diff --git a/.mailmap b/.mailmap index a8be42f87e02..ca6dc2575802 100644 --- a/.mailmap +++ b/.mailmap @@ -176,6 +176,7 @@ Brian Cain Brian King Brian Silverman Bryan Tan +Burak Emir Cai Huoqing Casey Connolly Casey Connolly @@ -648,6 +649,7 @@ Nicholas Piggin Nicholas Piggin Nicholas Piggin Nicolas Ferre +Nico Pache Nicolas Pitre Nicolas Pitre Nicolas Saenz Julienne @@ -695,6 +697,7 @@ Paulo Alcantara Paulo Alcantara Pavankumar Kondeti Peter A Jonsson +Peter Collingbourne Peter Hilber Peter Oruba Peter Oruba diff --git a/MAINTAINERS b/MAINTAINERS index 44b5555fc814..bff676f08c63 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4634,7 +4634,7 @@ F: rust/helpers/cpumask.c BITMAP API [RUST] M: Alice Ryhl -M: Burak Emir +M: Burak Emir R: Yury Norov S: Maintained F: lib/find_bit_benchmark_rust.rs @@ -17253,7 +17253,7 @@ M: Lorenzo Stoakes R: Zi Yan R: Baolin Wang R: Liam R. Howlett -R: Nico Pache +R: Nico Pache R: Ryan Roberts R: Dev Jain R: Barry Song diff --git a/arch/arm64/kernel/pi/relocate.c b/arch/arm64/kernel/pi/relocate.c index 2407d2696398..82592f3a5c1c 100644 --- a/arch/arm64/kernel/pi/relocate.c +++ b/arch/arm64/kernel/pi/relocate.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only // Copyright 2023 Google LLC // Authors: Ard Biesheuvel -// Peter Collingbourne +// Peter Collingbourne #include #include diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 3e450890be07..422efa11824b 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -63,7 +63,8 @@ EXPORT_SYMBOL(phys_ram_base); #ifdef CONFIG_SPARSEMEM_VMEMMAP #define VMEMMAP_ADDR_ALIGN max(1ULL << SECTION_SIZE_BITS, \ - MAX_FOLIO_VMEMMAP_ALIGN) + PFN_PHYS(MAX_FOLIO_VMEMMAP_ALIGN / \ + sizeof(struct page))) unsigned long vmemmap_start_pfn __ro_after_init; EXPORT_SYMBOL(vmemmap_start_pfn); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index fb2d7dd17de0..2289a0416cdc 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -4114,6 +4114,18 @@ static int __folio_split(struct folio *folio, unsigned int new_order, remap_page(folio, 1 << old_order, ttu_flags); + /* + * Drop the mapping while the inode is still pinned. @folio stays + * locked and present in the page cache until the loop below, so + * eviction cannot free the inode yet; @lock_at is not enough, it may + * be a tail beyond EOF that the split already dropped from the page + * cache. Nothing past this point may touch the inode or the mapping. + */ + if (mapping) { + i_mmap_unlock_read(mapping); + mapping = NULL; + } + /* * Unlock all after-split folios except the one containing * @lock_at page. If @folio is not split, it will be kept locked. diff --git a/mm/memcontrol-v1.h b/mm/memcontrol-v1.h index d3ed5b93290f..0f703f239c80 100644 --- a/mm/memcontrol-v1.h +++ b/mm/memcontrol-v1.h @@ -101,7 +101,11 @@ static inline void memcg1_remove_from_trees(struct mem_cgroup *memcg) {} static inline void memcg1_soft_limit_reset(struct mem_cgroup *memcg) {} static inline void memcg1_css_offline(struct mem_cgroup *memcg) {} -static inline bool memcg1_oom_prepare(struct mem_cgroup *memcg, bool *locked) { return true; } +static inline bool memcg1_oom_prepare(struct mem_cgroup *memcg, bool *locked) +{ + *locked = false; + return true; +} static inline void memcg1_oom_finish(struct mem_cgroup *memcg, bool locked) {} static inline void memcg1_oom_recover(struct mem_cgroup *memcg) {} diff --git a/mm/memremap.c b/mm/memremap.c index 81766d822400..accba23aef28 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -425,6 +425,7 @@ void free_zone_device_folio(struct folio *folio) mem_cgroup_uncharge(folio); if (folio_test_anon(folio)) { + mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, -1); for (i = 0; i < nr; i++) __ClearPageAnonExclusive(folio_page(folio, i)); } diff --git a/mm/migrate.c b/mm/migrate.c index b6f56b67e367..d3bd5cc8f552 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -595,7 +595,8 @@ static int __folio_migrate_mapping(struct address_space *mapping, /* No turning back from here */ newfolio->index = folio->index; newfolio->mapping = folio->mapping; - if (folio_test_anon(folio) && folio_test_large(folio)) + if (folio_test_anon(folio) && folio_test_large(folio) && + !folio_test_hugetlb(folio)) mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); if (folio_test_swapbacked(folio)) __folio_set_swapbacked(newfolio); diff --git a/mm/page_reporting.c b/mm/page_reporting.c index 9d21f9255779..1cce8729696e 100644 --- a/mm/page_reporting.c +++ b/mm/page_reporting.c @@ -81,7 +81,8 @@ __page_reporting_request(struct page_reporting_dev_info *prdev) * now we are limiting this to running no more than once every * couple of seconds. */ - schedule_delayed_work(&prdev->work, PAGE_REPORTING_DELAY); + queue_delayed_work(system_freezable_wq, &prdev->work, + PAGE_REPORTING_DELAY); } /* notify prdev of free page reporting request */ @@ -341,7 +342,8 @@ static void page_reporting_process(struct work_struct *work) */ state = atomic_cmpxchg(&prdev->state, state, PAGE_REPORTING_IDLE); if (state == PAGE_REPORTING_REQUESTED) - schedule_delayed_work(&prdev->work, PAGE_REPORTING_DELAY); + queue_delayed_work(system_freezable_wq, &prdev->work, + PAGE_REPORTING_DELAY); } static DEFINE_MUTEX(page_reporting_mutex); diff --git a/mm/vmscan.c b/mm/vmscan.c index 454e9d0930ab..347565278a55 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4919,6 +4919,9 @@ static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc) int i; enum zone_watermarks mark; + if (unlikely(sc->proactive && signal_pending(current))) + return true; + if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order))) return true; @@ -7899,8 +7902,15 @@ int user_proactive_reclaim(char *buf, unsigned long batch_size = (nr_to_reclaim - nr_reclaimed) / 4; unsigned long reclaimed; + /* + * Return -ERESTARTSYS to allow the freezer to interrupt the + * task. The syscall will be transparently restarted upon + * resume. For real signals, it either restarts the syscall + * (if SA_RESTART is set) or is converted to -EINTR by the + * signal layer. + */ if (signal_pending(current)) - return -EINTR; + return -ERESTARTSYS; /* * This is the final attempt, drain percpu lru caches in the diff --git a/tools/testing/selftests/clone3/clone3_set_tid.c b/tools/testing/selftests/clone3/clone3_set_tid.c index 5c944aee6b41..485efa7c9eed 100644 --- a/tools/testing/selftests/clone3/clone3_set_tid.c +++ b/tools/testing/selftests/clone3/clone3_set_tid.c @@ -141,7 +141,7 @@ int main(int argc, char *argv[]) { FILE *f; char buf; - char *line; + char *line = NULL; int status; int ret = -1; size_t len = 0; diff --git a/tools/testing/selftests/mm/mlock-random-test.c b/tools/testing/selftests/mm/mlock-random-test.c index 9d349c151360..16294bc7dae6 100644 --- a/tools/testing/selftests/mm/mlock-random-test.c +++ b/tools/testing/selftests/mm/mlock-random-test.c @@ -84,7 +84,7 @@ int get_proc_locked_vm_size(void) int get_proc_page_size(unsigned long addr) { FILE *smaps; - char *line; + char *line = NULL; unsigned long mmupage_size = 0; size_t size;