The patch titled
mm-only: vmscan: noreclaim LRU scan sysctl
has been added to the -mm tree. Its filename is
mm-only-vmscan-noreclaim-lru-scan-sysctl.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: mm-only: vmscan: noreclaim LRU scan sysctl
From: Lee Schermerhorn <lee.schermerhorn@xxxxxx>
Add a function to scan individual or all zones' noreclaim lists and move
any pages that have become reclaimable onto the respective zone's inactive
list, where shrink_inactive_list() will deal with them.
Adds sysctl to scan all nodes, and per node attributes to individual
nodes' zones.
Kosaki: If reclaimable page found in noreclaim lru when write
/proc/sys/vm/scan_noreclaim_pages, print filename and file offset of these
pages.
TODO: DEBUGGING ONLY: NOT FOR UPSTREAM MERGE
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@xxxxxx>
Signed-off-by: Rik van Riel <riel@xxxxxxxxxx>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/base/node.c | 5 +
include/linux/rmap.h | 3
include/linux/swap.h | 15 +++
kernel/sysctl.c | 10 ++
mm/rmap.c | 4 -
mm/vmscan.c | 161 +++++++++++++++++++++++++++++++++++++++++
6 files changed, 196 insertions(+), 2 deletions(-)
diff -puN drivers/base/node.c~mm-only-vmscan-noreclaim-lru-scan-sysctl drivers/base/node.c
--- a/drivers/base/node.c~mm-only-vmscan-noreclaim-lru-scan-sysctl
+++ a/drivers/base/node.c
@@ -13,6 +13,7 @@
#include <linux/nodemask.h>
#include <linux/cpu.h>
#include <linux/device.h>
+#include <linux/swap.h>
static struct sysdev_class node_class = {
.name = "node",
@@ -190,6 +191,8 @@ int register_node(struct node *node, int
sysdev_create_file(&node->sysdev, &attr_meminfo);
sysdev_create_file(&node->sysdev, &attr_numastat);
sysdev_create_file(&node->sysdev, &attr_distance);
+
+ scan_noreclaim_register_node(node);
}
return error;
}
@@ -209,6 +212,8 @@ void unregister_node(struct node *node)
sysdev_remove_file(&node->sysdev, &attr_numastat);
sysdev_remove_file(&node->sysdev, &attr_distance);
+ scan_noreclaim_unregister_node(node);
+
sysdev_unregister(&node->sysdev);
}
diff -puN include/linux/rmap.h~mm-only-vmscan-noreclaim-lru-scan-sysctl include/linux/rmap.h
--- a/include/linux/rmap.h~mm-only-vmscan-noreclaim-lru-scan-sysctl
+++ a/include/linux/rmap.h
@@ -67,6 +67,9 @@ void anon_vma_unlink(struct vm_area_stru
void anon_vma_link(struct vm_area_struct *);
void __anon_vma_link(struct vm_area_struct *);
+extern struct anon_vma *page_lock_anon_vma(struct page *page);
+extern void page_unlock_anon_vma(struct anon_vma *anon_vma);
+
/*
* rmap interfaces called when adding or removing pte of page
*/
diff -puN include/linux/swap.h~mm-only-vmscan-noreclaim-lru-scan-sysctl include/linux/swap.h
--- a/include/linux/swap.h~mm-only-vmscan-noreclaim-lru-scan-sysctl
+++ a/include/linux/swap.h
@@ -7,6 +7,7 @@
#include <linux/list.h>
#include <linux/memcontrol.h>
#include <linux/sched.h>
+#include <linux/node.h>
#include <asm/atomic.h>
#include <asm/page.h>
@@ -235,15 +236,29 @@ static inline int zone_reclaim(struct zo
#ifdef CONFIG_NORECLAIM_LRU
extern int page_reclaimable(struct page *page, struct vm_area_struct *vma);
extern void scan_mapping_noreclaim_pages(struct address_space *);
+
+extern unsigned long scan_noreclaim_pages;
+extern int scan_noreclaim_handler(struct ctl_table *, int, struct file *,
+ void __user *, size_t *, loff_t *);
+extern int scan_noreclaim_register_node(struct node *node);
+extern void scan_noreclaim_unregister_node(struct node *node);
#else
static inline int page_reclaimable(struct page *page,
struct vm_area_struct *vma)
{
return 1;
}
+
static inline void scan_mapping_noreclaim_pages(struct address_space *mapping)
{
}
+
+static inline int scan_noreclaim_register_node(struct node *node)
+{
+ return 0;
+}
+
+static inline void scan_noreclaim_unregister_node(struct node *node) { }
#endif
extern int kswapd_run(int nid);
diff -puN kernel/sysctl.c~mm-only-vmscan-noreclaim-lru-scan-sysctl kernel/sysctl.c
--- a/kernel/sysctl.c~mm-only-vmscan-noreclaim-lru-scan-sysctl
+++ a/kernel/sysctl.c
@@ -1141,6 +1141,16 @@ static struct ctl_table vm_table[] = {
.extra2 = &one,
},
#endif
+#ifdef CONFIG_NORECLAIM_LRU
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "scan_noreclaim_pages",
+ .data = &scan_noreclaim_pages,
+ .maxlen = sizeof(scan_noreclaim_pages),
+ .mode = 0644,
+ .proc_handler = &scan_noreclaim_handler,
+ },
+#endif
/*
* NOTE: do not add new entries to this table unless you have read
* Documentation/sysctl/ctl_unnumbered.txt
diff -puN mm/rmap.c~mm-only-vmscan-noreclaim-lru-scan-sysctl mm/rmap.c
--- a/mm/rmap.c~mm-only-vmscan-noreclaim-lru-scan-sysctl
+++ a/mm/rmap.c
@@ -158,7 +158,7 @@ void __init anon_vma_init(void)
* Getting a lock on a stable anon_vma from a page off the LRU is
* tricky: page_lock_anon_vma rely on RCU to guard against the races.
*/
-static struct anon_vma *page_lock_anon_vma(struct page *page)
+struct anon_vma *page_lock_anon_vma(struct page *page)
{
struct anon_vma *anon_vma;
unsigned long anon_mapping;
@@ -178,7 +178,7 @@ out:
return NULL;
}
-static void page_unlock_anon_vma(struct anon_vma *anon_vma)
+void page_unlock_anon_vma(struct anon_vma *anon_vma)
{
spin_unlock(&anon_vma->lock);
rcu_read_unlock();
diff -puN mm/vmscan.c~mm-only-vmscan-noreclaim-lru-scan-sysctl mm/vmscan.c
--- a/mm/vmscan.c~mm-only-vmscan-noreclaim-lru-scan-sysctl
+++ a/mm/vmscan.c
@@ -28,6 +28,7 @@
#include <linux/mm_inline.h>
#include <linux/pagevec.h>
#include <linux/backing-dev.h>
+#include <linux/sysctl.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
@@ -2378,6 +2379,37 @@ int page_reclaimable(struct page *page,
return 1;
}
+static void show_page_path(struct page *page)
+{
+ char buf[256];
+ if (page_file_cache(page)) {
+ struct address_space *mapping = page->mapping;
+ struct dentry *dentry;
+ pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+
+ spin_lock(&mapping->i_mmap_lock);
+ dentry = d_find_alias(mapping->host);
+ printk(KERN_INFO "rescued: %s %lu\n",
+ dentry_path(dentry, buf, 256), pgoff);
+ spin_unlock(&mapping->i_mmap_lock);
+ } else {
+ struct anon_vma *anon_vma;
+ struct vm_area_struct *vma;
+
+ anon_vma = page_lock_anon_vma(page);
+ if (!anon_vma)
+ return;
+
+ list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
+ printk(KERN_INFO "rescued: anon %s\n",
+ vma->vm_mm->owner->comm);
+ break;
+ }
+ page_unlock_anon_vma(anon_vma);
+ }
+}
+
+
/**
* check_move_noreclaim_page - check page for reclaimability and move to appropriate lru list
* @page: page to check reclaimability and move to appropriate lru list
@@ -2395,6 +2427,9 @@ static void check_move_noreclaim_page(st
ClearPageNoreclaim(page); /* for page_reclaimable() */
if (page_reclaimable(page, NULL)) {
enum lru_list l = LRU_INACTIVE_ANON + page_file_cache(page);
+
+ show_page_path(page);
+
__dec_zone_state(zone, NR_NORECLAIM);
list_move(&page->lru, &zone->list[l]);
__inc_zone_state(zone, NR_INACTIVE_ANON + l);
@@ -2475,4 +2510,130 @@ void scan_mapping_noreclaim_pages(struct
}
}
+
+/**
+ * scan_zone_noreclaim_pages - check noreclaim list for reclaimable pages
+ * @zone - zone of which to scan the noreclaim list
+ *
+ * Scan @zone's noreclaim LRU lists to check for pages that have become
+ * reclaimable. Move those that have to @zone's inactive list where they
+ * become candidates for reclaim, unless shrink_inactive_zone() decides
+ * to reactivate them. Pages that are still non-reclaimable are rotated
+ * back onto @zone's noreclaim list.
+ */
+#define SCAN_NORECLAIM_BATCH_SIZE 16UL /* arbitrary lock hold batch size */
+void scan_zone_noreclaim_pages(struct zone *zone)
+{
+ struct list_head *l_noreclaim = &zone->list[LRU_NORECLAIM];
+ unsigned long scan;
+ unsigned long nr_to_scan = zone_page_state(zone, NR_NORECLAIM);
+
+ while (nr_to_scan > 0) {
+ unsigned long batch_size = min(nr_to_scan,
+ SCAN_NORECLAIM_BATCH_SIZE);
+
+ spin_lock_irq(&zone->lru_lock);
+ for (scan = 0; scan < batch_size; scan++) {
+ struct page *page = lru_to_page(l_noreclaim);
+
+ if (TestSetPageLocked(page))
+ continue;
+
+ prefetchw_prev_lru_page(page, l_noreclaim, flags);
+
+ if (likely(PageLRU(page) && PageNoreclaim(page)))
+ check_move_noreclaim_page(page, zone);
+
+ unlock_page(page);
+ }
+ spin_unlock_irq(&zone->lru_lock);
+
+ nr_to_scan -= batch_size;
+ }
+}
+
+
+/**
+ * scan_all_zones_noreclaim_pages - scan all noreclaim lists for reclaimable pages
+ *
+ * A really big hammer: scan all zones' noreclaim LRU lists to check for
+ * pages that have become reclaimable. Move those back to the zones'
+ * inactive list where they become candidates for reclaim.
+ * This occurs when, e.g., we have unswappable pages on the noreclaim lists,
+ * and we add swap to the system. As such, it runs in the context of a task
+ * that has possibly/probably made some previously non-reclaimable pages
+ * reclaimable.
+ */
+void scan_all_zones_noreclaim_pages(void)
+{
+ struct zone *zone;
+
+ for_each_zone(zone) {
+ scan_zone_noreclaim_pages(zone);
+ }
+}
+
+/*
+ * scan_noreclaim_pages [vm] sysctl handler. On demand re-scan of
+ * all nodes' noreclaim lists for reclaimable pages
+ */
+unsigned long scan_noreclaim_pages;
+
+int scan_noreclaim_handler(struct ctl_table *table, int write,
+ struct file *file, void __user *buffer,
+ size_t *length, loff_t *ppos)
+{
+ proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
+
+ if (write && *(unsigned long *)table->data)
+ scan_all_zones_noreclaim_pages();
+
+ scan_noreclaim_pages = 0;
+ return 0;
+}
+
+/*
+ * per node 'scan_noreclaim_pages' attribute. On demand re-scan of
+ * a specified node's per zone noreclaim lists for reclaimable pages.
+ */
+
+static ssize_t read_scan_noreclaim_node(struct sys_device *dev, char *buf)
+{
+ return sprintf(buf, "0\n"); /* always zero; should fit... */
+}
+
+static ssize_t write_scan_noreclaim_node(struct sys_device *dev,
+ const char *buf, size_t count)
+{
+ struct zone *node_zones = NODE_DATA(dev->id)->node_zones;
+ struct zone *zone;
+ unsigned long res;
+ unsigned long req = strict_strtoul(buf, 10, &res);
+
+ if (!req)
+ return 1; /* zero is no-op */
+
+ for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
+ if (!populated_zone(zone))
+ continue;
+ scan_zone_noreclaim_pages(zone);
+ }
+ return 1;
+}
+
+
+static SYSDEV_ATTR(scan_noreclaim_pages, S_IRUGO | S_IWUSR,
+ read_scan_noreclaim_node,
+ write_scan_noreclaim_node);
+
+int scan_noreclaim_register_node(struct node *node)
+{
+ return sysdev_create_file(&node->sysdev, &attr_scan_noreclaim_pages);
+}
+
+void scan_noreclaim_unregister_node(struct node *node)
+{
+ sysdev_remove_file(&node->sysdev, &attr_scan_noreclaim_pages);
+}
+
#endif
_
Patches currently in -mm which might be from lee.schermerhorn@xxxxxx are
page-allocator-inlnie-some-__alloc_pages-wrappers.patch
page-allocator-inlnie-some-__alloc_pages-wrappers-fix.patch
vmscan-use-an-indexed-array-for-lru-variables.patch
vmscan-define-page_file_cache-function.patch
vmscan-pageflag-helpers-for-configed-out-flags.patch
vmscan-noreclaim-lru-infrastructure.patch
vmscan-noreclaim-lru-page-statistics.patch
vmscan-ramfs-and-ram-disk-pages-are-non-reclaimable.patch
vmscan-shm_locked-pages-are-non-reclaimable.patch
vmscan-mlocked-pages-are-non-reclaimable.patch
vmscan-downgrade-mmap-sem-while-populating-mlocked-regions.patch
vmscan-handle-mlocked-pages-during-map-remap-unmap.patch
vmscan-mlocked-pages-statistics.patch
vmscan-cull-non-reclaimable-pages-in-fault-path.patch
vmscan-noreclaim-and-mlocked-pages-vm-events.patch
mm-only-vmscan-noreclaim-lru-scan-sysctl.patch
vmscan-mlocked-pages-count-attempts-to-free-mlocked-page.patch
vmscan-noreclaim-lru-and-mlocked-pages-documentation.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
