summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
blob: b7291f60399c0e759e8bf618a2966fa565ae106b (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Resource Director Technology(RDT)
 * - Cache Allocation code.
 *
 * Copyright (C) 2016 Intel Corporation
 *
 * Authors:
 *    Fenghua Yu <fenghua.yu@intel.com>
 *    Tony Luck <tony.luck@intel.com>
 *
 * More information about RDT be found in the Intel (R) x86 Architecture
 * Software Developer Manual June 2016, volume 3, section 17.17.
 */

#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt

#include <linux/cpu.h>
#include <linux/kernfs.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/tick.h>

#include "internal.h"

/*
 * Check whether MBA bandwidth percentage value is correct. The value is
 * checked against the minimum and max bandwidth values specified by the
 * hardware. The allocated bandwidth percentage is rounded to the next
 * control step available on the hardware.
 */
static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
{
	unsigned long bw;
	int ret;

	/*
	 * Only linear delay values is supported for current Intel SKUs.
	 */
	if (!r->membw.delay_linear && r->membw.arch_needs_linear) {
		rdt_last_cmd_puts("No support for non-linear MB domains\n");
		return false;
	}

	ret = kstrtoul(buf, 10, &bw);
	if (ret) {
		rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
		return false;
	}

	if ((bw < r->membw.min_bw || bw > r->default_ctrl) &&
	    !is_mba_sc(r)) {
		rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw,
				    r->membw.min_bw, r->default_ctrl);
		return false;
	}

	*data = roundup(bw, (unsigned long)r->membw.bw_gran);
	return true;
}

int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
	     struct rdt_domain *d)
{
	struct resctrl_staged_config *cfg;
	u32 closid = data->rdtgrp->closid;
	struct rdt_resource *r = s->res;
	unsigned long bw_val;

	cfg = &d->staged_config[s->conf_type];
	if (cfg->have_new_ctrl) {
		rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
		return -EINVAL;
	}

	if (!bw_validate(data->buf, &bw_val, r))
		return -EINVAL;

	if (is_mba_sc(r)) {
		d->mbps_val[closid] = bw_val;
		return 0;
	}

	cfg->new_ctrl = bw_val;
	cfg->have_new_ctrl = true;

	return 0;
}

/*
 * Check whether a cache bit mask is valid.
 * On Intel CPUs, non-contiguous 1s value support is indicated by CPUID:
 *   - CPUID.0x10.1:ECX[3]: L3 non-contiguous 1s value supported if 1
 *   - CPUID.0x10.2:ECX[3]: L2 non-contiguous 1s value supported if 1
 *
 * Haswell does not support a non-contiguous 1s value and additionally
 * requires at least two bits set.
 * AMD allows non-contiguous bitmasks.
 */
static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
{
	unsigned long first_bit, zero_bit, val;
	unsigned int cbm_len = r->cache.cbm_len;
	int ret;

	ret = kstrtoul(buf, 16, &val);
	if (ret) {
		rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf);
		return false;
	}

	if ((r->cache.min_cbm_bits > 0 && val == 0) || val > r->default_ctrl) {
		rdt_last_cmd_puts("Mask out of range\n");
		return false;
	}

	first_bit = find_first_bit(&val, cbm_len);
	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);

	/* Are non-contiguous bitmasks allowed? */
	if (!r->cache.arch_has_sparse_bitmasks &&
	    (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) {
		rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val);
		return false;
	}

	if ((zero_bit - first_bit) < r->cache.min_cbm_bits) {
		rdt_last_cmd_printf("Need at least %d bits in the mask\n",
				    r->cache.min_cbm_bits);
		return false;
	}

	*data = val;
	return true;
}

/*
 * Read one cache bit mask (hex). Check that it is valid for the current
 * resource type.
 */
int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
	      struct rdt_domain *d)
{
	struct rdtgroup *rdtgrp = data->rdtgrp;
	struct resctrl_staged_config *cfg;
	struct rdt_resource *r = s->res;
	u32 cbm_val;

	cfg = &d->staged_config[s->conf_type];
	if (cfg->have_new_ctrl) {
		rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
		return -EINVAL;
	}

	/*
	 * Cannot set up more than one pseudo-locked region in a cache
	 * hierarchy.
	 */
	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
	    rdtgroup_pseudo_locked_in_hierarchy(d)) {
		rdt_last_cmd_puts("Pseudo-locked region in hierarchy\n");
		return -EINVAL;
	}

	if (!cbm_validate(data->buf, &cbm_val, r))
		return -EINVAL;

	if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
	     rdtgrp->mode == RDT_MODE_SHAREABLE) &&
	    rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) {
		rdt_last_cmd_puts("CBM overlaps with pseudo-locked region\n");
		return -EINVAL;
	}

	/*
	 * The CBM may not overlap with the CBM of another closid if
	 * either is exclusive.
	 */
	if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, true)) {
		rdt_last_cmd_puts("Overlaps with exclusive group\n");
		return -EINVAL;
	}

	if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, false)) {
		if (rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
			rdt_last_cmd_puts("Overlaps with other group\n");
			return -EINVAL;
		}
	}

	cfg->new_ctrl = cbm_val;
	cfg->have_new_ctrl = true;

	return 0;
}

/*
 * For each domain in this resource we expect to find a series of:
 *	id=mask
 * separated by ";". The "id" is in decimal, and must match one of
 * the "id"s for this resource.
 */
static int parse_line(char *line, struct resctrl_schema *s,
		      struct rdtgroup *rdtgrp)
{
	enum resctrl_conf_type t = s->conf_type;
	struct resctrl_staged_config *cfg;
	struct rdt_resource *r = s->res;
	struct rdt_parse_data data;
	char *dom = NULL, *id;
	struct rdt_domain *d;
	unsigned long dom_id;

	/* Walking r->domains, ensure it can't race with cpuhp */
	lockdep_assert_cpus_held();

	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
	    (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) {
		rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
		return -EINVAL;
	}

next:
	if (!line || line[0] == '\0')
		return 0;
	dom = strsep(&line, ";");
	id = strsep(&dom, "=");
	if (!dom || kstrtoul(id, 10, &dom_id)) {
		rdt_last_cmd_puts("Missing '=' or non-numeric domain\n");
		return -EINVAL;
	}
	dom = strim(dom);
	list_for_each_entry(d, &r->domains, list) {
		if (d->id == dom_id) {
			data.buf = dom;
			data.rdtgrp = rdtgrp;
			if (r->parse_ctrlval(&data, s, d))
				return -EINVAL;
			if (rdtgrp->mode ==  RDT_MODE_PSEUDO_LOCKSETUP) {
				cfg = &d->staged_config[t];
				/*
				 * In pseudo-locking setup mode and just
				 * parsed a valid CBM that should be
				 * pseudo-locked. Only one locked region per
				 * resource group and domain so just do
				 * the required initialization for single
				 * region and return.
				 */
				rdtgrp->plr->s = s;
				rdtgrp->plr->d = d;
				rdtgrp->plr->cbm = cfg->new_ctrl;
				d->plr = rdtgrp->plr;
				return 0;
			}
			goto next;
		}
	}
	return -EINVAL;
}

static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
{
	switch (type) {
	default:
	case CDP_NONE:
		return closid;
	case CDP_CODE:
		return closid * 2 + 1;
	case CDP_DATA:
		return closid * 2;
	}
}

int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
			    u32 closid, enum resctrl_conf_type t, u32 cfg_val)
{
	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
	u32 idx = get_config_index(closid, t);
	struct msr_param msr_param;

	if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
		return -EINVAL;

	hw_dom->ctrl_val[idx] = cfg_val;

	msr_param.res = r;
	msr_param.dom = d;
	msr_param.low = idx;
	msr_param.high = idx + 1;
	hw_res->msr_update(&msr_param);

	return 0;
}

int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
{
	struct resctrl_staged_config *cfg;
	struct rdt_hw_domain *hw_dom;
	struct msr_param msr_param;
	enum resctrl_conf_type t;
	struct rdt_domain *d;
	u32 idx;

	/* Walking r->domains, ensure it can't race with cpuhp */
	lockdep_assert_cpus_held();

	list_for_each_entry(d, &r->domains, list) {
		hw_dom = resctrl_to_arch_dom(d);
		msr_param.res = NULL;
		for (t = 0; t < CDP_NUM_TYPES; t++) {
			cfg = &hw_dom->d_resctrl.staged_config[t];
			if (!cfg->have_new_ctrl)
				continue;

			idx = get_config_index(closid, t);
			if (cfg->new_ctrl == hw_dom->ctrl_val[idx])
				continue;
			hw_dom->ctrl_val[idx] = cfg->new_ctrl;

			if (!msr_param.res) {
				msr_param.low = idx;
				msr_param.high = msr_param.low + 1;
				msr_param.res = r;
				msr_param.dom = d;
			} else {
				msr_param.low = min(msr_param.low, idx);
				msr_param.high = max(msr_param.high, idx + 1);
			}
		}
		if (msr_param.res)
			smp_call_function_any(&d->cpu_mask, rdt_ctrl_update, &msr_param, 1);
	}

	return 0;
}

static int rdtgroup_parse_resource(char *resname, char *tok,
				   struct rdtgroup *rdtgrp)
{
	struct resctrl_schema *s;

	list_for_each_entry(s, &resctrl_schema_all, list) {
		if (!strcmp(resname, s->name) && rdtgrp->closid < s->num_closid)
			return parse_line(tok, s, rdtgrp);
	}
	rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname);
	return -EINVAL;
}

ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
				char *buf, size_t nbytes, loff_t off)
{
	struct resctrl_schema *s;
	struct rdtgroup *rdtgrp;
	struct rdt_resource *r;
	char *tok, *resname;
	int ret = 0;

	/* Valid input requires a trailing newline */
	if (nbytes == 0 || buf[nbytes - 1] != '\n')
		return -EINVAL;
	buf[nbytes - 1] = '\0';

	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	if (!rdtgrp) {
		rdtgroup_kn_unlock(of->kn);
		return -ENOENT;
	}
	rdt_last_cmd_clear();

	/*
	 * No changes to pseudo-locked region allowed. It has to be removed
	 * and re-created instead.
	 */
	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
		ret = -EINVAL;
		rdt_last_cmd_puts("Resource group is pseudo-locked\n");
		goto out;
	}

	rdt_staged_configs_clear();

	while ((tok = strsep(&buf, "\n")) != NULL) {
		resname = strim(strsep(&tok, ":"));
		if (!tok) {
			rdt_last_cmd_puts("Missing ':'\n");
			ret = -EINVAL;
			goto out;
		}
		if (tok[0] == '\0') {
			rdt_last_cmd_printf("Missing '%s' value\n", resname);
			ret = -EINVAL;
			goto out;
		}
		ret = rdtgroup_parse_resource(resname, tok, rdtgrp);
		if (ret)
			goto out;
	}

	list_for_each_entry(s, &resctrl_schema_all, list) {
		r = s->res;

		/*
		 * Writes to mba_sc resources update the software controller,
		 * not the control MSR.
		 */
		if (is_mba_sc(r))
			continue;

		ret = resctrl_arch_update_domains(r, rdtgrp->closid);
		if (ret)
			goto out;
	}

	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
		/*
		 * If pseudo-locking fails we keep the resource group in
		 * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service
		 * active and updated for just the domain the pseudo-locked
		 * region was requested for.
		 */
		ret = rdtgroup_pseudo_lock_create(rdtgrp);
	}

out:
	rdt_staged_configs_clear();
	rdtgroup_kn_unlock(of->kn);
	return ret ?: nbytes;
}

u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
			    u32 closid, enum resctrl_conf_type type)
{
	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
	u32 idx = get_config_index(closid, type);

	return hw_dom->ctrl_val[idx];
}

static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid)
{
	struct rdt_resource *r = schema->res;
	struct rdt_domain *dom;
	bool sep = false;
	u32 ctrl_val;

	/* Walking r->domains, ensure it can't race with cpuhp */
	lockdep_assert_cpus_held();

	seq_printf(s, "%*s:", max_name_width, schema->name);
	list_for_each_entry(dom, &r->domains, list) {
		if (sep)
			seq_puts(s, ";");

		if (is_mba_sc(r))
			ctrl_val = dom->mbps_val[closid];
		else
			ctrl_val = resctrl_arch_get_config(r, dom, closid,
							   schema->conf_type);

		seq_printf(s, r->format_str, dom->id, max_data_width,
			   ctrl_val);
		sep = true;
	}
	seq_puts(s, "\n");
}

int rdtgroup_schemata_show(struct kernfs_open_file *of,
			   struct seq_file *s, void *v)
{
	struct resctrl_schema *schema;
	struct rdtgroup *rdtgrp;
	int ret = 0;
	u32 closid;

	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	if (rdtgrp) {
		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
			list_for_each_entry(schema, &resctrl_schema_all, list) {
				seq_printf(s, "%s:uninitialized\n", schema->name);
			}
		} else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
			if (!rdtgrp->plr->d) {
				rdt_last_cmd_clear();
				rdt_last_cmd_puts("Cache domain offline\n");
				ret = -ENODEV;
			} else {
				seq_printf(s, "%s:%d=%x\n",
					   rdtgrp->plr->s->res->name,
					   rdtgrp->plr->d->id,
					   rdtgrp->plr->cbm);
			}
		} else {
			closid = rdtgrp->closid;
			list_for_each_entry(schema, &resctrl_schema_all, list) {
				if (closid < schema->num_closid)
					show_doms(s, schema, closid);
			}
		}
	} else {
		ret = -ENOENT;
	}
	rdtgroup_kn_unlock(of->kn);
	return ret;
}

static int smp_mon_event_count(void *arg)
{
	mon_event_count(arg);

	return 0;
}

void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
		    int evtid, int first)
{
	int cpu;

	/* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */
	lockdep_assert_cpus_held();

	/*
	 * Setup the parameters to pass to mon_event_count() to read the data.
	 */
	rr->rgrp = rdtgrp;
	rr->evtid = evtid;
	rr->r = r;
	rr->d = d;
	rr->val = 0;
	rr->first = first;
	rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
	if (IS_ERR(rr->arch_mon_ctx)) {
		rr->err = -EINVAL;
		return;
	}

	cpu = cpumask_any_housekeeping(&d->cpu_mask, RESCTRL_PICK_ANY_CPU);

	/*
	 * cpumask_any_housekeeping() prefers housekeeping CPUs, but
	 * are all the CPUs nohz_full? If yes, pick a CPU to IPI.
	 * MPAM's resctrl_arch_rmid_read() is unable to read the
	 * counters on some platforms if its called in IRQ context.
	 */
	if (tick_nohz_full_cpu(cpu))
		smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
	else
		smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);

	resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
}

int rdtgroup_mondata_show(struct seq_file *m, void *arg)
{
	struct kernfs_open_file *of = m->private;
	u32 resid, evtid, domid;
	struct rdtgroup *rdtgrp;
	struct rdt_resource *r;
	union mon_data_bits md;
	struct rdt_domain *d;
	struct rmid_read rr;
	int ret = 0;

	rdtgrp = rdtgroup_kn_lock_live(of->kn);
	if (!rdtgrp) {
		ret = -ENOENT;
		goto out;
	}

	md.priv = of->kn->priv;
	resid = md.u.rid;
	domid = md.u.domid;
	evtid = md.u.evtid;

	r = &rdt_resources_all[resid].r_resctrl;
	d = rdt_find_domain(r, domid, NULL);
	if (IS_ERR_OR_NULL(d)) {
		ret = -ENOENT;
		goto out;
	}

	mon_event_read(&rr, r, d, rdtgrp, evtid, false);

	if (rr.err == -EIO)
		seq_puts(m, "Error\n");
	else if (rr.err == -EINVAL)
		seq_puts(m, "Unavailable\n");
	else
		seq_printf(m, "%llu\n", rr.val);

out:
	rdtgroup_kn_unlock(of->kn);
	return ret;
}