diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/capability.c | 111 | ||||
| -rw-r--r-- | kernel/cpuset.c | 20 | ||||
| -rw-r--r-- | kernel/futex.c | 93 | ||||
| -rw-r--r-- | kernel/kgdb.c | 19 | ||||
| -rw-r--r-- | kernel/kprobes.c | 15 | ||||
| -rw-r--r-- | kernel/rcupreempt.c | 2 | ||||
| -rw-r--r-- | kernel/relay.c | 2 | ||||
| -rw-r--r-- | kernel/sched.c | 517 | ||||
| -rw-r--r-- | kernel/sched_clock.c | 18 | ||||
| -rw-r--r-- | kernel/sched_debug.c | 5 | ||||
| -rw-r--r-- | kernel/sched_fair.c | 254 | ||||
| -rw-r--r-- | kernel/sched_rt.c | 70 | ||||
| -rw-r--r-- | kernel/sched_stats.h | 7 | ||||
| -rw-r--r-- | kernel/signal.c | 50 | ||||
| -rw-r--r-- | kernel/softlockup.c | 15 |
15 files changed, 475 insertions, 723 deletions
diff --git a/kernel/capability.c b/kernel/capability.c index 39e8193b41ea..cfbe44299488 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -53,6 +53,69 @@ static void warn_legacy_capability_use(void) } /* + * Version 2 capabilities worked fine, but the linux/capability.h file + * that accompanied their introduction encouraged their use without + * the necessary user-space source code changes. As such, we have + * created a version 3 with equivalent functionality to version 2, but + * with a header change to protect legacy source code from using + * version 2 when it wanted to use version 1. If your system has code + * that trips the following warning, it is using version 2 specific + * capabilities and may be doing so insecurely. + * + * The remedy is to either upgrade your version of libcap (to 2.10+, + * if the application is linked against it), or recompile your + * application with modern kernel headers and this warning will go + * away. + */ + +static void warn_deprecated_v2(void) +{ + static int warned; + + if (!warned) { + char name[sizeof(current->comm)]; + + printk(KERN_INFO "warning: `%s' uses deprecated v2" + " capabilities in a way that may be insecure.\n", + get_task_comm(name, current)); + warned = 1; + } +} + +/* + * Version check. Return the number of u32s in each capability flag + * array, or a negative value on error. + */ +static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) +{ + __u32 version; + + if (get_user(version, &header->version)) + return -EFAULT; + + switch (version) { + case _LINUX_CAPABILITY_VERSION_1: + warn_legacy_capability_use(); + *tocopy = _LINUX_CAPABILITY_U32S_1; + break; + case _LINUX_CAPABILITY_VERSION_2: + warn_deprecated_v2(); + /* + * fall through - v3 is otherwise equivalent to v2. + */ + case _LINUX_CAPABILITY_VERSION_3: + *tocopy = _LINUX_CAPABILITY_U32S_3; + break; + default: + if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version)) + return -EFAULT; + return -EINVAL; + } + + return 0; +} + +/* * For sys_getproccap() and sys_setproccap(), any of the three * capability set pointers may be NULL -- indicating that that set is * uninteresting and/or not to be changed. @@ -71,27 +134,13 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr) { int ret = 0; pid_t pid; - __u32 version; struct task_struct *target; unsigned tocopy; kernel_cap_t pE, pI, pP; - if (get_user(version, &header->version)) - return -EFAULT; - - switch (version) { - case _LINUX_CAPABILITY_VERSION_1: - warn_legacy_capability_use(); - tocopy = _LINUX_CAPABILITY_U32S_1; - break; - case _LINUX_CAPABILITY_VERSION_2: - tocopy = _LINUX_CAPABILITY_U32S_2; - break; - default: - if (put_user(_LINUX_CAPABILITY_VERSION, &header->version)) - return -EFAULT; - return -EINVAL; - } + ret = cap_validate_magic(header, &tocopy); + if (ret != 0) + return ret; if (get_user(pid, &header->pid)) return -EFAULT; @@ -118,7 +167,7 @@ out: spin_unlock(&task_capability_lock); if (!ret) { - struct __user_cap_data_struct kdata[_LINUX_CAPABILITY_U32S]; + struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i; for (i = 0; i < tocopy; i++) { @@ -128,7 +177,7 @@ out: } /* - * Note, in the case, tocopy < _LINUX_CAPABILITY_U32S, + * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, * we silently drop the upper capabilities here. This * has the effect of making older libcap * implementations implicitly drop upper capability @@ -240,30 +289,16 @@ static inline int cap_set_all(kernel_cap_t *effective, */ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) { - struct __user_cap_data_struct kdata[_LINUX_CAPABILITY_U32S]; + struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i, tocopy; kernel_cap_t inheritable, permitted, effective; - __u32 version; struct task_struct *target; int ret; pid_t pid; - if (get_user(version, &header->version)) - return -EFAULT; - - switch (version) { - case _LINUX_CAPABILITY_VERSION_1: - warn_legacy_capability_use(); - tocopy = _LINUX_CAPABILITY_U32S_1; - break; - case _LINUX_CAPABILITY_VERSION_2: - tocopy = _LINUX_CAPABILITY_U32S_2; - break; - default: - if (put_user(_LINUX_CAPABILITY_VERSION, &header->version)) - return -EFAULT; - return -EINVAL; - } + ret = cap_validate_magic(header, &tocopy); + if (ret != 0) + return ret; if (get_user(pid, &header->pid)) return -EFAULT; @@ -281,7 +316,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) permitted.cap[i] = kdata[i].permitted; inheritable.cap[i] = kdata[i].inheritable; } - while (i < _LINUX_CAPABILITY_U32S) { + while (i < _KERNEL_CAPABILITY_U32S) { effective.cap[i] = 0; permitted.cap[i] = 0; inheritable.cap[i] = 0; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 86ea9e34e326..9fceb97e989c 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -797,8 +797,10 @@ static int update_cpumask(struct cpuset *cs, char *buf) retval = cpulist_parse(buf, trialcs.cpus_allowed); if (retval < 0) return retval; + + if (!cpus_subset(trialcs.cpus_allowed, cpu_online_map)) + return -EINVAL; } - cpus_and(trialcs.cpus_allowed, trialcs.cpus_allowed, cpu_online_map); retval = validate_change(cs, &trialcs); if (retval < 0) return retval; @@ -932,9 +934,11 @@ static int update_nodemask(struct cpuset *cs, char *buf) retval = nodelist_parse(buf, trialcs.mems_allowed); if (retval < 0) goto done; + + if (!nodes_subset(trialcs.mems_allowed, + node_states[N_HIGH_MEMORY])) + return -EINVAL; } - nodes_and(trialcs.mems_allowed, trialcs.mems_allowed, - node_states[N_HIGH_MEMORY]); oldmem = cs->mems_allowed; if (nodes_equal(oldmem, trialcs.mems_allowed)) { retval = 0; /* Too easy - nothing to do */ @@ -1033,8 +1037,8 @@ int current_cpuset_is_being_rebound(void) static int update_relax_domain_level(struct cpuset *cs, s64 val) { - if ((int)val < 0) - val = -1; + if (val < -1 || val >= SD_LV_MAX) + return -EINVAL; if (val != cs->relax_domain_level) { cs->relax_domain_level = val; @@ -1886,6 +1890,12 @@ static void common_cpu_mem_hotplug_unplug(void) top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; scan_for_empty_cpusets(&top_cpuset); + /* + * Scheduler destroys domains on hotplug events. + * Rebuild them based on the current settings. + */ + rebuild_sched_domains(); + cgroup_unlock(); } diff --git a/kernel/futex.c b/kernel/futex.c index 449def8074fe..7d1136e97c14 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1096,21 +1096,64 @@ static void unqueue_me_pi(struct futex_q *q) * private futexes. */ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - struct task_struct *newowner) + struct task_struct *newowner, + struct rw_semaphore *fshared) { u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; struct futex_pi_state *pi_state = q->pi_state; + struct task_struct *oldowner = pi_state->owner; u32 uval, curval, newval; - int ret; + int ret, attempt = 0; /* Owner died? */ + if (!pi_state->owner) + newtid |= FUTEX_OWNER_DIED; + + /* + * We are here either because we stole the rtmutex from the + * pending owner or we are the pending owner which failed to + * get the rtmutex. We have to replace the pending owner TID + * in the user space variable. This must be atomic as we have + * to preserve the owner died bit here. + * + * Note: We write the user space value _before_ changing the + * pi_state because we can fault here. Imagine swapped out + * pages or a fork, which was running right before we acquired + * mmap_sem, that marked all the anonymous memory readonly for + * cow. + * + * Modifying pi_state _before_ the user space value would + * leave the pi_state in an inconsistent state when we fault + * here, because we need to drop the hash bucket lock to + * handle the fault. This might be observed in the PID check + * in lookup_pi_state. + */ +retry: + if (get_futex_value_locked(&uval, uaddr)) + goto handle_fault; + + while (1) { + newval = (uval & FUTEX_OWNER_DIED) | newtid; + + curval = cmpxchg_futex_value_locked(uaddr, uval, newval); + + if (curval == -EFAULT) + goto handle_fault; + if (curval == uval) + break; + uval = curval; + } + + /* + * We fixed up user space. Now we need to fix the pi_state + * itself. + */ if (pi_state->owner != NULL) { spin_lock_irq(&pi_state->owner->pi_lock); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); spin_unlock_irq(&pi_state->owner->pi_lock); - } else - newtid |= FUTEX_OWNER_DIED; + } pi_state->owner = newowner; @@ -1118,26 +1161,35 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &newowner->pi_state_list); spin_unlock_irq(&newowner->pi_lock); + return 0; /* - * We own it, so we have to replace the pending owner - * TID. This must be atomic as we have preserve the - * owner died bit here. + * To handle the page fault we need to drop the hash bucket + * lock here. That gives the other task (either the pending + * owner itself or the task which stole the rtmutex) the + * chance to try the fixup of the pi_state. So once we are + * back from handling the fault we need to check the pi_state + * after reacquiring the hash bucket lock and before trying to + * do another fixup. When the fixup has been done already we + * simply return. */ - ret = get_futex_value_locked(&uval, uaddr); +handle_fault: + spin_unlock(q->lock_ptr); - while (!ret) { - newval = (uval & FUTEX_OWNER_DIED) | newtid; + ret = futex_handle_fault((unsigned long)uaddr, fshared, attempt++); - curval = cmpxchg_futex_value_locked(uaddr, uval, newval); + spin_lock(q->lock_ptr); - if (curval == -EFAULT) - ret = -EFAULT; - if (curval == uval) - break; - uval = curval; - } - return ret; + /* + * Check if someone else fixed it for us: + */ + if (pi_state->owner != oldowner) + return 0; + + if (ret) + return ret; + + goto retry; } /* @@ -1507,7 +1559,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, * that case: */ if (q.pi_state->owner != curr) - ret = fixup_pi_state_owner(uaddr, &q, curr); + ret = fixup_pi_state_owner(uaddr, &q, curr, fshared); } else { /* * Catch the rare case, where the lock was released @@ -1539,7 +1591,8 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, int res; owner = rt_mutex_owner(&q.pi_state->pi_mutex); - res = fixup_pi_state_owner(uaddr, &q, owner); + res = fixup_pi_state_owner(uaddr, &q, owner, + fshared); /* propagate -EFAULT, if the fixup failed */ if (res) diff --git a/kernel/kgdb.c b/kernel/kgdb.c index 14787de568b3..3ec23c3ec97f 100644 --- a/kernel/kgdb.c +++ b/kernel/kgdb.c @@ -52,6 +52,7 @@ #include <asm/byteorder.h> #include <asm/atomic.h> #include <asm/system.h> +#include <asm/unaligned.h> static int kgdb_break_asap; @@ -227,8 +228,6 @@ void __weak kgdb_disable_hw_debug(struct pt_regs *regs) * GDB remote protocol parser: */ -static const char hexchars[] = "0123456789abcdef"; - static int hex(char ch) { if ((ch >= 'a') && (ch <= 'f')) @@ -316,8 +315,8 @@ static void put_packet(char *buffer) } kgdb_io_ops->write_char('#'); - kgdb_io_ops->write_char(hexchars[checksum >> 4]); - kgdb_io_ops->write_char(hexchars[checksum & 0xf]); + kgdb_io_ops->write_char(hex_asc_hi(checksum)); + kgdb_io_ops->write_char(hex_asc_lo(checksum)); if (kgdb_io_ops->flush) kgdb_io_ops->flush(); @@ -478,8 +477,8 @@ static void error_packet(char *pkt, int error) { error = -error; pkt[0] = 'E'; - pkt[1] = hexchars[(error / 10)]; - pkt[2] = hexchars[(error % 10)]; + pkt[1] = hex_asc[(error / 10)]; + pkt[2] = hex_asc[(error % 10)]; pkt[3] = '\0'; } @@ -510,10 +509,7 @@ static void int_to_threadref(unsigned char *id, int value) scan = (unsigned char *)id; while (i--) *scan++ = 0; - *scan++ = (value >> 24) & 0xff; - *scan++ = (value >> 16) & 0xff; - *scan++ = (value >> 8) & 0xff; - *scan++ = (value & 0xff); + put_unaligned_be32(value, scan); } static struct task_struct *getthread(struct pt_regs *regs, int tid) @@ -1503,7 +1499,8 @@ int kgdb_nmicallback(int cpu, void *regs) return 1; } -void kgdb_console_write(struct console *co, const char *s, unsigned count) +static void kgdb_console_write(struct console *co, const char *s, + unsigned count) { unsigned long flags; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 1e0250cb9486..d4998f81e229 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -699,8 +699,9 @@ static int __register_kprobes(struct kprobe **kps, int num, return -EINVAL; for (i = 0; i < num; i++) { ret = __register_kprobe(kps[i], called_from); - if (ret < 0 && i > 0) { - unregister_kprobes(kps, i); + if (ret < 0) { + if (i > 0) + unregister_kprobes(kps, i); break; } } @@ -776,8 +777,9 @@ static int __register_jprobes(struct jprobe **jps, int num, jp->kp.break_handler = longjmp_break_handler; ret = __register_kprobe(&jp->kp, called_from); } - if (ret < 0 && i > 0) { - unregister_jprobes(jps, i); + if (ret < 0) { + if (i > 0) + unregister_jprobes(jps, i); break; } } @@ -920,8 +922,9 @@ static int __register_kretprobes(struct kretprobe **rps, int num, return -EINVAL; for (i = 0; i < num; i++) { ret = __register_kretprobe(rps[i], called_from); - if (ret < 0 && i > 0) { - unregister_kretprobes(rps, i); + if (ret < 0) { + if (i > 0) + unregister_kretprobes(rps, i); break; } } diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c index e1cdf196a515..5e02b7740702 100644 --- a/kernel/rcupreempt.c +++ b/kernel/rcupreempt.c @@ -217,8 +217,6 @@ long rcu_batches_completed(void) } EXPORT_SYMBOL_GPL(rcu_batches_completed); -EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); - void __rcu_read_lock(void) { int idx; diff --git a/kernel/relay.c b/kernel/relay.c index bc24dcdc570f..7de644cdec43 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -1191,7 +1191,7 @@ static ssize_t relay_file_splice_read(struct file *in, ret = 0; spliced = 0; - while (len) { + while (len && !spliced) { ret = subbuf_splice_actor(in, ppos, pipe, len, flags, &nonpad_ret); if (ret < 0) break; diff --git a/kernel/sched.c b/kernel/sched.c index a964ed945094..0cdb50260dbf 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -136,7 +136,7 @@ static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val) static inline int rt_policy(int policy) { - if (unlikely(policy == SCHED_FIFO) || unlikely(policy == SCHED_RR)) + if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR)) return 1; return 0; } @@ -312,12 +312,15 @@ static DEFINE_SPINLOCK(task_group_lock); #endif /* - * A weight of 0, 1 or ULONG_MAX can cause arithmetics problems. + * A weight of 0 or 1 can cause arithmetics problems. + * A weight of a cfs_rq is the sum of weights of which entities + * are queued on this cfs_rq, so a weight of a entity should not be + * too large, so as the shares value of a task group. * (The default weight is 1024 - so there's no practical * limitation from this.) */ #define MIN_SHARES 2 -#define MAX_SHARES (ULONG_MAX - 1) +#define MAX_SHARES (1UL << 18) static int init_task_group_load = INIT_TASK_GROUP_LOAD; #endif @@ -398,43 +401,6 @@ struct cfs_rq { */ struct list_head leaf_cfs_rq_list; struct task_group *tg; /* group that "owns" this runqueue */ - -#ifdef CONFIG_SMP - unsigned long task_weight; - unsigned long shares; - /* - * We need space to build a sched_domain wide view of the full task - * group tree, in order to avoid depending on dynamic memory allocation - * during the load balancing we place this in the per cpu task group - * hierarchy. This limits the load balancing to one instance per cpu, - * but more should not be needed anyway. - */ - struct aggregate_struct { - /* - * load = weight(cpus) * f(tg) - * - * Where f(tg) is the recursive weight fraction assigned to - * this group. - */ - unsigned long load; - - /* - * part of the group weight distributed to this span. - */ - unsigned long shares; - - /* - * The sum of all runqueue weights within this span. - */ - unsigned long rq_weight; - - /* - * Weight contributed by tasks; this is the part we can - * influence by moving tasks around. - */ - unsigned long task_weight; - } aggregate; -#endif #endif }; @@ -1161,6 +1127,7 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer) return HRTIMER_NORESTART; } +#ifdef CONFIG_SMP static void hotplug_hrtick_disable(int cpu) { struct rq *rq = cpu_rq(cpu); @@ -1216,6 +1183,7 @@ static void init_hrtick(void) { hotcpu_notifier(hotplug_hrtick, 0); } +#endif /* CONFIG_SMP */ static void init_rq_hrtick(struct rq *rq) { @@ -1368,17 +1336,19 @@ static void __resched_task(struct task_struct *p, int tif_bit) */ #define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y)) -/* - * delta *= weight / lw - */ static unsigned long calc_delta_mine(unsigned long delta_exec, unsigned long weight, struct load_weight *lw) { u64 tmp; - if (!lw->inv_weight) - lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)/(lw->weight+1); + if (!lw->inv_weight) { + if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST)) + lw->inv_weight = 1; + else + lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2) + / (lw->weight+1); + } tmp = (u64)delta_exec * weight; /* @@ -1393,6 +1363,12 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight, return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX); } +static inline unsigned long +calc_delta_fair(unsigned long delta_exec, struct load_weight *lw) +{ + return calc_delta_mine(delta_exec, NICE_0_LOAD, lw); +} + static inline void update_load_add(struct load_weight *lw, unsigned long inc) { lw->weight += inc; @@ -1505,326 +1481,6 @@ static unsigned long source_load(int cpu, int type); static unsigned long target_load(int cpu, int type); static unsigned long cpu_avg_load_per_task(int cpu); static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); - -#ifdef CONFIG_FAIR_GROUP_SCHED - -/* - * Group load balancing. - * - * We calculate a few balance domain wide aggregate numbers; load and weight. - * Given the pictures below, and assuming each item has equal weight: - * - * root 1 - thread - * / | \ A - group - * A 1 B - * /|\ / \ - * C 2 D 3 4 - * | | - * 5 6 - * - * load: - * A and B get 1/3-rd of the total load. C and D get 1/3-rd of A's 1/3-rd, - * which equals 1/9-th of the total load. - * - * shares: - * The weight of this group on the selected cpus. - * - * rq_weight: - * Direct sum of all the cpu's their rq weight, e.g. A would get 3 while - * B would get 2. - * - * task_weight: - * Part of the rq_weight contributed by tasks; all groups except B would - * get 1, B gets 2. - */ - -static inline struct aggregate_struct * -aggregate(struct task_group *tg, struct sched_domain *sd) -{ - return &tg->cfs_rq[sd->first_cpu]->aggregate; -} - -typedef void (*aggregate_func)(struct task_group *, struct sched_domain *); - -/* - * Iterate the full tree, calling @down when first entering a node and @up when - * leaving it for the final time. - */ -static -void aggregate_walk_tree(aggregate_func down, aggregate_func up, - struct sched_domain *sd) -{ - struct task_group *parent, *child; - - rcu_read_lock(); - parent = &root_task_group; -down: - (*down)(parent, sd); - list_for_each_entry_rcu(child, &parent->children, siblings) { - parent = child; - goto down; - -up: - continue; - } - (*up)(parent, sd); - - child = parent; - parent = parent->parent; - if (parent) - goto up; - rcu_read_unlock(); -} - -/* - * Calculate the aggregate runqueue weight. - */ -static -void aggregate_group_weight(struct task_group *tg, struct sched_domain *sd) -{ - unsigned long rq_weight = 0; - unsigned long task_weight = 0; - int i; - - for_each_cpu_mask(i, sd->span) { - rq_weight += tg->cfs_rq[i]->load.weight; - task_weight += tg->cfs_rq[i]->task_weight; - } - - aggregate(tg, sd)->rq_weight = rq_weight; - aggregate(tg, sd)->task_weight = task_weight; -} - -/* - * Compute the weight of this group on the given cpus. - */ -static -void aggregate_group_shares(struct task_group *tg, struct sched_domain *sd) -{ - unsigned long shares = 0; - int i; - - for_each_cpu_mask(i, sd->span) - shares += tg->cfs_rq[i]->shares; - - if ((!shares && aggregate(tg, sd)->rq_weight) || shares > tg->shares) - shares = tg->shares; - - aggregate(tg, sd)->shares = shares; -} - -/* - * Compute the load fraction assigned to this group, relies on the aggregate - * weight and this group's parent's load, i.e. top-down. - */ -static -void aggregate_group_load(struct task_group *tg, struct sched_domain *sd) -{ - unsigned long load; - - if (!tg->parent) { - int i; - - load = 0; - for_each_cpu_mask(i, sd->span) - load += cpu_rq(i)->load.weight; - - } else { - load = aggregate(tg->parent, sd)->load; - - /* - * shares is our weight in the parent's rq so - * shares/parent->rq_weight gives our fraction of the load - */ - load *= aggregate(tg, sd)->shares; - load /= aggregate(tg->parent, sd)->rq_weight + 1; - } - - aggregate(tg, sd)->load = load; -} - -static void __set_se_shares(struct sched_entity *se, unsigned long shares); - -/* - * Calculate and set the cpu's group shares. - */ -static void -__update_group_shares_cpu(struct task_group *tg, struct sched_domain *sd, - int tcpu) -{ - int boost = 0; - unsigned long shares; - unsigned long rq_weight; - - if (!tg->se[tcpu]) - return; - - rq_weight = tg->cfs_rq[tcpu]->load.weight; - - /* - * If there are currently no tasks on the cpu pretend there is one of - * average load so that when a new task gets to run here it will not - * get delayed by group starvation. - */ - if (!rq_weight) { - boost = 1; - rq_weight = NICE_0_LOAD; - } - - /* - * \Sum shares * rq_weight - * shares = ----------------------- - * \Sum rq_weight - * - */ - shares = aggregate(tg, sd)->shares * rq_weight; - shares /= aggregate(tg, sd)->rq_weight + 1; - - /* - * record the actual number of shares, not the boosted amount. - */ - tg->cfs_rq[tcpu]->shares = boost ? 0 : shares; - - if (shares < MIN_SHARES) - shares = MIN_SHARES; - else if (shares > MAX_SHARES) - shares = MAX_SHARES; - - __set_se_shares(tg->se[tcpu], shares); -} - -/* - * Re-adjust the weights on the cpu the task came from and on the cpu the - * task went to. - */ -static void -__move_group_shares(struct task_group *tg, struct sched_domain *sd, - int scpu, int dcpu) -{ - unsigned long shares; - - shares = tg->cfs_rq[scpu]->shares + tg->cfs_rq[dcpu]->shares; - - __update_group_shares_cpu(tg, sd, scpu); - __update_group_shares_cpu(tg, sd, dcpu); - - /* - * ensure we never loose shares due to rounding errors in the - * above redistribution. - */ - shares -= tg->cfs_rq[scpu]->shares + tg->cfs_rq[dcpu]->shares; - if (shares) - tg->cfs_rq[dcpu]->shares += shares; -} - -/* - * Because changing a group's shares changes the weight of the super-group - * we need to walk up the tree and change all shares until we hit the root. - */ -static void -move_group_shares(struct task_group *tg, struct sched_domain *sd, - int scpu, int dcpu) -{ - while (tg) { - __move_group_shares(tg, sd, scpu, dcpu); - tg = tg->parent; - } -} - -static -void aggregate_group_set_shares(struct task_group *tg, struct sched_domain *sd) -{ - unsigned long shares = aggregate(tg, sd)->shares; - int i; - - for_each_cpu_mask(i, sd->span) { - struct rq *rq = cpu_rq(i); - unsigned long flags; - - spin_lock_irqsave(&rq->lock, flags); - __update_group_shares_cpu(tg, sd, i); - spin_unlock_irqrestore(&rq->lock, flags); - } - - aggregate_group_shares(tg, sd); - - /* - * ensure we never loose shares due to rounding errors in the - * above redistribution. - */ - shares -= aggregate(tg, sd)->shares; - if (shares) { - tg->cfs_rq[sd->first_cpu]->shares += shares; - aggregate(tg, sd)->shares += shares; - } -} - -/* - * Calculate the accumulative weight and recursive load of each task group - * while walking down the tree. - */ -static -void aggregate_get_down(struct task_group *tg, struct sched_domain *sd) -{ - aggregate_group_weight(tg, sd); - aggregate_group_shares(tg, sd); - aggregate_group_load(tg, sd); -} - -/* - * Rebalance the cpu shares while walking back up the tree. - */ -static -void aggregate_get_up(struct task_group *tg, struct sched_domain *sd) -{ - aggregate_group_set_shares(tg, sd); -} - -static DEFINE_PER_CPU(spinlock_t, aggregate_lock); - -static void __init init_aggregate(void) -{ - int i; - - for_each_possible_cpu(i) - spin_lock_init(&per_cpu(aggregate_lock, i)); -} - -static int get_aggregate(struct sched_domain *sd) -{ - if (!spin_trylock(&per_cpu(aggregate_lock, sd->first_cpu))) - return 0; - - aggregate_walk_tree(aggregate_get_down, aggregate_get_up, sd); - return 1; -} - -static void put_aggregate(struct sched_domain *sd) -{ - spin_unlock(&per_cpu(aggregate_lock, sd->first_cpu)); -} - -static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) -{ - cfs_rq->shares = shares; -} - -#else - -static inline void init_aggregate(void) -{ -} - -static inline int get_aggregate(struct sched_domain *sd) -{ - return 0; -} - -static inline void put_aggregate(struct sched_domain *sd) -{ -} -#endif - #else /* CONFIG_SMP */ #ifdef CONFIG_FAIR_GROUP_SCHED @@ -1845,14 +1501,26 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) #define sched_class_highest (&rt_sched_class) -static void inc_nr_running(struct rq *rq) +static inline void inc_load(struct rq *rq, const struct task_struct *p) +{ + update_load_add(&rq->load, p->se.load.weight); +} + +static inline void dec_load(struct rq *rq, const struct task_struct *p) +{ + update_load_sub(&rq->load, p->se.load.weight); +} + +static void inc_nr_running(struct task_struct *p, struct rq *rq) { rq->nr_running++; + inc_load(rq, p); } -static void dec_nr_running(struct rq *rq) +static void dec_nr_running(struct task_struct *p, struct rq *rq) { rq->nr_running--; + dec_load(rq, p); } static void set_load_weight(struct task_struct *p) @@ -1944,7 +1612,7 @@ static void activate_task(struct rq *rq, struct task_struct *p, int wakeup) rq->nr_uninterruptible--; enqueue_task(rq, p, wakeup); - inc_nr_running(rq); + inc_nr_running(p, rq); } /* @@ -1956,7 +1624,7 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep) rq->nr_uninterruptible++; dequeue_task(rq, p, sleep); - dec_nr_running(rq); + dec_nr_running(p, rq); } /** @@ -2609,7 +2277,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) * management (if any): */ p->sched_class->task_new(rq, p); - inc_nr_running(rq); + inc_nr_running(p, rq); } check_preempt_curr(rq, p); #ifdef CONFIG_SMP @@ -3600,12 +3268,9 @@ static int load_balance(int this_cpu, struct rq *this_rq, unsigned long imbalance; struct rq *busiest; unsigned long flags; - int unlock_aggregate; cpus_setall(*cpus); - unlock_aggregate = get_aggregate(sd); - /* * When power savings policy is enabled for the parent domain, idle * sibling can pick up load irrespective of busy siblings. In this case, @@ -3721,9 +3386,8 @@ redo: if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER && !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - ld_moved = -1; - - goto out; + return -1; + return ld_moved; out_balanced: schedstat_inc(sd, lb_balanced[idle]); @@ -3738,13 +3402,8 @@ out_one_pinned: if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - ld_moved = -1; - else - ld_moved = 0; -out: - if (unlock_aggregate) - put_aggregate(sd); - return ld_moved; + return -1; + return 0; } /* @@ -4430,7 +4089,7 @@ static inline void schedule_debug(struct task_struct *prev) * schedule() atomically, we ignore that path for now. * Otherwise, whine if we are scheduling when we should not be. */ - if (unlikely(in_atomic_preempt_off()) && unlikely(!prev->exit_state)) + if (unlikely(in_atomic_preempt_off() && !prev->exit_state)) __schedule_bug(prev); profile_hit(SCHED_PROFILING, __builtin_return_address(0)); @@ -4510,12 +4169,10 @@ need_resched_nonpreemptible: clear_tsk_need_resched(prev); if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { - if (unlikely((prev->state & TASK_INTERRUPTIBLE) && - signal_pending(prev))) { + if (unlikely(signal_pending_state(prev->state, prev))) prev->state = TASK_RUNNING; - } else { + else deactivate_task(rq, prev, 1); - } switch_count = &prev->nvcsw; } @@ -4741,22 +4398,20 @@ do_wait_for_common(struct completion *x, long timeout, int state) signal_pending(current)) || (state == TASK_KILLABLE && fatal_signal_pending(current))) { - __remove_wait_queue(&x->wait, &wait); - return -ERESTARTSYS; + timeout = -ERESTARTSYS; + break; } __set_current_state(state); spin_unlock_irq(&x->wait.lock); timeout = schedule_timeout(timeout); spin_lock_irq(&x->wait.lock); - if (!timeout) { - __remove_wait_queue(&x->wait, &wait); - return timeout; - } - } while (!x->done); + } while (!x->done && timeout); __remove_wait_queue(&x->wait, &wait); + if (!x->done) + return timeout; } x->done--; - return timeout; + return timeout ?: 1; } static long __sched @@ -4931,8 +4586,10 @@ void set_user_nice(struct task_struct *p, long nice) goto out_unlock; } on_rq = p->se.on_rq; - if (on_rq) + if (on_rq) { dequeue_task(rq, p, 0); + dec_load(rq, p); + } p->static_prio = NICE_TO_PRIO(nice); set_load_weight(p); @@ -4942,6 +4599,7 @@ void set_user_nice(struct task_struct *p, long nice) if (on_rq) { enqueue_task(rq, p, 0); + inc_load(rq, p); /* * If the task increased its priority or is running and * lowered its priority, then reschedule its CPU: @@ -7214,7 +6872,12 @@ static int default_relax_domain_level = -1; static int __init setup_relax_domain_level(char *str) { - default_relax_domain_level = simple_strtoul(str, NULL, 0); + unsigned long val; + + val = simple_strtoul(str, NULL, 0); + if (val < SD_LV_MAX) + default_relax_domain_level = val; + return 1; } __setup("relax_domain_level=", setup_relax_domain_level); @@ -7311,7 +6974,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map, SD_INIT(sd, ALLNODES); set_domain_attribute(sd, attr); sd->span = *cpu_map; - sd->first_cpu = first_cpu(sd->span); cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask); p = sd; sd_allnodes = 1; @@ -7322,7 +6984,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map, SD_INIT(sd, NODE); set_domain_attribute(sd, attr); sched_domain_node_span(cpu_to_node(i), &sd->span); - sd->first_cpu = first_cpu(sd->span); sd->parent = p; if (p) p->child = sd; @@ -7334,7 +6995,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map, SD_INIT(sd, CPU); set_domain_attribute(sd, attr); sd->span = *nodemask; - sd->first_cpu = first_cpu(sd->span); sd->parent = p; if (p) p->child = sd; @@ -7346,7 +7006,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map, SD_INIT(sd, MC); set_domain_attribute(sd, attr); sd->span = cpu_coregroup_map(i); - sd->first_cpu = first_cpu(sd->span); cpus_and(sd->span, sd->span, *cpu_map); sd->parent = p; p->child = sd; @@ -7359,7 +7018,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map, SD_INIT(sd, SIBLING); set_domain_attribute(sd, attr); sd->span = per_cpu(cpu_sibling_map, i); - sd->first_cpu = first_cpu(sd->span); cpus_and(sd->span, sd->span, *cpu_map); sd->parent = p; p->child = sd; @@ -7563,8 +7221,8 @@ static int build_sched_domains(const cpumask_t *cpu_map) static cpumask_t *doms_cur; /* current sched domains */ static int ndoms_cur; /* number of sched domains in 'doms_cur' */ -static struct sched_domain_attr *dattr_cur; /* attribues of custom domains - in 'doms_cur' */ +static struct sched_domain_attr *dattr_cur; + /* attribues of custom domains in 'doms_cur' */ /* * Special case: If a kmalloc of a doms_cur partition (array of @@ -7578,6 +7236,18 @@ void __attribute__((weak)) arch_update_cpu_topology(void) } /* + * Free current domain masks. + * Called after all cpus are attached to NULL domain. + */ +static void free_sched_domains(void) +{ + ndoms_cur = 0; + if (doms_cur != &fallback_doms) + kfree(doms_cur); + doms_cur = &fallback_doms; +} + +/* * Set up scheduler domains and groups. Callers must hold the hotplug lock. * For now this just excludes isolated cpus, but could be used to * exclude other special cases in the future. @@ -7724,6 +7394,7 @@ int arch_reinit_sched_domains(void) get_online_cpus(); mutex_lock(&sched_domains_mutex); detach_destroy_domains(&cpu_online_map); + free_sched_domains(); err = arch_init_sched_domains(&cpu_online_map); mutex_unlock(&sched_domains_mutex); put_online_cpus(); @@ -7809,6 +7480,7 @@ static int update_sched_domains(struct notifier_block *nfb, case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: detach_destroy_domains(&cpu_online_map); + free_sched_domains(); return NOTIFY_OK; case CPU_UP_CANCELED: @@ -7827,8 +7499,16 @@ static int update_sched_domains(struct notifier_block *nfb, return NOTIFY_DONE; } +#ifndef CONFIG_CPUSETS + /* + * Create default domain partitioning if cpusets are disabled. + * Otherwise we let cpusets rebuild the domains based on the + * current setup. + */ + /* The hotplug lock is already held by cpu_up/cpu_down */ arch_init_sched_domains(&cpu_online_map); +#endif return NOTIFY_OK; } @@ -7968,7 +7648,6 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, else rt_se->rt_rq = parent->my_q; - rt_se->rt_rq = &rq->rt; rt_se->my_q = rt_rq; rt_se->parent = parent; INIT_LIST_HEAD(&rt_se->run_list); @@ -8029,7 +7708,6 @@ void __init sched_init(void) } #ifdef CONFIG_SMP - init_aggregate(); init_defrootdomain(); #endif @@ -8594,11 +8272,14 @@ void sched_move_task(struct task_struct *tsk) #endif #ifdef CONFIG_FAIR_GROUP_SCHED -static void __set_se_shares(struct sched_entity *se, unsigned long shares) +static void set_se_shares(struct sched_entity *se, unsigned long shares) { struct cfs_rq *cfs_rq = se->cfs_rq; + struct rq *rq = cfs_rq->rq; int on_rq; + spin_lock_irq(&rq->lock); + on_rq = se->on_rq; if (on_rq) dequeue_entity(cfs_rq, se, 0); @@ -8608,17 +8289,8 @@ static void __set_se_shares(struct sched_entity *se, unsigned long shares) if (on_rq) enqueue_entity(cfs_rq, se, 0); -} - -static void set_se_shares(struct sched_entity *se, unsigned long shares) -{ - struct cfs_rq *cfs_rq = se->cfs_rq; - struct rq *rq = cfs_rq->rq; - unsigned long flags; - spin_lock_irqsave(&rq->lock, flags); - __set_se_shares(se, shares); - spin_unlock_irqrestore(&rq->lock, flags); + spin_unlock_irq(&rq->lock); } static DEFINE_MUTEX(shares_mutex); @@ -8657,13 +8329,8 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) * w/o tripping rebalance_share or load_balance_fair. */ tg->shares = shares; - for_each_possible_cpu(i) { - /* - * force a rebalance - */ - cfs_rq_set_shares(tg->cfs_rq[i], 0); + for_each_possible_cpu(i) set_se_shares(tg->se[i], shares); - } /* * Enable load balance activity on this group, by inserting it back on @@ -8702,7 +8369,7 @@ static unsigned long to_ratio(u64 period, u64 runtime) #ifdef CONFIG_CGROUP_SCHED static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) { - struct task_group *tgi, *parent = tg->parent; + struct task_group *tgi, *parent = tg ? tg->parent : NULL; unsigned long total = 0; if (!parent) { diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index 9c597e37f7de..ce05271219ab 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -59,22 +59,26 @@ static inline struct sched_clock_data *cpu_sdc(int cpu) return &per_cpu(sched_clock_data, cpu); } +static __read_mostly int sched_clock_running; + void sched_clock_init(void) { u64 ktime_now = ktime_to_ns(ktime_get()); - u64 now = 0; + unsigned long now_jiffies = jiffies; int cpu; for_each_possible_cpu(cpu) { struct sched_clock_data *scd = cpu_sdc(cpu); scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; - scd->prev_jiffies = jiffies; - scd->prev_raw = now; - scd->tick_raw = now; + scd->prev_jiffies = now_jiffies; + scd->prev_raw = 0; + scd->tick_raw = 0; scd->tick_gtod = ktime_now; scd->clock = ktime_now; } + + sched_clock_running = 1; } /* @@ -136,6 +140,9 @@ u64 sched_clock_cpu(int cpu) struct sched_clock_data *scd = cpu_sdc(cpu); u64 now, clock; + if (unlikely(!sched_clock_running)) + return 0ull; + WARN_ON_ONCE(!irqs_disabled()); now = sched_clock(); @@ -174,6 +181,9 @@ void sched_clock_tick(void) struct sched_clock_data *scd = this_scd(); u64 now, now_gtod; + if (unlikely(!sched_clock_running)) + return; + WARN_ON_ONCE(!irqs_disabled()); now = sched_clock(); diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 5f06118fbc31..8bb713040ac9 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -167,11 +167,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) #endif SEQ_printf(m, " .%-30s: %ld\n", "nr_spread_over", cfs_rq->nr_spread_over); -#ifdef CONFIG_FAIR_GROUP_SCHED -#ifdef CONFIG_SMP - SEQ_printf(m, " .%-30s: %lu\n", "shares", cfs_rq->shares); -#endif -#endif } static void print_cpu(struct seq_file *m, int cpu) diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index e24ecd39c4b8..08ae848b71d4 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -334,34 +334,6 @@ int sched_nr_latency_handler(struct ctl_table *table, int write, #endif /* - * delta *= w / rw - */ -static inline unsigned long -calc_delta_weight(unsigned long delta, struct sched_entity *se) -{ - for_each_sched_entity(se) { - delta = calc_delta_mine(delta, - se->load.weight, &cfs_rq_of(se)->load); - } - - return delta; -} - -/* - * delta *= rw / w - */ -static inline unsigned long -calc_delta_fair(unsigned long delta, struct sched_entity *se) -{ - for_each_sched_entity(se) { - delta = calc_delta_mine(delta, - cfs_rq_of(se)->load.weight, &se->load); - } - - return delta; -} - -/* * The idea is to set a period in which each task runs once. * * When there are too many tasks (sysctl_sched_nr_latency) we have to stretch @@ -390,54 +362,47 @@ static u64 __sched_period(unsigned long nr_running) */ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) { - return calc_delta_weight(__sched_period(cfs_rq->nr_running), se); + u64 slice = __sched_period(cfs_rq->nr_running); + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + + slice *= se->load.weight; + do_div(slice, cfs_rq->load.weight); + } + + + return slice; } /* * We calculate the vruntime slice of a to be inserted task * - * vs = s*rw/w = p + * vs = s/w = p/rw */ static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se) { unsigned long nr_running = cfs_rq->nr_running; + unsigned long weight; + u64 vslice; if (!se->on_rq) nr_running++; - return __sched_period(nr_running); -} - -/* - * The goal of calc_delta_asym() is to be asymmetrically around NICE_0_LOAD, in - * that it favours >=0 over <0. - * - * -20 | - * | - * 0 --------+------- - * .' - * 19 .' - * - */ -static unsigned long -calc_delta_asym(unsigned long delta, struct sched_entity *se) -{ - struct load_weight lw = { - .weight = NICE_0_LOAD, - .inv_weight = 1UL << (WMULT_SHIFT-NICE_0_SHIFT) - }; + vslice = __sched_period(nr_running); for_each_sched_entity(se) { - struct load_weight *se_lw = &se->load; + cfs_rq = cfs_rq_of(se); - if (se->load.weight < NICE_0_LOAD) - se_lw = &lw; + weight = cfs_rq->load.weight; + if (!se->on_rq) + weight += se->load.weight; - delta = calc_delta_mine(delta, - cfs_rq_of(se)->load.weight, se_lw); + vslice *= NICE_0_LOAD; + do_div(vslice, weight); } - return delta; + return vslice; } /* @@ -454,7 +419,11 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, curr->sum_exec_runtime += delta_exec; schedstat_add(cfs_rq, exec_clock, delta_exec); - delta_exec_weighted = calc_delta_fair(delta_exec, curr); + delta_exec_weighted = delta_exec; + if (unlikely(curr->load.weight != NICE_0_LOAD)) { + delta_exec_weighted = calc_delta_fair(delta_exec_weighted, + &curr->load); + } curr->vruntime += delta_exec_weighted; } @@ -541,27 +510,10 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) * Scheduling class queueing methods: */ -#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED -static void -add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight) -{ - cfs_rq->task_weight += weight; -} -#else -static inline void -add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight) -{ -} -#endif - static void account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_add(&cfs_rq->load, se->load.weight); - if (!parent_entity(se)) - inc_cpu_load(rq_of(cfs_rq), se->load.weight); - if (entity_is_task(se)) - add_cfs_task_weight(cfs_rq, se->load.weight); cfs_rq->nr_running++; se->on_rq = 1; list_add(&se->group_node, &cfs_rq->tasks); @@ -571,10 +523,6 @@ static void account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_sub(&cfs_rq->load, se->load.weight); - if (!parent_entity(se)) - dec_cpu_load(rq_of(cfs_rq), se->load.weight); - if (entity_is_task(se)) - add_cfs_task_weight(cfs_rq, -se->load.weight); cfs_rq->nr_running--; se->on_rq = 0; list_del_init(&se->group_node); @@ -661,17 +609,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) if (!initial) { /* sleeps upto a single latency don't count. */ - if (sched_feat(NEW_FAIR_SLEEPERS)) { - unsigned long thresh = sysctl_sched_latency; - - /* - * convert the sleeper threshold into virtual time - */ - if (sched_feat(NORMALIZED_SLEEPER)) - thresh = calc_delta_fair(thresh, se); - - vruntime -= thresh; - } + if (sched_feat(NEW_FAIR_SLEEPERS)) + vruntime -= sysctl_sched_latency; /* ensure we never gain time by being placed backwards. */ vruntime = max_vruntime(se->vruntime, vruntime); @@ -1057,16 +996,27 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq, struct task_struct *curr = this_rq->curr; unsigned long tl = this_load; unsigned long tl_per_task; + int balanced; - if (!(this_sd->flags & SD_WAKE_AFFINE)) + if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS)) return 0; /* + * If sync wakeup then subtract the (maximum possible) + * effect of the currently running task from the load + * of the current CPU: + */ + if (sync) + tl -= current->se.load.weight; + + balanced = 100*(tl + p->se.load.weight) <= imbalance*load; + + /* * If the currently running task will sleep within * a reasonable amount of time then attract this newly * woken task: */ - if (sync && curr->sched_class == &fair_sched_class) { + if (sync && balanced && curr->sched_class == &fair_sched_class) { if (curr->se.avg_overlap < sysctl_sched_migration_cost && p->se.avg_overlap < sysctl_sched_migration_cost) return 1; @@ -1075,16 +1025,8 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq, schedstat_inc(p, se.nr_wakeups_affine_attempts); tl_per_task = cpu_avg_load_per_task(this_cpu); - /* - * If sync wakeup then subtract the (maximum possible) - * effect of the currently running task from the load - * of the current CPU: - */ - if (sync) - tl -= current->se.load.weight; - if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) || - 100*(tl + p->se.load.weight) <= imbalance*load) { + balanced) { /* * This domain has SD_WAKE_AFFINE and * p is cache cold in this domain, and @@ -1169,10 +1111,11 @@ static unsigned long wakeup_gran(struct sched_entity *se) unsigned long gran = sysctl_sched_wakeup_granularity; /* - * More easily preempt - nice tasks, while not making it harder for - * + nice tasks. + * More easily preempt - nice tasks, while not making + * it harder for + nice tasks. */ - gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se); + if (unlikely(se->load.weight > NICE_0_LOAD)) + gran = calc_delta_fair(gran, &se->load); return gran; } @@ -1366,90 +1309,75 @@ static struct task_struct *load_balance_next_fair(void *arg) return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator); } -static unsigned long -__load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, struct sched_domain *sd, - enum cpu_idle_type idle, int *all_pinned, int *this_best_prio, - struct cfs_rq *cfs_rq) +#ifdef CONFIG_FAIR_GROUP_SCHED +static int cfs_rq_best_prio(struct cfs_rq *cfs_rq) { - struct rq_iterator cfs_rq_iterator; + struct sched_entity *curr; + struct task_struct *p; - cfs_rq_iterator.start = load_balance_start_fair; - cfs_rq_iterator.next = load_balance_next_fair; - cfs_rq_iterator.arg = cfs_rq; + if (!cfs_rq->nr_running || !first_fair(cfs_rq)) + return MAX_PRIO; + + curr = cfs_rq->curr; + if (!curr) + curr = __pick_next_entity(cfs_rq); + + p = task_of(curr); - return balance_tasks(this_rq, this_cpu, busiest, - max_load_move, sd, idle, all_pinned, - this_best_prio, &cfs_rq_iterator); + return p->prio; } +#endif -#ifdef CONFIG_FAIR_GROUP_SCHED static unsigned long load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_load_move, struct sched_domain *sd, enum cpu_idle_type idle, int *all_pinned, int *this_best_prio) { + struct cfs_rq *busy_cfs_rq; long rem_load_move = max_load_move; - int busiest_cpu = cpu_of(busiest); - struct task_group *tg; - - rcu_read_lock(); - list_for_each_entry(tg, &task_groups, list) { - long imbalance; - unsigned long this_weight, busiest_weight; - long rem_load, max_load, moved_load; - - /* - * empty group - */ - if (!aggregate(tg, sd)->task_weight) - continue; - - rem_load = rem_load_move * aggregate(tg, sd)->rq_weight; - rem_load /= aggregate(tg, sd)->load + 1; - - this_weight = tg->cfs_rq[this_cpu]->task_weight; - busiest_weight = tg->cfs_rq[busiest_cpu]->task_weight; + struct rq_iterator cfs_rq_iterator; - imbalance = (busiest_weight - this_weight) / 2; + cfs_rq_iterator.start = load_balance_start_fair; + cfs_rq_iterator.next = load_balance_next_fair; - if (imbalance < 0) - imbalance = busiest_weight; + for_each_leaf_cfs_rq(busiest, busy_cfs_rq) { +#ifdef CONFIG_FAIR_GROUP_SCHED + struct cfs_rq *this_cfs_rq; + long imbalance; + unsigned long maxload; - max_load = max(rem_load, imbalance); - moved_load = __load_balance_fair(this_rq, this_cpu, busiest, - max_load, sd, idle, all_pinned, this_best_prio, - tg->cfs_rq[busiest_cpu]); + this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu); - if (!moved_load) + imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight; + /* Don't pull if this_cfs_rq has more load than busy_cfs_rq */ + if (imbalance <= 0) continue; - move_group_shares(tg, sd, busiest_cpu, this_cpu); + /* Don't pull more than imbalance/2 */ + imbalance /= 2; + maxload = min(rem_load_move, imbalance); - moved_load *= aggregate(tg, sd)->load; - moved_load /= aggregate(tg, sd)->rq_weight + 1; + *this_best_prio = cfs_rq_best_prio(this_cfs_rq); +#else +# define maxload rem_load_move +#endif + /* + * pass busy_cfs_rq argument into + * load_balance_[start|next]_fair iterators + */ + cfs_rq_iterator.arg = busy_cfs_rq; + rem_load_move -= balance_tasks(this_rq, this_cpu, busiest, + maxload, sd, idle, all_pinned, + this_best_prio, + &cfs_rq_iterator); - rem_load_move -= moved_load; - if (rem_load_move < 0) + if (rem_load_move <= 0) break; } - rcu_read_unlock(); return max_load_move - rem_load_move; } -#else -static unsigned long -load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, int *this_best_prio) -{ - return __load_balance_fair(this_rq, this_cpu, busiest, - max_load_move, sd, idle, all_pinned, - this_best_prio, &busiest->cfs); -} -#endif static int move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 060e87b0cb1c..0f3c19197fa4 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -250,7 +250,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) if (rt_rq->rt_time || rt_rq->rt_nr_running) idle = 0; spin_unlock(&rt_rq->rt_runtime_lock); - } + } else if (rt_rq->rt_nr_running) + idle = 0; if (enqueue) sched_rt_rq_enqueue(rt_rq); @@ -449,13 +450,19 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) #endif } -static void enqueue_rt_entity(struct sched_rt_entity *rt_se) +static void __enqueue_rt_entity(struct sched_rt_entity *rt_se) { struct rt_rq *rt_rq = rt_rq_of_se(rt_se); struct rt_prio_array *array = &rt_rq->active; struct rt_rq *group_rq = group_rt_rq(rt_se); - if (group_rq && rt_rq_throttled(group_rq)) + /* + * Don't enqueue the group if its throttled, or when empty. + * The latter is a consequence of the former when a child group + * get throttled and the current group doesn't have any other + * active members. + */ + if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) return; list_add_tail(&rt_se->run_list, array->queue + rt_se_prio(rt_se)); @@ -464,7 +471,7 @@ static void enqueue_rt_entity(struct sched_rt_entity *rt_se) inc_rt_tasks(rt_se, rt_rq); } -static void dequeue_rt_entity(struct sched_rt_entity *rt_se) +static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) { struct rt_rq *rt_rq = rt_rq_of_se(rt_se); struct rt_prio_array *array = &rt_rq->active; @@ -480,11 +487,10 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se) * Because the prio of an upper entry depends on the lower * entries, we must remove entries top - down. */ -static void dequeue_rt_stack(struct task_struct *p) +static void dequeue_rt_stack(struct sched_rt_entity *rt_se) { - struct sched_rt_entity *rt_se, *back = NULL; + struct sched_rt_entity *back = NULL; - rt_se = &p->rt; for_each_sched_rt_entity(rt_se) { rt_se->back = back; back = rt_se; @@ -492,7 +498,26 @@ static void dequeue_rt_stack(struct task_struct *p) for (rt_se = back; rt_se; rt_se = rt_se->back) { if (on_rt_rq(rt_se)) - dequeue_rt_entity(rt_se); + __dequeue_rt_entity(rt_se); + } +} + +static void enqueue_rt_entity(struct sched_rt_entity *rt_se) +{ + dequeue_rt_stack(rt_se); + for_each_sched_rt_entity(rt_se) + __enqueue_rt_entity(rt_se); +} + +static void dequeue_rt_entity(struct sched_rt_entity *rt_se) +{ + dequeue_rt_stack(rt_se); + + for_each_sched_rt_entity(rt_se) { + struct rt_rq *rt_rq = group_rt_rq(rt_se); + + if (rt_rq && rt_rq->rt_nr_running) + __enqueue_rt_entity(rt_se); } } @@ -506,36 +531,15 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup) if (wakeup) rt_se->timeout = 0; - dequeue_rt_stack(p); - - /* - * enqueue everybody, bottom - up. - */ - for_each_sched_rt_entity(rt_se) - enqueue_rt_entity(rt_se); - - inc_cpu_load(rq, p->se.load.weight); + enqueue_rt_entity(rt_se); } static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep) { struct sched_rt_entity *rt_se = &p->rt; - struct rt_rq *rt_rq; update_curr_rt(rq); - - dequeue_rt_stack(p); - - /* - * re-enqueue all non-empty rt_rq entities. - */ - for_each_sched_rt_entity(rt_se) { - rt_rq = group_rt_rq(rt_se); - if (rt_rq && rt_rq->rt_nr_running) - enqueue_rt_entity(rt_se); - } - - dec_cpu_load(rq, p->se.load.weight); + dequeue_rt_entity(rt_se); } /* @@ -546,8 +550,10 @@ static void requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se) { struct rt_prio_array *array = &rt_rq->active; + struct list_head *queue = array->queue + rt_se_prio(rt_se); - list_move_tail(&rt_se->run_list, array->queue + rt_se_prio(rt_se)); + if (on_rt_rq(rt_se)) + list_move_tail(&rt_se->run_list, queue); } static void requeue_task_rt(struct rq *rq, struct task_struct *p) diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 5bae2e0c3ff2..80179ef7450e 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -67,6 +67,7 @@ static int show_schedstat(struct seq_file *seq, void *v) preempt_enable(); #endif } + kfree(mask_str); return 0; } @@ -197,6 +198,9 @@ static inline void sched_info_queued(struct task_struct *t) /* * Called when a process ceases being the active-running process, either * voluntarily or involuntarily. Now we can calculate how long we ran. + * Also, if the process is still in the TASK_RUNNING state, call + * sched_info_queued() to mark that it has now again started waiting on + * the runqueue. */ static inline void sched_info_depart(struct task_struct *t) { @@ -205,6 +209,9 @@ static inline void sched_info_depart(struct task_struct *t) t->sched_info.cpu_time += delta; rq_sched_info_depart(task_rq(t), delta); + + if (t->state == TASK_RUNNING) + sched_info_queued(t); } /* diff --git a/kernel/signal.c b/kernel/signal.c index 12ffea7c201d..6c0958e52ea7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -231,6 +231,40 @@ void flush_signals(struct task_struct *t) spin_unlock_irqrestore(&t->sighand->siglock, flags); } +static void __flush_itimer_signals(struct sigpending *pending) +{ + sigset_t signal, retain; + struct sigqueue *q, *n; + + signal = pending->signal; + sigemptyset(&retain); + + list_for_each_entry_safe(q, n, &pending->list, list) { + int sig = q->info.si_signo; + + if (likely(q->info.si_code != SI_TIMER)) { + sigaddset(&retain, sig); + } else { + sigdelset(&signal, sig); + list_del_init(&q->list); + __sigqueue_free(q); + } + } + + sigorsets(&pending->signal, &signal, &retain); +} + +void flush_itimer_signals(void) +{ + struct task_struct *tsk = current; + unsigned long flags; + + spin_lock_irqsave(&tsk->sighand->siglock, flags); + __flush_itimer_signals(&tsk->pending); + __flush_itimer_signals(&tsk->signal->shared_pending); + spin_unlock_irqrestore(&tsk->sighand->siglock, flags); +} + void ignore_signals(struct task_struct *t) { int i; @@ -1240,18 +1274,22 @@ void sigqueue_free(struct sigqueue *q) BUG_ON(!(q->flags & SIGQUEUE_PREALLOC)); /* - * If the signal is still pending remove it from the - * pending queue. We must hold ->siglock while testing - * q->list to serialize with collect_signal() or with + * We must hold ->siglock while testing q->list + * to serialize with collect_signal() or with * __exit_signal()->flush_sigqueue(). */ spin_lock_irqsave(lock, flags); + q->flags &= ~SIGQUEUE_PREALLOC; + /* + * If it is queued it will be freed when dequeued, + * like the "regular" sigqueue. + */ if (!list_empty(&q->list)) - list_del_init(&q->list); + q = NULL; spin_unlock_irqrestore(lock, flags); - q->flags &= ~SIGQUEUE_PREALLOC; - __sigqueue_free(q); + if (q) + __sigqueue_free(q); } int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group) diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 01b6522fd92b..c828c2339cc9 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -49,12 +49,17 @@ static unsigned long get_timestamp(int this_cpu) return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */ } -void touch_softlockup_watchdog(void) +static void __touch_softlockup_watchdog(void) { int this_cpu = raw_smp_processor_id(); __raw_get_cpu_var(touch_timestamp) = get_timestamp(this_cpu); } + +void touch_softlockup_watchdog(void) +{ + __raw_get_cpu_var(touch_timestamp) = 0; +} EXPORT_SYMBOL(touch_softlockup_watchdog); void touch_all_softlockup_watchdogs(void) @@ -80,7 +85,7 @@ void softlockup_tick(void) unsigned long now; if (touch_timestamp == 0) { - touch_softlockup_watchdog(); + __touch_softlockup_watchdog(); return; } @@ -95,7 +100,7 @@ void softlockup_tick(void) /* do not print during early bootup: */ if (unlikely(system_state != SYSTEM_RUNNING)) { - touch_softlockup_watchdog(); + __touch_softlockup_watchdog(); return; } @@ -214,7 +219,7 @@ static int watchdog(void *__bind_cpu) sched_setscheduler(current, SCHED_FIFO, ¶m); /* initialize timestamp */ - touch_softlockup_watchdog(); + __touch_softlockup_watchdog(); set_current_state(TASK_INTERRUPTIBLE); /* @@ -223,7 +228,7 @@ static int watchdog(void *__bind_cpu) * debug-printout triggers in softlockup_tick(). */ while (!kthread_should_stop()) { - touch_softlockup_watchdog(); + __touch_softlockup_watchdog(); schedule(); if (kthread_should_stop()) |