From c8eaf6ac76f40f6c59fc7d056e2e08c4a57ea9c7 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Fri, 28 Jan 2022 17:50:25 +0800 Subject: sched: move autogroup sysctls into its own file move autogroup sysctls to autogroup.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220128095025.8745-1-nizhen@uniontech.com --- include/linux/sched/sysctl.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index c19dd5a2c05c..3f2b70f8d32c 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -45,10 +45,6 @@ extern unsigned int sysctl_sched_uclamp_util_min_rt_default; extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif -#ifdef CONFIG_SCHED_AUTOGROUP -extern unsigned int sysctl_sched_autogroup_enabled; -#endif - extern int sysctl_sched_rr_timeslice; extern int sched_rr_timeslice; -- cgit v1.2.3 From e496132ebedd870b67f1f6d2428f9bb9d7ae27fd Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 8 Feb 2022 09:43:34 +0000 Subject: sched/fair: Adjust the allowed NUMA imbalance when SD_NUMA spans multiple LLCs Commit 7d2b5dd0bcc4 ("sched/numa: Allow a floating imbalance between NUMA nodes") allowed an imbalance between NUMA nodes such that communicating tasks would not be pulled apart by the load balancer. This works fine when there is a 1:1 relationship between LLC and node but can be suboptimal for multiple LLCs if independent tasks prematurely use CPUs sharing cache. Zen* has multiple LLCs per node with local memory channels and due to the allowed imbalance, it's far harder to tune some workloads to run optimally than it is on hardware that has 1 LLC per node. This patch allows an imbalance to exist up to the point where LLCs should be balanced between nodes. On a Zen3 machine running STREAM parallelised with OMP to have on instance per LLC the results and without binding, the results are 5.17.0-rc0 5.17.0-rc0 vanilla sched-numaimb-v6 MB/sec copy-16 162596.94 ( 0.00%) 580559.74 ( 257.05%) MB/sec scale-16 136901.28 ( 0.00%) 374450.52 ( 173.52%) MB/sec add-16 157300.70 ( 0.00%) 564113.76 ( 258.62%) MB/sec triad-16 151446.88 ( 0.00%) 564304.24 ( 272.61%) STREAM can use directives to force the spread if the OpenMP is new enough but that doesn't help if an application uses threads and it's not known in advance how many threads will be created. Coremark is a CPU and cache intensive benchmark parallelised with threads. When running with 1 thread per core, the vanilla kernel allows threads to contend on cache. With the patch; 5.17.0-rc0 5.17.0-rc0 vanilla sched-numaimb-v5 Min Score-16 368239.36 ( 0.00%) 389816.06 ( 5.86%) Hmean Score-16 388607.33 ( 0.00%) 427877.08 * 10.11%* Max Score-16 408945.69 ( 0.00%) 481022.17 ( 17.62%) Stddev Score-16 15247.04 ( 0.00%) 24966.82 ( -63.75%) CoeffVar Score-16 3.92 ( 0.00%) 5.82 ( -48.48%) It can also make a big difference for semi-realistic workloads like specjbb which can execute arbitrary numbers of threads without advance knowledge of how they should be placed. Even in cases where the average performance is neutral, the results are more stable. 5.17.0-rc0 5.17.0-rc0 vanilla sched-numaimb-v6 Hmean tput-1 71631.55 ( 0.00%) 73065.57 ( 2.00%) Hmean tput-8 582758.78 ( 0.00%) 556777.23 ( -4.46%) Hmean tput-16 1020372.75 ( 0.00%) 1009995.26 ( -1.02%) Hmean tput-24 1416430.67 ( 0.00%) 1398700.11 ( -1.25%) Hmean tput-32 1687702.72 ( 0.00%) 1671357.04 ( -0.97%) Hmean tput-40 1798094.90 ( 0.00%) 2015616.46 * 12.10%* Hmean tput-48 1972731.77 ( 0.00%) 2333233.72 ( 18.27%) Hmean tput-56 2386872.38 ( 0.00%) 2759483.38 ( 15.61%) Hmean tput-64 2909475.33 ( 0.00%) 2925074.69 ( 0.54%) Hmean tput-72 2585071.36 ( 0.00%) 2962443.97 ( 14.60%) Hmean tput-80 2994387.24 ( 0.00%) 3015980.59 ( 0.72%) Hmean tput-88 3061408.57 ( 0.00%) 3010296.16 ( -1.67%) Hmean tput-96 3052394.82 ( 0.00%) 2784743.41 ( -8.77%) Hmean tput-104 2997814.76 ( 0.00%) 2758184.50 ( -7.99%) Hmean tput-112 2955353.29 ( 0.00%) 2859705.09 ( -3.24%) Hmean tput-120 2889770.71 ( 0.00%) 2764478.46 ( -4.34%) Hmean tput-128 2871713.84 ( 0.00%) 2750136.73 ( -4.23%) Stddev tput-1 5325.93 ( 0.00%) 2002.53 ( 62.40%) Stddev tput-8 6630.54 ( 0.00%) 10905.00 ( -64.47%) Stddev tput-16 25608.58 ( 0.00%) 6851.16 ( 73.25%) Stddev tput-24 12117.69 ( 0.00%) 4227.79 ( 65.11%) Stddev tput-32 27577.16 ( 0.00%) 8761.05 ( 68.23%) Stddev tput-40 59505.86 ( 0.00%) 2048.49 ( 96.56%) Stddev tput-48 168330.30 ( 0.00%) 93058.08 ( 44.72%) Stddev tput-56 219540.39 ( 0.00%) 30687.02 ( 86.02%) Stddev tput-64 121750.35 ( 0.00%) 9617.36 ( 92.10%) Stddev tput-72 223387.05 ( 0.00%) 34081.13 ( 84.74%) Stddev tput-80 128198.46 ( 0.00%) 22565.19 ( 82.40%) Stddev tput-88 136665.36 ( 0.00%) 27905.97 ( 79.58%) Stddev tput-96 111925.81 ( 0.00%) 99615.79 ( 11.00%) Stddev tput-104 146455.96 ( 0.00%) 28861.98 ( 80.29%) Stddev tput-112 88740.49 ( 0.00%) 58288.23 ( 34.32%) Stddev tput-120 186384.86 ( 0.00%) 45812.03 ( 75.42%) Stddev tput-128 78761.09 ( 0.00%) 57418.48 ( 27.10%) Similarly, for embarassingly parallel problems like NPB-ep, there are improvements due to better spreading across LLC when the machine is not fully utilised. vanilla sched-numaimb-v6 Min ep.D 31.79 ( 0.00%) 26.11 ( 17.87%) Amean ep.D 31.86 ( 0.00%) 26.17 * 17.86%* Stddev ep.D 0.07 ( 0.00%) 0.05 ( 24.41%) CoeffVar ep.D 0.22 ( 0.00%) 0.20 ( 7.97%) Max ep.D 31.93 ( 0.00%) 26.21 ( 17.91%) Signed-off-by: Mel Gorman Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Gautham R. Shenoy Tested-by: K Prateek Nayak Link: https://lore.kernel.org/r/20220208094334.16379-3-mgorman@techsingularity.net --- include/linux/sched/topology.h | 1 + kernel/sched/fair.c | 22 ++++++++++-------- kernel/sched/topology.c | 53 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 66 insertions(+), 10 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 8054641c0a7b..56cffe42abbc 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -93,6 +93,7 @@ struct sched_domain { unsigned int busy_factor; /* less balancing by factor if busy */ unsigned int imbalance_pct; /* No balance until over watermark */ unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ + unsigned int imb_numa_nr; /* Nr running tasks that allows a NUMA imbalance */ int nohz_idle; /* NOHZ IDLE status */ int flags; /* See SD_* */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ea710168ae91..5c4bfffe8c2c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1489,6 +1489,7 @@ struct task_numa_env { int src_cpu, src_nid; int dst_cpu, dst_nid; + int imb_numa_nr; struct numa_stats src_stats, dst_stats; @@ -1503,7 +1504,7 @@ struct task_numa_env { static unsigned long cpu_load(struct rq *rq); static unsigned long cpu_runnable(struct rq *rq); static inline long adjust_numa_imbalance(int imbalance, - int dst_running, int dst_weight); + int dst_running, int imb_numa_nr); static inline enum numa_type numa_classify(unsigned int imbalance_pct, @@ -1884,7 +1885,7 @@ static void task_numa_find_cpu(struct task_numa_env *env, dst_running = env->dst_stats.nr_running + 1; imbalance = max(0, dst_running - src_running); imbalance = adjust_numa_imbalance(imbalance, dst_running, - env->dst_stats.weight); + env->imb_numa_nr); /* Use idle CPU if there is no imbalance */ if (!imbalance) { @@ -1949,8 +1950,10 @@ static int task_numa_migrate(struct task_struct *p) */ rcu_read_lock(); sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu)); - if (sd) + if (sd) { env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2; + env.imb_numa_nr = sd->imb_numa_nr; + } rcu_read_unlock(); /* @@ -9005,10 +9008,9 @@ static bool update_pick_idlest(struct sched_group *idlest, * This is an approximation as the number of running tasks may not be * related to the number of busy CPUs due to sched_setaffinity. */ -static inline bool -allow_numa_imbalance(unsigned int running, unsigned int weight) +static inline bool allow_numa_imbalance(int running, int imb_numa_nr) { - return (running < (weight >> 2)); + return running <= imb_numa_nr; } /* @@ -9148,7 +9150,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) * allowed. If there is a real need of migration, * periodic load balance will take care of it. */ - if (allow_numa_imbalance(local_sgs.sum_nr_running + 1, local_sgs.group_weight)) + if (allow_numa_imbalance(local_sgs.sum_nr_running + 1, sd->imb_numa_nr)) return NULL; } @@ -9240,9 +9242,9 @@ next_group: #define NUMA_IMBALANCE_MIN 2 static inline long adjust_numa_imbalance(int imbalance, - int dst_running, int dst_weight) + int dst_running, int imb_numa_nr) { - if (!allow_numa_imbalance(dst_running, dst_weight)) + if (!allow_numa_imbalance(dst_running, imb_numa_nr)) return imbalance; /* @@ -9354,7 +9356,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /* Consider allowing a small imbalance between NUMA groups */ if (env->sd->flags & SD_NUMA) { env->imbalance = adjust_numa_imbalance(env->imbalance, - local->sum_nr_running + 1, local->group_weight); + local->sum_nr_running + 1, env->sd->imb_numa_nr); } return; diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index d201a7052a29..e6cd55951304 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -2242,6 +2242,59 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att } } + /* + * Calculate an allowed NUMA imbalance such that LLCs do not get + * imbalanced. + */ + for_each_cpu(i, cpu_map) { + unsigned int imb = 0; + unsigned int imb_span = 1; + + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + struct sched_domain *child = sd->child; + + if (!(sd->flags & SD_SHARE_PKG_RESOURCES) && child && + (child->flags & SD_SHARE_PKG_RESOURCES)) { + struct sched_domain *top, *top_p; + unsigned int nr_llcs; + + /* + * For a single LLC per node, allow an + * imbalance up to 25% of the node. This is an + * arbitrary cutoff based on SMT-2 to balance + * between memory bandwidth and avoiding + * premature sharing of HT resources and SMT-4 + * or SMT-8 *may* benefit from a different + * cutoff. + * + * For multiple LLCs, allow an imbalance + * until multiple tasks would share an LLC + * on one node while LLCs on another node + * remain idle. + */ + nr_llcs = sd->span_weight / child->span_weight; + if (nr_llcs == 1) + imb = sd->span_weight >> 2; + else + imb = nr_llcs; + sd->imb_numa_nr = imb; + + /* Set span based on the first NUMA domain. */ + top = sd; + top_p = top->parent; + while (top_p && !(top_p->flags & SD_NUMA)) { + top = top->parent; + top_p = top->parent; + } + imb_span = top_p ? top_p->span_weight : sd->span_weight; + } else { + int factor = max(1U, (sd->span_weight / imb_span)); + + sd->imb_numa_nr = imb * factor; + } + } + } + /* Calculate CPU capacity for physical packages and nodes */ for (i = nr_cpumask_bits-1; i >= 0; i--) { if (!cpumask_test_cpu(i, cpu_map)) -- cgit v1.2.3 From a6cbd44093ef305b02ad5f80ed54abf0148a696c Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Mon, 7 Feb 2022 15:02:47 -0800 Subject: kernel/fork: Initialize mm's PASID A new mm doesn't have a PASID yet when it's created. Initialize the mm's PASID on fork() or for init_mm to INVALID_IOASID (-1). INIT_PASID (0) is reserved for kernel legacy DMA PASID. It cannot be allocated to a user process. Initializing the process's PASID to 0 may cause confusion that's why the process uses the reserved kernel legacy DMA PASID. Initializing the PASID to INVALID_IOASID (-1) explicitly tells the process doesn't have a valid PASID yet. Even though the only user of mm_pasid_init() is in fork.c, define it in as the first of three mm/pasid life cycle functions (init/set/drop) to keep these all together. Suggested-by: Dave Hansen Signed-off-by: Fenghua Yu Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220207230254.3342514-5-fenghua.yu@intel.com --- include/linux/sched/mm.h | 10 ++++++++++ kernel/fork.c | 10 ++-------- mm/init-mm.c | 4 ++++ 3 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index aa5f09ca5bcf..c74d1edbac2f 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -8,6 +8,7 @@ #include #include #include +#include /* * Routines for handling mm_structs @@ -433,4 +434,13 @@ static inline void membarrier_update_current_mm(struct mm_struct *next_mm) } #endif +#ifdef CONFIG_IOMMU_SVA +static inline void mm_pasid_init(struct mm_struct *mm) +{ + mm->pasid = INVALID_IOASID; +} +#else +static inline void mm_pasid_init(struct mm_struct *mm) {} +#endif + #endif /* _LINUX_SCHED_MM_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 6ee7551d3bd2..deacd2c17a7f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -97,6 +97,7 @@ #include #include #include +#include #include #include @@ -1019,13 +1020,6 @@ static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) #endif } -static void mm_init_pasid(struct mm_struct *mm) -{ -#ifdef CONFIG_IOMMU_SVA - mm->pasid = INIT_PASID; -#endif -} - static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES @@ -1054,7 +1048,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); - mm_init_pasid(mm); + mm_pasid_init(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); diff --git a/mm/init-mm.c b/mm/init-mm.c index b4a6f38fb51d..fbe7844d0912 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -10,6 +10,7 @@ #include #include +#include #include #ifndef INIT_MM_CONTEXT @@ -38,6 +39,9 @@ struct mm_struct init_mm = { .mmlist = LIST_HEAD_INIT(init_mm.mmlist), .user_ns = &init_user_ns, .cpu_bitmap = CPU_BITS_NONE, +#ifdef CONFIG_IOMMU_SVA + .pasid = INVALID_IOASID, +#endif INIT_MM_CONTEXT(init_mm) }; -- cgit v1.2.3 From 701fac40384f07197b106136012804c3cae0b3de Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Mon, 7 Feb 2022 15:02:48 -0800 Subject: iommu/sva: Assign a PASID to mm on PASID allocation and free it on mm exit PASIDs are process-wide. It was attempted to use refcounted PASIDs to free them when the last thread drops the refcount. This turned out to be complex and error prone. Given the fact that the PASID space is 20 bits, which allows up to 1M processes to have a PASID associated concurrently, PASID resource exhaustion is not a realistic concern. Therefore, it was decided to simplify the approach and stick with lazy on demand PASID allocation, but drop the eager free approach and make an allocated PASID's lifetime bound to the lifetime of the process. Get rid of the refcounting mechanisms and replace/rename the interfaces to reflect this new approach. [ bp: Massage commit message. ] Suggested-by: Dave Hansen Signed-off-by: Fenghua Yu Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Reviewed-by: Lu Baolu Reviewed-by: Jacob Pan Reviewed-by: Thomas Gleixner Acked-by: Joerg Roedel Link: https://lore.kernel.org/r/20220207230254.3342514-6-fenghua.yu@intel.com --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 5 +--- drivers/iommu/intel/iommu.c | 4 +-- drivers/iommu/intel/svm.c | 9 ------ drivers/iommu/ioasid.c | 39 +++---------------------- drivers/iommu/iommu-sva-lib.c | 39 ++++++++----------------- drivers/iommu/iommu-sva-lib.h | 1 - include/linux/ioasid.h | 12 ++------ include/linux/sched/mm.h | 16 ++++++++++ kernel/fork.c | 1 + 9 files changed, 38 insertions(+), 88 deletions(-) (limited to 'include/linux/sched') diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c index a737ba5f727e..22ddd05bbdcd 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -340,14 +340,12 @@ __arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm) bond->smmu_mn = arm_smmu_mmu_notifier_get(smmu_domain, mm); if (IS_ERR(bond->smmu_mn)) { ret = PTR_ERR(bond->smmu_mn); - goto err_free_pasid; + goto err_free_bond; } list_add(&bond->list, &master->bonds); return &bond->sva; -err_free_pasid: - iommu_sva_free_pasid(mm); err_free_bond: kfree(bond); return ERR_PTR(ret); @@ -377,7 +375,6 @@ void arm_smmu_sva_unbind(struct iommu_sva *handle) if (refcount_dec_and_test(&bond->refs)) { list_del(&bond->list); arm_smmu_mmu_notifier_put(bond->smmu_mn); - iommu_sva_free_pasid(bond->mm); kfree(bond); } mutex_unlock(&sva_lock); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 92fea3fbbb11..ef03b2176bbd 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4781,7 +4781,7 @@ attach_failed: link_failed: spin_unlock_irqrestore(&device_domain_lock, flags); if (list_empty(&domain->subdevices) && domain->default_pasid > 0) - ioasid_put(domain->default_pasid); + ioasid_free(domain->default_pasid); return ret; } @@ -4811,7 +4811,7 @@ static void aux_domain_remove_dev(struct dmar_domain *domain, spin_unlock_irqrestore(&device_domain_lock, flags); if (list_empty(&domain->subdevices) && domain->default_pasid > 0) - ioasid_put(domain->default_pasid); + ioasid_free(domain->default_pasid); } static int prepare_domain_attach_device(struct iommu_domain *domain, diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 5b5d69b04fcc..51ac2096b3da 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -514,11 +514,6 @@ static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm, return iommu_sva_alloc_pasid(mm, PASID_MIN, max_pasid - 1); } -static void intel_svm_free_pasid(struct mm_struct *mm) -{ - iommu_sva_free_pasid(mm); -} - static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev, struct mm_struct *mm, @@ -662,8 +657,6 @@ static int intel_svm_unbind_mm(struct device *dev, u32 pasid) kfree(svm); } } - /* Drop a PASID reference and free it if no reference. */ - intel_svm_free_pasid(mm); } out: return ret; @@ -1047,8 +1040,6 @@ struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, void } sva = intel_svm_bind_mm(iommu, dev, mm, flags); - if (IS_ERR_OR_NULL(sva)) - intel_svm_free_pasid(mm); mutex_unlock(&pasid_mutex); return sva; diff --git a/drivers/iommu/ioasid.c b/drivers/iommu/ioasid.c index 06fee7416816..a786c034907c 100644 --- a/drivers/iommu/ioasid.c +++ b/drivers/iommu/ioasid.c @@ -2,7 +2,7 @@ /* * I/O Address Space ID allocator. There is one global IOASID space, split into * subsets. Users create a subset with DECLARE_IOASID_SET, then allocate and - * free IOASIDs with ioasid_alloc and ioasid_put. + * free IOASIDs with ioasid_alloc() and ioasid_free(). */ #include #include @@ -15,7 +15,6 @@ struct ioasid_data { struct ioasid_set *set; void *private; struct rcu_head rcu; - refcount_t refs; }; /* @@ -315,7 +314,6 @@ ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, data->set = set; data->private = private; - refcount_set(&data->refs, 1); /* * Custom allocator needs allocator data to perform platform specific @@ -348,35 +346,11 @@ exit_free: EXPORT_SYMBOL_GPL(ioasid_alloc); /** - * ioasid_get - obtain a reference to the IOASID - * @ioasid: the ID to get - */ -void ioasid_get(ioasid_t ioasid) -{ - struct ioasid_data *ioasid_data; - - spin_lock(&ioasid_allocator_lock); - ioasid_data = xa_load(&active_allocator->xa, ioasid); - if (ioasid_data) - refcount_inc(&ioasid_data->refs); - else - WARN_ON(1); - spin_unlock(&ioasid_allocator_lock); -} -EXPORT_SYMBOL_GPL(ioasid_get); - -/** - * ioasid_put - Release a reference to an ioasid + * ioasid_free - Free an ioasid * @ioasid: the ID to remove - * - * Put a reference to the IOASID, free it when the number of references drops to - * zero. - * - * Return: %true if the IOASID was freed, %false otherwise. */ -bool ioasid_put(ioasid_t ioasid) +void ioasid_free(ioasid_t ioasid) { - bool free = false; struct ioasid_data *ioasid_data; spin_lock(&ioasid_allocator_lock); @@ -386,10 +360,6 @@ bool ioasid_put(ioasid_t ioasid) goto exit_unlock; } - free = refcount_dec_and_test(&ioasid_data->refs); - if (!free) - goto exit_unlock; - active_allocator->ops->free(ioasid, active_allocator->ops->pdata); /* Custom allocator needs additional steps to free the xa element */ if (active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) { @@ -399,9 +369,8 @@ bool ioasid_put(ioasid_t ioasid) exit_unlock: spin_unlock(&ioasid_allocator_lock); - return free; } -EXPORT_SYMBOL_GPL(ioasid_put); +EXPORT_SYMBOL_GPL(ioasid_free); /** * ioasid_find - Find IOASID data diff --git a/drivers/iommu/iommu-sva-lib.c b/drivers/iommu/iommu-sva-lib.c index bd41405d34e9..106506143896 100644 --- a/drivers/iommu/iommu-sva-lib.c +++ b/drivers/iommu/iommu-sva-lib.c @@ -18,8 +18,7 @@ static DECLARE_IOASID_SET(iommu_sva_pasid); * * Try to allocate a PASID for this mm, or take a reference to the existing one * provided it fits within the [@min, @max] range. On success the PASID is - * available in mm->pasid, and must be released with iommu_sva_free_pasid(). - * @min must be greater than 0, because 0 indicates an unused mm->pasid. + * available in mm->pasid and will be available for the lifetime of the mm. * * Returns 0 on success and < 0 on error. */ @@ -33,38 +32,24 @@ int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max) return -EINVAL; mutex_lock(&iommu_sva_lock); - if (mm->pasid) { - if (mm->pasid >= min && mm->pasid <= max) - ioasid_get(mm->pasid); - else + /* Is a PASID already associated with this mm? */ + if (pasid_valid(mm->pasid)) { + if (mm->pasid < min || mm->pasid >= max) ret = -EOVERFLOW; - } else { - pasid = ioasid_alloc(&iommu_sva_pasid, min, max, mm); - if (pasid == INVALID_IOASID) - ret = -ENOMEM; - else - mm->pasid = pasid; + goto out; } + + pasid = ioasid_alloc(&iommu_sva_pasid, min, max, mm); + if (!pasid_valid(pasid)) + ret = -ENOMEM; + else + mm_pasid_set(mm, pasid); +out: mutex_unlock(&iommu_sva_lock); return ret; } EXPORT_SYMBOL_GPL(iommu_sva_alloc_pasid); -/** - * iommu_sva_free_pasid - Release the mm's PASID - * @mm: the mm - * - * Drop one reference to a PASID allocated with iommu_sva_alloc_pasid() - */ -void iommu_sva_free_pasid(struct mm_struct *mm) -{ - mutex_lock(&iommu_sva_lock); - if (ioasid_put(mm->pasid)) - mm->pasid = 0; - mutex_unlock(&iommu_sva_lock); -} -EXPORT_SYMBOL_GPL(iommu_sva_free_pasid); - /* ioasid_find getter() requires a void * argument */ static bool __mmget_not_zero(void *mm) { diff --git a/drivers/iommu/iommu-sva-lib.h b/drivers/iommu/iommu-sva-lib.h index 95dc3ebc1928..8909ea1094e3 100644 --- a/drivers/iommu/iommu-sva-lib.h +++ b/drivers/iommu/iommu-sva-lib.h @@ -9,7 +9,6 @@ #include int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max); -void iommu_sva_free_pasid(struct mm_struct *mm); struct mm_struct *iommu_sva_find(ioasid_t pasid); /* I/O Page fault */ diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index 2237f64dbaae..af1c9d62e642 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -34,8 +34,7 @@ struct ioasid_allocator_ops { #if IS_ENABLED(CONFIG_IOASID) ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, void *private); -void ioasid_get(ioasid_t ioasid); -bool ioasid_put(ioasid_t ioasid); +void ioasid_free(ioasid_t ioasid); void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, bool (*getter)(void *)); int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); @@ -53,14 +52,7 @@ static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, return INVALID_IOASID; } -static inline void ioasid_get(ioasid_t ioasid) -{ -} - -static inline bool ioasid_put(ioasid_t ioasid) -{ - return false; -} +static inline void ioasid_free(ioasid_t ioasid) { } static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, bool (*getter)(void *)) diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index c74d1edbac2f..a80356e9dc69 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -439,8 +439,24 @@ static inline void mm_pasid_init(struct mm_struct *mm) { mm->pasid = INVALID_IOASID; } + +/* Associate a PASID with an mm_struct: */ +static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) +{ + mm->pasid = pasid; +} + +static inline void mm_pasid_drop(struct mm_struct *mm) +{ + if (pasid_valid(mm->pasid)) { + ioasid_free(mm->pasid); + mm->pasid = INVALID_IOASID; + } +} #else static inline void mm_pasid_init(struct mm_struct *mm) {} +static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) {} +static inline void mm_pasid_drop(struct mm_struct *mm) {} #endif #endif /* _LINUX_SCHED_MM_H */ diff --git a/kernel/fork.c b/kernel/fork.c index deacd2c17a7f..c03c6682464c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1115,6 +1115,7 @@ static inline void __mmput(struct mm_struct *mm) } if (mm->binfmt) module_put(mm->binfmt->module); + mm_pasid_drop(mm); mmdrop(mm); } -- cgit v1.2.3 From 04d4e665a60902cf36e7ad39af1179cb5df542ad Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 7 Feb 2022 16:59:06 +0100 Subject: sched/isolation: Use single feature type while referring to housekeeping cpumask Refer to housekeeping APIs using single feature types instead of flags. This prevents from passing multiple isolation features at once to housekeeping interfaces, which soon won't be possible anymore as each isolation features will have their own cpumask. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Juri Lelli Reviewed-by: Phil Auld Link: https://lore.kernel.org/r/20220207155910.527133-5-frederic@kernel.org --- arch/x86/kernel/cpu/aperfmperf.c | 6 +++--- arch/x86/kvm/x86.c | 2 +- drivers/base/cpu.c | 2 +- drivers/pci/pci-driver.c | 4 ++-- include/linux/sched/isolation.h | 43 ++++++++++++++++++++-------------------- kernel/cgroup/cpuset.c | 6 +++--- kernel/cpu.c | 4 ++-- kernel/irq/cpuhotplug.c | 4 ++-- kernel/irq/manage.c | 4 ++-- kernel/kthread.c | 4 ++-- kernel/rcu/tasks.h | 2 +- kernel/rcu/tree_plugin.h | 6 +++--- kernel/sched/core.c | 12 +++++------ kernel/sched/fair.c | 10 +++++----- kernel/sched/isolation.c | 32 ++++++++++++++++++++---------- kernel/sched/topology.c | 8 ++++---- kernel/watchdog.c | 2 +- kernel/workqueue.c | 4 ++-- net/core/net-sysfs.c | 4 ++-- 19 files changed, 86 insertions(+), 73 deletions(-) (limited to 'include/linux/sched') diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index 22911deacb6e..9ca008f9e9b1 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -91,7 +91,7 @@ unsigned int aperfmperf_get_khz(int cpu) if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) return 0; - if (!housekeeping_cpu(cpu, HK_FLAG_MISC)) + if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) return 0; if (rcu_is_idle_cpu(cpu)) @@ -114,7 +114,7 @@ void arch_freq_prepare_all(void) return; for_each_online_cpu(cpu) { - if (!housekeeping_cpu(cpu, HK_FLAG_MISC)) + if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) continue; if (rcu_is_idle_cpu(cpu)) continue; /* Idle CPUs are completely uninteresting. */ @@ -136,7 +136,7 @@ unsigned int arch_freq_get_on_cpu(int cpu) if (!boot_cpu_has(X86_FEATURE_APERFMPERF)) return 0; - if (!housekeeping_cpu(cpu, HK_FLAG_MISC)) + if (!housekeeping_cpu(cpu, HK_TYPE_MISC)) return 0; if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true)) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9e43d756312f..02a7ac1b6bb2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8769,7 +8769,7 @@ int kvm_arch_init(void *opaque) } if (pi_inject_timer == -1) - pi_inject_timer = housekeeping_enabled(HK_FLAG_TIMER); + pi_inject_timer = housekeeping_enabled(HK_TYPE_TIMER); #ifdef CONFIG_X86_64 pvclock_gtod_register_notifier(&pvclock_gtod_notifier); diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 5fc258073bc7..2ef23fce0860 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -275,7 +275,7 @@ static ssize_t print_cpus_isolated(struct device *dev, return -ENOMEM; cpumask_andnot(isolated, cpu_possible_mask, - housekeeping_cpumask(HK_FLAG_DOMAIN)); + housekeeping_cpumask(HK_TYPE_DOMAIN)); len = sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(isolated)); free_cpumask_var(isolated); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 4a5792c82d08..f61c40a47891 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -377,8 +377,8 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev, goto out; } cpumask_and(wq_domain_mask, - housekeeping_cpumask(HK_FLAG_WQ), - housekeeping_cpumask(HK_FLAG_DOMAIN)); + housekeeping_cpumask(HK_TYPE_WQ), + housekeeping_cpumask(HK_TYPE_DOMAIN)); cpu = cpumask_any_and(cpumask_of_node(node), wq_domain_mask); diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index cc9f393e2a70..8c15abd67aed 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -5,54 +5,55 @@ #include #include -enum hk_flags { - HK_FLAG_TIMER = 1, - HK_FLAG_RCU = (1 << 1), - HK_FLAG_MISC = (1 << 2), - HK_FLAG_SCHED = (1 << 3), - HK_FLAG_TICK = (1 << 4), - HK_FLAG_DOMAIN = (1 << 5), - HK_FLAG_WQ = (1 << 6), - HK_FLAG_MANAGED_IRQ = (1 << 7), - HK_FLAG_KTHREAD = (1 << 8), +enum hk_type { + HK_TYPE_TIMER, + HK_TYPE_RCU, + HK_TYPE_MISC, + HK_TYPE_SCHED, + HK_TYPE_TICK, + HK_TYPE_DOMAIN, + HK_TYPE_WQ, + HK_TYPE_MANAGED_IRQ, + HK_TYPE_KTHREAD, + HK_TYPE_MAX }; #ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE(housekeeping_overridden); -extern int housekeeping_any_cpu(enum hk_flags flags); -extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags); -extern bool housekeeping_enabled(enum hk_flags flags); -extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags); -extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags); +extern int housekeeping_any_cpu(enum hk_type type); +extern const struct cpumask *housekeeping_cpumask(enum hk_type type); +extern bool housekeeping_enabled(enum hk_type type); +extern void housekeeping_affine(struct task_struct *t, enum hk_type type); +extern bool housekeeping_test_cpu(int cpu, enum hk_type type); extern void __init housekeeping_init(void); #else -static inline int housekeeping_any_cpu(enum hk_flags flags) +static inline int housekeeping_any_cpu(enum hk_type type) { return smp_processor_id(); } -static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags) +static inline const struct cpumask *housekeeping_cpumask(enum hk_type type) { return cpu_possible_mask; } -static inline bool housekeeping_enabled(enum hk_flags flags) +static inline bool housekeeping_enabled(enum hk_type type) { return false; } static inline void housekeeping_affine(struct task_struct *t, - enum hk_flags flags) { } + enum hk_type type) { } static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ -static inline bool housekeeping_cpu(int cpu, enum hk_flags flags) +static inline bool housekeeping_cpu(int cpu, enum hk_type type) { #ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely(&housekeeping_overridden)) - return housekeeping_test_cpu(cpu, flags); + return housekeeping_test_cpu(cpu, type); #endif return true; } diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index dc653ab26e50..e4e18a2cb404 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -803,7 +803,7 @@ static int generate_sched_domains(cpumask_var_t **domains, update_domain_attr_tree(dattr, &top_cpuset); } cpumask_and(doms[0], top_cpuset.effective_cpus, - housekeeping_cpumask(HK_FLAG_DOMAIN)); + housekeeping_cpumask(HK_TYPE_DOMAIN)); goto done; } @@ -833,7 +833,7 @@ static int generate_sched_domains(cpumask_var_t **domains, if (!cpumask_empty(cp->cpus_allowed) && !(is_sched_load_balance(cp) && cpumask_intersects(cp->cpus_allowed, - housekeeping_cpumask(HK_FLAG_DOMAIN)))) + housekeeping_cpumask(HK_TYPE_DOMAIN)))) continue; if (root_load_balance && @@ -922,7 +922,7 @@ restart: if (apn == b->pn) { cpumask_or(dp, dp, b->effective_cpus); - cpumask_and(dp, dp, housekeeping_cpumask(HK_FLAG_DOMAIN)); + cpumask_and(dp, dp, housekeeping_cpumask(HK_TYPE_DOMAIN)); if (dattr) update_domain_attr_tree(dattr + nslot, b); diff --git a/kernel/cpu.c b/kernel/cpu.c index 407a2568f35e..f39eb0b52dfe 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1488,8 +1488,8 @@ int freeze_secondary_cpus(int primary) cpu_maps_update_begin(); if (primary == -1) { primary = cpumask_first(cpu_online_mask); - if (!housekeeping_cpu(primary, HK_FLAG_TIMER)) - primary = housekeeping_any_cpu(HK_FLAG_TIMER); + if (!housekeeping_cpu(primary, HK_TYPE_TIMER)) + primary = housekeeping_any_cpu(HK_TYPE_TIMER); } else { if (!cpu_online(primary)) primary = cpumask_first(cpu_online_mask); diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 39a41c56ad4f..1ed2b1739363 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -176,10 +176,10 @@ static bool hk_should_isolate(struct irq_data *data, unsigned int cpu) { const struct cpumask *hk_mask; - if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) + if (!housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) return false; - hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask)) return false; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index f23ffd30385b..c03f71d5ec10 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -247,13 +247,13 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, * online. */ if (irqd_affinity_is_managed(data) && - housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) { + housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) { const struct cpumask *hk_mask, *prog_mask; static DEFINE_RAW_SPINLOCK(tmp_mask_lock); static struct cpumask tmp_mask; - hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); raw_spin_lock(&tmp_mask_lock); cpumask_and(&tmp_mask, mask, hk_mask); diff --git a/kernel/kthread.c b/kernel/kthread.c index 38c6dd822da8..d100d5a15b38 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -356,7 +356,7 @@ static int kthread(void *_create) * back to default in case they have been changed. */ sched_setscheduler_nocheck(current, SCHED_NORMAL, ¶m); - set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_KTHREAD)); + set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_KTHREAD)); /* OK, tell user we're spawned, wait for stop or wakeup */ __set_current_state(TASK_UNINTERRUPTIBLE); @@ -722,7 +722,7 @@ int kthreadd(void *unused) /* Setup a clean context for our children to inherit. */ set_task_comm(tsk, "kthreadd"); ignore_signals(tsk); - set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_FLAG_KTHREAD)); + set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_TYPE_KTHREAD)); set_mems_allowed(node_states[N_MEMORY]); current->flags |= PF_NOFREEZE; diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 84f1d91604cc..6093b200dff7 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -492,7 +492,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) struct rcu_tasks *rtp = arg; /* Run on housekeeping CPUs by default. Sysadm can move if desired. */ - housekeeping_affine(current, HK_FLAG_RCU); + housekeeping_affine(current, HK_TYPE_RCU); WRITE_ONCE(rtp->kthread_ptr, current); // Let GPs start! /* diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index c5b45c2f68a1..65f25a32f6d7 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1214,9 +1214,9 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) if ((mask & leaf_node_cpu_bit(rnp, cpu)) && cpu != outgoingcpu) cpumask_set_cpu(cpu, cm); - cpumask_and(cm, cm, housekeeping_cpumask(HK_FLAG_RCU)); + cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU)); if (cpumask_weight(cm) == 0) - cpumask_copy(cm, housekeeping_cpumask(HK_FLAG_RCU)); + cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU)); set_cpus_allowed_ptr(t, cm); free_cpumask_var(cm); } @@ -1291,7 +1291,7 @@ static void rcu_bind_gp_kthread(void) { if (!tick_nohz_full_enabled()) return; - housekeeping_affine(current, HK_FLAG_RCU); + housekeeping_affine(current, HK_TYPE_RCU); } /* Record the current task on dyntick-idle entry. */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b2226922206d..1e08b02e0cd5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1025,13 +1025,13 @@ int get_nohz_timer_target(void) struct sched_domain *sd; const struct cpumask *hk_mask; - if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) { + if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) { if (!idle_cpu(cpu)) return cpu; default_cpu = cpu; } - hk_mask = housekeeping_cpumask(HK_FLAG_TIMER); + hk_mask = housekeeping_cpumask(HK_TYPE_TIMER); rcu_read_lock(); for_each_domain(cpu, sd) { @@ -1047,7 +1047,7 @@ int get_nohz_timer_target(void) } if (default_cpu == -1) - default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER); + default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER); cpu = default_cpu; unlock: rcu_read_unlock(); @@ -5371,7 +5371,7 @@ static void sched_tick_start(int cpu) int os; struct tick_work *twork; - if (housekeeping_cpu(cpu, HK_FLAG_TICK)) + if (housekeeping_cpu(cpu, HK_TYPE_TICK)) return; WARN_ON_ONCE(!tick_work_cpu); @@ -5392,7 +5392,7 @@ static void sched_tick_stop(int cpu) struct tick_work *twork; int os; - if (housekeeping_cpu(cpu, HK_FLAG_TICK)) + if (housekeeping_cpu(cpu, HK_TYPE_TICK)) return; WARN_ON_ONCE(!tick_work_cpu); @@ -9251,7 +9251,7 @@ void __init sched_init_smp(void) mutex_unlock(&sched_domains_mutex); /* Move init over to a non-isolated CPU */ - if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0) + if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_DOMAIN)) < 0) BUG(); current->flags &= ~PF_NO_SETAFFINITY; sched_init_granularity(); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 11a72e1b3b2c..dcbd3110c687 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -10337,7 +10337,7 @@ static inline int on_null_domain(struct rq *rq) * - When one of the busy CPUs notice that there may be an idle rebalancing * needed, they will kick the idle load balancer, which then does idle * load balancing for all the idle CPUs. - * - HK_FLAG_MISC CPUs are used for this task, because HK_FLAG_SCHED not set + * - HK_TYPE_MISC CPUs are used for this task, because HK_TYPE_SCHED not set * anywhere yet. */ @@ -10346,7 +10346,7 @@ static inline int find_new_ilb(void) int ilb; const struct cpumask *hk_mask; - hk_mask = housekeeping_cpumask(HK_FLAG_MISC); + hk_mask = housekeeping_cpumask(HK_TYPE_MISC); for_each_cpu_and(ilb, nohz.idle_cpus_mask, hk_mask) { @@ -10362,7 +10362,7 @@ static inline int find_new_ilb(void) /* * Kick a CPU to do the nohz balancing, if it is time for it. We pick any - * idle CPU in the HK_FLAG_MISC housekeeping set (if there is one). + * idle CPU in the HK_TYPE_MISC housekeeping set (if there is one). */ static void kick_ilb(unsigned int flags) { @@ -10575,7 +10575,7 @@ void nohz_balance_enter_idle(int cpu) return; /* Spare idle load balancing on CPUs that don't want to be disturbed: */ - if (!housekeeping_cpu(cpu, HK_FLAG_SCHED)) + if (!housekeeping_cpu(cpu, HK_TYPE_SCHED)) return; /* @@ -10791,7 +10791,7 @@ static void nohz_newidle_balance(struct rq *this_rq) * This CPU doesn't want to be disturbed by scheduler * housekeeping */ - if (!housekeeping_cpu(this_cpu, HK_FLAG_SCHED)) + if (!housekeeping_cpu(this_cpu, HK_TYPE_SCHED)) return; /* Will wake up very soon. No time for doing anything else*/ diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 7f06eaf12818..a735d9e229dd 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -9,23 +9,35 @@ */ #include "sched.h" +enum hk_flags { + HK_FLAG_TIMER = BIT(HK_TYPE_TIMER), + HK_FLAG_RCU = BIT(HK_TYPE_RCU), + HK_FLAG_MISC = BIT(HK_TYPE_MISC), + HK_FLAG_SCHED = BIT(HK_TYPE_SCHED), + HK_FLAG_TICK = BIT(HK_TYPE_TICK), + HK_FLAG_DOMAIN = BIT(HK_TYPE_DOMAIN), + HK_FLAG_WQ = BIT(HK_TYPE_WQ), + HK_FLAG_MANAGED_IRQ = BIT(HK_TYPE_MANAGED_IRQ), + HK_FLAG_KTHREAD = BIT(HK_TYPE_KTHREAD), +}; + DEFINE_STATIC_KEY_FALSE(housekeeping_overridden); EXPORT_SYMBOL_GPL(housekeeping_overridden); static cpumask_var_t housekeeping_mask; static unsigned int housekeeping_flags; -bool housekeeping_enabled(enum hk_flags flags) +bool housekeeping_enabled(enum hk_type type) { - return !!(housekeeping_flags & flags); + return !!(housekeeping_flags & BIT(type)); } EXPORT_SYMBOL_GPL(housekeeping_enabled); -int housekeeping_any_cpu(enum hk_flags flags) +int housekeeping_any_cpu(enum hk_type type) { int cpu; if (static_branch_unlikely(&housekeeping_overridden)) { - if (housekeeping_flags & flags) { + if (housekeeping_flags & BIT(type)) { cpu = sched_numa_find_closest(housekeeping_mask, smp_processor_id()); if (cpu < nr_cpu_ids) return cpu; @@ -37,27 +49,27 @@ int housekeeping_any_cpu(enum hk_flags flags) } EXPORT_SYMBOL_GPL(housekeeping_any_cpu); -const struct cpumask *housekeeping_cpumask(enum hk_flags flags) +const struct cpumask *housekeeping_cpumask(enum hk_type type) { if (static_branch_unlikely(&housekeeping_overridden)) - if (housekeeping_flags & flags) + if (housekeeping_flags & BIT(type)) return housekeeping_mask; return cpu_possible_mask; } EXPORT_SYMBOL_GPL(housekeeping_cpumask); -void housekeeping_affine(struct task_struct *t, enum hk_flags flags) +void housekeeping_affine(struct task_struct *t, enum hk_type type) { if (static_branch_unlikely(&housekeeping_overridden)) - if (housekeeping_flags & flags) + if (housekeeping_flags & BIT(type)) set_cpus_allowed_ptr(t, housekeeping_mask); } EXPORT_SYMBOL_GPL(housekeeping_affine); -bool housekeeping_test_cpu(int cpu, enum hk_flags flags) +bool housekeeping_test_cpu(int cpu, enum hk_type type) { if (static_branch_unlikely(&housekeeping_overridden)) - if (housekeeping_flags & flags) + if (housekeeping_flags & BIT(type)) return cpumask_test_cpu(cpu, housekeeping_mask); return true; } diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 5db322c9cb3f..32841c6741d1 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1366,7 +1366,7 @@ static void asym_cpu_capacity_scan(void) list_for_each_entry(entry, &asym_cap_list, link) cpumask_clear(cpu_capacity_span(entry)); - for_each_cpu_and(cpu, cpu_possible_mask, housekeeping_cpumask(HK_FLAG_DOMAIN)) + for_each_cpu_and(cpu, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)) asym_cpu_capacity_update_data(cpu); list_for_each_entry_safe(entry, next, &asym_cap_list, link) { @@ -2440,7 +2440,7 @@ int sched_init_domains(const struct cpumask *cpu_map) doms_cur = alloc_sched_domains(ndoms_cur); if (!doms_cur) doms_cur = &fallback_doms; - cpumask_and(doms_cur[0], cpu_map, housekeeping_cpumask(HK_FLAG_DOMAIN)); + cpumask_and(doms_cur[0], cpu_map, housekeeping_cpumask(HK_TYPE_DOMAIN)); err = build_sched_domains(doms_cur[0], NULL); return err; @@ -2529,7 +2529,7 @@ void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[], if (doms_new) { n = 1; cpumask_and(doms_new[0], cpu_active_mask, - housekeeping_cpumask(HK_FLAG_DOMAIN)); + housekeeping_cpumask(HK_TYPE_DOMAIN)); } } else { n = ndoms_new; @@ -2564,7 +2564,7 @@ match1: n = 0; doms_new = &fallback_doms; cpumask_and(doms_new[0], cpu_active_mask, - housekeeping_cpumask(HK_FLAG_DOMAIN)); + housekeeping_cpumask(HK_TYPE_DOMAIN)); } /* Build new domains: */ diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 99afb88d2e85..9166220457bc 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -848,7 +848,7 @@ void __init lockup_detector_init(void) pr_info("Disabling watchdog on nohz_full cores by default\n"); cpumask_copy(&watchdog_cpumask, - housekeeping_cpumask(HK_FLAG_TIMER)); + housekeeping_cpumask(HK_TYPE_TIMER)); if (!watchdog_nmi_probe()) nmi_watchdog_available = true; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 61ed310621ea..52e9abbb7759 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -6011,8 +6011,8 @@ void __init workqueue_init_early(void) BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); - cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_FLAG_WQ)); - cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_FLAG_DOMAIN)); + cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_WQ)); + cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_DOMAIN)); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index ed8da7b8d35b..7ceb3460161b 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -839,8 +839,8 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, } if (!cpumask_empty(mask)) { - cpumask_and(mask, mask, housekeeping_cpumask(HK_FLAG_DOMAIN)); - cpumask_and(mask, mask, housekeeping_cpumask(HK_FLAG_WQ)); + cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); + cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ)); if (cpumask_empty(mask)) { free_cpumask_var(mask); return -EINVAL; -- cgit v1.2.3 From 1a03d3f13ffe5dd24142d6db629e72c11b704d99 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 17 Feb 2022 11:24:04 +0100 Subject: fork: Move task stack accounting to do_exit() There is no need to perform the stack accounting of the outgoing task in its final schedule() invocation which happens with preemption disabled. The task is leaving, the resources will be freed and the accounting can happen in do_exit() before the actual schedule invocation which frees the stack memory. Move the accounting of the stack memory from release_task_stack() to exit_task_stack_account() which then can be invoked from do_exit(). Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: Andy Lutomirski Link: https://lore.kernel.org/r/20220217102406.3697941-7-bigeasy@linutronix.de --- include/linux/sched/task_stack.h | 2 ++ kernel/exit.c | 1 + kernel/fork.c | 35 +++++++++++++++++++++++------------ 3 files changed, 26 insertions(+), 12 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index d10150587d81..892562ebbd3a 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -79,6 +79,8 @@ static inline void *try_get_task_stack(struct task_struct *tsk) static inline void put_task_stack(struct task_struct *tsk) {} #endif +void exit_task_stack_account(struct task_struct *tsk); + #define task_stack_end_corrupted(task) \ (*(end_of_stack(task)) != STACK_END_MAGIC) diff --git a/kernel/exit.c b/kernel/exit.c index b00a25bb4ab9..c303cffe7fdb 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -845,6 +845,7 @@ void __noreturn do_exit(long code) put_page(tsk->task_frag.page); validate_creds_for_do_exit(tsk); + exit_task_stack_account(tsk); check_stack_usage(); preempt_disable(); diff --git a/kernel/fork.c b/kernel/fork.c index ac63e7fa8816..25828127db8d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -211,9 +211,8 @@ static int free_vm_stack_cache(unsigned int cpu) return 0; } -static int memcg_charge_kernel_stack(struct task_struct *tsk) +static int memcg_charge_kernel_stack(struct vm_struct *vm) { - struct vm_struct *vm = task_stack_vm_area(tsk); int i; int ret; @@ -239,6 +238,7 @@ err: static int alloc_thread_stack_node(struct task_struct *tsk, int node) { + struct vm_struct *vm; void *stack; int i; @@ -256,7 +256,7 @@ static int alloc_thread_stack_node(struct task_struct *tsk, int node) /* Clear stale pointers from reused stack. */ memset(s->addr, 0, THREAD_SIZE); - if (memcg_charge_kernel_stack(tsk)) { + if (memcg_charge_kernel_stack(s)) { vfree(s->addr); return -ENOMEM; } @@ -279,7 +279,8 @@ static int alloc_thread_stack_node(struct task_struct *tsk, int node) if (!stack) return -ENOMEM; - if (memcg_charge_kernel_stack(tsk)) { + vm = find_vm_area(stack); + if (memcg_charge_kernel_stack(vm)) { vfree(stack); return -ENOMEM; } @@ -288,19 +289,15 @@ static int alloc_thread_stack_node(struct task_struct *tsk, int node) * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ - tsk->stack_vm_area = find_vm_area(stack); + tsk->stack_vm_area = vm; tsk->stack = stack; return 0; } static void free_thread_stack(struct task_struct *tsk) { - struct vm_struct *vm = task_stack_vm_area(tsk); int i; - for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) - memcg_kmem_uncharge_page(vm->pages[i], 0); - for (i = 0; i < NR_CACHED_STACKS; i++) { if (this_cpu_cmpxchg(cached_stacks[i], NULL, tsk->stack_vm_area) != NULL) @@ -454,12 +451,25 @@ static void account_kernel_stack(struct task_struct *tsk, int account) } } +void exit_task_stack_account(struct task_struct *tsk) +{ + account_kernel_stack(tsk, -1); + + if (IS_ENABLED(CONFIG_VMAP_STACK)) { + struct vm_struct *vm; + int i; + + vm = task_stack_vm_area(tsk); + for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) + memcg_kmem_uncharge_page(vm->pages[i], 0); + } +} + static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD)) return; /* Better to leak the stack than to free prematurely */ - account_kernel_stack(tsk, -1); free_thread_stack(tsk); } @@ -918,6 +928,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) #ifdef CONFIG_THREAD_INFO_IN_TASK refcount_set(&tsk->stack_refcount, 1); #endif + account_kernel_stack(tsk, 1); err = scs_prepare(tsk, node); if (err) @@ -961,8 +972,6 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->wake_q.next = NULL; tsk->worker_private = NULL; - account_kernel_stack(tsk, 1); - kcov_task_init(tsk); kmap_local_fork(tsk); @@ -981,6 +990,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) return tsk; free_stack: + exit_task_stack_account(tsk); free_thread_stack(tsk); free_tsk: free_task_struct(tsk); @@ -2459,6 +2469,7 @@ bad_fork_cleanup_count: exit_creds(p); bad_fork_free: WRITE_ONCE(p->__state, TASK_DEAD); + exit_task_stack_account(p); put_task_stack(p); delayed_free_task(p); fork_out: -- cgit v1.2.3 From 669f45f19cf7feea7066dce86a0ce89dfc8a2065 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 22 Feb 2022 13:23:59 +0100 Subject: sched/headers: Add initial new headers as identity mappings This allows code sharing between fast-headers tree and the vanilla scheduler tree. Signed-off-by: Ingo Molnar Reviewed-by: Peter Zijlstra --- arch/arm64/include/asm/paravirt_api_clock.h | 1 + arch/x86/include/asm/paravirt_api_clock.h | 1 + include/linux/cgroup_api.h | 1 + include/linux/cpumask_api.h | 1 + include/linux/fs_api.h | 1 + include/linux/gfp_api.h | 1 + include/linux/hashtable_api.h | 1 + include/linux/hrtimer_api.h | 1 + include/linux/kobject_api.h | 1 + include/linux/kref_api.h | 1 + include/linux/ktime_api.h | 1 + include/linux/llist_api.h | 1 + include/linux/lockdep_api.h | 1 + include/linux/mm_api.h | 1 + include/linux/mutex_api.h | 1 + include/linux/perf_event_api.h | 1 + include/linux/pgtable_api.h | 1 + include/linux/ptrace_api.h | 1 + include/linux/rcuwait_api.h | 1 + include/linux/refcount_api.h | 1 + include/linux/sched/affinity.h | 1 + include/linux/sched/cond_resched.h | 1 + include/linux/sched/posix-timers.h | 1 + include/linux/sched/rseq_api.h | 1 + include/linux/sched/task_flags.h | 1 + include/linux/sched/thread_info_api.h | 1 + include/linux/seqlock_api.h | 1 + include/linux/softirq.h | 1 + include/linux/spinlock_api.h | 1 + include/linux/swait_api.h | 1 + include/linux/syscalls_api.h | 1 + include/linux/u64_stats_sync_api.h | 1 + include/linux/wait_api.h | 1 + include/linux/workqueue_api.h | 1 + 34 files changed, 34 insertions(+) create mode 100644 arch/arm64/include/asm/paravirt_api_clock.h create mode 100644 arch/x86/include/asm/paravirt_api_clock.h create mode 100644 include/linux/cgroup_api.h create mode 100644 include/linux/cpumask_api.h create mode 100644 include/linux/fs_api.h create mode 100644 include/linux/gfp_api.h create mode 100644 include/linux/hashtable_api.h create mode 100644 include/linux/hrtimer_api.h create mode 100644 include/linux/kobject_api.h create mode 100644 include/linux/kref_api.h create mode 100644 include/linux/ktime_api.h create mode 100644 include/linux/llist_api.h create mode 100644 include/linux/lockdep_api.h create mode 100644 include/linux/mm_api.h create mode 100644 include/linux/mutex_api.h create mode 100644 include/linux/perf_event_api.h create mode 100644 include/linux/pgtable_api.h create mode 100644 include/linux/ptrace_api.h create mode 100644 include/linux/rcuwait_api.h create mode 100644 include/linux/refcount_api.h create mode 100644 include/linux/sched/affinity.h create mode 100644 include/linux/sched/cond_resched.h create mode 100644 include/linux/sched/posix-timers.h create mode 100644 include/linux/sched/rseq_api.h create mode 100644 include/linux/sched/task_flags.h create mode 100644 include/linux/sched/thread_info_api.h create mode 100644 include/linux/seqlock_api.h create mode 100644 include/linux/softirq.h create mode 100644 include/linux/spinlock_api.h create mode 100644 include/linux/swait_api.h create mode 100644 include/linux/syscalls_api.h create mode 100644 include/linux/u64_stats_sync_api.h create mode 100644 include/linux/wait_api.h create mode 100644 include/linux/workqueue_api.h (limited to 'include/linux/sched') diff --git a/arch/arm64/include/asm/paravirt_api_clock.h b/arch/arm64/include/asm/paravirt_api_clock.h new file mode 100644 index 000000000000..65ac7cee0dad --- /dev/null +++ b/arch/arm64/include/asm/paravirt_api_clock.h @@ -0,0 +1 @@ +#include diff --git a/arch/x86/include/asm/paravirt_api_clock.h b/arch/x86/include/asm/paravirt_api_clock.h new file mode 100644 index 000000000000..65ac7cee0dad --- /dev/null +++ b/arch/x86/include/asm/paravirt_api_clock.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/cgroup_api.h b/include/linux/cgroup_api.h new file mode 100644 index 000000000000..d0cfe8025111 --- /dev/null +++ b/include/linux/cgroup_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/cpumask_api.h b/include/linux/cpumask_api.h new file mode 100644 index 000000000000..83bd3ebe82b0 --- /dev/null +++ b/include/linux/cpumask_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/fs_api.h b/include/linux/fs_api.h new file mode 100644 index 000000000000..83be38d6d413 --- /dev/null +++ b/include/linux/fs_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/gfp_api.h b/include/linux/gfp_api.h new file mode 100644 index 000000000000..5a05a2764a86 --- /dev/null +++ b/include/linux/gfp_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/hashtable_api.h b/include/linux/hashtable_api.h new file mode 100644 index 000000000000..c268ac2c5c0e --- /dev/null +++ b/include/linux/hashtable_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/hrtimer_api.h b/include/linux/hrtimer_api.h new file mode 100644 index 000000000000..8d9700894468 --- /dev/null +++ b/include/linux/hrtimer_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/kobject_api.h b/include/linux/kobject_api.h new file mode 100644 index 000000000000..6e36a054c2d6 --- /dev/null +++ b/include/linux/kobject_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/kref_api.h b/include/linux/kref_api.h new file mode 100644 index 000000000000..d67e554721d2 --- /dev/null +++ b/include/linux/kref_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/ktime_api.h b/include/linux/ktime_api.h new file mode 100644 index 000000000000..f697d493960f --- /dev/null +++ b/include/linux/ktime_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/llist_api.h b/include/linux/llist_api.h new file mode 100644 index 000000000000..625bec0393a1 --- /dev/null +++ b/include/linux/llist_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/lockdep_api.h b/include/linux/lockdep_api.h new file mode 100644 index 000000000000..907e66979ab2 --- /dev/null +++ b/include/linux/lockdep_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/mm_api.h b/include/linux/mm_api.h new file mode 100644 index 000000000000..a5ace2b198b8 --- /dev/null +++ b/include/linux/mm_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/mutex_api.h b/include/linux/mutex_api.h new file mode 100644 index 000000000000..85ab9491e13e --- /dev/null +++ b/include/linux/mutex_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/perf_event_api.h b/include/linux/perf_event_api.h new file mode 100644 index 000000000000..c2fd6048b790 --- /dev/null +++ b/include/linux/perf_event_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/pgtable_api.h b/include/linux/pgtable_api.h new file mode 100644 index 000000000000..ff367a4ba8c4 --- /dev/null +++ b/include/linux/pgtable_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/ptrace_api.h b/include/linux/ptrace_api.h new file mode 100644 index 000000000000..26e7d275ad8d --- /dev/null +++ b/include/linux/ptrace_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/rcuwait_api.h b/include/linux/rcuwait_api.h new file mode 100644 index 000000000000..f962e28544dd --- /dev/null +++ b/include/linux/rcuwait_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/refcount_api.h b/include/linux/refcount_api.h new file mode 100644 index 000000000000..5f032589f568 --- /dev/null +++ b/include/linux/refcount_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/sched/affinity.h b/include/linux/sched/affinity.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/affinity.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/sched/cond_resched.h b/include/linux/sched/cond_resched.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/cond_resched.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/sched/posix-timers.h b/include/linux/sched/posix-timers.h new file mode 100644 index 000000000000..523a381d6c88 --- /dev/null +++ b/include/linux/sched/posix-timers.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/sched/rseq_api.h b/include/linux/sched/rseq_api.h new file mode 100644 index 000000000000..cf2af72693e1 --- /dev/null +++ b/include/linux/sched/rseq_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/sched/task_flags.h b/include/linux/sched/task_flags.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/task_flags.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/sched/thread_info_api.h b/include/linux/sched/thread_info_api.h new file mode 100644 index 000000000000..2c60fbc16c08 --- /dev/null +++ b/include/linux/sched/thread_info_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/seqlock_api.h b/include/linux/seqlock_api.h new file mode 100644 index 000000000000..be91e7d3b826 --- /dev/null +++ b/include/linux/seqlock_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/softirq.h b/include/linux/softirq.h new file mode 100644 index 000000000000..c73d7dcb4cb5 --- /dev/null +++ b/include/linux/softirq.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/spinlock_api.h b/include/linux/spinlock_api.h new file mode 100644 index 000000000000..6338b27f98df --- /dev/null +++ b/include/linux/spinlock_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/swait_api.h b/include/linux/swait_api.h new file mode 100644 index 000000000000..1eeaaaaa5ea7 --- /dev/null +++ b/include/linux/swait_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/syscalls_api.h b/include/linux/syscalls_api.h new file mode 100644 index 000000000000..23e012b04db4 --- /dev/null +++ b/include/linux/syscalls_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/u64_stats_sync_api.h b/include/linux/u64_stats_sync_api.h new file mode 100644 index 000000000000..c72ca63da44b --- /dev/null +++ b/include/linux/u64_stats_sync_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/wait_api.h b/include/linux/wait_api.h new file mode 100644 index 000000000000..4e930548935a --- /dev/null +++ b/include/linux/wait_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/workqueue_api.h b/include/linux/workqueue_api.h new file mode 100644 index 000000000000..77debb5d2760 --- /dev/null +++ b/include/linux/workqueue_api.h @@ -0,0 +1 @@ +#include -- cgit v1.2.3 From fbed5664b73830dcb1a19af4f7f1f1b424f54609 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 22 Feb 2022 13:28:20 +0100 Subject: sched/headers: Make the header build standalone This header depends on various scheduler definitions. Signed-off-by: Ingo Molnar Reviewed-by: Peter Zijlstra --- include/linux/sched/deadline.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/sched') diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 1aff00b65f3c..7c83d4d5a971 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -6,6 +6,8 @@ * NORMAL/BATCH tasks. */ +#include + #define MAX_DL_PRIO 0 static inline int dl_prio(int prio) -- cgit v1.2.3 From 593febb143d17aa2096cd123c9d62b6981eb1d97 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 9 Feb 2022 11:46:54 -0600 Subject: signal: Move set_notify_signal and clear_notify_signal into sched/signal.h The header tracehook.h is no place for code to live. The functions set_notify_signal and clear_notify_signal are not about signals. They are about interruptions that act like signals. The fundamental signal primitives wind up calling set_notify_signal and clear_notify_signal. Which means they need to be maintained with the signal code. Since set_notify_signal and clear_notify_signal must be maintained with the signal subsystem move them into sched/signal.h and claim them as part of the signal subsystem. Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20220309162454.123006-10-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 17 +++++++++++++++++ include/linux/tracehook.h | 17 ----------------- 2 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index b6ecb9fc4cd2..3c8b34876744 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -349,6 +349,23 @@ extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); +static inline void clear_notify_signal(void) +{ + clear_thread_flag(TIF_NOTIFY_SIGNAL); + smp_mb__after_atomic(); +} + +/* + * Called to break out of interruptible wait loops, and enter the + * exit_to_user_mode_loop(). + */ +static inline void set_notify_signal(struct task_struct *task) +{ + if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && + !wake_up_state(task, TASK_INTERRUPTIBLE)) + kick_process(task); +} + static inline int restart_syscall(void) { set_tsk_thread_flag(current, TIF_SIGPENDING); diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index e5d676e841e3..1b7365aef8da 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -106,21 +106,4 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) rseq_handle_notify_resume(NULL, regs); } -static inline void clear_notify_signal(void) -{ - clear_thread_flag(TIF_NOTIFY_SIGNAL); - smp_mb__after_atomic(); -} - -/* - * Called to break out of interruptible wait loops, and enter the - * exit_to_user_mode_loop(). - */ -static inline void set_notify_signal(struct task_struct *task) -{ - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && - !wake_up_state(task, TASK_INTERRUPTIBLE)) - kick_process(task); -} - #endif /* */ -- cgit v1.2.3 From eae654f1c21216daa9fbb92591c0d9f5ae46cfc5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 8 Mar 2022 16:30:48 +0100 Subject: exit: Mark do_group_exit() __noreturn vmlinux.o: warning: objtool: get_signal()+0x108: unreachable instruction 0000 000000000007f930 : ... 0103 7fa33: e8 00 00 00 00 call 7fa38 7fa34: R_X86_64_PLT32 do_group_exit-0x4 0108 7fa38: 41 8b 45 74 mov 0x74(%r13),%eax Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20220308154319.351270711@infradead.org --- include/linux/sched/task.h | 2 +- kernel/exit.c | 2 +- tools/objtool/check.c | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index e84e54d1b490..719c9a6cac8d 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -79,7 +79,7 @@ static inline void exit_thread(struct task_struct *tsk) { } #endif -extern void do_group_exit(int); +extern __noreturn void do_group_exit(int); extern void exit_files(struct task_struct *); extern void exit_itimers(struct signal_struct *); diff --git a/kernel/exit.c b/kernel/exit.c index b00a25bb4ab9..b71f9df9074e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -906,7 +906,7 @@ SYSCALL_DEFINE1(exit, int, error_code) * Take down every thread in the group. This is called by fatal signals * as well as by sys_exit_group (below). */ -void +void __noreturn do_group_exit(int exit_code) { struct signal_struct *sig = current->signal; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index c3ddcecdab57..9896562350a8 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -181,6 +181,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "kunit_try_catch_throw", "xen_start_kernel", "cpu_bringup_and_idle", + "do_group_exit", "stop_this_cpu", }; -- cgit v1.2.3 From c574bbe917036c8968b984c82c7b13194fe5ce98 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Tue, 22 Mar 2022 14:46:23 -0700 Subject: NUMA balancing: optimize page placement for memory tiering system With the advent of various new memory types, some machines will have multiple types of memory, e.g. DRAM and PMEM (persistent memory). The memory subsystem of these machines can be called memory tiering system, because the performance of the different types of memory are usually different. In such system, because of the memory accessing pattern changing etc, some pages in the slow memory may become hot globally. So in this patch, the NUMA balancing mechanism is enhanced to optimize the page placement among the different memory types according to hot/cold dynamically. In a typical memory tiering system, there are CPUs, fast memory and slow memory in each physical NUMA node. The CPUs and the fast memory will be put in one logical node (called fast memory node), while the slow memory will be put in another (faked) logical node (called slow memory node). That is, the fast memory is regarded as local while the slow memory is regarded as remote. So it's possible for the recently accessed pages in the slow memory node to be promoted to the fast memory node via the existing NUMA balancing mechanism. The original NUMA balancing mechanism will stop to migrate pages if the free memory of the target node becomes below the high watermark. This is a reasonable policy if there's only one memory type. But this makes the original NUMA balancing mechanism almost do not work to optimize page placement among different memory types. Details are as follows. It's the common cases that the working-set size of the workload is larger than the size of the fast memory nodes. Otherwise, it's unnecessary to use the slow memory at all. So, there are almost always no enough free pages in the fast memory nodes, so that the globally hot pages in the slow memory node cannot be promoted to the fast memory node. To solve the issue, we have 2 choices as follows, a. Ignore the free pages watermark checking when promoting hot pages from the slow memory node to the fast memory node. This will create some memory pressure in the fast memory node, thus trigger the memory reclaiming. So that, the cold pages in the fast memory node will be demoted to the slow memory node. b. Define a new watermark called wmark_promo which is higher than wmark_high, and have kswapd reclaiming pages until free pages reach such watermark. The scenario is as follows: when we want to promote hot-pages from a slow memory to a fast memory, but fast memory's free pages would go lower than high watermark with such promotion, we wake up kswapd with wmark_promo watermark in order to demote cold pages and free us up some space. So, next time we want to promote hot-pages we might have a chance of doing so. The choice "a" may create high memory pressure in the fast memory node. If the memory pressure of the workload is high, the memory pressure may become so high that the memory allocation latency of the workload is influenced, e.g. the direct reclaiming may be triggered. The choice "b" works much better at this aspect. If the memory pressure of the workload is high, the hot pages promotion will stop earlier because its allocation watermark is higher than that of the normal memory allocation. So in this patch, choice "b" is implemented. A new zone watermark (WMARK_PROMO) is added. Which is larger than the high watermark and can be controlled via watermark_scale_factor. In addition to the original page placement optimization among sockets, the NUMA balancing mechanism is extended to be used to optimize page placement according to hot/cold among different memory types. So the sysctl user space interface (numa_balancing) is extended in a backward compatible way as follow, so that the users can enable/disable these functionality individually. The sysctl is converted from a Boolean value to a bits field. The definition of the flags is, - 0: NUMA_BALANCING_DISABLED - 1: NUMA_BALANCING_NORMAL - 2: NUMA_BALANCING_MEMORY_TIERING We have tested the patch with the pmbench memory accessing benchmark with the 80:20 read/write ratio and the Gauss access address distribution on a 2 socket Intel server with Optane DC Persistent Memory Model. The test results shows that the pmbench score can improve up to 95.9%. Thanks Andrew Morton to help fix the document format error. Link: https://lkml.kernel.org/r/20220221084529.1052339-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" Tested-by: Baolin Wang Reviewed-by: Baolin Wang Acked-by: Johannes Weiner Reviewed-by: Oscar Salvador Reviewed-by: Yang Shi Cc: Michal Hocko Cc: Rik van Riel Cc: Mel Gorman Cc: Peter Zijlstra Cc: Dave Hansen Cc: Zi Yan Cc: Wei Xu Cc: Shakeel Butt Cc: zhongjiang-ali Cc: Randy Dunlap Cc: Feng Tang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/sysctl/kernel.rst | 29 ++++++++++++++++++++--------- include/linux/mmzone.h | 1 + include/linux/sched/sysctl.h | 10 ++++++++++ kernel/sched/core.c | 21 +++++++++++++++++---- kernel/sysctl.c | 2 +- mm/migrate.c | 16 ++++++++++++++-- mm/page_alloc.c | 3 ++- mm/vmscan.c | 6 +++++- 8 files changed, 70 insertions(+), 18 deletions(-) (limited to 'include/linux/sched') diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index d359bcfadd39..fdfd2b684822 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -595,16 +595,23 @@ Documentation/admin-guide/kernel-parameters.rst). numa_balancing ============== -Enables/disables automatic page fault based NUMA memory -balancing. Memory is moved automatically to nodes -that access it often. +Enables/disables and configures automatic page fault based NUMA memory +balancing. Memory is moved automatically to nodes that access it often. +The value to set can be the result of ORing the following: -Enables/disables automatic NUMA memory balancing. On NUMA machines, there -is a performance penalty if remote memory is accessed by a CPU. When this -feature is enabled the kernel samples what task thread is accessing memory -by periodically unmapping pages and later trapping a page fault. At the -time of the page fault, it is determined if the data being accessed should -be migrated to a local memory node. += ================================= +0 NUMA_BALANCING_DISABLED +1 NUMA_BALANCING_NORMAL +2 NUMA_BALANCING_MEMORY_TIERING += ================================= + +Or NUMA_BALANCING_NORMAL to optimize page placement among different +NUMA nodes to reduce remote accessing. On NUMA machines, there is a +performance penalty if remote memory is accessed by a CPU. When this +feature is enabled the kernel samples what task thread is accessing +memory by periodically unmapping pages and later trapping a page +fault. At the time of the page fault, it is determined if the data +being accessed should be migrated to a local memory node. The unmapping of pages and trapping faults incur additional overhead that ideally is offset by improved memory locality but there is no universal @@ -615,6 +622,10 @@ faults may be controlled by the `numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb`_, and numa_balancing_settle_count sysctls. +Or NUMA_BALANCING_MEMORY_TIERING to optimize page placement among +different types of memory (represented as different NUMA nodes) to +place the hot pages in the fast memory. This is implemented based on +unmapping and page fault too. numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb =============================================================================================================================== diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 310b6e7ce58a..962b14d403e8 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -353,6 +353,7 @@ enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, + WMARK_PROMO, NR_WMARK }; diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index c19dd5a2c05c..b5eec8854c5a 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -23,6 +23,16 @@ enum sched_tunable_scaling { SCHED_TUNABLESCALING_END, }; +#define NUMA_BALANCING_DISABLED 0x0 +#define NUMA_BALANCING_NORMAL 0x1 +#define NUMA_BALANCING_MEMORY_TIERING 0x2 + +#ifdef CONFIG_NUMA_BALANCING +extern int sysctl_numa_balancing_mode; +#else +#define sysctl_numa_balancing_mode 0 +#endif + /* * control realtime throttling: * diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9745613d531c..da6a60383645 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4279,7 +4279,9 @@ DEFINE_STATIC_KEY_FALSE(sched_numa_balancing); #ifdef CONFIG_NUMA_BALANCING -void set_numabalancing_state(bool enabled) +int sysctl_numa_balancing_mode; + +static void __set_numabalancing_state(bool enabled) { if (enabled) static_branch_enable(&sched_numa_balancing); @@ -4287,13 +4289,22 @@ void set_numabalancing_state(bool enabled) static_branch_disable(&sched_numa_balancing); } +void set_numabalancing_state(bool enabled) +{ + if (enabled) + sysctl_numa_balancing_mode = NUMA_BALANCING_NORMAL; + else + sysctl_numa_balancing_mode = NUMA_BALANCING_DISABLED; + __set_numabalancing_state(enabled); +} + #ifdef CONFIG_PROC_SYSCTL int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int err; - int state = static_branch_likely(&sched_numa_balancing); + int state = sysctl_numa_balancing_mode; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; @@ -4303,8 +4314,10 @@ int sysctl_numa_balancing(struct ctl_table *table, int write, err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (err < 0) return err; - if (write) - set_numabalancing_state(state); + if (write) { + sysctl_numa_balancing_mode = state; + __set_numabalancing_state(state); + } return err; } #endif diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 730ab56d9e92..3395b99d59a4 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1696,7 +1696,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = sysctl_numa_balancing, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ { diff --git a/mm/migrate.c b/mm/migrate.c index dc4adf979201..78b2cf87946d 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -51,6 +51,7 @@ #include #include #include +#include #include @@ -2031,16 +2032,27 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) { int page_lru; int nr_pages = thp_nr_pages(page); + int order = compound_order(page); - VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page); + VM_BUG_ON_PAGE(order && !PageTransHuge(page), page); /* Do not migrate THP mapped by multiple processes */ if (PageTransHuge(page) && total_mapcount(page) > 1) return 0; /* Avoid migrating to a node that is nearly full */ - if (!migrate_balanced_pgdat(pgdat, nr_pages)) + if (!migrate_balanced_pgdat(pgdat, nr_pages)) { + int z; + + if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)) + return 0; + for (z = pgdat->nr_zones - 1; z >= 0; z--) { + if (populated_zone(pgdat->node_zones + z)) + break; + } + wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE); return 0; + } if (isolate_lru_page(page)) return 0; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a573aa9f5160..8b18a077c409 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8441,7 +8441,8 @@ static void __setup_per_zone_wmarks(void) zone->watermark_boost = 0; zone->_watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp; - zone->_watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2; + zone->_watermark[WMARK_HIGH] = low_wmark_pages(zone) + tmp; + zone->_watermark[WMARK_PROMO] = high_wmark_pages(zone) + tmp; spin_unlock_irqrestore(&zone->lock, flags); } diff --git a/mm/vmscan.c b/mm/vmscan.c index f5ec53f19f3b..499fa86e754a 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -56,6 +56,7 @@ #include #include +#include #include "internal.h" @@ -3895,7 +3896,10 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) if (!managed_zone(zone)) continue; - mark = high_wmark_pages(zone); + if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) + mark = wmark_pages(zone, WMARK_PROMO); + else + mark = high_wmark_pages(zone); if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) return true; } -- cgit v1.2.3 From e87f4152e542610d0b4c6c8548964a68a59d2040 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 23 Mar 2022 20:02:41 +0100 Subject: task_stack, x86/cea: Force-inline stack helpers Force-inline two stack helpers to fix the following objtool warnings: vmlinux.o: warning: objtool: in_task_stack()+0xc: call to task_stack_page() leaves .noinstr.text section vmlinux.o: warning: objtool: in_entry_stack()+0x10: call to cpu_entry_stack() leaves .noinstr.text section Signed-off-by: Borislav Petkov Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220324183607.31717-2-bp@alien8.de --- arch/x86/include/asm/cpu_entry_area.h | 2 +- include/linux/sched/task_stack.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/sched') diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index dd5ea1bdf04c..75efc4c6f076 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -143,7 +143,7 @@ extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags); extern struct cpu_entry_area *get_cpu_entry_area(int cpu); -static inline struct entry_stack *cpu_entry_stack(int cpu) +static __always_inline struct entry_stack *cpu_entry_stack(int cpu) { return &get_cpu_entry_area(cpu)->entry_stack_page.stack; } diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index 892562ebbd3a..5e799a47431e 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -16,7 +16,7 @@ * try_get_task_stack() instead. task_stack_page will return a pointer * that could get freed out from under you. */ -static inline void *task_stack_page(const struct task_struct *task) +static __always_inline void *task_stack_page(const struct task_struct *task) { return task->stack; } -- cgit v1.2.3 From a60707d74bd1d119cf7bcc5101cda912fc46d5e3 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:45:57 +0800 Subject: sched: Move child_runs_first sysctls to fair.c move child_runs_first sysctls to fair.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 2 -- kernel/sched/fair.c | 19 +++++++++++++++++++ kernel/sched/sched.h | 2 ++ kernel/sysctl.c | 7 ------- 4 files changed, 21 insertions(+), 9 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index c1076b5e17fb..1d2ff3cd1728 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -14,8 +14,6 @@ extern unsigned long sysctl_hung_task_timeout_secs; enum { sysctl_hung_task_timeout_secs = 0 }; #endif -extern unsigned int sysctl_sched_child_runs_first; - enum sched_tunable_scaling { SCHED_TUNABLESCALING_NONE, SCHED_TUNABLESCALING_LOG, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d4bd299d67ab..788b1d6a3248 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -109,6 +109,25 @@ static unsigned int sched_nr_latency = 8; * parent will (try to) run first. */ unsigned int sysctl_sched_child_runs_first __read_mostly; +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_child_runs_first_sysctls[] = { + { + .procname = "sched_child_runs_first", + .data = &sysctl_sched_child_runs_first, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + {} +}; + +static int __init sched_child_runs_first_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_child_runs_first_sysctls); + return 0; +} +late_initcall(sched_child_runs_first_sysctl_init); +#endif /* * SCHED_OTHER wake-up granularity. diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 58263f90c559..767fc1de9646 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -108,6 +108,8 @@ extern __read_mostly int scheduler_running; extern unsigned long calc_load_update; extern atomic_long_t calc_load_tasks; +extern unsigned int sysctl_sched_child_runs_first; + extern void calc_global_load_tick(struct rq *this_rq); extern long calc_load_fold_active(struct rq *this_rq, long adjust); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 830aaf8ca08e..6bbb8e1af675 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1659,13 +1659,6 @@ int proc_do_static_key(struct ctl_table *table, int write, } static struct ctl_table kern_table[] = { - { - .procname = "sched_child_runs_first", - .data = &sysctl_sched_child_runs_first, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, #ifdef CONFIG_SCHEDSTATS { .procname = "sched_schedstats", -- cgit v1.2.3 From f5ef06d58be8311a9425e6a54a053ecb350952f3 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:45:58 +0800 Subject: sched: Move schedstats sysctls to core.c move schedstats sysctls to core.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 2 -- kernel/sched/core.c | 22 +++++++++++++++++++++- kernel/sysctl.c | 11 ----------- 3 files changed, 21 insertions(+), 14 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 1d2ff3cd1728..6c7a6850559b 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -64,8 +64,6 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) extern unsigned int sysctl_sched_energy_aware; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d575b4914925..04440da5955f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4430,7 +4430,7 @@ out: __setup("schedstats=", setup_schedstats); #ifdef CONFIG_PROC_SYSCTL -int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, +static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; @@ -4449,6 +4449,26 @@ int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, set_schedstats(state); return err; } + +static struct ctl_table sched_schedstats_sysctls[] = { + { + .procname = "sched_schedstats", + .data = NULL, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_schedstats, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static int __init sched_schedstats_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_schedstats_sysctls); + return 0; +} +late_initcall(sched_schedstats_sysctl_init); #endif /* CONFIG_PROC_SYSCTL */ #endif /* CONFIG_SCHEDSTATS */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6bbb8e1af675..fc0eeca20718 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1659,17 +1659,6 @@ int proc_do_static_key(struct ctl_table *table, int write, } static struct ctl_table kern_table[] = { -#ifdef CONFIG_SCHEDSTATS - { - .procname = "sched_schedstats", - .data = NULL, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sysctl_schedstats, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_SCHEDSTATS */ #ifdef CONFIG_TASK_DELAY_ACCT { .procname = "task_delayacct", -- cgit v1.2.3 From d9ab0e63fa7f8405fbb19e28c5191e0880a7f2db Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:45:59 +0800 Subject: sched: Move rt_period/runtime sysctls to rt.c move rt_period/runtime sysctls to rt.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 11 ----------- kernel/rcu/rcu.h | 2 ++ kernel/sched/core.c | 13 ------------- kernel/sched/rt.c | 43 ++++++++++++++++++++++++++++++++++++++++++- kernel/sched/sched.h | 4 ++++ kernel/sysctl.c | 14 -------------- 6 files changed, 48 insertions(+), 39 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 6c7a6850559b..4391c1307945 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,15 +31,6 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -/* - * control realtime throttling: - * - * /proc/sys/kernel/sched_rt_period_us - * /proc/sys/kernel/sched_rt_runtime_us - */ -extern unsigned int sysctl_sched_rt_period; -extern int sysctl_sched_rt_runtime; - extern unsigned int sysctl_sched_dl_period_max; extern unsigned int sysctl_sched_dl_period_min; @@ -58,8 +49,6 @@ extern int sched_rr_timeslice; int sched_rr_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int sched_rt_handler(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 24b5f2c2de87..7812c740b3bf 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -23,6 +23,8 @@ #define RCU_SEQ_CTR_SHIFT 2 #define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1) +extern int sysctl_sched_rt_runtime; + /* * Return the counter portion of a sequence number previously returned * by rcu_seq_snap() or rcu_seq_current(). diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 04440da5955f..774f3229db37 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -145,12 +145,6 @@ const_debug unsigned int sysctl_sched_nr_migrate = 8; const_debug unsigned int sysctl_sched_nr_migrate = 32; #endif -/* - * period over which we measure -rt task CPU usage in us. - * default: 1s - */ -unsigned int sysctl_sched_rt_period = 1000000; - __read_mostly int scheduler_running; #ifdef CONFIG_SCHED_CORE @@ -444,13 +438,6 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { } #endif /* CONFIG_SCHED_CORE */ -/* - * part of the period that we allow rt tasks to run in us. - * default: 0.95s - */ -int sysctl_sched_rt_runtime = 950000; - - /* * Serialization rules: * diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index a32c46889af8..5663bb5ff890 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -13,6 +13,47 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun); struct rt_bandwidth def_rt_bandwidth; +/* + * period over which we measure -rt task CPU usage in us. + * default: 1s + */ +unsigned int sysctl_sched_rt_period = 1000000; + +/* + * part of the period that we allow rt tasks to run in us. + * default: 0.95s + */ +int sysctl_sched_rt_runtime = 950000; + +static int sched_rt_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_rt_sysctls[] = { + { + .procname = "sched_rt_period_us", + .data = &sysctl_sched_rt_period, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sched_rt_handler, + }, + { + .procname = "sched_rt_runtime_us", + .data = &sysctl_sched_rt_runtime, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sched_rt_handler, + }, + {} +}; + +static int __init sched_rt_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_rt_sysctls); + return 0; +} +late_initcall(sched_rt_sysctl_init); +#endif + static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer) { struct rt_bandwidth *rt_b = @@ -2925,7 +2966,7 @@ static void sched_rt_do_global(void) raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); } -int sched_rt_handler(struct ctl_table *table, int write, void *buffer, +static int sched_rt_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_period, old_runtime; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 767fc1de9646..3b406c78a8e9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -114,6 +114,10 @@ extern void calc_global_load_tick(struct rq *this_rq); extern long calc_load_fold_active(struct rq *this_rq, long adjust); extern void call_trace_sched_update_nr_running(struct rq *rq, int count); + +extern unsigned int sysctl_sched_rt_period; +extern int sysctl_sched_rt_runtime; + /* * Helpers for converting nanosecond timing to jiffy resolution */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index fc0eeca20718..029bfe06c68d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1681,20 +1681,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ - { - .procname = "sched_rt_period_us", - .data = &sysctl_sched_rt_period, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sched_rt_handler, - }, - { - .procname = "sched_rt_runtime_us", - .data = &sysctl_sched_rt_runtime, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = sched_rt_handler, - }, { .procname = "sched_deadline_period_max_us", .data = &sysctl_sched_dl_period_max, -- cgit v1.2.3 From 84227c12888b1105725cd2de14705b029bcbb4b2 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:00 +0800 Subject: sched: Move deadline_period sysctls to deadline.c move deadline_period sysctls to deadline.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 3 --- kernel/sched/deadline.c | 42 ++++++++++++++++++++++++++++++++++-------- kernel/sysctl.c | 14 -------------- 3 files changed, 34 insertions(+), 25 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 4391c1307945..7da9b94c5e1c 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,9 +31,6 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -extern unsigned int sysctl_sched_dl_period_max; -extern unsigned int sysctl_sched_dl_period_min; - #ifdef CONFIG_UCLAMP_TASK extern unsigned int sysctl_sched_uclamp_util_min; extern unsigned int sysctl_sched_uclamp_util_max; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fb4255ae0b2c..82e10b74a7b2 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -16,6 +16,40 @@ * Fabio Checconi */ +/* + * Default limits for DL period; on the top end we guard against small util + * tasks still getting ridiculously long effective runtimes, on the bottom end we + * guard against timer DoS. + */ +static unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */ +static unsigned int sysctl_sched_dl_period_min = 100; /* 100 us */ +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_dl_sysctls[] = { + { + .procname = "sched_deadline_period_max_us", + .data = &sysctl_sched_dl_period_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sched_deadline_period_min_us", + .data = &sysctl_sched_dl_period_min, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + {} +}; + +static int __init sched_dl_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_dl_sysctls); + return 0; +} +late_initcall(sched_dl_sysctl_init); +#endif + static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se) { return container_of(dl_se, struct task_struct, dl); @@ -2879,14 +2913,6 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr) attr->sched_flags |= dl_se->flags; } -/* - * Default limits for DL period; on the top end we guard against small util - * tasks still getting ridiculously long effective runtimes, on the bottom end we - * guard against timer DoS. - */ -unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */ -unsigned int sysctl_sched_dl_period_min = 100; /* 100 us */ - /* * This function validates the new parameters of a -deadline task. * We ask for the deadline not being zero, and greater or equal diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 029bfe06c68d..2c8c75e11a37 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1681,20 +1681,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ - { - .procname = "sched_deadline_period_max_us", - .data = &sysctl_sched_dl_period_max, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "sched_deadline_period_min_us", - .data = &sysctl_sched_dl_period_min, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { .procname = "sched_rr_timeslice_ms", .data = &sysctl_sched_rr_timeslice, -- cgit v1.2.3 From dafd7a9dad22fadcb290b24dff54e2eae3b89776 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:01 +0800 Subject: sched: Move rr_timeslice sysctls to rt.c move rr_timeslice sysctls to rt.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 5 ----- kernel/sched/rt.c | 13 +++++++++++-- kernel/sched/sched.h | 1 + kernel/sysctl.c | 7 ------- 4 files changed, 12 insertions(+), 14 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 7da9b94c5e1c..3d307e512d1f 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -41,11 +41,6 @@ extern unsigned int sysctl_sched_uclamp_util_min_rt_default; extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif -extern int sysctl_sched_rr_timeslice; -extern int sched_rr_timeslice; - -int sched_rr_handler(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 5663bb5ff890..71791be36065 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -5,7 +5,7 @@ */ int sched_rr_timeslice = RR_TIMESLICE; -int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; +static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; /* More than 4 hours if BW_SHIFT equals 20. */ static const u64 max_rt_runtime = MAX_BW; @@ -27,6 +27,8 @@ int sysctl_sched_rt_runtime = 950000; static int sched_rt_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); +static int sched_rr_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); #ifdef CONFIG_SYSCTL static struct ctl_table sched_rt_sysctls[] = { { @@ -43,6 +45,13 @@ static struct ctl_table sched_rt_sysctls[] = { .mode = 0644, .proc_handler = sched_rt_handler, }, + { + .procname = "sched_rr_timeslice_ms", + .data = &sysctl_sched_rr_timeslice, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sched_rr_handler, + }, {} }; @@ -3005,7 +3014,7 @@ undo: return ret; } -int sched_rr_handler(struct ctl_table *table, int write, void *buffer, +static int sched_rr_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 3b406c78a8e9..ae0f6e5a76f9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -117,6 +117,7 @@ extern void call_trace_sched_update_nr_running(struct rq *rq, int count); extern unsigned int sysctl_sched_rt_period; extern int sysctl_sched_rt_runtime; +extern int sched_rr_timeslice; /* * Helpers for converting nanosecond timing to jiffy resolution diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 2c8c75e11a37..b074f70a3e11 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1681,13 +1681,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ - { - .procname = "sched_rr_timeslice_ms", - .data = &sysctl_sched_rr_timeslice, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = sched_rr_handler, - }, #ifdef CONFIG_UCLAMP_TASK { .procname = "sched_util_clamp_min", -- cgit v1.2.3 From 3267e0156c3341ac25b37a0f60551cdae1634b60 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:02 +0800 Subject: sched: Move uclamp_util sysctls to core.c move uclamp_util sysctls to core.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 8 -------- kernel/sched/core.c | 48 ++++++++++++++++++++++++++++++++++---------- kernel/sysctl.c | 23 --------------------- 3 files changed, 37 insertions(+), 42 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 3d307e512d1f..0934b21a57a4 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,18 +31,10 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -#ifdef CONFIG_UCLAMP_TASK -extern unsigned int sysctl_sched_uclamp_util_min; -extern unsigned int sysctl_sched_uclamp_util_max; -extern unsigned int sysctl_sched_uclamp_util_min_rt_default; -#endif - #ifdef CONFIG_CFS_BANDWIDTH extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif -int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 774f3229db37..ef31751c5799 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1306,10 +1306,10 @@ static void set_load_weight(struct task_struct *p, bool update_load) static DEFINE_MUTEX(uclamp_mutex); /* Max allowed minimum utilization */ -unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE; +static unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE; /* Max allowed maximum utilization */ -unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; +static unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; /* * By default RT tasks run at the maximum performance point/capacity of the @@ -1326,7 +1326,7 @@ unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; * This knob will not override the system default sched_util_clamp_min defined * above. */ -unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE; +static unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE; /* All clamps are required to be less or equal than these values */ static struct uclamp_se uclamp_default[UCLAMP_CNT]; @@ -1779,7 +1779,7 @@ static void uclamp_update_root_tg(void) static void uclamp_update_root_tg(void) { } #endif -int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, +static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { bool update_root_tg = false; @@ -4436,8 +4436,12 @@ static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, set_schedstats(state); return err; } +#endif /* CONFIG_PROC_SYSCTL */ +#endif /* CONFIG_SCHEDSTATS */ -static struct ctl_table sched_schedstats_sysctls[] = { +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_core_sysctls[] = { +#ifdef CONFIG_SCHEDSTATS { .procname = "sched_schedstats", .data = NULL, @@ -4447,17 +4451,39 @@ static struct ctl_table sched_schedstats_sysctls[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, +#endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_UCLAMP_TASK + { + .procname = "sched_util_clamp_min", + .data = &sysctl_sched_uclamp_util_min, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, + { + .procname = "sched_util_clamp_max", + .data = &sysctl_sched_uclamp_util_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, + { + .procname = "sched_util_clamp_min_rt_default", + .data = &sysctl_sched_uclamp_util_min_rt_default, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, +#endif /* CONFIG_UCLAMP_TASK */ {} }; - -static int __init sched_schedstats_sysctl_init(void) +static int __init sched_core_sysctl_init(void) { - register_sysctl_init("kernel", sched_schedstats_sysctls); + register_sysctl_init("kernel", sched_core_sysctls); return 0; } -late_initcall(sched_schedstats_sysctl_init); -#endif /* CONFIG_PROC_SYSCTL */ -#endif /* CONFIG_SCHEDSTATS */ +late_initcall(sched_core_sysctl_init); +#endif /* CONFIG_SYSCTL */ /* * fork()/clone()-time setup: diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b074f70a3e11..a48c090d57f9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1681,29 +1681,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ -#ifdef CONFIG_UCLAMP_TASK - { - .procname = "sched_util_clamp_min", - .data = &sysctl_sched_uclamp_util_min, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sysctl_sched_uclamp_handler, - }, - { - .procname = "sched_util_clamp_max", - .data = &sysctl_sched_uclamp_util_max, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sysctl_sched_uclamp_handler, - }, - { - .procname = "sched_util_clamp_min_rt_default", - .data = &sysctl_sched_uclamp_util_min_rt_default, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sysctl_sched_uclamp_handler, - }, -#endif #ifdef CONFIG_CFS_BANDWIDTH { .procname = "sched_cfs_bandwidth_slice_us", -- cgit v1.2.3 From d4ae80ffa64f87b9c355692b680b603add084e96 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:03 +0800 Subject: sched: Move cfs_bandwidth_slice sysctls to fair.c move cfs_bandwidth_slice sysctls to fair.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 4 ---- kernel/sched/fair.c | 51 +++++++++++++++++++++++++++----------------- kernel/sysctl.c | 10 --------- 3 files changed, 31 insertions(+), 34 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 0934b21a57a4..198f77c8a873 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,10 +31,6 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -#ifdef CONFIG_CFS_BANDWIDTH -extern unsigned int sysctl_sched_cfs_bandwidth_slice; -#endif - int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 788b1d6a3248..265bf7a75a37 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -109,25 +109,6 @@ static unsigned int sched_nr_latency = 8; * parent will (try to) run first. */ unsigned int sysctl_sched_child_runs_first __read_mostly; -#ifdef CONFIG_SYSCTL -static struct ctl_table sched_child_runs_first_sysctls[] = { - { - .procname = "sched_child_runs_first", - .data = &sysctl_sched_child_runs_first, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - {} -}; - -static int __init sched_child_runs_first_sysctl_init(void) -{ - register_sysctl_init("kernel", sched_child_runs_first_sysctls); - return 0; -} -late_initcall(sched_child_runs_first_sysctl_init); -#endif /* * SCHED_OTHER wake-up granularity. @@ -192,7 +173,37 @@ int __weak arch_asym_cpu_priority(int cpu) * * (default: 5 msec, units: microseconds) */ -unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; +static unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; +#endif + +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_fair_sysctls[] = { + { + .procname = "sched_child_runs_first", + .data = &sysctl_sched_child_runs_first, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_CFS_BANDWIDTH + { + .procname = "sched_cfs_bandwidth_slice_us", + .data = &sysctl_sched_cfs_bandwidth_slice, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + }, +#endif + {} +}; + +static int __init sched_fair_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_fair_sysctls); + return 0; +} +late_initcall(sched_fair_sysctl_init); #endif static inline void update_load_add(struct load_weight *lw, unsigned long inc) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index a48c090d57f9..10ab81c7c457 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1681,16 +1681,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ -#ifdef CONFIG_CFS_BANDWIDTH - { - .procname = "sched_cfs_bandwidth_slice_us", - .data = &sysctl_sched_cfs_bandwidth_slice, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ONE, - }, -#endif #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) { .procname = "sched_energy_aware", -- cgit v1.2.3 From 8a0441415b3f9b9a920a6a5086580ea3daa7b884 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:04 +0800 Subject: sched: Move energy_aware sysctls to topology.c move energy_aware sysctls to topology.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 6 ------ kernel/sched/topology.c | 25 +++++++++++++++++++++++-- kernel/sysctl.c | 11 ----------- 3 files changed, 23 insertions(+), 19 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 198f77c8a873..e650946816d0 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -34,10 +34,4 @@ extern int sysctl_numa_balancing_mode; int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) -extern unsigned int sysctl_sched_energy_aware; -int sched_energy_aware_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - #endif /* _LINUX_SCHED_SYSCTL_H */ diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 810750e62118..05b6c2ad90b9 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -206,7 +206,7 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) DEFINE_STATIC_KEY_FALSE(sched_energy_present); -unsigned int sysctl_sched_energy_aware = 1; +static unsigned int sysctl_sched_energy_aware = 1; DEFINE_MUTEX(sched_energy_mutex); bool sched_energy_update; @@ -220,7 +220,7 @@ void rebuild_sched_domains_energy(void) } #ifdef CONFIG_PROC_SYSCTL -int sched_energy_aware_handler(struct ctl_table *table, int write, +static int sched_energy_aware_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, state; @@ -237,6 +237,27 @@ int sched_energy_aware_handler(struct ctl_table *table, int write, return ret; } + +static struct ctl_table sched_energy_aware_sysctls[] = { + { + .procname = "sched_energy_aware", + .data = &sysctl_sched_energy_aware, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sched_energy_aware_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static int __init sched_energy_aware_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_energy_aware_sysctls); + return 0; +} + +late_initcall(sched_energy_aware_sysctl_init); #endif static void free_pd(struct perf_domain *pd) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 10ab81c7c457..8241c5401ee8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1681,17 +1681,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ -#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) - { - .procname = "sched_energy_aware", - .data = &sysctl_sched_energy_aware, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sched_energy_aware_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif #ifdef CONFIG_PROVE_LOCKING { .procname = "prove_locking", -- cgit v1.2.3 From 5f24d5a579d1eace79d505b148808a850b417d4c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 21 Apr 2022 16:35:46 -0700 Subject: mm, hugetlb: allow for "high" userspace addresses This is a fix for commit f6795053dac8 ("mm: mmap: Allow for "high" userspace addresses") for hugetlb. This patch adds support for "high" userspace addresses that are optionally supported on the system and have to be requested via a hint mechanism ("high" addr parameter to mmap). Architectures such as powerpc and x86 achieve this by making changes to their architectural versions of hugetlb_get_unmapped_area() function. However, arm64 uses the generic version of that function. So take into account arch_get_mmap_base() and arch_get_mmap_end() in hugetlb_get_unmapped_area(). To allow that, move those two macros out of mm/mmap.c into include/linux/sched/mm.h If these macros are not defined in architectural code then they default to (TASK_SIZE) and (base) so should not introduce any behavioural changes to architectures that do not define them. For the time being, only ARM64 is affected by this change. Catalin (ARM64) said "We should have fixed hugetlb_get_unmapped_area() as well when we added support for 52-bit VA. The reason for commit f6795053dac8 was to prevent normal mmap() from returning addresses above 48-bit by default as some user-space had hard assumptions about this. It's a slight ABI change if you do this for hugetlb_get_unmapped_area() but I doubt anyone would notice. It's more likely that the current behaviour would cause issues, so I'd rather have them consistent. Basically when arm64 gained support for 52-bit addresses we did not want user-space calling mmap() to suddenly get such high addresses, otherwise we could have inadvertently broken some programs (similar behaviour to x86 here). Hence we added commit f6795053dac8. But we missed hugetlbfs which could still get such high mmap() addresses. So in theory that's a potential regression that should have bee addressed at the same time as commit f6795053dac8 (and before arm64 enabled 52-bit addresses)" Link: https://lkml.kernel.org/r/ab847b6edb197bffdfe189e70fb4ac76bfe79e0d.1650033747.git.christophe.leroy@csgroup.eu Fixes: f6795053dac8 ("mm: mmap: Allow for "high" userspace addresses") Signed-off-by: Christophe Leroy Reviewed-by: Catalin Marinas Cc: Steve Capper Cc: Will Deacon Cc: [5.0.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 9 +++++---- include/linux/sched/mm.h | 8 ++++++++ mm/mmap.c | 8 -------- 3 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include/linux/sched') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 99c7477cee5c..dd3a088db11d 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -206,7 +206,7 @@ hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, info.flags = 0; info.length = len; info.low_limit = current->mm->mmap_base; - info.high_limit = TASK_SIZE; + info.high_limit = arch_get_mmap_end(addr); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; return vm_unmapped_area(&info); @@ -222,7 +222,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = max(PAGE_SIZE, mmap_min_addr); - info.high_limit = current->mm->mmap_base; + info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; addr = vm_unmapped_area(&info); @@ -237,7 +237,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = current->mm->mmap_base; - info.high_limit = TASK_SIZE; + info.high_limit = arch_get_mmap_end(addr); addr = vm_unmapped_area(&info); } @@ -251,6 +251,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct hstate *h = hstate_file(file); + const unsigned long mmap_end = arch_get_mmap_end(addr); if (len & ~huge_page_mask(h)) return -EINVAL; @@ -266,7 +267,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, if (addr) { addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && + if (mmap_end - len >= addr && (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index a80356e9dc69..1ad1f4bfa025 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -136,6 +136,14 @@ static inline void mm_update_next_owner(struct mm_struct *mm) #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU +#ifndef arch_get_mmap_end +#define arch_get_mmap_end(addr) (TASK_SIZE) +#endif + +#ifndef arch_get_mmap_base +#define arch_get_mmap_base(addr, base) (base) +#endif + extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); extern unsigned long diff --git a/mm/mmap.c b/mm/mmap.c index 3aa839f81e63..313b57d55a63 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2117,14 +2117,6 @@ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) return addr; } -#ifndef arch_get_mmap_end -#define arch_get_mmap_end(addr) (TASK_SIZE) -#endif - -#ifndef arch_get_mmap_base -#define arch_get_mmap_base(addr, base) (base) -#endif - /* Get an address range which is currently unmapped. * For shmat() with addr=0. * -- cgit v1.2.3 From 78ed93d72ded679e3caf0758357209887bda885f Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 4 Apr 2022 13:12:04 +0200 Subject: signal: Deliver SIGTRAP on perf event asynchronously if blocked With SIGTRAP on perf events, we have encountered termination of processes due to user space attempting to block delivery of SIGTRAP. Consider this case: ... sigset_t s; sigemptyset(&s); sigaddset(&s, SIGTRAP | ); sigprocmask(SIG_BLOCK, &s, ...); ... When the perf event triggers, while SIGTRAP is blocked, force_sig_perf() will force the signal, but revert back to the default handler, thus terminating the task. This makes sense for error conditions, but not so much for explicitly requested monitoring. However, the expectation is still that signals generated by perf events are synchronous, which will no longer be the case if the signal is blocked and delivered later. To give user space the ability to clearly distinguish synchronous from asynchronous signals, introduce siginfo_t::si_perf_flags and TRAP_PERF_FLAG_ASYNC (opted for flags in case more binary information is required in future). The resolution to the problem is then to (a) no longer force the signal (avoiding the terminations), but (b) tell user space via si_perf_flags if the signal was synchronous or not, so that such signals can be handled differently (e.g. let user space decide to ignore or consider the data imprecise). The alternative of making the kernel ignore SIGTRAP on perf events if the signal is blocked may work for some usecases, but likely causes issues in others that then have to revert back to interception of sigprocmask() (which we want to avoid). [ A concrete example: when using breakpoint perf events to track data-flow, in a region of code where signals are blocked, data-flow can no longer be tracked accurately. When a relevant asynchronous signal is received after unblocking the signal, the data-flow tracking logic needs to know its state is imprecise. ] Fixes: 97ba62b27867 ("perf: Add support for SIGTRAP on perf events") Reported-by: Dmitry Vyukov Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Acked-by: Geert Uytterhoeven Tested-by: Dmitry Vyukov Link: https://lore.kernel.org/r/20220404111204.935357-1-elver@google.com --- arch/arm/kernel/signal.c | 1 + arch/arm64/kernel/signal.c | 1 + arch/arm64/kernel/signal32.c | 1 + arch/m68k/kernel/signal.c | 1 + arch/sparc/kernel/signal32.c | 1 + arch/sparc/kernel/signal_64.c | 1 + arch/x86/kernel/signal_compat.c | 2 ++ include/linux/compat.h | 1 + include/linux/sched/signal.h | 2 +- include/uapi/asm-generic/siginfo.h | 7 +++++++ kernel/events/core.c | 4 ++-- kernel/signal.c | 18 ++++++++++++++++-- 12 files changed, 35 insertions(+), 5 deletions(-) (limited to 'include/linux/sched') diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 459abc5d1819..ea128e32e8ca 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -708,6 +708,7 @@ static_assert(offsetof(siginfo_t, si_upper) == 0x18); static_assert(offsetof(siginfo_t, si_pkey) == 0x14); static_assert(offsetof(siginfo_t, si_perf_data) == 0x10); static_assert(offsetof(siginfo_t, si_perf_type) == 0x14); +static_assert(offsetof(siginfo_t, si_perf_flags) == 0x18); static_assert(offsetof(siginfo_t, si_band) == 0x0c); static_assert(offsetof(siginfo_t, si_fd) == 0x10); static_assert(offsetof(siginfo_t, si_call_addr) == 0x0c); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 4a4122ef6f39..41b5d9d3672a 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -1011,6 +1011,7 @@ static_assert(offsetof(siginfo_t, si_upper) == 0x28); static_assert(offsetof(siginfo_t, si_pkey) == 0x20); static_assert(offsetof(siginfo_t, si_perf_data) == 0x18); static_assert(offsetof(siginfo_t, si_perf_type) == 0x20); +static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24); static_assert(offsetof(siginfo_t, si_band) == 0x10); static_assert(offsetof(siginfo_t, si_fd) == 0x18); static_assert(offsetof(siginfo_t, si_call_addr) == 0x10); diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index d984282b979f..4700f8522d27 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -487,6 +487,7 @@ static_assert(offsetof(compat_siginfo_t, si_upper) == 0x18); static_assert(offsetof(compat_siginfo_t, si_pkey) == 0x14); static_assert(offsetof(compat_siginfo_t, si_perf_data) == 0x10); static_assert(offsetof(compat_siginfo_t, si_perf_type) == 0x14); +static_assert(offsetof(compat_siginfo_t, si_perf_flags) == 0x18); static_assert(offsetof(compat_siginfo_t, si_band) == 0x0c); static_assert(offsetof(compat_siginfo_t, si_fd) == 0x10); static_assert(offsetof(compat_siginfo_t, si_call_addr) == 0x0c); diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index 49533f65958a..b9f6908a31bc 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -625,6 +625,7 @@ static inline void siginfo_build_tests(void) /* _sigfault._perf */ BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x10); BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x14); + BUILD_BUG_ON(offsetof(siginfo_t, si_perf_flags) != 0x18); /* _sigpoll */ BUILD_BUG_ON(offsetof(siginfo_t, si_band) != 0x0c); diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index f9fe502b81c6..dad38960d1a8 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -779,5 +779,6 @@ static_assert(offsetof(compat_siginfo_t, si_upper) == 0x18); static_assert(offsetof(compat_siginfo_t, si_pkey) == 0x14); static_assert(offsetof(compat_siginfo_t, si_perf_data) == 0x10); static_assert(offsetof(compat_siginfo_t, si_perf_type) == 0x14); +static_assert(offsetof(compat_siginfo_t, si_perf_flags) == 0x18); static_assert(offsetof(compat_siginfo_t, si_band) == 0x0c); static_assert(offsetof(compat_siginfo_t, si_fd) == 0x10); diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 8b9fc76cd3e0..570e43e6fda5 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -590,5 +590,6 @@ static_assert(offsetof(siginfo_t, si_upper) == 0x28); static_assert(offsetof(siginfo_t, si_pkey) == 0x20); static_assert(offsetof(siginfo_t, si_perf_data) == 0x18); static_assert(offsetof(siginfo_t, si_perf_type) == 0x20); +static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24); static_assert(offsetof(siginfo_t, si_band) == 0x10); static_assert(offsetof(siginfo_t, si_fd) == 0x14); diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index b52407c56000..879ef8c72f5c 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -149,8 +149,10 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(offsetof(siginfo_t, si_perf_data) != 0x18); BUILD_BUG_ON(offsetof(siginfo_t, si_perf_type) != 0x20); + BUILD_BUG_ON(offsetof(siginfo_t, si_perf_flags) != 0x24); BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_data) != 0x10); BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_type) != 0x14); + BUILD_BUG_ON(offsetof(compat_siginfo_t, si_perf_flags) != 0x18); CHECK_CSI_OFFSET(_sigpoll); CHECK_CSI_SIZE (_sigpoll, 2*sizeof(int)); diff --git a/include/linux/compat.h b/include/linux/compat.h index 1c758b0e0359..01fddf72a81f 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -235,6 +235,7 @@ typedef struct compat_siginfo { struct { compat_ulong_t _data; u32 _type; + u32 _flags; } _perf; }; } _sigfault; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..bab7cc56b13a 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -320,7 +320,7 @@ int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); -int force_sig_perf(void __user *addr, u32 type, u64 sig_data); +int send_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno); diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index 3ba180f550d7..ffbe4cec9f32 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -99,6 +99,7 @@ union __sifields { struct { unsigned long _data; __u32 _type; + __u32 _flags; } _perf; }; } _sigfault; @@ -164,6 +165,7 @@ typedef struct siginfo { #define si_pkey _sifields._sigfault._addr_pkey._pkey #define si_perf_data _sifields._sigfault._perf._data #define si_perf_type _sifields._sigfault._perf._type +#define si_perf_flags _sifields._sigfault._perf._flags #define si_band _sifields._sigpoll._band #define si_fd _sifields._sigpoll._fd #define si_call_addr _sifields._sigsys._call_addr @@ -270,6 +272,11 @@ typedef struct siginfo { * that are of the form: ((PTRACE_EVENT_XXX << 8) | SIGTRAP) */ +/* + * Flags for si_perf_flags if SIGTRAP si_code is TRAP_PERF. + */ +#define TRAP_PERF_FLAG_ASYNC (1u << 0) + /* * SIGCHLD si_codes */ diff --git a/kernel/events/core.c b/kernel/events/core.c index cfde994ce61c..6eafb1b0ad4a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6533,8 +6533,8 @@ static void perf_sigtrap(struct perf_event *event) if (current->flags & PF_EXITING) return; - force_sig_perf((void __user *)event->pending_addr, - event->attr.type, event->attr.sig_data); + send_sig_perf((void __user *)event->pending_addr, + event->attr.type, event->attr.sig_data); } static void perf_pending_event_disable(struct perf_event *event) diff --git a/kernel/signal.c b/kernel/signal.c index 30cd1ca43bcd..e43bc2a692f5 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1805,7 +1805,7 @@ int force_sig_pkuerr(void __user *addr, u32 pkey) } #endif -int force_sig_perf(void __user *addr, u32 type, u64 sig_data) +int send_sig_perf(void __user *addr, u32 type, u64 sig_data) { struct kernel_siginfo info; @@ -1817,7 +1817,18 @@ int force_sig_perf(void __user *addr, u32 type, u64 sig_data) info.si_perf_data = sig_data; info.si_perf_type = type; - return force_sig_info(&info); + /* + * Signals generated by perf events should not terminate the whole + * process if SIGTRAP is blocked, however, delivering the signal + * asynchronously is better than not delivering at all. But tell user + * space if the signal was asynchronous, so it can clearly be + * distinguished from normal synchronous ones. + */ + info.si_perf_flags = sigismember(¤t->blocked, info.si_signo) ? + TRAP_PERF_FLAG_ASYNC : + 0; + + return send_sig_info(info.si_signo, &info, current); } /** @@ -3432,6 +3443,7 @@ void copy_siginfo_to_external32(struct compat_siginfo *to, to->si_addr = ptr_to_compat(from->si_addr); to->si_perf_data = from->si_perf_data; to->si_perf_type = from->si_perf_type; + to->si_perf_flags = from->si_perf_flags; break; case SIL_CHLD: to->si_pid = from->si_pid; @@ -3509,6 +3521,7 @@ static int post_copy_siginfo_from_user32(kernel_siginfo_t *to, to->si_addr = compat_ptr(from->si_addr); to->si_perf_data = from->si_perf_data; to->si_perf_type = from->si_perf_type; + to->si_perf_flags = from->si_perf_flags; break; case SIL_CHLD: to->si_pid = from->si_pid; @@ -4722,6 +4735,7 @@ static inline void siginfo_buildtime_checks(void) CHECK_OFFSET(si_pkey); CHECK_OFFSET(si_perf_data); CHECK_OFFSET(si_perf_type); + CHECK_OFFSET(si_perf_flags); /* sigpoll */ CHECK_OFFSET(si_band); -- cgit v1.2.3 From e788be95a57a9bebe446878ce9bf2750f6fe4974 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 28 Apr 2022 17:25:16 -0600 Subject: task_work: allow TWA_SIGNAL without a rescheduling IPI Some use cases don't always need an IPI when sending a TWA_SIGNAL notification. Add TWA_SIGNAL_NO_IPI, which is just like TWA_SIGNAL, except it doesn't send an IPI to the target task. It merely sets TIF_NOTIFY_SIGNAL and wakes up the task. This can be useful in avoiding a forceful transition to the kernel if the task is running in userspace. Depending on the task_work in question, it may be quite fine waiting for the next reschedule or kernel enter anyway, or the use case may even have other mechanisms for hinting to the task that a transition may be useful. This can drive more cooperative scheduling of task_work. Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/821f42b6-7d91-8074-8212-d34998097de4@kernel.dk Signed-off-by: Jens Axboe --- include/linux/sched/signal.h | 13 +++++++++++-- include/linux/task_work.h | 1 + kernel/task_work.c | 25 +++++++++++++++++++------ 3 files changed, 31 insertions(+), 8 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..66b689f6cfcb 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -355,14 +355,23 @@ static inline void clear_notify_signal(void) smp_mb__after_atomic(); } +/* + * Returns 'true' if kick_process() is needed to force a transition from + * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work. + */ +static inline bool __set_notify_signal(struct task_struct *task) +{ + return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && + !wake_up_state(task, TASK_INTERRUPTIBLE); +} + /* * Called to break out of interruptible wait loops, and enter the * exit_to_user_mode_loop(). */ static inline void set_notify_signal(struct task_struct *task) { - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && - !wake_up_state(task, TASK_INTERRUPTIBLE)) + if (__set_notify_signal(task)) kick_process(task); } diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 897494b597ba..795ef5a68429 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -17,6 +17,7 @@ enum task_work_notify_mode { TWA_NONE, TWA_RESUME, TWA_SIGNAL, + TWA_SIGNAL_NO_IPI, }; static inline bool task_work_pending(struct task_struct *task) diff --git a/kernel/task_work.c b/kernel/task_work.c index c59e1a49bc40..dff75bcde151 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -12,12 +12,22 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */ * @notify: how to notify the targeted task * * Queue @work for task_work_run() below and notify the @task if @notify - * is @TWA_RESUME or @TWA_SIGNAL. @TWA_SIGNAL works like signals, in that the - * it will interrupt the targeted task and run the task_work. @TWA_RESUME - * work is run only when the task exits the kernel and returns to user mode, - * or before entering guest mode. Fails if the @task is exiting/exited and thus - * it can't process this @work. Otherwise @work->func() will be called when the - * @task goes through one of the aforementioned transitions, or exits. + * is @TWA_RESUME, @TWA_SIGNAL, or @TWA_SIGNAL_NO_IPI. + * + * @TWA_SIGNAL works like signals, in that the it will interrupt the targeted + * task and run the task_work, regardless of whether the task is currently + * running in the kernel or userspace. + * @TWA_SIGNAL_NO_IPI works like @TWA_SIGNAL, except it doesn't send a + * reschedule IPI to force the targeted task to reschedule and run task_work. + * This can be advantageous if there's no strict requirement that the + * task_work be run as soon as possible, just whenever the task enters the + * kernel anyway. + * @TWA_RESUME work is run only when the task exits the kernel and returns to + * user mode, or before entering guest mode. + * + * Fails if the @task is exiting/exited and thus it can't process this @work. + * Otherwise @work->func() will be called when the @task goes through one of + * the aforementioned transitions, or exits. * * If the targeted task is exiting, then an error is returned and the work item * is not queued. It's up to the caller to arrange for an alternative mechanism @@ -53,6 +63,9 @@ int task_work_add(struct task_struct *task, struct callback_head *work, case TWA_SIGNAL: set_notify_signal(task); break; + case TWA_SIGNAL_NO_IPI: + __set_notify_signal(task); + break; default: WARN_ON_ONCE(1); break; -- cgit v1.2.3 From 4b439e25e29ec336c0e71ef1d1b212c412526518 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 9 Apr 2022 19:17:27 +0200 Subject: mm, hugetlbfs: Allow an arch to always use generic versions of get_unmapped_area functions Unlike most architectures, powerpc can only define at runtime if it is going to use the generic arch_get_unmapped_area() or not. Today, powerpc has a copy of the generic arch_get_unmapped_area() because when selection HAVE_ARCH_UNMAPPED_AREA the generic arch_get_unmapped_area() is not available. Rename it generic_get_unmapped_area() and make it independent of HAVE_ARCH_UNMAPPED_AREA. Do the same for arch_get_unmapped_area_topdown() versus HAVE_ARCH_UNMAPPED_AREA_TOPDOWN. Do the same for hugetlb_get_unmapped_area() versus HAVE_ARCH_HUGETLB_UNMAPPED_AREA. Signed-off-by: Christophe Leroy Reviewed-by: Nicholas Piggin Acked-by: Andrew Morton Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/77f9d3e592f1c8511df9381aa1c4e754651da4d1.1649523076.git.christophe.leroy@csgroup.eu --- fs/hugetlbfs/inode.c | 17 +++++++++++++---- include/linux/hugetlb.h | 5 +++++ include/linux/sched/mm.h | 9 +++++++++ mm/mmap.c | 31 ++++++++++++++++++++++++------- 4 files changed, 51 insertions(+), 11 deletions(-) (limited to 'include/linux/sched') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index dd3a088db11d..ec611c7de9e3 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -195,7 +195,6 @@ out: * Called under mmap_write_lock(mm). */ -#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) @@ -244,9 +243,10 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, return addr; } -static unsigned long -hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) +unsigned long +generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; @@ -283,6 +283,15 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, return hugetlb_get_unmapped_area_bottomup(file, addr, len, pgoff, flags); } + +#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA +static unsigned long +hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags); +} #endif static size_t diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ac2a1d758a80..bc97c8458df6 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -519,6 +519,11 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long flags); #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ +unsigned long +generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); + /* * huegtlb page specific state flags. These flags are located in page.private * of the hugetlb head page. Functions created via the below macros should be diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 1ad1f4bfa025..da3a32d05b34 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -153,6 +153,15 @@ extern unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); + +unsigned long +generic_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); +unsigned long +generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) {} diff --git a/mm/mmap.c b/mm/mmap.c index 313b57d55a63..d2b6c3fbfb8c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2128,10 +2128,10 @@ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) * * This function "knows" that -ENOMEM has the bits set. */ -#ifndef HAVE_ARCH_UNMAPPED_AREA unsigned long -arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) +generic_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; @@ -2161,17 +2161,25 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, info.align_offset = 0; return vm_unmapped_area(&info); } + +#ifndef HAVE_ARCH_UNMAPPED_AREA +unsigned long +arch_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + return generic_get_unmapped_area(filp, addr, len, pgoff, flags); +} #endif /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): */ -#ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN unsigned long -arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags) +generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) { struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; @@ -2219,6 +2227,15 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, return addr; } + +#ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN +unsigned long +arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); +} #endif unsigned long -- cgit v1.2.3 From 2cb4de085f383cb9289083d1bedbaad046f640eb Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 9 Apr 2022 19:17:28 +0200 Subject: mm: Add len and flags parameters to arch_get_mmap_end() Powerpc needs flags and len to make decision on arch_get_mmap_end(). So add them as parameters to arch_get_mmap_end(). Signed-off-by: Christophe Leroy Acked-by: Catalin Marinas Acked-by: Andrew Morton Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/b556daabe7d2bdb2361c4d6130280da7c1ba2c14.1649523076.git.christophe.leroy@csgroup.eu --- arch/arm64/include/asm/processor.h | 4 ++-- fs/hugetlbfs/inode.c | 6 +++--- include/linux/sched/mm.h | 2 +- mm/mmap.c | 4 ++-- 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux/sched') diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 73e38d9a540c..bd22d94e844d 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -92,8 +92,8 @@ #endif /* CONFIG_COMPAT */ #ifndef CONFIG_ARM64_FORCE_52BIT -#define arch_get_mmap_end(addr) ((addr > DEFAULT_MAP_WINDOW) ? TASK_SIZE :\ - DEFAULT_MAP_WINDOW) +#define arch_get_mmap_end(addr, len, flags) \ + (((addr) > DEFAULT_MAP_WINDOW) ? TASK_SIZE : DEFAULT_MAP_WINDOW) #define arch_get_mmap_base(addr, base) ((addr > DEFAULT_MAP_WINDOW) ? \ base + TASK_SIZE - DEFAULT_MAP_WINDOW :\ diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index ec611c7de9e3..6f863497bd69 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -205,7 +205,7 @@ hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, info.flags = 0; info.length = len; info.low_limit = current->mm->mmap_base; - info.high_limit = arch_get_mmap_end(addr); + info.high_limit = arch_get_mmap_end(addr, len, flags); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; return vm_unmapped_area(&info); @@ -236,7 +236,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = current->mm->mmap_base; - info.high_limit = arch_get_mmap_end(addr); + info.high_limit = arch_get_mmap_end(addr, len, flags); addr = vm_unmapped_area(&info); } @@ -251,7 +251,7 @@ generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct hstate *h = hstate_file(file); - const unsigned long mmap_end = arch_get_mmap_end(addr); + const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); if (len & ~huge_page_mask(h)) return -EINVAL; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index da3a32d05b34..8cd975a8bfeb 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -137,7 +137,7 @@ static inline void mm_update_next_owner(struct mm_struct *mm) #ifdef CONFIG_MMU #ifndef arch_get_mmap_end -#define arch_get_mmap_end(addr) (TASK_SIZE) +#define arch_get_mmap_end(addr, len, flags) (TASK_SIZE) #endif #ifndef arch_get_mmap_base diff --git a/mm/mmap.c b/mm/mmap.c index d2b6c3fbfb8c..e9b7d74e58bc 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2136,7 +2136,7 @@ generic_get_unmapped_area(struct file *filp, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vm_unmapped_area_info info; - const unsigned long mmap_end = arch_get_mmap_end(addr); + const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); if (len > mmap_end - mmap_min_addr) return -ENOMEM; @@ -2184,7 +2184,7 @@ generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; struct vm_unmapped_area_info info; - const unsigned long mmap_end = arch_get_mmap_end(addr); + const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); /* requested length too big for entire address space */ if (len > mmap_end - mmap_min_addr) -- cgit v1.2.3 From 343f4c49f2438d8920f1f76fa823ee59b91f02e4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 11 Apr 2022 11:40:14 -0500 Subject: kthread: Don't allocate kthread_struct for init and umh MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If kthread_is_per_cpu runs concurrently with free_kthread_struct the kthread_struct that was just freed may be read from. This bug was introduced by commit 40966e316f86 ("kthread: Ensure struct kthread is present for all kthreads"). When kthread_struct started to be allocated for all tasks that have PF_KTHREAD set. This in turn required the kthread_struct to be freed in kernel_execve and violated the assumption that kthread_struct will have the same lifetime as the task. Looking a bit deeper this only applies to callers of kernel_execve which is just the init process and the user mode helper processes. These processes really don't want to be kernel threads but are for historical reasons. Mostly that copy_thread does not know how to take a kernel mode function to the process with for processes without PF_KTHREAD or PF_IO_WORKER set. Solve this by not allocating kthread_struct for the init process and the user mode helper processes. This is done by adding a kthread member to struct kernel_clone_args. Setting kthread in fork_idle and kernel_thread. Adding user_mode_thread that works like kernel_thread except it does not set kthread. In fork only allocating the kthread_struct if .kthread is set. I have looked at kernel/kthread.c and since commit 40966e316f86 ("kthread: Ensure struct kthread is present for all kthreads") there have been no assumptions added that to_kthread or __to_kthread will not return NULL. There are a few callers of to_kthread or __to_kthread that assume a non-NULL struct kthread pointer will be returned. These functions are kthread_data(), kthread_parmme(), kthread_exit(), kthread(), kthread_park(), kthread_unpark(), kthread_stop(). All of those functions can reasonably expected to be called when it is know that a task is a kthread so that assumption seems reasonable. Cc: stable@vger.kernel.org Fixes: 40966e316f86 ("kthread: Ensure struct kthread is present for all kthreads") Reported-by: Максим Кутявин Link: https://lkml.kernel.org/r/20220506141512.516114-1-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- fs/exec.c | 6 ++++-- include/linux/sched/task.h | 2 ++ init/main.c | 2 +- kernel/fork.c | 22 ++++++++++++++++++++-- kernel/umh.c | 6 +++--- 5 files changed, 30 insertions(+), 8 deletions(-) (limited to 'include/linux/sched') diff --git a/fs/exec.c b/fs/exec.c index e3e55d5e0be1..75eb6e0ee7b2 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1308,8 +1308,6 @@ int begin_new_exec(struct linux_binprm * bprm) if (retval) goto out_unlock; - if (me->flags & PF_KTHREAD) - free_kthread_struct(me); me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD | PF_NOFREEZE | PF_NO_SETAFFINITY); flush_thread(); @@ -1955,6 +1953,10 @@ int kernel_execve(const char *kernel_filename, int fd = AT_FDCWD; int retval; + if (WARN_ON_ONCE((current->flags & PF_KTHREAD) && + (current->worker_private))) + return -EINVAL; + filename = getname_kernel(kernel_filename); if (IS_ERR(filename)) return PTR_ERR(filename); diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 719c9a6cac8d..4492266935dd 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -32,6 +32,7 @@ struct kernel_clone_args { size_t set_tid_size; int cgroup; int io_thread; + int kthread; struct cgroup *cgrp; struct css_set *cset; }; @@ -89,6 +90,7 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); +extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); diff --git a/init/main.c b/init/main.c index 98182c3c2c4b..39baac0211c6 100644 --- a/init/main.c +++ b/init/main.c @@ -688,7 +688,7 @@ noinline void __ref rest_init(void) * the init task will end up wanting to create kthreads, which, if * we schedule it before we create kthreadd, will OOPS. */ - pid = kernel_thread(kernel_init, NULL, CLONE_FS); + pid = user_mode_thread(kernel_init, NULL, CLONE_FS); /* * Pin init on the boot CPU. Task migration is not properly working * until sched_init_smp() has been run. It will set the allowed diff --git a/kernel/fork.c b/kernel/fork.c index 9796897560ab..27c5203750b4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2157,7 +2157,7 @@ static __latent_entropy struct task_struct *copy_process( p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); - if (p->flags & PF_KTHREAD) { + if (args->kthread) { if (!set_kthread_struct(p)) goto bad_fork_cleanup_delayacct; } @@ -2548,7 +2548,8 @@ struct task_struct * __init fork_idle(int cpu) { struct task_struct *task; struct kernel_clone_args args = { - .flags = CLONE_VM, + .flags = CLONE_VM, + .kthread = 1, }; task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args); @@ -2679,6 +2680,23 @@ pid_t kernel_clone(struct kernel_clone_args *args) * Create a kernel thread. */ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) +{ + struct kernel_clone_args args = { + .flags = ((lower_32_bits(flags) | CLONE_VM | + CLONE_UNTRACED) & ~CSIGNAL), + .exit_signal = (lower_32_bits(flags) & CSIGNAL), + .stack = (unsigned long)fn, + .stack_size = (unsigned long)arg, + .kthread = 1, + }; + + return kernel_clone(&args); +} + +/* + * Create a user mode thread. + */ +pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | diff --git a/kernel/umh.c b/kernel/umh.c index 36c123360ab8..b989736e8707 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -132,7 +132,7 @@ static void call_usermodehelper_exec_sync(struct subprocess_info *sub_info) /* If SIGCLD is ignored do_wait won't populate the status. */ kernel_sigaction(SIGCHLD, SIG_DFL); - pid = kernel_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD); + pid = user_mode_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD); if (pid < 0) sub_info->retval = pid; else @@ -171,8 +171,8 @@ static void call_usermodehelper_exec_work(struct work_struct *work) * want to pollute current->children, and we need a parent * that always ignores SIGCHLD to ensure auto-reaping. */ - pid = kernel_thread(call_usermodehelper_exec_async, sub_info, - CLONE_PARENT | SIGCHLD); + pid = user_mode_thread(call_usermodehelper_exec_async, sub_info, + CLONE_PARENT | SIGCHLD); if (pid < 0) { sub_info->retval = pid; umh_complete(sub_info); -- cgit v1.2.3 From c5febea0956fd3874e8fb59c6f84d68f128d68f8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 8 Apr 2022 18:07:50 -0500 Subject: fork: Pass struct kernel_clone_args into copy_thread With io_uring we have started supporting tasks that are for most purposes user space tasks that exclusively run code in kernel mode. The kernel task that exec's init and tasks that exec user mode helpers are also user mode tasks that just run kernel code until they call kernel execve. Pass kernel_clone_args into copy_thread so these oddball tasks can be supported more cleanly and easily. v2: Fix spelling of kenrel_clone_args on h8300 Link: https://lkml.kernel.org/r/20220506141512.516114-2-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- arch/alpha/kernel/process.c | 8 +++++--- arch/arc/kernel/process.c | 8 +++++--- arch/arm/kernel/process.c | 7 +++++-- arch/arm64/kernel/process.c | 7 +++++-- arch/csky/kernel/process.c | 10 +++++----- arch/h8300/kernel/process.c | 5 +++-- arch/hexagon/kernel/process.c | 7 +++++-- arch/ia64/kernel/process.c | 7 +++++-- arch/m68k/kernel/process.c | 7 +++++-- arch/microblaze/kernel/process.c | 7 +++++-- arch/mips/kernel/process.c | 8 +++++--- arch/nios2/kernel/process.c | 7 +++++-- arch/openrisc/kernel/process.c | 7 +++++-- arch/parisc/kernel/process.c | 7 +++++-- arch/powerpc/kernel/process.c | 8 +++++--- arch/riscv/kernel/process.c | 7 +++++-- arch/s390/kernel/process.c | 7 +++++-- arch/sh/kernel/process_32.c | 7 +++++-- arch/sparc/kernel/process_32.c | 7 +++++-- arch/sparc/kernel/process_64.c | 7 +++++-- arch/um/kernel/process.c | 7 +++++-- arch/x86/kernel/process.c | 7 +++++-- arch/xtensa/kernel/process.c | 8 +++++--- include/linux/sched/task.h | 3 +-- kernel/fork.c | 4 ++-- 25 files changed, 116 insertions(+), 58 deletions(-) (limited to 'include/linux/sched') diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 5f8527081da9..732e39217c7f 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -233,10 +233,12 @@ release_thread(struct task_struct *dead_task) /* * Copy architecture-specific thread state */ -int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long kthread_arg, struct task_struct *p, - unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long kthread_arg = args->stack_size; + unsigned long tls = args->tls; extern void ret_from_fork(void); extern void ret_from_kernel_thread(void); diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index 5f7f5aab361f..caf948ba647c 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -162,10 +162,12 @@ asmlinkage void ret_from_fork(void); * | user_r25 | * ------------------ <===== END of PAGE */ -int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long kthread_arg, struct task_struct *p, - unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long kthread_arg = args->stack_size; + unsigned long tls = args->tls; struct pt_regs *c_regs; /* child's pt_regs */ unsigned long *childksp; /* to unwind out of __switch_to() */ struct callee_regs *c_callee; /* child's callee regs */ diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 0617af11377f..8e13b426dd26 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -238,9 +238,12 @@ void release_thread(struct task_struct *dead_task) asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); -int copy_thread(unsigned long clone_flags, unsigned long stack_start, - unsigned long stk_sz, struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long stack_start = args->stack; + unsigned long stk_sz = args->stack_size; + unsigned long tls = args->tls; struct thread_info *thread = task_thread_info(p); struct pt_regs *childregs = task_pt_regs(p); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 7fa97df55e3a..e002f6681c8d 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -316,9 +316,12 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) asmlinkage void ret_from_fork(void) asm("ret_from_fork"); -int copy_thread(unsigned long clone_flags, unsigned long stack_start, - unsigned long stk_sz, struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long stack_start = args->stack; + unsigned long stk_sz = args->stack_size; + unsigned long tls = args->tls; struct pt_regs *childregs = task_pt_regs(p); memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context)); diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index 3d0ca22cd0e2..7dba33d37e1a 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -30,12 +30,12 @@ asmlinkage void ret_from_kernel_thread(void); */ void flush_thread(void){} -int copy_thread(unsigned long clone_flags, - unsigned long usp, - unsigned long kthread_arg, - struct task_struct *p, - unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long kthread_arg = args->stack_size; + unsigned long tls = args->tls; struct switch_stack *childstack; struct pt_regs *childregs = task_pt_regs(p); diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index 8833fa4f5d51..752cbd9b0bf6 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -105,9 +105,10 @@ void flush_thread(void) { } -int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long topstk, struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long usp = args->stack; + unsigned long topstk = args->stack_size; struct pt_regs *childregs; childregs = (struct pt_regs *) (THREAD_SIZE + task_stack_page(p)) - 1; diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index eab03c691f53..f1c1f6f21941 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -50,9 +50,12 @@ void arch_cpu_idle(void) /* * Copy architecture-specific thread state */ -int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, - struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long arg = args->stack_size; + unsigned long tls = args->tls; struct thread_info *ti = task_thread_info(p); struct hexagon_switch_stack *ss; struct pt_regs *childregs; diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index d7a256bd9d6b..10d41ded05a5 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -295,9 +295,12 @@ ia64_load_extra (struct task_struct *task) * so there is nothing to worry about. */ int -copy_thread(unsigned long clone_flags, unsigned long user_stack_base, - unsigned long user_stack_size, struct task_struct *p, unsigned long tls) +copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long user_stack_base = args->stack; + unsigned long user_stack_size = args->stack_size; + unsigned long tls = args->tls; extern char ia64_ret_from_clone; struct switch_stack *child_stack, *stack; unsigned long rbs, child_rbs, rbs_size; diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index a6030dbaa089..8ac575656fc4 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -138,9 +138,12 @@ asmlinkage int m68k_clone3(struct pt_regs *regs) return sys_clone3((struct clone_args __user *)regs->d1, regs->d2); } -int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, - struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long arg = args->stack_size; + unsigned long tls = args->tls; struct fork_frame { struct switch_stack sw; struct pt_regs regs; diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index 1b944d319d73..b5f549125c6a 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -52,9 +52,12 @@ void flush_thread(void) { } -int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, - struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long arg = args->stack_size; + unsigned long tls = args->tls; struct pt_regs *childregs = task_pt_regs(p); struct thread_info *ti = task_thread_info(p); diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index c2d5f4bfe1f3..a572d097b16b 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -105,10 +105,12 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) /* * Copy architecture-specific thread state */ -int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long kthread_arg, struct task_struct *p, - unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long kthread_arg = args->stack_size; + unsigned long tls = args->tls; struct thread_info *ti = task_thread_info(p); struct pt_regs *childregs, *regs = current_pt_regs(); unsigned long childksp; diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c index f8ea522a1588..98c4bfe972e0 100644 --- a/arch/nios2/kernel/process.c +++ b/arch/nios2/kernel/process.c @@ -100,9 +100,12 @@ void flush_thread(void) { } -int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, - struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long arg = args->stack_size; + unsigned long tls = args->tls; struct pt_regs *childregs = task_pt_regs(p); struct pt_regs *regs; struct switch_stack *stack; diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 3c0c91bcdcba..486e46dd5883 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -152,9 +152,12 @@ extern asmlinkage void ret_from_fork(void); */ int -copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, - struct task_struct *p, unsigned long tls) +copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long arg = args->stack_size; + unsigned long tls = args->tls; struct pt_regs *userregs; struct pt_regs *kregs; unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE; diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 28b6a2a5574c..129c17de45ba 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -206,9 +206,12 @@ arch_initcall(parisc_idle_init); * Copy architecture-specific thread state */ int -copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long kthread_arg, struct task_struct *p, unsigned long tls) +copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long kthread_arg = args->stack_size; + unsigned long tls = args->tls; struct pt_regs *cregs = &(p->thread.regs); void *stack = task_stack_page(p); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 984813a4d5dc..3fd67c861d54 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1716,10 +1716,12 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp) /* * Copy architecture-specific thread state */ -int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long kthread_arg, struct task_struct *p, - unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long kthread_arg = args->stack_size; + unsigned long tls = args->tls; struct pt_regs *childregs, *kregs; extern void ret_from_fork(void); extern void ret_from_fork_scv(void); diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 504b496787aa..334382731725 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -120,9 +120,12 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) return 0; } -int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, - struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long arg = args->stack_size; + unsigned long tls = args->tls; struct pt_regs *childregs = task_pt_regs(p); /* p->thread holds context to be restored by __switch_to() */ diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 71d86f73b02c..bb5daec39516 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -94,9 +94,12 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) return 0; } -int copy_thread(unsigned long clone_flags, unsigned long new_stackp, - unsigned long arg, struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long new_stackp = args->stack; + unsigned long arg = args->stack_size; + unsigned long tls = args->tls; struct fake_frame { struct stack_frame sf; diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index ca01286a0610..6023399b1892 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -92,9 +92,12 @@ void release_thread(struct task_struct *dead_task) asmlinkage void ret_from_fork(void); asmlinkage void ret_from_kernel_thread(void); -int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, - struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long arg = args->stack_size; + unsigned long tls = args->tls; struct thread_info *ti = task_thread_info(p); struct pt_regs *childregs; diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index 88c0c14aaff0..80e6775e18c0 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -259,9 +259,12 @@ clone_stackframe(struct sparc_stackf __user *dst, extern void ret_from_fork(void); extern void ret_from_kernel_thread(void); -int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, - struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long sp = args->stack; + unsigned long arg = args->stack_size; + unsigned long tls = args->tls; struct thread_info *ti = task_thread_info(p); struct pt_regs *childregs, *regs = current_pt_regs(); char *new_stack; diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 9a2ceb080ac9..38c46ca826d9 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -564,9 +564,12 @@ barf: * Parent --> %o0 == childs pid, %o1 == 0 * Child --> %o0 == parents pid, %o1 == 1 */ -int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, - struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long sp = args->stack; + unsigned long arg = args->stack_size; + unsigned long tls = args->tls; struct thread_info *t = task_thread_info(p); struct pt_regs *regs = current_pt_regs(); struct sparc_stackf *parent_sf; diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 80504680be08..fd2d2361484d 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -154,9 +154,12 @@ void fork_handler(void) userspace(¤t->thread.regs.regs, current_thread_info()->aux_fp_regs); } -int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, struct task_struct * p, unsigned long tls) +int copy_thread(struct task_struct * p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long sp = args->stack; + unsigned long arg = args->stack_size; + unsigned long tls = args->tls; void (*handler)(void); int kthread = current->flags & (PF_KTHREAD | PF_IO_WORKER); int ret = 0; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b370767f5b19..0fce52b10dc4 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -130,9 +130,12 @@ static int set_new_tls(struct task_struct *p, unsigned long tls) return do_set_thread_area_64(p, ARCH_SET_FS, tls); } -int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, - struct task_struct *p, unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long sp = args->stack; + unsigned long arg = args->stack_size; + unsigned long tls = args->tls; struct inactive_task_frame *frame; struct fork_frame *fork_frame; struct pt_regs *childregs; diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index e8bfbca5f001..15ce25073142 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -201,10 +201,12 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) * involved. Much simpler to just not copy those live frames across. */ -int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn, - unsigned long thread_fn_arg, struct task_struct *p, - unsigned long tls) +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + unsigned long clone_flags = args->flags; + unsigned long usp_thread_fn = args->stack; + unsigned long thread_fn_arg = args->stack_size; + unsigned long tls = args->tls; struct pt_regs *childregs = task_pt_regs(p); #if (XTENSA_HAVE_COPROCESSORS || XTENSA_HAVE_IO_PORTS) diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 4492266935dd..fcdcba231aac 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -68,8 +68,7 @@ extern void fork_init(void); extern void release_task(struct task_struct * p); -extern int copy_thread(unsigned long, unsigned long, unsigned long, - struct task_struct *, unsigned long); +extern int copy_thread(struct task_struct *, const struct kernel_clone_args *); extern void flush_thread(void); diff --git a/kernel/fork.c b/kernel/fork.c index 27c5203750b4..d39a248a8d8d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1979,7 +1979,7 @@ static __latent_entropy struct task_struct *copy_process( struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; - u64 clone_flags = args->flags; + const u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* @@ -2240,7 +2240,7 @@ static __latent_entropy struct task_struct *copy_process( retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; - retval = copy_thread(clone_flags, args->stack, args->stack_size, p, args->tls); + retval = copy_thread(p, args); if (retval) goto bad_fork_cleanup_io; -- cgit v1.2.3 From 36cb0e1cda645ee645b85a6ce652cb46a16e14e5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 11 Apr 2022 16:17:28 -0500 Subject: fork: Explicity test for idle tasks in copy_thread The architectures ia64 and parisc have special handling for the idle thread in copy_process. Add a flag named idle to kernel_clone_args and use it to explicity test if an idle process is being created. Fullfill the expectations of the rest of the copy_thread implemetations and pass a function pointer in .stack from fork_idle(). This makes what is happening in copy_thread better defined, and is useful to make idle threads less special. Link: https://lkml.kernel.org/r/20220506141512.516114-3-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- arch/ia64/kernel/process.c | 2 +- arch/parisc/kernel/process.c | 2 +- include/linux/sched/task.h | 1 + kernel/fork.c | 9 +++++++++ 4 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux/sched') diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 10d41ded05a5..8f010ae818bc 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -342,7 +342,7 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args) ia64_drop_fpu(p); /* don't pick up stale state from a CPU's fph */ if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { - if (unlikely(!user_stack_base)) { + if (unlikely(args->idle)) { /* fork_idle() called us */ return 0; } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 129c17de45ba..30a5874ca845 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -224,7 +224,7 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { /* kernel thread */ memset(cregs, 0, sizeof(struct pt_regs)); - if (!usp) /* idle thread */ + if (args->idle) /* idle thread */ return 0; /* Must exit via ret_from_kernel_thread in order * to call schedule_tail() diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index fcdcba231aac..3d6b99ce5408 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -33,6 +33,7 @@ struct kernel_clone_args { int cgroup; int io_thread; int kthread; + int idle; struct cgroup *cgrp; struct css_set *cset; }; diff --git a/kernel/fork.c b/kernel/fork.c index d39a248a8d8d..93d77ee921ff 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2544,12 +2544,21 @@ static inline void init_idle_pids(struct task_struct *idle) } } +static int idle_dummy(void *dummy) +{ + /* This function is never called */ + return 0; +} + struct task_struct * __init fork_idle(int cpu) { struct task_struct *task; struct kernel_clone_args args = { .flags = CLONE_VM, + .stack = (unsigned long)&idle_dummy, + .stack_size = (unsigned long)NULL, .kthread = 1, + .idle = 1, }; task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args); -- cgit v1.2.3 From 5bd2e97c868a8a44470950ed01846cab6328e540 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 12 Apr 2022 10:18:48 -0500 Subject: fork: Generalize PF_IO_WORKER handling Add fn and fn_arg members into struct kernel_clone_args and test for them in copy_thread (instead of testing for PF_KTHREAD | PF_IO_WORKER). This allows any task that wants to be a user space task that only runs in kernel mode to use this functionality. The code on x86 is an exception and still retains a PF_KTHREAD test because x86 unlikely everything else handles kthreads slightly differently than user space tasks that start with a function. The functions that created tasks that start with a function have been updated to set ".fn" and ".fn_arg" instead of ".stack" and ".stack_size". These functions are fork_idle(), create_io_thread(), kernel_thread(), and user_mode_thread(). Link: https://lkml.kernel.org/r/20220506141512.516114-4-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- arch/alpha/kernel/process.c | 7 +++---- arch/arc/kernel/process.c | 7 +++---- arch/arm/kernel/process.c | 7 +++---- arch/arm64/kernel/process.c | 7 +++---- arch/csky/kernel/process.c | 7 +++---- arch/h8300/kernel/process.c | 7 +++---- arch/hexagon/kernel/process.c | 7 +++---- arch/ia64/kernel/process.c | 6 +++--- arch/m68k/kernel/process.c | 7 +++---- arch/microblaze/kernel/process.c | 7 +++---- arch/mips/kernel/process.c | 7 +++---- arch/nios2/kernel/process.c | 7 +++---- arch/openrisc/kernel/process.c | 7 +++---- arch/parisc/kernel/process.c | 11 +++++------ arch/powerpc/kernel/process.c | 9 ++++----- arch/riscv/kernel/process.c | 7 +++---- arch/s390/kernel/process.c | 7 +++---- arch/sh/kernel/process_32.c | 7 +++---- arch/sparc/kernel/process_32.c | 7 +++---- arch/sparc/kernel/process_64.c | 7 +++---- arch/um/kernel/process.c | 10 ++++------ arch/x86/include/asm/fpu/sched.h | 2 +- arch/x86/include/asm/switch_to.h | 8 ++++---- arch/x86/kernel/fpu/core.c | 4 ++-- arch/x86/kernel/process.c | 13 ++++++------- arch/xtensa/kernel/process.c | 11 +++++------ include/linux/sched/task.h | 2 ++ kernel/fork.c | 16 ++++++++-------- 28 files changed, 95 insertions(+), 116 deletions(-) (limited to 'include/linux/sched') diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 732e39217c7f..6cbba7370b4e 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -237,7 +237,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp = args->stack; - unsigned long kthread_arg = args->stack_size; unsigned long tls = args->tls; extern void ret_from_fork(void); extern void ret_from_kernel_thread(void); @@ -251,13 +250,13 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) childti->pcb.ksp = (unsigned long) childstack; childti->pcb.flags = 1; /* set FEN, clear everything else */ - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { /* kernel thread */ memset(childstack, 0, sizeof(struct switch_stack) + sizeof(struct pt_regs)); childstack->r26 = (unsigned long) ret_from_kernel_thread; - childstack->r9 = usp; /* function */ - childstack->r10 = kthread_arg; + childstack->r9 = (unsigned long) args->fn; + childstack->r10 = (unsigned long) args->fn_arg; childregs->hae = alpha_mv.hae_cache; childti->pcb.usp = 0; return 0; diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index caf948ba647c..3369f0700702 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -166,7 +166,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp = args->stack; - unsigned long kthread_arg = args->stack_size; unsigned long tls = args->tls; struct pt_regs *c_regs; /* child's pt_regs */ unsigned long *childksp; /* to unwind out of __switch_to() */ @@ -193,11 +192,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) childksp[0] = 0; /* fp */ childksp[1] = (unsigned long)ret_from_fork; /* blink */ - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { memset(c_regs, 0, sizeof(struct pt_regs)); - c_callee->r13 = kthread_arg; - c_callee->r14 = usp; /* function */ + c_callee->r13 = (unsigned long)args->fn_arg; + c_callee->r14 = (unsigned long)args->fn; return 0; } diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 8e13b426dd26..3d9cace63884 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -242,7 +242,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long stack_start = args->stack; - unsigned long stk_sz = args->stack_size; unsigned long tls = args->tls; struct thread_info *thread = task_thread_info(p); struct pt_regs *childregs = task_pt_regs(p); @@ -259,15 +258,15 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) thread->cpu_domain = get_domain(); #endif - if (likely(!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))) { + if (likely(!args->fn)) { *childregs = *current_pt_regs(); childregs->ARM_r0 = 0; if (stack_start) childregs->ARM_sp = stack_start; } else { memset(childregs, 0, sizeof(struct pt_regs)); - thread->cpu_context.r4 = stk_sz; - thread->cpu_context.r5 = stack_start; + thread->cpu_context.r4 = (unsigned long)args->fn_arg; + thread->cpu_context.r5 = (unsigned long)args->fn; childregs->ARM_cpsr = SVC_MODE; } thread->cpu_context.pc = (unsigned long)ret_from_fork; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index e002f6681c8d..d0ef05c661b0 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -320,7 +320,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long stack_start = args->stack; - unsigned long stk_sz = args->stack_size; unsigned long tls = args->tls; struct pt_regs *childregs = task_pt_regs(p); @@ -337,7 +336,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) ptrauth_thread_init_kernel(p); - if (likely(!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))) { + if (likely(!args->fn)) { *childregs = *current_pt_regs(); childregs->regs[0] = 0; @@ -371,8 +370,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) memset(childregs, 0, sizeof(struct pt_regs)); childregs->pstate = PSR_MODE_EL1h | PSR_IL_BIT; - p->thread.cpu_context.x19 = stack_start; - p->thread.cpu_context.x20 = stk_sz; + p->thread.cpu_context.x19 = (unsigned long)args->fn; + p->thread.cpu_context.x20 = (unsigned long)args->fn_arg; } p->thread.cpu_context.pc = (unsigned long)ret_from_fork; p->thread.cpu_context.sp = (unsigned long)childregs; diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index 7dba33d37e1a..9af49aea1c3b 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -34,7 +34,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp = args->stack; - unsigned long kthread_arg = args->stack_size; unsigned long tls = args->tls; struct switch_stack *childstack; struct pt_regs *childregs = task_pt_regs(p); @@ -49,11 +48,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) /* setup thread.sp for switch_to !!! */ p->thread.sp = (unsigned long)childstack; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { memset(childregs, 0, sizeof(struct pt_regs)); childstack->r15 = (unsigned long) ret_from_kernel_thread; - childstack->r10 = kthread_arg; - childstack->r9 = usp; + childstack->r10 = (unsigned long) args->fn_arg; + childstack->r9 = (unsigned long) args->fn; childregs->sr = mfcr("psr"); } else { *childregs = *(current_pt_regs()); diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index 752cbd9b0bf6..9028262c96a9 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -108,16 +108,15 @@ void flush_thread(void) int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long usp = args->stack; - unsigned long topstk = args->stack_size; struct pt_regs *childregs; childregs = (struct pt_regs *) (THREAD_SIZE + task_stack_page(p)) - 1; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { memset(childregs, 0, sizeof(struct pt_regs)); childregs->retpc = (unsigned long) ret_from_kernel_thread; - childregs->er4 = topstk; /* arg */ - childregs->er5 = usp; /* fn */ + childregs->er4 = (unsigned long) args->fn_arg; + childregs->er5 = (unsigned long) args->fn; } else { *childregs = *current_pt_regs(); childregs->er0 = 0; diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index f1c1f6f21941..f0552f98a7ba 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -54,7 +54,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp = args->stack; - unsigned long arg = args->stack_size; unsigned long tls = args->tls; struct thread_info *ti = task_thread_info(p); struct hexagon_switch_stack *ss; @@ -76,11 +75,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) sizeof(*ss)); ss->lr = (unsigned long)ret_from_fork; p->thread.switch_sp = ss; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { memset(childregs, 0, sizeof(struct pt_regs)); /* r24 <- fn, r25 <- arg */ - ss->r24 = usp; - ss->r25 = arg; + ss->r24 = (unsigned long)args->fn; + ss->r25 = (unsigned long)args->fn_arg; pt_set_kmode(childregs); return 0; } diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 8f010ae818bc..167b1765bea1 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -341,14 +341,14 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args) ia64_drop_fpu(p); /* don't pick up stale state from a CPU's fph */ - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { if (unlikely(args->idle)) { /* fork_idle() called us */ return 0; } memset(child_stack, 0, sizeof(*child_ptregs) + sizeof(*child_stack)); - child_stack->r4 = user_stack_base; /* payload */ - child_stack->r5 = user_stack_size; /* argument */ + child_stack->r4 = (unsigned long) args->fn; + child_stack->r5 = (unsigned long) args->fn_arg; /* * Preserve PSR bits, except for bits 32-34 and 37-45, * which we can't read. diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index 8ac575656fc4..221feb0269f1 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -142,7 +142,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp = args->stack; - unsigned long arg = args->stack_size; unsigned long tls = args->tls; struct fork_frame { struct switch_stack sw; @@ -160,12 +159,12 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) */ p->thread.fc = USER_DATA; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { /* kernel thread */ memset(frame, 0, sizeof(struct fork_frame)); frame->regs.sr = PS_S; - frame->sw.a3 = usp; /* function */ - frame->sw.d7 = arg; + frame->sw.a3 = (unsigned long)args->fn; + frame->sw.d7 = (unsigned long)args->fn_arg; frame->sw.retpc = (unsigned long)ret_from_kernel_thread; p->thread.usp = 0; return 0; diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index b5f549125c6a..3c6241bcaea8 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -56,19 +56,18 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp = args->stack; - unsigned long arg = args->stack_size; unsigned long tls = args->tls; struct pt_regs *childregs = task_pt_regs(p); struct thread_info *ti = task_thread_info(p); - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { /* if we're creating a new kernel thread then just zeroing all * the registers. That's OK for a brand new thread.*/ memset(childregs, 0, sizeof(struct pt_regs)); memset(&ti->cpu_context, 0, sizeof(struct cpu_context)); ti->cpu_context.r1 = (unsigned long)childregs; - ti->cpu_context.r20 = (unsigned long)usp; /* fn */ - ti->cpu_context.r19 = (unsigned long)arg; + ti->cpu_context.r20 = (unsigned long)args->fn; + ti->cpu_context.r19 = (unsigned long)args->fn_arg; childregs->pt_mode = 1; local_save_flags(childregs->msr); ti->cpu_context.msr = childregs->msr & ~MSR_IE; diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index a572d097b16b..35b912bce429 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -109,7 +109,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp = args->stack; - unsigned long kthread_arg = args->stack_size; unsigned long tls = args->tls; struct thread_info *ti = task_thread_info(p); struct pt_regs *childregs, *regs = current_pt_regs(); @@ -122,12 +121,12 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) /* Put the stack after the struct pt_regs. */ childksp = (unsigned long) childregs; p->thread.cp0_status = (read_c0_status() & ~(ST0_CU2|ST0_CU1)) | ST0_KERNEL_CUMASK; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { /* kernel thread */ unsigned long status = p->thread.cp0_status; memset(childregs, 0, sizeof(struct pt_regs)); - p->thread.reg16 = usp; /* fn */ - p->thread.reg17 = kthread_arg; + p->thread.reg16 = (unsigned long)args->fn; + p->thread.reg17 = (unsigned long)args->fn_arg; p->thread.reg29 = childksp; p->thread.reg31 = (unsigned long) ret_from_kernel_thread; #if defined(CONFIG_CPU_R3000) diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c index 98c4bfe972e0..29593b98567d 100644 --- a/arch/nios2/kernel/process.c +++ b/arch/nios2/kernel/process.c @@ -104,7 +104,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp = args->stack; - unsigned long arg = args->stack_size; unsigned long tls = args->tls; struct pt_regs *childregs = task_pt_regs(p); struct pt_regs *regs; @@ -112,12 +111,12 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) struct switch_stack *childstack = ((struct switch_stack *)childregs) - 1; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { memset(childstack, 0, sizeof(struct switch_stack) + sizeof(struct pt_regs)); - childstack->r16 = usp; /* fn */ - childstack->r17 = arg; + childstack->r16 = (unsigned long) args->fn; + childstack->r17 = (unsigned long) args->fn_arg; childstack->ra = (unsigned long) ret_from_kernel_thread; childregs->estatus = STATUS_PIE; childregs->sp = (unsigned long) childstack; diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 486e46dd5883..d9697cc9bc4d 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -156,7 +156,6 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp = args->stack; - unsigned long arg = args->stack_size; unsigned long tls = args->tls; struct pt_regs *userregs; struct pt_regs *kregs; @@ -175,10 +174,10 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args) sp -= sizeof(struct pt_regs); kregs = (struct pt_regs *)sp; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { memset(kregs, 0, sizeof(struct pt_regs)); - kregs->gpr[20] = usp; /* fn, kernel thread */ - kregs->gpr[22] = arg; + kregs->gpr[20] = (unsigned long)args->fn; + kregs->gpr[22] = (unsigned long)args->fn_arg; } else { *userregs = *current_pt_regs(); diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 30a5874ca845..a6a2a558fc5b 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -210,7 +210,6 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp = args->stack; - unsigned long kthread_arg = args->stack_size; unsigned long tls = args->tls; struct pt_regs *cregs = &(p->thread.regs); void *stack = task_stack_page(p); @@ -221,7 +220,7 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args) extern void * const ret_from_kernel_thread; extern void * const child_return; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { /* kernel thread */ memset(cregs, 0, sizeof(struct pt_regs)); if (args->idle) /* idle thread */ @@ -236,12 +235,12 @@ copy_thread(struct task_struct *p, const struct kernel_clone_args *args) * ret_from_kernel_thread. */ #ifdef CONFIG_64BIT - cregs->gr[27] = ((unsigned long *)usp)[3]; - cregs->gr[26] = ((unsigned long *)usp)[2]; + cregs->gr[27] = ((unsigned long *)args->fn)[3]; + cregs->gr[26] = ((unsigned long *)args->fn)[2]; #else - cregs->gr[26] = usp; + cregs->gr[26] = (unsigned long) args->fn; #endif - cregs->gr[25] = kthread_arg; + cregs->gr[25] = (unsigned long) args->fn_arg; } else { /* user thread */ /* usp must be word aligned. This also prevents users from diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 3fd67c861d54..4f367bb68906 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1720,7 +1720,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp = args->stack; - unsigned long kthread_arg = args->stack_size; unsigned long tls = args->tls; struct pt_regs *childregs, *kregs; extern void ret_from_fork(void); @@ -1738,18 +1737,18 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) /* Copy registers */ sp -= sizeof(struct pt_regs); childregs = (struct pt_regs *) sp; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + sizeof(struct pt_regs); /* function */ - if (usp) - childregs->gpr[14] = ppc_function_entry((void *)usp); + if (args->fn) + childregs->gpr[14] = ppc_function_entry((void *)args->fn); #ifdef CONFIG_PPC64 clear_tsk_thread_flag(p, TIF_32BIT); childregs->softe = IRQS_ENABLED; #endif - childregs->gpr[15] = kthread_arg; + childregs->gpr[15] = (unsigned long)args->fn_arg; p->thread.regs = NULL; /* no user register state */ ti->flags |= _TIF_RESTOREALL; f = ret_from_kernel_thread; diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 334382731725..24efabdbc551 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -124,12 +124,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp = args->stack; - unsigned long arg = args->stack_size; unsigned long tls = args->tls; struct pt_regs *childregs = task_pt_regs(p); /* p->thread holds context to be restored by __switch_to() */ - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { /* Kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); childregs->gp = gp_in_global; @@ -137,8 +136,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) childregs->status = SR_PP | SR_PIE; p->thread.ra = (unsigned long)ret_from_kernel_thread; - p->thread.s[0] = usp; /* fn */ - p->thread.s[1] = arg; + p->thread.s[0] = (unsigned long)args->fn; + p->thread.s[1] = (unsigned long)args->fn_arg; } else { *childregs = *(current_pt_regs()); if (usp) /* User fork */ diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index bb5daec39516..89949b9f3cf8 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -98,7 +98,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long new_stackp = args->stack; - unsigned long arg = args->stack_size; unsigned long tls = args->tls; struct fake_frame { @@ -133,15 +132,15 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) frame->sf.gprs[9] = (unsigned long)frame; /* Store access registers to kernel stack of new process. */ - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { /* kernel thread */ memset(&frame->childregs, 0, sizeof(struct pt_regs)); frame->childregs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; frame->childregs.psw.addr = (unsigned long)__ret_from_fork; - frame->childregs.gprs[9] = new_stackp; /* function */ - frame->childregs.gprs[10] = arg; + frame->childregs.gprs[9] = (unsigned long)args->fn; + frame->childregs.gprs[10] = (unsigned long)args->fn_arg; frame->childregs.orig_gpr2 = -1; frame->childregs.last_break = 1; return 0; diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 6023399b1892..a808843375e7 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -96,7 +96,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp = args->stack; - unsigned long arg = args->stack_size; unsigned long tls = args->tls; struct thread_info *ti = task_thread_info(p); struct pt_regs *childregs; @@ -117,11 +116,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) childregs = task_pt_regs(p); p->thread.sp = (unsigned long) childregs; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { memset(childregs, 0, sizeof(struct pt_regs)); p->thread.pc = (unsigned long) ret_from_kernel_thread; - childregs->regs[4] = arg; - childregs->regs[5] = usp; + childregs->regs[4] = (unsigned long) args->fn_arg; + childregs->regs[5] = (unsigned long) args->fn; childregs->sr = SR_MD; #if defined(CONFIG_SH_FPU) childregs->sr |= SR_FD; diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index 80e6775e18c0..33b0215a4182 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -263,7 +263,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long sp = args->stack; - unsigned long arg = args->stack_size; unsigned long tls = args->tls; struct thread_info *ti = task_thread_info(p); struct pt_regs *childregs, *regs = current_pt_regs(); @@ -299,13 +298,13 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) ti->ksp = (unsigned long) new_stack; p->thread.kregs = childregs; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { extern int nwindows; unsigned long psr; memset(new_stack, 0, STACKFRAME_SZ + TRACEREG_SZ); ti->kpc = (((unsigned long) ret_from_kernel_thread) - 0x8); - childregs->u_regs[UREG_G1] = sp; /* function */ - childregs->u_regs[UREG_G2] = arg; + childregs->u_regs[UREG_G1] = (unsigned long) args->fn; + childregs->u_regs[UREG_G2] = (unsigned long) args->fn_arg; psr = childregs->psr = get_psr(); ti->kpsr = psr | PSR_PIL; ti->kwim = 1 << (((psr & PSR_CWP) + 1) % nwindows); diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 38c46ca826d9..6335b698a4b4 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -568,7 +568,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long sp = args->stack; - unsigned long arg = args->stack_size; unsigned long tls = args->tls; struct thread_info *t = task_thread_info(p); struct pt_regs *regs = current_pt_regs(); @@ -587,12 +586,12 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) sizeof(struct sparc_stackf)); t->fpsaved[0] = 0; - if (unlikely(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (unlikely(args->fn)) { memset(child_trap_frame, 0, child_stack_sz); __thread_flag_byte_ptr(t)[TI_FLAG_BYTE_CWP] = (current_pt_regs()->tstate + 1) & TSTATE_CWP; - t->kregs->u_regs[UREG_G1] = sp; /* function */ - t->kregs->u_regs[UREG_G2] = arg; + t->kregs->u_regs[UREG_G1] = (unsigned long) args->fn; + t->kregs->u_regs[UREG_G2] = (unsigned long) args->fn_arg; return 0; } diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index fd2d2361484d..181cc9aafb25 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -158,15 +158,13 @@ int copy_thread(struct task_struct * p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long sp = args->stack; - unsigned long arg = args->stack_size; unsigned long tls = args->tls; void (*handler)(void); - int kthread = current->flags & (PF_KTHREAD | PF_IO_WORKER); int ret = 0; p->thread = (struct thread_struct) INIT_THREAD; - if (!kthread) { + if (!args->fn) { memcpy(&p->thread.regs.regs, current_pt_regs(), sizeof(p->thread.regs.regs)); PT_REGS_SET_SYSCALL_RETURN(&p->thread.regs, 0); @@ -178,14 +176,14 @@ int copy_thread(struct task_struct * p, const struct kernel_clone_args *args) arch_copy_thread(¤t->thread.arch, &p->thread.arch); } else { get_safe_registers(p->thread.regs.regs.gp, p->thread.regs.regs.fp); - p->thread.request.u.thread.proc = (int (*)(void *))sp; - p->thread.request.u.thread.arg = (void *)arg; + p->thread.request.u.thread.proc = args->fn; + p->thread.request.u.thread.arg = args->fn_arg; handler = new_thread_handler; } new_thread(task_stack_page(p), &p->thread.switch_buf, handler); - if (!kthread) { + if (!args->fn) { clear_flushed_tls(p); /* diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h index 99a8820e8cc4..b2486b2cbc6e 100644 --- a/arch/x86/include/asm/fpu/sched.h +++ b/arch/x86/include/asm/fpu/sched.h @@ -11,7 +11,7 @@ extern void save_fpregs_to_fpstate(struct fpu *fpu); extern void fpu__drop(struct fpu *fpu); -extern int fpu_clone(struct task_struct *dst, unsigned long clone_flags); +extern int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal); extern void fpu_flush_thread(void); /* diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index b5f0d2ff47e4..c08eb0fdd11f 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -78,13 +78,13 @@ static inline void update_task_stack(struct task_struct *task) } static inline void kthread_frame_init(struct inactive_task_frame *frame, - unsigned long fun, unsigned long arg) + int (*fun)(void *), void *arg) { - frame->bx = fun; + frame->bx = (unsigned long)fun; #ifdef CONFIG_X86_32 - frame->di = arg; + frame->di = (unsigned long)arg; #else - frame->r12 = arg; + frame->r12 = (unsigned long)arg; #endif } diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index c049561f373a..fbade5a3975b 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -556,7 +556,7 @@ static inline void fpu_inherit_perms(struct fpu *dst_fpu) } /* Clone current's FPU state on fork */ -int fpu_clone(struct task_struct *dst, unsigned long clone_flags) +int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal) { struct fpu *src_fpu = ¤t->thread.fpu; struct fpu *dst_fpu = &dst->thread.fpu; @@ -579,7 +579,7 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags) * No FPU state inheritance for kernel threads and IO * worker threads. */ - if (dst->flags & (PF_KTHREAD | PF_IO_WORKER)) { + if (minimal) { /* Clear out the minimal state */ memcpy(&dst_fpu->fpstate->regs, &init_fpstate.regs, init_fpstate_copy_size()); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 0fce52b10dc4..d20eaad52a85 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -134,7 +134,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long sp = args->stack; - unsigned long arg = args->stack_size; unsigned long tls = args->tls; struct inactive_task_frame *frame; struct fork_frame *fork_frame; @@ -172,13 +171,13 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) frame->flags = X86_EFLAGS_FIXED; #endif - fpu_clone(p, clone_flags); + fpu_clone(p, clone_flags, args->fn); /* Kernel thread ? */ if (unlikely(p->flags & PF_KTHREAD)) { p->thread.pkru = pkru_get_init_value(); memset(childregs, 0, sizeof(struct pt_regs)); - kthread_frame_init(frame, sp, arg); + kthread_frame_init(frame, args->fn, args->fn_arg); return 0; } @@ -198,10 +197,10 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) task_user_gs(p) = get_user_gs(current_pt_regs()); #endif - if (unlikely(p->flags & PF_IO_WORKER)) { + if (unlikely(args->fn)) { /* - * An IO thread is a user space thread, but it doesn't - * return to ret_after_fork(). + * A user space thread, but it doesn't return to + * ret_after_fork(). * * In order to indicate that to tools like gdb, * we reset the stack and instruction pointers. @@ -211,7 +210,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) */ childregs->sp = 0; childregs->ip = 0; - kthread_frame_init(frame, sp, arg); + kthread_frame_init(frame, args->fn, args->fn_arg); return 0; } diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 15ce25073142..c3751cc88e5d 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -205,7 +205,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; unsigned long usp_thread_fn = args->stack; - unsigned long thread_fn_arg = args->stack_size; unsigned long tls = args->tls; struct pt_regs *childregs = task_pt_regs(p); @@ -226,7 +225,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) #error Unsupported Xtensa ABI #endif - if (!(p->flags & (PF_KTHREAD | PF_IO_WORKER))) { + if (!args->fn) { struct pt_regs *regs = current_pt_regs(); unsigned long usp = usp_thread_fn ? usp_thread_fn : regs->areg[1]; @@ -278,15 +277,15 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) * Window underflow will load registers from the * spill slots on the stack on return from _switch_to. */ - SPILL_SLOT(childregs, 2) = usp_thread_fn; - SPILL_SLOT(childregs, 3) = thread_fn_arg; + SPILL_SLOT(childregs, 2) = (unsigned long)args->fn; + SPILL_SLOT(childregs, 3) = (unsigned long)args->fn_arg; #elif defined(__XTENSA_CALL0_ABI__) /* * a12 = thread_fn, a13 = thread_fn arg. * _switch_to epilogue will load registers from the stack. */ - ((unsigned long *)p->thread.sp)[0] = usp_thread_fn; - ((unsigned long *)p->thread.sp)[1] = thread_fn_arg; + ((unsigned long *)p->thread.sp)[0] = (unsigned long)args->fn; + ((unsigned long *)p->thread.sp)[1] = (unsigned long)args->fn_arg; #else #error Unsupported Xtensa ABI #endif diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 3d6b99ce5408..505aaf9fe477 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -34,6 +34,8 @@ struct kernel_clone_args { int io_thread; int kthread; int idle; + int (*fn)(void *); + void *fn_arg; struct cgroup *cgrp; struct css_set *cset; }; diff --git a/kernel/fork.c b/kernel/fork.c index 93d77ee921ff..8e17c3fbce42 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2555,8 +2555,8 @@ struct task_struct * __init fork_idle(int cpu) struct task_struct *task; struct kernel_clone_args args = { .flags = CLONE_VM, - .stack = (unsigned long)&idle_dummy, - .stack_size = (unsigned long)NULL, + .fn = &idle_dummy, + .fn_arg = NULL, .kthread = 1, .idle = 1, }; @@ -2589,8 +2589,8 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), - .stack = (unsigned long)fn, - .stack_size = (unsigned long)arg, + .fn = fn, + .fn_arg = arg, .io_thread = 1, }; @@ -2694,8 +2694,8 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), - .stack = (unsigned long)fn, - .stack_size = (unsigned long)arg, + .fn = fn, + .fn_arg = arg, .kthread = 1, }; @@ -2711,8 +2711,8 @@ pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags) .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), - .stack = (unsigned long)fn, - .stack_size = (unsigned long)arg, + .fn = fn, + .fn_arg = arg, }; return kernel_clone(&args); -- cgit v1.2.3 From 2500ad1c7fa42ad734677853961a3a8bec0772c5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 29 Apr 2022 08:43:34 -0500 Subject: ptrace: Don't change __state Stop playing with tsk->__state to remove TASK_WAKEKILL while a ptrace command is executing. Instead remove TASK_WAKEKILL from the definition of TASK_TRACED, and implement a new jobctl flag TASK_PTRACE_FROZEN. This new flag is set in jobctl_freeze_task and cleared when ptrace_stop is awoken or in jobctl_unfreeze_task (when ptrace_stop remains asleep). In signal_wake_up add __TASK_TRACED to state along with TASK_WAKEKILL when the wake up is for a fatal signal. Skip adding __TASK_TRACED when TASK_PTRACE_FROZEN is not set. This has the same effect as changing TASK_TRACED to __TASK_TRACED as all of the wake_ups that use TASK_KILLABLE go through signal_wake_up. Handle a ptrace_stop being called with a pending fatal signal. Previously it would have been handled by schedule simply failing to sleep. As TASK_WAKEKILL is no longer part of TASK_TRACED schedule will sleep with a fatal_signal_pending. The code in signal_wake_up guarantees that the code will be awaked by any fatal signal that codes after TASK_TRACED is set. Previously the __state value of __TASK_TRACED was changed to TASK_RUNNING when woken up or back to TASK_TRACED when the code was left in ptrace_stop. Now when woken up ptrace_stop now clears JOBCTL_PTRACE_FROZEN and when left sleeping ptrace_unfreezed_traced clears JOBCTL_PTRACE_FROZEN. Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-10-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched.h | 2 +- include/linux/sched/jobctl.h | 2 ++ include/linux/sched/signal.h | 5 +++-- kernel/ptrace.c | 21 ++++++++------------- kernel/sched/core.c | 5 +---- kernel/signal.c | 14 ++++++-------- 6 files changed, 21 insertions(+), 28 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched.h b/include/linux/sched.h index d5e3c00b74e1..610f2fdb1e2c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -103,7 +103,7 @@ struct task_group; /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) -#define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED) +#define TASK_TRACED __TASK_TRACED #define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h index fa067de9f1a9..d556c3425963 100644 --- a/include/linux/sched/jobctl.h +++ b/include/linux/sched/jobctl.h @@ -19,6 +19,7 @@ struct task_struct; #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ #define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ #define JOBCTL_TRAP_FREEZE_BIT 23 /* trap for cgroup freezer */ +#define JOBCTL_PTRACE_FROZEN_BIT 24 /* frozen for ptrace */ #define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) @@ -28,6 +29,7 @@ struct task_struct; #define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) #define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) #define JOBCTL_TRAP_FREEZE (1UL << JOBCTL_TRAP_FREEZE_BIT) +#define JOBCTL_PTRACE_FROZEN (1UL << JOBCTL_PTRACE_FROZEN_BIT) #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) #define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..e66948abbee4 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -435,9 +435,10 @@ extern void calculate_sigpending(void); extern void signal_wake_up_state(struct task_struct *t, unsigned int state); -static inline void signal_wake_up(struct task_struct *t, bool resume) +static inline void signal_wake_up(struct task_struct *t, bool fatal) { - signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0); + fatal = fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN); + signal_wake_up_state(t, fatal ? TASK_WAKEKILL | __TASK_TRACED : 0); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 05953ac9f7bd..83ed28262708 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -197,7 +197,7 @@ static bool ptrace_freeze_traced(struct task_struct *task) spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && !__fatal_signal_pending(task)) { - WRITE_ONCE(task->__state, __TASK_TRACED); + task->jobctl |= JOBCTL_PTRACE_FROZEN; ret = true; } spin_unlock_irq(&task->sighand->siglock); @@ -207,23 +207,19 @@ static bool ptrace_freeze_traced(struct task_struct *task) static void ptrace_unfreeze_traced(struct task_struct *task) { - if (READ_ONCE(task->__state) != __TASK_TRACED) - return; - - WARN_ON(!task->ptrace || task->parent != current); + unsigned long flags; /* - * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely. - * Recheck state under the lock to close this race. + * The child may be awake and may have cleared + * JOBCTL_PTRACE_FROZEN (see ptrace_resume). The child will + * not set JOBCTL_PTRACE_FROZEN or enter __TASK_TRACED anew. */ - spin_lock_irq(&task->sighand->siglock); - if (READ_ONCE(task->__state) == __TASK_TRACED) { + if (lock_task_sighand(task, &flags)) { + task->jobctl &= ~JOBCTL_PTRACE_FROZEN; if (__fatal_signal_pending(task)) wake_up_state(task, __TASK_TRACED); - else - WRITE_ONCE(task->__state, TASK_TRACED); + unlock_task_sighand(task, &flags); } - spin_unlock_irq(&task->sighand->siglock); } /** @@ -256,7 +252,6 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) */ read_lock(&tasklist_lock); if (child->ptrace && child->parent == current) { - WARN_ON(READ_ONCE(child->__state) == __TASK_TRACED); /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d575b4914925..3c351707e830 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6304,10 +6304,7 @@ static void __sched notrace __schedule(unsigned int sched_mode) /* * We must load prev->state once (task_struct::state is volatile), such - * that: - * - * - we form a control dependency vs deactivate_task() below. - * - ptrace_{,un}freeze_traced() can change ->state underneath us. + * that we form a control dependency vs deactivate_task() below. */ prev_state = READ_ONCE(prev->__state); if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) { diff --git a/kernel/signal.c b/kernel/signal.c index d2d0c753156c..a58b68a2d3c6 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2209,14 +2209,12 @@ static int ptrace_stop(int exit_code, int why, unsigned long message, } /* - * schedule() will not sleep if there is a pending signal that - * can awaken the task. - * - * After this point ptrace_signal_wake_up will clear TASK_TRACED - * if ptrace_unlink happens. Handle previous ptrace_unlinks - * here to prevent ptrace_stop sleeping in schedule. + * After this point ptrace_signal_wake_up or signal_wake_up + * will clear TASK_TRACED if ptrace_unlink happens or a fatal + * signal comes in. Handle previous ptrace_unlinks and fatal + * signals here to prevent ptrace_stop sleeping in schedule. */ - if (!current->ptrace) + if (!current->ptrace || __fatal_signal_pending(current)) return exit_code; set_special_state(TASK_TRACED); @@ -2305,7 +2303,7 @@ static int ptrace_stop(int exit_code, int why, unsigned long message, current->exit_code = 0; /* LISTENING can be set only during STOP traps, clear it */ - current->jobctl &= ~JOBCTL_LISTENING; + current->jobctl &= ~(JOBCTL_LISTENING | JOBCTL_PTRACE_FROZEN); /* * Queued signals ignored us while we were stopped for tracing. -- cgit v1.2.3 From 31cae1eaae4fd65095ad6a3659db467bc3c2599e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 3 May 2022 15:57:47 -0500 Subject: sched,signal,ptrace: Rework TASK_TRACED, TASK_STOPPED state Currently ptrace_stop() / do_signal_stop() rely on the special states TASK_TRACED and TASK_STOPPED resp. to keep unique state. That is, this state exists only in task->__state and nowhere else. There's two spots of bother with this: - PREEMPT_RT has task->saved_state which complicates matters, meaning task_is_{traced,stopped}() needs to check an additional variable. - An alternative freezer implementation that itself relies on a special TASK state would loose TASK_TRACED/TASK_STOPPED and will result in misbehaviour. As such, add additional state to task->jobctl to track this state outside of task->__state. NOTE: this doesn't actually fix anything yet, just adds extra state. --EWB * didn't add a unnecessary newline in signal.h * Update t->jobctl in signal_wake_up and ptrace_signal_wake_up instead of in signal_wake_up_state. This prevents the clearing of TASK_STOPPED and TASK_TRACED from getting lost. * Added warnings if JOBCTL_STOPPED or JOBCTL_TRACED are not cleared Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220421150654.757693825@infradead.org Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-12-ebiederm@xmission.com Signed-off-by: Eric W. Biederman --- include/linux/sched.h | 8 +++----- include/linux/sched/jobctl.h | 6 ++++++ include/linux/sched/signal.h | 19 +++++++++++++++---- kernel/ptrace.c | 16 +++++++++++++--- kernel/signal.c | 10 ++++++++-- 5 files changed, 45 insertions(+), 14 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched.h b/include/linux/sched.h index 610f2fdb1e2c..cbe5c899599c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -118,11 +118,9 @@ struct task_group; #define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) -#define task_is_traced(task) ((READ_ONCE(task->__state) & __TASK_TRACED) != 0) - -#define task_is_stopped(task) ((READ_ONCE(task->__state) & __TASK_STOPPED) != 0) - -#define task_is_stopped_or_traced(task) ((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0) +#define task_is_traced(task) ((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0) +#define task_is_stopped(task) ((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0) +#define task_is_stopped_or_traced(task) ((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0) /* * Special states are those that do not use the normal wait-loop pattern. See diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h index d556c3425963..68876d0a7ef9 100644 --- a/include/linux/sched/jobctl.h +++ b/include/linux/sched/jobctl.h @@ -21,6 +21,9 @@ struct task_struct; #define JOBCTL_TRAP_FREEZE_BIT 23 /* trap for cgroup freezer */ #define JOBCTL_PTRACE_FROZEN_BIT 24 /* frozen for ptrace */ +#define JOBCTL_STOPPED_BIT 26 /* do_signal_stop() */ +#define JOBCTL_TRACED_BIT 27 /* ptrace_stop() */ + #define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) #define JOBCTL_STOP_CONSUME (1UL << JOBCTL_STOP_CONSUME_BIT) @@ -31,6 +34,9 @@ struct task_struct; #define JOBCTL_TRAP_FREEZE (1UL << JOBCTL_TRAP_FREEZE_BIT) #define JOBCTL_PTRACE_FROZEN (1UL << JOBCTL_PTRACE_FROZEN_BIT) +#define JOBCTL_STOPPED (1UL << JOBCTL_STOPPED_BIT) +#define JOBCTL_TRACED (1UL << JOBCTL_TRACED_BIT) + #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) #define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index e66948abbee4..07ba3404fcde 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -294,8 +294,10 @@ static inline int kernel_dequeue_signal(void) static inline void kernel_signal_stop(void) { spin_lock_irq(¤t->sighand->siglock); - if (current->jobctl & JOBCTL_STOP_DEQUEUED) + if (current->jobctl & JOBCTL_STOP_DEQUEUED) { + current->jobctl |= JOBCTL_STOPPED; set_special_state(TASK_STOPPED); + } spin_unlock_irq(¤t->sighand->siglock); schedule(); @@ -437,12 +439,21 @@ extern void signal_wake_up_state(struct task_struct *t, unsigned int state); static inline void signal_wake_up(struct task_struct *t, bool fatal) { - fatal = fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN); - signal_wake_up_state(t, fatal ? TASK_WAKEKILL | __TASK_TRACED : 0); + unsigned int state = 0; + if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) { + t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED); + state = TASK_WAKEKILL | __TASK_TRACED; + } + signal_wake_up_state(t, state); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { - signal_wake_up_state(t, resume ? __TASK_TRACED : 0); + unsigned int state = 0; + if (resume) { + t->jobctl &= ~JOBCTL_TRACED; + state = __TASK_TRACED; + } + signal_wake_up_state(t, state); } void task_join_group_stop(struct task_struct *task); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 36a5b7a00d2f..328a34a99124 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -185,7 +185,12 @@ static bool looks_like_a_spurious_pid(struct task_struct *task) return true; } -/* Ensure that nothing can wake it up, even SIGKILL */ +/* + * Ensure that nothing can wake it up, even SIGKILL + * + * A task is switched to this state while a ptrace operation is in progress; + * such that the ptrace operation is uninterruptible. + */ static bool ptrace_freeze_traced(struct task_struct *task) { bool ret = false; @@ -216,8 +221,10 @@ static void ptrace_unfreeze_traced(struct task_struct *task) */ if (lock_task_sighand(task, &flags)) { task->jobctl &= ~JOBCTL_PTRACE_FROZEN; - if (__fatal_signal_pending(task)) + if (__fatal_signal_pending(task)) { + task->jobctl &= ~TASK_TRACED; wake_up_state(task, __TASK_TRACED); + } unlock_task_sighand(task, &flags); } } @@ -462,8 +469,10 @@ static int ptrace_attach(struct task_struct *task, long request, * in and out of STOPPED are protected by siglock. */ if (task_is_stopped(task) && - task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) + task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) { + task->jobctl &= ~JOBCTL_STOPPED; signal_wake_up_state(task, __TASK_STOPPED); + } spin_unlock(&task->sighand->siglock); @@ -875,6 +884,7 @@ static int ptrace_resume(struct task_struct *child, long request, */ spin_lock_irq(&child->sighand->siglock); child->exit_code = data; + child->jobctl &= ~JOBCTL_TRACED; wake_up_state(child, __TASK_TRACED); spin_unlock_irq(&child->sighand->siglock); diff --git a/kernel/signal.c b/kernel/signal.c index a58b68a2d3c6..e782c2611b64 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -762,7 +762,10 @@ still_pending: */ void signal_wake_up_state(struct task_struct *t, unsigned int state) { + lockdep_assert_held(&t->sighand->siglock); + set_tsk_thread_flag(t, TIF_SIGPENDING); + /* * TASK_WAKEKILL also means wake it up in the stopped/traced/killable * case. We don't check t->state here because there is a race with it @@ -930,9 +933,10 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force) for_each_thread(p, t) { flush_sigqueue_mask(&flush, &t->pending); task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING); - if (likely(!(t->ptrace & PT_SEIZED))) + if (likely(!(t->ptrace & PT_SEIZED))) { + t->jobctl &= ~JOBCTL_STOPPED; wake_up_state(t, __TASK_STOPPED); - else + } else ptrace_trap_notify(t); } @@ -2218,6 +2222,7 @@ static int ptrace_stop(int exit_code, int why, unsigned long message, return exit_code; set_special_state(TASK_TRACED); + current->jobctl |= JOBCTL_TRACED; /* * We're committing to trapping. TRACED should be visible before @@ -2436,6 +2441,7 @@ static bool do_signal_stop(int signr) if (task_participate_group_stop(current)) notify = CLD_STOPPED; + current->jobctl |= JOBCTL_STOPPED; set_special_state(TASK_STOPPED); spin_unlock_irq(¤t->sighand->siglock); -- cgit v1.2.3 From b265cdebdfefbee4ef1ae2972af36f7a7cac5148 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 19 May 2022 14:08:48 -0700 Subject: sched: coredump.h: clarify the use of MMF_VM_HUGEPAGE Patch series "Make khugepaged collapse readonly FS THP more consistent", v4. The readonly FS THP relies on khugepaged to collapse THP for suitable vmas. But the behavior is inconsistent for "always" mode (https://lore.kernel.org/linux-mm/00f195d4-d039-3cf2-d3a1-a2c88de397a0@suse.cz/). The "always" mode means THP allocation should be tried all the time and khugepaged should try to collapse THP all the time. Of course the allocation and collapse may fail due to other factors and conditions. Currently file THP may not be collapsed by khugepaged even though all the conditions are met. That does break the semantics of "always" mode. So make sure readonly FS vmas are registered to khugepaged to fix the break. Register suitable vmas in common mmap path, that could cover both readonly FS vmas and shmem vmas, so remove the khugepaged calls in shmem.c. The patch 1-7 are minor bug fixes, clean up and preparation patches. Patch 8 is the real meat. Tested with khugepaged test in selftests and the testcase provided by Vlastimil Babka in https://lore.kernel.org/lkml/df3b5d1c-a36b-2c73-3e27-99e74983de3a@suse.cz/ by commenting out MADV_HUGEPAGE call. This patch (of 8): MMF_VM_HUGEPAGE is set as long as the mm is available for khugepaged by khugepaged_enter(), not only when VM_HUGEPAGE is set on vma. Correct the comment to avoid confusion. Link: https://lkml.kernel.org/r/20220510203222.24246-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20220510203222.24246-2-shy828301@gmail.com Signed-off-by: Yang Shi Reviewed-by: Miaohe Lin Acked-by: Song Liu Acked-by: Vlastmil Babka Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Rik van Riel Cc: Song Liu Cc: Theodore Ts'o Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/sched/coredump.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 4d9e3a656875..4d0a5be28b70 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -57,7 +57,8 @@ static inline int get_dumpable(struct mm_struct *mm) #endif /* leave room for more dump flags */ #define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ -#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */ +#define MMF_VM_HUGEPAGE 17 /* set when mm is available for + khugepaged */ /* * This one-shot flag is dropped due to necessity of changing exe once again * on NFS restore -- cgit v1.2.3