@@ -48,6 +48,10 @@ Values Components
verified on x86 varieties other than Intel and AMD. If it is
disabled, the multi-gen LRU will suffer a negligible
performance degradation.
+0x0008 Clear the accessed bit in secondary MMU page tables when aging
+ instead of waiting until eviction time. This results in accurate
+ page age information for pages that are mainly used by a
+ secondary MMU.
[yYnN] Apply to all the components above.
====== ===============================================================
@@ -56,7 +60,7 @@ E.g.,
echo y >/sys/kernel/mm/lru_gen/enabled
cat /sys/kernel/mm/lru_gen/enabled
- 0x0007
+ 0x000f
echo 5 >/sys/kernel/mm/lru_gen/enabled
cat /sys/kernel/mm/lru_gen/enabled
0x0005
@@ -400,6 +400,7 @@ enum {
LRU_GEN_CORE,
LRU_GEN_MM_WALK,
LRU_GEN_NONLEAF_YOUNG,
+ LRU_GEN_SECONDARY_MMU_WALK,
NR_LRU_GEN_CAPS
};
@@ -557,7 +558,7 @@ struct lru_gen_memcg {
void lru_gen_init_pgdat(struct pglist_data *pgdat);
void lru_gen_init_lruvec(struct lruvec *lruvec);
-void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
+bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
void lru_gen_init_memcg(struct mem_cgroup *memcg);
void lru_gen_exit_memcg(struct mem_cgroup *memcg);
@@ -576,8 +577,9 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec)
{
}
-static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
{
+ return false;
}
static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
@@ -870,13 +870,10 @@ static bool folio_referenced_one(struct folio *folio,
continue;
}
- if (pvmw.pte) {
- if (lru_gen_enabled() &&
- pte_young(ptep_get(pvmw.pte))) {
- lru_gen_look_around(&pvmw);
+ if (lru_gen_enabled() && pvmw.pte) {
+ if (lru_gen_look_around(&pvmw))
referenced++;
- }
-
+ } else if (pvmw.pte) {
if (ptep_clear_flush_young_notify(vma, address,
pvmw.pte))
referenced++;
@@ -56,6 +56,7 @@
#include <linux/khugepaged.h>
#include <linux/rculist_nulls.h>
#include <linux/random.h>
+#include <linux/mmu_notifier.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
@@ -2579,6 +2580,11 @@ static bool should_clear_pmd_young(void)
return arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG);
}
+static bool should_walk_secondary_mmu(void)
+{
+ return get_cap(LRU_GEN_SECONDARY_MMU_WALK);
+}
+
/******************************************************************************
* shorthand helpers
******************************************************************************/
@@ -3276,7 +3282,8 @@ static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk
return false;
}
-static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr)
+static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr,
+ struct pglist_data *pgdat)
{
unsigned long pfn = pte_pfn(pte);
@@ -3291,10 +3298,15 @@ static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned
if (WARN_ON_ONCE(!pfn_valid(pfn)))
return -1;
+ /* try to avoid unnecessary memory loads */
+ if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
+ return -1;
+
return pfn;
}
-static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr)
+static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr,
+ struct pglist_data *pgdat)
{
unsigned long pfn = pmd_pfn(pmd);
@@ -3309,6 +3321,10 @@ static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned
if (WARN_ON_ONCE(!pfn_valid(pfn)))
return -1;
+ /* try to avoid unnecessary memory loads */
+ if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
+ return -1;
+
return pfn;
}
@@ -3317,10 +3333,6 @@ static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg,
{
struct folio *folio;
- /* try to avoid unnecessary memory loads */
- if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
- return NULL;
-
folio = pfn_folio(pfn);
if (folio_nid(folio) != pgdat->node_id)
return NULL;
@@ -3343,6 +3355,26 @@ static bool suitable_to_scan(int total, int young)
return young * n >= total;
}
+static bool lru_gen_notifier_clear_young(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+ return should_walk_secondary_mmu() &&
+ mmu_notifier_clear_young_fast_only(mm, start, end);
+}
+
+static bool lru_gen_pmdp_test_and_clear_young(struct vm_area_struct *vma,
+ unsigned long addr,
+ pmd_t *pmd)
+{
+ bool young = pmdp_test_and_clear_young(vma, addr, pmd);
+
+ if (lru_gen_notifier_clear_young(vma->vm_mm, addr, addr + PMD_SIZE))
+ young = true;
+
+ return young;
+}
+
static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
struct mm_walk *args)
{
@@ -3357,8 +3389,9 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
DEFINE_MAX_SEQ(walk->lruvec);
int old_gen, new_gen = lru_gen_from_seq(max_seq);
+ struct mm_struct *mm = args->mm;
- pte = pte_offset_map_nolock(args->mm, pmd, start & PMD_MASK, &ptl);
+ pte = pte_offset_map_nolock(mm, pmd, start & PMD_MASK, &ptl);
if (!pte)
return false;
if (!spin_trylock(ptl)) {
@@ -3376,11 +3409,11 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
total++;
walk->mm_stats[MM_LEAF_TOTAL]++;
- pfn = get_pte_pfn(ptent, args->vma, addr);
+ pfn = get_pte_pfn(ptent, args->vma, addr, pgdat);
if (pfn == -1)
continue;
- if (!pte_young(ptent)) {
+ if (!pte_young(ptent) && !mm_has_notifiers(mm)) {
walk->mm_stats[MM_LEAF_OLD]++;
continue;
}
@@ -3389,8 +3422,14 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
if (!folio)
continue;
- if (!ptep_test_and_clear_young(args->vma, addr, pte + i))
- VM_WARN_ON_ONCE(true);
+ if (!lru_gen_notifier_clear_young(mm, addr, addr + PAGE_SIZE) &&
+ !pte_young(ptent)) {
+ walk->mm_stats[MM_LEAF_OLD]++;
+ continue;
+ }
+
+ if (pte_young(ptent))
+ ptep_test_and_clear_young(args->vma, addr, pte + i);
young++;
walk->mm_stats[MM_LEAF_YOUNG]++;
@@ -3456,22 +3495,25 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area
/* don't round down the first address */
addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first;
- pfn = get_pmd_pfn(pmd[i], vma, addr);
- if (pfn == -1)
- goto next;
-
- if (!pmd_trans_huge(pmd[i])) {
- if (should_clear_pmd_young())
+ if (pmd_present(pmd[i]) && !pmd_trans_huge(pmd[i])) {
+ if (should_clear_pmd_young() &&
+ !should_walk_secondary_mmu())
pmdp_test_and_clear_young(vma, addr, pmd + i);
goto next;
}
+ pfn = get_pmd_pfn(pmd[i], vma, addr, pgdat);
+ if (pfn == -1)
+ goto next;
+
folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap);
if (!folio)
goto next;
- if (!pmdp_test_and_clear_young(vma, addr, pmd + i))
+ if (!lru_gen_pmdp_test_and_clear_young(vma, addr, pmd + i)) {
+ walk->mm_stats[MM_LEAF_OLD]++;
goto next;
+ }
walk->mm_stats[MM_LEAF_YOUNG]++;
@@ -3528,19 +3570,18 @@ static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
}
if (pmd_trans_huge(val)) {
- unsigned long pfn = pmd_pfn(val);
struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
+ unsigned long pfn = get_pmd_pfn(val, vma, addr, pgdat);
walk->mm_stats[MM_LEAF_TOTAL]++;
- if (!pmd_young(val)) {
- walk->mm_stats[MM_LEAF_OLD]++;
+ if (pfn == -1)
continue;
- }
- /* try to avoid unnecessary memory loads */
- if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
+ if (!pmd_young(val) && !mm_has_notifiers(args->mm)) {
+ walk->mm_stats[MM_LEAF_OLD]++;
continue;
+ }
walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first);
continue;
@@ -3548,7 +3589,7 @@ static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
walk->mm_stats[MM_NONLEAF_TOTAL]++;
- if (should_clear_pmd_young()) {
+ if (should_clear_pmd_young() && !should_walk_secondary_mmu()) {
if (!pmd_young(val))
continue;
@@ -3994,6 +4035,31 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
* rmap/PT walk feedback
******************************************************************************/
+static bool should_look_around(struct vm_area_struct *vma, unsigned long addr,
+ pte_t *pte, int *young)
+{
+ int secondary_young = mmu_notifier_clear_young(
+ vma->vm_mm, addr, addr + PAGE_SIZE);
+
+ /*
+ * Look around if (1) the PTE is young or (2) the secondary PTE was
+ * young and one of the "fast" MMUs of one of the secondary MMUs
+ * reported that the page was young.
+ */
+ if (pte_young(ptep_get(pte))) {
+ ptep_test_and_clear_young(vma, addr, pte);
+ *young = true;
+ return true;
+ }
+
+ if (secondary_young) {
+ *young = true;
+ return mm_has_fast_young_notifiers(vma->vm_mm);
+ }
+
+ return false;
+}
+
/*
* This function exploits spatial locality when shrink_folio_list() walks the
* rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages. If
@@ -4001,7 +4067,7 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
* the PTE table to the Bloom filter. This forms a feedback loop between the
* eviction and the aging.
*/
-void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
{
int i;
unsigned long start;
@@ -4019,16 +4085,20 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
DEFINE_MAX_SEQ(lruvec);
int old_gen, new_gen = lru_gen_from_seq(max_seq);
+ struct mm_struct *mm = pvmw->vma->vm_mm;
lockdep_assert_held(pvmw->ptl);
VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio);
+ if (!should_look_around(vma, addr, pte, &young))
+ return young;
+
if (spin_is_contended(pvmw->ptl))
- return;
+ return young;
/* exclude special VMAs containing anon pages from COW */
if (vma->vm_flags & VM_SPECIAL)
- return;
+ return young;
/* avoid taking the LRU lock under the PTL when possible */
walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL;
@@ -4036,6 +4106,9 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
start = max(addr & PMD_MASK, vma->vm_start);
end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1;
+ if (end - start == PAGE_SIZE)
+ return young;
+
if (end - start > MIN_LRU_BATCH * PAGE_SIZE) {
if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2)
end = start + MIN_LRU_BATCH * PAGE_SIZE;
@@ -4049,7 +4122,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
/* folio_update_gen() requires stable folio_memcg() */
if (!mem_cgroup_trylock_pages(memcg))
- return;
+ return young;
arch_enter_lazy_mmu_mode();
@@ -4059,19 +4132,23 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
unsigned long pfn;
pte_t ptent = ptep_get(pte + i);
- pfn = get_pte_pfn(ptent, vma, addr);
+ pfn = get_pte_pfn(ptent, vma, addr, pgdat);
if (pfn == -1)
continue;
- if (!pte_young(ptent))
+ if (!pte_young(ptent) && !mm_has_notifiers(mm))
continue;
folio = get_pfn_folio(pfn, memcg, pgdat, can_swap);
if (!folio)
continue;
- if (!ptep_test_and_clear_young(vma, addr, pte + i))
- VM_WARN_ON_ONCE(true);
+ if (!lru_gen_notifier_clear_young(mm, addr, addr + PAGE_SIZE) &&
+ !pte_young(ptent))
+ continue;
+
+ if (pte_young(ptent))
+ ptep_test_and_clear_young(vma, addr, pte + i);
young++;
@@ -4101,6 +4178,8 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
/* feedback from rmap walkers to page table walkers */
if (mm_state && suitable_to_scan(i, young))
update_bloom_filter(mm_state, max_seq, pvmw->pmd);
+
+ return young;
}
/******************************************************************************
@@ -5137,6 +5216,9 @@ static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, c
if (should_clear_pmd_young())
caps |= BIT(LRU_GEN_NONLEAF_YOUNG);
+ if (should_walk_secondary_mmu())
+ caps |= BIT(LRU_GEN_SECONDARY_MMU_WALK);
+
return sysfs_emit(buf, "0x%04x\n", caps);
}
Secondary MMUs are currently consulted for access/age information at eviction time, but before then, we don't get accurate age information. That is, pages that are mostly accessed through a secondary MMU (like guest memory, used by KVM) will always just proceed down to the oldest generation, and then at eviction time, if KVM reports the page to be young, the page will be activated/promoted back to the youngest generation. The added feature bit (0x8), if disabled, will make MGLRU behave as if there are no secondary MMUs subscribed to MMU notifiers except at eviction time. Implement aging with the new mmu_notifier_clear_young_fast_only() notifier. For architectures that do not support this notifier, this becomes a no-op. For architectures that do implement it, it should be fast enough to make aging worth it (usually the case if the notifier is implemented locklessly). Suggested-by: Yu Zhao <yuzhao@google.com> Signed-off-by: James Houghton <jthoughton@google.com> --- Documentation/admin-guide/mm/multigen_lru.rst | 6 +- include/linux/mmzone.h | 6 +- mm/rmap.c | 9 +- mm/vmscan.c | 148 ++++++++++++++---- 4 files changed, 127 insertions(+), 42 deletions(-)