From 143e1e28cb40bed836b0a06567208bd7347c9672 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 11 Apr 2014 11:44:37 +0200 Subject: sched: Rework sched_domain topology definition We replace the old way to configure the scheduler topology with a new method which enables a platform to declare additionnal level (if needed). We still have a default topology table definition that can be used by platform that don't want more level than the SMT, MC, CPU and NUMA ones. This table can be overwritten by an arch which either wants to add new level where a load balance make sense like BOOK or powergating level or wants to change the flags configuration of some levels. For each level, we need a function pointer that returns cpumask for each cpu, a function pointer that returns the flags for the level and a name. Only flags that describe topology, can be set by an architecture. The current topology flags are: SD_SHARE_CPUPOWER SD_SHARE_PKG_RESOURCES SD_NUMA SD_ASYM_PACKING Then, each level must be a subset on the next one. The build sequence of the sched_domain will take care of removing useless levels like those with 1 CPU and those with the same CPU span and no more relevant information for load balancing than its children. Signed-off-by: Vincent Guittot Tested-by: Dietmar Eggemann Reviewed-by: Preeti U Murthy Reviewed-by: Dietmar Eggemann Signed-off-by: Peter Zijlstra Cc: Andrew Morton Cc: Benjamin Herrenschmidt Cc: Bjorn Helgaas Cc: Chris Metcalf Cc: Christoph Lameter Cc: David S. Miller Cc: Fenghua Yu Cc: Greg Kroah-Hartman Cc: Hanjun Guo Cc: Heiko Carstens Cc: Jason Low Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Tony Luck Cc: linux390@de.ibm.com Cc: linux-ia64@vger.kernel.org Cc: linux-s390@vger.kernel.org Link: http://lkml.kernel.org/r/1397209481-28542-2-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 233 +++++++++++++++++++++++++++------------------------- 1 file changed, 120 insertions(+), 113 deletions(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 13584f1cccfc..7d332b7899cc 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5566,17 +5566,6 @@ static int __init isolated_cpu_setup(char *str) __setup("isolcpus=", isolated_cpu_setup); -static const struct cpumask *cpu_cpu_mask(int cpu) -{ - return cpumask_of_node(cpu_to_node(cpu)); -} - -struct sd_data { - struct sched_domain **__percpu sd; - struct sched_group **__percpu sg; - struct sched_group_power **__percpu sgp; -}; - struct s_data { struct sched_domain ** __percpu sd; struct root_domain *rd; @@ -5589,21 +5578,6 @@ enum s_alloc { sa_none, }; -struct sched_domain_topology_level; - -typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu); -typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); - -#define SDTL_OVERLAP 0x01 - -struct sched_domain_topology_level { - sched_domain_init_f init; - sched_domain_mask_f mask; - int flags; - int numa_level; - struct sd_data data; -}; - /* * Build an iteration mask that can exclude certain CPUs from the upwards * domain traversal. @@ -5832,34 +5806,6 @@ int __weak arch_sd_sibling_asym_packing(void) * Non-inlined to reduce accumulated stack pressure in build_sched_domains() */ -#ifdef CONFIG_SCHED_DEBUG -# define SD_INIT_NAME(sd, type) sd->name = #type -#else -# define SD_INIT_NAME(sd, type) do { } while (0) -#endif - -#define SD_INIT_FUNC(type) \ -static noinline struct sched_domain * \ -sd_init_##type(struct sched_domain_topology_level *tl, int cpu) \ -{ \ - struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); \ - *sd = SD_##type##_INIT; \ - SD_INIT_NAME(sd, type); \ - sd->private = &tl->data; \ - return sd; \ -} - -SD_INIT_FUNC(CPU) -#ifdef CONFIG_SCHED_SMT - SD_INIT_FUNC(SIBLING) -#endif -#ifdef CONFIG_SCHED_MC - SD_INIT_FUNC(MC) -#endif -#ifdef CONFIG_SCHED_BOOK - SD_INIT_FUNC(BOOK) -#endif - static int default_relax_domain_level = -1; int sched_domain_level_max; @@ -5947,99 +5893,156 @@ static void claim_allocations(int cpu, struct sched_domain *sd) *per_cpu_ptr(sdd->sgp, cpu) = NULL; } -#ifdef CONFIG_SCHED_SMT -static const struct cpumask *cpu_smt_mask(int cpu) -{ - return topology_thread_cpumask(cpu); -} -#endif - -/* - * Topology list, bottom-up. - */ -static struct sched_domain_topology_level default_topology[] = { -#ifdef CONFIG_SCHED_SMT - { sd_init_SIBLING, cpu_smt_mask, }, -#endif -#ifdef CONFIG_SCHED_MC - { sd_init_MC, cpu_coregroup_mask, }, -#endif -#ifdef CONFIG_SCHED_BOOK - { sd_init_BOOK, cpu_book_mask, }, -#endif - { sd_init_CPU, cpu_cpu_mask, }, - { NULL, }, -}; - -static struct sched_domain_topology_level *sched_domain_topology = default_topology; - -#define for_each_sd_topology(tl) \ - for (tl = sched_domain_topology; tl->init; tl++) - #ifdef CONFIG_NUMA - static int sched_domains_numa_levels; static int *sched_domains_numa_distance; static struct cpumask ***sched_domains_numa_masks; static int sched_domains_curr_level; +#endif -static inline int sd_local_flags(int level) -{ - if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE) - return 0; - - return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE; -} +/* + * SD_flags allowed in topology descriptions. + * + * SD_SHARE_CPUPOWER - describes SMT topologies + * SD_SHARE_PKG_RESOURCES - describes shared caches + * SD_NUMA - describes NUMA topologies + * + * Odd one out: + * SD_ASYM_PACKING - describes SMT quirks + */ +#define TOPOLOGY_SD_FLAGS \ + (SD_SHARE_CPUPOWER | \ + SD_SHARE_PKG_RESOURCES | \ + SD_NUMA | \ + SD_ASYM_PACKING) static struct sched_domain * -sd_numa_init(struct sched_domain_topology_level *tl, int cpu) +sd_init(struct sched_domain_topology_level *tl, int cpu) { struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); - int level = tl->numa_level; - int sd_weight = cpumask_weight( - sched_domains_numa_masks[level][cpu_to_node(cpu)]); + int sd_weight, sd_flags = 0; + +#ifdef CONFIG_NUMA + /* + * Ugly hack to pass state to sd_numa_mask()... + */ + sched_domains_curr_level = tl->numa_level; +#endif + + sd_weight = cpumask_weight(tl->mask(cpu)); + + if (tl->sd_flags) + sd_flags = (*tl->sd_flags)(); + if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, + "wrong sd_flags in topology description\n")) + sd_flags &= ~TOPOLOGY_SD_FLAGS; *sd = (struct sched_domain){ .min_interval = sd_weight, .max_interval = 2*sd_weight, .busy_factor = 32, .imbalance_pct = 125, - .cache_nice_tries = 2, - .busy_idx = 3, - .idle_idx = 2, + + .cache_nice_tries = 0, + .busy_idx = 0, + .idle_idx = 0, .newidle_idx = 0, .wake_idx = 0, .forkexec_idx = 0, .flags = 1*SD_LOAD_BALANCE | 1*SD_BALANCE_NEWIDLE - | 0*SD_BALANCE_EXEC - | 0*SD_BALANCE_FORK + | 1*SD_BALANCE_EXEC + | 1*SD_BALANCE_FORK | 0*SD_BALANCE_WAKE - | 0*SD_WAKE_AFFINE + | 1*SD_WAKE_AFFINE | 0*SD_SHARE_CPUPOWER | 0*SD_SHARE_PKG_RESOURCES - | 1*SD_SERIALIZE + | 0*SD_SERIALIZE | 0*SD_PREFER_SIBLING - | 1*SD_NUMA - | sd_local_flags(level) + | 0*SD_NUMA + | sd_flags , + .last_balance = jiffies, .balance_interval = sd_weight, + .smt_gain = 0, .max_newidle_lb_cost = 0, .next_decay_max_lb_cost = jiffies, +#ifdef CONFIG_SCHED_DEBUG + .name = tl->name, +#endif }; - SD_INIT_NAME(sd, NUMA); - sd->private = &tl->data; /* - * Ugly hack to pass state to sd_numa_mask()... + * Convert topological properties into behaviour. */ - sched_domains_curr_level = tl->numa_level; + + if (sd->flags & SD_SHARE_CPUPOWER) { + sd->imbalance_pct = 110; + sd->smt_gain = 1178; /* ~15% */ + sd->flags |= arch_sd_sibling_asym_packing(); + + } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { + sd->imbalance_pct = 117; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + +#ifdef CONFIG_NUMA + } else if (sd->flags & SD_NUMA) { + sd->cache_nice_tries = 2; + sd->busy_idx = 3; + sd->idle_idx = 2; + + sd->flags |= SD_SERIALIZE; + if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + sd->flags &= ~(SD_BALANCE_EXEC | + SD_BALANCE_FORK | + SD_WAKE_AFFINE); + } + +#endif + } else { + sd->flags |= SD_PREFER_SIBLING; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + sd->idle_idx = 1; + } + + sd->private = &tl->data; return sd; } +/* + * Topology list, bottom-up. + */ +static struct sched_domain_topology_level default_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif +#ifdef CONFIG_SCHED_BOOK + { cpu_book_mask, SD_INIT_NAME(BOOK) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + +struct sched_domain_topology_level *sched_domain_topology = default_topology; + +#define for_each_sd_topology(tl) \ + for (tl = sched_domain_topology; tl->mask; tl++) + +void set_sched_topology(struct sched_domain_topology_level *tl) +{ + sched_domain_topology = tl; +} + +#ifdef CONFIG_NUMA + static const struct cpumask *sd_numa_mask(int cpu) { return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; @@ -6183,7 +6186,10 @@ static void sched_init_numa(void) } } - tl = kzalloc((ARRAY_SIZE(default_topology) + level) * + /* Compute default topology size */ + for (i = 0; sched_domain_topology[i].mask; i++); + + tl = kzalloc((i + level) * sizeof(struct sched_domain_topology_level), GFP_KERNEL); if (!tl) return; @@ -6191,18 +6197,19 @@ static void sched_init_numa(void) /* * Copy the default topology bits.. */ - for (i = 0; default_topology[i].init; i++) - tl[i] = default_topology[i]; + for (i = 0; sched_domain_topology[i].mask; i++) + tl[i] = sched_domain_topology[i]; /* * .. and append 'j' levels of NUMA goodness. */ for (j = 0; j < level; i++, j++) { tl[i] = (struct sched_domain_topology_level){ - .init = sd_numa_init, .mask = sd_numa_mask, + .sd_flags = cpu_numa_flags, .flags = SDTL_OVERLAP, .numa_level = j, + SD_INIT_NAME(NUMA) }; } @@ -6360,7 +6367,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, const struct cpumask *cpu_map, struct sched_domain_attr *attr, struct sched_domain *child, int cpu) { - struct sched_domain *sd = tl->init(tl, cpu); + struct sched_domain *sd = sd_init(tl, cpu); if (!sd) return child; -- cgit v1.2.3 From 2dfd747629e65f89d2dbceb92fffc763f66228b2 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 11 Apr 2014 11:44:38 +0200 Subject: sched, s390: Create a dedicated topology table BOOK level is only relevant for s390 so we create a dedicated topology table with BOOK level and remove it from default table. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra Cc: Heiko Carstens Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Philipp Hachtmann Cc: cmetcalf@tilera.com Cc: benh@kernel.crashing.org Cc: dietmar.eggemann@arm.com Cc: preeti@linux.vnet.ibm.com Cc: tony.luck@intel.com Cc: fenghua.yu@intel.com Cc: linux390@de.ibm.com Cc: linux-s390@vger.kernel.org Link: http://lkml.kernel.org/r/1397209481-28542-3-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7d332b7899cc..e59e5aec745a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6023,9 +6023,6 @@ static struct sched_domain_topology_level default_topology[] = { #endif #ifdef CONFIG_SCHED_MC { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, -#endif -#ifdef CONFIG_SCHED_BOOK - { cpu_book_mask, SD_INIT_NAME(BOOK) }, #endif { cpu_cpu_mask, SD_INIT_NAME(DIE) }, { NULL, }, -- cgit v1.2.3 From 607b45e9a216e89a63351556e488eea06be0ff48 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 11 Apr 2014 11:44:39 +0200 Subject: sched, powerpc: Create a dedicated topology table Create a dedicated topology table for handling asymetric feature of powerpc. Signed-off-by: Vincent Guittot Reviewed-by: Preeti U Murthy Signed-off-by: Peter Zijlstra Cc: Andy Fleming Cc: Anton Blanchard Cc: Benjamin Herrenschmidt Cc: Grant Likely Cc: Linus Torvalds Cc: Michael Ellerman Cc: Paul Gortmaker Cc: Paul Mackerras Cc: Preeti U. Murthy Cc: Rob Herring Cc: Srivatsa S. Bhat Cc: Toshi Kani Cc: Vasant Hegde Cc: tony.luck@intel.com Cc: fenghua.yu@intel.com Cc: schwidefsky@de.ibm.com Cc: cmetcalf@tilera.com Cc: dietmar.eggemann@arm.com Cc: devicetree@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Link: http://lkml.kernel.org/r/1397209481-28542-4-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e59e5aec745a..7e348e238bf1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5796,11 +5796,6 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) atomic_set(&sg->sgp->nr_busy_cpus, sg->group_weight); } -int __weak arch_sd_sibling_asym_packing(void) -{ - return 0*SD_ASYM_PACKING; -} - /* * Initializers for schedule domains * Non-inlined to reduce accumulated stack pressure in build_sched_domains() @@ -5981,7 +5976,6 @@ sd_init(struct sched_domain_topology_level *tl, int cpu) if (sd->flags & SD_SHARE_CPUPOWER) { sd->imbalance_pct = 110; sd->smt_gain = 1178; /* ~15% */ - sd->flags |= arch_sd_sibling_asym_packing(); } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { sd->imbalance_pct = 117; -- cgit v1.2.3 From d77b3ed5c9f8ebedf154b52b5e943c461f3d37e6 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Fri, 11 Apr 2014 11:44:40 +0200 Subject: sched: Add a new SD_SHARE_POWERDOMAIN for sched_domain A new flag SD_SHARE_POWERDOMAIN is created to reflect whether groups of CPUs in a sched_domain level can or not reach different power state. As an example, the flag should be cleared at CPU level if groups of cores can be power gated independently. This information can be used in the load balance decision or to add load balancing level between group of CPUs that can power gate independantly. This flag is part of the topology flags that can be set by arch. Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Cc: tony.luck@intel.com Cc: fenghua.yu@intel.com Cc: schwidefsky@de.ibm.com Cc: cmetcalf@tilera.com Cc: benh@kernel.crashing.org Cc: preeti@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1397209481-28542-5-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7e348e238bf1..1c9c3b7b26af 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5261,7 +5261,8 @@ static int sd_degenerate(struct sched_domain *sd) SD_BALANCE_FORK | SD_BALANCE_EXEC | SD_SHARE_CPUPOWER | - SD_SHARE_PKG_RESOURCES)) { + SD_SHARE_PKG_RESOURCES | + SD_SHARE_POWERDOMAIN)) { if (sd->groups != sd->groups->next) return 0; } @@ -5292,7 +5293,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) SD_BALANCE_EXEC | SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES | - SD_PREFER_SIBLING); + SD_PREFER_SIBLING | + SD_SHARE_POWERDOMAIN); if (nr_node_ids == 1) pflags &= ~SD_SERIALIZE; } @@ -5901,6 +5903,7 @@ static int sched_domains_curr_level; * SD_SHARE_CPUPOWER - describes SMT topologies * SD_SHARE_PKG_RESOURCES - describes shared caches * SD_NUMA - describes NUMA topologies + * SD_SHARE_POWERDOMAIN - describes shared power domain * * Odd one out: * SD_ASYM_PACKING - describes SMT quirks @@ -5909,7 +5912,8 @@ static int sched_domains_curr_level; (SD_SHARE_CPUPOWER | \ SD_SHARE_PKG_RESOURCES | \ SD_NUMA | \ - SD_ASYM_PACKING) + SD_ASYM_PACKING | \ + SD_SHARE_POWERDOMAIN) static struct sched_domain * sd_init(struct sched_domain_topology_level *tl, int cpu) -- cgit v1.2.3 From fd99f91aa007ba255aac44fe6cf21c1db398243a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 9 Apr 2014 15:35:08 +0200 Subject: sched/idle: Avoid spurious wakeup IPIs Because mwait_idle_with_hints() gets called from !idle context it must call current_clr_polling(). This however means that resched_task() is very likely to send an IPI even when we were polling: CPU0 CPU1 if (current_set_polling_and_test()) goto out; __monitor(&ti->flags); if (!need_resched()) __mwait(eax, ecx); set_tsk_need_resched(p); smp_mb(); out: current_clr_polling(); if (!tsk_is_polling(p)) smp_send_reschedule(cpu); So while it is correct (extra IPIs aren't a problem, whereas a missed IPI would be) it is a performance problem (for some). Avoid this issue by using fetch_or() to atomically set NEED_RESCHED and test if POLLING_NRFLAG is set. Since a CPU stuck in mwait is unlikely to modify the flags word, contention on the cmpxchg is unlikely and thus we should mostly succeed in a single go. Signed-off-by: Peter Zijlstra Acked-by: Nicolas Pitre Cc: Andy Lutomirski Cc: Linus Torvalds Link: http://lkml.kernel.org/n/tip-kf5suce6njh5xf5d3od13rr0@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 41 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 36 insertions(+), 5 deletions(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1c9c3b7b26af..4b82622b6252 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -505,6 +505,39 @@ static inline void init_hrtick(void) } #endif /* CONFIG_SCHED_HRTICK */ +/* + * cmpxchg based fetch_or, macro so it works for different integer types + */ +#define fetch_or(ptr, val) \ +({ typeof(*(ptr)) __old, __val = *(ptr); \ + for (;;) { \ + __old = cmpxchg((ptr), __val, __val | (val)); \ + if (__old == __val) \ + break; \ + __val = __old; \ + } \ + __old; \ +}) + +#ifdef TIF_POLLING_NRFLAG +/* + * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, + * this avoids any races wrt polling state changes and thereby avoids + * spurious IPIs. + */ +static bool set_nr_and_not_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG); +} +#else +static bool set_nr_and_not_polling(struct task_struct *p) +{ + set_tsk_need_resched(p); + return true; +} +#endif + /* * resched_task - mark a task 'to be rescheduled now'. * @@ -521,17 +554,15 @@ void resched_task(struct task_struct *p) if (test_tsk_need_resched(p)) return; - set_tsk_need_resched(p); - cpu = task_cpu(p); + if (cpu == smp_processor_id()) { + set_tsk_need_resched(p); set_preempt_need_resched(); return; } - /* NEED_RESCHED must be visible before we test polling */ - smp_mb(); - if (!tsk_is_polling(p)) + if (set_nr_and_not_polling(p)) smp_send_reschedule(cpu); } -- cgit v1.2.3 From e78c7bca56dab5ce4f22694f99115ec07e4935f6 Mon Sep 17 00:00:00 2001 From: Michael Kerrisk Date: Fri, 9 May 2014 16:54:28 +0200 Subject: sched: Simplify return logic in sched_copy_attr() The logic in this function is a little contorted, clean it up: * Rather than having chained gotos for the -EFBIG case, just return -EFBIG directly. * Now, the label 'out' is no longer needed, and 'ret' must be zero zero by the time we fall through to this point, so just return 0. Signed-off-by: Michael Kerrisk Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/536CEC24.9080201@gmail.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2551b6db470e..2318fc484d8b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3657,13 +3657,11 @@ static int sched_copy_attr(struct sched_attr __user *uattr, */ attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE); -out: - return ret; + return 0; err_size: put_user(sizeof(*attr), &uattr->size); - ret = -E2BIG; - goto out; + return -E2BIG; } /** -- cgit v1.2.3 From 22400674945c562cf3c176d6c4178cd545e2dec9 Mon Sep 17 00:00:00 2001 From: Michael Kerrisk Date: Fri, 9 May 2014 16:54:33 +0200 Subject: sched: Simplify return logic in sched_read_attr() Gotos are chained pointlessly here, and the 'out' label can be dispensed with. Signed-off-by: Michael Kerrisk Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/536CEC29.9090503@gmail.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2318fc484d8b..a78c5b62a470 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3821,7 +3821,7 @@ static int sched_read_attr(struct sched_attr __user *uattr, for (; addr < end; addr++) { if (*addr) - goto err_size; + return -EFBIG; } attr->size = usize; @@ -3831,12 +3831,7 @@ static int sched_read_attr(struct sched_attr __user *uattr, if (ret) return -EFAULT; -out: - return ret; - -err_size: - ret = -E2BIG; - goto out; + return 0; } /** -- cgit v1.2.3 From c515db8cd311ef77b2dc7cbd6b695022655bb0f3 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Tue, 13 May 2014 11:11:01 +0200 Subject: sched/numa: Fix initialization of sched_domain_topology for NUMA Jet Chen has reported a kernel panics when booting qemu-system-x86_64 with kvm64 cpu. A panic occured while building the sched_domain. In sched_init_numa, we create a new topology table in which both default levels and numa levels are copied. The last row of the table must have a null pointer in the mask field. The current implementation doesn't add this last row in the computation of the table size. So we add 1 row in the allocation size that will be used as the last row of the table. The kzalloc will ensure that the mask field is NULL. Reported-by: Jet Chen Tested-by: Jet Chen Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra Cc: fengguang.wu@intel.com Link: http://lkml.kernel.org/r/1399972261-25693-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a78c5b62a470..45d077ed24fb 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6231,7 +6231,7 @@ static void sched_init_numa(void) /* Compute default topology size */ for (i = 0; sched_domain_topology[i].mask; i++); - tl = kzalloc((i + level) * + tl = kzalloc((i + level + 1) * sizeof(struct sched_domain_topology_level), GFP_KERNEL); if (!tl) return; -- cgit v1.2.3 From caffcdd8d27ba78730d5540396ce72ad022aff2c Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Wed, 30 Apr 2014 14:39:38 +0100 Subject: sched: Do not zero sg->cpumask and sg->sgp->power in build_sched_groups() There is no need to zero struct sched_group member cpumask and struct sched_group_power member power since both structures are already allocated as zeroed memory in __sdt_alloc(). This patch has been tested with BUG_ON(!cpumask_empty(sched_group_cpus(sg))); and BUG_ON(sg->sgp->power); in build_sched_groups() on ARM TC2 and INTEL i5 M520 platform including CPU hotplug scenarios. Signed-off-by: Dietmar Eggemann Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1398865178-12577-1-git-send-email-dietmar.eggemann@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 45d077ed24fb..6340c601475d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5794,8 +5794,6 @@ build_sched_groups(struct sched_domain *sd, int cpu) continue; group = get_group(i, sdd, &sg); - cpumask_clear(sched_group_cpus(sg)); - sg->sgp->power = 0; cpumask_setall(sched_group_mask(sg)); for_each_cpu(j, span) { -- cgit v1.2.3 From a9467fa3cd2d5bf39e7cb7d0706d29d7ef4df212 Mon Sep 17 00:00:00 2001 From: Dongsheng Yang Date: Thu, 8 May 2014 18:35:15 +0900 Subject: sched: Use clamp() and clamp_val() to make sys_nice() more readable Suggested-by: Kees Cook Signed-off-by: Dongsheng Yang Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1399541715-19568-1-git-send-email-yangds.fnst@cn.fujitsu.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6340c601475d..f5605b6deea4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3057,17 +3057,10 @@ SYSCALL_DEFINE1(nice, int, increment) * We don't have to worry. Conceptually one call occurs first * and we have a single winner. */ - if (increment < -40) - increment = -40; - if (increment > 40) - increment = 40; - + increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); nice = task_nice(current) + increment; - if (nice < MIN_NICE) - nice = MIN_NICE; - if (nice > MAX_NICE) - nice = MAX_NICE; + nice = clamp_val(nice, MIN_NICE, MAX_NICE); if (increment < 0 && !can_nice(current, nice)) return -EPERM; -- cgit v1.2.3 From a803f0261bb2bb57aab5542af3174db43b2a3887 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Thu, 8 May 2014 13:47:39 -0500 Subject: sched: Initialize rq->age_stamp on processor start If the sched_clock time starts at a large value, the kernel will spin in sched_avg_update for a long time while rq->age_stamp catches up with rq->clock. The comment in kernel/sched/clock.c says that there is no strict promise that it starts at zero. So initialize rq->age_stamp when a cpu starts up to avoid this. I was seeing long delays on a simulator that didn't start the clock at zero. This might also be an issue on reboots on processors that don't re-initialize the timer to zero on reset, and when using kexec. Signed-off-by: Corey Minyard Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1399574859-11714-1-git-send-email-minyard@acm.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f5605b6deea4..da302ca98f60 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5089,10 +5089,20 @@ static struct notifier_block migration_notifier = { .priority = CPU_PRI_MIGRATION, }; +static void __cpuinit set_cpu_rq_start_time(void) +{ + int cpu = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); + rq->age_stamp = sched_clock_cpu(cpu); +} + static int sched_cpu_active(struct notifier_block *nfb, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { + case CPU_STARTING: + set_cpu_rq_start_time(); + return NOTIFY_OK; case CPU_DOWN_FAILED: set_cpu_active((long)hcpu, true); return NOTIFY_OK; @@ -6970,6 +6980,7 @@ void __init sched_init(void) if (cpu_isolated_map == NULL) zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); idle_thread_set_boot_cpu(); + set_cpu_rq_start_time(); #endif init_sched_fair_class(); -- cgit v1.2.3 From 7aa2c016db2162defff77f6f5731bff3f25e5175 Mon Sep 17 00:00:00 2001 From: Dongsheng Yang Date: Thu, 8 May 2014 18:33:49 +0900 Subject: sched: Consolidate open coded implementations of nice level frobbing into nice_to_rlimit() and rlimit_to_nice() Signed-off-by: Dongsheng Yang Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/a568a1e3cc8e78648f41b5035fa5e381d36274da.1399532322.git.yangds.fnst@cn.fujitsu.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/sched/core.c') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index da302ca98f60..321d800e4baa 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3033,7 +3033,7 @@ EXPORT_SYMBOL(set_user_nice); int can_nice(const struct task_struct *p, const int nice) { /* convert nice value [19,-20] to rlimit style value [1,40] */ - int nice_rlim = 20 - nice; + int nice_rlim = nice_to_rlimit(nice); return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || capable(CAP_SYS_NICE)); -- cgit v1.2.3