Blame view
mm/vmstat.c
47.4 KB
f6ac2354d [PATCH] zoned vm ... |
1 2 3 4 5 |
/* * linux/mm/vmstat.c * * Manages VM statistics * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds |
2244b95a7 [PATCH] zoned vm ... |
6 7 8 9 |
* * zoned VM statistics * Copyright (C) 2006 Silicon Graphics, Inc., * Christoph Lameter <christoph@lameter.com> |
7cc36bbdd vmstat: on-demand... |
10 |
* Copyright (C) 2008-2014 Christoph Lameter |
f6ac2354d [PATCH] zoned vm ... |
11 |
*/ |
8f32f7e5a proc: move /proc/... |
12 |
#include <linux/fs.h> |
f6ac2354d [PATCH] zoned vm ... |
13 |
#include <linux/mm.h> |
4e950f6f0 Remove fs.h from ... |
14 |
#include <linux/err.h> |
2244b95a7 [PATCH] zoned vm ... |
15 |
#include <linux/module.h> |
5a0e3ad6a include cleanup: ... |
16 |
#include <linux/slab.h> |
df9ecaba3 [PATCH] ZVC: Scal... |
17 |
#include <linux/cpu.h> |
7cc36bbdd vmstat: on-demand... |
18 |
#include <linux/cpumask.h> |
c748e1340 mm/vmstat.c: prop... |
19 |
#include <linux/vmstat.h> |
3c4868710 mm/vmstat.c: fix/... |
20 21 22 |
#include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/debugfs.h> |
e8edc6e03 Detach sched.h fr... |
23 |
#include <linux/sched.h> |
f1a5ab121 mm: export fragme... |
24 |
#include <linux/math64.h> |
79da826ae writeback: report... |
25 |
#include <linux/writeback.h> |
36deb0be3 vmstat: include c... |
26 |
#include <linux/compaction.h> |
6e543d578 mm: vmscan: fix d... |
27 |
#include <linux/mm_inline.h> |
48c96a368 mm/page_owner: ke... |
28 29 |
#include <linux/page_ext.h> #include <linux/page_owner.h> |
6e543d578 mm: vmscan: fix d... |
30 31 |
#include "internal.h" |
f6ac2354d [PATCH] zoned vm ... |
32 |
|
f8891e5e1 [PATCH] Light wei... |
33 34 35 |
#ifdef CONFIG_VM_EVENT_COUNTERS DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}}; EXPORT_PER_CPU_SYMBOL(vm_event_states); |
31f961a89 mm: use for_each_... |
36 |
static void sum_vm_events(unsigned long *ret) |
f8891e5e1 [PATCH] Light wei... |
37 |
{ |
9eccf2a81 vmstat: remove pr... |
38 |
int cpu; |
f8891e5e1 [PATCH] Light wei... |
39 40 41 |
int i; memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long)); |
31f961a89 mm: use for_each_... |
42 |
for_each_online_cpu(cpu) { |
f8891e5e1 [PATCH] Light wei... |
43 |
struct vm_event_state *this = &per_cpu(vm_event_states, cpu); |
f8891e5e1 [PATCH] Light wei... |
44 45 46 47 48 49 50 51 52 53 54 55 |
for (i = 0; i < NR_VM_EVENT_ITEMS; i++) ret[i] += this->event[i]; } } /* * Accumulate the vm event counters across all CPUs. * The result is unavoidably approximate - it can change * during and after execution of this function. */ void all_vm_events(unsigned long *ret) { |
b5be11329 make vmstat cpu-u... |
56 |
get_online_cpus(); |
31f961a89 mm: use for_each_... |
57 |
sum_vm_events(ret); |
b5be11329 make vmstat cpu-u... |
58 |
put_online_cpus(); |
f8891e5e1 [PATCH] Light wei... |
59 |
} |
32dd66fce [PATCH] vmstat: e... |
60 |
EXPORT_SYMBOL_GPL(all_vm_events); |
f8891e5e1 [PATCH] Light wei... |
61 |
|
f8891e5e1 [PATCH] Light wei... |
62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
/* * Fold the foreign cpu events into our own. * * This is adding to the events on one processor * but keeps the global counts constant. */ void vm_events_fold_cpu(int cpu) { struct vm_event_state *fold_state = &per_cpu(vm_event_states, cpu); int i; for (i = 0; i < NR_VM_EVENT_ITEMS; i++) { count_vm_events(i, fold_state->event[i]); fold_state->event[i] = 0; } } |
f8891e5e1 [PATCH] Light wei... |
78 79 |
#endif /* CONFIG_VM_EVENT_COUNTERS */ |
2244b95a7 [PATCH] zoned vm ... |
80 81 82 83 84 |
/* * Manage combined zone based / global counters * * vm_stat contains the global counters */ |
75ef71840 mm, vmstat: add i... |
85 86 87 88 |
atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp; atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp; EXPORT_SYMBOL(vm_zone_stat); EXPORT_SYMBOL(vm_node_stat); |
2244b95a7 [PATCH] zoned vm ... |
89 90 |
#ifdef CONFIG_SMP |
b44129b30 mm: vmstat: use a... |
91 |
int calculate_pressure_threshold(struct zone *zone) |
88f5acf88 mm: page allocato... |
92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 |
{ int threshold; int watermark_distance; /* * As vmstats are not up to date, there is drift between the estimated * and real values. For high thresholds and a high number of CPUs, it * is possible for the min watermark to be breached while the estimated * value looks fine. The pressure threshold is a reduced value such * that even the maximum amount of drift will not accidentally breach * the min watermark */ watermark_distance = low_wmark_pages(zone) - min_wmark_pages(zone); threshold = max(1, (int)(watermark_distance / num_online_cpus())); /* * Maximum threshold is 125 */ threshold = min(125, threshold); return threshold; } |
b44129b30 mm: vmstat: use a... |
114 |
int calculate_normal_threshold(struct zone *zone) |
df9ecaba3 [PATCH] ZVC: Scal... |
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 |
{ int threshold; int mem; /* memory in 128 MB units */ /* * The threshold scales with the number of processors and the amount * of memory per zone. More memory means that we can defer updates for * longer, more processors could lead to more contention. * fls() is used to have a cheap way of logarithmic scaling. * * Some sample thresholds: * * Threshold Processors (fls) Zonesize fls(mem+1) * ------------------------------------------------------------------ * 8 1 1 0.9-1 GB 4 * 16 2 2 0.9-1 GB 4 * 20 2 2 1-2 GB 5 * 24 2 2 2-4 GB 6 * 28 2 2 4-8 GB 7 * 32 2 2 8-16 GB 8 * 4 2 2 <128M 1 * 30 4 3 2-4 GB 5 * 48 4 3 8-16 GB 8 * 32 8 4 1-2 GB 4 * 32 8 4 0.9-1GB 4 * 10 16 5 <128M 1 * 40 16 5 900M 4 * 70 64 7 2-4 GB 5 * 84 64 7 4-8 GB 6 * 108 512 9 4-8 GB 6 * 125 1024 10 8-16 GB 8 * 125 1024 10 16-32 GB 9 */ |
b40da0494 mm: use zone->pre... |
148 |
mem = zone->managed_pages >> (27 - PAGE_SHIFT); |
df9ecaba3 [PATCH] ZVC: Scal... |
149 150 151 152 153 154 155 156 157 158 |
threshold = 2 * fls(num_online_cpus()) * (1 + fls(mem)); /* * Maximum threshold is 125 */ threshold = min(125, threshold); return threshold; } |
2244b95a7 [PATCH] zoned vm ... |
159 160 |
/* |
df9ecaba3 [PATCH] ZVC: Scal... |
161 |
* Refresh the thresholds for each zone. |
2244b95a7 [PATCH] zoned vm ... |
162 |
*/ |
a6cccdc36 mm, mem-hotplug: ... |
163 |
void refresh_zone_stat_thresholds(void) |
2244b95a7 [PATCH] zoned vm ... |
164 |
{ |
75ef71840 mm, vmstat: add i... |
165 |
struct pglist_data *pgdat; |
df9ecaba3 [PATCH] ZVC: Scal... |
166 167 168 |
struct zone *zone; int cpu; int threshold; |
75ef71840 mm, vmstat: add i... |
169 170 171 172 173 174 |
/* Zero current pgdat thresholds */ for_each_online_pgdat(pgdat) { for_each_online_cpu(cpu) { per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold = 0; } } |
ee99c71c5 mm: introduce for... |
175 |
for_each_populated_zone(zone) { |
75ef71840 mm, vmstat: add i... |
176 |
struct pglist_data *pgdat = zone->zone_pgdat; |
aa4548403 mm: page allocato... |
177 |
unsigned long max_drift, tolerate_drift; |
b44129b30 mm: vmstat: use a... |
178 |
threshold = calculate_normal_threshold(zone); |
df9ecaba3 [PATCH] ZVC: Scal... |
179 |
|
75ef71840 mm, vmstat: add i... |
180 181 |
for_each_online_cpu(cpu) { int pgdat_threshold; |
99dcc3e5a this_cpu: Page al... |
182 183 |
per_cpu_ptr(zone->pageset, cpu)->stat_threshold = threshold; |
aa4548403 mm: page allocato... |
184 |
|
75ef71840 mm, vmstat: add i... |
185 186 187 188 189 |
/* Base nodestat threshold on the largest populated zone. */ pgdat_threshold = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold; per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->stat_threshold = max(threshold, pgdat_threshold); } |
aa4548403 mm: page allocato... |
190 191 192 193 194 195 196 197 198 199 |
/* * Only set percpu_drift_mark if there is a danger that * NR_FREE_PAGES reports the low watermark is ok when in fact * the min watermark could be breached by an allocation */ tolerate_drift = low_wmark_pages(zone) - min_wmark_pages(zone); max_drift = num_online_cpus() * threshold; if (max_drift > tolerate_drift) zone->percpu_drift_mark = high_wmark_pages(zone) + max_drift; |
df9ecaba3 [PATCH] ZVC: Scal... |
200 |
} |
2244b95a7 [PATCH] zoned vm ... |
201 |
} |
b44129b30 mm: vmstat: use a... |
202 203 |
void set_pgdat_percpu_threshold(pg_data_t *pgdat, int (*calculate_pressure)(struct zone *)) |
88f5acf88 mm: page allocato... |
204 205 206 207 208 |
{ struct zone *zone; int cpu; int threshold; int i; |
88f5acf88 mm: page allocato... |
209 210 211 212 |
for (i = 0; i < pgdat->nr_zones; i++) { zone = &pgdat->node_zones[i]; if (!zone->percpu_drift_mark) continue; |
b44129b30 mm: vmstat: use a... |
213 |
threshold = (*calculate_pressure)(zone); |
bb0b6dffa mm: vmscan: only ... |
214 |
for_each_online_cpu(cpu) |
88f5acf88 mm: page allocato... |
215 216 217 |
per_cpu_ptr(zone->pageset, cpu)->stat_threshold = threshold; } |
88f5acf88 mm: page allocato... |
218 |
} |
2244b95a7 [PATCH] zoned vm ... |
219 |
/* |
bea04b073 mm: use the light... |
220 221 222 |
* For use when we know that interrupts are disabled, * or when we know that preemption is disabled and that * particular counter cannot be updated from interrupt context. |
2244b95a7 [PATCH] zoned vm ... |
223 224 |
*/ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, |
6cdb18ad9 mm/vmstat: fix ov... |
225 |
long delta) |
2244b95a7 [PATCH] zoned vm ... |
226 |
{ |
12938a922 vmstat: Optimize ... |
227 228 |
struct per_cpu_pageset __percpu *pcp = zone->pageset; s8 __percpu *p = pcp->vm_stat_diff + item; |
2244b95a7 [PATCH] zoned vm ... |
229 |
long x; |
12938a922 vmstat: Optimize ... |
230 231 232 |
long t; x = delta + __this_cpu_read(*p); |
2244b95a7 [PATCH] zoned vm ... |
233 |
|
12938a922 vmstat: Optimize ... |
234 |
t = __this_cpu_read(pcp->stat_threshold); |
2244b95a7 [PATCH] zoned vm ... |
235 |
|
12938a922 vmstat: Optimize ... |
236 |
if (unlikely(x > t || x < -t)) { |
2244b95a7 [PATCH] zoned vm ... |
237 238 239 |
zone_page_state_add(x, zone, item); x = 0; } |
12938a922 vmstat: Optimize ... |
240 |
__this_cpu_write(*p, x); |
2244b95a7 [PATCH] zoned vm ... |
241 242 |
} EXPORT_SYMBOL(__mod_zone_page_state); |
75ef71840 mm, vmstat: add i... |
243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 |
void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, long delta) { struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; s8 __percpu *p = pcp->vm_node_stat_diff + item; long x; long t; x = delta + __this_cpu_read(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(x > t || x < -t)) { node_page_state_add(x, pgdat, item); x = 0; } __this_cpu_write(*p, x); } EXPORT_SYMBOL(__mod_node_page_state); |
2244b95a7 [PATCH] zoned vm ... |
262 |
/* |
2244b95a7 [PATCH] zoned vm ... |
263 264 265 266 267 268 269 270 271 |
* Optimized increment and decrement functions. * * These are only for a single page and therefore can take a struct page * * argument instead of struct zone *. This allows the inclusion of the code * generated for page_zone(page) into the optimized functions. * * No overflow check is necessary and therefore the differential can be * incremented or decremented in place which may allow the compilers to * generate better code. |
2244b95a7 [PATCH] zoned vm ... |
272 273 274 |
* The increment or decrement is known and therefore one boundary check can * be omitted. * |
df9ecaba3 [PATCH] ZVC: Scal... |
275 276 277 |
* NOTE: These functions are very performance sensitive. Change only * with care. * |
2244b95a7 [PATCH] zoned vm ... |
278 279 280 281 282 283 284 |
* Some processors have inc/dec instructions that are atomic vs an interrupt. * However, the code must first determine the differential location in a zone * based on the processor number and then inc/dec the counter. There is no * guarantee without disabling preemption that the processor will not change * in between and therefore the atomicity vs. interrupt cannot be exploited * in a useful way here. */ |
c87853859 [PATCH] Use ZVC f... |
285 |
void __inc_zone_state(struct zone *zone, enum zone_stat_item item) |
2244b95a7 [PATCH] zoned vm ... |
286 |
{ |
12938a922 vmstat: Optimize ... |
287 288 289 |
struct per_cpu_pageset __percpu *pcp = zone->pageset; s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; |
2244b95a7 [PATCH] zoned vm ... |
290 |
|
908ee0f12 vmstat: Use this_... |
291 |
v = __this_cpu_inc_return(*p); |
12938a922 vmstat: Optimize ... |
292 293 294 |
t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v > t)) { s8 overstep = t >> 1; |
df9ecaba3 [PATCH] ZVC: Scal... |
295 |
|
12938a922 vmstat: Optimize ... |
296 297 |
zone_page_state_add(v + overstep, zone, item); __this_cpu_write(*p, -overstep); |
2244b95a7 [PATCH] zoned vm ... |
298 299 |
} } |
ca889e6c4 [PATCH] Use Zoned... |
300 |
|
75ef71840 mm, vmstat: add i... |
301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 |
void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) { struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; s8 __percpu *p = pcp->vm_node_stat_diff + item; s8 v, t; v = __this_cpu_inc_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v > t)) { s8 overstep = t >> 1; node_page_state_add(v + overstep, pgdat, item); __this_cpu_write(*p, -overstep); } } |
ca889e6c4 [PATCH] Use Zoned... |
316 317 318 319 |
void __inc_zone_page_state(struct page *page, enum zone_stat_item item) { __inc_zone_state(page_zone(page), item); } |
2244b95a7 [PATCH] zoned vm ... |
320 |
EXPORT_SYMBOL(__inc_zone_page_state); |
75ef71840 mm, vmstat: add i... |
321 322 323 324 325 |
void __inc_node_page_state(struct page *page, enum node_stat_item item) { __inc_node_state(page_pgdat(page), item); } EXPORT_SYMBOL(__inc_node_page_state); |
c87853859 [PATCH] Use ZVC f... |
326 |
void __dec_zone_state(struct zone *zone, enum zone_stat_item item) |
2244b95a7 [PATCH] zoned vm ... |
327 |
{ |
12938a922 vmstat: Optimize ... |
328 329 330 |
struct per_cpu_pageset __percpu *pcp = zone->pageset; s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; |
2244b95a7 [PATCH] zoned vm ... |
331 |
|
908ee0f12 vmstat: Use this_... |
332 |
v = __this_cpu_dec_return(*p); |
12938a922 vmstat: Optimize ... |
333 334 335 |
t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v < - t)) { s8 overstep = t >> 1; |
2244b95a7 [PATCH] zoned vm ... |
336 |
|
12938a922 vmstat: Optimize ... |
337 338 |
zone_page_state_add(v - overstep, zone, item); __this_cpu_write(*p, overstep); |
2244b95a7 [PATCH] zoned vm ... |
339 340 |
} } |
c87853859 [PATCH] Use ZVC f... |
341 |
|
75ef71840 mm, vmstat: add i... |
342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 |
void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) { struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; s8 __percpu *p = pcp->vm_node_stat_diff + item; s8 v, t; v = __this_cpu_dec_return(*p); t = __this_cpu_read(pcp->stat_threshold); if (unlikely(v < - t)) { s8 overstep = t >> 1; node_page_state_add(v - overstep, pgdat, item); __this_cpu_write(*p, overstep); } } |
c87853859 [PATCH] Use ZVC f... |
357 358 359 360 |
void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } |
2244b95a7 [PATCH] zoned vm ... |
361 |
EXPORT_SYMBOL(__dec_zone_page_state); |
75ef71840 mm, vmstat: add i... |
362 363 364 365 366 |
void __dec_node_page_state(struct page *page, enum node_stat_item item) { __dec_node_state(page_pgdat(page), item); } EXPORT_SYMBOL(__dec_node_page_state); |
4156153c4 mm,x86,um: move C... |
367 |
#ifdef CONFIG_HAVE_CMPXCHG_LOCAL |
7c8391206 vmstat: User per ... |
368 369 370 371 372 373 374 375 376 377 378 379 |
/* * If we have cmpxchg_local support then we do not need to incur the overhead * that comes with local_irq_save/restore if we use this_cpu_cmpxchg. * * mod_state() modifies the zone counter state through atomic per cpu * operations. * * Overstep mode specifies how overstep should handled: * 0 No overstepping * 1 Overstepping half of threshold * -1 Overstepping minus half of threshold */ |
75ef71840 mm, vmstat: add i... |
380 381 |
static inline void mod_zone_state(struct zone *zone, enum zone_stat_item item, long delta, int overstep_mode) |
7c8391206 vmstat: User per ... |
382 383 384 385 386 387 388 389 390 391 392 |
{ struct per_cpu_pageset __percpu *pcp = zone->pageset; s8 __percpu *p = pcp->vm_stat_diff + item; long o, n, t, z; do { z = 0; /* overflow to zone counters */ /* * The fetching of the stat_threshold is racy. We may apply * a counter threshold to the wrong the cpu if we get |
d3bc23671 vmstat: update co... |
393 394 395 396 397 398 |
* rescheduled while executing here. However, the next * counter update will apply the threshold again and * therefore bring the counter under the threshold again. * * Most of the time the thresholds are the same anyways * for all cpus in a zone. |
7c8391206 vmstat: User per ... |
399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 |
*/ t = this_cpu_read(pcp->stat_threshold); o = this_cpu_read(*p); n = delta + o; if (n > t || n < -t) { int os = overstep_mode * (t >> 1) ; /* Overflow must be added to zone counters */ z = n + os; n = -os; } } while (this_cpu_cmpxchg(*p, o, n) != o); if (z) zone_page_state_add(z, zone, item); } void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, |
6cdb18ad9 mm/vmstat: fix ov... |
419 |
long delta) |
7c8391206 vmstat: User per ... |
420 |
{ |
75ef71840 mm, vmstat: add i... |
421 |
mod_zone_state(zone, item, delta, 0); |
7c8391206 vmstat: User per ... |
422 423 |
} EXPORT_SYMBOL(mod_zone_page_state); |
7c8391206 vmstat: User per ... |
424 425 |
void inc_zone_page_state(struct page *page, enum zone_stat_item item) { |
75ef71840 mm, vmstat: add i... |
426 |
mod_zone_state(page_zone(page), item, 1, 1); |
7c8391206 vmstat: User per ... |
427 428 429 430 431 |
} EXPORT_SYMBOL(inc_zone_page_state); void dec_zone_page_state(struct page *page, enum zone_stat_item item) { |
75ef71840 mm, vmstat: add i... |
432 |
mod_zone_state(page_zone(page), item, -1, -1); |
7c8391206 vmstat: User per ... |
433 434 |
} EXPORT_SYMBOL(dec_zone_page_state); |
75ef71840 mm, vmstat: add i... |
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 |
static inline void mod_node_state(struct pglist_data *pgdat, enum node_stat_item item, int delta, int overstep_mode) { struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats; s8 __percpu *p = pcp->vm_node_stat_diff + item; long o, n, t, z; do { z = 0; /* overflow to node counters */ /* * The fetching of the stat_threshold is racy. We may apply * a counter threshold to the wrong the cpu if we get * rescheduled while executing here. However, the next * counter update will apply the threshold again and * therefore bring the counter under the threshold again. * * Most of the time the thresholds are the same anyways * for all cpus in a node. */ t = this_cpu_read(pcp->stat_threshold); o = this_cpu_read(*p); n = delta + o; if (n > t || n < -t) { int os = overstep_mode * (t >> 1) ; /* Overflow must be added to node counters */ z = n + os; n = -os; } } while (this_cpu_cmpxchg(*p, o, n) != o); if (z) node_page_state_add(z, pgdat, item); } void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, long delta) { mod_node_state(pgdat, item, delta, 0); } EXPORT_SYMBOL(mod_node_page_state); void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) { mod_node_state(pgdat, item, 1, 1); } void inc_node_page_state(struct page *page, enum node_stat_item item) { mod_node_state(page_pgdat(page), item, 1, 1); } EXPORT_SYMBOL(inc_node_page_state); void dec_node_page_state(struct page *page, enum node_stat_item item) { mod_node_state(page_pgdat(page), item, -1, -1); } EXPORT_SYMBOL(dec_node_page_state); |
7c8391206 vmstat: User per ... |
497 498 499 500 501 |
#else /* * Use interrupt disable to serialize counter updates */ void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, |
6cdb18ad9 mm/vmstat: fix ov... |
502 |
long delta) |
7c8391206 vmstat: User per ... |
503 504 505 506 507 508 509 510 |
{ unsigned long flags; local_irq_save(flags); __mod_zone_page_state(zone, item, delta); local_irq_restore(flags); } EXPORT_SYMBOL(mod_zone_page_state); |
2244b95a7 [PATCH] zoned vm ... |
511 512 513 514 |
void inc_zone_page_state(struct page *page, enum zone_stat_item item) { unsigned long flags; struct zone *zone; |
2244b95a7 [PATCH] zoned vm ... |
515 516 517 |
zone = page_zone(page); local_irq_save(flags); |
ca889e6c4 [PATCH] Use Zoned... |
518 |
__inc_zone_state(zone, item); |
2244b95a7 [PATCH] zoned vm ... |
519 520 521 522 523 524 525 |
local_irq_restore(flags); } EXPORT_SYMBOL(inc_zone_page_state); void dec_zone_page_state(struct page *page, enum zone_stat_item item) { unsigned long flags; |
2244b95a7 [PATCH] zoned vm ... |
526 |
|
2244b95a7 [PATCH] zoned vm ... |
527 |
local_irq_save(flags); |
a302eb4e4 [PATCH] ZVC: Over... |
528 |
__dec_zone_page_state(page, item); |
2244b95a7 [PATCH] zoned vm ... |
529 530 531 |
local_irq_restore(flags); } EXPORT_SYMBOL(dec_zone_page_state); |
75ef71840 mm, vmstat: add i... |
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 |
void inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) { unsigned long flags; local_irq_save(flags); __inc_node_state(pgdat, item); local_irq_restore(flags); } EXPORT_SYMBOL(inc_node_state); void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, long delta) { unsigned long flags; local_irq_save(flags); __mod_node_page_state(pgdat, item, delta); local_irq_restore(flags); } EXPORT_SYMBOL(mod_node_page_state); void inc_node_page_state(struct page *page, enum node_stat_item item) { unsigned long flags; struct pglist_data *pgdat; pgdat = page_pgdat(page); local_irq_save(flags); __inc_node_state(pgdat, item); local_irq_restore(flags); } EXPORT_SYMBOL(inc_node_page_state); void dec_node_page_state(struct page *page, enum node_stat_item item) { unsigned long flags; local_irq_save(flags); __dec_node_page_state(page, item); local_irq_restore(flags); } EXPORT_SYMBOL(dec_node_page_state); #endif |
7cc36bbdd vmstat: on-demand... |
575 576 577 578 579 |
/* * Fold a differential into the global counters. * Returns the number of counters updated. */ |
75ef71840 mm, vmstat: add i... |
580 |
static int fold_diff(int *zone_diff, int *node_diff) |
4edb0748b vmstat: create fo... |
581 582 |
{ int i; |
7cc36bbdd vmstat: on-demand... |
583 |
int changes = 0; |
4edb0748b vmstat: create fo... |
584 585 |
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) |
75ef71840 mm, vmstat: add i... |
586 587 588 589 590 591 592 593 |
if (zone_diff[i]) { atomic_long_add(zone_diff[i], &vm_zone_stat[i]); changes++; } for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) if (node_diff[i]) { atomic_long_add(node_diff[i], &vm_node_stat[i]); |
7cc36bbdd vmstat: on-demand... |
594 595 596 |
changes++; } return changes; |
4edb0748b vmstat: create fo... |
597 |
} |
2244b95a7 [PATCH] zoned vm ... |
598 |
/* |
2bb921e52 vmstat: create se... |
599 |
* Update the zone counters for the current cpu. |
a7f75e258 vmstat: small rev... |
600 |
* |
4037d4522 Move remote node ... |
601 602 603 604 605 606 607 608 609 610 |
* Note that refresh_cpu_vm_stats strives to only access * node local memory. The per cpu pagesets on remote zones are placed * in the memory local to the processor using that pageset. So the * loop over all zones will access a series of cachelines local to * the processor. * * The call to zone_page_state_add updates the cachelines with the * statistics in the remote zone struct as well as the global cachelines * with the global counters. These could cause remote node cache line * bouncing and will have to be only done when necessary. |
7cc36bbdd vmstat: on-demand... |
611 612 |
* * The function returns the number of global counters updated. |
2244b95a7 [PATCH] zoned vm ... |
613 |
*/ |
0eb77e988 vmstat: make vmst... |
614 |
static int refresh_cpu_vm_stats(bool do_pagesets) |
2244b95a7 [PATCH] zoned vm ... |
615 |
{ |
75ef71840 mm, vmstat: add i... |
616 |
struct pglist_data *pgdat; |
2244b95a7 [PATCH] zoned vm ... |
617 618 |
struct zone *zone; int i; |
75ef71840 mm, vmstat: add i... |
619 620 |
int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, }; |
7cc36bbdd vmstat: on-demand... |
621 |
int changes = 0; |
2244b95a7 [PATCH] zoned vm ... |
622 |
|
ee99c71c5 mm: introduce for... |
623 |
for_each_populated_zone(zone) { |
fbc2edb05 vmstat: use this_... |
624 |
struct per_cpu_pageset __percpu *p = zone->pageset; |
2244b95a7 [PATCH] zoned vm ... |
625 |
|
fbc2edb05 vmstat: use this_... |
626 627 |
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { int v; |
2244b95a7 [PATCH] zoned vm ... |
628 |
|
fbc2edb05 vmstat: use this_... |
629 630 |
v = this_cpu_xchg(p->vm_stat_diff[i], 0); if (v) { |
a7f75e258 vmstat: small rev... |
631 |
|
a7f75e258 vmstat: small rev... |
632 |
atomic_long_add(v, &zone->vm_stat[i]); |
75ef71840 mm, vmstat: add i... |
633 |
global_zone_diff[i] += v; |
4037d4522 Move remote node ... |
634 635 |
#ifdef CONFIG_NUMA /* 3 seconds idle till flush */ |
fbc2edb05 vmstat: use this_... |
636 |
__this_cpu_write(p->expire, 3); |
4037d4522 Move remote node ... |
637 |
#endif |
2244b95a7 [PATCH] zoned vm ... |
638 |
} |
fbc2edb05 vmstat: use this_... |
639 |
} |
4037d4522 Move remote node ... |
640 |
#ifdef CONFIG_NUMA |
0eb77e988 vmstat: make vmst... |
641 642 643 644 645 646 647 648 649 650 |
if (do_pagesets) { cond_resched(); /* * Deal with draining the remote pageset of this * processor * * Check if there are pages remaining in this pageset * if not then there is nothing to expire. */ if (!__this_cpu_read(p->expire) || |
fbc2edb05 vmstat: use this_... |
651 |
!__this_cpu_read(p->pcp.count)) |
0eb77e988 vmstat: make vmst... |
652 |
continue; |
4037d4522 Move remote node ... |
653 |
|
0eb77e988 vmstat: make vmst... |
654 655 656 657 658 659 660 |
/* * We never drain zones local to this processor. */ if (zone_to_nid(zone) == numa_node_id()) { __this_cpu_write(p->expire, 0); continue; } |
4037d4522 Move remote node ... |
661 |
|
0eb77e988 vmstat: make vmst... |
662 663 |
if (__this_cpu_dec_return(p->expire)) continue; |
4037d4522 Move remote node ... |
664 |
|
0eb77e988 vmstat: make vmst... |
665 666 667 668 |
if (__this_cpu_read(p->pcp.count)) { drain_zone_pages(zone, this_cpu_ptr(&p->pcp)); changes++; } |
7cc36bbdd vmstat: on-demand... |
669 |
} |
4037d4522 Move remote node ... |
670 |
#endif |
2244b95a7 [PATCH] zoned vm ... |
671 |
} |
75ef71840 mm, vmstat: add i... |
672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 |
for_each_online_pgdat(pgdat) { struct per_cpu_nodestat __percpu *p = pgdat->per_cpu_nodestats; for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { int v; v = this_cpu_xchg(p->vm_node_stat_diff[i], 0); if (v) { atomic_long_add(v, &pgdat->vm_stat[i]); global_node_diff[i] += v; } } } changes += fold_diff(global_zone_diff, global_node_diff); |
7cc36bbdd vmstat: on-demand... |
688 |
return changes; |
2244b95a7 [PATCH] zoned vm ... |
689 |
} |
40f4b1ead mm/vmstat: add no... |
690 |
/* |
2bb921e52 vmstat: create se... |
691 692 693 694 695 696 |
* Fold the data for an offline cpu into the global array. * There cannot be any access by the offline cpu and therefore * synchronization is simplified. */ void cpu_vm_stats_fold(int cpu) { |
75ef71840 mm, vmstat: add i... |
697 |
struct pglist_data *pgdat; |
2bb921e52 vmstat: create se... |
698 699 |
struct zone *zone; int i; |
75ef71840 mm, vmstat: add i... |
700 701 |
int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, }; |
2bb921e52 vmstat: create se... |
702 703 704 705 706 707 708 709 710 711 712 713 714 |
for_each_populated_zone(zone) { struct per_cpu_pageset *p; p = per_cpu_ptr(zone->pageset, cpu); for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) if (p->vm_stat_diff[i]) { int v; v = p->vm_stat_diff[i]; p->vm_stat_diff[i] = 0; atomic_long_add(v, &zone->vm_stat[i]); |
75ef71840 mm, vmstat: add i... |
715 |
global_zone_diff[i] += v; |
2bb921e52 vmstat: create se... |
716 717 |
} } |
75ef71840 mm, vmstat: add i... |
718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 |
for_each_online_pgdat(pgdat) { struct per_cpu_nodestat *p; p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu); for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) if (p->vm_node_stat_diff[i]) { int v; v = p->vm_node_stat_diff[i]; p->vm_node_stat_diff[i] = 0; atomic_long_add(v, &pgdat->vm_stat[i]); global_node_diff[i] += v; } } fold_diff(global_zone_diff, global_node_diff); |
2bb921e52 vmstat: create se... |
735 736 737 |
} /* |
40f4b1ead mm/vmstat: add no... |
738 739 740 |
* this is only called if !populated_zone(zone), which implies no other users of * pset->vm_stat_diff[] exsist. */ |
5a8838138 memory-hotplug: f... |
741 742 743 744 745 746 747 748 749 |
void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) { int i; for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) if (pset->vm_stat_diff[i]) { int v = pset->vm_stat_diff[i]; pset->vm_stat_diff[i] = 0; atomic_long_add(v, &zone->vm_stat[i]); |
75ef71840 mm, vmstat: add i... |
750 |
atomic_long_add(v, &vm_zone_stat[i]); |
5a8838138 memory-hotplug: f... |
751 752 |
} } |
2244b95a7 [PATCH] zoned vm ... |
753 |
#endif |
ca889e6c4 [PATCH] Use Zoned... |
754 755 |
#ifdef CONFIG_NUMA /* |
75ef71840 mm, vmstat: add i... |
756 757 758 |
* Determine the per node value of a stat item. This function * is called frequently in a NUMA machine, so try to be as * frugal as possible. |
c2d42c16a mm/vmstat.c: unin... |
759 |
*/ |
75ef71840 mm, vmstat: add i... |
760 761 |
unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item) |
c2d42c16a mm/vmstat.c: unin... |
762 763 |
{ struct zone *zones = NODE_DATA(node)->node_zones; |
e87d59f7a mm/vmstat: make n... |
764 765 |
int i; unsigned long count = 0; |
c2d42c16a mm/vmstat.c: unin... |
766 |
|
e87d59f7a mm/vmstat: make n... |
767 768 769 770 |
for (i = 0; i < MAX_NR_ZONES; i++) count += zone_page_state(zones + i, item); return count; |
c2d42c16a mm/vmstat.c: unin... |
771 |
} |
75ef71840 mm, vmstat: add i... |
772 773 774 775 776 777 778 779 780 781 782 783 784 |
/* * Determine the per node value of a stat item. */ unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item) { long x = atomic_long_read(&pgdat->vm_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } |
ca889e6c4 [PATCH] Use Zoned... |
785 |
#endif |
d7a5752c0 mm: export unusab... |
786 |
#ifdef CONFIG_COMPACTION |
36deb0be3 vmstat: include c... |
787 |
|
d7a5752c0 mm: export unusab... |
788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 |
struct contig_page_info { unsigned long free_pages; unsigned long free_blocks_total; unsigned long free_blocks_suitable; }; /* * Calculate the number of free pages in a zone, how many contiguous * pages are free and how many are large enough to satisfy an allocation of * the target size. Note that this function makes no attempt to estimate * how many suitable free blocks there *might* be if MOVABLE pages were * migrated. Calculating that is possible, but expensive and can be * figured out from userspace */ static void fill_contig_page_info(struct zone *zone, unsigned int suitable_order, struct contig_page_info *info) { unsigned int order; info->free_pages = 0; info->free_blocks_total = 0; info->free_blocks_suitable = 0; for (order = 0; order < MAX_ORDER; order++) { unsigned long blocks; /* Count number of free blocks */ blocks = zone->free_area[order].nr_free; info->free_blocks_total += blocks; /* Count free base pages */ info->free_pages += blocks << order; /* Count the suitable free blocks */ if (order >= suitable_order) info->free_blocks_suitable += blocks << (order - suitable_order); } } |
f1a5ab121 mm: export fragme... |
828 829 830 831 832 833 834 835 |
/* * A fragmentation index only makes sense if an allocation of a requested * size would fail. If that is true, the fragmentation index indicates * whether external fragmentation or a lack of memory was the problem. * The value can be used to determine if page reclaim or compaction * should be used */ |
56de7263f mm: compaction: d... |
836 |
static int __fragmentation_index(unsigned int order, struct contig_page_info *info) |
f1a5ab121 mm: export fragme... |
837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 |
{ unsigned long requested = 1UL << order; if (!info->free_blocks_total) return 0; /* Fragmentation index only makes sense when a request would fail */ if (info->free_blocks_suitable) return -1000; /* * Index is between 0 and 1 so return within 3 decimal places * * 0 => allocation would fail due to lack of memory * 1 => allocation would fail due to fragmentation */ return 1000 - div_u64( (1000+(div_u64(info->free_pages * 1000ULL, requested))), info->free_blocks_total); } |
56de7263f mm: compaction: d... |
855 856 857 858 859 860 861 862 863 |
/* Same as __fragmentation index but allocs contig_page_info on stack */ int fragmentation_index(struct zone *zone, unsigned int order) { struct contig_page_info info; fill_contig_page_info(zone, order, &info); return __fragmentation_index(order, &info); } |
d7a5752c0 mm: export unusab... |
864 |
#endif |
0d6617c77 numa: fix NUMA co... |
865 |
#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA) |
fa25c503d mm: per-node vmst... |
866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 |
#ifdef CONFIG_ZONE_DMA #define TEXT_FOR_DMA(xx) xx "_dma", #else #define TEXT_FOR_DMA(xx) #endif #ifdef CONFIG_ZONE_DMA32 #define TEXT_FOR_DMA32(xx) xx "_dma32", #else #define TEXT_FOR_DMA32(xx) #endif #ifdef CONFIG_HIGHMEM #define TEXT_FOR_HIGHMEM(xx) xx "_high", #else #define TEXT_FOR_HIGHMEM(xx) #endif #define TEXTS_FOR_ZONES(xx) TEXT_FOR_DMA(xx) TEXT_FOR_DMA32(xx) xx "_normal", \ TEXT_FOR_HIGHMEM(xx) xx "_movable", const char * const vmstat_text[] = { |
09316c09d mm/balloon_compac... |
888 |
/* enum zone_stat_item countes */ |
fa25c503d mm: per-node vmst... |
889 |
"nr_free_pages", |
71c799f49 mm: add per-zone ... |
890 891 892 893 894 |
"nr_zone_inactive_anon", "nr_zone_active_anon", "nr_zone_inactive_file", "nr_zone_active_file", "nr_zone_unevictable", |
5a1c84b40 mm: remove reclai... |
895 |
"nr_zone_write_pending", |
fa25c503d mm: per-node vmst... |
896 |
"nr_mlock", |
fa25c503d mm: per-node vmst... |
897 898 899 900 |
"nr_slab_reclaimable", "nr_slab_unreclaimable", "nr_page_table_pages", "nr_kernel_stack", |
fa25c503d mm: per-node vmst... |
901 |
"nr_bounce", |
91537fee0 mm: add NR_ZSMALL... |
902 903 904 |
#if IS_ENABLED(CONFIG_ZSMALLOC) "nr_zspages", #endif |
fa25c503d mm: per-node vmst... |
905 906 907 908 909 910 911 912 |
#ifdef CONFIG_NUMA "numa_hit", "numa_miss", "numa_foreign", "numa_interleave", "numa_local", "numa_other", #endif |
d1ce749a0 cma: count free C... |
913 |
"nr_free_cma", |
09316c09d mm/balloon_compac... |
914 |
|
599d0c954 mm, vmscan: move ... |
915 916 917 918 919 920 921 922 923 |
/* Node-based counters */ "nr_inactive_anon", "nr_active_anon", "nr_inactive_file", "nr_active_file", "nr_unevictable", "nr_isolated_anon", "nr_isolated_file", "nr_pages_scanned", |
1e6b10857 mm, workingset: m... |
924 925 926 |
"workingset_refault", "workingset_activate", "workingset_nodereclaim", |
50658e2e0 mm: move page map... |
927 928 |
"nr_anon_pages", "nr_mapped", |
11fb99898 mm: move most fil... |
929 930 931 932 933 934 935 936 937 |
"nr_file_pages", "nr_dirty", "nr_writeback", "nr_writeback_temp", "nr_shmem", "nr_shmem_hugepages", "nr_shmem_pmdmapped", "nr_anon_transparent_hugepages", "nr_unstable", |
c4a25635b mm: move vmscan w... |
938 939 940 941 |
"nr_vmscan_write", "nr_vmscan_immediate_reclaim", "nr_dirtied", "nr_written", |
599d0c954 mm, vmscan: move ... |
942 |
|
09316c09d mm/balloon_compac... |
943 |
/* enum writeback_stat_item counters */ |
fa25c503d mm: per-node vmst... |
944 945 946 947 |
"nr_dirty_threshold", "nr_dirty_background_threshold", #ifdef CONFIG_VM_EVENT_COUNTERS |
09316c09d mm/balloon_compac... |
948 |
/* enum vm_event_item counters */ |
fa25c503d mm: per-node vmst... |
949 950 951 952 953 954 |
"pgpgin", "pgpgout", "pswpin", "pswpout", TEXTS_FOR_ZONES("pgalloc") |
7cc30fcfd mm: vmstat: accou... |
955 956 |
TEXTS_FOR_ZONES("allocstall") TEXTS_FOR_ZONES("pgskip") |
fa25c503d mm: per-node vmst... |
957 958 959 960 961 962 963 |
"pgfree", "pgactivate", "pgdeactivate", "pgfault", "pgmajfault", |
854e9ed09 mm: support madvi... |
964 |
"pglazyfreed", |
fa25c503d mm: per-node vmst... |
965 |
|
599d0c954 mm, vmscan: move ... |
966 967 968 969 970 |
"pgrefill", "pgsteal_kswapd", "pgsteal_direct", "pgscan_kswapd", "pgscan_direct", |
68243e76e mm: account for t... |
971 |
"pgscan_direct_throttle", |
fa25c503d mm: per-node vmst... |
972 973 974 975 976 977 |
#ifdef CONFIG_NUMA "zone_reclaim_failed", #endif "pginodesteal", "slabs_scanned", |
fa25c503d mm: per-node vmst... |
978 979 980 |
"kswapd_inodesteal", "kswapd_low_wmark_hit_quickly", "kswapd_high_wmark_hit_quickly", |
fa25c503d mm: per-node vmst... |
981 |
"pageoutrun", |
fa25c503d mm: per-node vmst... |
982 983 |
"pgrotated", |
5509a5d27 drop_caches: add ... |
984 985 |
"drop_pagecache", "drop_slab", |
03c5a6e16 mm: numa: Add pte... |
986 987 |
#ifdef CONFIG_NUMA_BALANCING "numa_pte_updates", |
72403b4a0 mm: numa: return ... |
988 |
"numa_huge_pte_updates", |
03c5a6e16 mm: numa: Add pte... |
989 990 991 992 |
"numa_hint_faults", "numa_hint_faults_local", "numa_pages_migrated", #endif |
5647bc293 mm: compaction: M... |
993 994 995 996 |
#ifdef CONFIG_MIGRATION "pgmigrate_success", "pgmigrate_fail", #endif |
fa25c503d mm: per-node vmst... |
997 |
#ifdef CONFIG_COMPACTION |
397487db6 mm: compaction: A... |
998 999 1000 |
"compact_migrate_scanned", "compact_free_scanned", "compact_isolated", |
fa25c503d mm: per-node vmst... |
1001 1002 1003 |
"compact_stall", "compact_fail", "compact_success", |
698b1b306 mm, compaction: i... |
1004 |
"compact_daemon_wake", |
fa25c503d mm: per-node vmst... |
1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 |
#endif #ifdef CONFIG_HUGETLB_PAGE "htlb_buddy_alloc_success", "htlb_buddy_alloc_fail", #endif "unevictable_pgs_culled", "unevictable_pgs_scanned", "unevictable_pgs_rescued", "unevictable_pgs_mlocked", "unevictable_pgs_munlocked", "unevictable_pgs_cleared", "unevictable_pgs_stranded", |
fa25c503d mm: per-node vmst... |
1018 1019 1020 1021 1022 1023 |
#ifdef CONFIG_TRANSPARENT_HUGEPAGE "thp_fault_alloc", "thp_fault_fallback", "thp_collapse_alloc", "thp_collapse_alloc_failed", |
95ecedcd6 thp, vmstats: add... |
1024 1025 |
"thp_file_alloc", "thp_file_mapped", |
122afea96 mm, vmstats: new ... |
1026 1027 |
"thp_split_page", "thp_split_page_failed", |
f9719a03d thp, vmstats: cou... |
1028 |
"thp_deferred_split_page", |
122afea96 mm, vmstats: new ... |
1029 |
"thp_split_pmd", |
d8a8e1f0d thp, vmstat: impl... |
1030 1031 |
"thp_zero_page_alloc", "thp_zero_page_alloc_failed", |
fa25c503d mm: per-node vmst... |
1032 |
#endif |
09316c09d mm/balloon_compac... |
1033 1034 1035 1036 1037 1038 1039 |
#ifdef CONFIG_MEMORY_BALLOON "balloon_inflate", "balloon_deflate", #ifdef CONFIG_BALLOON_COMPACTION "balloon_migrate", #endif #endif /* CONFIG_MEMORY_BALLOON */ |
ec6599344 mm, x86: Account ... |
1040 |
#ifdef CONFIG_DEBUG_TLBFLUSH |
6df46865f mm: vmstats: trac... |
1041 |
#ifdef CONFIG_SMP |
9824cf975 mm: vmstats: tlb ... |
1042 1043 |
"nr_tlb_remote_flush", "nr_tlb_remote_flush_received", |
ec6599344 mm, x86: Account ... |
1044 |
#endif /* CONFIG_SMP */ |
9824cf975 mm: vmstats: tlb ... |
1045 1046 |
"nr_tlb_local_flush_all", "nr_tlb_local_flush_one", |
ec6599344 mm, x86: Account ... |
1047 |
#endif /* CONFIG_DEBUG_TLBFLUSH */ |
fa25c503d mm: per-node vmst... |
1048 |
|
4f115147f mm,vmacache: add ... |
1049 1050 1051 |
#ifdef CONFIG_DEBUG_VM_VMACACHE "vmacache_find_calls", "vmacache_find_hits", |
f5f302e21 mm,vmacache: coun... |
1052 |
"vmacache_full_flushes", |
4f115147f mm,vmacache: add ... |
1053 |
#endif |
fa25c503d mm: per-node vmst... |
1054 1055 |
#endif /* CONFIG_VM_EVENTS_COUNTERS */ }; |
0d6617c77 numa: fix NUMA co... |
1056 |
#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */ |
fa25c503d mm: per-node vmst... |
1057 |
|
3c4868710 mm/vmstat.c: fix/... |
1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 |
#if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)) || \ defined(CONFIG_PROC_FS) static void *frag_start(struct seq_file *m, loff_t *pos) { pg_data_t *pgdat; loff_t node = *pos; for (pgdat = first_online_pgdat(); pgdat && node; pgdat = next_online_pgdat(pgdat)) --node; return pgdat; } static void *frag_next(struct seq_file *m, void *arg, loff_t *pos) { pg_data_t *pgdat = (pg_data_t *)arg; (*pos)++; return next_online_pgdat(pgdat); } static void frag_stop(struct seq_file *m, void *arg) { } /* Walk all the zones in a node and print using a callback */ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, void (*print)(struct seq_file *m, pg_data_t *, struct zone *)) { struct zone *zone; struct zone *node_zones = pgdat->node_zones; unsigned long flags; for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { if (!populated_zone(zone)) continue; spin_lock_irqsave(&zone->lock, flags); print(m, pgdat, zone); spin_unlock_irqrestore(&zone->lock, flags); } } #endif |
d7a5752c0 mm: export unusab... |
1103 |
#ifdef CONFIG_PROC_FS |
467c996c1 Print out statist... |
1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 |
static void frag_show_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { int order; seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); for (order = 0; order < MAX_ORDER; ++order) seq_printf(m, "%6lu ", zone->free_area[order].nr_free); seq_putc(m, ' '); } /* * This walks the free areas for each zone. */ static int frag_show(struct seq_file *m, void *arg) { pg_data_t *pgdat = (pg_data_t *)arg; walk_zones_in_node(m, pgdat, frag_show_print); return 0; } static void pagetypeinfo_showfree_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { int order, mtype; for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) { seq_printf(m, "Node %4d, zone %8s, type %12s ", pgdat->node_id, zone->name, migratetype_names[mtype]); for (order = 0; order < MAX_ORDER; ++order) { unsigned long freecount = 0; struct free_area *area; struct list_head *curr; area = &(zone->free_area[order]); list_for_each(curr, &area->free_list[mtype]) freecount++; seq_printf(m, "%6lu ", freecount); } |
f6ac2354d [PATCH] zoned vm ... |
1147 1148 1149 |
seq_putc(m, ' '); } |
467c996c1 Print out statist... |
1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 |
} /* Print out the free pages at each order for each migatetype */ static int pagetypeinfo_showfree(struct seq_file *m, void *arg) { int order; pg_data_t *pgdat = (pg_data_t *)arg; /* Print header */ seq_printf(m, "%-43s ", "Free pages count per migrate type at order"); for (order = 0; order < MAX_ORDER; ++order) seq_printf(m, "%6d ", order); seq_putc(m, ' '); walk_zones_in_node(m, pgdat, pagetypeinfo_showfree_print); return 0; } static void pagetypeinfo_showblockcount_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { int mtype; unsigned long pfn; unsigned long start_pfn = zone->zone_start_pfn; |
108bcc96e mm: add & use zon... |
1176 |
unsigned long end_pfn = zone_end_pfn(zone); |
467c996c1 Print out statist... |
1177 1178 1179 1180 1181 1182 1183 1184 1185 |
unsigned long count[MIGRATE_TYPES] = { 0, }; for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { struct page *page; if (!pfn_valid(pfn)) continue; page = pfn_to_page(pfn); |
eb33575cf [ARM] Double chec... |
1186 1187 1188 |
/* Watch for unexpected holes punched in the memmap */ if (!memmap_valid_within(pfn, page, zone)) |
e80d6a248 [ARM] Skip memory... |
1189 |
continue; |
eb33575cf [ARM] Double chec... |
1190 |
|
a91c43c73 mm/vmstat: add zo... |
1191 1192 |
if (page_zone(page) != zone) continue; |
467c996c1 Print out statist... |
1193 |
mtype = get_pageblock_migratetype(page); |
e80d6a248 [ARM] Skip memory... |
1194 1195 |
if (mtype < MIGRATE_TYPES) count[mtype]++; |
467c996c1 Print out statist... |
1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 |
} /* Print counts */ seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) seq_printf(m, "%12lu ", count[mtype]); seq_putc(m, ' '); } /* Print out the free pages at each order for each migratetype */ static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg) { int mtype; pg_data_t *pgdat = (pg_data_t *)arg; seq_printf(m, " %-23s", "Number of blocks type "); for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) seq_printf(m, "%12s ", migratetype_names[mtype]); seq_putc(m, ' '); walk_zones_in_node(m, pgdat, pagetypeinfo_showblockcount_print); return 0; } |
48c96a368 mm/page_owner: ke... |
1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 |
/* * Print out the number of pageblocks for each migratetype that contain pages * of other types. This gives an indication of how well fallbacks are being * contained by rmqueue_fallback(). It requires information from PAGE_OWNER * to determine what is going on */ static void pagetypeinfo_showmixedcount(struct seq_file *m, pg_data_t *pgdat) { #ifdef CONFIG_PAGE_OWNER int mtype; |
7dd80b8af mm, page_owner: c... |
1232 |
if (!static_branch_unlikely(&page_owner_inited)) |
48c96a368 mm/page_owner: ke... |
1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 |
return; drain_all_pages(NULL); seq_printf(m, " %-23s", "Number of mixed blocks "); for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) seq_printf(m, "%12s ", migratetype_names[mtype]); seq_putc(m, ' '); walk_zones_in_node(m, pgdat, pagetypeinfo_showmixedcount_print); #endif /* CONFIG_PAGE_OWNER */ } |
467c996c1 Print out statist... |
1247 1248 1249 1250 1251 1252 1253 |
/* * This prints out statistics in relation to grouping pages by mobility. * It is expensive to collect so do not constantly read the file. */ static int pagetypeinfo_show(struct seq_file *m, void *arg) { pg_data_t *pgdat = (pg_data_t *)arg; |
41b25a378 /proc/pagetypeinf... |
1254 |
/* check memoryless node */ |
a47b53c5f vmstat: use N_MEM... |
1255 |
if (!node_state(pgdat->node_id, N_MEMORY)) |
41b25a378 /proc/pagetypeinf... |
1256 |
return 0; |
467c996c1 Print out statist... |
1257 1258 1259 1260 1261 1262 1263 1264 |
seq_printf(m, "Page block order: %d ", pageblock_order); seq_printf(m, "Pages per block: %lu ", pageblock_nr_pages); seq_putc(m, ' '); pagetypeinfo_showfree(m, pgdat); pagetypeinfo_showblockcount(m, pgdat); |
48c96a368 mm/page_owner: ke... |
1265 |
pagetypeinfo_showmixedcount(m, pgdat); |
467c996c1 Print out statist... |
1266 |
|
f6ac2354d [PATCH] zoned vm ... |
1267 1268 |
return 0; } |
8f32f7e5a proc: move /proc/... |
1269 |
static const struct seq_operations fragmentation_op = { |
f6ac2354d [PATCH] zoned vm ... |
1270 1271 1272 1273 1274 |
.start = frag_start, .next = frag_next, .stop = frag_stop, .show = frag_show, }; |
8f32f7e5a proc: move /proc/... |
1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 |
static int fragmentation_open(struct inode *inode, struct file *file) { return seq_open(file, &fragmentation_op); } static const struct file_operations fragmentation_file_operations = { .open = fragmentation_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; |
74e2e8e8c proc: move /proc/... |
1286 |
static const struct seq_operations pagetypeinfo_op = { |
467c996c1 Print out statist... |
1287 1288 1289 1290 1291 |
.start = frag_start, .next = frag_next, .stop = frag_stop, .show = pagetypeinfo_show, }; |
74e2e8e8c proc: move /proc/... |
1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 |
static int pagetypeinfo_open(struct inode *inode, struct file *file) { return seq_open(file, &pagetypeinfo_op); } static const struct file_operations pagetypeinfo_file_ops = { .open = pagetypeinfo_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; |
e2ecc8a79 mm, vmstat: print... |
1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 |
static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone) { int zid; for (zid = 0; zid < MAX_NR_ZONES; zid++) { struct zone *compare = &pgdat->node_zones[zid]; if (populated_zone(compare)) return zone == compare; } /* The zone must be somewhere! */ WARN_ON_ONCE(1); return false; } |
467c996c1 Print out statist... |
1318 1319 |
static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) |
f6ac2354d [PATCH] zoned vm ... |
1320 |
{ |
467c996c1 Print out statist... |
1321 1322 |
int i; seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name); |
e2ecc8a79 mm, vmstat: print... |
1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 |
if (is_zone_first_populated(pgdat, zone)) { seq_printf(m, " per-node stats"); for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { seq_printf(m, " %-12s %lu", vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], node_page_state(pgdat, i)); } } |
467c996c1 Print out statist... |
1333 1334 1335 1336 1337 1338 1339 1340 1341 |
seq_printf(m, " pages free %lu" " min %lu" " low %lu" " high %lu" |
599d0c954 mm, vmscan: move ... |
1342 1343 |
" node_scanned %lu" |
467c996c1 Print out statist... |
1344 1345 |
" spanned %lu" |
9feedc9d8 mm: introduce new... |
1346 1347 1348 1349 |
" present %lu" " managed %lu", |
88f5acf88 mm: page allocato... |
1350 |
zone_page_state(zone, NR_FREE_PAGES), |
418589663 page allocator: u... |
1351 1352 1353 |
min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), |
599d0c954 mm, vmscan: move ... |
1354 |
node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED), |
467c996c1 Print out statist... |
1355 |
zone->spanned_pages, |
9feedc9d8 mm: introduce new... |
1356 1357 |
zone->present_pages, zone->managed_pages); |
467c996c1 Print out statist... |
1358 1359 |
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) |
599d0c954 mm, vmscan: move ... |
1360 1361 |
seq_printf(m, " %-12s %lu", vmstat_text[i], |
467c996c1 Print out statist... |
1362 1363 1364 |
zone_page_state(zone, i)); seq_printf(m, |
3484b2de9 mm: rearrange zon... |
1365 1366 |
" protection: (%ld", |
467c996c1 Print out statist... |
1367 1368 |
zone->lowmem_reserve[0]); for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++) |
3484b2de9 mm: rearrange zon... |
1369 |
seq_printf(m, ", %ld", zone->lowmem_reserve[i]); |
467c996c1 Print out statist... |
1370 1371 1372 1373 1374 1375 |
seq_printf(m, ")" " pagesets"); for_each_online_cpu(i) { struct per_cpu_pageset *pageset; |
467c996c1 Print out statist... |
1376 |
|
99dcc3e5a this_cpu: Page al... |
1377 |
pageset = per_cpu_ptr(zone->pageset, i); |
3dfa5721f Page allocator: g... |
1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 |
seq_printf(m, " cpu: %i" " count: %i" " high: %i" " batch: %i", i, pageset->pcp.count, pageset->pcp.high, pageset->pcp.batch); |
df9ecaba3 [PATCH] ZVC: Scal... |
1391 |
#ifdef CONFIG_SMP |
467c996c1 Print out statist... |
1392 1393 1394 |
seq_printf(m, " vm stats threshold: %d", pageset->stat_threshold); |
df9ecaba3 [PATCH] ZVC: Scal... |
1395 |
#endif |
f6ac2354d [PATCH] zoned vm ... |
1396 |
} |
467c996c1 Print out statist... |
1397 |
seq_printf(m, |
599d0c954 mm, vmscan: move ... |
1398 1399 1400 1401 1402 1403 1404 |
" node_unreclaimable: %u" " start_pfn: %lu" " node_inactive_ratio: %u", !pgdat_reclaimable(zone->zone_pgdat), |
556adecba vmscan: second ch... |
1405 |
zone->zone_start_pfn, |
599d0c954 mm, vmscan: move ... |
1406 |
zone->zone_pgdat->inactive_ratio); |
467c996c1 Print out statist... |
1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 |
seq_putc(m, ' '); } /* * Output information about zones in @pgdat. */ static int zoneinfo_show(struct seq_file *m, void *arg) { pg_data_t *pgdat = (pg_data_t *)arg; walk_zones_in_node(m, pgdat, zoneinfo_show_print); |
f6ac2354d [PATCH] zoned vm ... |
1418 1419 |
return 0; } |
5c9fe6281 proc: move /proc/... |
1420 |
static const struct seq_operations zoneinfo_op = { |
f6ac2354d [PATCH] zoned vm ... |
1421 1422 1423 1424 1425 1426 |
.start = frag_start, /* iterate over all zones. The same as in * fragmentation. */ .next = frag_next, .stop = frag_stop, .show = zoneinfo_show, }; |
5c9fe6281 proc: move /proc/... |
1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 |
static int zoneinfo_open(struct inode *inode, struct file *file) { return seq_open(file, &zoneinfo_op); } static const struct file_operations proc_zoneinfo_file_operations = { .open = zoneinfo_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; |
79da826ae writeback: report... |
1438 1439 1440 1441 1442 |
enum writeback_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, NR_VM_WRITEBACK_STAT_ITEMS, }; |
f6ac2354d [PATCH] zoned vm ... |
1443 1444 |
static void *vmstat_start(struct seq_file *m, loff_t *pos) { |
2244b95a7 [PATCH] zoned vm ... |
1445 |
unsigned long *v; |
79da826ae writeback: report... |
1446 |
int i, stat_items_size; |
f6ac2354d [PATCH] zoned vm ... |
1447 1448 1449 |
if (*pos >= ARRAY_SIZE(vmstat_text)) return NULL; |
79da826ae writeback: report... |
1450 |
stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) + |
75ef71840 mm, vmstat: add i... |
1451 |
NR_VM_NODE_STAT_ITEMS * sizeof(unsigned long) + |
79da826ae writeback: report... |
1452 |
NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long); |
f6ac2354d [PATCH] zoned vm ... |
1453 |
|
f8891e5e1 [PATCH] Light wei... |
1454 |
#ifdef CONFIG_VM_EVENT_COUNTERS |
79da826ae writeback: report... |
1455 |
stat_items_size += sizeof(struct vm_event_state); |
f8891e5e1 [PATCH] Light wei... |
1456 |
#endif |
79da826ae writeback: report... |
1457 1458 |
v = kmalloc(stat_items_size, GFP_KERNEL); |
2244b95a7 [PATCH] zoned vm ... |
1459 1460 |
m->private = v; if (!v) |
f6ac2354d [PATCH] zoned vm ... |
1461 |
return ERR_PTR(-ENOMEM); |
2244b95a7 [PATCH] zoned vm ... |
1462 1463 |
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) v[i] = global_page_state(i); |
79da826ae writeback: report... |
1464 |
v += NR_VM_ZONE_STAT_ITEMS; |
75ef71840 mm, vmstat: add i... |
1465 1466 1467 |
for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) v[i] = global_node_page_state(i); v += NR_VM_NODE_STAT_ITEMS; |
79da826ae writeback: report... |
1468 1469 1470 |
global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD, v + NR_DIRTY_THRESHOLD); v += NR_VM_WRITEBACK_STAT_ITEMS; |
f8891e5e1 [PATCH] Light wei... |
1471 |
#ifdef CONFIG_VM_EVENT_COUNTERS |
79da826ae writeback: report... |
1472 1473 1474 |
all_vm_events(v); v[PGPGIN] /= 2; /* sectors -> kbytes */ v[PGPGOUT] /= 2; |
f8891e5e1 [PATCH] Light wei... |
1475 |
#endif |
ff8b16d7e vmstat: fix offse... |
1476 |
return (unsigned long *)m->private + *pos; |
f6ac2354d [PATCH] zoned vm ... |
1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 |
} static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos) { (*pos)++; if (*pos >= ARRAY_SIZE(vmstat_text)) return NULL; return (unsigned long *)m->private + *pos; } static int vmstat_show(struct seq_file *m, void *arg) { unsigned long *l = arg; unsigned long off = l - (unsigned long *)m->private; |
68ba0326b proc: much faster... |
1491 1492 |
seq_puts(m, vmstat_text[off]); |
75ba1d07f seq/proc: modify ... |
1493 |
seq_put_decimal_ull(m, " ", *l); |
68ba0326b proc: much faster... |
1494 1495 |
seq_putc(m, ' '); |
f6ac2354d [PATCH] zoned vm ... |
1496 1497 1498 1499 1500 1501 1502 1503 |
return 0; } static void vmstat_stop(struct seq_file *m, void *arg) { kfree(m->private); m->private = NULL; } |
b6aa44ab6 proc: move /proc/... |
1504 |
static const struct seq_operations vmstat_op = { |
f6ac2354d [PATCH] zoned vm ... |
1505 1506 1507 1508 1509 |
.start = vmstat_start, .next = vmstat_next, .stop = vmstat_stop, .show = vmstat_show, }; |
b6aa44ab6 proc: move /proc/... |
1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 |
static int vmstat_open(struct inode *inode, struct file *file) { return seq_open(file, &vmstat_op); } static const struct file_operations proc_vmstat_file_operations = { .open = vmstat_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; |
f6ac2354d [PATCH] zoned vm ... |
1521 |
#endif /* CONFIG_PROC_FS */ |
df9ecaba3 [PATCH] ZVC: Scal... |
1522 |
#ifdef CONFIG_SMP |
373ccbe59 mm, vmstat: allow... |
1523 |
static struct workqueue_struct *vmstat_wq; |
d1187ed21 vmstat: use our o... |
1524 |
static DEFINE_PER_CPU(struct delayed_work, vmstat_work); |
77461ab33 Make vm statistic... |
1525 |
int sysctl_stat_interval __read_mostly = HZ; |
d1187ed21 vmstat: use our o... |
1526 |
|
52b6f46bc mm: /proc/sys/vm/... |
1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 |
#ifdef CONFIG_PROC_FS static void refresh_vm_stats(struct work_struct *work) { refresh_cpu_vm_stats(true); } int vmstat_refresh(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { long val; int err; int i; /* * The regular update, every sysctl_stat_interval, may come later * than expected: leaving a significant amount in per_cpu buckets. * This is particularly misleading when checking a quantity of HUGE * pages, immediately after running a test. /proc/sys/vm/stat_refresh, * which can equally be echo'ed to or cat'ted from (by root), * can be used to update the stats just before reading them. * * Oh, and since global_page_state() etc. are so careful to hide * transiently negative values, report an error here if any of * the stats is negative, so we know to go looking for imbalance. */ err = schedule_on_each_cpu(refresh_vm_stats); if (err) return err; for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { |
75ef71840 mm, vmstat: add i... |
1556 |
val = atomic_long_read(&vm_zone_stat[i]); |
52b6f46bc mm: /proc/sys/vm/... |
1557 1558 |
if (val < 0) { switch (i) { |
52b6f46bc mm: /proc/sys/vm/... |
1559 1560 |
case NR_PAGES_SCANNED: /* |
e6cbd7f2e mm, page_alloc: r... |
1561 |
* This is often seen to go negative in |
52b6f46bc mm: /proc/sys/vm/... |
1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 |
* recent kernels, but not to go permanently * negative. Whilst it would be nicer not to * have exceptions, rooting them out would be * another task, of rather low priority. */ break; default: pr_warn("%s: %s %ld ", __func__, vmstat_text[i], val); err = -EINVAL; break; } } } if (err) return err; if (write) *ppos += *lenp; else *lenp = 0; return 0; } #endif /* CONFIG_PROC_FS */ |
d1187ed21 vmstat: use our o... |
1586 1587 |
static void vmstat_update(struct work_struct *w) { |
0eb77e988 vmstat: make vmst... |
1588 |
if (refresh_cpu_vm_stats(true)) { |
7cc36bbdd vmstat: on-demand... |
1589 1590 1591 1592 1593 |
/* * Counters were updated so we expect more updates * to occur in the future. Keep on running the * update worker thread. */ |
7b8da4c7f vmstat: get rid o... |
1594 |
queue_delayed_work_on(smp_processor_id(), vmstat_wq, |
f01f17d37 mm, vmstat: make ... |
1595 1596 |
this_cpu_ptr(&vmstat_work), round_jiffies_relative(sysctl_stat_interval)); |
7cc36bbdd vmstat: on-demand... |
1597 1598 1599 1600 |
} } /* |
0eb77e988 vmstat: make vmst... |
1601 1602 1603 1604 |
* Switch off vmstat processing and then fold all the remaining differentials * until the diffs stay at zero. The function is used by NOHZ and can only be * invoked when tick processing is not active. */ |
0eb77e988 vmstat: make vmst... |
1605 |
/* |
7cc36bbdd vmstat: on-demand... |
1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 |
* Check if the diffs for a certain cpu indicate that * an update is needed. */ static bool need_update(int cpu) { struct zone *zone; for_each_populated_zone(zone) { struct per_cpu_pageset *p = per_cpu_ptr(zone->pageset, cpu); BUILD_BUG_ON(sizeof(p->vm_stat_diff[0]) != 1); /* * The fast way of checking if there are any vmstat diffs. * This works because the diffs are byte sized items. */ if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS)) return true; } return false; } |
7b8da4c7f vmstat: get rid o... |
1627 1628 1629 1630 1631 |
/* * Switch off vmstat processing and then fold all the remaining differentials * until the diffs stay at zero. The function is used by NOHZ and can only be * invoked when tick processing is not active. */ |
f01f17d37 mm, vmstat: make ... |
1632 1633 1634 1635 |
void quiet_vmstat(void) { if (system_state != SYSTEM_RUNNING) return; |
7b8da4c7f vmstat: get rid o... |
1636 |
if (!delayed_work_pending(this_cpu_ptr(&vmstat_work))) |
f01f17d37 mm, vmstat: make ... |
1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 |
return; if (!need_update(smp_processor_id())) return; /* * Just refresh counters and do not care about the pending delayed * vmstat_update. It doesn't fire that often to matter and canceling * it would be too expensive from this path. * vmstat_shepherd will take care about that for us. */ refresh_cpu_vm_stats(false); } |
7cc36bbdd vmstat: on-demand... |
1650 1651 1652 1653 1654 1655 1656 |
/* * Shepherd worker thread that checks the * differentials of processors that have their worker * threads for vm statistics updates disabled because of * inactivity. */ static void vmstat_shepherd(struct work_struct *w); |
0eb77e988 vmstat: make vmst... |
1657 |
static DECLARE_DEFERRABLE_WORK(shepherd, vmstat_shepherd); |
7cc36bbdd vmstat: on-demand... |
1658 1659 1660 1661 1662 1663 1664 |
static void vmstat_shepherd(struct work_struct *w) { int cpu; get_online_cpus(); /* Check processors whose vmstat worker threads have been disabled */ |
7b8da4c7f vmstat: get rid o... |
1665 |
for_each_online_cpu(cpu) { |
f01f17d37 mm, vmstat: make ... |
1666 |
struct delayed_work *dw = &per_cpu(vmstat_work, cpu); |
7cc36bbdd vmstat: on-demand... |
1667 |
|
7b8da4c7f vmstat: get rid o... |
1668 1669 |
if (!delayed_work_pending(dw) && need_update(cpu)) queue_delayed_work_on(cpu, vmstat_wq, dw, 0); |
f01f17d37 mm, vmstat: make ... |
1670 |
} |
7cc36bbdd vmstat: on-demand... |
1671 1672 1673 |
put_online_cpus(); schedule_delayed_work(&shepherd, |
98f4ebb29 mm: align vmstat_... |
1674 |
round_jiffies_relative(sysctl_stat_interval)); |
d1187ed21 vmstat: use our o... |
1675 |
} |
7cc36bbdd vmstat: on-demand... |
1676 |
static void __init start_shepherd_timer(void) |
d1187ed21 vmstat: use our o... |
1677 |
{ |
7cc36bbdd vmstat: on-demand... |
1678 1679 1680 |
int cpu; for_each_possible_cpu(cpu) |
ccde8bd40 vmstat: make vmst... |
1681 |
INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu), |
7cc36bbdd vmstat: on-demand... |
1682 |
vmstat_update); |
751e5f5c7 vmstat: allocate ... |
1683 |
vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); |
7cc36bbdd vmstat: on-demand... |
1684 1685 |
schedule_delayed_work(&shepherd, round_jiffies_relative(sysctl_stat_interval)); |
d1187ed21 vmstat: use our o... |
1686 |
} |
03e86dba5 cpu: fix node sta... |
1687 1688 1689 1690 1691 1692 1693 1694 1695 |
static void __init init_cpu_node_state(void) { int cpu; get_online_cpus(); for_each_online_cpu(cpu) node_set_state(cpu_to_node(cpu), N_CPU); put_online_cpus(); } |
807a1bd2b mm: clear N_CPU f... |
1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 |
static void vmstat_cpu_dead(int node) { int cpu; get_online_cpus(); for_each_online_cpu(cpu) if (cpu_to_node(cpu) == node) goto end; node_clear_state(node, N_CPU); end: put_online_cpus(); } |
df9ecaba3 [PATCH] ZVC: Scal... |
1709 1710 1711 1712 |
/* * Use the cpu notifier to insure that the thresholds are recalculated * when necessary. */ |
0db0628d9 kernel: delete __... |
1713 |
static int vmstat_cpuup_callback(struct notifier_block *nfb, |
df9ecaba3 [PATCH] ZVC: Scal... |
1714 1715 1716 |
unsigned long action, void *hcpu) { |
d1187ed21 vmstat: use our o... |
1717 |
long cpu = (long)hcpu; |
df9ecaba3 [PATCH] ZVC: Scal... |
1718 |
switch (action) { |
d1187ed21 vmstat: use our o... |
1719 1720 |
case CPU_ONLINE: case CPU_ONLINE_FROZEN: |
5ee28a447 vmstat: update zo... |
1721 |
refresh_zone_stat_thresholds(); |
ad596925e this_cpu: Remove ... |
1722 |
node_set_state(cpu_to_node(cpu), N_CPU); |
d1187ed21 vmstat: use our o... |
1723 1724 1725 |
break; case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: |
afe2c511f workqueue: conver... |
1726 |
cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu)); |
d1187ed21 vmstat: use our o... |
1727 1728 1729 |
break; case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: |
d1187ed21 vmstat: use our o... |
1730 |
break; |
ce421c799 [PATCH] mm: clean... |
1731 |
case CPU_DEAD: |
8bb784428 Add suspend-relat... |
1732 |
case CPU_DEAD_FROZEN: |
ce421c799 [PATCH] mm: clean... |
1733 |
refresh_zone_stat_thresholds(); |
807a1bd2b mm: clear N_CPU f... |
1734 |
vmstat_cpu_dead(cpu_to_node(cpu)); |
ce421c799 [PATCH] mm: clean... |
1735 1736 1737 |
break; default: break; |
df9ecaba3 [PATCH] ZVC: Scal... |
1738 1739 1740 |
} return NOTIFY_OK; } |
0db0628d9 kernel: delete __... |
1741 |
static struct notifier_block vmstat_notifier = |
df9ecaba3 [PATCH] ZVC: Scal... |
1742 |
{ &vmstat_cpuup_callback, NULL, 0 }; |
8f32f7e5a proc: move /proc/... |
1743 |
#endif |
df9ecaba3 [PATCH] ZVC: Scal... |
1744 |
|
e2fc88d06 mm/vmstat.c: clea... |
1745 |
static int __init setup_vmstat(void) |
df9ecaba3 [PATCH] ZVC: Scal... |
1746 |
{ |
8f32f7e5a proc: move /proc/... |
1747 |
#ifdef CONFIG_SMP |
0be94bad0 mm, vmstat: Fix C... |
1748 1749 |
cpu_notifier_register_begin(); __register_cpu_notifier(&vmstat_notifier); |
03e86dba5 cpu: fix node sta... |
1750 |
init_cpu_node_state(); |
d1187ed21 vmstat: use our o... |
1751 |
|
7cc36bbdd vmstat: on-demand... |
1752 |
start_shepherd_timer(); |
0be94bad0 mm, vmstat: Fix C... |
1753 |
cpu_notifier_register_done(); |
8f32f7e5a proc: move /proc/... |
1754 1755 1756 |
#endif #ifdef CONFIG_PROC_FS proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); |
74e2e8e8c proc: move /proc/... |
1757 |
proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops); |
b6aa44ab6 proc: move /proc/... |
1758 |
proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations); |
5c9fe6281 proc: move /proc/... |
1759 |
proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations); |
8f32f7e5a proc: move /proc/... |
1760 |
#endif |
df9ecaba3 [PATCH] ZVC: Scal... |
1761 1762 1763 |
return 0; } module_init(setup_vmstat) |
d7a5752c0 mm: export unusab... |
1764 1765 |
#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION) |
d7a5752c0 mm: export unusab... |
1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 |
/* * Return an index indicating how much of the available free memory is * unusable for an allocation of the requested size. */ static int unusable_free_index(unsigned int order, struct contig_page_info *info) { /* No free memory is interpreted as all free memory is unusable */ if (info->free_pages == 0) return 1000; /* * Index should be a value between 0 and 1. Return a value to 3 * decimal places. * * 0 => no fragmentation * 1 => high fragmentation */ return div_u64((info->free_pages - (info->free_blocks_suitable << order)) * 1000ULL, info->free_pages); } static void unusable_show_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { unsigned int order; int index; struct contig_page_info info; seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); for (order = 0; order < MAX_ORDER; ++order) { fill_contig_page_info(zone, order, &info); index = unusable_free_index(order, &info); seq_printf(m, "%d.%03d ", index / 1000, index % 1000); } seq_putc(m, ' '); } /* * Display unusable free space index * * The unusable free space index measures how much of the available free * memory cannot be used to satisfy an allocation of a given size and is a * value between 0 and 1. The higher the value, the more of free memory is * unusable and by implication, the worse the external fragmentation is. This * can be expressed as a percentage by multiplying by 100. */ static int unusable_show(struct seq_file *m, void *arg) { pg_data_t *pgdat = (pg_data_t *)arg; /* check memoryless node */ |
a47b53c5f vmstat: use N_MEM... |
1823 |
if (!node_state(pgdat->node_id, N_MEMORY)) |
d7a5752c0 mm: export unusab... |
1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 |
return 0; walk_zones_in_node(m, pgdat, unusable_show_print); return 0; } static const struct seq_operations unusable_op = { .start = frag_start, .next = frag_next, .stop = frag_stop, .show = unusable_show, }; static int unusable_open(struct inode *inode, struct file *file) { return seq_open(file, &unusable_op); } static const struct file_operations unusable_file_ops = { .open = unusable_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; |
f1a5ab121 mm: export fragme... |
1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 |
static void extfrag_show_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { unsigned int order; int index; /* Alloc on stack as interrupts are disabled for zone walk */ struct contig_page_info info; seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); for (order = 0; order < MAX_ORDER; ++order) { fill_contig_page_info(zone, order, &info); |
56de7263f mm: compaction: d... |
1863 |
index = __fragmentation_index(order, &info); |
f1a5ab121 mm: export fragme... |
1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 |
seq_printf(m, "%d.%03d ", index / 1000, index % 1000); } seq_putc(m, ' '); } /* * Display fragmentation index for orders that allocations would fail for */ static int extfrag_show(struct seq_file *m, void *arg) { pg_data_t *pgdat = (pg_data_t *)arg; walk_zones_in_node(m, pgdat, extfrag_show_print); return 0; } static const struct seq_operations extfrag_op = { .start = frag_start, .next = frag_next, .stop = frag_stop, .show = extfrag_show, }; static int extfrag_open(struct inode *inode, struct file *file) { return seq_open(file, &extfrag_op); } static const struct file_operations extfrag_file_ops = { .open = extfrag_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; |
d7a5752c0 mm: export unusab... |
1901 1902 |
static int __init extfrag_debug_init(void) { |
bde8bd8a1 mm/vmstat.c: remo... |
1903 |
struct dentry *extfrag_debug_root; |
d7a5752c0 mm: export unusab... |
1904 1905 1906 1907 1908 1909 |
extfrag_debug_root = debugfs_create_dir("extfrag", NULL); if (!extfrag_debug_root) return -ENOMEM; if (!debugfs_create_file("unusable_index", 0444, extfrag_debug_root, NULL, &unusable_file_ops)) |
bde8bd8a1 mm/vmstat.c: remo... |
1910 |
goto fail; |
d7a5752c0 mm: export unusab... |
1911 |
|
f1a5ab121 mm: export fragme... |
1912 1913 |
if (!debugfs_create_file("extfrag_index", 0444, extfrag_debug_root, NULL, &extfrag_file_ops)) |
bde8bd8a1 mm/vmstat.c: remo... |
1914 |
goto fail; |
f1a5ab121 mm: export fragme... |
1915 |
|
d7a5752c0 mm: export unusab... |
1916 |
return 0; |
bde8bd8a1 mm/vmstat.c: remo... |
1917 1918 1919 |
fail: debugfs_remove_recursive(extfrag_debug_root); return -ENOMEM; |
d7a5752c0 mm: export unusab... |
1920 1921 1922 1923 |
} module_init(extfrag_debug_init); #endif |