summaryrefslogtreecommitdiffstats
path: root/mm/rmap.c
diff options
context:
space:
mode:
authorYu Zhao <yuzhao@google.com>2022-12-30 14:52:51 -0700
committerAndrew Morton <akpm@linux-foundation.org>2023-01-18 17:12:57 -0800
commit8788f6781486769d9598dcaedc3fe0eb12fc3e59 (patch)
tree6016e5f416dff55046e98aab401486edef2bf045 /mm/rmap.c
parent997931ce02b72f15c40e742ee035ce5643ba574f (diff)
downloadlinux-stable-8788f6781486769d9598dcaedc3fe0eb12fc3e59.tar.gz
linux-stable-8788f6781486769d9598dcaedc3fe0eb12fc3e59.tar.bz2
linux-stable-8788f6781486769d9598dcaedc3fe0eb12fc3e59.zip
mm: add vma_has_recency()
Add vma_has_recency() to indicate whether a VMA may exhibit temporal locality that the LRU algorithm relies on. This function returns false for VMAs marked by VM_SEQ_READ or VM_RAND_READ. While the former flag indicates linear access, i.e., a special case of spatial locality, both flags indicate a lack of temporal locality, i.e., the reuse of an area within a relatively small duration. "Recency" is chosen over "locality" to avoid confusion between temporal and spatial localities. Before this patch, the active/inactive LRU only ignored the accessed bit from VMAs marked by VM_SEQ_READ. After this patch, the active/inactive LRU and MGLRU share the same logic: they both ignore the accessed bit if vma_has_recency() returns false. For the active/inactive LRU, the following fio test showed a [6, 8]% increase in IOPS when randomly accessing mapped files under memory pressure. kb=$(awk '/MemTotal/ { print $2 }' /proc/meminfo) kb=$((kb - 8*1024*1024)) modprobe brd rd_nr=1 rd_size=$kb dd if=/dev/zero of=/dev/ram0 bs=1M mkfs.ext4 /dev/ram0 mount /dev/ram0 /mnt/ swapoff -a fio --name=test --directory=/mnt/ --ioengine=mmap --numjobs=8 \ --size=8G --rw=randrw --time_based --runtime=10m \ --group_reporting The discussion that led to this patch is here [1]. Additional test results are available in that thread. [1] https://lore.kernel.org/r/Y31s%2FK8T85jh05wH@google.com/ Link: https://lkml.kernel.org/r/20221230215252.2628425-1-yuzhao@google.com Signed-off-by: Yu Zhao <yuzhao@google.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Andrea Righi <andrea.righi@canonical.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michael Larabel <Michael@MichaelLarabel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/rmap.c')
-rw-r--r--mm/rmap.c42
1 files changed, 18 insertions, 24 deletions
diff --git a/mm/rmap.c b/mm/rmap.c
index 32e48b1c5847..ab74e0547a52 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -823,25 +823,14 @@ static bool folio_referenced_one(struct folio *folio,
}
if (pvmw.pte) {
- if (lru_gen_enabled() && pte_young(*pvmw.pte) &&
- !(vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))) {
+ if (lru_gen_enabled() && pte_young(*pvmw.pte)) {
lru_gen_look_around(&pvmw);
referenced++;
}
if (ptep_clear_flush_young_notify(vma, address,
- pvmw.pte)) {
- /*
- * Don't treat a reference through
- * a sequentially read mapping as such.
- * If the folio has been used in another mapping,
- * we will catch it; if this other mapping is
- * already gone, the unmap path will have set
- * the referenced flag or activated the folio.
- */
- if (likely(!(vma->vm_flags & VM_SEQ_READ)))
- referenced++;
- }
+ pvmw.pte))
+ referenced++;
} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
if (pmdp_clear_flush_young_notify(vma, address,
pvmw.pmd))
@@ -875,7 +864,20 @@ static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg)
struct folio_referenced_arg *pra = arg;
struct mem_cgroup *memcg = pra->memcg;
- if (!mm_match_cgroup(vma->vm_mm, memcg))
+ /*
+ * Ignore references from this mapping if it has no recency. If the
+ * folio has been used in another mapping, we will catch it; if this
+ * other mapping is already gone, the unmap path will have set the
+ * referenced flag or activated the folio in zap_pte_range().
+ */
+ if (!vma_has_recency(vma))
+ return true;
+
+ /*
+ * If we are reclaiming on behalf of a cgroup, skip counting on behalf
+ * of references from different cgroups.
+ */
+ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg))
return true;
return false;
@@ -906,6 +908,7 @@ int folio_referenced(struct folio *folio, int is_locked,
.arg = (void *)&pra,
.anon_lock = folio_lock_anon_vma_read,
.try_lock = true,
+ .invalid_vma = invalid_folio_referenced_vma,
};
*vm_flags = 0;
@@ -921,15 +924,6 @@ int folio_referenced(struct folio *folio, int is_locked,
return 1;
}
- /*
- * If we are reclaiming on behalf of a cgroup, skip
- * counting on behalf of references from different
- * cgroups
- */
- if (memcg) {
- rwc.invalid_vma = invalid_folio_referenced_vma;
- }
-
rmap_walk(folio, &rwc);
*vm_flags = pra.vm_flags;