android_kernel_xiaomi_sm7250/mm/mm_init.c
Yu Zhao c5b899bcd2 FROMLIST: mm: multi-gen LRU: groundwork
Evictable pages are divided into multiple generations for each lruvec.
The youngest generation number is stored in lrugen->max_seq for both
anon and file types as they are aged on an equal footing. The oldest
generation numbers are stored in lrugen->min_seq[] separately for anon
and file types as clean file pages can be evicted regardless of swap
constraints. These three variables are monotonically increasing.

Generation numbers are truncated into order_base_2(MAX_NR_GENS+1) bits
in order to fit into the gen counter in page->flags. Each truncated
generation number is an index to lrugen->lists[]. The sliding window
technique is used to track at least MIN_NR_GENS and at most
MAX_NR_GENS generations. The gen counter stores a value within [1,
MAX_NR_GENS] while a page is on one of lrugen->lists[]. Otherwise it
stores 0.

There are two conceptually independent procedures: "the aging", which
produces young generations, and "the eviction", which consumes old
generations. They form a closed-loop system, i.e., "the page reclaim".
Both procedures can be invoked from userspace for the purposes of
working set estimation and proactive reclaim. These features are
required to optimize job scheduling (bin packing) in data centers. The
variable size of the sliding window is designed for such use cases
[1][2].

To avoid confusion, the terms "hot" and "cold" will be applied to the
multi-gen LRU, as a new convention; the terms "active" and "inactive"
will be applied to the active/inactive LRU, as usual.

The protection of hot pages and the selection of cold pages are based
on page access channels and patterns. There are two access channels:
one through page tables and the other through file descriptors. The
protection of the former channel is by design stronger because:
1. The uncertainty in determining the access patterns of the former
   channel is higher due to the approximation of the accessed bit.
2. The cost of evicting the former channel is higher due to the TLB
   flushes required and the likelihood of encountering the dirty bit.
3. The penalty of underprotecting the former channel is higher because
   applications usually do not prepare themselves for major page
   faults like they do for blocked I/O. E.g., GUI applications
   commonly use dedicated I/O threads to avoid blocking the rendering
   threads.
There are also two access patterns: one with temporal locality and the
other without. For the reasons listed above, the former channel is
assumed to follow the former pattern unless VM_SEQ_READ or
VM_RAND_READ is present; the latter channel is assumed to follow the
latter pattern unless outlying refaults have been observed [3][4].

The next patch will address the "outlying refaults". Three macros,
i.e., LRU_REFS_WIDTH, LRU_REFS_PGOFF and LRU_REFS_MASK, used later are
added in this patch to make the entire patchset less diffy.

A page is added to the youngest generation on faulting. The aging
needs to check the accessed bit at least twice before handing this
page over to the eviction. The first check takes care of the accessed
bit set on the initial fault; the second check makes sure this page
has not been used since then. This protocol, AKA second chance,
requires a minimum of two generations, hence MIN_NR_GENS.

[1] https://dl.acm.org/doi/10.1145/3297858.3304053
[2] https://dl.acm.org/doi/10.1145/3503222.3507731
[3] https://lwn.net/Articles/495543/
[4] https://lwn.net/Articles/815342/

Link: https://lore.kernel.org/r/20220309021230.721028-6-yuzhao@google.com/
Signed-off-by: Yu Zhao <yuzhao@google.com>
Acked-by: Brian Geffon <bgeffon@google.com>
Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: Steven Barrett <steven@liquorix.net>
Acked-by: Suleiman Souhlal <suleiman@google.com>
Tested-by: Daniel Byrne <djbyrne@mtu.edu>
Tested-by: Donald Carr <d@chaos-reins.com>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
Tested-by: Sofia Trinh <sofia.trinh@edi.works>
Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Bug: 228114874
Change-Id: I333ec6a1d2abfa60d93d6adc190ed3eefe441512
2022-11-12 11:21:15 +00:00

197 lines
4.9 KiB
C

/*
* mm_init.c - Memory initialisation verification and debugging
*
* Copyright 2008 IBM Corporation, 2008
* Author Mel Gorman <mel@csn.ul.ie>
*
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/kobject.h>
#include <linux/export.h>
#include <linux/memory.h>
#include <linux/notifier.h>
#include <linux/sched.h>
#include "internal.h"
#ifdef CONFIG_DEBUG_MEMORY_INIT
int __meminitdata mminit_loglevel;
#ifndef SECTIONS_SHIFT
#define SECTIONS_SHIFT 0
#endif
/* The zonelists are simply reported, validation is manual. */
void __init mminit_verify_zonelist(void)
{
int nid;
if (mminit_loglevel < MMINIT_VERIFY)
return;
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
struct zone *zone;
struct zoneref *z;
struct zonelist *zonelist;
int i, listid, zoneid;
BUG_ON(MAX_ZONELISTS > 2);
for (i = 0; i < MAX_ZONELISTS * MAX_NR_ZONES; i++) {
/* Identify the zone and nodelist */
zoneid = i % MAX_NR_ZONES;
listid = i / MAX_NR_ZONES;
zonelist = &pgdat->node_zonelists[listid];
zone = &pgdat->node_zones[zoneid];
if (!populated_zone(zone))
continue;
/* Print information about the zonelist */
printk(KERN_DEBUG "mminit::zonelist %s %d:%s = ",
listid > 0 ? "thisnode" : "general", nid,
zone->name);
/* Iterate the zonelist */
for_each_zone_zonelist(zone, z, zonelist, zoneid)
pr_cont("%d:%s ", zone_to_nid(zone), zone->name);
pr_cont("\n");
}
}
}
void __init mminit_verify_pageflags_layout(void)
{
int shift, width;
unsigned long or_mask, add_mask;
shift = 8 * sizeof(unsigned long);
width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH
- LAST_CPUPID_SHIFT - KASAN_TAG_WIDTH - LRU_GEN_WIDTH - LRU_REFS_WIDTH;
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
"Section %d Node %d Zone %d Lastcpupid %d Kasantag %d Gen %d Tier %d Flags %d\n",
SECTIONS_WIDTH,
NODES_WIDTH,
ZONES_WIDTH,
LAST_CPUPID_WIDTH,
KASAN_TAG_WIDTH,
LRU_GEN_WIDTH,
LRU_REFS_WIDTH,
NR_PAGEFLAGS);
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
"Section %d Node %d Zone %d Lastcpupid %d\n",
SECTIONS_SHIFT,
NODES_SHIFT,
ZONES_SHIFT,
LAST_CPUPID_SHIFT);
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts",
"Section %lu Node %lu Zone %lu Lastcpupid %lu\n",
(unsigned long)SECTIONS_PGSHIFT,
(unsigned long)NODES_PGSHIFT,
(unsigned long)ZONES_PGSHIFT,
(unsigned long)LAST_CPUPID_PGSHIFT);
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid",
"Node/Zone ID: %lu -> %lu\n",
(unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT),
(unsigned long)ZONEID_PGOFF);
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_usage",
"location: %d -> %d layout %d -> %d unused %d -> %d page-flags\n",
shift, width, width, NR_PAGEFLAGS, NR_PAGEFLAGS, 0);
#ifdef NODE_NOT_IN_PAGE_FLAGS
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
"Node not in page flags");
#endif
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
"Last cpupid not in page flags");
#endif
if (SECTIONS_WIDTH) {
shift -= SECTIONS_WIDTH;
BUG_ON(shift != SECTIONS_PGSHIFT);
}
if (NODES_WIDTH) {
shift -= NODES_WIDTH;
BUG_ON(shift != NODES_PGSHIFT);
}
if (ZONES_WIDTH) {
shift -= ZONES_WIDTH;
BUG_ON(shift != ZONES_PGSHIFT);
}
/* Check for bitmask overlaps */
or_mask = (ZONES_MASK << ZONES_PGSHIFT) |
(NODES_MASK << NODES_PGSHIFT) |
(SECTIONS_MASK << SECTIONS_PGSHIFT);
add_mask = (ZONES_MASK << ZONES_PGSHIFT) +
(NODES_MASK << NODES_PGSHIFT) +
(SECTIONS_MASK << SECTIONS_PGSHIFT);
BUG_ON(or_mask != add_mask);
}
static __init int set_mminit_loglevel(char *str)
{
get_option(&str, &mminit_loglevel);
return 0;
}
early_param("mminit_loglevel", set_mminit_loglevel);
#endif /* CONFIG_DEBUG_MEMORY_INIT */
struct kobject *mm_kobj;
EXPORT_SYMBOL_GPL(mm_kobj);
#ifdef CONFIG_SMP
s32 vm_committed_as_batch = 32;
static void __meminit mm_compute_batch(void)
{
u64 memsized_batch;
s32 nr = num_present_cpus();
s32 batch = max_t(s32, nr*2, 32);
/* batch size set to 0.4% of (total memory/#cpus), or max int32 */
memsized_batch = min_t(u64, (totalram_pages/nr)/256, 0x7fffffff);
vm_committed_as_batch = max_t(s32, memsized_batch, batch);
}
static int __meminit mm_compute_batch_notifier(struct notifier_block *self,
unsigned long action, void *arg)
{
switch (action) {
case MEM_ONLINE:
case MEM_OFFLINE:
mm_compute_batch();
default:
break;
}
return NOTIFY_OK;
}
static struct notifier_block compute_batch_nb __meminitdata = {
.notifier_call = mm_compute_batch_notifier,
.priority = IPC_CALLBACK_PRI, /* use lowest priority */
};
static int __init mm_compute_batch_init(void)
{
mm_compute_batch();
register_hotmemory_notifier(&compute_batch_nb);
return 0;
}
__initcall(mm_compute_batch_init);
#endif
static int __init mm_sysfs_init(void)
{
mm_kobj = kobject_create_and_add("mm", kernel_kobj);
if (!mm_kobj)
return -ENOMEM;
return 0;
}
postcore_initcall(mm_sysfs_init);