mm: oom analysis: Show kernel stack usage in /proc/meminfo and OOM log output

The amount of memory allocated to kernel stacks can become significant and
cause OOM conditions.  However, we do not display the amount of memory
consumed by stacks.

Add code to display the amount of memory used for stacks in /proc/meminfo.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 22 insertions, 1 deletions

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 91d4087b4039..b560c17f6d4e 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -85,6 +85,7 @@ static ssize_t node_read_meminfo(struct sys_device * dev,
                        "Node %d FilePages:      %8lu kB\n"
                        "Node %d Mapped:         %8lu kB\n"
                        "Node %d AnonPages:      %8lu kB\n"
+                       "Node %d KernelStack:    %8lu kB\n"
                        "Node %d PageTables:     %8lu kB\n"
                        "Node %d NFS_Unstable:   %8lu kB\n"
                        "Node %d Bounce:         %8lu kB\n"
@@ -116,6 +117,8 @@ static ssize_t node_read_meminfo(struct sys_device * dev,
                        nid, K(node_page_state(nid, NR_FILE_PAGES)),
                        nid, K(node_page_state(nid, NR_FILE_MAPPED)),
                        nid, K(node_page_state(nid, NR_ANON_PAGES)),
+                       nid, node_page_state(nid, NR_KERNEL_STACK) *
+                                THREAD_SIZE / 1024,
                        nid, K(node_page_state(nid, NR_PAGETABLE)),
                        nid, K(node_page_state(nid, NR_UNSTABLE_NFS)),
                        nid, K(node_page_state(nid, NR_BOUNCE)),
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index d5c410d47fae..1fc588f430e4 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -84,6 +84,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
                 "Slab:           %8lu kB\n"
                 "SReclaimable:   %8lu kB\n"
                 "SUnreclaim:     %8lu kB\n"
+                "KernelStack:    %8lu kB\n"
                 "PageTables:     %8lu kB\n"
 #ifdef CONFIG_QUICKLIST
                 "Quicklists:     %8lu kB\n"
@@ -128,6 +129,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
                                 global_page_state(NR_SLAB_UNRECLAIMABLE)),
                 K(global_page_state(NR_SLAB_RECLAIMABLE)),
                 K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
+                global_page_state(NR_KERNEL_STACK) * THREAD_SIZE / 1024,
                 K(global_page_state(NR_PAGETABLE)),
 #ifdef CONFIG_QUICKLIST
                 K(quicklist_total_size()),
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 889598537370..d9335b8de84a 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -94,10 +94,11 @@ enum zone_stat_item {
         NR_SLAB_RECLAIMABLE,
         NR_SLAB_UNRECLAIMABLE,
         NR_PAGETABLE,           /* used for pagetables */
+        NR_KERNEL_STACK,
+        /* Second 128 byte cacheline */
         NR_UNSTABLE_NFS,        /* NFS unstable pages */
         NR_BOUNCE,
         NR_VMSCAN_WRITE,
-        /* Second 128 byte cacheline */
         NR_WRITEBACK_TEMP,      /* Writeback using temporary buffers */
 #ifdef CONFIG_NUMA
         NUMA_HIT,               /* allocated in intended node */
diff --git a/kernel/fork.c b/kernel/fork.c
index 2cebfb23b0b8..d4638c8cc19e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -136,9 +136,17 @@ struct kmem_cache *vm_area_cachep;
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
+static void account_kernel_stack(struct thread_info *ti, int account)
+{
+        struct zone *zone = page_zone(virt_to_page(ti));
+
+        mod_zone_page_state(zone, NR_KERNEL_STACK, account);
+}
+
 void free_task(struct task_struct *tsk)
 {
         prop_local_destroy_single(&tsk->dirties);
+        account_kernel_stack(tsk->stack, -1);
         free_thread_info(tsk->stack);
         rt_mutex_debug_task_free(tsk);
         ftrace_graph_exit_task(tsk);
@@ -253,6 +261,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
         tsk->btrace_seq = 0;
 #endif
         tsk->splice_pipe = NULL;
+
+        account_kernel_stack(ti, 1);
+
         return tsk;
 
 out:
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 494c09196c30..4e050f325ebd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2177,6 +2177,7 @@ void show_free_areas(void)
                         " mapped:%lukB"
                         " slab_reclaimable:%lukB"
                         " slab_unreclaimable:%lukB"
+                        " kernel_stack:%lukB"
                         " pagetables:%lukB"
                         " unstable:%lukB"
                         " bounce:%lukB"
@@ -2201,6 +2202,8 @@ void show_free_areas(void)
                         K(zone_page_state(zone, NR_FILE_MAPPED)),
                         K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)),
                         K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)),
+                        zone_page_state(zone, NR_KERNEL_STACK) *
+                                THREAD_SIZE / 1024,
                         K(zone_page_state(zone, NR_PAGETABLE)),
                         K(zone_page_state(zone, NR_UNSTABLE_NFS)),
                         K(zone_page_state(zone, NR_BOUNCE)),
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 138bed53706e..ceda39b63d7e 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -639,6 +639,7 @@ static const char * const vmstat_text[] = {
         "nr_slab_reclaimable",
         "nr_slab_unreclaimable",
         "nr_page_table_pages",
+        "nr_kernel_stack",
         "nr_unstable",
         "nr_bounce",
         "nr_vmscan_write",