diff options
author | Arve Hjønnevåg <arve@android.com> | 2010-03-10 16:38:33 -0800 |
---|---|---|
committer | Arve Hjønnevåg <arve@android.com> | 2010-03-10 16:38:33 -0800 |
commit | 67078ecae3edb5b4657dcb9f67f744ecccd18a97 (patch) | |
tree | 90333318a7229fd977881577e0d19fd8e7e26423 /kernel | |
parent | dc136618cb23810dd3d4adfcb836b289cd528b4f (diff) | |
parent | 7f5e918e62cbc9ac27c2f47d3c3dd4b86f67ff0e (diff) |
Merge commit 'v2.6.32.9' into android-2.6.32
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/acct.c | 3 | ||||
-rw-r--r-- | kernel/audit_tree.c | 13 | ||||
-rw-r--r-- | kernel/cgroup.c | 1 | ||||
-rw-r--r-- | kernel/cpu.c | 23 | ||||
-rw-r--r-- | kernel/cpuset.c | 16 | ||||
-rw-r--r-- | kernel/cred.c | 2 | ||||
-rw-r--r-- | kernel/futex.c | 67 | ||||
-rw-r--r-- | kernel/module.c | 45 | ||||
-rw-r--r-- | kernel/perf_event.c | 36 | ||||
-rw-r--r-- | kernel/rcutree.c | 227 | ||||
-rw-r--r-- | kernel/rcutree.h | 13 | ||||
-rw-r--r-- | kernel/rcutree_plugin.h | 4 | ||||
-rw-r--r-- | kernel/sched.c | 98 | ||||
-rw-r--r-- | kernel/sched_clock.c | 23 | ||||
-rw-r--r-- | kernel/sched_debug.c | 4 | ||||
-rw-r--r-- | kernel/sched_fair.c | 54 | ||||
-rw-r--r-- | kernel/signal.c | 3 | ||||
-rw-r--r-- | kernel/sysctl.c | 5 | ||||
-rw-r--r-- | kernel/sysctl_check.c | 1 | ||||
-rw-r--r-- | kernel/time/clockevents.c | 21 | ||||
-rw-r--r-- | kernel/time/clocksource.c | 44 | ||||
-rw-r--r-- | kernel/time/tick-sched.c | 52 | ||||
-rw-r--r-- | kernel/time/timekeeping.c | 13 |
23 files changed, 545 insertions, 223 deletions
diff --git a/kernel/acct.c b/kernel/acct.c index 9a4715a2f6bf..a6605ca921b6 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -536,7 +536,8 @@ static void do_acct_process(struct bsd_acct_struct *acct, do_div(elapsed, AHZ); ac.ac_btime = get_seconds() - elapsed; /* we really need to bite the bullet and change layout */ - current_uid_gid(&ac.ac_uid, &ac.ac_gid); + ac.ac_uid = orig_cred->uid; + ac.ac_gid = orig_cred->gid; #if ACCT_VERSION==2 ac.ac_ahz = AHZ; #endif diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 2451dc6f3282..4b05bd9479db 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -277,7 +277,7 @@ static void untag_chunk(struct node *p) owner->root = NULL; } - for (i = j = 0; i < size; i++, j++) { + for (i = j = 0; j <= size; i++, j++) { struct audit_tree *s; if (&chunk->owners[j] == p) { list_del_init(&p->list); @@ -290,7 +290,7 @@ static void untag_chunk(struct node *p) if (!s) /* result of earlier fallback */ continue; get_tree(s); - list_replace_init(&chunk->owners[i].list, &new->owners[j].list); + list_replace_init(&chunk->owners[j].list, &new->owners[i].list); } list_replace_rcu(&chunk->hash, &new->hash); @@ -373,15 +373,17 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) for (n = 0; n < old->count; n++) { if (old->owners[n].owner == tree) { spin_unlock(&hash_lock); - put_inotify_watch(watch); + put_inotify_watch(&old->watch); return 0; } } spin_unlock(&hash_lock); chunk = alloc_chunk(old->count + 1); - if (!chunk) + if (!chunk) { + put_inotify_watch(&old->watch); return -ENOMEM; + } mutex_lock(&inode->inotify_mutex); if (inotify_clone_watch(&old->watch, &chunk->watch) < 0) { @@ -425,7 +427,8 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) spin_unlock(&hash_lock); inotify_evict_watch(&old->watch); mutex_unlock(&inode->inotify_mutex); - put_inotify_watch(&old->watch); + put_inotify_watch(&old->watch); /* pair to inotify_find_watch */ + put_inotify_watch(&old->watch); /* and kill it */ return 0; } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 455689fd1971..29500c8fe8e6 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2469,7 +2469,6 @@ static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, /* make sure l doesn't vanish out from under us */ down_write(&l->mutex); mutex_unlock(&cgrp->pidlist_mutex); - l->use_count++; return l; } } diff --git a/kernel/cpu.c b/kernel/cpu.c index 6ba0f1ecb212..291ac586f37f 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -212,6 +212,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); if (err == NOTIFY_BAD) { + set_cpu_active(cpu, true); + nr_calls--; __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL); @@ -223,11 +225,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) /* Ensure that we are not runnable on dying cpu */ cpumask_copy(old_allowed, ¤t->cpus_allowed); - set_cpus_allowed_ptr(current, - cpumask_of(cpumask_any_but(cpu_online_mask, cpu))); + set_cpus_allowed_ptr(current, cpu_active_mask); err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); if (err) { + set_cpu_active(cpu, true); /* CPU didn't die: tell everyone. Can't complain. */ if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod, hcpu) == NOTIFY_BAD) @@ -292,9 +294,6 @@ int __ref cpu_down(unsigned int cpu) err = _cpu_down(cpu, 0); - if (cpu_online(cpu)) - set_cpu_active(cpu, true); - out: cpu_maps_update_done(); stop_machine_destroy(); @@ -387,15 +386,23 @@ int disable_nonboot_cpus(void) * with the userspace trying to use the CPU hotplug at the same time */ cpumask_clear(frozen_cpus); + + for_each_online_cpu(cpu) { + if (cpu == first_cpu) + continue; + set_cpu_active(cpu, false); + } + + synchronize_sched(); + printk("Disabling non-boot CPUs ...\n"); for_each_online_cpu(cpu) { if (cpu == first_cpu) continue; error = _cpu_down(cpu, 1); - if (!error) { + if (!error) cpumask_set_cpu(cpu, frozen_cpus); - printk("CPU%d is down\n", cpu); - } else { + else { printk(KERN_ERR "Error taking CPU%d down: %d\n", cpu, error); break; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 2b637ca37be4..5d03d305a2b1 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -873,7 +873,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, if (retval < 0) return retval; - if (!cpumask_subset(trialcs->cpus_allowed, cpu_online_mask)) + if (!cpumask_subset(trialcs->cpus_allowed, cpu_active_mask)) return -EINVAL; } retval = validate_change(cs, trialcs); @@ -2018,7 +2018,7 @@ static void scan_for_empty_cpusets(struct cpuset *root) } /* Continue past cpusets with all cpus, mems online */ - if (cpumask_subset(cp->cpus_allowed, cpu_online_mask) && + if (cpumask_subset(cp->cpus_allowed, cpu_active_mask) && nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY])) continue; @@ -2027,7 +2027,7 @@ static void scan_for_empty_cpusets(struct cpuset *root) /* Remove offline cpus and mems from this cpuset. */ mutex_lock(&callback_mutex); cpumask_and(cp->cpus_allowed, cp->cpus_allowed, - cpu_online_mask); + cpu_active_mask); nodes_and(cp->mems_allowed, cp->mems_allowed, node_states[N_HIGH_MEMORY]); mutex_unlock(&callback_mutex); @@ -2065,8 +2065,10 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, switch (phase) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: - case CPU_DEAD: - case CPU_DEAD_FROZEN: + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + case CPU_DOWN_FAILED: + case CPU_DOWN_FAILED_FROZEN: break; default: @@ -2075,7 +2077,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, cgroup_lock(); mutex_lock(&callback_mutex); - cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask); + cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); mutex_unlock(&callback_mutex); scan_for_empty_cpusets(&top_cpuset); ndoms = generate_sched_domains(&doms, &attr); @@ -2122,7 +2124,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self, void __init cpuset_init_smp(void) { - cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask); + cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; hotcpu_notifier(cpuset_track_online_cpus, 0); diff --git a/kernel/cred.c b/kernel/cred.c index dd76cfe5f5b0..1ed8ca18790c 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -224,7 +224,7 @@ struct cred *cred_alloc_blank(void) #ifdef CONFIG_KEYS new->tgcred = kzalloc(sizeof(*new->tgcred), GFP_KERNEL); if (!new->tgcred) { - kfree(new); + kmem_cache_free(cred_jar, new); return NULL; } atomic_set(&new->tgcred->usage, 1); diff --git a/kernel/futex.c b/kernel/futex.c index 546e13300d3b..c6a80616fcfd 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -203,8 +203,6 @@ static void drop_futex_key_refs(union futex_key *key) * @uaddr: virtual address of the futex * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED * @key: address where result is stored. - * @rw: mapping needs to be read/write (values: VERIFY_READ, - * VERIFY_WRITE) * * Returns a negative error code or 0 * The key words are stored in *key on success. @@ -216,7 +214,7 @@ static void drop_futex_key_refs(union futex_key *key) * lock_page() might sleep, the caller should not hold a spinlock. */ static int -get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) +get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; @@ -240,7 +238,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) * but access_ok() should be faster than find_vma() */ if (!fshared) { - if (unlikely(!access_ok(rw, uaddr, sizeof(u32)))) + if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))) return -EFAULT; key->private.mm = mm; key->private.address = address; @@ -280,7 +278,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) } again: - err = get_user_pages_fast(address, 1, rw == VERIFY_WRITE, &page); + err = get_user_pages_fast(address, 1, 1, &page); if (err < 0) return err; @@ -336,8 +334,14 @@ void put_futex_key(int fshared, union futex_key *key) */ static int fault_in_user_writeable(u32 __user *uaddr) { - int ret = get_user_pages(current, current->mm, (unsigned long)uaddr, - 1, 1, 0, NULL, NULL); + struct mm_struct *mm = current->mm; + int ret; + + down_read(&mm->mmap_sem); + ret = get_user_pages(current, mm, (unsigned long)uaddr, + 1, 1, 0, NULL, NULL); + up_read(&mm->mmap_sem); + return ret < 0 ? ret : 0; } @@ -558,8 +562,25 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, return -EINVAL; WARN_ON(!atomic_read(&pi_state->refcount)); - WARN_ON(pid && pi_state->owner && - pi_state->owner->pid != pid); + + /* + * When pi_state->owner is NULL then the owner died + * and another waiter is on the fly. pi_state->owner + * is fixed up by the task which acquires + * pi_state->rt_mutex. + * + * We do not check for pid == 0 which can happen when + * the owner died and robust_list_exit() cleared the + * TID. + */ + if (pid && pi_state->owner) { + /* + * Bail out if user space manipulated the + * futex value. + */ + if (pid != task_pid_vnr(pi_state->owner)) + return -EINVAL; + } atomic_inc(&pi_state->refcount); *ps = pi_state; @@ -786,6 +807,13 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) if (!pi_state) return -EINVAL; + /* + * If current does not own the pi_state then the futex is + * inconsistent and user space fiddled with the futex value. + */ + if (pi_state->owner != current) + return -EINVAL; + spin_lock(&pi_state->pi_mutex.wait_lock); new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); @@ -893,7 +921,7 @@ static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset) if (!bitset) return -EINVAL; - ret = get_futex_key(uaddr, fshared, &key, VERIFY_READ); + ret = get_futex_key(uaddr, fshared, &key); if (unlikely(ret != 0)) goto out; @@ -939,10 +967,10 @@ futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2, int ret, op_ret; retry: - ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ); + ret = get_futex_key(uaddr1, fshared, &key1); if (unlikely(ret != 0)) goto out; - ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE); + ret = get_futex_key(uaddr2, fshared, &key2); if (unlikely(ret != 0)) goto out_put_key1; @@ -1201,11 +1229,10 @@ retry: pi_state = NULL; } - ret = get_futex_key(uaddr1, fshared, &key1, VERIFY_READ); + ret = get_futex_key(uaddr1, fshared, &key1); if (unlikely(ret != 0)) goto out; - ret = get_futex_key(uaddr2, fshared, &key2, - requeue_pi ? VERIFY_WRITE : VERIFY_READ); + ret = get_futex_key(uaddr2, fshared, &key2); if (unlikely(ret != 0)) goto out_put_key1; @@ -1764,7 +1791,7 @@ static int futex_wait_setup(u32 __user *uaddr, u32 val, int fshared, */ retry: q->key = FUTEX_KEY_INIT; - ret = get_futex_key(uaddr, fshared, &q->key, VERIFY_READ); + ret = get_futex_key(uaddr, fshared, &q->key); if (unlikely(ret != 0)) return ret; @@ -1930,7 +1957,7 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared, q.requeue_pi_key = NULL; retry: q.key = FUTEX_KEY_INIT; - ret = get_futex_key(uaddr, fshared, &q.key, VERIFY_WRITE); + ret = get_futex_key(uaddr, fshared, &q.key); if (unlikely(ret != 0)) goto out; @@ -2000,7 +2027,7 @@ retry_private: /* Unqueue and drop the lock */ unqueue_me_pi(&q); - goto out; + goto out_put_key; out_unlock_put_key: queue_unlock(&q, hb); @@ -2049,7 +2076,7 @@ retry: if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current)) return -EPERM; - ret = get_futex_key(uaddr, fshared, &key, VERIFY_WRITE); + ret = get_futex_key(uaddr, fshared, &key); if (unlikely(ret != 0)) goto out; @@ -2241,7 +2268,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared, rt_waiter.task = NULL; key2 = FUTEX_KEY_INIT; - ret = get_futex_key(uaddr2, fshared, &key2, VERIFY_WRITE); + ret = get_futex_key(uaddr2, fshared, &key2); if (unlikely(ret != 0)) goto out; diff --git a/kernel/module.c b/kernel/module.c index 5842a71cf052..dfa33e8ee2a9 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1030,11 +1030,23 @@ static int try_to_force_load(struct module *mod, const char *reason) } #ifdef CONFIG_MODVERSIONS +/* If the arch applies (non-zero) relocations to kernel kcrctab, unapply it. */ +static unsigned long maybe_relocated(unsigned long crc, + const struct module *crc_owner) +{ +#ifdef ARCH_RELOCATES_KCRCTAB + if (crc_owner == NULL) + return crc - (unsigned long)reloc_start; +#endif + return crc; +} + static int check_version(Elf_Shdr *sechdrs, unsigned int versindex, const char *symname, struct module *mod, - const unsigned long *crc) + const unsigned long *crc, + const struct module *crc_owner) { unsigned int i, num_versions; struct modversion_info *versions; @@ -1055,10 +1067,10 @@ static int check_version(Elf_Shdr *sechdrs, if (strcmp(versions[i].name, symname) != 0) continue; - if (versions[i].crc == *crc) + if (versions[i].crc == maybe_relocated(*crc, crc_owner)) return 1; DEBUGP("Found checksum %lX vs module %lX\n", - *crc, versions[i].crc); + maybe_relocated(*crc, crc_owner), versions[i].crc); goto bad_version; } @@ -1081,7 +1093,8 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs, if (!find_symbol(MODULE_SYMBOL_PREFIX "module_layout", NULL, &crc, true, false)) BUG(); - return check_version(sechdrs, versindex, "module_layout", mod, crc); + return check_version(sechdrs, versindex, "module_layout", mod, crc, + NULL); } /* First part is kernel version, which we ignore if module has crcs. */ @@ -1099,7 +1112,8 @@ static inline int check_version(Elf_Shdr *sechdrs, unsigned int versindex, const char *symname, struct module *mod, - const unsigned long *crc) + const unsigned long *crc, + const struct module *crc_owner) { return 1; } @@ -1134,8 +1148,8 @@ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, /* use_module can fail due to OOM, or module initialization or unloading */ if (sym) { - if (!check_version(sechdrs, versindex, name, mod, crc) || - !use_module(mod, owner)) + if (!check_version(sechdrs, versindex, name, mod, crc, owner) + || !use_module(mod, owner)) sym = NULL; } return sym; @@ -1146,6 +1160,12 @@ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, * J. Corbet <corbet@lwn.net> */ #if defined(CONFIG_KALLSYMS) && defined(CONFIG_SYSFS) + +static inline bool sect_empty(const Elf_Shdr *sect) +{ + return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0; +} + struct module_sect_attr { struct module_attribute mattr; @@ -1187,8 +1207,7 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, /* Count loaded sections and allocate structures */ for (i = 0; i < nsect; i++) - if (sechdrs[i].sh_flags & SHF_ALLOC - && sechdrs[i].sh_size) + if (!sect_empty(&sechdrs[i])) nloaded++; size[0] = ALIGN(sizeof(*sect_attrs) + nloaded * sizeof(sect_attrs->attrs[0]), @@ -1206,9 +1225,7 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, sattr = §_attrs->attrs[0]; gattr = §_attrs->grp.attrs[0]; for (i = 0; i < nsect; i++) { - if (! (sechdrs[i].sh_flags & SHF_ALLOC)) - continue; - if (!sechdrs[i].sh_size) + if (sect_empty(&sechdrs[i])) continue; sattr->address = sechdrs[i].sh_addr; sattr->name = kstrdup(secstrings + sechdrs[i].sh_name, @@ -1292,7 +1309,7 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, /* Count notes sections and allocate structures. */ notes = 0; for (i = 0; i < nsect; i++) - if ((sechdrs[i].sh_flags & SHF_ALLOC) && + if (!sect_empty(&sechdrs[i]) && (sechdrs[i].sh_type == SHT_NOTE)) ++notes; @@ -1308,7 +1325,7 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, notes_attrs->notes = notes; nattr = ¬es_attrs->attrs[0]; for (loaded = i = 0; i < nsect; ++i) { - if (!(sechdrs[i].sh_flags & SHF_ALLOC)) + if (sect_empty(&sechdrs[i])) continue; if (sechdrs[i].sh_type == SHT_NOTE) { nattr->attr.name = mod->sect_attrs->attrs[loaded].name; diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 7f29643c8985..413d101ca8ee 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -1359,6 +1359,9 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx) if (event->state != PERF_EVENT_STATE_ACTIVE) continue; + if (event->cpu != -1 && event->cpu != smp_processor_id()) + continue; + hwc = &event->hw; interrupts = hwc->interrupts; @@ -1583,7 +1586,7 @@ static struct perf_event_context *find_get_context(pid_t pid, int cpu) if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) return ERR_PTR(-EACCES); - if (cpu < 0 || cpu > num_possible_cpus()) + if (cpu < 0 || cpu >= nr_cpumask_bits) return ERR_PTR(-EINVAL); /* @@ -2174,6 +2177,7 @@ static void perf_mmap_data_free(struct perf_mmap_data *data) perf_mmap_free_page((unsigned long)data->user_page); for (i = 0; i < data->nr_pages; i++) perf_mmap_free_page((unsigned long)data->data_pages[i]); + kfree(data); } #else @@ -2214,6 +2218,7 @@ static void perf_mmap_data_free_work(struct work_struct *work) perf_mmap_unmark_page(base + (i * PAGE_SIZE)); vfree(base); + kfree(data); } static void perf_mmap_data_free(struct perf_mmap_data *data) @@ -2319,7 +2324,6 @@ static void perf_mmap_data_free_rcu(struct rcu_head *rcu_head) data = container_of(rcu_head, struct perf_mmap_data, rcu_head); perf_mmap_data_free(data); - kfree(data); } static void perf_mmap_data_release(struct perf_event *event) @@ -3225,6 +3229,12 @@ static void perf_event_task_output(struct perf_event *event, static int perf_event_task_match(struct perf_event *event) { + if (event->state != PERF_EVENT_STATE_ACTIVE) + return 0; + + if (event->cpu != -1 && event->cpu != smp_processor_id()) + return 0; + if (event->attr.comm || event->attr.mmap || event->attr.task) return 1; @@ -3254,13 +3264,13 @@ static void perf_event_task_event(struct perf_task_event *task_event) cpuctx = &get_cpu_var(perf_cpu_context); perf_event_task_ctx(&cpuctx->ctx, task_event); - put_cpu_var(perf_cpu_context); rcu_read_lock(); if (!ctx) ctx = rcu_dereference(task_event->task->perf_event_ctxp); if (ctx) perf_event_task_ctx(ctx, task_event); + put_cpu_var(perf_cpu_context); rcu_read_unlock(); } @@ -3337,6 +3347,12 @@ static void perf_event_comm_output(struct perf_event *event, static int perf_event_comm_match(struct perf_event *event) { + if (event->state != PERF_EVENT_STATE_ACTIVE) + return 0; + + if (event->cpu != -1 && event->cpu != smp_processor_id()) + return 0; + if (event->attr.comm) return 1; @@ -3377,7 +3393,6 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) cpuctx = &get_cpu_var(perf_cpu_context); perf_event_comm_ctx(&cpuctx->ctx, comm_event); - put_cpu_var(perf_cpu_context); rcu_read_lock(); /* @@ -3387,6 +3402,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) ctx = rcu_dereference(current->perf_event_ctxp); if (ctx) perf_event_comm_ctx(ctx, comm_event); + put_cpu_var(perf_cpu_context); rcu_read_unlock(); } @@ -3461,6 +3477,12 @@ static void perf_event_mmap_output(struct perf_event *event, static int perf_event_mmap_match(struct perf_event *event, struct perf_mmap_event *mmap_event) { + if (event->state != PERF_EVENT_STATE_ACTIVE) + return 0; + + if (event->cpu != -1 && event->cpu != smp_processor_id()) + return 0; + if (event->attr.mmap) return 1; @@ -3538,7 +3560,6 @@ got_name: cpuctx = &get_cpu_var(perf_cpu_context); perf_event_mmap_ctx(&cpuctx->ctx, mmap_event); - put_cpu_var(perf_cpu_context); rcu_read_lock(); /* @@ -3548,6 +3569,7 @@ got_name: ctx = rcu_dereference(current->perf_event_ctxp); if (ctx) perf_event_mmap_ctx(ctx, mmap_event); + put_cpu_var(perf_cpu_context); rcu_read_unlock(); kfree(buf); @@ -3810,6 +3832,9 @@ static int perf_swevent_match(struct perf_event *event, enum perf_type_id type, u32 event_id, struct pt_regs *regs) { + if (event->cpu != -1 && event->cpu != smp_processor_id()) + return 0; + if (!perf_swevent_is_counting(event)) return 0; @@ -3949,6 +3974,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) event->pmu->read(event); data.addr = 0; + data.period = event->hw.last_period; regs = get_irq_regs(); /* * In case we exclude kernel IPs or are somehow not in interrupt diff --git a/kernel/rcutree.c b/kernel/rcutree.c index f3077c0ab181..683c4f3b87e0 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -176,9 +176,29 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) return &rsp->node[0]; } +/* + * Record the specified "completed" value, which is later used to validate + * dynticks counter manipulations and CPU-offline checks. Specify + * "rsp->completed - 1" to unconditionally invalidate any future dynticks + * manipulations and CPU-offline checks. Such invalidation is useful at + * the beginning of a grace period. + */ +static void dyntick_record_completed(struct rcu_state *rsp, long comp) +{ + rsp->dynticks_completed = comp; +} + #ifdef CONFIG_SMP /* + * Recall the previously recorded value of the completion for dynticks. + */ +static long dyntick_recall_completed(struct rcu_state *rsp) +{ + return rsp->dynticks_completed; +} + +/* * If the specified CPU is offline, tell the caller that it is in * a quiescent state. Otherwise, whack it with a reschedule IPI. * Grace periods can end up waiting on an offline CPU when that @@ -335,28 +355,9 @@ void rcu_irq_exit(void) set_need_resched(); } -/* - * Record the specified "completed" value, which is later used to validate - * dynticks counter manipulations. Specify "rsp->completed - 1" to - * unconditionally invalidate any future dynticks manipulations (which is - * useful at the beginning of a grace period). - */ -static void dyntick_record_completed(struct rcu_state *rsp, long comp) -{ - rsp->dynticks_completed = comp; -} - #ifdef CONFIG_SMP /* - * Recall the previously recorded value of the completion for dynticks. - */ -static long dyntick_recall_completed(struct rcu_state *rsp) -{ - return rsp->dynticks_completed; -} - -/* * Snapshot the specified CPU's dynticks counter so that we can later * credit them with an implicit quiescent state. Return 1 if this CPU * is in dynticks idle mode, which is an extended quiescent state. @@ -419,24 +420,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) #else /* #ifdef CONFIG_NO_HZ */ -static void dyntick_record_completed(struct rcu_state *rsp, long comp) -{ -} - #ifdef CONFIG_SMP -/* - * If there are no dynticks, then the only way that a CPU can passively - * be in a quiescent state is to be offline. Unlike dynticks idle, which - * is a point in time during the prior (already finished) grace period, - * an offline CPU is always in a quiescent state, and thus can be - * unconditionally applied. So just return the current value of completed. - */ -static long dyntick_recall_completed(struct rcu_state *rsp) -{ - return rsp->completed; -} - static int dyntick_save_progress_counter(struct rcu_data *rdp) { return 0; @@ -553,13 +538,33 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) /* * Update CPU-local rcu_data state to record the newly noticed grace period. * This is used both when we started the grace period and when we notice - * that someone else started the grace period. + * that someone else started the grace period. The caller must hold the + * ->lock of the leaf rcu_node structure corresponding to the current CPU, + * and must have irqs disabled. */ +static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) +{ + if (rdp->gpnum != rnp->gpnum) { + rdp->qs_pending = 1; + rdp->passed_quiesc = 0; + rdp->gpnum = rnp->gpnum; + } +} + static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp) { - rdp->qs_pending = 1; - rdp->passed_quiesc = 0; - rdp->gpnum = rsp->gpnum; + unsigned long flags; + struct rcu_node *rnp; + + local_irq_save(flags); + rnp = rdp->mynode; + if (rdp->gpnum == ACCESS_ONCE(rnp->gpnum) || /* outside lock. */ + !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */ + local_irq_restore(flags); + return; + } + __note_new_gpnum(rsp, rnp, rdp); + spin_unlock_irqrestore(&rnp->lock, flags); } /* @@ -583,6 +588,79 @@ check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp) } /* + * Advance this CPU's callbacks, but only if the current grace period + * has ended. This may be called only from the CPU to whom the rdp + * belongs. In addition, the corresponding leaf rcu_node structure's + * ->lock must be held by the caller, with irqs disabled. + */ +static void +__rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) +{ + /* Did another grace period end? */ + if (rdp->completed != rnp->completed) { + + /* Advance callbacks. No harm if list empty. */ + rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL]; + rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL]; + rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + + /* Remember that we saw this grace-period completion. */ + rdp->completed = rnp->completed; + } +} + +/* + * Advance this CPU's callbacks, but only if the current grace period + * has ended. This may be called only from the CPU to whom the rdp + * belongs. + */ +static void +rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp) +{ + unsigned long flags; + struct rcu_node *rnp; + + local_irq_save(flags); + rnp = rdp->mynode; + if (rdp->completed == ACCESS_ONCE(rnp->completed) || /* outside lock. */ + !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */ + local_irq_restore(flags); + return; + } + __rcu_process_gp_end(rsp, rnp, rdp); + spin_unlock_irqrestore(&rnp->lock, flags); +} + +/* + * Do per-CPU grace-period initialization for running CPU. The caller + * must hold the lock of the leaf rcu_node structure corresponding to + * this CPU. + */ +static void +rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) +{ + /* Prior grace period ended, so advance callbacks for current CPU. */ + __rcu_process_gp_end(rsp, rnp, rdp); + + /* + * Because this CPU just now started the new grace period, we know + * that all of its callbacks will be covered by this upcoming grace + * period, even the ones that were registered arbitrarily recently. + * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL. + * + * Other CPUs cannot be sure exactly when the grace period started. + * Therefore, their recently registered callbacks must pass through + * an additional RCU_NEXT_READY stage, so that they will be handled + * by the next RCU grace period. + */ + rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + + /* Set state so that this CPU will detect the next quiescent state. */ + __note_new_gpnum(rsp, rnp, rdp); +} + +/* * Start a new RCU grace period if warranted, re-initializing the hierarchy * in preparation for detecting the next grace period. The caller must hold * the root node's ->lock, which is released before return. Hard irqs must @@ -607,28 +685,15 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; record_gp_stall_check_time(rsp); dyntick_record_completed(rsp, rsp->completed - 1); - note_new_gpnum(rsp, rdp); - - /* - * Because this CPU just now started the new grace period, we know - * that all of its callbacks will be covered by this upcoming grace - * period, even the ones that were registered arbitrarily recently. - * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL. - * - * Other CPUs cannot be sure exactly when the grace period started. - * Therefore, their recently registered callbacks must pass through - * an additional RCU_NEXT_READY stage, so that they will be handled - * by the next RCU grace period. - */ - rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; - rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; /* Special-case the common single-level case. */ if (NUM_RCU_NODES == 1) { rcu_preempt_check_blocked_tasks(rnp); rnp->qsmask = rnp->qsmaskinit; rnp->gpnum = rsp->gpnum; + rnp->completed = rsp->completed; rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */ + rcu_start_gp_per_cpu(rsp, rnp, rdp); spin_unlock_irqrestore(&rnp->lock, flags); return; } @@ -661,6 +726,9 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) rcu_preempt_check_blocked_tasks(rnp); rnp->qsmask = rnp->qsmaskinit; rnp->gpnum = rsp->gpnum; + rnp->completed = rsp->completed; + if (rnp == rdp->mynode) + rcu_start_gp_per_cpu(rsp, rnp, rdp); spin_unlock(&rnp->lock); /* irqs remain disabled. */ } @@ -672,34 +740,6 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) } /* - * Advance this CPU's callbacks, but only if the current grace period - * has ended. This may be called only from the CPU to whom the rdp - * belongs. - */ -static void -rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp) -{ - long completed_snap; - unsigned long flags; - - local_irq_save(flags); - completed_snap = ACCESS_ONCE(rsp->completed); /* outside of lock. */ - - /* Did another grace period end? */ - if (rdp->completed != completed_snap) { - - /* Advance callbacks. No harm if list empty. */ - rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL]; - rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL]; - rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; - - /* Remember that we saw this grace-period completion. */ - rdp->completed = completed_snap; - } - local_irq_restore(flags); -} - -/* * Clean up after the prior grace period and let rcu_start_gp() start up * the next grace period if one is needed. Note that the caller must * hold rnp->lock, as required by rcu_start_gp(), which will release it. @@ -710,7 +750,6 @@ static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags) WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); rsp->completed = rsp->gpnum; rsp->signaled = RCU_GP_IDLE; - rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]); rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */ } @@ -1144,6 +1183,7 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) long lastcomp; struct rcu_node *rnp = rcu_get_root(rsp); u8 signaled; + u8 forcenow; if (!rcu_gp_in_progress(rsp)) return; /* No grace period in progress, nothing to force. */ @@ -1180,16 +1220,23 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) if (rcu_process_dyntick(rsp, lastcomp, dyntick_save_progress_counter)) goto unlock_ret; + /* fall into next case. */ + + case RCU_SAVE_COMPLETED: /* Update state, record completion counter. */ + forcenow = 0; spin_lock(&rnp->lock); if (lastcomp == rsp->completed && - rsp->signaled == RCU_SAVE_DYNTICK) { + rsp->signaled == signaled) { rsp->signaled = RCU_FORCE_QS; dyntick_record_completed(rsp, lastcomp); + forcenow = signaled == RCU_SAVE_COMPLETED; } spin_unlock(&rnp->lock); - break; + if (!forcenow) + break; + /* fall into next case. */ case RCU_FORCE_QS: @@ -1544,21 +1591,16 @@ static void __cpuinit rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable) { unsigned long flags; - long lastcomp; unsigned long mask; struct rcu_data *rdp = rsp->rda[cpu]; struct rcu_node *rnp = rcu_get_root(rsp); /* Set up local state, ensuring consistent view of global state. */ spin_lock_irqsave(&rnp->lock, flags); - lastcomp = rsp->completed; - rdp->completed = lastcomp; - rdp->gpnum = lastcomp; rdp->passed_quiesc = 0; /* We could be racing with new GP, */ rdp->qs_pending = 1; /* so set up to respond to current GP. */ rdp->beenonline = 1; /* We have now been online. */ rdp->preemptable = preemptable; - rdp->passed_quiesc_completed = lastcomp - 1; rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; @@ -1580,6 +1622,11 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable) spin_lock(&rnp->lock); /* irqs already disabled. */ rnp->qsmaskinit |= mask; mask = rnp->grpmask; + if (rnp == rdp->mynode) { + rdp->gpnum = rnp->completed; /* if GP in progress... */ + rdp->completed = rnp->completed; + rdp->passed_quiesc_completed = rnp->completed - 1; + } spin_unlock(&rnp->lock); /* irqs already disabled. */ rnp = rnp->parent; } while (rnp != NULL && !(rnp->qsmaskinit & mask)); diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 1899023b0962..ddb79ece05eb 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -84,6 +84,9 @@ struct rcu_node { long gpnum; /* Current grace period for this node. */ /* This will either be equal to or one */ /* behind the root rcu_node's gpnum. */ + long completed; /* Last grace period completed for this node. */ + /* This will either be equal to or one */ + /* behind the root rcu_node's gpnum. */ unsigned long qsmask; /* CPUs or groups that need to switch in */ /* order for current grace period to proceed.*/ /* In leaf rcu_node, each bit corresponds to */ @@ -204,11 +207,12 @@ struct rcu_data { #define RCU_GP_IDLE 0 /* No grace period in progress. */ #define RCU_GP_INIT 1 /* Grace period being initialized. */ #define RCU_SAVE_DYNTICK 2 /* Need to scan dyntick state. */ -#define RCU_FORCE_QS 3 /* Need to force quiescent state. */ +#define RCU_SAVE_COMPLETED 3 /* Need to save rsp->completed. */ +#define RCU_FORCE_QS 4 /* Need to force quiescent state. */ #ifdef CONFIG_NO_HZ #define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK #else /* #ifdef CONFIG_NO_HZ */ -#define RCU_SIGNAL_INIT RCU_FORCE_QS +#define RCU_SIGNAL_INIT RCU_SAVE_COMPLETED #endif /* #else #ifdef CONFIG_NO_HZ */ #define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */ @@ -274,9 +278,8 @@ struct rcu_state { unsigned long jiffies_stall; /* Time at which to check */ /* for CPU stalls. */ #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ -#ifdef CONFIG_NO_HZ long dynticks_completed; /* Value of completed @ snap. */ -#endif /* #ifdef CONFIG_NO_HZ */ + /* Protected by fqslock. */ }; #ifdef RCU_TREE_NONCORE @@ -298,7 +301,7 @@ DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data); #else /* #ifdef RCU_TREE_NONCORE */ /* Forward declarations for rcutree_plugin.h */ -static inline void rcu_bootup_announce(void); +static void rcu_bootup_announce(void); long rcu_batches_completed(void); static void rcu_preempt_note_context_switch(int cpu); static int rcu_preempted_readers(struct rcu_node *rnp); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index ef2a58c2b9d5..c03edf766357 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -33,7 +33,7 @@ DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); /* * Tell them what RCU they are running. */ -static inline void rcu_bootup_announce(void) +static void rcu_bootup_announce(void) { printk(KERN_INFO "Experimental preemptable hierarchical RCU implementation.\n"); @@ -481,7 +481,7 @@ void exit_rcu(void) /* * Tell them what RCU they are running. */ -static inline void rcu_bootup_announce(void) +static void rcu_bootup_announce(void) { printk(KERN_INFO "Hierarchical RCU implementation.\n"); } diff --git a/kernel/sched.c b/kernel/sched.c index 117b2b4ebbaf..f297f4c2be50 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -591,6 +591,8 @@ struct rq { u64 rt_avg; u64 age_stamp; + u64 idle_stamp; + u64 avg_idle; #endif /* calc_load related fields */ @@ -814,6 +816,7 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32; * default: 0.25ms */ unsigned int sysctl_sched_shares_ratelimit = 250000; +unsigned int normalized_sysctl_sched_shares_ratelimit = 250000; /* * Inject some fuzzyness into changing the per-cpu group shares @@ -1810,6 +1813,7 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) #endif static void calc_load_account_active(struct rq *this_rq); +static void update_sysctl(void); #include "sched_stats.h" #include "sched_idletask.c" @@ -2034,6 +2038,9 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) { s64 delta; + if (p->sched_class != &fair_sched_class) + return 0; + /* * Buddy candidates are cache hot: */ @@ -2042,9 +2049,6 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) &p->se == cfs_rq_of(&p->se)->last)) return 1; - if (p->sched_class != &fair_sched_class) - return 0; - if (sysctl_sched_migration_cost == -1) return 1; if (sysctl_sched_migration_cost == 0) @@ -2440,6 +2444,17 @@ out_running: #ifdef CONFIG_SMP if (p->sched_class->task_wake_up) p->sched_class->task_wake_up(rq, p); + + if (unlikely(rq->idle_stamp)) { + u64 delta = rq->clock - rq->idle_stamp; + u64 max = 2*sysctl_sched_migration_cost; + + if (delta > max) + rq->avg_idle = max; + else + update_avg(&rq->avg_idle, delta); + rq->idle_stamp = 0; + } #endif out: task_rq_unlock(rq, &flags); @@ -4122,7 +4137,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, unsigned long flags; struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); - cpumask_setall(cpus); + cpumask_copy(cpus, cpu_active_mask); /* * When power savings policy is enabled for the parent domain, idle @@ -4285,7 +4300,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd) int all_pinned = 0; struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); - cpumask_setall(cpus); + cpumask_copy(cpus, cpu_active_mask); /* * When power savings policy is enabled for the parent domain, idle @@ -4425,6 +4440,11 @@ static void idle_balance(int this_cpu, struct rq *this_rq) int pulled_task = 0; unsigned long next_balance = jiffies + HZ; + this_rq->idle_stamp = this_rq->clock; + + if (this_rq->avg_idle < sysctl_sched_migration_cost) + return; + for_each_domain(this_cpu, sd) { unsigned long interval; @@ -4439,8 +4459,10 @@ static void idle_balance(int this_cpu, struct rq *this_rq) interval = msecs_to_jiffies(sd->balance_interval); if (time_after(next_balance, sd->last_balance + interval)) next_balance = sd->last_balance + interval; - if (pulled_task) + if (pulled_task) { + this_rq->idle_stamp = 0; break; + } } if (pulled_task || time_after(jiffies, this_rq->next_balance)) { /* @@ -4675,7 +4697,7 @@ int select_nohz_load_balancer(int stop_tick) cpumask_set_cpu(cpu, nohz.cpu_mask); /* time for ilb owner also to sleep */ - if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { + if (cpumask_weight(nohz.cpu_mask) == num_active_cpus()) { if (atomic_read(&nohz.load_balancer) == cpu) atomic_set(&nohz.load_balancer, -1); return 0; @@ -6998,22 +7020,23 @@ cpumask_var_t nohz_cpu_mask; * * This idea comes from the SD scheduler of Con Kolivas: */ -static inline void sched_init_granularity(void) +static void update_sysctl(void) { - unsigned int factor = 1 + ilog2(num_online_cpus()); - const unsigned long limit = 200000000; + unsigned int cpus = min(num_online_cpus(), 8U); + unsigned int factor = 1 + ilog2(cpus); - sysctl_sched_min_granularity *= factor; - if (sysctl_sched_min_granularity > limit) - sysctl_sched_min_granularity = limit; - - sysctl_sched_latency *= factor; - if (sysctl_sched_latency > limit) - sysctl_sched_latency = limit; - - sysctl_sched_wakeup_granularity *= factor; +#define SET_SYSCTL(name) \ + (sysctl_##name = (factor) * normalized_sysctl_##name) + SET_SYSCTL(sched_min_granularity); + SET_SYSCTL(sched_latency); + SET_SYSCTL(sched_wakeup_granularity); + SET_SYSCTL(sched_shares_ratelimit); +#undef SET_SYSCTL +} - sysctl_sched_shares_ratelimit *= factor; +static inline void sched_init_granularity(void) +{ + update_sysctl(); } #ifdef CONFIG_SMP @@ -7050,7 +7073,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) int ret = 0; rq = task_rq_lock(p, &flags); - if (!cpumask_intersects(new_mask, cpu_online_mask)) { + if (!cpumask_intersects(new_mask, cpu_active_mask)) { ret = -EINVAL; goto out; } @@ -7072,7 +7095,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) if (cpumask_test_cpu(task_cpu(p), new_mask)) goto out; - if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) { + if (migrate_task(p, cpumask_any_and(cpu_active_mask, new_mask), &req)) { /* Need help from migration thread: drop lock and wait. */ struct task_struct *mt = rq->migration_thread; @@ -7226,19 +7249,19 @@ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) again: /* Look for allowed, online CPU in same node. */ - for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask) + for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask) if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) goto move; /* Any allowed, online CPU? */ - dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask); + dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask); if (dest_cpu < nr_cpu_ids) goto move; /* No more Mr. Nice Guy. */ if (dest_cpu >= nr_cpu_ids) { cpuset_cpus_allowed_locked(p, &p->cpus_allowed); - dest_cpu = cpumask_any_and(cpu_online_mask, &p->cpus_allowed); + dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed); /* * Don't tell them about moving exiting tasks or @@ -7267,7 +7290,7 @@ move: */ static void migrate_nr_uninterruptible(struct rq *rq_src) { - struct rq *rq_dest = cpu_rq(cpumask_any(cpu_online_mask)); + struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask)); unsigned long flags; local_irq_save(flags); @@ -7521,7 +7544,7 @@ static ctl_table *sd_alloc_ctl_cpu_table(int cpu) static struct ctl_table_header *sd_sysctl_header; static void register_sched_domain_sysctl(void) { - int i, cpu_num = num_online_cpus(); + int i, cpu_num = num_possible_cpus(); struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); char buf[32]; @@ -7531,7 +7554,7 @@ static void register_sched_domain_sysctl(void) if (entry == NULL) return; - for_each_online_cpu(i) { + for_each_possible_cpu(i) { snprintf(buf, 32, "cpu%d", i); entry->procname = kstrdup(buf, GFP_KERNEL); entry->mode = 0555; @@ -7899,6 +7922,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) static void free_rootdomain(struct root_domain *rd) { + synchronize_sched(); + cpupri_cleanup(&rd->cpupri); free_cpumask_var(rd->rto_mask); @@ -8039,6 +8064,7 @@ static cpumask_var_t cpu_isolated_map; /* Setup the mask of cpus configured for isolated domains */ static int __init isolated_cpu_setup(char *str) { + alloc_bootmem_cpumask_var(&cpu_isolated_map); cpulist_parse(str, cpu_isolated_map); return 1; } @@ -9016,7 +9042,7 @@ match1: if (doms_new == NULL) { ndoms_cur = 0; doms_new = fallback_doms; - cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map); + cpumask_andnot(&doms_new[0], cpu_active_mask, cpu_isolated_map); WARN_ON_ONCE(dattr_new); } @@ -9147,8 +9173,10 @@ static int update_sched_domains(struct notifier_block *nfb, switch (action) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: - case CPU_DEAD: - case CPU_DEAD_FROZEN: + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + case CPU_DOWN_FAILED: + case CPU_DOWN_FAILED_FROZEN: partition_sched_domains(1, NULL, NULL); return NOTIFY_OK; @@ -9195,7 +9223,7 @@ void __init sched_init_smp(void) #endif get_online_cpus(); mutex_lock(&sched_domains_mutex); - arch_init_sched_domains(cpu_online_mask); + arch_init_sched_domains(cpu_active_mask); cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); if (cpumask_empty(non_isolated_cpus)) cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); @@ -9516,6 +9544,8 @@ void __init sched_init(void) rq->cpu = i; rq->online = 0; rq->migration_thread = NULL; + rq->idle_stamp = 0; + rq->avg_idle = 2*sysctl_sched_migration_cost; INIT_LIST_HEAD(&rq->migration_queue); rq_attach_root(rq, &def_root_domain); #endif @@ -9565,7 +9595,9 @@ void __init sched_init(void) zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT); alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT); #endif - zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); + /* May be allocated at isolcpus cmdline parse time */ + if (cpu_isolated_map == NULL) + zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); #endif /* SMP */ perf_event_init(); diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index 479ce5682d7c..5b496132c28a 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -236,6 +236,18 @@ void sched_clock_idle_wakeup_event(u64 delta_ns) } EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); +unsigned long long cpu_clock(int cpu) +{ + unsigned long long clock; + unsigned long flags; + + local_irq_save(flags); + clock = sched_clock_cpu(cpu); + local_irq_restore(flags); + + return clock; +} + #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ void sched_clock_init(void) @@ -251,17 +263,12 @@ u64 sched_clock_cpu(int cpu) return sched_clock(); } -#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ unsigned long long cpu_clock(int cpu) { - unsigned long long clock; - unsigned long flags; + return sched_clock_cpu(cpu); +} - local_irq_save(flags); - clock = sched_clock_cpu(cpu); - local_irq_restore(flags); +#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ - return clock; -} EXPORT_SYMBOL_GPL(cpu_clock); diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index efb84409bc43..6988cf08f705 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -285,12 +285,16 @@ static void print_cpu(struct seq_file *m, int cpu) #ifdef CONFIG_SCHEDSTATS #define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); +#define P64(n) SEQ_printf(m, " .%-30s: %Ld\n", #n, rq->n); P(yld_count); P(sched_switch); P(sched_count); P(sched_goidle); +#ifdef CONFIG_SMP + P64(avg_idle); +#endif P(ttwu_count); P(ttwu_local); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 37087a7fac22..d80812d39d62 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -35,12 +35,14 @@ * run vmstat and monitor the context-switches (cs) field) */ unsigned int sysctl_sched_latency = 5000000ULL; +unsigned int normalized_sysctl_sched_latency = 5000000ULL; /* * Minimal preemption granularity for CPU-bound tasks: * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds) */ unsigned int sysctl_sched_min_granularity = 1000000ULL; +unsigned int normalized_sysctl_sched_min_granularity = 1000000ULL; /* * is kept at sysctl_sched_latency / sysctl_sched_min_granularity @@ -70,6 +72,7 @@ unsigned int __read_mostly sysctl_sched_compat_yield; * have immediate wakeup/sleep latencies. */ unsigned int sysctl_sched_wakeup_granularity = 1000000UL; +unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; const_debug unsigned int sysctl_sched_migration_cost = 500000UL; @@ -1374,6 +1377,9 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag rcu_read_lock(); for_each_domain(cpu, tmp) { + if (!(tmp->flags & SD_LOAD_BALANCE)) + continue; + /* * If power savings logic is enabled for a domain, see if we * are not overloaded, if so, don't balance wider. @@ -1398,11 +1404,38 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag want_sd = 0; } - if (want_affine && (tmp->flags & SD_WAKE_AFFINE) && - cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) { + if (want_affine && (tmp->flags & SD_WAKE_AFFINE)) { + int candidate = -1, i; + + if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) + candidate = cpu; + + /* + * Check for an idle shared cache. + */ + if (tmp->flags & SD_PREFER_SIBLING) { + if (candidate == cpu) { + if (!cpu_rq(prev_cpu)->cfs.nr_running) + candidate = prev_cpu; + } + + if (candidate == -1 || candidate == cpu) { + for_each_cpu(i, sched_domain_span(tmp)) { + if (!cpumask_test_cpu(i, &p->cpus_allowed)) + continue; + if (!cpu_rq(i)->cfs.nr_running) { + candidate = i; + break; + } + } + } + } - affine_sd = tmp; - want_affine = 0; + if (candidate >= 0) { + affine_sd = tmp; + want_affine = 0; + cpu = candidate; + } } if (!want_sd && !want_affine) @@ -1850,6 +1883,17 @@ move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, return 0; } + +static void rq_online_fair(struct rq *rq) +{ + update_sysctl(); +} + +static void rq_offline_fair(struct rq *rq) +{ + update_sysctl(); +} + #endif /* CONFIG_SMP */ /* @@ -1997,6 +2041,8 @@ static const struct sched_class fair_sched_class = { .load_balance = load_balance_fair, .move_one_task = move_one_task_fair, + .rq_online = rq_online_fair, + .rq_offline = rq_offline_fair, #endif .set_curr_task = set_curr_task_fair, diff --git a/kernel/signal.c b/kernel/signal.c index 6705320784fd..4d0658dda0e5 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -939,7 +939,8 @@ static void print_fatal_signal(struct pt_regs *regs, int signr) for (i = 0; i < 16; i++) { unsigned char insn; - __get_user(insn, (unsigned char *)(regs->ip + i)); + if (get_user(insn, (unsigned char *)(regs->ip + i))) + break; printk("%02x ", insn); } } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 79d527a99561..771ac48f1652 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1354,6 +1354,7 @@ static struct ctl_table vm_table[] = { .strategy = &sysctl_jiffies, }, #endif +#ifdef CONFIG_MMU { .ctl_name = CTL_UNNUMBERED, .procname = "mmap_min_addr", @@ -1362,6 +1363,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &mmap_min_addr_handler, }, +#endif #ifdef CONFIG_NUMA { .ctl_name = CTL_UNNUMBERED, @@ -1614,7 +1616,8 @@ static struct ctl_table debug_table[] = { .data = &show_unhandled_signals, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, }, #endif { .ctl_name = 0 } diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index b6e7aaea4604..469193ccf5b7 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -220,6 +220,7 @@ static const struct trans_ctl_table trans_net_ipv4_conf_vars_table[] = { { NET_IPV4_CONF_PROMOTE_SECONDARIES, "promote_secondaries" }, { NET_IPV4_CONF_ARP_ACCEPT, "arp_accept" }, { NET_IPV4_CONF_ARP_NOTIFY, "arp_notify" }, + { NET_IPV4_CONF_SRC_VMARK, "src_valid_mark" }, {} }; diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 620b58abdc32..0d809ae02d60 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -20,6 +20,8 @@ #include <linux/sysdev.h> #include <linux/tick.h> +#include "tick-internal.h" + /* The registered clock event devices */ static LIST_HEAD(clockevent_devices); static LIST_HEAD(clockevents_released); @@ -237,8 +239,9 @@ void clockevents_exchange_device(struct clock_event_device *old, */ void clockevents_notify(unsigned long reason, void *arg) { - struct list_head *node, *tmp; + struct clock_event_device *dev, *tmp; unsigned long flags; + int cpu; spin_lock_irqsave(&clockevents_lock, flags); clockevents_do_notify(reason, arg); @@ -249,8 +252,20 @@ void clockevents_notify(unsigned long reason, void *arg) * Unregister the clock event devices which were * released from the users in the notify chain. */ - list_for_each_safe(node, tmp, &clockevents_released) - list_del(node); + list_for_each_entry_safe(dev, tmp, &clockevents_released, list) + list_del(&dev->list); + /* + * Now check whether the CPU has left unused per cpu devices + */ + cpu = *((int *)arg); + list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) { + if (cpumask_test_cpu(cpu, dev->cpumask) && + cpumask_weight(dev->cpumask) == 1 && + !tick_is_broadcast_device(dev)) { + BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); + list_del(&dev->list); + } + } break; default: break; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 5e18c6ab2c6a..ecc7adbf0918 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -413,6 +413,47 @@ void clocksource_touch_watchdog(void) clocksource_resume_watchdog(); } +/** + * clocksource_max_deferment - Returns max time the clocksource can be deferred + * @cs: Pointer to clocksource + * + */ +static u64 clocksource_max_deferment(struct clocksource *cs) +{ + u64 max_nsecs, max_cycles; + + /* + * Calculate the maximum number of cycles that we can pass to the + * cyc2ns function without overflowing a 64-bit signed result. The + * maximum number of cycles is equal to ULLONG_MAX/cs->mult which + * is equivalent to the below. + * max_cycles < (2^63)/cs->mult + * max_cycles < 2^(log2((2^63)/cs->mult)) + * max_cycles < 2^(log2(2^63) - log2(cs->mult)) + * max_cycles < 2^(63 - log2(cs->mult)) + * max_cycles < 1 << (63 - log2(cs->mult)) + * Please note that we add 1 to the result of the log2 to account for + * any rounding errors, ensure the above inequality is satisfied and + * no overflow will occur. + */ + max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1)); + + /* + * The actual maximum number of cycles we can defer the clocksource is + * determined by the minimum of max_cycles and cs->mask. + */ + max_cycles = min_t(u64, max_cycles, (u64) cs->mask); + max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift); + + /* + * To ensure that the clocksource does not wrap whilst we are idle, + * limit the time the clocksource can be deferred by 12.5%. Please + * note a margin of 12.5% is used because this can be computed with + * a shift, versus say 10% which would require division. + */ + return max_nsecs - (max_nsecs >> 5); +} + #ifdef CONFIG_GENERIC_TIME /** @@ -511,6 +552,9 @@ static void clocksource_enqueue(struct clocksource *cs) */ int clocksource_register(struct clocksource *cs) { + /* calculate max idle time permitted for this clocksource */ + cs->max_idle_ns = clocksource_max_deferment(cs); + mutex_lock(&clocksource_mutex); clocksource_enqueue(cs); clocksource_select(); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 89aed5933ed4..44320b1e2a6c 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -216,6 +216,7 @@ void tick_nohz_stop_sched_tick(int inidle) struct tick_sched *ts; ktime_t last_update, expires, now; struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev; + u64 time_delta; int cpu; local_irq_save(flags); @@ -275,6 +276,17 @@ void tick_nohz_stop_sched_tick(int inidle) seq = read_seqbegin(&xtime_lock); last_update = last_jiffies_update; last_jiffies = jiffies; + + /* + * On SMP we really should only care for the CPU which + * has the do_timer duty assigned. All other CPUs can + * sleep as long as they want. + */ + if (cpu == tick_do_timer_cpu || + tick_do_timer_cpu == TICK_DO_TIMER_NONE) + time_delta = timekeeping_max_deferment(); + else + time_delta = KTIME_MAX; } while (read_seqretry(&xtime_lock, seq)); /* Get the next timer wheel timer */ @@ -294,11 +306,26 @@ void tick_nohz_stop_sched_tick(int inidle) if ((long)delta_jiffies >= 1) { /* - * calculate the expiry time for the next timer wheel - * timer - */ - expires = ktime_add_ns(last_update, tick_period.tv64 * - delta_jiffies); + * calculate the expiry time for the next timer wheel + * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals + * that there is no timer pending or at least extremely + * far into the future (12 days for HZ=1000). In this + * case we set the expiry to the end of time. + */ + if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) { + /* + * Calculate the time delta for the next timer event. + * If the time delta exceeds the maximum time delta + * permitted by the current clocksource then adjust + * the time delta accordingly to ensure the + * clocksource does not wrap. + */ + time_delta = min_t(u64, time_delta, + tick_period.tv64 * delta_jiffies); + expires = ktime_add_ns(last_update, time_delta); + } else { + expires.tv64 = KTIME_MAX; + } /* * If this cpu is the one which updates jiffies, then @@ -342,22 +369,19 @@ void tick_nohz_stop_sched_tick(int inidle) ts->idle_sleeps++; + /* Mark expires */ + ts->idle_expires = expires; + /* - * delta_jiffies >= NEXT_TIMER_MAX_DELTA signals that - * there is no timer pending or at least extremly far - * into the future (12 days for HZ=1000). In this case - * we simply stop the tick timer: + * If the expiration time == KTIME_MAX, then + * in this case we simply stop the tick timer. */ - if (unlikely(delta_jiffies >= NEXT_TIMER_MAX_DELTA)) { - ts->idle_expires.tv64 = KTIME_MAX; + if (unlikely(expires.tv64 == KTIME_MAX)) { if (ts->nohz_mode == NOHZ_MODE_HIGHRES) hrtimer_cancel(&ts->sched_timer); goto out; } - /* Mark expiries */ - ts->idle_expires = expires; - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { hrtimer_start(&ts->sched_timer, expires, HRTIMER_MODE_ABS_PINNED); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index c3a4e2907eaa..8b709dee8e34 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -488,6 +488,17 @@ int timekeeping_valid_for_hres(void) } /** + * timekeeping_max_deferment - Returns max time the clocksource can be deferred + * + * Caller must observe xtime_lock via read_seqbegin/read_seqretry to + * ensure that the clocksource does not change! + */ +u64 timekeeping_max_deferment(void) +{ + return timekeeper.clock->max_idle_ns; +} + +/** * read_persistent_clock - Return time from the persistent clock. * * Weak dummy function for arches that do not yet support it. @@ -834,6 +845,7 @@ void getboottime(struct timespec *ts) set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec); } +EXPORT_SYMBOL_GPL(getboottime); /** * monotonic_to_bootbased - Convert the monotonic time to boot based. @@ -843,6 +855,7 @@ void monotonic_to_bootbased(struct timespec *ts) { *ts = timespec_add_safe(*ts, total_sleep_time); } +EXPORT_SYMBOL_GPL(monotonic_to_bootbased); unsigned long get_seconds(void) { |