mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-05 18:14:07 +08:00
1c676e0d9b
PG_idle and PG_young allow the two PTE Accessed bit users, Idle Page Tracking and the reclaim logic concurrently work while not interfering with each other. That is, when they need to clear the Accessed bit, they set PG_young to represent the previous state of the bit, respectively. And when they need to read the bit, if the bit is cleared, they further read the PG_young to know whether the other has cleared the bit meanwhile or not. For yet another user of the PTE Accessed bit, we could add another page flag, or extend the mechanism to use the flags. For the DAMON usecase, however, we don't need to do that just yet. IDLE_PAGE_TRACKING and DAMON are mutually exclusive, so there's only ever going to be one user of the current set of flags. In this commit, we split out the CONFIG options to allow for the use of PG_young and PG_idle outside of idle page tracking. In the next commit, DAMON's reference implementation of the virtual memory address space monitoring primitives will use it. [sjpark@amazon.de: set PAGE_EXTENSION for non-64BIT] Link: https://lkml.kernel.org/r/20210806095153.6444-1-sj38.park@gmail.com [akpm@linux-foundation.org: tweak Kconfig text] [sjpark@amazon.de: hide PAGE_IDLE_FLAG from users] Link: https://lkml.kernel.org/r/20210813081238.34705-1-sj38.park@gmail.com Link: https://lkml.kernel.org/r/20210716081449.22187-5-sj38.park@gmail.com Signed-off-by: SeongJae Park <sjpark@amazon.de> Reviewed-by: Shakeel Butt <shakeelb@google.com> Reviewed-by: Fernand Sieber <sieberf@amazon.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Amit Shah <amit@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Brendan Higgins <brendanhiggins@google.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: David Woodhouse <dwmw@amazon.com> Cc: Fan Du <fan.du@intel.com> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Greg Thelen <gthelen@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Leonard Foerster <foersleo@amazon.de> Cc: Marco Elver <elver@google.com> Cc: Markus Boehme <markubo@amazon.de> Cc: Maximilian Heyne <mheyne@amazon.de> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@surriel.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
222 lines
5.2 KiB
C
222 lines
5.2 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/init.h>
|
|
#include <linux/memblock.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/sysfs.h>
|
|
#include <linux/kobject.h>
|
|
#include <linux/memory_hotplug.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/mmzone.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/rmap.h>
|
|
#include <linux/mmu_notifier.h>
|
|
#include <linux/page_ext.h>
|
|
#include <linux/page_idle.h>
|
|
|
|
#define BITMAP_CHUNK_SIZE sizeof(u64)
|
|
#define BITMAP_CHUNK_BITS (BITMAP_CHUNK_SIZE * BITS_PER_BYTE)
|
|
|
|
/*
|
|
* Idle page tracking only considers user memory pages, for other types of
|
|
* pages the idle flag is always unset and an attempt to set it is silently
|
|
* ignored.
|
|
*
|
|
* We treat a page as a user memory page if it is on an LRU list, because it is
|
|
* always safe to pass such a page to rmap_walk(), which is essential for idle
|
|
* page tracking. With such an indicator of user pages we can skip isolated
|
|
* pages, but since there are not usually many of them, it will hardly affect
|
|
* the overall result.
|
|
*
|
|
* This function tries to get a user memory page by pfn as described above.
|
|
*/
|
|
static struct page *page_idle_get_page(unsigned long pfn)
|
|
{
|
|
struct page *page = pfn_to_online_page(pfn);
|
|
|
|
if (!page || !PageLRU(page) ||
|
|
!get_page_unless_zero(page))
|
|
return NULL;
|
|
|
|
if (unlikely(!PageLRU(page))) {
|
|
put_page(page);
|
|
page = NULL;
|
|
}
|
|
return page;
|
|
}
|
|
|
|
static bool page_idle_clear_pte_refs_one(struct page *page,
|
|
struct vm_area_struct *vma,
|
|
unsigned long addr, void *arg)
|
|
{
|
|
struct page_vma_mapped_walk pvmw = {
|
|
.page = page,
|
|
.vma = vma,
|
|
.address = addr,
|
|
};
|
|
bool referenced = false;
|
|
|
|
while (page_vma_mapped_walk(&pvmw)) {
|
|
addr = pvmw.address;
|
|
if (pvmw.pte) {
|
|
/*
|
|
* For PTE-mapped THP, one sub page is referenced,
|
|
* the whole THP is referenced.
|
|
*/
|
|
if (ptep_clear_young_notify(vma, addr, pvmw.pte))
|
|
referenced = true;
|
|
} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
|
|
if (pmdp_clear_young_notify(vma, addr, pvmw.pmd))
|
|
referenced = true;
|
|
} else {
|
|
/* unexpected pmd-mapped page? */
|
|
WARN_ON_ONCE(1);
|
|
}
|
|
}
|
|
|
|
if (referenced) {
|
|
clear_page_idle(page);
|
|
/*
|
|
* We cleared the referenced bit in a mapping to this page. To
|
|
* avoid interference with page reclaim, mark it young so that
|
|
* page_referenced() will return > 0.
|
|
*/
|
|
set_page_young(page);
|
|
}
|
|
return true;
|
|
}
|
|
|
|
static void page_idle_clear_pte_refs(struct page *page)
|
|
{
|
|
/*
|
|
* Since rwc.arg is unused, rwc is effectively immutable, so we
|
|
* can make it static const to save some cycles and stack.
|
|
*/
|
|
static const struct rmap_walk_control rwc = {
|
|
.rmap_one = page_idle_clear_pte_refs_one,
|
|
.anon_lock = page_lock_anon_vma_read,
|
|
};
|
|
bool need_lock;
|
|
|
|
if (!page_mapped(page) ||
|
|
!page_rmapping(page))
|
|
return;
|
|
|
|
need_lock = !PageAnon(page) || PageKsm(page);
|
|
if (need_lock && !trylock_page(page))
|
|
return;
|
|
|
|
rmap_walk(page, (struct rmap_walk_control *)&rwc);
|
|
|
|
if (need_lock)
|
|
unlock_page(page);
|
|
}
|
|
|
|
static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj,
|
|
struct bin_attribute *attr, char *buf,
|
|
loff_t pos, size_t count)
|
|
{
|
|
u64 *out = (u64 *)buf;
|
|
struct page *page;
|
|
unsigned long pfn, end_pfn;
|
|
int bit;
|
|
|
|
if (pos % BITMAP_CHUNK_SIZE || count % BITMAP_CHUNK_SIZE)
|
|
return -EINVAL;
|
|
|
|
pfn = pos * BITS_PER_BYTE;
|
|
if (pfn >= max_pfn)
|
|
return 0;
|
|
|
|
end_pfn = pfn + count * BITS_PER_BYTE;
|
|
if (end_pfn > max_pfn)
|
|
end_pfn = max_pfn;
|
|
|
|
for (; pfn < end_pfn; pfn++) {
|
|
bit = pfn % BITMAP_CHUNK_BITS;
|
|
if (!bit)
|
|
*out = 0ULL;
|
|
page = page_idle_get_page(pfn);
|
|
if (page) {
|
|
if (page_is_idle(page)) {
|
|
/*
|
|
* The page might have been referenced via a
|
|
* pte, in which case it is not idle. Clear
|
|
* refs and recheck.
|
|
*/
|
|
page_idle_clear_pte_refs(page);
|
|
if (page_is_idle(page))
|
|
*out |= 1ULL << bit;
|
|
}
|
|
put_page(page);
|
|
}
|
|
if (bit == BITMAP_CHUNK_BITS - 1)
|
|
out++;
|
|
cond_resched();
|
|
}
|
|
return (char *)out - buf;
|
|
}
|
|
|
|
static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj,
|
|
struct bin_attribute *attr, char *buf,
|
|
loff_t pos, size_t count)
|
|
{
|
|
const u64 *in = (u64 *)buf;
|
|
struct page *page;
|
|
unsigned long pfn, end_pfn;
|
|
int bit;
|
|
|
|
if (pos % BITMAP_CHUNK_SIZE || count % BITMAP_CHUNK_SIZE)
|
|
return -EINVAL;
|
|
|
|
pfn = pos * BITS_PER_BYTE;
|
|
if (pfn >= max_pfn)
|
|
return -ENXIO;
|
|
|
|
end_pfn = pfn + count * BITS_PER_BYTE;
|
|
if (end_pfn > max_pfn)
|
|
end_pfn = max_pfn;
|
|
|
|
for (; pfn < end_pfn; pfn++) {
|
|
bit = pfn % BITMAP_CHUNK_BITS;
|
|
if ((*in >> bit) & 1) {
|
|
page = page_idle_get_page(pfn);
|
|
if (page) {
|
|
page_idle_clear_pte_refs(page);
|
|
set_page_idle(page);
|
|
put_page(page);
|
|
}
|
|
}
|
|
if (bit == BITMAP_CHUNK_BITS - 1)
|
|
in++;
|
|
cond_resched();
|
|
}
|
|
return (char *)in - buf;
|
|
}
|
|
|
|
static struct bin_attribute page_idle_bitmap_attr =
|
|
__BIN_ATTR(bitmap, 0600,
|
|
page_idle_bitmap_read, page_idle_bitmap_write, 0);
|
|
|
|
static struct bin_attribute *page_idle_bin_attrs[] = {
|
|
&page_idle_bitmap_attr,
|
|
NULL,
|
|
};
|
|
|
|
static const struct attribute_group page_idle_attr_group = {
|
|
.bin_attrs = page_idle_bin_attrs,
|
|
.name = "page_idle",
|
|
};
|
|
|
|
static int __init page_idle_init(void)
|
|
{
|
|
int err;
|
|
|
|
err = sysfs_create_group(mm_kobj, &page_idle_attr_group);
|
|
if (err) {
|
|
pr_err("page_idle: register sysfs failed\n");
|
|
return err;
|
|
}
|
|
return 0;
|
|
}
|
|
subsys_initcall(page_idle_init);
|