aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/xsave.c
blob: cdc6cf90307800abb83f1b4b516ba389212c3dd0 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
/*
 * xsave/xrstor support.
 *
 * Author: Suresh Siddha <suresh.b.siddha@intel.com>
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/bootmem.h>
#include <linux/compat.h>
#include <linux/cpu.h>
#include <asm/i387.h>
#include <asm/fpu-internal.h>
#include <asm/sigframe.h>
#include <asm/tlbflush.h>
#include <asm/xcr.h>

/*
 * Supported feature mask by the CPU and the kernel.
 */
u64 pcntxt_mask;

/*
 * Represents init state for the supported extended state.
 */
struct xsave_struct *init_xstate_buf;

static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
static unsigned int *xstate_offsets, *xstate_sizes;
static unsigned int xstate_comp_offsets[sizeof(pcntxt_mask)*8];
static unsigned int xstate_features;

/*
 * If a processor implementation discern that a processor state component is
 * in its initialized state it may modify the corresponding bit in the
 * xsave_hdr.xstate_bv as '0', with out modifying the corresponding memory
 * layout in the case of xsaveopt. While presenting the xstate information to
 * the user, we always ensure that the memory layout of a feature will be in
 * the init state if the corresponding header bit is zero. This is to ensure
 * that the user doesn't see some stale state in the memory layout during
 * signal handling, debugging etc.
 */
void __sanitize_i387_state(struct task_struct *tsk)
{
	struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
	int feature_bit = 0x2;
	u64 xstate_bv;

	if (!fx)
		return;

	xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;

	/*
	 * None of the feature bits are in init state. So nothing else
	 * to do for us, as the memory layout is up to date.
	 */
	if ((xstate_bv & pcntxt_mask) == pcntxt_mask)
		return;

	/*
	 * FP is in init state
	 */
	if (!(xstate_bv & XSTATE_FP)) {
		fx->cwd = 0x37f;
		fx->swd = 0;
		fx->twd = 0;
		fx->fop = 0;
		fx->rip = 0;
		fx->rdp = 0;
		memset(&fx->st_space[0], 0, 128);
	}

	/*
	 * SSE is in init state
	 */
	if (!(xstate_bv & XSTATE_SSE))
		memset(&fx->xmm_space[0], 0, 256);

	xstate_bv = (pcntxt_mask & ~xstate_bv) >> 2;

	/*
	 * Update all the other memory layouts for which the corresponding
	 * header bit is in the init state.
	 */
	while (xstate_bv) {
		if (xstate_bv & 0x1) {
			int offset = xstate_offsets[feature_bit];
			int size = xstate_sizes[feature_bit];

			memcpy(((void *) fx) + offset,
			       ((void *) init_xstate_buf) + offset,
			       size);
		}

		xstate_bv >>= 1;
		feature_bit++;
	}
}

/*
 * Check for the presence of extended state information in the
 * user fpstate pointer in the sigcontext.
 */
static inline int check_for_xstate(struct i387_fxsave_struct __user *buf,
				   void __user *fpstate,
				   struct _fpx_sw_bytes *fx_sw)
{
	int min_xstate_size = sizeof(struct i387_fxsave_struct) +
			      sizeof(struct xsave_hdr_struct);
	unsigned int magic2;

	if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
		return -1;

	/* Check for the first magic field and other error scenarios. */
	if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
	    fx_sw->xstate_size < min_xstate_size ||
	    fx_sw->xstate_size > xstate_size ||
	    fx_sw->xstate_size > fx_sw->extended_size)
		return -1;

	/*
	 * Check for the presence of second magic word at the end of memory
	 * layout. This detects the case where the user just copied the legacy
	 * fpstate layout with out copying the extended state information
	 * in the memory layout.
	 */
	if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
	    || magic2 != FP_XSTATE_MAGIC2)
		return -1;

	return 0;
}

/*
 * Signal frame handlers.
 */
static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
{
	if (use_fxsr()) {
		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
		struct user_i387_ia32_struct env;
		struct _fpstate_ia32 __user *fp = buf;

		convert_from_fxsr(&env, tsk);

		if (__copy_to_user(buf, &env, sizeof(env)) ||
		    __put_user(xsave->i387.swd, &fp->status) ||
		    __put_user(X86_FXSR_MAGIC, &fp->magic))
			return -1;
	} else {
		struct i387_fsave_struct __user *fp = buf;
		u32 swd;
		if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
			return -1;
	}

	return 0;
}

static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
{
	struct xsave_struct __user *x = buf;
	struct _fpx_sw_bytes *sw_bytes;
	u32 xstate_bv;
	int err;

	/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
	sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
	err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));

	if (!use_xsave())
		return err;

	err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));

	/*
	 * Read the xstate_bv which we copied (directly from the cpu or
	 * from the state in task struct) to the user buffers.
	 */
	err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);

	/*
	 * For legacy compatible, we always set FP/SSE bits in the bit
	 * vector while saving the state to the user context. This will
	 * enable us capturing any changes(during sigreturn) to
	 * the FP/SSE bits by the legacy applications which don't touch
	 * xstate_bv in the xsave header.
	 *
	 * xsave aware apps can change the xstate_bv in the xsave
	 * header as well as change any contents in the memory layout.
	 * xrestore as part of sigreturn will capture all the changes.
	 */
	xstate_bv |= XSTATE_FPSSE;

	err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);

	return err;
}

static inline int save_user_xstate(struct xsave_struct __user *buf)
{
	int err;

	if (use_xsave())
		err = xsave_user(buf);
	else if (use_fxsr())
		err = fxsave_user((struct i387_fxsave_struct __user *) buf);
	else
		err = fsave_user((struct i387_fsave_struct __user *) buf);

	if (unlikely(err) && __clear_user(buf, xstate_size))
		err = -EFAULT;
	return err;
}

/*
 * Save the fpu, extended register state to the user signal frame.
 *
 * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
 *  state is copied.
 *  'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
 *
 *	buf == buf_fx for 64-bit frames and 32-bit fsave frame.
 *	buf != buf_fx for 32-bit frames with fxstate.
 *
 * If the fpu, extended register state is live, save the state directly
 * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
 * copy the thread's fpu state to the user frame starting at 'buf_fx'.
 *
 * If this is a 32-bit frame with fxstate, put a fsave header before
 * the aligned state at 'buf_fx'.
 *
 * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
 * indicating the absence/presence of the extended state to the user.
 */
int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
{
	struct xsave_struct *xsave = &current->thread.fpu.state->xsave;
	struct task_struct *tsk = current;
	int ia32_fxstate = (buf != buf_fx);

	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
			 config_enabled(CONFIG_IA32_EMULATION));

	if (!access_ok(VERIFY_WRITE, buf, size))
		return -EACCES;

	if (!static_cpu_has(X86_FEATURE_FPU))
		return fpregs_soft_get(current, NULL, 0,
			sizeof(struct user_i387_ia32_struct), NULL,
			(struct _fpstate_ia32 __user *) buf) ? -1 : 1;

	if (user_has_fpu()) {
		/* Save the live register state to the user directly. */
		if (save_user_xstate(buf_fx))
			return -1;
		/* Update the thread's fxstate to save the fsave header. */
		if (ia32_fxstate)
			fpu_fxsave(&tsk->thread.fpu);
	} else {
		sanitize_i387_state(tsk);
		if (__copy_to_user(buf_fx, xsave, xstate_size))
			return -1;
	}

	/* Save the fsave header for the 32-bit frames. */
	if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
		return -1;

	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
		return -1;

	return 0;
}

static inline void
sanitize_restored_xstate(struct task_struct *tsk,
			 struct user_i387_ia32_struct *ia32_env,
			 u64 xstate_bv, int fx_only)
{
	struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
	struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr;

	if (use_xsave()) {
		/* These bits must be zero. */
		memset(xsave_hdr->reserved, 0, 48);

		/*
		 * Init the state that is not present in the memory
		 * layout and not enabled by the OS.
		 */
		if (fx_only)
			xsave_hdr->xstate_bv = XSTATE_FPSSE;
		else
			xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv);
	}

	if (use_fxsr()) {
		/*
		 * mscsr reserved bits must be masked to zero for security
		 * reasons.
		 */
		xsave->i387.mxcsr &= mxcsr_feature_mask;

		convert_to_fxsr(tsk, ia32_env);
	}
}

/*
 * Restore the extended state if present. Otherwise, restore the FP/SSE state.
 */
static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only)
{
	if (use_xsave()) {
		if ((unsigned long)buf % 64 || fx_only) {
			u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE;
			xrstor_state(init_xstate_buf, init_bv);
			return fxrstor_user(buf);
		} else {
			u64 init_bv = pcntxt_mask & ~xbv;
			if (unlikely(init_bv))
				xrstor_state(init_xstate_buf, init_bv);
			return xrestore_user(buf, xbv);
		}
	} else if (use_fxsr()) {
		return fxrstor_user(buf);
	} else
		return frstor_user(buf);
}

int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
{
	int ia32_fxstate = (buf != buf_fx);
	struct task_struct *tsk = current;
	int state_size = xstate_size;
	u64 xstate_bv = 0;
	int fx_only = 0;

	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
			 config_enabled(CONFIG_IA32_EMULATION));

	if (!buf) {
		drop_init_fpu(tsk);
		return 0;
	}

	if (!access_ok(VERIFY_READ, buf, size))
		return -EACCES;

	if (!used_math() && init_fpu(tsk))
		return -1;

	if (!static_cpu_has(X86_FEATURE_FPU))
		return fpregs_soft_set(current, NULL,
				       0, sizeof(struct user_i387_ia32_struct),
				       NULL, buf) != 0;

	if (use_xsave()) {
		struct _fpx_sw_bytes fx_sw_user;
		if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
			/*
			 * Couldn't find the extended state information in the
			 * memory layout. Restore just the FP/SSE and init all
			 * the other extended state.
			 */
			state_size = sizeof(struct i387_fxsave_struct);
			fx_only = 1;
		} else {
			state_size = fx_sw_user.xstate_size;
			xstate_bv = fx_sw_user.xstate_bv;
		}
	}

	if (ia32_fxstate) {
		/*
		 * For 32-bit frames with fxstate, copy the user state to the
		 * thread's fpu state, reconstruct fxstate from the fsave
		 * header. Sanitize the copied state etc.
		 */
		struct fpu *fpu = &tsk->thread.fpu;
		struct user_i387_ia32_struct env;
		int err = 0;

		/*
		 * Drop the current fpu which clears used_math(). This ensures
		 * that any context-switch during the copy of the new state,
		 * avoids the intermediate state from getting restored/saved.
		 * Thus avoiding the new restored state from getting corrupted.
		 * We will be ready to restore/save the state only after
		 * set_used_math() is again set.
		 */
		drop_fpu(tsk);

		if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) ||
		    __copy_from_user(&env, buf, sizeof(env))) {
			fpu_finit(fpu);
			err = -1;
		} else {
			sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
		}

		set_used_math();
		if (use_eager_fpu()) {
			preempt_disable();
			math_state_restore();
			preempt_enable();
		}

		return err;
	} else {
		/*
		 * For 64-bit frames and 32-bit fsave frames, restore the user
		 * state to the registers directly (with exceptions handled).
		 */
		user_fpu_begin();
		if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) {
			drop_init_fpu(tsk);
			return -1;
		}
	}

	return 0;
}

/*
 * Prepare the SW reserved portion of the fxsave memory layout, indicating
 * the presence of the extended state information in the memory layout
 * pointed by the fpstate pointer in the sigcontext.
 * This will be saved when ever the FP and extended state context is
 * saved on the user stack during the signal handler delivery to the user.
 */
static void prepare_fx_sw_frame(void)
{
	int fsave_header_size = sizeof(struct i387_fsave_struct);
	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;

	if (config_enabled(CONFIG_X86_32))
		size += fsave_header_size;

	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
	fx_sw_reserved.extended_size = size;
	fx_sw_reserved.xstate_bv = pcntxt_mask;
	fx_sw_reserved.xstate_size = xstate_size;

	if (config_enabled(CONFIG_IA32_EMULATION)) {
		fx_sw_reserved_ia32 = fx_sw_reserved;
		fx_sw_reserved_ia32.extended_size += fsave_header_size;
	}
}

/*
 * Enable the extended processor state save/restore feature
 */
static inline void xstate_enable(void)
{
	cr4_set_bits(X86_CR4_OSXSAVE);
	xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask);
}

/*
 * Record the offsets and sizes of different state managed by the xsave
 * memory layout.
 */
static void __init setup_xstate_features(void)
{
	int eax, ebx, ecx, edx, leaf = 0x2;

	xstate_features = fls64(pcntxt_mask);
	xstate_offsets = alloc_bootmem(xstate_features * sizeof(int));
	xstate_sizes = alloc_bootmem(xstate_features * sizeof(int));

	do {
		cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx);

		if (eax == 0)
			break;

		xstate_offsets[leaf] = ebx;
		xstate_sizes[leaf] = eax;

		leaf++;
	} while (1);
}

/*
 * This function sets up offsets and sizes of all extended states in
 * xsave area. This supports both standard format and compacted format
 * of the xsave aread.
 *
 * Input: void
 * Output: void
 */
void setup_xstate_comp(void)
{
	unsigned int xstate_comp_sizes[sizeof(pcntxt_mask)*8];
	int i;

	/*
	 * The FP xstates and SSE xstates are legacy states. They are always
	 * in the fixed offsets in the xsave area in either compacted form
	 * or standard form.
	 */
	xstate_comp_offsets[0] = 0;
	xstate_comp_offsets[1] = offsetof(struct i387_fxsave_struct, xmm_space);

	if (!cpu_has_xsaves) {
		for (i = 2; i < xstate_features; i++) {
			if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
				xstate_comp_offsets[i] = xstate_offsets[i];
				xstate_comp_sizes[i] = xstate_sizes[i];
			}
		}
		return;
	}

	xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE;

	for (i = 2; i < xstate_features; i++) {
		if (test_bit(i, (unsigned long *)&pcntxt_mask))
			xstate_comp_sizes[i] = xstate_sizes[i];
		else
			xstate_comp_sizes[i] = 0;

		if (i > 2)
			xstate_comp_offsets[i] = xstate_comp_offsets[i-1]
					+ xstate_comp_sizes[i-1];

	}
}

/*
 * setup the xstate image representing the init state
 */
static void __init setup_init_fpu_buf(void)
{
	/*
	 * Setup init_xstate_buf to represent the init state of
	 * all the features managed by the xsave
	 */
	init_xstate_buf = alloc_bootmem_align(xstate_size,
					      __alignof__(struct xsave_struct));
	fx_finit(&init_xstate_buf->i387);

	if (!cpu_has_xsave)
		return;

	setup_xstate_features();

	if (cpu_has_xsaves) {
		init_xstate_buf->xsave_hdr.xcomp_bv =
						(u64)1 << 63 | pcntxt_mask;
		init_xstate_buf->xsave_hdr.xstate_bv = pcntxt_mask;
	}

	/*
	 * Init all the features state with header_bv being 0x0
	 */
	xrstor_state_booting(init_xstate_buf, -1);
	/*
	 * Dump the init state again. This is to identify the init state
	 * of any feature which is not represented by all zero's.
	 */
	xsave_state_booting(init_xstate_buf, -1);
}

static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
static int __init eager_fpu_setup(char *s)
{
	if (!strcmp(s, "on"))
		eagerfpu = ENABLE;
	else if (!strcmp(s, "off"))
		eagerfpu = DISABLE;
	else if (!strcmp(s, "auto"))
		eagerfpu = AUTO;
	return 1;
}
__setup("eagerfpu=", eager_fpu_setup);


/*
 * Calculate total size of enabled xstates in XCR0/pcntxt_mask.
 */
static void __init init_xstate_size(void)
{
	unsigned int eax, ebx, ecx, edx;
	int i;

	if (!cpu_has_xsaves) {
		cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
		xstate_size = ebx;
		return;
	}

	xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE;
	for (i = 2; i < 64; i++) {
		if (test_bit(i, (unsigned long *)&pcntxt_mask)) {
			cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx);
			xstate_size += eax;
		}
	}
}

/*
 * Enable and initialize the xsave feature.
 */
static void __init xstate_enable_boot_cpu(void)
{
	unsigned int eax, ebx, ecx, edx;

	if (boot_cpu_data.cpuid_level < XSTATE_CPUID) {
		WARN(1, KERN_ERR "XSTATE_CPUID missing\n");
		return;
	}

	cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx);
	pcntxt_mask = eax + ((u64)edx << 32);

	if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) {
		pr_err("FP/SSE not shown under xsave features 0x%llx\n",
		       pcntxt_mask);
		BUG();
	}

	/*
	 * Support only the state known to OS.
	 */
	pcntxt_mask = pcntxt_mask & XCNTXT_MASK;

	xstate_enable();

	/*
	 * Recompute the context size for enabled features
	 */
	init_xstate_size();

	update_regset_xstate_info(xstate_size, pcntxt_mask);
	prepare_fx_sw_frame();
	setup_init_fpu_buf();

	/* Auto enable eagerfpu for xsaveopt */
	if (cpu_has_xsaveopt && eagerfpu != DISABLE)
		eagerfpu = ENABLE;

	if (pcntxt_mask & XSTATE_EAGER) {
		if (eagerfpu == DISABLE) {
			pr_err("eagerfpu not present, disabling some xstate features: 0x%llx\n",
					pcntxt_mask & XSTATE_EAGER);
			pcntxt_mask &= ~XSTATE_EAGER;
		} else {
			eagerfpu = ENABLE;
		}
	}

	pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x using %s\n",
		pcntxt_mask, xstate_size,
		cpu_has_xsaves ? "compacted form" : "standard form");
}

/*
 * For the very first instance, this calls xstate_enable_boot_cpu();
 * for all subsequent instances, this calls xstate_enable().
 *
 * This is somewhat obfuscated due to the lack of powerful enough
 * overrides for the section checks.
 */
void xsave_init(void)
{
	static __refdata void (*next_func)(void) = xstate_enable_boot_cpu;
	void (*this_func)(void);

	if (!cpu_has_xsave)
		return;

	this_func = next_func;
	next_func = xstate_enable;
	this_func();
}

static inline void __init eager_fpu_init_bp(void)
{
	current->thread.fpu.state =
	    alloc_bootmem_align(xstate_size, __alignof__(struct xsave_struct));
	if (!init_xstate_buf)
		setup_init_fpu_buf();
}

void eager_fpu_init(void)
{
	static __refdata void (*boot_func)(void) = eager_fpu_init_bp;

	clear_used_math();
	current_thread_info()->status = 0;

	if (eagerfpu == ENABLE)
		setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);

	if (!cpu_has_eager_fpu) {
		stts();
		return;
	}

	if (boot_func) {
		boot_func();
		boot_func = NULL;
	}

	/*
	 * This is same as math_state_restore(). But use_xsave() is
	 * not yet patched to use math_state_restore().
	 */
	init_fpu(current);
	__thread_fpu_begin(current);
	if (cpu_has_xsave)
		xrstor_state(init_xstate_buf, -1);
	else
		fxrstor_checking(&init_xstate_buf->i387);
}

/*
 * Given the xsave area and a state inside, this function returns the
 * address of the state.
 *
 * This is the API that is called to get xstate address in either
 * standard format or compacted format of xsave area.
 *
 * Inputs:
 *	xsave: base address of the xsave area;
 *	xstate: state which is defined in xsave.h (e.g. XSTATE_FP, XSTATE_SSE,
 *	etc.)
 * Output:
 *	address of the state in the xsave area.
 */
void *get_xsave_addr(struct xsave_struct *xsave, int xstate)
{
	int feature = fls64(xstate) - 1;
	if (!test_bit(feature, (unsigned long *)&pcntxt_mask))
		return NULL;

	return (void *)xsave + xstate_comp_offsets[feature];
}
EXPORT_SYMBOL_GPL(get_xsave_addr);
rb_node; while (n) { struct vmap_area *va; va = rb_entry(n, struct vmap_area, rb_node); if (addr < va->va_start) n = n->rb_left; else if (addr > va->va_start) n = n->rb_right; else return va; } return NULL; } static void __insert_vmap_area(struct vmap_area *va) { struct rb_node **p = &vmap_area_root.rb_node; struct rb_node *parent = NULL; struct rb_node *tmp; while (*p) { struct vmap_area *tmp; parent = *p; tmp = rb_entry(parent, struct vmap_area, rb_node); if (va->va_start < tmp->va_end) p = &(*p)->rb_left; else if (va->va_end > tmp->va_start) p = &(*p)->rb_right; else BUG(); } rb_link_node(&va->rb_node, parent, p); rb_insert_color(&va->rb_node, &vmap_area_root); /* address-sort this list so it is usable like the vmlist */ tmp = rb_prev(&va->rb_node); if (tmp) { struct vmap_area *prev; prev = rb_entry(tmp, struct vmap_area, rb_node); list_add_rcu(&va->list, &prev->list); } else list_add_rcu(&va->list, &vmap_area_list); } static void purge_vmap_area_lazy(void); /* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. */ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int node, gfp_t gfp_mask) { struct vmap_area *va; struct rb_node *n; unsigned long addr; int purged = 0; BUG_ON(!size); BUG_ON(size & ~PAGE_MASK); va = kmalloc_node(sizeof(struct vmap_area), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!va)) return ERR_PTR(-ENOMEM); retry: addr = ALIGN(vstart, align); spin_lock(&vmap_area_lock); if (addr + size - 1 < addr) goto overflow; /* XXX: could have a last_hole cache */ n = vmap_area_root.rb_node; if (n) { struct vmap_area *first = NULL; do { struct vmap_area *tmp; tmp = rb_entry(n, struct vmap_area, rb_node); if (tmp->va_end >= addr) { if (!first && tmp->va_start < addr + size) first = tmp; n = n->rb_left; } else { first = tmp; n = n->rb_right; } } while (n); if (!first) goto found; if (first->va_end < addr) { n = rb_next(&first->rb_node); if (n) first = rb_entry(n, struct vmap_area, rb_node); else goto found; } while (addr + size > first->va_start && addr + size <= vend) { addr = ALIGN(first->va_end + PAGE_SIZE, align); if (addr + size - 1 < addr) goto overflow; n = rb_next(&first->rb_node); if (n) first = rb_entry(n, struct vmap_area, rb_node); else goto found; } } found: if (addr + size > vend) { overflow: spin_unlock(&vmap_area_lock); if (!purged) { purge_vmap_area_lazy(); purged = 1; goto retry; } if (printk_ratelimit()) printk(KERN_WARNING "vmap allocation for size %lu failed: " "use vmalloc=<size> to increase size.\n", size); kfree(va); return ERR_PTR(-EBUSY); } BUG_ON(addr & (align-1)); va->va_start = addr; va->va_end = addr + size; va->flags = 0; __insert_vmap_area(va); spin_unlock(&vmap_area_lock); return va; } static void rcu_free_va(struct rcu_head *head) { struct vmap_area *va = container_of(head, struct vmap_area, rcu_head); kfree(va); } static void __free_vmap_area(struct vmap_area *va) { BUG_ON(RB_EMPTY_NODE(&va->rb_node)); rb_erase(&va->rb_node, &vmap_area_root); RB_CLEAR_NODE(&va->rb_node); list_del_rcu(&va->list); call_rcu(&va->rcu_head, rcu_free_va); } /* * Free a region of KVA allocated by alloc_vmap_area */ static void free_vmap_area(struct vmap_area *va) { spin_lock(&vmap_area_lock); __free_vmap_area(va); spin_unlock(&vmap_area_lock); } /* * Clear the pagetable entries of a given vmap_area */ static void unmap_vmap_area(struct vmap_area *va) { vunmap_page_range(va->va_start, va->va_end); } static void vmap_debug_free_range(unsigned long start, unsigned long end) { /* * Unmap page tables and force a TLB flush immediately if * CONFIG_DEBUG_PAGEALLOC is set. This catches use after free * bugs similarly to those in linear kernel virtual address * space after a page has been freed. * * All the lazy freeing logic is still retained, in order to * minimise intrusiveness of this debugging feature. * * This is going to be *slow* (linear kernel virtual address * debugging doesn't do a broadcast TLB flush so it is a lot * faster). */ #ifdef CONFIG_DEBUG_PAGEALLOC vunmap_page_range(start, end); flush_tlb_kernel_range(start, end); #endif } /* * lazy_max_pages is the maximum amount of virtual address space we gather up * before attempting to purge with a TLB flush. * * There is a tradeoff here: a larger number will cover more kernel page tables * and take slightly longer to purge, but it will linearly reduce the number of * global TLB flushes that must be performed. It would seem natural to scale * this number up linearly with the number of CPUs (because vmapping activity * could also scale linearly with the number of CPUs), however it is likely * that in practice, workloads might be constrained in other ways that mean * vmap activity will not scale linearly with CPUs. Also, I want to be * conservative and not introduce a big latency on huge systems, so go with * a less aggressive log scale. It will still be an improvement over the old * code, and it will be simple to change the scale factor if we find that it * becomes a problem on bigger systems. */ static unsigned long lazy_max_pages(void) { unsigned int log; log = fls(num_online_cpus()); return log * (32UL * 1024 * 1024 / PAGE_SIZE); } static atomic_t vmap_lazy_nr = ATOMIC_INIT(0); /* * Purges all lazily-freed vmap areas. * * If sync is 0 then don't purge if there is already a purge in progress. * If force_flush is 1, then flush kernel TLBs between *start and *end even * if we found no lazy vmap areas to unmap (callers can use this to optimise * their own TLB flushing). * Returns with *start = min(*start, lowest purged address) * *end = max(*end, highest purged address) */ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, int sync, int force_flush) { static DEFINE_SPINLOCK(purge_lock); LIST_HEAD(valist); struct vmap_area *va; struct vmap_area *n_va; int nr = 0; /* * If sync is 0 but force_flush is 1, we'll go sync anyway but callers * should not expect such behaviour. This just simplifies locking for * the case that isn't actually used at the moment anyway. */ if (!sync && !force_flush) { if (!spin_trylock(&purge_lock)) return; } else spin_lock(&purge_lock); rcu_read_lock(); list_for_each_entry_rcu(va, &vmap_area_list, list) { if (va->flags & VM_LAZY_FREE) { if (va->va_start < *start) *start = va->va_start; if (va->va_end > *end) *end = va->va_end; nr += (va->va_end - va->va_start) >> PAGE_SHIFT; unmap_vmap_area(va); list_add_tail(&va->purge_list, &valist); va->flags |= VM_LAZY_FREEING; va->flags &= ~VM_LAZY_FREE; } } rcu_read_unlock(); if (nr) { BUG_ON(nr > atomic_read(&vmap_lazy_nr)); atomic_sub(nr, &vmap_lazy_nr); } if (nr || force_flush) flush_tlb_kernel_range(*start, *end); if (nr) { spin_lock(&vmap_area_lock); list_for_each_entry_safe(va, n_va, &valist, purge_list) __free_vmap_area(va); spin_unlock(&vmap_area_lock); } spin_unlock(&purge_lock); } /* * Kick off a purge of the outstanding lazy areas. Don't bother if somebody * is already purging. */ static void try_purge_vmap_area_lazy(void) { unsigned long start = ULONG_MAX, end = 0; __purge_vmap_area_lazy(&start, &end, 0, 0); } /* * Kick off a purge of the outstanding lazy areas. */ static void purge_vmap_area_lazy(void) { unsigned long start = ULONG_MAX, end = 0; __purge_vmap_area_lazy(&start, &end, 1, 0); } /* * Free and unmap a vmap area, caller ensuring flush_cache_vunmap had been * called for the correct range previously. */ static void free_unmap_vmap_area_noflush(struct vmap_area *va) { va->flags |= VM_LAZY_FREE; atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr); if (unlikely(atomic_read(&vmap_lazy_nr) > lazy_max_pages())) try_purge_vmap_area_lazy(); } /* * Free and unmap a vmap area */ static void free_unmap_vmap_area(struct vmap_area *va) { flush_cache_vunmap(va->va_start, va->va_end); free_unmap_vmap_area_noflush(va); } static struct vmap_area *find_vmap_area(unsigned long addr) { struct vmap_area *va; spin_lock(&vmap_area_lock); va = __find_vmap_area(addr); spin_unlock(&vmap_area_lock); return va; } static void free_unmap_vmap_area_addr(unsigned long addr) { struct vmap_area *va; va = find_vmap_area(addr); BUG_ON(!va); free_unmap_vmap_area(va); } /*** Per cpu kva allocator ***/ /* * vmap space is limited especially on 32 bit architectures. Ensure there is * room for at least 16 percpu vmap blocks per CPU. */ /* * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able * to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess * instead (we just need a rough idea) */ #if BITS_PER_LONG == 32 #define VMALLOC_SPACE (128UL*1024*1024) #else #define VMALLOC_SPACE (128UL*1024*1024*1024) #endif #define VMALLOC_PAGES (VMALLOC_SPACE / PAGE_SIZE) #define VMAP_MAX_ALLOC BITS_PER_LONG /* 256K with 4K pages */ #define VMAP_BBMAP_BITS_MAX 1024 /* 4MB with 4K pages */ #define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2) #define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */ #define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */ #define VMAP_BBMAP_BITS VMAP_MIN(VMAP_BBMAP_BITS_MAX, \ VMAP_MAX(VMAP_BBMAP_BITS_MIN, \ VMALLOC_PAGES / NR_CPUS / 16)) #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) static bool vmap_initialized __read_mostly = false; struct vmap_block_queue { spinlock_t lock; struct list_head free; struct list_head dirty; unsigned int nr_dirty; }; struct vmap_block { spinlock_t lock; struct vmap_area *va; struct vmap_block_queue *vbq; unsigned long free, dirty; DECLARE_BITMAP(alloc_map, VMAP_BBMAP_BITS); DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS); union { struct list_head free_list; struct rcu_head rcu_head; }; }; /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); /* * Radix tree of vmap blocks, indexed by address, to quickly find a vmap block * in the free path. Could get rid of this if we change the API to return a * "cookie" from alloc, to be passed to free. But no big deal yet. */ static DEFINE_SPINLOCK(vmap_block_tree_lock); static RADIX_TREE(vmap_block_tree, GFP_ATOMIC); /* * We should probably have a fallback mechanism to allocate virtual memory * out of partially filled vmap blocks. However vmap block sizing should be * fairly reasonable according to the vmalloc size, so it shouldn't be a * big problem. */ static unsigned long addr_to_vb_idx(unsigned long addr) { addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1); addr /= VMAP_BLOCK_SIZE; return addr; } static struct vmap_block *new_vmap_block(gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; struct vmap_area *va; unsigned long vb_idx; int node, err; node = numa_node_id(); vb = kmalloc_node(sizeof(struct vmap_block), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!vb)) return ERR_PTR(-ENOMEM); va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, VMALLOC_START, VMALLOC_END, node, gfp_mask); if (unlikely(IS_ERR(va))) { kfree(vb); return ERR_PTR(PTR_ERR(va)); } err = radix_tree_preload(gfp_mask); if (unlikely(err)) { kfree(vb); free_vmap_area(va); return ERR_PTR(err); } spin_lock_init(&vb->lock); vb->va = va; vb->free = VMAP_BBMAP_BITS; vb->dirty = 0; bitmap_zero(vb->alloc_map, VMAP_BBMAP_BITS); bitmap_zero(vb->dirty_map, VMAP_BBMAP_BITS); INIT_LIST_HEAD(&vb->free_list); vb_idx = addr_to_vb_idx(va->va_start); spin_lock(&vmap_block_tree_lock); err = radix_tree_insert(&vmap_block_tree, vb_idx, vb); spin_unlock(&vmap_block_tree_lock); BUG_ON(err); radix_tree_preload_end(); vbq = &get_cpu_var(vmap_block_queue); vb->vbq = vbq; spin_lock(&vbq->lock); list_add(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); put_cpu_var(vmap_cpu_blocks); return vb; } static void rcu_free_vb(struct rcu_head *head) { struct vmap_block *vb = container_of(head, struct vmap_block, rcu_head); kfree(vb); } static void free_vmap_block(struct vmap_block *vb) { struct vmap_block *tmp; unsigned long vb_idx; BUG_ON(!list_empty(&vb->free_list)); vb_idx = addr_to_vb_idx(vb->va->va_start); spin_lock(&vmap_block_tree_lock); tmp = radix_tree_delete(&vmap_block_tree, vb_idx); spin_unlock(&vmap_block_tree_lock); BUG_ON(tmp != vb); free_unmap_vmap_area_noflush(vb->va); call_rcu(&vb->rcu_head, rcu_free_vb); } static void *vb_alloc(unsigned long size, gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; unsigned long addr = 0; unsigned int order; BUG_ON(size & ~PAGE_MASK); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); order = get_order(size); again: rcu_read_lock(); vbq = &get_cpu_var(vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { int i; spin_lock(&vb->lock); i = bitmap_find_free_region(vb->alloc_map, VMAP_BBMAP_BITS, order); if (i >= 0) { addr = vb->va->va_start + (i << PAGE_SHIFT); BUG_ON(addr_to_vb_idx(addr) != addr_to_vb_idx(vb->va->va_start)); vb->free -= 1UL << order; if (vb->free == 0) { spin_lock(&vbq->lock); list_del_init(&vb->free_list); spin_unlock(&vbq->lock); } spin_unlock(&vb->lock); break; } spin_unlock(&vb->lock); } put_cpu_var(vmap_cpu_blocks); rcu_read_unlock(); if (!addr) { vb = new_vmap_block(gfp_mask); if (IS_ERR(vb)) return vb; goto again; } return (void *)addr; } static void vb_free(const void *addr, unsigned long size) { unsigned long offset; unsigned long vb_idx; unsigned int order; struct vmap_block *vb; BUG_ON(size & ~PAGE_MASK); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); flush_cache_vunmap((unsigned long)addr, (unsigned long)addr + size); order = get_order(size); offset = (unsigned long)addr & (VMAP_BLOCK_SIZE - 1); vb_idx = addr_to_vb_idx((unsigned long)addr); rcu_read_lock(); vb = radix_tree_lookup(&vmap_block_tree, vb_idx); rcu_read_unlock(); BUG_ON(!vb); spin_lock(&vb->lock); bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order); vb->dirty += 1UL << order; if (vb->dirty == VMAP_BBMAP_BITS) { BUG_ON(vb->free || !list_empty(&vb->free_list)); spin_unlock(&vb->lock); free_vmap_block(vb); } else spin_unlock(&vb->lock); } /** * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer * * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily * to amortize TLB flushing overheads. What this means is that any page you * have now, may, in a former life, have been mapped into kernel virtual * address by the vmap layer and so there might be some CPUs with TLB entries * still referencing that page (additional to the regular 1:1 kernel mapping). * * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can * be sure that none of the pages we have control over will have any aliases * from the vmap layer. */ void vm_unmap_aliases(void) { unsigned long start = ULONG_MAX, end = 0; int cpu; int flush = 0; if (unlikely(!vmap_initialized)) return; for_each_possible_cpu(cpu) { struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); struct vmap_block *vb; rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { int i; spin_lock(&vb->lock); i = find_first_bit(vb->dirty_map, VMAP_BBMAP_BITS); while (i < VMAP_BBMAP_BITS) { unsigned long s, e; int j; j = find_next_zero_bit(vb->dirty_map, VMAP_BBMAP_BITS, i); s = vb->va->va_start + (i << PAGE_SHIFT); e = vb->va->va_start + (j << PAGE_SHIFT); vunmap_page_range(s, e); flush = 1; if (s < start) start = s; if (e > end) end = e; i = j; i = find_next_bit(vb->dirty_map, VMAP_BBMAP_BITS, i); } spin_unlock(&vb->lock); } rcu_read_unlock(); } __purge_vmap_area_lazy(&start, &end, 1, flush); } EXPORT_SYMBOL_GPL(vm_unmap_aliases); /** * vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram * @mem: the pointer returned by vm_map_ram * @count: the count passed to that vm_map_ram call (cannot unmap partial) */ void vm_unmap_ram(const void *mem, unsigned int count) { unsigned long size = count << PAGE_SHIFT; unsigned long addr = (unsigned long)mem; BUG_ON(!addr); BUG_ON(addr < VMALLOC_START); BUG_ON(addr > VMALLOC_END); BUG_ON(addr & (PAGE_SIZE-1)); debug_check_no_locks_freed(mem, size); vmap_debug_free_range(addr, addr+size); if (likely(count <= VMAP_MAX_ALLOC)) vb_free(mem, size); else free_unmap_vmap_area_addr(addr); } EXPORT_SYMBOL(vm_unmap_ram); /** * vm_map_ram - map pages linearly into kernel virtual address (vmalloc space) * @pages: an array of pointers to the pages to be mapped * @count: number of pages * @node: prefer to allocate data structures on this node * @prot: memory protection to use. PAGE_KERNEL for regular RAM * * Returns: a pointer to the address that has been mapped, or %NULL on failure */ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot) { unsigned long size = count << PAGE_SHIFT; unsigned long addr; void *mem; if (likely(count <= VMAP_MAX_ALLOC)) { mem = vb_alloc(size, GFP_KERNEL); if (IS_ERR(mem)) return NULL; addr = (unsigned long)mem; } else { struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, VMALLOC_START, VMALLOC_END, node, GFP_KERNEL); if (IS_ERR(va)) return NULL; addr = va->va_start; mem = (void *)addr; } if (vmap_page_range(addr, addr + size, prot, pages) < 0) { vm_unmap_ram(mem, count); return NULL; } return mem; } EXPORT_SYMBOL(vm_map_ram); /** * vm_area_register_early - register vmap area early during boot * @vm: vm_struct to register * @align: requested alignment * * This function is used to register kernel vm area before * vmalloc_init() is called. @vm->size and @vm->flags should contain * proper values on entry and other fields should be zero. On return, * vm->addr contains the allocated address. * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING. */ void __init vm_area_register_early(struct vm_struct *vm, size_t align) { static size_t vm_init_off __initdata; unsigned long addr; addr = ALIGN(VMALLOC_START + vm_init_off, align); vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START; vm->addr = (void *)addr; vm->next = vmlist; vmlist = vm; } void __init vmalloc_init(void) { struct vmap_area *va; struct vm_struct *tmp; int i; for_each_possible_cpu(i) { struct vmap_block_queue *vbq; vbq = &per_cpu(vmap_block_queue, i); spin_lock_init(&vbq->lock); INIT_LIST_HEAD(&vbq->free); INIT_LIST_HEAD(&vbq->dirty); vbq->nr_dirty = 0; } /* Import existing vmlist entries. */ for (tmp = vmlist; tmp; tmp = tmp->next) { va = kzalloc(sizeof(struct vmap_area), GFP_NOWAIT); va->flags = tmp->flags | VM_VM_AREA; va->va_start = (unsigned long)tmp->addr; va->va_end = va->va_start + tmp->size; __insert_vmap_area(va); } vmap_initialized = true; } /** * map_kernel_range_noflush - map kernel VM area with the specified pages * @addr: start of the VM area to map * @size: size of the VM area to map * @prot: page protection flags to use * @pages: pages to map * * Map PFN_UP(@size) pages at @addr. The VM area @addr and @size * specify should have been allocated using get_vm_area() and its * friends. * * NOTE: * This function does NOT do any cache flushing. The caller is * responsible for calling flush_cache_vmap() on to-be-mapped areas * before calling this function. * * RETURNS: * The number of pages mapped on success, -errno on failure. */ int map_kernel_range_noflush(unsigned long addr, unsigned long size, pgprot_t prot, struct page **pages) { return vmap_page_range_noflush(addr, addr + size, prot, pages); } /** * unmap_kernel_range_noflush - unmap kernel VM area * @addr: start of the VM area to unmap * @size: size of the VM area to unmap * * Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size * specify should have been allocated using get_vm_area() and its * friends. * * NOTE: * This function does NOT do any cache flushing. The caller is * responsible for calling flush_cache_vunmap() on to-be-mapped areas * before calling this function and flush_tlb_kernel_range() after. */ void unmap_kernel_range_noflush(unsigned long addr, unsigned long size) { vunmap_page_range(addr, addr + size); } /** * unmap_kernel_range - unmap kernel VM area and flush cache and TLB * @addr: start of the VM area to unmap * @size: size of the VM area to unmap * * Similar to unmap_kernel_range_noflush() but flushes vcache before * the unmapping and tlb after. */ void unmap_kernel_range(unsigned long addr, unsigned long size) { unsigned long end = addr + size; flush_cache_vunmap(addr, end); vunmap_page_range(addr, end); flush_tlb_kernel_range(addr, end); } int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages) { unsigned long addr = (unsigned long)area->addr; unsigned long end = addr + area->size - PAGE_SIZE; int err; err = vmap_page_range(addr, end, prot, *pages); if (err > 0) { *pages += err; err = 0; } return err; } EXPORT_SYMBOL_GPL(map_vm_area); /*** Old vmalloc interfaces ***/ DEFINE_RWLOCK(vmlist_lock); struct vm_struct *vmlist; static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, void *caller) { static struct vmap_area *va; struct vm_struct *area; struct vm_struct *tmp, **p; unsigned long align = 1; BUG_ON(in_interrupt()); if (flags & VM_IOREMAP) { int bit = fls(size); if (bit > IOREMAP_MAX_ORDER) bit = IOREMAP_MAX_ORDER; else if (bit < PAGE_SHIFT) bit = PAGE_SHIFT; align = 1ul << bit; } size = PAGE_ALIGN(size); if (unlikely(!size)) return NULL; area = kmalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!area)) return NULL; /* * We always allocate a guard page. */ size += PAGE_SIZE; va = alloc_vmap_area(size, align, start, end, node, gfp_mask); if (IS_ERR(va)) { kfree(area); return NULL; } area->flags = flags; area->addr = (void *)va->va_start; area->size = size; area->pages = NULL; area->nr_pages = 0; area->phys_addr = 0; area->caller = caller; va->private = area; va->flags |= VM_VM_AREA; write_lock(&vmlist_lock); for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { if (tmp->addr >= area->addr) break; } area->next = *p; *p = area; write_unlock(&vmlist_lock); return area; } struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, unsigned long start, unsigned long end) { return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL, __builtin_return_address(0)); } EXPORT_SYMBOL_GPL(__get_vm_area); struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, void *caller) { return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL, caller); } /** * get_vm_area - reserve a contiguous kernel virtual area * @size: size of the area * @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC * * Search an area of @size in the kernel virtual mapping area, * and reserved it for out purposes. Returns the area descriptor * on success or %NULL on failure. */ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) { return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, -1, GFP_KERNEL, __builtin_return_address(0)); } struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, void *caller) { return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, -1, GFP_KERNEL, caller); } struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags, int node, gfp_t gfp_mask) { return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node, gfp_mask, __builtin_return_address(0)); } static struct vm_struct *find_vm_area(const void *addr) { struct vmap_area *va; va = find_vmap_area((unsigned long)addr); if (va && va->flags & VM_VM_AREA) return va->private; return NULL; } /** * remove_vm_area - find and remove a continuous kernel virtual area * @addr: base address * * Search for the kernel VM area starting at @addr, and remove it. * This function returns the found VM area, but using it is NOT safe * on SMP machines, except for its size or flags. */ struct vm_struct *remove_vm_area(const void *addr) { struct vmap_area *va; va = find_vmap_area((unsigned long)addr); if (va && va->flags & VM_VM_AREA) { struct vm_struct *vm = va->private; struct vm_struct *tmp, **p; vmap_debug_free_range(va->va_start, va->va_end); free_unmap_vmap_area(va); vm->size -= PAGE_SIZE; write_lock(&vmlist_lock); for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next) ; *p = tmp->next; write_unlock(&vmlist_lock); return vm; } return NULL; } static void __vunmap(const void *addr, int deallocate_pages) { struct vm_struct *area; if (!addr) return; if ((PAGE_SIZE-1) & (unsigned long)addr) { WARN(1, KERN_ERR "Trying to vfree() bad address (%p)\n", addr); return; } area = remove_vm_area(addr); if (unlikely(!area)) { WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n", addr); return; } debug_check_no_locks_freed(addr, area->size); debug_check_no_obj_freed(addr, area->size); if (deallocate_pages) { int i; for (i = 0; i < area->nr_pages; i++) { struct page *page = area->pages[i]; BUG_ON(!page); __free_page(page); } if (area->flags & VM_VPAGES) vfree(area->pages); else kfree(area->pages); } kfree(area); return; } /** * vfree - release memory allocated by vmalloc() * @addr: memory base address * * Free the virtually continuous memory area starting at @addr, as * obtained from vmalloc(), vmalloc_32() or __vmalloc(). If @addr is * NULL, no operation is performed. * * Must not be called in interrupt context. */ void vfree(const void *addr) { BUG_ON(in_interrupt()); kmemleak_free(addr); __vunmap(addr, 1); } EXPORT_SYMBOL(vfree); /** * vunmap - release virtual mapping obtained by vmap() * @addr: memory base address * * Free the virtually contiguous memory area starting at @addr, * which was created from the page array passed to vmap(). * * Must not be called in interrupt context. */ void vunmap(const void *addr) { BUG_ON(in_interrupt()); might_sleep(); __vunmap(addr, 0); } EXPORT_SYMBOL(vunmap); /** * vmap - map an array of pages into virtually contiguous space * @pages: array of page pointers * @count: number of pages to map * @flags: vm_area->flags * @prot: page protection for the mapping * * Maps @count pages from @pages into contiguous kernel virtual * space. */ void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot) { struct vm_struct *area; might_sleep(); if (count > num_physpages) return NULL; area = get_vm_area_caller((count << PAGE_SHIFT), flags, __builtin_return_address(0)); if (!area) return NULL; if (map_vm_area(area, prot, &pages)) { vunmap(area->addr); return NULL; } return area->addr; } EXPORT_SYMBOL(vmap); static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot, int node, void *caller); static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot, int node, void *caller) { struct page **pages; unsigned int nr_pages, array_size, i; nr_pages = (area->size - PAGE_SIZE) >> PAGE_SHIFT; array_size = (nr_pages * sizeof(struct page *)); area->nr_pages = nr_pages; /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { pages = __vmalloc_node(array_size, gfp_mask | __GFP_ZERO, PAGE_KERNEL, node, caller); area->flags |= VM_VPAGES; } else { pages = kmalloc_node(array_size, (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO, node); } area->pages = pages; area->caller = caller; if (!area->pages) { remove_vm_area(area->addr); kfree(area); return NULL; } for (i = 0; i < area->nr_pages; i++) { struct page *page; if (node < 0) page = alloc_page(gfp_mask); else page = alloc_pages_node(node, gfp_mask, 0); if (unlikely(!page)) { /* Successfully allocated i pages, free them in __vunmap() */ area->nr_pages = i; goto fail; } area->pages[i] = page; } if (map_vm_area(area, prot, &pages)) goto fail; return area->addr; fail: vfree(area->addr); return NULL; } void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot) { void *addr = __vmalloc_area_node(area, gfp_mask, prot, -1, __builtin_return_address(0)); /* * A ref_count = 3 is needed because the vm_struct and vmap_area * structures allocated in the __get_vm_area_node() function contain * references to the virtual address of the vmalloc'ed block. */ kmemleak_alloc(addr, area->size - PAGE_SIZE, 3, gfp_mask); return addr; } /** * __vmalloc_node - allocate virtually contiguous memory * @size: allocation size * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages * @node: node to use for allocation or -1 * @caller: caller's return address * * Allocate enough pages to cover @size from the page level * allocator with @gfp_mask flags. Map them into contiguous * kernel virtual space, using a pagetable protection of @prot. */ static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot, int node, void *caller) { struct vm_struct *area; void *addr; unsigned long real_size = size; size = PAGE_ALIGN(size); if (!size || (size >> PAGE_SHIFT) > num_physpages) return NULL; area = __get_vm_area_node(size, VM_ALLOC, VMALLOC_START, VMALLOC_END, node, gfp_mask, caller); if (!area) return NULL; addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller); /* * A ref_count = 3 is needed because the vm_struct and vmap_area * structures allocated in the __get_vm_area_node() function contain * references to the virtual address of the vmalloc'ed block. */ kmemleak_alloc(addr, real_size, 3, gfp_mask); return addr; } void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) { return __vmalloc_node(size, gfp_mask, prot, -1, __builtin_return_address(0)); } EXPORT_SYMBOL(__vmalloc); /** * vmalloc - allocate virtually contiguous memory * @size: allocation size * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. */ void *vmalloc(unsigned long size) { return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, -1, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc); /** * vmalloc_user - allocate zeroed virtually contiguous memory for userspace * @size: allocation size * * The resulting memory area is zeroed so it can be mapped to userspace * without leaking data. */ void *vmalloc_user(unsigned long size) { struct vm_struct *area; void *ret; ret = __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL, -1, __builtin_return_address(0)); if (ret) { area = find_vm_area(ret); area->flags |= VM_USERMAP; } return ret; } EXPORT_SYMBOL(vmalloc_user); /** * vmalloc_node - allocate memory on a specific node * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. */ void *vmalloc_node(unsigned long size, int node) { return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, node, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_node); #ifndef PAGE_KERNEL_EXEC # define PAGE_KERNEL_EXEC PAGE_KERNEL #endif /** * vmalloc_exec - allocate virtually contiguous, executable memory * @size: allocation size * * Kernel-internal function to allocate enough pages to cover @size * the page level allocator and map them into contiguous and * executable kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. */ void *vmalloc_exec(unsigned long size) { return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, -1, __builtin_return_address(0)); } #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) #define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) #define GFP_VMALLOC32 GFP_DMA | GFP_KERNEL #else #define GFP_VMALLOC32 GFP_KERNEL #endif /** * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) * @size: allocation size * * Allocate enough 32bit PA addressable pages to cover @size from the * page level allocator and map them into contiguous kernel virtual space. */ void *vmalloc_32(unsigned long size) { return __vmalloc_node(size, GFP_VMALLOC32, PAGE_KERNEL, -1, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32); /** * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory * @size: allocation size * * The resulting memory area is 32bit addressable and zeroed so it can be * mapped to userspace without leaking data. */ void *vmalloc_32_user(unsigned long size) { struct vm_struct *area; void *ret; ret = __vmalloc_node(size, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, -1, __builtin_return_address(0)); if (ret) { area = find_vm_area(ret); area->flags |= VM_USERMAP; } return ret; } EXPORT_SYMBOL(vmalloc_32_user); long vread(char *buf, char *addr, unsigned long count) { struct vm_struct *tmp; char *vaddr, *buf_start = buf; unsigned long n; /* Don't allow overflow */ if ((unsigned long) addr + count < count) count = -(unsigned long) addr; read_lock(&vmlist_lock); for (tmp = vmlist; tmp; tmp = tmp->next) { vaddr = (char *) tmp->addr; if (addr >= vaddr + tmp->size - PAGE_SIZE) continue; while (addr < vaddr) { if (count == 0) goto finished; *buf = '\0';