From 0c3b9168017cbad2c4af3dd65ec93fe646eeaa62 Mon Sep 17 00:00:00 2001 From: Balbir Singh Date: Thu, 3 Mar 2011 17:04:35 +0530 Subject: sched: Fix sched rt group scheduling when hierachy is enabled The current sched rt code is broken when it comes to hierarchical scheduling, this patch fixes two problems 1. It adds redundant enqueuing (harmless) when it finds a queue has tasks enqueued, but it has no run time and it is not throttled. 2. The most important change is in sched_rt_rq_enqueue/dequeue. The code just picks the rt_rq belonging to the current cpu on which the period timer runs, the patch fixes it, so that the correct rt_se is enqueued/dequeued. Tested with a simple hierarchy /c/d, c and d assigned similar runtimes of 50,000 and a while 1 loop runs within "d". Both c and d get throttled, without the patch, the task just stops running and never runs (depends on where the sched_rt b/w timer runs). With the patch, the task is throttled and runs as expected. [ bharata, suggestions on how to pick the rt_se belong to the rt_rq and correct cpu ] Signed-off-by: Balbir Singh Acked-by: Bharata B Rao Signed-off-by: Peter Zijlstra Cc: stable@kernel.org LKML-Reference: <20110303113435.GA2868@balbir.in.ibm.com> Signed-off-by: Ingo Molnar --- kernel/sched_rt.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index ad6267714c84..01f75a5f17af 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -210,11 +210,12 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se); static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) { - int this_cpu = smp_processor_id(); struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr; struct sched_rt_entity *rt_se; - rt_se = rt_rq->tg->rt_se[this_cpu]; + int cpu = cpu_of(rq_of_rt_rq(rt_rq)); + + rt_se = rt_rq->tg->rt_se[cpu]; if (rt_rq->rt_nr_running) { if (rt_se && !on_rt_rq(rt_se)) @@ -226,10 +227,10 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) { - int this_cpu = smp_processor_id(); struct sched_rt_entity *rt_se; + int cpu = cpu_of(rq_of_rt_rq(rt_rq)); - rt_se = rt_rq->tg->rt_se[this_cpu]; + rt_se = rt_rq->tg->rt_se[cpu]; if (rt_se && on_rt_rq(rt_se)) dequeue_rt_entity(rt_se); @@ -565,8 +566,11 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) if (rt_rq->rt_time || rt_rq->rt_nr_running) idle = 0; raw_spin_unlock(&rt_rq->rt_runtime_lock); - } else if (rt_rq->rt_nr_running) + } else if (rt_rq->rt_nr_running) { idle = 0; + if (!rt_rq_throttled(rt_rq)) + enqueue = 1; + } if (enqueue) sched_rt_rq_enqueue(rt_rq); -- cgit v1.2.3 From e3e89cc535223433a619d0969db3fa05cdd946b8 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 4 Mar 2011 09:23:30 -0800 Subject: Mark ptrace_{traceme,attach,detach} static They are only used inside kernel/ptrace.c, and have been for a long time. We don't want to go back to the bad-old-days when architectures did things on their own, so make them static and private. Signed-off-by: Linus Torvalds --- kernel/ptrace.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 1708b1e2972d..e2302e40b360 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -163,7 +163,7 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode) return !err; } -int ptrace_attach(struct task_struct *task) +static int ptrace_attach(struct task_struct *task) { int retval; @@ -219,7 +219,7 @@ out: * Performs checks and sets PT_PTRACED. * Should be used by all ptrace implementations for PTRACE_TRACEME. */ -int ptrace_traceme(void) +static int ptrace_traceme(void) { int ret = -EPERM; @@ -293,7 +293,7 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) return false; } -int ptrace_detach(struct task_struct *child, unsigned int data) +static int ptrace_detach(struct task_struct *child, unsigned int data) { bool dead = false; -- cgit v1.2.3 From b75f38d659e6fc747eda64cb72f3920e29dd44a4 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 4 Mar 2011 17:36:21 -0800 Subject: cpuset: add a missing unlock in cpuset_write_resmask() Don't forget to release cgroup_mutex if alloc_trial_cpuset() fails. [akpm@linux-foundation.org: avoid multiple return points] Signed-off-by: Li Zefan Cc: Paul Menage Acked-by: David Rientjes Cc: Miao Xie Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 4349935c2ad8..e92e98189032 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1575,8 +1575,10 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, return -ENODEV; trialcs = alloc_trial_cpuset(cs); - if (!trialcs) - return -ENOMEM; + if (!trialcs) { + retval = -ENOMEM; + goto out; + } switch (cft->private) { case FILE_CPULIST: @@ -1591,6 +1593,7 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, } free_trial_cpuset(trialcs); +out: cgroup_unlock(); return retval; } -- cgit v1.2.3 From dfef6dcd35cb4a251f6322ca9b2c06f0bb1aa1f4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 8 Mar 2011 01:25:28 -0500 Subject: unfuck proc_sysctl ->d_compare() a) struct inode is not going to be freed under ->d_compare(); however, the thing PROC_I(inode)->sysctl points to just might. Fortunately, it's enough to make freeing that sucker delayed, provided that we don't step on its ->unregistering, clear the pointer to it in PROC_I(inode) before dropping the reference and check if it's NULL in ->d_compare(). b) I'm not sure that we *can* walk into NULL inode here (we recheck dentry->seq between verifying that it's still hashed / fetching dentry->d_inode and passing it to ->d_compare() and there's no negative hashed dentries in /proc/sys/*), but if we can walk into that, we really should not have ->d_compare() return 0 on it! Said that, I really suspect that this check can be simply killed. Nick? Signed-off-by: Al Viro --- kernel/sysctl.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 0f1bd83db985..4eed0af5d144 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -194,9 +194,9 @@ static int sysrq_sysctl_handler(ctl_table *table, int write, static struct ctl_table root_table[]; static struct ctl_table_root sysctl_table_root; static struct ctl_table_header root_table_header = { - .count = 1, + {{.count = 1, .ctl_table = root_table, - .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list), + .ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),}}, .root = &sysctl_table_root, .set = &sysctl_table_root.default_set, }; @@ -1567,11 +1567,16 @@ void sysctl_head_get(struct ctl_table_header *head) spin_unlock(&sysctl_lock); } +static void free_head(struct rcu_head *rcu) +{ + kfree(container_of(rcu, struct ctl_table_header, rcu)); +} + void sysctl_head_put(struct ctl_table_header *head) { spin_lock(&sysctl_lock); if (!--head->count) - kfree(head); + call_rcu(&head->rcu, free_head); spin_unlock(&sysctl_lock); } @@ -1948,10 +1953,10 @@ void unregister_sysctl_table(struct ctl_table_header * header) start_unregistering(header); if (!--header->parent->count) { WARN_ON(1); - kfree(header->parent); + call_rcu(&header->parent->rcu, free_head); } if (!--header->count) - kfree(header); + call_rcu(&header->rcu, free_head); spin_unlock(&sysctl_lock); } -- cgit v1.2.3