[ANNOUNCE] v4.9.30-rt21

Dear RT folks!

I'm pleased to announce the v4.9.30-rt21 patch set.

Changes since v4.9.30-rt20:

  - gdb. While gdb is following a task was is possible that after a
    fork() operation the task was waiting for gdb and gdb waiting for
    the task. Reported by Mathias Koehrer and David Hauck. Patched by
    Thomas Gleixner.

  - Since the change above the define TASK_ALL remains unused and got
    removed by Peter Zijlstra.

Known issues
	- CPU hotplug got a little better but can deadlock.

The delta patch against v4.9.30-rt20 is appended below and can be found here:

     https://cdn.kernel.org/pub/linux/kernel/projects/rt/4.9/incr/patch-4.9.30-rt20-rt21.patch.xz

You can get this release via the git tree at:

    git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git v4.9.30-rt21

The RT patch against v4.9.30 can be found here:

    https://cdn.kernel.org/pub/linux/kernel/projects/rt/4.9/older/patch-4.9.30-rt21.patch.xz

The split quilt queue is available at:

    https://cdn.kernel.org/pub/linux/kernel/projects/rt/4.9/older/patches-4.9.30-rt21.tar.xz

Sebastian

12 files changed, 121 insertions, 13 deletions

diff --git a/patches/cond-resched-softirq-rt.patch b/patches/cond-resched-softirq-rt.patch
index cd245953aff9ff..5475b66575de39 100644
--- a/patches/cond-resched-softirq-rt.patch
+++ b/patches/cond-resched-softirq-rt.patch
@@ -15,7 +15,7 @@ Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
 
 --- a/include/linux/sched.h
 +++ b/include/linux/sched.h
-@@ -3373,12 +3373,16 @@ extern int __cond_resched_lock(spinlock_
+@@ -3372,12 +3372,16 @@ extern int __cond_resched_lock(spinlock_
  	__cond_resched_lock(lock);				\
  })
  
diff --git a/patches/cpu-rt-rework-cpu-down.patch b/patches/cpu-rt-rework-cpu-down.patch
index ecfa0355015a38..00b2a2b57fcf29 100644
--- a/patches/cpu-rt-rework-cpu-down.patch
+++ b/patches/cpu-rt-rework-cpu-down.patch
@@ -56,7 +56,7 @@ Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
 
 --- a/include/linux/sched.h
 +++ b/include/linux/sched.h
-@@ -2480,6 +2480,10 @@ extern void do_set_cpus_allowed(struct t
+@@ -2479,6 +2479,10 @@ extern void do_set_cpus_allowed(struct t
  
  extern int set_cpus_allowed_ptr(struct task_struct *p,
  				const struct cpumask *new_mask);
@@ -67,7 +67,7 @@ Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
  #else
  static inline void do_set_cpus_allowed(struct task_struct *p,
  				      const struct cpumask *new_mask)
-@@ -2492,6 +2496,9 @@ static inline int set_cpus_allowed_ptr(s
+@@ -2491,6 +2495,9 @@ static inline int set_cpus_allowed_ptr(s
  		return -EINVAL;
  	return 0;
  }
diff --git a/patches/localversion.patch b/patches/localversion.patch
index d7c1a50b87ee55..bba4391fd1bdb9 100644
--- a/patches/localversion.patch
+++ b/patches/localversion.patch
@@ -10,4 +10,4 @@ Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
 --- /dev/null
 +++ b/localversion-rt
 @@ -0,0 +1 @@
-+-rt20
++-rt21
diff --git a/patches/mm-rt-kmap-atomic-scheduling.patch b/patches/mm-rt-kmap-atomic-scheduling.patch
index 6e7e6203024a32..0b521f4b9a92da 100644
--- a/patches/mm-rt-kmap-atomic-scheduling.patch
+++ b/patches/mm-rt-kmap-atomic-scheduling.patch
@@ -229,7 +229,7 @@ Link: http://lkml.kernel.org/r/1311842631.5890.208.camel@twins
  
  #include <asm/page.h>
  #include <asm/ptrace.h>
-@@ -1986,6 +1987,12 @@ struct task_struct {
+@@ -1985,6 +1986,12 @@ struct task_struct {
  	int softirq_nestcnt;
  	unsigned int softirqs_raised;
  #endif
diff --git a/patches/net-move-xmit_recursion-to-per-task-variable-on-RT.patch b/patches/net-move-xmit_recursion-to-per-task-variable-on-RT.patch
index 63795fe8c2bd32..6c6125c6d2aff2 100644
--- a/patches/net-move-xmit_recursion-to-per-task-variable-on-RT.patch
+++ b/patches/net-move-xmit_recursion-to-per-task-variable-on-RT.patch
@@ -80,7 +80,7 @@ Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
  struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
 --- a/include/linux/sched.h
 +++ b/include/linux/sched.h
-@@ -1989,6 +1989,9 @@ struct task_struct {
+@@ -1988,6 +1988,9 @@ struct task_struct {
  #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
  	unsigned long	task_state_change;
  #endif
diff --git a/patches/preempt-lazy-support.patch b/patches/preempt-lazy-support.patch
index b1f3fcf35d1d7d..131245a37735a8 100644
--- a/patches/preempt-lazy-support.patch
+++ b/patches/preempt-lazy-support.patch
@@ -127,7 +127,7 @@ Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
  
 --- a/include/linux/sched.h
 +++ b/include/linux/sched.h
-@@ -3349,6 +3349,43 @@ static inline int test_tsk_need_resched(
+@@ -3348,6 +3348,43 @@ static inline int test_tsk_need_resched(
  	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
  }
  
diff --git a/patches/ptrace-fix-ptrace-vs-tasklist_lock-race.patch b/patches/ptrace-fix-ptrace-vs-tasklist_lock-race.patch
index f14263f8b2df7d..dd83349b49d15b 100644
--- a/patches/ptrace-fix-ptrace-vs-tasklist_lock-race.patch
+++ b/patches/ptrace-fix-ptrace-vs-tasklist_lock-race.patch
@@ -30,7 +30,7 @@ Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
 
 --- a/include/linux/sched.h
 +++ b/include/linux/sched.h
-@@ -243,10 +243,7 @@ extern char ___assert_task_state[1 - 2*!
+@@ -242,10 +242,7 @@ extern char ___assert_task_state[1 - 2*!
  				 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
  				 __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD)
  
@@ -41,7 +41,7 @@ Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
  #define task_contributes_to_load(task)	\
  				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
  				 (task->flags & PF_FROZEN) == 0 && \
-@@ -3366,6 +3363,51 @@ static inline int signal_pending_state(l
+@@ -3365,6 +3362,51 @@ static inline int signal_pending_state(l
  	return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p);
  }
  
diff --git a/patches/rt-add-rt-locks.patch b/patches/rt-add-rt-locks.patch
index 90426cd427bf5e..e53cd235d57bcc 100644
--- a/patches/rt-add-rt-locks.patch
+++ b/patches/rt-add-rt-locks.patch
@@ -600,7 +600,7 @@ Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
 +#endif
 --- a/include/linux/sched.h
 +++ b/include/linux/sched.h
-@@ -312,6 +312,11 @@ extern char ___assert_task_state[1 - 2*!
+@@ -311,6 +311,11 @@ extern char ___assert_task_state[1 - 2*!
  
  #endif
  
@@ -612,7 +612,7 @@ Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
  /* Task command name length */
  #define TASK_COMM_LEN 16
  
-@@ -1013,8 +1018,18 @@ struct wake_q_head {
+@@ -1012,8 +1017,18 @@ struct wake_q_head {
  	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
  
  extern void wake_q_add(struct wake_q_head *head,
diff --git a/patches/sched-Prevent-task-state-corruption-by-spurious-lock.patch b/patches/sched-Prevent-task-state-corruption-by-spurious-lock.patch
new file mode 100644
index 00000000000000..93f554941463c8
--- /dev/null
+++ b/patches/sched-Prevent-task-state-corruption-by-spurious-lock.patch
@@ -0,0 +1,77 @@
+From: Thomas Gleixner <tglx@linutronix.de>
+Date: Tue, 6 Jun 2017 14:20:37 +0200
+Subject: sched: Prevent task state corruption by spurious lock wakeup
+
+Mathias and others reported GDB failures on RT.
+
+The following scenario leads to task state corruption:
+
+CPU0						CPU1
+
+T1->state = TASK_XXX;
+spin_lock(&lock)
+  rt_spin_lock_slowlock(&lock->rtmutex)
+    raw_spin_lock(&rtm->wait_lock);
+    T1->saved_state = current->state;
+    T1->state = TASK_UNINTERRUPTIBLE;
+						spin_unlock(&lock)
+    task_blocks_on_rt_mutex(rtm)  		  rt_spin_lock_slowunlock(&lock->rtmutex)
+      queue_waiter(rtm)				    raw_spin_lock(&rtm->wait_lock);
+      pi_chain_walk(rtm)
+        raw_spin_unlock(&rtm->wait_lock);
+						    wake_top_waiter(T1)
+
+      raw_spin_lock(&rtm->wait_lock);
+
+    for (;;) {
+      if (__try_to_take_rt_mutex())  <- Succeeds
+        break;
+      ...
+    }
+
+    T1->state = T1->saved_state;
+						     try_to_wake_up(T1)
+						       ttwu_do_wakeup(T1)
+						         T1->state = TASK_RUNNING;
+
+In most cases this is harmless because waiting for some event, which is the
+usual reason for TASK_[UN]INTERRUPTIBLE has to be safe against other forms
+of spurious wakeups anyway.
+
+But in case of TASK_TRACED this is actually fatal, because the task loses
+the TASK_TRACED state. In consequence it fails to consume SIGSTOP which was
+sent from the debugger and actually delivers SIGSTOP to the task which
+breaks the ptrace mechanics and brings the debugger into an unexpected
+state.
+
+The TASK_TRACED state should prevent getting there due to the state
+matching logic in try_to_wake_up(). But that's not true because
+wake_up_lock_sleeper() uses TASK_ALL as state mask. That's bogus because
+lock sleepers always use TASK_UNINTERRUPTIBLE, so the wakeup should use
+that as well.
+
+The cure is way simpler as figuring it out:
+
+Change the mask used in wake_up_lock_sleeper() from TASK_ALL to
+TASK_UNINTERRUPTIBLE.
+
+Cc: stable-rt@vger.kernel.org
+Reported-by: Mathias Koehrer <mathias.koehrer@etas.com>
+Reported-by: David Hauck <davidh@netacquire.com>
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+---
+ kernel/sched/core.c |    2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+--- a/kernel/sched/core.c
++++ b/kernel/sched/core.c
+@@ -2207,7 +2207,7 @@ EXPORT_SYMBOL(wake_up_process);
+  */
+ int wake_up_lock_sleeper(struct task_struct *p)
+ {
+-	return try_to_wake_up(p, TASK_ALL, WF_LOCK_SLEEPER);
++	return try_to_wake_up(p, TASK_UNINTERRUPTIBLE, WF_LOCK_SLEEPER);
+ }
+ 
+ int wake_up_state(struct task_struct *p, unsigned int state)
diff --git a/patches/sched-Remove-TASK_ALL.patch b/patches/sched-Remove-TASK_ALL.patch
new file mode 100644
index 00000000000000..6b25930e3dedd9
--- /dev/null
+++ b/patches/sched-Remove-TASK_ALL.patch
@@ -0,0 +1,29 @@
+From: Peter Zijlstra <peterz@infradead.org>
+Date: Wed, 7 Jun 2017 10:12:45 +0200
+Subject: [PATCH] sched: Remove TASK_ALL
+
+It's unused:
+
+$ git grep "\<TASK_ALL\>" | wc -l
+1
+
+And dangerous, kill the bugger.
+
+Cc: stable-rt@vger.kernel.org
+Acked-by: Thomas Gleixner <tglx@linutronix.de>
+Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
+Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+---
+ include/linux/sched.h |    1 -
+ 1 file changed, 1 deletion(-)
+
+--- a/include/linux/sched.h
++++ b/include/linux/sched.h
+@@ -236,7 +236,6 @@ extern char ___assert_task_state[1 - 2*!
+ 
+ /* Convenience macros for the sake of wake_up */
+ #define TASK_NORMAL		(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
+-#define TASK_ALL		(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
+ 
+ /* get_task_state() */
+ #define TASK_REPORT		(TASK_RUNNING | TASK_INTERRUPTIBLE | \
diff --git a/patches/series b/patches/series
index 2dbc3f45e48a18..601935aca5cc30 100644
--- a/patches/series
+++ b/patches/series
@@ -305,6 +305,8 @@ sched-limit-nr-migrate.patch
 sched-mmdrop-delayed.patch
 kernel-sched-move-stack-kprobe-clean-up-to-__put_tas.patch
 sched-rt-mutex-wakeup.patch
+sched-Prevent-task-state-corruption-by-spurious-lock.patch
+sched-Remove-TASK_ALL.patch
 sched-might-sleep-do-not-account-rcu-depth.patch
 cond-resched-softirq-rt.patch
 cond-resched-lock-rt-tweak.patch
diff --git a/patches/softirq-split-locks.patch b/patches/softirq-split-locks.patch
index 7db052dc25eb87..9c2c45c2d96912 100644
--- a/patches/softirq-split-locks.patch
+++ b/patches/softirq-split-locks.patch
@@ -172,7 +172,7 @@ Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
   * Are we in NMI context?
 --- a/include/linux/sched.h
 +++ b/include/linux/sched.h
-@@ -1971,6 +1971,8 @@ struct task_struct {
+@@ -1970,6 +1970,8 @@ struct task_struct {
  #endif
  #ifdef CONFIG_PREEMPT_RT_BASE
  	struct rcu_head put_rcu;
@@ -181,7 +181,7 @@ Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
  #endif
  #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
  	unsigned long	task_state_change;
-@@ -2287,6 +2289,7 @@ extern void thread_group_cputime_adjuste
+@@ -2286,6 +2288,7 @@ extern void thread_group_cputime_adjuste
  /*
   * Per process flags
   */