#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+/*
+ * Special states are those that do not use the normal wait-loop pattern. See
+ * the comment with set_special_state().
+ */
+#define is_special_task_state(state) \
+ ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_DEAD))
+
#define __set_current_state(state_value) \
do { \
+ WARN_ON_ONCE(is_special_task_state(state_value));\
current->task_state_change = _THIS_IP_; \
current->state = (state_value); \
} while (0)
+
#define set_current_state(state_value) \
do { \
+ WARN_ON_ONCE(is_special_task_state(state_value));\
current->task_state_change = _THIS_IP_; \
smp_store_mb(current->state, (state_value)); \
} while (0)
+#define set_special_state(state_value) \
+ do { \
+ unsigned long flags; /* may shadow */ \
+ WARN_ON_ONCE(!is_special_task_state(state_value)); \
+ raw_spin_lock_irqsave(¤t->pi_lock, flags); \
+ current->task_state_change = _THIS_IP_; \
+ current->state = (state_value); \
+ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \
+ } while (0)
#else
/*
* set_current_state() includes a barrier so that the write of current->state
*
* The above is typically ordered against the wakeup, which does:
*
- * need_sleep = false;
- * wake_up_state(p, TASK_UNINTERRUPTIBLE);
+ * need_sleep = false;
+ * wake_up_state(p, TASK_UNINTERRUPTIBLE);
*
* Where wake_up_state() (and all other wakeup primitives) imply enough
* barriers to order the store of the variable against wakeup.
* once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
* TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING).
*
- * This is obviously fine, since they both store the exact same value.
+ * However, with slightly different timing the wakeup TASK_RUNNING store can
+ * also collide with the TASK_UNINTERRUPTIBLE store. Loosing that store is not
+ * a problem either because that will result in one extra go around the loop
+ * and our @cond test will save the day.
*
* Also see the comments of try_to_wake_up().
*/
-#define __set_current_state(state_value) do { current->state = (state_value); } while (0)
-#define set_current_state(state_value) smp_store_mb(current->state, (state_value))
+#define __set_current_state(state_value) \
+ current->state = (state_value)
+
+#define set_current_state(state_value) \
+ smp_store_mb(current->state, (state_value))
+
+/*
+ * set_special_state() should be used for those states when the blocking task
+ * can not use the regular condition based wait-loop. In that case we must
+ * serialize against wakeups such that any possible in-flight TASK_RUNNING stores
+ * will not collide with our state change.
+ */
+#define set_special_state(state_value) \
+ do { \
+ unsigned long flags; /* may shadow */ \
+ raw_spin_lock_irqsave(¤t->pi_lock, flags); \
+ current->state = (state_value); \
+ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \
+ } while (0)
+
#endif
/* Task command name length: */
u32 inv_weight;
};
+/**
+ * struct util_est - Estimation utilization of FAIR tasks
+ * @enqueued: instantaneous estimated utilization of a task/cpu
+ * @ewma: the Exponential Weighted Moving Average (EWMA)
+ * utilization of a task
+ *
+ * Support data structure to track an Exponential Weighted Moving Average
+ * (EWMA) of a FAIR task's utilization. New samples are added to the moving
+ * average each time a task completes an activation. Sample's weight is chosen
+ * so that the EWMA will be relatively insensitive to transient changes to the
+ * task's workload.
+ *
+ * The enqueued attribute has a slightly different meaning for tasks and cpus:
+ * - task: the task's util_avg at last task dequeue time
+ * - cfs_rq: the sum of util_est.enqueued for each RUNNABLE task on that CPU
+ * Thus, the util_est.enqueued of a task represents the contribution on the
+ * estimated utilization of the CPU where that task is currently enqueued.
+ *
+ * Only for tasks we track a moving average of the past instantaneous
+ * estimated utilization. This allows to absorb sporadic drops in utilization
+ * of an otherwise almost periodic task.
+ */
+struct util_est {
+ unsigned int enqueued;
+ unsigned int ewma;
+#define UTIL_EST_WEIGHT_SHIFT 2
+};
+
/*
* The load_avg/util_avg accumulates an infinite geometric series
* (see __update_load_avg() in kernel/sched/fair.c).
u32 period_contrib;
unsigned long load_avg;
unsigned long util_avg;
+ struct util_est util_est;
};
-#define NOT_ONTIME 1
-#define ONTIME_MIGRATING 2
-#define ONTIME 4
-
-#define ontime_of(p) (&p->se.ontime)
-
struct ontime_avg {
u64 ontime_migration_time;
u64 load_sum;
struct ontime_entity {
struct ontime_avg avg;
- int flags;
+ int migrating;
int cpu;
};
#endif
#ifdef CONFIG_SMP
+#ifdef CONFIG_SCHED_USE_FLUID_RT
+ int sync_flag;
+#endif
/*
* Per entity load average tracking.
*
int victim_flag;
#endif
+#ifdef CONFIG_SCHED_EMS
+ struct task_band *band;
+ struct list_head band_members;
+#endif
+
#ifdef CONFIG_CGROUP_SCHED
struct task_group *sched_task_group;
#endif
unsigned sched_contributes_to_load:1;
unsigned sched_migrated:1;
unsigned sched_remote_wakeup:1;
+#ifdef CONFIG_PSI
+ unsigned sched_psi_wake_requeue:1;
+#endif
+
/* Force alignment to the next boundary: */
unsigned :0;
u64 stimescaled;
#endif
u64 gtime;
+#ifdef CONFIG_CPU_FREQ_TIMES
+ u64 *time_in_state;
+ unsigned int max_state;
+#endif
struct prev_cputime prev_cputime;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
struct vtime vtime;
siginfo_t *last_siginfo;
struct task_io_accounting ioac;
+#ifdef CONFIG_PSI
+ /* Pressure stall state */
+ unsigned int psi_flags;
+#endif
#ifdef CONFIG_TASK_XACCT
/* Accumulated RSS usage: */
u64 acct_rss_mem1;
#define PF_KTHREAD 0x00200000 /* I am a kernel thread */
#define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */
#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */
+#define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */
#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */
#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */
#define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */
#define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */
#define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */
-
+#define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */
+#define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/
+#define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */
+#define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */
+#define PFA_LMK_WAITING 7 /* Lowmemorykiller is waiting */
#define TASK_PFA_TEST(name, func) \
static inline bool task_##func(struct task_struct *p) \
TASK_PFA_SET(SPREAD_SLAB, spread_slab)
TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
+TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable)
+TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable)
+TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable)
+
+TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
+TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable)
+
+TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable)
+TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable)
+TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable)
+
+TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)
+TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable)
+
+TASK_PFA_TEST(LMK_WAITING, lmk_waiting)
+TASK_PFA_SET(LMK_WAITING, lmk_waiting)
+
static inline void
current_restore_flags(unsigned long orig_flags, unsigned long flags)
{