openwrt/target/linux/generic/backport-5.15/020-v6.3-19-mm-add-vma_has_recency.patch

From 6c7f552a48b49a8612786a28a2239fbc24fac289 Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
Date: Fri, 30 Dec 2022 14:52:51 -0700
Subject: [PATCH 19/29] 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>
---
 include/linux/mm_inline.h |  9 +++++++++
 mm/memory.c               |  8 ++++----
 mm/rmap.c                 | 42 +++++++++++++++++----------------------
 mm/vmscan.c               |  5 ++++-
 4 files changed, 35 insertions(+), 29 deletions(-)

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index e095c1c24311..e8c723053a52 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -333,4 +333,13 @@ static __always_inline void del_page_from_lru_list(struct page *page,
 	update_lru_size(lruvec, page_lru(page), page_zonenum(page),
 			-thp_nr_pages(page));
 }
+
+static inline bool vma_has_recency(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))
+		return false;
+
+	return true;
+}
+
 #endif
diff --git a/mm/memory.c b/mm/memory.c
index 7d5be951de9e..1306b1ff0c10 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -41,6 +41,7 @@
 
 #include <linux/kernel_stat.h>
 #include <linux/mm.h>
+#include <linux/mm_inline.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
 #include <linux/sched/numa_balancing.h>
@@ -1353,8 +1354,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 					force_flush = 1;
 					set_page_dirty(page);
 				}
-				if (pte_young(ptent) &&
-				    likely(!(vma->vm_flags & VM_SEQ_READ)))
+				if (pte_young(ptent) && likely(vma_has_recency(vma)))
 					mark_page_accessed(page);
 			}
 			rss[mm_counter(page)]--;
@@ -4781,8 +4781,8 @@ static inline void mm_account_fault(struct pt_regs *regs,
 #ifdef CONFIG_LRU_GEN
 static void lru_gen_enter_fault(struct vm_area_struct *vma)
 {
-	/* the LRU algorithm doesn't apply to sequential or random reads */
-	current->in_lru_fault = !(vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ));
+	/* the LRU algorithm only applies to accesses with recency */
+	current->in_lru_fault = vma_has_recency(vma);
 }
 
 static void lru_gen_exit_fault(void)
diff --git a/mm/rmap.c b/mm/rmap.c
index 22a86122732e..53df47753f3c 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -794,25 +794,14 @@ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		}
 
 		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 page has been used in another mapping,
-				 * we will catch it; if this other mapping is
-				 * already gone, the unmap path will have set
-				 * PG_referenced or activated the page.
-				 */
-				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))
@@ -846,7 +835,20 @@ static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg)
 	struct page_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
+	 * page 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 page 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;
@@ -876,6 +878,7 @@ int page_referenced(struct page *page,
 		.rmap_one = page_referenced_one,
 		.arg = (void *)&pra,
 		.anon_lock = page_lock_anon_vma_read,
+		.invalid_vma = invalid_page_referenced_vma,
 	};
 
 	*vm_flags = 0;
@@ -891,15 +894,6 @@ int page_referenced(struct page *page,
 			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_page_referenced_vma;
-	}
-
 	rmap_walk(page, &rwc);
 	*vm_flags = pra.vm_flags;
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 96f1af44bb77..4ab376abeaae 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3486,7 +3486,10 @@ static int should_skip_vma(unsigned long start, unsigned long end, struct mm_wal
 	if (is_vm_hugetlb_page(vma))
 		return true;
 
-	if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL | VM_SEQ_READ | VM_RAND_READ))
+	if (!vma_has_recency(vma))
+		return true;
+
+	if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL))
 		return true;
 
 	if (vma == get_gate_vma(vma->vm_mm))
-- 
2.40.0