Loading...
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 | /*
* Virtual Processor Dispatch Trace Log
*
* (C) Copyright IBM Corporation 2009
*
* Author: Jeremy Kerr <jk@ozlabs.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2, or (at your option)
* any later version.
*
* This program is distributed in the hope that 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.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/slab.h>
#include <linux/debugfs.h>
#include <linux/spinlock.h>
#include <asm/smp.h>
#include <asm/uaccess.h>
#include <asm/firmware.h>
#include <asm/lppaca.h>
#include <asm/debug.h>
#include <asm/plpar_wrappers.h>
#include <asm/machdep.h>
struct dtl {
struct dtl_entry *buf;
struct dentry *file;
int cpu;
int buf_entries;
u64 last_idx;
spinlock_t lock;
};
static DEFINE_PER_CPU(struct dtl, cpu_dtl);
/*
* Dispatch trace log event mask:
* 0x7: 0x1: voluntary virtual processor waits
* 0x2: time-slice preempts
* 0x4: virtual partition memory page faults
*/
static u8 dtl_event_mask = 0x7;
/*
* Size of per-cpu log buffers. Firmware requires that the buffer does
* not cross a 4k boundary.
*/
static int dtl_buf_entries = N_DISPATCH_LOG;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
struct dtl_ring {
u64 write_index;
struct dtl_entry *write_ptr;
struct dtl_entry *buf;
struct dtl_entry *buf_end;
u8 saved_dtl_mask;
};
static DEFINE_PER_CPU(struct dtl_ring, dtl_rings);
static atomic_t dtl_count;
/*
* The cpu accounting code controls the DTL ring buffer, and we get
* given entries as they are processed.
*/
static void consume_dtle(struct dtl_entry *dtle, u64 index)
{
struct dtl_ring *dtlr = this_cpu_ptr(&dtl_rings);
struct dtl_entry *wp = dtlr->write_ptr;
struct lppaca *vpa = local_paca->lppaca_ptr;
if (!wp)
return;
*wp = *dtle;
barrier();
/* check for hypervisor ring buffer overflow, ignore this entry if so */
if (index + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx))
return;
++wp;
if (wp == dtlr->buf_end)
wp = dtlr->buf;
dtlr->write_ptr = wp;
/* incrementing write_index makes the new entry visible */
smp_wmb();
++dtlr->write_index;
}
static int dtl_start(struct dtl *dtl)
{
struct dtl_ring *dtlr = &per_cpu(dtl_rings, dtl->cpu);
dtlr->buf = dtl->buf;
dtlr->buf_end = dtl->buf + dtl->buf_entries;
dtlr->write_index = 0;
/* setting write_ptr enables logging into our buffer */
smp_wmb();
dtlr->write_ptr = dtl->buf;
/* enable event logging */
dtlr->saved_dtl_mask = lppaca_of(dtl->cpu).dtl_enable_mask;
lppaca_of(dtl->cpu).dtl_enable_mask |= dtl_event_mask;
dtl_consumer = consume_dtle;
atomic_inc(&dtl_count);
return 0;
}
static void dtl_stop(struct dtl *dtl)
{
struct dtl_ring *dtlr = &per_cpu(dtl_rings, dtl->cpu);
dtlr->write_ptr = NULL;
smp_wmb();
dtlr->buf = NULL;
/* restore dtl_enable_mask */
lppaca_of(dtl->cpu).dtl_enable_mask = dtlr->saved_dtl_mask;
if (atomic_dec_and_test(&dtl_count))
dtl_consumer = NULL;
}
static u64 dtl_current_index(struct dtl *dtl)
{
return per_cpu(dtl_rings, dtl->cpu).write_index;
}
#else /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
static int dtl_start(struct dtl *dtl)
{
unsigned long addr;
int ret, hwcpu;
/* Register our dtl buffer with the hypervisor. The HV expects the
* buffer size to be passed in the second word of the buffer */
((u32 *)dtl->buf)[1] = DISPATCH_LOG_BYTES;
hwcpu = get_hard_smp_processor_id(dtl->cpu);
addr = __pa(dtl->buf);
ret = register_dtl(hwcpu, addr);
if (ret) {
printk(KERN_WARNING "%s: DTL registration for cpu %d (hw %d) "
"failed with %d\n", __func__, dtl->cpu, hwcpu, ret);
return -EIO;
}
/* set our initial buffer indices */
lppaca_of(dtl->cpu).dtl_idx = 0;
/* ensure that our updates to the lppaca fields have occurred before
* we actually enable the logging */
smp_wmb();
/* enable event logging */
lppaca_of(dtl->cpu).dtl_enable_mask = dtl_event_mask;
return 0;
}
static void dtl_stop(struct dtl *dtl)
{
int hwcpu = get_hard_smp_processor_id(dtl->cpu);
lppaca_of(dtl->cpu).dtl_enable_mask = 0x0;
unregister_dtl(hwcpu);
}
static u64 dtl_current_index(struct dtl *dtl)
{
return lppaca_of(dtl->cpu).dtl_idx;
}
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
static int dtl_enable(struct dtl *dtl)
{
long int n_entries;
long int rc;
struct dtl_entry *buf = NULL;
if (!dtl_cache)
return -ENOMEM;
/* only allow one reader */
if (dtl->buf)
return -EBUSY;
n_entries = dtl_buf_entries;
buf = kmem_cache_alloc_node(dtl_cache, GFP_KERNEL, cpu_to_node(dtl->cpu));
if (!buf) {
printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n",
__func__, dtl->cpu);
return -ENOMEM;
}
spin_lock(&dtl->lock);
rc = -EBUSY;
if (!dtl->buf) {
/* store the original allocation size for use during read */
dtl->buf_entries = n_entries;
dtl->buf = buf;
dtl->last_idx = 0;
rc = dtl_start(dtl);
if (rc)
dtl->buf = NULL;
}
spin_unlock(&dtl->lock);
if (rc)
kmem_cache_free(dtl_cache, buf);
return rc;
}
static void dtl_disable(struct dtl *dtl)
{
spin_lock(&dtl->lock);
dtl_stop(dtl);
kmem_cache_free(dtl_cache, dtl->buf);
dtl->buf = NULL;
dtl->buf_entries = 0;
spin_unlock(&dtl->lock);
}
/* file interface */
static int dtl_file_open(struct inode *inode, struct file *filp)
{
struct dtl *dtl = inode->i_private;
int rc;
rc = dtl_enable(dtl);
if (rc)
return rc;
filp->private_data = dtl;
return 0;
}
static int dtl_file_release(struct inode *inode, struct file *filp)
{
struct dtl *dtl = inode->i_private;
dtl_disable(dtl);
return 0;
}
static ssize_t dtl_file_read(struct file *filp, char __user *buf, size_t len,
loff_t *pos)
{
long int rc, n_read, n_req, read_size;
struct dtl *dtl;
u64 cur_idx, last_idx, i;
if ((len % sizeof(struct dtl_entry)) != 0)
return -EINVAL;
dtl = filp->private_data;
/* requested number of entries to read */
n_req = len / sizeof(struct dtl_entry);
/* actual number of entries read */
n_read = 0;
spin_lock(&dtl->lock);
cur_idx = dtl_current_index(dtl);
last_idx = dtl->last_idx;
if (last_idx + dtl->buf_entries <= cur_idx)
last_idx = cur_idx - dtl->buf_entries + 1;
if (last_idx + n_req > cur_idx)
n_req = cur_idx - last_idx;
if (n_req > 0)
dtl->last_idx = last_idx + n_req;
spin_unlock(&dtl->lock);
if (n_req <= 0)
return 0;
i = last_idx % dtl->buf_entries;
/* read the tail of the buffer if we've wrapped */
if (i + n_req > dtl->buf_entries) {
read_size = dtl->buf_entries - i;
rc = copy_to_user(buf, &dtl->buf[i],
read_size * sizeof(struct dtl_entry));
if (rc)
return -EFAULT;
i = 0;
n_req -= read_size;
n_read += read_size;
buf += read_size * sizeof(struct dtl_entry);
}
/* .. and now the head */
rc = copy_to_user(buf, &dtl->buf[i], n_req * sizeof(struct dtl_entry));
if (rc)
return -EFAULT;
n_read += n_req;
return n_read * sizeof(struct dtl_entry);
}
static const struct file_operations dtl_fops = {
.open = dtl_file_open,
.release = dtl_file_release,
.read = dtl_file_read,
.llseek = no_llseek,
};
static struct dentry *dtl_dir;
static int dtl_setup_file(struct dtl *dtl)
{
char name[10];
sprintf(name, "cpu-%d", dtl->cpu);
dtl->file = debugfs_create_file(name, 0400, dtl_dir, dtl, &dtl_fops);
if (!dtl->file)
return -ENOMEM;
return 0;
}
static int dtl_init(void)
{
struct dentry *event_mask_file, *buf_entries_file;
int rc, i;
if (!firmware_has_feature(FW_FEATURE_SPLPAR))
return -ENODEV;
/* set up common debugfs structure */
rc = -ENOMEM;
dtl_dir = debugfs_create_dir("dtl", powerpc_debugfs_root);
if (!dtl_dir) {
printk(KERN_WARNING "%s: can't create dtl root dir\n",
__func__);
goto err;
}
event_mask_file = debugfs_create_x8("dtl_event_mask", 0600,
dtl_dir, &dtl_event_mask);
buf_entries_file = debugfs_create_u32("dtl_buf_entries", 0400,
dtl_dir, &dtl_buf_entries);
if (!event_mask_file || !buf_entries_file) {
printk(KERN_WARNING "%s: can't create dtl files\n", __func__);
goto err_remove_dir;
}
/* set up the per-cpu log structures */
for_each_possible_cpu(i) {
struct dtl *dtl = &per_cpu(cpu_dtl, i);
spin_lock_init(&dtl->lock);
dtl->cpu = i;
rc = dtl_setup_file(dtl);
if (rc)
goto err_remove_dir;
}
return 0;
err_remove_dir:
debugfs_remove_recursive(dtl_dir);
err:
return rc;
}
machine_arch_initcall(pseries, dtl_init);
|