// SPDX-License-Identifier: GPL-2.0-only /* * Memory merging support. * * This code enables dynamic sharing of identical pages found in different * memory areas, even if they are not shared by fork() * * Copyright (C) 2008-2009 Red Hat, Inc. * Authors: * Izik Eidus * Andrea Arcangeli * Chris Wright * Hugh Dickins
*/
#ifdef CONFIG_NUMA #define NUMA(x) (x) #define DO_NUMA(x) do { (x); } while (0) #else #define NUMA(x) (0) #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: * * In order to reduce excessive scanning, KSM sorts the memory pages by their * contents into a data structure that holds pointers to the pages' locations. * * Since the contents of the pages may change at any moment, KSM cannot just * insert the pages into a normal sorted tree and expect it to find anything. * Therefore KSM uses two data structures - the stable and the unstable tree. * * The stable tree holds pointers to all the merged pages (ksm pages), sorted * by their contents. Because each such page is write-protected, searching on * 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 * by their contents, but since they are not write-protected, KSM cannot rely * upon the unstable tree to work correctly - the unstable tree is liable to * be corrupted as its contents are modified, and so it is called unstable. * * KSM solves this problem by several techniques: * * 1) The unstable tree is flushed every time KSM completes scanning all * memory areas, and then the tree is rebuilt again from the beginning. * 2) KSM will only insert into the unstable tree, pages whose hash value * has not changed since the previous scan of all memory areas. * 3) The unstable tree is a RedBlack Tree - so its balancing is based on the * colors of the nodes and not on their contents, assuring that even when * the tree gets "corrupted" it won't get out of balance, so scanning time * remains the same (also, searching and inserting nodes in an rbtree uses * the same algorithm, so we have no overhead when we flush and rebuild). * 4) KSM never flushes the stable tree, which means that even if it were to * take 10 attempts to find a page in the unstable tree, once it is found, * it is secured in the stable tree. (When we scan a new page, we first * compare it against the stable tree, and then against the unstable tree.) * * If the merge_across_nodes tunable is unset, then KSM maintains multiple * stable trees and multiple unstable trees: one of each for each NUMA node.
*/
/** * 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
*/ struct ksm_mm_slot { struct mm_slot slot; struct ksm_rmap_item *rmap_list;
};
/** * struct ksm_scan - cursor for scanning * @mm_slot: the current mm_slot we are scanning * @address: the next address inside that to be scanned * @rmap_list: link to the next rmap to be scanned in the rmap_list * @seqnr: count of completed full scans (needed when removing unstable node) * * There is only the one ksm_scan instance of this cursor structure.
*/ struct ksm_scan { struct ksm_mm_slot *mm_slot; unsignedlong address; struct ksm_rmap_item **rmap_list; unsignedlong seqnr;
};
/** * 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 * @list: linked into migrate_nodes, pending placement in the proper node tree * @hlist: hlist head of rmap_items using this ksm page * @kpfn: page frame number of this ksm page (perhaps temporarily on wrong nid) * @chain_prune_time: time of the last full garbage collection * @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 ksm_stable_node { union { struct rb_node node; /* when node of stable tree */ struct { /* when listed for migration */ struct list_head *head; struct { struct hlist_node hlist_dup; struct list_head list;
};
};
}; struct hlist_head hlist; union { unsignedlong kpfn; unsignedlong chain_prune_time;
}; /* * STABLE_NODE_CHAIN can be any negative number in * rmap_hlist_len negative range, but better not -1 to be able * to reliably detect underflows.
*/ #define STABLE_NODE_CHAIN -1024 int rmap_hlist_len; #ifdef CONFIG_NUMA int nid; #endif
};
/** * 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) * @mm: the memory structure this rmap_item is pointing into * @address: the virtual address this rmap_item tracks (+ flags in low bits) * @oldchecksum: previous checksum of the page at that virtual address * @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 ksm_rmap_item { struct ksm_rmap_item *rmap_list; union { struct anon_vma *anon_vma; /* when stable */ #ifdef CONFIG_NUMA int nid; /* when node of unstable tree */ #endif
}; struct mm_struct *mm; unsignedlong address; /* + low bits used for flags below */ unsignedint 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 ksm_stable_node *head; struct hlist_node hlist;
};
};
};
#define SEQNR_MASK 0x0ff /* low bits of unstable tree seqnr */ #define UNSTABLE_FLAG 0x100 /* is a node of the unstable tree */ #define STABLE_FLAG 0x200 /* is listed from the stable tree */
/** * 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; unsignedlong scan_time; unsignedlong change; unsignedlonglong cpu_time;
}; staticstruct advisor_ctx advisor_ctx;
/* * Use previous scan time if available, otherwise use current scan time as an * approximation for the previous scan time.
*/ staticinlineunsignedlong prev_scan_time(struct advisor_ctx *ctx, unsignedlong scan_time)
{ return ctx->scan_time ? ctx->scan_time : scan_time;
}
/* * 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 facor * * 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.
*/ staticvoid scan_time_advisor(void)
{ unsignedint cpu_percent; unsignedlong cpu_time; unsignedlong cpu_time_diff; unsignedlong cpu_time_diff_ms; unsignedlong pages; unsignedlong per_page_cost; unsignedlong factor; unsignedlong change; unsignedlong last_scan_time; unsignedlong 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 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;
staticinlinestruct ksm_stable_node *alloc_stable_node(void)
{ /* * The allocation can take too long with GFP_KERNEL when memory is under * pressure, which may lead to hung task warnings. Adding __GFP_HIGH * grants access to memory reserves, helping to avoid this problem.
*/ return kmem_cache_alloc(stable_node_cache, GFP_KERNEL | __GFP_HIGH);
}
/* * 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_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.
*/ staticinlinebool ksm_test_exit(struct mm_struct *mm)
{ return atomic_read(&mm->mm_users) == 0;
}
/* * 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. * * 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, where we would not want to touch it. * * 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.
*/ staticint break_ksm(struct vm_area_struct *vma, unsignedlong addr, bool lock_vma)
{
vm_fault_t ret = 0;
cond_resched();
folio = folio_walk_start(&fw, vma, addr,
FW_MIGRATION | FW_ZEROPAGE); if (folio) { /* Small folio implies FW_LEVEL_PTE. */ if (!folio_test_large(folio) &&
(folio_test_ksm(folio) || is_ksm_zero_pte(fw.pte)))
ksm_page = true;
folio_walk_end(&fw, vma);
}
if (!ksm_page) return 0;
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 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 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 * current task has TIF_MEMDIE set, and will be OOM killed on return * to user; and ksmd, having no mm, would never be chosen for that. * * But if the mm is in a limited mem_cgroup, then the fault may fail * with VM_FAULT_OOM even if the current task is not TIF_MEMDIE; and * even ksmd can fail in this way - though it's usually breaking ksm * just to undo a merge it made a moment before, so unlikely to oom. * * That's a pity: we might therefore have more kernel pages allocated * than we're counting as nodes in the stable tree; but ksm_do_scan * will retry to break_cow on each pass, so should recover the page * in due course. The important thing is to not let VM_MERGEABLE * be cleared while any such pages might remain in the area.
*/ return (ret & VM_FAULT_OOM) ? -ENOMEM : 0;
}
staticbool ksm_compatible(conststruct file *file, vm_flags_t vm_flags)
{ if (vm_flags & (VM_SHARED | VM_MAYSHARE | VM_SPECIAL |
VM_HUGETLB | VM_DROPPABLE)) returnfalse; /* just ignore the advice */
if (file_is_dax(file)) returnfalse;
#ifdef VM_SAO if (vm_flags & VM_SAO) returnfalse; #endif #ifdef VM_SPARC_ADI if (vm_flags & VM_SPARC_ADI) returnfalse; #endif
/* * It is not an accident that whenever we want to break COW * to undo, we also need to drop a reference to the anon_vma.
*/
put_anon_vma(rmap_item->anon_vma);
/* * This helper is used for getting right index into array of tree roots. * When merge_across_nodes knob is set to 1, there are only two rb-trees for * stable and unstable pages from all nodes with roots in index 0. Otherwise, * every node has its own stable and unstable tree.
*/ staticinlineint get_kpfn_nid(unsignedlong kpfn)
{ return ksm_merge_across_nodes ? 0 : NUMA(pfn_to_nid(kpfn));
}
/* * Put the stable node chain in the first dimension of * the stable tree and at the same time remove the old * stable node.
*/
rb_replace_node(&dup->node, &chain->node, root);
/* * 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 write protected and have the exact same * content.
*/
stable_node_chain_add_dup(dup, chain);
} return chain;
}
/* * We need the second aligned pointer of the migrate_nodes * 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. 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);
trace_ksm_remove_ksm_page(stable_node->kpfn); if (stable_node->head == &migrate_nodes)
list_del(&stable_node->list); else
stable_node_dup_del(stable_node);
free_stable_node(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, * remove the stale node from the stable tree and return NULL. * But beware, the stable node's page might be being migrated. * * You would expect the stable_node to hold a reference to the ksm page. * But if it increments the page's count, swapping out has to wait for * ksmd to come around again before it can free the page, which may take * seconds or even minutes: much too unresponsive. So instead we use a * "keyhole reference": access to the ksm page from the stable node peeps * out through its keyhole to see if that page still holds the right key, * pointing back to this stable node. This relies on freeing a PageAnon * page to reset its page->mapping to NULL, and relies on no other use of * 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.
*/ staticstruct folio *ksm_get_folio(struct ksm_stable_node *stable_node, enum ksm_get_folio_flags flags)
{ struct folio *folio; void *expected_mapping; unsignedlong kpfn;
/* * 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_ref_freeze(). * The __remove_mapping() case is easy, again the node is now stale; * 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 (!folio_try_get(folio)) { /* * 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 (!folio_test_swapcache(folio)) goto stale;
cpu_relax();
}
if (READ_ONCE(folio->mapping) != expected_mapping) {
folio_put(folio); goto stale;
}
if (flags == KSM_GET_FOLIO_TRYLOCK) { if (!folio_trylock(folio)) {
folio_put(folio); return ERR_PTR(-EBUSY);
}
} elseif (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 folio;
stale: /* * 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 folio_migrate_ksm(), * before checking whether node->kpfn has been changed.
*/
smp_rmb(); if (READ_ONCE(stable_node->kpfn) != kpfn) goto again;
remove_node_from_stable_tree(stable_node); return NULL;
}
/* * Removing rmap_item from stable or unstable tree. * This function will clean the information from the stable/unstable tree.
*/ staticvoid remove_rmap_item_from_tree(struct ksm_rmap_item *rmap_item)
{ if (rmap_item->address & STABLE_FLAG) { struct ksm_stable_node *stable_node; struct folio *folio;
} elseif (rmap_item->address & UNSTABLE_FLAG) { unsignedchar age; /* * Usually ksmd can and must skip the rb_erase, because * root_unstable_tree was already reset to RB_ROOT. * But be careful when an mm is exiting: do the rb_erase * if this rmap_item was inserted by this scan, rather * than left over from before.
*/
age = (unsignedchar)(ksm_scan.seqnr - rmap_item->address);
BUG_ON(age > 1); if (!age)
rb_erase(&rmap_item->node,
root_unstable_tree + NUMA(rmap_item->nid));
ksm_pages_unshared--;
rmap_item->address &= PAGE_MASK;
}
out:
cond_resched(); /* we're called from many long loops */
}
/* * 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). * * 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.
*/ staticint unmerge_ksm_pages(struct vm_area_struct *vma, unsignedlong start, unsignedlong end, bool lock_vma)
{ unsignedlong addr; int err = 0;
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, lock_vma);
} return err;
}
#ifdef CONFIG_SYSFS /* * Only called through the sysfs control interface:
*/ staticint remove_stable_node(struct ksm_stable_node *stable_node)
{ struct folio *folio; int err;
folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_LOCK); if (!folio) { /* * ksm_get_folio did remove_node_from_stable_tree itself.
*/ return 0;
}
/* * 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 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 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.
*/
folio_set_stable_node(folio, NULL);
remove_node_from_stable_tree(stable_node);
err = 0;
}
if (!is_stable_node_chain(stable_node)) {
VM_BUG_ON(is_stable_node_dup(stable_node)); if (remove_stable_node(stable_node)) returntrue; else returnfalse;
}
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;
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;
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 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(vma, pvmw.address, pvmw.pte); /* * Check that no O_DIRECT or similar I/O is in progress on the * 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))
folio_mark_dirty(folio);
entry = pte_mkclean(entry);
if (pte_write(entry))
entry = pte_wrprotect(entry);
/** * replace_page - replace page in vma by new ksm page * @vma: vma that holds the pte pointing to page * @page: the page we are replacing by kpage * @kpage: the ksm page we replace page by * @orig_pte: the original value of the pte * * Returns 0 on success, -EFAULT on failure.
*/ staticint 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; unsignedlong addr; int err = -EFAULT; struct mmu_notifier_range range;
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;
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr,
addr + PAGE_SIZE);
mmu_notifier_invalidate_range_start(&range);
/* * No need to check ksm_use_zero_pages here: we can only have a * zero_page here if ksm_use_zero_pages was enabled already.
*/ if (!is_zero_pfn(page_to_pfn(kpage))) {
folio_get(kfolio);
folio_add_anon_rmap_pte(kfolio, kpage, vma, addr, RMAP_NONE);
newpte = mk_pte(kpage, vma->vm_page_prot);
} else { /* * 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_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);
folio_remove_rmap_pte(folio, page, vma); if (!folio_mapped(folio))
folio_free_swap(folio);
folio_put(folio);
/* * 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 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.
*/ staticint 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;
/* * 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 (!folio_trylock(folio)) goto out;
if (folio_test_large(folio)) { if (split_huge_page(page)) goto out_unlock;
folio = page_folio(page);
}
/* * If this anonymous page is mapped only here, its pte may need * to be write-protected. If it's mapped elsewhere, all of its * 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, folio, &orig_pte) == 0) { if (!kpage) { /* * 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.
*/
folio_set_stable_node(folio, NULL);
folio_mark_accessed(folio); /* * Page reclaim just frees a clean folio with no dirty * ptes: make sure that the ksm page would be swapped.
*/ if (!folio_test_dirty(folio))
folio_mark_dirty(folio);
err = 0;
} elseif (pages_identical(page, kpage))
err = replace_page(vma, page, kpage, orig_pte);
}
/* * This function returns 0 if the pages were merged or if they are * no longer merging candidates (e.g., VMA stale), -EFAULT otherwise.
*/ staticint 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);
}
return err;
}
/* * try_to_merge_with_ksm_page - like try_to_merge_two_pages, * but no new kernel page is allocated: kpage must already be a ksm page. * * This function returns 0 if the pages were merged, -EFAULT otherwise.
*/ staticint 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;
mmap_read_lock(mm);
vma = find_mergeable_vma(mm, rmap_item->address); if (!vma) goto out;
err = try_to_merge_one_page(vma, page, kpage); if (err) goto out;
/* 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_lock */
rmap_item->anon_vma = vma->anon_vma;
get_anon_vma(vma->anon_vma);
out:
mmap_read_unlock(mm);
trace_ksm_merge_with_ksm_page(kpage, page_to_pfn(kpage ? kpage : page),
rmap_item, mm, err); return err;
}
/* * try_to_merge_two_pages - take two identical pages and prepare them * to be merged into one page. * * This function returns the kpage if we successfully merged two identical * pages into one ksm page, NULL otherwise. * * 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.
*/ staticstruct folio *try_to_merge_two_pages(struct ksm_rmap_item *rmap_item, struct page *page, struct ksm_rmap_item *tree_rmap_item, struct page *tree_page)
{ int err;
err = try_to_merge_with_ksm_page(rmap_item, page, NULL); if (!err) {
err = try_to_merge_with_ksm_page(tree_rmap_item,
tree_page, page); /* * If that fails, we have a ksm page with only one pte * pointing to it: so break it.
*/ if (err)
break_cow(rmap_item);
} return err ? NULL : page_folio(page);
}
static __always_inline bool __is_page_sharing_candidate(struct ksm_stable_node *stable_node, int offset)
{
VM_BUG_ON(stable_node->rmap_hlist_len < 0); /* * Check that at least one mapping still exists, otherwise * there's no much point to merge and share with this * stable_node, as the underlying tree_page of the other * sharer is going to be freed soon.
*/ return stable_node->rmap_hlist_len &&
stable_node->rmap_hlist_len + offset < ksm_max_page_sharing;
}
hlist_for_each_entry_safe(dup, hlist_safe,
&stable_node->hlist, hlist_dup) {
cond_resched(); /* * We must walk all stable_node_dup to prune the stale * stable nodes during lookup. * * 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.
*/
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;
}
folio_put(folio);
}
if (found) { 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 * context with no lock held it's not even * fatal.
*/
BUG_ON(stable_node->hlist.first->next);
/* * There's just one entry and it is below the * deduplication limit so drop the chain.
*/
rb_replace_node(&stable_node->node, &found->node,
root);
free_stable_node(stable_node);
ksm_stable_node_chains--;
ksm_stable_node_dups--; /* * NOTE: the caller depends on the stable_node * to be equal to stable_node_dup if the chain * was collapsed.
*/
*_stable_node = found; /* * Just for robustness, as stable_node is * otherwise left as a stable pointer, the * compiler shall optimize it away at build * time.
*/
stable_node = NULL;
} elseif (stable_node->hlist.first != &found->hlist_dup &&
__is_page_sharing_candidate(found, 1)) { /* * If the found stable_node dup can accept one * more future merge (in addition to the one * that is underway) and is not at the head of * the chain, put it there so next search will * be quicker in the !prune_stale_stable_nodes * case. * * NOTE: it would be inaccurate to use nr > 1 * instead of checking the hlist.first pointer * directly, because in the * prune_stale_stable_nodes case "nr" isn't * the position of the found dup in the chain, * but the total number of dups in the chain.
*/
hlist_del(&found->hlist_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_folio;
}
/* * 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 * stable_node_dup if the chain is collapsed (in which case * *_stable_node will be equal to *_stable_node_dup like if the chain * never existed). It's up to the caller to verify tree_page is not * NULL before dereferencing *_stable_node or *_stable_node_dup. * * *_stable_node_dup is really a second output parameter of this * function and will be overwritten in all cases, the caller doesn't * need to initialize it.
*/ staticstruct 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 ksm_stable_node *stable_node = *_stable_node;
/* * stable_tree_search - search for page inside the stable tree * * This function checks if there is a page inside the stable tree * with identical content to the page that we are scanning right now. * * This function returns the stable tree node of identical content if found, * -EBUSY if the stable node's page is being migrated, NULL otherwise.
*/ staticstruct folio *stable_tree_search(struct page *page)
{ int nid; struct rb_root *root; struct rb_node **new; struct rb_node *parent; struct ksm_stable_node *stable_node, *stable_node_dup; struct ksm_stable_node *page_node; struct folio *folio;
nid = get_kpfn_nid(folio_pfn(folio));
root = root_stable_tree + nid;
again: new = &root->rb_node;
parent = NULL;
while (*new) { struct folio *tree_folio; int ret;
cond_resched();
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, * 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 * false negative insertions just because some * stable_node was stale.
*/ goto again;
}
ret = memcmp_pages(page, &tree_folio->page);
folio_put(tree_folio);
parent = *new; if (ret < 0) new = &parent->rb_left; elseif (ret > 0) new = &parent->rb_right; else { if (page_node) {
VM_BUG_ON(page_node->head != &migrate_nodes); /* * 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 (folio_mapcount(folio) > 1) goto chain_append;
}
if (!is_page_sharing_candidate(stable_node_dup)) { /* * If the stable_node is a chain and * we got a payload match in memcmp * but we cannot merge the scanned * page in any of the existing * stable_node dups because they're * all full, we need to wait the * scanned page to find itself a match * in the unstable tree to create a * brand new KSM page to add later to * the dups of this stable_node.
*/ return NULL;
}
/* * Lock and unlock the stable_node's page (which * might already have been migrated) so that page * migration is sure to notice its raised count. * It would be more elegant to return stable_node * than kpage, but that involves more changes.
*/
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;
folio_unlock(tree_folio);
replace: /* * If stable_node was a chain and chain_prune collapsed it, * stable_node has been updated to be the new regular * stable_node. A collapse of the chain is indistinguishable * from the case there was no chain in the stable * rbtree. Otherwise stable_node is the chain and * 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)); /* there is no chain */ if (page_node) {
VM_BUG_ON(page_node->head != &migrate_nodes);
list_del(&page_node->list);
DO_NUMA(page_node->nid = nid);
rb_replace_node(&stable_node_dup->node,
&page_node->node,
root); if (is_page_sharing_candidate(page_node))
folio_get(folio); else
folio = NULL;
} else {
rb_erase(&stable_node_dup->node, root);
folio = NULL;
}
} else {
VM_BUG_ON(!is_stable_node_chain(stable_node));
__stable_node_dup_del(stable_node_dup); if (page_node) {
VM_BUG_ON(page_node->head != &migrate_nodes);
list_del(&page_node->list);
DO_NUMA(page_node->nid = nid);
stable_node_chain_add_dup(page_node, stable_node); if (is_page_sharing_candidate(page_node))
folio_get(folio); else
folio = NULL;
} else {
folio = NULL;
}
}
stable_node_dup->head = &migrate_nodes;
list_add(&stable_node_dup->list, stable_node_dup->head); return folio;
chain_append: /* * If stable_node was a chain and chain_prune collapsed it, * stable_node has been updated to be the new regular * stable_node. A collapse of the chain is indistinguishable * from the case there was no chain in the stable * rbtree. Otherwise stable_node is the chain and * stable_node_dup is the dup to replace.
*/ if (stable_node_dup == stable_node) {
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,
root); if (!stable_node) return NULL;
} /* * Add this stable_node dup that was * migrated to the stable_node chain * of the current nid for this page * content.
*/
VM_BUG_ON(!is_stable_node_dup(stable_node_dup));
VM_BUG_ON(page_node->head != &migrate_nodes);
list_del(&page_node->list);
DO_NUMA(page_node->nid = nid);
stable_node_chain_add_dup(page_node, stable_node); goto out;
}
/* * stable_tree_insert - insert stable tree node pointing to new ksm page * into the stable tree. * * This function returns the stable tree node just allocated on success, * NULL otherwise.
*/ staticstruct ksm_stable_node *stable_tree_insert(struct folio *kfolio)
{ int nid; unsignedlong kpfn; struct rb_root *root; struct rb_node **new; struct rb_node *parent; struct ksm_stable_node *stable_node, *stable_node_dup; bool need_chain = false;
kpfn = folio_pfn(kfolio);
nid = get_kpfn_nid(kpfn);
root = root_stable_tree + nid;
again:
parent = NULL; new = &root->rb_node;
while (*new) { struct folio *tree_folio; int ret;
cond_resched();
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, * 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 * false negative insertions just because some * stable_node was stale.
*/ goto again;
}
ret = memcmp_pages(&kfolio->page, &tree_folio->page);
folio_put(tree_folio);
parent = *new; if (ret < 0) new = &parent->rb_left; elseif (ret > 0) new = &parent->rb_right; else {
need_chain = true; break;
}
}
stable_node_dup = alloc_stable_node(); if (!stable_node_dup) return NULL;
INIT_HLIST_HEAD(&stable_node_dup->hlist);
stable_node_dup->kpfn = kpfn;
stable_node_dup->rmap_hlist_len = 0;
DO_NUMA(stable_node_dup->nid = nid); if (!need_chain) {
rb_link_node(&stable_node_dup->node, parent, new);
rb_insert_color(&stable_node_dup->node, root);
} else { if (!is_stable_node_chain(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) {
free_stable_node(stable_node_dup); return NULL;
}
}
stable_node_chain_add_dup(stable_node_dup, stable_node);
}
folio_set_stable_node(kfolio, stable_node_dup);
return stable_node_dup;
}
/* * unstable_tree_search_insert - search for identical page, * else insert rmap_item into the unstable tree. * * This function searches for a page in the unstable tree identical to the * page currently being scanned; and if no identical page is found in the * tree, we insert rmap_item as a new object into the unstable tree. * * This function returns pointer to rmap_item found to be identical * to the currently scanned page, NULL otherwise. * * This function does both searching and inserting, because they share * the same walking algorithm in an rbtree.
*/ static struct ksm_rmap_item *unstable_tree_search_insert(struct ksm_rmap_item *rmap_item, struct page *page, struct page **tree_pagep)
{ struct rb_node **new; struct rb_root *root; struct rb_node *parent = NULL; int nid;
nid = get_kpfn_nid(page_to_pfn(page));
root = root_unstable_tree + nid; new = &root->rb_node;
while (*new) { struct ksm_rmap_item *tree_rmap_item; struct page *tree_page; int ret;
/* * Don't substitute a ksm page for a forked page.
*/ if (page == tree_page) {
put_page(tree_page); return NULL;
}
ret = memcmp_pages(page, tree_page);
parent = *new; if (ret < 0) {
put_page(tree_page); new = &parent->rb_left;
} elseif (ret > 0) {
put_page(tree_page); new = &parent->rb_right;
} elseif (!ksm_merge_across_nodes &&
page_to_nid(tree_page) != nid) { /* * If tree_page has been migrated to another NUMA node, * it will be flushed out and put in the right unstable * tree next time: only merge with it when across_nodes.
*/
put_page(tree_page); return NULL;
} else {
*tree_pagep = tree_page; return tree_rmap_item;
}
}
/* * stable_tree_append - add another rmap_item to the linked list of * rmap_items hanging off a given node of the stable tree, all sharing * the same ksm page.
*/ staticvoid stable_tree_append(struct ksm_rmap_item *rmap_item, struct ksm_stable_node *stable_node, bool max_page_sharing_bypass)
{ /* * rmap won't find this mapping if we don't insert the * rmap_item in the right stable_node * duplicate. page_migration could break later if rmap breaks, * so we can as well crash here. We really need to check for
--> --------------------
--> maximum size reached
--> --------------------
Messung V0.5
¤ Dauer der Verarbeitung: 0.25 Sekunden
(vorverarbeitet)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.