diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
index ac23379b7a87634a22137cfbf32ef9eeae0f4e8c..f3258fbf03d0349d1431922d91b74aff5812f776 100644
--- a/arch/alpha/include/uapi/asm/mman.h
+++ b/arch/alpha/include/uapi/asm/mman.h
@@ -68,6 +68,8 @@
#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */
#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */
+#define MADV_COLD 20 /* deactivate these pages */
+
/* compatibility flags */
#define MAP_FILE 0
diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index c2b40969eb1fa5c6ce586395e2c62c08dfc15a1f..00ad09fc5eb16f0c478d5b7dfedda7fb6fc35cd1 100644
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -95,6 +95,8 @@
#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */
#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */
+#define MADV_COLD 20 /* deactivate these pages */
+
/* compatibility flags */
#define MAP_FILE 0
diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index c98162f494dbbed2e08b395e488e033b0ac75ec7..eb14e3a7b8f378ed5b60377158d11c29338b1a8a 100644
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -48,6 +48,8 @@
#define MADV_DONTFORK 10 /* don't inherit across fork */
#define MADV_DOFORK 11 /* do inherit across fork */
+#define MADV_COLD 20 /* deactivate these pages */
+
#define MADV_MERGEABLE 65 /* KSM may merge identical pages */
#define MADV_UNMERGEABLE 66 /* KSM may not merge identical pages */
diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
index ebbb48842190dd0f493e5da7d0c5d1e65edea643..f926b00ff11f96a88b0d7b6dcab6d1217f1fbb63 100644
--- a/arch/xtensa/include/uapi/asm/mman.h
+++ b/arch/xtensa/include/uapi/asm/mman.h
@@ -103,6 +103,8 @@
#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */
#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */
+#define MADV_COLD 20 /* deactivate these pages */
+
/* compatibility flags */
#define MAP_FILE 0
diff --git a/include/linux/swap.h b/include/linux/swap.h
index de2c67a33b7e7e9ed09eccb577e6b991731084a2..0ce997edb8bbc44b5d330265e6253f05328b8018 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -340,6 +340,7 @@ extern void lru_add_drain_cpu(int cpu);
extern void lru_add_drain_all(void);
extern void rotate_reclaimable_page(struct page *page);
extern void deactivate_file_page(struct page *page);
+extern void deactivate_page(struct page *page);
extern void mark_page_lazyfree(struct page *page);
extern void swap_setup(void);
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index 63b1f506ea678200d9433002e207ee9cf7996ad9..23431faf0eb6e8509f3cf32a078ac698806b88df 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -67,6 +67,8 @@
#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */
#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */
+#define MADV_COLD 20 /* deactivate these pages */
+
/* compatibility flags */
#define MAP_FILE 0
diff --git a/mm/internal.h b/mm/internal.h
index e32390802fd3f10b3972c4b30e96b6b2db72ffa7..0d5f720c75abf0291d4c2a3f494cb7d6553804bd 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -39,7 +39,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf);
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
unsigned long floor, unsigned long ceiling);
-static inline bool can_madv_dontneed_vma(struct vm_area_struct *vma)
+static inline bool can_madv_lru_vma(struct vm_area_struct *vma)
{
return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP));
}
diff --git a/mm/madvise.c b/mm/madvise.c
index 1f8a6fdc687856f12b406bb381acfc75946519e3..e1aee62967c3a9015b22ebaff023d82ea838a27d 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -11,6 +11,7 @@
#include <linux/syscalls.h>
#include <linux/mempolicy.h>
#include <linux/page-isolation.h>
+#include <linux/page_idle.h>
#include <linux/userfaultfd_k.h>
#include <linux/hugetlb.h>
#include <linux/falloc.h>
@@ -42,6 +43,7 @@ static int madvise_need_mmap_write(int behavior)
case MADV_REMOVE:
case MADV_WILLNEED:
case MADV_DONTNEED:
+ case MADV_COLD:
case MADV_FREE:
return 0;
default:
@@ -289,6 +291,176 @@ static long madvise_willneed(struct vm_area_struct *vma,
return 0;
}
+static int madvise_cold_pte_range(pmd_t *pmd, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
+{
+ struct mmu_gather *tlb = walk->private;
+ struct mm_struct *mm = tlb->mm;
+ struct vm_area_struct *vma = walk->vma;
+ pte_t *orig_pte, *pte, ptent;
+ spinlock_t *ptl;
+ struct page *page;
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ if (pmd_trans_huge(*pmd)) {
+ pmd_t orig_pmd;
+ unsigned long next = pmd_addr_end(addr, end);
+
+ tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
+ ptl = pmd_trans_huge_lock(pmd, vma);
+ if (!ptl)
+ return 0;
+
+ orig_pmd = *pmd;
+ if (is_huge_zero_pmd(orig_pmd))
+ goto huge_unlock;
+
+ if (unlikely(!pmd_present(orig_pmd))) {
+ VM_BUG_ON(thp_migration_supported() &&
+ !is_pmd_migration_entry(orig_pmd));
+ goto huge_unlock;
+ }
+
+ page = pmd_page(orig_pmd);
+ if (next - addr != HPAGE_PMD_SIZE) {
+ int err;
+
+ if (page_mapcount(page) != 1)
+ goto huge_unlock;
+
+ get_page(page);
+ spin_unlock(ptl);
+ lock_page(page);
+ err = split_huge_page(page);
+ unlock_page(page);
+ put_page(page);
+ if (!err)
+ goto regular_page;
+ return 0;
+ }
+
+ if (pmd_young(orig_pmd)) {
+ pmdp_invalidate(vma, addr, pmd);
+ orig_pmd = pmd_mkold(orig_pmd);
+
+ set_pmd_at(mm, addr, pmd, orig_pmd);
+ tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+ }
+
+ test_and_clear_page_young(page);
+ deactivate_page(page);
+huge_unlock:
+ spin_unlock(ptl);
+ return 0;
+ }
+
+ if (pmd_trans_unstable(pmd))
+ return 0;
+regular_page:
+#endif
+ tlb_change_page_size(tlb, PAGE_SIZE);
+ orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ flush_tlb_batched_pending(mm);
+ arch_enter_lazy_mmu_mode();
+ for (; addr < end; pte++, addr += PAGE_SIZE) {
+ ptent = *pte;
+
+ if (pte_none(ptent))
+ continue;
+
+ if (!pte_present(ptent))
+ continue;
+
+ page = vm_normal_page(vma, addr, ptent);
+ if (!page)
+ continue;
+
+ /*
+ * Creating a THP page is expensive so split it only if we
+ * are sure it's worth. Split it if we are only owner.
+ */
+ if (PageTransCompound(page)) {
+ if (page_mapcount(page) != 1)
+ break;
+ get_page(page);
+ if (!trylock_page(page)) {
+ put_page(page);
+ break;
+ }
+ pte_unmap_unlock(orig_pte, ptl);
+ if (split_huge_page(page)) {
+ unlock_page(page);
+ put_page(page);
+ pte_offset_map_lock(mm, pmd, addr, &ptl);
+ break;
+ }
+ unlock_page(page);
+ put_page(page);
+ pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ pte--;
+ addr -= PAGE_SIZE;
+ continue;
+ }
+
+ VM_BUG_ON_PAGE(PageTransCompound(page), page);
+
+ if (pte_young(ptent)) {
+ ptent = ptep_get_and_clear_full(mm, addr, pte,
+ tlb->fullmm);
+ ptent = pte_mkold(ptent);
+ set_pte_at(mm, addr, pte, ptent);
+ tlb_remove_tlb_entry(tlb, pte, addr);
+ }
+
+ /*
+ * We are deactivating a page for accelerating reclaiming.
+ * VM couldn't reclaim the page unless we clear PG_young.
+ * As a side effect, it makes confuse idle-page tracking
+ * because they will miss recent referenced history.
+ */
+ test_and_clear_page_young(page);
+ deactivate_page(page);
+ }
+
+ arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(orig_pte, ptl);
+ cond_resched();
+
+ return 0;
+}
+
+static const struct mm_walk_ops cold_walk_ops = {
+ .pmd_entry = madvise_cold_pte_range,
+};
+
+static void madvise_cold_page_range(struct mmu_gather *tlb,
+ struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end)
+{
+ tlb_start_vma(tlb, vma);
+ walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, NULL);
+ tlb_end_vma(tlb, vma);
+}
+
+static long madvise_cold(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
+ unsigned long start_addr, unsigned long end_addr)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ struct mmu_gather tlb;
+
+ *prev = vma;
+ if (!can_madv_lru_vma(vma))
+ return -EINVAL;
+
+ lru_add_drain();
+ tlb_gather_mmu(&tlb, mm, start_addr, end_addr);
+ madvise_cold_page_range(&tlb, vma, start_addr, end_addr);
+ tlb_finish_mmu(&tlb, start_addr, end_addr);
+
+ return 0;
+}
+
static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
@@ -493,7 +665,7 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
int behavior)
{
*prev = vma;
- if (!can_madv_dontneed_vma(vma))
+ if (!can_madv_lru_vma(vma))
return -EINVAL;
if (!userfaultfd_remove(vma, start, end)) {
@@ -515,7 +687,7 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
*/
return -ENOMEM;
}
- if (!can_madv_dontneed_vma(vma))
+ if (!can_madv_lru_vma(vma))
return -EINVAL;
if (end > vma->vm_end) {
/*
@@ -669,6 +841,8 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
return madvise_remove(vma, prev, start, end);
case MADV_WILLNEED:
return madvise_willneed(vma, prev, start, end);
+ case MADV_COLD:
+ return madvise_cold(vma, prev, start, end);
case MADV_FREE:
case MADV_DONTNEED:
return madvise_dontneed_free(vma, prev, start, end, behavior);
@@ -690,6 +864,7 @@ madvise_behavior_valid(int behavior)
case MADV_WILLNEED:
case MADV_DONTNEED:
case MADV_FREE:
+ case MADV_COLD:
#ifdef CONFIG_KSM
case MADV_MERGEABLE:
case MADV_UNMERGEABLE:
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index c1d9496b4c4326a1fb633234cce580b5019b9e39..71e3acea781764248161da9d7e80046fe823eb72 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -523,7 +523,7 @@ bool __oom_reap_task_mm(struct mm_struct *mm)
set_bit(MMF_UNSTABLE, &mm->flags);
for (vma = mm->mmap ; vma; vma = vma->vm_next) {
- if (!can_madv_dontneed_vma(vma))
+ if (!can_madv_lru_vma(vma))
continue;
/*
diff --git a/mm/swap.c b/mm/swap.c
index 784dc162062004e9b9e8540095c6fa1201e223f8..38c3fa4308e210e4b70bf9b47ab2699d41111e98 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -47,6 +47,7 @@ int page_cluster;
static DEFINE_PER_CPU(struct pagevec, lru_add_pvec);
static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs);
+static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);
static DEFINE_PER_CPU(struct pagevec, lru_lazyfree_pvecs);
#ifdef CONFIG_SMP
static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);
@@ -538,6 +539,22 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec,
update_page_reclaim_stat(lruvec, file, 0);
}
+static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec,
+ void *arg)
+{
+ if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
+ int file = page_is_file_cache(page);
+ int lru = page_lru_base_type(page);
+
+ del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE);
+ ClearPageActive(page);
+ ClearPageReferenced(page);
+ add_page_to_lru_list(page, lruvec, lru);
+
+ __count_vm_events(PGDEACTIVATE, hpage_nr_pages(page));
+ update_page_reclaim_stat(lruvec, file, 0);
+ }
+}
static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec,
void *arg)
@@ -590,6 +607,10 @@ void lru_add_drain_cpu(int cpu)
if (pagevec_count(pvec))
pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
+ pvec = &per_cpu(lru_deactivate_pvecs, cpu);
+ if (pagevec_count(pvec))
+ pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+
pvec = &per_cpu(lru_lazyfree_pvecs, cpu);
if (pagevec_count(pvec))
pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL);
@@ -623,6 +644,26 @@ void deactivate_file_page(struct page *page)
}
}
+/*
+ * deactivate_page - deactivate a page
+ * @page: page to deactivate
+ *
+ * deactivate_page() moves @page to the inactive list if @page was on the active
+ * list and was not an unevictable page. This is done to accelerate the reclaim
+ * of @page.
+ */
+void deactivate_page(struct page *page)
+{
+ if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
+ struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
+
+ get_page(page);
+ if (!pagevec_add(pvec, page) || PageCompound(page))
+ pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
+ put_cpu_var(lru_deactivate_pvecs);
+ }
+}
+
/**
* mark_page_lazyfree - make an anon page lazyfree
* @page: page to deactivate
@@ -687,6 +728,7 @@ void lru_add_drain_all(void)
if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) ||
+ pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
pagevec_count(&per_cpu(lru_lazyfree_pvecs, cpu)) ||
need_activate_page_drain(cpu)) {
INIT_WORK(work, lru_add_drain_per_cpu);