]>
Commit | Line | Data |
---|---|---|
5ff193fb FY |
1 | /* |
2 | * User interface for Resource Alloction in Resource Director Technology(RDT) | |
3 | * | |
4 | * Copyright (C) 2016 Intel Corporation | |
5 | * | |
6 | * Author: Fenghua Yu <fenghua.yu@intel.com> | |
7 | * | |
8 | * This program is free software; you can redistribute it and/or modify it | |
9 | * under the terms and conditions of the GNU General Public License, | |
10 | * version 2, as published by the Free Software Foundation. | |
11 | * | |
12 | * This program is distributed in the hope it will be useful, but WITHOUT | |
13 | * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | |
14 | * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | |
15 | * more details. | |
16 | * | |
17 | * More information about RDT be found in the Intel (R) x86 Architecture | |
18 | * Software Developer Manual. | |
19 | */ | |
20 | ||
21 | #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt | |
22 | ||
12e0110c | 23 | #include <linux/cpu.h> |
5ff193fb FY |
24 | #include <linux/fs.h> |
25 | #include <linux/sysfs.h> | |
26 | #include <linux/kernfs.h> | |
4e978d06 | 27 | #include <linux/seq_file.h> |
3f07c014 | 28 | #include <linux/sched/signal.h> |
5ff193fb | 29 | #include <linux/slab.h> |
60cf5e10 | 30 | #include <linux/cpu.h> |
e02737d5 | 31 | #include <linux/task_work.h> |
5ff193fb FY |
32 | |
33 | #include <uapi/linux/magic.h> | |
34 | ||
35 | #include <asm/intel_rdt.h> | |
60cf5e10 | 36 | #include <asm/intel_rdt_common.h> |
5ff193fb FY |
37 | |
38 | DEFINE_STATIC_KEY_FALSE(rdt_enable_key); | |
39 | struct kernfs_root *rdt_root; | |
40 | struct rdtgroup rdtgroup_default; | |
41 | LIST_HEAD(rdt_all_groups); | |
42 | ||
4e978d06 FY |
43 | /* Kernel fs node for "info" directory under root */ |
44 | static struct kernfs_node *kn_info; | |
45 | ||
60cf5e10 FY |
46 | /* |
47 | * Trivial allocator for CLOSIDs. Since h/w only supports a small number, | |
48 | * we can keep a bitmap of free CLOSIDs in a single integer. | |
49 | * | |
50 | * Using a global CLOSID across all resources has some advantages and | |
51 | * some drawbacks: | |
52 | * + We can simply set "current->closid" to assign a task to a resource | |
53 | * group. | |
54 | * + Context switch code can avoid extra memory references deciding which | |
55 | * CLOSID to load into the PQR_ASSOC MSR | |
56 | * - We give up some options in configuring resource groups across multi-socket | |
57 | * systems. | |
58 | * - Our choices on how to configure each resource become progressively more | |
59 | * limited as the number of resources grows. | |
60 | */ | |
61 | static int closid_free_map; | |
62 | ||
63 | static void closid_init(void) | |
64 | { | |
65 | struct rdt_resource *r; | |
66 | int rdt_min_closid = 32; | |
67 | ||
68 | /* Compute rdt_min_closid across all resources */ | |
69 | for_each_enabled_rdt_resource(r) | |
70 | rdt_min_closid = min(rdt_min_closid, r->num_closid); | |
71 | ||
72 | closid_free_map = BIT_MASK(rdt_min_closid) - 1; | |
73 | ||
74 | /* CLOSID 0 is always reserved for the default group */ | |
75 | closid_free_map &= ~1; | |
76 | } | |
77 | ||
78 | int closid_alloc(void) | |
79 | { | |
80 | int closid = ffs(closid_free_map); | |
81 | ||
82 | if (closid == 0) | |
83 | return -ENOSPC; | |
84 | closid--; | |
85 | closid_free_map &= ~(1 << closid); | |
86 | ||
87 | return closid; | |
88 | } | |
89 | ||
90 | static void closid_free(int closid) | |
91 | { | |
92 | closid_free_map |= 1 << closid; | |
93 | } | |
94 | ||
4e978d06 FY |
95 | /* set uid and gid of rdtgroup dirs and files to that of the creator */ |
96 | static int rdtgroup_kn_set_ugid(struct kernfs_node *kn) | |
97 | { | |
98 | struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, | |
99 | .ia_uid = current_fsuid(), | |
100 | .ia_gid = current_fsgid(), }; | |
101 | ||
102 | if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) && | |
103 | gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID)) | |
104 | return 0; | |
105 | ||
106 | return kernfs_setattr(kn, &iattr); | |
107 | } | |
108 | ||
109 | static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft) | |
110 | { | |
111 | struct kernfs_node *kn; | |
112 | int ret; | |
113 | ||
114 | kn = __kernfs_create_file(parent_kn, rft->name, rft->mode, | |
115 | 0, rft->kf_ops, rft, NULL, NULL); | |
116 | if (IS_ERR(kn)) | |
117 | return PTR_ERR(kn); | |
118 | ||
119 | ret = rdtgroup_kn_set_ugid(kn); | |
120 | if (ret) { | |
121 | kernfs_remove(kn); | |
122 | return ret; | |
123 | } | |
124 | ||
125 | return 0; | |
126 | } | |
127 | ||
128 | static int rdtgroup_add_files(struct kernfs_node *kn, struct rftype *rfts, | |
129 | int len) | |
130 | { | |
131 | struct rftype *rft; | |
132 | int ret; | |
133 | ||
134 | lockdep_assert_held(&rdtgroup_mutex); | |
135 | ||
136 | for (rft = rfts; rft < rfts + len; rft++) { | |
137 | ret = rdtgroup_add_file(kn, rft); | |
138 | if (ret) | |
139 | goto error; | |
140 | } | |
141 | ||
142 | return 0; | |
143 | error: | |
144 | pr_warn("Failed to add %s, err=%d\n", rft->name, ret); | |
145 | while (--rft >= rfts) | |
146 | kernfs_remove_by_name(kn, rft->name); | |
147 | return ret; | |
148 | } | |
149 | ||
150 | static int rdtgroup_seqfile_show(struct seq_file *m, void *arg) | |
151 | { | |
152 | struct kernfs_open_file *of = m->private; | |
153 | struct rftype *rft = of->kn->priv; | |
154 | ||
155 | if (rft->seq_show) | |
156 | return rft->seq_show(of, m, arg); | |
157 | return 0; | |
158 | } | |
159 | ||
160 | static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf, | |
161 | size_t nbytes, loff_t off) | |
162 | { | |
163 | struct rftype *rft = of->kn->priv; | |
164 | ||
165 | if (rft->write) | |
166 | return rft->write(of, buf, nbytes, off); | |
167 | ||
168 | return -EINVAL; | |
169 | } | |
170 | ||
171 | static struct kernfs_ops rdtgroup_kf_single_ops = { | |
172 | .atomic_write_len = PAGE_SIZE, | |
173 | .write = rdtgroup_file_write, | |
174 | .seq_show = rdtgroup_seqfile_show, | |
175 | }; | |
176 | ||
12e0110c TL |
177 | static int rdtgroup_cpus_show(struct kernfs_open_file *of, |
178 | struct seq_file *s, void *v) | |
179 | { | |
180 | struct rdtgroup *rdtgrp; | |
181 | int ret = 0; | |
182 | ||
183 | rdtgrp = rdtgroup_kn_lock_live(of->kn); | |
184 | ||
185 | if (rdtgrp) | |
186 | seq_printf(s, "%*pb\n", cpumask_pr_args(&rdtgrp->cpu_mask)); | |
187 | else | |
188 | ret = -ENOENT; | |
189 | rdtgroup_kn_unlock(of->kn); | |
190 | ||
191 | return ret; | |
192 | } | |
193 | ||
f4107702 FY |
194 | /* |
195 | * This is safe against intel_rdt_sched_in() called from __switch_to() | |
196 | * because __switch_to() is executed with interrupts disabled. A local call | |
0efc89be | 197 | * from rdt_update_closid() is proteced against __switch_to() because |
f4107702 FY |
198 | * preemption is disabled. |
199 | */ | |
0efc89be | 200 | static void rdt_update_cpu_closid(void *closid) |
f4107702 | 201 | { |
0efc89be FY |
202 | if (closid) |
203 | this_cpu_write(cpu_closid, *(int *)closid); | |
f4107702 FY |
204 | /* |
205 | * We cannot unconditionally write the MSR because the current | |
206 | * executing task might have its own closid selected. Just reuse | |
207 | * the context switch code. | |
208 | */ | |
209 | intel_rdt_sched_in(); | |
210 | } | |
211 | ||
0efc89be FY |
212 | /* |
213 | * Update the PGR_ASSOC MSR on all cpus in @cpu_mask, | |
214 | * | |
215 | * Per task closids must have been set up before calling this function. | |
216 | * | |
217 | * The per cpu closids are updated with the smp function call, when @closid | |
218 | * is not NULL. If @closid is NULL then all affected percpu closids must | |
219 | * have been set up before calling this function. | |
220 | */ | |
221 | static void | |
222 | rdt_update_closid(const struct cpumask *cpu_mask, int *closid) | |
f4107702 FY |
223 | { |
224 | int cpu = get_cpu(); | |
225 | ||
226 | if (cpumask_test_cpu(cpu, cpu_mask)) | |
0efc89be FY |
227 | rdt_update_cpu_closid(closid); |
228 | smp_call_function_many(cpu_mask, rdt_update_cpu_closid, closid, 1); | |
f4107702 FY |
229 | put_cpu(); |
230 | } | |
231 | ||
12e0110c TL |
232 | static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, |
233 | char *buf, size_t nbytes, loff_t off) | |
234 | { | |
235 | cpumask_var_t tmpmask, newmask; | |
236 | struct rdtgroup *rdtgrp, *r; | |
f4107702 | 237 | int ret; |
12e0110c TL |
238 | |
239 | if (!buf) | |
240 | return -EINVAL; | |
241 | ||
242 | if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) | |
243 | return -ENOMEM; | |
244 | if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) { | |
245 | free_cpumask_var(tmpmask); | |
246 | return -ENOMEM; | |
247 | } | |
a2584e1d | 248 | |
12e0110c TL |
249 | rdtgrp = rdtgroup_kn_lock_live(of->kn); |
250 | if (!rdtgrp) { | |
251 | ret = -ENOENT; | |
252 | goto unlock; | |
253 | } | |
254 | ||
255 | ret = cpumask_parse(buf, newmask); | |
256 | if (ret) | |
257 | goto unlock; | |
258 | ||
12e0110c TL |
259 | /* check that user didn't specify any offline cpus */ |
260 | cpumask_andnot(tmpmask, newmask, cpu_online_mask); | |
261 | if (cpumask_weight(tmpmask)) { | |
262 | ret = -EINVAL; | |
a2584e1d | 263 | goto unlock; |
12e0110c TL |
264 | } |
265 | ||
266 | /* Check whether cpus are dropped from this group */ | |
267 | cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); | |
268 | if (cpumask_weight(tmpmask)) { | |
269 | /* Can't drop from default group */ | |
270 | if (rdtgrp == &rdtgroup_default) { | |
271 | ret = -EINVAL; | |
a2584e1d | 272 | goto unlock; |
12e0110c TL |
273 | } |
274 | /* Give any dropped cpus to rdtgroup_default */ | |
275 | cpumask_or(&rdtgroup_default.cpu_mask, | |
276 | &rdtgroup_default.cpu_mask, tmpmask); | |
0efc89be | 277 | rdt_update_closid(tmpmask, &rdtgroup_default.closid); |
12e0110c TL |
278 | } |
279 | ||
280 | /* | |
281 | * If we added cpus, remove them from previous group that owned them | |
282 | * and update per-cpu closid | |
283 | */ | |
284 | cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); | |
285 | if (cpumask_weight(tmpmask)) { | |
286 | list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) { | |
287 | if (r == rdtgrp) | |
288 | continue; | |
289 | cpumask_andnot(&r->cpu_mask, &r->cpu_mask, tmpmask); | |
290 | } | |
0efc89be | 291 | rdt_update_closid(tmpmask, &rdtgrp->closid); |
12e0110c TL |
292 | } |
293 | ||
294 | /* Done pushing/pulling - update this group with new mask */ | |
295 | cpumask_copy(&rdtgrp->cpu_mask, newmask); | |
296 | ||
12e0110c TL |
297 | unlock: |
298 | rdtgroup_kn_unlock(of->kn); | |
299 | free_cpumask_var(tmpmask); | |
300 | free_cpumask_var(newmask); | |
301 | ||
302 | return ret ?: nbytes; | |
303 | } | |
304 | ||
e02737d5 FY |
305 | struct task_move_callback { |
306 | struct callback_head work; | |
307 | struct rdtgroup *rdtgrp; | |
308 | }; | |
309 | ||
310 | static void move_myself(struct callback_head *head) | |
311 | { | |
312 | struct task_move_callback *callback; | |
313 | struct rdtgroup *rdtgrp; | |
314 | ||
315 | callback = container_of(head, struct task_move_callback, work); | |
316 | rdtgrp = callback->rdtgrp; | |
317 | ||
318 | /* | |
319 | * If resource group was deleted before this task work callback | |
320 | * was invoked, then assign the task to root group and free the | |
321 | * resource group. | |
322 | */ | |
323 | if (atomic_dec_and_test(&rdtgrp->waitcount) && | |
324 | (rdtgrp->flags & RDT_DELETED)) { | |
325 | current->closid = 0; | |
326 | kfree(rdtgrp); | |
327 | } | |
328 | ||
74fcdae1 | 329 | preempt_disable(); |
4f341a5e FY |
330 | /* update PQR_ASSOC MSR to make resource group go into effect */ |
331 | intel_rdt_sched_in(); | |
74fcdae1 | 332 | preempt_enable(); |
4f341a5e | 333 | |
e02737d5 FY |
334 | kfree(callback); |
335 | } | |
336 | ||
337 | static int __rdtgroup_move_task(struct task_struct *tsk, | |
338 | struct rdtgroup *rdtgrp) | |
339 | { | |
340 | struct task_move_callback *callback; | |
341 | int ret; | |
342 | ||
343 | callback = kzalloc(sizeof(*callback), GFP_KERNEL); | |
344 | if (!callback) | |
345 | return -ENOMEM; | |
346 | callback->work.func = move_myself; | |
347 | callback->rdtgrp = rdtgrp; | |
348 | ||
349 | /* | |
350 | * Take a refcount, so rdtgrp cannot be freed before the | |
351 | * callback has been invoked. | |
352 | */ | |
353 | atomic_inc(&rdtgrp->waitcount); | |
354 | ret = task_work_add(tsk, &callback->work, true); | |
355 | if (ret) { | |
356 | /* | |
357 | * Task is exiting. Drop the refcount and free the callback. | |
358 | * No need to check the refcount as the group cannot be | |
359 | * deleted before the write function unlocks rdtgroup_mutex. | |
360 | */ | |
361 | atomic_dec(&rdtgrp->waitcount); | |
362 | kfree(callback); | |
363 | } else { | |
364 | tsk->closid = rdtgrp->closid; | |
365 | } | |
366 | return ret; | |
367 | } | |
368 | ||
369 | static int rdtgroup_task_write_permission(struct task_struct *task, | |
370 | struct kernfs_open_file *of) | |
371 | { | |
372 | const struct cred *tcred = get_task_cred(task); | |
373 | const struct cred *cred = current_cred(); | |
374 | int ret = 0; | |
375 | ||
376 | /* | |
377 | * Even if we're attaching all tasks in the thread group, we only | |
378 | * need to check permissions on one of them. | |
379 | */ | |
380 | if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && | |
381 | !uid_eq(cred->euid, tcred->uid) && | |
382 | !uid_eq(cred->euid, tcred->suid)) | |
383 | ret = -EPERM; | |
384 | ||
385 | put_cred(tcred); | |
386 | return ret; | |
387 | } | |
388 | ||
389 | static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp, | |
390 | struct kernfs_open_file *of) | |
391 | { | |
392 | struct task_struct *tsk; | |
393 | int ret; | |
394 | ||
395 | rcu_read_lock(); | |
396 | if (pid) { | |
397 | tsk = find_task_by_vpid(pid); | |
398 | if (!tsk) { | |
399 | rcu_read_unlock(); | |
400 | return -ESRCH; | |
401 | } | |
402 | } else { | |
403 | tsk = current; | |
404 | } | |
405 | ||
406 | get_task_struct(tsk); | |
407 | rcu_read_unlock(); | |
408 | ||
409 | ret = rdtgroup_task_write_permission(tsk, of); | |
410 | if (!ret) | |
411 | ret = __rdtgroup_move_task(tsk, rdtgrp); | |
412 | ||
413 | put_task_struct(tsk); | |
414 | return ret; | |
415 | } | |
416 | ||
417 | static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, | |
418 | char *buf, size_t nbytes, loff_t off) | |
419 | { | |
420 | struct rdtgroup *rdtgrp; | |
421 | int ret = 0; | |
422 | pid_t pid; | |
423 | ||
424 | if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) | |
425 | return -EINVAL; | |
426 | rdtgrp = rdtgroup_kn_lock_live(of->kn); | |
427 | ||
428 | if (rdtgrp) | |
429 | ret = rdtgroup_move_task(pid, rdtgrp, of); | |
430 | else | |
431 | ret = -ENOENT; | |
432 | ||
433 | rdtgroup_kn_unlock(of->kn); | |
434 | ||
435 | return ret ?: nbytes; | |
436 | } | |
437 | ||
438 | static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s) | |
439 | { | |
440 | struct task_struct *p, *t; | |
441 | ||
442 | rcu_read_lock(); | |
443 | for_each_process_thread(p, t) { | |
444 | if (t->closid == r->closid) | |
445 | seq_printf(s, "%d\n", t->pid); | |
446 | } | |
447 | rcu_read_unlock(); | |
448 | } | |
449 | ||
450 | static int rdtgroup_tasks_show(struct kernfs_open_file *of, | |
451 | struct seq_file *s, void *v) | |
452 | { | |
453 | struct rdtgroup *rdtgrp; | |
454 | int ret = 0; | |
455 | ||
456 | rdtgrp = rdtgroup_kn_lock_live(of->kn); | |
457 | if (rdtgrp) | |
458 | show_rdt_tasks(rdtgrp, s); | |
459 | else | |
460 | ret = -ENOENT; | |
461 | rdtgroup_kn_unlock(of->kn); | |
462 | ||
463 | return ret; | |
464 | } | |
465 | ||
12e0110c TL |
466 | /* Files in each rdtgroup */ |
467 | static struct rftype rdtgroup_base_files[] = { | |
468 | { | |
469 | .name = "cpus", | |
470 | .mode = 0644, | |
471 | .kf_ops = &rdtgroup_kf_single_ops, | |
472 | .write = rdtgroup_cpus_write, | |
473 | .seq_show = rdtgroup_cpus_show, | |
474 | }, | |
e02737d5 FY |
475 | { |
476 | .name = "tasks", | |
477 | .mode = 0644, | |
478 | .kf_ops = &rdtgroup_kf_single_ops, | |
479 | .write = rdtgroup_tasks_write, | |
480 | .seq_show = rdtgroup_tasks_show, | |
481 | }, | |
60ec2440 TL |
482 | { |
483 | .name = "schemata", | |
484 | .mode = 0644, | |
485 | .kf_ops = &rdtgroup_kf_single_ops, | |
486 | .write = rdtgroup_schemata_write, | |
487 | .seq_show = rdtgroup_schemata_show, | |
488 | }, | |
12e0110c TL |
489 | }; |
490 | ||
4e978d06 FY |
491 | static int rdt_num_closids_show(struct kernfs_open_file *of, |
492 | struct seq_file *seq, void *v) | |
493 | { | |
494 | struct rdt_resource *r = of->kn->parent->priv; | |
495 | ||
496 | seq_printf(seq, "%d\n", r->num_closid); | |
497 | ||
498 | return 0; | |
499 | } | |
500 | ||
501 | static int rdt_cbm_mask_show(struct kernfs_open_file *of, | |
502 | struct seq_file *seq, void *v) | |
503 | { | |
504 | struct rdt_resource *r = of->kn->parent->priv; | |
505 | ||
506 | seq_printf(seq, "%x\n", r->max_cbm); | |
507 | ||
508 | return 0; | |
509 | } | |
510 | ||
53a114a6 SL |
511 | static int rdt_min_cbm_bits_show(struct kernfs_open_file *of, |
512 | struct seq_file *seq, void *v) | |
513 | { | |
514 | struct rdt_resource *r = of->kn->parent->priv; | |
515 | ||
516 | seq_printf(seq, "%d\n", r->min_cbm_bits); | |
517 | ||
518 | return 0; | |
519 | } | |
520 | ||
4e978d06 FY |
521 | /* rdtgroup information files for one cache resource. */ |
522 | static struct rftype res_info_files[] = { | |
523 | { | |
524 | .name = "num_closids", | |
525 | .mode = 0444, | |
526 | .kf_ops = &rdtgroup_kf_single_ops, | |
527 | .seq_show = rdt_num_closids_show, | |
528 | }, | |
529 | { | |
530 | .name = "cbm_mask", | |
531 | .mode = 0444, | |
532 | .kf_ops = &rdtgroup_kf_single_ops, | |
533 | .seq_show = rdt_cbm_mask_show, | |
534 | }, | |
53a114a6 SL |
535 | { |
536 | .name = "min_cbm_bits", | |
537 | .mode = 0444, | |
538 | .kf_ops = &rdtgroup_kf_single_ops, | |
539 | .seq_show = rdt_min_cbm_bits_show, | |
540 | }, | |
4e978d06 FY |
541 | }; |
542 | ||
543 | static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) | |
544 | { | |
545 | struct kernfs_node *kn_subdir; | |
546 | struct rdt_resource *r; | |
547 | int ret; | |
548 | ||
549 | /* create the directory */ | |
550 | kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL); | |
551 | if (IS_ERR(kn_info)) | |
552 | return PTR_ERR(kn_info); | |
553 | kernfs_get(kn_info); | |
554 | ||
555 | for_each_enabled_rdt_resource(r) { | |
556 | kn_subdir = kernfs_create_dir(kn_info, r->name, | |
557 | kn_info->mode, r); | |
558 | if (IS_ERR(kn_subdir)) { | |
559 | ret = PTR_ERR(kn_subdir); | |
560 | goto out_destroy; | |
561 | } | |
562 | kernfs_get(kn_subdir); | |
563 | ret = rdtgroup_kn_set_ugid(kn_subdir); | |
564 | if (ret) | |
565 | goto out_destroy; | |
566 | ret = rdtgroup_add_files(kn_subdir, res_info_files, | |
567 | ARRAY_SIZE(res_info_files)); | |
568 | if (ret) | |
569 | goto out_destroy; | |
570 | kernfs_activate(kn_subdir); | |
571 | } | |
572 | ||
573 | /* | |
574 | * This extra ref will be put in kernfs_remove() and guarantees | |
575 | * that @rdtgrp->kn is always accessible. | |
576 | */ | |
577 | kernfs_get(kn_info); | |
578 | ||
579 | ret = rdtgroup_kn_set_ugid(kn_info); | |
580 | if (ret) | |
581 | goto out_destroy; | |
582 | ||
583 | kernfs_activate(kn_info); | |
584 | ||
585 | return 0; | |
586 | ||
587 | out_destroy: | |
588 | kernfs_remove(kn_info); | |
589 | return ret; | |
590 | } | |
591 | ||
5ff193fb FY |
592 | static void l3_qos_cfg_update(void *arg) |
593 | { | |
594 | bool *enable = arg; | |
595 | ||
596 | wrmsrl(IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL); | |
597 | } | |
598 | ||
599 | static int set_l3_qos_cfg(struct rdt_resource *r, bool enable) | |
600 | { | |
601 | cpumask_var_t cpu_mask; | |
602 | struct rdt_domain *d; | |
603 | int cpu; | |
604 | ||
605 | if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) | |
606 | return -ENOMEM; | |
607 | ||
608 | list_for_each_entry(d, &r->domains, list) { | |
609 | /* Pick one CPU from each domain instance to update MSR */ | |
610 | cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); | |
611 | } | |
612 | cpu = get_cpu(); | |
613 | /* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */ | |
614 | if (cpumask_test_cpu(cpu, cpu_mask)) | |
615 | l3_qos_cfg_update(&enable); | |
616 | /* Update QOS_CFG MSR on all other cpus in cpu_mask. */ | |
617 | smp_call_function_many(cpu_mask, l3_qos_cfg_update, &enable, 1); | |
618 | put_cpu(); | |
619 | ||
620 | free_cpumask_var(cpu_mask); | |
621 | ||
622 | return 0; | |
623 | } | |
624 | ||
625 | static int cdp_enable(void) | |
626 | { | |
627 | struct rdt_resource *r_l3data = &rdt_resources_all[RDT_RESOURCE_L3DATA]; | |
628 | struct rdt_resource *r_l3code = &rdt_resources_all[RDT_RESOURCE_L3CODE]; | |
629 | struct rdt_resource *r_l3 = &rdt_resources_all[RDT_RESOURCE_L3]; | |
630 | int ret; | |
631 | ||
632 | if (!r_l3->capable || !r_l3data->capable || !r_l3code->capable) | |
633 | return -EINVAL; | |
634 | ||
635 | ret = set_l3_qos_cfg(r_l3, true); | |
636 | if (!ret) { | |
637 | r_l3->enabled = false; | |
638 | r_l3data->enabled = true; | |
639 | r_l3code->enabled = true; | |
640 | } | |
641 | return ret; | |
642 | } | |
643 | ||
644 | static void cdp_disable(void) | |
645 | { | |
646 | struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3]; | |
647 | ||
648 | r->enabled = r->capable; | |
649 | ||
650 | if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) { | |
651 | rdt_resources_all[RDT_RESOURCE_L3DATA].enabled = false; | |
652 | rdt_resources_all[RDT_RESOURCE_L3CODE].enabled = false; | |
653 | set_l3_qos_cfg(r, false); | |
654 | } | |
655 | } | |
656 | ||
657 | static int parse_rdtgroupfs_options(char *data) | |
658 | { | |
659 | char *token, *o = data; | |
660 | int ret = 0; | |
661 | ||
662 | while ((token = strsep(&o, ",")) != NULL) { | |
663 | if (!*token) | |
664 | return -EINVAL; | |
665 | ||
666 | if (!strcmp(token, "cdp")) | |
667 | ret = cdp_enable(); | |
668 | } | |
669 | ||
670 | return ret; | |
671 | } | |
672 | ||
60cf5e10 FY |
673 | /* |
674 | * We don't allow rdtgroup directories to be created anywhere | |
675 | * except the root directory. Thus when looking for the rdtgroup | |
676 | * structure for a kernfs node we are either looking at a directory, | |
677 | * in which case the rdtgroup structure is pointed at by the "priv" | |
678 | * field, otherwise we have a file, and need only look to the parent | |
679 | * to find the rdtgroup. | |
680 | */ | |
681 | static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn) | |
682 | { | |
f57b3087 FY |
683 | if (kernfs_type(kn) == KERNFS_DIR) { |
684 | /* | |
685 | * All the resource directories use "kn->priv" | |
686 | * to point to the "struct rdtgroup" for the | |
687 | * resource. "info" and its subdirectories don't | |
688 | * have rdtgroup structures, so return NULL here. | |
689 | */ | |
690 | if (kn == kn_info || kn->parent == kn_info) | |
691 | return NULL; | |
692 | else | |
693 | return kn->priv; | |
694 | } else { | |
60cf5e10 | 695 | return kn->parent->priv; |
f57b3087 | 696 | } |
60cf5e10 FY |
697 | } |
698 | ||
699 | struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn) | |
700 | { | |
701 | struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn); | |
702 | ||
f57b3087 FY |
703 | if (!rdtgrp) |
704 | return NULL; | |
705 | ||
60cf5e10 FY |
706 | atomic_inc(&rdtgrp->waitcount); |
707 | kernfs_break_active_protection(kn); | |
708 | ||
709 | mutex_lock(&rdtgroup_mutex); | |
710 | ||
711 | /* Was this group deleted while we waited? */ | |
712 | if (rdtgrp->flags & RDT_DELETED) | |
713 | return NULL; | |
714 | ||
715 | return rdtgrp; | |
716 | } | |
717 | ||
718 | void rdtgroup_kn_unlock(struct kernfs_node *kn) | |
719 | { | |
720 | struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn); | |
721 | ||
f57b3087 FY |
722 | if (!rdtgrp) |
723 | return; | |
724 | ||
60cf5e10 FY |
725 | mutex_unlock(&rdtgroup_mutex); |
726 | ||
727 | if (atomic_dec_and_test(&rdtgrp->waitcount) && | |
728 | (rdtgrp->flags & RDT_DELETED)) { | |
729 | kernfs_unbreak_active_protection(kn); | |
730 | kernfs_put(kn); | |
731 | kfree(rdtgrp); | |
732 | } else { | |
733 | kernfs_unbreak_active_protection(kn); | |
734 | } | |
735 | } | |
736 | ||
5ff193fb FY |
737 | static struct dentry *rdt_mount(struct file_system_type *fs_type, |
738 | int flags, const char *unused_dev_name, | |
739 | void *data) | |
740 | { | |
741 | struct dentry *dentry; | |
742 | int ret; | |
743 | ||
744 | mutex_lock(&rdtgroup_mutex); | |
745 | /* | |
746 | * resctrl file system can only be mounted once. | |
747 | */ | |
748 | if (static_branch_unlikely(&rdt_enable_key)) { | |
749 | dentry = ERR_PTR(-EBUSY); | |
750 | goto out; | |
751 | } | |
752 | ||
753 | ret = parse_rdtgroupfs_options(data); | |
754 | if (ret) { | |
755 | dentry = ERR_PTR(ret); | |
756 | goto out_cdp; | |
757 | } | |
758 | ||
60cf5e10 FY |
759 | closid_init(); |
760 | ||
4e978d06 | 761 | ret = rdtgroup_create_info_dir(rdtgroup_default.kn); |
7bff0af5 SL |
762 | if (ret) { |
763 | dentry = ERR_PTR(ret); | |
4e978d06 | 764 | goto out_cdp; |
7bff0af5 | 765 | } |
4e978d06 | 766 | |
5ff193fb FY |
767 | dentry = kernfs_mount(fs_type, flags, rdt_root, |
768 | RDTGROUP_SUPER_MAGIC, NULL); | |
769 | if (IS_ERR(dentry)) | |
770 | goto out_cdp; | |
771 | ||
772 | static_branch_enable(&rdt_enable_key); | |
773 | goto out; | |
774 | ||
775 | out_cdp: | |
776 | cdp_disable(); | |
777 | out: | |
778 | mutex_unlock(&rdtgroup_mutex); | |
779 | ||
780 | return dentry; | |
781 | } | |
782 | ||
783 | static int reset_all_cbms(struct rdt_resource *r) | |
784 | { | |
785 | struct msr_param msr_param; | |
786 | cpumask_var_t cpu_mask; | |
787 | struct rdt_domain *d; | |
788 | int i, cpu; | |
789 | ||
790 | if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) | |
791 | return -ENOMEM; | |
792 | ||
793 | msr_param.res = r; | |
794 | msr_param.low = 0; | |
795 | msr_param.high = r->num_closid; | |
796 | ||
797 | /* | |
798 | * Disable resource control for this resource by setting all | |
799 | * CBMs in all domains to the maximum mask value. Pick one CPU | |
800 | * from each domain to update the MSRs below. | |
801 | */ | |
802 | list_for_each_entry(d, &r->domains, list) { | |
803 | cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask); | |
804 | ||
805 | for (i = 0; i < r->num_closid; i++) | |
806 | d->cbm[i] = r->max_cbm; | |
807 | } | |
808 | cpu = get_cpu(); | |
809 | /* Update CBM on this cpu if it's in cpu_mask. */ | |
810 | if (cpumask_test_cpu(cpu, cpu_mask)) | |
811 | rdt_cbm_update(&msr_param); | |
812 | /* Update CBM on all other cpus in cpu_mask. */ | |
813 | smp_call_function_many(cpu_mask, rdt_cbm_update, &msr_param, 1); | |
814 | put_cpu(); | |
815 | ||
816 | free_cpumask_var(cpu_mask); | |
817 | ||
818 | return 0; | |
819 | } | |
820 | ||
4e978d06 | 821 | /* |
0efc89be FY |
822 | * Move tasks from one to the other group. If @from is NULL, then all tasks |
823 | * in the systems are moved unconditionally (used for teardown). | |
824 | * | |
825 | * If @mask is not NULL the cpus on which moved tasks are running are set | |
826 | * in that mask so the update smp function call is restricted to affected | |
827 | * cpus. | |
4e978d06 | 828 | */ |
0efc89be FY |
829 | static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, |
830 | struct cpumask *mask) | |
4e978d06 | 831 | { |
e02737d5 FY |
832 | struct task_struct *p, *t; |
833 | ||
e02737d5 | 834 | read_lock(&tasklist_lock); |
0efc89be FY |
835 | for_each_process_thread(p, t) { |
836 | if (!from || t->closid == from->closid) { | |
837 | t->closid = to->closid; | |
838 | #ifdef CONFIG_SMP | |
839 | /* | |
840 | * This is safe on x86 w/o barriers as the ordering | |
841 | * of writing to task_cpu() and t->on_cpu is | |
842 | * reverse to the reading here. The detection is | |
843 | * inaccurate as tasks might move or schedule | |
844 | * before the smp function call takes place. In | |
845 | * such a case the function call is pointless, but | |
846 | * there is no other side effect. | |
847 | */ | |
848 | if (mask && t->on_cpu) | |
849 | cpumask_set_cpu(task_cpu(t), mask); | |
850 | #endif | |
851 | } | |
852 | } | |
e02737d5 | 853 | read_unlock(&tasklist_lock); |
0efc89be FY |
854 | } |
855 | ||
856 | /* | |
857 | * Forcibly remove all of subdirectories under root. | |
858 | */ | |
859 | static void rmdir_all_sub(void) | |
860 | { | |
861 | struct rdtgroup *rdtgrp, *tmp; | |
862 | ||
863 | /* Move all tasks to the default resource group */ | |
864 | rdt_move_group_tasks(NULL, &rdtgroup_default, NULL); | |
60cf5e10 | 865 | |
60cf5e10 FY |
866 | list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) { |
867 | /* Remove each rdtgroup other than root */ | |
868 | if (rdtgrp == &rdtgroup_default) | |
869 | continue; | |
c7cc0cc1 FY |
870 | |
871 | /* | |
872 | * Give any CPUs back to the default group. We cannot copy | |
873 | * cpu_online_mask because a CPU might have executed the | |
874 | * offline callback already, but is still marked online. | |
875 | */ | |
876 | cpumask_or(&rdtgroup_default.cpu_mask, | |
877 | &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); | |
878 | ||
60cf5e10 FY |
879 | kernfs_remove(rdtgrp->kn); |
880 | list_del(&rdtgrp->rdtgroup_list); | |
881 | kfree(rdtgrp); | |
882 | } | |
0efc89be FY |
883 | /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */ |
884 | get_online_cpus(); | |
885 | rdt_update_closid(cpu_online_mask, &rdtgroup_default.closid); | |
886 | put_online_cpus(); | |
887 | ||
4e978d06 FY |
888 | kernfs_remove(kn_info); |
889 | } | |
890 | ||
5ff193fb FY |
891 | static void rdt_kill_sb(struct super_block *sb) |
892 | { | |
893 | struct rdt_resource *r; | |
894 | ||
895 | mutex_lock(&rdtgroup_mutex); | |
896 | ||
897 | /*Put everything back to default values. */ | |
898 | for_each_enabled_rdt_resource(r) | |
899 | reset_all_cbms(r); | |
900 | cdp_disable(); | |
4e978d06 | 901 | rmdir_all_sub(); |
5ff193fb FY |
902 | static_branch_disable(&rdt_enable_key); |
903 | kernfs_kill_sb(sb); | |
904 | mutex_unlock(&rdtgroup_mutex); | |
905 | } | |
906 | ||
907 | static struct file_system_type rdt_fs_type = { | |
908 | .name = "resctrl", | |
909 | .mount = rdt_mount, | |
910 | .kill_sb = rdt_kill_sb, | |
911 | }; | |
912 | ||
60cf5e10 FY |
913 | static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, |
914 | umode_t mode) | |
915 | { | |
916 | struct rdtgroup *parent, *rdtgrp; | |
917 | struct kernfs_node *kn; | |
918 | int ret, closid; | |
919 | ||
920 | /* Only allow mkdir in the root directory */ | |
921 | if (parent_kn != rdtgroup_default.kn) | |
922 | return -EPERM; | |
923 | ||
924 | /* Do not accept '\n' to avoid unparsable situation. */ | |
925 | if (strchr(name, '\n')) | |
926 | return -EINVAL; | |
927 | ||
928 | parent = rdtgroup_kn_lock_live(parent_kn); | |
929 | if (!parent) { | |
930 | ret = -ENODEV; | |
931 | goto out_unlock; | |
932 | } | |
933 | ||
934 | ret = closid_alloc(); | |
935 | if (ret < 0) | |
936 | goto out_unlock; | |
937 | closid = ret; | |
938 | ||
939 | /* allocate the rdtgroup. */ | |
940 | rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL); | |
941 | if (!rdtgrp) { | |
942 | ret = -ENOSPC; | |
943 | goto out_closid_free; | |
944 | } | |
945 | rdtgrp->closid = closid; | |
946 | list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); | |
947 | ||
948 | /* kernfs creates the directory for rdtgrp */ | |
949 | kn = kernfs_create_dir(parent->kn, name, mode, rdtgrp); | |
950 | if (IS_ERR(kn)) { | |
951 | ret = PTR_ERR(kn); | |
952 | goto out_cancel_ref; | |
953 | } | |
954 | rdtgrp->kn = kn; | |
955 | ||
956 | /* | |
957 | * kernfs_remove() will drop the reference count on "kn" which | |
958 | * will free it. But we still need it to stick around for the | |
959 | * rdtgroup_kn_unlock(kn} call below. Take one extra reference | |
960 | * here, which will be dropped inside rdtgroup_kn_unlock(). | |
961 | */ | |
962 | kernfs_get(kn); | |
963 | ||
964 | ret = rdtgroup_kn_set_ugid(kn); | |
965 | if (ret) | |
966 | goto out_destroy; | |
967 | ||
12e0110c TL |
968 | ret = rdtgroup_add_files(kn, rdtgroup_base_files, |
969 | ARRAY_SIZE(rdtgroup_base_files)); | |
970 | if (ret) | |
971 | goto out_destroy; | |
972 | ||
60cf5e10 FY |
973 | kernfs_activate(kn); |
974 | ||
975 | ret = 0; | |
976 | goto out_unlock; | |
977 | ||
978 | out_destroy: | |
979 | kernfs_remove(rdtgrp->kn); | |
980 | out_cancel_ref: | |
981 | list_del(&rdtgrp->rdtgroup_list); | |
982 | kfree(rdtgrp); | |
983 | out_closid_free: | |
984 | closid_free(closid); | |
985 | out_unlock: | |
986 | rdtgroup_kn_unlock(parent_kn); | |
987 | return ret; | |
988 | } | |
989 | ||
990 | static int rdtgroup_rmdir(struct kernfs_node *kn) | |
991 | { | |
0efc89be | 992 | int ret, cpu, closid = rdtgroup_default.closid; |
60cf5e10 | 993 | struct rdtgroup *rdtgrp; |
0efc89be FY |
994 | cpumask_var_t tmpmask; |
995 | ||
996 | if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) | |
997 | return -ENOMEM; | |
60cf5e10 FY |
998 | |
999 | rdtgrp = rdtgroup_kn_lock_live(kn); | |
1000 | if (!rdtgrp) { | |
0efc89be FY |
1001 | ret = -EPERM; |
1002 | goto out; | |
60cf5e10 FY |
1003 | } |
1004 | ||
e02737d5 | 1005 | /* Give any tasks back to the default group */ |
0efc89be | 1006 | rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask); |
e02737d5 | 1007 | |
12e0110c TL |
1008 | /* Give any CPUs back to the default group */ |
1009 | cpumask_or(&rdtgroup_default.cpu_mask, | |
1010 | &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); | |
0efc89be FY |
1011 | |
1012 | /* Update per cpu closid of the moved CPUs first */ | |
1013 | for_each_cpu(cpu, &rdtgrp->cpu_mask) | |
1014 | per_cpu(cpu_closid, cpu) = closid; | |
1015 | /* | |
1016 | * Update the MSR on moved CPUs and CPUs which have moved | |
1017 | * task running on them. | |
1018 | */ | |
1019 | cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); | |
1020 | rdt_update_closid(tmpmask, NULL); | |
12e0110c | 1021 | |
60cf5e10 FY |
1022 | rdtgrp->flags = RDT_DELETED; |
1023 | closid_free(rdtgrp->closid); | |
1024 | list_del(&rdtgrp->rdtgroup_list); | |
1025 | ||
1026 | /* | |
1027 | * one extra hold on this, will drop when we kfree(rdtgrp) | |
1028 | * in rdtgroup_kn_unlock() | |
1029 | */ | |
1030 | kernfs_get(kn); | |
1031 | kernfs_remove(rdtgrp->kn); | |
0efc89be FY |
1032 | ret = 0; |
1033 | out: | |
60cf5e10 | 1034 | rdtgroup_kn_unlock(kn); |
0efc89be FY |
1035 | free_cpumask_var(tmpmask); |
1036 | return ret; | |
60cf5e10 FY |
1037 | } |
1038 | ||
76ae054c SL |
1039 | static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) |
1040 | { | |
1041 | if (rdt_resources_all[RDT_RESOURCE_L3DATA].enabled) | |
1042 | seq_puts(seq, ",cdp"); | |
1043 | return 0; | |
1044 | } | |
1045 | ||
5ff193fb | 1046 | static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = { |
76ae054c SL |
1047 | .mkdir = rdtgroup_mkdir, |
1048 | .rmdir = rdtgroup_rmdir, | |
1049 | .show_options = rdtgroup_show_options, | |
5ff193fb FY |
1050 | }; |
1051 | ||
1052 | static int __init rdtgroup_setup_root(void) | |
1053 | { | |
12e0110c TL |
1054 | int ret; |
1055 | ||
5ff193fb FY |
1056 | rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops, |
1057 | KERNFS_ROOT_CREATE_DEACTIVATED, | |
1058 | &rdtgroup_default); | |
1059 | if (IS_ERR(rdt_root)) | |
1060 | return PTR_ERR(rdt_root); | |
1061 | ||
1062 | mutex_lock(&rdtgroup_mutex); | |
1063 | ||
1064 | rdtgroup_default.closid = 0; | |
1065 | list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); | |
1066 | ||
12e0110c TL |
1067 | ret = rdtgroup_add_files(rdt_root->kn, rdtgroup_base_files, |
1068 | ARRAY_SIZE(rdtgroup_base_files)); | |
1069 | if (ret) { | |
1070 | kernfs_destroy_root(rdt_root); | |
1071 | goto out; | |
1072 | } | |
1073 | ||
5ff193fb FY |
1074 | rdtgroup_default.kn = rdt_root->kn; |
1075 | kernfs_activate(rdtgroup_default.kn); | |
1076 | ||
12e0110c | 1077 | out: |
5ff193fb FY |
1078 | mutex_unlock(&rdtgroup_mutex); |
1079 | ||
12e0110c | 1080 | return ret; |
5ff193fb FY |
1081 | } |
1082 | ||
1083 | /* | |
1084 | * rdtgroup_init - rdtgroup initialization | |
1085 | * | |
1086 | * Setup resctrl file system including set up root, create mount point, | |
1087 | * register rdtgroup filesystem, and initialize files under root directory. | |
1088 | * | |
1089 | * Return: 0 on success or -errno | |
1090 | */ | |
1091 | int __init rdtgroup_init(void) | |
1092 | { | |
1093 | int ret = 0; | |
1094 | ||
1095 | ret = rdtgroup_setup_root(); | |
1096 | if (ret) | |
1097 | return ret; | |
1098 | ||
1099 | ret = sysfs_create_mount_point(fs_kobj, "resctrl"); | |
1100 | if (ret) | |
1101 | goto cleanup_root; | |
1102 | ||
1103 | ret = register_filesystem(&rdt_fs_type); | |
1104 | if (ret) | |
1105 | goto cleanup_mountpoint; | |
1106 | ||
1107 | return 0; | |
1108 | ||
1109 | cleanup_mountpoint: | |
1110 | sysfs_remove_mount_point(fs_kobj, "resctrl"); | |
1111 | cleanup_root: | |
1112 | kernfs_destroy_root(rdt_root); | |
1113 | ||
1114 | return ret; | |
1115 | } |