Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index ec912d0..ecdc654 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -71,6 +71,7 @@
#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */
#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */
#define MMF_OOM_VICTIM 25 /* mm is the oom victim */
+#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */
#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP)
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
index 5966744..afa940c 100644
--- a/include/linux/sched/cpufreq.h
+++ b/include/linux/sched/cpufreq.h
@@ -20,6 +20,12 @@
void (*func)(struct update_util_data *data, u64 time,
unsigned int flags));
void cpufreq_remove_update_util_hook(int cpu);
+
+static inline unsigned long map_util_freq(unsigned long util,
+ unsigned long freq, unsigned long cap)
+{
+ return (freq + (freq >> 2)) * util / cap;
+}
#endif /* CONFIG_CPU_FREQ */
#endif /* _LINUX_SCHED_CPUFREQ_H */
diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h
index 53f883f..6c9f19a 100644
--- a/include/linux/sched/cputime.h
+++ b/include/linux/sched/cputime.h
@@ -61,8 +61,7 @@
* Thread group CPU time accounting.
*/
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
-void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
-
+void thread_group_sample_cputime(struct task_struct *tsk, u64 *samples);
/*
* The following are functions that support scheduler-internal time accounting.
@@ -71,7 +70,7 @@
*/
/**
- * get_running_cputimer - return &tsk->signal->cputimer if cputimer is running
+ * get_running_cputimer - return &tsk->signal->cputimer if cputimers are active
*
* @tsk: Pointer to target task.
*/
@@ -81,8 +80,11 @@
{
struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
- /* Check if cputimer isn't running. This is accessed without locking. */
- if (!READ_ONCE(cputimer->running))
+ /*
+ * Check whether posix CPU timers are active. If not the thread
+ * group accounting is not active either. Lockless check.
+ */
+ if (!READ_ONCE(tsk->signal->posix_cputimers.timers_active))
return NULL;
/*
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 0cb0343..1aff00b 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -24,3 +24,11 @@
{
return (s64)(a - b) < 0;
}
+
+#ifdef CONFIG_SMP
+
+struct root_domain;
+extern void dl_add_task_root_domain(struct task_struct *p);
+extern void dl_clear_root_domain(struct root_domain *rd);
+
+#endif /* CONFIG_SMP */
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 4a6582c..6c8512d 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -16,9 +16,10 @@
};
#ifdef CONFIG_CPU_ISOLATION
-DECLARE_STATIC_KEY_FALSE(housekeeping_overriden);
+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 void __init housekeeping_init(void);
@@ -35,6 +36,11 @@
return cpu_possible_mask;
}
+static inline bool housekeeping_enabled(enum hk_flags flags)
+{
+ return false;
+}
+
static inline void housekeeping_affine(struct task_struct *t,
enum hk_flags flags) { }
static inline void housekeeping_init(void) { }
@@ -43,7 +49,7 @@
static inline bool housekeeping_cpu(int cpu, enum hk_flags flags)
{
#ifdef CONFIG_CPU_ISOLATION
- if (static_branch_unlikely(&housekeeping_overriden))
+ if (static_branch_unlikely(&housekeeping_overridden))
return housekeeping_test_cpu(cpu, flags);
#endif
return true;
diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index 98228bd..fa067de 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -18,6 +18,7 @@
#define JOBCTL_TRAP_NOTIFY_BIT 20 /* trap for NOTIFY */
#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_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT)
#define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT)
@@ -26,6 +27,7 @@
#define JOBCTL_TRAP_NOTIFY (1UL << JOBCTL_TRAP_NOTIFY_BIT)
#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_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h
index 80bc84b..4859bea 100644
--- a/include/linux/sched/loadavg.h
+++ b/include/linux/sched/loadavg.h
@@ -22,10 +22,26 @@
#define EXP_5 2014 /* 1/exp(5sec/5min) */
#define EXP_15 2037 /* 1/exp(5sec/15min) */
-#define CALC_LOAD(load,exp,n) \
- load *= exp; \
- load += n*(FIXED_1-exp); \
- load >>= FSHIFT;
+/*
+ * a1 = a0 * e + a * (1 - e)
+ */
+static inline unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+ unsigned long newload;
+
+ newload = load * exp + active * (FIXED_1 - exp);
+ if (active >= load)
+ newload += FIXED_1-1;
+
+ return newload / FIXED_1;
+}
+
+extern unsigned long calc_load_n(unsigned long load, unsigned long exp,
+ unsigned long active, unsigned int n);
+
+#define LOAD_INT(x) ((x) >> FSHIFT)
+#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
extern void calc_global_load(unsigned long ticks);
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index aebb370..c49257a 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -49,6 +49,31 @@
__mmdrop(mm);
}
+/*
+ * This has to be called after a get_task_mm()/mmget_not_zero()
+ * followed by taking the mmap_sem for writing before modifying the
+ * vmas or anything the coredump pretends not to change from under it.
+ *
+ * It also has to be called when mmgrab() is used in the context of
+ * the process, but then the mm_count refcount is transferred outside
+ * the context of the process to run down_write() on that pinned mm.
+ *
+ * NOTE: find_extend_vma() called from GUP context is the only place
+ * that can modify the "mm" (notably the vm_start/end) under mmap_sem
+ * for reading and outside the context of the process, so it is also
+ * the only case that holds the mmap_sem for reading that must call
+ * this function. Generally if the mmap_sem is hold for reading
+ * there's no need of this check after get_task_mm()/mmget_not_zero().
+ *
+ * This function can be obsoleted and the check can be removed, after
+ * the coredump code will hold the mmap_sem for writing before
+ * invoking the ->core_dump methods.
+ */
+static inline bool mmget_still_valid(struct mm_struct *mm)
+{
+ return likely(!mm->core_state);
+}
+
/**
* mmget() - Pin the address space associated with a &struct mm_struct.
* @mm: The address space to pin.
@@ -92,8 +117,10 @@
* 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);
@@ -148,17 +175,25 @@
* Applies per-task gfp context to the given allocation flags.
* PF_MEMALLOC_NOIO implies GFP_NOIO
* PF_MEMALLOC_NOFS implies GFP_NOFS
+ * PF_MEMALLOC_NOCMA implies no allocation from CMA region.
*/
static inline gfp_t current_gfp_context(gfp_t flags)
{
- /*
- * NOIO implies both NOIO and NOFS and it is a weaker context
- * so always make sure it makes precendence
- */
- if (unlikely(current->flags & PF_MEMALLOC_NOIO))
- flags &= ~(__GFP_IO | __GFP_FS);
- else if (unlikely(current->flags & PF_MEMALLOC_NOFS))
- flags &= ~__GFP_FS;
+ if (unlikely(current->flags &
+ (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) {
+ /*
+ * NOIO implies both NOIO and NOFS and it is a weaker context
+ * so always make sure it makes precedence
+ */
+ if (current->flags & PF_MEMALLOC_NOIO)
+ flags &= ~(__GFP_IO | __GFP_FS);
+ else if (current->flags & PF_MEMALLOC_NOFS)
+ flags &= ~__GFP_FS;
+#ifdef CONFIG_CMA
+ if (current->flags & PF_MEMALLOC_NOCMA)
+ flags &= ~__GFP_MOVABLE;
+#endif
+ }
return flags;
}
@@ -248,6 +283,30 @@
current->flags = (current->flags & ~PF_MEMALLOC) | flags;
}
+#ifdef CONFIG_CMA
+static inline unsigned int memalloc_nocma_save(void)
+{
+ unsigned int flags = current->flags & PF_MEMALLOC_NOCMA;
+
+ current->flags |= PF_MEMALLOC_NOCMA;
+ return flags;
+}
+
+static inline void memalloc_nocma_restore(unsigned int flags)
+{
+ current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags;
+}
+#else
+static inline unsigned int memalloc_nocma_save(void)
+{
+ return 0;
+}
+
+static inline void memalloc_nocma_restore(unsigned int flags)
+{
+}
+#endif
+
#ifdef CONFIG_MEMCG
/**
* memalloc_use_memcg - Starts the remote memcg charging scope.
@@ -305,16 +364,16 @@
static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
{
+ if (current->mm != mm)
+ return;
if (likely(!(atomic_read(&mm->membarrier_state) &
MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE)))
return;
sync_core_before_usermode();
}
-static inline void membarrier_execve(struct task_struct *t)
-{
- atomic_set(&t->mm->membarrier_state, 0);
-}
+extern void membarrier_exec_mmap(struct mm_struct *mm);
+
#else
#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
@@ -323,7 +382,7 @@
{
}
#endif
-static inline void membarrier_execve(struct task_struct *t)
+static inline void membarrier_exec_mmap(struct mm_struct *mm)
{
}
static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h
index b36f4cf..1abe91f 100644
--- a/include/linux/sched/nohz.h
+++ b/include/linux/sched/nohz.h
@@ -7,14 +7,6 @@
*/
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
-extern void cpu_load_update_nohz_start(void);
-extern void cpu_load_update_nohz_stop(void);
-#else
-static inline void cpu_load_update_nohz_start(void) { }
-static inline void cpu_load_update_nohz_stop(void) { }
-#endif
-
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
extern void nohz_balance_enter_idle(int cpu);
extern int get_nohz_timer_target(void);
#else
diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h
index e7dd04a..3988762 100644
--- a/include/linux/sched/numa_balancing.h
+++ b/include/linux/sched/numa_balancing.h
@@ -19,7 +19,7 @@
extern void task_numa_fault(int last_node, int node, int pages, int flags);
extern pid_t task_numa_group_id(struct task_struct *p);
extern void set_numabalancing_state(bool enabled);
-extern void task_numa_free(struct task_struct *p);
+extern void task_numa_free(struct task_struct *p, bool final);
extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page,
int src_nid, int dst_cpu);
#else
@@ -34,7 +34,7 @@
static inline void set_numabalancing_state(bool enabled)
{
}
-static inline void task_numa_free(struct task_struct *p)
+static inline void task_numa_free(struct task_struct *p, bool final)
{
}
static inline bool should_numa_migrate_memory(struct task_struct *p,
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 1be3572..8805025 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -8,16 +8,18 @@
#include <linux/sched/jobctl.h>
#include <linux/sched/task.h>
#include <linux/cred.h>
+#include <linux/refcount.h>
+#include <linux/posix-timers.h>
/*
* Types defining task->signal and task->sighand and APIs using them:
*/
struct sighand_struct {
- atomic_t count;
- struct k_sigaction action[_NSIG];
spinlock_t siglock;
+ refcount_t count;
wait_queue_head_t signalfd_wqh;
+ struct k_sigaction action[_NSIG];
};
/*
@@ -55,18 +57,12 @@
/**
* struct thread_group_cputimer - thread group interval timer counts
* @cputime_atomic: atomic thread group interval timers.
- * @running: true when there are timers running and
- * @cputime_atomic receives updates.
- * @checking_timer: true when a thread in the group is in the
- * process of checking for thread group timers.
*
* This structure contains the version of task_cputime, above, that is
* used for thread group CPU timer calculations.
*/
struct thread_group_cputimer {
struct task_cputime_atomic cputime_atomic;
- bool running;
- bool checking_timer;
};
struct multiprocess_signals {
@@ -82,7 +78,7 @@
* the locking of signal_struct.
*/
struct signal_struct {
- atomic_t sigcnt;
+ refcount_t sigcnt;
atomic_t live;
int nr_threads;
struct list_head thread_head;
@@ -147,12 +143,9 @@
*/
struct thread_group_cputimer cputimer;
- /* Earliest-expiration cache. */
- struct task_cputime cputime_expires;
-
- struct list_head cpu_timers[3];
-
#endif
+ /* Empty if CONFIG_POSIX_TIMERS=n */
+ struct posix_cputimers posix_cputimers;
/* PID/PID hash table linkage. */
struct pid *pids[PIDTYPE_MAX];
@@ -270,17 +263,18 @@
extern void flush_signals(struct task_struct *);
extern void ignore_signals(struct task_struct *);
extern void flush_signal_handlers(struct task_struct *, int force_default);
-extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
+extern int dequeue_signal(struct task_struct *task,
+ sigset_t *mask, kernel_siginfo_t *info);
-static inline int kernel_dequeue_signal(siginfo_t *info)
+static inline int kernel_dequeue_signal(void)
{
- struct task_struct *tsk = current;
- siginfo_t __info;
+ struct task_struct *task = current;
+ kernel_siginfo_t __info;
int ret;
- spin_lock_irq(&tsk->sighand->siglock);
- ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info);
- spin_unlock_irq(&tsk->sighand->siglock);
+ spin_lock_irq(&task->sighand->siglock);
+ ret = dequeue_signal(task, &task->blocked, &__info);
+ spin_unlock_irq(&task->sighand->siglock);
return ret;
}
@@ -305,16 +299,19 @@
# define ___ARCH_SI_IA64(_a1, _a2, _a3)
#endif
-int force_sig_fault(int sig, int code, void __user *addr
+int force_sig_fault_to_task(int sig, int code, void __user *addr
___ARCH_SI_TRAPNO(int trapno)
___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)
, struct task_struct *t);
+int force_sig_fault(int sig, int code, void __user *addr
+ ___ARCH_SI_TRAPNO(int trapno)
+ ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr));
int send_sig_fault(int sig, int code, void __user *addr
___ARCH_SI_TRAPNO(int trapno)
___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)
, struct task_struct *t);
-int force_sig_mceerr(int code, void __user *, short, struct task_struct *);
+int force_sig_mceerr(int code, void __user *, short);
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);
@@ -322,18 +319,18 @@
int force_sig_ptrace_errno_trap(int errno, void __user *addr);
-extern int send_sig_info(int, struct siginfo *, struct task_struct *);
-extern void force_sigsegv(int sig, struct task_struct *p);
-extern int force_sig_info(int, struct siginfo *, struct task_struct *);
-extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp);
-extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid);
-extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *,
+extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *);
+extern void force_sigsegv(int sig);
+extern int force_sig_info(struct kernel_siginfo *);
+extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp);
+extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid);
+extern int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr, struct pid *,
const struct cred *);
extern int kill_pgrp(struct pid *pid, int sig, int priv);
extern int kill_pid(struct pid *pid, int sig, int priv);
extern __must_check bool do_notify_parent(struct task_struct *, int);
extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
-extern void force_sig(int, struct task_struct *);
+extern void force_sig(int);
extern int send_sig(int, struct task_struct *, int);
extern int zap_other_threads(struct task_struct *p);
extern struct sigqueue *sigqueue_alloc(void);
@@ -415,12 +412,21 @@
static inline void set_restore_sigmask(void)
{
set_thread_flag(TIF_RESTORE_SIGMASK);
- WARN_ON(!test_thread_flag(TIF_SIGPENDING));
}
+
+static inline void clear_tsk_restore_sigmask(struct task_struct *task)
+{
+ clear_tsk_thread_flag(task, TIF_RESTORE_SIGMASK);
+}
+
static inline void clear_restore_sigmask(void)
{
clear_thread_flag(TIF_RESTORE_SIGMASK);
}
+static inline bool test_tsk_restore_sigmask(struct task_struct *task)
+{
+ return test_tsk_thread_flag(task, TIF_RESTORE_SIGMASK);
+}
static inline bool test_restore_sigmask(void)
{
return test_thread_flag(TIF_RESTORE_SIGMASK);
@@ -436,7 +442,10 @@
static inline void set_restore_sigmask(void)
{
current->restore_sigmask = true;
- WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+}
+static inline void clear_tsk_restore_sigmask(struct task_struct *task)
+{
+ task->restore_sigmask = false;
}
static inline void clear_restore_sigmask(void)
{
@@ -446,6 +455,10 @@
{
return current->restore_sigmask;
}
+static inline bool test_tsk_restore_sigmask(struct task_struct *task)
+{
+ return task->restore_sigmask;
+}
static inline bool test_and_clear_restore_sigmask(void)
{
if (!current->restore_sigmask)
@@ -461,6 +474,16 @@
__set_current_blocked(¤t->saved_sigmask);
}
+extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize);
+
+static inline void restore_saved_sigmask_unless(bool interrupted)
+{
+ if (interrupted)
+ WARN_ON(!test_thread_flag(TIF_SIGPENDING));
+ else
+ restore_saved_sigmask();
+}
+
static inline sigset_t *sigmask_to_save(void)
{
sigset_t *res = ¤t->blocked;
@@ -475,9 +498,8 @@
}
/* These can be the second arg to send_sig_info/send_group_sig_info. */
-#define SEND_SIG_NOINFO ((struct siginfo *) 0)
-#define SEND_SIG_PRIV ((struct siginfo *) 1)
-#define SEND_SIG_FORCED ((struct siginfo *) 2)
+#define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0)
+#define SEND_SIG_PRIV ((struct kernel_siginfo *) 1)
/*
* True if we are on the alternate signal stack.
@@ -599,9 +621,9 @@
return task->signal->pids[PIDTYPE_SID];
}
-static inline int get_nr_threads(struct task_struct *tsk)
+static inline int get_nr_threads(struct task_struct *task)
{
- return tsk->signal->nr_threads;
+ return task->signal->nr_threads;
}
static inline bool thread_group_leader(struct task_struct *p)
@@ -640,35 +662,35 @@
#define delay_group_leader(p) \
(thread_group_leader(p) && !thread_group_empty(p))
-extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
+extern struct sighand_struct *__lock_task_sighand(struct task_struct *task,
unsigned long *flags);
-static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
+static inline struct sighand_struct *lock_task_sighand(struct task_struct *task,
unsigned long *flags)
{
struct sighand_struct *ret;
- ret = __lock_task_sighand(tsk, flags);
- (void)__cond_lock(&tsk->sighand->siglock, ret);
+ ret = __lock_task_sighand(task, flags);
+ (void)__cond_lock(&task->sighand->siglock, ret);
return ret;
}
-static inline void unlock_task_sighand(struct task_struct *tsk,
+static inline void unlock_task_sighand(struct task_struct *task,
unsigned long *flags)
{
- spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
+ spin_unlock_irqrestore(&task->sighand->siglock, *flags);
}
-static inline unsigned long task_rlimit(const struct task_struct *tsk,
+static inline unsigned long task_rlimit(const struct task_struct *task,
unsigned int limit)
{
- return READ_ONCE(tsk->signal->rlim[limit].rlim_cur);
+ return READ_ONCE(task->signal->rlim[limit].rlim_cur);
}
-static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
+static inline unsigned long task_rlimit_max(const struct task_struct *task,
unsigned int limit)
{
- return READ_ONCE(tsk->signal->rlim[limit].rlim_max);
+ return READ_ONCE(task->signal->rlim[limit].rlim_max);
}
static inline unsigned long rlimit(unsigned int limit)
diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h
index 04f1321..5682864 100644
--- a/include/linux/sched/stat.h
+++ b/include/linux/sched/stat.h
@@ -8,7 +8,7 @@
* Various counters maintained by the scheduler and fork(),
* exposed via /proc, sys.c or used by drivers via these APIs.
*
- * ( Note that all these values are aquired without locking,
+ * ( Note that all these values are acquired without locking,
* so they can only be relied on in narrow circumstances. )
*/
@@ -20,7 +20,6 @@
extern bool single_task_running(void);
extern unsigned long nr_iowait(void);
extern unsigned long nr_iowait_cpu(int cpu);
-extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
static inline int sched_info_on(void)
{
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index a9c32da..d4f6215 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -56,6 +56,11 @@
extern unsigned int sysctl_sched_rt_period;
extern int sysctl_sched_rt_runtime;
+#ifdef CONFIG_UCLAMP_TASK
+extern unsigned int sysctl_sched_uclamp_util_min;
+extern unsigned int sysctl_sched_uclamp_util_max;
+#endif
+
#ifdef CONFIG_CFS_BANDWIDTH
extern unsigned int sysctl_sched_cfs_bandwidth_slice;
#endif
@@ -75,6 +80,12 @@
void __user *buffer, size_t *lenp,
loff_t *ppos);
+#ifdef CONFIG_UCLAMP_TASK
+extern int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos);
+#endif
+
extern int sysctl_numa_balancing(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
@@ -83,4 +94,11 @@
void __user *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;
+extern int sched_energy_aware_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos);
+#endif
+
#endif /* _LINUX_SCHED_SYSCTL_H */
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 108ede9..4b1c3b6 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -8,11 +8,26 @@
*/
#include <linux/sched.h>
+#include <linux/uaccess.h>
struct task_struct;
struct rusage;
union thread_union;
+/* All the bits taken by the old clone syscall. */
+#define CLONE_LEGACY_FLAGS 0xffffffffULL
+
+struct kernel_clone_args {
+ u64 flags;
+ int __user *pidfd;
+ int __user *child_tid;
+ int __user *parent_tid;
+ int exit_signal;
+ unsigned long stack;
+ unsigned long stack_size;
+ unsigned long tls;
+};
+
/*
* This serializes "schedule()" and also protects
* the run-queue from deletions/modifications (but
@@ -39,6 +54,8 @@
extern void proc_caches_init(void);
+extern void fork_init(void);
+
extern void release_task(struct task_struct * p);
#ifdef CONFIG_HAVE_COPY_THREAD_TLS
@@ -71,9 +88,11 @@
extern void exit_files(struct task_struct *);
extern void exit_itimers(struct signal_struct *);
-extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long);
+extern long _do_fork(struct kernel_clone_args *kargs);
+extern bool legacy_clone_args_valid(const struct kernel_clone_args *kargs);
extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
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 long kernel_wait4(pid_t, int __user *, int, struct rusage *);
@@ -86,17 +105,21 @@
#define sched_exec() {}
#endif
-#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
+static inline struct task_struct *get_task_struct(struct task_struct *t)
+{
+ refcount_inc(&t->usage);
+ return t;
+}
extern void __put_task_struct(struct task_struct *t);
static inline void put_task_struct(struct task_struct *t)
{
- if (atomic_dec_and_test(&t->usage))
+ if (refcount_dec_and_test(&t->usage))
__put_task_struct(t);
}
-struct task_struct *task_rcu_dereference(struct task_struct **ptask);
+void put_task_struct_rcu_user(struct task_struct *task);
#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
extern int arch_task_struct_size __read_mostly;
diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index 6a84192..2413427 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -61,7 +61,7 @@
#ifdef CONFIG_THREAD_INFO_IN_TASK
static inline void *try_get_task_stack(struct task_struct *tsk)
{
- return atomic_inc_not_zero(&tsk->stack_refcount) ?
+ return refcount_inc_not_zero(&tsk->stack_refcount) ?
task_stack_page(tsk) : NULL;
}
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 2634774..f341163 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -7,12 +7,6 @@
#include <linux/sched/idle.h>
/*
- * Increase resolution of cpu_capacity calculations
- */
-#define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT
-#define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT)
-
-/*
* sched-domains (multiprocessor balancing) declarations:
*/
#ifdef CONFIG_SMP
@@ -23,10 +17,10 @@
#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */
#define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */
#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */
-#define SD_ASYM_CPUCAPACITY 0x0040 /* Groups have different max cpu capacities */
-#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share cpu capacity */
+#define SD_ASYM_CPUCAPACITY 0x0040 /* Domain members have different CPU capacities */
+#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share CPU capacity */
#define SD_SHARE_POWERDOMAIN 0x0100 /* Domain members share power domain */
-#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */
+#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share CPU pkg resources */
#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */
#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */
#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */
@@ -76,20 +70,14 @@
struct sched_domain {
/* These fields must be setup */
- struct sched_domain *parent; /* top domain must be null terminated */
- struct sched_domain *child; /* bottom domain must be null terminated */
+ struct sched_domain __rcu *parent; /* top domain must be null terminated */
+ struct sched_domain __rcu *child; /* bottom domain must be null terminated */
struct sched_group *groups; /* the balancing groups of the domain */
unsigned long min_interval; /* Minimum balance interval ms */
unsigned long max_interval; /* Maximum balance interval ms */
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 busy_idx;
- unsigned int idle_idx;
- unsigned int newidle_idx;
- unsigned int wake_idx;
- unsigned int forkexec_idx;
- unsigned int smt_gain;
int nohz_idle; /* NOHZ IDLE status */
int flags; /* See SD_* */
@@ -162,6 +150,10 @@
return to_cpumask(sd->span);
}
+extern void partition_sched_domains_locked(int ndoms_new,
+ cpumask_var_t doms_new[],
+ struct sched_domain_attr *dattr_new);
+
extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new);
@@ -177,10 +169,10 @@
#define SDTL_OVERLAP 0x01
struct sd_data {
- struct sched_domain **__percpu sd;
- struct sched_domain_shared **__percpu sds;
- struct sched_group **__percpu sg;
- struct sched_group_capacity **__percpu sgc;
+ struct sched_domain *__percpu *sd;
+ struct sched_domain_shared *__percpu *sds;
+ struct sched_group *__percpu *sg;
+ struct sched_group_capacity *__percpu *sgc;
};
struct sched_domain_topology_level {
@@ -207,6 +199,12 @@
struct sched_domain_attr;
static inline void
+partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
+ struct sched_domain_attr *dattr_new)
+{
+}
+
+static inline void
partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new)
{
@@ -219,6 +217,14 @@
#endif /* !CONFIG_SMP */
+#ifndef arch_scale_cpu_capacity
+static __always_inline
+unsigned long arch_scale_cpu_capacity(int cpu)
+{
+ return SCHED_CAPACITY_SCALE;
+}
+#endif
+
static inline int task_node(const struct task_struct *p)
{
return cpu_to_node(task_cpu(p));
diff --git a/include/linux/sched/types.h b/include/linux/sched/types.h
new file mode 100644
index 0000000..3c3e049
--- /dev/null
+++ b/include/linux/sched/types.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_TYPES_H
+#define _LINUX_SCHED_TYPES_H
+
+#include <linux/types.h>
+
+/**
+ * struct task_cputime - collected CPU time counts
+ * @stime: time spent in kernel mode, in nanoseconds
+ * @utime: time spent in user mode, in nanoseconds
+ * @sum_exec_runtime: total time spent on the CPU, in nanoseconds
+ *
+ * This structure groups together three kinds of CPU time that are tracked for
+ * threads and thread groups. Most things considering CPU time want to group
+ * these counts together and treat all three of them in parallel.
+ */
+struct task_cputime {
+ u64 stime;
+ u64 utime;
+ unsigned long long sum_exec_runtime;
+};
+
+#endif
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 39ad98c..917d88e 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -7,8 +7,6 @@
#include <linux/refcount.h>
#include <linux/ratelimit.h>
-struct key;
-
/*
* Some day this will be a full-fledged user tracking system..
*/
@@ -30,17 +28,12 @@
unsigned long unix_inflight; /* How many files in flight in unix sockets */
atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */
-#ifdef CONFIG_KEYS
- struct key *uid_keyring; /* UID specific keyring */
- struct key *session_keyring; /* UID's default session keyring */
-#endif
-
/* Hash table maintenance information */
struct hlist_node uidhash_node;
kuid_t uid;
#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \
- defined(CONFIG_NET)
+ defined(CONFIG_NET) || defined(CONFIG_IO_URING)
atomic_long_t locked_vm;
#endif
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index 10b19a1..26a2013 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -24,9 +24,13 @@
* called near the end of a function. Otherwise, the list can be
* re-initialized for later re-use by wake_q_init().
*
- * Note that this can cause spurious wakeups. schedule() callers
+ * NOTE that this can cause spurious wakeups. schedule() callers
* must ensure the call is done inside a loop, confirming that the
* wakeup condition has in fact occurred.
+ *
+ * NOTE that there is no guarantee the wakeup will happen any later than the
+ * wake_q_add() location. Therefore task must be ready to be woken at the
+ * location of the wake_q_add().
*/
#include <linux/sched.h>
@@ -47,8 +51,13 @@
head->lastp = &head->first;
}
-extern void wake_q_add(struct wake_q_head *head,
- struct task_struct *task);
+static inline bool wake_q_empty(struct wake_q_head *head)
+{
+ return head->first == WAKE_Q_TAIL;
+}
+
+extern void wake_q_add(struct wake_q_head *head, struct task_struct *task);
+extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task);
extern void wake_up_q(struct wake_q_head *head);
#endif /* _LINUX_SCHED_WAKE_Q_H */