sched/debug: Fix 'schedstats=enable' cmdline option

The 'schedstats=enable' option doesn't work, and also produces the
following warning during boot:

  WARNING: CPU: 0 PID: 0 at /home/jpoimboe/git/linux/kernel/jump_label.c:61 static_key_slow_inc+0x8c/0xa0
  static_key_slow_inc used before call to jump_label_init
  Modules linked in:
  CPU: 0 PID: 0 Comm: swapper Not tainted 4.7.0-rc1+ #25
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014
   0000000000000086 3ae3475a4bea95d4 ffffffff81e03da8 ffffffff8143fc83
   ffffffff81e03df8 0000000000000000 ffffffff81e03de8 ffffffff810b1ffb
   0000003d00000096 ffffffff823514d0 ffff88007ff197c8 0000000000000000
  Call Trace:
   [<ffffffff8143fc83>] dump_stack+0x85/0xc2
   [<ffffffff810b1ffb>] __warn+0xcb/0xf0
   [<ffffffff810b207f>] warn_slowpath_fmt+0x5f/0x80
   [<ffffffff811e9c0c>] static_key_slow_inc+0x8c/0xa0
   [<ffffffff810e07c6>] static_key_enable+0x16/0x40
   [<ffffffff8216d633>] setup_schedstats+0x29/0x94
   [<ffffffff82148a05>] unknown_bootoption+0x89/0x191
   [<ffffffff810d8617>] parse_args+0x297/0x4b0
   [<ffffffff82148d61>] start_kernel+0x1d8/0x4a9
   [<ffffffff8214897c>] ? set_init_arg+0x55/0x55
   [<ffffffff82148120>] ? early_idt_handler_array+0x120/0x120
   [<ffffffff821482db>] x86_64_start_reservations+0x2f/0x31
   [<ffffffff82148427>] x86_64_start_kernel+0x14a/0x16d

The problem is that it tries to update the 'sched_schedstats' static key
before jump labels have been initialized.

Changing jump_label_init() to be called earlier before
parse_early_param() wouldn't fix it: it would still fail trying to
poke_text() because mm isn't yet initialized.

Instead, just create a temporary '__sched_schedstats' variable which can
be copied to the static key later during sched_init() after jump labels
have been initialized.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: cb2517653fcc ("sched/debug: Make schedstats a runtime tunable that is disabled by default")
Link: http://lkml.kernel.org/r/453775fe3433bed65731a583e228ccea806d18cd.1465322027.git.jpoimboe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7f2cae4..385c947 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2253,9 +2253,11 @@ int sysctl_numa_balancing(struct ctl_table *table, int write,
 #endif
 #endif
 
+#ifdef CONFIG_SCHEDSTATS
+
 DEFINE_STATIC_KEY_FALSE(sched_schedstats);
+static bool __initdata __sched_schedstats = false;
 
-#ifdef CONFIG_SCHEDSTATS
 static void set_schedstats(bool enabled)
 {
        if (enabled)
@@ -2278,11 +2280,16 @@ static int __init setup_schedstats(char *str)
        if (!str)
                goto out;
 
+       /*
+        * This code is called before jump labels have been set up, so we can't
+        * change the static branch directly just yet.  Instead set a temporary
+        * variable so init_schedstats() can do it later.
+        */
        if (!strcmp(str, "enable")) {
-               set_schedstats(true);
+               __sched_schedstats = true;
                ret = 1;
        } else if (!strcmp(str, "disable")) {
-               set_schedstats(false);
+               __sched_schedstats = false;
                ret = 1;
        }
 out:
@@ -2293,6 +2300,11 @@ out:
 }
 __setup("schedstats=", setup_schedstats);
 
+static void __init init_schedstats(void)
+{
+       set_schedstats(__sched_schedstats);
+}
+
 #ifdef CONFIG_PROC_SYSCTL
 int sysctl_schedstats(struct ctl_table *table, int write,
                         void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -2313,8 +2325,10 @@ int sysctl_schedstats(struct ctl_table *table, int write,
                set_schedstats(state);
        return err;
 }
-#endif
-#endif
+#endif /* CONFIG_PROC_SYSCTL */
+#else  /* !CONFIG_SCHEDSTATS */
+static inline void init_schedstats(void) {}
+#endif /* CONFIG_SCHEDSTATS */
 
 /*
  * fork()/clone()-time setup:
@@ -7487,6 +7501,8 @@ void __init sched_init(void)
 #endif
        init_sched_fair_class();
 
+       init_schedstats();
+
        scheduler_running = 1;
 }