9030fb0bb9
- 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()
...
111 lines
2.5 KiB
C
111 lines
2.5 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* linux/mm/mmzone.c
|
|
*
|
|
* management codes for pgdats, zones and page flags
|
|
*/
|
|
|
|
|
|
#include <linux/stddef.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/mmzone.h>
|
|
|
|
struct pglist_data *first_online_pgdat(void)
|
|
{
|
|
return NODE_DATA(first_online_node);
|
|
}
|
|
|
|
struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
|
|
{
|
|
int nid = next_online_node(pgdat->node_id);
|
|
|
|
if (nid == MAX_NUMNODES)
|
|
return NULL;
|
|
return NODE_DATA(nid);
|
|
}
|
|
|
|
/*
|
|
* next_zone - helper magic for for_each_zone()
|
|
*/
|
|
struct zone *next_zone(struct zone *zone)
|
|
{
|
|
pg_data_t *pgdat = zone->zone_pgdat;
|
|
|
|
if (zone < pgdat->node_zones + MAX_NR_ZONES - 1)
|
|
zone++;
|
|
else {
|
|
pgdat = next_online_pgdat(pgdat);
|
|
if (pgdat)
|
|
zone = pgdat->node_zones;
|
|
else
|
|
zone = NULL;
|
|
}
|
|
return zone;
|
|
}
|
|
|
|
static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes)
|
|
{
|
|
#ifdef CONFIG_NUMA
|
|
return node_isset(zonelist_node_idx(zref), *nodes);
|
|
#else
|
|
return 1;
|
|
#endif /* CONFIG_NUMA */
|
|
}
|
|
|
|
/* Returns the next zone at or below highest_zoneidx in a zonelist */
|
|
struct zoneref *__next_zones_zonelist(struct zoneref *z,
|
|
enum zone_type highest_zoneidx,
|
|
nodemask_t *nodes)
|
|
{
|
|
/*
|
|
* Find the next suitable zone to use for the allocation.
|
|
* Only filter based on nodemask if it's set
|
|
*/
|
|
if (unlikely(nodes == NULL))
|
|
while (zonelist_zone_idx(z) > highest_zoneidx)
|
|
z++;
|
|
else
|
|
while (zonelist_zone_idx(z) > highest_zoneidx ||
|
|
(z->zone && !zref_in_nodemask(z, nodes)))
|
|
z++;
|
|
|
|
return z;
|
|
}
|
|
|
|
void lruvec_init(struct lruvec *lruvec)
|
|
{
|
|
enum lru_list lru;
|
|
|
|
memset(lruvec, 0, sizeof(struct lruvec));
|
|
spin_lock_init(&lruvec->lru_lock);
|
|
|
|
for_each_lru(lru)
|
|
INIT_LIST_HEAD(&lruvec->lists[lru]);
|
|
/*
|
|
* The "Unevictable LRU" is imaginary: though its size is maintained,
|
|
* it is never scanned, and unevictable pages are not threaded on it
|
|
* (so that their lru fields can be reused to hold mlock_count).
|
|
* Poison its list head, so that any operations on it would crash.
|
|
*/
|
|
list_del(&lruvec->lists[LRU_UNEVICTABLE]);
|
|
}
|
|
|
|
#if defined(CONFIG_NUMA_BALANCING) && !defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS)
|
|
int page_cpupid_xchg_last(struct page *page, int cpupid)
|
|
{
|
|
unsigned long old_flags, flags;
|
|
int last_cpupid;
|
|
|
|
old_flags = READ_ONCE(page->flags);
|
|
do {
|
|
flags = old_flags;
|
|
last_cpupid = (flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK;
|
|
|
|
flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
|
|
flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT;
|
|
} while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags)));
|
|
|
|
return last_cpupid;
|
|
}
|
|
#endif
|