b24413180f
Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
550 lines
18 KiB
C
550 lines
18 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Workingset detection
|
|
*
|
|
* Copyright (C) 2013 Red Hat, Inc., Johannes Weiner
|
|
*/
|
|
|
|
#include <linux/memcontrol.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/shmem_fs.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/atomic.h>
|
|
#include <linux/module.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/dax.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mm.h>
|
|
|
|
/*
|
|
* Double CLOCK lists
|
|
*
|
|
* Per node, two clock lists are maintained for file pages: the
|
|
* 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
|
|
*
|
|
* For each node's file LRU lists, a counter for inactive evictions
|
|
* and activations is maintained (node->inactive_age).
|
|
*
|
|
* On eviction, a snapshot of this counter (along with some bits to
|
|
* identify the node) is stored in the now empty page cache radix tree
|
|
* 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.
|
|
*/
|
|
|
|
#define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \
|
|
NODES_SHIFT + \
|
|
MEM_CGROUP_ID_SHIFT)
|
|
#define EVICTION_MASK (~0UL >> EVICTION_SHIFT)
|
|
|
|
/*
|
|
* 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;
|
|
|
|
static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction)
|
|
{
|
|
eviction >>= bucket_order;
|
|
eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
|
|
eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
|
|
eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);
|
|
|
|
return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
|
|
}
|
|
|
|
static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
|
|
unsigned long *evictionp)
|
|
{
|
|
unsigned long entry = (unsigned long)shadow;
|
|
int memcgid, nid;
|
|
|
|
entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
|
|
nid = entry & ((1UL << NODES_SHIFT) - 1);
|
|
entry >>= NODES_SHIFT;
|
|
memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1);
|
|
entry >>= MEM_CGROUP_ID_SHIFT;
|
|
|
|
*memcgidp = memcgid;
|
|
*pgdat = NODE_DATA(nid);
|
|
*evictionp = entry << bucket_order;
|
|
}
|
|
|
|
/**
|
|
* 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)
|
|
{
|
|
struct mem_cgroup *memcg = page_memcg(page);
|
|
struct pglist_data *pgdat = page_pgdat(page);
|
|
int memcgid = mem_cgroup_id(memcg);
|
|
unsigned long eviction;
|
|
struct lruvec *lruvec;
|
|
|
|
/* 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);
|
|
|
|
lruvec = mem_cgroup_lruvec(pgdat, memcg);
|
|
eviction = atomic_long_inc_return(&lruvec->inactive_age);
|
|
return pack_shadow(memcgid, pgdat, eviction);
|
|
}
|
|
|
|
/**
|
|
* 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
|
|
* evicted page in the context of the node it was allocated in.
|
|
*
|
|
* Returns %true if the page should be activated, %false otherwise.
|
|
*/
|
|
bool workingset_refault(void *shadow)
|
|
{
|
|
unsigned long refault_distance;
|
|
unsigned long active_file;
|
|
struct mem_cgroup *memcg;
|
|
unsigned long eviction;
|
|
struct lruvec *lruvec;
|
|
unsigned long refault;
|
|
struct pglist_data *pgdat;
|
|
int memcgid;
|
|
|
|
unpack_shadow(shadow, &memcgid, &pgdat, &eviction);
|
|
|
|
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;
|
|
}
|
|
lruvec = mem_cgroup_lruvec(pgdat, memcg);
|
|
refault = atomic_long_read(&lruvec->inactive_age);
|
|
active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES);
|
|
|
|
/*
|
|
* 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;
|
|
|
|
inc_lruvec_state(lruvec, WORKINGSET_REFAULT);
|
|
|
|
if (refault_distance <= active_file) {
|
|
inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE);
|
|
rcu_read_unlock();
|
|
return true;
|
|
}
|
|
rcu_read_unlock();
|
|
return false;
|
|
}
|
|
|
|
/**
|
|
* workingset_activation - note a page activation
|
|
* @page: page that is being activated
|
|
*/
|
|
void workingset_activation(struct page *page)
|
|
{
|
|
struct mem_cgroup *memcg;
|
|
struct lruvec *lruvec;
|
|
|
|
rcu_read_lock();
|
|
/*
|
|
* 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.
|
|
*/
|
|
memcg = page_memcg_rcu(page);
|
|
if (!mem_cgroup_disabled() && !memcg)
|
|
goto out;
|
|
lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
|
|
atomic_long_inc(&lruvec->inactive_age);
|
|
out:
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
|
|
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) {
|
|
if (list_empty(&node->private_list))
|
|
list_lru_add(&shadow_nodes, &node->private_list);
|
|
} else {
|
|
if (!list_empty(&node->private_list))
|
|
list_lru_del(&shadow_nodes, &node->private_list);
|
|
}
|
|
}
|
|
|
|
static unsigned long count_shadow_nodes(struct shrinker *shrinker,
|
|
struct shrink_control *sc)
|
|
{
|
|
unsigned long max_nodes;
|
|
unsigned long nodes;
|
|
unsigned long cache;
|
|
|
|
/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
|
|
local_irq_disable();
|
|
nodes = list_lru_shrink_count(&shadow_nodes, sc);
|
|
local_irq_enable();
|
|
|
|
/*
|
|
* 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.
|
|
*
|
|
* On 64-bit with 7 radix_tree_nodes per page and 64 slots
|
|
* each, this will reclaim shadow entries when they consume
|
|
* ~1.8% of available memory:
|
|
*
|
|
* PAGE_SIZE / radix_tree_nodes / node_entries * 8 / PAGE_SIZE
|
|
*/
|
|
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);
|
|
|
|
if (nodes <= max_nodes)
|
|
return 0;
|
|
return nodes - max_nodes;
|
|
}
|
|
|
|
static enum lru_status shadow_lru_isolate(struct list_head *item,
|
|
struct list_lru_one *lru,
|
|
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);
|
|
mapping = container_of(node->root, struct address_space, page_tree);
|
|
|
|
/* Coming from the list, invert the lock order */
|
|
if (!spin_trylock(&mapping->tree_lock)) {
|
|
spin_unlock(lru_lock);
|
|
ret = LRU_RETRY;
|
|
goto out;
|
|
}
|
|
|
|
list_lru_isolate(lru, item);
|
|
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.
|
|
*/
|
|
if (WARN_ON_ONCE(!node->exceptional))
|
|
goto out_invalid;
|
|
if (WARN_ON_ONCE(node->count != node->exceptional))
|
|
goto out_invalid;
|
|
for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
|
|
if (node->slots[i]) {
|
|
if (WARN_ON_ONCE(!radix_tree_exceptional_entry(node->slots[i])))
|
|
goto out_invalid;
|
|
if (WARN_ON_ONCE(!node->exceptional))
|
|
goto out_invalid;
|
|
if (WARN_ON_ONCE(!mapping->nrexceptional))
|
|
goto out_invalid;
|
|
node->slots[i] = NULL;
|
|
node->exceptional--;
|
|
node->count--;
|
|
mapping->nrexceptional--;
|
|
}
|
|
}
|
|
if (WARN_ON_ONCE(node->exceptional))
|
|
goto out_invalid;
|
|
inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM);
|
|
__radix_tree_delete_node(&mapping->page_tree, node,
|
|
workingset_update_node, mapping);
|
|
|
|
out_invalid:
|
|
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();
|
|
ret = list_lru_shrink_walk(&shadow_nodes, sc, shadow_lru_isolate, NULL);
|
|
local_irq_enable();
|
|
return ret;
|
|
}
|
|
|
|
static struct shrinker workingset_shadow_shrinker = {
|
|
.count_objects = count_shadow_nodes,
|
|
.scan_objects = scan_shadow_nodes,
|
|
.seeks = DEFAULT_SEEKS,
|
|
.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE,
|
|
};
|
|
|
|
/*
|
|
* 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)
|
|
{
|
|
unsigned int timestamp_bits;
|
|
unsigned int max_order;
|
|
int ret;
|
|
|
|
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;
|
|
pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",
|
|
timestamp_bits, max_order, bucket_order);
|
|
|
|
ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key);
|
|
if (ret)
|
|
goto err;
|
|
ret = register_shrinker(&workingset_shadow_shrinker);
|
|
if (ret)
|
|
goto err_list_lru;
|
|
return 0;
|
|
err_list_lru:
|
|
list_lru_destroy(&shadow_nodes);
|
|
err:
|
|
return ret;
|
|
}
|
|
module_init(workingset_init);
|