From 7f51412a415d87ea8598d14722fb31e4f5701257 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Fri, 19 Sep 2014 10:22:40 +0100 Subject: sched/deadline: Fix bandwidth check/update when migrating tasks between exclusive cpusets Exclusive cpusets are the only way users can restrict SCHED_DEADLINE tasks affinity (performing what is commonly called clustered scheduling). Unfortunately, such thing is currently broken for two reasons: - No check is performed when the user tries to attach a task to an exlusive cpuset (recall that exclusive cpusets have an associated maximum allowed bandwidth). - Bandwidths of source and destination cpusets are not correctly updated after a task is migrated between them. This patch fixes both things at once, as they are opposite faces of the same coin. The check is performed in cpuset_can_attach(), as there aren't any points of failure after that function. The updated is split in two halves. We first reserve bandwidth in the destination cpuset, after we pass the check in cpuset_can_attach(). And we then release bandwidth from the source cpuset when the task's affinity is actually changed. Even if there can be time windows when sched_setattr() may erroneously fail in the source cpuset, we are fine with it, as we can't perfom an atomic update of both cpusets at once. Reported-by: Daniel Wagner Reported-by: Vincent Legout Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra (Intel) Cc: Dario Faggioli Cc: Michael Trimarchi Cc: Fabio Checconi Cc: michael@amarulasolutions.com Cc: luca.abeni@unitn.it Cc: Li Zefan Cc: Linus Torvalds Cc: cgroups@vger.kernel.org Link: http://lkml.kernel.org/r/1411118561-26323-3-git-send-email-juri.lelli@arm.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5e344bbe63ec..1d1fa081d44f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2052,6 +2052,8 @@ static inline void tsk_restore_flags(struct task_struct *task, task->flags |= orig_flags & flags; } +extern int task_can_attach(struct task_struct *p, + const struct cpumask *cs_cpus_allowed); #ifdef CONFIG_SMP extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); -- cgit v1.2.3 From f82f80426f7afcf55953924e71555984a4bd6ce6 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Tue, 7 Oct 2014 09:52:11 +0100 Subject: sched/deadline: Ensure that updates to exclusive cpusets don't break AC How we deal with updates to exclusive cpusets is currently broken. As an example, suppose we have an exclusive cpuset composed of two cpus: A[cpu0,cpu1]. We can assign SCHED_DEADLINE task to it up to the allowed bandwidth. If we want now to modify cpusetA's cpumask, we have to check that removing a cpu's amount of bandwidth doesn't break AC guarantees. This thing isn't checked in the current code. This patch fixes the problem above, denying an update if the new cpumask won't have enough bandwidth for SCHED_DEADLINE tasks that are currently active. Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Li Zefan Cc: cgroups@vger.kernel.org Link: http://lkml.kernel.org/r/5433E6AF.5080105@arm.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 ++ kernel/cpuset.c | 10 ++++++++++ kernel/sched/core.c | 19 +++++++++++++++++++ 3 files changed, 31 insertions(+) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 1d1fa081d44f..320a9779f1b4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2052,6 +2052,8 @@ static inline void tsk_restore_flags(struct task_struct *task, task->flags |= orig_flags & flags; } +extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, + const struct cpumask *trial); extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed); #ifdef CONFIG_SMP diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 7af8577fc8f8..723cfc9d0ad7 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -506,6 +506,16 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) goto out; } + /* + * We can't shrink if we won't have enough room for SCHED_DEADLINE + * tasks. + */ + ret = -EBUSY; + if (is_cpu_exclusive(cur) && + !cpuset_cpumask_can_shrink(cur->cpus_allowed, + trial->cpus_allowed)) + goto out; + ret = 0; out: rcu_read_unlock(); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9993feeb8b10..0456a55fc27f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4650,6 +4650,25 @@ void init_idle(struct task_struct *idle, int cpu) #endif } +int cpuset_cpumask_can_shrink(const struct cpumask *cur, + const struct cpumask *trial) +{ + int ret = 1, trial_cpus; + struct dl_bw *cur_dl_b; + unsigned long flags; + + cur_dl_b = dl_bw_of(cpumask_any(cur)); + trial_cpus = cpumask_weight(trial); + + raw_spin_lock_irqsave(&cur_dl_b->lock, flags); + if (cur_dl_b->bw != -1 && + cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw) + ret = 0; + raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags); + + return ret; +} + int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed) { -- cgit v1.2.3 From 8eb23b9f35aae413140d3fda766a98092c21e9b0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Sep 2014 10:18:55 +0200 Subject: sched: Debug nested sleeps Validate we call might_sleep() with TASK_RUNNING, which catches places where we nest blocking primitives, eg. mutex usage in a wait loop. Since all blocking is arranged through task_struct::state, nesting this will cause the inner primitive to set TASK_RUNNING and the outer will thus not block. Another observed problem is calling a blocking function from schedule()->sched_submit_work()->blk_schedule_flush_plug() which will then destroy the task state for the actual __schedule() call that comes after it. Signed-off-by: Peter Zijlstra (Intel) Cc: tglx@linutronix.de Cc: ilya.dryomov@inktank.com Cc: umgwanakikbuti@gmail.com Cc: oleg@redhat.com Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20140924082242.591637616@infradead.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 46 ++++++++++++++++++++++++++++++++++++++++++++-- kernel/sched/core.c | 13 +++++++++++++ 2 files changed, 57 insertions(+), 2 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 320a9779f1b4..4648e07f7d6f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -243,6 +243,43 @@ extern char ___assert_task_state[1 - 2*!!( ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ (task->flags & PF_FROZEN) == 0) +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP + +#define __set_task_state(tsk, state_value) \ + do { \ + (tsk)->task_state_change = _THIS_IP_; \ + (tsk)->state = (state_value); \ + } while (0) +#define set_task_state(tsk, state_value) \ + do { \ + (tsk)->task_state_change = _THIS_IP_; \ + set_mb((tsk)->state, (state_value)); \ + } while (0) + +/* + * set_current_state() includes a barrier so that the write of current->state + * is correctly serialised wrt the caller's subsequent test of whether to + * actually sleep: + * + * set_current_state(TASK_UNINTERRUPTIBLE); + * if (do_i_need_to_sleep()) + * schedule(); + * + * If the caller does not need such serialisation then use __set_current_state() + */ +#define __set_current_state(state_value) \ + do { \ + current->task_state_change = _THIS_IP_; \ + current->state = (state_value); \ + } while (0) +#define set_current_state(state_value) \ + do { \ + current->task_state_change = _THIS_IP_; \ + set_mb(current->state, (state_value)); \ + } while (0) + +#else + #define __set_task_state(tsk, state_value) \ do { (tsk)->state = (state_value); } while (0) #define set_task_state(tsk, state_value) \ @@ -259,11 +296,13 @@ extern char ___assert_task_state[1 - 2*!!( * * If the caller does not need such serialisation then use __set_current_state() */ -#define __set_current_state(state_value) \ +#define __set_current_state(state_value) \ do { current->state = (state_value); } while (0) -#define set_current_state(state_value) \ +#define set_current_state(state_value) \ set_mb(current->state, (state_value)) +#endif + /* Task command name length */ #define TASK_COMM_LEN 16 @@ -1661,6 +1700,9 @@ struct task_struct { unsigned int sequential_io; unsigned int sequential_io_avg; #endif +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; +#endif }; /* Future-safe accessor for struct task_struct's cpus_allowed. */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0456a55fc27f..5b4b96b27cd7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7298,6 +7298,19 @@ void __might_sleep(const char *file, int line, int preempt_offset) { static unsigned long prev_jiffy; /* ratelimiting */ + /* + * Blocking primitives will set (and therefore destroy) current->state, + * since we will exit with TASK_RUNNING make sure we enter with it, + * otherwise we will destroy state. + */ + if (WARN(current->state != TASK_RUNNING, + "do not call blocking ops when !TASK_RUNNING; " + "state=%lx set at [<%p>] %pS\n", + current->state, + (void *)current->task_state_change, + (void *)current->task_state_change)) + __set_current_state(TASK_RUNNING); + rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && !is_idle_task(current)) || -- cgit v1.2.3 From 3427445afd26bd2395f29241319283a93f362cd0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Sep 2014 10:18:56 +0200 Subject: sched: Exclude cond_resched() from nested sleep test cond_resched() is a preemption point, not strictly a blocking primitive, so exclude it from the ->state test. In particular, preemption preserves task_struct::state. Signed-off-by: Peter Zijlstra (Intel) Cc: tglx@linutronix.de Cc: ilya.dryomov@inktank.com Cc: umgwanakikbuti@gmail.com Cc: oleg@redhat.com Cc: Alex Elder Cc: Andrew Morton Cc: Axel Lin Cc: Daniel Borkmann Cc: Dave Jones Cc: Jason Baron Cc: Linus Torvalds Cc: Rusty Russell Cc: Steven Rostedt Link: http://lkml.kernel.org/r/20140924082242.656559952@infradead.org Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 3 +++ include/linux/sched.h | 6 +++--- kernel/sched/core.c | 12 +++++++++--- 3 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5068a0d9fecd..446d76a87ba1 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -162,6 +162,7 @@ extern int _cond_resched(void); #endif #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + void ___might_sleep(const char *file, int line, int preempt_offset); void __might_sleep(const char *file, int line, int preempt_offset); /** * might_sleep - annotation for functions that can sleep @@ -177,6 +178,8 @@ extern int _cond_resched(void); do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) # define sched_annotate_sleep() __set_current_state(TASK_RUNNING) #else + static inline void ___might_sleep(const char *file, int line, + int preempt_offset) { } static inline void __might_sleep(const char *file, int line, int preempt_offset) { } # define might_sleep() do { might_resched(); } while (0) diff --git a/include/linux/sched.h b/include/linux/sched.h index 4648e07f7d6f..4400ddc2fe73 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2806,7 +2806,7 @@ static inline int signal_pending_state(long state, struct task_struct *p) extern int _cond_resched(void); #define cond_resched() ({ \ - __might_sleep(__FILE__, __LINE__, 0); \ + ___might_sleep(__FILE__, __LINE__, 0); \ _cond_resched(); \ }) @@ -2819,14 +2819,14 @@ extern int __cond_resched_lock(spinlock_t *lock); #endif #define cond_resched_lock(lock) ({ \ - __might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ + ___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\ __cond_resched_lock(lock); \ }) extern int __cond_resched_softirq(void); #define cond_resched_softirq() ({ \ - __might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \ + ___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \ __cond_resched_softirq(); \ }) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5b4b96b27cd7..b9f78f12ac22 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7296,8 +7296,6 @@ static inline int preempt_count_equals(int preempt_offset) void __might_sleep(const char *file, int line, int preempt_offset) { - static unsigned long prev_jiffy; /* ratelimiting */ - /* * Blocking primitives will set (and therefore destroy) current->state, * since we will exit with TASK_RUNNING make sure we enter with it, @@ -7311,6 +7309,14 @@ void __might_sleep(const char *file, int line, int preempt_offset) (void *)current->task_state_change)) __set_current_state(TASK_RUNNING); + ___might_sleep(file, line, preempt_offset); +} +EXPORT_SYMBOL(__might_sleep); + +void ___might_sleep(const char *file, int line, int preempt_offset) +{ + static unsigned long prev_jiffy; /* ratelimiting */ + rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && !is_idle_task(current)) || @@ -7340,7 +7346,7 @@ void __might_sleep(const char *file, int line, int preempt_offset) #endif dump_stack(); } -EXPORT_SYMBOL(__might_sleep); +EXPORT_SYMBOL(___might_sleep); #endif #ifdef CONFIG_MAGIC_SYSRQ -- cgit v1.2.3 From 44dba3d5d6a10685fb15bd1954e62016334825e0 Mon Sep 17 00:00:00 2001 From: Iulia Manda Date: Fri, 31 Oct 2014 02:13:31 +0200 Subject: sched: Refactor task_struct to use numa_faults instead of numa_* pointers This patch simplifies task_struct by removing the four numa_* pointers in the same array and replacing them with the array pointer. By doing this, on x86_64, the size of task_struct is reduced by 3 ulong pointers (24 bytes on x86_64). A new parameter is added to the task_faults_idx function so that it can return an index to the correct offset, corresponding with the old precalculated pointers. All of the code in sched/ that depended on task_faults_idx and numa_* was changed in order to match the new logic. Signed-off-by: Iulia Manda Signed-off-by: Peter Zijlstra (Intel) Cc: mgorman@suse.de Cc: dave@stgolabs.net Cc: riel@redhat.com Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20141031001331.GA30662@winterfell Signed-off-by: Ingo Molnar --- include/linux/sched.h | 31 ++++++-------- kernel/sched/core.c | 3 +- kernel/sched/debug.c | 4 +- kernel/sched/fair.c | 110 ++++++++++++++++++++++++++------------------------ kernel/sched/sched.h | 7 ++++ 5 files changed, 80 insertions(+), 75 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4400ddc2fe73..bd7c14ba86c4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1597,27 +1597,22 @@ struct task_struct { struct numa_group *numa_group; /* - * Exponential decaying average of faults on a per-node basis. - * Scheduling placement decisions are made based on the these counts. - * The values remain static for the duration of a PTE scan + * numa_faults is an array split into four regions: + * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer + * in this precise order. + * + * faults_memory: Exponential decaying average of faults on a per-node + * basis. Scheduling placement decisions are made based on these + * counts. The values remain static for the duration of a PTE scan. + * faults_cpu: Track the nodes the process was running on when a NUMA + * hinting fault was incurred. + * faults_memory_buffer and faults_cpu_buffer: Record faults per node + * during the current scan window. When the scan completes, the counts + * in faults_memory and faults_cpu decay and these values are copied. */ - unsigned long *numa_faults_memory; + unsigned long *numa_faults; unsigned long total_numa_faults; - /* - * numa_faults_buffer records faults per node during the current - * scan window. When the scan completes, the counts in - * numa_faults_memory decay and these values are copied. - */ - unsigned long *numa_faults_buffer_memory; - - /* - * Track the nodes the process was running on when a NUMA hinting - * fault was incurred. - */ - unsigned long *numa_faults_cpu; - unsigned long *numa_faults_buffer_cpu; - /* * numa_faults_locality tracks if faults recorded during the last * scan window were remote/local. The task scan period is adapted diff --git a/kernel/sched/core.c b/kernel/sched/core.c index df0569ebec0f..72d9d926a034 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1857,8 +1857,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0; p->numa_scan_period = sysctl_numa_balancing_scan_delay; p->numa_work.next = &p->numa_work; - p->numa_faults_memory = NULL; - p->numa_faults_buffer_memory = NULL; + p->numa_faults = NULL; p->last_task_numa_placement = 0; p->last_sum_exec_runtime = 0; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index eeb6046d60c7..92cc52001e74 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -535,8 +535,8 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m) unsigned long nr_faults = -1; int cpu_current, home_node; - if (p->numa_faults_memory) - nr_faults = p->numa_faults_memory[2*node + i]; + if (p->numa_faults) + nr_faults = p->numa_faults[2*node + i]; cpu_current = !i ? (task_node(p) == node) : (pol && node_isset(node, pol->v.nodes)); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d03d76de7aff..826fdf326683 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -896,18 +896,24 @@ pid_t task_numa_group_id(struct task_struct *p) return p->numa_group ? p->numa_group->gid : 0; } -static inline int task_faults_idx(int nid, int priv) +/* + * The averaged statistics, shared & private, memory & cpu, + * occupy the first half of the array. The second half of the + * array is for current counters, which are averaged into the + * first set by task_numa_placement. + */ +static inline int task_faults_idx(enum numa_faults_stats s, int nid, int priv) { - return NR_NUMA_HINT_FAULT_TYPES * nid + priv; + return NR_NUMA_HINT_FAULT_TYPES * (s * nr_node_ids + nid) + priv; } static inline unsigned long task_faults(struct task_struct *p, int nid) { - if (!p->numa_faults_memory) + if (!p->numa_faults) return 0; - return p->numa_faults_memory[task_faults_idx(nid, 0)] + - p->numa_faults_memory[task_faults_idx(nid, 1)]; + return p->numa_faults[task_faults_idx(NUMA_MEM, nid, 0)] + + p->numa_faults[task_faults_idx(NUMA_MEM, nid, 1)]; } static inline unsigned long group_faults(struct task_struct *p, int nid) @@ -915,14 +921,14 @@ static inline unsigned long group_faults(struct task_struct *p, int nid) if (!p->numa_group) return 0; - return p->numa_group->faults[task_faults_idx(nid, 0)] + - p->numa_group->faults[task_faults_idx(nid, 1)]; + return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] + + p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)]; } static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) { - return group->faults_cpu[task_faults_idx(nid, 0)] + - group->faults_cpu[task_faults_idx(nid, 1)]; + return group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 0)] + + group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)]; } /* Handle placement on systems where not all nodes are directly connected. */ @@ -1001,7 +1007,7 @@ static inline unsigned long task_weight(struct task_struct *p, int nid, { unsigned long faults, total_faults; - if (!p->numa_faults_memory) + if (!p->numa_faults) return 0; total_faults = p->total_numa_faults; @@ -1517,7 +1523,7 @@ static void numa_migrate_preferred(struct task_struct *p) unsigned long interval = HZ; /* This task has no NUMA fault statistics yet */ - if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory)) + if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults)) return; /* Periodically retry migrating the task to the preferred node */ @@ -1779,18 +1785,23 @@ static void task_numa_placement(struct task_struct *p) /* Find the node with the highest number of faults */ for_each_online_node(nid) { + /* Keep track of the offsets in numa_faults array */ + int mem_idx, membuf_idx, cpu_idx, cpubuf_idx; unsigned long faults = 0, group_faults = 0; - int priv, i; + int priv; for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) { long diff, f_diff, f_weight; - i = task_faults_idx(nid, priv); + mem_idx = task_faults_idx(NUMA_MEM, nid, priv); + membuf_idx = task_faults_idx(NUMA_MEMBUF, nid, priv); + cpu_idx = task_faults_idx(NUMA_CPU, nid, priv); + cpubuf_idx = task_faults_idx(NUMA_CPUBUF, nid, priv); /* Decay existing window, copy faults since last scan */ - diff = p->numa_faults_buffer_memory[i] - p->numa_faults_memory[i] / 2; - fault_types[priv] += p->numa_faults_buffer_memory[i]; - p->numa_faults_buffer_memory[i] = 0; + diff = p->numa_faults[membuf_idx] - p->numa_faults[mem_idx] / 2; + fault_types[priv] += p->numa_faults[membuf_idx]; + p->numa_faults[membuf_idx] = 0; /* * Normalize the faults_from, so all tasks in a group @@ -1800,21 +1811,27 @@ static void task_numa_placement(struct task_struct *p) * faults are less important. */ f_weight = div64_u64(runtime << 16, period + 1); - f_weight = (f_weight * p->numa_faults_buffer_cpu[i]) / + f_weight = (f_weight * p->numa_faults[cpubuf_idx]) / (total_faults + 1); - f_diff = f_weight - p->numa_faults_cpu[i] / 2; - p->numa_faults_buffer_cpu[i] = 0; + f_diff = f_weight - p->numa_faults[cpu_idx] / 2; + p->numa_faults[cpubuf_idx] = 0; - p->numa_faults_memory[i] += diff; - p->numa_faults_cpu[i] += f_diff; - faults += p->numa_faults_memory[i]; + p->numa_faults[mem_idx] += diff; + p->numa_faults[cpu_idx] += f_diff; + faults += p->numa_faults[mem_idx]; p->total_numa_faults += diff; if (p->numa_group) { - /* safe because we can only change our own group */ - p->numa_group->faults[i] += diff; - p->numa_group->faults_cpu[i] += f_diff; + /* + * safe because we can only change our own group + * + * mem_idx represents the offset for a given + * nid and priv in a specific region because it + * is at the beginning of the numa_faults array. + */ + p->numa_group->faults[mem_idx] += diff; + p->numa_group->faults_cpu[mem_idx] += f_diff; p->numa_group->total_faults += diff; - group_faults += p->numa_group->faults[i]; + group_faults += p->numa_group->faults[mem_idx]; } } @@ -1886,7 +1903,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, node_set(task_node(current), grp->active_nodes); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) - grp->faults[i] = p->numa_faults_memory[i]; + grp->faults[i] = p->numa_faults[i]; grp->total_faults = p->total_numa_faults; @@ -1945,8 +1962,8 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, double_lock_irq(&my_grp->lock, &grp->lock); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) { - my_grp->faults[i] -= p->numa_faults_memory[i]; - grp->faults[i] += p->numa_faults_memory[i]; + my_grp->faults[i] -= p->numa_faults[i]; + grp->faults[i] += p->numa_faults[i]; } my_grp->total_faults -= p->total_numa_faults; grp->total_faults += p->total_numa_faults; @@ -1971,14 +1988,14 @@ no_join: void task_numa_free(struct task_struct *p) { struct numa_group *grp = p->numa_group; - void *numa_faults = p->numa_faults_memory; + void *numa_faults = p->numa_faults; unsigned long flags; int i; if (grp) { spin_lock_irqsave(&grp->lock, flags); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) - grp->faults[i] -= p->numa_faults_memory[i]; + grp->faults[i] -= p->numa_faults[i]; grp->total_faults -= p->total_numa_faults; list_del(&p->numa_entry); @@ -1988,10 +2005,7 @@ void task_numa_free(struct task_struct *p) put_numa_group(grp); } - p->numa_faults_memory = NULL; - p->numa_faults_buffer_memory = NULL; - p->numa_faults_cpu= NULL; - p->numa_faults_buffer_cpu = NULL; + p->numa_faults = NULL; kfree(numa_faults); } @@ -2014,24 +2028,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) return; /* Allocate buffer to track faults on a per-node basis */ - if (unlikely(!p->numa_faults_memory)) { - int size = sizeof(*p->numa_faults_memory) * + if (unlikely(!p->numa_faults)) { + int size = sizeof(*p->numa_faults) * NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids; - p->numa_faults_memory = kzalloc(size, GFP_KERNEL|__GFP_NOWARN); - if (!p->numa_faults_memory) + p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN); + if (!p->numa_faults) return; - BUG_ON(p->numa_faults_buffer_memory); - /* - * The averaged statistics, shared & private, memory & cpu, - * occupy the first half of the array. The second half of the - * array is for current counters, which are averaged into the - * first set by task_numa_placement. - */ - p->numa_faults_cpu = p->numa_faults_memory + (2 * nr_node_ids); - p->numa_faults_buffer_memory = p->numa_faults_memory + (4 * nr_node_ids); - p->numa_faults_buffer_cpu = p->numa_faults_memory + (6 * nr_node_ids); p->total_numa_faults = 0; memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality)); } @@ -2071,8 +2075,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) if (migrated) p->numa_pages_migrated += pages; - p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages; - p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages; + p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages; + p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages; p->numa_faults_locality[local] += pages; } @@ -5361,7 +5365,7 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) struct numa_group *numa_group = rcu_dereference(p->numa_group); int src_nid, dst_nid; - if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory || + if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults || !(env->sd->flags & SD_NUMA)) { return false; } @@ -5400,7 +5404,7 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER)) return false; - if (!p->numa_faults_memory || !(env->sd->flags & SD_NUMA)) + if (!p->numa_faults || !(env->sd->flags & SD_NUMA)) return false; src_nid = cpu_to_node(env->src_cpu); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 7e5c1eebc110..31f1e4d2996a 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -709,6 +709,13 @@ extern bool find_numa_distance(int distance); #endif #ifdef CONFIG_NUMA_BALANCING +/* The regions in numa_faults array from task_struct */ +enum numa_faults_stats { + NUMA_MEM = 0, + NUMA_CPU, + NUMA_MEMBUF, + NUMA_CPUBUF +}; extern void sched_setnuma(struct task_struct *p, int node); extern int migrate_task_to(struct task_struct *p, int cpu); extern int migrate_swap(struct task_struct *, struct task_struct *); -- cgit v1.2.3