From ee9c578527a93c66becb526c4a122c5358a959c5 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 20 Apr 2008 13:59:33 +0100 Subject: dyntick: Remove last reminants of dyntick support Remove the last reminants of dyntick support from the generic kernel. Signed-off-by: Russell King --- kernel/hrtimer.c | 2 +- kernel/sysctl.c | 12 ------------ kernel/timer.c | 10 +--------- 3 files changed, 2 insertions(+), 22 deletions(-) (limited to 'kernel') diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 421be5fe5cc..543d9ca9b4f 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1078,7 +1078,7 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer) } EXPORT_SYMBOL_GPL(hrtimer_get_remaining); -#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_HZ) +#ifdef CONFIG_NO_HZ /** * hrtimer_get_next_event - get the time until next expiry event * diff --git a/kernel/sysctl.c b/kernel/sysctl.c index d7ffdc59816..76426d93007 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -131,8 +131,6 @@ extern int sysctl_userprocess_debug; extern int spin_retry; #endif -extern int sysctl_hz_timer; - #ifdef CONFIG_BSD_PROCESS_ACCT extern int acct_parm[]; #endif @@ -561,16 +559,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, -#endif -#ifdef CONFIG_NO_IDLE_HZ - { - .ctl_name = KERN_HZ_TIMER, - .procname = "hz_timer", - .data = &sysctl_hz_timer, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, #endif { .ctl_name = KERN_S390_USER_DEBUG_LOGGING, diff --git a/kernel/timer.c b/kernel/timer.c index ceacc662657..ef3fa6906e8 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -812,7 +812,7 @@ static inline void __run_timers(struct tvec_base *base) spin_unlock_irq(&base->lock); } -#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_HZ) +#ifdef CONFIG_NO_HZ /* * Find out when the next timer event is due to happen. This * is used on S/390 to stop all activity when a cpus is idle. @@ -947,14 +947,6 @@ unsigned long get_next_timer_interrupt(unsigned long now) return cmp_next_hrtimer_event(now, expires); } - -#ifdef CONFIG_NO_IDLE_HZ -unsigned long next_timer_interrupt(void) -{ - return get_next_timer_interrupt(jiffies); -} -#endif - #endif #ifndef CONFIG_VIRT_CPU_ACCOUNTING -- cgit v1.2.3 From 13d5ef97f0675d789f559cfebc1df9d5e2b1879c Mon Sep 17 00:00:00 2001 From: Peng Haitao Date: Fri, 16 May 2008 10:15:04 +0800 Subject: [PATCH] kernel/audit.c: nlh->nlmsg_type is gotten more than once The first argument "nlh->nlmsg_type" of audit_receive_filter() should be modified to "msg_type" in audit_receive_msg(). Signed-off-by: Peng Haitao Signed-off-by: Al Viro --- kernel/audit.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/audit.c b/kernel/audit.c index e8692a5748c..56f30287e24 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -779,7 +779,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } /* fallthrough */ case AUDIT_LIST: - err = audit_receive_filter(nlh->nlmsg_type, NETLINK_CB(skb).pid, + err = audit_receive_filter(msg_type, NETLINK_CB(skb).pid, uid, seq, data, nlmsg_len(nlh), loginuid, sessionid, sid); break; @@ -798,7 +798,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } /* fallthrough */ case AUDIT_LIST_RULES: - err = audit_receive_filter(nlh->nlmsg_type, NETLINK_CB(skb).pid, + err = audit_receive_filter(msg_type, NETLINK_CB(skb).pid, uid, seq, data, nlmsg_len(nlh), loginuid, sessionid, sid); break; -- cgit v1.2.3 From 9f0aecdd1cd6aacee9aa8f08031f4f2e09e454dc Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 19 May 2008 15:09:21 -0700 Subject: [PATCH] audit: fix kernel-doc parameter notation Fix auditfilter kernel-doc misssing parameter description: Warning(lin2626-rc3//kernel/auditfilter.c:1551): No description found for parameter 'sessionid' Signed-off-by: Randy Dunlap Signed-off-by: Al Viro --- kernel/auditfilter.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 0e0bd27e651..75cdf262851 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1544,6 +1544,7 @@ static void audit_log_rule_change(uid_t loginuid, u32 sessionid, u32 sid, * @data: payload data * @datasz: size of payload data * @loginuid: loginuid of sender + * @sessionid: sessionid for netlink audit message * @sid: SE Linux Security ID of sender */ int audit_receive_filter(int type, int pid, int uid, int seq, void *data, -- cgit v1.2.3 From d8de72473effd674a3c1fe9621821f406f5587c9 Mon Sep 17 00:00:00 2001 From: Peng Haitao Date: Tue, 20 May 2008 09:13:02 +0800 Subject: [PATCH] remove useless argument type in audit_filter_user() The second argument "type" is not used in audit_filter_user(), so I think that type can be removed. If I'm wrong, please tell me. Signed-off-by: Peng Haitao Signed-off-by: Al Viro --- kernel/audit.c | 2 +- kernel/auditfilter.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/audit.c b/kernel/audit.c index 56f30287e24..e092f1c0ce3 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -738,7 +738,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (!audit_enabled && msg_type != AUDIT_USER_AVC) return 0; - err = audit_filter_user(&NETLINK_CB(skb), msg_type); + err = audit_filter_user(&NETLINK_CB(skb)); if (err == 1) { err = 0; if (msg_type == AUDIT_USER_TTY) { diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 75cdf262851..98c50cc671b 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1721,7 +1721,7 @@ static int audit_filter_user_rules(struct netlink_skb_parms *cb, return 1; } -int audit_filter_user(struct netlink_skb_parms *cb, int type) +int audit_filter_user(struct netlink_skb_parms *cb) { enum audit_state state = AUDIT_DISABLED; struct audit_entry *e; -- cgit v1.2.3 From 79c537998d143b127c8c662a403c3356cb885f1c Mon Sep 17 00:00:00 2001 From: Dmitry Adamushko Date: Sun, 29 Jun 2008 00:16:56 +0200 Subject: sched: fix cpu hotplug the CPU hotplug problems (crashes under high-volume unplug+replug tests) seem to be related to migrate_dead_tasks(). Firstly I added traces to see all tasks being migrated with migrate_live_tasks() and migrate_dead_tasks(). On my setup the problem pops up (the one with "se == NULL" in the loop of pick_next_task_fair()) shortly after the traces indicate that some has been migrated with migrate_dead_tasks()). btw., I can reproduce it much faster now with just a plain cpu down/up loop. [disclaimer] Well, unless I'm really missing something important in this late hour [/desclaimer] pick_next_task() is not something appropriate for migrate_dead_tasks() :-) the following change seems to eliminate the problem on my setup (although, I kept it running only for a few minutes to get a few messages indicating migrate_dead_tasks() does move tasks and the system is still ok) Signed-off-by: Ingo Molnar --- kernel/sched.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 3aaa5c8cb42..a66e85639de 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5887,6 +5887,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu) next = pick_next_task(rq, rq->curr); if (!next) break; + next->sched_class->put_prev_task(rq, next); migrate_dead(dead_cpu, next); } -- cgit v1.2.3 From 619b0488038224391e64fa03854651ca0f5efe56 Mon Sep 17 00:00:00 2001 From: Raistlin Date: Thu, 26 Jun 2008 18:54:09 +0200 Subject: sched: fix divide error when trying to configure rt_period to zero Here it is another little Oops we found while configuring invalid values via cgroups: echo 0 > /dev/cgroups/0/cpu.rt_period_us or echo 4294967296 > /dev/cgroups/0/cpu.rt_period_us [ 205.509825] divide error: 0000 [#1] [ 205.510151] Modules linked in: [ 205.510151] [ 205.510151] Pid: 2339, comm: bash Not tainted (2.6.26-rc8 #33) [ 205.510151] EIP: 0060:[] EFLAGS: 00000293 CPU: 0 [ 205.510151] EIP is at div64_u64+0x5f/0x70 [ 205.510151] EAX: 0000389f EBX: 00000000 ECX: 00000000 EDX: 00000000 [ 205.510151] ESI: d9800000 EDI: 00000000 EBP: c6cede60 ESP: c6cede50 [ 205.510151] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 0068 [ 205.510151] Process bash (pid: 2339, ti=c6cec000 task=c79be370 task.ti=c6cec000) [ 205.510151] Stack: d9800000 0000389f c05971a0 d9800000 c6cedeb4 c0214dbd 00000000 00000000 [ 205.510151] c6cede88 c0242bd8 c05377c0 c7a41b40 00000000 00000000 00000000 c05971a0 [ 205.510151] c780ed20 c7508494 c7a41b40 00000000 00000002 c6cedebc c05971a0 ffffffea [ 205.510151] Call Trace: [ 205.510151] [] ? __rt_schedulable+0x1cd/0x240 [ 205.510151] [] ? cgroup_file_open+0x18/0xe0 [ 205.510151] [] ? tg_set_bandwidth+0xa4/0xf0 [ 205.510151] [] ? sched_group_set_rt_period+0x36/0x50 [ 205.510151] [] ? cpu_rt_period_write_uint+0xe/0x10 [ 205.510151] [] ? cgroup_file_write+0x125/0x160 [ 205.510151] [] ? hrtimer_interrupt+0x155/0x190 [ 205.510151] [] ? security_file_permission+0xf/0x20 [ 205.510151] [] ? rw_verify_area+0x48/0xc0 [ 205.510151] [] ? dupfd+0x104/0x130 [ 205.510151] [] ? vfs_write+0x9c/0x160 [ 205.510151] [] ? cgroup_file_write+0x0/0x160 [ 205.510151] [] ? sys_write+0x3d/0x70 [ 205.510151] [] ? sysenter_past_esp+0x6a/0x91 [ 205.510151] ======================= [ 205.510151] Code: 0f 45 de 31 f6 0f ad d0 d3 ea f6 c1 20 0f 45 c2 0f 45 d6 89 45 f0 89 55 f4 8b 55 f4 31 c9 8b 45 f0 39 d3 89 c6 77 08 89 d0 31 d2 f3 89 c1 83 c4 08 89 f0 f7 f3 89 ca 5b 5e 5d c3 55 89 e5 56 [ 205.510151] EIP: [] div64_u64+0x5f/0x70 SS:ESP 0068:c6cede50 The attached patch solves the issue for me. I'm checking as soon as possible for the period not being zero since, if it is, going ahead is useless. This way we also save a mutex_lock() and a read_lock() wrt doing it inside tg_set_bandwidth() or __rt_schedulable(). Signed-off-by: Dario Faggioli Signed-off-by: Michael Trimarchi Signed-off-by: Ingo Molnar --- kernel/sched.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index a66e85639de..94ead43eda6 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -8502,6 +8502,9 @@ int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) rt_period = (u64)rt_period_us * NSEC_PER_USEC; rt_runtime = tg->rt_bandwidth.rt_runtime; + if (rt_period == 0) + return -EINVAL; + return tg_set_bandwidth(tg, rt_period, rt_runtime); } -- cgit v1.2.3 From 8558f8f81680a43d383abd1b5f23d3501fedfa65 Mon Sep 17 00:00:00 2001 From: Gautham R Shenoy Date: Fri, 27 Jun 2008 10:17:38 +0530 Subject: rcu: fix hotplug vs rcu race Dhaval Giani reported this warning during cpu hotplug stress-tests: | On running kernel compiles in parallel with cpu hotplug: | | WARNING: at arch/x86/kernel/smp.c:118 | native_smp_send_reschedule+0x21/0x36() | Modules linked in: | Pid: 27483, comm: cc1 Not tainted 2.6.26-rc7 #1 | [...] | [] native_smp_send_reschedule+0x21/0x36 | [] force_quiescent_state+0x47/0x57 | [] call_rcu+0x51/0x6d | [] __fput+0x130/0x158 | [] fput+0x17/0x19 | [] filp_close+0x4d/0x57 | [] sys_close+0x5c/0x97 IMHO the warning is a spurious one. cpu_online_map is updated by the _cpu_down() using stop_machine_run(). Since force_quiescent_state is invoked from irqs disabled section, stop_machine_run() won't be executing while a cpu is executing force_quiescent_state(). Hence the cpu_online_map is stable while we're in the irq disabled section. However, a cpu might have been offlined _just_ before we disabled irqs while entering force_quiescent_state(). And rcu subsystem might not yet have handled the CPU_DEAD notification, leading to the offlined cpu's bit being set in the rcp->cpumask. Hence cpumask = (rcp->cpumask & cpu_online_map) to prevent sending smp_reschedule() to an offlined CPU. Here's the timeline: CPU_A CPU_B -------------------------------------------------------------- cpu_down(): . . . . . stop_machine(): /* disables preemption, . * and irqs */ . . . . . take_cpu_down(); . . . . . . . cpu_disable(); /*this removes cpu . *from cpu_online_map . */ . . . . . restart_machine(); /* enables irqs */ . ------WINDOW DURING WHICH rcp->cpumask is stale --------------- . call_rcu(); . /* disables irqs here */ . .force_quiescent_state(); .CPU_DEAD: .for_each_cpu(rcp->cpumask) . . smp_send_reschedule(); . . . . WARN_ON() for offlined CPU! . . . rcu_cpu_notify: . -------- WINDOW ENDS ------------------------------------------ rcu_offline_cpu() /* Which calls cpu_quiet() * which removes * cpu from rcp->cpumask. */ If a new batch was started just before calling stop_machine_run(), the "tobe-offlined" cpu is still present in rcp-cpumask. During a cpu-offline, from take_cpu_down(), we queue an rt-prio idle task as the next task to be picked by the scheduler. We also call cpu_disable() which will disable any further interrupts and remove the cpu's bit from the cpu_online_map. Once the stop_machine_run() successfully calls take_cpu_down(), it calls schedule(). That's the last time a schedule is called on the offlined cpu, and hence the last time when rdp->passed_quiesc will be set to 1 through rcu_qsctr_inc(). But the cpu_quiet() will be on this cpu will be called only when the next RCU_SOFTIRQ occurs on this CPU. So at this time, the offlined CPU is still set in rcp->cpumask. Now coming back to the idle_task which truely offlines the CPU, it does check for a pending RCU and raises the softirq, since it will find rdp->passed_quiesc to be 0 in this case. However, since the cpu is offline I am not sure if the softirq will trigger on the CPU. Even if it doesn't the rcu_offline_cpu() will find that rcp->completed is not the same as rcp->cur, which means that our cpu could be holding up the grace period progression. Hence we call cpu_quiet() and move ahead. But because of the window explained in the timeline, we could still have a call_rcu() before the RCU subsystem executes it's CPU_DEAD notification, and we send smp_send_reschedule() to offlined cpu while trying to force the quiescent states. The appended patch adds comments and prevents checking for offlined cpu everytime. cpu_online_map is updated by the _cpu_down() using stop_machine_run(). Since force_quiescent_state is invoked from irqs disabled section, stop_machine_run() won't be executing while a cpu is executing force_quiescent_state(). Hence the cpu_online_map is stable while we're in the irq disabled section. Reported-by: Dhaval Giani Signed-off-by: Gautham R Shenoy Acked-by: Dhaval Giani Cc: Dipankar Sarma Cc: laijs@cn.fujitsu.com Cc: Peter Zijlstra Cc: Rusty Russel Cc: "Paul E. McKenney" Signed-off-by: Ingo Molnar --- kernel/rcuclassic.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c index f4ffbd0f306..a38895a5b8e 100644 --- a/kernel/rcuclassic.c +++ b/kernel/rcuclassic.c @@ -89,8 +89,22 @@ static void force_quiescent_state(struct rcu_data *rdp, /* * Don't send IPI to itself. With irqs disabled, * rdp->cpu is the current cpu. + * + * cpu_online_map is updated by the _cpu_down() + * using stop_machine_run(). Since we're in irqs disabled + * section, stop_machine_run() is not exectuting, hence + * the cpu_online_map is stable. + * + * However, a cpu might have been offlined _just_ before + * we disabled irqs while entering here. + * And rcu subsystem might not yet have handled the CPU_DEAD + * notification, leading to the offlined cpu's bit + * being set in the rcp->cpumask. + * + * Hence cpumask = (rcp->cpumask & cpu_online_map) to prevent + * sending smp_reschedule() to an offlined CPU. */ - cpumask = rcp->cpumask; + cpus_and(cpumask, rcp->cpumask, cpu_online_map); cpu_clear(rdp->cpu, cpumask); for_each_cpu_mask(cpu, cpumask) smp_send_reschedule(cpu); -- cgit v1.2.3