#include <linux/mmu_notifier.h>
#include <linux/swap.h>
#include <linux/ksm.h>
-#include <linux/hash.h>
+#include <linux/hashtable.h>
#include <linux/freezer.h>
#include <linux/oom.h>
+#include <linux/numa.h>
#include <asm/tlbflush.h>
#include "internal.h"
+#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
+
/*
* A few notes about the KSM scanning process,
* to make it easier to understand the data structures below:
* @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
+ * @nid: NUMA node id of unstable tree in which linked (may not match page)
* @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 mm_struct *mm;
unsigned long address; /* + low bits used for flags below */
unsigned int oldchecksum; /* when unstable */
+#ifdef CONFIG_NUMA
+ int nid;
+#endif
union {
struct rb_node node; /* when node of unstable tree */
struct { /* when listed from stable 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;
+static struct rb_root root_unstable_tree[MAX_NUMNODES];
+static struct rb_root root_stable_tree[MAX_NUMNODES];
-#define MM_SLOTS_HASH_SHIFT 10
-#define MM_SLOTS_HASH_HEADS (1 << MM_SLOTS_HASH_SHIFT)
-static struct hlist_head mm_slots_hash[MM_SLOTS_HASH_HEADS];
+#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),
/* Milliseconds ksmd should sleep between batches */
static unsigned int ksm_thread_sleep_millisecs = 20;
+#ifdef CONFIG_NUMA
+/* Zeroed when merging across nodes is not allowed */
+static unsigned int ksm_merge_across_nodes = 1;
+#else
+#define ksm_merge_across_nodes 1U
+#endif
+
#define KSM_RUN_STOP 0
#define KSM_RUN_MERGE 1
#define KSM_RUN_UNMERGE 2
static struct mm_slot *get_mm_slot(struct mm_struct *mm)
{
- struct mm_slot *mm_slot;
- struct hlist_head *bucket;
struct hlist_node *node;
+ struct mm_slot *slot;
+
+ hash_for_each_possible(mm_slots_hash, slot, node, link, (unsigned long)mm)
+ if (slot->mm == mm)
+ return slot;
- bucket = &mm_slots_hash[hash_ptr(mm, MM_SLOTS_HASH_SHIFT)];
- 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[hash_ptr(mm, MM_SLOTS_HASH_SHIFT)];
mm_slot->mm = mm;
- hlist_add_head(&mm_slot->link, bucket);
+ hash_add(mm_slots_hash, &mm_slot->link, (unsigned long)mm);
}
static inline int in_stable_tree(struct rmap_item *rmap_item)
return page;
}
+/*
+ * 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.
+ */
+static inline int get_kpfn_nid(unsigned long kpfn)
+{
+ return ksm_merge_across_nodes ? 0 : pfn_to_nid(kpfn);
+}
+
static void remove_node_from_stable_tree(struct stable_node *stable_node)
{
struct rmap_item *rmap_item;
struct hlist_node *hlist;
+ int nid;
hlist_for_each_entry(rmap_item, hlist, &stable_node->hlist, hlist) {
if (rmap_item->hlist.next)
cond_resched();
}
- rb_erase(&stable_node->node, &root_stable_tree);
+ nid = get_kpfn_nid(stable_node->kpfn);
+ rb_erase(&stable_node->node, &root_stable_tree[nid]);
free_stable_node(stable_node);
}
* 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
* 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)
+static struct page *get_ksm_page(struct stable_node *stable_node, bool locked)
{
struct page *page;
void *expected_mapping;
+ unsigned long kpfn;
- 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))
+again:
+ kpfn = ACCESS_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 (ACCESS_ONCE(page->mapping) != expected_mapping)
goto stale;
- if (page->mapping != expected_mapping) {
+
+ /*
+ * 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().
+ * 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.
+ */
+ while (!get_page_unless_zero(page)) {
+ /*
+ * 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().
+ */
+ if (!PageSwapCache(page))
+ goto stale;
+ cpu_relax();
+ }
+
+ if (ACCESS_ONCE(page->mapping) != expected_mapping) {
put_page(page);
goto stale;
}
- rcu_read_unlock();
+
+ if (locked) {
+ lock_page(page);
+ if (ACCESS_ONCE(page->mapping) != expected_mapping) {
+ unlock_page(page);
+ put_page(page);
+ goto stale;
+ }
+ }
return page;
+
stale:
- rcu_read_unlock();
+ /*
+ * We come here from above when page->mapping or !PageSwapCache
+ * suggests that the node is stale; but it might be under migration.
+ * We need smp_rmb(), matching the smp_wmb() in ksm_migrate_page(),
+ * before checking whether node->kpfn has been changed.
+ */
+ smp_rmb();
+ if (ACCESS_ONCE(stable_node->kpfn) != kpfn)
+ goto again;
remove_node_from_stable_tree(stable_node);
return NULL;
}
struct page *page;
stable_node = rmap_item->head;
- page = get_ksm_page(stable_node);
+ page = get_ksm_page(stable_node, true);
if (!page)
goto out;
- lock_page(page);
hlist_del(&rmap_item->hlist);
unlock_page(page);
put_page(page);
age = (unsigned char)(ksm_scan.seqnr - rmap_item->address);
BUG_ON(age > 1);
if (!age)
- rb_erase(&rmap_item->node, &root_unstable_tree);
-
+ rb_erase(&rmap_item->node,
+ &root_unstable_tree[NUMA(rmap_item->nid)]);
ksm_pages_unshared--;
rmap_item->address &= PAGE_MASK;
}
}
/*
- * Though it's very tempting to unmerge in_stable_tree(rmap_item)s rather
+ * 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
/*
* Only called through the sysfs control interface:
*/
+static int remove_stable_node(struct stable_node *stable_node)
+{
+ struct page *page;
+ int err;
+
+ page = get_ksm_page(stable_node, true);
+ if (!page) {
+ /*
+ * get_ksm_page did remove_node_from_stable_tree itself.
+ */
+ return 0;
+ }
+
+ if (WARN_ON_ONCE(page_mapped(page)))
+ err = -EBUSY;
+ else {
+ /*
+ * This page might be in a pagevec waiting to be freed,
+ * or it might be PageSwapCache (perhaps under writeback),
+ * or it might have been removed from swapcache a moment ago.
+ */
+ set_page_stable_node(page, NULL);
+ remove_node_from_stable_tree(stable_node);
+ err = 0;
+ }
+
+ unlock_page(page);
+ put_page(page);
+ return err;
+}
+
+static int remove_all_stable_nodes(void)
+{
+ struct stable_node *stable_node;
+ int nid;
+ int err = 0;
+
+ for (nid = 0; nid < 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);
+ if (remove_stable_node(stable_node)) {
+ err = -EBUSY;
+ break; /* proceed to next nid */
+ }
+ cond_resched();
+ }
+ }
+ return err;
+}
+
static int unmerge_and_remove_all_rmap_items(void)
{
struct mm_slot *mm_slot;
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);
+ hash_del(&mm_slot->link);
list_del(&mm_slot->mm_list);
spin_unlock(&ksm_mmlist_lock);
}
}
+ /* Clean up stable nodes, but don't worry if some are still busy */
+ remove_all_stable_nodes();
ksm_scan.seqnr = 0;
return 0;
*/
static struct page *stable_tree_search(struct page *page)
{
- struct rb_node *node = root_stable_tree.rb_node;
+ struct rb_node *node;
struct stable_node *stable_node;
+ int nid;
stable_node = page_stable_node(page);
if (stable_node) { /* ksm page forked */
return page;
}
+ nid = get_kpfn_nid(page_to_pfn(page));
+ node = root_stable_tree[nid].rb_node;
+
while (node) {
struct page *tree_page;
int ret;
cond_resched();
stable_node = rb_entry(node, struct stable_node, node);
- tree_page = get_ksm_page(stable_node);
+ tree_page = get_ksm_page(stable_node, false);
if (!tree_page)
return NULL;
ret = memcmp_pages(page, tree_page);
+ put_page(tree_page);
- if (ret < 0) {
- put_page(tree_page);
+ if (ret < 0)
node = node->rb_left;
- } else if (ret > 0) {
- put_page(tree_page);
+ else if (ret > 0)
node = node->rb_right;
- } else
+ else {
+ /*
+ * 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_page = get_ksm_page(stable_node, true);
+ if (tree_page)
+ unlock_page(tree_page);
return tree_page;
+ }
}
return NULL;
}
/*
- * stable_tree_insert - insert rmap_item pointing to new ksm page
+ * 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,
*/
static struct stable_node *stable_tree_insert(struct page *kpage)
{
- struct rb_node **new = &root_stable_tree.rb_node;
+ int nid;
+ unsigned long kpfn;
+ struct rb_node **new;
struct rb_node *parent = NULL;
struct stable_node *stable_node;
+ kpfn = page_to_pfn(kpage);
+ nid = get_kpfn_nid(kpfn);
+ new = &root_stable_tree[nid].rb_node;
+
while (*new) {
struct page *tree_page;
int ret;
cond_resched();
stable_node = rb_entry(*new, struct stable_node, node);
- tree_page = get_ksm_page(stable_node);
+ tree_page = get_ksm_page(stable_node, false);
if (!tree_page)
return NULL;
if (!stable_node)
return NULL;
- rb_link_node(&stable_node->node, parent, new);
- rb_insert_color(&stable_node->node, &root_stable_tree);
-
INIT_HLIST_HEAD(&stable_node->hlist);
-
- stable_node->kpfn = page_to_pfn(kpage);
+ stable_node->kpfn = kpfn;
set_page_stable_node(kpage, stable_node);
+ rb_link_node(&stable_node->node, parent, new);
+ rb_insert_color(&stable_node->node, &root_stable_tree[nid]);
return stable_node;
}
struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item,
struct page *page,
struct page **tree_pagep)
-
{
- struct rb_node **new = &root_unstable_tree.rb_node;
+ 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 rmap_item *tree_rmap_item;
return NULL;
}
+ /*
+ * If tree_page has been migrated to another NUMA node, it
+ * will be flushed out and put into the right unstable tree
+ * next time: only merge with it if merge_across_nodes.
+ */
+ if (!ksm_merge_across_nodes && page_to_nid(tree_page) != nid) {
+ put_page(tree_page);
+ return NULL;
+ }
+
ret = memcmp_pages(page, tree_page);
parent = *new;
rmap_item->address |= UNSTABLE_FLAG;
rmap_item->address |= (ksm_scan.seqnr & SEQNR_MASK);
+ DO_NUMA(rmap_item->nid = nid);
rb_link_node(&rmap_item->node, parent, new);
- rb_insert_color(&rmap_item->node, &root_unstable_tree);
+ rb_insert_color(&rmap_item->node, root);
ksm_pages_unshared++;
return NULL;
static void stable_tree_append(struct rmap_item *rmap_item,
struct stable_node *stable_node)
{
+ /*
+ * Usually rmap_item->nid is already set correctly,
+ * but it may be wrong after switching merge_across_nodes.
+ */
+ DO_NUMA(rmap_item->nid = get_kpfn_nid(stable_node->kpfn));
rmap_item->head = stable_node;
rmap_item->address |= STABLE_FLAG;
hlist_add_head(&rmap_item->hlist, &stable_node->hlist);
struct mm_slot *slot;
struct vm_area_struct *vma;
struct rmap_item *rmap_item;
+ int nid;
if (list_empty(&ksm_mm_head.mm_list))
return NULL;
*/
lru_add_drain_all();
- root_unstable_tree = RB_ROOT;
+ for (nid = 0; nid < nr_node_ids; nid++)
+ root_unstable_tree[nid] = RB_ROOT;
spin_lock(&ksm_mmlist_lock);
slot = list_entry(slot->mm_list.next, struct mm_slot, mm_list);
* or when all VM_MERGEABLE areas have been unmapped (and
* mmap_sem then protects against race with MADV_MERGEABLE).
*/
- hlist_del(&slot->link);
+ hash_del(&slot->link);
list_del(&slot->mm_list);
spin_unlock(&ksm_mmlist_lock);
spin_lock(&ksm_mmlist_lock);
insert_to_mm_slots_hash(mm, mm_slot);
/*
- * Insert just behind the scanning cursor, to let the area settle
+ * When KSM_RUN_MERGE (or KSM_RUN_STOP),
+ * insert just behind the scanning cursor, to let the area settle
* down a little; when fork is followed by immediate exec, we don't
* want ksmd to waste time setting up and tearing down an rmap_list.
+ *
+ * But when KSM_RUN_UNMERGE, it's important to insert ahead of its
+ * scanning cursor, otherwise KSM pages in newly forked mms will be
+ * missed: then we might as well insert at the end of the list.
*/
- list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list);
+ if (ksm_run & KSM_RUN_UNMERGE)
+ list_add_tail(&mm_slot->mm_list, &ksm_mm_head.mm_list);
+ else
+ list_add_tail(&mm_slot->mm_list, &ksm_scan.mm_slot->mm_list);
spin_unlock(&ksm_mmlist_lock);
set_bit(MMF_VM_MERGEABLE, &mm->flags);
mm_slot = get_mm_slot(mm);
if (mm_slot && ksm_scan.mm_slot != mm_slot) {
if (!mm_slot->rmap_list) {
- hlist_del(&mm_slot->link);
+ hash_del(&mm_slot->link);
list_del(&mm_slot->mm_list);
easy_to_free = 1;
} else {
}
}
-struct page *ksm_does_need_to_copy(struct page *page,
+struct page *ksm_might_need_to_copy(struct page *page,
struct vm_area_struct *vma, unsigned long address)
{
+ struct anon_vma *anon_vma = page_anon_vma(page);
struct page *new_page;
+ if (PageKsm(page)) {
+ if (page_stable_node(page) &&
+ !(ksm_run & KSM_RUN_UNMERGE))
+ return page; /* 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);
- SetPageSwapBacked(new_page);
__set_page_locked(new_page);
-
- if (!mlocked_vma_newpage(vma, new_page))
- lru_cache_add_lru(new_page, LRU_ACTIVE_ANON);
- else
- add_page_to_unevictable_list(new_page);
}
return new_page;
if (stable_node) {
VM_BUG_ON(stable_node->kpfn != page_to_pfn(oldpage));
stable_node->kpfn = page_to_pfn(newpage);
+ /*
+ * newpage->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).
+ */
+ smp_wmb();
+ set_page_stable_node(oldpage, NULL);
}
}
#endif /* CONFIG_MIGRATION */
#ifdef CONFIG_MEMORY_HOTREMOVE
-static struct stable_node *ksm_check_stable_tree(unsigned long start_pfn,
- unsigned long end_pfn)
+static void ksm_check_stable_tree(unsigned long start_pfn,
+ unsigned long end_pfn)
{
+ struct stable_node *stable_node;
struct rb_node *node;
-
- for (node = rb_first(&root_stable_tree); node; node = rb_next(node)) {
- struct stable_node *stable_node;
-
- stable_node = rb_entry(node, struct stable_node, node);
- if (stable_node->kpfn >= start_pfn &&
- stable_node->kpfn < end_pfn)
- return stable_node;
+ int nid;
+
+ for (nid = 0; nid < nr_node_ids; nid++) {
+ node = rb_first(&root_stable_tree[nid]);
+ while (node) {
+ stable_node = rb_entry(node, struct stable_node, node);
+ if (stable_node->kpfn >= start_pfn &&
+ stable_node->kpfn < end_pfn) {
+ /*
+ * Don't get_ksm_page, page has already gone:
+ * which is why we keep kpfn instead of page*
+ */
+ remove_node_from_stable_tree(stable_node);
+ node = rb_first(&root_stable_tree[nid]);
+ } else
+ node = rb_next(node);
+ cond_resched();
+ }
}
- return NULL;
}
static int ksm_memory_callback(struct notifier_block *self,
unsigned long action, void *arg)
{
struct memory_notify *mn = arg;
- struct stable_node *stable_node;
switch (action) {
case MEM_GOING_OFFLINE:
/*
* 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.
+ * pages which have been offlined: prune those from the tree,
+ * otherwise get_ksm_page() might later try to access a
+ * non-existent struct page.
*/
- while ((stable_node = ksm_check_stable_tree(mn->start_pfn,
- mn->start_pfn + mn->nr_pages)) != NULL)
- remove_node_from_stable_tree(stable_node);
+ ksm_check_stable_tree(mn->start_pfn,
+ mn->start_pfn + mn->nr_pages);
/* fallthrough */
case MEM_CANCEL_OFFLINE:
}
KSM_ATTR(run);
+#ifdef CONFIG_NUMA
+static ssize_t merge_across_nodes_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%u\n", ksm_merge_across_nodes);
+}
+
+static ssize_t merge_across_nodes_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ int err;
+ unsigned long knob;
+
+ err = kstrtoul(buf, 10, &knob);
+ if (err)
+ return err;
+ if (knob > 1)
+ return -EINVAL;
+
+ mutex_lock(&ksm_thread_mutex);
+ if (ksm_merge_across_nodes != knob) {
+ if (ksm_pages_shared || remove_all_stable_nodes())
+ err = -EBUSY;
+ else
+ ksm_merge_across_nodes = knob;
+ }
+ mutex_unlock(&ksm_thread_mutex);
+
+ return err ? err : count;
+}
+KSM_ATTR(merge_across_nodes);
+#endif
+
static ssize_t pages_shared_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
&pages_unshared_attr.attr,
&pages_volatile_attr.attr,
&full_scans_attr.attr,
+#ifdef CONFIG_NUMA
+ &merge_across_nodes_attr.attr,
+#endif
NULL,
};
{
struct task_struct *ksm_thread;
int err;
+ int nid;
err = ksm_slab_init();
if (err)
goto out;
+ for (nid = 0; nid < nr_node_ids; nid++)
+ root_stable_tree[nid] = RB_ROOT;
+
ksm_thread = kthread_run(ksm_scan_thread, NULL, "ksmd");
if (IS_ERR(ksm_thread)) {
printk(KERN_ERR "ksm: creating kthread failed\n");
projects / platform / adaptation / renesas_rcar / renesas_kernel.git / blobdiff