mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Michael wang <wangyun@linux.vnet.ibm.com>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>,
	Rik van Riel <riel@redhat.com>, Ingo Molnar <mingo@kernel.org>,
	Alex Shi <alex.shi@linaro.org>, Paul Turner <pjt@google.com>,
	Mel Gorman <mgorman@suse.de>,
	Daniel Lezcano <daniel.lezcano@linaro.org>,
	LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] sched: select 'idle' cfs_rq per task-group to prevent tg-internal imbalance
Date: Wed, 2 Jul 2014 15:15:07 +0200	[thread overview]
Message-ID: <20140702131507.GM3588@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <20140702124918.GE19379@twins.programming.kicks-ass.net>

[-- Attachment #1: Type: text/plain, Size: 9685 bytes --]

On Wed, Jul 02, 2014 at 02:49:18PM +0200, Peter Zijlstra wrote:
> Clearly I need to go take out all these things because people don't seem
> to know this and SCHED_DEBUG isn't a big enough hint. Tedious.

Maybe this would be enough clue?

---
 include/linux/kernel.h       |  1 +
 include/linux/sched/sysctl.h |  6 +++++
 kernel/panic.c               |  2 ++
 kernel/sched/core.c          | 59 +++++++++++++++++++++++++++++++++++---------
 kernel/sched/fair.c          |  3 +++
 kernel/sched/sched.h         |  2 ++
 kernel/sysctl.c              | 18 +++++++-------
 7 files changed, 70 insertions(+), 21 deletions(-)

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 4c52907a6d8b..e2dd5ca9e6bf 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -470,6 +470,7 @@ extern enum system_states {
 #define TAINT_FIRMWARE_WORKAROUND	11
 #define TAINT_OOT_MODULE		12
 #define TAINT_UNSIGNED_MODULE		13
+#define TAINT_DEBUG			14
 
 extern const char hex_asc[];
 #define hex_asc_lo(x)	hex_asc[((x) & 0x0f)]
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 596a0e007c62..9d8f04bc555d 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -60,6 +60,12 @@ extern unsigned int sysctl_sched_time_avg;
 extern unsigned int sysctl_timer_migration;
 extern unsigned int sysctl_sched_shares_window;
 
+int sched_debug_proc_dointvec_minmax(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp, loff_t *ppos);
+
+int sched_debug_proc_doulongvec_minmax(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp, loff_t *ppos);
+
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *length,
 		loff_t *ppos);
diff --git a/kernel/panic.c b/kernel/panic.c
index 62e16cef9cc2..e407bf59546c 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -224,6 +224,7 @@ static const struct tnt tnts[] = {
 	{ TAINT_FIRMWARE_WORKAROUND,	'I', ' ' },
 	{ TAINT_OOT_MODULE,		'O', ' ' },
 	{ TAINT_UNSIGNED_MODULE,	'E', ' ' },
+	{ TAINT_DEBUG,			'G', ' ' },
 };
 
 /**
@@ -243,6 +244,7 @@ static const struct tnt tnts[] = {
  *  'I' - Working around severe firmware bug.
  *  'O' - Out-of-tree module has been loaded.
  *  'E' - Unsigned module has been loaded.
+ *  'G' - The user fiddled with nonstandard settings.
  *
  *	The string is overwritten by the next call to print_tainted().
  */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f11515cf070b..851f6bf6abea 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -159,6 +159,36 @@ const_debug unsigned int sysctl_sched_features =
 #undef SCHED_FEAT
 
 #ifdef CONFIG_SCHED_DEBUG
+void sched_debug_taint(void)
+{
+	static bool once;
+
+	if (once)
+		return;
+
+	once = true;
+	add_taint(TAINT_DEBUG, true);
+	printk(KERN_WARN "Tained kernel 'G' -- poking at debug settings.\n");
+}
+
+int sched_debug_proc_dointvec_minmax(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	if (write)
+		sched_debug_taint();
+
+	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+}
+
+int sched_debug_proc_doulongvec_minmax(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	if (write)
+		sched_debug_taint();
+
+	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
+}
+
 #define SCHED_FEAT(name, enabled)	\
 	#name ,
 
@@ -246,6 +276,8 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 	char *cmp;
 	int i;
 
+	sched_debug_taint();
+
 	if (cnt > 63)
 		cnt = 63;
 
@@ -1855,6 +1887,9 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
 	int err;
 	int state = numabalancing_enabled;
 
+	if (write)
+		sched_debug_taint();
+
 	if (write && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
@@ -4956,31 +4991,31 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
 		return NULL;
 
 	set_table_entry(&table[0], "min_interval", &sd->min_interval,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
+		sizeof(long), 0644, sched_debug_proc_doulongvec_minmax, false);
 	set_table_entry(&table[1], "max_interval", &sd->max_interval,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
+		sizeof(long), 0644, sched_debug_proc_doulongvec_minmax, false);
 	set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
+		sizeof(int), 0644, sched_debug_proc_dointvec_minmax, true);
 	set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
+		sizeof(int), 0644, sched_debug_proc_dointvec_minmax, true);
 	set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
+		sizeof(int), 0644, sched_debug_proc_dointvec_minmax, true);
 	set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
+		sizeof(int), 0644, sched_debug_proc_dointvec_minmax, true);
 	set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
+		sizeof(int), 0644, sched_debug_proc_dointvec_minmax, true);
 	set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
+		sizeof(int), 0644, sched_debug_proc_dointvec_minmax, false);
 	set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
+		sizeof(int), 0644, sched_debug_proc_dointvec_minmax, false);
 	set_table_entry(&table[9], "cache_nice_tries",
 		&sd->cache_nice_tries,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
+		sizeof(int), 0644, sched_debug_proc_dointvec_minmax, false);
 	set_table_entry(&table[10], "flags", &sd->flags,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
+		sizeof(int), 0644, sched_debug_proc_dointvec_minmax, false);
 	set_table_entry(&table[11], "max_newidle_lb_cost",
 		&sd->max_newidle_lb_cost,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
+		sizeof(long), 0644, sched_debug_proc_doulongvec_minmax, false);
 	set_table_entry(&table[12], "name", sd->name,
 		CORENAME_MAX_SIZE, 0444, proc_dostring, false);
 	/* &table[13] is terminator */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 923fe32db6b3..e09202eb348f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -577,6 +577,9 @@ int sched_proc_update_handler(struct ctl_table *table, int write,
 	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	int factor = get_update_sysctl_factor();
 
+	if (write)
+		sched_debug_taint();
+
 	if (ret || !write)
 		return ret;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0191ed563bdd..fa880ca9ee4a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -874,6 +874,8 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 # define const_debug const
 #endif
 
+extern void sched_debug_taint(void);
+
 extern const_debug unsigned int sysctl_sched_features;
 
 #define SCHED_FEAT(name, enabled)	\
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 7de6555cfea0..f9810984f3ca 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -328,35 +328,35 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_sched_migration_cost,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= sched_debug_proc_dointvec_minmax,
 	},
 	{
 		.procname	= "sched_nr_migrate",
 		.data		= &sysctl_sched_nr_migrate,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= sched_debug_proc_dointvec_minmax,
 	},
 	{
 		.procname	= "sched_time_avg_ms",
 		.data		= &sysctl_sched_time_avg,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= sched_debug_proc_dointvec_minmax,
 	},
 	{
 		.procname	= "sched_shares_window_ns",
 		.data		= &sysctl_sched_shares_window,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= sched_debug_proc_dointvec_minmax,
 	},
 	{
 		.procname	= "timer_migration",
 		.data		= &sysctl_timer_migration,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= sched_debug_proc_dointvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
@@ -367,28 +367,28 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_numa_balancing_scan_delay,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= sched_debug_proc_dointvec_minmax,
 	},
 	{
 		.procname	= "numa_balancing_scan_period_min_ms",
 		.data		= &sysctl_numa_balancing_scan_period_min,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= sched_debug_proc_dointvec_minmax,
 	},
 	{
 		.procname	= "numa_balancing_scan_period_max_ms",
 		.data		= &sysctl_numa_balancing_scan_period_max,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= sched_debug_proc_dointvec_minmax,
 	},
 	{
 		.procname	= "numa_balancing_scan_size_mb",
 		.data		= &sysctl_numa_balancing_scan_size,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= sched_debug_proc_dointvec_minmax,
 	},
 	{
 		.procname	= "numa_balancing",

[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]

  reply	other threads:[~2014-07-02 13:15 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-06-18  4:50 Michael wang
2014-06-23  9:42 ` Peter Zijlstra
2014-06-24  3:34   ` Michael wang
2014-07-01  8:20     ` Peter Zijlstra
2014-07-01  8:38       ` Michael wang
2014-07-01  8:56         ` Peter Zijlstra
2014-07-02  2:47           ` Michael wang
2014-07-02 12:49             ` Peter Zijlstra
2014-07-02 13:15               ` Peter Zijlstra [this message]
2014-07-03 16:29                 ` Nicolas Pitre
2014-07-03  2:09               ` Michael wang
2014-07-02 14:47         ` Rik van Riel
2014-07-03  2:16           ` Michael wang
2014-07-03  3:51           ` Mike Galbraith
2014-07-11 16:11             ` Rik van Riel
2014-07-14  1:29               ` Michael wang
2014-06-30  7:36 ` Michael wang
2014-06-30  8:06   ` Mike Galbraith
2014-06-30  8:47     ` Michael wang
2014-06-30  9:27       ` Mike Galbraith
2014-07-01  2:57         ` Michael wang
2014-07-01  5:41           ` Mike Galbraith
2014-07-01  6:10             ` Michael wang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20140702131507.GM3588@twins.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=alex.shi@linaro.org \
    --cc=daniel.lezcano@linaro.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@kernel.org \
    --cc=pjt@google.com \
    --cc=riel@redhat.com \
    --cc=umgwanakikbuti@gmail.com \
    --cc=wangyun@linux.vnet.ibm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome