Blame view
mm/workingset.c
18.3 KB
b24413180 License cleanup: ... |
1 |
// SPDX-License-Identifier: GPL-2.0 |
a528910e1 mm: thrash detect... |
2 3 4 5 6 7 8 9 |
/* * Workingset detection * * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner */ #include <linux/memcontrol.h> #include <linux/writeback.h> |
3a4f8a0b3 mm: remove shmem_... |
10 |
#include <linux/shmem_fs.h> |
a528910e1 mm: thrash detect... |
11 12 13 14 |
#include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/module.h> #include <linux/swap.h> |
14b468791 mm: workingset: m... |
15 |
#include <linux/dax.h> |
a528910e1 mm: thrash detect... |
16 17 18 19 20 21 |
#include <linux/fs.h> #include <linux/mm.h> /* * Double CLOCK lists * |
1e6b10857 mm, workingset: m... |
22 |
* Per node, two clock lists are maintained for file pages: the |
a528910e1 mm: thrash detect... |
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 |
* inactive and the active list. Freshly faulted pages start out at * the head of the inactive list and page reclaim scans pages from the * tail. Pages that are accessed multiple times on the inactive list * are promoted to the active list, to protect them from reclaim, * whereas active pages are demoted to the inactive list when the * active list grows too big. * * fault ------------------------+ * | * +--------------+ | +-------------+ * reclaim <- | inactive | <-+-- demotion | active | <--+ * +--------------+ +-------------+ | * | | * +-------------- promotion ------------------+ * * * Access frequency and refault distance * * A workload is thrashing when its pages are frequently used but they * are evicted from the inactive list every time before another access * would have promoted them to the active list. * * In cases where the average access distance between thrashing pages * is bigger than the size of memory there is nothing that can be * done - the thrashing set could never fit into memory under any * circumstance. * * However, the average access distance could be bigger than the * inactive list, yet smaller than the size of memory. In this case, * the set could fit into memory if it weren't for the currently * active pages - which may be used more, hopefully less frequently: * * +-memory available to cache-+ * | | * +-inactive------+-active----+ * a b | c d e f g h i | J K L M N | * +---------------+-----------+ * * It is prohibitively expensive to accurately track access frequency * of pages. But a reasonable approximation can be made to measure * thrashing on the inactive list, after which refaulting pages can be * activated optimistically to compete with the existing active pages. * * Approximating inactive page access frequency - Observations: * * 1. When a page is accessed for the first time, it is added to the * head of the inactive list, slides every existing inactive page * towards the tail by one slot, and pushes the current tail page * out of memory. * * 2. When a page is accessed for the second time, it is promoted to * the active list, shrinking the inactive list by one slot. This * also slides all inactive pages that were faulted into the cache * more recently than the activated page towards the tail of the * inactive list. * * Thus: * * 1. The sum of evictions and activations between any two points in * time indicate the minimum number of inactive pages accessed in * between. * * 2. Moving one inactive page N page slots towards the tail of the * list requires at least N inactive page accesses. * * Combining these: * * 1. When a page is finally evicted from memory, the number of * inactive pages accessed while the page was in cache is at least * the number of page slots on the inactive list. * * 2. In addition, measuring the sum of evictions and activations (E) * at the time of a page's eviction, and comparing it to another * reading (R) at the time the page faults back into memory tells * the minimum number of accesses while the page was not cached. * This is called the refault distance. * * Because the first access of the page was the fault and the second * access the refault, we combine the in-cache distance with the * out-of-cache distance to get the complete minimum access distance * of this page: * * NR_inactive + (R - E) * * And knowing the minimum access distance of a page, we can easily * tell if the page would be able to stay in cache assuming all page * slots in the cache were available: * * NR_inactive + (R - E) <= NR_inactive + NR_active * * which can be further simplified to * * (R - E) <= NR_active * * Put into words, the refault distance (out-of-cache) can be seen as * a deficit in inactive list space (in-cache). If the inactive list * had (R - E) more page slots, the page would not have been evicted * in between accesses, but activated instead. And on a full system, * the only thing eating into inactive list space is active pages. * * * Activating refaulting pages * * All that is known about the active list is that the pages have been * accessed more than once in the past. This means that at any given * time there is actually a good chance that pages on the active list * are no longer in active use. * * So when a refault distance of (R - E) is observed and there are at * least (R - E) active pages, the refaulting page is activated * optimistically in the hope that (R - E) active pages are actually * used less frequently than the refaulting page - or even not used at * all anymore. * * If this is wrong and demotion kicks in, the pages which are truly * used more frequently will be reactivated while the less frequently * used once will be evicted from memory. * * But if this is right, the stale pages will be pushed out of memory * and the used pages get to stay in cache. * * * Implementation * |
1e6b10857 mm, workingset: m... |
147 148 |
* For each node's file LRU lists, a counter for inactive evictions * and activations is maintained (node->inactive_age). |
a528910e1 mm: thrash detect... |
149 150 |
* * On eviction, a snapshot of this counter (along with some bits to |
1e6b10857 mm, workingset: m... |
151 |
* identify the node) is stored in the now empty page cache radix tree |
a528910e1 mm: thrash detect... |
152 153 154 155 156 |
* slot of the evicted page. This is called a shadow entry. * * On cache misses for which there are shadow entries, an eligible * refault distance will immediately activate the refaulting page. */ |
689c94f03 mm: workingset: #... |
157 |
#define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \ |
1e6b10857 mm, workingset: m... |
158 |
NODES_SHIFT + \ |
23047a96d mm: workingset: p... |
159 |
MEM_CGROUP_ID_SHIFT) |
689c94f03 mm: workingset: #... |
160 |
#define EVICTION_MASK (~0UL >> EVICTION_SHIFT) |
612e44939 mm: workingset: e... |
161 162 163 164 165 166 167 168 169 |
/* * Eviction timestamps need to be able to cover the full range of * actionable refaults. However, bits are tight in the radix tree * entry, and after storing the identifier for the lruvec there might * not be enough left to represent every single actionable refault. In * that case, we have to sacrifice granularity for distance, and group * evictions into coarser buckets by shaving off lower timestamp bits. */ static unsigned int bucket_order __read_mostly; |
1e6b10857 mm, workingset: m... |
170 |
static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction) |
a528910e1 mm: thrash detect... |
171 |
{ |
612e44939 mm: workingset: e... |
172 |
eviction >>= bucket_order; |
23047a96d mm: workingset: p... |
173 |
eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; |
1e6b10857 mm, workingset: m... |
174 |
eviction = (eviction << NODES_SHIFT) | pgdat->node_id; |
a528910e1 mm: thrash detect... |
175 176 177 178 |
eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT); return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); } |
1e6b10857 mm, workingset: m... |
179 |
static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, |
162453bfb mm: workingset: s... |
180 |
unsigned long *evictionp) |
a528910e1 mm: thrash detect... |
181 182 |
{ unsigned long entry = (unsigned long)shadow; |
1e6b10857 mm, workingset: m... |
183 |
int memcgid, nid; |
a528910e1 mm: thrash detect... |
184 185 |
entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; |
a528910e1 mm: thrash detect... |
186 187 |
nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; |
23047a96d mm: workingset: p... |
188 189 |
memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); entry >>= MEM_CGROUP_ID_SHIFT; |
a528910e1 mm: thrash detect... |
190 |
|
23047a96d mm: workingset: p... |
191 |
*memcgidp = memcgid; |
1e6b10857 mm, workingset: m... |
192 |
*pgdat = NODE_DATA(nid); |
612e44939 mm: workingset: e... |
193 |
*evictionp = entry << bucket_order; |
a528910e1 mm: thrash detect... |
194 195 196 197 198 199 200 201 202 203 204 205 |
} /** * workingset_eviction - note the eviction of a page from memory * @mapping: address space the page was backing * @page: the page being evicted * * Returns a shadow entry to be stored in @mapping->page_tree in place * of the evicted @page so that a later refault can be detected. */ void *workingset_eviction(struct address_space *mapping, struct page *page) { |
23047a96d mm: workingset: p... |
206 |
struct mem_cgroup *memcg = page_memcg(page); |
1e6b10857 mm, workingset: m... |
207 |
struct pglist_data *pgdat = page_pgdat(page); |
23047a96d mm: workingset: p... |
208 |
int memcgid = mem_cgroup_id(memcg); |
a528910e1 mm: thrash detect... |
209 |
unsigned long eviction; |
23047a96d mm: workingset: p... |
210 |
struct lruvec *lruvec; |
a528910e1 mm: thrash detect... |
211 |
|
23047a96d mm: workingset: p... |
212 213 214 215 |
/* Page is fully exclusive and pins page->mem_cgroup */ VM_BUG_ON_PAGE(PageLRU(page), page); VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); |
1e6b10857 mm, workingset: m... |
216 |
lruvec = mem_cgroup_lruvec(pgdat, memcg); |
23047a96d mm: workingset: p... |
217 |
eviction = atomic_long_inc_return(&lruvec->inactive_age); |
1e6b10857 mm, workingset: m... |
218 |
return pack_shadow(memcgid, pgdat, eviction); |
a528910e1 mm: thrash detect... |
219 220 221 222 223 224 225 |
} /** * workingset_refault - evaluate the refault of a previously evicted page * @shadow: shadow entry of the evicted page * * Calculates and evaluates the refault distance of the previously |
1e6b10857 mm, workingset: m... |
226 |
* evicted page in the context of the node it was allocated in. |
a528910e1 mm: thrash detect... |
227 228 229 230 231 232 |
* * Returns %true if the page should be activated, %false otherwise. */ bool workingset_refault(void *shadow) { unsigned long refault_distance; |
23047a96d mm: workingset: p... |
233 234 |
unsigned long active_file; struct mem_cgroup *memcg; |
162453bfb mm: workingset: s... |
235 |
unsigned long eviction; |
23047a96d mm: workingset: p... |
236 |
struct lruvec *lruvec; |
162453bfb mm: workingset: s... |
237 |
unsigned long refault; |
1e6b10857 mm, workingset: m... |
238 |
struct pglist_data *pgdat; |
23047a96d mm: workingset: p... |
239 |
int memcgid; |
a528910e1 mm: thrash detect... |
240 |
|
1e6b10857 mm, workingset: m... |
241 |
unpack_shadow(shadow, &memcgid, &pgdat, &eviction); |
162453bfb mm: workingset: s... |
242 |
|
23047a96d mm: workingset: p... |
243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 |
rcu_read_lock(); /* * Look up the memcg associated with the stored ID. It might * have been deleted since the page's eviction. * * Note that in rare events the ID could have been recycled * for a new cgroup that refaults a shared page. This is * impossible to tell from the available data. However, this * should be a rare and limited disturbance, and activations * are always speculative anyway. Ultimately, it's the aging * algorithm's job to shake out the minimum access frequency * for the active cache. * * XXX: On !CONFIG_MEMCG, this will always return NULL; it * would be better if the root_mem_cgroup existed in all * configurations instead. */ memcg = mem_cgroup_from_id(memcgid); if (!mem_cgroup_disabled() && !memcg) { rcu_read_unlock(); return false; } |
1e6b10857 mm, workingset: m... |
265 |
lruvec = mem_cgroup_lruvec(pgdat, memcg); |
23047a96d mm: workingset: p... |
266 |
refault = atomic_long_read(&lruvec->inactive_age); |
fd5388037 mm, vmscan: clean... |
267 |
active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES); |
162453bfb mm: workingset: s... |
268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 |
/* * The unsigned subtraction here gives an accurate distance * across inactive_age overflows in most cases. * * There is a special case: usually, shadow entries have a * short lifetime and are either refaulted or reclaimed along * with the inode before they get too old. But it is not * impossible for the inactive_age to lap a shadow entry in * the field, which can then can result in a false small * refault distance, leading to a false activation should this * old entry actually refault again. However, earlier kernels * used to deactivate unconditionally with *every* reclaim * invocation for the longest time, so the occasional * inappropriate activation leading to pressure on the active * list is not a problem. */ refault_distance = (refault - eviction) & EVICTION_MASK; |
00f3ca2c2 mm: memcontrol: p... |
286 |
inc_lruvec_state(lruvec, WORKINGSET_REFAULT); |
a528910e1 mm: thrash detect... |
287 |
|
23047a96d mm: workingset: p... |
288 |
if (refault_distance <= active_file) { |
00f3ca2c2 mm: memcontrol: p... |
289 |
inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); |
2a2e48854 mm: vmscan: fix I... |
290 |
rcu_read_unlock(); |
a528910e1 mm: thrash detect... |
291 292 |
return true; } |
2a2e48854 mm: vmscan: fix I... |
293 |
rcu_read_unlock(); |
a528910e1 mm: thrash detect... |
294 295 296 297 298 299 300 301 302 |
return false; } /** * workingset_activation - note a page activation * @page: page that is being activated */ void workingset_activation(struct page *page) { |
55779ec75 mm: fix vm-scalab... |
303 |
struct mem_cgroup *memcg; |
23047a96d mm: workingset: p... |
304 |
struct lruvec *lruvec; |
55779ec75 mm: fix vm-scalab... |
305 |
rcu_read_lock(); |
23047a96d mm: workingset: p... |
306 307 308 309 310 311 312 |
/* * Filter non-memcg pages here, e.g. unmap can call * mark_page_accessed() on VDSO pages. * * XXX: See workingset_refault() - this should return * root_mem_cgroup even for !CONFIG_MEMCG. */ |
55779ec75 mm: fix vm-scalab... |
313 314 |
memcg = page_memcg_rcu(page); if (!mem_cgroup_disabled() && !memcg) |
23047a96d mm: workingset: p... |
315 |
goto out; |
ef8f23279 mm, memcg: move m... |
316 |
lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg); |
23047a96d mm: workingset: p... |
317 318 |
atomic_long_inc(&lruvec->inactive_age); out: |
55779ec75 mm: fix vm-scalab... |
319 |
rcu_read_unlock(); |
a528910e1 mm: thrash detect... |
320 |
} |
449dd6984 mm: keep page cac... |
321 322 323 324 325 326 327 328 329 330 331 332 |
/* * Shadow entries reflect the share of the working set that does not * fit into memory, so their number depends on the access pattern of * the workload. In most cases, they will refault or get reclaimed * along with the inode, but a (malicious) workload that streams * through files with a total size several times that of available * memory, while preventing the inodes from being reclaimed, can * create excessive amounts of shadow nodes. To keep a lid on this, * track shadow nodes and reclaim them when they grow way past the * point where they would still be useful. */ |
14b468791 mm: workingset: m... |
333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 |
static struct list_lru shadow_nodes; void workingset_update_node(struct radix_tree_node *node, void *private) { struct address_space *mapping = private; /* Only regular page cache has shadow entries */ if (dax_mapping(mapping) || shmem_mapping(mapping)) return; /* * Track non-empty nodes that contain only shadow entries; * unlink those that contain pages or are being freed. * * Avoid acquiring the list_lru lock when the nodes are * already where they should be. The list_empty() test is safe * as node->private_list is protected by &mapping->tree_lock. */ if (node->count && node->count == node->exceptional) { |
d58275bc9 radix-tree: Store... |
352 |
if (list_empty(&node->private_list)) |
14b468791 mm: workingset: m... |
353 |
list_lru_add(&shadow_nodes, &node->private_list); |
14b468791 mm: workingset: m... |
354 355 356 357 358 |
} else { if (!list_empty(&node->private_list)) list_lru_del(&shadow_nodes, &node->private_list); } } |
449dd6984 mm: keep page cac... |
359 360 361 362 |
static unsigned long count_shadow_nodes(struct shrinker *shrinker, struct shrink_control *sc) { |
449dd6984 mm: keep page cac... |
363 |
unsigned long max_nodes; |
14b468791 mm: workingset: m... |
364 |
unsigned long nodes; |
b53889987 mm: workingset: u... |
365 |
unsigned long cache; |
449dd6984 mm: keep page cac... |
366 367 368 |
/* list_lru lock nests inside IRQ-safe mapping->tree_lock */ local_irq_disable(); |
14b468791 mm: workingset: m... |
369 |
nodes = list_lru_shrink_count(&shadow_nodes, sc); |
449dd6984 mm: keep page cac... |
370 |
local_irq_enable(); |
449dd6984 mm: keep page cac... |
371 |
/* |
b53889987 mm: workingset: u... |
372 373 374 375 376 377 378 379 380 381 382 383 384 385 |
* Approximate a reasonable limit for the radix tree nodes * containing shadow entries. We don't need to keep more * shadow entries than possible pages on the active list, * since refault distances bigger than that are dismissed. * * The size of the active list converges toward 100% of * overall page cache as memory grows, with only a tiny * inactive list. Assume the total cache size for that. * * Nodes might be sparsely populated, with only one shadow * entry in the extreme case. Obviously, we cannot keep one * node for every eligible shadow entry, so compromise on a * worst-case density of 1/8th. Below that, not all eligible * refaults can be detected anymore. |
449dd6984 mm: keep page cac... |
386 387 388 |
* * On 64-bit with 7 radix_tree_nodes per page and 64 slots * each, this will reclaim shadow entries when they consume |
b53889987 mm: workingset: u... |
389 |
* ~1.8% of available memory: |
449dd6984 mm: keep page cac... |
390 |
* |
b53889987 mm: workingset: u... |
391 |
* PAGE_SIZE / radix_tree_nodes / node_entries * 8 / PAGE_SIZE |
449dd6984 mm: keep page cac... |
392 |
*/ |
b53889987 mm: workingset: u... |
393 394 395 396 397 398 399 400 |
if (sc->memcg) { cache = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid, LRU_ALL_FILE); } else { cache = node_page_state(NODE_DATA(sc->nid), NR_ACTIVE_FILE) + node_page_state(NODE_DATA(sc->nid), NR_INACTIVE_FILE); } max_nodes = cache >> (RADIX_TREE_MAP_SHIFT - 3); |
449dd6984 mm: keep page cac... |
401 |
|
14b468791 mm: workingset: m... |
402 |
if (nodes <= max_nodes) |
449dd6984 mm: keep page cac... |
403 |
return 0; |
14b468791 mm: workingset: m... |
404 |
return nodes - max_nodes; |
449dd6984 mm: keep page cac... |
405 406 407 |
} static enum lru_status shadow_lru_isolate(struct list_head *item, |
3f97b1632 list_lru: add hel... |
408 |
struct list_lru_one *lru, |
449dd6984 mm: keep page cac... |
409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 |
spinlock_t *lru_lock, void *arg) { struct address_space *mapping; struct radix_tree_node *node; unsigned int i; int ret; /* * Page cache insertions and deletions synchroneously maintain * the shadow node LRU under the mapping->tree_lock and the * lru_lock. Because the page cache tree is emptied before * the inode can be destroyed, holding the lru_lock pins any * address_space that has radix tree nodes on the LRU. * * We can then safely transition to the mapping->tree_lock to * pin only the address_space of the particular node we want * to reclaim, take the node off-LRU, and drop the lru_lock. */ node = container_of(item, struct radix_tree_node, private_list); |
d58275bc9 radix-tree: Store... |
430 |
mapping = container_of(node->root, struct address_space, page_tree); |
449dd6984 mm: keep page cac... |
431 432 433 434 435 436 437 |
/* Coming from the list, invert the lock order */ if (!spin_trylock(&mapping->tree_lock)) { spin_unlock(lru_lock); ret = LRU_RETRY; goto out; } |
3f97b1632 list_lru: add hel... |
438 |
list_lru_isolate(lru, item); |
449dd6984 mm: keep page cac... |
439 440 441 442 443 444 445 |
spin_unlock(lru_lock); /* * The nodes should only contain one or more shadow entries, * no pages, so we expect to be able to remove them all and * delete and free the empty node afterwards. */ |
14b468791 mm: workingset: m... |
446 |
if (WARN_ON_ONCE(!node->exceptional)) |
b936887e8 mm: workingset: t... |
447 |
goto out_invalid; |
14b468791 mm: workingset: m... |
448 |
if (WARN_ON_ONCE(node->count != node->exceptional)) |
b936887e8 mm: workingset: t... |
449 |
goto out_invalid; |
449dd6984 mm: keep page cac... |
450 451 |
for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { if (node->slots[i]) { |
b936887e8 mm: workingset: t... |
452 453 |
if (WARN_ON_ONCE(!radix_tree_exceptional_entry(node->slots[i]))) goto out_invalid; |
14b468791 mm: workingset: m... |
454 455 |
if (WARN_ON_ONCE(!node->exceptional)) goto out_invalid; |
b936887e8 mm: workingset: t... |
456 457 |
if (WARN_ON_ONCE(!mapping->nrexceptional)) goto out_invalid; |
449dd6984 mm: keep page cac... |
458 |
node->slots[i] = NULL; |
14b468791 mm: workingset: m... |
459 460 |
node->exceptional--; node->count--; |
f9fe48bec dax: support dirt... |
461 |
mapping->nrexceptional--; |
449dd6984 mm: keep page cac... |
462 463 |
} } |
14b468791 mm: workingset: m... |
464 |
if (WARN_ON_ONCE(node->exceptional)) |
b936887e8 mm: workingset: t... |
465 |
goto out_invalid; |
00f3ca2c2 mm: memcontrol: p... |
466 |
inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM); |
ea07b862a mm: workingset: f... |
467 468 |
__radix_tree_delete_node(&mapping->page_tree, node, workingset_update_node, mapping); |
449dd6984 mm: keep page cac... |
469 |
|
b936887e8 mm: workingset: t... |
470 |
out_invalid: |
449dd6984 mm: keep page cac... |
471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 |
spin_unlock(&mapping->tree_lock); ret = LRU_REMOVED_RETRY; out: local_irq_enable(); cond_resched(); local_irq_disable(); spin_lock(lru_lock); return ret; } static unsigned long scan_shadow_nodes(struct shrinker *shrinker, struct shrink_control *sc) { unsigned long ret; /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ local_irq_disable(); |
14b468791 mm: workingset: m... |
488 |
ret = list_lru_shrink_walk(&shadow_nodes, sc, shadow_lru_isolate, NULL); |
449dd6984 mm: keep page cac... |
489 490 491 492 493 494 495 496 |
local_irq_enable(); return ret; } static struct shrinker workingset_shadow_shrinker = { .count_objects = count_shadow_nodes, .scan_objects = scan_shadow_nodes, .seeks = DEFAULT_SEEKS, |
0a6b76dd2 mm: workingset: m... |
497 |
.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, |
449dd6984 mm: keep page cac... |
498 499 500 501 502 503 504 505 506 507 |
}; /* * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe * mapping->tree_lock. */ static struct lock_class_key shadow_nodes_key; static int __init workingset_init(void) { |
612e44939 mm: workingset: e... |
508 509 |
unsigned int timestamp_bits; unsigned int max_order; |
449dd6984 mm: keep page cac... |
510 |
int ret; |
612e44939 mm: workingset: e... |
511 512 513 514 515 516 517 518 519 520 521 522 |
BUILD_BUG_ON(BITS_PER_LONG < EVICTION_SHIFT); /* * Calculate the eviction bucket size to cover the longest * actionable refault distance, which is currently half of * memory (totalram_pages/2). However, memory hotplug may add * some more pages at runtime, so keep working with up to * double the initial memory by using totalram_pages as-is. */ timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT; max_order = fls_long(totalram_pages - 1); if (max_order > timestamp_bits) bucket_order = max_order - timestamp_bits; |
d3d36c4b5 mm: workingset: p... |
523 524 |
pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u ", |
612e44939 mm: workingset: e... |
525 |
timestamp_bits, max_order, bucket_order); |
0cefabdaf mm: workingset: f... |
526 |
ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key); |
449dd6984 mm: keep page cac... |
527 528 529 530 531 532 533 |
if (ret) goto err; ret = register_shrinker(&workingset_shadow_shrinker); if (ret) goto err_list_lru; return 0; err_list_lru: |
14b468791 mm: workingset: m... |
534 |
list_lru_destroy(&shadow_nodes); |
449dd6984 mm: keep page cac... |
535 536 537 538 |
err: return ret; } module_init(workingset_init); |