linux/mm/damon/paddr.c
Linus Torvalds 9030fb0bb9 Folio changes for 5.18
- Rewrite how munlock works to massively reduce the contention
    on i_mmap_rwsem (Hugh Dickins):
    https://lore.kernel.org/linux-mm/8e4356d-9622-a7f0-b2c-f116b5f2efea@google.com/
  - Sort out the page refcount mess for ZONE_DEVICE pages (Christoph Hellwig):
    https://lore.kernel.org/linux-mm/20220210072828.2930359-1-hch@lst.de/
  - Convert GUP to use folios and make pincount available for order-1
    pages. (Matthew Wilcox)
  - Convert a few more truncation functions to use folios (Matthew Wilcox)
  - Convert page_vma_mapped_walk to use PFNs instead of pages (Matthew Wilcox)
  - Convert rmap_walk to use folios (Matthew Wilcox)
  - Convert most of shrink_page_list() to use a folio (Matthew Wilcox)
  - Add support for creating large folios in readahead (Matthew Wilcox)
 -----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCgAdFiEEejHryeLBw/spnjHrDpNsjXcpgj4FAmI4ucgACgkQDpNsjXcp
 gj69Wgf6AwqwmO5Tmy+fLScDPqWxmXJofbocae1kyoGHf7Ui91OK4U2j6IpvAr+g
 P/vLIK+JAAcTQcrSCjymuEkf4HkGZOR03QQn7maPIEe4eLrZRQDEsmHC1L9gpeJp
 s/GMvDWiGE0Tnxu0EOzfVi/yT+qjIl/S8VvqtCoJv1HdzxitZ7+1RDuqImaMC5MM
 Qi3uHag78vLmCltLXpIOdpgZhdZexCdL2Y/1npf+b6FVkAJRRNUnA0gRbS7YpoVp
 CbxEJcmAl9cpJLuj5i5kIfS9trr+/QcvbUlzRxh4ggC58iqnmF2V09l2MJ7YU3XL
 v1O/Elq4lRhXninZFQEm9zjrri7LDQ==
 =n9Ad
 -----END PGP SIGNATURE-----

Merge tag 'folio-5.18c' of git://git.infradead.org/users/willy/pagecache

Pull folio updates from Matthew Wilcox:

 - Rewrite how munlock works to massively reduce the contention on
   i_mmap_rwsem (Hugh Dickins):

     https://lore.kernel.org/linux-mm/8e4356d-9622-a7f0-b2c-f116b5f2efea@google.com/

 - Sort out the page refcount mess for ZONE_DEVICE pages (Christoph
   Hellwig):

     https://lore.kernel.org/linux-mm/20220210072828.2930359-1-hch@lst.de/

 - Convert GUP to use folios and make pincount available for order-1
   pages. (Matthew Wilcox)

 - Convert a few more truncation functions to use folios (Matthew
   Wilcox)

 - Convert page_vma_mapped_walk to use PFNs instead of pages (Matthew
   Wilcox)

 - Convert rmap_walk to use folios (Matthew Wilcox)

 - Convert most of shrink_page_list() to use a folio (Matthew Wilcox)

 - Add support for creating large folios in readahead (Matthew Wilcox)

* tag 'folio-5.18c' of git://git.infradead.org/users/willy/pagecache: (114 commits)
  mm/damon: minor cleanup for damon_pa_young
  selftests/vm/transhuge-stress: Support file-backed PMD folios
  mm/filemap: Support VM_HUGEPAGE for file mappings
  mm/readahead: Switch to page_cache_ra_order
  mm/readahead: Align file mappings for non-DAX
  mm/readahead: Add large folio readahead
  mm: Support arbitrary THP sizes
  mm: Make large folios depend on THP
  mm: Fix READ_ONLY_THP warning
  mm/filemap: Allow large folios to be added to the page cache
  mm: Turn can_split_huge_page() into can_split_folio()
  mm/vmscan: Convert pageout() to take a folio
  mm/vmscan: Turn page_check_references() into folio_check_references()
  mm/vmscan: Account large folios correctly
  mm/vmscan: Optimise shrink_page_list for non-PMD-sized folios
  mm/vmscan: Free non-shmem folios without splitting them
  mm/rmap: Constify the rmap_walk_control argument
  mm/rmap: Convert rmap_walk() to take a folio
  mm: Turn page_anon_vma() into folio_anon_vma()
  mm/rmap: Turn page_lock_anon_vma_read() into folio_lock_anon_vma_read()
  ...
2022-03-22 17:03:12 -07:00

274 lines
6.0 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* DAMON Primitives for The Physical Address Space
*
* Author: SeongJae Park <sj@kernel.org>
*/
#define pr_fmt(fmt) "damon-pa: " fmt
#include <linux/mmu_notifier.h>
#include <linux/page_idle.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include "../internal.h"
#include "ops-common.h"
static bool __damon_pa_mkold(struct folio *folio, struct vm_area_struct *vma,
unsigned long addr, void *arg)
{
DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, addr, 0);
while (page_vma_mapped_walk(&pvmw)) {
addr = pvmw.address;
if (pvmw.pte)
damon_ptep_mkold(pvmw.pte, vma->vm_mm, addr);
else
damon_pmdp_mkold(pvmw.pmd, vma->vm_mm, addr);
}
return true;
}
static void damon_pa_mkold(unsigned long paddr)
{
struct folio *folio;
struct page *page = damon_get_page(PHYS_PFN(paddr));
struct rmap_walk_control rwc = {
.rmap_one = __damon_pa_mkold,
.anon_lock = folio_lock_anon_vma_read,
};
bool need_lock;
if (!page)
return;
folio = page_folio(page);
if (!folio_mapped(folio) || !folio_raw_mapping(folio)) {
folio_set_idle(folio);
goto out;
}
need_lock = !folio_test_anon(folio) || folio_test_ksm(folio);
if (need_lock && !folio_trylock(folio))
goto out;
rmap_walk(folio, &rwc);
if (need_lock)
folio_unlock(folio);
out:
folio_put(folio);
}
static void __damon_pa_prepare_access_check(struct damon_ctx *ctx,
struct damon_region *r)
{
r->sampling_addr = damon_rand(r->ar.start, r->ar.end);
damon_pa_mkold(r->sampling_addr);
}
static void damon_pa_prepare_access_checks(struct damon_ctx *ctx)
{
struct damon_target *t;
struct damon_region *r;
damon_for_each_target(t, ctx) {
damon_for_each_region(r, t)
__damon_pa_prepare_access_check(ctx, r);
}
}
struct damon_pa_access_chk_result {
unsigned long page_sz;
bool accessed;
};
static bool __damon_pa_young(struct folio *folio, struct vm_area_struct *vma,
unsigned long addr, void *arg)
{
struct damon_pa_access_chk_result *result = arg;
DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, addr, 0);
result->accessed = false;
result->page_sz = PAGE_SIZE;
while (page_vma_mapped_walk(&pvmw)) {
addr = pvmw.address;
if (pvmw.pte) {
result->accessed = pte_young(*pvmw.pte) ||
!folio_test_idle(folio) ||
mmu_notifier_test_young(vma->vm_mm, addr);
} else {
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
result->accessed = pmd_young(*pvmw.pmd) ||
!folio_test_idle(folio) ||
mmu_notifier_test_young(vma->vm_mm, addr);
result->page_sz = ((1UL) << HPAGE_PMD_SHIFT);
#else
WARN_ON_ONCE(1);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
}
if (result->accessed) {
page_vma_mapped_walk_done(&pvmw);
break;
}
}
/* If accessed, stop walking */
return !result->accessed;
}
static bool damon_pa_young(unsigned long paddr, unsigned long *page_sz)
{
struct folio *folio;
struct page *page = damon_get_page(PHYS_PFN(paddr));
struct damon_pa_access_chk_result result = {
.page_sz = PAGE_SIZE,
.accessed = false,
};
struct rmap_walk_control rwc = {
.arg = &result,
.rmap_one = __damon_pa_young,
.anon_lock = folio_lock_anon_vma_read,
};
bool need_lock;
if (!page)
return false;
folio = page_folio(page);
if (!folio_mapped(folio) || !folio_raw_mapping(folio)) {
if (folio_test_idle(folio))
result.accessed = false;
else
result.accessed = true;
folio_put(folio);
goto out;
}
need_lock = !folio_test_anon(folio) || folio_test_ksm(folio);
if (need_lock && !folio_trylock(folio)) {
folio_put(folio);
return false;
}
rmap_walk(folio, &rwc);
if (need_lock)
folio_unlock(folio);
folio_put(folio);
out:
*page_sz = result.page_sz;
return result.accessed;
}
static void __damon_pa_check_access(struct damon_ctx *ctx,
struct damon_region *r)
{
static unsigned long last_addr;
static unsigned long last_page_sz = PAGE_SIZE;
static bool last_accessed;
/* If the region is in the last checked page, reuse the result */
if (ALIGN_DOWN(last_addr, last_page_sz) ==
ALIGN_DOWN(r->sampling_addr, last_page_sz)) {
if (last_accessed)
r->nr_accesses++;
return;
}
last_accessed = damon_pa_young(r->sampling_addr, &last_page_sz);
if (last_accessed)
r->nr_accesses++;
last_addr = r->sampling_addr;
}
static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx)
{
struct damon_target *t;
struct damon_region *r;
unsigned int max_nr_accesses = 0;
damon_for_each_target(t, ctx) {
damon_for_each_region(r, t) {
__damon_pa_check_access(ctx, r);
max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
}
}
return max_nr_accesses;
}
static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx,
struct damon_target *t, struct damon_region *r,
struct damos *scheme)
{
unsigned long addr, applied;
LIST_HEAD(page_list);
if (scheme->action != DAMOS_PAGEOUT)
return 0;
for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
struct page *page = damon_get_page(PHYS_PFN(addr));
if (!page)
continue;
ClearPageReferenced(page);
test_and_clear_page_young(page);
if (isolate_lru_page(page)) {
put_page(page);
continue;
}
if (PageUnevictable(page)) {
putback_lru_page(page);
} else {
list_add(&page->lru, &page_list);
put_page(page);
}
}
applied = reclaim_pages(&page_list);
cond_resched();
return applied * PAGE_SIZE;
}
static int damon_pa_scheme_score(struct damon_ctx *context,
struct damon_target *t, struct damon_region *r,
struct damos *scheme)
{
switch (scheme->action) {
case DAMOS_PAGEOUT:
return damon_pageout_score(context, r, scheme);
default:
break;
}
return DAMOS_MAX_SCORE;
}
static int __init damon_pa_initcall(void)
{
struct damon_operations ops = {
.id = DAMON_OPS_PADDR,
.init = NULL,
.update = NULL,
.prepare_access_checks = damon_pa_prepare_access_checks,
.check_accesses = damon_pa_check_accesses,
.reset_aggregated = NULL,
.target_valid = NULL,
.cleanup = NULL,
.apply_scheme = damon_pa_apply_scheme,
.get_scheme_score = damon_pa_scheme_score,
};
return damon_register_ops(&ops);
};
subsys_initcall(damon_pa_initcall);