The patch titled Subject: mm/mglru: reset page lru tier bits when activating has been added to the -mm mm-unstable branch. Its filename is mm-mglru-reset-page-lru-tier-bits-when-activating.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-mglru-reset-page-lru-tier-bits-when-activating.patch This patch will later appear in the mm-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Wei Xu <weixugc@xxxxxxxxxx> Subject: mm/mglru: reset page lru tier bits when activating Date: Thu, 17 Oct 2024 18:15:28 +0000 When a folio is activated, lru_gen_add_folio() moves the folio to the youngest generation. But unlike folio_update_gen()/folio_inc_gen(), lru_gen_add_folio() doesn't reset the folio lru tier bits (LRU_REFS_MASK | LRU_REFS_FLAGS). This inconsistency can affect how pages are aged via folio_mark_accessed() (e.g. fd accesses), though no user visible impact related to this has been detected yet. Note that lru_gen_add_folio() cannot clear PG_workingset if the activation is due to workingset refault, otherwise PSI accounting will be skipped. So fix lru_gen_add_folio() to clear the lru tier bits other than PG_workingset when activating a folio, and also clear all the lru tier bits when a folio is activated via folio_activate() in lru_gen_look_around(). Link: https://lkml.kernel.org/r/20241017181528.3358821-1-weixugc@xxxxxxxxxx Fixes: 018ee47f1489 ("mm: multi-gen LRU: exploit locality in rmap") Signed-off-by: Wei Xu <weixugc@xxxxxxxxxx> Cc: Axel Rasmussen <axelrasmussen@xxxxxxxxxx> Cc: Brian Geffon <bgeffon@xxxxxxxxxx> Cc: Jan Alexander Steffens <heftig@xxxxxxxxxxxxx> Cc: Suleiman Souhlal <suleiman@xxxxxxxxxx> Cc: Yu Zhao <yuzhao@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/mm_inline.h | 15 ++++++++++++++- include/linux/mmzone.h | 2 ++ mm/vmscan.c | 8 ++++---- 3 files changed, 20 insertions(+), 5 deletions(-) --- a/include/linux/mm_inline.h~mm-mglru-reset-page-lru-tier-bits-when-activating +++ a/include/linux/mm_inline.h @@ -155,6 +155,11 @@ static inline int folio_lru_refs(struct return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; } +static inline void folio_clear_lru_refs(struct folio *folio) +{ + set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); +} + static inline int folio_lru_gen(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); @@ -222,6 +227,7 @@ static inline bool lru_gen_add_folio(str { unsigned long seq; unsigned long flags; + unsigned long mask; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); @@ -257,7 +263,14 @@ static inline bool lru_gen_add_folio(str gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ - set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags); + mask = LRU_GEN_MASK; + /* + * Don't clear PG_workingset here because it can affect PSI accounting + * if the activation is due to workingset refault. + */ + if (folio_test_active(folio)) + mask |= LRU_REFS_MASK | BIT(PG_referenced) | BIT(PG_active); + set_mask_bits(&folio->flags, mask, flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ --- a/include/linux/mmzone.h~mm-mglru-reset-page-lru-tier-bits-when-activating +++ a/include/linux/mmzone.h @@ -403,6 +403,8 @@ enum { NR_LRU_GEN_CAPS }; +#define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset)) + #define MIN_LRU_BATCH BITS_PER_LONG #define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) --- a/mm/vmscan.c~mm-mglru-reset-page-lru-tier-bits-when-activating +++ a/mm/vmscan.c @@ -2602,8 +2602,6 @@ static bool should_clear_pmd_young(void) * shorthand helpers ******************************************************************************/ -#define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset)) - #define DEFINE_MAX_SEQ(lruvec) \ unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq) @@ -4138,8 +4136,10 @@ void lru_gen_look_around(struct page_vma old_gen = folio_lru_gen(folio); if (old_gen < 0) folio_set_referenced(folio); - else if (old_gen != new_gen) + else if (old_gen != new_gen) { + folio_clear_lru_refs(folio); folio_activate(folio); + } } arch_leave_lazy_mmu_mode(); @@ -4370,7 +4370,7 @@ static bool isolate_folio(struct lruvec /* see the comment on MAX_NR_TIERS */ if (!folio_test_referenced(folio)) - set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); + folio_clear_lru_refs(folio); /* for shrink_folio_list() */ folio_clear_reclaim(folio); _ Patches currently in -mm which might be from weixugc@xxxxxxxxxx are mm-mglru-reset-page-lru-tier-bits-when-activating.patch