diff options
Diffstat (limited to 'include/linux/sched')
| -rw-r--r-- | include/linux/sched/clock.h | 5 | ||||
| -rw-r--r-- | include/linux/sched/coredump.h | 47 | ||||
| -rw-r--r-- | include/linux/sched/exec_state.h | 31 | ||||
| -rw-r--r-- | include/linux/sched/ext.h | 9 | ||||
| -rw-r--r-- | include/linux/sched/smt.h | 4 | ||||
| -rw-r--r-- | include/linux/sched/topology.h | 32 |
6 files changed, 87 insertions, 41 deletions
diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h index 196f0ca351a2..39f0a7f94bfc 100644 --- a/include/linux/sched/clock.h +++ b/include/linux/sched/clock.h @@ -33,6 +33,11 @@ extern u64 sched_clock_cpu(int cpu); extern void sched_clock_init(void); #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK +static inline int sched_clock_stable(void) +{ + return 1; +} + static inline void sched_clock_tick(void) { } diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 624fda17a785..20957ccde3b5 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -2,43 +2,18 @@ #ifndef _LINUX_SCHED_COREDUMP_H #define _LINUX_SCHED_COREDUMP_H -#include <linux/mm_types.h> - -#define SUID_DUMP_DISABLE 0 /* No setuid dumping */ -#define SUID_DUMP_USER 1 /* Dump as user of process */ -#define SUID_DUMP_ROOT 2 /* Dump as root */ - -static inline unsigned long __mm_flags_get_dumpable(const struct mm_struct *mm) -{ - /* - * By convention, dumpable bits are contained in first 32 bits of the - * bitmap, so we can simply access this first unsigned long directly. - */ - return __mm_flags_get_word(mm); -} - -static inline void __mm_flags_set_mask_dumpable(struct mm_struct *mm, int value) -{ - __mm_flags_set_mask_bits_word(mm, MMF_DUMPABLE_MASK, value); -} - -extern void set_dumpable(struct mm_struct *mm, int value); /* - * This returns the actual value of the suid_dumpable flag. For things - * that are using this for checking for privilege transitions, it must - * test against SUID_DUMP_USER rather than treating it as a boolean - * value. + * Task dumpability mode. Gates core dump production and ptrace_attach() + * authorization. The numeric values are stable ABI (suid_dumpable + * sysctl, prctl(PR_SET_DUMPABLE)); do not renumber. */ -static inline int __get_dumpable(unsigned long mm_flags) -{ - return mm_flags & MMF_DUMPABLE_MASK; -} - -static inline int get_dumpable(struct mm_struct *mm) -{ - unsigned long flags = __mm_flags_get_dumpable(mm); - - return __get_dumpable(flags); -} +enum task_dumpable { + TASK_DUMPABLE_OFF = 0, /* no dump; ptrace needs CAP_SYS_PTRACE */ + TASK_DUMPABLE_OWNER = 1, /* default; dump and ptrace by uid match */ + TASK_DUMPABLE_ROOT = 2, /* dump as root; ptrace needs CAP_SYS_PTRACE */ +}; + +void task_exec_state_set_dumpable(enum task_dumpable value); +enum task_dumpable task_exec_state_get_dumpable(struct task_struct *task); #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/sched/exec_state.h b/include/linux/sched/exec_state.h new file mode 100644 index 000000000000..9b61782510b8 --- /dev/null +++ b/include/linux/sched/exec_state.h @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2026 Christian Brauner <brauner@kernel.org> */ +#ifndef _LINUX_SCHED_EXEC_STATE_H +#define _LINUX_SCHED_EXEC_STATE_H + +#include <linux/init.h> +#include <linux/rcupdate.h> +#include <linux/refcount.h> +#include <linux/sched/coredump.h> +#include <linux/user_namespace.h> + +struct task_exec_state { + refcount_t count; + enum task_dumpable dumpable; + struct user_namespace *user_ns; + struct rcu_head rcu; +}; + +extern struct task_exec_state init_task_exec_state; + +struct task_exec_state *alloc_task_exec_state(struct user_namespace *user_ns); +void put_task_exec_state(struct task_exec_state *exec_state); +struct task_exec_state *task_exec_state_rcu(const struct task_struct *tsk); +struct task_exec_state *task_exec_state_replace(struct task_struct *tsk, + struct task_exec_state *exec_state); +int task_exec_state_copy(struct task_struct *tsk); +void __init exec_state_init(void); + +DEFINE_FREE(put_task_exec_state, struct task_exec_state *, put_task_exec_state(_T)) + +#endif /* _LINUX_SCHED_EXEC_STATE_H */ diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 2129e18ada58..20b2343aa344 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -207,6 +207,15 @@ struct sched_ext_entity { u64 core_sched_at; /* see scx_prio_less() */ #endif + /* + * Unique non-zero task ID assigned at fork. Persists across exec and + * is never reused. Lets BPF schedulers identify tasks without storing + * kernel pointers - arena-backed schedulers being one example. See + * scx_bpf_tid_to_task(). + */ + u64 tid; + struct rhash_head tid_hash_node; /* see SCX_OPS_TID_TO_TASK */ + /* BPF scheduler modifiable fields */ /* diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h index 166b19af956f..cde6679c0278 100644 --- a/include/linux/sched/smt.h +++ b/include/linux/sched/smt.h @@ -4,16 +4,12 @@ #include <linux/static_key.h> -#ifdef CONFIG_SCHED_SMT extern struct static_key_false sched_smt_present; static __always_inline bool sched_smt_active(void) { return static_branch_likely(&sched_smt_present); } -#else -static __always_inline bool sched_smt_active(void) { return false; } -#endif void arch_smt_update(void); diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 36553e14866d..b5d9d7c2b8ad 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -67,7 +67,25 @@ struct sched_domain_shared { atomic_t ref; atomic_t nr_busy_cpus; int has_idle_cores; - int nr_idle_scan; + union { + int nr_idle_scan; + /* + * Used during allocation to claim the sched_domain_shared + * object at multiple levels. + * + * Note: between build and the first periodic LB tick, which + * rewrites the union via update_idle_cpu_scan(), readers of + * nr_idle_scan may observe the transient SD_* flag value as + * the scan bound. The flag bits are small positive integers, + * so the effect is just a slightly relaxed scan bound for one + * window and self-heals on the first tick. + */ + int alloc_flags; + }; +#ifdef CONFIG_SCHED_CACHE + unsigned long util_avg; + unsigned long capacity; +#endif }; struct sched_domain { @@ -99,6 +117,12 @@ struct sched_domain { u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; +#ifdef CONFIG_SCHED_CACHE + unsigned int llc_max; + unsigned int *llc_counts __counted_by_ptr(llc_max); + unsigned long llc_bytes; +#endif + #ifdef CONFIG_SCHEDSTATS /* sched_balance_rq() stats */ unsigned int lb_count[CPU_MAX_IDLE_TYPES]; @@ -256,4 +280,10 @@ static inline int task_node(const struct task_struct *p) return cpu_to_node(task_cpu(p)); } +#ifdef CONFIG_SCHED_CACHE +extern void sched_update_llc_bytes(unsigned int cpu); +#else +static inline void sched_update_llc_bytes(unsigned int cpu) { } +#endif + #endif /* _LINUX_SCHED_TOPOLOGY_H */ |