diff options
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/compat.h | 2 | ||||
| -rw-r--r-- | include/linux/context_tracking.h | 30 | ||||
| -rw-r--r-- | include/linux/context_tracking_state.h | 21 | ||||
| -rw-r--r-- | include/linux/efi.h | 2 | ||||
| -rw-r--r-- | include/linux/futex.h | 40 | ||||
| -rw-r--r-- | include/linux/jbd2.h | 2 | ||||
| -rw-r--r-- | include/linux/kernel.h | 7 | ||||
| -rw-r--r-- | include/linux/kernel_stat.h | 18 | ||||
| -rw-r--r-- | include/linux/lockdep.h | 21 | ||||
| -rw-r--r-- | include/linux/lsm_hooks.h | 15 | ||||
| -rw-r--r-- | include/linux/percpu-rwsem.h | 4 | ||||
| -rw-r--r-- | include/linux/perf_event.h | 64 | ||||
| -rw-r--r-- | include/linux/rculist_bl.h | 28 | ||||
| -rw-r--r-- | include/linux/rcupdate.h | 20 | ||||
| -rw-r--r-- | include/linux/rcutiny.h | 1 | ||||
| -rw-r--r-- | include/linux/rcutree.h | 1 | ||||
| -rw-r--r-- | include/linux/refcount.h | 269 | ||||
| -rw-r--r-- | include/linux/rwlock_api_smp.h | 16 | ||||
| -rw-r--r-- | include/linux/sched.h | 12 | ||||
| -rw-r--r-- | include/linux/sched/mm.h | 6 | ||||
| -rw-r--r-- | include/linux/security.h | 39 | ||||
| -rw-r--r-- | include/linux/seqlock.h | 4 | ||||
| -rw-r--r-- | include/linux/spinlock_api_smp.h | 8 | ||||
| -rw-r--r-- | include/linux/tick.h | 9 | ||||
| -rw-r--r-- | include/linux/vtime.h | 59 | ||||
| -rw-r--r-- | include/linux/ww_mutex.h | 2 |
26 files changed, 515 insertions, 185 deletions
diff --git a/include/linux/compat.h b/include/linux/compat.h index 16dafd9f4b86..c4c389c7e1b4 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -410,8 +410,6 @@ struct compat_kexec_segment; struct compat_mq_attr; struct compat_msgbuf; -extern void compat_exit_robust_list(struct task_struct *curr); - #define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t)) #define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG) diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d05609ad329d..64ec82851aa3 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -22,26 +22,26 @@ extern void context_tracking_user_exit(void); static inline void user_enter(void) { - if (context_tracking_is_enabled()) + if (context_tracking_enabled()) context_tracking_enter(CONTEXT_USER); } static inline void user_exit(void) { - if (context_tracking_is_enabled()) + if (context_tracking_enabled()) context_tracking_exit(CONTEXT_USER); } /* Called with interrupts disabled. */ static inline void user_enter_irqoff(void) { - if (context_tracking_is_enabled()) + if (context_tracking_enabled()) __context_tracking_enter(CONTEXT_USER); } static inline void user_exit_irqoff(void) { - if (context_tracking_is_enabled()) + if (context_tracking_enabled()) __context_tracking_exit(CONTEXT_USER); } @@ -49,7 +49,7 @@ static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; - if (!context_tracking_is_enabled()) + if (!context_tracking_enabled()) return 0; prev_ctx = this_cpu_read(context_tracking.state); @@ -61,7 +61,7 @@ static inline enum ctx_state exception_enter(void) static inline void exception_exit(enum ctx_state prev_ctx) { - if (context_tracking_is_enabled()) { + if (context_tracking_enabled()) { if (prev_ctx != CONTEXT_KERNEL) context_tracking_enter(prev_ctx); } @@ -77,7 +77,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) */ static inline enum ctx_state ct_state(void) { - return context_tracking_is_enabled() ? + return context_tracking_enabled() ? this_cpu_read(context_tracking.state) : CONTEXT_DISABLED; } #else @@ -90,7 +90,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) { } static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; } #endif /* !CONFIG_CONTEXT_TRACKING */ -#define CT_WARN_ON(cond) WARN_ON(context_tracking_is_enabled() && (cond)) +#define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) #ifdef CONFIG_CONTEXT_TRACKING_FORCE extern void context_tracking_init(void); @@ -103,12 +103,12 @@ static inline void context_tracking_init(void) { } /* must be called with irqs disabled */ static inline void guest_enter_irqoff(void) { - if (vtime_accounting_cpu_enabled()) + if (vtime_accounting_enabled_this_cpu()) vtime_guest_enter(current); else current->flags |= PF_VCPU; - if (context_tracking_is_enabled()) + if (context_tracking_enabled()) __context_tracking_enter(CONTEXT_GUEST); /* KVM does not hold any references to rcu protected data when it @@ -118,16 +118,16 @@ static inline void guest_enter_irqoff(void) * one time slice). Lets treat guest mode as quiescent state, just like * we do with user-mode execution. */ - if (!context_tracking_cpu_is_enabled()) + if (!context_tracking_enabled_this_cpu()) rcu_virt_note_context_switch(smp_processor_id()); } static inline void guest_exit_irqoff(void) { - if (context_tracking_is_enabled()) + if (context_tracking_enabled()) __context_tracking_exit(CONTEXT_GUEST); - if (vtime_accounting_cpu_enabled()) + if (vtime_accounting_enabled_this_cpu()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; @@ -141,7 +141,7 @@ static inline void guest_enter_irqoff(void) * to assume that it's the stime pending cputime * to flush. */ - vtime_account_system(current); + vtime_account_kernel(current); current->flags |= PF_VCPU; rcu_virt_note_context_switch(smp_processor_id()); } @@ -149,7 +149,7 @@ static inline void guest_enter_irqoff(void) static inline void guest_exit_irqoff(void) { /* Flush the guest cputime we spent on the guest */ - vtime_account_system(current); + vtime_account_kernel(current); current->flags &= ~PF_VCPU; } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index f128dc3be0df..e7fe6678b7ad 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -23,17 +23,22 @@ struct context_tracking { }; #ifdef CONFIG_CONTEXT_TRACKING -extern struct static_key_false context_tracking_enabled; +extern struct static_key_false context_tracking_key; DECLARE_PER_CPU(struct context_tracking, context_tracking); -static inline bool context_tracking_is_enabled(void) +static inline bool context_tracking_enabled(void) { - return static_branch_unlikely(&context_tracking_enabled); + return static_branch_unlikely(&context_tracking_key); } -static inline bool context_tracking_cpu_is_enabled(void) +static inline bool context_tracking_enabled_cpu(int cpu) { - return __this_cpu_read(context_tracking.active); + return context_tracking_enabled() && per_cpu(context_tracking.active, cpu); +} + +static inline bool context_tracking_enabled_this_cpu(void) +{ + return context_tracking_enabled() && __this_cpu_read(context_tracking.active); } static inline bool context_tracking_in_user(void) @@ -42,9 +47,9 @@ static inline bool context_tracking_in_user(void) } #else static inline bool context_tracking_in_user(void) { return false; } -static inline bool context_tracking_active(void) { return false; } -static inline bool context_tracking_is_enabled(void) { return false; } -static inline bool context_tracking_cpu_is_enabled(void) { return false; } +static inline bool context_tracking_enabled(void) { return false; } +static inline bool context_tracking_enabled_cpu(int cpu) { return false; } +static inline bool context_tracking_enabled_this_cpu(void) { return false; } #endif /* CONFIG_CONTEXT_TRACKING */ #endif diff --git a/include/linux/efi.h b/include/linux/efi.h index d87acf62958e..028efa7a9f3b 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1645,6 +1645,8 @@ static inline void efi_enable_reset_attack_mitigation(efi_system_table_t *sys_table_arg) { } #endif +efi_status_t efi_random_get_seed(efi_system_table_t *sys_table_arg); + void efi_retrieve_tpm2_eventlog(efi_system_table_t *sys_table); /* diff --git a/include/linux/futex.h b/include/linux/futex.h index ccaef0097785..5cc3fed27d4c 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -2,7 +2,9 @@ #ifndef _LINUX_FUTEX_H #define _LINUX_FUTEX_H +#include <linux/sched.h> #include <linux/ktime.h> + #include <uapi/linux/futex.h> struct inode; @@ -48,15 +50,35 @@ union futex_key { #define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } } #ifdef CONFIG_FUTEX -extern void exit_robust_list(struct task_struct *curr); +enum { + FUTEX_STATE_OK, + FUTEX_STATE_EXITING, + FUTEX_STATE_DEAD, +}; -long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, - u32 __user *uaddr2, u32 val2, u32 val3); -#else -static inline void exit_robust_list(struct task_struct *curr) +static inline void futex_init_task(struct task_struct *tsk) { + tsk->robust_list = NULL; +#ifdef CONFIG_COMPAT + tsk->compat_robust_list = NULL; +#endif + INIT_LIST_HEAD(&tsk->pi_state_list); + tsk->pi_state_cache = NULL; + tsk->futex_state = FUTEX_STATE_OK; + mutex_init(&tsk->futex_exit_mutex); } +void futex_exit_recursive(struct task_struct *tsk); +void futex_exit_release(struct task_struct *tsk); +void futex_exec_release(struct task_struct *tsk); + +long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, + u32 __user *uaddr2, u32 val2, u32 val3); +#else +static inline void futex_init_task(struct task_struct *tsk) { } +static inline void futex_exit_recursive(struct task_struct *tsk) { } +static inline void futex_exit_release(struct task_struct *tsk) { } +static inline void futex_exec_release(struct task_struct *tsk) { } static inline long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) @@ -65,12 +87,4 @@ static inline long do_futex(u32 __user *uaddr, int op, u32 val, } #endif -#ifdef CONFIG_FUTEX_PI -extern void exit_pi_state_list(struct task_struct *curr); -#else -static inline void exit_pi_state_list(struct task_struct *curr) -{ -} -#endif - #endif diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 603fbc4e2f70..564793c24d12 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1170,7 +1170,7 @@ struct journal_s #define jbd2_might_wait_for_commit(j) \ do { \ rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ - rwsem_release(&j->j_trans_commit_map, 1, _THIS_IP_); \ + rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \ } while (0) /* journal feature predicate functions */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d83d403dac2e..09f759228e3f 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -328,13 +328,6 @@ extern int oops_may_print(void); void do_exit(long error_code) __noreturn; void complete_and_exit(struct completion *, long) __noreturn; -#ifdef CONFIG_ARCH_HAS_REFCOUNT -void refcount_error_report(struct pt_regs *regs, const char *err); -#else -static inline void refcount_error_report(struct pt_regs *regs, const char *err) -{ } -#endif - /* Internal, do not use. */ int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); int __must_check _kstrtol(const char *s, unsigned int base, long *res); diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 7ee2bb43b251..89f0745c096d 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -78,6 +78,24 @@ static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu) return kstat_cpu(cpu).irqs_sum; } +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +extern u64 kcpustat_field(struct kernel_cpustat *kcpustat, + enum cpu_usage_stat usage, int cpu); +extern void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu); +#else +static inline u64 kcpustat_field(struct kernel_cpustat *kcpustat, + enum cpu_usage_stat usage, int cpu) +{ + return kcpustat->cpustat[usage]; +} + +static inline void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu) +{ + *dst = kcpustat_cpu(cpu); +} + +#endif + extern void account_user_time(struct task_struct *, u64); extern void account_guest_time(struct task_struct *, u64); extern void account_system_time(struct task_struct *, int, u64); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index b8a835fd611b..c50d01ef1414 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -349,8 +349,7 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, struct lockdep_map *nest_lock, unsigned long ip); -extern void lock_release(struct lockdep_map *lock, int nested, - unsigned long ip); +extern void lock_release(struct lockdep_map *lock, unsigned long ip); /* * Same "read" as for lock_acquire(), except -1 means any. @@ -428,7 +427,7 @@ static inline void lockdep_set_selftest_task(struct task_struct *task) } # define lock_acquire(l, s, t, r, c, n, i) do { } while (0) -# define lock_release(l, n, i) do { } while (0) +# define lock_release(l, i) do { } while (0) # define lock_downgrade(l, i) do { } while (0) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) @@ -591,42 +590,42 @@ static inline void print_irqtrace_events(struct task_struct *curr) #define spin_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define spin_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) -#define spin_release(l, n, i) lock_release(l, n, i) +#define spin_release(l, i) lock_release(l, i) #define rwlock_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define rwlock_acquire_read(l, s, t, i) lock_acquire_shared_recursive(l, s, t, NULL, i) -#define rwlock_release(l, n, i) lock_release(l, n, i) +#define rwlock_release(l, i) lock_release(l, i) #define seqcount_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define seqcount_acquire_read(l, s, t, i) lock_acquire_shared_recursive(l, s, t, NULL, i) -#define seqcount_release(l, n, i) lock_release(l, n, i) +#define seqcount_release(l, i) lock_release(l, i) #define mutex_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define mutex_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) -#define mutex_release(l, n, i) lock_release(l, n, i) +#define mutex_release(l, i) lock_release(l, i) #define rwsem_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define rwsem_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) #define rwsem_acquire_read(l, s, t, i) lock_acquire_shared(l, s, t, NULL, i) -#define rwsem_release(l, n, i) lock_release(l, n, i) +#define rwsem_release(l, i) lock_release(l, i) #define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) -#define lock_map_release(l) lock_release(l, 1, _THIS_IP_) +#define lock_map_release(l) lock_release(l, _THIS_IP_) #ifdef CONFIG_PROVE_LOCKING # define might_lock(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, 0, 0, 0, 1, NULL, _THIS_IP_); \ - lock_release(&(lock)->dep_map, 0, _THIS_IP_); \ + lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) # define might_lock_read(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_); \ - lock_release(&(lock)->dep_map, 0, _THIS_IP_); \ + lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) #define lockdep_assert_irqs_enabled() do { \ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index a3763247547c..20d8cf194fb7 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1818,6 +1818,14 @@ union security_list_options { void (*bpf_prog_free_security)(struct bpf_prog_aux *aux); #endif /* CONFIG_BPF_SYSCALL */ int (*locked_down)(enum lockdown_reason what); +#ifdef CONFIG_PERF_EVENTS + int (*perf_event_open)(struct perf_event_attr *attr, int type); + int (*perf_event_alloc)(struct perf_event *event); + void (*perf_event_free)(struct perf_event *event); + int (*perf_event_read)(struct perf_event *event); + int (*perf_event_write)(struct perf_event *event); + +#endif }; struct security_hook_heads { @@ -2060,6 +2068,13 @@ struct security_hook_heads { struct hlist_head bpf_prog_free_security; #endif /* CONFIG_BPF_SYSCALL */ struct hlist_head locked_down; +#ifdef CONFIG_PERF_EVENTS + struct hlist_head perf_event_open; + struct hlist_head perf_event_alloc; + struct hlist_head perf_event_free; + struct hlist_head perf_event_read; + struct hlist_head perf_event_write; +#endif } __randomize_layout; /* diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index 3998cdf9cd14..ad2ca2a89d5b 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -93,7 +93,7 @@ static inline void percpu_up_read(struct percpu_rw_semaphore *sem) __percpu_up_read(sem); /* Unconditional memory barrier */ preempt_enable(); - rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_); + rwsem_release(&sem->rw_sem.dep_map, _RET_IP_); } extern void percpu_down_write(struct percpu_rw_semaphore *); @@ -118,7 +118,7 @@ extern void percpu_free_rwsem(struct percpu_rw_semaphore *); static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { - lock_release(&sem->rw_sem.dep_map, 1, ip); + lock_release(&sem->rw_sem.dep_map, ip); #ifdef CONFIG_RWSEM_SPIN_ON_OWNER if (!read) atomic_long_set(&sem->rw_sem.owner, RWSEM_OWNER_UNKNOWN); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index a07bfdb7d8ea..6d4c22aee384 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -56,6 +56,7 @@ struct perf_guest_info_callbacks { #include <linux/perf_regs.h> #include <linux/cgroup.h> #include <linux/refcount.h> +#include <linux/security.h> #include <asm/local.h> struct perf_callchain_entry { @@ -248,6 +249,8 @@ struct perf_event; #define PERF_PMU_CAP_NO_EXCLUDE 0x80 #define PERF_PMU_CAP_AUX_OUTPUT 0x100 +struct perf_output_handle; + /** * struct pmu - generic performance monitoring unit */ @@ -409,6 +412,15 @@ struct pmu { */ size_t task_ctx_size; + /* + * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data) + * can be synchronized using this function. See Intel LBR callstack support + * implementation and Perf core context switch handling callbacks for usage + * examples. + */ + void (*swap_task_ctx) (struct perf_event_context *prev, + struct perf_event_context *next); + /* optional */ /* * Set up pmu-private data structures for an AUX area @@ -423,6 +435,19 @@ struct pmu { void (*free_aux) (void *aux); /* optional */ /* + * Take a snapshot of the AUX buffer without touching the event + * state, so that preempting ->start()/->stop() callbacks does + * not interfere with their logic. Called in PMI context. + * + * Returns the size of AUX data copied to the output handle. + * + * Optional. + */ + long (*snapshot_aux) (struct perf_event *event, + struct perf_output_handle *handle, + unsigned long size); + + /* * Validate address range filters: make sure the HW supports the * requested configuration and number of filters; return 0 if the * supplied filters are valid, -errno otherwise. @@ -721,6 +746,9 @@ struct perf_event { struct perf_cgroup *cgrp; /* cgroup event is attach to */ #endif +#ifdef CONFIG_SECURITY + void *security; +#endif struct list_head sb_list; #endif /* CONFIG_PERF_EVENTS */ }; @@ -960,6 +988,7 @@ struct perf_sample_data { u32 reserved; } cpu_entry; struct perf_callchain_entry *callchain; + u64 aux_size; /* * regs_user may point to task_pt_regs or to regs_user_copy, depending @@ -1241,19 +1270,41 @@ extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, int perf_event_max_stack_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -static inline bool perf_paranoid_tracepoint_raw(void) +/* Access to perf_event_open(2) syscall. */ +#define PERF_SECURITY_OPEN 0 + +/* Finer grained perf_event_open(2) access control. */ +#define PERF_SECURITY_CPU 1 +#define PERF_SECURITY_KERNEL 2 +#define PERF_SECURITY_TRACEPOINT 3 + +static inline int perf_is_paranoid(void) { return sysctl_perf_event_paranoid > -1; } -static inline bool perf_paranoid_cpu(void) +static inline int perf_allow_kernel(struct perf_event_attr *attr) { - return sysctl_perf_event_paranoid > 0; + if (sysctl_perf_event_paranoid > 1 && !capable(CAP_SYS_ADMIN)) + return -EACCES; + + return security_perf_event_open(attr, PERF_SECURITY_KERNEL); } -static inline bool perf_paranoid_kernel(void) +static inline int perf_allow_cpu(struct perf_event_attr *attr) { - return sysctl_perf_event_paranoid > 1; + if (sysctl_perf_event_paranoid > 0 && !capable(CAP_SYS_ADMIN)) + return -EACCES; + + return security_perf_event_open(attr, PERF_SECURITY_CPU); +} + +static inline int perf_allow_tracepoint(struct perf_event_attr *attr) +{ + if (sysctl_perf_event_paranoid > -1 && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); } extern void perf_event_init(void); @@ -1327,6 +1378,9 @@ extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len); +extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, + struct perf_output_handle *handle, + unsigned long from, unsigned long to); extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); diff --git a/include/linux/rculist_bl.h b/include/linux/rculist_bl.h index 66e73ec1aa99..0b952d06eb0b 100644 --- a/include/linux/rculist_bl.h +++ b/include/linux/rculist_bl.h @@ -25,34 +25,6 @@ static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h) } /** - * hlist_bl_del_init_rcu - deletes entry from hash list with re-initialization - * @n: the element to delete from the hash list. - * - * Note: hlist_bl_unhashed() on the node returns true after this. It is - * useful for RCU based read lockfree traversal if the writer side - * must know if the list entry is still hashed or already unhashed. - * - * In particular, it means that we can not poison the forward pointers - * that may still be used for walking the hash list and we can only - * zero the pprev pointer so list_unhashed() will return true after - * this. - * - * The caller must take whatever precautions are necessary (such as - * holding appropriate locks) to avoid racing with another - * list-mutation primitive, such as hlist_bl_add_head_rcu() or - * hlist_bl_del_rcu(), running on this same list. However, it is - * perfectly legal to run concurrently with the _rcu list-traversal - * primitives, such as hlist_bl_for_each_entry_rcu(). - */ -static inline void hlist_bl_del_init_rcu(struct hlist_bl_node *n) -{ - if (!hlist_bl_unhashed(n)) { - __hlist_bl_del(n); - n->pprev = NULL; - } -} - -/** * hlist_bl_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 75a2eded7aa2..0b7506330c87 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -210,7 +210,7 @@ static inline void rcu_lock_acquire(struct lockdep_map *map) static inline void rcu_lock_release(struct lockdep_map *map) { - lock_release(map, 1, _THIS_IP_); + lock_release(map, _THIS_IP_); } extern struct lockdep_map rcu_lock_map; @@ -383,6 +383,24 @@ do { \ } while (0) /** + * rcu_replace_pointer() - replace an RCU pointer, returning its old value + * @rcu_ptr: RCU pointer, whose old value is returned + * @ptr: regular pointer + * @c: the lockdep conditions under which the dereference will take place + * + * Perform a replacement, where @rcu_ptr is an RCU-annotated + * pointer and @c is the lockdep argument that is passed to the + * rcu_dereference_protected() call used to read that pointer. The old + * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. + */ +#define rcu_replace_pointer(rcu_ptr, ptr, c) \ +({ \ + typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ + rcu_assign_pointer((rcu_ptr), (ptr)); \ + __tmp; \ +}) + +/** * rcu_swap_protected() - swap an RCU and a regular pointer * @rcu_ptr: RCU pointer * @ptr: regular pointer diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 9bf1dfe7781f..37b6f0c2b79d 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -84,6 +84,7 @@ static inline void rcu_scheduler_starting(void) { } #endif /* #else #ifndef CONFIG_SRCU */ static inline void rcu_end_inkernel_boot(void) { } static inline bool rcu_is_watching(void) { return true; } +static inline void rcu_momentary_dyntick_idle(void) { } /* Avoid RCU read-side critical sections leaking across. */ static inline void rcu_all_qs(void) { barrier(); } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 18b1ed9864b0..c5147de885ec 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -37,6 +37,7 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier(void); bool rcu_eqs_special_set(int cpu); +void rcu_momentary_dyntick_idle(void); unsigned long get_state_synchronize_rcu(void); void cond_synchronize_rcu(unsigned long oldstate); diff --git a/include/linux/refcount.h b/include/linux/refcount.h index e28cce21bad6..0ac50cf62d06 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -1,9 +1,88 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Variant of atomic_t specialized for reference counts. + * + * The interface matches the atomic_t interface (to aid in porting) but only + * provides the few functions one should use for reference counting. + * + * Saturation semantics + * ==================== + * + * refcount_t differs from atomic_t in that the counter saturates at + * REFCOUNT_SATURATED and will not move once there. This avoids wrapping the + * counter and causing 'spurious' use-after-free issues. In order to avoid the + * cost associated with introducing cmpxchg() loops into all of the saturating + * operations, we temporarily allow the counter to take on an unchecked value + * and then explicitly set it to REFCOUNT_SATURATED on detecting that underflow + * or overflow has occurred. Although this is racy when multiple threads + * access the refcount concurrently, by placing REFCOUNT_SATURATED roughly + * equidistant from 0 and INT_MAX we minimise the scope for error: + * + * INT_MAX REFCOUNT_SATURATED UINT_MAX + * 0 (0x7fff_ffff) (0xc000_0000) (0xffff_ffff) + * +--------------------------------+----------------+----------------+ + * <---------- bad value! ----------> + * + * (in a signed view of the world, the "bad value" range corresponds to + * a negative counter value). + * + * As an example, consider a refcount_inc() operation that causes the counter + * to overflow: + * + * int old = atomic_fetch_add_relaxed(r); + * // old is INT_MAX, refcount now INT_MIN (0x8000_0000) + * if (old < 0) + * atomic_set(r, REFCOUNT_SATURATED); + * + * If another thread also performs a refcount_inc() operation between the two + * atomic operations, then the count will continue to edge closer to 0. If it + * reaches a value of 1 before /any/ of the threads reset it to the saturated + * value, then a concurrent refcount_dec_and_test() may erroneously free the + * underlying object. Given the precise timing details involved with the + * round-robin scheduling of each thread manipulating the refcount and the need + * to hit the race multiple times in succession, there doesn't appear to be a + * practical avenue of attack even if using refcount_add() operations with + * larger increments. + * + * Memory ordering + * =============== + * + * Memory ordering rules are slightly relaxed wrt regular atomic_t functions + * and provide only what is strictly required for refcounts. + * + * The increments are fully relaxed; these will not provide ordering. The + * rationale is that whatever is used to obtain the object we're increasing the + * reference count on will provide the ordering. For locked data structures, + * its the lock acquire, for RCU/lockless data structures its the dependent + * load. + * + * Do note that inc_not_zero() provides a control dependency which will order + * future stores against the inc, this ensures we'll never modify the object + * if we did not in fact acquire a reference. + * + * The decrements will provide release order, such that all the prior loads and + * stores will be issued before, it also provides a control dependency, which + * will order us against the subsequent free(). + * + * The control dependency is against the load of the cmpxchg (ll/sc) that + * succeeded. This means the stores aren't fully ordered, but this is fine + * because the 1->0 transition indicates no concurrency. + * + * Note that the allocator is responsible for ordering things between free() + * and alloc(). + * + * The decrements dec_and_test() and sub_and_test() also provide acquire + * ordering on success. + * + */ + #ifndef _LINUX_REFCOUNT_H #define _LINUX_REFCOUNT_H #include <linux/atomic.h> +#include <linux/bug.h> #include <linux/compiler.h> +#include <linux/limits.h> #include <linux/spinlock_types.h> struct mutex; @@ -12,7 +91,7 @@ struct mutex; * struct refcount_t - variant of atomic_t specialized for reference counts * @refs: atomic_t counter field * - * The counter saturates at UINT_MAX and will not move once + * The counter saturates at REFCOUNT_SATURATED and will not move once * there. This avoids wrapping the counter and causing 'spurious' * use-after-free bugs. */ @@ -21,13 +100,25 @@ typedef struct refcount_struct { } refcount_t; #define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } +#define REFCOUNT_MAX INT_MAX +#define REFCOUNT_SATURATED (INT_MIN / 2) + +enum refcount_saturation_type { + REFCOUNT_ADD_NOT_ZERO_OVF, + REFCOUNT_ADD_OVF, + REFCOUNT_ADD_UAF, + REFCOUNT_SUB_UAF, + REFCOUNT_DEC_LEAK, +}; + +void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t); /** * refcount_set - set a refcount's value * @r: the refcount * @n: value to which the refcount will be set */ -static inline void refcount_set(refcount_t *r, unsigned int n) +static inline void refcount_set(refcount_t *r, int n) { atomic_set(&r->refs, n); } @@ -43,70 +134,168 @@ static inline unsigned int refcount_read(const refcount_t *r) return atomic_read(&r->refs); } -extern __must_check bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r); -extern void refcount_add_checked(unsigned int i, refcount_t *r); - -extern __must_check bool refcount_inc_not_zero_checked(refcount_t *r); -extern void refcount_inc_checked(refcount_t *r); - -extern __must_check bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r); - -extern __must_check bool refcount_dec_and_test_checked(refcount_t *r); -extern void refcount_dec_checked(refcount_t *r); - -#ifdef CONFIG_REFCOUNT_FULL - -#define refcount_add_not_zero refcount_add_not_zero_checked -#define refcount_add refcount_add_checked - -#define refcount_inc_not_zero refcount_inc_not_zero_checked -#define refcount_inc refcount_inc_checked +/** + * refcount_add_not_zero - add a value to a refcount unless it is 0 + * @i: the value to add to the refcount + * @r: the refcount + * + * Will saturate at REFCOUNT_SATURATED and WARN. + * + * Provides no memory ordering, it is assumed the caller has guaranteed the + * object memory to be stable (RCU, etc.). It does provide a control dependency + * and thereby orders future stores. See the comment on top. + * + * Use of this function is not recommended for the normal reference counting + * use case in which references are taken and released one at a time. In these + * cases, refcount_inc(), or one of its variants, should instead be used to + * increment a reference count. + * + * Return: false if the passed refcount is 0, true otherwise + */ +static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) +{ + int old = refcount_read(r); -#define refcount_sub_and_test refcount_sub_and_test_checked + do { + if (!old) + break; + } while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i)); -#define refcount_dec_and_test refcount_dec_and_test_checked -#define refcount_dec refcount_dec_checked + if (unlikely(old < 0 || old + i < 0)) + refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); -#else -# ifdef CONFIG_ARCH_HAS_REFCOUNT -# include <asm/refcount.h> -# else -static inline __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r) -{ - return atomic_add_unless(&r->refs, i, 0); + return old; } -static inline void refcount_add(unsigned int i, refcount_t *r) +/** + * refcount_add - add a value to a refcount + * @i: the value to add to the refcount + * @r: the refcount + * + * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. + * + * Provides no memory ordering, it is assumed the caller has guaranteed the + * object memory to be stable (RCU, etc.). It does provide a control dependency + * and thereby orders future stores. See the comment on top. + * + * Use of this function is not recommended for the normal reference counting + * use case in which references are taken and released one at a time. In these + * cases, refcount_inc(), or one of its variants, should instead be used to + * increment a reference count. + */ +static inline void refcount_add(int i, refcount_t *r) { - atomic_add(i, &r->refs); + int old = atomic_fetch_add_relaxed(i, &r->refs); + + if (unlikely(!old)) + refcount_warn_saturate(r, REFCOUNT_ADD_UAF); + else if (unlikely(old < 0 || old + i < 0)) + refcount_warn_saturate(r, REFCOUNT_ADD_OVF); } +/** + * refcount_inc_not_zero - increment a refcount unless it is 0 + * @r: the refcount to increment + * + * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED + * and WARN. + * + * Provides no memory ordering, it is assumed the caller has guaranteed the + * object memory to be stable (RCU, etc.). It does provide a control dependency + * and thereby orders future stores. See the comment on top. + * + * Return: true if the increment was successful, false otherwise + */ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) { - return atomic_add_unless(&r->refs, 1, 0); + return refcount_add_not_zero(1, r); } +/** + * refcount_inc - increment a refcount + * @r: the refcount to increment + * + * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN. + * + * Provides no memory ordering, it is assumed the caller already has a + * reference on the object. + * + * Will WARN if the refcount is 0, as this represents a possible use-after-free + * condition. + */ static inline void refcount_inc(refcount_t *r) { - atomic_inc(&r->refs); + refcount_add(1, r); } -static inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r) +/** + * refcount_sub_and_test - subtract from a refcount and test if it is 0 + * @i: amount to subtract from the refcount + * @r: the refcount + * + * Similar to atomic_dec_and_test(), but it will WARN, return false and + * ultimately leak on underflow and will fail to decrement when saturated + * at REFCOUNT_SATURATED. + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides an acquire ordering on success such that free() + * must come after. + * + * Use of this function is not recommended for the normal reference counting + * use case in which references are taken and released one at a time. In these + * cases, refcount_dec(), or one of its variants, should instead be used to + * decrement a reference count. + * + * Return: true if the resulting refcount is 0, false otherwise + */ +static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) { - return atomic_sub_and_test(i, &r->refs); + int old = atomic_fetch_sub_release(i, &r->refs); + + if (old == i) { + smp_acquire__after_ctrl_dep(); + return true; + } + + if (unlikely(old < 0 || old - i < 0)) + refcount_warn_saturate(r, REFCOUNT_SUB_UAF); + + return false; } +/** + * refcount_dec_and_test - decrement a refcount and test if it is 0 + * @r: the refcount + * + * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to + * decrement when saturated at REFCOUNT_SATURATED. + * + * Provides release memory ordering, such that prior loads and stores are done + * before, and provides an acquire ordering on success such that free() + * must come after. + * + * Return: true if the resulting refcount is 0, false otherwise + */ static inline __must_check bool refcount_dec_and_test(refcount_t *r) { - return atomic_dec_and_test(&r->refs); + return refcount_sub_and_test(1, r); } +/** + * refcount_dec - decrement a refcount + * @r: the refcount + * + * Similar to atomic_dec(), it will WARN on underflow and fail to decrement + * when saturated at REFCOUNT_SATURATED. + * + * Provides release memory ordering, such that prior loads and stores are done + * before. + */ static inline void refcount_dec(refcount_t *r) { - atomic_dec(&r->refs); + if (unlikely(atomic_fetch_sub_release(1, &r->refs) <= 1)) + refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } -# endif /* !CONFIG_ARCH_HAS_REFCOUNT */ -#endif /* CONFIG_REFCOUNT_FULL */ extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h index 86ebb4bf9c6e..abfb53ab11be 100644 --- a/include/linux/rwlock_api_smp.h +++ b/include/linux/rwlock_api_smp.h @@ -215,14 +215,14 @@ static inline void __raw_write_lock(rwlock_t *lock) static inline void __raw_write_unlock(rwlock_t *lock) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_write_unlock(lock); preempt_enable(); } static inline void __raw_read_unlock(rwlock_t *lock) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_read_unlock(lock); preempt_enable(); } @@ -230,7 +230,7 @@ static inline void __raw_read_unlock(rwlock_t *lock) static inline void __raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_read_unlock(lock); local_irq_restore(flags); preempt_enable(); @@ -238,7 +238,7 @@ __raw_read_unlock_irqrestore(rwlock_t *lock, unsigned long flags) static inline void __raw_read_unlock_irq(rwlock_t *lock) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_read_unlock(lock); local_irq_enable(); preempt_enable(); @@ -246,7 +246,7 @@ static inline void __raw_read_unlock_irq(rwlock_t *lock) static inline void __raw_read_unlock_bh(rwlock_t *lock) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_read_unlock(lock); __local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET); } @@ -254,7 +254,7 @@ static inline void __raw_read_unlock_bh(rwlock_t *lock) static inline void __raw_write_unlock_irqrestore(rwlock_t *lock, unsigned long flags) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_write_unlock(lock); local_irq_restore(flags); preempt_enable(); @@ -262,7 +262,7 @@ static inline void __raw_write_unlock_irqrestore(rwlock_t *lock, static inline void __raw_write_unlock_irq(rwlock_t *lock) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_write_unlock(lock); local_irq_enable(); preempt_enable(); @@ -270,7 +270,7 @@ static inline void __raw_write_unlock_irq(rwlock_t *lock) static inline void __raw_write_unlock_bh(rwlock_t *lock) { - rwlock_release(&lock->dep_map, 1, _RET_IP_); + rwlock_release(&lock->dep_map, _RET_IP_); do_raw_write_unlock(lock); __local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET); } diff --git a/include/linux/sched.h b/include/linux/sched.h index 6666e25606b7..07e68d9f5dc4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -250,16 +250,21 @@ struct prev_cputime { enum vtime_state { /* Task is sleeping or running in a CPU with VTIME inactive: */ VTIME_INACTIVE = 0, - /* Task runs in userspace in a CPU with VTIME active: */ - VTIME_USER, + /* Task is idle */ + VTIME_IDLE, /* Task runs in kernelspace in a CPU with VTIME active: */ VTIME_SYS, + /* Task runs in userspace in a CPU with VTIME active: */ + VTIME_USER, + /* Task runs as guests in a CPU with VTIME active: */ + VTIME_GUEST, }; struct vtime { seqcount_t seqcount; unsigned long long starttime; enum vtime_state state; + unsigned int cpu; u64 utime; u64 stime; u64 gtime; @@ -1054,6 +1059,8 @@ struct task_struct { #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; + struct mutex futex_exit_mutex; + unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts]; @@ -1442,7 +1449,6 @@ extern struct pid *cad_pid; */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ -#define PF_EXITPIDONE 0x00000008 /* PI exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index e6770012db18..c49257a3b510 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -117,8 +117,10 @@ extern struct mm_struct *get_task_mm(struct task_struct *task); * succeeds. */ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); -/* Remove the current tasks stale references to the old mm_struct */ -extern void mm_release(struct task_struct *, struct mm_struct *); +/* Remove the current tasks stale references to the old mm_struct on exit() */ +extern void exit_mm_release(struct task_struct *, struct mm_struct *); +/* Remove the current tasks stale references to the old mm_struct on exec() */ +extern void exec_mm_release(struct task_struct *, struct mm_struct *); #ifdef CONFIG_MEMCG extern void mm_update_next_owner(struct mm_struct *mm); diff --git a/include/linux/security.h b/include/linux/security.h index 9df7547afc0c..06ff66834501 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1895,5 +1895,42 @@ static inline void security_bpf_prog_free(struct bpf_prog_aux *aux) #endif /* CONFIG_SECURITY */ #endif /* CONFIG_BPF_SYSCALL */ -#endif /* ! __LINUX_SECURITY_H */ +#ifdef CONFIG_PERF_EVENTS +struct perf_event_attr; +struct perf_event; + +#ifdef CONFIG_SECURITY +extern int security_perf_event_open(struct perf_event_attr *attr, int type); +extern int security_perf_event_alloc(struct perf_event *event); +extern void security_perf_event_free(struct perf_event *event); +extern int security_perf_event_read(struct perf_event *event); +extern int security_perf_event_write(struct perf_event *event); +#else +static inline int security_perf_event_open(struct perf_event_attr *attr, + int type) +{ + return 0; +} + +static inline int security_perf_event_alloc(struct perf_event *event) +{ + return 0; +} + +static inline void security_perf_event_free(struct perf_event *event) +{ +} + +static inline int security_perf_event_read(struct perf_event *event) +{ + return 0; +} +static inline int security_perf_event_write(struct perf_event *event) +{ + return 0; +} +#endif /* CONFIG_SECURITY */ +#endif /* CONFIG_PERF_EVENTS */ + +#endif /* ! __LINUX_SECURITY_H */ diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index bcf4cf26b8c8..0491d963d47e 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -79,7 +79,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) local_irq_save(flags); seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_); - seqcount_release(&l->dep_map, 1, _RET_IP_); + seqcount_release(&l->dep_map, _RET_IP_); local_irq_restore(flags); } @@ -384,7 +384,7 @@ static inline void write_seqcount_begin(seqcount_t *s) static inline void write_seqcount_end(seqcount_t *s) { - seqcount_release(&s->dep_map, 1, _RET_IP_); + seqcount_release(&s->dep_map, _RET_IP_); raw_write_seqcount_end(s); } diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index b762eaba4cdf..19a9be9d97ee 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -147,7 +147,7 @@ static inline void __raw_spin_lock(raw_spinlock_t *lock) static inline void __raw_spin_unlock(raw_spinlock_t *lock) { - spin_release(&lock->dep_map, 1, _RET_IP_); + spin_release(&lock->dep_map, _RET_IP_); do_raw_spin_unlock(lock); preempt_enable(); } @@ -155,7 +155,7 @@ static inline void __raw_spin_unlock(raw_spinlock_t *lock) static inline void __raw_spin_unlock_irqrestore(raw_spinlock_t *lock, unsigned long flags) { - spin_release(&lock->dep_map, 1, _RET_IP_); + spin_release(&lock->dep_map, _RET_IP_); do_raw_spin_unlock(lock); local_irq_restore(flags); preempt_enable(); @@ -163,7 +163,7 @@ static inline void __raw_spin_unlock_irqrestore(raw_spinlock_t *lock, static inline void __raw_spin_unlock_irq(raw_spinlock_t *lock) { - spin_release(&lock->dep_map, 1, _RET_IP_); + spin_release(&lock->dep_map, _RET_IP_); do_raw_spin_unlock(lock); local_irq_enable(); preempt_enable(); @@ -171,7 +171,7 @@ static inline void __raw_spin_unlock_irq(raw_spinlock_t *lock) static inline void __raw_spin_unlock_bh(raw_spinlock_t *lock) { - spin_release(&lock->dep_map, 1, _RET_IP_); + spin_release(&lock->dep_map, _RET_IP_); do_raw_spin_unlock(lock); __local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET); } diff --git a/include/linux/tick.h b/include/linux/tick.h index f92a10b5e112..7896f792d3b0 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -108,7 +108,8 @@ enum tick_dep_bits { TICK_DEP_BIT_POSIX_TIMER = 0, TICK_DEP_BIT_PERF_EVENTS = 1, TICK_DEP_BIT_SCHED = 2, - TICK_DEP_BIT_CLOCK_UNSTABLE = 3 + TICK_DEP_BIT_CLOCK_UNSTABLE = 3, + TICK_DEP_BIT_RCU = 4 }; #define TICK_DEP_MASK_NONE 0 @@ -116,6 +117,7 @@ enum tick_dep_bits { #define TICK_DEP_MASK_PERF_EVENTS (1 << TICK_DEP_BIT_PERF_EVENTS) #define TICK_DEP_MASK_SCHED (1 << TICK_DEP_BIT_SCHED) #define TICK_DEP_MASK_CLOCK_UNSTABLE (1 << TICK_DEP_BIT_CLOCK_UNSTABLE) +#define TICK_DEP_MASK_RCU (1 << TICK_DEP_BIT_RCU) #ifdef CONFIG_NO_HZ_COMMON extern bool tick_nohz_enabled; @@ -174,7 +176,7 @@ extern cpumask_var_t tick_nohz_full_mask; static inline bool tick_nohz_full_enabled(void) { - if (!context_tracking_is_enabled()) + if (!context_tracking_enabled()) return false; return tick_nohz_full_running; @@ -268,6 +270,9 @@ static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } +static inline void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { } +static inline void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { } + static inline void tick_dep_set(enum tick_dep_bits bit) { } static inline void tick_dep_clear(enum tick_dep_bits bit) { } static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit) { } diff --git a/include/linux/vtime.h b/include/linux/vtime.h index a26ed10a4eac..2cdeca062db3 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -11,11 +11,15 @@ struct task_struct; /* - * vtime_accounting_cpu_enabled() definitions/declarations + * vtime_accounting_enabled_this_cpu() definitions/declarations */ #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) -static inline bool vtime_accounting_cpu_enabled(void) { return true; } + +static inline bool vtime_accounting_enabled_this_cpu(void) { return true; } +extern void vtime_task_switch(struct task_struct *prev); + #elif defined(CONFIG_VIRT_CPU_ACCOUNTING_GEN) + /* * Checks if vtime is enabled on some CPU. Cputime readers want to be careful * in that case and compute the tickless cputime. @@ -24,46 +28,43 @@ static inline bool vtime_accounting_cpu_enabled(void) { return true; } */ static inline bool vtime_accounting_enabled(void) { - return context_tracking_is_enabled(); + return context_tracking_enabled(); } -static inline bool vtime_accounting_cpu_enabled(void) +static inline bool vtime_accounting_enabled_cpu(int cpu) { - if (vtime_accounting_enabled()) { - if (context_tracking_cpu_is_enabled()) - return true; - } - - return false; + return context_tracking_enabled_cpu(cpu); } -#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ -static inline bool vtime_accounting_cpu_enabled(void) { return false; } -#endif +static inline bool vtime_accounting_enabled_this_cpu(void) +{ + return context_tracking_enabled_this_cpu(); +} -/* - * Common vtime APIs - */ -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +extern void vtime_task_switch_generic(struct task_struct *prev); -#ifdef __ARCH_HAS_VTIME_TASK_SWITCH -extern void vtime_task_switch(struct task_struct *prev); -#else -extern void vtime_common_task_switch(struct task_struct *prev); static inline void vtime_task_switch(struct task_struct *prev) { - if (vtime_accounting_cpu_enabled()) - vtime_common_task_switch(prev); + if (vtime_accounting_enabled_this_cpu()) + vtime_task_switch_generic(prev); } -#endif /* __ARCH_HAS_VTIME_TASK_SWITCH */ - -extern void vtime_account_system(struct task_struct *tsk); -extern void vtime_account_idle(struct task_struct *tsk); #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ +static inline bool vtime_accounting_enabled_cpu(int cpu) {return false; } +static inline bool vtime_accounting_enabled_this_cpu(void) { return false; } static inline void vtime_task_switch(struct task_struct *prev) { } -static inline void vtime_account_system(struct task_struct *tsk) { } + +#endif + +/* + * Common vtime APIs + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING +extern void vtime_account_kernel(struct task_struct *tsk); +extern void vtime_account_idle(struct task_struct *tsk); +#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ +static inline void vtime_account_kernel(struct task_struct *tsk) { } #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN @@ -86,7 +87,7 @@ extern void vtime_account_irq_enter(struct task_struct *tsk); static inline void vtime_account_irq_exit(struct task_struct *tsk) { /* On hard|softirq exit we always account to hard|softirq cputime */ - vtime_account_system(tsk); + vtime_account_kernel(tsk); } extern void vtime_flush(struct task_struct *tsk); #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 3af7c0e03be5..d7554252404c 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -182,7 +182,7 @@ static inline void ww_acquire_done(struct ww_acquire_ctx *ctx) static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) { #ifdef CONFIG_DEBUG_MUTEXES - mutex_release(&ctx->dep_map, 0, _THIS_IP_); + mutex_release(&ctx->dep_map, _THIS_IP_); DEBUG_LOCKS_WARN_ON(ctx->acquired); if (!IS_ENABLED(CONFIG_PROVE_LOCKING)) |
