diff options
Diffstat (limited to 'mm/ksm.c')
| -rw-r--r-- | mm/ksm.c | 2501 |
1 files changed, 1713 insertions, 788 deletions
@@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Memory merging support. * @@ -10,22 +11,21 @@ * Andrea Arcangeli * Chris Wright * Hugh Dickins - * - * This work is licensed under the terms of the GNU GPL, version 2. */ #include <linux/errno.h> #include <linux/mm.h> +#include <linux/mm_inline.h> #include <linux/fs.h> #include <linux/mman.h> #include <linux/sched.h> #include <linux/sched/mm.h> -#include <linux/sched/coredump.h> +#include <linux/sched/cputime.h> #include <linux/rwsem.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/spinlock.h> -#include <linux/jhash.h> +#include <linux/xxhash.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/wait.h> @@ -39,9 +39,14 @@ #include <linux/freezer.h> #include <linux/oom.h> #include <linux/numa.h> +#include <linux/pagewalk.h> #include <asm/tlbflush.h> #include "internal.h" +#include "mm_slot.h" + +#define CREATE_TRACE_POINTS +#include <trace/events/ksm.h> #ifdef CONFIG_NUMA #define NUMA(x) (x) @@ -51,7 +56,11 @@ #define DO_NUMA(x) do { } while (0) #endif -/* +typedef u8 rmap_age_t; + +/** + * DOC: Overview + * * A few notes about the KSM scanning process, * to make it easier to understand the data structures below: * @@ -67,6 +76,21 @@ * 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 struct ksm_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 @@ -95,17 +119,13 @@ */ /** - * struct mm_slot - ksm information per mm that is being scanned - * @link: link to the mm_slots hash list - * @mm_list: link into the mm_slots list, rooted in ksm_mm_head + * struct ksm_mm_slot - ksm information per mm that is being scanned + * @slot: hash lookup from mm to mm_slot * @rmap_list: head for this mm_slot's singly-linked list of rmap_items - * @mm: the mm that this information is valid for */ -struct mm_slot { - struct hlist_node link; - struct list_head mm_list; - struct rmap_item *rmap_list; - struct mm_struct *mm; +struct ksm_mm_slot { + struct mm_slot slot; + struct ksm_rmap_item *rmap_list; }; /** @@ -118,14 +138,14 @@ struct mm_slot { * There is only the one ksm_scan instance of this cursor structure. */ struct ksm_scan { - struct mm_slot *mm_slot; + struct ksm_mm_slot *mm_slot; unsigned long address; - struct rmap_item **rmap_list; + struct ksm_rmap_item **rmap_list; unsigned long seqnr; }; /** - * struct stable_node - node of the stable rbtree + * struct ksm_stable_node - node of the stable rbtree * @node: rb node of this ksm page in the stable tree * @head: (overlaying parent) &migrate_nodes indicates temporarily on that list * @hlist_dup: linked into the stable_node->hlist with a stable_node chain @@ -136,7 +156,7 @@ struct ksm_scan { * @rmap_hlist_len: number of rmap_item entries in hlist or STABLE_NODE_CHAIN * @nid: NUMA node id of stable tree in which linked (may not match kpfn) */ -struct stable_node { +struct ksm_stable_node { union { struct rb_node node; /* when node of stable tree */ struct { /* when listed for migration */ @@ -165,7 +185,7 @@ struct stable_node { }; /** - * struct rmap_item - reverse mapping item for virtual addresses + * struct ksm_rmap_item - reverse mapping item for virtual addresses * @rmap_list: next rmap_item in mm_slot's singly-linked rmap_list * @anon_vma: pointer to anon_vma for this mm,address, when in stable tree * @nid: NUMA node id of unstable tree in which linked (may not match page) @@ -175,9 +195,11 @@ struct stable_node { * @node: rb node of this rmap_item in the unstable tree * @head: pointer to stable_node heading this list in the stable tree * @hlist: link into hlist of rmap_items hanging off that stable_node + * @age: number of scan iterations since creation + * @remaining_skips: how many scans to skip */ -struct rmap_item { - struct rmap_item *rmap_list; +struct ksm_rmap_item { + struct ksm_rmap_item *rmap_list; union { struct anon_vma *anon_vma; /* when stable */ #ifdef CONFIG_NUMA @@ -187,10 +209,12 @@ struct rmap_item { struct mm_struct *mm; unsigned long address; /* + low bits used for flags below */ unsigned int oldchecksum; /* when unstable */ + rmap_age_t age; + rmap_age_t remaining_skips; union { struct rb_node node; /* when node of unstable tree */ struct { /* when listed from stable tree */ - struct stable_node *head; + struct ksm_stable_node *head; struct hlist_node hlist; }; }; @@ -213,8 +237,8 @@ static LIST_HEAD(migrate_nodes); #define MM_SLOTS_HASH_BITS 10 static DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); -static struct mm_slot ksm_mm_head = { - .mm_list = LIST_HEAD_INIT(ksm_mm_head.mm_list), +static struct ksm_mm_slot ksm_mm_head = { + .slot.mm_node = LIST_HEAD_INIT(ksm_mm_head.slot.mm_node), }; static struct ksm_scan ksm_scan = { .mm_slot = &ksm_mm_head, @@ -224,6 +248,12 @@ static struct kmem_cache *rmap_item_cache; static struct kmem_cache *stable_node_cache; static struct kmem_cache *mm_slot_cache; +/* Default number of pages to scan per batch */ +#define DEFAULT_PAGES_TO_SCAN 100 + +/* The number of pages scanned */ +static unsigned long ksm_pages_scanned; + /* The number of nodes in the stable tree */ static unsigned long ksm_pages_shared; @@ -243,13 +273,13 @@ static unsigned long ksm_stable_node_chains; static unsigned long ksm_stable_node_dups; /* Delay in pruning stale stable_node_dups in the stable_node_chains */ -static int ksm_stable_node_chains_prune_millisecs = 2000; +static unsigned int ksm_stable_node_chains_prune_millisecs = 2000; /* Maximum number of page slots sharing a stable node */ static int ksm_max_page_sharing = 256; /* Number of pages ksmd should scan in one batch */ -static unsigned int ksm_thread_pages_to_scan = 100; +static unsigned int ksm_thread_pages_to_scan = DEFAULT_PAGES_TO_SCAN; /* Milliseconds ksmd should sleep between batches */ static unsigned int ksm_thread_sleep_millisecs = 20; @@ -260,6 +290,182 @@ static unsigned int zero_checksum __read_mostly; /* Whether to merge empty (zeroed) pages with actual zero pages */ static bool ksm_use_zero_pages __read_mostly; +/* Skip pages that couldn't be de-duplicated previously */ +/* Default to true at least temporarily, for testing */ +static bool ksm_smart_scan = true; + +/* The number of zero pages which is placed by KSM */ +atomic_long_t ksm_zero_pages = ATOMIC_LONG_INIT(0); + +/* The number of pages that have been skipped due to "smart scanning" */ +static unsigned long ksm_pages_skipped; + +/* Don't scan more than max pages per batch. */ +static unsigned long ksm_advisor_max_pages_to_scan = 30000; + +/* Min CPU for scanning pages per scan */ +#define KSM_ADVISOR_MIN_CPU 10 + +/* Max CPU for scanning pages per scan */ +static unsigned int ksm_advisor_max_cpu = 70; + +/* Target scan time in seconds to analyze all KSM candidate pages. */ +static unsigned long ksm_advisor_target_scan_time = 200; + +/* Exponentially weighted moving average. */ +#define EWMA_WEIGHT 30 + +/** + * struct advisor_ctx - metadata for KSM advisor + * @start_scan: start time of the current scan + * @scan_time: scan time of previous scan + * @change: change in percent to pages_to_scan parameter + * @cpu_time: cpu time consumed by the ksmd thread in the previous scan + */ +struct advisor_ctx { + ktime_t start_scan; + unsigned long scan_time; + unsigned long change; + unsigned long long cpu_time; +}; +static struct advisor_ctx advisor_ctx; + +/* Define different advisor's */ +enum ksm_advisor_type { + KSM_ADVISOR_NONE, + KSM_ADVISOR_SCAN_TIME, +}; +static enum ksm_advisor_type ksm_advisor; + +#ifdef CONFIG_SYSFS +/* + * Only called through the sysfs control interface: + */ + +/* At least scan this many pages per batch. */ +static unsigned long ksm_advisor_min_pages_to_scan = 500; + +static void set_advisor_defaults(void) +{ + if (ksm_advisor == KSM_ADVISOR_NONE) { + ksm_thread_pages_to_scan = DEFAULT_PAGES_TO_SCAN; + } else if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) { + advisor_ctx = (const struct advisor_ctx){ 0 }; + ksm_thread_pages_to_scan = ksm_advisor_min_pages_to_scan; + } +} +#endif /* CONFIG_SYSFS */ + +static inline void advisor_start_scan(void) +{ + if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) + advisor_ctx.start_scan = ktime_get(); +} + +/* + * Use previous scan time if available, otherwise use current scan time as an + * approximation for the previous scan time. + */ +static inline unsigned long prev_scan_time(struct advisor_ctx *ctx, + unsigned long scan_time) +{ + return ctx->scan_time ? ctx->scan_time : scan_time; +} + +/* Calculate exponential weighted moving average */ +static unsigned long ewma(unsigned long prev, unsigned long curr) +{ + return ((100 - EWMA_WEIGHT) * prev + EWMA_WEIGHT * curr) / 100; +} + +/* + * The scan time advisor is based on the current scan rate and the target + * scan rate. + * + * new_pages_to_scan = pages_to_scan * (scan_time / target_scan_time) + * + * To avoid perturbations it calculates a change factor of previous changes. + * A new change factor is calculated for each iteration and it uses an + * exponentially weighted moving average. The new pages_to_scan value is + * multiplied with that change factor: + * + * new_pages_to_scan *= change factor + * + * The new_pages_to_scan value is limited by the cpu min and max values. It + * calculates the cpu percent for the last scan and calculates the new + * estimated cpu percent cost for the next scan. That value is capped by the + * cpu min and max setting. + * + * In addition the new pages_to_scan value is capped by the max and min + * limits. + */ +static void scan_time_advisor(void) +{ + unsigned int cpu_percent; + unsigned long cpu_time; + unsigned long cpu_time_diff; + unsigned long cpu_time_diff_ms; + unsigned long pages; + unsigned long per_page_cost; + unsigned long factor; + unsigned long change; + unsigned long last_scan_time; + unsigned long scan_time; + + /* Convert scan time to seconds */ + scan_time = div_s64(ktime_ms_delta(ktime_get(), advisor_ctx.start_scan), + MSEC_PER_SEC); + scan_time = scan_time ? scan_time : 1; + + /* Calculate CPU consumption of ksmd background thread */ + cpu_time = task_sched_runtime(current); + cpu_time_diff = cpu_time - advisor_ctx.cpu_time; + cpu_time_diff_ms = cpu_time_diff / 1000 / 1000; + + cpu_percent = (cpu_time_diff_ms * 100) / (scan_time * 1000); + cpu_percent = cpu_percent ? cpu_percent : 1; + last_scan_time = prev_scan_time(&advisor_ctx, scan_time); + + /* Calculate scan time as percentage of target scan time */ + factor = ksm_advisor_target_scan_time * 100 / scan_time; + factor = factor ? factor : 1; + + /* + * Calculate scan time as percentage of last scan time and use + * exponentially weighted average to smooth it + */ + change = scan_time * 100 / last_scan_time; + change = change ? change : 1; + change = ewma(advisor_ctx.change, change); + + /* Calculate new scan rate based on target scan rate. */ + pages = ksm_thread_pages_to_scan * 100 / factor; + /* Update pages_to_scan by weighted change percentage. */ + pages = pages * change / 100; + + /* Cap new pages_to_scan value */ + per_page_cost = ksm_thread_pages_to_scan / cpu_percent; + per_page_cost = per_page_cost ? per_page_cost : 1; + + pages = min(pages, per_page_cost * ksm_advisor_max_cpu); + pages = max(pages, per_page_cost * KSM_ADVISOR_MIN_CPU); + pages = min(pages, ksm_advisor_max_pages_to_scan); + + /* Update advisor context */ + advisor_ctx.change = change; + advisor_ctx.scan_time = scan_time; + advisor_ctx.cpu_time = cpu_time; + + ksm_thread_pages_to_scan = pages; + trace_ksm_advisor(scan_time, pages, cpu_percent); +} + +static void advisor_stop_scan(void) +{ + if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) + scan_time_advisor(); +} + #ifdef CONFIG_NUMA /* Zeroed when merging across nodes is not allowed */ static unsigned int ksm_merge_across_nodes = 1; @@ -277,24 +483,21 @@ static unsigned long ksm_run = KSM_RUN_STOP; static void wait_while_offlining(void); static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait); +static DECLARE_WAIT_QUEUE_HEAD(ksm_iter_wait); static DEFINE_MUTEX(ksm_thread_mutex); static DEFINE_SPINLOCK(ksm_mmlist_lock); -#define KSM_KMEM_CACHE(__struct, __flags) kmem_cache_create("ksm_"#__struct,\ - sizeof(struct __struct), __alignof__(struct __struct),\ - (__flags), NULL) - static int __init ksm_slab_init(void) { - rmap_item_cache = KSM_KMEM_CACHE(rmap_item, 0); + rmap_item_cache = KMEM_CACHE(ksm_rmap_item, 0); if (!rmap_item_cache) goto out; - stable_node_cache = KSM_KMEM_CACHE(stable_node, 0); + stable_node_cache = KMEM_CACHE(ksm_stable_node, 0); if (!stable_node_cache) goto out_free1; - mm_slot_cache = KSM_KMEM_CACHE(mm_slot, 0); + mm_slot_cache = KMEM_CACHE(ksm_mm_slot, 0); if (!mm_slot_cache) goto out_free2; @@ -316,18 +519,18 @@ static void __init ksm_slab_free(void) mm_slot_cache = NULL; } -static __always_inline bool is_stable_node_chain(struct stable_node *chain) +static __always_inline bool is_stable_node_chain(struct ksm_stable_node *chain) { return chain->rmap_hlist_len == STABLE_NODE_CHAIN; } -static __always_inline bool is_stable_node_dup(struct stable_node *dup) +static __always_inline bool is_stable_node_dup(struct ksm_stable_node *dup) { return dup->head == STABLE_NODE_DUP_HEAD; } -static inline void stable_node_chain_add_dup(struct stable_node *dup, - struct stable_node *chain) +static inline void stable_node_chain_add_dup(struct ksm_stable_node *dup, + struct ksm_stable_node *chain) { VM_BUG_ON(is_stable_node_dup(dup)); dup->head = STABLE_NODE_DUP_HEAD; @@ -336,14 +539,14 @@ static inline void stable_node_chain_add_dup(struct stable_node *dup, ksm_stable_node_dups++; } -static inline void __stable_node_dup_del(struct stable_node *dup) +static inline void __stable_node_dup_del(struct ksm_stable_node *dup) { VM_BUG_ON(!is_stable_node_dup(dup)); hlist_del(&dup->hlist_dup); ksm_stable_node_dups--; } -static inline void stable_node_dup_del(struct stable_node *dup) +static inline void stable_node_dup_del(struct ksm_stable_node *dup) { VM_BUG_ON(is_stable_node_chain(dup)); if (is_stable_node_dup(dup)) @@ -355,9 +558,9 @@ static inline void stable_node_dup_del(struct stable_node *dup) #endif } -static inline struct rmap_item *alloc_rmap_item(void) +static inline struct ksm_rmap_item *alloc_rmap_item(void) { - struct rmap_item *rmap_item; + struct ksm_rmap_item *rmap_item; rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); @@ -366,14 +569,15 @@ static inline struct rmap_item *alloc_rmap_item(void) return rmap_item; } -static inline void free_rmap_item(struct rmap_item *rmap_item) +static inline void free_rmap_item(struct ksm_rmap_item *rmap_item) { ksm_rmap_items--; + rmap_item->mm->ksm_rmap_items--; rmap_item->mm = NULL; /* debug safety */ kmem_cache_free(rmap_item_cache, rmap_item); } -static inline struct stable_node *alloc_stable_node(void) +static inline struct ksm_stable_node *alloc_stable_node(void) { /* * The allocation can take too long with GFP_KERNEL when memory is under @@ -383,47 +587,17 @@ static inline struct stable_node *alloc_stable_node(void) return kmem_cache_alloc(stable_node_cache, GFP_KERNEL | __GFP_HIGH); } -static inline void free_stable_node(struct stable_node *stable_node) +static inline void free_stable_node(struct ksm_stable_node *stable_node) { VM_BUG_ON(stable_node->rmap_hlist_len && !is_stable_node_chain(stable_node)); kmem_cache_free(stable_node_cache, stable_node); } -static inline struct mm_slot *alloc_mm_slot(void) -{ - if (!mm_slot_cache) /* initialization failed */ - return NULL; - return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL); -} - -static inline void free_mm_slot(struct mm_slot *mm_slot) -{ - kmem_cache_free(mm_slot_cache, mm_slot); -} - -static struct mm_slot *get_mm_slot(struct mm_struct *mm) -{ - struct mm_slot *slot; - - hash_for_each_possible(mm_slots_hash, slot, link, (unsigned long)mm) - if (slot->mm == mm) - return slot; - - return NULL; -} - -static void insert_to_mm_slots_hash(struct mm_struct *mm, - struct mm_slot *mm_slot) -{ - mm_slot->mm = mm; - hash_add(mm_slots_hash, &mm_slot->link, (unsigned long)mm); -} - /* * ksmd, and unmerge_and_remove_all_rmap_items(), must not touch an mm's * page tables after it has passed through ksm_exit() - which, if necessary, - * takes mmap_sem briefly to serialize against them. ksm_exit() does not set + * takes mmap_lock briefly to serialize against them. ksm_exit() does not set * a special flag: they can just back out as soon as mm_users goes to zero. * ksm_test_exit() is used throughout to make this test for exit: in some * places for correctness, in some places just to avoid unnecessary work. @@ -433,50 +607,114 @@ static inline bool ksm_test_exit(struct mm_struct *mm) return atomic_read(&mm->mm_users) == 0; } +static int break_ksm_pmd_entry(pmd_t *pmdp, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + unsigned long *found_addr = (unsigned long *) walk->private; + struct mm_struct *mm = walk->mm; + pte_t *start_ptep, *ptep; + spinlock_t *ptl; + int found = 0; + + if (ksm_test_exit(walk->mm)) + return 0; + if (signal_pending(current)) + return -ERESTARTSYS; + + start_ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); + if (!start_ptep) + return 0; + + for (ptep = start_ptep; addr < end; ptep++, addr += PAGE_SIZE) { + pte_t pte = ptep_get(ptep); + struct folio *folio = NULL; + + if (pte_present(pte)) { + folio = vm_normal_folio(walk->vma, addr, pte); + } else if (!pte_none(pte)) { + const softleaf_t entry = softleaf_from_pte(pte); + + /* + * As KSM pages remain KSM pages until freed, no need to wait + * here for migration to end. + */ + if (softleaf_is_migration(entry)) + folio = softleaf_to_folio(entry); + } + /* return 1 if the page is an normal ksm page or KSM-placed zero page */ + found = (folio && folio_test_ksm(folio)) || + (pte_present(pte) && is_ksm_zero_pte(pte)); + if (found) { + *found_addr = addr; + goto out_unlock; + } + } +out_unlock: + pte_unmap_unlock(ptep, ptl); + return found; +} + +static const struct mm_walk_ops break_ksm_ops = { + .pmd_entry = break_ksm_pmd_entry, + .walk_lock = PGWALK_RDLOCK, +}; + +static const struct mm_walk_ops break_ksm_lock_vma_ops = { + .pmd_entry = break_ksm_pmd_entry, + .walk_lock = PGWALK_WRLOCK, +}; + /* - * We use break_ksm to break COW on a ksm page: it's a stripped down + * Though it's very tempting to unmerge rmap_items from stable tree rather + * than check every pte of a given vma, the locking doesn't quite work for + * that - an rmap_item is assigned to the stable tree after inserting ksm + * page and upping mmap_lock. Nor does it fit with the way we skip dup'ing + * rmap_items from parent to child at fork time (so as not to waste time + * if exit comes before the next scan reaches it). * - * if (get_user_pages(addr, 1, 1, 1, &page, NULL) == 1) - * put_page(page); + * Similarly, although we'd like to remove rmap_items (so updating counts + * and freeing memory) when unmerging an area, it's easier to leave that + * to the next pass of ksmd - consider, for example, how ksmd might be + * in cmp_and_merge_page on one of the rmap_items we would be removing. + * + * We use break_ksm to break COW on a ksm page by triggering unsharing, + * such that the ksm page will get replaced by an exclusive anonymous page. * - * but taking great care only to touch a ksm page, in a VM_MERGEABLE vma, + * We take great care only to touch a ksm page, in a VM_MERGEABLE vma, * in case the application has unmapped and remapped mm,addr meanwhile. * Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP - * mmap of /dev/mem or /dev/kmem, where we would not want to touch it. + * mmap of /dev/mem, where we would not want to touch it. * - * FAULT_FLAG/FOLL_REMOTE are because we do this outside the context + * FAULT_FLAG_REMOTE/FOLL_REMOTE are because we do this outside the context * of the process that owns 'vma'. We also do not want to enforce * protection keys here anyway. */ -static int break_ksm(struct vm_area_struct *vma, unsigned long addr) +static int break_ksm(struct vm_area_struct *vma, unsigned long addr, + unsigned long end, bool lock_vma) { - struct page *page; - int ret = 0; + vm_fault_t ret = 0; + const struct mm_walk_ops *ops = lock_vma ? + &break_ksm_lock_vma_ops : &break_ksm_ops; do { + int ksm_page; + cond_resched(); - page = follow_page(vma, addr, - FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE); - if (IS_ERR_OR_NULL(page)) - break; - if (PageKsm(page)) - ret = handle_mm_fault(vma, addr, - FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE); - else - ret = VM_FAULT_WRITE; - put_page(page); - } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); + ksm_page = walk_page_range_vma(vma, addr, end, ops, &addr); + if (ksm_page <= 0) + return ksm_page; + ret = handle_mm_fault(vma, addr, + FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE, + NULL); + } while (!(ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); /* - * We must loop because handle_mm_fault() may back out if there's - * any difficulty e.g. if pte accessed bit gets updated concurrently. - * - * VM_FAULT_WRITE is what we have been hoping for: it indicates that - * COW has been broken, even if the vma does not permit VM_WRITE; - * but note that a concurrent fault might break PageKsm for us. + * We must loop until we no longer find a KSM page because + * handle_mm_fault() may back out if there's any difficulty e.g. if + * pte accessed bit gets updated concurrently. * * VM_FAULT_SIGBUS could occur if we race with truncation of the * backing file, which also invalidates anonymous pages: that's - * okay, that truncation will have unmapped the PageKsm for us. + * okay, that truncation will have unmapped the KSM page for us. * * VM_FAULT_OOM: at the time of writing (late July 2009), setting * aside mem_cgroup limits, VM_FAULT_OOM would only be set if the @@ -497,21 +735,45 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) return (ret & VM_FAULT_OOM) ? -ENOMEM : 0; } +static bool ksm_compatible(const struct file *file, vm_flags_t vm_flags) +{ + if (vm_flags & (VM_SHARED | VM_MAYSHARE | VM_SPECIAL | + VM_HUGETLB | VM_DROPPABLE)) + return false; /* just ignore the advice */ + + if (file_is_dax(file)) + return false; + +#ifdef VM_SAO + if (vm_flags & VM_SAO) + return false; +#endif +#ifdef VM_SPARC_ADI + if (vm_flags & VM_SPARC_ADI) + return false; +#endif + + return true; +} + +static bool vma_ksm_compatible(struct vm_area_struct *vma) +{ + return ksm_compatible(vma->vm_file, vma->vm_flags); +} + static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma; if (ksm_test_exit(mm)) return NULL; - vma = find_vma(mm, addr); - if (!vma || vma->vm_start > addr) - return NULL; - if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) + vma = vma_lookup(mm, addr); + if (!vma || !(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) return NULL; return vma; } -static void break_cow(struct rmap_item *rmap_item) +static void break_cow(struct ksm_rmap_item *rmap_item) { struct mm_struct *mm = rmap_item->mm; unsigned long addr = rmap_item->address; @@ -523,37 +785,42 @@ static void break_cow(struct rmap_item *rmap_item) */ put_anon_vma(rmap_item->anon_vma); - down_read(&mm->mmap_sem); + mmap_read_lock(mm); vma = find_mergeable_vma(mm, addr); if (vma) - break_ksm(vma, addr); - up_read(&mm->mmap_sem); + break_ksm(vma, addr, addr + PAGE_SIZE, false); + mmap_read_unlock(mm); } -static struct page *get_mergeable_page(struct rmap_item *rmap_item) +static struct page *get_mergeable_page(struct ksm_rmap_item *rmap_item) { struct mm_struct *mm = rmap_item->mm; unsigned long addr = rmap_item->address; struct vm_area_struct *vma; - struct page *page; + struct page *page = NULL; + struct folio_walk fw; + struct folio *folio; - down_read(&mm->mmap_sem); + mmap_read_lock(mm); vma = find_mergeable_vma(mm, addr); if (!vma) goto out; - page = follow_page(vma, addr, FOLL_GET); - if (IS_ERR_OR_NULL(page)) - goto out; - if (PageAnon(page)) { + folio = folio_walk_start(&fw, vma, addr, 0); + if (folio) { + if (!folio_is_zone_device(folio) && + folio_test_anon(folio)) { + folio_get(folio); + page = fw.page; + } + folio_walk_end(&fw, vma); + } +out: + if (page) { flush_anon_page(vma, page, addr); flush_dcache_page(page); - } else { - put_page(page); -out: - page = NULL; } - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); return page; } @@ -568,17 +835,17 @@ static inline int get_kpfn_nid(unsigned long kpfn) return ksm_merge_across_nodes ? 0 : NUMA(pfn_to_nid(kpfn)); } -static struct stable_node *alloc_stable_node_chain(struct stable_node *dup, +static struct ksm_stable_node *alloc_stable_node_chain(struct ksm_stable_node *dup, struct rb_root *root) { - struct stable_node *chain = alloc_stable_node(); + struct ksm_stable_node *chain = alloc_stable_node(); VM_BUG_ON(is_stable_node_chain(dup)); if (likely(chain)) { INIT_HLIST_HEAD(&chain->hlist); chain->chain_prune_time = jiffies; chain->rmap_hlist_len = STABLE_NODE_CHAIN; #if defined (CONFIG_DEBUG_VM) && defined(CONFIG_NUMA) - chain->nid = -1; /* debug */ + chain->nid = NUMA_NO_NODE; /* debug */ #endif ksm_stable_node_chains++; @@ -593,7 +860,7 @@ static struct stable_node *alloc_stable_node_chain(struct stable_node *dup, * Move the old stable node to the second dimension * queued in the hlist_dup. The invariant is that all * dup stable_nodes in the chain->hlist point to pages - * that are wrprotected and have the exact same + * that are write protected and have the exact same * content. */ stable_node_chain_add_dup(dup, chain); @@ -601,7 +868,7 @@ static struct stable_node *alloc_stable_node_chain(struct stable_node *dup, return chain; } -static inline void free_stable_node_chain(struct stable_node *chain, +static inline void free_stable_node_chain(struct ksm_stable_node *chain, struct rb_root *root) { rb_erase(&chain->node, root); @@ -609,18 +876,23 @@ static inline void free_stable_node_chain(struct stable_node *chain, ksm_stable_node_chains--; } -static void remove_node_from_stable_tree(struct stable_node *stable_node) +static void remove_node_from_stable_tree(struct ksm_stable_node *stable_node) { - struct rmap_item *rmap_item; + struct ksm_rmap_item *rmap_item; /* check it's not STABLE_NODE_CHAIN or negative */ BUG_ON(stable_node->rmap_hlist_len < 0); hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { - if (rmap_item->hlist.next) + if (rmap_item->hlist.next) { ksm_pages_sharing--; - else + trace_ksm_remove_rmap_item(stable_node->kpfn, rmap_item, rmap_item->mm); + } else { ksm_pages_shared--; + } + + rmap_item->mm->ksm_merging_pages--; + VM_BUG_ON(stable_node->rmap_hlist_len <= 0); stable_node->rmap_hlist_len--; put_anon_vma(rmap_item->anon_vma); @@ -633,13 +905,12 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node) * list_head to stay clear from the rb_parent_color union * (aligned and different than any node) and also different * from &migrate_nodes. This will verify that future list.h changes - * don't break STABLE_NODE_DUP_HEAD. + * don't break STABLE_NODE_DUP_HEAD. Only recent gcc can handle it. */ -#if GCC_VERSION >= 40903 /* only recent gcc can handle it */ BUILD_BUG_ON(STABLE_NODE_DUP_HEAD <= &migrate_nodes); BUILD_BUG_ON(STABLE_NODE_DUP_HEAD >= &migrate_nodes + 1); -#endif + trace_ksm_remove_ksm_page(stable_node->kpfn); if (stable_node->head == &migrate_nodes) list_del(&stable_node->list); else @@ -647,8 +918,14 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node) free_stable_node(stable_node); } +enum ksm_get_folio_flags { + KSM_GET_FOLIO_NOLOCK, + KSM_GET_FOLIO_LOCK, + KSM_GET_FOLIO_TRYLOCK +}; + /* - * get_ksm_page: checks if the page indicated by the stable node + * ksm_get_folio: checks if the page indicated by the stable node * is still its ksm page, despite having held no reference to it. * In which case we can trust the content of the page, and it * returns the gotten page; but if the page has now been zapped, @@ -666,70 +943,73 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node) * a page to put something that might look like our key in page->mapping. * is on its way to being freed; but it is an anomaly to bear in mind. */ -static struct page *get_ksm_page(struct stable_node *stable_node, bool lock_it) +static struct folio *ksm_get_folio(struct ksm_stable_node *stable_node, + enum ksm_get_folio_flags flags) { - struct page *page; + struct folio *folio; void *expected_mapping; unsigned long kpfn; expected_mapping = (void *)((unsigned long)stable_node | - PAGE_MAPPING_KSM); + FOLIO_MAPPING_KSM); again: - kpfn = READ_ONCE(stable_node->kpfn); - page = pfn_to_page(kpfn); - - /* - * page is computed from kpfn, so on most architectures reading - * page->mapping is naturally ordered after reading node->kpfn, - * but on Alpha we need to be more careful. - */ - smp_read_barrier_depends(); - if (READ_ONCE(page->mapping) != expected_mapping) + kpfn = READ_ONCE(stable_node->kpfn); /* Address dependency. */ + folio = pfn_folio(kpfn); + if (READ_ONCE(folio->mapping) != expected_mapping) goto stale; /* * We cannot do anything with the page while its refcount is 0. * Usually 0 means free, or tail of a higher-order page: in which * case this node is no longer referenced, and should be freed; - * however, it might mean that the page is under page_freeze_refs(). + * however, it might mean that the page is under page_ref_freeze(). * The __remove_mapping() case is easy, again the node is now stale; - * but if page is swapcache in migrate_page_move_mapping(), it might - * still be our page, in which case it's essential to keep the node. + * the same is in reuse_ksm_page() case; but if page is swapcache + * in folio_migrate_mapping(), it might still be our page, + * in which case it's essential to keep the node. */ - while (!get_page_unless_zero(page)) { + while (!folio_try_get(folio)) { /* - * Another check for page->mapping != expected_mapping would - * work here too. We have chosen the !PageSwapCache test to - * optimize the common case, when the page is or is about to - * be freed: PageSwapCache is cleared (under spin_lock_irq) - * in the freeze_refs section of __remove_mapping(); but Anon - * page->mapping reset to NULL later, in free_pages_prepare(). + * Another check for folio->mapping != expected_mapping + * would work here too. We have chosen to test the + * swapcache flag to optimize the common case, when the + * folio is or is about to be freed: the swapcache flag + * is cleared (under spin_lock_irq) in the ref_freeze + * section of __remove_mapping(); but anon folio->mapping + * is reset to NULL later, in free_pages_prepare(). */ - if (!PageSwapCache(page)) + if (!folio_test_swapcache(folio)) goto stale; cpu_relax(); } - if (READ_ONCE(page->mapping) != expected_mapping) { - put_page(page); + if (READ_ONCE(folio->mapping) != expected_mapping) { + folio_put(folio); goto stale; } - if (lock_it) { - lock_page(page); - if (READ_ONCE(page->mapping) != expected_mapping) { - unlock_page(page); - put_page(page); + if (flags == KSM_GET_FOLIO_TRYLOCK) { + if (!folio_trylock(folio)) { + folio_put(folio); + return ERR_PTR(-EBUSY); + } + } else if (flags == KSM_GET_FOLIO_LOCK) + folio_lock(folio); + + if (flags != KSM_GET_FOLIO_NOLOCK) { + if (READ_ONCE(folio->mapping) != expected_mapping) { + folio_unlock(folio); + folio_put(folio); goto stale; } } - return page; + return folio; stale: /* - * We come here from above when page->mapping or !PageSwapCache + * We come here from above when folio->mapping or the swapcache flag * suggests that the node is stale; but it might be under migration. - * We need smp_rmb(), matching the smp_wmb() in ksm_migrate_page(), + * We need smp_rmb(), matching the smp_wmb() in folio_migrate_ksm(), * before checking whether node->kpfn has been changed. */ smp_rmb(); @@ -743,29 +1023,33 @@ stale: * Removing rmap_item from stable or unstable tree. * This function will clean the information from the stable/unstable tree. */ -static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) +static void remove_rmap_item_from_tree(struct ksm_rmap_item *rmap_item) { if (rmap_item->address & STABLE_FLAG) { - struct stable_node *stable_node; - struct page *page; + struct ksm_stable_node *stable_node; + struct folio *folio; stable_node = rmap_item->head; - page = get_ksm_page(stable_node, true); - if (!page) + folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_LOCK); + if (!folio) goto out; hlist_del(&rmap_item->hlist); - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (!hlist_empty(&stable_node->hlist)) ksm_pages_sharing--; else ksm_pages_shared--; + + rmap_item->mm->ksm_merging_pages--; + VM_BUG_ON(stable_node->rmap_hlist_len <= 0); stable_node->rmap_hlist_len--; put_anon_vma(rmap_item->anon_vma); + rmap_item->head = NULL; rmap_item->address &= PAGE_MASK; } else if (rmap_item->address & UNSTABLE_FLAG) { @@ -789,93 +1073,75 @@ out: cond_resched(); /* we're called from many long loops */ } -static void remove_trailing_rmap_items(struct mm_slot *mm_slot, - struct rmap_item **rmap_list) +static void remove_trailing_rmap_items(struct ksm_rmap_item **rmap_list) { while (*rmap_list) { - struct rmap_item *rmap_item = *rmap_list; + struct ksm_rmap_item *rmap_item = *rmap_list; *rmap_list = rmap_item->rmap_list; remove_rmap_item_from_tree(rmap_item); free_rmap_item(rmap_item); } } -/* - * Though it's very tempting to unmerge rmap_items from stable tree rather - * than check every pte of a given vma, the locking doesn't quite work for - * that - an rmap_item is assigned to the stable tree after inserting ksm - * page and upping mmap_sem. Nor does it fit with the way we skip dup'ing - * rmap_items from parent to child at fork time (so as not to waste time - * if exit comes before the next scan reaches it). - * - * Similarly, although we'd like to remove rmap_items (so updating counts - * and freeing memory) when unmerging an area, it's easier to leave that - * to the next pass of ksmd - consider, for example, how ksmd might be - * in cmp_and_merge_page on one of the rmap_items we would be removing. - */ -static int unmerge_ksm_pages(struct vm_area_struct *vma, - unsigned long start, unsigned long end) +static inline +struct ksm_stable_node *folio_stable_node(const struct folio *folio) { - unsigned long addr; - int err = 0; + return folio_test_ksm(folio) ? folio_raw_mapping(folio) : NULL; +} - for (addr = start; addr < end && !err; addr += PAGE_SIZE) { - if (ksm_test_exit(vma->vm_mm)) - break; - if (signal_pending(current)) - err = -ERESTARTSYS; - else - err = break_ksm(vma, addr); - } - return err; +static inline void folio_set_stable_node(struct folio *folio, + struct ksm_stable_node *stable_node) +{ + VM_WARN_ON_FOLIO(folio_test_anon(folio) && PageAnonExclusive(&folio->page), folio); + folio->mapping = (void *)((unsigned long)stable_node | FOLIO_MAPPING_KSM); } #ifdef CONFIG_SYSFS /* * Only called through the sysfs control interface: */ -static int remove_stable_node(struct stable_node *stable_node) +static int remove_stable_node(struct ksm_stable_node *stable_node) { - struct page *page; + struct folio *folio; int err; - page = get_ksm_page(stable_node, true); - if (!page) { + folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_LOCK); + if (!folio) { /* - * get_ksm_page did remove_node_from_stable_tree itself. + * ksm_get_folio did remove_node_from_stable_tree itself. */ return 0; } - if (WARN_ON_ONCE(page_mapped(page))) { - /* - * This should not happen: but if it does, just refuse to let - * merge_across_nodes be switched - there is no need to panic. - */ - err = -EBUSY; - } else { + /* + * Page could be still mapped if this races with __mmput() running in + * between ksm_exit() and exit_mmap(). Just refuse to let + * merge_across_nodes/max_page_sharing be switched. + */ + err = -EBUSY; + if (!folio_mapped(folio)) { /* - * The stable node did not yet appear stale to get_ksm_page(), - * since that allows for an unmapped ksm page to be recognized + * The stable node did not yet appear stale to ksm_get_folio(), + * since that allows for an unmapped ksm folio to be recognized * right up until it is freed; but the node is safe to remove. - * This page might be in a pagevec waiting to be freed, - * or it might be PageSwapCache (perhaps under writeback), + * This folio might be in an LRU cache waiting to be freed, + * or it might be in the swapcache (perhaps under writeback), * or it might have been removed from swapcache a moment ago. */ - set_page_stable_node(page, NULL); + folio_set_stable_node(folio, NULL); remove_node_from_stable_tree(stable_node); err = 0; } - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return err; } -static int remove_stable_node_chain(struct stable_node *stable_node, +static int remove_stable_node_chain(struct ksm_stable_node *stable_node, struct rb_root *root) { - struct stable_node *dup; + struct ksm_stable_node *dup; struct hlist_node *hlist_safe; if (!is_stable_node_chain(stable_node)) { @@ -899,14 +1165,14 @@ static int remove_stable_node_chain(struct stable_node *stable_node, static int remove_all_stable_nodes(void) { - struct stable_node *stable_node, *next; + struct ksm_stable_node *stable_node, *next; int nid; int err = 0; for (nid = 0; nid < ksm_nr_node_ids; nid++) { while (root_stable_tree[nid].rb_node) { stable_node = rb_entry(root_stable_tree[nid].rb_node, - struct stable_node, node); + struct ksm_stable_node, node); if (remove_stable_node_chain(stable_node, root_stable_tree + nid)) { err = -EBUSY; @@ -925,44 +1191,56 @@ static int remove_all_stable_nodes(void) static int unmerge_and_remove_all_rmap_items(void) { - struct mm_slot *mm_slot; + struct ksm_mm_slot *mm_slot; + struct mm_slot *slot; struct mm_struct *mm; struct vm_area_struct *vma; int err = 0; spin_lock(&ksm_mmlist_lock); - ksm_scan.mm_slot = list_entry(ksm_mm_head.mm_list.next, - struct mm_slot, mm_list); + slot = list_entry(ksm_mm_head.slot.mm_node.next, + struct mm_slot, mm_node); + ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); spin_unlock(&ksm_mmlist_lock); - for (mm_slot = ksm_scan.mm_slot; - mm_slot != &ksm_mm_head; mm_slot = ksm_scan.mm_slot) { - mm = mm_slot->mm; - down_read(&mm->mmap_sem); - for (vma = mm->mmap; vma; vma = vma->vm_next) { - if (ksm_test_exit(mm)) - break; + for (mm_slot = ksm_scan.mm_slot; mm_slot != &ksm_mm_head; + mm_slot = ksm_scan.mm_slot) { + VMA_ITERATOR(vmi, mm_slot->slot.mm, 0); + + mm = mm_slot->slot.mm; + mmap_read_lock(mm); + + /* + * Exit right away if mm is exiting to avoid lockdep issue in + * the maple tree + */ + if (ksm_test_exit(mm)) + goto mm_exiting; + + for_each_vma(vmi, vma) { if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) continue; - err = unmerge_ksm_pages(vma, - vma->vm_start, vma->vm_end); + err = break_ksm(vma, vma->vm_start, vma->vm_end, false); if (err) goto error; } - remove_trailing_rmap_items(mm_slot, &mm_slot->rmap_list); - up_read(&mm->mmap_sem); +mm_exiting: + remove_trailing_rmap_items(&mm_slot->rmap_list); + mmap_read_unlock(mm); spin_lock(&ksm_mmlist_lock); - ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next, - struct mm_slot, mm_list); + slot = list_entry(mm_slot->slot.mm_node.next, + struct mm_slot, mm_node); + ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); if (ksm_test_exit(mm)) { - hash_del(&mm_slot->link); - list_del(&mm_slot->mm_list); + hash_del(&mm_slot->slot.hash); + list_del(&mm_slot->slot.mm_node); spin_unlock(&ksm_mmlist_lock); - free_mm_slot(mm_slot); - clear_bit(MMF_VM_MERGEABLE, &mm->flags); + mm_slot_free(mm_slot_cache, mm_slot); + mm_flags_clear(MMF_VM_MERGEABLE, mm); + mm_flags_clear(MMF_VM_MERGE_ANY, mm); mmdrop(mm); } else spin_unlock(&ksm_mmlist_lock); @@ -974,7 +1252,7 @@ static int unmerge_and_remove_all_rmap_items(void) return 0; error: - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); spin_lock(&ksm_mmlist_lock); ksm_scan.mm_slot = &ksm_mm_head; spin_unlock(&ksm_mmlist_lock); @@ -985,98 +1263,99 @@ error: static u32 calc_checksum(struct page *page) { u32 checksum; - void *addr = kmap_atomic(page); - checksum = jhash2(addr, PAGE_SIZE / 4, 17); - kunmap_atomic(addr); + void *addr = kmap_local_page(page); + checksum = xxhash(addr, PAGE_SIZE, 0); + kunmap_local(addr); return checksum; } -static int memcmp_pages(struct page *page1, struct page *page2) -{ - char *addr1, *addr2; - int ret; - - addr1 = kmap_atomic(page1); - addr2 = kmap_atomic(page2); - ret = memcmp(addr1, addr2, PAGE_SIZE); - kunmap_atomic(addr2); - kunmap_atomic(addr1); - return ret; -} - -static inline int pages_identical(struct page *page1, struct page *page2) -{ - return !memcmp_pages(page1, page2); -} - -static int write_protect_page(struct vm_area_struct *vma, struct page *page, +static int write_protect_page(struct vm_area_struct *vma, struct folio *folio, pte_t *orig_pte) { struct mm_struct *mm = vma->vm_mm; - struct page_vma_mapped_walk pvmw = { - .page = page, - .vma = vma, - }; + DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, 0, 0); int swapped; int err = -EFAULT; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ + struct mmu_notifier_range range; + bool anon_exclusive; + pte_t entry; - pvmw.address = page_address_in_vma(page, vma); + if (WARN_ON_ONCE(folio_test_large(folio))) + return err; + + pvmw.address = page_address_in_vma(folio, folio_page(folio, 0), vma); if (pvmw.address == -EFAULT) goto out; - BUG_ON(PageTransCompound(page)); - - mmun_start = pvmw.address; - mmun_end = pvmw.address + PAGE_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, pvmw.address, + pvmw.address + PAGE_SIZE); + mmu_notifier_invalidate_range_start(&range); if (!page_vma_mapped_walk(&pvmw)) goto out_mn; if (WARN_ONCE(!pvmw.pte, "Unexpected PMD mapping?")) goto out_unlock; - if (pte_write(*pvmw.pte) || pte_dirty(*pvmw.pte) || - (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte))) { - pte_t entry; + entry = ptep_get(pvmw.pte); + /* + * Handle PFN swap PTEs, such as device-exclusive ones, that actually + * map pages: give up just like the next folio_walk would. + */ + if (unlikely(!pte_present(entry))) + goto out_unlock; - swapped = PageSwapCache(page); - flush_cache_page(vma, pvmw.address, page_to_pfn(page)); + anon_exclusive = PageAnonExclusive(&folio->page); + if (pte_write(entry) || pte_dirty(entry) || + anon_exclusive || mm_tlb_flush_pending(mm)) { + swapped = folio_test_swapcache(folio); + flush_cache_page(vma, pvmw.address, folio_pfn(folio)); /* * Ok this is tricky, when get_user_pages_fast() run it doesn't * take any lock, therefore the check that we are going to make - * with the pagecount against the mapcount is racey and + * with the pagecount against the mapcount is racy and * O_DIRECT can happen right after the check. * So we clear the pte and flush the tlb before the check * this assure us that no O_DIRECT can happen after the check * or in the middle of the check. + * + * No need to notify as we are downgrading page table to read + * only not changing it to point to a new page. + * + * See Documentation/mm/mmu_notifier.rst */ - entry = ptep_clear_flush_notify(vma, pvmw.address, pvmw.pte); + entry = ptep_clear_flush(vma, pvmw.address, pvmw.pte); /* * Check that no O_DIRECT or similar I/O is in progress on the * page */ - if (page_mapcount(page) + 1 + swapped != page_count(page)) { + if (folio_mapcount(folio) + 1 + swapped != folio_ref_count(folio)) { + set_pte_at(mm, pvmw.address, pvmw.pte, entry); + goto out_unlock; + } + + /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ + if (anon_exclusive && + folio_try_share_anon_rmap_pte(folio, &folio->page)) { set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; } + if (pte_dirty(entry)) - set_page_dirty(page); + folio_mark_dirty(folio); + entry = pte_mkclean(entry); - if (pte_protnone(entry)) - entry = pte_mkclean(pte_clear_savedwrite(entry)); - else - entry = pte_mkclean(pte_wrprotect(entry)); - set_pte_at_notify(mm, pvmw.address, pvmw.pte, entry); + if (pte_write(entry)) + entry = pte_wrprotect(entry); + + set_pte_at(mm, pvmw.address, pvmw.pte, entry); } - *orig_pte = *pvmw.pte; + *orig_pte = entry; err = 0; out_unlock: page_vma_mapped_walk_done(&pvmw); out_mn: - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + mmu_notifier_invalidate_range_end(&range); out: return err; } @@ -1093,60 +1372,93 @@ out: static int replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage, pte_t orig_pte) { + struct folio *kfolio = page_folio(kpage); struct mm_struct *mm = vma->vm_mm; + struct folio *folio = page_folio(page); pmd_t *pmd; + pmd_t pmde; pte_t *ptep; pte_t newpte; spinlock_t *ptl; unsigned long addr; int err = -EFAULT; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ + struct mmu_notifier_range range; - addr = page_address_in_vma(page, vma); + addr = page_address_in_vma(folio, page, vma); if (addr == -EFAULT) goto out; pmd = mm_find_pmd(mm, addr); if (!pmd) goto out; + /* + * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at() + * without holding anon_vma lock for write. So when looking for a + * genuine pmde (in which to find pte), test present and !THP together. + */ + pmde = pmdp_get_lockless(pmd); + if (!pmd_present(pmde) || pmd_trans_huge(pmde)) + goto out; - mmun_start = addr; - mmun_end = addr + PAGE_SIZE; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, + addr + PAGE_SIZE); + mmu_notifier_invalidate_range_start(&range); ptep = pte_offset_map_lock(mm, pmd, addr, &ptl); - if (!pte_same(*ptep, orig_pte)) { + if (!ptep) + goto out_mn; + if (!pte_same(ptep_get(ptep), orig_pte)) { pte_unmap_unlock(ptep, ptl); goto out_mn; } + VM_BUG_ON_PAGE(PageAnonExclusive(page), page); + VM_BUG_ON_FOLIO(folio_test_anon(kfolio) && PageAnonExclusive(kpage), + kfolio); /* * No need to check ksm_use_zero_pages here: we can only have a - * zero_page here if ksm_use_zero_pages was enabled alreaady. + * zero_page here if ksm_use_zero_pages was enabled already. */ if (!is_zero_pfn(page_to_pfn(kpage))) { - get_page(kpage); - page_add_anon_rmap(kpage, vma, addr, false); + folio_get(kfolio); + folio_add_anon_rmap_pte(kfolio, kpage, vma, addr, RMAP_NONE); newpte = mk_pte(kpage, vma->vm_page_prot); } else { - newpte = pte_mkspecial(pfn_pte(page_to_pfn(kpage), - vma->vm_page_prot)); + /* + * Use pte_mkdirty to mark the zero page mapped by KSM, and then + * we can easily track all KSM-placed zero pages by checking if + * the dirty bit in zero page's PTE is set. + */ + newpte = pte_mkdirty(pte_mkspecial(pfn_pte(page_to_pfn(kpage), vma->vm_page_prot))); + ksm_map_zero_page(mm); + /* + * We're replacing an anonymous page with a zero page, which is + * not anonymous. We need to do proper accounting otherwise we + * will get wrong values in /proc, and a BUG message in dmesg + * when tearing down the mm. + */ + dec_mm_counter(mm, MM_ANONPAGES); } - flush_cache_page(vma, addr, pte_pfn(*ptep)); - ptep_clear_flush_notify(vma, addr, ptep); - set_pte_at_notify(mm, addr, ptep, newpte); + flush_cache_page(vma, addr, pte_pfn(ptep_get(ptep))); + /* + * No need to notify as we are replacing a read only page with another + * read only page with the same content. + * + * See Documentation/mm/mmu_notifier.rst + */ + ptep_clear_flush(vma, addr, ptep); + set_pte_at(mm, addr, ptep, newpte); - page_remove_rmap(page, false); - if (!page_mapped(page)) - try_to_free_swap(page); - put_page(page); + folio_remove_rmap_pte(folio, page, vma); + if (!folio_mapped(folio)) + folio_free_swap(folio); + folio_put(folio); pte_unmap_unlock(ptep, ptl); err = 0; out_mn: - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + mmu_notifier_invalidate_range_end(&range); out: return err; } @@ -1155,7 +1467,7 @@ out: * try_to_merge_one_page - take two pages and merge them into one * @vma: the vma that holds the pte pointing to page * @page: the PageAnon page that we want to replace with kpage - * @kpage: the PageKsm page that we want to map instead of page, + * @kpage: the KSM page that we want to map instead of page, * or NULL the first time when we want to use page as kpage. * * This function returns 0 if the pages were merged, -EFAULT otherwise. @@ -1163,28 +1475,29 @@ out: static int try_to_merge_one_page(struct vm_area_struct *vma, struct page *page, struct page *kpage) { + struct folio *folio = page_folio(page); pte_t orig_pte = __pte(0); int err = -EFAULT; if (page == kpage) /* ksm page forked */ return 0; - if (!PageAnon(page)) + if (!folio_test_anon(folio)) goto out; /* - * We need the page lock to read a stable PageSwapCache in - * write_protect_page(). We use trylock_page() instead of - * lock_page() because we don't want to wait here - we - * prefer to continue scanning and merging different pages, - * then come back to this page when it is unlocked. + * We need the folio lock to read a stable swapcache flag in + * write_protect_page(). We trylock because we don't want to wait + * here - we prefer to continue scanning and merging different + * pages, then come back to this page when it is unlocked. */ - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto out; - if (PageTransCompound(page)) { + if (folio_test_large(folio)) { if (split_huge_page(page)) goto out_unlock; + folio = page_folio(page); } /* @@ -1193,39 +1506,67 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, * ptes are necessarily already write-protected. But in either * case, we need to lock and check page_count is not raised. */ - if (write_protect_page(vma, page, &orig_pte) == 0) { + if (write_protect_page(vma, folio, &orig_pte) == 0) { if (!kpage) { /* - * While we hold page lock, upgrade page from - * PageAnon+anon_vma to PageKsm+NULL stable_node: + * While we hold folio lock, upgrade folio from + * anon to a NULL stable_node with the KSM flag set: * stable_tree_insert() will update stable_node. */ - set_page_stable_node(page, NULL); - mark_page_accessed(page); + folio_set_stable_node(folio, NULL); + folio_mark_accessed(folio); /* - * Page reclaim just frees a clean page with no dirty + * Page reclaim just frees a clean folio with no dirty * ptes: make sure that the ksm page would be swapped. */ - if (!PageDirty(page)) - SetPageDirty(page); + if (!folio_test_dirty(folio)) + folio_mark_dirty(folio); err = 0; } else if (pages_identical(page, kpage)) err = replace_page(vma, page, kpage, orig_pte); } - if ((vma->vm_flags & VM_LOCKED) && kpage && !err) { - munlock_vma_page(page); - if (!PageMlocked(kpage)) { - unlock_page(page); - lock_page(kpage); - mlock_vma_page(kpage); - page = kpage; /* for final unlock */ +out_unlock: + folio_unlock(folio); +out: + return err; +} + +/* + * This function returns 0 if the pages were merged or if they are + * no longer merging candidates (e.g., VMA stale), -EFAULT otherwise. + */ +static int try_to_merge_with_zero_page(struct ksm_rmap_item *rmap_item, + struct page *page) +{ + struct mm_struct *mm = rmap_item->mm; + int err = -EFAULT; + + /* + * Same checksum as an empty page. We attempt to merge it with the + * appropriate zero page if the user enabled this via sysfs. + */ + if (ksm_use_zero_pages && (rmap_item->oldchecksum == zero_checksum)) { + struct vm_area_struct *vma; + + mmap_read_lock(mm); + vma = find_mergeable_vma(mm, rmap_item->address); + if (vma) { + err = try_to_merge_one_page(vma, page, + ZERO_PAGE(rmap_item->address)); + trace_ksm_merge_one_page( + page_to_pfn(ZERO_PAGE(rmap_item->address)), + rmap_item, mm, err); + } else { + /* + * If the vma is out of date, we do not need to + * continue. + */ + err = 0; } + mmap_read_unlock(mm); } -out_unlock: - unlock_page(page); -out: return err; } @@ -1235,14 +1576,14 @@ out: * * This function returns 0 if the pages were merged, -EFAULT otherwise. */ -static int try_to_merge_with_ksm_page(struct rmap_item *rmap_item, +static int try_to_merge_with_ksm_page(struct ksm_rmap_item *rmap_item, struct page *page, struct page *kpage) { struct mm_struct *mm = rmap_item->mm; struct vm_area_struct *vma; int err = -EFAULT; - down_read(&mm->mmap_sem); + mmap_read_lock(mm); vma = find_mergeable_vma(mm, rmap_item->address); if (!vma) goto out; @@ -1254,11 +1595,13 @@ static int try_to_merge_with_ksm_page(struct rmap_item *rmap_item, /* Unstable nid is in union with stable anon_vma: remove first */ remove_rmap_item_from_tree(rmap_item); - /* Must get reference to anon_vma while still holding mmap_sem */ + /* Must get reference to anon_vma while still holding mmap_lock */ rmap_item->anon_vma = vma->anon_vma; get_anon_vma(vma->anon_vma); out: - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); + trace_ksm_merge_with_ksm_page(kpage, page_to_pfn(kpage ? kpage : page), + rmap_item, mm, err); return err; } @@ -1272,9 +1615,9 @@ out: * Note that this function upgrades page to ksm page: if one of the pages * is already a ksm page, try_to_merge_with_ksm_page should be used. */ -static struct page *try_to_merge_two_pages(struct rmap_item *rmap_item, +static struct folio *try_to_merge_two_pages(struct ksm_rmap_item *rmap_item, struct page *page, - struct rmap_item *tree_rmap_item, + struct ksm_rmap_item *tree_rmap_item, struct page *tree_page) { int err; @@ -1290,11 +1633,11 @@ static struct page *try_to_merge_two_pages(struct rmap_item *rmap_item, if (err) break_cow(rmap_item); } - return err ? NULL : page; + return err ? NULL : page_folio(page); } static __always_inline -bool __is_page_sharing_candidate(struct stable_node *stable_node, int offset) +bool __is_page_sharing_candidate(struct ksm_stable_node *stable_node, int offset) { VM_BUG_ON(stable_node->rmap_hlist_len < 0); /* @@ -1308,20 +1651,19 @@ bool __is_page_sharing_candidate(struct stable_node *stable_node, int offset) } static __always_inline -bool is_page_sharing_candidate(struct stable_node *stable_node) +bool is_page_sharing_candidate(struct ksm_stable_node *stable_node) { return __is_page_sharing_candidate(stable_node, 0); } -struct page *stable_node_dup(struct stable_node **_stable_node_dup, - struct stable_node **_stable_node, - struct rb_root *root, - bool prune_stale_stable_nodes) +static struct folio *stable_node_dup(struct ksm_stable_node **_stable_node_dup, + struct ksm_stable_node **_stable_node, + struct rb_root *root, + bool prune_stale_stable_nodes) { - struct stable_node *dup, *found = NULL, *stable_node = *_stable_node; + struct ksm_stable_node *dup, *found = NULL, *stable_node = *_stable_node; struct hlist_node *hlist_safe; - struct page *_tree_page, *tree_page = NULL; - int nr = 0; + struct folio *folio, *tree_folio = NULL; int found_rmap_hlist_len; if (!prune_stale_stable_nodes || @@ -1339,42 +1681,35 @@ struct page *stable_node_dup(struct stable_node **_stable_node_dup, * We must walk all stable_node_dup to prune the stale * stable nodes during lookup. * - * get_ksm_page can drop the nodes from the + * ksm_get_folio can drop the nodes from the * stable_node->hlist if they point to freed pages * (that's why we do a _safe walk). The "dup" * stable_node parameter itself will be freed from * under us if it returns NULL. */ - _tree_page = get_ksm_page(dup, false); - if (!_tree_page) + folio = ksm_get_folio(dup, KSM_GET_FOLIO_NOLOCK); + if (!folio) + continue; + /* Pick the best candidate if possible. */ + if (!found || (is_page_sharing_candidate(dup) && + (!is_page_sharing_candidate(found) || + dup->rmap_hlist_len > found_rmap_hlist_len))) { + if (found) + folio_put(tree_folio); + found = dup; + found_rmap_hlist_len = found->rmap_hlist_len; + tree_folio = folio; + /* skip put_page for found candidate */ + if (!prune_stale_stable_nodes && + is_page_sharing_candidate(found)) + break; continue; - nr += 1; - if (is_page_sharing_candidate(dup)) { - if (!found || - dup->rmap_hlist_len > found_rmap_hlist_len) { - if (found) - put_page(tree_page); - found = dup; - found_rmap_hlist_len = found->rmap_hlist_len; - tree_page = _tree_page; - - /* skip put_page for found dup */ - if (!prune_stale_stable_nodes) - break; - continue; - } } - put_page(_tree_page); + folio_put(folio); } if (found) { - /* - * nr is counting all dups in the chain only if - * prune_stale_stable_nodes is true, otherwise we may - * break the loop at nr == 1 even if there are - * multiple entries. - */ - if (prune_stale_stable_nodes && nr == 1) { + if (hlist_is_singular_node(&found->hlist_dup, &stable_node->hlist)) { /* * If there's not just one entry it would * corrupt memory, better BUG_ON. In KSM @@ -1399,7 +1734,7 @@ struct page *stable_node_dup(struct stable_node **_stable_node_dup, */ *_stable_node = found; /* - * Just for robustneess as stable_node is + * Just for robustness, as stable_node is * otherwise left as a stable pointer, the * compiler shall optimize it away at build * time. @@ -1426,27 +1761,17 @@ struct page *stable_node_dup(struct stable_node **_stable_node_dup, hlist_add_head(&found->hlist_dup, &stable_node->hlist); } + } else { + /* Its hlist must be empty if no one found. */ + free_stable_node_chain(stable_node, root); } *_stable_node_dup = found; - return tree_page; -} - -static struct stable_node *stable_node_dup_any(struct stable_node *stable_node, - struct rb_root *root) -{ - if (!is_stable_node_chain(stable_node)) - return stable_node; - if (hlist_empty(&stable_node->hlist)) { - free_stable_node_chain(stable_node, root); - return NULL; - } - return hlist_entry(stable_node->hlist.first, - typeof(*stable_node), hlist_dup); + return tree_folio; } /* - * Like for get_ksm_page, this function can free the *_stable_node and + * Like for ksm_get_folio, this function can free the *_stable_node and * *_stable_node_dup if the returned tree_page is NULL. * * It can also free and overwrite *_stable_node with the found @@ -1459,46 +1784,33 @@ static struct stable_node *stable_node_dup_any(struct stable_node *stable_node, * function and will be overwritten in all cases, the caller doesn't * need to initialize it. */ -static struct page *__stable_node_chain(struct stable_node **_stable_node_dup, - struct stable_node **_stable_node, - struct rb_root *root, - bool prune_stale_stable_nodes) +static struct folio *__stable_node_chain(struct ksm_stable_node **_stable_node_dup, + struct ksm_stable_node **_stable_node, + struct rb_root *root, + bool prune_stale_stable_nodes) { - struct stable_node *stable_node = *_stable_node; + struct ksm_stable_node *stable_node = *_stable_node; + if (!is_stable_node_chain(stable_node)) { - if (is_page_sharing_candidate(stable_node)) { - *_stable_node_dup = stable_node; - return get_ksm_page(stable_node, false); - } - /* - * _stable_node_dup set to NULL means the stable_node - * reached the ksm_max_page_sharing limit. - */ - *_stable_node_dup = NULL; - return NULL; + *_stable_node_dup = stable_node; + return ksm_get_folio(stable_node, KSM_GET_FOLIO_NOLOCK); } return stable_node_dup(_stable_node_dup, _stable_node, root, prune_stale_stable_nodes); } -static __always_inline struct page *chain_prune(struct stable_node **s_n_d, - struct stable_node **s_n, - struct rb_root *root) +static __always_inline struct folio *chain_prune(struct ksm_stable_node **s_n_d, + struct ksm_stable_node **s_n, + struct rb_root *root) { return __stable_node_chain(s_n_d, s_n, root, true); } -static __always_inline struct page *chain(struct stable_node **s_n_d, - struct stable_node *s_n, - struct rb_root *root) +static __always_inline struct folio *chain(struct ksm_stable_node **s_n_d, + struct ksm_stable_node **s_n, + struct rb_root *root) { - struct stable_node *old_stable_node = s_n; - struct page *tree_page; - - tree_page = __stable_node_chain(s_n_d, &s_n, root, false); - /* not pruning dups so s_n cannot have changed */ - VM_BUG_ON(s_n != old_stable_node); - return tree_page; + return __stable_node_chain(s_n_d, s_n, root, false); } /* @@ -1508,78 +1820,43 @@ static __always_inline struct page *chain(struct stable_node **s_n_d, * with identical content to the page that we are scanning right now. * * This function returns the stable tree node of identical content if found, - * NULL otherwise. + * -EBUSY if the stable node's page is being migrated, NULL otherwise. */ -static struct page *stable_tree_search(struct page *page) +static struct folio *stable_tree_search(struct page *page) { int nid; struct rb_root *root; struct rb_node **new; struct rb_node *parent; - struct stable_node *stable_node, *stable_node_dup, *stable_node_any; - struct stable_node *page_node; + struct ksm_stable_node *stable_node, *stable_node_dup; + struct ksm_stable_node *page_node; + struct folio *folio; - page_node = page_stable_node(page); + folio = page_folio(page); + page_node = folio_stable_node(folio); if (page_node && page_node->head != &migrate_nodes) { /* ksm page forked */ - get_page(page); - return page; + folio_get(folio); + return folio; } - nid = get_kpfn_nid(page_to_pfn(page)); + nid = get_kpfn_nid(folio_pfn(folio)); root = root_stable_tree + nid; again: new = &root->rb_node; parent = NULL; while (*new) { - struct page *tree_page; + struct folio *tree_folio; int ret; cond_resched(); - stable_node = rb_entry(*new, struct stable_node, node); - stable_node_any = NULL; - tree_page = chain_prune(&stable_node_dup, &stable_node, root); - /* - * NOTE: stable_node may have been freed by - * chain_prune() if the returned stable_node_dup is - * not NULL. stable_node_dup may have been inserted in - * the rbtree instead as a regular stable_node (in - * order to collapse the stable_node chain if a single - * stable_node dup was found in it). In such case the - * stable_node is overwritten by the calleee to point - * to the stable_node_dup that was collapsed in the - * stable rbtree and stable_node will be equal to - * stable_node_dup like if the chain never existed. - */ - if (!stable_node_dup) { - /* - * Either all stable_node dups were full in - * this stable_node chain, or this chain was - * empty and should be rb_erased. - */ - stable_node_any = stable_node_dup_any(stable_node, - root); - if (!stable_node_any) { - /* rb_erase just run */ - goto again; - } - /* - * Take any of the stable_node dups page of - * this stable_node chain to let the tree walk - * continue. All KSM pages belonging to the - * stable_node dups in a stable_node chain - * have the same content and they're - * wrprotected at all times. Any will work - * fine to continue the walk. - */ - tree_page = get_ksm_page(stable_node_any, false); - } - VM_BUG_ON(!stable_node_dup ^ !!stable_node_any); - if (!tree_page) { + stable_node = rb_entry(*new, struct ksm_stable_node, node); + tree_folio = chain_prune(&stable_node_dup, &stable_node, root); + if (!tree_folio) { /* * If we walked over a stale stable_node, - * get_ksm_page() will call rb_erase() and it + * ksm_get_folio() will call rb_erase() and it * may rebalance the tree from under us. So * restart the search from scratch. Returning * NULL would be safe too, but we'd generate @@ -1589,8 +1866,8 @@ again: goto again; } - ret = memcmp_pages(page, tree_page); - put_page(tree_page); + ret = memcmp_pages(page, &tree_folio->page); + folio_put(tree_folio); parent = *new; if (ret < 0) @@ -1601,16 +1878,19 @@ again: if (page_node) { VM_BUG_ON(page_node->head != &migrate_nodes); /* - * Test if the migrated page should be merged - * into a stable node dup. If the mapcount is - * 1 we can migrate it with another KSM page - * without adding it to the chain. + * If the mapcount of our migrated KSM folio is + * at most 1, we can merge it with another + * KSM folio where we know that we have space + * for one more mapping without exceeding the + * ksm_max_page_sharing limit: see + * chain_prune(). This way, we can avoid adding + * this stable node to the chain. */ - if (page_mapcount(page) > 1) + if (folio_mapcount(folio) > 1) goto chain_append; } - if (!stable_node_dup) { + if (!is_page_sharing_candidate(stable_node_dup)) { /* * If the stable_node is a chain and * we got a payload match in memcmp @@ -1633,21 +1913,26 @@ again: * It would be more elegant to return stable_node * than kpage, but that involves more changes. */ - tree_page = get_ksm_page(stable_node_dup, true); - if (unlikely(!tree_page)) + tree_folio = ksm_get_folio(stable_node_dup, + KSM_GET_FOLIO_TRYLOCK); + + if (PTR_ERR(tree_folio) == -EBUSY) + return ERR_PTR(-EBUSY); + + if (unlikely(!tree_folio)) /* * The tree may have been rebalanced, * so re-evaluate parent and new. */ goto again; - unlock_page(tree_page); + folio_unlock(tree_folio); if (get_kpfn_nid(stable_node_dup->kpfn) != NUMA(stable_node_dup->nid)) { - put_page(tree_page); + folio_put(tree_folio); goto replace; } - return tree_page; + return tree_folio; } } @@ -1660,8 +1945,8 @@ again: rb_insert_color(&page_node->node, root); out: if (is_page_sharing_candidate(page_node)) { - get_page(page); - return page; + folio_get(folio); + return folio; } else return NULL; @@ -1686,12 +1971,12 @@ replace: &page_node->node, root); if (is_page_sharing_candidate(page_node)) - get_page(page); + folio_get(folio); else - page = NULL; + folio = NULL; } else { rb_erase(&stable_node_dup->node, root); - page = NULL; + folio = NULL; } } else { VM_BUG_ON(!is_stable_node_chain(stable_node)); @@ -1702,21 +1987,18 @@ replace: DO_NUMA(page_node->nid = nid); stable_node_chain_add_dup(page_node, stable_node); if (is_page_sharing_candidate(page_node)) - get_page(page); + folio_get(folio); else - page = NULL; + folio = NULL; } else { - page = NULL; + folio = NULL; } } stable_node_dup->head = &migrate_nodes; list_add(&stable_node_dup->list, stable_node_dup->head); - return page; + return folio; chain_append: - /* stable_node_dup could be null if it reached the limit */ - if (!stable_node_dup) - stable_node_dup = stable_node_any; /* * If stable_node was a chain and chain_prune collapsed it, * stable_node has been updated to be the new regular @@ -1726,7 +2008,6 @@ chain_append: * stable_node_dup is the dup to replace. */ if (stable_node_dup == stable_node) { - VM_BUG_ON(is_stable_node_chain(stable_node_dup)); VM_BUG_ON(is_stable_node_dup(stable_node_dup)); /* chain is missing so create it */ stable_node = alloc_stable_node_chain(stable_node_dup, @@ -1740,7 +2021,6 @@ chain_append: * of the current nid for this page * content. */ - VM_BUG_ON(!is_stable_node_chain(stable_node)); VM_BUG_ON(!is_stable_node_dup(stable_node_dup)); VM_BUG_ON(page_node->head != &migrate_nodes); list_del(&page_node->list); @@ -1756,17 +2036,17 @@ chain_append: * This function returns the stable tree node just allocated on success, * NULL otherwise. */ -static struct stable_node *stable_tree_insert(struct page *kpage) +static struct ksm_stable_node *stable_tree_insert(struct folio *kfolio) { int nid; unsigned long kpfn; struct rb_root *root; struct rb_node **new; struct rb_node *parent; - struct stable_node *stable_node, *stable_node_dup, *stable_node_any; + struct ksm_stable_node *stable_node, *stable_node_dup; bool need_chain = false; - kpfn = page_to_pfn(kpage); + kpfn = folio_pfn(kfolio); nid = get_kpfn_nid(kpfn); root = root_stable_tree + nid; again: @@ -1774,41 +2054,16 @@ again: new = &root->rb_node; while (*new) { - struct page *tree_page; + struct folio *tree_folio; int ret; cond_resched(); - stable_node = rb_entry(*new, struct stable_node, node); - stable_node_any = NULL; - tree_page = chain(&stable_node_dup, stable_node, root); - if (!stable_node_dup) { - /* - * Either all stable_node dups were full in - * this stable_node chain, or this chain was - * empty and should be rb_erased. - */ - stable_node_any = stable_node_dup_any(stable_node, - root); - if (!stable_node_any) { - /* rb_erase just run */ - goto again; - } - /* - * Take any of the stable_node dups page of - * this stable_node chain to let the tree walk - * continue. All KSM pages belonging to the - * stable_node dups in a stable_node chain - * have the same content and they're - * wrprotected at all times. Any will work - * fine to continue the walk. - */ - tree_page = get_ksm_page(stable_node_any, false); - } - VM_BUG_ON(!stable_node_dup ^ !!stable_node_any); - if (!tree_page) { + stable_node = rb_entry(*new, struct ksm_stable_node, node); + tree_folio = chain(&stable_node_dup, &stable_node, root); + if (!tree_folio) { /* * If we walked over a stale stable_node, - * get_ksm_page() will call rb_erase() and it + * ksm_get_folio() will call rb_erase() and it * may rebalance the tree from under us. So * restart the search from scratch. Returning * NULL would be safe too, but we'd generate @@ -1818,8 +2073,8 @@ again: goto again; } - ret = memcmp_pages(kpage, tree_page); - put_page(tree_page); + ret = memcmp_pages(&kfolio->page, &tree_folio->page); + folio_put(tree_folio); parent = *new; if (ret < 0) @@ -1838,7 +2093,6 @@ again: INIT_HLIST_HEAD(&stable_node_dup->hlist); stable_node_dup->kpfn = kpfn; - set_page_stable_node(kpage, stable_node_dup); stable_node_dup->rmap_hlist_len = 0; DO_NUMA(stable_node_dup->nid = nid); if (!need_chain) { @@ -1846,7 +2100,7 @@ again: rb_insert_color(&stable_node_dup->node, root); } else { if (!is_stable_node_chain(stable_node)) { - struct stable_node *orig = stable_node; + struct ksm_stable_node *orig = stable_node; /* chain is missing so create it */ stable_node = alloc_stable_node_chain(orig, root); if (!stable_node) { @@ -1857,6 +2111,8 @@ again: stable_node_chain_add_dup(stable_node_dup, stable_node); } + folio_set_stable_node(kfolio, stable_node_dup); + return stable_node_dup; } @@ -1875,7 +2131,7 @@ again: * the same walking algorithm in an rbtree. */ static -struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item, +struct ksm_rmap_item *unstable_tree_search_insert(struct ksm_rmap_item *rmap_item, struct page *page, struct page **tree_pagep) { @@ -1889,12 +2145,12 @@ struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item, new = &root->rb_node; while (*new) { - struct rmap_item *tree_rmap_item; + struct ksm_rmap_item *tree_rmap_item; struct page *tree_page; int ret; cond_resched(); - tree_rmap_item = rb_entry(*new, struct rmap_item, node); + tree_rmap_item = rb_entry(*new, struct ksm_rmap_item, node); tree_page = get_mergeable_page(tree_rmap_item); if (!tree_page) return NULL; @@ -1946,8 +2202,8 @@ struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item, * rmap_items hanging off a given node of the stable tree, all sharing * the same ksm page. */ -static void stable_tree_append(struct rmap_item *rmap_item, - struct stable_node *stable_node, +static void stable_tree_append(struct ksm_rmap_item *rmap_item, + struct ksm_stable_node *stable_node, bool max_page_sharing_bypass) { /* @@ -1956,7 +2212,7 @@ static void stable_tree_append(struct rmap_item *rmap_item, * duplicate. page_migration could break later if rmap breaks, * so we can as well crash here. We really need to check for * rmap_hlist_len == STABLE_NODE_CHAIN, but we can as well check - * for other negative values as an undeflow if detected here + * for other negative values as an underflow if detected here * for the first time (and not when decreasing rmap_hlist_len) * would be sign of memory corruption in the stable_node. */ @@ -1976,6 +2232,8 @@ static void stable_tree_append(struct rmap_item *rmap_item, ksm_pages_sharing++; else ksm_pages_shared++; + + rmap_item->mm->ksm_merging_pages++; } /* @@ -1987,17 +2245,18 @@ static void stable_tree_append(struct rmap_item *rmap_item, * @page: the page that we are searching identical page to. * @rmap_item: the reverse mapping into the virtual address of this page */ -static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) +static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_item) { - struct rmap_item *tree_rmap_item; + struct folio *folio = page_folio(page); + struct ksm_rmap_item *tree_rmap_item; struct page *tree_page = NULL; - struct stable_node *stable_node; - struct page *kpage; + struct ksm_stable_node *stable_node; + struct folio *kfolio; unsigned int checksum; int err; bool max_page_sharing_bypass = false; - stable_node = page_stable_node(page); + stable_node = folio_stable_node(folio); if (stable_node) { if (stable_node->head != &migrate_nodes && get_kpfn_nid(READ_ONCE(stable_node->kpfn)) != @@ -2015,82 +2274,87 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) */ if (!is_page_sharing_candidate(stable_node)) max_page_sharing_bypass = true; + } else { + remove_rmap_item_from_tree(rmap_item); + + /* + * If the hash value of the page has changed from the last time + * we calculated it, this page is changing frequently: therefore we + * don't want to insert it in the unstable tree, and we don't want + * to waste our time searching for something identical to it there. + */ + checksum = calc_checksum(page); + if (rmap_item->oldchecksum != checksum) { + rmap_item->oldchecksum = checksum; + return; + } + + if (!try_to_merge_with_zero_page(rmap_item, page)) + return; } - /* We first start with searching the page inside the stable tree */ - kpage = stable_tree_search(page); - if (kpage == page && rmap_item->head == stable_node) { - put_page(kpage); + /* Start by searching for the folio in the stable tree */ + kfolio = stable_tree_search(page); + if (kfolio == folio && rmap_item->head == stable_node) { + folio_put(kfolio); return; } remove_rmap_item_from_tree(rmap_item); - if (kpage) { - err = try_to_merge_with_ksm_page(rmap_item, page, kpage); + if (kfolio) { + if (kfolio == ERR_PTR(-EBUSY)) + return; + + err = try_to_merge_with_ksm_page(rmap_item, page, &kfolio->page); if (!err) { /* * The page was successfully merged: * add its rmap_item to the stable tree. */ - lock_page(kpage); - stable_tree_append(rmap_item, page_stable_node(kpage), + folio_lock(kfolio); + stable_tree_append(rmap_item, folio_stable_node(kfolio), max_page_sharing_bypass); - unlock_page(kpage); + folio_unlock(kfolio); } - put_page(kpage); - return; - } - - /* - * If the hash value of the page has changed from the last time - * we calculated it, this page is changing frequently: therefore we - * don't want to insert it in the unstable tree, and we don't want - * to waste our time searching for something identical to it there. - */ - checksum = calc_checksum(page); - if (rmap_item->oldchecksum != checksum) { - rmap_item->oldchecksum = checksum; + folio_put(kfolio); return; } - /* - * Same checksum as an empty page. We attempt to merge it with the - * appropriate zero page if the user enabled this via sysfs. - */ - if (ksm_use_zero_pages && (checksum == zero_checksum)) { - struct vm_area_struct *vma; - - vma = find_mergeable_vma(rmap_item->mm, rmap_item->address); - err = try_to_merge_one_page(vma, page, - ZERO_PAGE(rmap_item->address)); - /* - * In case of failure, the page was not really empty, so we - * need to continue. Otherwise we're done. - */ - if (!err) - return; - } tree_rmap_item = unstable_tree_search_insert(rmap_item, page, &tree_page); if (tree_rmap_item) { - kpage = try_to_merge_two_pages(rmap_item, page, + bool split; + + kfolio = try_to_merge_two_pages(rmap_item, page, tree_rmap_item, tree_page); + /* + * If both pages we tried to merge belong to the same compound + * page, then we actually ended up increasing the reference + * count of the same compound page twice, and split_huge_page + * failed. + * Here we set a flag if that happened, and we use it later to + * try split_huge_page again. Since we call put_page right + * afterwards, the reference count will be correct and + * split_huge_page should succeed. + */ + split = PageTransCompound(page) + && compound_head(page) == compound_head(tree_page); put_page(tree_page); - if (kpage) { + if (kfolio) { /* * The pages were successfully merged: insert new * node in the stable tree and add both rmap_items. */ - lock_page(kpage); - stable_node = stable_tree_insert(kpage); + folio_lock(kfolio); + stable_node = stable_tree_insert(kfolio); if (stable_node) { stable_tree_append(tree_rmap_item, stable_node, false); stable_tree_append(rmap_item, stable_node, false); } - unlock_page(kpage); + folio_unlock(kfolio); /* * If we fail to insert the page into the stable tree, @@ -2102,15 +2366,30 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) break_cow(tree_rmap_item); break_cow(rmap_item); } + } else if (split) { + /* + * We are here if we tried to merge two pages and + * failed because they both belonged to the same + * compound page. We will split the page now, but no + * merging will take place. + * We do not want to add the cost of a full lock; if + * the page is locked, it is better to skip it and + * perhaps try again later. + */ + if (!folio_trylock(folio)) + return; + split_huge_page(page); + folio = page_folio(page); + folio_unlock(folio); } } } -static struct rmap_item *get_next_rmap_item(struct mm_slot *mm_slot, - struct rmap_item **rmap_list, +static struct ksm_rmap_item *get_next_rmap_item(struct ksm_mm_slot *mm_slot, + struct ksm_rmap_item **rmap_list, unsigned long addr) { - struct rmap_item *rmap_item; + struct ksm_rmap_item *rmap_item; while (*rmap_list) { rmap_item = *rmap_list; @@ -2126,7 +2405,8 @@ static struct rmap_item *get_next_rmap_item(struct mm_slot *mm_slot, rmap_item = alloc_rmap_item(); if (rmap_item) { /* It has already been zeroed */ - rmap_item->mm = mm_slot->mm; + rmap_item->mm = mm_slot->slot.mm; + rmap_item->mm->ksm_rmap_items++; rmap_item->address = addr; rmap_item->rmap_list = *rmap_list; *rmap_list = rmap_item; @@ -2134,22 +2414,184 @@ static struct rmap_item *get_next_rmap_item(struct mm_slot *mm_slot, return rmap_item; } -static struct rmap_item *scan_get_next_rmap_item(struct page **page) +/* + * Calculate skip age for the ksm page age. The age determines how often + * de-duplicating has already been tried unsuccessfully. If the age is + * smaller, the scanning of this page is skipped for less scans. + * + * @age: rmap_item age of page + */ +static unsigned int skip_age(rmap_age_t age) +{ + if (age <= 3) + return 1; + if (age <= 5) + return 2; + if (age <= 8) + return 4; + + return 8; +} + +/* + * Determines if a page should be skipped for the current scan. + * + * @folio: folio containing the page to check + * @rmap_item: associated rmap_item of page + */ +static bool should_skip_rmap_item(struct folio *folio, + struct ksm_rmap_item *rmap_item) +{ + rmap_age_t age; + + if (!ksm_smart_scan) + return false; + + /* + * Never skip pages that are already KSM; pages cmp_and_merge_page() + * will essentially ignore them, but we still have to process them + * properly. + */ + if (folio_test_ksm(folio)) + return false; + + age = rmap_item->age; + if (age != U8_MAX) + rmap_item->age++; + + /* + * Smaller ages are not skipped, they need to get a chance to go + * through the different phases of the KSM merging. + */ + if (age < 3) + return false; + + /* + * Are we still allowed to skip? If not, then don't skip it + * and determine how much more often we are allowed to skip next. + */ + if (!rmap_item->remaining_skips) { + rmap_item->remaining_skips = skip_age(age); + return false; + } + + /* Skip this page */ + ksm_pages_skipped++; + rmap_item->remaining_skips--; + remove_rmap_item_from_tree(rmap_item); + return true; +} + +struct ksm_next_page_arg { + struct folio *folio; + struct page *page; + unsigned long addr; +}; + +static int ksm_next_page_pmd_entry(pmd_t *pmdp, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct ksm_next_page_arg *private = walk->private; + struct vm_area_struct *vma = walk->vma; + pte_t *start_ptep = NULL, *ptep, pte; + struct mm_struct *mm = walk->mm; + struct folio *folio; + struct page *page; + spinlock_t *ptl; + pmd_t pmd; + + if (ksm_test_exit(mm)) + return 0; + + cond_resched(); + + pmd = pmdp_get_lockless(pmdp); + if (!pmd_present(pmd)) + return 0; + + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && pmd_leaf(pmd)) { + ptl = pmd_lock(mm, pmdp); + pmd = pmdp_get(pmdp); + + if (!pmd_present(pmd)) { + goto not_found_unlock; + } else if (pmd_leaf(pmd)) { + page = vm_normal_page_pmd(vma, addr, pmd); + if (!page) + goto not_found_unlock; + folio = page_folio(page); + + if (folio_is_zone_device(folio) || !folio_test_anon(folio)) + goto not_found_unlock; + + page += ((addr & (PMD_SIZE - 1)) >> PAGE_SHIFT); + goto found_unlock; + } + spin_unlock(ptl); + } + + start_ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); + if (!start_ptep) + return 0; + + for (ptep = start_ptep; addr < end; ptep++, addr += PAGE_SIZE) { + pte = ptep_get(ptep); + + if (!pte_present(pte)) + continue; + + page = vm_normal_page(vma, addr, pte); + if (!page) + continue; + folio = page_folio(page); + + if (folio_is_zone_device(folio) || !folio_test_anon(folio)) + continue; + goto found_unlock; + } + +not_found_unlock: + spin_unlock(ptl); + if (start_ptep) + pte_unmap(start_ptep); + return 0; +found_unlock: + folio_get(folio); + spin_unlock(ptl); + if (start_ptep) + pte_unmap(start_ptep); + private->page = page; + private->folio = folio; + private->addr = addr; + return 1; +} + +static struct mm_walk_ops ksm_next_page_ops = { + .pmd_entry = ksm_next_page_pmd_entry, + .walk_lock = PGWALK_RDLOCK, +}; + +static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) { struct mm_struct *mm; + struct ksm_mm_slot *mm_slot; struct mm_slot *slot; struct vm_area_struct *vma; - struct rmap_item *rmap_item; + struct ksm_rmap_item *rmap_item; + struct vma_iterator vmi; int nid; - if (list_empty(&ksm_mm_head.mm_list)) + if (list_empty(&ksm_mm_head.slot.mm_node)) return NULL; - slot = ksm_scan.mm_slot; - if (slot == &ksm_mm_head) { + mm_slot = ksm_scan.mm_slot; + if (mm_slot == &ksm_mm_head) { + advisor_start_scan(); + trace_ksm_start_scan(ksm_scan.seqnr, ksm_rmap_items); + /* - * A number of pages can hang around indefinitely on per-cpu - * pagevecs, raised page count preventing write_protect_page + * A number of pages can hang around indefinitely in per-cpu + * LRU cache, raised page count preventing write_protect_page * from merging them. Though it doesn't really matter much, * it is puzzling to see some stuck in pages_volatile until * other activity jostles them out, and they also prevented @@ -2166,14 +2608,15 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page) * so prune them once before each full scan. */ if (!ksm_merge_across_nodes) { - struct stable_node *stable_node, *next; - struct page *page; + struct ksm_stable_node *stable_node, *next; + struct folio *folio; list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { - page = get_ksm_page(stable_node, false); - if (page) - put_page(page); + folio = ksm_get_folio(stable_node, + KSM_GET_FOLIO_NOLOCK); + if (folio) + folio_put(folio); cond_resched(); } } @@ -2182,28 +2625,31 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page) root_unstable_tree[nid] = RB_ROOT; spin_lock(&ksm_mmlist_lock); - slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list); - ksm_scan.mm_slot = slot; + slot = list_entry(mm_slot->slot.mm_node.next, + struct mm_slot, mm_node); + mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); + ksm_scan.mm_slot = mm_slot; spin_unlock(&ksm_mmlist_lock); /* * Although we tested list_empty() above, a racing __ksm_exit * of the last mm on the list may have removed it since then. */ - if (slot == &ksm_mm_head) + if (mm_slot == &ksm_mm_head) return NULL; next_mm: ksm_scan.address = 0; - ksm_scan.rmap_list = &slot->rmap_list; + ksm_scan.rmap_list = &mm_slot->rmap_list; } + slot = &mm_slot->slot; mm = slot->mm; - down_read(&mm->mmap_sem); + vma_iter_init(&vmi, mm, ksm_scan.address); + + mmap_read_lock(mm); if (ksm_test_exit(mm)) - vma = NULL; - else - vma = find_vma(mm, ksm_scan.address); + goto no_vmas; - for (; vma; vma = vma->vm_next) { + for_each_vma(vmi, vma) { if (!(vma->vm_flags & VM_MERGEABLE)) continue; if (ksm_scan.address < vma->vm_start) @@ -2212,69 +2658,101 @@ next_mm: ksm_scan.address = vma->vm_end; while (ksm_scan.address < vma->vm_end) { + struct ksm_next_page_arg ksm_next_page_arg; + struct page *tmp_page = NULL; + struct folio *folio; + if (ksm_test_exit(mm)) break; - *page = follow_page(vma, ksm_scan.address, FOLL_GET); - if (IS_ERR_OR_NULL(*page)) { - ksm_scan.address += PAGE_SIZE; - cond_resched(); - continue; + + int found; + + found = walk_page_range_vma(vma, ksm_scan.address, + vma->vm_end, + &ksm_next_page_ops, + &ksm_next_page_arg); + + if (found > 0) { + folio = ksm_next_page_arg.folio; + tmp_page = ksm_next_page_arg.page; + ksm_scan.address = ksm_next_page_arg.addr; + } else { + VM_WARN_ON_ONCE(found < 0); + ksm_scan.address = vma->vm_end - PAGE_SIZE; } - if (PageAnon(*page)) { - flush_anon_page(vma, *page, ksm_scan.address); - flush_dcache_page(*page); - rmap_item = get_next_rmap_item(slot, + + if (tmp_page) { + flush_anon_page(vma, tmp_page, ksm_scan.address); + flush_dcache_page(tmp_page); + rmap_item = get_next_rmap_item(mm_slot, ksm_scan.rmap_list, ksm_scan.address); if (rmap_item) { ksm_scan.rmap_list = &rmap_item->rmap_list; + + if (should_skip_rmap_item(folio, rmap_item)) { + folio_put(folio); + goto next_page; + } + ksm_scan.address += PAGE_SIZE; - } else - put_page(*page); - up_read(&mm->mmap_sem); + *page = tmp_page; + } else { + folio_put(folio); + } + mmap_read_unlock(mm); return rmap_item; } - put_page(*page); +next_page: ksm_scan.address += PAGE_SIZE; cond_resched(); } } if (ksm_test_exit(mm)) { +no_vmas: ksm_scan.address = 0; - ksm_scan.rmap_list = &slot->rmap_list; + ksm_scan.rmap_list = &mm_slot->rmap_list; } /* * Nuke all the rmap_items that are above this current rmap: * because there were no VM_MERGEABLE vmas with such addresses. */ - remove_trailing_rmap_items(slot, ksm_scan.rmap_list); + remove_trailing_rmap_items(ksm_scan.rmap_list); spin_lock(&ksm_mmlist_lock); - ksm_scan.mm_slot = list_entry(slot->mm_list.next, - struct mm_slot, mm_list); + slot = list_entry(mm_slot->slot.mm_node.next, + struct mm_slot, mm_node); + ksm_scan.mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); if (ksm_scan.address == 0) { /* - * We've completed a full scan of all vmas, holding mmap_sem + * We've completed a full scan of all vmas, holding mmap_lock * throughout, and found no VM_MERGEABLE: so do the same as * __ksm_exit does to remove this mm from all our lists now. * This applies either when cleaning up after __ksm_exit * (but beware: we can reach here even before __ksm_exit), * or when all VM_MERGEABLE areas have been unmapped (and - * mmap_sem then protects against race with MADV_MERGEABLE). + * mmap_lock then protects against race with MADV_MERGEABLE). */ - hash_del(&slot->link); - list_del(&slot->mm_list); + hash_del(&mm_slot->slot.hash); + list_del(&mm_slot->slot.mm_node); spin_unlock(&ksm_mmlist_lock); - free_mm_slot(slot); - clear_bit(MMF_VM_MERGEABLE, &mm->flags); - up_read(&mm->mmap_sem); + mm_slot_free(mm_slot_cache, mm_slot); + /* + * Only clear MMF_VM_MERGEABLE. We must not clear + * MMF_VM_MERGE_ANY, because for those MMF_VM_MERGE_ANY process, + * perhaps their mm_struct has just been added to ksm_mm_slot + * list, and its process has not yet officially started running + * or has not yet performed mmap/brk to allocate anonymous VMAS. + */ + mm_flags_clear(MMF_VM_MERGEABLE, mm); + mmap_read_unlock(mm); mmdrop(mm); } else { - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); /* - * up_read(&mm->mmap_sem) first because after + * mmap_read_unlock(mm) first because after * spin_unlock(&ksm_mmlist_lock) run, the "mm" may * already have been freed under us by __ksm_exit() * because the "mm_slot" is still hashed and @@ -2284,22 +2762,25 @@ next_mm: } /* Repeat until we've completed scanning the whole list */ - slot = ksm_scan.mm_slot; - if (slot != &ksm_mm_head) + mm_slot = ksm_scan.mm_slot; + if (mm_slot != &ksm_mm_head) goto next_mm; + advisor_stop_scan(); + + trace_ksm_stop_scan(ksm_scan.seqnr, ksm_rmap_items); ksm_scan.seqnr++; return NULL; } /** * ksm_do_scan - the ksm scanner main worker function. - * @scan_npages - number of pages we want to scan before we return. + * @scan_npages: number of pages we want to scan before we return. */ static void ksm_do_scan(unsigned int scan_npages) { - struct rmap_item *rmap_item; - struct page *uninitialized_var(page); + struct ksm_rmap_item *rmap_item; + struct page *page; while (scan_npages-- && likely(!freezing(current))) { cond_resched(); @@ -2308,16 +2789,19 @@ static void ksm_do_scan(unsigned int scan_npages) return; cmp_and_merge_page(page, rmap_item); put_page(page); + ksm_pages_scanned++; } } static int ksmd_should_run(void) { - return (ksm_run & KSM_RUN_MERGE) && !list_empty(&ksm_mm_head.mm_list); + return (ksm_run & KSM_RUN_MERGE) && !list_empty(&ksm_mm_head.slot.mm_node); } static int ksm_scan_thread(void *nothing) { + unsigned int sleep_ms; + set_freezable(); set_user_nice(current, 5); @@ -2328,11 +2812,11 @@ static int ksm_scan_thread(void *nothing) ksm_do_scan(ksm_thread_pages_to_scan); mutex_unlock(&ksm_thread_mutex); - try_to_freeze(); - if (ksmd_should_run()) { - schedule_timeout_interruptible( - msecs_to_jiffies(ksm_thread_sleep_millisecs)); + sleep_ms = READ_ONCE(ksm_thread_sleep_millisecs); + wait_event_freezable_timeout(ksm_iter_wait, + sleep_ms != READ_ONCE(ksm_thread_sleep_millisecs), + msecs_to_jiffies(sleep_ms)); } else { wait_event_freezable(ksm_thread_wait, ksmd_should_run() || kthread_should_stop()); @@ -2341,28 +2825,167 @@ static int ksm_scan_thread(void *nothing) return 0; } +static bool __ksm_should_add_vma(const struct file *file, vm_flags_t vm_flags) +{ + if (vm_flags & VM_MERGEABLE) + return false; + + return ksm_compatible(file, vm_flags); +} + +static void __ksm_add_vma(struct vm_area_struct *vma) +{ + if (__ksm_should_add_vma(vma->vm_file, vma->vm_flags)) + vm_flags_set(vma, VM_MERGEABLE); +} + +static int __ksm_del_vma(struct vm_area_struct *vma) +{ + int err; + + if (!(vma->vm_flags & VM_MERGEABLE)) + return 0; + + if (vma->anon_vma) { + err = break_ksm(vma, vma->vm_start, vma->vm_end, true); + if (err) + return err; + } + + vm_flags_clear(vma, VM_MERGEABLE); + return 0; +} +/** + * ksm_vma_flags - Update VMA flags to mark as mergeable if compatible + * + * @mm: Proposed VMA's mm_struct + * @file: Proposed VMA's file-backed mapping, if any. + * @vm_flags: Proposed VMA"s flags. + * + * Returns: @vm_flags possibly updated to mark mergeable. + */ +vm_flags_t ksm_vma_flags(struct mm_struct *mm, const struct file *file, + vm_flags_t vm_flags) +{ + if (mm_flags_test(MMF_VM_MERGE_ANY, mm) && + __ksm_should_add_vma(file, vm_flags)) { + vm_flags |= VM_MERGEABLE; + /* + * Generally, the flags here always include MMF_VM_MERGEABLE. + * However, in rare cases, this flag may be cleared by ksmd who + * scans a cycle without finding any mergeable vma. + */ + if (unlikely(!mm_flags_test(MMF_VM_MERGEABLE, mm))) + __ksm_enter(mm); + } + + return vm_flags; +} + +static void ksm_add_vmas(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + + VMA_ITERATOR(vmi, mm, 0); + for_each_vma(vmi, vma) + __ksm_add_vma(vma); +} + +static int ksm_del_vmas(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + int err; + + VMA_ITERATOR(vmi, mm, 0); + for_each_vma(vmi, vma) { + err = __ksm_del_vma(vma); + if (err) + return err; + } + return 0; +} + +/** + * ksm_enable_merge_any - Add mm to mm ksm list and enable merging on all + * compatible VMA's + * + * @mm: Pointer to mm + * + * Returns 0 on success, otherwise error code + */ +int ksm_enable_merge_any(struct mm_struct *mm) +{ + int err; + + if (mm_flags_test(MMF_VM_MERGE_ANY, mm)) + return 0; + + if (!mm_flags_test(MMF_VM_MERGEABLE, mm)) { + err = __ksm_enter(mm); + if (err) + return err; + } + + mm_flags_set(MMF_VM_MERGE_ANY, mm); + ksm_add_vmas(mm); + + return 0; +} + +/** + * ksm_disable_merge_any - Disable merging on all compatible VMA's of the mm, + * previously enabled via ksm_enable_merge_any(). + * + * Disabling merging implies unmerging any merged pages, like setting + * MADV_UNMERGEABLE would. If unmerging fails, the whole operation fails and + * merging on all compatible VMA's remains enabled. + * + * @mm: Pointer to mm + * + * Returns 0 on success, otherwise error code + */ +int ksm_disable_merge_any(struct mm_struct *mm) +{ + int err; + + if (!mm_flags_test(MMF_VM_MERGE_ANY, mm)) + return 0; + + err = ksm_del_vmas(mm); + if (err) { + ksm_add_vmas(mm); + return err; + } + + mm_flags_clear(MMF_VM_MERGE_ANY, mm); + return 0; +} + +int ksm_disable(struct mm_struct *mm) +{ + mmap_assert_write_locked(mm); + + if (!mm_flags_test(MMF_VM_MERGEABLE, mm)) + return 0; + if (mm_flags_test(MMF_VM_MERGE_ANY, mm)) + return ksm_disable_merge_any(mm); + return ksm_del_vmas(mm); +} + int ksm_madvise(struct vm_area_struct *vma, unsigned long start, - unsigned long end, int advice, unsigned long *vm_flags) + unsigned long end, int advice, vm_flags_t *vm_flags) { struct mm_struct *mm = vma->vm_mm; int err; switch (advice) { case MADV_MERGEABLE: - /* - * Be somewhat over-protective for now! - */ - if (*vm_flags & (VM_MERGEABLE | VM_SHARED | VM_MAYSHARE | - VM_PFNMAP | VM_IO | VM_DONTEXPAND | - VM_HUGETLB | VM_MIXEDMAP)) - return 0; /* just ignore the advice */ - -#ifdef VM_SAO - if (*vm_flags & VM_SAO) + if (vma->vm_flags & VM_MERGEABLE) + return 0; + if (!vma_ksm_compatible(vma)) return 0; -#endif - if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) { + if (!mm_flags_test(MMF_VM_MERGEABLE, mm)) { err = __ksm_enter(mm); if (err) return err; @@ -2376,7 +2999,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, return 0; /* just ignore the advice */ if (vma->anon_vma) { - err = unmerge_ksm_pages(vma, start, end); + err = break_ksm(vma, start, end, true); if (err) return err; } @@ -2387,21 +3010,25 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, return 0; } +EXPORT_SYMBOL_GPL(ksm_madvise); int __ksm_enter(struct mm_struct *mm) { - struct mm_slot *mm_slot; + struct ksm_mm_slot *mm_slot; + struct mm_slot *slot; int needs_wakeup; - mm_slot = alloc_mm_slot(); + mm_slot = mm_slot_alloc(mm_slot_cache); if (!mm_slot) return -ENOMEM; + slot = &mm_slot->slot; + /* Check ksm_run too? Would need tighter locking */ - needs_wakeup = list_empty(&ksm_mm_head.mm_list); + needs_wakeup = list_empty(&ksm_mm_head.slot.mm_node); spin_lock(&ksm_mmlist_lock); - insert_to_mm_slots_hash(mm, mm_slot); + mm_slot_insert(mm_slots_hash, mm, slot); /* * When KSM_RUN_MERGE (or KSM_RUN_STOP), * insert just behind the scanning cursor, to let the area settle @@ -2413,104 +3040,130 @@ int __ksm_enter(struct mm_struct *mm) * missed: then we might as well insert at the end of the list. */ if (ksm_run & KSM_RUN_UNMERGE) - list_add_tail(&mm_slot->mm_list, &ksm_mm_head.mm_list); + list_add_tail(&slot->mm_node, &ksm_mm_head.slot.mm_node); else - list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list); + list_add_tail(&slot->mm_node, &ksm_scan.mm_slot->slot.mm_node); spin_unlock(&ksm_mmlist_lock); - set_bit(MMF_VM_MERGEABLE, &mm->flags); + mm_flags_set(MMF_VM_MERGEABLE, mm); mmgrab(mm); if (needs_wakeup) wake_up_interruptible(&ksm_thread_wait); + trace_ksm_enter(mm); return 0; } void __ksm_exit(struct mm_struct *mm) { - struct mm_slot *mm_slot; + struct ksm_mm_slot *mm_slot = NULL; + struct mm_slot *slot; int easy_to_free = 0; /* * This process is exiting: if it's straightforward (as is the * case when ksmd was never running), free mm_slot immediately. * But if it's at the cursor or has rmap_items linked to it, use - * mmap_sem to synchronize with any break_cows before pagetables + * mmap_lock to synchronize with any break_cows before pagetables * are freed, and leave the mm_slot on the list for ksmd to free. * Beware: ksm may already have noticed it exiting and freed the slot. */ spin_lock(&ksm_mmlist_lock); - mm_slot = get_mm_slot(mm); - if (mm_slot && ksm_scan.mm_slot != mm_slot) { - if (!mm_slot->rmap_list) { - hash_del(&mm_slot->link); - list_del(&mm_slot->mm_list); - easy_to_free = 1; - } else { - list_move(&mm_slot->mm_list, - &ksm_scan.mm_slot->mm_list); - } + slot = mm_slot_lookup(mm_slots_hash, mm); + if (!slot) + goto unlock; + mm_slot = mm_slot_entry(slot, struct ksm_mm_slot, slot); + if (ksm_scan.mm_slot == mm_slot) + goto unlock; + if (!mm_slot->rmap_list) { + hash_del(&slot->hash); + list_del(&slot->mm_node); + easy_to_free = 1; + } else { + list_move(&slot->mm_node, + &ksm_scan.mm_slot->slot.mm_node); } +unlock: spin_unlock(&ksm_mmlist_lock); if (easy_to_free) { - free_mm_slot(mm_slot); - clear_bit(MMF_VM_MERGEABLE, &mm->flags); + mm_slot_free(mm_slot_cache, mm_slot); + mm_flags_clear(MMF_VM_MERGE_ANY, mm); + mm_flags_clear(MMF_VM_MERGEABLE, mm); mmdrop(mm); } else if (mm_slot) { - down_write(&mm->mmap_sem); - up_write(&mm->mmap_sem); + mmap_write_lock(mm); + mmap_write_unlock(mm); } + + trace_ksm_exit(mm); } -struct page *ksm_might_need_to_copy(struct page *page, - struct vm_area_struct *vma, unsigned long address) +struct folio *ksm_might_need_to_copy(struct folio *folio, + struct vm_area_struct *vma, unsigned long addr) { - struct anon_vma *anon_vma = page_anon_vma(page); - struct page *new_page; + struct page *page = folio_page(folio, 0); + struct anon_vma *anon_vma = folio_anon_vma(folio); + struct folio *new_folio; - if (PageKsm(page)) { - if (page_stable_node(page) && + if (folio_test_large(folio)) + return folio; + + if (folio_test_ksm(folio)) { + if (folio_stable_node(folio) && !(ksm_run & KSM_RUN_UNMERGE)) - return page; /* no need to copy it */ + return folio; /* no need to copy it */ } else if (!anon_vma) { - return page; /* no need to copy it */ - } else if (anon_vma->root == vma->anon_vma->root && - page->index == linear_page_index(vma, address)) { - return page; /* still no need to copy it */ - } - if (!PageUptodate(page)) - return page; /* let do_swap_page report the error */ - - new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); - if (new_page) { - copy_user_highpage(new_page, page, address, vma); - - SetPageDirty(new_page); - __SetPageUptodate(new_page); - __SetPageLocked(new_page); + return folio; /* no need to copy it */ + } else if (folio->index == linear_page_index(vma, addr) && + anon_vma->root == vma->anon_vma->root) { + return folio; /* still no need to copy it */ + } + if (PageHWPoison(page)) + return ERR_PTR(-EHWPOISON); + if (!folio_test_uptodate(folio)) + return folio; /* let do_swap_page report the error */ + + new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr); + if (new_folio && + mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL)) { + folio_put(new_folio); + new_folio = NULL; + } + if (new_folio) { + if (copy_mc_user_highpage(folio_page(new_folio, 0), page, + addr, vma)) { + folio_put(new_folio); + return ERR_PTR(-EHWPOISON); + } + folio_set_dirty(new_folio); + __folio_mark_uptodate(new_folio); + __folio_set_locked(new_folio); +#ifdef CONFIG_SWAP + count_vm_event(KSM_SWPIN_COPY); +#endif } - return new_page; + return new_folio; } -void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc) +void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { - struct stable_node *stable_node; - struct rmap_item *rmap_item; + struct ksm_stable_node *stable_node; + struct ksm_rmap_item *rmap_item; int search_new_forks = 0; - VM_BUG_ON_PAGE(!PageKsm(page), page); + VM_BUG_ON_FOLIO(!folio_test_ksm(folio), folio); /* * Rely on the page lock to protect against concurrent modifications * to that page's node of the stable tree. */ - VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - stable_node = page_stable_node(page); + stable_node = folio_stable_node(folio); if (!stable_node) return; again: @@ -2520,13 +3173,24 @@ again: struct vm_area_struct *vma; cond_resched(); - anon_vma_lock_read(anon_vma); + if (!anon_vma_trylock_read(anon_vma)) { + if (rwc->try_lock) { + rwc->contended = true; + return; + } + anon_vma_lock_read(anon_vma); + } anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root, 0, ULONG_MAX) { + unsigned long addr; + cond_resched(); vma = vmac->vma; - if (rmap_item->address < vma->vm_start || - rmap_item->address >= vma->vm_end) + + /* Ignore the stable/unstable/sqnr flags */ + addr = rmap_item->address & PAGE_MASK; + + if (addr < vma->vm_start || addr >= vma->vm_end) continue; /* * Initially we examine only the vma which covers this @@ -2540,12 +3204,11 @@ again: if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; - if (!rwc->rmap_one(page, vma, - rmap_item->address, rwc->arg)) { + if (!rwc->rmap_one(folio, vma, addr, rwc->arg)) { anon_vma_unlock_read(anon_vma); return; } - if (rwc->done && rwc->done(page)) { + if (rwc->done && rwc->done(folio)) { anon_vma_unlock_read(anon_vma); return; } @@ -2556,27 +3219,71 @@ again: goto again; } +#ifdef CONFIG_MEMORY_FAILURE +/* + * Collect processes when the error hit an ksm page. + */ +void collect_procs_ksm(const struct folio *folio, const struct page *page, + struct list_head *to_kill, int force_early) +{ + struct ksm_stable_node *stable_node; + struct ksm_rmap_item *rmap_item; + struct vm_area_struct *vma; + struct task_struct *tsk; + + stable_node = folio_stable_node(folio); + if (!stable_node) + return; + hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { + struct anon_vma *av = rmap_item->anon_vma; + + anon_vma_lock_read(av); + rcu_read_lock(); + for_each_process(tsk) { + struct anon_vma_chain *vmac; + unsigned long addr; + struct task_struct *t = + task_early_kill(tsk, force_early); + if (!t) + continue; + anon_vma_interval_tree_foreach(vmac, &av->rb_root, 0, + ULONG_MAX) + { + vma = vmac->vma; + if (vma->vm_mm == t->mm) { + addr = rmap_item->address & PAGE_MASK; + add_to_kill_ksm(t, page, vma, to_kill, + addr); + } + } + } + rcu_read_unlock(); + anon_vma_unlock_read(av); + } +} +#endif + #ifdef CONFIG_MIGRATION -void ksm_migrate_page(struct page *newpage, struct page *oldpage) +void folio_migrate_ksm(struct folio *newfolio, struct folio *folio) { - struct stable_node *stable_node; + struct ksm_stable_node *stable_node; - VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); - VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); - VM_BUG_ON_PAGE(newpage->mapping != oldpage->mapping, newpage); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(!folio_test_locked(newfolio), newfolio); + VM_BUG_ON_FOLIO(newfolio->mapping != folio->mapping, newfolio); - stable_node = page_stable_node(newpage); + stable_node = folio_stable_node(folio); if (stable_node) { - VM_BUG_ON_PAGE(stable_node->kpfn != page_to_pfn(oldpage), oldpage); - stable_node->kpfn = page_to_pfn(newpage); + VM_BUG_ON_FOLIO(stable_node->kpfn != folio_pfn(folio), folio); + stable_node->kpfn = folio_pfn(newfolio); /* - * newpage->mapping was set in advance; now we need smp_wmb() + * newfolio->mapping was set in advance; now we need smp_wmb() * to make sure that the new stable_node->kpfn is visible - * to get_ksm_page() before it can see that oldpage->mapping - * has gone stale (or that PageSwapCache has been cleared). + * to ksm_get_folio() before it can see that folio->mapping + * has gone stale (or that the swapcache flag has been cleared). */ smp_wmb(); - set_page_stable_node(oldpage, NULL); + folio_set_stable_node(folio, NULL); } } #endif /* CONFIG_MIGRATION */ @@ -2592,14 +3299,14 @@ static void wait_while_offlining(void) } } -static bool stable_node_dup_remove_range(struct stable_node *stable_node, +static bool stable_node_dup_remove_range(struct ksm_stable_node *stable_node, unsigned long start_pfn, unsigned long end_pfn) { if (stable_node->kpfn >= start_pfn && stable_node->kpfn < end_pfn) { /* - * Don't get_ksm_page, page has already gone: + * Don't ksm_get_folio, page has already gone: * which is why we keep kpfn instead of page* */ remove_node_from_stable_tree(stable_node); @@ -2608,12 +3315,12 @@ static bool stable_node_dup_remove_range(struct stable_node *stable_node, return false; } -static bool stable_node_chain_remove_range(struct stable_node *stable_node, +static bool stable_node_chain_remove_range(struct ksm_stable_node *stable_node, unsigned long start_pfn, unsigned long end_pfn, struct rb_root *root) { - struct stable_node *dup; + struct ksm_stable_node *dup; struct hlist_node *hlist_safe; if (!is_stable_node_chain(stable_node)) { @@ -2637,14 +3344,14 @@ static bool stable_node_chain_remove_range(struct stable_node *stable_node, static void ksm_check_stable_tree(unsigned long start_pfn, unsigned long end_pfn) { - struct stable_node *stable_node, *next; + struct ksm_stable_node *stable_node, *next; struct rb_node *node; int nid; for (nid = 0; nid < ksm_nr_node_ids; nid++) { node = rb_first(root_stable_tree + nid); while (node) { - stable_node = rb_entry(node, struct stable_node, node); + stable_node = rb_entry(node, struct ksm_stable_node, node); if (stable_node_chain_remove_range(stable_node, start_pfn, end_pfn, root_stable_tree + @@ -2674,7 +3381,7 @@ static int ksm_memory_callback(struct notifier_block *self, * Prevent ksm_do_scan(), unmerge_and_remove_all_rmap_items() * and remove_all_stable_nodes() while memory is going offline: * it is unsafe for them to touch the stable tree at this time. - * But unmerge_ksm_pages(), rmap lookups and other entry points + * But break_ksm(), rmap lookups and other entry points * which do not need the ksm_thread_mutex are all safe. */ mutex_lock(&ksm_thread_mutex); @@ -2687,13 +3394,12 @@ static int ksm_memory_callback(struct notifier_block *self, * Most of the work is done by page migration; but there might * be a few stable_nodes left over, still pointing to struct * pages which have been offlined: prune those from the tree, - * otherwise get_ksm_page() might later try to access a + * otherwise ksm_get_folio() might later try to access a * non-existent struct page. */ ksm_check_stable_tree(mn->start_pfn, mn->start_pfn + mn->nr_pages); - /* fallthrough */ - + fallthrough; case MEM_CANCEL_OFFLINE: mutex_lock(&ksm_thread_mutex); ksm_run &= ~KSM_RUN_OFFLINE; @@ -2711,6 +3417,33 @@ static void wait_while_offlining(void) } #endif /* CONFIG_MEMORY_HOTREMOVE */ +#ifdef CONFIG_PROC_FS +/* + * The process is mergeable only if any VMA is currently + * applicable to KSM. + * + * The mmap lock must be held in read mode. + */ +bool ksm_process_mergeable(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + + mmap_assert_locked(mm); + VMA_ITERATOR(vmi, mm, 0); + for_each_vma(vmi, vma) + if (vma->vm_flags & VM_MERGEABLE) + return true; + + return false; +} + +long ksm_process_profit(struct mm_struct *mm) +{ + return (long)(mm->ksm_merging_pages + mm_ksm_zero_pages(mm)) * PAGE_SIZE - + mm->ksm_rmap_items * sizeof(struct ksm_rmap_item); +} +#endif /* CONFIG_PROC_FS */ + #ifdef CONFIG_SYSFS /* * This all compiles without CONFIG_SYSFS, but is a waste of space. @@ -2719,27 +3452,27 @@ static void wait_while_offlining(void) #define KSM_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) #define KSM_ATTR(_name) \ - static struct kobj_attribute _name##_attr = \ - __ATTR(_name, 0644, _name##_show, _name##_store) + static struct kobj_attribute _name##_attr = __ATTR_RW(_name) static ssize_t sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%u\n", ksm_thread_sleep_millisecs); + return sysfs_emit(buf, "%u\n", ksm_thread_sleep_millisecs); } static ssize_t sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - unsigned long msecs; + unsigned int msecs; int err; - err = kstrtoul(buf, 10, &msecs); - if (err || msecs > UINT_MAX) + err = kstrtouint(buf, 10, &msecs); + if (err) return -EINVAL; ksm_thread_sleep_millisecs = msecs; + wake_up_interruptible(&ksm_iter_wait); return count; } @@ -2748,18 +3481,21 @@ KSM_ATTR(sleep_millisecs); static ssize_t pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%u\n", ksm_thread_pages_to_scan); + return sysfs_emit(buf, "%u\n", ksm_thread_pages_to_scan); } static ssize_t pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { + unsigned int nr_pages; int err; - unsigned long nr_pages; - err = kstrtoul(buf, 10, &nr_pages); - if (err || nr_pages > UINT_MAX) + if (ksm_advisor != KSM_ADVISOR_NONE) + return -EINVAL; + + err = kstrtouint(buf, 10, &nr_pages); + if (err) return -EINVAL; ksm_thread_pages_to_scan = nr_pages; @@ -2771,17 +3507,17 @@ KSM_ATTR(pages_to_scan); static ssize_t run_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%lu\n", ksm_run); + return sysfs_emit(buf, "%lu\n", ksm_run); } static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { + unsigned int flags; int err; - unsigned long flags; - err = kstrtoul(buf, 10, &flags); - if (err || flags > UINT_MAX) + err = kstrtouint(buf, 10, &flags); + if (err) return -EINVAL; if (flags > KSM_RUN_UNMERGE) return -EINVAL; @@ -2818,9 +3554,9 @@ KSM_ATTR(run); #ifdef CONFIG_NUMA static ssize_t merge_across_nodes_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%u\n", ksm_merge_across_nodes); + return sysfs_emit(buf, "%u\n", ksm_merge_across_nodes); } static ssize_t merge_across_nodes_store(struct kobject *kobj, @@ -2875,9 +3611,9 @@ KSM_ATTR(merge_across_nodes); #endif static ssize_t use_zero_pages_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) + struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%u\n", ksm_use_zero_pages); + return sysfs_emit(buf, "%u\n", ksm_use_zero_pages); } static ssize_t use_zero_pages_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -2899,7 +3635,7 @@ KSM_ATTR(use_zero_pages); static ssize_t max_page_sharing_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%u\n", ksm_max_page_sharing); + return sysfs_emit(buf, "%u\n", ksm_max_page_sharing); } static ssize_t max_page_sharing_store(struct kobject *kobj, @@ -2937,24 +3673,31 @@ static ssize_t max_page_sharing_store(struct kobject *kobj, } KSM_ATTR(max_page_sharing); +static ssize_t pages_scanned_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%lu\n", ksm_pages_scanned); +} +KSM_ATTR_RO(pages_scanned); + static ssize_t pages_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%lu\n", ksm_pages_shared); + return sysfs_emit(buf, "%lu\n", ksm_pages_shared); } KSM_ATTR_RO(pages_shared); static ssize_t pages_sharing_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%lu\n", ksm_pages_sharing); + return sysfs_emit(buf, "%lu\n", ksm_pages_sharing); } KSM_ATTR_RO(pages_sharing); static ssize_t pages_unshared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%lu\n", ksm_pages_unshared); + return sysfs_emit(buf, "%lu\n", ksm_pages_unshared); } KSM_ATTR_RO(pages_unshared); @@ -2971,21 +3714,47 @@ static ssize_t pages_volatile_show(struct kobject *kobj, */ if (ksm_pages_volatile < 0) ksm_pages_volatile = 0; - return sprintf(buf, "%ld\n", ksm_pages_volatile); + return sysfs_emit(buf, "%ld\n", ksm_pages_volatile); } KSM_ATTR_RO(pages_volatile); +static ssize_t pages_skipped_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%lu\n", ksm_pages_skipped); +} +KSM_ATTR_RO(pages_skipped); + +static ssize_t ksm_zero_pages_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%ld\n", atomic_long_read(&ksm_zero_pages)); +} +KSM_ATTR_RO(ksm_zero_pages); + +static ssize_t general_profit_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + long general_profit; + + general_profit = (ksm_pages_sharing + atomic_long_read(&ksm_zero_pages)) * PAGE_SIZE - + ksm_rmap_items * sizeof(struct ksm_rmap_item); + + return sysfs_emit(buf, "%ld\n", general_profit); +} +KSM_ATTR_RO(general_profit); + static ssize_t stable_node_dups_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%lu\n", ksm_stable_node_dups); + return sysfs_emit(buf, "%lu\n", ksm_stable_node_dups); } KSM_ATTR_RO(stable_node_dups); static ssize_t stable_node_chains_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%lu\n", ksm_stable_node_chains); + return sysfs_emit(buf, "%lu\n", ksm_stable_node_chains); } KSM_ATTR_RO(stable_node_chains); @@ -2994,7 +3763,7 @@ stable_node_chains_prune_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%u\n", ksm_stable_node_chains_prune_millisecs); + return sysfs_emit(buf, "%u\n", ksm_stable_node_chains_prune_millisecs); } static ssize_t @@ -3002,11 +3771,11 @@ stable_node_chains_prune_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - unsigned long msecs; + unsigned int msecs; int err; - err = kstrtoul(buf, 10, &msecs); - if (err || msecs > UINT_MAX) + err = kstrtouint(buf, 10, &msecs); + if (err) return -EINVAL; ksm_stable_node_chains_prune_millisecs = msecs; @@ -3018,18 +3787,167 @@ KSM_ATTR(stable_node_chains_prune_millisecs); static ssize_t full_scans_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%lu\n", ksm_scan.seqnr); + return sysfs_emit(buf, "%lu\n", ksm_scan.seqnr); } KSM_ATTR_RO(full_scans); +static ssize_t smart_scan_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%u\n", ksm_smart_scan); +} + +static ssize_t smart_scan_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + bool value; + + err = kstrtobool(buf, &value); + if (err) + return -EINVAL; + + ksm_smart_scan = value; + return count; +} +KSM_ATTR(smart_scan); + +static ssize_t advisor_mode_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + const char *output; + + if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) + output = "none [scan-time]"; + else + output = "[none] scan-time"; + + return sysfs_emit(buf, "%s\n", output); +} + +static ssize_t advisor_mode_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, + size_t count) +{ + enum ksm_advisor_type curr_advisor = ksm_advisor; + + if (sysfs_streq("scan-time", buf)) + ksm_advisor = KSM_ADVISOR_SCAN_TIME; + else if (sysfs_streq("none", buf)) + ksm_advisor = KSM_ADVISOR_NONE; + else + return -EINVAL; + + /* Set advisor default values */ + if (curr_advisor != ksm_advisor) + set_advisor_defaults(); + + return count; +} +KSM_ATTR(advisor_mode); + +static ssize_t advisor_max_cpu_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%u\n", ksm_advisor_max_cpu); +} + +static ssize_t advisor_max_cpu_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long value; + + err = kstrtoul(buf, 10, &value); + if (err) + return -EINVAL; + + ksm_advisor_max_cpu = value; + return count; +} +KSM_ATTR(advisor_max_cpu); + +static ssize_t advisor_min_pages_to_scan_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%lu\n", ksm_advisor_min_pages_to_scan); +} + +static ssize_t advisor_min_pages_to_scan_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long value; + + err = kstrtoul(buf, 10, &value); + if (err) + return -EINVAL; + + ksm_advisor_min_pages_to_scan = value; + return count; +} +KSM_ATTR(advisor_min_pages_to_scan); + +static ssize_t advisor_max_pages_to_scan_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%lu\n", ksm_advisor_max_pages_to_scan); +} + +static ssize_t advisor_max_pages_to_scan_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long value; + + err = kstrtoul(buf, 10, &value); + if (err) + return -EINVAL; + + ksm_advisor_max_pages_to_scan = value; + return count; +} +KSM_ATTR(advisor_max_pages_to_scan); + +static ssize_t advisor_target_scan_time_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%lu\n", ksm_advisor_target_scan_time); +} + +static ssize_t advisor_target_scan_time_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long value; + + err = kstrtoul(buf, 10, &value); + if (err) + return -EINVAL; + if (value < 1) + return -EINVAL; + + ksm_advisor_target_scan_time = value; + return count; +} +KSM_ATTR(advisor_target_scan_time); + static struct attribute *ksm_attrs[] = { &sleep_millisecs_attr.attr, &pages_to_scan_attr.attr, &run_attr.attr, + &pages_scanned_attr.attr, &pages_shared_attr.attr, &pages_sharing_attr.attr, &pages_unshared_attr.attr, &pages_volatile_attr.attr, + &pages_skipped_attr.attr, + &ksm_zero_pages_attr.attr, &full_scans_attr.attr, #ifdef CONFIG_NUMA &merge_across_nodes_attr.attr, @@ -3039,10 +3957,17 @@ static struct attribute *ksm_attrs[] = { &stable_node_dups_attr.attr, &stable_node_chains_prune_millisecs_attr.attr, &use_zero_pages_attr.attr, + &general_profit_attr.attr, + &smart_scan_attr.attr, + &advisor_mode_attr.attr, + &advisor_max_cpu_attr.attr, + &advisor_min_pages_to_scan_attr.attr, + &advisor_max_pages_to_scan_attr.attr, + &advisor_target_scan_time_attr.attr, NULL, }; -static struct attribute_group ksm_attr_group = { +static const struct attribute_group ksm_attr_group = { .attrs = ksm_attrs, .name = "ksm", }; @@ -3083,7 +4008,7 @@ static int __init ksm_init(void) #ifdef CONFIG_MEMORY_HOTREMOVE /* There is no significance to this priority 100 */ - hotplug_memory_notifier(ksm_memory_callback, 100); + hotplug_memory_notifier(ksm_memory_callback, KSM_CALLBACK_PRI); #endif return 0; |