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
|
// SPDX-License-Identifier: GPL-2.0
/*
* Intel Platform Monitory Technology Telemetry driver
*
* Copyright (c) 2020, Intel Corporation.
* All Rights Reserved.
*
* Author: "Alexander Duyck" <alexander.h.duyck@linux.intel.com>
*/
#include <linux/kernel.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/pci.h>
#include "../vsec.h"
#include "class.h"
#define PMT_XA_START 0
#define PMT_XA_MAX INT_MAX
#define PMT_XA_LIMIT XA_LIMIT(PMT_XA_START, PMT_XA_MAX)
#define GUID_SPR_PUNIT 0x9956f43f
bool intel_pmt_is_early_client_hw(struct device *dev)
{
struct intel_vsec_device *ivdev = dev_to_ivdev(dev);
/*
* Early implementations of PMT on client platforms have some
* differences from the server platforms (which use the Out Of Band
* Management Services Module OOBMSM).
*/
return !!(ivdev->quirks & VSEC_QUIRK_EARLY_HW);
}
EXPORT_SYMBOL_NS_GPL(intel_pmt_is_early_client_hw, INTEL_PMT);
static inline int
pmt_memcpy64_fromio(void *to, const u64 __iomem *from, size_t count)
{
int i, remain;
u64 *buf = to;
if (!IS_ALIGNED((unsigned long)from, 8))
return -EFAULT;
for (i = 0; i < count/8; i++)
buf[i] = readq(&from[i]);
/* Copy any remaining bytes */
remain = count % 8;
if (remain) {
u64 tmp = readq(&from[i]);
memcpy(&buf[i], &tmp, remain);
}
return count;
}
/*
* sysfs
*/
static ssize_t
intel_pmt_read(struct file *filp, struct kobject *kobj,
struct bin_attribute *attr, char *buf, loff_t off,
size_t count)
{
struct intel_pmt_entry *entry = container_of(attr,
struct intel_pmt_entry,
pmt_bin_attr);
if (off < 0)
return -EINVAL;
if (off >= entry->size)
return 0;
if (count > entry->size - off)
count = entry->size - off;
if (entry->guid == GUID_SPR_PUNIT)
/* PUNIT on SPR only supports aligned 64-bit read */
count = pmt_memcpy64_fromio(buf, entry->base + off, count);
else
memcpy_fromio(buf, entry->base + off, count);
return count;
}
static int
intel_pmt_mmap(struct file *filp, struct kobject *kobj,
struct bin_attribute *attr, struct vm_area_struct *vma)
{
struct intel_pmt_entry *entry = container_of(attr,
struct intel_pmt_entry,
pmt_bin_attr);
unsigned long vsize = vma->vm_end - vma->vm_start;
struct device *dev = kobj_to_dev(kobj);
unsigned long phys = entry->base_addr;
unsigned long pfn = PFN_DOWN(phys);
unsigned long psize;
if (vma->vm_flags & (VM_WRITE | VM_MAYWRITE))
return -EROFS;
psize = (PFN_UP(entry->base_addr + entry->size) - pfn) * PAGE_SIZE;
if (vsize > psize) {
dev_err(dev, "Requested mmap size is too large\n");
return -EINVAL;
}
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
if (io_remap_pfn_range(vma, vma->vm_start, pfn,
vsize, vma->vm_page_prot))
return -EAGAIN;
return 0;
}
static ssize_t
guid_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct intel_pmt_entry *entry = dev_get_drvdata(dev);
return sprintf(buf, "0x%x\n", entry->guid);
}
static DEVICE_ATTR_RO(guid);
static ssize_t size_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct intel_pmt_entry *entry = dev_get_drvdata(dev);
return sprintf(buf, "%zu\n", entry->size);
}
static DEVICE_ATTR_RO(size);
static ssize_t
offset_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct intel_pmt_entry *entry = dev_get_drvdata(dev);
return sprintf(buf, "%lu\n", offset_in_page(entry->base_addr));
}
static DEVICE_ATTR_RO(offset);
static struct attribute *intel_pmt_attrs[] = {
&dev_attr_guid.attr,
&dev_attr_size.attr,
&dev_attr_offset.attr,
NULL
};
ATTRIBUTE_GROUPS(intel_pmt);
static struct class intel_pmt_class = {
.name = "intel_pmt",
.dev_groups = intel_pmt_groups,
};
static int intel_pmt_populate_entry(struct intel_pmt_entry *entry,
struct intel_pmt_header *header,
struct intel_vsec_device *ivdev,
struct resource *disc_res)
{
struct pci_dev *pci_dev = ivdev->pcidev;
struct device *dev = &ivdev->auxdev.dev;
u8 bir;
/*
* The base offset should always be 8 byte aligned.
*
* For non-local access types the lower 3 bits of base offset
* contains the index of the base address register where the
* telemetry can be found.
*/
bir = GET_BIR(header->base_offset);
/* Local access and BARID only for now */
switch (header->access_type) {
case ACCESS_LOCAL:
if (bir) {
dev_err(dev,
"Unsupported BAR index %d for access type %d\n",
bir, header->access_type);
return -EINVAL;
}
/*
* For access_type LOCAL, the base address is as follows:
* base address = end of discovery region + base offset
*/
entry->base_addr = disc_res->end + 1 + header->base_offset;
/*
* Some hardware use a different calculation for the base address
* when access_type == ACCESS_LOCAL. On the these systems
* ACCCESS_LOCAL refers to an address in the same BAR as the
* header but at a fixed offset. But as the header address was
* supplied to the driver, we don't know which BAR it was in.
* So search for the bar whose range includes the header address.
*/
if (intel_pmt_is_early_client_hw(dev)) {
int i;
entry->base_addr = 0;
for (i = 0; i < 6; i++)
if (disc_res->start >= pci_resource_start(pci_dev, i) &&
(disc_res->start <= pci_resource_end(pci_dev, i))) {
entry->base_addr = pci_resource_start(pci_dev, i) +
header->base_offset;
break;
}
if (!entry->base_addr)
return -EINVAL;
}
break;
case ACCESS_BARID:
/* Use the provided base address if it exists */
if (ivdev->base_addr) {
entry->base_addr = ivdev->base_addr +
GET_ADDRESS(header->base_offset);
break;
}
/*
* If another BAR was specified then the base offset
* represents the offset within that BAR. SO retrieve the
* address from the parent PCI device and add offset.
*/
entry->base_addr = pci_resource_start(pci_dev, bir) +
GET_ADDRESS(header->base_offset);
break;
default:
dev_err(dev, "Unsupported access type %d\n",
header->access_type);
return -EINVAL;
}
entry->guid = header->guid;
entry->size = header->size;
return 0;
}
static int intel_pmt_dev_register(struct intel_pmt_entry *entry,
struct intel_pmt_namespace *ns,
struct device *parent)
{
struct resource res = {0};
struct device *dev;
int ret;
ret = xa_alloc(ns->xa, &entry->devid, entry, PMT_XA_LIMIT, GFP_KERNEL);
if (ret)
return ret;
dev = device_create(&intel_pmt_class, parent, MKDEV(0, 0), entry,
"%s%d", ns->name, entry->devid);
if (IS_ERR(dev)) {
dev_err(parent, "Could not create %s%d device node\n",
ns->name, entry->devid);
ret = PTR_ERR(dev);
goto fail_dev_create;
}
entry->kobj = &dev->kobj;
if (ns->attr_grp) {
ret = sysfs_create_group(entry->kobj, ns->attr_grp);
if (ret)
goto fail_sysfs;
}
/* if size is 0 assume no data buffer, so no file needed */
if (!entry->size)
return 0;
res.start = entry->base_addr;
res.end = res.start + entry->size - 1;
res.flags = IORESOURCE_MEM;
entry->base = devm_ioremap_resource(dev, &res);
if (IS_ERR(entry->base)) {
ret = PTR_ERR(entry->base);
goto fail_ioremap;
}
sysfs_bin_attr_init(&entry->pmt_bin_attr);
entry->pmt_bin_attr.attr.name = ns->name;
entry->pmt_bin_attr.attr.mode = 0440;
entry->pmt_bin_attr.mmap = intel_pmt_mmap;
entry->pmt_bin_attr.read = intel_pmt_read;
entry->pmt_bin_attr.size = entry->size;
ret = sysfs_create_bin_file(&dev->kobj, &entry->pmt_bin_attr);
if (!ret)
return 0;
fail_ioremap:
if (ns->attr_grp)
sysfs_remove_group(entry->kobj, ns->attr_grp);
fail_sysfs:
device_unregister(dev);
fail_dev_create:
xa_erase(ns->xa, entry->devid);
return ret;
}
int intel_pmt_dev_create(struct intel_pmt_entry *entry, struct intel_pmt_namespace *ns,
struct intel_vsec_device *intel_vsec_dev, int idx)
{
struct device *dev = &intel_vsec_dev->auxdev.dev;
struct intel_pmt_header header;
struct resource *disc_res;
int ret;
disc_res = &intel_vsec_dev->resource[idx];
entry->disc_table = devm_ioremap_resource(dev, disc_res);
if (IS_ERR(entry->disc_table))
return PTR_ERR(entry->disc_table);
ret = ns->pmt_header_decode(entry, &header, dev);
if (ret)
return ret;
ret = intel_pmt_populate_entry(entry, &header, intel_vsec_dev, disc_res);
if (ret)
return ret;
return intel_pmt_dev_register(entry, ns, dev);
}
EXPORT_SYMBOL_NS_GPL(intel_pmt_dev_create, INTEL_PMT);
void intel_pmt_dev_destroy(struct intel_pmt_entry *entry,
struct intel_pmt_namespace *ns)
{
struct device *dev = kobj_to_dev(entry->kobj);
if (entry->size)
sysfs_remove_bin_file(entry->kobj, &entry->pmt_bin_attr);
if (ns->attr_grp)
sysfs_remove_group(entry->kobj, ns->attr_grp);
device_unregister(dev);
xa_erase(ns->xa, entry->devid);
}
EXPORT_SYMBOL_NS_GPL(intel_pmt_dev_destroy, INTEL_PMT);
static int __init pmt_class_init(void)
{
return class_register(&intel_pmt_class);
}
static void __exit pmt_class_exit(void)
{
class_unregister(&intel_pmt_class);
}
module_init(pmt_class_init);
module_exit(pmt_class_exit);
MODULE_AUTHOR("Alexander Duyck <alexander.h.duyck@linux.intel.com>");
MODULE_DESCRIPTION("Intel PMT Class driver");
MODULE_LICENSE("GPL v2");
|