diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 9 | ||||
| -rw-r--r-- | mm/backing-dev.c | 18 | ||||
| -rw-r--r-- | mm/cleancache.c | 2 | ||||
| -rw-r--r-- | mm/frontswap.c | 2 | ||||
| -rw-r--r-- | mm/hmm.c | 2 | ||||
| -rw-r--r-- | mm/huge_memory.c | 4 | ||||
| -rw-r--r-- | mm/hugetlb.c | 4 | ||||
| -rw-r--r-- | mm/ksm.c | 23 | ||||
| -rw-r--r-- | mm/memcontrol.c | 2 | ||||
| -rw-r--r-- | mm/mempool.c | 108 | ||||
| -rw-r--r-- | mm/mmap.c | 2 | ||||
| -rw-r--r-- | mm/rmap.c | 6 | ||||
| -rw-r--r-- | mm/util.c | 2 | ||||
| -rw-r--r-- | mm/vmalloc.c | 21 | ||||
| -rw-r--r-- | mm/vmstat.c | 56 |
15 files changed, 145 insertions, 116 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index e14c01513bfd..3e0b6e87f65d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -266,7 +266,7 @@ config ARCH_ENABLE_THP_MIGRATION bool config PHYS_ADDR_T_64BIT - def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT + def_bool 64BIT config BOUNCE bool "Enable bounce buffers" @@ -305,7 +305,7 @@ config KSM the many instances by a single page with that content, so saving memory until one or another app needs to modify the content. Recommended for use with KVM, or with other duplicative applications. - See Documentation/vm/ksm.txt for more information: KSM is inactive + See Documentation/vm/ksm.rst for more information: KSM is inactive until a program has madvised that an area is MADV_MERGEABLE, and root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set). @@ -530,7 +530,7 @@ config MEM_SOFT_DIRTY into a page just as regular dirty bit, but unlike the latter it can be cleared by hands. - See Documentation/vm/soft-dirty.txt for more details. + See Documentation/admin-guide/mm/soft-dirty.rst for more details. config ZSWAP bool "Compressed cache for swap pages (EXPERIMENTAL)" @@ -657,7 +657,8 @@ config IDLE_PAGE_TRACKING be useful to tune memory cgroup limits and/or for job placement within a compute cluster. - See Documentation/vm/idle_page_tracking.txt for more details. + See Documentation/admin-guide/mm/idle_page_tracking.rst for + more details. # arch_add_memory() comprehends device memory config ARCH_HAS_ZONE_DEVICE diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 7441bd93b732..8fe3ebd6ac00 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -412,6 +412,7 @@ static void wb_exit(struct bdi_writeback *wb) * protected. */ static DEFINE_SPINLOCK(cgwb_lock); +static struct workqueue_struct *cgwb_release_wq; /** * wb_congested_get_create - get or create a wb_congested @@ -522,7 +523,7 @@ static void cgwb_release(struct percpu_ref *refcnt) { struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback, refcnt); - schedule_work(&wb->release_work); + queue_work(cgwb_release_wq, &wb->release_work); } static void cgwb_kill(struct bdi_writeback *wb) @@ -784,6 +785,21 @@ static void cgwb_bdi_register(struct backing_dev_info *bdi) spin_unlock_irq(&cgwb_lock); } +static int __init cgwb_init(void) +{ + /* + * There can be many concurrent release work items overwhelming + * system_wq. Put them in a separate wq and limit concurrency. + * There's no point in executing many of these in parallel. + */ + cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1); + if (!cgwb_release_wq) + return -ENOMEM; + + return 0; +} +subsys_initcall(cgwb_init); + #else /* CONFIG_CGROUP_WRITEBACK */ static int cgwb_bdi_init(struct backing_dev_info *bdi) diff --git a/mm/cleancache.c b/mm/cleancache.c index f7b9fdc79d97..126548b5a292 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -3,7 +3,7 @@ * * This code provides the generic "frontend" layer to call a matching * "backend" driver implementation of cleancache. See - * Documentation/vm/cleancache.txt for more information. + * Documentation/vm/cleancache.rst for more information. * * Copyright (C) 2009-2010 Oracle Corp. All rights reserved. * Author: Dan Magenheimer diff --git a/mm/frontswap.c b/mm/frontswap.c index fec8b5044040..4f5476a0f955 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -3,7 +3,7 @@ * * This code provides the generic "frontend" layer to call a matching * "backend" driver implementation of frontswap. See - * Documentation/vm/frontswap.txt for more information. + * Documentation/vm/frontswap.rst for more information. * * Copyright (C) 2009-2012 Oracle Corp. All rights reserved. * Author: Dan Magenheimer @@ -37,7 +37,7 @@ #if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC) /* - * Device private memory see HMM (Documentation/vm/hmm.txt) or hmm.h + * Device private memory see HMM (Documentation/vm/hmm.rst) or hmm.h */ DEFINE_STATIC_KEY_FALSE(device_private_key); EXPORT_SYMBOL(device_private_key); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b9f3dbd885bd..ac5591d8622c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1185,7 +1185,7 @@ static int do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, pmd_t orig_pmd, * mmu_notifier_invalidate_range_end() happens which can lead to a * device seeing memory write in different order than CPU. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ pmdp_huge_clear_flush_notify(vma, haddr, vmf->pmd); @@ -2037,7 +2037,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, * replacing a zero pmd write protected page with a zero pte write * protected page. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ pmdp_huge_clear_flush(vma, haddr, pmd); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 218679138255..129088710510 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3291,7 +3291,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, * table protection not changing it to point * to a new page. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); } @@ -4357,7 +4357,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * No need to call mmu_notifier_invalidate_range() we are downgrading * page table protection not changing it to point to a new page. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); mmu_notifier_invalidate_range_end(mm, start, end); @@ -51,7 +51,9 @@ #define DO_NUMA(x) do { } while (0) #endif -/* +/** + * DOC: Overview + * * A few notes about the KSM scanning process, * to make it easier to understand the data structures below: * @@ -67,6 +69,21 @@ * this tree is fully assured to be working (except when pages are unmapped), * and therefore this tree is called the stable tree. * + * The stable tree node includes information required for reverse + * mapping from a KSM page to virtual addresses that map this page. + * + * In order to avoid large latencies of the rmap walks on KSM pages, + * KSM maintains two types of nodes in the stable tree: + * + * * the regular nodes that keep the reverse mapping structures in a + * linked list + * * the "chains" that link nodes ("dups") that represent the same + * write protected memory content, but each "dup" corresponds to a + * different KSM page copy of that content + * + * Internally, the regular nodes, "dups" and "chains" are represented + * using the same :c:type:`struct stable_node` structure. + * * In addition to the stable tree, KSM uses a second data structure called the * unstable tree: this tree holds pointers to pages which have been found to * be "unchanged for a period of time". The unstable tree sorts these pages @@ -1049,7 +1066,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, * No need to notify as we are downgrading page table to read * only not changing it to point to a new page. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ entry = ptep_clear_flush(vma, pvmw.address, pvmw.pte); /* @@ -1145,7 +1162,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, * No need to notify as we are replacing a read only page with another * read only page with the same content. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ ptep_clear_flush(vma, addr, ptep); set_pte_at_notify(mm, addr, ptep, newpte); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2bd3df3d101a..1695f38630f1 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3849,7 +3849,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, if (ret) goto out_put_css; - efile.file->f_op->poll(efile.file, &event->pt); + vfs_poll(efile.file, &event->pt); spin_lock(&memcg->event_list_lock); list_add(&event->list, &memcg->event_list); diff --git a/mm/mempool.c b/mm/mempool.c index 5c9dce34719b..b54f2c20e5e0 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -138,6 +138,28 @@ static void *remove_element(mempool_t *pool, gfp_t flags) } /** + * mempool_exit - exit a mempool initialized with mempool_init() + * @pool: pointer to the memory pool which was initialized with + * mempool_init(). + * + * Free all reserved elements in @pool and @pool itself. This function + * only sleeps if the free_fn() function sleeps. + * + * May be called on a zeroed but uninitialized mempool (i.e. allocated with + * kzalloc()). + */ +void mempool_exit(mempool_t *pool) +{ + while (pool->curr_nr) { + void *element = remove_element(pool, GFP_KERNEL); + pool->free(element, pool->pool_data); + } + kfree(pool->elements); + pool->elements = NULL; +} +EXPORT_SYMBOL(mempool_exit); + +/** * mempool_destroy - deallocate a memory pool * @pool: pointer to the memory pool which was allocated via * mempool_create(). @@ -150,15 +172,65 @@ void mempool_destroy(mempool_t *pool) if (unlikely(!pool)) return; - while (pool->curr_nr) { - void *element = remove_element(pool, GFP_KERNEL); - pool->free(element, pool->pool_data); - } - kfree(pool->elements); + mempool_exit(pool); kfree(pool); } EXPORT_SYMBOL(mempool_destroy); +int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, + mempool_free_t *free_fn, void *pool_data, + gfp_t gfp_mask, int node_id) +{ + spin_lock_init(&pool->lock); + pool->min_nr = min_nr; + pool->pool_data = pool_data; + pool->alloc = alloc_fn; + pool->free = free_fn; + init_waitqueue_head(&pool->wait); + + pool->elements = kmalloc_array_node(min_nr, sizeof(void *), + gfp_mask, node_id); + if (!pool->elements) + return -ENOMEM; + + /* + * First pre-allocate the guaranteed number of buffers. + */ + while (pool->curr_nr < pool->min_nr) { + void *element; + + element = pool->alloc(gfp_mask, pool->pool_data); + if (unlikely(!element)) { + mempool_exit(pool); + return -ENOMEM; + } + add_element(pool, element); + } + + return 0; +} +EXPORT_SYMBOL(mempool_init_node); + +/** + * mempool_init - initialize a memory pool + * @min_nr: the minimum number of elements guaranteed to be + * allocated for this pool. + * @alloc_fn: user-defined element-allocation function. + * @free_fn: user-defined element-freeing function. + * @pool_data: optional private data available to the user-defined functions. + * + * Like mempool_create(), but initializes the pool in (i.e. embedded in another + * structure). + */ +int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, + mempool_free_t *free_fn, void *pool_data) +{ + return mempool_init_node(pool, min_nr, alloc_fn, free_fn, + pool_data, GFP_KERNEL, NUMA_NO_NODE); + +} +EXPORT_SYMBOL(mempool_init); + /** * mempool_create - create a memory pool * @min_nr: the minimum number of elements guaranteed to be @@ -186,35 +258,17 @@ mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, gfp_t gfp_mask, int node_id) { mempool_t *pool; + pool = kzalloc_node(sizeof(*pool), gfp_mask, node_id); if (!pool) return NULL; - pool->elements = kmalloc_array_node(min_nr, sizeof(void *), - gfp_mask, node_id); - if (!pool->elements) { + + if (mempool_init_node(pool, min_nr, alloc_fn, free_fn, pool_data, + gfp_mask, node_id)) { kfree(pool); return NULL; } - spin_lock_init(&pool->lock); - pool->min_nr = min_nr; - pool->pool_data = pool_data; - init_waitqueue_head(&pool->wait); - pool->alloc = alloc_fn; - pool->free = free_fn; - /* - * First pre-allocate the guaranteed number of buffers. - */ - while (pool->curr_nr < pool->min_nr) { - void *element; - - element = pool->alloc(gfp_mask, pool->pool_data); - if (unlikely(!element)) { - mempool_destroy(pool); - return NULL; - } - add_element(pool, element); - } return pool; } EXPORT_SYMBOL(mempool_create_node); diff --git a/mm/mmap.c b/mm/mmap.c index fc41c0543d7f..d817764a9974 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2828,7 +2828,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long ret = -EINVAL; struct file *file; - pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.txt.\n", + pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.rst.\n", current->comm, current->pid); if (prot) diff --git a/mm/rmap.c b/mm/rmap.c index 8d5337fed37b..6db729dc4c50 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -942,7 +942,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, * downgrading page table protection not changing it to point * to a new page. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ if (ret) (*cleaned)++; @@ -1599,7 +1599,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * point at new page while a device still is using this * page. * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ dec_mm_counter(mm, mm_counter_file(page)); } @@ -1609,7 +1609,7 @@ discard: * done above for all cases requiring it to happen under page * table lock before mmu_notifier_invalidate_range_end() * - * See Documentation/vm/mmu_notifier.txt + * See Documentation/vm/mmu_notifier.rst */ page_remove_rmap(subpage, PageHuge(page)); put_page(page); diff --git a/mm/util.c b/mm/util.c index 45fc3169e7b0..c2d0a7cdb189 100644 --- a/mm/util.c +++ b/mm/util.c @@ -621,7 +621,7 @@ EXPORT_SYMBOL_GPL(vm_memory_committed); * succeed and -ENOMEM implies there is not. * * We currently support three overcommit policies, which are set via the - * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting + * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting.rst * * Strict overcommit modes added 2002 Feb 26 by Alan Cox. * Additional code 2002 Jul 20 by Robert Love. diff --git a/mm/vmalloc.c b/mm/vmalloc.c index ebff729cc956..63a5f502da08 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2751,25 +2751,14 @@ static const struct seq_operations vmalloc_op = { .show = s_show, }; -static int vmalloc_open(struct inode *inode, struct file *file) +static int __init proc_vmalloc_init(void) { if (IS_ENABLED(CONFIG_NUMA)) - return seq_open_private(file, &vmalloc_op, - nr_node_ids * sizeof(unsigned int)); + proc_create_seq_private("vmallocinfo", S_IRUSR, NULL, + &vmalloc_op, + nr_node_ids * sizeof(unsigned int), NULL); else - return seq_open(file, &vmalloc_op); -} - -static const struct file_operations proc_vmalloc_operations = { - .open = vmalloc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, -}; - -static int __init proc_vmalloc_init(void) -{ - proc_create("vmallocinfo", S_IRUSR, NULL, &proc_vmalloc_operations); + proc_create_seq("vmallocinfo", S_IRUSR, NULL, &vmalloc_op); return 0; } module_init(proc_vmalloc_init); diff --git a/mm/vmstat.c b/mm/vmstat.c index a2b9518980ce..75eda9c2b260 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1516,18 +1516,6 @@ static const struct seq_operations fragmentation_op = { .show = frag_show, }; -static int fragmentation_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &fragmentation_op); -} - -static const struct file_operations buddyinfo_file_operations = { - .open = fragmentation_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - static const struct seq_operations pagetypeinfo_op = { .start = frag_start, .next = frag_next, @@ -1535,18 +1523,6 @@ static const struct seq_operations pagetypeinfo_op = { .show = pagetypeinfo_show, }; -static int pagetypeinfo_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &pagetypeinfo_op); -} - -static const struct file_operations pagetypeinfo_file_operations = { - .open = pagetypeinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone) { int zid; @@ -1663,18 +1639,6 @@ static const struct seq_operations zoneinfo_op = { .show = zoneinfo_show, }; -static int zoneinfo_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &zoneinfo_op); -} - -static const struct file_operations zoneinfo_file_operations = { - .open = zoneinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - enum writeback_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, @@ -1762,18 +1726,6 @@ static const struct seq_operations vmstat_op = { .stop = vmstat_stop, .show = vmstat_show, }; - -static int vmstat_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &vmstat_op); -} - -static const struct file_operations vmstat_file_operations = { - .open = vmstat_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SMP @@ -2020,10 +1972,10 @@ void __init init_mm_internals(void) start_shepherd_timer(); #endif #ifdef CONFIG_PROC_FS - proc_create("buddyinfo", 0444, NULL, &buddyinfo_file_operations); - proc_create("pagetypeinfo", 0444, NULL, &pagetypeinfo_file_operations); - proc_create("vmstat", 0444, NULL, &vmstat_file_operations); - proc_create("zoneinfo", 0444, NULL, &zoneinfo_file_operations); + proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op); + proc_create_seq("pagetypeinfo", 0444, NULL, &pagetypeinfo_op); + proc_create_seq("vmstat", 0444, NULL, &vmstat_op); + proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op); #endif } |
