litmus-rt.git - The LITMUS^RT kernel.

diff options

author	Greg Kroah-Hartman <gregkh@suse.de>	2007-11-06 18:03:30 -0500
committer	Greg Kroah-Hartman <gregkh@suse.de>	2008-01-24 23:40:24 -0500
commit	2fb9113b974c3c7c43e76647bd5077238e274e1c (patch)
tree	b87912c7d2c7a24b35a9a5e82fe462d7cffcbacb
parent	0ff21e46630abce11fdaaffabd72bbd4eed5ac2c (diff)

kobject: remove subsystem_(un)register functions

These functions are no longer used and are the last remants of the old subsystem crap. So delete them for good. Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

Diffstat

-rw-r--r--

drivers/base/bus.c

-rw-r--r--

drivers/base/class.c

-rw-r--r--

include/linux/kobject.h

-rw-r--r--

lib/kobject.c

4 files changed, 5 insertions, 21 deletions

         bus->subsys.kobj.kset = bus_kset;
         bus->subsys.kobj.ktype = &bus_ktype;
-        retval = subsystem_register(&bus->subsys);
+        retval = kset_register(&bus->subsys);
         if (retval)
                 goto out;
 bus_devices_fail:
         bus_remove_file(bus, &bus_attr_uevent);
 bus_uevent_fail:
-        subsystem_unregister(&bus->subsys);
+        kset_unregister(&bus->subsys);
 out:
         return retval;
 }
         kset_unregister(bus->drivers_kset);
         kset_unregister(bus->devices_kset);
         bus_remove_file(bus, &bus_attr_uevent);
-        subsystem_unregister(&bus->subsys);
+        kset_unregister(&bus->subsys);
 }
 int bus_register_notifier(struct bus_type *bus, struct notifier_block *nb)
         cls->subsys.kobj.kset = class_kset;
         cls->subsys.kobj.ktype = &class_ktype;
-        error = subsystem_register(&cls->subsys);
+        error = kset_register(&cls->subsys);
         if (!error) {
                 error = add_class_attrs(class_get(cls));
                 class_put(cls);
 {
         pr_debug("device class '%s': unregistering\n", cls->name);
         remove_class_attrs(cls);
-        subsystem_unregister(&cls->subsys);
+        kset_unregister(&cls->subsys);
 }
 static void class_create_release(struct class *cls)
 /* The global /sys/firmware/ kobject for people to chain off of */
 extern struct kobject *firmware_kobj;
-extern int __must_check subsystem_register(struct kset *);
-extern void subsystem_unregister(struct kset *);
 #if defined(CONFIG_HOTPLUG)
 int kobject_uevent(struct kobject *kobj, enum kobject_action action);
 int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
         return ret;
 }
-int subsystem_register(struct kset *s)
-{
-        return kset_register(s);
-}
-void subsystem_unregister(struct kset *s)
-{
-        kset_unregister(s);
-}
 static void kset_release(struct kobject *kobj)
 {
         struct kset *kset = container_of(kobj, struct kset, kobj);
 EXPORT_SYMBOL(kset_register);
 EXPORT_SYMBOL(kset_unregister);
-EXPORT_SYMBOL(subsystem_register);
-EXPORT_SYMBOL(subsystem_unregister);

463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515

689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752

/* * 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 * * This work is licensed under the terms of the GNU GPL, version 2. */ #include <linux/errno.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/mman.h> #include <linux/sched.h> #include <linux/rwsem.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/spinlock.h> #include <linux/jhash.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/wait.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/memory.h> #include <linux/mmu_notifier.h> #include <linux/swap.h> #include <linux/ksm.h> #include <asm/tlbflush.h> #include "internal.h" /* * 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. * * 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.) */ /** * 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 * @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_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 mm_slot *mm_slot; unsigned long address; struct rmap_item **rmap_list; unsigned long seqnr; }; /** * struct stable_node - node of the stable rbtree * @node: rb node of this ksm page in the stable tree * @hlist: hlist head of rmap_items using this ksm page * @kpfn: page frame number of this ksm page */ struct stable_node { struct rb_node node; struct hlist_head hlist; unsigned long kpfn; }; /** * struct 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 * @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 */ struct rmap_item { struct rmap_item *rmap_list; struct anon_vma *anon_vma; /* when stable */ struct mm_struct *mm; unsigned long address; /* + low bits used for flags below */ unsigned int oldchecksum; /* when unstable */ union { struct rb_node node; /* when node of unstable tree */ struct { /* when listed from stable tree */ struct 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 */ /* The stable and unstable tree heads */ static struct rb_root root_stable_tree = RB_ROOT; static struct rb_root root_unstable_tree = RB_ROOT; #define MM_SLOTS_HASH_HEADS 1024 static struct hlist_head *mm_slots_hash; static struct mm_slot ksm_mm_head = { .mm_list = LIST_HEAD_INIT(ksm_mm_head.mm_list), }; static struct ksm_scan ksm_scan = { .mm_slot = &ksm_mm_head, }; static struct kmem_cache *rmap_item_cache; static struct kmem_cache *stable_node_cache; static struct kmem_cache *mm_slot_cache; /* The number of nodes in the stable tree */ static unsigned long ksm_pages_shared; /* The number of page slots additionally sharing those nodes */ static unsigned long ksm_pages_sharing; /* The number of nodes in the unstable tree */ static unsigned long ksm_pages_unshared; /* The number of rmap_items in use: to calculate pages_volatile */ static unsigned long ksm_rmap_items; /* Number of pages ksmd should scan in one batch */ static unsigned int ksm_thread_pages_to_scan = 100; /* Milliseconds ksmd should sleep between batches */ static unsigned int ksm_thread_sleep_millisecs = 20; #define KSM_RUN_STOP 0 #define KSM_RUN_MERGE 1 #define KSM_RUN_UNMERGE 2 static unsigned int ksm_run = KSM_RUN_STOP; static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_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); if (!rmap_item_cache) goto out; stable_node_cache = KSM_KMEM_CACHE(stable_node, 0); if (!stable_node_cache) goto out_free1; mm_slot_cache = KSM_KMEM_CACHE(mm_slot, 0); if (!mm_slot_cache) goto out_free2; return 0; out_free2: kmem_cache_destroy(stable_node_cache); out_free1: kmem_cache_destroy(rmap_item_cache); out: return -ENOMEM; } static void __init ksm_slab_free(void) { kmem_cache_destroy(mm_slot_cache); kmem_cache_destroy(stable_node_cache); kmem_cache_destroy(rmap_item_cache); mm_slot_cache = NULL; } static inline struct rmap_item *alloc_rmap_item(void) { struct rmap_item *rmap_item; rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL); if (rmap_item) ksm_rmap_items++; return rmap_item; } static inline void free_rmap_item(struct rmap_item *rmap_item) { 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) { return kmem_cache_alloc(stable_node_cache, GFP_KERNEL); } static inline void free_stable_node(struct stable_node *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 int __init mm_slots_hash_init(void) { mm_slots_hash = kzalloc(MM_SLOTS_HASH_HEADS * sizeof(struct hlist_head), GFP_KERNEL); if (!mm_slots_hash) return -ENOMEM; return 0; } static void __init mm_slots_hash_free(void) { kfree(mm_slots_hash); } static struct mm_slot *get_mm_slot(struct mm_struct *mm) { struct mm_slot *mm_slot; struct hlist_head *bucket; struct hlist_node *node; bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct)) % MM_SLOTS_HASH_HEADS]; hlist_for_each_entry(mm_slot, node, bucket, link) { if (mm == mm_slot->mm) return mm_slot; } return NULL; } static void insert_to_mm_slots_hash(struct mm_struct *mm, struct mm_slot *mm_slot) { struct hlist_head *bucket; bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct)) % MM_SLOTS_HASH_HEADS]; mm_slot->mm = mm; hlist_add_head(&mm_slot->link, bucket); } static inline int in_stable_tree(struct rmap_item *rmap_item) { return rmap_item->address & STABLE_FLAG; } static void hold_anon_vma(struct rmap_item *rmap_item, struct anon_vma *anon_vma) { rmap_item->anon_vma = anon_vma; atomic_inc(&anon_vma->ksm_refcount); } static void drop_anon_vma(struct rmap_item *rmap_item) { struct anon_vma *anon_vma = rmap_item->anon_vma; if (atomic_dec_and_lock(&anon_vma->ksm_refcount, &anon_vma->lock)) { int empty = list_empty(&anon_vma->head); spin_unlock(&anon_vma->lock); if (empty) anon_vma_free(anon_vma); } } /* * 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 * 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. */ static inline bool 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: it's a stripped down * * if (get_user_pages(current, mm, addr, 1, 1, 1, &page, NULL) == 1) * put_page(page); * * but taking 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. */ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) { struct page *page; int ret = 0; do { cond_resched(); page = follow_page(vma, addr, FOLL_GET); if (!page) break; if (PageKsm(page)) ret = handle_mm_fault(vma->vm_mm, vma, addr, FAULT_FLAG_WRITE); else ret = VM_FAULT_WRITE; put_page(page); } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | 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. * * 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. * * 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; } static void break_cow(struct rmap_item *rmap_item) { struct mm_struct *mm = rmap_item->mm; unsigned long addr = rmap_item->address; struct vm_area_struct *vma; /* * 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. */ drop_anon_vma(rmap_item); down_read(&mm->mmap_sem); if (ksm_test_exit(mm)) goto out; vma = find_vma(mm, addr); if (!vma || vma->vm_start > addr) goto out; if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) goto out; break_ksm(vma, addr); out: up_read(&mm->mmap_sem); } static struct page *get_mergeable_page(struct 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; down_read(&mm->mmap_sem); if (ksm_test_exit(mm)) goto out; vma = find_vma(mm, addr); if (!vma || vma->vm_start > addr) goto out; if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) goto out; page = follow_page(vma, addr, FOLL_GET); if (!page) goto out; if (PageAnon(page)) { flush_anon_page(vma, page, addr); flush_dcache_page(page); } else { put_page(page); out: page = NULL; } up_read(&mm->mmap_sem); return page; } static void remove_node_from_stable_tree(struct stable_node *stable_node) { struct rmap_item *rmap_item; struct hlist_node *hlist; hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) { if (rmap_item->hlist.next) ksm_pages_sharing--; else ksm_pages_shared--; drop_anon_vma(rmap_item); rmap_item->address &= PAGE_MASK; cond_resched(); } rb_erase(&stable_node->node, &root_stable_tree); free_stable_node(stable_node); } /* * get_ksm_page: 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. * * 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. * * include/linux/pagemap.h page_cache_get_speculative() is a good reference, * but this is different - made simpler by ksm_thread_mutex being held, but * interesting for assuming that no other use of the struct page could ever * put our expected_mapping into page->mapping (or a field of the union which * coincides with page->mapping). The RCU calls are not for KSM at all, but * to keep the page_count protocol described with page_cache_get_speculative. * * Note: it is possible that get_ksm_page() will return NULL one moment, * then page the next, if the page is in between page_freeze_refs() and * page_unfreeze_refs(): this shouldn't be a problem anywhere, the page * 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) { struct page *page; void *expected_mapping; page = pfn_to_page(stable_node->kpfn); expected_mapping = (void *)stable_node + (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM); rcu_read_lock(); if (page->mapping != expected_mapping) goto stale; if (!get_page_unless_zero(page)) goto stale; if (page->mapping != expected_mapping) { put_page(page); goto stale; } rcu_read_unlock(); return page; stale: rcu_read_unlock(); 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. */ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) { if (rmap_item->address & STABLE_FLAG) { struct stable_node *stable_node; struct page *page; stable_node = rmap_item->head; page = get_ksm_page(stable_node); if (!page) goto out; lock_page(page); hlist_del(&rmap_item->hlist); unlock_page(page); put_page(page); if (stable_node->hlist.first) ksm_pages_sharing--; else ksm_pages_shared--; drop_anon_vma(rmap_item); rmap_item->address &= PAGE_MASK; } else if (rmap_item->address & UNSTABLE_FLAG) { unsigned char 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 = (unsigned char)(ksm_scan.seqnr - rmap_item->address); BUG_ON(age > 1); if (!age) rb_erase(&rmap_item->node, &root_unstable_tree); ksm_pages_unshared--; rmap_item->address &= PAGE_MASK; } 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) { while (*rmap_list) { struct 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 in_stable_tree(rmap_item)s 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) { unsigned long 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); } return err; } #ifdef CONFIG_SYSFS /* * Only called through the sysfs control interface: */ static int unmerge_and_remove_all_rmap_items(void) { struct mm_slot *mm_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); 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; if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) continue; err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end); if (err) goto error; } remove_trailing_rmap_items(mm_slot, &mm_slot->rmap_list); spin_lock(&ksm_mmlist_lock); ksm_scan.mm_slot = list_entry(mm_slot->mm_list.next, struct mm_slot, mm_list); if (ksm_test_exit(mm)) { hlist_del(&mm_slot->link); list_del(&mm_slot->mm_list); spin_unlock(&ksm_mmlist_lock); free_mm_slot(mm_slot); clear_bit(MMF_VM_MERGEABLE, &mm->flags); up_read(&mm->mmap_sem); mmdrop(mm); } else { spin_unlock(&ksm_mmlist_lock); up_read(&mm->mmap_sem); } } ksm_scan.seqnr = 0; return 0; error: up_read(&mm->mmap_sem); spin_lock(&ksm_mmlist_lock); ksm_scan.mm_slot = &ksm_mm_head; spin_unlock(&ksm_mmlist_lock); return err; } #endif /* CONFIG_SYSFS */ static u32 calc_checksum(struct page *page) { u32 checksum; void *addr = kmap_atomic(page, KM_USER0); checksum = jhash2(addr, PAGE_SIZE / 4, 17); kunmap_atomic(addr, KM_USER0); return checksum; } static int memcmp_pages(struct page *page1, struct page *page2) { char *addr1, *addr2; int ret; addr1 = kmap_atomic(page1, KM_USER0); addr2 = kmap_atomic(page2, KM_USER1); ret = memcmp(addr1, addr2, PAGE_SIZE); kunmap_atomic(addr2, KM_USER1); kunmap_atomic(addr1, KM_USER0); 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, pte_t *orig_pte) { struct mm_struct *mm = vma->vm_mm; unsigned long addr; pte_t *ptep; spinlock_t *ptl; int swapped; int err = -EFAULT; addr = page_address_in_vma(page, vma); if (addr == -EFAULT) goto out; ptep = page_check_address(page, mm, addr, &ptl, 0); if (!ptep) goto out; if (pte_write(*ptep)) { pte_t entry; swapped = PageSwapCache(page); flush_cache_page(vma, addr, page_to_pfn(page)); /* * Ok this is tricky, when get_user_pages_fast() run it doesnt * take any lock, therefore the check that we are going to make * with the pagecount against the mapcount is racey 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. */ entry = ptep_clear_flush(vma, addr, ptep); /* * Check that no O_DIRECT or similar I/O is in progress on the * page */ if (page_mapcount(page) + 1 + swapped != page_count(page)) { set_pte_at_notify(mm, addr, ptep, entry); goto out_unlock; } entry = pte_wrprotect(entry); set_pte_at_notify(mm, addr, ptep, entry); } *orig_pte = *ptep; err = 0; out_unlock: pte_unmap_unlock(ptep, ptl); out: return err; } /** * 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. */ static int replace_page(struct vm_area_struct *vma, struct page *page, struct page *kpage, pte_t orig_pte) { struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *ptep; spinlock_t *ptl; unsigned long addr; int err = -EFAULT; addr = page_address_in_vma(page, vma); if (addr == -EFAULT) goto out; pgd = pgd_offset(mm, addr); if (!pgd_present(*pgd)) goto out; pud = pud_offset(pgd, addr); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, addr); if (!pmd_present(*pmd)) goto out; ptep = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!pte_same(*ptep, orig_pte)) { pte_unmap_unlock(ptep, ptl); goto out; } get_page(kpage); page_add_anon_rmap(kpage, vma, addr); flush_cache_page(vma, addr, pte_pfn(*ptep)); ptep_clear_flush(vma, addr, ptep); set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot)); page_remove_rmap(page); put_page(page); pte_unmap_unlock(ptep, ptl); err = 0; out: return err; } /* * 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, * or NULL the first time when we want to use page as kpage. * * This function returns 0 if the pages were merged, -EFAULT otherwise. */ static int try_to_merge_one_page(struct vm_area_struct *vma, struct page *page, struct page *kpage) { pte_t orig_pte = __pte(0); int err = -EFAULT; if (page == kpage) /* ksm page forked */ return 0; if (!(vma->vm_flags & VM_MERGEABLE)) goto out; if (!PageAnon(page)) 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. */ if (!trylock_page(page)) goto out; /* * 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, page, &orig_pte) == 0) { if (!kpage) { /* * While we hold page lock, upgrade page from * PageAnon+anon_vma to PageKsm+NULL stable_node: * stable_tree_insert() will update stable_node. */ set_page_stable_node(page, NULL); mark_page_accessed(page); 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 */ } } unlock_page(page); out: 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. */ static int try_to_merge_with_ksm_page(struct 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); if (ksm_test_exit(mm)) goto out; vma = find_vma(mm, rmap_item->address); if (!vma || vma->vm_start > rmap_item->address) goto out; err = try_to_merge_one_page(vma, page, kpage); if (err) goto out; /* Must get reference to anon_vma while still holding mmap_sem */


context:
space:
mode: