Add a helper to report the minimum remaining chargeable space from a page counter up to the root of its hierarchy. This makes the hierarchical margin calculation reusable by callers that need to know whether a smaller charge could still fit after a larger charge failed. Suggested-by: Johannes Weiner Signed-off-by: Xueyuan Chen --- include/linux/page_counter.h | 1 + mm/page_counter.c | 20 ++++++++++++++++++++ 2 files changed, 21 insertions(+) diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index d649b6bbbc87..07b7cb12249c 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -68,6 +68,7 @@ static inline unsigned long page_counter_read(struct page_counter *counter) return atomic_long_read(&counter->usage); } +long page_counter_margin(struct page_counter *counter); void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages); void page_counter_charge(struct page_counter *counter, unsigned long nr_pages); bool page_counter_try_charge(struct page_counter *counter, diff --git a/mm/page_counter.c b/mm/page_counter.c index 661e0f2a5127..6e55c7628025 100644 --- a/mm/page_counter.c +++ b/mm/page_counter.c @@ -171,6 +171,26 @@ bool page_counter_try_charge(struct page_counter *counter, return false; } +/** + * page_counter_margin - remaining chargeable pages within hierarchical limits + * @counter: counter + * + * Returns the smallest remaining margin between @counter and the root. + */ +long page_counter_margin(struct page_counter *counter) +{ + long margin = PAGE_COUNTER_MAX; + + for (; counter; counter = counter->parent) { + long limit = READ_ONCE(counter->max); + long usage = page_counter_read(counter); + + margin = min(margin, limit - usage); + } + + return margin; +} + /** * page_counter_uncharge - hierarchically uncharge pages * @counter: counter -- 2.47.3 folio_alloc_swap() reports most allocation failures with a generic negative error code. Reclaim cannot tell whether splitting a large folio could make progress or whether there is no backing space at all. Track the global free swap count around the allocation attempt and let the memcg swap charge path cap it by the remaining hierarchical swap margin. Return -E2BIG for large folios when a smaller allocation might still fit, -ENOSPC when no swap space is available, and -ENOMEM when the failure is not helped by splitting. This only refines folio_alloc_swap() return codes. The reclaim caller is updated separately. Signed-off-by: Xueyuan Chen --- include/linux/swap.h | 10 ++++++---- mm/memcontrol.c | 15 ++++++++++----- mm/swapfile.c | 21 +++++++++++++++------ 3 files changed, 31 insertions(+), 15 deletions(-) diff --git a/include/linux/swap.h b/include/linux/swap.h index 7a09df6977a5..0695ac56457f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -571,13 +571,14 @@ static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) #endif #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) -int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); +int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry, + long *nr_swap_pages); static inline int mem_cgroup_try_charge_swap(struct folio *folio, - swp_entry_t entry) + swp_entry_t entry, long *nr_swap_pages) { if (mem_cgroup_disabled()) return 0; - return __mem_cgroup_try_charge_swap(folio, entry); + return __mem_cgroup_try_charge_swap(folio, entry, nr_swap_pages); } extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); @@ -592,7 +593,8 @@ extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct folio *folio); #else static inline int mem_cgroup_try_charge_swap(struct folio *folio, - swp_entry_t entry) + swp_entry_t entry, + long *nr_swap_pages) { return 0; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 177732fef010..71600d41958e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5472,12 +5472,14 @@ int __init mem_cgroup_init(void) * __mem_cgroup_try_charge_swap - try charging swap space for a folio * @folio: folio being added to swap * @entry: swap entry to charge + * @nr_swap_pages: optional swap availability to cap by memcg margin * * Try to charge @folio's memcg for the swap space at @entry. * * Returns 0 on success, -ENOMEM on failure. */ -int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) +int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry, + long *nr_swap_pages) { unsigned int nr_pages = folio_nr_pages(folio); struct page_counter *counter; @@ -5495,6 +5497,9 @@ int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) rcu_read_lock(); memcg = obj_cgroup_memcg(objcg); if (!entry.val) { + if (nr_swap_pages && !mem_cgroup_is_root(memcg)) + *nr_swap_pages = min(*nr_swap_pages, + page_counter_margin(&memcg->swap)); memcg_memory_event(memcg, MEMCG_SWAP_FAIL); rcu_read_unlock(); return 0; @@ -5509,6 +5514,9 @@ int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) memcg_memory_event(memcg, MEMCG_SWAP_MAX); memcg_memory_event(memcg, MEMCG_SWAP_FAIL); mem_cgroup_private_id_put(memcg, nr_pages); + if (nr_swap_pages) + *nr_swap_pages = min(*nr_swap_pages, + page_counter_margin(counter)); return -ENOMEM; } mod_memcg_state(memcg, MEMCG_SWAP, nr_pages); @@ -5550,10 +5558,7 @@ long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) if (mem_cgroup_disabled() || do_memsw_account()) return nr_swap_pages; - for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) - nr_swap_pages = min_t(long, nr_swap_pages, - READ_ONCE(memcg->swap.max) - - page_counter_read(&memcg->swap)); + nr_swap_pages = min(nr_swap_pages, page_counter_margin(&memcg->swap)); return nr_swap_pages; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 9174f1eeffb0..53a921ca099a 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1690,12 +1690,14 @@ static int swap_dup_entries_cluster(struct swap_info_struct *si, * swap cache. * * Context: Caller needs to hold the folio lock. - * Return: Whether the folio was added to the swap cache. + * Return: 0 on success, -E2BIG if splitting the folio might allow swapout, + * or another negative error code if splitting would not help. */ int folio_alloc_swap(struct folio *folio) { unsigned int order = folio_order(folio); unsigned int size = 1 << order; + long nr_swap_pages; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio); @@ -1706,7 +1708,7 @@ int folio_alloc_swap(struct folio *folio) * the caller should split the folio and try again. */ if (!IS_ENABLED(CONFIG_THP_SWAP)) - return -EAGAIN; + return -E2BIG; /* * Allocation size should never exceed cluster size @@ -1714,10 +1716,12 @@ int folio_alloc_swap(struct folio *folio) */ if (size > SWAPFILE_CLUSTER) { VM_WARN_ON_ONCE(1); - return -EINVAL; + return -E2BIG; } } + nr_swap_pages = get_nr_swap_pages(); + again: local_lock(&percpu_swap_cluster.lock); if (!swap_alloc_fast(folio)) @@ -1730,11 +1734,16 @@ int folio_alloc_swap(struct folio *folio) } /* Need to call this even if allocation failed, for MEMCG_SWAP_FAIL. */ - if (unlikely(mem_cgroup_try_charge_swap(folio, folio->swap))) + if (unlikely(mem_cgroup_try_charge_swap(folio, folio->swap, + &nr_swap_pages))) { swap_cache_del_folio(folio); + return order && nr_swap_pages > 0 ? -E2BIG : -ENOMEM; + } - if (unlikely(!folio_test_swapcache(folio))) - return -ENOMEM; + if (unlikely(!folio_test_swapcache(folio))) { + nr_swap_pages = get_nr_swap_pages(); + return order && nr_swap_pages > 0 ? -E2BIG : -ENOSPC; + } return 0; } -- 2.47.3 From: "Barry Song (Xiaomi)" When swap is disabled, exhausted, or unavailable due to memcg swap limits, splitting a large anonymous folio cannot make swapout progress. The fallback only destroys the large folio and inflates split statistics. Use -E2BIG from folio_alloc_swap() as the explicit signal that splitting the folio might allow swapout of smaller pieces. For other allocation failures, keep the existing activation path and avoid the split. This preserves the split fallback for fragmented or partially available swap, while avoiding it when there is no backing space for any part of the folio. Reported-by: Nanzhe Zhao Signed-off-by: Barry Song (Xiaomi) --- mm/vmscan.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index bd1b1aa12581..40340a88f78e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1260,6 +1260,8 @@ static unsigned int shrink_folio_list(struct list_head *folio_list, */ if (folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio)) { + int ret; + if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; if (folio_maybe_dma_pinned(folio)) @@ -1278,10 +1280,11 @@ static unsigned int shrink_folio_list(struct list_head *folio_list, split_folio_to_list(folio, folio_list)) goto activate_locked; } - if (folio_alloc_swap(folio)) { + ret = folio_alloc_swap(folio); + if (ret) { int __maybe_unused order = folio_order(folio); - if (!folio_test_large(folio)) + if (!folio_test_large(folio) || ret != -E2BIG) goto activate_locked_split; /* Fallback to swap normal pages */ if (split_folio_to_list(folio, folio_list)) -- 2.47.3