[PATCH] VM: add page_state info to per-node meminfo

Add page_state info to the per-node meminfo file in sysfs.  This is mostly
just for informational purposes.

The lack of this information was brought up recently during a discussion
regarding pagecache clearing, and I put this patch together to test out one
of the suggestions.

It seems like interesting info to have, so I'm submitting the patch.

Signed-off-by: Martin Hicks <mort@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 43 insertions, 7 deletions

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 904b27caf69..16c513aa4d4 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -39,13 +39,25 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
         int n;
         int nid = dev->id;
         struct sysinfo i;
+        struct page_state ps;
         unsigned long inactive;
         unsigned long active;
         unsigned long free;
 
         si_meminfo_node(&i, nid);
+        get_page_state_node(&ps, nid);
         __get_zone_counts(&active, &inactive, &free, NODE_DATA(nid));
 
+        /* Check for negative values in these approximate counters */
+        if ((long)ps.nr_dirty < 0)
+                ps.nr_dirty = 0;
+        if ((long)ps.nr_writeback < 0)
+                ps.nr_writeback = 0;
+        if ((long)ps.nr_mapped < 0)
+                ps.nr_mapped = 0;
+        if ((long)ps.nr_slab < 0)
+                ps.nr_slab = 0;
+
         n = sprintf(buf, "\n"
                        "Node %d MemTotal:     %8lu kB\n"
                        "Node %d MemFree:      %8lu kB\n"
@@ -55,7 +67,11 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
                        "Node %d HighTotal:    %8lu kB\n"
                        "Node %d HighFree:     %8lu kB\n"
                        "Node %d LowTotal:     %8lu kB\n"
-                       "Node %d LowFree:      %8lu kB\n",
+                       "Node %d LowFree:      %8lu kB\n"
+                       "Node %d Dirty:        %8lu kB\n"
+                       "Node %d Writeback:    %8lu kB\n"
+                       "Node %d Mapped:       %8lu kB\n"
+                       "Node %d Slab:         %8lu kB\n",
                        nid, K(i.totalram),
                        nid, K(i.freeram),
                        nid, K(i.totalram - i.freeram),
@@ -64,7 +80,11 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
                        nid, K(i.totalhigh),
                        nid, K(i.freehigh),
                        nid, K(i.totalram - i.totalhigh),
-                       nid, K(i.freeram - i.freehigh));
+                       nid, K(i.freeram - i.freehigh),
+                       nid, K(ps.nr_dirty),
+                       nid, K(ps.nr_writeback),
+                       nid, K(ps.nr_mapped),
+                       nid, K(ps.nr_slab));
         n += hugetlb_report_node_meminfo(nid, buf + n);
         return n;
 }
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 99f7cc49506..f34767c5fc7 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -134,6 +134,7 @@ struct page_state {
 };
 
 extern void get_page_state(struct page_state *ret);
+extern void get_page_state_node(struct page_state *ret, int node);
 extern void get_full_page_state(struct page_state *ret);
 extern unsigned long __read_page_state(unsigned long offset);
 extern void __mod_page_state(unsigned long offset, unsigned long delta);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d157dae8c9f..b06a9636d97 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1130,19 +1130,20 @@ EXPORT_SYMBOL(nr_pagecache);
 DEFINE_PER_CPU(long, nr_pagecache_local) = 0;
 #endif
 
-void __get_page_state(struct page_state *ret, int nr)
+void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask)
 {
         int cpu = 0;
 
         memset(ret, 0, sizeof(*ret));
+        cpus_and(*cpumask, *cpumask, cpu_online_map);
 
-        cpu = first_cpu(cpu_online_map);
+        cpu = first_cpu(*cpumask);
         while (cpu < NR_CPUS) {
                 unsigned long *in, *out, off;
 
                 in = (unsigned long *)&per_cpu(page_states, cpu);
 
-                cpu = next_cpu(cpu, cpu_online_map);
+                cpu = next_cpu(cpu, *cpumask);
 
                 if (cpu < NR_CPUS)
                         prefetch(&per_cpu(page_states, cpu));
@@ -1153,19 +1154,33 @@ void __get_page_state(struct page_state *ret, int nr)
         }
 }
 
+void get_page_state_node(struct page_state *ret, int node)
+{
+        int nr;
+        cpumask_t mask = node_to_cpumask(node);
+
+        nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
+        nr /= sizeof(unsigned long);
+
+        __get_page_state(ret, nr+1, &mask);
+}
+
 void get_page_state(struct page_state *ret)
 {
         int nr;
+        cpumask_t mask = CPU_MASK_ALL;
 
         nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
         nr /= sizeof(unsigned long);
 
-        __get_page_state(ret, nr + 1);
+        __get_page_state(ret, nr + 1, &mask);
 }
 
 void get_full_page_state(struct page_state *ret)
 {
-        __get_page_state(ret, sizeof(*ret) / sizeof(unsigned long));
+        cpumask_t mask = CPU_MASK_ALL;
+
+        __get_page_state(ret, sizeof(*ret) / sizeof(unsigned long), &mask);
 }
 
 unsigned long __read_page_state(unsigned long offset)