idle memory tracking

This function returns the inode number of the closest online ancestor of the memory cgroup a page is charged to. It is required for exporting information about which page is charged to which cgroup to userspace, which will be introduced by a following patch.

Signed-off-by Vladimir Davydov <[email protected]>

---
 include/linux/memcontrol.h |  1 +
 mm/memcontrol.c            | 23 +++++++++++++++++++++++
 2 files changed, 24 insertions(+)

include/linux/memcontrol.h +1 -0

index 73b02b0a8f60..50069abebc3c 100644
@@ -116,6 +116,7 @@ static inline bool mm_match_cgroup(struct mm_struct *mm,
 
 extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
 extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page);
+extern unsigned long page_cgroup_ino(struct page *page);
 
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
                                   struct mem_cgroup *,

mm/memcontrol.c +23 -1

index acb93c554f6e..894dc2169979 100644
@@ -631,6 +631,29 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
        return &memcg->css;
 }
 
+/**
+ * page_cgroup_ino - return inode number of the memcg a page is charged to
+ * @page: the page
+ *
+ * Look up the closest online ancestor of the memory cgroup @page is charged to
+ * and return its inode number or 0 if @page is not charged to any cgroup. It
+ * is safe to call this function without holding a reference to @page.
+ */
+unsigned long page_cgroup_ino(struct page *page)
+{
+       struct mem_cgroup *memcg;
+       unsigned long ino = 0;
+
+       rcu_read_lock();
+       memcg = READ_ONCE(page->mem_cgroup);
+       while (memcg && !(memcg->css.flags & CSS_ONLINE))
+               memcg = parent_mem_cgroup(memcg);
+       if (memcg)
+               ino = cgroup_ino(memcg->css.cgroup);
+       rcu_read_unlock();
+       return ino;
+}
+
 static struct mem_cgroup_per_zone *
 mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page)
 {
--

2.1.4

Hwpoison allows to filter pages by memory cgroup ino. Currently, it calls try_get_mem_cgroup_from_page to obtain the cgroup from a page and then its ino using cgroup_ino, but now we have an apter method for that, page_cgroup_ino, so use it instead.

Signed-off-by Vladimir Davydov <[email protected]>

---
 mm/hwpoison-inject.c |  5 +----
 mm/memory-failure.c  | 16 ++--------------
 2 files changed, 3 insertions(+), 18 deletions(-)

mm/hwpoison-inject.c +1 -4

index bf73ac17dad4..5015679014c1 100644
@@ -45,12 +45,9 @@ static int hwpoison_inject(void *data, u64 val)
        /*
         * do a racy check with elevated page count, to make sure PG_hwpoison
         * will only be set for the targeted owner (or on a free page).
-        * We temporarily take page lock for try_get_mem_cgroup_from_page().
         * memory_failure() will redo the check reliably inside page lock.
         */
-       lock_page(hpage);
        err = hwpoison_filter(hpage);
-       unlock_page(hpage);
        if (err)
                goto put_out;
 

@@ -126,7 +123,7 @@ static int pfn_inject_init(void)
        if (!dentry)
                goto fail;
 
-#ifdef CONFIG_MEMCG_SWAP
+#ifdef CONFIG_MEMCG
        dentry = debugfs_create_u64("corrupt-filter-memcg", 0600,
                                    hwpoison_dir, &hwpoison_filter_memcg);
        if (!dentry)

mm/memory-failure.c +2 -15

index 1cf7f2988422..97005396a507 100644
@@ -130,27 +130,15 @@ static int hwpoison_filter_flags(struct page *p)
  * can only guarantee that the page either belongs to the memcg tasks, or is
  * a freed page.
  */
-#ifdef CONFIG_MEMCG_SWAP
+#ifdef CONFIG_MEMCG
 u64 hwpoison_filter_memcg;
 EXPORT_SYMBOL_GPL(hwpoison_filter_memcg);
 static int hwpoison_filter_task(struct page *p)
 {
-       struct mem_cgroup *mem;
-       struct cgroup_subsys_state *css;
-       unsigned long ino;
-
        if (!hwpoison_filter_memcg)
                return 0;
 
-       mem = try_get_mem_cgroup_from_page(p);
-       if (!mem)
-               return -EINVAL;
-
-       css = mem_cgroup_css(mem);
-       ino = cgroup_ino(css->cgroup);
-       css_put(css);
-
-       if (ino != hwpoison_filter_memcg)
+       if (page_cgroup_ino(p) != hwpoison_filter_memcg)
                return -EINVAL;
 
        return 0;
--

2.1.4

/proc/kpagecgroup contains a 64-bit inode number of the memory cgroup each page is charged to, indexed by PFN. Having this information is useful for estimating a cgroup working set size.

The file is present if CONFIG_PROC_PAGE_MONITOR && CONFIG_MEMCG.

Signed-off-by Vladimir Davydov <[email protected]>

---
 Documentation/vm/pagemap.txt |  6 ++++-
 fs/proc/page.c               | 53 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 58 insertions(+), 1 deletion(-)

Documentation/vm/pagemap.txt +5 -1

index 6bfbc172cdb9..a9b7afc8fbc6 100644
@@ -5,7 +5,7 @@ pagemap is a new (as of 2.6.25) set of interfaces in the kernel that allow
 userspace programs to examine the page tables and related information by
 reading files in /proc.
 
-There are three components to pagemap:
+There are four components to pagemap:
 
  * /proc/pid/pagemap.  This file lets a userspace process find out which
    physical frame each virtual page is mapped to.  It contains one 64-bit

@@ -65,6 +65,10 @@ There are three components to pagemap:
     23. BALLOON
     24. ZERO_PAGE
 
+ * /proc/kpagecgroup.  This file contains a 64-bit inode number of the
+   memory cgroup each page is charged to, indexed by PFN. Only available when
+   CONFIG_MEMCG is set.
+
 Short descriptions to the page flags:
 
  0. LOCKED

fs/proc/page.c +18 -0

index 7eee2d8b97d9..70d23245dd43 100644
@@ -9,6 +9,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/hugetlb.h>
+#include <linux/memcontrol.h>
 #include <linux/kernel-page-flags.h>
 #include <asm/uaccess.h>
 #include "internal.h"

@@ -225,10 +226,62 @@ static const struct file_operations proc_kpageflags_operations = {
        .read = kpageflags_read,
 };
 
+#ifdef CONFIG_MEMCG
+static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
+                               size_t count, loff_t *ppos)
+{
+       u64 __user *out = (u64 __user *)buf;
+       struct page *ppage;
+       unsigned long src = *ppos;
+       unsigned long pfn;
+       ssize_t ret = 0;
+       u64 ino;
+
+       pfn = src / KPMSIZE;
+       count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
+       if (src & KPMMASK || count & KPMMASK)
+               return -EINVAL;
+
+       while (count > 0) {

fs/proc/page.c +25 -1

+               if (put_user(ino, out)) {
+                       ret = -EFAULT;
+                       break;
+               }
+
+               pfn++;
+               out++;
+               count -= KPMSIZE;
+       }
+
+       *ppos += (char __user *)out - buf;
+       if (!ret)
+               ret = (char __user *)out - buf;
+       return ret;
+}
+
+static const struct file_operations proc_kpagecgroup_operations = {
+       .llseek = mem_lseek,
+       .read = kpagecgroup_read,
+};
+#endif /* CONFIG_MEMCG */
+
 static int __init proc_page_init(void)
 {
        proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);
        proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations);
+#ifdef CONFIG_MEMCG
+       proc_create("kpagecgroup", S_IRUSR, NULL, &proc_kpagecgroup_operations);
+#endif
        return 0;
 }
 fs_initcall(proc_page_init);
--

2.1.4

In the scope of the idle memory tracking feature, which is introduced by the following patch, we need to clear the referenced/accessed bit not only in primary, but also in secondary ptes. The latter is required in order to estimate wss of KVM VMs. At the same time we want to avoid flushing tlb, because it is quite expensive and it won't really affect the final result.

Currently, there is no function for clearing pte young bit that would meet our requirements, so this patch introduces one. To achieve that we have to add a new mmu-notifier callback, clear_young, since there is no method for testing-and-clearing a secondary pte w/o flushing tlb. The new method is not mandatory and currently only implemented by KVM.

Signed-off-by Vladimir Davydov <[email protected]>

---
 include/linux/mmu_notifier.h | 44 ++++++++++++++++++++++++++++++++++++++++++++
 mm/mmu_notifier.c            | 17 +++++++++++++++++
 virt/kvm/kvm_main.c          | 18 ++++++++++++++++++
 3 files changed, 79 insertions(+)

include/linux/mmu_notifier.h +44 -0

index 61cd67f4d788..a5b17137c683 100644
@@ -66,6 +66,16 @@ struct mmu_notifier_ops {
                                 unsigned long end);
 
        /*
+        * clear_young is a lightweight version of clear_flush_young. Like the
+        * latter, it is supposed to test-and-clear the young/accessed bitflag
+        * in the secondary pte, but it may omit flushing the secondary tlb.
+        */
+       int (*clear_young)(struct mmu_notifier *mn,
+                          struct mm_struct *mm,
+                          unsigned long start,
+                          unsigned long end);
+
+       /*
         * test_young is called to check the young/accessed bitflag in
         * the secondary pte. This is used to know if the page is
         * frequently used without actually clearing the flag or tearing

@@ -203,6 +213,9 @@ extern void __mmu_notifier_release(struct mm_struct *mm);
 extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
                                          unsigned long start,
                                          unsigned long end);
+extern int __mmu_notifier_clear_young(struct mm_struct *mm,
+                                     unsigned long start,
+                                     unsigned long end);
 extern int __mmu_notifier_test_young(struct mm_struct *mm,
                                     unsigned long address);
 extern void __mmu_notifier_change_pte(struct mm_struct *mm,

@@ -231,6 +244,15 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
        return 0;
 }
 
+static inline int mmu_notifier_clear_young(struct mm_struct *mm,
+                                          unsigned long start,
+                                          unsigned long end)
+{
+       if (mm_has_notifiers(mm))
+               return __mmu_notifier_clear_young(mm, start, end);
+       return 0;
+}
+
 static inline int mmu_notifier_test_young(struct mm_struct *mm,
                                          unsigned long address)
 {

@@ -311,6 +333,28 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
        __young;                                                        \
 })
 
+#define ptep_clear_young_notify(__vma, __address, __ptep)              \
+({                                                                     \
+       int __young;                                                    \
+       struct vm_area_struct *___vma = __vma;                          \
+       unsigned long ___address = __address;                           \
+       __young = ptep_test_and_clear_young(___vma, ___address, __ptep);\
+       __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address,  \
+                                           ___address + PAGE_SIZE);    \
+       __young;                                                        \
+})
+
+#define pmdp_clear_young_notify(__vma, __address, __pmdp)              \
+({                                                                     \
+       int __young;                                                    \
+       struct vm_area_struct *___vma = __vma;                          \
+       unsigned long ___address = __address;                           \
+       __young = pmdp_test_and_clear_young(___vma, ___address, __pmdp);\
+       __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address,  \
+                                           ___address + PMD_SIZE);     \
+       __young;                                                        \
+})
+
 #define        ptep_clear_flush_notify(__vma, __address, __ptep)               \
 ({                                                                     \
        unsigned long ___addr = __address & PAGE_MASK;                  \

mm/mmu_notifier.c +17 -0

index 3b9b3d0741b2..5fbdd367bbed 100644
@@ -123,6 +123,23 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
        return young;
 }
 
+int __mmu_notifier_clear_young(struct mm_struct *mm,
+                              unsigned long start,
+                              unsigned long end)
+{
+       struct mmu_notifier *mn;
+       int young = 0, id;
+
+       id = srcu_read_lock(&srcu);
+       hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+               if (mn->ops->clear_young)
+                       young |= mn->ops->clear_young(mn, mm, start, end);
+       }
+       srcu_read_unlock(&srcu, id);
+
+       return young;
+}
+
 int __mmu_notifier_test_young(struct mm_struct *mm,
                              unsigned long address)
 {

virt/kvm/kvm_main.c +0 -0

index 05148a43ef9c..61500cb028a3 100644

virt/kvm/kvm_main.c +7 -1

+       spin_unlock(&kvm->mmu_lock);
+       srcu_read_unlock(&kvm->srcu, idx);
+
+       return young;
+}
+
 static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
                                       struct mm_struct *mm,
                                       unsigned long address)

@@ -420,6 +437,7 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
        .invalidate_range_start = kvm_mmu_notifier_invalidate_range_start,
        .invalidate_range_end   = kvm_mmu_notifier_invalidate_range_end,
        .clear_flush_young      = kvm_mmu_notifier_clear_flush_young,
+       .clear_young            = kvm_mmu_notifier_clear_young,
        .test_young             = kvm_mmu_notifier_test_young,
        .change_pte             = kvm_mmu_notifier_change_pte,
        .release                = kvm_mmu_notifier_release,
--

2.1.4

As noted by Minchan, a benefit of reading idle flag from /proc/kpageflags is that one can easily filter dirty and/or unevictable pages while estimating the size of unused memory.

Note that idle flag read from /proc/kpageflags may be stale in case the page was accessed via a PTE, because it would be too costly to iterate over all page mappings on each /proc/kpageflags read to provide an up-to-date value. To make sure the flag is up-to-date one has to read /proc/kpageidle first.

Signed-off-by Vladimir Davydov <[email protected]>

---
 Documentation/vm/pagemap.txt           | 6 ++++++
 fs/proc/page.c                         | 3 +++
 include/uapi/linux/kernel-page-flags.h | 1 +
 3 files changed, 10 insertions(+)

Documentation/vm/pagemap.txt +6 -0

index c9266340852c..5896b7d7fd74 100644
@@ -64,6 +64,7 @@ There are five components to pagemap:
     22. THP
     23. BALLOON
     24. ZERO_PAGE
+    25. IDLE
 
  * /proc/kpagecgroup.  This file contains a 64-bit inode number of the
    memory cgroup each page is charged to, indexed by PFN. Only available when

@@ -124,6 +125,11 @@ Short descriptions to the page flags:
 24. ZERO_PAGE
     zero page for pfn_zero or huge_zero page
 
+25. IDLE
+    page has not been accessed since it was marked idle (see /proc/kpageidle)
+    Note that this flag may be stale in case the page was accessed via a PTE.
+    To make sure the flag is up-to-date one has to read /proc/kpageidle first.
+
     [IO related page flags]
  1. ERROR     IO error occurred
  3. UPTODATE  page has up-to-date data

fs/proc/page.c +3 -0

index 273537885ab4..13dcb823fe4e 100644
@@ -150,6 +150,9 @@ u64 stable_page_flags(struct page *page)
        if (PageBalloon(page))
                u |= 1 << KPF_BALLOON;
 
+       if (page_is_idle(page))
+               u |= 1 << KPF_IDLE;
+
        u |= kpf_copy_bit(k, KPF_LOCKED,        PG_locked);
 
        u |= kpf_copy_bit(k, KPF_SLAB,          PG_slab);

include/uapi/linux/kernel-page-flags.h +1 -1

index a6c4962e5d46..5da5f8751ce7 100644
@@ -33,6 +33,7 @@
 #define KPF_THP                        22
 #define KPF_BALLOON            23
 #define KPF_ZERO_PAGE          24
+#define KPF_IDLE               25
 
 
 #endif /* _UAPILINUX_KERNEL_PAGE_FLAGS_H */
--

2.1.4

Knowing the portion of memory that is not used by a certain application or memory cgroup (idle memory) can be useful for partitioning the system efficiently, e.g. by setting memory cgroup limits appropriately. Currently, the only means to estimate the amount of idle memory provided by the kernel is /proc/PID/{clear_refs,smaps}: the user can clear the access bit for all pages mapped to a particular process by writing 1 to clear_refs, wait for some time, and then count smaps:Referenced. However, this method has two serious shortcomings:

- it does not count unmapped file pages
- it affects the reclaimer logic

To overcome these drawbacks, this patch introduces two new page flags, Idle and Young, and a new proc file, /proc/kpageidle. A page's Idle flag can only be set from userspace by setting bit in /proc/kpageidle at the offset corresponding to the page, and it is cleared whenever the page is accessed either through page tables (it is cleared in page_referenced() in this case) or using the read(2) system call (mark_page_accessed()). Thus by setting the Idle flag for pages of a particular workload, which can be found e.g. by reading /proc/PID/pagemap, waiting for some time to let the workload access its working set, and then reading the kpageidle file, one can estimate the amount of pages that are not used by the workload.

The Young page flag is used to avoid interference with the memory reclaimer. A page's Young flag is set whenever the Access bit of a page table entry pointing to the page is cleared by writing to kpageidle. If page_referenced() is called on a Young page, it will add 1 to its return value, therefore concealing the fact that the Access bit was cleared.

Note, since there is no room for extra page flags on 32 bit, this feature uses extended page flags when compiled on 32 bit.

Signed-off-by Vladimir Davydov <[email protected]>

---
 Documentation/vm/pagemap.txt |  12 ++-
 fs/proc/page.c               | 218 +++++++++++++++++++++++++++++++++++++++++++
 fs/proc/task_mmu.c           |   4 +-
 include/linux/mm.h           |  98 +++++++++++++++++++
 include/linux/page-flags.h   |  11 +++
 include/linux/page_ext.h     |   4 +
 mm/Kconfig                   |  12 +++
 mm/debug.c                   |   4 +
 mm/huge_memory.c             |  11 ++-
 mm/migrate.c                 |   5 +
 mm/page_ext.c                |   3 +
 mm/rmap.c                    |   5 +
 mm/swap.c                    |   2 +
 13 files changed, 385 insertions(+), 4 deletions(-)

Documentation/vm/pagemap.txt +11 -1

index a9b7afc8fbc6..c9266340852c 100644
@@ -5,7 +5,7 @@ pagemap is a new (as of 2.6.25) set of interfaces in the kernel that allow
 userspace programs to examine the page tables and related information by
 reading files in /proc.
 
-There are four components to pagemap:
+There are five components to pagemap:
 
  * /proc/pid/pagemap.  This file lets a userspace process find out which
    physical frame each virtual page is mapped to.  It contains one 64-bit

@@ -69,6 +69,16 @@ There are four components to pagemap:
    memory cgroup each page is charged to, indexed by PFN. Only available when
    CONFIG_MEMCG is set.
 
+ * /proc/kpageidle.  This file implements a bitmap where each bit corresponds
+   to a page, indexed by PFN. When the bit is set, the corresponding page is
+   idle. A page is considered idle if it has not been accessed since it was
+   marked idle. To mark a page idle one should set the bit corresponding to the
+   page by writing to the file. A value written to the file is OR-ed with the
+   current bitmap value. Only user memory pages can be marked idle, for other
+   page types input is silently ignored. Writing to this file beyond max PFN
+   results in the ENXIO error. Only available when CONFIG_IDLE_PAGE_TRACKING is
+   set.
+
 Short descriptions to the page flags:
 
  0. LOCKED

fs/proc/page.c +75 -0

index 70d23245dd43..273537885ab4 100644
@@ -5,6 +5,8 @@
 #include <linux/ksm.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
+#include <linux/rmap.h>
+#include <linux/mmu_notifier.h>
 #include <linux/huge_mm.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>

@@ -16,6 +18,7 @@
 
 #define KPMSIZE sizeof(u64)
 #define KPMMASK (KPMSIZE - 1)
+#define KPMBITS (KPMSIZE * BITS_PER_BYTE)
 
 /* /proc/kpagecount - an array exposing page counts
  *

@@ -275,6 +278,217 @@ static const struct file_operations proc_kpagecgroup_operations = {
 };
 #endif /* CONFIG_MEMCG */
 
+#ifdef CONFIG_IDLE_PAGE_TRACKING
+/*
+ * Idle page tracking only considers user memory pages, for other types of
+ * pages the idle flag is always unset and an attempt to set it is silently
+ * ignored.
+ *
+ * We treat a page as a user memory page if it is on an LRU list, because it is
+ * always safe to pass such a page to rmap_walk(), which is essential for idle
+ * page tracking. With such an indicator of user pages we can skip isolated
+ * pages, but since there are not usually many of them, it will hardly affect
+ * the overall result.
+ *
+ * This function tries to get a user memory page by pfn as described above.
+ */
+static struct page *kpageidle_get_page(unsigned long pfn)
+{
+       struct page *page;
+       struct zone *zone;
+
+       if (!pfn_valid(pfn))
+               return NULL;
+
+       page = pfn_to_page(pfn);
+       if (!page || !PageLRU(page) ||
+           !get_page_unless_zero(page))
+               return NULL;
+
+       zone = page_zone(page);
+       spin_lock_irq(&zone->lru_lock);
+       if (unlikely(!PageLRU(page))) {
+               put_page(page);
+               page = NULL;
+       }
+       spin_unlock_irq(&zone->lru_lock);
+       return page;
+}
+
+static int kpageidle_clear_pte_refs_one(struct page *page,
+                                       struct vm_area_struct *vma,
+                                       unsigned long addr, void *arg)
+{
+       struct mm_struct *mm = vma->vm_mm;
+       spinlock_t *ptl;
+       pmd_t *pmd;
+       pte_t *pte;
+       bool referenced = false;
+
+       if (unlikely(PageTransHuge(page))) {
+               pmd = page_check_address_pmd(page, mm, addr,
+                                            PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl);
+               if (pmd) {
+                       referenced = pmdp_clear_young_notify(vma, addr, pmd);
+                       spin_unlock(ptl);
+               }
+       } else {
+               pte = page_check_address(page, mm, addr, &ptl, 0);
+               if (pte) {
+                       referenced = ptep_clear_young_notify(vma, addr, pte);
+                       pte_unmap_unlock(pte, ptl);
+               }
+       }
+       if (referenced) {
+               clear_page_idle(page);
+               /*
+                * We cleared the referenced bit in a mapping to this page. To
+                * avoid interference with page reclaim, mark it young so that
+                * page_referenced() will return > 0.
+                */
+               set_page_young(page);
+       }
+       return SWAP_AGAIN;
+}

fs/proc/page.c +40 -0

+               return;
+
+       need_lock = !PageAnon(page) || PageKsm(page);
+       if (need_lock && !trylock_page(page))
+               return;
+
+       rmap_walk(page, &rwc);
+
+       if (need_lock)
+               unlock_page(page);
+}
+
+static ssize_t kpageidle_read(struct file *file, char __user *buf,
+                             size_t count, loff_t *ppos)
+{
+       u64 __user *out = (u64 __user *)buf;
+       struct page *page;
+       unsigned long pfn, end_pfn;
+       ssize_t ret = 0;
+       u64 idle_bitmap = 0;
+       int bit;
+
+       if (*ppos & KPMMASK || count & KPMMASK)
+               return -EINVAL;
+
+       pfn = *ppos * BITS_PER_BYTE;
+       if (pfn >= max_pfn)
+               return 0;
+
+       end_pfn = pfn + count * BITS_PER_BYTE;
+       if (end_pfn > max_pfn)
+               end_pfn = ALIGN(max_pfn, KPMBITS);
+
+       for (; pfn < end_pfn; pfn++) {
+               bit = pfn % KPMBITS;
+               page = kpageidle_get_page(pfn);
+               if (page) {
+                       if (page_is_idle(page)) {
+                               /*
+                                * The page might have been referenced via a

fs/proc/page.c +30 -0

+                       if (put_user(idle_bitmap, out)) {
+                               ret = -EFAULT;
+                               break;
+                       }
+                       idle_bitmap = 0;
+                       out++;
+               }
+       }
+
+       *ppos += (char __user *)out - buf;
+       if (!ret)
+               ret = (char __user *)out - buf;
+       return ret;
+}
+
+static ssize_t kpageidle_write(struct file *file, const char __user *buf,
+                              size_t count, loff_t *ppos)
+{
+       const u64 __user *in = (const u64 __user *)buf;
+       struct page *page;
+       unsigned long pfn, end_pfn;
+       ssize_t ret = 0;
+       u64 idle_bitmap = 0;
+       int bit;
+
+       if (*ppos & KPMMASK || count & KPMMASK)
+               return -EINVAL;
+
+       pfn = *ppos * BITS_PER_BYTE;
+       if (pfn >= max_pfn)

fs/proc/page.c +42 -0

+                               ret = -EFAULT;
+                               break;
+                       }
+                       in++;
+               }
+               if (idle_bitmap >> bit & 1) {
+                       page = kpageidle_get_page(pfn);
+                       if (page) {
+                               kpageidle_clear_pte_refs(page);
+                               set_page_idle(page);
+                               put_page(page);
+                       }
+               }
+       }
+
+       *ppos += (const char __user *)in - buf;
+       if (!ret)
+               ret = (const char __user *)in - buf;
+       return ret;
+}
+
+static const struct file_operations proc_kpageidle_operations = {
+       .llseek = mem_lseek,
+       .read = kpageidle_read,
+       .write = kpageidle_write,
+};
+
+#ifndef CONFIG_64BIT
+static bool need_page_idle(void)
+{
+       return true;
+}
+struct page_ext_operations page_idle_ops = {
+       .need = need_page_idle,
+};
+#endif
+#endif /* CONFIG_IDLE_PAGE_TRACKING */
+
 static int __init proc_page_init(void)
 {
        proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);

@@ -282,6 +496,10 @@ static int __init proc_page_init(void)
 #ifdef CONFIG_MEMCG
        proc_create("kpagecgroup", S_IRUSR, NULL, &proc_kpagecgroup_operations);
 #endif
+#ifdef CONFIG_IDLE_PAGE_TRACKING
+       proc_create("kpageidle", S_IRUSR | S_IWUSR, NULL,
+                   &proc_kpageidle_operations);
+#endif
        return 0;
 }
 fs_initcall(proc_page_init);

fs/proc/task_mmu.c +3 -1

index 3b4d8255e806..3efd7f641f92 100644
@@ -458,7 +458,7 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
 
        mss->resident += size;
        /* Accumulate the size in pages that have been accessed. */
-       if (young || PageReferenced(page))
+       if (young || page_is_young(page) || PageReferenced(page))
                mss->referenced += size;
        mapcount = page_mapcount(page);
        if (mapcount >= 2) {

@@ -810,6 +810,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 
                /* Clear accessed and referenced bits. */
                pmdp_test_and_clear_young(vma, addr, pmd);
+               test_and_clear_page_young(page);
                ClearPageReferenced(page);
 out:
                spin_unlock(ptl);

@@ -837,6 +838,7 @@ out:
 
                /* Clear accessed and referenced bits. */
                ptep_test_and_clear_young(vma, addr, pte);
+               test_and_clear_page_young(page);
                ClearPageReferenced(page);
        }
        pte_unmap_unlock(pte - 1, ptl);

include/linux/mm.h +98 -0

index 7f471789781a..de450c1191b9 100644
@@ -2205,5 +2205,103 @@ void __init setup_nr_node_ids(void);
 static inline void setup_nr_node_ids(void) {}
 #endif
 
+#ifdef CONFIG_IDLE_PAGE_TRACKING
+#ifdef CONFIG_64BIT
+static inline bool page_is_young(struct page *page)
+{
+       return PageYoung(page);
+}
+
+static inline void set_page_young(struct page *page)
+{
+       SetPageYoung(page);
+}
+
+static inline bool test_and_clear_page_young(struct page *page)
+{
+       return TestClearPageYoung(page);
+}
+
+static inline bool page_is_idle(struct page *page)
+{
+       return PageIdle(page);
+}
+
+static inline void set_page_idle(struct page *page)
+{
+       SetPageIdle(page);
+}
+
+static inline void clear_page_idle(struct page *page)
+{
+       ClearPageIdle(page);
+}
+#else /* !CONFIG_64BIT */
+/*
+ * If there is not enough space to store Idle and Young bits in page flags, use
+ * page ext flags instead.
+ */
+extern struct page_ext_operations page_idle_ops;
+
+static inline bool page_is_young(struct page *page)
+{
+       return test_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+}
+
+static inline void set_page_young(struct page *page)
+{
+       set_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags);
+}
+
+static inline bool test_and_clear_page_young(struct page *page)
+{
+       return test_and_clear_bit(PAGE_EXT_YOUNG,
+                                 &lookup_page_ext(page)->flags);
+}
+
+static inline bool page_is_idle(struct page *page)
+{
+       return test_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+}
+
+static inline void set_page_idle(struct page *page)
+{
+       set_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+}
+
+static inline void clear_page_idle(struct page *page)
+{
+       clear_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags);
+}
+#endif /* CONFIG_64BIT */
+#else /* !CONFIG_IDLE_PAGE_TRACKING */
+static inline bool page_is_young(struct page *page)
+{
+       return false;
+}
+
+static inline void set_page_young(struct page *page)
+{
+}
+
+static inline bool test_and_clear_page_young(struct page *page)
+{
+       return false;
+}
+
+static inline bool page_is_idle(struct page *page)
+{
+       return false;
+}
+
+static inline void set_page_idle(struct page *page)
+{
+}
+
+static inline void clear_page_idle(struct page *page)
+{
+}
+#endif /* CONFIG_IDLE_PAGE_TRACKING */
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */

include/linux/page-flags.h +11 -0

index 91b7f9b2b774..478f2241f284 100644
@@ -109,6 +109,10 @@ enum pageflags {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
        PG_compound_lock,
 #endif
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+       PG_young,
+       PG_idle,
+#endif
        __NR_PAGEFLAGS,
 
        /* Filesystems */

@@ -363,6 +367,13 @@ PAGEFLAG_FALSE(HWPoison)
 #define __PG_HWPOISON 0
 #endif
 
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+TESTPAGEFLAG(Young, young, PF_ANY)
+SETPAGEFLAG(Young, young, PF_ANY)
+TESTCLEARFLAG(Young, young, PF_ANY)
+PAGEFLAG(Idle, idle, PF_ANY)
+#endif
+
 /*
  * On an anonymous page mapped into a user virtual memory area,
  * page->mapping points to its anon_vma, not to a struct address_space;

include/linux/page_ext.h +4 -0

index c42981cd99aa..17f118a82854 100644
@@ -26,6 +26,10 @@ enum page_ext_flags {
        PAGE_EXT_DEBUG_POISON,          /* Page is poisoned */
        PAGE_EXT_DEBUG_GUARD,
        PAGE_EXT_OWNER,
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
+       PAGE_EXT_YOUNG,
+       PAGE_EXT_IDLE,
+#endif
 };
 
 /*

mm/Kconfig +12 -0

index e79de2bd12cd..db817e2c2ec8 100644
@@ -654,3 +654,15 @@ config DEFERRED_STRUCT_PAGE_INIT
          when kswapd starts. This has a potential performance impact on
          processes running early in the lifetime of the systemm until kswapd
          finishes the initialisation.
+
+config IDLE_PAGE_TRACKING
+       bool "Enable idle page tracking"
+       select PROC_PAGE_MONITOR
+       select PAGE_EXTENSION if !64BIT
+       help
+         This feature allows to estimate the amount of user pages that have
+         not been touched during a given period of time. This information can
+         be useful to tune memory cgroup limits and/or for job placement
+         within a compute cluster.
+
+         See Documentation/vm/pagemap.txt for more details.

mm/debug.c +4 -0

index 76089ddf99ea..6c1b3ea61bfd 100644
@@ -48,6 +48,10 @@ static const struct trace_print_flags pageflag_names[] = {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
        {1UL << PG_compound_lock,       "compound_lock" },
 #endif
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+       {1UL << PG_young,               "young"         },
+       {1UL << PG_idle,                "idle"          },
+#endif
 };
 
 static void dump_flags(unsigned long flags,

mm/huge_memory.c +0 -0

index 9671f51e954d..bb6d2ec1f268 100644

mm/huge_memory.c +2 -1

                /*
                 * __split_huge_page_splitting() already set the
                 * splitting bit in all pmd that could map this

@@ -2259,7 +2264,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
                VM_BUG_ON_PAGE(PageLRU(page), page);
 
                /* If there is no mapped pte young don't collapse the page */
-               if (pte_young(pteval) || PageReferenced(page) ||
+               if (pte_young(pteval) ||
+                   page_is_young(page) || PageReferenced(page) ||
                    mmu_notifier_test_young(vma->vm_mm, address))
                        referenced = true;
        }

mm/migrate.c +5 -0

index 236ee25e79d9..3e7bb4f2b51c 100644
@@ -524,6 +524,11 @@ void migrate_page_copy(struct page *newpage, struct page *page)
                        __set_page_dirty_nobuffers(newpage);
        }
 
+       if (page_is_young(page))
+               set_page_young(newpage);
+       if (page_is_idle(page))
+               set_page_idle(newpage);
+
        /*
         * Copy NUMA information to the new page, to prevent over-eager
         * future migrations of this same page.

mm/page_ext.c +3 -0

index d86fd2f5353f..e4b3af054bf2 100644
@@ -59,6 +59,9 @@ static struct page_ext_operations *page_ext_ops[] = {
 #ifdef CONFIG_PAGE_OWNER
        &page_owner_ops,
 #endif
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
+       &page_idle_ops,
+#endif
 };
 
 static unsigned long total_usage;

mm/rmap.c +5 -0

index 49b244b1f18c..c96677ade3d1 100644
@@ -798,6 +798,11 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
                pte_unmap_unlock(pte, ptl);
        }
 
+       if (referenced)
+               clear_page_idle(page);
+       if (test_and_clear_page_young(page))
+               referenced++;
+
        if (referenced) {
                pra->referenced++;
                pra->vm_flags |= vma->vm_flags;

mm/swap.c +2 -1

index ab7c338eda87..db43c9b4891d 100644
@@ -623,6 +623,8 @@ void mark_page_accessed(struct page *page)
        } else if (!PageReferenced(page)) {
                SetPageReferenced(page);
        }
+       if (page_is_idle(page))
+               clear_page_idle(page);
 }
 EXPORT_SYMBOL(mark_page_accessed);
 
--

2.1.4

Hi,

This patch set introduces a new user API for tracking user memory pages that have not been used for a given period of time. The purpose of this is to provide the userspace with the means of tracking a workload's working set, i.e. the set of pages that are actively used by the workload. Knowing the working set size can be useful for partitioning the system more efficiently, e.g. by tuning memory cgroup limits appropriately, or for job placement within a compute cluster.

It is based on top of v4.2-rc1-mmotm-2015-07-06-16-25

---- USE CASES ----

The unified cgroup hierarchy has memory.low and memory.high knobs, which are defined as the low and high boundaries for the workload working set size. However, the working set size of a workload may be unknown or change in time. With this patch set, one can periodically estimate the amount of memory unused by each cgroup and tune their memory.low and memory.high parameters accordingly, therefore optimizing the overall memory utilization.

Another use case is balancing workloads within a compute cluster. Knowing how much memory is not really used by a workload unit may help take a more optimal decision when considering migrating the unit to another node within the cluster.

Also, as noted by Minchan, this would be useful for per-process reclaim
(https://lwn.net/Articles/545668/). With idle tracking, we could reclaim idle pages only by smart user memory manager.

---- USER API ----

The user API consists of two new proc files:

* /proc/kpageidle. This file implements a bitmap where each bit corresponds to a page, indexed by PFN. When the bit is set, the corresponding page is idle. A page is considered idle if it has not been accessed since it was marked idle. To mark a page idle one should set the bit corresponding to the page by writing to the file. A value written to the file is OR-ed with the current bitmap value. Only user memory pages can be marked idle, for other page types input is silently ignored. Writing to this file beyond max PFN results in the ENXIO error. Only available when CONFIG_IDLE_PAGE_TRACKING is set.

This file can be used to estimate the amount of pages that are not used by a particular workload as follows:

1. mark all pages of interest idle by setting corresponding bits in the /proc/kpageidle bitmap
2. wait until the workload accesses its working set
3. read /proc/kpageidle and count the number of bits set

* /proc/kpagecgroup. This file contains a 64-bit inode number of the memory cgroup each page is charged to, indexed by PFN. Only available when CONFIG_MEMCG is set.

This file can be used to find all pages (including unmapped file pages) accounted to a particular cgroup. Using /proc/kpageidle, one can then estimate the cgroup working set size.

For an example of using these files for estimating the amount of unused memory pages per each memory cgroup, please see the script attached below.

---- REASONING ----

The reason to introduce the new user API instead of using /proc/PID/{clear_refs,smaps} is that the latter has two serious drawbacks:

- it does not count unmapped file pages
- it affects the reclaimer logic

The new API attempts to overcome them both. For more details on how it is achieved, please see the comment to patch 5.

---- CHANGE LOG ----

Changes in v8:

- clear referenced/accessed bit in secondary ptes while accessing /proc/kpageidle; this is required to estimate wss of KVM VMs (Andres)
- check the young flag when collapsing a huge page
- copy idle/young flags on page migration

Changes in v7:

This iteration addresses Andres's comments to v6:

- do not reuse page_referenced for clearing idle flag, introduce a separate function instead; this way we won't issue expensive tlb flushes on /proc/kpageidle read/write
- propagate young/idle flags from head to tail pages on thp split
- skip compound tail pages while reading/writing /proc/kpageidle
- cleanup page_referenced_one

Changes in v6:

- Split the patch introducing page_cgroup_ino helper to ease review.
- Rebase on top of v4.1-rc7-mmotm-2015-06-09-16-55

Changes in v5:

- Fix possible race between kpageidle_clear_pte_refs() and __page_set_anon_rmap() by checking that a page is on an LRU list under zone->lru_lock (Minchan).
- Export idle flag via /proc/kpageflags (Minchan).
- Rebase on top of 4.1-rc3.

Changes in v4:

This iteration primarily addresses Minchan's comments to v3:

- Implement /proc/kpageidle as a bitmap instead of using u64 per each page, because there does not seem to be any future uses for the other 63 bits.
- Do not double-increase pra->referenced in page_referenced_one() if the page was young and referenced recently.
- Remove the pointless (page_count == 0) check from kpageidle_get_page().
- Rename kpageidle_clear_refs() to kpageidle_clear_pte_refs().
- Improve comments to kpageidle-related functions.
- Rebase on top of 4.1-rc2.

Note it does not address Minchan's concern of possible __page_set_anon_rmap vs page_referenced race (see https://lkml.org/lkml/2015/5/3/220) since it is still unclear if this race can really happen (see https://lkml.org/lkml/2015/5/4/160)

Changes in v3:

- Enable CONFIG_IDLE_PAGE_TRACKING for 32 bit. Since this feature requires two extra page flags and there is no space for them on 32 bit, page ext is used (thanks to Minchan Kim).
- Minor code cleanups and comments improved.
- Rebase on top of 4.1-rc1.

Changes in v2:

- The main difference from v1 is the API change. In v1 the user can only set the idle flag for all pages at once, and for clearing the Idle flag on pages accessed via page tables /proc/PID/clear_refs should be used.
The main drawback of the v1 approach, as noted by Minchan, is that on big machines setting the idle flag for each pages can result in CPU bursts, which would be especially frustrating if the user only wanted to estimate the amount of idle pages for a particular process or VMA. With the new API a more fine-grained approach is possible: one can read a process's /proc/PID/pagemap and set/check the Idle flag only for those pages of the process's address space he or she is interested in.
Another good point about the v2 API is that it is possible to limit /proc/kpage* scanning rate when the user wants to estimate the total number of idle pages, which is unachievable with the v1 approach.
- Make /proc/kpagecgroup return the ino of the closest online ancestor in case the cgroup a page is charged to is offline.
- Fix /proc/PID/clear_refs not clearing Young page flag.
- Rebase on top of v4.0-rc6-mmotm-2015-04-01-14-54

v7: https://lkml.org/lkml/2015/7/11/119
v6: https://lkml.org/lkml/2015/6/12/301
v5: https://lkml.org/lkml/2015/5/12/449
v4: https://lkml.org/lkml/2015/5/7/580
v3: https://lkml.org/lkml/2015/4/28/224
v2: https://lkml.org/lkml/2015/4/7/260
v1: https://lkml.org/lkml/2015/3/18/794

---- PATCH SET STRUCTURE ----

The patch set is organized as follows:

- patch 1 adds page_cgroup_ino() helper for the sake of /proc/kpagecgroup and patches 2-3 do related cleanup
- patch 4 adds /proc/kpagecgroup, which reports cgroup ino each page is charged to
- patch 5 introduces a new mmu notifier callback, clear_young, which is a lightweight version of clear_flush_young; it is used in patch 6
- patch 6 implements the idle page tracking feature, including the userspace API, /proc/kpageidle
- patch 7 exports idle flag via /proc/kpageflags

---- SIMILAR WORKS ----

Originally, the patch for tracking idle memory was proposed back in 2011 by Michel Lespinasse (see http://lwn.net/Articles/459269/). The main difference between Michel's patch and this one is that Michel implemented a kernel space daemon for estimating idle memory size per cgroup while this patch only provides the userspace with the minimal API for doing the job, leaving the rest up to the userspace. However, they both share the same idea of Idle/Young page flags to avoid affecting the reclaimer logic.

---- SCRIPT FOR COUNTING IDLE PAGES PER CGROUP ---- #! /usr/bin/python
#

import os
import stat
import errno
import struct

CGROUP_MOUNT = "/sys/fs/cgroup/memory"
BUFSIZE = 8 * 1024 # must be multiple of 8

def get_hugepage_size():

    with open("/proc/meminfo", "r") as f:
        for s in f:
            k, v = s.split(":")
            if k == "Hugepagesize":
                return int(v.split()[0]) * 1024

PAGE_SIZE = os.sysconf("SC_PAGE_SIZE")
HUGEPAGE_SIZE = get_hugepage_size()

def set_idle():

    f = open("/proc/kpageidle", "wb", BUFSIZE)
    while True:
        try:
            f.write(struct.pack("Q", pow(2, 64) - 1))
        except IOError as err:
            if err.errno == errno.ENXIO:
                break
            raise
    f.close()

def count_idle():

    f_flags = open("/proc/kpageflags", "rb", BUFSIZE)
    f_cgroup = open("/proc/kpagecgroup", "rb", BUFSIZE)

    with open("/proc/kpageidle", "rb", BUFSIZE) as f:
        while f.read(BUFSIZE): pass  # update idle flag

    idlememsz = {}
    while True:
        s1, s2 = f_flags.read(8), f_cgroup.read(8)
        if not s1 or not s2:
            break

        flags, = struct.unpack('Q', s1)
        cgino, = struct.unpack('Q', s2)

        unevictable = (flags >> 18) & 1
        huge = (flags >> 22) & 1
        idle = (flags >> 25) & 1

        if idle and not unevictable:
            idlememsz[cgino] = idlememsz.get(cgino, 0) + \
                (HUGEPAGE_SIZE if huge else PAGE_SIZE)

    f_flags.close()
    f_cgroup.close()
    return idlememsz

if __name__ == "__main__":
print "Setting the idle flag for each page..." set_idle()

raw_input("Wait until the workload accesses its working set, "
"then press Enter")

print "Counting idle pages..."
idlememsz = count_idle()

for dir, subdirs, files in os.walk(CGROUP_MOUNT):
ino = os.stat(dir)[stat.ST_INO]
print dir + ": " + str(idlememsz.get(ino, 0) / 1024) + " kB"
---- END SCRIPT ----

Comments are more than welcome.

Thanks,

Vladimir Davydov (7):
memcg: add page_cgroup_ino helper
hwpoison: use page_cgroup_ino for filtering by memcg
memcg: zap try_get_mem_cgroup_from_page
proc: add kpagecgroup file
mmu-notifier: add clear_young callback
proc: add kpageidle file
proc: export idle flag via kpageflags

 Documentation/vm/pagemap.txt           |  22 ++-
 fs/proc/page.c                         | 274 +++++++++++++++++++++++++++++++++
 fs/proc/task_mmu.c                     |   4 +-
 include/linux/memcontrol.h             |   7 +-
 include/linux/mm.h                     |  98 ++++++++++++
 include/linux/mmu_notifier.h           |  44 ++++++
 include/linux/page-flags.h             |  11 ++
 include/linux/page_ext.h               |   4 +
 include/uapi/linux/kernel-page-flags.h |   1 +
 mm/Kconfig                             |  12 ++
 mm/debug.c                             |   4 +
 mm/huge_memory.c                       |  11 +-
 mm/hwpoison-inject.c                   |   5 +-
 mm/memcontrol.c                        |  71 +++++----
 mm/memory-failure.c                    |  16 +-
 mm/migrate.c                           |   5 +
 mm/mmu_notifier.c                      |  17 ++
 mm/page_ext.c                          |   3 +
 mm/rmap.c                              |   5 +
 mm/swap.c                              |   2 +
 virt/kvm/kvm_main.c                    |  18 +++
 21 files changed, 570 insertions(+), 64 deletions(-)

--
2.1.4

For both /proc/kpage* interfaces you add (and more critically for the rmap-causing one, kpageidle):

It's a good idea to do cond_sched(). Whether after each pfn, each Nth pfn, each put_user, I leave to you, but a reasonable cadence is needed, because user-space can call this on the entire physical address space, and that's a lot of work to do without re-scheduling.

On Wed, Jul 15, 2015 at 6:54 AM, Vladimir Davydov
<[email protected]> wrote:

Quoted 4 lines

fs/proc/page.c +4 -0

+static void kpageidle_clear_pte_refs(struct page *page)
+{
+       struct rmap_walk_control rwc = {
+               .rmap_one = kpageidle_clear_pte_refs_one,

fs/proc/page.c static const struct file_operations proc_kpagecgroup_operations = { · line 362

Quoted 5 lines

fs/proc/page.c +5 -0

+               .anon_lock = page_lock_anon_vma_read,
+       };
+       bool need_lock;
+
+       if (!page_mapped(page) ||

Question: what about mlocked pages? Is there any point in calculating their idleness?

Quoted 2 lines

+ !page_rmapping(page))

Not sure, does this skip SwapCache pages? Is there any point in calculating their idleness?

Quoted 12 lines

fs/proc/page.c +11 -0

+               return;
+
+       need_lock = !PageAnon(page) || PageKsm(page);
+       if (need_lock && !trylock_page(page))
+               return;
+
+       rmap_walk(page, &rwc);
+
+       if (need_lock)
+               unlock_page(page);
+}

mm/huge_memory.c static void __split_huge_page_refcount(struct page *page, · line 1761

Quoted 9 lines

mm/huge_memory.c +5 -0

@@ -1754,6 +1754,11 @@ static void __split_huge_page_refcount(struct page *page,
                /* clear PageTail before overwriting first_page */
                smp_wmb();
 
+               if (page_is_young(page))
+                       set_page_young(page_tail);
+               if (page_is_idle(page))
+                       set_page_idle(page_tail);
+

Why not in the block above?

page_tail->flags |= (page->flags &
...
#ifdef CONFIG_WHATEVER_IT_WAS
1 << PG_idle
1 << PG_young
#endif

I think the remaining question here is performance.

Have you conducted any studies where
- there is a workload
- a daemon is poking kpageidle every N seconds/minutes
- what is the daemon cpu consumption?
- what is the workload degradation if any?

N candidates include 30 seconds, 1 minute, 2 minutes, 5 minutes....

Workload candidates include TPC, spec int memory intensive things like 429.mcf, stream (http://www.cs.virginia.edu/stream/ "sustainable memory bandwidth" vs floating point performance)

I'm not asking for a research paper, but if, say, a 2 minute-period daemon introduces no degradation and adds up to a minute of cpu per hour, then we're golden.

Quoted 7 lines

virt/kvm/kvm_main.c static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, · line 397

Quoted 7 lines

virt/kvm/kvm_main.c +7 -0

+static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
+                                       struct mm_struct *mm,
+                                       unsigned long start,
+                                       unsigned long end)
+{
+       struct kvm *kvm = mmu_notifier_to_kvm(mn);
+       int young, idx;

For reclaim, the clear_flush_young notifier may blow up the secondary pte to estimate the access pattern, depending on hardware support (EPT access bits available in Haswell onwards, not sure about AMD, PPC, etc).

Quoted 7 lines · Andres Lagar-Cavilla

For both /proc/kpage* interfaces you add (and more critically for the rmap-causing one, kpageidle):

It's a good idea to do cond_sched(). Whether after each pfn, each Nth pfn, each put_user, I leave to you, but a reasonable cadence is needed, because user-space can call this on the entire physical address space, and that's a lot of work to do without re-scheduling.

I really don't think it's necessary. These files can only be read/written by the root, who has plenty ways to kill the system anyway. The program that is allowed to read/write these files must be conscious and do it in batches of reasonable size. AFAICS the same reasoning already lays behind /proc/kpagecount and /proc/kpageflag, which also do not thrust the "right" batch size on their readers.

Thanks,
Vladimir

Quoted 9 lines · Vladimir Davydov

Quoted 7 lines · Andres Lagar-Cavilla

For both /proc/kpage* interfaces you add (and more critically for the rmap-causing one, kpageidle):

It's a good idea to do cond_sched(). Whether after each pfn, each Nth pfn, each put_user, I leave to you, but a reasonable cadence is needed, because user-space can call this on the entire physical address space, and that's a lot of work to do without re-scheduling.

Quoted 7 lines

I really don't think it's necessary. These files can only be read/written by the root, who has plenty ways to kill the system anyway. The program that is allowed to read/write these files must be conscious and do it in batches of reasonable size. AFAICS the same reasoning already lays behind /proc/kpagecount and /proc/kpageflag, which also do not thrust the "right" batch size on their readers.

Beg to disagree. You're conflating intended use with system health. A cond_sched() is a one-liner.