diff options
| -rw-r--r-- | .mailmap | 1 | ||||
| -rw-r--r-- | Documentation/admin-guide/cgroup-v2.rst | 9 | ||||
| -rw-r--r-- | Documentation/admin-guide/kernel-parameters.txt | 2 | ||||
| -rw-r--r-- | Documentation/admin-guide/mm/transhuge.rst | 2 | ||||
| -rw-r--r-- | fs/ocfs2/xattr.c | 3 | ||||
| -rw-r--r-- | fs/proc/vmcore.c | 9 | ||||
| -rw-r--r-- | include/linux/memcontrol.h | 12 | ||||
| -rw-r--r-- | include/linux/mmzone.h | 1 | ||||
| -rw-r--r-- | include/linux/user_namespace.h | 3 | ||||
| -rw-r--r-- | include/linux/vm_event_item.h | 2 | ||||
| -rw-r--r-- | kernel/signal.c | 3 | ||||
| -rw-r--r-- | kernel/ucount.c | 9 | ||||
| -rw-r--r-- | lib/objpool.c | 18 | ||||
| -rw-r--r-- | mm/damon/core.c | 42 | ||||
| -rw-r--r-- | mm/memcontrol.c | 4 | ||||
| -rw-r--r-- | mm/mlock.c | 9 | ||||
| -rw-r--r-- | mm/page_alloc.c | 10 | ||||
| -rw-r--r-- | mm/page_io.c | 16 | ||||
| -rw-r--r-- | mm/vmstat.c | 2 | ||||
| -rw-r--r-- | mm/zswap.c | 6 | ||||
| -rw-r--r-- | tools/testing/selftests/mm/hugetlb_dio.c | 19 |
21 files changed, 127 insertions, 55 deletions
@@ -666,6 +666,7 @@ Tomeu Vizoso <tomeu@tomeuvizoso.net> <tomeu.vizoso@collabora.com> Thomas Graf <tgraf@suug.ch> Thomas Körper <socketcan@esd.eu> <thomas.koerper@esd.eu> Thomas Pedersen <twp@codeaurora.org> +Thorsten Blum <thorsten.blum@linux.dev> <thorsten.blum@toblux.com> Tiezhu Yang <yangtiezhu@loongson.cn> <kernelpatch@126.com> Tingwei Zhang <quic_tingwei@quicinc.com> <tingwei@codeaurora.org> Tirupathi Reddy <quic_tirupath@quicinc.com> <tirupath@codeaurora.org> diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 69af2173555f..6d02168d78be 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1599,6 +1599,15 @@ The following nested keys are defined. pglazyfreed (npn) Amount of reclaimed lazyfree pages + swpin_zero + Number of pages swapped into memory and filled with zero, where I/O + was optimized out because the page content was detected to be zero + during swapout. + + swpout_zero + Number of zero-filled pages swapped out with I/O skipped due to the + content being detected as zero. + zswpin Number of pages moved in to memory from zswap. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 1518343bbe22..1666576acc0e 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6688,7 +6688,7 @@ 0: no polling (default) thp_anon= [KNL] - Format: <size>,<size>[KMG]:<state>;<size>-<size>[KMG]:<state> + Format: <size>[KMG],<size>[KMG]:<state>;<size>[KMG]-<size>[KMG]:<state> state is one of "always", "madvise", "never" or "inherit". Control the default behavior of the system with respect to anonymous transparent hugepages. diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index cfdd16a52e39..a1bb495eab59 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -303,7 +303,7 @@ control by passing the parameter ``transparent_hugepage=always`` or kernel command line. Alternatively, each supported anonymous THP size can be controlled by -passing ``thp_anon=<size>,<size>[KMG]:<state>;<size>-<size>[KMG]:<state>``, +passing ``thp_anon=<size>[KMG],<size>[KMG]:<state>;<size>[KMG]-<size>[KMG]:<state>``, where ``<size>`` is the THP size (must be a power of 2 of PAGE_SIZE and supported anonymous THP) and ``<state>`` is one of ``always``, ``madvise``, ``never`` or ``inherit``. diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index dd0a05365e79..73a6f6fd8a8e 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -2036,8 +2036,7 @@ static int ocfs2_xa_remove(struct ocfs2_xa_loc *loc, rc = 0; ocfs2_xa_cleanup_value_truncate(loc, "removing", orig_clusters); - if (rc) - goto out; + goto out; } } diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index b52d85f8ad59..b4521b096058 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -457,10 +457,6 @@ static vm_fault_t mmap_vmcore_fault(struct vm_fault *vmf) #endif } -static const struct vm_operations_struct vmcore_mmap_ops = { - .fault = mmap_vmcore_fault, -}; - /** * vmcore_alloc_buf - allocate buffer in vmalloc memory * @size: size of buffer @@ -488,6 +484,11 @@ static inline char *vmcore_alloc_buf(size_t size) * virtually contiguous user-space in ELF layout. */ #ifdef CONFIG_MMU + +static const struct vm_operations_struct vmcore_mmap_ops = { + .fault = mmap_vmcore_fault, +}; + /* * remap_oldmem_pfn_checked - do remap_oldmem_pfn_range replacing all pages * reported as not being ram with the zero page. diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 8e4608be811d..0bd8f61a5597 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1711,8 +1711,9 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) struct mem_cgroup *mem_cgroup_from_slab_obj(void *p); -static inline void count_objcg_event(struct obj_cgroup *objcg, - enum vm_event_item idx) +static inline void count_objcg_events(struct obj_cgroup *objcg, + enum vm_event_item idx, + unsigned long count) { struct mem_cgroup *memcg; @@ -1721,7 +1722,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, rcu_read_lock(); memcg = obj_cgroup_memcg(objcg); - count_memcg_events(memcg, idx, 1); + count_memcg_events(memcg, idx, count); rcu_read_unlock(); } @@ -1776,8 +1777,9 @@ static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) return NULL; } -static inline void count_objcg_event(struct obj_cgroup *objcg, - enum vm_event_item idx) +static inline void count_objcg_events(struct obj_cgroup *objcg, + enum vm_event_item idx, + unsigned long count) { } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2e8c4307c728..5e8f567753bd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -825,6 +825,7 @@ struct zone { unsigned long watermark_boost; unsigned long nr_reserved_highatomic; + unsigned long nr_free_highatomic; /* * We don't know if the memory that we're going to allocate will be diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 3625096d5f85..7183e5aca282 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -141,7 +141,8 @@ static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type ty long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); -long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type); +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type, + bool override_rlimit); void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type); bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max); diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index aed952d04132..f70d0958095c 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -134,6 +134,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_SWAP SWAP_RA, SWAP_RA_HIT, + SWPIN_ZERO, + SWPOUT_ZERO, #ifdef CONFIG_KSM KSM_SWPIN_COPY, #endif diff --git a/kernel/signal.c b/kernel/signal.c index 4344860ffcac..cbabb2d05e0a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -419,7 +419,8 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags, */ rcu_read_lock(); ucounts = task_ucounts(t); - sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING); + sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, + override_rlimit); rcu_read_unlock(); if (!sigpending) return NULL; diff --git a/kernel/ucount.c b/kernel/ucount.c index 8c07714ff27d..696406939be5 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -307,7 +307,8 @@ void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type) do_dec_rlimit_put_ucounts(ucounts, NULL, type); } -long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type) +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type, + bool override_rlimit) { /* Caller must hold a reference to ucounts */ struct ucounts *iter; @@ -317,10 +318,11 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type) for (iter = ucounts; iter; iter = iter->ns->ucounts) { long new = atomic_long_add_return(1, &iter->rlimit[type]); if (new < 0 || new > max) - goto unwind; + goto dec_unwind; if (iter == ucounts) ret = new; - max = get_userns_rlimit_max(iter->ns, type); + if (!override_rlimit) + max = get_userns_rlimit_max(iter->ns, type); /* * Grab an extra ucount reference for the caller when * the rlimit count was previously 0. @@ -334,7 +336,6 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type) dec_unwind: dec = atomic_long_sub_return(1, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); -unwind: do_dec_rlimit_put_ucounts(ucounts, iter, type); return 0; } diff --git a/lib/objpool.c b/lib/objpool.c index fd108fe0d095..b998b720c732 100644 --- a/lib/objpool.c +++ b/lib/objpool.c @@ -74,15 +74,21 @@ objpool_init_percpu_slots(struct objpool_head *pool, int nr_objs, * warm caches and TLB hits. in default vmalloc is used to * reduce the pressure of kernel slab system. as we know, * mimimal size of vmalloc is one page since vmalloc would - * always align the requested size to page size + * always align the requested size to page size. + * but if vmalloc fails or it is not available (e.g. GFP_ATOMIC) + * allocate percpu slot with kmalloc. */ - if ((pool->gfp & GFP_ATOMIC) == GFP_ATOMIC) - slot = kmalloc_node(size, pool->gfp, cpu_to_node(i)); - else + slot = NULL; + + if ((pool->gfp & (GFP_ATOMIC | GFP_KERNEL)) != GFP_ATOMIC) slot = __vmalloc_node(size, sizeof(void *), pool->gfp, cpu_to_node(i), __builtin_return_address(0)); - if (!slot) - return -ENOMEM; + + if (!slot) { + slot = kmalloc_node(size, pool->gfp, cpu_to_node(i)); + if (!slot) + return -ENOMEM; + } memset(slot, 0, size); pool->cpu_slots[i] = slot; diff --git a/mm/damon/core.c b/mm/damon/core.c index a83f3b736d51..511c3f61ab44 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1412,7 +1412,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c, damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; - if (c->passed_sample_intervals != s->next_apply_sis) + if (c->passed_sample_intervals < s->next_apply_sis) continue; if (!s->wmarks.activated) @@ -1456,17 +1456,31 @@ static unsigned long damon_feed_loop_next_input(unsigned long last_input, unsigned long score) { const unsigned long goal = 10000; - unsigned long score_goal_diff = max(goal, score) - min(goal, score); - unsigned long score_goal_diff_bp = score_goal_diff * 10000 / goal; - unsigned long compensation = last_input * score_goal_diff_bp / 10000; /* Set minimum input as 10000 to avoid compensation be zero */ const unsigned long min_input = 10000; + unsigned long score_goal_diff, compensation; + bool over_achieving = score > goal; - if (goal > score) + if (score == goal) + return last_input; + if (score >= goal * 2) + return min_input; + + if (over_achieving) + score_goal_diff = score - goal; + else + score_goal_diff = goal - score; + + if (last_input < ULONG_MAX / score_goal_diff) + compensation = last_input * score_goal_diff / goal; + else + compensation = last_input / goal * score_goal_diff; + + if (over_achieving) + return max(last_input - compensation, min_input); + if (last_input < ULONG_MAX - compensation) return last_input + compensation; - if (last_input > compensation + min_input) - return last_input - compensation; - return min_input; + return ULONG_MAX; } #ifdef CONFIG_PSI @@ -1622,7 +1636,7 @@ static void kdamond_apply_schemes(struct damon_ctx *c) bool has_schemes_to_apply = false; damon_for_each_scheme(s, c) { - if (c->passed_sample_intervals != s->next_apply_sis) + if (c->passed_sample_intervals < s->next_apply_sis) continue; if (!s->wmarks.activated) @@ -1642,9 +1656,9 @@ static void kdamond_apply_schemes(struct damon_ctx *c) } damon_for_each_scheme(s, c) { - if (c->passed_sample_intervals != s->next_apply_sis) + if (c->passed_sample_intervals < s->next_apply_sis) continue; - s->next_apply_sis += + s->next_apply_sis = c->passed_sample_intervals + (s->apply_interval_us ? s->apply_interval_us : c->attrs.aggr_interval) / sample_interval; } @@ -2000,7 +2014,7 @@ static int kdamond_fn(void *data) if (ctx->ops.check_accesses) max_nr_accesses = ctx->ops.check_accesses(ctx); - if (ctx->passed_sample_intervals == next_aggregation_sis) { + if (ctx->passed_sample_intervals >= next_aggregation_sis) { kdamond_merge_regions(ctx, max_nr_accesses / 10, sz_limit); @@ -2018,7 +2032,7 @@ static int kdamond_fn(void *data) sample_interval = ctx->attrs.sample_interval ? ctx->attrs.sample_interval : 1; - if (ctx->passed_sample_intervals == next_aggregation_sis) { + if (ctx->passed_sample_intervals >= next_aggregation_sis) { ctx->next_aggregation_sis = next_aggregation_sis + ctx->attrs.aggr_interval / sample_interval; @@ -2028,7 +2042,7 @@ static int kdamond_fn(void *data) ctx->ops.reset_aggregated(ctx); } - if (ctx->passed_sample_intervals == next_ops_update_sis) { + if (ctx->passed_sample_intervals >= next_ops_update_sis) { ctx->next_ops_update_sis = next_ops_update_sis + ctx->attrs.ops_update_interval / sample_interval; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bc0033a2aa3c..3402b6d13bc2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -438,6 +438,10 @@ static const unsigned int memcg_vm_event_stat[] = { PGDEACTIVATE, PGLAZYFREE, PGLAZYFREED, +#ifdef CONFIG_SWAP + SWPIN_ZERO, + SWPOUT_ZERO, +#endif #ifdef CONFIG_ZSWAP ZSWPIN, ZSWPOUT, diff --git a/mm/mlock.c b/mm/mlock.c index e3e3dc2b2956..cde076fa7d5e 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -725,14 +725,17 @@ static int apply_mlockall_flags(int flags) } for_each_vma(vmi, vma) { + int error; vm_flags_t newflags; newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= to_add; - /* Ignore errors */ - mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end, - newflags); + error = mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end, + newflags); + /* Ignore errors, but prev needs fixing up. */ + if (error) + prev = vma; cond_resched(); } out: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0d6301120fc4..744c1a413fdb 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -635,6 +635,8 @@ compaction_capture(struct capture_control *capc, struct page *page, static inline void account_freepages(struct zone *zone, int nr_pages, int migratetype) { + lockdep_assert_held(&zone->lock); + if (is_migrate_isolate(migratetype)) return; @@ -642,6 +644,9 @@ static inline void account_freepages(struct zone *zone, int nr_pages, if (is_migrate_cma(migratetype)) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages); + else if (is_migrate_highatomic(migratetype)) + WRITE_ONCE(zone->nr_free_highatomic, + zone->nr_free_highatomic + nr_pages); } /* Used for pages not on another list */ @@ -3079,11 +3084,10 @@ static inline long __zone_watermark_unusable_free(struct zone *z, /* * If the caller does not have rights to reserves below the min - * watermark then subtract the high-atomic reserves. This will - * over-estimate the size of the atomic reserve but it avoids a search. + * watermark then subtract the free pages reserved for highatomic. */ if (likely(!(alloc_flags & ALLOC_RESERVES))) - unusable_free += z->nr_reserved_highatomic; + unusable_free += READ_ONCE(z->nr_free_highatomic); #ifdef CONFIG_CMA /* If allocation can't use CMA areas don't use free CMA pages */ diff --git a/mm/page_io.c b/mm/page_io.c index ef42651d5ef8..39e8be23bd95 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -204,7 +204,9 @@ static bool is_folio_zero_filled(struct folio *folio) static void swap_zeromap_folio_set(struct folio *folio) { + struct obj_cgroup *objcg = get_obj_cgroup_from_folio(folio); struct swap_info_struct *sis = swp_swap_info(folio->swap); + int nr_pages = folio_nr_pages(folio); swp_entry_t entry; unsigned int i; @@ -212,6 +214,12 @@ static void swap_zeromap_folio_set(struct folio *folio) entry = page_swap_entry(folio_page(folio, i)); set_bit(swp_offset(entry), sis->zeromap); } + + count_vm_events(SWPOUT_ZERO, nr_pages); + if (objcg) { + count_objcg_events(objcg, SWPOUT_ZERO, nr_pages); + obj_cgroup_put(objcg); + } } static void swap_zeromap_folio_clear(struct folio *folio) @@ -505,6 +513,7 @@ static void sio_read_complete(struct kiocb *iocb, long ret) static bool swap_read_folio_zeromap(struct folio *folio) { int nr_pages = folio_nr_pages(folio); + struct obj_cgroup *objcg; bool is_zeromap; /* @@ -519,6 +528,13 @@ static bool swap_read_folio_zeromap(struct folio *folio) if (!is_zeromap) return false; + objcg = get_obj_cgroup_from_folio(folio); + count_vm_events(SWPIN_ZERO, nr_pages); + if (objcg) { + count_objcg_events(objcg, SWPIN_ZERO, nr_pages); + obj_cgroup_put(objcg); + } + folio_zero_range(folio, 0, folio_size(folio)); folio_mark_uptodate(folio); return true; diff --git a/mm/vmstat.c b/mm/vmstat.c index 7b62bfb19afa..3d82bb906dcf 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1415,6 +1415,8 @@ const char * const vmstat_text[] = { #ifdef CONFIG_SWAP "swap_ra", "swap_ra_hit", + "swpin_zero", + "swpout_zero", #ifdef CONFIG_KSM "ksm_swpin_copy", #endif diff --git a/mm/zswap.c b/mm/zswap.c index a9f4fa121eb2..a400324a45a7 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1053,7 +1053,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry, count_vm_event(ZSWPWB); if (entry->objcg) - count_objcg_event(entry->objcg, ZSWPWB); + count_objcg_events(entry->objcg, ZSWPWB, 1); zswap_entry_free(entry); @@ -1483,7 +1483,7 @@ bool zswap_store(struct folio *folio) if (objcg) { obj_cgroup_charge_zswap(objcg, entry->length); - count_objcg_event(objcg, ZSWPOUT); + count_objcg_events(objcg, ZSWPOUT, 1); } /* @@ -1577,7 +1577,7 @@ bool zswap_load(struct folio *folio) count_vm_event(ZSWPIN); if (entry->objcg) - count_objcg_event(entry->objcg, ZSWPIN); + count_objcg_events(entry->objcg, ZSWPIN, 1); if (swapcache) { zswap_entry_free(entry); diff --git a/tools/testing/selftests/mm/hugetlb_dio.c b/tools/testing/selftests/mm/hugetlb_dio.c index f9ac20c657ec..60001c142ce9 100644 --- a/tools/testing/selftests/mm/hugetlb_dio.c +++ b/tools/testing/selftests/mm/hugetlb_dio.c @@ -44,13 +44,6 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off) if (fd < 0) ksft_exit_fail_perror("Error opening file\n"); - /* Get the free huge pages before allocation */ - free_hpage_b = get_free_hugepages(); - if (free_hpage_b == 0) { - close(fd); - ksft_exit_skip("No free hugepage, exiting!\n"); - } - /* Allocate a hugetlb page */ orig_buffer = mmap(NULL, h_pagesize, mmap_prot, mmap_flags, -1, 0); if (orig_buffer == MAP_FAILED) { @@ -94,8 +87,20 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off) int main(void) { size_t pagesize = 0; + int fd; ksft_print_header(); + + /* Open the file to DIO */ + fd = open("/tmp", O_TMPFILE | O_RDWR | O_DIRECT, 0664); + if (fd < 0) + ksft_exit_skip("Unable to allocate file: %s\n", strerror(errno)); + close(fd); + + /* Check if huge pages are free */ + if (!get_free_hugepages()) + ksft_exit_skip("No free hugepage, exiting\n"); + ksft_set_plan(4); /* Get base page size */ |