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
|
/*
* 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>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* 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/kernfs.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <asm/intel_rdt.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)
return false;
ret = kstrtoul(buf, 10, &bw);
if (ret)
return false;
if (bw < r->membw.min_bw || bw > r->default_ctrl)
return false;
*data = roundup(bw, (unsigned long)r->membw.bw_gran);
return true;
}
int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d)
{
unsigned long data;
if (d->have_new_ctrl)
return -EINVAL;
if (!bw_validate(buf, &data, r))
return -EINVAL;
d->new_ctrl = data;
d->have_new_ctrl = true;
return 0;
}
/*
* Check whether a cache bit mask is valid. The SDM says:
* Please note that all (and only) contiguous '1' combinations
* are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
* Additionally Haswell requires at least two bits set.
*/
static bool cbm_validate(char *buf, unsigned long *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)
return false;
if (val == 0 || val > r->default_ctrl)
return false;
first_bit = find_first_bit(&val, cbm_len);
zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)
return false;
if ((zero_bit - first_bit) < 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(char *buf, struct rdt_resource *r, struct rdt_domain *d)
{
unsigned long data;
if (d->have_new_ctrl)
return -EINVAL;
if(!cbm_validate(buf, &data, r))
return -EINVAL;
d->new_ctrl = data;
d->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 rdt_resource *r)
{
char *dom = NULL, *id;
struct rdt_domain *d;
unsigned long dom_id;
next:
if (!line || line[0] == '\0')
return 0;
dom = strsep(&line, ";");
id = strsep(&dom, "=");
if (!dom || kstrtoul(id, 10, &dom_id))
return -EINVAL;
dom = strim(dom);
list_for_each_entry(d, &r->domains, list) {
if (d->id == dom_id) {
if (r->parse_ctrlval(dom, r, d))
return -EINVAL;
goto next;
}
}
return -EINVAL;
}
static int update_domains(struct rdt_resource *r, int closid)
{
struct msr_param msr_param;
cpumask_var_t cpu_mask;
struct rdt_domain *d;
int cpu;
if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
return -ENOMEM;
msr_param.low = closid;
msr_param.high = msr_param.low + 1;
msr_param.res = r;
list_for_each_entry(d, &r->domains, list) {
if (d->have_new_ctrl && d->new_ctrl != d->ctrl_val[closid]) {
cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
d->ctrl_val[closid] = d->new_ctrl;
}
}
if (cpumask_empty(cpu_mask))
goto done;
cpu = get_cpu();
/* Update CBM on this cpu if it's in cpu_mask. */
if (cpumask_test_cpu(cpu, cpu_mask))
rdt_ctrl_update(&msr_param);
/* Update CBM on other cpus. */
smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
put_cpu();
done:
free_cpumask_var(cpu_mask);
return 0;
}
static int rdtgroup_parse_resource(char *resname, char *tok, int closid)
{
struct rdt_resource *r;
for_each_enabled_rdt_resource(r) {
if (!strcmp(resname, r->name) && closid < r->num_closid)
return parse_line(tok, r);
}
return -EINVAL;
}
ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct rdtgroup *rdtgrp;
struct rdt_domain *dom;
struct rdt_resource *r;
char *tok, *resname;
int closid, 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;
}
closid = rdtgrp->closid;
for_each_enabled_rdt_resource(r) {
list_for_each_entry(dom, &r->domains, list)
dom->have_new_ctrl = false;
}
while ((tok = strsep(&buf, "\n")) != NULL) {
resname = strim(strsep(&tok, ":"));
if (!tok) {
ret = -EINVAL;
goto out;
}
ret = rdtgroup_parse_resource(resname, tok, closid);
if (ret)
goto out;
}
for_each_enabled_rdt_resource(r) {
ret = update_domains(r, closid);
if (ret)
goto out;
}
out:
rdtgroup_kn_unlock(of->kn);
return ret ?: nbytes;
}
static void show_doms(struct seq_file *s, struct rdt_resource *r, int closid)
{
struct rdt_domain *dom;
bool sep = false;
seq_printf(s, "%*s:", max_name_width, r->name);
list_for_each_entry(dom, &r->domains, list) {
if (sep)
seq_puts(s, ";");
seq_printf(s, r->format_str, dom->id, max_data_width,
dom->ctrl_val[closid]);
sep = true;
}
seq_puts(s, "\n");
}
int rdtgroup_schemata_show(struct kernfs_open_file *of,
struct seq_file *s, void *v)
{
struct rdtgroup *rdtgrp;
struct rdt_resource *r;
int closid, ret = 0;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (rdtgrp) {
closid = rdtgrp->closid;
for_each_enabled_rdt_resource(r) {
if (closid < r->num_closid)
show_doms(s, r, closid);
}
} else {
ret = -ENOENT;
}
rdtgroup_kn_unlock(of->kn);
return
|