#include <linux/hashtable.h>
#include <linux/userfaultfd_k.h>
#include <linux/page_idle.h>
+#include <linux/swapops.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
SCAN_SWAP_CACHE_PAGE,
SCAN_DEL_PAGE_LRU,
SCAN_ALLOC_HUGE_PAGE_FAIL,
- SCAN_CGROUP_CHARGE_FAIL
+ SCAN_CGROUP_CHARGE_FAIL,
+ SCAN_EXCEED_SWAP_PTE
};
#define CREATE_TRACE_POINTS
* fault.
*/
static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1;
+static unsigned int khugepaged_max_ptes_swap __read_mostly = HPAGE_PMD_NR/8;
static int khugepaged(void *none);
static int khugepaged_slab_init(void);
__ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show,
khugepaged_max_ptes_none_store);
+static ssize_t khugepaged_max_ptes_swap_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%u\n", khugepaged_max_ptes_swap);
+}
+
+static ssize_t khugepaged_max_ptes_swap_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ int err;
+ unsigned long max_ptes_swap;
+
+ err = kstrtoul(buf, 10, &max_ptes_swap);
+ if (err || max_ptes_swap > HPAGE_PMD_NR-1)
+ return -EINVAL;
+
+ khugepaged_max_ptes_swap = max_ptes_swap;
+
+ return count;
+}
+
+static struct kobj_attribute khugepaged_max_ptes_swap_attr =
+ __ATTR(max_ptes_swap, 0644, khugepaged_max_ptes_swap_show,
+ khugepaged_max_ptes_swap_store);
+
static struct attribute *khugepaged_attr[] = {
&khugepaged_defrag_attr.attr,
&khugepaged_max_ptes_none_attr.attr,
&full_scans_attr.attr,
&scan_sleep_millisecs_attr.attr,
&alloc_sleep_millisecs_attr.attr,
+ &khugepaged_max_ptes_swap_attr.attr,
NULL,
};
return true;
}
+/*
+ * Bring missing pages in from swap, to complete THP collapse.
+ * Only done if khugepaged_scan_pmd believes it is worthwhile.
+ *
+ * Called and returns without pte mapped or spinlocks held,
+ * but with mmap_sem held to protect against vma changes.
+ */
+
+static void __collapse_huge_page_swapin(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmd)
+{
+ unsigned long _address;
+ pte_t *pte, pteval;
+ int swapped_in = 0, ret = 0;
+
+ pte = pte_offset_map(pmd, address);
+ for (_address = address; _address < address + HPAGE_PMD_NR*PAGE_SIZE;
+ pte++, _address += PAGE_SIZE) {
+ pteval = *pte;
+ if (!is_swap_pte(pteval))
+ continue;
+ swapped_in++;
+ ret = do_swap_page(mm, vma, _address, pte, pmd,
+ FAULT_FLAG_ALLOW_RETRY|FAULT_FLAG_RETRY_NOWAIT,
+ pteval);
+ if (ret & VM_FAULT_ERROR) {
+ trace_mm_collapse_huge_page_swapin(mm, swapped_in, 0);
+ return;
+ }
+ /* pte is unmapped now, we need to map it */
+ pte = pte_offset_map(pmd, _address);
+ }
+ pte--;
+ pte_unmap(pte);
+ trace_mm_collapse_huge_page_swapin(mm, swapped_in, 1);
+}
+
static void collapse_huge_page(struct mm_struct *mm,
unsigned long address,
struct page **hpage,
goto out;
}
+ __collapse_huge_page_swapin(mm, vma, address, pmd);
+
anon_vma_lock_write(vma->anon_vma);
pte = pte_offset_map(pmd, address);
result = SCAN_SUCCEED;
out_up_write:
up_write(&mm->mmap_sem);
- trace_mm_collapse_huge_page(mm, isolated, result);
- return;
-
out_nolock:
trace_mm_collapse_huge_page(mm, isolated, result);
return;
struct page *page = NULL;
unsigned long _address;
spinlock_t *ptl;
- int node = NUMA_NO_NODE;
+ int node = NUMA_NO_NODE, unmapped = 0;
bool writable = false, referenced = false;
VM_BUG_ON(address & ~HPAGE_PMD_MASK);
for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR;
_pte++, _address += PAGE_SIZE) {
pte_t pteval = *_pte;
+ if (is_swap_pte(pteval)) {
+ if (++unmapped <= khugepaged_max_ptes_swap) {
+ continue;
+ } else {
+ result = SCAN_EXCEED_SWAP_PTE;
+ goto out_unmap;
+ }
+ }
if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
if (!userfaultfd_armed(vma) &&
++none_or_zero <= khugepaged_max_ptes_none) {
}
out:
trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
- none_or_zero, result);
+ none_or_zero, result, unmapped);
return ret;
}
}
}
-static int __split_huge_page_tail(struct page *head, int tail,
+static void __split_huge_page_tail(struct page *head, int tail,
struct lruvec *lruvec, struct list_head *list)
{
- int mapcount;
struct page *page_tail = head + tail;
- mapcount = atomic_read(&page_tail->_mapcount) + 1;
+ VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail);
VM_BUG_ON_PAGE(atomic_read(&page_tail->_count) != 0, page_tail);
/*
* tail_page->_count is zero and not changing from under us. But
* get_page_unless_zero() may be running from under us on the
- * tail_page. If we used atomic_set() below instead of atomic_add(), we
+ * tail_page. If we used atomic_set() below instead of atomic_inc(), we
* would then run atomic_set() concurrently with
* get_page_unless_zero(), and atomic_set() is implemented in C not
* using locked ops. spin_unlock on x86 sometime uses locked ops
* because of PPro errata 66, 92, so unless somebody can guarantee
* atomic_set() here would be safe on all archs (and not only on x86),
- * it's safer to use atomic_add().
+ * it's safer to use atomic_inc().
*/
- atomic_add(mapcount + 1, &page_tail->_count);
-
+ atomic_inc(&page_tail->_count);
page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
page_tail->flags |= (head->flags &
page_tail->index = head->index + tail;
page_cpupid_xchg_last(page_tail, page_cpupid_last(head));
lru_add_page_tail(head, page_tail, lruvec, list);
-
- return mapcount;
}
static void __split_huge_page(struct page *page, struct list_head *list)
struct page *head = compound_head(page);
struct zone *zone = page_zone(head);
struct lruvec *lruvec;
- int i, tail_mapcount;
+ int i;
/* prevent PageLRU to go away from under us, and freeze lru stats */
spin_lock_irq(&zone->lru_lock);
/* complete memcg works before add pages to LRU */
mem_cgroup_split_huge_fixup(head);
- tail_mapcount = 0;
for (i = HPAGE_PMD_NR - 1; i >= 1; i--)
- tail_mapcount += __split_huge_page_tail(head, i, lruvec, list);
- atomic_sub(tail_mapcount, &head->_count);
+ __split_huge_page_tail(head, i, lruvec, list);
ClearPageCompound(head);
spin_unlock_irq(&zone->lru_lock);
spin_lock_irqsave(&pgdata->split_queue_lock, flags);
if (list_empty(page_deferred_list(page))) {
+ count_vm_event(THP_DEFERRED_SPLIT_PAGE);
list_add_tail(page_deferred_list(page), &pgdata->split_queue);
pgdata->split_queue_len++;
}
projects / karo-tx-linux.git / blobdiff