From e8129c642155616d9e2160a75f103e127c8c3708 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 25 Nov 2010 09:52:45 +0100 Subject: [S390] nmi: fix clock comparator revalidation On each machine check all registers are revalidated. The save area for the clock comparator however only contains the upper most seven bytes of the former contents, if valid. Therefore the machine check handler uses a store clock instruction to get the current time and writes that to the clock comparator register which in turn will generate an immediate timer interrupt. However within the lowcore the expected time of the next timer interrupt is stored. If the interrupt happens before that time the handler won't be called. In turn the clock comparator won't be reprogrammed and therefore the interrupt condition stays pending which causes an interrupt loop until the expected time is reached. On NOHZ machines this can result in unresponsive machines since the time of the next expected interrupted can be a couple of days in the future. To fix this just revalidate the clock comparator register with the expected value. In addition the special handling for udelay must be changed as well. Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/nmi.c | 10 ++++------ arch/s390/lib/delay.c | 14 +++++++++----- 2 files changed, 13 insertions(+), 11 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index ac15139..1995c17 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -95,7 +95,6 @@ EXPORT_SYMBOL_GPL(s390_handle_mcck); static int notrace s390_revalidate_registers(struct mci *mci) { int kill_task; - u64 tmpclock; u64 zero; void *fpt_save_area, *fpt_creg_save_area; @@ -214,11 +213,10 @@ static int notrace s390_revalidate_registers(struct mci *mci) : "0", "cc"); #endif /* Revalidate clock comparator register */ - asm volatile( - " stck 0(%1)\n" - " sckc 0(%1)" - : "=m" (tmpclock) : "a" (&(tmpclock)) : "cc", "memory"); - + if (S390_lowcore.clock_comparator == -1) + set_clock_comparator(S390_lowcore.mcck_clock); + else + set_clock_comparator(S390_lowcore.clock_comparator); /* Check if old PSW is valid */ if (!mci->wp) /* diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index 752b362..7c37ec3 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -29,17 +29,21 @@ static void __udelay_disabled(unsigned long long usecs) { unsigned long mask, cr0, cr0_saved; u64 clock_saved; + u64 end; + mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT; + end = get_clock() + (usecs << 12); clock_saved = local_tick_disable(); - set_clock_comparator(get_clock() + (usecs << 12)); __ctl_store(cr0_saved, 0, 0); cr0 = (cr0_saved & 0xffff00e0) | 0x00000800; __ctl_load(cr0 , 0, 0); - mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT; lockdep_off(); - trace_hardirqs_on(); - __load_psw_mask(mask); - local_irq_disable(); + do { + set_clock_comparator(end); + trace_hardirqs_on(); + __load_psw_mask(mask); + local_irq_disable(); + } while (get_clock() < end); lockdep_on(); __ctl_load(cr0_saved, 0, 0); local_tick_enable(clock_saved); -- cgit v1.1 From 398812159e328478ae49b4bd01f0d71efea96c39 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 1 Dec 2010 10:08:01 +0100 Subject: [S390] nohz/s390: fix arch_needs_cpu() return value on offline cpus This fixes the same problem as described in the patch "nohz: fix printk_needs_cpu() return value on offline cpus" for the arch_needs_cpu() primitive: arch_needs_cpu() may return 1 if called on offline cpus. When a cpu gets offlined it schedules the idle process which, before killing its own cpu, will call tick_nohz_stop_sched_tick(). That function in turn will call arch_needs_cpu() in order to check if the local tick can be disabled. On offline cpus this function should naturally return 0 since regardless if the tick gets disabled or not the cpu will be dead short after. That is besides the fact that __cpu_disable() should already have made sure that no interrupts on the offlined cpu will be delivered anyway. In this case it prevents tick_nohz_stop_sched_tick() to call select_nohz_load_balancer(). No idea if that really is a problem. However what made me debug this is that on 2.6.32 the function get_nohz_load_balancer() is used within __mod_timer() to select a cpu on which a timer gets enqueued. If arch_needs_cpu() returns 1 then the nohz_load_balancer cpu doesn't get updated when a cpu gets offlined. It may contain the cpu number of an offline cpu. In turn timers get enqueued on an offline cpu and not very surprisingly they never expire and cause system hangs. This has been observed 2.6.32 kernels. On current kernels __mod_timer() uses get_nohz_timer_target() which doesn't have that problem. However there might be other problems because of the too early exit tick_nohz_stop_sched_tick() in case a cpu goes offline. This specific bug was indrocuded with 3c5d92a0 "nohz: Introduce arch_needs_cpu". In this case a cpu hotplug notifier is used to fix the issue in order to keep the normal/fast path small. All we need to do is to clear the condition that makes arch_needs_cpu() return 1 since it is just a performance improvement which is supposed to keep the local tick running for a short period if a cpu goes idle. Nothing special needs to be done except for clearing the condition. Cc: stable@kernel.org Acked-by: Peter Zijlstra Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/vtime.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'arch/s390') diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 56c8687..7eff9b7 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -566,6 +567,23 @@ void init_cpu_vtimer(void) __ctl_set_bit(0,10); } +static int __cpuinit s390_nohz_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + struct s390_idle_data *idle; + long cpu = (long) hcpu; + + idle = &per_cpu(s390_idle, cpu); + switch (action) { + case CPU_DYING: + case CPU_DYING_FROZEN: + idle->nohz_delay = 0; + default: + break; + } + return NOTIFY_OK; +} + void __init vtime_init(void) { /* request the cpu timer external interrupt */ @@ -574,5 +592,6 @@ void __init vtime_init(void) /* Enable cpu timer interrupts on the boot cpu. */ init_cpu_vtimer(); + cpu_notifier(s390_nohz_notify, 0); } -- cgit v1.1