
	case PIPE_B:
		dsparb = I915_READ(DSPARB);
		dsparb2 = I915_READ(DSPARB2);
		sprite0_start = VLV_FIFO_START(dsparb, dsparb2, 16, 8);
		sprite1_start = VLV_FIFO_START(dsparb, dsparb2, 24, 12);
		break;
	case PIPE_C:
		dsparb2 = I915_READ(DSPARB2);
		dsparb3 = I915_READ(DSPARB3);
		sprite0_start = VLV_FIFO_START(dsparb3, dsparb2, 0, 16);
		sprite1_start = VLV_FIFO_START(dsparb3, dsparb2, 8, 20);
		break;
	default:
		MISSING_CASE(pipe);
		return;
	}

	fifo_state->plane[PLANE_PRIMARY] = sprite0_start;
	fifo_state->plane[PLANE_SPRITE0] = sprite1_start - sprite0_start;
	fifo_state->plane[PLANE_SPRITE1] = 511 - sprite1_start;
	fifo_state->plane[PLANE_CURSOR] = 63;
}

static int i9xx_get_fifo_size(struct drm_i915_private *dev_priv, int plane)
{
	uint32_t dsparb = I915_READ(DSPARB);
	int size;

	size = dsparb & 0x7f;
	if (plane)
		size = ((dsparb >> DSPARB_CSTART_SHIFT) & 0x7f) - size;

	DRM_DEBUG_KMS("FIFO size - (0x%08x) %s: %d\n", dsparb,
		      plane ? "B" : "A", size);

	return size;
}

static int i830_get_fifo_size(struct drm_i915_private *dev_priv, int plane)
{
	uint32_t dsparb = I915_READ(DSPARB);
	int size;

	size = dsparb & 0x1ff;
	if (plane)
		size = ((dsparb >> DSPARB_BEND_SHIFT) & 0x1ff) - size;
	size >>= 1; /* Convert to cachelines */

	DRM_DEBUG_KMS("FIFO size - (0x%08x) %s: %d\n", dsparb,
		      plane ? "B" : "A", size);

	return size;
}

static int i845_get_fifo_size(struct drm_i915_private *dev_priv, int plane)
{
	uint32_t dsparb = I915_READ(DSPARB);
	int size;

	size = dsparb & 0x7f;
	size >>= 2; /* Convert to cachelines */

	DRM_DEBUG_KMS("FIFO size - (0x%08x) %s: %d\n", dsparb,
		      plane ? "B" : "A",
		      size);

	return size;
}

/* Pineview has different values for various configs */
static const struct intel_watermark_params pineview_display_wm = {
	.fifo_size = PINEVIEW_DISPLAY_FIFO,
	.max_wm = PINEVIEW_MAX_WM,
	.default_wm = PINEVIEW_DFT_WM,
	.guard_size = PINEVIEW_GUARD_WM,
	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
};
static const struct intel_watermark_params pineview_display_hplloff_wm = {
	.fifo_size = PINEVIEW_DISPLAY_FIFO,
	.max_wm = PINEVIEW_MAX_WM,
	.default_wm = PINEVIEW_DFT_HPLLOFF_WM,
	.guard_size = PINEVIEW_GUARD_WM,
	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
};
static const struct intel_watermark_params pineview_cursor_wm = {
	.fifo_size = PINEVIEW_CURSOR_FIFO,
	.max_wm = PINEVIEW_CURSOR_MAX_WM,
	.default_wm = PINEVIEW_CURSOR_DFT_WM,
	.guard_size = PINEVIEW_CURSOR_GUARD_WM,
	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
};
static const struct intel_watermark_params pineview_cursor_hplloff_wm = {
	.fifo_size = PINEVIEW_CURSOR_FIFO,
	.max_wm = PINEVIEW_CURSOR_MAX_WM,
	.default_wm = PINEVIEW_CURSOR_DFT_WM,
	.guard_size = PINEVIEW_CURSOR_GUARD_WM,
	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
};
static const struct intel_watermark_params i965_cursor_wm_info = {
	.fifo_size = I965_CURSOR_FIFO,
	.max_wm = I965_CURSOR_MAX_WM,
	.default_wm = I965_CURSOR_DFT_WM,
	.guard_size = 2,
	.cacheline_size = I915_FIFO_LINE_SIZE,
};
static const struct intel_watermark_params i945_wm_info = {
	.fifo_size = I945_FIFO_SIZE,
	.max_wm = I915_MAX_WM,
	.default_wm = 1,
	.guard_size = 2,
	.cacheline_size = I915_FIFO_LINE_SIZE,
};
static const struct intel_watermark_params i915_wm_info = {
	.fifo_size = I915_FIFO_SIZE,
	.max_wm = I915_MAX_WM,
	.default_wm = 1,
	.guard_size = 2,
	.cacheline_size = I915_FIFO_LINE_SIZE,
};
static const struct intel_watermark_params i830_a_wm_info = {
	.fifo_size = I855GM_FIFO_SIZE,
	.max_wm = I915_MAX_WM,
	.default_wm = 1,
	.guard_size = 2,
	.cacheline_size = I830_FIFO_LINE_SIZE,
};
static const struct intel_watermark_params i830_bc_wm_info = {
	.fifo_size = I855GM_FIFO_SIZE,
	.max_wm = I915_MAX_WM/2,
	.default_wm = 1,
	.guard_size = 2,
	.cacheline_size = I830_FIFO_LINE_SIZE,
};
static const struct intel_watermark_params i845_wm_info = {
	.fifo_size = I830_FIFO_SIZE,
	.max_wm = I915_MAX_WM,
	.default_wm = 1,
	.guard_size = 2,
	.cacheline_size = I830_FIFO_LINE_SIZE,
};

/**
 * intel_wm_method1 - Method 1 / "small buffer" watermark formula
 * @pixel_rate: Pipe pixel rate in kHz
 * @cpp: Plane bytes per pixel
 * @latency: Memory wakeup latency in 0.1us units
 *
 * Compute the watermark using the method 1 or "small buffer"
 * formula. The caller may additonally add extra cachelines
 * to account for TLB misses and clock crossings.
 *
 * This method is concerned with the short term drain rate
 * of the FIFO, ie. it does not account for blanking periods
 * which would effectively reduce the average drain rate across
 * a longer period. The name "small" refers to the fact the
 * FIFO is relatively small compared to the amount of data
 * fetched.
 *
 * The FIFO level vs. time graph might look something like:
 *
 *   |\   |\
 *   | \  | \
 * __---__---__ (- plane active, _ blanking)
 * -> time
 *
 * or perhaps like this:
 *
 *   |\|\  |\|\
 * __----__----__ (- plane active, _ blanking)
 * -> time
 *
 * Returns:
 * The watermark in bytes
 */
static unsigned int intel_wm_method1(unsigned int pixel_rate,
				     unsigned int cpp,
				     unsigned int latency)
{
	uint64_t ret;

	ret = (uint64_t) pixel_rate * cpp * latency;
	ret = DIV_ROUND_UP_ULL(ret, 10000);

	return ret;
}

/**
 * intel_wm_method2 - Method 2 / "large buffer" watermark formula
 * @pixel_rate: Pipe pixel rate in kHz
 * @htotal: Pipe horizontal total
 * @width: Plane width in pixels
 * @cpp: Plane bytes per pixel
 * @latency: Memory wakeup latency in 0.1us units
 *
 * Compute the watermark using the method 2 or "large buffer"
 * formula. The caller may additonally add extra cachelines
 * to account for TLB misses and clock crossings.
 *
 * This method is concerned with the long term drain rate
 * of the FIFO, ie. it does account for blanking periods
 * which effectively reduce the average drain rate across
 * a longer period. The name "large" refers to the fact the
 * FIFO is relatively large compared to the amount of data
 * fetched.
 *
 * The FIFO level vs. time graph might look something like:
 *
 *    |\___       |\___
 *    |    \___   |    \___
 *    |        \  |        \
 * __ --__--__--__--__--__--__ (- plane active, _ blanking)
 * -> time
 *
 * Returns:
 * The watermark in bytes
 */
static unsigned int intel_wm_method2(unsigned int pixel_rate,
				     unsigned int htotal,
				     unsigned int width,
				     unsigned int cpp,
				     unsigned int latency)
{
	unsigned int ret;

	/*
	 * FIXME remove once all users are computing
	 * watermarks in the correct place.
	 */
	if (WARN_ON_ONCE(htotal == 0))
		htotal = 1;

	ret = (latency * pixel_rate) / (htotal * 10000);
	ret = (ret + 1) * width * cpp;

	return ret;
}

/**
 * intel_calculate_wm - calculate watermark level
 * @pixel_rate: pixel clock
 * @wm: chip FIFO params
 * @cpp: bytes per pixel
 * @latency_ns: memory latency for the platform
 *
 * Calculate the watermark level (the level at which the display plane will
 * start fetching from memory again).  Each chip has a different display
 * FIFO size and allocation, so the caller needs to figure that out and pass
 * in the correct intel_watermark_params structure.
 *
 * As the pixel clock runs, the FIFO will be drained at a rate that depends
 * on the pixel size.  When it reaches the watermark level, it'll start
 * fetching FIFO line sized based chunks from memory until the FIFO fills
 * past the watermark point.  If the FIFO drains completely, a FIFO underrun
 * will occur, and a display engine hang could result.
 */
static unsigned int intel_calculate_wm(int pixel_rate,
				       const struct intel_watermark_params *wm,
				       int fifo_size, int cpp,
				       unsigned int latency_ns)
{
	int entries, wm_size;

	/*
	 * Note: we need to make sure we don't overflow for various clock &
	 * latency values.
	 * clocks go from a few thousand to several hundred thousand.
	 * latency is usually a few thousand
	 */
	entries = intel_wm_method1(pixel_rate, cpp,
				   latency_ns / 100);
	entries = DIV_ROUND_UP(entries, wm->cacheline_size) +
		wm->guard_size;
	DRM_DEBUG_KMS("FIFO entries required for mode: %d\n", entries);

	wm_size = fifo_size - entries;
	DRM_DEBUG_KMS("FIFO watermark level: %d\n", wm_size);

	/* Don't promote wm_size to unsigned... */
	if (wm_size > wm->max_wm)
		wm_size = wm->max_wm;
	if (wm_size <= 0)
		wm_size = wm->default_wm;

	/*
	 * Bspec seems to indicate that the value shouldn't be lower than
	 * 'burst size + 1'. Certainly 830 is quite unhappy with low values.
	 * Lets go for 8 which is the burst size since certain platforms
	 * already use a hardcoded 8 (which is what the spec says should be
	 * done).
	 */
	if (wm_size <= 8)
		wm_size = 8;

	return wm_size;
}

static bool is_disabling(int old, int new, int threshold)
{
	return old >= threshold && new < threshold;
}

static bool is_enabling(int old, int new, int threshold)
{
	return old < threshold && new >= threshold;
}

static int intel_wm_num_levels(struct drm_i915_private *dev_priv)
{
	return dev_priv->wm.max_level + 1;
}

static bool intel_wm_plane_visible(const struct intel_crtc_state *crtc_state,
				   const struct intel_plane_state *plane_state)
{
	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);

	/* FIXME check the 'enable' instead */
	if (!crtc_state->base.active)
		return false;

	/*
	 * Treat cursor with fb as always visible since cursor updates
	 * can happen faster than the vrefresh rate, and the current
	 * watermark code doesn't handle that correctly. Cursor updates
	 * which set/clear the fb or change the cursor size are going
	 * to get throttled by intel_legacy_cursor_update() to work
	 * around this problem with the watermark code.
	 */
	if (plane->id == PLANE_CURSOR)
		return plane_state->base.fb != NULL;
	else
		return plane_state->base.visible;
}

static struct intel_crtc *single_enabled_crtc(struct drm_i915_private *dev_priv)
{
	struct intel_crtc *crtc, *enabled = NULL;

	for_each_intel_crtc(&dev_priv->drm, crtc) {
		if (intel_crtc_active(crtc)) {
			if (enabled)
				return NULL;
			enabled = crtc;
		}
	}

	return enabled;
}

static void pineview_update_wm(struct intel_crtc *unused_crtc)
{
	struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev);
	struct intel_crtc *crtc;
	const struct cxsr_latency *latency;
	u32 reg;
	unsigned int wm;

	latency = intel_get_cxsr_latency(IS_PINEVIEW_G(dev_priv),
					 dev_priv->is_ddr3,
					 dev_priv->fsb_freq,
					 dev_priv->mem_freq);
	if (!latency) {
		DRM_DEBUG_KMS("Unknown FSB/MEM found, disable CxSR\n");
		intel_set_memory_cxsr(dev_priv, false);
		return;
	}

	crtc = single_enabled_crtc(dev_priv);
	if (crtc) {
		const struct drm_display_mode *adjusted_mode =
			&crtc->config->base.adjusted_mode;
		const struct drm_framebuffer *fb =
			crtc->base.primary->state->fb;
		int cpp = fb->format->cpp[0];
		int clock = adjusted_mode->crtc_clock;

		/* Display SR */
		wm = intel_calculate_wm(clock, &pineview_display_wm,
					pineview_display_wm.fifo_size,
					cpp, latency->display_sr);
		reg = I915_READ(DSPFW1);
		reg &= ~DSPFW_SR_MASK;
		reg |= FW_WM(wm, SR);
		I915_WRITE(DSPFW1, reg);
		DRM_DEBUG_KMS("DSPFW1 register is %x\n", reg);

		/* cursor SR */
		wm = intel_calculate_wm(clock, &pineview_cursor_wm,
					pineview_display_wm.fifo_size,
					4, latency->cursor_sr);
		reg = I915_READ(DSPFW3);
		reg &= ~DSPFW_CURSOR_SR_MASK;
		reg |= FW_WM(wm, CURSOR_SR);
		I915_WRITE(DSPFW3, reg);

		/* Display HPLL off SR */
		wm = intel_calculate_wm(clock, &pineview_display_hplloff_wm,
					pineview_display_hplloff_wm.fifo_size,
					cpp, latency->display_hpll_disable);
		reg = I915_READ(DSPFW3);
		reg &= ~DSPFW_HPLL_SR_MASK;
		reg |= FW_WM(wm, HPLL_SR);
		I915_WRITE(DSPFW3, reg);

		/* cursor HPLL off SR */
		wm = intel_calculate_wm(clock, &pineview_cursor_hplloff_wm,
					pineview_display_hplloff_wm.fifo_size,
					4, latency->cursor_hpll_disable);
		reg = I915_READ(DSPFW3);
		reg &= ~DSPFW_HPLL_CURSOR_MASK;
		reg |= FW_WM(wm, HPLL_CURSOR);
		I915_WRITE(DSPFW3, reg);
		DRM_DEBUG_KMS("DSPFW3 register is %x\n", reg);

		intel_set_memory_cxsr(dev_priv, true);
	} else {
		intel_set_memory_cxsr(dev_priv, false);
	}
}

/*
 * Documentation says:
 * "If the line size is small, the TLB fetches can get in the way of the
 *  data fetches, causing some lag in the pixel data return which is not
 *  accounted for in the above formulas. The following adjustment only
 *  needs to be applied if eight whole lines fit in the buffer at once.
 *  The WM is adjusted upwards by the difference between the FIFO size
 *  and the size of 8 whole lines. This adjustment is always performed
 *  in the actual pixel depth regardless of whether FBC is enabled or not."
 */
static int g4x_tlb_miss_wa(int fifo_size, int width, int cpp)
{
	int tlb_miss = fifo_size * 64 - width * cpp * 8;

	return max(0, tlb_miss);
}

static void g4x_write_wm_values(struct drm_i915_private *dev_priv,
				const struct g4x_wm_values *wm)
{
	enum pipe pipe;

	for_each_pipe(dev_priv, pipe)
		trace_g4x_wm(intel_get_crtc_for_pipe(dev_priv, pipe), wm);

	I915_WRITE(DSPFW1,
		   FW_WM(wm->sr.plane, SR) |
		   FW_WM(wm->pipe[PIPE_B].plane[PLANE_CURSOR], CURSORB) |
		   FW_WM(wm->pipe[PIPE_B].plane[PLANE_PRIMARY], PLANEB) |
		   FW_WM(wm->pipe[PIPE_A].plane[PLANE_PRIMARY], PLANEA));
	I915_WRITE(DSPFW2,
		   (wm->fbc_en ? DSPFW_FBC_SR_EN : 0) |
		   FW_WM(wm->sr.fbc, FBC_SR) |
		   FW_WM(wm->hpll.fbc, FBC_HPLL_SR) |
		   FW_WM(wm->pipe[PIPE_B].plane[PLANE_SPRITE0], SPRITEB) |
		   FW_WM(wm->pipe[PIPE_A].plane[PLANE_CURSOR], CURSORA) |
		   FW_WM(wm->pipe[PIPE_A].plane[PLANE_SPRITE0], SPRITEA));
	I915_WRITE(DSPFW3,
		   (wm->hpll_en ? DSPFW_HPLL_SR_EN : 0) |
		   FW_WM(wm->sr.cursor, CURSOR_SR) |
		   FW_WM(wm->hpll.cursor, HPLL_CURSOR) |
		   FW_WM(wm->hpll.plane, HPLL_SR));

	POSTING_READ(DSPFW1);
}

#define FW_WM_VLV(value, plane) \
	(((value) << DSPFW_ ## plane ## _SHIFT) & DSPFW_ ## plane ## _MASK_VLV)

static void vlv_write_wm_values(struct drm_i915_private *dev_priv,
				const struct vlv_wm_values *wm)
{
	enum pipe pipe;

	for_each_pipe(dev_priv, pipe) {
		trace_vlv_wm(intel_get_crtc_for_pipe(dev_priv, pipe), wm);

		I915_WRITE(VLV_DDL(pipe),
			   (wm->ddl[pipe].plane[PLANE_CURSOR] << DDL_CURSOR_SHIFT) |
			   (wm->ddl[pipe].plane[PLANE_SPRITE1] << DDL_SPRITE_SHIFT(1)) |
			   (wm->ddl[pipe].plane[PLANE_SPRITE0] << DDL_SPRITE_SHIFT(0)) |
			   (wm->ddl[pipe].plane[PLANE_PRIMARY] << DDL_PLANE_SHIFT));
	}

	/*
	 * Zero the (unused) WM1 watermarks, and also clear all the
	 * high order bits so that there are no out of bounds values
	 * present in the registers during the reprogramming.
	 */
	I915_WRITE(DSPHOWM, 0);
	I915_WRITE(DSPHOWM1, 0);
	I915_WRITE(DSPFW4, 0);
	I915_WRITE(DSPFW5, 0);
	I915_WRITE(DSPFW6, 0);

	I915_WRITE(DSPFW1,
		   FW_WM(wm->sr.plane, SR) |
		   FW_WM(wm->pipe[PIPE_B].plane[PLANE_CURSOR], CURSORB) |
		   FW_WM_VLV(wm->pipe[PIPE_B].plane[PLANE_PRIMARY], PLANEB) |
		   FW_WM_VLV(wm->pipe[PIPE_A].plane[PLANE_PRIMARY], PLANEA));
	I915_WRITE(DSPFW2,
		   FW_WM_VLV(wm->pipe[PIPE_A].plane[PLANE_SPRITE1], SPRITEB) |
		   FW_WM(wm->pipe[PIPE_A].plane[PLANE_CURSOR], CURSORA) |
		   FW_WM_VLV(wm->pipe[PIPE_A].plane[PLANE_SPRITE0], SPRITEA));
	I915_WRITE(DSPFW3,
		   FW_WM(wm->sr.cursor, CURSOR_SR));

	if (IS_CHERRYVIEW(dev_priv)) {
		I915_WRITE(DSPFW7_CHV,
			   FW_WM_VLV(wm->pipe[PIPE_B].plane[PLANE_SPRITE1], SPRITED) |
			   FW_WM_VLV(wm->pipe[PIPE_B].plane[PLANE_SPRITE0], SPRITEC));
		I915_WRITE(DSPFW8_CHV,
			   FW_WM_VLV(wm->pipe[PIPE_C].plane[PLANE_SPRITE1], SPRITEF) |
			   FW_WM_VLV(wm->pipe[PIPE_C].plane[PLANE_SPRITE0], SPRITEE));
		I915_WRITE(DSPFW9_CHV,
			   FW_WM_VLV(wm->pipe[PIPE_C].plane[PLANE_PRIMARY], PLANEC) |
			   FW_WM(wm->pipe[PIPE_C].plane[PLANE_CURSOR], CURSORC));
		I915_WRITE(DSPHOWM,
			   FW_WM(wm->sr.plane >> 9, SR_HI) |
			   FW_WM(wm->pipe[PIPE_C].plane[PLANE_SPRITE1] >> 8, SPRITEF_HI) |
			   FW_WM(wm->pipe[PIPE_C].plane[PLANE_SPRITE0] >> 8, SPRITEE_HI) |
			   FW_WM(wm->pipe[PIPE_C].plane[PLANE_PRIMARY] >> 8, PLANEC_HI) |
			   FW_WM(wm->pipe[PIPE_B].plane[PLANE_SPRITE1] >> 8, SPRITED_HI) |
			   FW_WM(wm->pipe[PIPE_B].plane[PLANE_SPRITE0] >> 8, SPRITEC_HI) |
			   FW_WM(wm->pipe[PIPE_B].plane[PLANE_PRIMARY] >> 8, PLANEB_HI) |
			   FW_WM(wm->pipe[PIPE_A].plane[PLANE_SPRITE1] >> 8, SPRITEB_HI) |
			   FW_WM(wm->pipe[PIPE_A].plane[PLANE_SPRITE0] >> 8, SPRITEA_HI) |
			   FW_WM(wm->pipe[PIPE_A].plane[PLANE_PRIMARY] >> 8, PLANEA_HI));
	} else {
		I915_WRITE(DSPFW7,
			   FW_WM_VLV(wm->pipe[PIPE_B].plane[PLANE_SPRITE1], SPRITED) |
			   FW_WM_VLV(wm->pipe[PIPE_B].plane[PLANE_SPRITE0], SPRITEC));
		I915_WRITE(DSPHOWM,
			   FW_WM(wm->sr.plane >> 9, SR_HI) |
			   FW_WM(wm->pipe[PIPE_B].plane[PLANE_SPRITE1] >> 8, SPRITED_HI) |
			   FW_WM(wm->pipe[PIPE_B].plane[PLANE_SPRITE0] >> 8, SPRITEC_HI) |
			   FW_WM(wm->pipe[PIPE_B].plane[PLANE_PRIMARY] >> 8, PLANEB_HI) |
			   FW_WM(wm->pipe[PIPE_A].plane[PLANE_SPRITE1] >> 8, SPRITEB_HI) |
			   FW_WM(wm->pipe[PIPE_A].plane[PLANE_SPRITE0] >> 8, SPRITEA_HI) |
			   FW_WM(wm->pipe[PIPE_A].plane[PLANE_PRIMARY] >> 8, PLANEA_HI));
	}

	POSTING_READ(DSPFW1);
}

#undef FW_WM_VLV

static void g4x_setup_wm_latency(struct drm_i915_private *dev_priv)
{
	/* all latencies in usec */
	dev_priv->wm.pri_latency[G4X_WM_LEVEL_NORMAL] = 5;
	dev_priv->wm.pri_latency[G4X_WM_LEVEL_SR] = 12;
	dev_priv->wm.pri_latency[G4X_WM_LEVEL_HPLL] = 35;

	dev_priv->wm.max_level = G4X_WM_LEVEL_HPLL;
}

static int g4x_plane_fifo_size(enum plane_id plane_id, int level)
{
	/*
	 * DSPCNTR[13] supposedly controls whether the
	 * primary plane can use the FIFO space otherwise
	 * reserved for the sprite plane. It's not 100% clear
	 * what the actual FIFO size is, but it looks like we
	 * can happily set both primary and sprite watermarks
	 * up to 127 cachelines. So that would seem to mean
	 * that either DSPCNTR[13] doesn't do anything, or that
	 * the total FIFO is >= 256 cachelines in size. Either
	 * way, we don't seem to have to worry about this
	 * repartitioning as the maximum watermark value the
	 * register can hold for each plane is lower than the
	 * minimum FIFO size.
	 */
	switch (plane_id) {
	case PLANE_CURSOR:
		return 63;
	case PLANE_PRIMARY:
		return level == G4X_WM_LEVEL_NORMAL ? 127 : 511;
	case PLANE_SPRITE0:
		return level == G4X_WM_LEVEL_NORMAL ? 127 : 0;
	default:
		MISSING_CASE(plane_id);
		return 0;
	}
}

static int g4x_fbc_fifo_size(int level)
{
	switch (level) {
	case G4X_WM_LEVEL_SR:
		return 7;
	case G4X_WM_LEVEL_HPLL:
		return 15;
	default:
		MISSING_CASE(level);
		return 0;
	}
}

static uint16_t g4x_compute_wm(const struct intel_crtc_state *crtc_state,
			       const struct intel_plane_state *plane_state,
			       int level)
{
	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
	const struct drm_display_mode *adjusted_mode =
		&crtc_state->base.adjusted_mode;
	int clock, htotal, cpp, width, wm;
	int latency = dev_priv->wm.pri_latency[level] * 10;

	if (latency == 0)
		return USHRT_MAX;

	if (!intel_wm_plane_visible(crtc_state, plane_state))
		return 0;

	/*
	 * Not 100% sure which way ELK should go here as the
	 * spec only says CL/CTG should assume 32bpp and BW
	 * doesn't need to. But as these things followed the
	 * mobile vs. desktop lines on gen3 as well, let's
	 * assume ELK doesn't need this.
	 *
	 * The spec also fails to list such a restriction for
	 * the HPLL watermark, which seems a little strange.
	 * Let's use 32bpp for the HPLL watermark as well.
	 */
	if (IS_GM45(dev_priv) && plane->id == PLANE_PRIMARY &&
	    level != G4X_WM_LEVEL_NORMAL)
		cpp = 4;
	else
		cpp = plane_state->base.fb->format->cpp[0];

	clock = adjusted_mode->crtc_clock;
	htotal = adjusted_mode->crtc_htotal;

	if (plane->id == PLANE_CURSOR)
		width = plane_state->base.crtc_w;
	else
		width = drm_rect_width(&plane_state->base.dst);

	if (plane->id == PLANE_CURSOR) {
		wm = intel_wm_method2(clock, htotal, width, cpp, latency);
	} else if (plane->id == PLANE_PRIMARY &&
		   level == G4X_WM_LEVEL_NORMAL) {
		wm = intel_wm_method1(clock, cpp, latency);
	} else {
		int small, large;

		small = intel_wm_method1(clock, cpp, latency);
		large = intel_wm_method2(clock, htotal, width, cpp, latency);

		wm = min(small, large);
	}

	wm += g4x_tlb_miss_wa(g4x_plane_fifo_size(plane->id, level),
			      width, cpp);

	wm = DIV_ROUND_UP(wm, 64) + 2;

	return min_t(int, wm, USHRT_MAX);
}

static bool g4x_raw_plane_wm_set(struct intel_crtc_state *crtc_state,
				 int level, enum plane_id plane_id, u16 value)
{
	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
	bool dirty = false;

	for (; level < intel_wm_num_levels(dev_priv); level++) {
		struct g4x_pipe_wm *raw = &crtc_state->wm.g4x.raw[level];

		dirty |= raw->plane[plane_id] != value;
		raw->plane[plane_id] = value;
	}

	return dirty;
}

static bool g4x_raw_fbc_wm_set(struct intel_crtc_state *crtc_state,
			       int level, u16 value)
{
	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
	bool dirty = false;

	/* NORMAL level doesn't have an FBC watermark */
	level = max(level, G4X_WM_LEVEL_SR);

	for (; level < intel_wm_num_levels(dev_priv); level++) {
		struct g4x_pipe_wm *raw = &crtc_state->wm.g4x.raw[level];

		dirty |= raw->fbc != value;
		raw->fbc = value;
	}

	return dirty;
}

static uint32_t ilk_compute_fbc_wm(const struct intel_crtc_state *cstate,
				   const struct intel_plane_state *pstate,
				   uint32_t pri_val);

static bool g4x_raw_plane_wm_compute(struct intel_crtc_state *crtc_state,
				     const struct intel_plane_state *plane_state)
{
	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
	int num_levels = intel_wm_num_levels(to_i915(plane->base.dev));
	enum plane_id plane_id = plane->id;
	bool dirty = false;
	int level;

	if (!intel_wm_plane_visible(crtc_state, plane_state)) {
		dirty |= g4x_raw_plane_wm_set(crtc_state, 0, plane_id, 0);
		if (plane_id == PLANE_PRIMARY)
			dirty |= g4x_raw_fbc_wm_set(crtc_state, 0, 0);
		goto out;
	}

	for (level = 0; level < num_levels; level++) {
		struct g4x_pipe_wm *raw = &crtc_state->wm.g4x.raw[level];
		int wm, max_wm;

		wm = g4x_compute_wm(crtc_state, plane_state, level);
		max_wm = g4x_plane_fifo_size(plane_id, level);

		if (wm > max_wm)
			break;

		dirty |= raw->plane[plane_id] != wm;
		raw->plane[plane_id] = wm;

		if (plane_id != PLANE_PRIMARY ||
		    level == G4X_WM_LEVEL_NORMAL)
			continue;

		wm = ilk_compute_fbc_wm(crtc_state, plane_state,
					raw->plane[plane_id]);
		max_wm = g4x_fbc_fifo_size(level);

		/*
		 * FBC wm is not mandatory as we
		 * can always just disable its use.
		 */
		if (wm > max_wm)
			wm = USHRT_MAX;

		dirty |= raw->fbc != wm;
		raw->fbc = wm;
	}

	/* mark watermarks as invalid */
	dirty |= g4x_raw_plane_wm_set(crtc_state, level, plane_id, USHRT_MAX);

	if (plane_id == PLANE_PRIMARY)
		dirty |= g4x_raw_fbc_wm_set(crtc_state, level, USHRT_MAX);

 out:
	if (dirty) {
		DRM_DEBUG_KMS("%s watermarks: normal=%d, SR=%d, HPLL=%d\n",
			      plane->base.name,
			      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_NORMAL].plane[plane_id],
			      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].plane[plane_id],
			      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].plane[plane_id]);

		if (plane_id == PLANE_PRIMARY)
			DRM_DEBUG_KMS("FBC watermarks: SR=%d, HPLL=%d\n",
				      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].fbc,
				      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].fbc);
	}

	return dirty;
}

static bool g4x_raw_plane_wm_is_valid(const struct intel_crtc_state *crtc_state,
				      enum plane_id plane_id, int level)
{
	const struct g4x_pipe_wm *raw = &crtc_state->wm.g4x.raw[level];

	return raw->plane[plane_id] <= g4x_plane_fifo_size(plane_id, level);
}

static bool g4x_raw_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state,
				     int level)
{
	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);

	if (level > dev_priv->wm.max_level)
		return false;

	return g4x_raw_plane_wm_is_valid(crtc_state, PLANE_PRIMARY, level) &&
		g4x_raw_plane_wm_is_valid(crtc_state, PLANE_SPRITE0, level) &&
		g4x_raw_plane_wm_is_valid(crtc_state, PLANE_CURSOR, level);
}

/* mark all levels starting from 'level' as invalid */
static void g4x_invalidate_wms(struct intel_crtc *crtc,
			       struct g4x_wm_state *wm_state, int level)
{
	if (level <= G4X_WM_LEVEL_NORMAL) {
		enum plane_id plane_id;

		for_each_plane_id_on_crtc(crtc, plane_id)
			wm_state->wm.plane[plane_id] = USHRT_MAX;
	}

	if (level <= G4X_WM_LEVEL_SR) {
		wm_state->cxsr = false;
		wm_state->sr.cursor = USHRT_MAX;
		wm_state->sr.plane = USHRT_MAX;
		wm_state->sr.fbc = USHRT_MAX;
	}

	if (level <= G4X_WM_LEVEL_HPLL) {
		wm_state->hpll_en = false;
		wm_state->hpll.cursor = USHRT_MAX;
		wm_state->hpll.plane = USHRT_MAX;
		wm_state->hpll.fbc = USHRT_MAX;
	}
}

static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state)
{
	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
	struct intel_atomic_state *state =
		to_intel_atomic_state(crtc_state->base.state);
	struct g4x_wm_state *wm_state = &crtc_state->wm.g4x.optimal;
	int num_active_planes = hweight32(crtc_state->active_planes &
					  ~BIT(PLANE_CURSOR));
	const struct g4x_pipe_wm *raw;
	struct intel_plane_state *plane_state;
	struct intel_plane *plane;
	enum plane_id plane_id;
	int i, level;
	unsigned int dirty = 0;

	for_each_intel_plane_in_state(state, plane, plane_state, i) {
		const struct intel_plane_state *old_plane_state =
			to_intel_plane_state(plane->base.state);

		if (plane_state->base.crtc != &crtc->base &&
		    old_plane_state->base.crtc != &crtc->base)
			continue;

		if (g4x_raw_plane_wm_compute(crtc_state, plane_state))
			dirty |= BIT(plane->id);
	}

	if (!dirty)
		return 0;

	level = G4X_WM_LEVEL_NORMAL;
	if (!g4x_raw_crtc_wm_is_valid(crtc_state, level))
		goto out;

	raw = &crtc_state->wm.g4x.raw[level];
	for_each_plane_id_on_crtc(crtc, plane_id)
		wm_state->wm.plane[plane_id] = raw->plane[plane_id];

	level = G4X_WM_LEVEL_SR;

	if (!g4x_raw_crtc_wm_is_valid(crtc_state, level))
		goto out;

	raw = &crtc_state->wm.g4x.raw[level];
	wm_state->sr.plane = raw->plane[PLANE_PRIMARY];
	wm_state->sr.cursor = raw->plane[PLANE_CURSOR];
	wm_state->sr.fbc = raw->fbc;

	wm_state->cxsr = num_active_planes == BIT(PLANE_PRIMARY);

	level = G4X_WM_LEVEL_HPLL;

	if (!g4x_raw_crtc_wm_is_valid(crtc_state, level))
		goto out;

	raw = &crtc_state->wm.g4x.raw[level];
	wm_state->hpll.plane = raw->plane[PLANE_PRIMARY];
	wm_state->hpll.cursor = raw->plane[PLANE_CURSOR];
	wm_state->hpll.fbc = raw->fbc;

	wm_state->hpll_en = wm_state->cxsr;

	level++;

 out:
	if (level == G4X_WM_LEVEL_NORMAL)
		return -EINVAL;

	/* invalidate the higher levels */
	g4x_invalidate_wms(crtc, wm_state, level);

	/*
	 * Determine if the FBC watermark(s) can be used. IF
	 * this isn't the case we prefer to disable the FBC
	 ( watermark(s) rather than disable the SR/HPLL
	 * level(s) entirely.
	 */
	wm_state->fbc_en = level > G4X_WM_LEVEL_NORMAL;

	if (level >= G4X_WM_LEVEL_SR &&
	    wm_state->sr.fbc > g4x_fbc_fifo_size(G4X_WM_LEVEL_SR))
		wm_state->fbc_en = false;
	else if (level >= G4X_WM_LEVEL_HPLL &&
		 wm_state->hpll.fbc > g4x_fbc_fifo_size(G4X_WM_LEVEL_HPLL))
		wm_state->fbc_en = false;

	return 0;
}

static int g4x_compute_intermediate_wm(struct drm_device *dev,
				       struct intel_crtc *crtc,
				       struct intel_crtc_state *crtc_state)
{
	struct g4x_wm_state *intermediate = &crtc_state->wm.g4x.intermediate;
	const struct g4x_wm_state *optimal = &crtc_state->wm.g4x.optimal;
	const struct g4x_wm_state *active = &crtc->wm.active.g4x;
	enum plane_id plane_id;

	intermediate->cxsr = optimal->cxsr && active->cxsr &&
		!crtc_state->disable_cxsr;
	intermediate->hpll_en = optimal->hpll_en && active->hpll_en &&
		!crtc_state->disable_cxsr;
	intermediate->fbc_en = optimal->fbc_en && active->fbc_en;

	for_each_plane_id_on_crtc(crtc, plane_id) {
		intermediate->wm.plane[plane_id] =
			max(optimal->wm.plane[plane_id],
			    active->wm.plane[plane_id]);

		WARN_ON(intermediate->wm.plane[plane_id] >
			g4x_plane_fifo_size(plane_id, G4X_WM_LEVEL_NORMAL));
	}

	intermediate->sr.plane = max(optimal->sr.plane,
				     active->sr.plane);
	intermediate->sr.cursor = max(optimal->sr.cursor,
				      active->sr.cursor);
	intermediate->sr.fbc = max(optimal->sr.fbc,
				   active->sr.fbc);

	intermediate->hpll.plane = max(optimal->hpll.plane,
				       active->hpll.plane);
	intermediate->hpll.cursor = max(optimal->hpll.cursor,
					active->hpll.cursor);
	intermediate->hpll.fbc = max(optimal->hpll.fbc,
				     active->hpll.fbc);

	WARN_ON((intermediate->sr.plane >
		 g4x_plane_fifo_size(PLANE_PRIMARY, G4X_WM_LEVEL_SR) ||
		 intermediate->sr.cursor >
		 g4x_plane_fifo_size(PLANE_CURSOR, G4X_WM_LEVEL_SR)) &&
		intermediate->cxsr);
	WARN_ON((intermediate->sr.plane >
		 g4x_plane_fifo_size(PLANE_PRIMARY, G4X_WM_LEVEL_HPLL) ||
		 intermediate->sr.cursor >
		 g4x_plane_fifo_size(PLANE_CURSOR, G4X_WM_LEVEL_HPLL)) &&
		intermediate->hpll_en);

	WARN_ON(intermediate->sr.fbc > g4x_fbc_fifo_size(1) &&
		intermediate->fbc_en && intermediate->cxsr);
	WARN_ON(intermediate->hpll.fbc > g4x_fbc_fifo_size(2) &&
		intermediate->fbc_en && intermediate->hpll_en);

	/*
	 * If our intermediate WM are identical to the final WM, then we can
	 * omit the post-vblank programming; only update if it's different.
	 */
	if (memcmp(intermediate, optimal, sizeof(*intermediate)) != 0)
		crtc_state->wm.need_postvbl_update = true;

	return 0;
}

static void g4x_merge_wm(struct drm_i915_private *dev_priv,
			 struct g4x_wm_values *wm)
{
	struct intel_crtc *crtc;
	int num_active_crtcs = 0;

	wm->cxsr = true;
	wm->hpll_en = true;
	wm->fbc_en = true;

	for_each_intel_crtc(&dev_priv->drm, crtc) {
		const struct g4x_wm_state *wm_state = &crtc->wm.active.g4x;

		if (!crtc->active)
			continue;

		if (!wm_state->cxsr)
			wm->cxsr = false;
		if (!wm_state->hpll_en)
			wm->hpll_en = false;
		if (!wm_state->fbc_en)
			wm->fbc_en = false;

		num_active_crtcs++;
	}

	if (num_active_crtcs != 1) {
		wm->cxsr = false;
		wm->hpll_en = false;
		wm->fbc_en = false;
	}

	for_each_intel_crtc(&dev_priv->drm, crtc) {
		const struct g4x_wm_state *wm_state = &crtc->wm.active.g4x;
		enum pipe pipe = crtc->pipe;

		wm->pipe[pipe] = wm_state->wm;
		if (crtc->active && wm->cxsr)
			wm->sr = wm_state->sr;
		if (crtc->active && wm->hpll_en)
			wm->hpll = wm_state->hpll;
	}
}

static void g4x_program_watermarks(struct drm_i915_private *dev_priv)
{
	struct g4x_wm_values *old_wm = &dev_priv->wm.g4x;
	struct g4x_wm_values new_wm = {};

	g4x_merge_wm(dev_priv, &new_wm);

	if (memcmp(old_wm, &new_wm, sizeof(new_wm)) == 0)
		return;

	if (is_disabling(old_wm->cxsr, new_wm.cxsr, true))
		_intel_set_memory_cxsr(dev_priv, false);

	g4x_write_wm_values(dev_priv, &new_wm);

	if (is_enabling(old_wm->cxsr, new_wm.cxsr, true))
		_intel_set_memory_cxsr(dev_priv, true);

	*old_wm = new_wm;
}

static void g4x_initial_watermarks(struct intel_atomic_state *state,
				   struct intel_crtc_state *crtc_state)
{
	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);

	mutex_lock(&dev_priv->wm.wm_mutex);
	crtc->wm.active.g4x = crtc_state->wm.g4x.intermediate;
	g4x_program_watermarks(dev_priv);
	mutex_unlock(&dev_priv->wm.wm_mutex);
}

static void g4x_optimize_watermarks(struct intel_atomic_state *state,
				    struct intel_crtc_state *crtc_state)
{
	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);

	if (!crtc_state->wm.need_postvbl_update)
		return;

	mutex_lock(&dev_priv->wm.wm_mutex);
	intel_crtc->wm.active.g4x = crtc_state->wm.g4x.optimal;
	g4x_program_watermarks(dev_priv);
	mutex_unlock(&dev_priv->wm.wm_mutex);
}

/* latency must be in 0.1us units. */
static unsigned int vlv_wm_method2(unsigned int pixel_rate,
				   unsigned int htotal,
				   unsigned int width,
				   unsigned int cpp,
				   unsigned int latency)
{
	unsigned int ret;

	ret = intel_wm_method2(pixel_rate, htotal,
			       width, cpp, latency);
	ret = DIV_ROUND_UP(ret, 64);

	return ret;
}

static void vlv_setup_wm_latency(struct drm_i915_private *dev_priv)
{
	/* all latencies in usec */
	dev_priv->wm.pri_latency[VLV_WM_LEVEL_PM2] = 3;

	dev_priv->wm.max_level = VLV_WM_LEVEL_PM2;

	if (IS_CHERRYVIEW(dev_priv)) {
		dev_priv->wm.pri_latency[VLV_WM_LEVEL_PM5] = 12;
		dev_priv->wm.pri_latency[VLV_WM_LEVEL_DDR_DVFS] = 33;

		dev_priv->wm.max_level = VLV_WM_LEVEL_DDR_DVFS;
	}
}

static uint16_t vlv_compute_wm_level(const struct intel_crtc_state *crtc_state,
				     const struct intel_plane_state *plane_state,
				     int level)
{
	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
	const struct drm_display_mode *adjusted_mode =
		&crtc_state->base.adjusted_mode;
	int clock, htotal, cpp, width, wm;

	if (dev_priv->wm.pri_latency[level] == 0)
		return USHRT_MAX;

	if (!intel_wm_plane_visible(crtc_state, plane_state))
		return 0;

	cpp = plane_state->base.fb->format->cpp[0];
	clock = adjusted_mode->crtc_clock;
	htotal = adjusted_mode->crtc_htotal;
	width = crtc_state->pipe_src_w;

	if (plane->id == PLANE_CURSOR) {
		/*
		 * FIXME the formula gives values that are
		 * too big for the cursor FIFO, and hence we
		 * would never be able to use cursors. For
		 * now just hardcode the watermark.
		 */
		wm = 63;
	} else {
		wm = vlv_wm_method2(clock, htotal, width, cpp,
				    dev_priv->wm.pri_latency[level] * 10);
	}

	return min_t(int, wm, USHRT_MAX);
}

static bool vlv_need_sprite0_fifo_workaround(unsigned int active_planes)
{
	return (active_planes & (BIT(PLANE_SPRITE0) |
				 BIT(PLANE_SPRITE1))) == BIT(PLANE_SPRITE1);
}

static int vlv_compute_fifo(struct intel_crtc_state *crtc_state)
{
	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
	const struct g4x_pipe_wm *raw =
		&crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2];
	struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state;
	unsigned int active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
	int num_active_planes = hweight32(active_planes);
	const int fifo_size = 511;
	int fifo_extra, fifo_left = fifo_size;
	int sprite0_fifo_extra = 0;
	unsigned int total_rate;
	enum plane_id plane_id;

	/*
	 * When enabling sprite0 after sprite1 has already been enabled
	 * we tend to get an underrun unless sprite0 already has some
	 * FIFO space allcoated. Hence we always allocate at least one
	 * cacheline for sprite0 whenever sprite1 is enabled.
	 *
	 * All other plane enable sequences appear immune to this problem.
	 */
	if (vlv_need_sprite0_fifo_workaround(active_planes))
		sprite0_fifo_extra = 1;

	total_rate = raw->plane[PLANE_PRIMARY] +
		raw->plane[PLANE_SPRITE0] +
		raw->plane[PLANE_SPRITE1] +
		sprite0_fifo_extra;

	if (total_rate > fifo_size)
		return -EINVAL;

	if (total_rate == 0)
		total_rate = 1;

	for_each_plane_id_on_crtc(crtc, plane_id) {
		unsigned int rate;

		if ((active_planes & BIT(plane_id)) == 0) {
			fifo_state->plane[plane_id] = 0;
			continue;
		}

		rate = raw->plane[plane_id];
		fifo_state->plane[plane_id] = fifo_size * rate / total_rate;
		fifo_left -= fifo_state->plane[plane_id];
	}

	fifo_state->plane[PLANE_SPRITE0] += sprite0_fifo_extra;
	fifo_left -= sprite0_fifo_extra;

	fifo_state->plane[PLANE_CURSOR] = 63;

	fifo_extra = DIV_ROUND_UP(fifo_left, num_active_planes ?: 1);

	/* spread the remainder evenly */
	for_each_plane_id_on_crtc(crtc, plane_id) {
		int plane_extra;

		if (fifo_left == 0)
			break;

		if ((active_planes & BIT(plane_id)) == 0)
			continue;

		plane_extra = min(fifo_extra, fifo_left);
		fifo_state->plane[plane_id] += plane_extra;
		fifo_left -= plane_extra;
	}

	WARN_ON(active_planes != 0 && fifo_left != 0);

	/* give it all to the first plane if none are active */
	if (active_planes == 0) {
		WARN_ON(fifo_left != fifo_size);
		fifo_state->plane[PLANE_PRIMARY] = fifo_left;
	}

	return 0;
}

/* mark all levels starting from 'level' as invalid */
static void vlv_invalidate_wms(struct intel_crtc *crtc,
			       struct vlv_wm_state *wm_state, int level)
{
	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);

	for (; level < intel_wm_num_levels(dev_priv); level++) {
		enum plane_id plane_id;

		for_each_plane_id_on_crtc(crtc, plane_id)
			wm_state->wm[level].plane[plane_id] = USHRT_MAX;

		wm_state->sr[level].cursor = USHRT_MAX;
		wm_state->sr[level].plane = USHRT_MAX;
	}
}

static u16 vlv_invert_wm_value(u16 wm, u16 fifo_size)
{
	if (wm > fifo_size)
		return USHRT_MAX;
	else
		return fifo_size - wm;
}

/*
 * Starting from 'level' set all higher
 * levels to 'value' in the "raw" watermarks.
 */
static bool vlv_raw_plane_wm_set(struct intel_crtc_state *crtc_state,
				 int level, enum plane_id plane_id, u16 value)
{
	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
	int num_levels = intel_wm_num_levels(dev_priv);
	bool dirty = false;

	for (; level < num_levels; level++) {
		struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[level];

		dirty |= raw->plane[plane_id] != value;
		raw->plane[plane_id] = value;
	}

	return dirty;
}

static bool vlv_raw_plane_wm_compute(struct intel_crtc_state *crtc_state,
				     const struct intel_plane_state *plane_state)
{
	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
	enum plane_id plane_id = plane->id;
	int num_levels = intel_wm_num_levels(to_i915(plane->base.dev));
	int level;
	bool dirty = false;

	if (!intel_wm_plane_visible(crtc_state, plane_state)) {
		dirty |= vlv_raw_plane_wm_set(crtc_state, 0, plane_id, 0);
		goto out;
	}

	for (level = 0; level < num_levels; level++) {
		struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[level];
		int wm = vlv_compute_wm_level(crtc_state, plane_state, level);
		int max_wm = plane_id == PLANE_CURSOR ? 63 : 511;

		if (wm > max_wm)
			break;

		dirty |= raw->plane[plane_id] != wm;
		raw->plane[plane_id] = wm;
	}

	/* mark all higher levels as invalid */
	dirty |= vlv_raw_plane_wm_set(crtc_state, level, plane_id, USHRT_MAX);

out:
	if (dirty)
		DRM_DEBUG_KMS("%s watermarks: PM2=%d, PM5=%d, DDR DVFS=%d\n",
			      plane->base.name,
			      crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2].plane[plane_id],
			      crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM5].plane[plane_id],
			      crtc_state->wm.vlv.raw[VLV_WM_LEVEL_DDR_DVFS].plane[plane_id]);

	return dirty;
}

static bool vlv_raw_plane_wm_is_valid(const struct intel_crtc_state *crtc_state,
				      enum plane_id plane_id, int level)
{
	const struct g4x_pipe_wm *raw =
		&crtc_state->wm.vlv.raw[level];
	const struct vlv_fifo_state *fifo_state =
		&crtc_state->wm.vlv.fifo_state;

	return raw->plane[plane_id] <= fifo_state->plane[plane_id];
}

static bool vlv_raw_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state, int level)
{
	return vlv_raw_plane_wm_is_valid(crtc_state, PLANE_PRIMARY, level) &&
		vlv_raw_plane_wm_is_valid(crtc_state, PLANE_SPRITE0, level) &&
		vlv_raw_plane_wm_is_valid(crtc_state, PLANE_SPRITE1, level) &&
		vlv_raw_plane_wm_is_valid(crtc_state, PLANE_CURSOR, level);
}

static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
{
	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
	struct intel_atomic_state *state =
		to_intel_atomic_state(crtc_state->base.state);
	struct vlv_wm_state *wm_state = &crtc_state->wm.vlv.optimal;
	const struct vlv_fifo_state *fifo_state =
		&crtc_state->wm.vlv.fifo_state;
	int num_active_planes = hweight32(crtc_state->active_planes &
					  ~BIT(PLANE_CURSOR));
	bool needs_modeset = drm_atomic_crtc_needs_modeset(&crtc_state->base);
	struct intel_plane_state *plane_state;
	struct intel_plane *plane;
	enum plane_id plane_id;
	int level, ret, i;
	unsigned int dirty = 0;

	for_each_intel_plane_in_state(state, plane, plane_state, i) {
		const struct intel_plane_state *old_plane_state =
			to_intel_plane_state(plane->base.state);

		if (plane_state->base.crtc != &crtc->base &&
		    old_plane_state->base.crtc != &crtc->base)
			continue;

		if (vlv_raw_plane_wm_compute(crtc_state, plane_state))
			dirty |= BIT(plane->id);
	}

	/*
	 * DSPARB registers may have been reset due to the
	 * power well being turned off. Make sure we restore
	 * them to a consistent state even if no primary/sprite
	 * planes are initially active.
	 */
	if (needs_modeset)
		crtc_state->fifo_changed = true;

	if (!dirty)
		return 0;

	/* cursor changes don't warrant a FIFO recompute */
	if (dirty & ~BIT(PLANE_CURSOR)) {
		const struct intel_crtc_state *old_crtc_state =
			to_intel_crtc_state(crtc->base.state);
		const struct vlv_fifo_state *old_fifo_state =
			&old_crtc_state->wm.vlv.fifo_state;

		ret = vlv_compute_fifo(crtc_state);
		if (ret)
			return ret;

		if (needs_modeset ||
		    memcmp(old_fifo_state, fifo_state,
			   sizeof(*fifo_state)) != 0)
			crtc_state->fifo_changed = true;
	}

	/* initially allow all levels */
	wm_state->num_levels = intel_wm_num_levels(dev_priv);
	/*
	 * Note that enabling cxsr with no primary/sprite planes
	 * enabled can wedge the pipe. Hence we only allow cxsr
	 * with exactly one enabled primary/sprite plane.
	 */
	wm_state->cxsr = crtc->pipe != PIPE_C && num_active_planes == 1;

	for (level = 0; level < wm_state->num_levels; level++) {
		const struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[level];
		const int sr_fifo_size = INTEL_INFO(dev_priv)->num_pipes * 512 - 1;

		if (!vlv_raw_crtc_wm_is_valid(crtc_state, level))
			break;

		for_each_plane_id_on_crtc(crtc, plane_id) {
			wm_state->wm[level].plane[plane_id] =
				vlv_invert_wm_value(raw->plane[plane_id],
						    fifo_state->plane[plane_id]);
		}

		wm_state->sr[level].plane =
			vlv_invert_wm_value(max3(raw->plane[PLANE_PRIMARY],
						 raw->plane[PLANE_SPRITE0],
						 raw->plane[PLANE_SPRITE1]),
					    sr_fifo_size);

		wm_state->sr[level].cursor =
			vlv_invert_wm_value(raw->plane[PLANE_CURSOR],
					    63);
	}

	if (level == 0)
		return -EINVAL;

	/* limit to only levels we can actually handle */
	wm_state->num_levels = level;

	/* invalidate the higher levels */
	vlv_invalidate_wms(crtc, wm_state, level);

	return 0;
}

#define VLV_FIFO(plane, value) \
	(((value) << DSPARB_ ## plane ## _SHIFT_VLV) & DSPARB_ ## plane ## _MASK_VLV)

static void vlv_atomic_update_fifo(struct intel_atomic_state *state,
				   struct intel_crtc_state *crtc_state)
{
	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
	const struct vlv_fifo_state *fifo_state =
		&crtc_state->wm.vlv.fifo_state;
	int sprite0_start, sprite1_start, fifo_size;

	if (!crtc_state->fifo_changed)
		return;

	sprite0_start = fifo_state->plane[PLANE_PRIMARY];
	sprite1_start = fifo_state->plane[PLANE_SPRITE0] + sprite0_start;
	fifo_size = fifo_state->plane[PLANE_SPRITE1] + sprite1_start;

	WARN_ON(fifo_state->plane[PLANE_CURSOR] != 63);
	WARN_ON(fifo_size != 511);

	trace_vlv_fifo_size(crtc, sprite0_start, sprite1_start, fifo_size);

	/*
	 * uncore.lock serves a double purpose here. It allows us to
	 * use the less expensive I915_{READ,WRITE}_FW() functions, and
	 * it protects the DSPARB registers from getting clobbered by
	 * parallel updates from multiple pipes.
	 *
	 * intel_pipe_update_start() has already disabled interrupts
	 * for us, so a plain spin_lock() is sufficient here.
	 */
	spin_lock(&dev_priv->uncore.lock);

	switch (crtc->pipe) {
		uint32_t dsparb, dsparb2, dsparb3;
	case PIPE_A:
		dsparb = I915_READ_FW(DSPARB);
		dsparb2 = I915_READ_FW(DSPARB2);

		dsparb &= ~(VLV_FIFO(SPRITEA, 0xff) |
			    VLV_FIFO(SPRITEB, 0xff));
		dsparb |= (VLV_FIFO(SPRITEA, sprite0_start) |
			   VLV_FIFO(SPRITEB, sprite1_start));

		dsparb2 &= ~(VLV_FIFO(SPRITEA_HI, 0x1) |
			     VLV_FIFO(SPRITEB_HI, 0x1));
		dsparb2 |= (VLV_FIFO(SPRITEA_HI, sprite0_start >> 8) |
			   VLV_FIFO(SPRITEB_HI, sprite1_start >> 8));

		I915_WRITE_FW(DSPARB, dsparb);
		I915_WRITE_FW(DSPARB2, dsparb2);
		break;
	case PIPE_B:
		dsparb = I915_READ_FW(DSPARB);
		dsparb2 = I915_READ_FW(DSPARB2);

		dsparb &= ~(VLV_FIFO(SPRITEC, 0xff) |
			    VLV_FIFO(SPRITED, 0xff));
		dsparb |= (VLV_FIFO(SPRITEC, sprite0_start) |
			   VLV_FIFO(SPRITED, sprite1_start));

		dsparb2 &= ~(VLV_FIFO(SPRITEC_HI, 0xff) |
			     VLV_FIFO(SPRITED_HI, 0xff));
		dsparb2 |= (VLV_FIFO(SPRITEC_HI, sprite0_start >> 8) |
			   VLV_FIFO(SPRITED_HI, sprite1_start >> 8));

		I915_WRITE_FW(DSPARB, dsparb);
		I915_WRITE_FW(DSPARB2, dsparb2);
		break;
	case PIPE_C:
		dsparb3 = I915_READ_FW(DSPARB3);
		dsparb2 = I915_READ_FW(DSPARB2);

		dsparb3 &= ~(VLV_FIFO(SPRITEE, 0xff) |
			     VLV_FIFO(SPRITEF, 0xff));
		dsparb3 |= (VLV_FIFO(SPRITEE, sprite0_start) |
			    VLV_FIFO(SPRITEF, sprite1_start));

		dsparb2 &= ~(VLV_FIFO(SPRITEE_HI, 0xff) |
			     VLV_FIFO(SPRITEF_HI, 0xff));
		dsparb2 |= (VLV_FIFO(SPRITEE_HI, sprite0_start >> 8) |
			   VLV_FIFO(SPRITEF_HI, sprite1_start >> 8));

		I915_WRITE_FW(DSPARB3, dsparb3);
		I915_WRITE_FW(DSPARB2, dsparb2);
		break;
	default:
		break;
	}

	POSTING_READ_FW(DSPARB);

	spin_unlock(&dev_priv->uncore.lock);
}

#undef VLV_FIFO

static int vlv_compute_intermediate_wm(struct drm_device *dev,
				       struct intel_crtc *crtc,
				       struct intel_crtc_state *crtc_state)
{
	struct vlv_wm_state *intermediate = &crtc_state->wm.vlv.intermediate;
	const struct vlv_wm_state *optimal = &crtc_state->wm.vlv.optimal;
	const struct vlv_wm_state *active = &crtc->wm.active.vlv;
	int level;

	intermediate->num_levels = min(optimal->num_levels, active->num_levels);
	intermediate->cxsr = optimal->cxsr && active->cxsr &&
		!crtc_state->disable_cxsr;

	for (level = 0; level < intermediate->num_levels; level++) {
		enum plane_id plane_id;

		for_each_plane_id_on_crtc(crtc, plane_id) {
			intermediate->wm[level].plane[plane_id] =
				min(optimal->wm[level].plane[plane_id],
				    active->wm[level].plane[plane_id]);
		}

		intermediate->sr[level].plane = min(optimal->sr[level].plane,
						    active->sr[level].plane);
		intermediate->sr[level].cursor = min(optimal->sr[level].cursor,
						     active->sr[level].cursor);
	}

	vlv_invalidate_wms(crtc, intermediate, level);

	/*
	 * If our intermediate WM are identical to the final WM, then we can
	 * omit the post-vblank programming; only update if it's different.
	 */
	if (memcmp(intermediate, optimal, sizeof(*intermediate)) != 0)
		crtc_state->wm.need_postvbl_update = true;

	return 0;
}

static void vlv_merge_wm(struct drm_i915_private *dev_priv,
			 struct vlv_wm_values *wm)
{
	struct intel_crtc *crtc;
	int num_active_crtcs = 0;

	wm->level = dev_priv->wm.max_level;
	wm->cxsr = true;

	for_each_intel_crtc(&dev_priv->drm, crtc) {
		const struct vlv_wm_state *wm_state = &crtc->wm.active.vlv;

		if (!crtc->active)
			continue;

		if (!wm_state->cxsr)
			wm->cxsr = false;

		num_active_crtcs++;
		wm->level = min_t(int, wm->level, wm_state->num_levels - 1);
	}

	if (num_active_crtcs != 1)
		wm->cxsr = false;

	if (num_active_crtcs > 1)
		wm->level = VLV_WM_LEVEL_PM2;

	for_each_intel_crtc(&dev_priv->drm, crtc) {
		const struct vlv_wm_state *wm_state = &crtc->wm.active.vlv;
		enum pipe pipe = crtc->pipe;

		wm->pipe[pipe] = wm_state->wm[wm->level];
		if (crtc->active && wm->cxsr)
			wm->sr = wm_state->sr[wm->level];

		wm->ddl[pipe].plane[PLANE_PRIMARY] = DDL_PRECISION_HIGH | 2;
		wm->ddl[pipe].plane[PLANE_SPRITE0] = DDL_PRECISION_HIGH | 2;
		wm->ddl[pipe].plane[PLANE_SPRITE1] = DDL_PRECISION_HIGH | 2;
		wm->ddl[pipe].plane[PLANE_CURSOR] = DDL_PRECISION_HIGH | 2;
	}
}

static void vlv_program_watermarks(struct drm_i915_private *dev_priv)
{
	struct vlv_wm_values *old_wm = &dev_priv->wm.vlv;
	struct vlv_wm_values new_wm = {};

	vlv_merge_wm(dev_priv, &new_wm);

	if (memcmp(old_wm, &new_wm, sizeof(new_wm)) == 0)
		return;

	if (is_disabling(old_wm->level, new_wm.level, VLV_WM_LEVEL_DDR_DVFS))
		chv_set_memory_dvfs(dev_priv, false);

	if (is_disabling(old_wm->level, new_wm.level, VLV_WM_LEVEL_PM5))
		chv_set_memory_pm5(dev_priv, false);

	if (is_disabling(old_wm->cxsr, new_wm.cxsr, true))
		_intel_set_memory_cxsr(dev_priv, false);

	vlv_write_wm_values(dev_priv, &new_wm);

	if (is_enabling(old_wm->cxsr, new_wm.cxsr, true))
		_intel_set_memory_cxsr(dev_priv, true);

	if (is_enabling(old_wm->level, new_wm.level, VLV_WM_LEVEL_PM5))
		chv_set_memory_pm5(dev_priv, true);

	if (is_enabling(old_wm->level, new_wm.level, VLV_WM_LEVEL_DDR_DVFS))
		chv_set_memory_dvfs(dev_priv, true);

	*old_wm = new_wm;
}

static void vlv_initial_watermarks(struct intel_atomic_state *state,
				   struct intel_crtc_state *crtc_state)
{
	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);

	mutex_lock(&dev_priv->wm.wm_mutex);
	crtc->wm.active.vlv = crtc_state->wm.vlv.intermediate;
	vlv_program_watermarks(dev_priv);
	mutex_unlock(&dev_priv->wm.wm_mutex);
}

static void vlv_optimize_watermarks(struct intel_atomic_state *state,
				    struct intel_crtc_state *crtc_state)
{
	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);

	if (!crtc_state->wm.need_postvbl_update)
		return;

	mutex_lock(&dev_priv->wm.wm_mutex);
	intel_crtc->wm.active.vlv = crtc_state->wm.vlv.optimal;
	vlv_program_watermarks(dev_priv);
	mutex_unlock(&dev_priv->wm.wm_mutex);
}

static void i965_update_wm(struct intel_crtc *unused_crtc)
{
	struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev);
	struct intel_crtc *crtc;
	int srwm = 1;
	int cursor_sr = 16;
	bool cxsr_enabled;

	/* Calc sr entries for one plane configs */
	crtc = single_enabled_crtc(dev_priv);
	if (crtc) {
		/* self-refresh has much higher latency */
		static const int sr_latency_ns = 12000;
		const struct drm_display_mode *adjusted_mode =
			&crtc->config->base.adjusted_mode;
		const struct drm_framebuffer *fb =
			crtc->base.primary->state->fb;
		int clock = adjusted_mode->crtc_clock;
		int htotal = adjusted_mode->crtc_htotal;
		int hdisplay = crtc->config->pipe_src_w;
		int cpp = fb->format->cpp[0];
		int entries;

		entries = intel_wm_method2(clock, htotal,
					   hdisplay, cpp, sr_latency_ns / 100);
		entries = DIV_ROUND_UP(entries, I915_FIFO_LINE_SIZE);
		srwm = I965_FIFO_SIZE - entries;
		if (srwm < 0)
			srwm = 1;
		srwm &= 0x1ff;
		DRM_DEBUG_KMS("self-refresh entries: %d, wm: %d\n",
			      entries, srwm);

		entries = intel_wm_method2(clock, htotal,
					   crtc->base.cursor->state->crtc_w, 4,
					   sr_latency_ns / 100);
		entries = DIV_ROUND_UP(entries,
				       i965_cursor_wm_info.cacheline_size) +
			i965_cursor_wm_info.guard_size;

		cursor_sr = i965_cursor_wm_info.fifo_size - entries;
		if (cursor_sr > i965_cursor_wm_info.max_wm)
			cursor_sr = i965_cursor_wm_info.max_wm;

		DRM_DEBUG_KMS("self-refresh watermark: display plane %d "
			      "cursor %d\n", srwm, cursor_sr);

		cxsr_enabled = true;
	} else {
		cxsr_enabled = false;
		/* Turn off self refresh if both pipes are enabled */
		intel_set_memory_cxsr(dev_priv, false);
	}

	DRM_DEBUG_KMS("Setting FIFO watermarks - A: 8, B: 8, C: 8, SR %d\n",
		      srwm);

	/* 965 has limitations... */
	I915_WRITE(DSPFW1, FW_WM(srwm, SR) |
		   FW_WM(8, CURSORB) |
		   FW_WM(8, PLANEB) |
		   FW_WM(8, PLANEA));
	I915_WRITE(DSPFW2, FW_WM(8, CURSORA) |
		   FW_WM(8, PLANEC_OLD));
	/* update cursor SR watermark */
	I915_WRITE(DSPFW3, FW_WM(cursor_sr, CURSOR_SR));

	if (cxsr_enabled)
		intel_set_memory_cxsr(dev_priv, true);
}

#undef FW_WM

static void i9xx_update_wm(struct intel_crtc *unused_crtc)
{
	struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev);
	const struct intel_watermark_params *wm_info;
	uint32_t fwater_lo;
	uint32_t fwater_hi;
	int cwm, srwm = 1;
	int fifo_size;
	int planea_wm, planeb_wm;
	struct intel_crtc *crtc, *enabled = NULL;

	if (IS_I945GM(dev_priv))
		wm_info = &i945_wm_info;
	else if (!IS_GEN2(dev_priv))
		wm_info = &i915_wm_info;
	else
		wm_info = &i830_a_wm_info;

	fifo_size = dev_priv->display.get_fifo_size(dev_priv, 0);
	crtc = intel_get_crtc_for_plane(dev_priv, 0);
	if (intel_crtc_active(crtc)) {
		const struct drm_display_mode *adjusted_mode =
			&crtc->config->base.adjusted_mode;
		const struct drm_framebuffer *fb =
			crtc->base.primary->state->fb;
		int cpp;

		if (IS_GEN2(dev_priv))
			cpp = 4;
		else
			cpp = fb->format->cpp[0];

		planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
					       wm_info, fifo_size, cpp,
					       pessimal_latency_ns);
		enabled = crtc;
	} else {
		planea_wm = fifo_size - wm_info->guard_size;
		if (planea_wm > (long)wm_info->max_wm)
			planea_wm = wm_info->max_wm;
	}

	if (IS_GEN2(dev_priv))
		wm_info = &i830_bc_wm_info;

	fifo_size = dev_priv->display.get_fifo_size(dev_priv, 1);
	crtc = intel_get_crtc_for_plane(dev_priv, 1);
	if (intel_crtc_active(crtc)) {
		const struct drm_display_mode *adjusted_mode =
			&crtc->config->base.adjusted_mode;
		const struct drm_framebuffer *fb =
			crtc->base.primary->state->fb;
		int cpp;

		if (IS_GEN2(dev_priv))
			cpp = 4;
		else
			cpp = fb->format->cpp[0];

		planeb_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
					       wm_info, fifo_size, cpp,
					       pessimal_latency_ns);
		if (enabled == NULL)
			enabled = crtc;
		else
			enabled = NULL;
	} else {
		planeb_wm = fifo_size - wm_info->guard_size;
		if (planeb_wm > (long)wm_info->max_wm)
			planeb_wm = wm_info->max_wm;
	}

	DRM_DEBUG_KMS("FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm);

	if (IS_I915GM(dev_priv) && enabled) {
		struct drm_i915_gem_object *obj;

		obj = intel_fb_obj(enabled->base.primary->state->fb);

		/* self-refresh seems busted with untiled */
		if (!i915_gem_object_is_tiled(obj))
			enabled = NULL;
	}

	/*
	 * Overlay gets an aggressive default since video jitter is bad.
	 */
	cwm = 2;

	/* Play safe and disable self-refresh before adjusting watermarks. */
	intel_set_memory_cxsr(dev_priv, false);

	/* Calc sr entries for one plane configs */
	if (HAS_FW_BLC(dev_priv) && enabled) {
		/* self-refresh has much higher latency */
		static const int sr_latency_ns = 6000;
		const struct drm_display_mode *adjusted_mode =
			&enabled->config->base.adjusted_mode;
		const struct drm_framebuffer *fb =
			enabled->base.primary->state->fb;
		int clock = adjusted_mode->crtc_clock;
		int htotal = adjusted_mode->crtc_htotal;
		int hdisplay = enabled->config->pipe_src_w;
		int cpp;
		int entries;

		if (IS_I915GM(dev_priv) || IS_I945GM(dev_priv))
			cpp = 4;
		else
			cpp = fb->format->cpp[0];

		entries = intel_wm_method2(clock, htotal, hdisplay, cpp,
					   sr_latency_ns / 100);
		entries = DIV_ROUND_UP(entries, wm_info->cacheline_size);
		DRM_DEBUG_KMS("self-refresh entries: %d\n", entries);
		srwm = wm_info->fifo_size - entries;
		if (srwm < 0)
			srwm = 1;

		if (IS_I945G(dev_priv) || IS_I945GM(dev_priv))
			I915_WRITE(FW_BLC_SELF,
				   FW_BLC_SELF_FIFO_MASK | (srwm & 0xff));
		else
			I915_WRITE(FW_BLC_SELF, srwm & 0x3f);
	}

	DRM_DEBUG_KMS("Setting FIFO watermarks - A: %d, B: %d, C: %d, SR %d\n",
		      planea_wm, planeb_wm, cwm, srwm);

	fwater_lo = ((planeb_wm & 0x3f) << 16) | (planea_wm & 0x3f);
	fwater_hi = (cwm & 0x1f);

	/* Set request length to 8 cachelines per fetch */
	fwater_lo = fwater_lo | (1 << 24) | (1 << 8);
	fwater_hi = fwater_hi | (1 << 8);

	I915_WRITE(FW_BLC, fwater_lo);
	I915_WRITE(FW_BLC2, fwater_hi);

	if (enabled)
		intel_set_memory_cxsr(dev_priv, true);
}

static void i845_update_wm(struct intel_crtc *unused_crtc)
{
	struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev);
	struct intel_crtc *crtc;
	const struct drm_display_mode *adjusted_mode;
	uint32_t fwater_lo;
	int planea_wm;

	crtc = single_enabled_crtc(dev_priv);
	if (crtc == NULL)
		return;

	adjusted_mode = &crtc->config->base.adjusted_mode;
	planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
				       &i845_wm_info,
				       dev_priv->display.get_fifo_size(dev_priv, 0),
				       4, pessimal_latency_ns);
	fwater_lo = I915_READ(FW_BLC) & ~0xfff;
	fwater_lo |= (3<<8) | planea_wm;

	DRM_DEBUG_KMS("Setting FIFO watermarks - A: %d\n", planea_wm);

	I915_WRITE(FW_BLC, fwater_lo);
}

/* latency must be in 0.1us units. */
static unsigned int ilk_wm_method1(unsigned int pixel_rate,
				   unsigned int cpp,
				   unsigned int latency)
{
	unsigned int ret;

	ret = intel_wm_method1(pixel_rate, cpp, latency);
	ret = DIV_ROUND_UP(ret, 64) + 2;

	return ret;
}

/* latency must be in 0.1us units. */
static unsigned int ilk_wm_method2(unsigned int pixel_rate,
				   unsigned int htotal,
				   unsigned int width,
				   unsigned int cpp,
				   unsigned int latency)
{
	unsigned int ret;

	ret = intel_wm_method2(pixel_rate, htotal,
			       width, cpp, latency);
	ret = DIV_ROUND_UP(ret, 64) + 2;

	return ret;
}

static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels,
			   uint8_t cpp)
{
	/*
	 * Neither of these should be possible since this function shouldn't be
	 * called if the CRTC is off or the plane is invisible.  But let's be
	 * extra paranoid to avoid a potential divide-by-zero if we screw up
	 * elsewhere in the driver.
	 */
	if (WARN_ON(!cpp))
		return 0;
	if (WARN_ON(!horiz_pixels))
		return 0;

	return DIV_ROUND_UP(pri_val * 64, horiz_pixels * cpp) + 2;
}

struct ilk_wm_maximums {
	uint16_t pri;
	uint16_t spr;
	uint16_t cur;
	uint16_t fbc;
};

/*
 * For both WM_PIPE and WM_LP.
 * mem_value must be in 0.1us units.
 */
static uint32_t ilk_compute_pri_wm(const struct intel_crtc_state *cstate,
				   const struct intel_plane_state *pstate,
				   uint32_t mem_value,
				   bool is_lp)
{
	uint32_t method1, method2;
	int cpp;

	if (!intel_wm_plane_visible(cstate, pstate))
		return 0;

	cpp = pstate->base.fb->format->cpp[0];

	method1 = ilk_wm_method1(cstate->pixel_rate, cpp, mem_value);

	if (!is_lp)
		return method1;

	method2 = ilk_wm_method2(cstate->pixel_rate,
				 cstate->base.adjusted_mode.crtc_htotal,
				 drm_rect_width(&pstate->base.dst),
				 cpp, mem_value);

	return min(method1, method2);
}

/*
 * For both WM_PIPE and WM_LP.
 * mem_value must be in 0.1us units.
 */
static uint32_t ilk_compute_spr_wm(const struct intel_crtc_state *cstate,
				   const struct intel_plane_state *pstate,
				   uint32_t mem_value)
{
	uint32_t method1, method2;
	int cpp;

	if (!intel_wm_plane_visible(cstate, pstate))
		return 0;

	cpp = pstate->base.fb->format->cpp[0];

	method1 = ilk_wm_method1(cstate->pixel_rate, cpp, mem_value);
	method2 = ilk_wm_method2(cstate->pixel_rate,
				 cstate->base.adjusted_mode.crtc_htotal,
				 drm_rect_width(&pstate->base.dst),
				 cpp, mem_value);
	return min(method1, method2);
}

/*
 * For both WM_PIPE and WM_LP.
 * mem_value must be in 0.1us units.
 */
static uint32_t ilk_compute_cur_wm(const struct intel_crtc_state *cstate,
				   const struct intel_plane_state *pstate,
				   uint32_t mem_value)
{
	int cpp;

	if (!intel_wm_plane_visible(cstate, pstate))
		return 0;

	cpp = pstate->base.fb->format->cpp[0];

	return ilk_wm_method2(cstate->pixel_rate,
			      cstate->base.adjusted_mode.crtc_htotal,
			      pstate->base.crtc_w, cpp, mem_value);
}

/* Only for WM_LP. */
static uint32_t ilk_compute_fbc_wm(const struct intel_crtc_state *cstate,
				   const struct intel_plane_state *pstate,
				   uint32_t pri_val)
{
	int cpp;

	if (!intel_wm_plane_visible(cstate, pstate))
		return 0;

	cpp = pstate->base.fb->format->cpp[0];

	return ilk_wm_fbc(pri_val, drm_rect_width(&pstate->base.dst), cpp);
}

static unsigned int
ilk_display_fifo_size(const struct drm_i915_private *dev_priv)
{
	if (INTEL_GEN(dev_priv) >= 8)
		return 3072;
	else if (INTEL_GEN(dev_priv) >= 7)
		return 768;
	else
		return 512;
}

static unsigned int
ilk_plane_wm_reg_max(const struct drm_i915_private *dev_priv,
		     int level, bool is_sprite)
{
	if (INTEL_GEN(dev_priv) >= 8)
		/* BDW primary/sprite plane watermarks */
		return level == 0 ? 255 : 2047;
	else if (INTEL_GEN(dev_priv) >= 7)
		/* IVB/HSW primary/sprite plane watermarks */
		return level == 0 ? 127 : 1023;
	else if (!is_sprite)
		/* ILK/SNB primary plane watermarks */
		return level == 0 ? 127 : 511;
	else
		/* ILK/SNB sprite plane watermarks */
		return level == 0 ? 63 : 255;
}

static unsigned int
ilk_cursor_wm_reg_max(const struct drm_i915_private *dev_priv, int level)
{
	if (INTEL_GEN(dev_priv) >= 7)
		return level == 0 ? 63 : 255;
	else
		return level == 0 ? 31 : 63;
}

static unsigned int ilk_fbc_wm_reg_max(const struct drm_i915_private *dev_priv)
{
	if (INTEL_GEN(dev_priv) >= 8)
		return 31;
	else
		return 15;
}

/* Calculate the maximum primary/sprite plane watermark */
static unsigned int ilk_plane_wm_max(const struct drm_device *dev,
				     int level,
				     const struct intel_wm_config *config,
				     enum intel_ddb_partitioning ddb_partitioning,
				     bool is_sprite)
{
	struct drm_i915_private *dev_priv = to_i915(dev);
	unsigned int fifo_size = ilk_display_fifo_size(dev_priv);

	/* if sprites aren't enabled, sprites get nothing */
	if (is_sprite && !config->sprites_enabled)
		return 0;

	/* HSW allows LP1+ watermarks even with multiple pipes */
	if (level == 0 || config->num_pipes_active > 1) {
		fifo_size /= INTEL_INFO(dev_priv)->num_pipes;

		/*
		 * For some reason the non self refresh
		 * FIFO size is only half of the self
		 * refresh FIFO size on ILK/SNB.
		 */
		if (INTEL_GEN(dev_priv) <= 6)
			fifo_size /= 2;
	}

	if (config->sprites_enabled) {
		/* level 0 is always calculated with 1:1 split */
		if (level > 0 && ddb_partitioning == INTEL_DDB_PART_5_6) {
			if (is_sprite)
				fifo_size *= 5;
			fifo_size /= 6;
		} else {
			fifo_size /= 2;
		}
	}

	/* clamp to max that the registers can hold */
	return min(fifo_size, ilk_plane_wm_reg_max(dev_priv, level, is_sprite));
}

/* Calculate the maximum cursor plane watermark */
static unsigned int ilk_cursor_wm_max(const struct drm_device *dev,
				      int level,
				      const struct intel_wm_config *config)
{
	/* HSW LP1+ watermarks w/ multiple pipes */
	if (level > 0 && config->num_pipes_active > 1)
		return 64;

	/* otherwise just report max that registers can hold */
	return ilk_cursor_wm_reg_max(to_i915(dev), level);
}

static void ilk_compute_wm_maximums(const struct drm_device *dev,
				    int level,
				    const struct intel_wm_config *config,
				    enum intel_ddb_partitioning ddb_partitioning,
				    struct ilk_wm_maximums *max)
{
	max->pri = ilk_plane_wm_max(dev, level, config, ddb_partitioning, false);
	max->spr = ilk_plane_wm_max(dev, level, config, ddb_partitioning, true);
	max->cur = ilk_cursor_wm_max(dev, level, config);
	max->fbc = ilk_fbc_wm_reg_max(to_i915(dev));
}

static void ilk_compute_wm_reg_maximums(const struct drm_i915_private *dev_priv,
					int level,
					struct ilk_wm_maximums *max)
{
	max->pri = ilk_plane_wm_reg_max(dev_priv, level, false);
	max->spr = ilk_plane_wm_reg_max(dev_priv, level, true);
	max->cur = ilk_cursor_wm_reg_max(dev_priv, level);
	max->fbc = ilk_fbc_wm_reg_max(dev_priv);
}

static bool ilk_validate_wm_level(int level,
				  const struct ilk_wm_maximums *max,
				  struct intel_wm_level *result)
{
	bool ret;

	/* already determined to be invalid? */
	if (!result->enable)
		return false;

	result->enable = result->pri_val <= max->pri &&
			 result->spr_val <= max->spr &&
			 result->cur_val <= max->cur;

	ret = result->enable;

	/*
	 * HACK until we can pre-compute everything,
	 * and thus fail gracefully if LP0 watermarks
	 * are exceeded...
	 */
	if (level == 0 && !result->enable) {
		if (result->pri_val > max->pri)
			DRM_DEBUG_KMS("Primary WM%d too large %u (max %u)\n",
				      level, result->pri_val, max->pri);
		if (result->spr_val > max->spr)
			DRM_DEBUG_KMS("Sprite WM%d too large %u (max %u)\n",
				      level, result->spr_val, max->spr);
		if (result->cur_val > max->cur)
			DRM_DEBUG_KMS("Cursor WM%d too large %u (max %u)\n",
				      level, result->cur_val, max->cur);

		result->pri_val = min_t(uint32_t, result->pri_val, max->pri);
		result->spr_val = min_t(uint32_t, result->spr_val, max->spr);
		result->cur_val = min_t(uint32_t, result->cur_val, max->cur);
		result->enable = true;
	}

	return ret;
}

static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv,
				 const struct intel_crtc *intel_crtc,
				 int level,
				 struct intel_crtc_state *cstate,
				 struct intel_plane_state *pristate,
				 struct intel_plane_state *sprstate,
				 struct intel_plane_state *curstate,
				 struct intel_wm_level *result)
{
	uint16_t pri_latency = dev_priv->wm.pri_latency[level];
	uint16_t spr_latency = dev_priv->wm.spr_latency[level];
	uint16_t cur_latency = dev_priv->wm.cur_latency[level];

	/* WM1+ latency values stored in 0.5us units */
	if (level > 0) {
		pri_latency *= 5;
		spr_latency *= 5;
		cur_latency *= 5;
	}

	if (pristate) {
		result->pri_val = ilk_compute_pri_wm(cstate, pristate,
						     pri_latency, level);
		result->fbc_val = ilk_compute_fbc_wm(cstate, pristate, result->pri_val);
	}

	if (sprstate)
		result->spr_val = ilk_compute_spr_wm(cstate, sprstate, spr_latency);

	if (curstate)
		result->cur_val = ilk_compute_cur_wm(cstate, curstate, cur_latency);

	result->enable = true;
}

static uint32_t
hsw_compute_linetime_wm(const struct intel_crtc_state *cstate)
{
	const struct intel_atomic_state *intel_state =
		to_intel_atomic_state(cstate->base.state);
	const struct drm_display_mode *adjusted_mode =
		&cstate->base.adjusted_mode;
	u32 linetime, ips_linetime;

	if (!cstate->base.active)
		return 0;
	if (WARN_ON(adjusted_mode->crtc_clock == 0))
		return 0;
	if (WARN_ON(intel_state->cdclk.logical.cdclk == 0))
		return 0;

	/* The WM are computed with base on how long it takes to fill a single
	 * row at the given clock rate, multiplied by 8.
	 * */
	linetime = DIV_ROUND_CLOSEST(adjusted_mode->crtc_htotal * 1000 * 8,
				     adjusted_mode->crtc_clock);
	ips_linetime = DIV_ROUND_CLOSEST(adjusted_mode->crtc_htotal * 1000 * 8,
					 intel_state->cdclk.logical.cdclk);

	return PIPE_WM_LINETIME_IPS_LINETIME(ips_linetime) |
	       PIPE_WM_LINETIME_TIME(linetime);
}

static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
				  uint16_t wm[8])
{
	if (INTEL_GEN(dev_priv) >= 9) {
		uint32_t val;
		int ret, i;
		int level, max_level = ilk_wm_max_level(dev_priv);

		/* read the first set of memory latencies[0:3] */
		val = 0; /* data0 to be programmed to 0 for first set */
		mutex_lock(&dev_priv->rps.hw_lock);
		ret = sandybridge_pcode_read(dev_priv,
					     GEN9_PCODE_READ_MEM_LATENCY,
					     &val);
		mutex_unlock(&dev_priv->rps.hw_lock);

		if (ret) {
			DRM_ERROR("SKL Mailbox read error = %d\n", ret);
			return;
		}

		wm[0] = val & GEN9_MEM_LATENCY_LEVEL_MASK;
		wm[1] = (val >> GEN9_MEM_LATENCY_LEVEL_1_5_SHIFT) &
				GEN9_MEM_LATENCY_LEVEL_MASK;
		wm[2] = (val >> GEN9_MEM_LATENCY_LEVEL_2_6_SHIFT) &
				GEN9_MEM_LATENCY_LEVEL_MASK;
		wm[3] = (val >> GEN9_MEM_LATENCY_LEVEL_3_7_SHIFT) &
				GEN9_MEM_LATENCY_LEVEL_MASK;

		/* read the second set of memory latencies[4:7] */
		val = 1; /* data0 to be programmed to 1 for second set */
		mutex_lock(&dev_priv->rps.hw_lock);
		ret = sandybridge_pcode_read(dev_priv,
					     GEN9_PCODE_READ_MEM_LATENCY,
					     &val);
		mutex_unlock(&dev_priv->rps.hw_lock);
		if (ret) {
			DRM_ERROR("SKL Mailbox read error = %d\n", ret);
			return;
		}

		wm[4] = val & GEN9_MEM_LATENCY_LEVEL_MASK;
		wm[5] = (val >> GEN9_MEM_LATENCY_LEVEL_1_5_SHIFT) &
				GEN9_MEM_LATENCY_LEVEL_MASK;
		wm[6] = (val >> GEN9_MEM_LATENCY_LEVEL_2_6_SHIFT) &
				GEN9_MEM_LATENCY_LEVEL_MASK;
		wm[7] = (val >> GEN9_MEM_LATENCY_LEVEL_3_7_SHIFT) &
				GEN9_MEM_LATENCY_LEVEL_MASK;

		/*
		 * If a level n (n > 1) has a 0us latency, all levels m (m >= n)
		 * need to be disabled. We make sure to sanitize the values out
		 * of the punit to satisfy this requirement.
		 */
		for (level = 1; level <= max_level; level++) {
			if (wm[level] == 0) {
				for (i = level + 1; i <= max_level; i++)
					wm[i] = 0;
				break;
			}
		}

		/*
		 * WaWmMemoryReadLatency:skl+,glk
		 *
		 * punit doesn't take into account the read latency so we need
		 * to add 2us to the various latency levels we retrieve from the
		 * punit when level 0 response data us 0us.
		 */
		if (wm[0] == 0) {
			wm[0] += 2;
			for (level = 1; level <= max_level; level++) {
				if (wm[level] == 0)
					break;
				wm[level] += 2;
			}
		}

	} else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
		uint64_t sskpd = I915_READ64(MCH_SSKPD);

		wm[0] = (sskpd >> 56) & 0xFF;
		if (wm[0] == 0)
			wm[0] = sskpd & 0xF;
		wm[1] = (sskpd >> 4) & 0xFF;
		wm[2] = (sskpd >> 12) & 0xFF;
		wm[3] = (sskpd >> 20) & 0x1FF;
		wm[4] = (sskpd >> 32) & 0x1FF;
	} else if (INTEL_GEN(dev_priv) >= 6) {
		uint32_t sskpd = I915_READ(MCH_SSKPD);

		wm[0] = (sskpd >> SSKPD_WM0_SHIFT) & SSKPD_WM_MASK;
		wm[1] = (sskpd >> SSKPD_WM1_SHIFT) & SSKPD_WM_MASK;
		wm[2] = (sskpd >> SSKPD_WM2_SHIFT) & SSKPD_WM_MASK;
		wm[3] = (sskpd >> SSKPD_WM3_SHIFT) & SSKPD_WM_MASK;
	} else if (INTEL_GEN(dev_priv) >= 5) {
		uint32_t mltr = I915_READ(MLTR_ILK);

		/* ILK primary LP0 latency is 700 ns */
		wm[0] = 7;
		wm[1] = (mltr >> MLTR_WM1_SHIFT) & ILK_SRLT_MASK;
		wm[2] = (mltr >> MLTR_WM2_SHIFT) & ILK_SRLT_MASK;
	} else {
		MISSING_CASE(INTEL_DEVID(dev_priv));
	}
}

static void intel_fixup_spr_wm_latency(struct drm_i915_private *dev_priv,
				       uint16_t wm[5])
{
	/* ILK sprite LP0 latency is 1300 ns */
	if (IS_GEN5(dev_priv))
		wm[0] = 13;
}

static void intel_fixup_cur_wm_latency(struct drm_i915_private *dev_priv,
				       uint16_t wm[5])
{
	/* ILK cursor LP0 latency is 1300 ns */
	if (IS_GEN5(dev_priv))
		wm[0] = 13;

	/* WaDoubleCursorLP3Latency:ivb */
	if (IS_IVYBRIDGE(dev_priv))
		wm[3] *= 2;
}

int ilk_wm_max_level(const struct drm_i915_private *dev_priv)
{
	/* how many WM levels are we expecting */
	if (INTEL_GEN(dev_priv) >= 9)
		return 7;
	else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
		return 4;
	else if (INTEL_GEN(dev_priv) >= 6)
		return 3;
	else
		return 2;
}

static void intel_print_wm_latency(struct drm_i915_private *dev_priv,
				   const char *name,
				   const uint16_t wm[8])
{
	int level, max_level = ilk_wm_max_level(dev_priv);

	for (level = 0; level <= max_level; level++) {
		unsigned int latency = wm[level];

		if (latency == 0) {
			DRM_ERROR("%s WM%d latency not provided\n",
				  name, level);
			continue;
		}

		/*
		 * - latencies are in us on gen9.
		 * - before then, WM1+ latency values are in 0.5us units
		 */
		if (INTEL_GEN(dev_priv) >= 9)
			latency *= 10;
		else if (level > 0)
			latency *= 5;

		DRM_DEBUG_KMS("%s WM%d latency %u (%u.%u usec)\n",
			      name, level, wm[level],
			      latency / 10, latency % 10);
	}
}

static bool ilk_increase_wm_latency(struct drm_i915_private *dev_priv,
				    uint16_t wm[5], uint16_t min)
{
	int level, max_level = ilk_wm_max_level(dev_priv);

	if (wm[0] >= min)
		return false;

	wm[0] = max(wm[0], min);
	for (level = 1; level <= max_level; level++)
		wm[level] = max_t(uint16_t, wm[level], DIV_ROUND_UP(min, 5));

	return true;
}

static void snb_wm_latency_quirk(struct drm_i915_private *dev_priv)
{
	bool changed;

	/*
	 * The BIOS provided WM memory latency values are often
	 * inadequate for high resolution displays. Adjust them.
	 */
	changed = ilk_increase_wm_latency(dev_priv, dev_priv->wm.pri_latency, 12) |
		ilk_increase_wm_latency(dev_priv, dev_priv->wm.spr_latency, 12) |
		ilk_increase_wm_latency(dev_priv, dev_priv->wm.cur_latency, 12);

	if (!changed)
		return;

	DRM_DEBUG_KMS("WM latency values increased to avoid potential underruns\n");
	intel_print_wm_latency(dev_priv, "Primary", dev_priv->wm.pri_latency);
	intel_print_wm_latency(dev_priv, "Sprite", dev_priv->wm.spr_latency);
	intel_print_wm_latency(dev_priv, "Cursor", dev_priv->wm.cur_latency);
}

static void ilk_setup_wm_latency(struct drm_i915_private *dev_priv)
{
	intel_read_wm_latency(dev_priv, dev_priv->wm.pri_latency);

	memcpy(dev_priv->wm.spr_latency, dev_priv->wm.pri_latency,
	       sizeof(dev_priv->wm.pri_latency));
	memcpy(dev_priv->wm.cur_latency, dev_priv->wm.pri_latency,
	       sizeof(dev_priv->wm.pri_latency));

	intel_fixup_spr_wm_latency(dev_priv, dev_priv->wm.spr_latency);
	intel_fixup_cur_wm_latency(dev_priv, dev_priv->wm.cur_latency);

	intel_print_wm_latency(dev_priv, "Primary", dev_priv->wm.pri_latency);
	intel_print_wm_latency(dev_priv, "Sprite", dev_priv->wm.spr_latency);
	intel_print_wm_latency(dev_priv, "Cursor", dev_priv->wm.cur_latency);

	if (IS_GEN6(dev_priv))
		snb_wm_latency_quirk(dev_priv);
}

static void skl_setup_wm_latency(struct drm_i915_private *dev_priv)
{
	intel_read_wm_latency(dev_priv, dev_priv->wm.skl_latency);
	intel_print_wm_latency(dev_priv, "Gen9 Plane", dev_priv->wm.skl_latency);
}

static bool ilk_validate_pipe_wm(struct drm_device *dev,
				 struct intel_pipe_wm *pipe_wm)
{
	/* LP0 watermark maximums depend on this pipe alone */
	const struct intel_wm_config config = {
		.num_pipes_active = 1,
		.sprites_enabled = pipe_wm->sprites_enabled,
		.sprites_scaled = pipe_wm->sprites_scaled,
	};
	struct ilk_wm_maximums max;

	/* LP0 watermarks always use 1/2 DDB partitioning */
	ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max);

	/* At least LP0 must be valid */
	if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0])) {
		DRM_DEBUG_KMS("LP0 watermark invalid\n");
		return false;
	}

	return true;
}

/* Compute new watermarks for the pipe */
static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate)
{
	struct drm_atomic_state *state = cstate->base.state;
	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
	struct intel_pipe_wm *pipe_wm;
	struct drm_device *dev = state->dev;
	const struct drm_i915_private *dev_priv = to_i915(dev);
	struct intel_plane *intel_plane;
	struct intel_plane_state *pristate = NULL;
	struct intel_plane_state *sprstate = NULL;
	struct intel_plane_state *curstate = NULL;
	int level, max_level = ilk_wm_max_level(dev_priv), usable_level;
	struct ilk_wm_maximums max;

	pipe_wm = &cstate->wm.ilk.optimal;

	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
		struct intel_plane_state *ps;

		ps = intel_atomic_get_existing_plane_state(state,
							   intel_plane);
		if (!ps)
			continue;

		if (intel_plane->base.type == DRM_PLANE_TYPE_PRIMARY)
			pristate = ps;
		else if (intel_plane->base.type == DRM_PLANE_TYPE_OVERLAY)
			sprstate = ps;
		else if (intel_plane->base.type == DRM_PLANE_TYPE_CURSOR)
			curstate = ps;
	}

	pipe_wm->pipe_enabled = cstate->base.active;
	if (sprstate) {
		pipe_wm->sprites_enabled = sprstate->base.visible;
		pipe_wm->sprites_scaled = sprstate->base.visible &&
			(drm_rect_width(&sprstate->base.dst) != drm_rect_width(&sprstate->base.src) >> 16 ||
			 drm_rect_height(&sprstate->base.dst) != drm_rect_height(&sprstate->base.src) >> 16);
	}

	usable_level = max_level;

	/* ILK/SNB: LP2+ watermarks only w/o sprites */
	if (INTEL_GEN(dev_priv) <= 6 && pipe_wm->sprites_enabled)
		usable_level = 1;

	/* ILK/SNB/IVB: LP1+ watermarks only w/o scaling */
	if (pipe_wm->sprites_scaled)
		usable_level = 0;

	ilk_compute_wm_level(dev_priv, intel_crtc, 0, cstate,
			     pristate, sprstate, curstate, &pipe_wm->raw_wm[0]);

	memset(&pipe_wm->wm, 0, sizeof(pipe_wm->wm));
	pipe_wm->wm[0] = pipe_wm->raw_wm[0];

	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
		pipe_wm->linetime = hsw_compute_linetime_wm(cstate);

	if (!ilk_validate_pipe_wm(dev, pipe_wm))
		return -EINVAL;

	ilk_compute_wm_reg_maximums(dev_priv, 1, &max);

	for (level = 1; level <= max_level; level++) {
		struct intel_wm_level *wm = &pipe_wm->raw_wm[level];

		ilk_compute_wm_level(dev_priv, intel_crtc, level, cstate,
				     pristate, sprstate, curstate, wm);

		/*
		 * Disable any watermark level that exceeds the
		 * register maximums since such watermarks are
		 * always invalid.
		 */
		if (level > usable_level)
			continue;

		if (ilk_validate_wm_level(level, &max, wm))
			pipe_wm->wm[level] = *wm;
		else
			usable_level = level;
	}

	return 0;
}

/*
 * Build a set of 'intermediate' watermark values that satisfy both the old
 * state and the new state.  These can be programmed to the hardware
 * immediately.
 */
static int ilk_compute_intermediate_wm(struct drm_device *dev,
				       struct intel_crtc *intel_crtc,
				       struct intel_crtc_state *newstate)
{
	struct intel_pipe_wm *a = &newstate->wm.ilk.intermediate;
	struct intel_pipe_wm *b = &intel_crtc->wm.active.ilk;
	int level, max_level = ilk_wm_max_level(to_i915(dev));

	/*
	 * Start with the final, target watermarks, then combine with the
	 * currently active watermarks to get values that are safe both before
	 * and after the vblank.
	 */
	*a = newstate->wm.ilk.optimal;
	a->pipe_enabled |= b->pipe_enabled;
	a->sprites_enabled |= b->sprites_enabled;
	a->sprites_scaled |= b->sprites_scaled;

	for (level = 0; level <= max_level; level++) {
		struct intel_wm_level *a_wm = &a->wm[level];
		const struct intel_wm_level *b_wm = &b->wm[level];

		a_wm->enable &= b_wm->enable;
		a_wm->pri_val = max(a_wm->pri_val, b_wm->pri_val);
		a_wm->spr_val = max(a_wm->spr_val, b_wm->spr_val);
		a_wm->cur_val = max(a_wm->cur_val, b_wm->cur_val);
		a_wm->fbc_val = max(a_wm->fbc_val, b_wm->fbc_val);
	}

	/*
	 * We need to make sure that these merged watermark values are
	 * actually a valid configuration themselves.  If they're not,
	 * there's no safe way to transition from the old state to
	 * the new state, so we need to fail the atomic transaction.
	 */
	if (!ilk_validate_pipe_wm(dev, a))
		return -EINVAL;

	/*
	 * If our intermediate WM are identical to the final WM, then we can
	 * omit the post-vblank programming; only update if it's different.
	 */
	if (memcmp(a, &newstate->wm.ilk.optimal, sizeof(*a)) != 0)
		newstate->wm.need_postvbl_update = true;

	return 0;
}

/*
 * Merge the watermarks from all active pipes for a specific level.
 */
static void ilk_merge_wm_level(struct drm_device *dev,
			       int level,
			       struct intel_wm_level *ret_wm)
{
	const struct intel_crtc *intel_crtc;

	ret_wm->enable = true;

	for_each_intel_crtc(dev, intel_crtc) {
		const struct intel_pipe_wm *active = &intel_crtc->wm.active.ilk;
		const struct intel_wm_level *wm = &active->wm[level];

		if (!active->pipe_enabled)
			continue;

		/*
		 * The watermark values may have been used in the past,
		 * so we must maintain them in the registers for some
		 * time even if the level is now disabled.
		 */
		if (!wm->enable)
			ret_wm->enable = false;

		ret_wm->pri_val = max(ret_wm->pri_val, wm->pri_val);
		ret_wm->spr_val = max(ret_wm->spr_val, wm->spr_val);
		ret_wm->cur_val = max(ret_wm->cur_val, wm->cur_val);
		ret_wm->fbc_val = max(ret_wm->fbc_val, wm->fbc_val);
	}
}

/*
 * Merge all low power watermarks for all active pipes.
 */
static void ilk_wm_merge(struct drm_device *dev,
			 const struct intel_wm_config *config,
			 const struct ilk_wm_maximums *max,
			 struct intel_pipe_wm *merged)
{
	struct drm_i915_private *dev_priv = to_i915(dev);
	int level, max_level = ilk_wm_max_level(dev_priv);
	int last_enabled_level = max_level;

	/* ILK/SNB/IVB: LP1+ watermarks only w/ single pipe */
	if ((INTEL_GEN(dev_priv) <= 6 || IS_IVYBRIDGE(dev_priv)) &&
	    config->num_pipes_active > 1)
		last_enabled_level = 0;

	/* ILK: FBC WM must be disabled always */
	merged->fbc_wm_enabled = INTEL_GEN(dev_priv) >= 6;

	/* merge each WM1+ level */
	for (level = 1; level <= max_level; level++) {
		struct intel_wm_level *wm = &merged->wm[level];

		ilk_merge_wm_level(dev, level, wm);

		if (level > last_enabled_level)
			wm->enable = false;
		else if (!ilk_validate_wm_level(level, max, wm))
			/* make sure all following levels get disabled */
			last_enabled_level = level - 1;

		/*
		 * The spec says it is preferred to disable
		 * FBC WMs instead of disabling a WM level.
		 */
		if (wm->fbc_val > max->fbc) {
			if (wm->enable)
				merged->fbc_wm_enabled = false;
			wm->fbc_val = 0;
		}
	}

	/* ILK: LP2+ must be disabled when FBC WM is disabled but FBC enabled */
	/*
	 * FIXME this is racy. FBC might get enabled later.
	 * What we should check here is whether FBC can be
	 * enabled sometime later.
	 */
	if (IS_GEN5(dev_priv) && !merged->fbc_wm_enabled &&
	    intel_fbc_is_active(dev_priv)) {
		for (level = 2; level <= max_level; level++) {
			struct intel_wm_level *wm = &merged->wm[level];

			wm->enable = false;
		}
	}
}

static int ilk_wm_lp_to_level(int wm_lp, const struct intel_pipe_wm *pipe_wm)
{
	/* LP1,LP2,LP3 levels are either 1,2,3 or 1,3,4 */
	return wm_lp + (wm_lp >= 2 && pipe_wm->wm[4].enable);
}

/* The value we need to program into the WM_LPx latency field */
static unsigned int ilk_wm_lp_latency(struct drm_device *dev, int level)
{
	struct drm_i915_private *dev_priv = to_i915(dev);

	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
		return 2 * level;
	else
		return dev_priv->wm.pri_latency[level];
}

static void ilk_compute_wm_results(struct drm_device *dev,
				   const struct intel_pipe_wm *merged,
				   enum intel_ddb_partitioning partitioning,
				   struct ilk_wm_values *results)
{
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct intel_crtc *intel_crtc;
	int level, wm_lp;

	results->enable_fbc_wm = merged->fbc_wm_enabled;
	results->partitioning = partitioning;

	/* LP1+ register values */
	for (wm_lp = 1; wm_lp <= 3; wm_lp++) {
		const struct intel_wm_level *r;

		level = ilk_wm_lp_to_level(wm_lp, merged);

		r = &merged->wm[level];

		/*
		 * Maintain the watermark values even if the level is
		 * disabled. Doing otherwise could cause underruns.
		 */
		results->wm_lp[wm_lp - 1] =
			(ilk_wm_lp_latency(dev, level) << WM1_LP_LATENCY_SHIFT) |
			(r->pri_val << WM1_LP_SR_SHIFT) |
			r->cur_val;

		if (r->enable)
			results->wm_lp[wm_lp - 1] |= WM1_LP_SR_EN;

		if (INTEL_GEN(dev_priv) >= 8)
			results->wm_lp[wm_lp - 1] |=
				r->fbc_val << WM1_LP_FBC_SHIFT_BDW;
		else
			results->wm_lp[wm_lp - 1] |=
				r->fbc_val << WM1_LP_FBC_SHIFT;

		/*
		 * Always set WM1S_LP_EN when spr_val != 0, even if the
		 * level is disabled. Doing otherwise could cause underruns.
		 */
		if (INTEL_GEN(dev_priv) <= 6 && r->spr_val) {
			WARN_ON(wm_lp != 1);
			results->wm_lp_spr[wm_lp - 1] = WM1S_LP_EN | r->spr_val;
		} else
			results->wm_lp_spr[wm_lp - 1] = r->spr_val;
	}

	/* LP0 register values */
	for_each_intel_crtc(dev, intel_crtc) {
		enum pipe pipe = intel_crtc->pipe;
		const struct intel_wm_level *r =
			&intel_crtc->wm.active.ilk.wm[0];

		if (WARN_ON(!r->enable))
			continue;

		results->wm_linetime[pipe] = intel_crtc->wm.active.ilk.linetime;

		results->wm_pipe[pipe] =
			(r->pri_val << WM0_PIPE_PLANE_SHIFT) |
			(r->spr_val << WM0_PIPE_SPRITE_SHIFT) |
			r->cur_val;
	}
}

/* Find the result with the highest level enabled. Check for enable_fbc_wm in
 * case both are at the same level. Prefer r1 in case they're the same. */
static struct intel_pipe_wm *ilk_find_best_result(struct drm_device *dev,
						  struct intel_pipe_wm *r1,
						  struct intel_pipe_wm *r2)
{
	int level, max_level = ilk_wm_max_level(to_i915(dev));
	int level1 = 0, level2 = 0;

	for (level = 1; level <= max_level; level++) {
		if (r1->wm[level].enable)
			level1 = level;
		if (r2->wm[level].enable)
			level2 = level;
	}

	if (level1 == level2) {
		if (r2->fbc_wm_enabled && !r1->fbc_wm_enabled)
			return r2;
		else
			return r1;
	} else if (level1 > level2) {
		return r1;
	} else {
		return r2;
	}
}

/* dirty bits used to track which watermarks need changes */
#define WM_DIRTY_PIPE(pipe) (1 << (pipe))
#define WM_DIRTY_LINETIME(pipe) (1 << (8 + (pipe)))
#define WM_DIRTY_LP(wm_lp) (1 << (15 + (wm_lp)))
#define WM_DIRTY_LP_ALL (WM_DIRTY_LP(1) | WM_DIRTY_LP(2) | WM_DIRTY_LP(3))
#define WM_DIRTY_FBC (1 << 24)
#define WM_DIRTY_DDB (1 << 25)

static unsigned int ilk_compute_wm_dirty(struct drm_i915_private *dev_priv,
					 const struct ilk_wm_values *old,
					 const struct ilk_wm_values *new)
{
	unsigned int dirty = 0;
	enum pipe pipe;
	int wm_lp;

	for_each_pipe(dev_priv, pipe) {
		if (old->wm_linetime[pipe] != new->wm_linetime[pipe]) {
			dirty |= WM_DIRTY_LINETIME(pipe);
			/* Must disable LP1+ watermarks too */
			dirty |= WM_DIRTY_LP_ALL;
		}

		if (old->wm_pipe[pipe] != new->wm_pipe[pipe]) {
			dirty |= WM_DIRTY_PIPE(pipe);
			/* Must disable LP1+ watermarks too */
			dirty |= WM_DIRTY_LP_ALL;
		}
	}

	if (old->enable_fbc_wm != new->enable_fbc_wm) {
		dirty |= WM_DIRTY_FBC;
		/* Must disable LP1+ watermarks too */
		dirty |= WM_DIRTY_LP_ALL;
	}

	if (old->partitioning != new->partitioning) {
		dirty |= WM_DIRTY_DDB;
		/* Must disable LP1+ watermarks too */
		dirty |= WM_DIRTY_LP_ALL;
	}

	/* LP1+ watermarks already deemed dirty, no need to continue */
	if (dirty & WM_DIRTY_LP_ALL)
		return dirty;

	/* Find the lowest numbered LP1+ watermark in need of an update... */
	for (wm_lp = 1; wm_lp <= 3; wm_lp++) {
		if (old->wm_lp[wm_lp - 1] != new->wm_lp[wm_lp - 1] ||
		    old->wm_lp_spr[wm_lp - 1] != new->wm_lp_spr[wm_lp - 1])
			break;
	}

	/* ...and mark it and all higher numbered LP1+ watermarks as dirty */
	for (; wm_lp <= 3; wm_lp++)
		dirty |= WM_DIRTY_LP(wm_lp);

	return dirty;
}

static bool _ilk_disable_lp_wm(struct drm_i915_private *dev_priv,
			       unsigned int dirty)
{
	struct ilk_wm_values *previous = &dev_priv->wm.hw;
	bool changed = false;

	if (dirty & WM_DIRTY_LP(3) && previous->wm_lp[2] & WM1_LP_SR_EN) {
		previous->wm_lp[2] &= ~WM1_LP_SR_EN;
		I915_WRITE(WM3_LP_ILK, previous->wm_lp[2]);
		changed = true;
	}
	if (dirty & WM_DIRTY_LP(2) && previous->wm_lp[1] & WM1_LP_SR_EN) {
		previous->wm_lp[1] &= ~WM1_LP_SR_EN;
		I915_WRITE(WM2_LP_ILK, previous->wm_lp[1]);
		changed = true;
	}
	if (dirty & WM_DIRTY_LP(1) && previous->wm_lp[0] & WM1_LP_SR_EN) {
		previous->wm_lp[0] &= ~WM1_LP_SR_EN;
		I915_WRITE(WM1_LP_ILK, previous->wm_lp[0]);
		changed = true;
	}

	/*
	 * Don't touch WM1S_LP_EN here.
	 * Doing so could cause underruns.
	 */

	return changed;
}

/*
 * The spec says we shouldn't write when we don't need, because every write
 * causes WMs to be re-evaluated, expending some power.
 */
static void ilk_write_wm_values(struct drm_i915_private *dev_priv,
				struct ilk_wm_values *results)
{
	struct ilk_wm_values *previous = &dev_priv->wm.hw;
	unsigned int dirty;
	uint32_t val;

	dirty = ilk_compute_wm_dirty(dev_priv, previous, results);
	if (!dirty)
		return;

	_ilk_disable_lp_wm(dev_priv, dirty);

	if (dirty & WM_DIRTY_PIPE(PIPE_A))
		I915_WRITE(WM0_PIPEA_ILK, results->wm_pipe[0]);
	if (dirty & WM_DIRTY_PIPE(PIPE_B))
		I915_WRITE(WM0_PIPEB_ILK, results->wm_pipe[1]);
	if (dirty & WM_DIRTY_PIPE(PIPE_C))
		I915_WRITE(WM0_PIPEC_IVB, results->wm_pipe[2]);

	if (dirty & WM_DIRTY_LINETIME(PIPE_A))
		I915_WRITE(PIPE_WM_LINETIME(PIPE_A), results->wm_linetime[0]);
	if (dirty & WM_DIRTY_LINETIME(PIPE_B))
		I915_WRITE(PIPE_WM_LINETIME(PIPE_B), results->wm_linetime[1]);
	if (dirty & WM_DIRTY_LINETIME(PIPE_C))
		I915_WRITE(PIPE_WM_LINETIME(PIPE_C), results->wm_linetime[2]);

	if (dirty & WM_DIRTY_DDB) {
		if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
			val = I915_READ(WM_MISC);
			if (results->partitioning == INTEL_DDB_PART_1_2)
				val &= ~WM_MISC_DATA_PARTITION_5_6;
			else
				val |= WM_MISC_DATA_PARTITION_5_6;
			I915_WRITE(WM_MISC, val);
		} else {
			val = I915_READ(DISP_ARB_CTL2);
			if (results->partitioning == INTEL_DDB_PART_1_2)
				val &= ~DISP_DATA_PARTITION_5_6;
			else
				val |= DISP_DATA_PARTITION_5_6;
			I915_WRITE(DISP_ARB_CTL2, val);
		}
	}

	if (dirty & WM_DIRTY_FBC) {
		val = I915_READ(DISP_ARB_CTL);
		if (results->enable_fbc_wm)
			val &= ~DISP_FBC_WM_DIS;
		else
			val |= DISP_FBC_WM_DIS;
		I915_WRITE(DISP_ARB_CTL, val);
	}

	if (dirty & WM_DIRTY_LP(1) &&
	    previous->wm_lp_spr[0] != results->wm_lp_spr[0])
		I915_WRITE(WM1S_LP_ILK, results->wm_lp_spr[0]);

	if (INTEL_GEN(dev_priv) >= 7) {
		if (dirty & WM_DIRTY_LP(2) && previous->wm_lp_spr[1] != results->wm_lp_spr[1])
			I915_WRITE(WM2S_LP_IVB, results->wm_lp_spr[1]);
		if (dirty & WM_DIRTY_LP(3) && previous->wm_lp_spr[2] != results->wm_lp_spr[2])
			I915_WRITE(WM3S_LP_IVB, results->wm_lp_spr[2]);
	}

	if (dirty & WM_DIRTY_LP(1) && previous->wm_lp[0] != results->wm_lp[0])
		I915_WRITE(WM1_LP_ILK, results->wm_lp[0]);
	if (dirty & WM_DIRTY_LP(2) && previous->wm_lp[1] != results->wm_lp[1])
		I915_WRITE(WM2_LP_ILK, results->wm_lp[1]);
	if (dirty & WM_DIRTY_LP(3) && previous->wm_lp[2] != results->wm_lp[2])
		I915_WRITE(WM3_LP_ILK, results->wm_lp[2]);

	dev_priv->wm.hw = *results;
}

bool ilk_disable_lp_wm(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = to_i915(dev);

	return _ilk_disable_lp_wm(dev_priv, WM_DIRTY_LP_ALL);
}

/*
 * FIXME: We still don't have the proper code detect if we need to apply the WA,
 * so assume we'll always need it in order to avoid underruns.
 */
static bool skl_needs_memory_bw_wa(struct intel_atomic_state *state)
{
	struct drm_i915_private *dev_priv = to_i915(state->base.dev);

	if (IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv))
		return true;

	return false;
}

static bool
intel_has_sagv(struct drm_i915_private *dev_priv)
{
	if (IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv) ||
	    IS_CANNONLAKE(dev_priv))
		return true;

	if (IS_SKYLAKE(dev_priv) &&
	    dev_priv->sagv_status != I915_SAGV_NOT_CONTROLLED)
		return true;

	return false;
}

/*
 * SAGV dynamically adjusts the system agent voltage and clock frequencies
 * depending on power and performance requirements. The display engine access
 * to system memory is blocked during the adjustment time. Because of the
 * blocking time, having this enabled can cause full system hangs and/or pipe
 * underruns if we don't meet all of the following requirements:
 *
 *  - <= 1 pipe enabled
 *  - All planes can enable watermarks for latencies >= SAGV engine block time
 *  - We're not using an interlaced display configuration
 */
int
intel_enable_sagv(struct drm_i915_private *dev_priv)
{
	int ret;

	if (!intel_has_sagv(dev_priv))
		return 0;

	if (dev_priv->sagv_status == I915_SAGV_ENABLED)
		return 0;

	DRM_DEBUG_KMS("Enabling the SAGV\n");
	mutex_lock(&dev_priv->rps.hw_lock);

	ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL,
				      GEN9_SAGV_ENABLE);

	/* We don't need to wait for the SAGV when enabling */
	mutex_unlock(&dev_priv->rps.hw_lock);

	/*
	 * Some skl systems, pre-release machines in particular,
	 * don't actually have an SAGV.
	 */
	if (IS_SKYLAKE(dev_priv) && ret == -ENXIO) {
		DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
		dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED;
		return 0;
	} else if (ret < 0) {
		DRM_ERROR("Failed to enable the SAGV\n");
		return ret;
	}

	dev_priv->sagv_status = I915_SAGV_ENABLED;
	return 0;
}

int
intel_disable_sagv(struct drm_i915_private *dev_priv)
{
	int ret;

	if (!intel_has_sagv(dev_priv))
		return 0;

	if (dev_priv->sagv_status == I915_SAGV_DISABLED)
		return 0;

	DRM_DEBUG_KMS("Disabling the SAGV\n");
	mutex_lock(&dev_priv->rps.hw_lock);

	/* bspec says to keep retrying for at least 1 ms */
	ret = skl_pcode_request(dev_priv, GEN9_PCODE_SAGV_CONTROL,
				GEN9_SAGV_DISABLE,
				GEN9_SAGV_IS_DISABLED, GEN9_SAGV_IS_DISABLED,
				1);
	mutex_unlock(&dev_priv->rps.hw_lock);

	/*
	 * Some skl systems, pre-release machines in particular,
	 * don't actually have an SAGV.
	 */
	if (IS_SKYLAKE(dev_priv) && ret == -ENXIO) {
		DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
		dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED;
		return 0;
	} else if (ret < 0) {
		DRM_ERROR("Failed to disable the SAGV (%d)\n", ret);
		return ret;
	}

	dev_priv->sagv_status = I915_SAGV_DISABLED;
	return 0;
}

bool intel_can_enable_sagv(struct drm_atomic_state *state)
{
	struct drm_device *dev = state->dev;
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
	struct intel_crtc *crtc;
	struct intel_plane *plane;
	struct intel_crtc_state *cstate;
	enum pipe pipe;
	int level, latency;
	int sagv_block_time_us = IS_GEN9(dev_priv) ? 30 : 20;

	if (!intel_has_sagv(dev_priv))
		return false;

	/*
	 * SKL+ workaround: bspec recommends we disable the SAGV when we have
	 * more then one pipe enabled
	 *
	 * If there are no active CRTCs, no additional checks need be performed
	 */
	if (hweight32(intel_state->active_crtcs) == 0)
		return true;
	else if (hweight32(intel_state->active_crtcs) > 1)
		return false;

	/* Since we're now guaranteed to only have one active CRTC... */
	pipe = ffs(intel_state->active_crtcs) - 1;
	crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
	cstate = to_intel_crtc_state(crtc->base.state);

	if (crtc->base.state->adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
		return false;

	for_each_intel_plane_on_crtc(dev, crtc, plane) {
		struct skl_plane_wm *wm =
			&cstate->wm.skl.optimal.planes[plane->id];

		/* Skip this plane if it's not enabled */
		if (!wm->wm[0].plane_en)
			continue;

		/* Find the highest enabled wm level for this plane */
		for (level = ilk_wm_max_level(dev_priv);
		     !wm->wm[level].plane_en; --level)
		     { }

		latency = dev_priv->wm.skl_latency[level];

		if (skl_needs_memory_bw_wa(intel_state) &&
		    plane->base.state->fb->modifier ==
		    I915_FORMAT_MOD_X_TILED)
			latency += 15;

		/*
		 * If any of the planes on this pipe don't enable wm levels that
		 * incur memory latencies higher than sagv_block_time_us we
		 * can't enable the SAGV.
		 */
		if (latency < sagv_block_time_us)
			return false;
	}

	return true;
}

static void
skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
				   const struct intel_crtc_state *cstate,
				   struct skl_ddb_entry *alloc, /* out */
				   int *num_active /* out */)
{
	struct drm_atomic_state *state = cstate->base.state;
	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct drm_crtc *for_crtc = cstate->base.crtc;
	unsigned int pipe_size, ddb_size;
	int nth_active_pipe;

	if (WARN_ON(!state) || !cstate->base.active) {
		alloc->start = 0;
		alloc->end = 0;
		*num_active = hweight32(dev_priv->active_crtcs);
		return;
	}

	if (intel_state->active_pipe_changes)
		*num_active = hweight32(intel_state->active_crtcs);
	else
		*num_active = hweight32(dev_priv->active_crtcs);

	ddb_size = INTEL_INFO(dev_priv)->ddb_size;
	WARN_ON(ddb_size == 0);

	ddb_size -= 4; /* 4 blocks for bypass path allocation */

	/*
	 * If the state doesn't change the active CRTC's, then there's
	 * no need to recalculate; the existing pipe allocation limits
	 * should remain unchanged.  Note that we're safe from racing
	 * commits since any racing commit that changes the active CRTC
	 * list would need to grab _all_ crtc locks, including the one
	 * we currently hold.
	 */
	if (!intel_state->active_pipe_changes) {
		/*
		 * alloc may be cleared by clear_intel_crtc_state,
		 * copy from old state to be sure
		 */
		*alloc = to_intel_crtc_state(for_crtc->state)->wm.skl.ddb;
		return;
	}

	nth_active_pipe = hweight32(intel_state->active_crtcs &
				    (drm_crtc_mask(for_crtc) - 1));
	pipe_size = ddb_size / hweight32(intel_state->active_crtcs);
	alloc->start = nth_active_pipe * ddb_size / *num_active;
	alloc->end = alloc->start + pipe_size;
}

static unsigned int skl_cursor_allocation(int num_active)
{
	if (num_active == 1)
		return 32;

	return 8;
}

static void skl_ddb_entry_init_from_hw(struct skl_ddb_entry *entry, u32 reg)
{
	entry->start = reg & 0x3ff;
	entry->end = (reg >> 16) & 0x3ff;
	if (entry->end)
		entry->end += 1;
}

void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
			  struct skl_ddb_allocation *ddb /* out */)
{
	struct intel_crtc *crtc;

	memset(ddb, 0, sizeof(*ddb));

	for_each_intel_crtc(&dev_priv->drm, crtc) {
		enum intel_display_power_domain power_domain;
		enum plane_id plane_id;
		enum pipe pipe = crtc->pipe;

		power_domain = POWER_DOMAIN_PIPE(pipe);
		if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
			continue;

		for_each_plane_id_on_crtc(crtc, plane_id) {
			u32 val;

			if (plane_id != PLANE_CURSOR)
				val = I915_READ(PLANE_BUF_CFG(pipe, plane_id));
			else
				val = I915_READ(CUR_BUF_CFG(pipe));

			skl_ddb_entry_init_from_hw(&ddb->plane[pipe][plane_id], val);
		}

		intel_display_power_put(dev_priv, power_domain);
	}
}

/*
 * Determines the downscale amount of a plane for the purposes of watermark calculations.
 * The bspec defines downscale amount as:
 *
 * """
 * Horizontal down scale amount = maximum[1, Horizontal source size /
 *                                           Horizontal destination size]
 * Vertical down scale amount = maximum[1, Vertical source size /
 *                                         Vertical destination size]
 * Total down scale amount = Horizontal down scale amount *
 *                           Vertical down scale amount
 * """
 *
 * Return value is provided in 16.16 fixed point form to retain fractional part.
 * Caller should take care of dividing & rounding off the value.
 */
static uint_fixed_16_16_t
skl_plane_downscale_amount(const struct intel_crtc_state *cstate,
			   const struct intel_plane_state *pstate)
{
	struct intel_plane *plane = to_intel_plane(pstate->base.plane);
	uint32_t src_w, src_h, dst_w, dst_h;
	uint_fixed_16_16_t fp_w_ratio, fp_h_ratio;
	uint_fixed_16_16_t downscale_h, downscale_w;

	if (WARN_ON(!intel_wm_plane_visible(cstate, pstate)))
		return u32_to_fixed16(0);

	/* n.b., src is 16.16 fixed point, dst is whole integer */
	if (plane->id == PLANE_CURSOR) {
		/*
		 * Cursors only support 0/180 degree rotation,
		 * hence no need to account for rotation here.
		 */
		src_w = pstate->base.src_w >> 16;
		src_h = pstate->base.src_h >> 16;
		dst_w = pstate->base.crtc_w;
		dst_h = pstate->base.crtc_h;
	} else {
		/*
		 * Src coordinates are already rotated by 270 degrees for
		 * the 90/270 degree plane rotation cases (to match the
		 * GTT mapping), hence no need to account for rotation here.
		 */
		src_w = drm_rect_width(&pstate->base.src) >> 16;
		src_h = drm_rect_height(&pstate->base.src) >> 16;
		dst_w = drm_rect_width(&pstate->base.dst);
		dst_h = drm_rect_height(&pstate->base.dst);
	}

	fp_w_ratio = div_fixed16(src_w, dst_w);
	fp_h_ratio = div_fixed16(src_h, dst_h);
	downscale_w = max_fixed16(fp_w_ratio, u32_to_fixed16(1));
	downscale_h = max_fixed16(fp_h_ratio, u32_to_fixed16(1));

	return mul_fixed16(downscale_w, downscale_h);
}

static uint_fixed_16_16_t
skl_pipe_downscale_amount(const struct intel_crtc_state *crtc_state)
{
	uint_fixed_16_16_t pipe_downscale = u32_to_fixed16(1);

	if (!crtc_state->base.enable)
		return pipe_downscale;

	if (crtc_state->pch_pfit.enabled) {
		uint32_t src_w, src_h, dst_w, dst_h;
		uint32_t pfit_size = crtc_state->pch_pfit.size;
		uint_fixed_16_16_t fp_w_ratio, fp_h_ratio;
		uint_fixed_16_16_t downscale_h, downscale_w;

		src_w = crtc_state->pipe_src_w;
		src_h = crtc_state->pipe_src_h;
		dst_w = pfit_size >> 16;
		dst_h = pfit_size & 0xffff;

		if (!dst_w || !dst_h)
			return pipe_downscale;

		fp_w_ratio = div_fixed16(src_w, dst_w);
		fp_h_ratio = div_fixed16(src_h, dst_h);
		downscale_w = max_fixed16(fp_w_ratio, u32_to_fixed16(1));
		downscale_h = max_fixed16(fp_h_ratio, u32_to_fixed16(1));

		pipe_downscale = mul_fixed16(downscale_w, downscale_h);
	}

	return pipe_downscale;
}

int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc,
				  struct intel_crtc_state *cstate)
{
	struct drm_crtc_state *crtc_state = &cstate->base;
	struct drm_atomic_state *state = crtc_state->state;
	struct drm_plane *plane;
	const struct drm_plane_state *pstate;
	struct intel_plane_state *intel_pstate;
	int crtc_clock, dotclk;
	uint32_t pipe_max_pixel_rate;
	uint_fixed_16_16_t pipe_downscale;
	uint_fixed_16_16_t max_downscale = u32_to_fixed16(1);

	if (!cstate->base.enable)
		return 0;

	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) {
		uint_fixed_16_16_t plane_downscale;
		uint_fixed_16_16_t fp_9_div_8 = div_fixed16(9, 8);
		int bpp;

		if (!intel_wm_plane_visible(cstate,
					    to_intel_plane_state(pstate)))
			continue;

		if (WARN_ON(!pstate->fb))
			return -EINVAL;

		intel_pstate = to_intel_plane_state(pstate);
		plane_downscale = skl_plane_downscale_amount(cstate,
							     intel_pstate);
		bpp = pstate->fb->format->cpp[0] * 8;
		if (bpp == 64)
			plane_downscale = mul_fixed16(plane_downscale,
						      fp_9_div_8);

		max_downscale = max_fixed16(plane_downscale, max_downscale);
	}
	pipe_downscale = skl_pipe_downscale_amount(cstate);

	pipe_downscale = mul_fixed16(pipe_downscale, max_downscale);

	crtc_clock = crtc_state->adjusted_mode.crtc_clock;
	dotclk = to_intel_atomic_state(state)->cdclk.logical.cdclk;

	if (IS_GEMINILAKE(to_i915(intel_crtc->base.dev)))
		dotclk *= 2;

	pipe_max_pixel_rate = div_round_up_u32_fixed16(dotclk, pipe_downscale);

	if (pipe_max_pixel_rate < crtc_clock) {
		DRM_DEBUG_KMS("Max supported pixel clock with scaling exceeded\n");
		return -EINVAL;
	}

	return 0;
}

static unsigned int
skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
			     const struct drm_plane_state *pstate,
			     int y)
{
	struct intel_plane *plane = to_intel_plane(pstate->plane);
	struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate);
	uint32_t data_rate;
	uint32_t width = 0, height = 0;
	struct drm_framebuffer *fb;
	u32 format;
	uint_fixed_16_16_t down_scale_amount;

	if (!intel_pstate->base.visible)
		return 0;

	fb = pstate->fb;
	format = fb->format->format;

	if (plane->id == PLANE_CURSOR)
		return 0;
	if (y && format != DRM_FORMAT_NV12)
		return 0;

	/*
	 * Src coordinates are already rotated by 270 degrees for
	 * the 90/270 degree plane rotation cases (to match the
	 * GTT mapping), hence no need to account for rotation here.
	 */
	width = drm_rect_width(&intel_pstate->base.src) >> 16;
	height = drm_rect_height(&intel_pstate->base.src) >> 16;

	/* for planar format */
	if (format == DRM_FORMAT_NV12) {
		if (y)  /* y-plane data rate */
			data_rate = width * height *
				fb->format->cpp[0];
		else    /* uv-plane data rate */
			data_rate = (width / 2) * (height / 2) *
				fb->format->cpp[1];
	} else {
		/* for packed formats */
		data_rate = width * height * fb->format->cpp[0];
	}

	down_scale_amount = skl_plane_downscale_amount(cstate, intel_pstate);

	return mul_round_up_u32_fixed16(data_rate, down_scale_amount);
}

/*
 * We don't overflow 32 bits. Worst case is 3 planes enabled, each fetching
 * a 8192x4096@32bpp framebuffer:
 *   3 * 4096 * 8192  * 4 < 2^32
 */
static unsigned int
skl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate,
				 unsigned *plane_data_rate,
				 unsigned *plane_y_data_rate)
{
	struct drm_crtc_state *cstate = &intel_cstate->base;
	struct drm_atomic_state *state = cstate->state;
	struct drm_plane *plane;
	const struct drm_plane_state *pstate;
	unsigned int total_data_rate = 0;

	if (WARN_ON(!state))
		return 0;

	/* Calculate and cache data rate for each plane */
	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, cstate) {
		enum plane_id plane_id = to_intel_plane(plane)->id;
		unsigned int rate;

		/* packed/uv */
		rate = skl_plane_relative_data_rate(intel_cstate,
						    pstate, 0);
		plane_data_rate[plane_id] = rate;

		total_data_rate += rate;

		/* y-plane */
		rate = skl_plane_relative_data_rate(intel_cstate,
						    pstate, 1);
		plane_y_data_rate[plane_id] = rate;

		total_data_rate += rate;
	}

	return total_data_rate;
}

static uint16_t
skl_ddb_min_alloc(const struct drm_plane_state *pstate,
		  const int y)
{
	struct drm_framebuffer *fb = pstate->fb;
	struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate);
	uint32_t src_w, src_h;
	uint32_t min_scanlines = 8;
	uint8_t plane_bpp;

	if (WARN_ON(!fb))
		return 0;

	/* For packed formats, no y-plane, return 0 */
	if (y && fb->format->format != DRM_FORMAT_NV12)
		return 0;

	/* For Non Y-tile return 8-blocks */
	if (fb->modifier != I915_FORMAT_MOD_Y_TILED &&
	    fb->modifier != I915_FORMAT_MOD_Yf_TILED &&
	    fb->modifier != I915_FORMAT_MOD_Y_TILED_CCS &&
	    fb->modifier != I915_FORMAT_MOD_Yf_TILED_CCS)
		return 8;

	/*
	 * Src coordinates are already rotated by 270 degrees for
	 * the 90/270 degree plane rotation cases (to match the
	 * GTT mapping), hence no need to account for rotation here.
	 */
	src_w = drm_rect_width(&intel_pstate->base.src) >> 16;
	src_h = drm_rect_height(&intel_pstate->base.src) >> 16;

	/* Halve UV plane width and height for NV12 */
	if (fb->format->format == DRM_FORMAT_NV12 && !y) {
		src_w /= 2;
		src_h /= 2;
	}

	if (fb->format->format == DRM_FORMAT_NV12 && !y)
		plane_bpp = fb->format->cpp[1];
	else
		plane_bpp = fb->format->cpp[0];

	if (drm_rotation_90_or_270(pstate->rotation)) {
		switch (plane_bpp) {
		case 1:
			min_scanlines = 32;
			break;
		case 2:
			min_scanlines = 16;
			break;
		case 4:
			min_scanlines = 8;
			break;
		case 8:
			min_scanlines = 4;
			break;
		default:
			WARN(1, "Unsupported pixel depth %u for rotation",
			     plane_bpp);
			min_scanlines = 32;
		}
	}

	return DIV_ROUND_UP((4 * src_w * plane_bpp), 512) * min_scanlines/4 + 3;
}

static void
skl_ddb_calc_min(const struct intel_crtc_state *cstate, int num_active,
		 uint16_t *minimum, uint16_t *y_minimum)
{
	const struct drm_plane_state *pstate;
	struct drm_plane *plane;

	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, &cstate->base) {
		enum plane_id plane_id = to_intel_plane(plane)->id;

		if (plane_id == PLANE_CURSOR)
			continue;

		if (!pstate->visible)
			continue;

		minimum[plane_id] = skl_ddb_min_alloc(pstate, 0);
		y_minimum[plane_id] = skl_ddb_min_alloc(pstate, 1);
	}

	minimum[PLANE_CURSOR] = skl_cursor_allocation(num_active);
}

static int
skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
		      struct skl_ddb_allocation *ddb /* out */)
{
	struct drm_atomic_state *state = cstate->base.state;
	struct drm_crtc *crtc = cstate->base.crtc;
	struct drm_device *dev = crtc->dev;
	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
	enum pipe pipe = intel_crtc->pipe;
	struct skl_ddb_entry *alloc = &cstate->wm.skl.ddb;
	uint16_t alloc_size, start;
	uint16_t minimum[I915_MAX_PLANES] = {};
	uint16_t y_minimum[I915_MAX_PLANES] = {};
	unsigned int total_data_rate;
	enum plane_id plane_id;
	int num_active;
	unsigned plane_data_rate[I915_MAX_PLANES] = {};
	unsigned plane_y_data_rate[I915_MAX_PLANES] = {};
	uint16_t total_min_blocks = 0;

	/* Clear the partitioning for disabled planes. */
	memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe]));
	memset(ddb->y_plane[pipe], 0, sizeof(ddb->y_plane[pipe]));

	if (WARN_ON(!state))
		return 0;

	if (!cstate->base.active) {
		alloc->start = alloc->end = 0;
		return 0;
	}

	skl_ddb_get_pipe_allocation_limits(dev, cstate, alloc, &num_active);
	alloc_size = skl_ddb_entry_size(alloc);
	if (alloc_size == 0)
		return 0;

	skl_ddb_calc_min(cstate, num_active, minimum, y_minimum);

	/*
	 * 1. Allocate the mininum required blocks for each active plane
	 * and allocate the cursor, it doesn't require extra allocation
	 * proportional to the data rate.
	 */

	for_each_plane_id_on_crtc(intel_crtc, plane_id) {
		total_min_blocks += minimum[plane_id];
		total_min_blocks += y_minimum[plane_id];
	}

	if (total_min_blocks > alloc_size) {
		DRM_DEBUG_KMS("Requested display configuration exceeds system DDB limitations");
		DRM_DEBUG_KMS("minimum required %d/%d\n", total_min_blocks,
							alloc_size);
		return -EINVAL;
	}

	alloc_size -= total_min_blocks;
	ddb->plane[pipe][PLANE_CURSOR].start = alloc->end - minimum[PLANE_CURSOR];
	ddb->plane[pipe][PLANE_CURSOR].end = alloc->end;

	/*
	 * 2. Distribute the remaining space in proportion to the amount of
	 * data each plane needs to fetch from memory.
	 *
	 * FIXME: we may not allocate every single block here.
	 */
	total_data_rate = skl_get_total_relative_data_rate(cstate,
							   plane_data_rate,
							   plane_y_data_rate);
	if (total_data_rate == 0)
		return 0;

	start = alloc->start;
	for_each_plane_id_on_crtc(intel_crtc, plane_id) {
		unsigned int data_rate, y_data_rate;
		uint16_t plane_blocks, y_plane_blocks = 0;

		if (plane_id == PLANE_CURSOR)
			continue;

		data_rate = plane_data_rate[plane_id];

		/*
		 * allocation for (packed formats) or (uv-plane part of planar format):
		 * promote the expression to 64 bits to avoid overflowing, the
		 * result is < available as data_rate / total_data_rate < 1
		 */
		plane_blocks = minimum[plane_id];
		plane_blocks += div_u64((uint64_t)alloc_size * data_rate,
					total_data_rate);

		/* Leave disabled planes at (0,0) */
		if (data_rate) {
			ddb->plane[pipe][plane_id].start = start;
			ddb->plane[pipe][plane_id].end = start + plane_blocks;
		}

		start += plane_blocks;

		/*
		 * allocation for y_plane part of planar format:
		 */
		y_data_rate = plane_y_data_rate[plane_id];

		y_plane_blocks = y_minimum[plane_id];
		y_plane_blocks += div_u64((uint64_t)alloc_size * y_data_rate,
					total_data_rate);

		if (y_data_rate) {
			ddb->y_plane[pipe][plane_id].start = start;
			ddb->y_plane[pipe][plane_id].end = start + y_plane_blocks;
		}

		start += y_plane_blocks;
	}

	return 0;
}

/*
 * The max latency should be 257 (max the punit can code is 255 and we add 2us
 * for the read latency) and cpp should always be <= 8, so that
 * should allow pixel_rate up to ~2 GHz which seems sufficient since max
 * 2xcdclk is 1350 MHz and the pixel rate should never exceed that.
*/
static uint_fixed_16_16_t
skl_wm_method1(const struct drm_i915_private *dev_priv, uint32_t pixel_rate,
	       uint8_t cpp, uint32_t latency)
{
	uint32_t wm_intermediate_val;
	uint_fixed_16_16_t ret;

	if (latency == 0)
		return FP_16_16_MAX;

	wm_intermediate_val = latency * pixel_rate * cpp;
	ret = div_fixed16(wm_intermediate_val, 1000 * 512);

	if (INTEL_GEN(dev_priv) >= 10)
		ret = add_fixed16_u32(ret, 1);

	return ret;
}

static uint_fixed_16_16_t skl_wm_method2(uint32_t pixel_rate,
			uint32_t pipe_htotal,
			uint32_t latency,
			uint_fixed_16_16_t plane_blocks_per_line)
{
	uint32_t wm_intermediate_val;
	uint_fixed_16_16_t ret;

	if (latency == 0)
		return FP_16_16_MAX;

	wm_intermediate_val = latency * pixel_rate;
	wm_intermediate_val = DIV_ROUND_UP(wm_intermediate_val,
					   pipe_htotal * 1000);
	ret = mul_u32_fixed16(wm_intermediate_val, plane_blocks_per_line);
	return ret;
}

static uint_fixed_16_16_t
intel_get_linetime_us(struct intel_crtc_state *cstate)
{
	uint32_t pixel_rate;
	uint32_t crtc_htotal;
	uint_fixed_16_16_t linetime_us;

	if (!cstate->base.active)
		return u32_to_fixed16(0);

	pixel_rate = cstate->pixel_rate;

	if (WARN_ON(pixel_rate == 0))
		return u32_to_fixed16(0);

	crtc_htotal = cstate->base.adjusted_mode.crtc_htotal;
	linetime_us = div_fixed16(crtc_htotal * 1000, pixel_rate);

	return linetime_us;
}

static uint32_t
skl_adjusted_plane_pixel_rate(const struct intel_crtc_state *cstate,
			      const struct intel_plane_state *pstate)
{
	uint64_t adjusted_pixel_rate;
	uint_fixed_16_16_t downscale_amount;

	/* Shouldn't reach here on disabled planes... */
	if (WARN_ON(!intel_wm_plane_visible(cstate, pstate)))
		return 0;

	/*
	 * Adjusted plane pixel rate is just the pipe's adjusted pixel rate
	 * with additional adjustments for plane-specific scaling.
	 */
	adjusted_pixel_rate = cstate->pixel_rate;
	downscale_amount = skl_plane_downscale_amount(cstate, pstate);

	return mul_round_up_u32_fixed16(adjusted_pixel_rate,
					    downscale_amount);
}

static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
				struct intel_crtc_state *cstate,
				const struct intel_plane_state *intel_pstate,
				uint16_t ddb_allocation,
				int level,
				uint16_t *out_blocks, /* out */
				uint8_t *out_lines, /* out */
				bool *enabled /* out */)
{
	struct intel_plane *plane = to_intel_plane(intel_pstate->base.plane);
	const struct drm_plane_state *pstate = &intel_pstate->base;
	const struct drm_framebuffer *fb = pstate->fb;
	uint32_t latency = dev_priv->wm.skl_latency[level];
	uint_fixed_16_16_t method1, method2;
	uint_fixed_16_16_t plane_blocks_per_line;
	uint_fixed_16_16_t selected_result;
	uint32_t interm_pbpl;
	uint32_t plane_bytes_per_line;
	uint32_t res_blocks, res_lines;
	uint8_t cpp;
	uint32_t width = 0;
	uint32_t plane_pixel_rate;
	uint_fixed_16_16_t y_tile_minimum;
	uint32_t y_min_scanlines;
	struct intel_atomic_state *state =
		to_intel_atomic_state(cstate->base.state);
	bool apply_memory_bw_wa = skl_needs_memory_bw_wa(state);
	bool y_tiled, x_tiled;

	if (latency == 0 ||
	    !intel_wm_plane_visible(cstate, intel_pstate)) {
		*enabled = false;
		return 0;
	}

	y_tiled = fb->modifier == I915_FORMAT_MOD_Y_TILED ||
		  fb->modifier == I915_FORMAT_MOD_Yf_TILED ||
		  fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
		  fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
	x_tiled = fb->modifier == I915_FORMAT_MOD_X_TILED;

	/* Display WA #1141: kbl,cfl */
	if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) &&
	    dev_priv->ipc_enabled)
		latency += 4;

	if (apply_memory_bw_wa && x_tiled)
		latency += 15;

	if (plane->id == PLANE_CURSOR) {
		width = intel_pstate->base.crtc_w;
	} else {
		/*
		 * Src coordinates are already rotated by 270 degrees for
		 * the 90/270 degree plane rotation cases (to match the
		 * GTT mapping), hence no need to account for rotation here.
		 */
		width = drm_rect_width(&intel_pstate->base.src) >> 16;
	}

	cpp = (fb->format->format == DRM_FORMAT_NV12) ? fb->format->cpp[1] :
							fb->format->cpp[0];
	plane_pixel_rate = skl_adjusted_plane_pixel_rate(cstate, intel_pstate);

	if (drm_rotation_90_or_270(pstate->rotation)) {

		switch (cpp) {
		case 1:
			y_min_scanlines = 16;
			break;
		case 2:
			y_min_scanlines = 8;
			break;
		case 4:
			y_min_scanlines = 4;
			break;
		default:
			MISSING_CASE(cpp);
			return -EINVAL;
		}
	} else {
		y_min_scanlines = 4;
	}

	if (apply_memory_bw_wa)
		y_min_scanlines *= 2;

	plane_bytes_per_line = width * cpp;
	if (y_tiled) {
		interm_pbpl = DIV_ROUND_UP(plane_bytes_per_line *
					   y_min_scanlines, 512);

		if (INTEL_GEN(dev_priv) >= 10)
			interm_pbpl++;

		plane_blocks_per_line = div_fixed16(interm_pbpl,
							y_min_scanlines);
	} else if (x_tiled && INTEL_GEN(dev_priv) == 9) {
		interm_pbpl = DIV_ROUND_UP(plane_bytes_per_line, 512);
		plane_blocks_per_line = u32_to_fixed16(interm_pbpl);
	} else {
		interm_pbpl = DIV_ROUND_UP(plane_bytes_per_line, 512) + 1;
		plane_blocks_per_line = u32_to_fixed16(interm_pbpl);
	}

	method1 = skl_wm_method1(dev_priv, plane_pixel_rate, cpp, latency);
	method2 = skl_wm_method2(plane_pixel_rate,
				 cstate->base.adjusted_mode.crtc_htotal,
				 latency,
				 plane_blocks_per_line);

	y_tile_minimum = mul_u32_fixed16(y_min_scanlines,
					 plane_blocks_per_line);

	if (y_tiled) {
		selected_result = max_fixed16(method2, y_tile_minimum);
	} else {
		uint32_t linetime_us;

		linetime_us = fixed16_to_u32_round_up(
				intel_get_linetime_us(cstate));
		if ((cpp * cstate->base.adjusted_mode.crtc_htotal / 512 < 1) &&
		    (plane_bytes_per_line / 512 < 1))
			selected_result = method2;
		else if (ddb_allocation >=
			 fixed16_to_u32_round_up(plane_blocks_per_line))
			selected_result = min_fixed16(method1, method2);
		else if (latency >= linetime_us)
			selected_result = min_fixed16(method1, method2);
		else
			selected_result = method1;
	}

	res_blocks = fixed16_to_u32_round_up(selected_result) + 1;
	res_lines = div_round_up_fixed16(selected_result,
					 plane_blocks_per_line);

	/* Display WA #1125: skl,bxt,kbl,glk */
	if (level == 0 &&
	    (fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
	     fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS))
		res_blocks += fixed16_to_u32_round_up(y_tile_minimum);

	/* Display WA #1126: skl,bxt,kbl,glk */
	if (level >= 1 && level <= 7) {
		if (y_tiled) {
			res_blocks += fixed16_to_u32_round_up(y_tile_minimum);
			res_lines += y_min_scanlines;
		} else {
			res_blocks++;
		}
	}

	if (res_blocks >= ddb_allocation || res_lines > 31) {
		*enabled = false;

		/*
		 * If there are no valid level 0 watermarks, then we can't
		 * support this display configuration.
		 */
		if (level) {
			return 0;
		} else {
			struct drm_plane *plane = pstate->plane;

			DRM_DEBUG_KMS("Requested display configuration exceeds system watermark limitations\n");
			DRM_DEBUG_KMS("[PLANE:%d:%s] blocks required = %u/%u, lines required = %u/31\n",
				      plane->base.id, plane->name,
				      res_blocks, ddb_allocation, res_lines);
			return -EINVAL;
		}
	}

	*out_blocks = res_blocks;
	*out_lines = res_lines;
	*enabled = true;

	return 0;
}

static int
skl_compute_wm_levels(const struct drm_i915_private *dev_priv,
		      struct skl_ddb_allocation *ddb,
		      struct intel_crtc_state *cstate,
		      const struct intel_plane_state *intel_pstate,
		      struct skl_plane_wm *wm)
{
	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
	struct drm_plane *plane = intel_pstate->base.plane;
	struct intel_plane *intel_plane = to_intel_plane(plane);
	uint16_t ddb_blocks;
	enum pipe pipe = intel_crtc->pipe;
	int level, max_level = ilk_wm_max_level(dev_priv);
	int ret;

	if (WARN_ON(!intel_pstate->base.fb))
		return -EINVAL;

	ddb_blocks = skl_ddb_entry_size(&ddb->plane[pipe][intel_plane->id]);

	for (level = 0; level <= max_level; level++) {
		struct skl_wm_level *result = &wm->wm[level];

		ret = skl_compute_plane_wm(dev_priv,
					   cstate,
					   intel_pstate,
					   ddb_blocks,
					   level,
					   &result->plane_res_b,
					   &result->plane_res_l,
					   &result->plane_en);
		if (ret)
			return ret;
	}

	return 0;
}

static uint32_t
skl_compute_linetime_wm(struct intel_crtc_state *cstate)
{
	struct drm_atomic_state *state = cstate->base.state;
	struct drm_i915_private *dev_priv = to_i915(state->dev);
	uint_fixed_16_16_t linetime_us;
	uint32_t linetime_wm;

	linetime_us = intel_get_linetime_us(cstate);

	if (is_fixed16_zero(linetime_us))
		return 0;

	linetime_wm = fixed16_to_u32_round_up(mul_u32_fixed16(8, linetime_us));

	/* Display WA #1135: bxt. */
	if (IS_BROXTON(dev_priv) && dev_priv->ipc_enabled)
		linetime_wm = DIV_ROUND_UP(linetime_wm, 2);

	return linetime_wm;
}

static void skl_compute_transition_wm(struct intel_crtc_state *cstate,
				      struct skl_wm_level *trans_wm /* out */)
{
	if (!cstate->base.active)
		return;

	/* Until we know more, just disable transition WMs */
	trans_wm->plane_en = false;
}

static int skl_build_pipe_wm(struct intel_crtc_state *cstate,
			     struct skl_ddb_allocation *ddb,
			     struct skl_pipe_wm *pipe_wm)
{
	struct drm_device *dev = cstate->base.crtc->dev;
	struct drm_crtc_state *crtc_state = &cstate->base;
	const struct drm_i915_private *dev_priv = to_i915(dev);
	struct drm_plane *plane;
	const struct drm_plane_state *pstate;
	struct skl_plane_wm *wm;
	int ret;

	/*
	 * We'll only calculate watermarks for planes that are actually
	 * enabled, so make sure all other planes are set as disabled.
	 */
	memset(pipe_wm->planes, 0, sizeof(pipe_wm->planes));

	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) {
		const struct intel_plane_state *intel_pstate =
						to_intel_plane_state(pstate);
		enum plane_id plane_id = to_intel_plane(plane)->id;

		wm = &pipe_wm->planes[plane_id];

		ret = skl_compute_wm_levels(dev_priv, ddb, cstate,
					    intel_pstate, wm);
		if (ret)
			return ret;
		skl_compute_transition_wm(cstate, &wm->trans_wm);
	}
	pipe_wm->linetime = skl_compute_linetime_wm(cstate);

	return 0;
}

static void skl_ddb_entry_write(struct drm_i915_private *dev_priv,
				i915_reg_t reg,
				const struct skl_ddb_entry *entry)
{
	if (entry->end)
		I915_WRITE(reg, (entry->end - 1) << 16 | entry->start);
	else
		I915_WRITE(reg, 0);
}

static void skl_write_wm_level(struct drm_i915_private *dev_priv,
			       i915_reg_t reg,
			       const struct skl_wm_level *level)
{
	uint32_t val = 0;

	if (level->plane_en) {
		val |= PLANE_WM_EN;
		val |= level->plane_res_b;
		val |= level->plane_res_l << PLANE_WM_LINES_SHIFT;
	}

	I915_WRITE(reg, val);
}

static void skl_write_plane_wm(struct intel_crtc *intel_crtc,
			       const struct skl_plane_wm *wm,
			       const struct skl_ddb_allocation *ddb,
			       enum plane_id plane_id)
{
	struct drm_crtc *crtc = &intel_crtc->base;
	struct drm_device *dev = crtc->dev;
	struct drm_i915_private *dev_priv = to_i915(dev);
	int level, max_level = ilk_wm_max_level(dev_priv);
	enum pipe pipe = intel_crtc->pipe;

	for (level = 0; level <= max_level; level++) {
		skl_write_wm_level(dev_priv, PLANE_WM(pipe, plane_id, level),
				   &wm->wm[level]);
	}
	skl_write_wm_level(dev_priv, PLANE_WM_TRANS(pipe, plane_id),
			   &wm->trans_wm);

	skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id),
			    &ddb->plane[pipe][plane_id]);
	skl_ddb_entry_write(dev_priv, PLANE_NV12_BUF_CFG(pipe, plane_id),
			    &ddb->y_plane[pipe][plane_id]);
}

static void skl_write_cursor_wm(struct intel_crtc *intel_crtc,
				const struct skl_plane_wm *wm,
				const struct skl_ddb_allocation *ddb)
{
	struct drm_crtc *crtc = &intel_crtc->base;
	struct drm_device *dev = crtc->dev;
	struct drm_i915_private *dev_priv = to_i915(dev);
	int level, max_level = ilk_wm_max_level(dev_priv);
	enum pipe pipe = intel_crtc->pipe;

	for (level = 0; level <= max_level; level++) {
		skl_write_wm_level(dev_priv, CUR_WM(pipe, level),
				   &wm->wm[level]);
	}
	skl_write_wm_level(dev_priv, CUR_WM_TRANS(pipe), &wm->trans_wm);

	skl_ddb_entry_write(dev_priv, CUR_BUF_CFG(pipe),
			    &ddb->plane[pipe][PLANE_CURSOR]);
}

bool skl_wm_level_equals(const struct skl_wm_level *l1,
			 const struct skl_wm_level *l2)
{
	if (l1->plane_en != l2->plane_en)
		return false;

	/* If both planes aren't enabled, the rest shouldn't matter */
	if (!l1->plane_en)
		return true;

	return (l1->plane_res_l == l2->plane_res_l &&
		l1->plane_res_b == l2->plane_res_b);
}

static inline bool skl_ddb_entries_overlap(const struct skl_ddb_entry *a,
					   const struct skl_ddb_entry *b)
{
	return a->start < b->end && b->start < a->end;
}

bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry **entries,
				 const struct skl_ddb_entry *ddb,
				 int ignore)
{
	int i;

	for (i = 0; i < I915_MAX_PIPES; i++)
		if (i != ignore && entries[i] &&
		    skl_ddb_entries_overlap(ddb, entries[i]))
			return true;

	return false;
}

static int skl_update_pipe_wm(struct drm_crtc_state *cstate,
			      const struct skl_pipe_wm *old_pipe_wm,
			      struct skl_pipe_wm *pipe_wm, /* out */
			      struct skl_ddb_allocation *ddb, /* out */
			      bool *changed /* out */)
{
	struct intel_crtc_state *intel_cstate = to_intel_crtc_state(cstate);
	int ret;

	ret = skl_build_pipe_wm(intel_cstate, ddb, pipe_wm);
	if (ret)
		return ret;

	if (!memcmp(old_pipe_wm, pipe_wm, sizeof(*pipe_wm)))
		*changed = false;
	else
		*changed = true;

	return 0;
}

static uint32_t
pipes_modified(struct drm_atomic_state *state)
{
	struct drm_crtc *crtc;
	struct drm_crtc_state *cstate;
	uint32_t i, ret = 0;

	for_each_new_crtc_in_state(state, crtc, cstate, i)
		ret |= drm_crtc_mask(crtc);

	return ret;
}

static int
skl_ddb_add_affected_planes(struct intel_crtc_state *cstate)
{
	struct drm_atomic_state *state = cstate->base.state;
	struct drm_device *dev = state->dev;
	struct drm_crtc *crtc = cstate->base.crtc;
	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
	struct skl_ddb_allocation *new_ddb = &intel_state->wm_results.ddb;
	struct skl_ddb_allocation *cur_ddb = &dev_priv->wm.skl_hw.ddb;
	struct drm_plane_state *plane_state;
	struct drm_plane *plane;
	enum pipe pipe = intel_crtc->pipe;

	WARN_ON(!drm_atomic_get_existing_crtc_state(state, crtc));

	drm_for_each_plane_mask(plane, dev, cstate->base.plane_mask) {
		enum plane_id plane_id = to_intel_plane(plane)->id;

		if (skl_ddb_entry_equal(&cur_ddb->plane[pipe][plane_id],
					&new_ddb->plane[pipe][plane_id]) &&
		    skl_ddb_entry_equal(&cur_ddb->y_plane[pipe][plane_id],
					&new_ddb->y_plane[pipe][plane_id]))
			continue;

		plane_state = drm_atomic_get_plane_state(state, plane);
		if (IS_ERR(plane_state))
			return PTR_ERR(plane_state);
	}

	return 0;
}

static int
skl_compute_ddb(struct drm_atomic_state *state)
{
	struct drm_device *dev = state->dev;
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
	struct intel_crtc *intel_crtc;
	struct skl_ddb_allocation *ddb = &intel_state->wm_results.ddb;
	uint32_t realloc_pipes = pipes_modified(state);
	int ret;

	/*
	 * If this is our first atomic update following hardware readout,
	 * we can't trust the DDB that the BIOS programmed for us.  Let's
	 * pretend that all pipes switched active status so that we'll
	 * ensure a full DDB recompute.
	 */
	if (dev_priv->wm.distrust_bios_wm) {
		ret = drm_modeset_lock(&dev->mode_config.connection_mutex,
				       state->acquire_ctx);
		if (ret)
			return ret;

		intel_state->active_pipe_changes = ~0;

		/*
		 * We usually only initialize intel_state->active_crtcs if we
		 * we're doing a modeset; make sure this field is always
		 * initialized during the sanitization process that happens
		 * on the first commit too.
		 */
		if (!intel_state->modeset)
			intel_state->active_crtcs = dev_priv->active_crtcs;
	}

	/*
	 * If the modeset changes which CRTC's are active, we need to
	 * recompute the DDB allocation for *all* active pipes, even
	 * those that weren't otherwise being modified in any way by this
	 * atomic commit.  Due to the shrinking of the per-pipe allocations
	 * when new active CRTC's are added, it's possible for a pipe that
	 * we were already using and aren't changing at all here to suddenly
	 * become invalid if its DDB needs exceeds its new allocation.
	 *
	 * Note that if we wind up doing a full DDB recompute, we can't let
	 * any other display updates race with this transaction, so we need
	 * to grab the lock on *all* CRTC's.
	 */
	if (intel_state->active_pipe_changes) {
		realloc_pipes = ~0;
		intel_state->wm_results.dirty_pipes = ~0;
	}

	/*
	 * We're not recomputing for the pipes not included in the commit, so
	 * make sure we start with the current state.
	 */
	memcpy(ddb, &dev_priv->wm.skl_hw.ddb, sizeof(*ddb));

	for_each_intel_crtc_mask(dev, intel_crtc, realloc_pipes) {
		struct intel_crtc_state *cstate;

		cstate = intel_atomic_get_crtc_state(state, intel_crtc);
		if (IS_ERR(cstate))
			return PTR_ERR(cstate);

		ret = skl_allocate_pipe_ddb(cstate, ddb);
		if (ret)
			return ret;

		ret = skl_ddb_add_affected_planes(cstate);
		if (ret)
			return ret;
	}

	return 0;
}

static void
skl_copy_wm_for_pipe(struct skl_wm_values *dst,
		     struct skl_wm_values *src,
		     enum pipe pipe)
{
	memcpy(dst->ddb.y_plane[pipe], src->ddb.y_plane[pipe],
	       sizeof(dst->ddb.y_plane[pipe]));
	memcpy(dst->ddb.plane[pipe], src->ddb.plane[pipe],
	       sizeof(dst->ddb.plane[pipe]));
}

static void
skl_print_wm_changes(const struct drm_atomic_state *state)
{
	const struct drm_device *dev = state->dev;
	const struct drm_i915_private *dev_priv = to_i915(dev);
	const struct intel_atomic_state *intel_state =
		to_intel_atomic_state(state);
	const struct drm_crtc *crtc;
	const struct drm_crtc_state *cstate;
	const struct intel_plane *intel_plane;
	const struct skl_ddb_allocation *old_ddb = &dev_priv->wm.skl_hw.ddb;
	const struct skl_ddb_allocation *new_ddb = &intel_state->wm_results.ddb;
	int i;

	for_each_new_crtc_in_state(state, crtc, cstate, i) {
		const struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
		enum pipe pipe = intel_crtc->pipe;

		for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
			enum plane_id plane_id = intel_plane->id;
			const struct skl_ddb_entry *old, *new;

			old = &old_ddb->plane[pipe][plane_id];
			new = &new_ddb->plane[pipe][plane_id];

			if (skl_ddb_entry_equal(old, new))
				continue;

			DRM_DEBUG_ATOMIC("[PLANE:%d:%s] ddb (%d - %d) -> (%d - %d)\n",
					 intel_plane->base.base.id,
					 intel_plane->base.name,
					 old->start, old->end,
					 new->start, new->end);
		}
	}
}

static int
skl_compute_wm(struct drm_atomic_state *state)
{
	struct drm_crtc *crtc;
	struct drm_crtc_state *cstate;
	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
	struct skl_wm_values *results = &intel_state->wm_results;
	struct drm_device *dev = state->dev;
	struct skl_pipe_wm *pipe_wm;
	bool changed = false;
	int ret, i;

	/*
	 * When we distrust bios wm we always need to recompute to set the
	 * expected DDB allocations for each CRTC.
	 */
	if (to_i915(dev)->wm.distrust_bios_wm)
		changed = true;

	/*
	 * If this transaction isn't actually touching any CRTC's, don't
	 * bother with watermark calculation.  Note that if we pass this
	 * test, we're guaranteed to hold at least one CRTC state mutex,
	 * which means we can safely use values like dev_priv->active_crtcs
	 * since any racing commits that want to update them would need to
	 * hold _all_ CRTC state mutexes.
	 */
	for_each_new_crtc_in_state(state, crtc, cstate, i)
		changed = true;

	if (!changed)
		return 0;

	/* Clear all dirty flags */
	results->dirty_pipes = 0;

	ret = skl_compute_ddb(state);
	if (ret)
		return ret;

	/*
	 * Calculate WM's for all pipes that are part of this transaction.
	 * Note that the DDB allocation above may have added more CRTC's that
	 * weren't otherwise being modified (and set bits in dirty_pipes) if
	 * pipe allocations had to change.
	 *
	 * FIXME:  Now that we're doing this in the atomic check phase, we
	 * should allow skl_update_pipe_wm() to return failure in cases where
	 * no suitable watermark values can be found.
	 */
	for_each_new_crtc_in_state(state, crtc, cstate, i) {
		struct intel_crtc_state *intel_cstate =
			to_intel_crtc_state(cstate);
		const struct skl_pipe_wm *old_pipe_wm =
			&to_intel_crtc_state(crtc->state)->wm.skl.optimal;

		pipe_wm = &intel_cstate->wm.skl.optimal;
		ret = skl_update_pipe_wm(cstate, old_pipe_wm, pipe_wm,
					 &results->ddb, &changed);
		if (ret)
			return ret;

		if (changed)
			results->dirty_pipes |= drm_crtc_mask(crtc);

		if ((results->dirty_pipes & drm_crtc_mask(crtc)) == 0)
			/* This pipe's WM's did not change */
			continue;

		intel_cstate->update_wm_pre = true;
	}

	skl_print_wm_changes(state);

	return 0;
}

static void skl_atomic_update_crtc_wm(struct intel_atomic_state *state,
				      struct intel_crtc_state *cstate)
{
	struct intel_crtc *crtc = to_intel_crtc(cstate->base.crtc);
	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
	struct skl_pipe_wm *pipe_wm = &cstate->wm.skl.optimal;
	const struct skl_ddb_allocation *ddb = &state->wm_results.ddb;
	enum pipe pipe = crtc->pipe;
	enum plane_id plane_id;

	if (!(state->wm_results.dirty_pipes & drm_crtc_mask(&crtc->base)))
		return;

	I915_WRITE(PIPE_WM_LINETIME(pipe), pipe_wm->linetime);

	for_each_plane_id_on_crtc(crtc, plane_id) {
		if (plane_id != PLANE_CURSOR)
			skl_write_plane_wm(crtc, &pipe_wm->planes[plane_id],
					   ddb, plane_id);
		else
			skl_write_cursor_wm(crtc, &pipe_wm->planes[plane_id],
					    ddb);
	}
}

static void skl_initial_wm(struct intel_atomic_state *state,
			   struct intel_crtc_state *cstate)
{
	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
	struct drm_device *dev = intel_crtc->base.dev;
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct skl_wm_values *results = &state->wm_results;
	struct skl_wm_values *hw_vals = &dev_priv->wm.skl_hw;
	enum pipe pipe = intel_crtc->pipe;

	if ((results->dirty_pipes & drm_crtc_mask(&intel_crtc->base)) == 0)
		return;

	mutex_lock(&dev_priv->wm.wm_mutex);

	if (cstate->base.active_changed)
		skl_atomic_update_crtc_wm(state, cstate);

	skl_copy_wm_for_pipe(hw_vals, results, pipe);

	mutex_unlock(&dev_priv->wm.wm_mutex);
}

static void ilk_compute_wm_config(struct drm_device *dev,
				  struct intel_wm_config *config)
{
	struct intel_crtc *crtc;

	/* Compute the currently _active_ config */
	for_each_intel_crtc(dev, crtc) {
		const struct intel_pipe_wm *wm = &crtc->wm.active.ilk;

		if (!wm->pipe_enabled)
			continue;

		config->sprites_enabled |= wm->sprites_enabled;
		config->sprites_scaled |= wm->sprites_scaled;
		config->num_pipes_active++;
	}
}

static void ilk_program_watermarks(struct drm_i915_private *dev_priv)
{
	struct drm_device *dev = &dev_priv->drm;
	struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm;
	struct ilk_wm_maximums max;
	struct intel_wm_config config = {};
	struct ilk_wm_values results = {};
	enum intel_ddb_partitioning partitioning;

	ilk_compute_wm_config(dev, &config);

	ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_1_2, &max);
	ilk_wm_merge(dev, &config, &max, &lp_wm_1_2);

	/* 5/6 split only in single pipe config on IVB+ */
	if (INTEL_GEN(dev_priv) >= 7 &&
	    config.num_pipes_active == 1 && config.sprites_enabled) {
		ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_5_6, &max);
		ilk_wm_merge(dev, &config, &max, &lp_wm_5_6);

		best_lp_wm = ilk_find_best_result(dev, &lp_wm_1_2, &lp_wm_5_6);
	} else {
		best_lp_wm = &lp_wm_1_2;
	}

	partitioning = (best_lp_wm == &lp_wm_1_2) ?
		       INTEL_DDB_PART_1_2 : INTEL_DDB_PART_5_6;

	ilk_compute_wm_results(dev, best_lp_wm, partitioning, &results);

	ilk_write_wm_values(dev_priv, &results);
}

static void ilk_initial_watermarks(struct intel_atomic_state *state,
				   struct intel_crtc_state *cstate)
{
	struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);

	mutex_lock(&dev_priv->wm.wm_mutex);
	intel_crtc->wm.active.ilk = cstate->wm.ilk.intermediate;
	ilk_program_watermarks(dev_priv);
	mutex_unlock(&dev_priv->wm.wm_mutex);
}

static void ilk_optimize_watermarks(struct intel_atomic_state *state,
				    struct intel_crtc_state *cstate)
{
	struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);

	mutex_lock(&dev_priv->wm.wm_mutex);
	if (cstate->wm.need_postvbl_update) {
		intel_crtc->wm.active.ilk = cstate->wm.ilk.optimal;
		ilk_program_watermarks(dev_priv);
	}
	mutex_unlock(&dev_priv->wm.wm_mutex);
}

static inline void skl_wm_level_from_reg_val(uint32_t val,
					     struct skl_wm_level *level)
{
	level->plane_en = val & PLANE_WM_EN;
	level->plane_res_b = val & PLANE_WM_BLOCKS_MASK;
	level->plane_res_l = (val >> PLANE_WM_LINES_SHIFT) &
		PLANE_WM_LINES_MASK;
}

void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc,
			      struct skl_pipe_wm *out)
{
	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
	enum pipe pipe = intel_crtc->pipe;
	int level, max_level;
	enum plane_id plane_id;
	uint32_t val;

	max_level = ilk_wm_max_level(dev_priv);

	for_each_plane_id_on_crtc(intel_crtc, plane_id) {
		struct skl_plane_wm *wm = &out->planes[plane_id];

		for (level = 0; level <= max_level; level++) {
			if (plane_id != PLANE_CURSOR)
				val = I915_READ(PLANE_WM(pipe, plane_id, level));
			else
				val = I915_READ(CUR_WM(pipe, level));

			skl_wm_level_from_reg_val(val, &wm->wm[level]);
		}

		if (plane_id != PLANE_CURSOR)
			val = I915_READ(PLANE_WM_TRANS(pipe, plane_id));
		else
			val = I915_READ(CUR_WM_TRANS(pipe));

		skl_wm_level_from_reg_val(val, &wm->trans_wm);
	}

	if (!intel_crtc->active)
		return;

	out->linetime = I915_READ(PIPE_WM_LINETIME(pipe));
}

void skl_wm_get_hw_state(struct drm_device *dev)
{
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct skl_wm_values *hw = &dev_priv->wm.skl_hw;
	struct skl_ddb_allocation *ddb = &dev_priv->wm.skl_hw.ddb;
	struct drm_crtc *crtc;
	struct intel_crtc *intel_crtc;
	struct intel_crtc_state *cstate;

	skl_ddb_get_hw_state(dev_priv, ddb);
	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
		intel_crtc = to_intel_crtc(crtc);
		cstate = to_intel_crtc_state(crtc->state);

		skl_pipe_wm_get_hw_state(crtc, &cstate->wm.skl.optimal);

		if (intel_crtc->active)
			hw->dirty_pipes |= drm_crtc_mask(crtc);
	}

	if (dev_priv->active_crtcs) {
		/* Fully recompute DDB on first atomic commit */
		dev_priv->wm.distrust_bios_wm = true;
	} else {
		/* Easy/common case; just sanitize DDB now if everything off */
		memset(ddb, 0, sizeof(*ddb));
	}
}

static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc)
{
	struct drm_device *dev = crtc->dev;
	struct drm_i915_private *dev_priv = to_i915(dev);
	struct ilk_wm_values *hw = &dev_priv->wm.hw;
	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
	struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
	struct intel_pipe_wm *active = &cstate->wm.ilk.optimal;
	enum pipe pipe = intel_crtc->pipe;
	static const i915_reg_t wm0_pipe_reg[] = {
		[PIPE_A] = WM0_PIPEA_ILK,
		[PIPE_B] = WM0_PIPEB_ILK,
		[PIPE_C] = WM0_PIPEC_IVB,
	};

	hw->wm_pipe[pipe] = I915_READ(wm0_pipe_reg[pipe]);
	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
		hw->wm_linetime[pipe] = I915_READ(PIPE_WM_LINETIME(pipe));

	memset(active, 0, sizeof(*active));

	active->pipe_enabled = intel_crtc->active;

	if (active->pipe_enabled) {
		u32 tmp = hw->wm_pipe[pipe];

		/*
		 * For active pipes LP0 watermark is marked as
		 * enabled, and LP1+ watermaks as disabled since
		 * we can't really reverse compute them in case
		 * multiple pipes are active.
		 */
		active->wm[0].enable = true;
		active->wm[0].pri_val = (tmp & WM0_PIPE_PLANE_MASK) >> WM0_PIPE_PLANE_SHIFT;
		active->wm[0].spr_val = (tmp & WM0_PIPE_SPRITE_MASK) >> WM0_PIPE_SPRITE_SHIFT;
		active->wm[0].cur_val = tmp & WM0_PIPE_CURSOR_MASK;
		active->linetime = hw->wm_linetime[pipe];
	} else {
		int level, max_level = ilk_wm_max_level(dev_priv);

		/*
		 * For inactive pipes, all watermark levels
		 * should be marked as enabled but zeroed,
		 * which is what we'd compute them to.
		 */
		for (level = 0; level <= max_level; level++)
			active->wm[level].enable = true;
	}

	intel_crtc->wm.active.ilk = *active;
}

#define _FW_WM(value, plane) \
	(((value) & DSPFW_ ## plane ## _MASK) >> DSPFW_ ## plane ## _SHIFT)
#define _FW_WM_VLV(value, plane) \
	(((value) & DSPFW_ ## plane ## _MASK_VLV) >> DSPFW_ ## plane ## _SHIFT)

static void g4x_read_wm_values(struct drm_i915_private *dev_priv,
			       struct g4x_wm_values *wm)
{
	uint32_t tmp;

	tmp = I915_READ(DSPFW1);
	wm->sr.plane = _FW_WM(tmp, SR);
	wm->pipe[PIPE_B].plane[PLANE_CURSOR] = _FW_WM(tmp, CURSORB);
	wm->pipe[PIPE_B].plane[PLANE_PRIMARY] = _FW_WM(tmp, PLANEB);
	wm->pipe[PIPE_A].plane[PLANE_PRIMARY] = _FW_WM(tmp, PLANEA);

	tmp = I915_READ(DSPFW2);
	wm->fbc_en = tmp & DSPFW_FBC_SR_EN;
	wm->sr.fbc = _FW_WM(tmp, FBC_SR);
	wm->hpll.fbc = _FW_WM(tmp, FBC_HPLL_SR);
	wm->pipe[PIPE_B].plane[PLANE_SPRITE0] = _FW_WM(tmp, SPRITEB);
	wm->pipe[PIPE_A].plane[PLANE_CURSOR] = _FW_WM(tmp, CURSORA);
	wm->pipe[PIPE_A].plane[PLANE_SPRITE0] = _FW_WM(tmp, SPRITEA);

	tmp = I915_READ(DSPFW3);
	wm->hpll_en = tmp & DSPFW_HPLL_SR_EN;
	wm->sr.cursor = _FW_WM(tmp, CURSOR_SR);
	wm->hpll.cursor = _FW_WM(tmp, HPLL_CURSOR);
	wm->hpll.plane = _FW_WM(tmp, HPLL_SR);
}

static void vlv_read_wm_values(struct drm_i915_private *dev_priv,
			       struct vlv_wm_values *wm)
{
	enum pipe pipe;
	uint32_t tmp;

	for_each_pipe(dev_priv, pipe) {
		tmp = I915_READ(VLV_DDL(pipe));

		wm->ddl[pipe].plane[PLANE_PRIMARY] =
			(tmp >> DDL_PLANE_SHIFT) & (DDL_PRECISION_HIGH | DRAIN_LATENCY_MASK);
		wm->ddl[pipe].plane[PLANE_CURSOR] =
			(tmp >> DDL_CURSOR_SHIFT) & (DDL_PRECISION_HIGH | DRAIN_LATENCY_MASK);
		wm->ddl[pipe].plane[PLANE_SPRITE0] =
			(tmp >> DDL_SPRITE_SHIFT(0)) & (DDL_PRECISION_HIGH | DRAIN_LATENCY_MASK);
		wm->ddl[pipe].plane[PLANE_SPRITE1] =
			(tmp >> DDL_SPRITE_SHIFT(1)) & (DDL_PRECISION_HIGH | DRAIN_LATENCY_MASK);
	}

	tmp = I915_READ(DSPFW1);
	wm->sr.plane = _FW_WM(tmp, SR);
	wm->pipe[PIPE_B].plane[PLANE_CURSOR] = _FW_WM(tmp, CURSORB);
	wm->pipe[PIPE_B].plane[PLANE_PRIMARY] = _FW_WM_VLV(tmp, PLANEB);
	wm->pipe[PIPE_A].plane[PLANE_PRIMARY] = _FW_WM_VLV(tmp, PLANEA);

	tmp = I915_READ(DSPFW2);
	wm->pipe[PIPE_A].plane[PLANE_SPRITE1] = _FW_WM_VLV(tmp, SPRITEB);
	wm->pipe[PIPE_A].plane[PLANE_CURSOR] = _FW_WM(tmp, CURSORA);
	wm->pipe[PIPE_A].plane[PLANE_SPRITE0] = _FW_WM_VLV(tmp, SPRITEA);

	tmp = I915_READ(DSPFW3);
	wm->sr.cursor = _FW_WM(tmp, CURSOR_SR);

	if (IS_CHERRYVIEW(dev_priv)) {
		tmp = I915_READ(DSPFW7_CHV);