mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-21 10:05:00 +08:00
c11d34fa13
It is racy to non-atomically read a pte, then clear the young bit, then
write it back as this could discard dirty information. Further, it is bad
practice to directly set a pte entry within a table. Instead clearing
young must go through the arch-provided helper,
ptep_test_and_clear_young() to ensure it is modified atomically and to
give the arch code visibility and allow it to check (and potentially
modify) the operation.
Link: https://lkml.kernel.org/r/20230602092949.545577-3-ryan.roberts@arm.com
Fixes: 3f49584b26 ("mm/damon: implement primitives for the virtual memory address spaces").
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Reviewed-by: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
141 lines
3.4 KiB
C
141 lines
3.4 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Common Primitives for Data Access Monitoring
|
|
*
|
|
* Author: SeongJae Park <sj@kernel.org>
|
|
*/
|
|
|
|
#include <linux/mmu_notifier.h>
|
|
#include <linux/page_idle.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/rmap.h>
|
|
|
|
#include "ops-common.h"
|
|
|
|
/*
|
|
* Get an online page for a pfn if it's in the LRU list. Otherwise, returns
|
|
* NULL.
|
|
*
|
|
* The body of this function is stolen from the 'page_idle_get_folio()'. We
|
|
* steal rather than reuse it because the code is quite simple.
|
|
*/
|
|
struct folio *damon_get_folio(unsigned long pfn)
|
|
{
|
|
struct page *page = pfn_to_online_page(pfn);
|
|
struct folio *folio;
|
|
|
|
if (!page || PageTail(page))
|
|
return NULL;
|
|
|
|
folio = page_folio(page);
|
|
if (!folio_test_lru(folio) || !folio_try_get(folio))
|
|
return NULL;
|
|
if (unlikely(page_folio(page) != folio || !folio_test_lru(folio))) {
|
|
folio_put(folio);
|
|
folio = NULL;
|
|
}
|
|
return folio;
|
|
}
|
|
|
|
void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr)
|
|
{
|
|
bool referenced = false;
|
|
struct folio *folio = damon_get_folio(pte_pfn(*pte));
|
|
|
|
if (!folio)
|
|
return;
|
|
|
|
if (ptep_test_and_clear_young(vma, addr, pte))
|
|
referenced = true;
|
|
|
|
#ifdef CONFIG_MMU_NOTIFIER
|
|
if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE))
|
|
referenced = true;
|
|
#endif /* CONFIG_MMU_NOTIFIER */
|
|
|
|
if (referenced)
|
|
folio_set_young(folio);
|
|
|
|
folio_set_idle(folio);
|
|
folio_put(folio);
|
|
}
|
|
|
|
void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr)
|
|
{
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
bool referenced = false;
|
|
struct folio *folio = damon_get_folio(pmd_pfn(*pmd));
|
|
|
|
if (!folio)
|
|
return;
|
|
|
|
if (pmdp_test_and_clear_young(vma, addr, pmd))
|
|
referenced = true;
|
|
|
|
#ifdef CONFIG_MMU_NOTIFIER
|
|
if (mmu_notifier_clear_young(vma->vm_mm, addr, addr + HPAGE_PMD_SIZE))
|
|
referenced = true;
|
|
#endif /* CONFIG_MMU_NOTIFIER */
|
|
|
|
if (referenced)
|
|
folio_set_young(folio);
|
|
|
|
folio_set_idle(folio);
|
|
folio_put(folio);
|
|
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
}
|
|
|
|
#define DAMON_MAX_SUBSCORE (100)
|
|
#define DAMON_MAX_AGE_IN_LOG (32)
|
|
|
|
int damon_hot_score(struct damon_ctx *c, struct damon_region *r,
|
|
struct damos *s)
|
|
{
|
|
unsigned int max_nr_accesses;
|
|
int freq_subscore;
|
|
unsigned int age_in_sec;
|
|
int age_in_log, age_subscore;
|
|
unsigned int freq_weight = s->quota.weight_nr_accesses;
|
|
unsigned int age_weight = s->quota.weight_age;
|
|
int hotness;
|
|
|
|
max_nr_accesses = c->attrs.aggr_interval / c->attrs.sample_interval;
|
|
freq_subscore = r->nr_accesses * DAMON_MAX_SUBSCORE / max_nr_accesses;
|
|
|
|
age_in_sec = (unsigned long)r->age * c->attrs.aggr_interval / 1000000;
|
|
for (age_in_log = 0; age_in_log < DAMON_MAX_AGE_IN_LOG && age_in_sec;
|
|
age_in_log++, age_in_sec >>= 1)
|
|
;
|
|
|
|
/* If frequency is 0, higher age means it's colder */
|
|
if (freq_subscore == 0)
|
|
age_in_log *= -1;
|
|
|
|
/*
|
|
* Now age_in_log is in [-DAMON_MAX_AGE_IN_LOG, DAMON_MAX_AGE_IN_LOG].
|
|
* Scale it to be in [0, 100] and set it as age subscore.
|
|
*/
|
|
age_in_log += DAMON_MAX_AGE_IN_LOG;
|
|
age_subscore = age_in_log * DAMON_MAX_SUBSCORE /
|
|
DAMON_MAX_AGE_IN_LOG / 2;
|
|
|
|
hotness = (freq_weight * freq_subscore + age_weight * age_subscore);
|
|
if (freq_weight + age_weight)
|
|
hotness /= freq_weight + age_weight;
|
|
/*
|
|
* Transform it to fit in [0, DAMOS_MAX_SCORE]
|
|
*/
|
|
hotness = hotness * DAMOS_MAX_SCORE / DAMON_MAX_SUBSCORE;
|
|
|
|
return hotness;
|
|
}
|
|
|
|
int damon_cold_score(struct damon_ctx *c, struct damon_region *r,
|
|
struct damos *s)
|
|
{
|
|
int hotness = damon_hot_score(c, r, s);
|
|
|
|
/* Return coldness of the region */
|
|
return DAMOS_MAX_SCORE - hotness;
|
|
}
|