From ae5c677729e99b8cb3e6252aaa9b72a92985d203 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 30 Oct 2024 13:52:50 -0400 Subject: sched/core: Remove HK_TYPE_SCHED The HK_TYPE_SCHED housekeeping type is defined but not set anywhere. So any code that try to use HK_TYPE_SCHED are essentially dead code. So remove HK_TYPE_SCHED and any code that use it. Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Acked-by: Frederic Weisbecker Link: https://lore.kernel.org/r/20241030175253.125248-2-longman@redhat.com --- include/linux/sched/isolation.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 2b461129d1fa..499d5e480882 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -10,7 +10,6 @@ enum hk_type { HK_TYPE_TIMER, HK_TYPE_RCU, HK_TYPE_MISC, - HK_TYPE_SCHED, HK_TYPE_TICK, HK_TYPE_DOMAIN, HK_TYPE_WQ, -- cgit v1.2.3 From 6010d245ddc9f463bbf0311ac49073a78f444755 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 30 Oct 2024 13:52:52 -0400 Subject: sched/isolation: Consolidate housekeeping cpumasks that are always identical The housekeeping cpumasks are only set by two boot commandline parameters: "nohz_full" and "isolcpus". When there is more than one of "nohz_full" or "isolcpus", the extra ones must have the same CPU list or the setup will fail partially. The HK_TYPE_DOMAIN and HK_TYPE_MANAGED_IRQ types are settable by "isolcpus" only and their settings can be independent of the other types. The other housekeeping types are all set by "nohz_full" or "isolcpus=nohz" without a way to set them individually. So they all have identical cpumasks. There is actually no point in having different cpumasks for these "nohz_full" only housekeeping types. Consolidate these types to use the same cpumask by aliasing them to the same value. If there is a need to set any of them independently in the future, we can break them out to their own cpumasks again. With this change, the number of cpumasks in the housekeeping structure drops from 9 to 3. Other than that, there should be no other functional change. Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Acked-by: Frederic Weisbecker Link: https://lore.kernel.org/r/20241030175253.125248-4-longman@redhat.com --- include/linux/sched/isolation.h | 20 +++++++++++++------- kernel/sched/isolation.c | 19 ++++++------------- 2 files changed, 19 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 499d5e480882..d8501f4709b5 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -7,15 +7,21 @@ #include enum hk_type { - HK_TYPE_TIMER, - HK_TYPE_RCU, - HK_TYPE_MISC, - HK_TYPE_TICK, HK_TYPE_DOMAIN, - HK_TYPE_WQ, HK_TYPE_MANAGED_IRQ, - HK_TYPE_KTHREAD, - HK_TYPE_MAX + HK_TYPE_KERNEL_NOISE, + HK_TYPE_MAX, + + /* + * The following housekeeping types are only set by the nohz_full + * boot commandline option. So they can share the same value. + */ + HK_TYPE_TICK = HK_TYPE_KERNEL_NOISE, + HK_TYPE_TIMER = HK_TYPE_KERNEL_NOISE, + HK_TYPE_RCU = HK_TYPE_KERNEL_NOISE, + HK_TYPE_MISC = HK_TYPE_KERNEL_NOISE, + HK_TYPE_WQ = HK_TYPE_KERNEL_NOISE, + HK_TYPE_KTHREAD = HK_TYPE_KERNEL_NOISE }; #ifdef CONFIG_CPU_ISOLATION diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 6a686322ce3c..81bc8b329ef1 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -9,14 +9,9 @@ */ 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_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), + HK_FLAG_KERNEL_NOISE = BIT(HK_TYPE_KERNEL_NOISE), }; DEFINE_STATIC_KEY_FALSE(housekeeping_overridden); @@ -96,7 +91,7 @@ void __init housekeeping_init(void) static_branch_enable(&housekeeping_overridden); - if (housekeeping.flags & HK_FLAG_TICK) + if (housekeeping.flags & HK_FLAG_KERNEL_NOISE) sched_tick_offload_init(); for_each_set_bit(type, &housekeeping.flags, HK_TYPE_MAX) { @@ -120,7 +115,7 @@ static int __init housekeeping_setup(char *str, unsigned long flags) unsigned int first_cpu; int err = 0; - if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) { + if ((flags & HK_FLAG_KERNEL_NOISE) && !(housekeeping.flags & HK_FLAG_KERNEL_NOISE)) { if (!IS_ENABLED(CONFIG_NO_HZ_FULL)) { pr_warn("Housekeeping: nohz unsupported." " Build with CONFIG_NO_HZ_FULL\n"); @@ -176,7 +171,7 @@ static int __init housekeeping_setup(char *str, unsigned long flags) housekeeping_setup_type(type, housekeeping_staging); } - if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) + if ((flags & HK_FLAG_KERNEL_NOISE) && !(housekeeping.flags & HK_FLAG_KERNEL_NOISE)) tick_nohz_full_setup(non_housekeeping_mask); housekeeping.flags |= flags; @@ -194,8 +189,7 @@ static int __init housekeeping_nohz_full_setup(char *str) { unsigned long flags; - flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU | - HK_FLAG_MISC | HK_FLAG_KTHREAD; + flags = HK_FLAG_KERNEL_NOISE; return housekeeping_setup(str, flags); } @@ -214,8 +208,7 @@ static int __init housekeeping_isolcpus_setup(char *str) */ if (!strncmp(str, "nohz,", 5)) { str += 5; - flags |= HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | - HK_FLAG_RCU | HK_FLAG_MISC | HK_FLAG_KTHREAD; + flags |= HK_FLAG_KERNEL_NOISE; continue; } -- cgit v1.2.3 From 7d5265ffcd8b41da5e09066360540d6e0716e9cd Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 12 Nov 2024 10:28:26 -0500 Subject: rseq: Validate read-only fields under DEBUG_RSEQ config The rseq uapi requires cooperation between users of the rseq fields to ensure that all libraries and applications using rseq within a process do not interfere with each other. This is especially important for fields which are meant to be read-only from user-space, as documented in uapi/linux/rseq.h: - cpu_id_start, - cpu_id, - node_id, - mm_cid. Storing to those fields from a user-space library prevents any sharing of the rseq ABI with other libraries and applications, as other users are not aware that the content of those fields has been altered by a third-party library. This is unfortunately the current behavior of tcmalloc: it purposefully overlaps part of a cached value with the cpu_id_start upper bits to get notified about preemption, because the kernel clears those upper bits before returning to user-space. This behavior does not conform to the rseq uapi header ABI. This prevents tcmalloc from using rseq when rseq is registered by the GNU C library 2.35+. It requires tcmalloc users to disable glibc rseq registration with a glibc tunable, which is a sad state of affairs. Considering that tcmalloc and the GNU C library are the two first upstream projects using rseq, and that they are already incompatible due to use of this hack, adding kernel-level validation of all read-only fields content is necessary to ensure future users of rseq abide by the rseq ABI requirements. Validate that user-space does not corrupt the read-only fields and conform to the rseq uapi header ABI when the kernel is built with CONFIG_DEBUG_RSEQ=y. This is done by storing a copy of the read-only fields in the task_struct, and validating the prior values present in user-space before updating them. If the values do not match, print a warning on the console (printk_ratelimited()). This is a first step to identify misuses of the rseq ABI by printing a warning on the console. After a giving some time to userspace to correct its use of rseq, the plan is to eventually terminate offending processes with SIGSEGV. This change is expected to produce warnings for the upstream tcmalloc implementation, but tcmalloc developers mentioned they were open to adapt their implementation to kernel-level change. Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Link: https://github.com/google/tcmalloc/issues/144 --- include/linux/sched.h | 9 +++++ kernel/rseq.c | 98 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 107 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index d380bffee2ef..b5916be49f62 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1367,6 +1367,15 @@ struct task_struct { * with respect to preemption. */ unsigned long rseq_event_mask; +# ifdef CONFIG_DEBUG_RSEQ + /* + * This is a place holder to save a copy of the rseq fields for + * validation of read-only fields. The struct rseq has a + * variable-length array at the end, so it cannot be used + * directly. Reserve a size large enough for the known fields. + */ + char rseq_fields[sizeof(struct rseq)]; +# endif #endif #ifdef CONFIG_SCHED_MM_CID diff --git a/kernel/rseq.c b/kernel/rseq.c index 9de6e35fe679..e04bb30a2eb8 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #define CREATE_TRACE_POINTS @@ -25,6 +26,78 @@ RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL | \ RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE) +#ifdef CONFIG_DEBUG_RSEQ +static struct rseq *rseq_kernel_fields(struct task_struct *t) +{ + return (struct rseq *) t->rseq_fields; +} + +static int rseq_validate_ro_fields(struct task_struct *t) +{ + static DEFINE_RATELIMIT_STATE(_rs, + DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + u32 cpu_id_start, cpu_id, node_id, mm_cid; + struct rseq __user *rseq = t->rseq; + + /* + * Validate fields which are required to be read-only by + * user-space. + */ + if (!user_read_access_begin(rseq, t->rseq_len)) + goto efault; + unsafe_get_user(cpu_id_start, &rseq->cpu_id_start, efault_end); + unsafe_get_user(cpu_id, &rseq->cpu_id, efault_end); + unsafe_get_user(node_id, &rseq->node_id, efault_end); + unsafe_get_user(mm_cid, &rseq->mm_cid, efault_end); + user_read_access_end(); + + if ((cpu_id_start != rseq_kernel_fields(t)->cpu_id_start || + cpu_id != rseq_kernel_fields(t)->cpu_id || + node_id != rseq_kernel_fields(t)->node_id || + mm_cid != rseq_kernel_fields(t)->mm_cid) && __ratelimit(&_rs)) { + + pr_warn("Detected rseq corruption for pid: %d, name: %s\n" + "\tcpu_id_start: %u ?= %u\n" + "\tcpu_id: %u ?= %u\n" + "\tnode_id: %u ?= %u\n" + "\tmm_cid: %u ?= %u\n", + t->pid, t->comm, + cpu_id_start, rseq_kernel_fields(t)->cpu_id_start, + cpu_id, rseq_kernel_fields(t)->cpu_id, + node_id, rseq_kernel_fields(t)->node_id, + mm_cid, rseq_kernel_fields(t)->mm_cid); + } + + /* For now, only print a console warning on mismatch. */ + return 0; + +efault_end: + user_read_access_end(); +efault: + return -EFAULT; +} + +static void rseq_set_ro_fields(struct task_struct *t, u32 cpu_id_start, u32 cpu_id, + u32 node_id, u32 mm_cid) +{ + rseq_kernel_fields(t)->cpu_id_start = cpu_id; + rseq_kernel_fields(t)->cpu_id = cpu_id; + rseq_kernel_fields(t)->node_id = node_id; + rseq_kernel_fields(t)->mm_cid = mm_cid; +} +#else +static int rseq_validate_ro_fields(struct task_struct *t) +{ + return 0; +} + +static void rseq_set_ro_fields(struct task_struct *t, u32 cpu_id_start, u32 cpu_id, + u32 node_id, u32 mm_cid) +{ +} +#endif + /* * * Restartable sequences are a lightweight interface that allows @@ -92,6 +165,11 @@ static int rseq_update_cpu_node_id(struct task_struct *t) u32 node_id = cpu_to_node(cpu_id); u32 mm_cid = task_mm_cid(t); + /* + * Validate read-only rseq fields. + */ + if (rseq_validate_ro_fields(t)) + goto efault; WARN_ON_ONCE((int) mm_cid < 0); if (!user_write_access_begin(rseq, t->rseq_len)) goto efault; @@ -105,6 +183,7 @@ static int rseq_update_cpu_node_id(struct task_struct *t) * t->rseq_len != ORIG_RSEQ_SIZE. */ user_write_access_end(); + rseq_set_ro_fields(t, cpu_id, cpu_id, node_id, mm_cid); trace_rseq_update(t); return 0; @@ -119,6 +198,11 @@ static int rseq_reset_rseq_cpu_node_id(struct task_struct *t) u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED, node_id = 0, mm_cid = 0; + /* + * Validate read-only rseq fields. + */ + if (!rseq_validate_ro_fields(t)) + return -EFAULT; /* * Reset cpu_id_start to its initial state (0). */ @@ -141,6 +225,9 @@ static int rseq_reset_rseq_cpu_node_id(struct task_struct *t) */ if (put_user(mm_cid, &t->rseq->mm_cid)) return -EFAULT; + + rseq_set_ro_fields(t, cpu_id_start, cpu_id, node_id, mm_cid); + /* * Additional feature fields added after ORIG_RSEQ_SIZE * need to be conditionally reset only if @@ -423,6 +510,17 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, current->rseq = rseq; current->rseq_len = rseq_len; current->rseq_sig = sig; +#ifdef CONFIG_DEBUG_RSEQ + /* + * Initialize the in-kernel rseq fields copy for validation of + * read-only fields. + */ + if (get_user(rseq_kernel_fields(current)->cpu_id_start, &rseq->cpu_id_start) || + get_user(rseq_kernel_fields(current)->cpu_id, &rseq->cpu_id) || + get_user(rseq_kernel_fields(current)->node_id, &rseq->node_id) || + get_user(rseq_kernel_fields(current)->mm_cid, &rseq->mm_cid)) + return -EFAULT; +#endif /* * If rseq was previously inactive, and has just been * registered, ensure the cpu_id_start and cpu_id fields -- cgit v1.2.3 From a430d99e349026d53e2557b7b22bd2ebd61fe12a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 20 Dec 2024 06:32:19 +0000 Subject: sched/fair: Fix value reported by hot tasks pulled in /proc/schedstat In /proc/schedstat, lb_hot_gained reports the number hot tasks pulled during load balance. This value is incremented in can_migrate_task() if the task is migratable and hot. After incrementing the value, load balancer can still decide not to migrate this task leading to wrong accounting. Fix this by incrementing stats when hot tasks are detached. This issue only exists in detach_tasks() where we can decide to not migrate hot task even if it is migratable. However, in detach_one_task(), we migrate it unconditionally. [Swapnil: Handled the case where nr_failed_migrations_hot was not accounted properly and wrote commit log] Fixes: d31980846f96 ("sched: Move up affinity check to mitigate useless redoing overhead") Signed-off-by: Peter Zijlstra (Intel) Reported-by: "Gautham R. Shenoy" Not-yet-signed-off-by: Peter Zijlstra Signed-off-by: Swapnil Sapkal Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20241220063224.17767-2-swapnil.sapkal@amd.com --- include/linux/sched.h | 1 + kernel/sched/fair.c | 17 +++++++++++++---- 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index b5916be49f62..8c6a2ed9f80e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -937,6 +937,7 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; + unsigned sched_task_hot:1; /* Force alignment to the next boundary: */ unsigned :0; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ae8095aa4585..8fc6648a0aa8 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -9396,6 +9396,8 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) int tsk_cache_hot; lockdep_assert_rq_held(env->src_rq); + if (p->sched_task_hot) + p->sched_task_hot = 0; /* * We do not migrate tasks that are: @@ -9472,10 +9474,8 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) if (tsk_cache_hot <= 0 || env->sd->nr_balance_failed > env->sd->cache_nice_tries) { - if (tsk_cache_hot == 1) { - schedstat_inc(env->sd->lb_hot_gained[env->idle]); - schedstat_inc(p->stats.nr_forced_migrations); - } + if (tsk_cache_hot == 1) + p->sched_task_hot = 1; return 1; } @@ -9490,6 +9490,12 @@ static void detach_task(struct task_struct *p, struct lb_env *env) { lockdep_assert_rq_held(env->src_rq); + if (p->sched_task_hot) { + p->sched_task_hot = 0; + schedstat_inc(env->sd->lb_hot_gained[env->idle]); + schedstat_inc(p->stats.nr_forced_migrations); + } + deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK); set_task_cpu(p, env->dst_cpu); } @@ -9650,6 +9656,9 @@ static int detach_tasks(struct lb_env *env) continue; next: + if (p->sched_task_hot) + schedstat_inc(p->stats.nr_failed_migrations_hot); + list_move(&p->se.group_node, tasks); } -- cgit v1.2.3 From 3b2a793ea70fd14136b442df31e53935e8095034 Mon Sep 17 00:00:00 2001 From: Swapnil Sapkal Date: Fri, 20 Dec 2024 06:32:21 +0000 Subject: sched: Report the different kinds of imbalances in /proc/schedstat In /proc/schedstat, lb_imbalance reports the sum of imbalances discovered in sched domains with each call to sched_balance_rq(), which is not very useful because lb_imbalance does not mention whether the imbalance is due to load, utilization, nr_tasks or misfit_tasks. Remove this field from /proc/schedstat. Currently there is no field in /proc/schedstat to report different types of imbalances. Introduce new fields in /proc/schedstat to report the total imbalances in load, utilization, nr_tasks or misfit_tasks. Added fields to /proc/schedstat: - lb_imbalance_load: Total imbalance due to load. - lb_imbalance_util: Total imbalance due to utilization. - lb_imbalance_task: Total imbalance due to number of tasks. - lb_imbalance_misfit: Total imbalance due to misfit tasks. Signed-off-by: Swapnil Sapkal Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Shrikanth Hegde Link: https://lore.kernel.org/r/20241220063224.17767-4-swapnil.sapkal@amd.com --- include/linux/sched/topology.h | 5 ++++- kernel/sched/fair.c | 24 +++++++++++++++++++++++- kernel/sched/stats.c | 7 +++++-- 3 files changed, 32 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 4237daa5ac7a..76a662e1ec24 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -114,7 +114,10 @@ struct sched_domain { unsigned int lb_count[CPU_MAX_IDLE_TYPES]; unsigned int lb_failed[CPU_MAX_IDLE_TYPES]; unsigned int lb_balanced[CPU_MAX_IDLE_TYPES]; - unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_load[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_util[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_task[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance_misfit[CPU_MAX_IDLE_TYPES]; unsigned int lb_gained[CPU_MAX_IDLE_TYPES]; unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES]; unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES]; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index e5c0c61909b7..b3418b5d484f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -11705,6 +11705,28 @@ static int should_we_balance(struct lb_env *env) return group_balance_cpu(sg) == env->dst_cpu; } +static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd, + enum cpu_idle_type idle) +{ + if (!schedstat_enabled()) + return; + + switch (env->migration_type) { + case migrate_load: + __schedstat_add(sd->lb_imbalance_load[idle], env->imbalance); + break; + case migrate_util: + __schedstat_add(sd->lb_imbalance_util[idle], env->imbalance); + break; + case migrate_task: + __schedstat_add(sd->lb_imbalance_task[idle], env->imbalance); + break; + case migrate_misfit: + __schedstat_add(sd->lb_imbalance_misfit[idle], env->imbalance); + break; + } +} + /* * Check this_cpu to ensure it is balanced within domain. Attempt to move * tasks if there is an imbalance. @@ -11755,7 +11777,7 @@ redo: WARN_ON_ONCE(busiest == env.dst_rq); - schedstat_add(sd->lb_imbalance[idle], env.imbalance); + update_lb_imbalance_stat(&env, sd, idle); env.src_cpu = busiest->cpu; env.src_rq = busiest; diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index eb0cdcd4d921..802bd9398a2e 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -141,11 +141,14 @@ static int show_schedstat(struct seq_file *seq, void *v) seq_printf(seq, "domain%d %*pb", dcount++, cpumask_pr_args(sched_domain_span(sd))); for (itype = 0; itype < CPU_MAX_IDLE_TYPES; itype++) { - seq_printf(seq, " %u %u %u %u %u %u %u %u", + seq_printf(seq, " %u %u %u %u %u %u %u %u %u %u %u", sd->lb_count[itype], sd->lb_balanced[itype], sd->lb_failed[itype], - sd->lb_imbalance[itype], + sd->lb_imbalance_load[itype], + sd->lb_imbalance_util[itype], + sd->lb_imbalance_task[itype], + sd->lb_imbalance_misfit[itype], sd->lb_gained[itype], sd->lb_hot_gained[itype], sd->lb_nobusyq[itype], -- cgit v1.2.3 From 1c055a0f5d3bafaca5d218bbb3e4e63d6307be45 Mon Sep 17 00:00:00 2001 From: Swapnil Sapkal Date: Fri, 20 Dec 2024 06:32:22 +0000 Subject: sched: Move sched domain name out of CONFIG_SCHED_DEBUG /proc/schedstat file shows cpu and sched domain level scheduler statistics. It does not show domain name instead shows domain level. It will be very useful for tools like `perf sched stats`[1] to aggragate domain level stats if domain names are shown in /proc/schedstat. But sched domain name is guarded by CONFIG_SCHED_DEBUG. As per the discussion[2], move sched domain name out of CONFIG_SCHED_DEBUG. [1] https://lore.kernel.org/lkml/20241122084452.1064968-1-swapnil.sapkal@amd.com/ [2] https://lore.kernel.org/lkml/fcefeb4d-3acb-462d-9c9b-3df8d927e522@amd.com/ Suggested-by: "Gautham R. Shenoy" Signed-off-by: Swapnil Sapkal Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20241220063224.17767-5-swapnil.sapkal@amd.com --- include/linux/sched/topology.h | 8 -------- kernel/sched/topology.c | 4 ---- 2 files changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 76a662e1ec24..7f3dbafe1817 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -143,9 +143,7 @@ struct sched_domain { unsigned int ttwu_move_affine; unsigned int ttwu_move_balance; #endif -#ifdef CONFIG_SCHED_DEBUG char *name; -#endif union { void *private; /* used during construction */ struct rcu_head rcu; /* used during destruction */ @@ -201,18 +199,12 @@ struct sched_domain_topology_level { int flags; int numa_level; struct sd_data data; -#ifdef CONFIG_SCHED_DEBUG char *name; -#endif }; extern void __init set_sched_topology(struct sched_domain_topology_level *tl); -#ifdef CONFIG_SCHED_DEBUG # define SD_INIT_NAME(type) .name = #type -#else -# define SD_INIT_NAME(type) -#endif #else /* CONFIG_SMP */ diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 9c405f0e7b26..da33ec9e94ab 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1635,9 +1635,7 @@ sd_init(struct sched_domain_topology_level *tl, .max_newidle_lb_cost = 0, .last_decay_max_lb_cost = jiffies, .child = child, -#ifdef CONFIG_SCHED_DEBUG .name = tl->name, -#endif }; sd_span = sched_domain_span(sd); @@ -2338,10 +2336,8 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve if (!cpumask_subset(sched_domain_span(child), sched_domain_span(sd))) { pr_err("BUG: arch topology borken\n"); -#ifdef CONFIG_SCHED_DEBUG pr_err(" the %s domain not a subset of the %s domain\n", child->name, sd->name); -#endif /* Fixup, ensure @sd has at least @child CPUs. */ cpumask_or(sched_domain_span(sd), sched_domain_span(sd), -- cgit v1.2.3