linux-kernel - [PATCH v2] Show kernel stack usage to /proc/meminfo and OOM log

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20090701103622.85CD.A69D9226@jp.fujitsu.com>
Date:	Wed,  1 Jul 2009 10:37:09 +0900 (JST)
From:	KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
To:	Christoph Lameter <cl@...ux-foundation.org>
Cc:	kosaki.motohiro@...fujitsu.com,
	Minchan Kim <minchan.kim@...il.com>,
	Johannes Weiner <hannes@...xchg.org>,
	David Howells <dhowells@...hat.com>,
	"riel@...hat.com" <riel@...hat.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	LKML <linux-kernel@...r.kernel.org>,
	"peterz@...radead.org" <peterz@...radead.org>,
	"tytso@....edu" <tytso@....edu>,
	"linux-mm@...ck.org" <linux-mm@...ck.org>,
	"elladan@...imo.com" <elladan@...imo.com>,
	"npiggin@...e.de" <npiggin@...e.de>,
	"Barnes, Jesse" <jesse.barnes@...el.com>
Subject: [PATCH v2] Show kernel stack usage to /proc/meminfo and OOM log

Subject: [PATCH] Show kernel stack usage to /proc/meminfo and OOM log

if the system have a lot of thread, kernel stack consume unignorable large size
memory.
IOW, it make a lot of unaccountable memory.

Tons unaccountable memory bring to harder analyse memory related trouble.

Then, kernel stack account is useful.


Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
---
 fs/proc/meminfo.c      |    2 ++
 include/linux/mmzone.h |    3 ++-
 kernel/fork.c          |   12 ++++++++++++
 mm/page_alloc.c        |    6 ++++--
 mm/vmstat.c            |    1 +
 5 files changed, 21 insertions(+), 3 deletions(-)

Index: b/fs/proc/meminfo.c
===================================================================
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -85,6 +85,7 @@ static int meminfo_proc_show(struct seq_
 		"SReclaimable:   %8lu kB\n"
 		"SUnreclaim:     %8lu kB\n"
 		"PageTables:     %8lu kB\n"
+		"KernelStack     %8lu kB\n"
 #ifdef CONFIG_QUICKLIST
 		"Quicklists:     %8lu kB\n"
 #endif
@@ -129,6 +130,7 @@ static int meminfo_proc_show(struct seq_
 		K(global_page_state(NR_SLAB_RECLAIMABLE)),
 		K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
 		K(global_page_state(NR_PAGETABLE)),
+		K(global_page_state(NR_KERNEL_STACK)),
 #ifdef CONFIG_QUICKLIST
 		K(quicklist_total_size()),
 #endif
Index: b/include/linux/mmzone.h
===================================================================
--- 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 */
Index: b/kernel/fork.c
===================================================================
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -137,9 +137,18 @@ 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 on)
+{
+	struct zone *zone = page_zone(virt_to_page(ti));
+	int pages = THREAD_SIZE / PAGE_SIZE;
+
+	mod_zone_page_state(zone, NR_KERNEL_STACK, on ? pages : -pages);
+}
+
 void free_task(struct task_struct *tsk)
 {
 	prop_local_destroy_single(&tsk->dirties);
+	account_kernel_stack(tsk->stack, 0);
 	free_thread_info(tsk->stack);
 	rt_mutex_debug_task_free(tsk);
 	ftrace_graph_exit_task(tsk);
@@ -255,6 +264,9 @@ static struct task_struct *dup_task_stru
 	tsk->btrace_seq = 0;
 #endif
 	tsk->splice_pipe = NULL;
+
+	account_kernel_stack(ti, 1);
+
 	return tsk;
 
 out:
Index: b/mm/page_alloc.c
===================================================================
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2119,7 +2119,8 @@ void show_free_areas(void)
 		" inactive_file:%lu"
 		" unevictable:%lu"
 		" dirty:%lu writeback:%lu unstable:%lu\n"
-		" free:%lu slab:%lu mapped:%lu pagetables:%lu bounce:%lu\n",
+		" free:%lu slab:%lu mapped:%lu pagetables:%lu bounce:%lu\n"
+		" kernel_stack:%lu\n",
 		global_page_state(NR_ACTIVE_ANON),
 		global_page_state(NR_ACTIVE_FILE),
 		global_page_state(NR_INACTIVE_ANON),
@@ -2133,7 +2134,8 @@ void show_free_areas(void)
 			global_page_state(NR_SLAB_UNRECLAIMABLE),
 		global_page_state(NR_FILE_MAPPED),
 		global_page_state(NR_PAGETABLE),
-		global_page_state(NR_BOUNCE));
+		global_page_state(NR_BOUNCE),
+		global_page_state(NR_KERNEL_STACK));
 
 	for_each_populated_zone(zone) {
 		int i;
Index: b/mm/vmstat.c
===================================================================
--- 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",


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/