Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1489597 > unrolled thread

[PATCH RT 00/10] Linux 4.1.33-rt38-rc1

Back to article view | Back to linux.kernel

Contents

  [PATCH RT 00/10] Linux 4.1.33-rt38-rc1 Steven Rostedt <rostedt@goodmis.org> - 2016-09-23 00:00 +0200
    [PATCH RT 08/10] x86/preempt-lazy: fixup should_resched() Steven Rostedt <rostedt@goodmis.org> - 2016-09-23 00:00 +0200
    [PATCH RT 10/10] Linux 4.1.33-rt38-rc1 Steven Rostedt <rostedt@goodmis.org> - 2016-09-23 00:00 +0200
    [PATCH RT 01/10] timers: wakeup all timer waiters Steven Rostedt <rostedt@goodmis.org> - 2016-09-23 00:00 +0200
    [PATCH RT 02/10] timers: wakeup all timer waiters without holding the base lock Steven Rostedt <rostedt@goodmis.org> - 2016-09-23 00:10 +0200
    Re: [PATCH RT 05/10] net: add back the missing serialization in  ip_send_unicast_reply() Steven Rostedt <rostedt@goodmis.org> - 2016-09-23 00:10 +0200
    [PATCH RT 07/10] fs/dcache: resched/chill only if we make no progress Steven Rostedt <rostedt@goodmis.org> - 2016-09-23 00:10 +0200
    [PATCH RT 04/10] scsi/fcoe: Fix get_cpu()/put_cpu_light() imbalance in  fcoe_recv_frame() Steven Rostedt <rostedt@goodmis.org> - 2016-09-23 00:10 +0200

#1489597 — [PATCH RT 00/10] Linux 4.1.33-rt38-rc1

Dear RT Folks,

This is the RT stable review cycle of patch 4.1.33-rt38-rc1.

Please scream at me if I messed something up. Please test the patches too.

The -rc release will be uploaded to kernel.org and will be deleted when
the final release is out. This is just a review release (or release candidate).

The pre-releases will not be pushed to the git repository, only the
final release is.

If all goes well, this patch will be converted to the next main release
on 9/25/2016.

Enjoy,

-- Steve


To build 4.1.33-rt38-rc1 directly, the following patches should be applied:

  http://www.kernel.org/pub/linux/kernel/v4.x/linux-4.1.tar.xz

  http://www.kernel.org/pub/linux/kernel/v4.x/patch-4.1.33.xz

  http://www.kernel.org/pub/linux/kernel/projects/rt/4.1/patch-4.1.33-rt38-rc1.patch.xz

You can also build from 4.1.33-rt37 by applying the incremental patch:

http://www.kernel.org/pub/linux/kernel/projects/rt/4.1/incr/patch-4.1.33-rt37-rt38-rc1.patch.xz


Changes from 4.1.33-rt37:

---


Mike Galbraith (1):
      scsi/fcoe: Fix get_cpu()/put_cpu_light() imbalance in fcoe_recv_frame()

Sebastian Andrzej Siewior (8):
      timers: wakeup all timer waiters
      timers: wakeup all timer waiters without holding the base lock
      sched: lazy_preempt: avoid a warning in the !RT case
      net: add back the missing serialization in ip_send_unicast_reply()
      net: add a lock around icmp_sk()
      fs/dcache: resched/chill only if we make no progress
      x86/preempt-lazy: fixup should_resched()
      fs/dcache: incremental fixup of the retry routine

Steven Rostedt (Red Hat) (1):
      Linux 4.1.33-rt38-rc1

----
 arch/x86/include/asm/preempt.h | 17 +++++++++++++++--
 drivers/scsi/fcoe/fcoe.c       |  2 +-
 fs/dcache.c                    | 17 ++++++++++++-----
 kernel/sched/core.c            |  2 +-
 kernel/time/timer.c            |  4 ++--
 localversion-rt                |  2 +-
 net/ipv4/icmp.c                |  8 ++++++++
 net/ipv4/tcp_ipv4.c            |  7 +++++++
 8 files changed, 47 insertions(+), 12 deletions(-)

[toc] | [next] | [standalone]

#1489598 — [PATCH RT 08/10] x86/preempt-lazy: fixup should_resched()

4.1.33-rt38-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

should_resched() returns true if NEED_RESCHED is set and the
preempt_count is 0 _or_ if NEED_RESCHED_LAZY is set ignoring the preempt
counter. Ignoring the preemp counter is wrong. This patch adds this into
account.
While at it, __preempt_count_dec_and_test() ignores preempt_lazy_count
while checking TIF_NEED_RESCHED_LAZY so we this check, too.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/x86/include/asm/preempt.h | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index c08949b0314d..eff1b8609f77 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -92,6 +92,8 @@ static __always_inline bool __preempt_count_dec_and_test(void)
 	if (____preempt_count_dec_and_test())
 		return true;
 #ifdef CONFIG_PREEMPT_LAZY
+	if (current_thread_info()->preempt_lazy_count)
+		return false;
 	return test_thread_flag(TIF_NEED_RESCHED_LAZY);
 #else
 	return false;
@@ -104,8 +106,19 @@ static __always_inline bool __preempt_count_dec_and_test(void)
 static __always_inline bool should_resched(int preempt_offset)
 {
 #ifdef CONFIG_PREEMPT_LAZY
-	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset ||
-			test_thread_flag(TIF_NEED_RESCHED_LAZY));
+	u32 tmp;
+
+	tmp = raw_cpu_read_4(__preempt_count);
+	if (tmp == preempt_offset)
+		return true;
+
+	/* preempt count == 0 ? */
+	tmp &= ~PREEMPT_NEED_RESCHED;
+	if (tmp)
+		return false;
+	if (current_thread_info()->preempt_lazy_count)
+		return false;
+	return test_thread_flag(TIF_NEED_RESCHED_LAZY);
 #else
 	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
 #endif
-- 
2.8.1

[toc] | [prev] | [next] | [standalone]

#1489600 — [PATCH RT 10/10] Linux 4.1.33-rt38-rc1

4.1.33-rt38-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

---
 localversion-rt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/localversion-rt b/localversion-rt
index a3b2408c1da6..625367387621 100644
--- a/localversion-rt
+++ b/localversion-rt
@@ -1 +1 @@
--rt37
+-rt38-rc1
-- 
2.8.1

[toc] | [prev] | [next] | [standalone]

#1489603 — [PATCH RT 01/10] timers: wakeup all timer waiters

4.1.33-rt38-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

The base lock is dropped during the invocation if the timer. That means
it is possible that we have one waiter while timer1 is running and once
this one finished, we get another waiter while timer2 is running. Since
we wake up only one waiter it is possible that we miss the other one.
This will probably heal itself over time because most of the time we
complete timers without an active wake up.
To avoid the scenario where we don't wake up all waiters at once,
wake_up_all() is used.

Cc: stable-rt@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/time/timer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index c68ba873da3c..5a45162ae924 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1019,7 +1019,7 @@ static void wait_for_running_timer(struct timer_list *timer)
 			   base->running_timer != timer);
 }
 
-# define wakeup_timer_waiters(b)	wake_up(&(b)->wait_for_running_timer)
+# define wakeup_timer_waiters(b)	wake_up_all(&(b)->wait_for_running_timer)
 #else
 static inline void wait_for_running_timer(struct timer_list *timer)
 {
-- 
2.8.1

[toc] | [prev] | [next] | [standalone]

#1489605 — [PATCH RT 02/10] timers: wakeup all timer waiters without holding the base lock

4.1.33-rt38-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

There should be no need to hold the base lock during the wakeup. There
should be no boosting involved, the wakeup list has its own lock so it
should be safe to do this without the lock.

Cc: stable-rt@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/time/timer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 5a45162ae924..b1f9e6c5bec4 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1279,8 +1279,8 @@ static inline void __run_timers(struct tvec_base *base)
 			}
 		}
 	}
-	wakeup_timer_waiters(base);
 	spin_unlock_irq(&base->lock);
+	wakeup_timer_waiters(base);
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
-- 
2.8.1

[toc] | [prev] | [next] | [standalone]

#1489606 — Re: [PATCH RT 05/10] net: add back the missing serialization in ip_send_unicast_reply()

And again. I need to fix quilt mail to handle this.

-- Steve


On Thu, 22 Sep 2016 17:57:52 -0400
Steven Rostedt <rostedt@goodmis.org> wrote:

> 4.1.33-rt38-rc1 stable review patch.
> If anyone has any objections, please let me know.
> 
> ------------------
> 
> From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> 
> Some time ago Sami PietikÀinen reported a crash on -RT in
> ip_send_unicast_reply() which was later fixed by Nicholas Mc Guire
> (v3.12.8-rt11). Later (v3.18.8) the code was reworked and I dropped the
> patch. As it turns out it was mistake.
> I have reports that the same crash is possible with a similar backtrace.
> It seems that vanilla protects access to this_cpu_ptr() via
> local_bh_disable(). This does not work the on -RT since we can have
> NET_RX and NET_TX running in parallel on the same CPU.
> This is brings back the old locks.
> 
> |Unable to handle kernel NULL pointer dereference at virtual address 00000010
> |PC is at __ip_make_skb+0x198/0x3e8
> |[<c04e39d8>] (__ip_make_skb) from [<c04e3ca8>] (ip_push_pending_frames+0x20/0x40)
> |[<c04e3ca8>] (ip_push_pending_frames) from [<c04e3ff0>] (ip_send_unicast_reply+0x210/0x22c)
> |[<c04e3ff0>] (ip_send_unicast_reply) from [<c04fbb54>] (tcp_v4_send_reset+0x190/0x1c0)
> |[<c04fbb54>] (tcp_v4_send_reset) from [<c04fcc1c>] (tcp_v4_do_rcv+0x22c/0x288)
> |[<c04fcc1c>] (tcp_v4_do_rcv) from [<c0474364>] (release_sock+0xb4/0x150)
> |[<c0474364>] (release_sock) from [<c04ed904>] (tcp_close+0x240/0x454)
> |[<c04ed904>] (tcp_close) from [<c0511408>] (inet_release+0x74/0x7c)
> |[<c0511408>] (inet_release) from [<c0470728>] (sock_release+0x30/0xb0)
> |[<c0470728>] (sock_release) from [<c0470abc>] (sock_close+0x1c/0x24)
> |[<c0470abc>] (sock_close) from [<c0115ec4>] (__fput+0xe8/0x20c)
> |[<c0115ec4>] (__fput) from [<c0116050>] (____fput+0x18/0x1c)
> |[<c0116050>] (____fput) from [<c0058138>] (task_work_run+0xa4/0xb8)
> |[<c0058138>] (task_work_run) from [<c0011478>] (do_work_pending+0xd0/0xe4)
> |[<c0011478>] (do_work_pending) from [<c000e740>] (work_pending+0xc/0x20)
> |Code: e3530001 8a000001 e3a00040 ea000011 (e5973010)
> 
> Cc: stable-rt@vger.kernel.org
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
> ---
>  net/ipv4/tcp_ipv4.c | 7 +++++++
>  1 file changed, 7 insertions(+)
> 
> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> index 13b92d595138..6bfa68fb5f21 100644
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
> @@ -62,6 +62,7 @@
>  #include <linux/init.h>
>  #include <linux/times.h>
>  #include <linux/slab.h>
> +#include <linux/locallock.h>
>  
>  #include <net/net_namespace.h>
>  #include <net/icmp.h>
> @@ -563,6 +564,7 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
>  }
>  EXPORT_SYMBOL(tcp_v4_send_check);
>  
> +static DEFINE_LOCAL_IRQ_LOCK(tcp_sk_lock);
>  /*
>   *	This routine will send an RST to the other tcp.
>   *
> @@ -684,10 +686,13 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
>  		arg.bound_dev_if = sk->sk_bound_dev_if;
>  
>  	arg.tos = ip_hdr(skb)->tos;
> +
> +	local_lock(tcp_sk_lock);
>  	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
>  			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
>  			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
>  			      &arg, arg.iov[0].iov_len);
> +	local_unlock(tcp_sk_lock);
>  
>  	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
>  	TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
> @@ -769,10 +774,12 @@ static void tcp_v4_send_ack(struct net *net,
>  	if (oif)
>  		arg.bound_dev_if = oif;
>  	arg.tos = tos;
> +	local_lock(tcp_sk_lock);
>  	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
>  			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
>  			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
>  			      &arg, arg.iov[0].iov_len);
> +	local_unlock(tcp_sk_lock);
>  
>  	TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
>  }

[toc] | [prev] | [next] | [standalone]

#1489608 — [PATCH RT 07/10] fs/dcache: resched/chill only if we make no progress

4.1.33-rt38-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

Upstream commit 47be61845c77 ("fs/dcache.c: avoid soft-lockup in
dput()") changed the condition _when_ cpu_relax() / cond_resched() was
invoked. This change was adapted in -RT into mostly the same thing
except that if cond_resched() did nothing we had to do cpu_chill() to
force the task off CPU for a tiny little bit in case the task had RT
priority and did not want to leave the CPU.
This change resulted in a performance regression (in my testcase the
build time on /dev/shm increased from 19min to 24min). The reason is
that with this change cpu_chill() was invoked even dput() made progress
(dentry_kill() returned a different dentry) instead only if we were
trying this operation on the same dentry over and over again.

This patch brings back to the old behavior back to cond_resched() &
chill if we make no progress. A little improvement is to invoke
cpu_chill() only if we are a RT task (and avoid the sleep otherwise).
Otherwise the scheduler should remove us from the CPU if we make no
progress.

Cc: stable-rt@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 fs/dcache.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index d96330db7f80..9a6c0a5ec1a3 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -40,6 +40,8 @@
 #include <linux/ratelimit.h>
 #include <linux/list_lru.h>
 #include <linux/kasan.h>
+#include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 
 #include "internal.h"
 #include "mount.h"
@@ -748,6 +750,8 @@ static inline bool fast_dput(struct dentry *dentry)
  */
 void dput(struct dentry *dentry)
 {
+	struct dentry *parent;
+
 	if (unlikely(!dentry))
 		return;
 
@@ -784,13 +788,17 @@ repeat:
 	return;
 
 kill_it:
-	dentry = dentry_kill(dentry);
-	if (dentry) {
+	parent = dentry_kill(dentry);
+	if (parent) {
 		int r;
 
-		r = cond_resched();
-		if (!r)
-			cpu_chill();
+		if (parent == dentry) {
+			/* the task with the highest priority won't schedule */
+			r = cond_resched();
+			if (!r && (rt_task(current) || dl_task(current)))
+				cpu_chill();
+		} else
+			dentry = parent;
 		goto repeat;
 	}
 }
-- 
2.8.1

[toc] | [prev] | [next] | [standalone]

#1489609 — [PATCH RT 04/10] scsi/fcoe: Fix get_cpu()/put_cpu_light() imbalance in fcoe_recv_frame()

4.1.33-rt38-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Mike Galbraith <umgwanakikbuti@gmail.com>

During master->rt merge, I stumbled across the buglet below.

Fix get_cpu()/put_cpu_light() imbalance.

Cc: stable-rt@vger.kernel.org
Signed-off-by: Mike Gabraith <umgwanakikbuti@gmail.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 drivers/scsi/fcoe/fcoe.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index d6b6dde64fb9..455bf9c67b16 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -1815,7 +1815,7 @@ static void fcoe_recv_frame(struct sk_buff *skb)
 	 */
 	hp = (struct fcoe_hdr *) skb_network_header(skb);
 
-	stats = per_cpu_ptr(lport->stats, get_cpu());
+	stats = per_cpu_ptr(lport->stats, get_cpu_light());
 	if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) {
 		if (stats->ErrorFrames < 5)
 			printk(KERN_WARNING "fcoe: FCoE version "
-- 
2.8.1

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web