mm: Multi-gen LRU: fix use of mm/page_idle/bitmap
Subsystems (3)
When Multi-Gen LRU is enabled, we can't use /sys/kernel/mm/page_idle/bitmap to track memory which is actually been used.
Unfortunately we didn't find anyone report this problem, or it just by design ?
Detail information, how-to-reproduct and our way to fix are written in our fix patch.
Henry Huang (1):
mm: Multi-Gen LRU: fix use mm/page_idle/bitmap
mm/swap.c | 3 +++ mm/vmscan.c | 37 ++++++++++++++++++++++++++----------- 2 files changed, 29 insertions(+), 11 deletions(-)
Signature · 1 line
2.43.0
RFC 1/1 mm: Multi-Gen LRU: fix use mm/page_idle/bitmap
Multi-Gen LRU page-table walker clears pte young flag, but it doesn't clear page idle flag. When we use /sys/kernel/mm/page_idle/bitmap to check whether one page is accessed, it would tell us this page is idle, but actually this page has been accessed.
For those unmapped filecache pages, page idle flag would not been cleared in folio_mark_accessed if Multi-Gen LRU is enabled. So we couln't use /sys/kernel/mm/page_idle/bitmap to check whether a filecache page is read or written.
What's more, /sys/kernel/mm/page_idle/bitmap also clears pte young flag. If one page is accessed, it would set page young flag. Multi-Gen LRU page-table walker should check both page&pte young flags.
how-to-reproduce-problem
idle_page_track
a tools to track process accessed memory during a specific time
usage
idle_page_track $pid $time
how-it-works
1. scan process vma from /proc/$pid/maps
2. vfn --> pfn from /proc/$pid/pagemap
3. write /sys/kernel/mm/page_idle/bitmap to
mark phy page idle flag and clear pte young flag
4. sleep $time
5. read /sys/kernel/mm/page_idle/bitmap to test_and_clear pte young flag and
return whether phy page is accessed
test ---- test program
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
int main(int argc, const char *argv[])
{
char *buf = NULL;
char pipe_info[4096];
int n;
int fd = -1;
buf = malloc(1024*1024*1024UL);
memset(buf, 0, 1024*1024*1024UL);
fd = open("access.pipe", O_RDONLY);
if (fd < 0)
goto out;
while (1) {
n = read(fd, pipe_info, sizeof(pipe_info));
if (!n) {
sleep(1);
continue;
} else if (n < 0) {
break;
}
memset(buf, 0, 1024*1024*1024UL);
puts("finish access");
}
out:
if (fd >=0)
close(fd);
if (buf)
free(buf);
return 0;}
prepare:
mkfifo access.pipe
./test
ps -ef | grep test
root 4106 3148 8 06:47 pts/0 00:00:01 ./test
We use /sys/kernel/debug/lru_gen to simulate mglru page-table scan.
case 1: mglru walker break page_idle ./idle_page_track 4106 60 &
sleep 5; echo 1 > access.pipe
sleep 5; echo '+ 8 0 6 1 1' > /sys/kernel/debug/lru_gen
the output of idle_page_track is:
Est(s) Ref(MB)
64.822 1.00
only found 1MB were accessed during 64.822s, but actually 1024MB were accessed.
case 2: page_idle break mglru walker
echo 1 > access.pipe
./idle_page_track 4106 10
echo '+ 8 0 7 1 1' > /sys/kernel/debug/lru_gen
lru gen status:
memcg 8 /user.slice
node 0
5 772458 1065 9735
6 737435 262244 72
7 538053 1184 632
8 59404 6422 0almost pages should be in max_seq-1 queue, but actually not.
--- mm/swap.c | 3 +++ mm/vmscan.c | 37 ++++++++++++++++++++++++++----------- 2 files changed, 29 insertions(+), 11 deletions(-)
mm/swap.c +3 -0
@@ -416,6 +416,9 @@ static void folio_inc_refs(struct folio *folio) {unsigned long new_flags, old_flags =READ_ONCE (folio->flags); +if (folio_test_idle (folio)) +folio_clear_idle (folio); +if (folio_test_unevictable (folio))return ;
mm/vmscan.c +26 -11
@@ -3355,6 +3355,7 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,unsigned long pfn;struct folio *folio;pte_t ptent =ptep_get (pte + i); +int is_pte_young; total++; walk->mm_stats[MM_LEAF_TOTAL ]++;
@@ -3363,18 +3364,22 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,if (pfn ==-1 )continue ; -if (!pte_young (ptent)) { - walk->mm_stats[MM_LEAF_OLD ]++; -continue ; - } - folio =get_pfn_folio (pfn, memcg, pgdat, walk->can_swap);if (!folio)continue ; -if (!ptep_test_and_clear_young (args->vma, addr, pte + i)) + is_pte_young =pte_young (ptent); +if (!folio_test_clear_young (folio) && !is_pte_young) { + walk->mm_stats[MM_LEAF_OLD ]++; +continue ; + } + +if (is_pte_young && !ptep_test_and_clear_young (args->vma, addr, pte + i))VM_WARN_ON_ONCE (true); +if (folio_test_idle (folio)) +folio_clear_idle (folio); + young++; walk->mm_stats[MM_LEAF_YOUNG ]++;
@@ -3435,6 +3440,7 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area do { unsigned long pfn; struct folio *folio; + int is_pmd_young; /* don't round down the first address */ addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first;
@@ -3453,9 +3459,13 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_areaif (!folio) goto next; -if (!pmdp_test_and_clear_young (vma, addr, pmd + i)) + is_pmd_young =pmdp_test_and_clear_young (vma, addr, pmd + i); +if (!folio_test_clear_young (folio) && !is_pmd_young) goto next; +if (folio_test_idle (folio)) +folio_clear_idle (folio); + walk->mm_stats[MM_LEAF_YOUNG ]++; if (pmd_dirty(pmd[i]) && !folio_test_dirty(folio) &&
@@ -4025,21 +4035,26 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)for (i =0 , addr = start; addr != end; i++, addr +=PAGE_SIZE ) {unsigned long pfn;pte_t ptent =ptep_get (pte + i); +int is_pte_young; pfn =get_pte_pfn (ptent, pvmw->vma, addr);if (pfn ==-1 )continue ; -if (!pte_young (ptent)) -continue ; - folio =get_pfn_folio (pfn, memcg, pgdat, can_swap);if (!folio)continue ; -if (!ptep_test_and_clear_young (pvmw->vma, addr, pte + i)) + is_pte_young =pte_young (ptent); +if (!folio_test_clear_young (folio) && !is_pte_young) +continue ; + +if (is_pte_young && !ptep_test_and_clear_young (pvmw->vma, addr, pte + i))VM_WARN_ON_ONCE (true); +if (folio_test_idle (folio)) +folio_clear_idle (folio); + young++; if (pte_dirty(ptent) && !folio_test_dirty(folio) &&
Signature · 1 line
2.43.0