diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/audit_tree.c | 48 | ||||
-rw-r--r-- | kernel/fork.c | 2 | ||||
-rw-r--r-- | kernel/futex.c | 11 | ||||
-rw-r--r-- | kernel/hrtimer.c | 206 | ||||
-rw-r--r-- | kernel/irq/chip.c | 3 | ||||
-rw-r--r-- | kernel/module.c | 284 | ||||
-rw-r--r-- | kernel/panic.c | 17 | ||||
-rw-r--r-- | kernel/params.c | 274 | ||||
-rw-r--r-- | kernel/posix-timers.c | 10 | ||||
-rw-r--r-- | kernel/power/disk.c | 2 | ||||
-rw-r--r-- | kernel/power/power.h | 2 | ||||
-rw-r--r-- | kernel/power/swap.c | 14 | ||||
-rw-r--r-- | kernel/rcupdate.c | 19 | ||||
-rw-r--r-- | kernel/rtmutex.c | 3 | ||||
-rw-r--r-- | kernel/sched.c | 58 | ||||
-rw-r--r-- | kernel/sched_fair.c | 62 | ||||
-rw-r--r-- | kernel/sched_features.h | 2 | ||||
-rw-r--r-- | kernel/sched_stats.h | 2 | ||||
-rw-r--r-- | kernel/stop_machine.c | 120 | ||||
-rw-r--r-- | kernel/sys.c | 10 | ||||
-rw-r--r-- | kernel/sysctl.c | 10 | ||||
-rw-r--r-- | kernel/time.c | 18 | ||||
-rw-r--r-- | kernel/time/ntp.c | 3 | ||||
-rw-r--r-- | kernel/time/tick-sched.c | 35 | ||||
-rw-r--r-- | kernel/time/timer_list.c | 8 | ||||
-rw-r--r-- | kernel/workqueue.c | 7 |
26 files changed, 706 insertions, 524 deletions
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index f7921a2..8ba0e0d 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -532,7 +532,7 @@ void audit_trim_trees(void) list_add(&cursor, &tree_list); while (cursor.next != &tree_list) { struct audit_tree *tree; - struct nameidata nd; + struct path path; struct vfsmount *root_mnt; struct node *node; struct list_head list; @@ -544,12 +544,12 @@ void audit_trim_trees(void) list_add(&cursor, &tree->list); mutex_unlock(&audit_filter_mutex); - err = path_lookup(tree->pathname, 0, &nd); + err = kern_path(tree->pathname, 0, &path); if (err) goto skip_it; - root_mnt = collect_mounts(nd.path.mnt, nd.path.dentry); - path_put(&nd.path); + root_mnt = collect_mounts(path.mnt, path.dentry); + path_put(&path); if (!root_mnt) goto skip_it; @@ -580,19 +580,19 @@ skip_it: } static int is_under(struct vfsmount *mnt, struct dentry *dentry, - struct nameidata *nd) + struct path *path) { - if (mnt != nd->path.mnt) { + if (mnt != path->mnt) { for (;;) { if (mnt->mnt_parent == mnt) return 0; - if (mnt->mnt_parent == nd->path.mnt) + if (mnt->mnt_parent == path->mnt) break; mnt = mnt->mnt_parent; } dentry = mnt->mnt_mountpoint; } - return is_subdir(dentry, nd->path.dentry); + return is_subdir(dentry, path->dentry); } int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op) @@ -618,7 +618,7 @@ void audit_put_tree(struct audit_tree *tree) int audit_add_tree_rule(struct audit_krule *rule) { struct audit_tree *seed = rule->tree, *tree; - struct nameidata nd; + struct path path; struct vfsmount *mnt, *p; struct list_head list; int err; @@ -637,11 +637,11 @@ int audit_add_tree_rule(struct audit_krule *rule) /* do not set rule->tree yet */ mutex_unlock(&audit_filter_mutex); - err = path_lookup(tree->pathname, 0, &nd); + err = kern_path(tree->pathname, 0, &path); if (err) goto Err; - mnt = collect_mounts(nd.path.mnt, nd.path.dentry); - path_put(&nd.path); + mnt = collect_mounts(path.mnt, path.dentry); + path_put(&path); if (!mnt) { err = -ENOMEM; goto Err; @@ -690,29 +690,29 @@ int audit_tag_tree(char *old, char *new) { struct list_head cursor, barrier; int failed = 0; - struct nameidata nd; + struct path path; struct vfsmount *tagged; struct list_head list; struct vfsmount *mnt; struct dentry *dentry; int err; - err = path_lookup(new, 0, &nd); + err = kern_path(new, 0, &path); if (err) return err; - tagged = collect_mounts(nd.path.mnt, nd.path.dentry); - path_put(&nd.path); + tagged = collect_mounts(path.mnt, path.dentry); + path_put(&path); if (!tagged) return -ENOMEM; - err = path_lookup(old, 0, &nd); + err = kern_path(old, 0, &path); if (err) { drop_collected_mounts(tagged); return err; } - mnt = mntget(nd.path.mnt); - dentry = dget(nd.path.dentry); - path_put(&nd.path); + mnt = mntget(path.mnt); + dentry = dget(path.dentry); + path_put(&path); if (dentry == tagged->mnt_root && dentry == mnt->mnt_root) follow_up(&mnt, &dentry); @@ -733,7 +733,7 @@ int audit_tag_tree(char *old, char *new) list_add(&cursor, &tree->list); mutex_unlock(&audit_filter_mutex); - err = path_lookup(tree->pathname, 0, &nd); + err = kern_path(tree->pathname, 0, &path); if (err) { put_tree(tree); mutex_lock(&audit_filter_mutex); @@ -741,15 +741,15 @@ int audit_tag_tree(char *old, char *new) } spin_lock(&vfsmount_lock); - if (!is_under(mnt, dentry, &nd)) { + if (!is_under(mnt, dentry, &path)) { spin_unlock(&vfsmount_lock); - path_put(&nd.path); + path_put(&path); put_tree(tree); mutex_lock(&audit_filter_mutex); continue; } spin_unlock(&vfsmount_lock); - path_put(&nd.path); + path_put(&path); list_for_each_entry(p, &list, mnt_list) { failed = tag_chunk(p->mnt_root->d_inode, tree); diff --git a/kernel/fork.c b/kernel/fork.c index 4d09355..f608356 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1018,6 +1018,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->prev_utime = cputime_zero; p->prev_stime = cputime_zero; + p->default_timer_slack_ns = current->timer_slack_ns; + #ifdef CONFIG_DETECT_SOFTLOCKUP p->last_switch_count = 0; p->last_switch_timestamp = 0; diff --git a/kernel/futex.c b/kernel/futex.c index 7d1136e..8af1002 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1296,13 +1296,16 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, if (!abs_time) schedule(); else { + unsigned long slack; + slack = current->timer_slack_ns; + if (rt_task(current)) + slack = 0; hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); hrtimer_init_sleeper(&t, current); - t.timer.expires = *abs_time; + hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack); - hrtimer_start(&t.timer, t.timer.expires, - HRTIMER_MODE_ABS); + hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS); if (!hrtimer_active(&t.timer)) t.task = NULL; @@ -1404,7 +1407,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); hrtimer_init_sleeper(to, current); - to->timer.expires = *time; + hrtimer_set_expires(&to->timer, *time); } q.pi_state = NULL; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 95978f4..2b465df 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -517,7 +517,7 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base) if (!base->first) continue; timer = rb_entry(base->first, struct hrtimer, node); - expires = ktime_sub(timer->expires, base->offset); + expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires.tv64 < cpu_base->expires_next.tv64) cpu_base->expires_next = expires; } @@ -539,10 +539,10 @@ static int hrtimer_reprogram(struct hrtimer *timer, struct hrtimer_clock_base *base) { ktime_t *expires_next = &__get_cpu_var(hrtimer_bases).expires_next; - ktime_t expires = ktime_sub(timer->expires, base->offset); + ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); int res; - WARN_ON_ONCE(timer->expires.tv64 < 0); + WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0); /* * When the callback is running, we do not reprogram the clock event @@ -795,7 +795,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) u64 orun = 1; ktime_t delta; - delta = ktime_sub(now, timer->expires); + delta = ktime_sub(now, hrtimer_get_expires(timer)); if (delta.tv64 < 0) return 0; @@ -807,8 +807,8 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) s64 incr = ktime_to_ns(interval); orun = ktime_divns(delta, incr); - timer->expires = ktime_add_ns(timer->expires, incr * orun); - if (timer->expires.tv64 > now.tv64) + hrtimer_add_expires_ns(timer, incr * orun); + if (hrtimer_get_expires_tv64(timer) > now.tv64) return orun; /* * This (and the ktime_add() below) is the @@ -816,7 +816,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) */ orun++; } - timer->expires = ktime_add_safe(timer->expires, interval); + hrtimer_add_expires(timer, interval); return orun; } @@ -848,7 +848,8 @@ static void enqueue_hrtimer(struct hrtimer *timer, * We dont care about collisions. Nodes with * the same expiry time stay together. */ - if (timer->expires.tv64 < entry->expires.tv64) { + if (hrtimer_get_expires_tv64(timer) < + hrtimer_get_expires_tv64(entry)) { link = &(*link)->rb_left; } else { link = &(*link)->rb_right; @@ -945,9 +946,10 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base) } /** - * hrtimer_start - (re)start an relative timer on the current CPU + * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU * @timer: the timer to be added * @tim: expiry time + * @delta_ns: "slack" range for the timer * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL) * * Returns: @@ -955,7 +957,8 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base) * 1 when the timer was active */ int -hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) +hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_ns, + const enum hrtimer_mode mode) { struct hrtimer_clock_base *base, *new_base; unsigned long flags; @@ -983,7 +986,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) #endif } - timer->expires = tim; + hrtimer_set_expires_range_ns(timer, tim, delta_ns); timer_stats_hrtimer_set_start_info(timer); @@ -1016,8 +1019,26 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) return ret; } +EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); + +/** + * hrtimer_start - (re)start an hrtimer on the current CPU + * @timer: the timer to be added + * @tim: expiry time + * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL) + * + * Returns: + * 0 on success + * 1 when the timer was active + */ +int +hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) +{ + return hrtimer_start_range_ns(timer, tim, 0, mode); +} EXPORT_SYMBOL_GPL(hrtimer_start); + /** * hrtimer_try_to_cancel - try to deactivate a timer * @timer: hrtimer to stop @@ -1077,7 +1098,7 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer) ktime_t rem; base = lock_hrtimer_base(timer, &flags); - rem = ktime_sub(timer->expires, base->get_time()); + rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; @@ -1109,7 +1130,7 @@ ktime_t hrtimer_get_next_event(void) continue; timer = rb_entry(base->first, struct hrtimer, node); - delta.tv64 = timer->expires.tv64; + delta.tv64 = hrtimer_get_expires_tv64(timer); delta = ktime_sub(delta, base->get_time()); if (delta.tv64 < mindelta.tv64) mindelta.tv64 = delta.tv64; @@ -1310,10 +1331,23 @@ void hrtimer_interrupt(struct clock_event_device *dev) timer = rb_entry(node, struct hrtimer, node); - if (basenow.tv64 < timer->expires.tv64) { + /* + * The immediate goal for using the softexpires is + * minimizing wakeups, not running timers at the + * earliest interrupt after their soft expiration. + * This allows us to avoid using a Priority Search + * Tree, which can answer a stabbing querry for + * overlapping intervals and instead use the simple + * BST we already have. + * We don't add extra wakeups by delaying timers that + * are right-of a not yet expired timer, because that + * timer will have to trigger a wakeup anyway. + */ + + if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) { ktime_t expires; - expires = ktime_sub(timer->expires, + expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires.tv64 < expires_next.tv64) expires_next = expires; @@ -1349,6 +1383,30 @@ void hrtimer_interrupt(struct clock_event_device *dev) raise_softirq(HRTIMER_SOFTIRQ); } +/** + * hrtimer_peek_ahead_timers -- run soft-expired timers now + * + * hrtimer_peek_ahead_timers will peek at the timer queue of + * the current cpu and check if there are any timers for which + * the soft expires time has passed. If any such timers exist, + * they are run immediately and then removed from the timer queue. + * + */ +void hrtimer_peek_ahead_timers(void) +{ + struct tick_device *td; + unsigned long flags; + + if (!hrtimer_hres_active()) + return; + + local_irq_save(flags); + td = &__get_cpu_var(tick_cpu_device); + if (td && td->evtdev) + hrtimer_interrupt(td->evtdev); + local_irq_restore(flags); +} + static void run_hrtimer_softirq(struct softirq_action *h) { run_hrtimer_pending(&__get_cpu_var(hrtimer_bases)); @@ -1414,7 +1472,8 @@ void hrtimer_run_queues(void) struct hrtimer *timer; timer = rb_entry(node, struct hrtimer, node); - if (base->softirq_time.tv64 <= timer->expires.tv64) + if (base->softirq_time.tv64 <= + hrtimer_get_expires_tv64(timer)) break; if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) { @@ -1462,7 +1521,7 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod do { set_current_state(TASK_INTERRUPTIBLE); - hrtimer_start(&t->timer, t->timer.expires, mode); + hrtimer_start_expires(&t->timer, mode); if (!hrtimer_active(&t->timer)) t->task = NULL; @@ -1484,7 +1543,7 @@ static int update_rmtp(struct hrtimer *timer, struct timespec __user *rmtp) struct timespec rmt; ktime_t rem; - rem = ktime_sub(timer->expires, timer->base->get_time()); + rem = hrtimer_expires_remaining(timer); if (rem.tv64 <= 0) return 0; rmt = ktime_to_timespec(rem); @@ -1503,7 +1562,7 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart) hrtimer_init_on_stack(&t.timer, restart->nanosleep.index, HRTIMER_MODE_ABS); - t.timer.expires.tv64 = restart->nanosleep.expires; + hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); if (do_nanosleep(&t, HRTIMER_MODE_ABS)) goto out; @@ -1528,9 +1587,14 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; + unsigned long slack; + + slack = current->timer_slack_ns; + if (rt_task(current)) + slack = 0; hrtimer_init_on_stack(&t.timer, clockid, mode); - t.timer.expires = timespec_to_ktime(*rqtp); + hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack); if (do_nanosleep(&t, mode)) goto out; @@ -1550,7 +1614,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, restart->fn = hrtimer_nanosleep_restart; restart->nanosleep.index = t.timer.base->index; restart->nanosleep.rmtp = rmtp; - restart->nanosleep.expires = t.timer.expires.tv64; + restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); ret = -ERESTART_RESTARTBLOCK; out: @@ -1752,3 +1816,103 @@ void __init hrtimers_init(void) #endif } +/** + * schedule_hrtimeout_range - sleep until timeout + * @expires: timeout value (ktime_t) + * @delta: slack in expires timeout (ktime_t) + * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL + * + * Make the current task sleep until the given expiry time has + * elapsed. The routine will return immediately unless + * the current task state has been set (see set_current_state()). + * + * The @delta argument gives the kernel the freedom to schedule the + * actual wakeup to a time that is both power and performance friendly. + * The kernel give the normal best effort behavior for "@expires+@delta", + * but may decide to fire the timer earlier, but no earlier than @expires. + * + * You can set the task state as follows - + * + * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to + * pass before the routine returns. + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task. + * + * The current task state is guaranteed to be TASK_RUNNING when this + * routine returns. + * + * Returns 0 when the timer has expired otherwise -EINTR + */ +int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta, + const enum hrtimer_mode mode) +{ + struct hrtimer_sleeper t; + + /* + * Optimize when a zero timeout value is given. It does not + * matter whether this is an absolute or a relative time. + */ + if (expires && !expires->tv64) { + __set_current_state(TASK_RUNNING); + return 0; + } + + /* + * A NULL parameter means "inifinte" + */ + if (!expires) { + schedule(); + __set_current_state(TASK_RUNNING); + return -EINTR; + } + + hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode); + hrtimer_set_expires_range_ns(&t.timer, *expires, delta); + + hrtimer_init_sleeper(&t, current); + + hrtimer_start_expires(&t.timer, mode); + if (!hrtimer_active(&t.timer)) + t.task = NULL; + + if (likely(t.task)) + schedule(); + + hrtimer_cancel(&t.timer); + destroy_hrtimer_on_stack(&t.timer); + + __set_current_state(TASK_RUNNING); + + return !t.task ? 0 : -EINTR; +} +EXPORT_SYMBOL_GPL(schedule_hrtimeout_range); + +/** + * schedule_hrtimeout - sleep until timeout + * @expires: timeout value (ktime_t) + * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL + * + * Make the current task sleep until the given expiry time has + * elapsed. The routine will return immediately unless + * the current task state has been set (see set_current_state()). + * + * You can set the task state as follows - + * + * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to + * pass before the routine returns. + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task. + * + * The current task state is guaranteed to be TASK_RUNNING when this + * routine returns. + * + * Returns 0 when the timer has expired otherwise -EINTR + */ +int __sched schedule_hrtimeout(ktime_t *expires, + const enum hrtimer_mode mode) +{ + return schedule_hrtimeout_range(expires, 0, mode); +} +EXPORT_SYMBOL_GPL(schedule_hrtimeout); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 4895fde..10b5092 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -76,6 +76,7 @@ void dynamic_irq_cleanup(unsigned int irq) desc->chip_data = NULL; desc->handle_irq = handle_bad_irq; desc->chip = &no_irq_chip; + desc->name = NULL; spin_unlock_irqrestore(&desc->lock, flags); } @@ -127,7 +128,7 @@ int set_irq_type(unsigned int irq, unsigned int type) return 0; spin_lock_irqsave(&desc->lock, flags); - ret = __irq_set_trigger(desc, irq, flags); + ret = __irq_set_trigger(desc, irq, type); spin_unlock_irqrestore(&desc->lock, flags); return ret; } diff --git a/kernel/module.c b/kernel/module.c index 6fded84..1f4cc00 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -44,6 +44,7 @@ #include <linux/string.h> #include <linux/mutex.h> #include <linux/unwind.h> +#include <linux/rculist.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> #include <linux/license.h> @@ -65,7 +66,7 @@ #define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1)) /* List of modules, protected by module_mutex or preempt_disable - * (add/delete uses stop_machine). */ + * (delete uses stop_machine/add uses RCU list operations). */ static DEFINE_MUTEX(module_mutex); static LIST_HEAD(modules); @@ -134,6 +135,29 @@ static unsigned int find_sec(Elf_Ehdr *hdr, return 0; } +/* Find a module section, or NULL. */ +static void *section_addr(Elf_Ehdr *hdr, Elf_Shdr *shdrs, + const char *secstrings, const char *name) +{ + /* Section 0 has sh_addr 0. */ + return (void *)shdrs[find_sec(hdr, shdrs, secstrings, name)].sh_addr; +} + +/* Find a module section, or NULL. Fill in number of "objects" in section. */ +static void *section_objs(Elf_Ehdr *hdr, + Elf_Shdr *sechdrs, + const char *secstrings, + const char *name, + size_t object_size, + unsigned int *num) +{ + unsigned int sec = find_sec(hdr, sechdrs, secstrings, name); + + /* Section 0 has sh_addr 0 and sh_size 0. */ + *num = sechdrs[sec].sh_size / object_size; + return (void *)sechdrs[sec].sh_addr; +} + /* Provided by the linker */ extern const struct kernel_symbol __start___ksymtab[]; extern const struct kernel_symbol __stop___ksymtab[]; @@ -220,7 +244,7 @@ static bool each_symbol(bool (*fn)(const struct symsearch *arr, if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data)) return true; - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { struct symsearch arr[] = { { mod->syms, mod->syms + mod->num_syms, mod->crcs, NOT_GPL_ONLY, false }, @@ -1396,17 +1420,6 @@ static void mod_kobject_remove(struct module *mod) } /* - * link the module with the whole machine is stopped with interrupts off - * - this defends against kallsyms not taking locks - */ -static int __link_module(void *_mod) -{ - struct module *mod = _mod; - list_add(&mod->list, &modules); - return 0; -} - -/* * unlink the module with the whole machine is stopped with interrupts off * - this defends against kallsyms not taking locks */ @@ -1791,32 +1804,20 @@ static inline void add_kallsyms(struct module *mod, } #endif /* CONFIG_KALLSYMS */ -#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG -static void dynamic_printk_setup(Elf_Shdr *sechdrs, unsigned int verboseindex) +static void dynamic_printk_setup(struct mod_debug *debug, unsigned int num) { - struct mod_debug *debug_info; - unsigned long pos, end; - unsigned int num_verbose; - - pos = sechdrs[verboseindex].sh_addr; - num_verbose = sechdrs[verboseindex].sh_size / - sizeof(struct mod_debug); - end = pos + (num_verbose * sizeof(struct mod_debug)); +#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG + unsigned int i; - for (; pos < end; pos += sizeof(struct mod_debug)) { - debug_info = (struct mod_debug *)pos; - register_dynamic_debug_module(debug_info->modname, - debug_info->type, debug_info->logical_modname, - debug_info->flag_names, debug_info->hash, - debug_info->hash2); + for (i = 0; i < num; i++) { + register_dynamic_debug_module(debug[i].modname, + debug[i].type, + debug[i].logical_modname, + debug[i].flag_names, + debug[i].hash, debug[i].hash2); } -} -#else -static inline void dynamic_printk_setup(Elf_Shdr *sechdrs, - unsigned int verboseindex) -{ -} #endif /* CONFIG_DYNAMIC_PRINTK_DEBUG */ +} static void *module_alloc_update_bounds(unsigned long size) { @@ -1845,37 +1846,14 @@ static noinline struct module *load_module(void __user *umod, unsigned int i; unsigned int symindex = 0; unsigned int strindex = 0; - unsigned int setupindex; - unsigned int exindex; - unsigned int exportindex; - unsigned int modindex; - unsigned int obsparmindex; - unsigned int infoindex; - unsigned int gplindex; - unsigned int crcindex; - unsigned int gplcrcindex; - unsigned int versindex; - unsigned int pcpuindex; - unsigned int gplfutureindex; - unsigned int gplfuturecrcindex; + unsigned int modindex, versindex, infoindex, pcpuindex; unsigned int unwindex = 0; -#ifdef CONFIG_UNUSED_SYMBOLS - unsigned int unusedindex; - unsigned int unusedcrcindex; - unsigned int unusedgplindex; - unsigned int unusedgplcrcindex; -#endif - unsigned int markersindex; - unsigned int markersstringsindex; - unsigned int verboseindex; - unsigned int tracepointsindex; - unsigned int tracepointsstringsindex; - unsigned int mcountindex; + unsigned int num_kp, num_mcount; + struct kernel_param *kp; struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ - void *mseg; - struct exception_table_entry *extable; + unsigned long *mseg; mm_segment_t old_fs; DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", @@ -1939,6 +1917,7 @@ static noinline struct module *load_module(void __user *umod, err = -ENOEXEC; goto free_hdr; } + /* This is temporary: point mod into copy of data. */ mod = (void *)sechdrs[modindex].sh_addr; if (symindex == 0) { @@ -1948,22 +1927,6 @@ static noinline struct module *load_module(void __user *umod, goto free_hdr; } - /* Optional sections */ - exportindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab"); - gplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl"); - gplfutureindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl_future"); - crcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab"); - gplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl"); - gplfuturecrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl_future"); -#ifdef CONFIG_UNUSED_SYMBOLS - unusedindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused"); - unusedgplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused_gpl"); - unusedcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused"); - unusedgplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused_gpl"); -#endif - setupindex = find_sec(hdr, sechdrs, secstrings, "__param"); - exindex = find_sec(hdr, sechdrs, secstrings, "__ex_table"); - obsparmindex = find_sec(hdr, sechdrs, secstrings, "__obsparm"); versindex = find_sec(hdr, sechdrs, secstrings, "__versions"); infoindex = find_sec(hdr, sechdrs, secstrings, ".modinfo"); pcpuindex = find_pcpusec(hdr, sechdrs, secstrings); @@ -2119,42 +2082,57 @@ static noinline struct module *load_module(void __user *umod, if (err < 0) goto cleanup; - /* Set up EXPORTed & EXPORT_GPLed symbols (section 0 is 0 length) */ - mod->num_syms = sechdrs[exportindex].sh_size / sizeof(*mod->syms); - mod->syms = (void *)sechdrs[exportindex].sh_addr; - if (crcindex) - mod->crcs = (void *)sechdrs[crcindex].sh_addr; - mod->num_gpl_syms = sechdrs[gplindex].sh_size / sizeof(*mod->gpl_syms); - mod->gpl_syms = (void *)sechdrs[gplindex].sh_addr; - if (gplcrcindex) - mod->gpl_crcs = (void *)sechdrs[gplcrcindex].sh_addr; - mod->num_gpl_future_syms = sechdrs[gplfutureindex].sh_size / - sizeof(*mod->gpl_future_syms); - mod->gpl_future_syms = (void *)sechdrs[gplfutureindex].sh_addr; - if (gplfuturecrcindex) - mod->gpl_future_crcs = (void *)sechdrs[gplfuturecrcindex].sh_addr; + /* Now we've got everything in the final locations, we can + * find optional sections. */ + kp = section_objs(hdr, sechdrs, secstrings, "__param", sizeof(*kp), + &num_kp); + mod->syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab", + sizeof(*mod->syms), &mod->num_syms); + mod->crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab"); + mod->gpl_syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab_gpl", + sizeof(*mod->gpl_syms), + &mod->num_gpl_syms); + mod->gpl_crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab_gpl"); + mod->gpl_future_syms = section_objs(hdr, sechdrs, secstrings, + "__ksymtab_gpl_future", + sizeof(*mod->gpl_future_syms), + &mod->num_gpl_future_syms); + mod->gpl_future_crcs = section_addr(hdr, sechdrs, secstrings, + "__kcrctab_gpl_future"); #ifdef CONFIG_UNUSED_SYMBOLS - mod->num_unused_syms = sechdrs[unusedindex].sh_size / - sizeof(*mod->unused_syms); - mod->num_unused_gpl_syms = sechdrs[unusedgplindex].sh_size / - sizeof(*mod->unused_gpl_syms); - mod->unused_syms = (void *)sechdrs[unusedindex].sh_addr; - if (unusedcrcindex) - mod->unused_crcs = (void *)sechdrs[unusedcrcindex].sh_addr; - mod->unused_gpl_syms = (void *)sechdrs[unusedgplindex].sh_addr; - if (unusedgplcrcindex) - mod->unused_gpl_crcs - = (void *)sechdrs[unusedgplcrcindex].sh_addr; + mod->unused_syms = section_objs(hdr, sechdrs, secstrings, + "__ksymtab_unused", + sizeof(*mod->unused_syms), + &mod->num_unused_syms); + mod->unused_crcs = section_addr(hdr, sechdrs, secstrings, + "__kcrctab_unused"); + mod->unused_gpl_syms = section_objs(hdr, sechdrs, secstrings, + "__ksymtab_unused_gpl", + sizeof(*mod->unused_gpl_syms), + &mod->num_unused_gpl_syms); + mod->unused_gpl_crcs = section_addr(hdr, sechdrs, secstrings, + "__kcrctab_unused_gpl"); +#endif + +#ifdef CONFIG_MARKERS + mod->markers = section_objs(hdr, sechdrs, secstrings, "__markers", + sizeof(*mod->markers), &mod->num_markers); +#endif +#ifdef CONFIG_TRACEPOINTS + mod->tracepoints = section_objs(hdr, sechdrs, secstrings, + "__tracepoints", + sizeof(*mod->tracepoints), + &mod->num_tracepoints); #endif #ifdef CONFIG_MODVERSIONS - if ((mod->num_syms && !crcindex) - || (mod->num_gpl_syms && !gplcrcindex) - || (mod->num_gpl_future_syms && !gplfuturecrcindex) + if ((mod->num_syms && !mod->crcs) + || (mod->num_gpl_syms && !mod->gpl_crcs) + || (mod->num_gpl_future_syms && !mod->gpl_future_crcs) #ifdef CONFIG_UNUSED_SYMBOLS - || (mod->num_unused_syms && !unusedcrcindex) - || (mod->num_unused_gpl_syms && !unusedgplcrcindex) + || (mod->num_unused_syms && !mod->unused_crcs) + || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs) #endif ) { printk(KERN_WARNING "%s: No versions for exported symbols.\n", mod->name); @@ -2163,16 +2141,6 @@ static noinline struct module *load_module(void __user *umod, goto cleanup; } #endif - markersindex = find_sec(hdr, sechdrs, secstrings, "__markers"); - markersstringsindex = find_sec(hdr, sechdrs, secstrings, - "__markers_strings"); - verboseindex = find_sec(hdr, sechdrs, secstrings, "__verbose"); - tracepointsindex = find_sec(hdr, sechdrs, secstrings, "__tracepoints"); - tracepointsstringsindex = find_sec(hdr, sechdrs, secstrings, - "__tracepoints_strings"); - - mcountindex = find_sec(hdr, sechdrs, secstrings, - "__mcount_loc"); /* Now do relocations. */ for (i = 1; i < hdr->e_shnum; i++) { @@ -2195,28 +2163,16 @@ static noinline struct module *load_module(void __user *umod, if (err < 0) goto cleanup; } -#ifdef CONFIG_MARKERS - mod->markers = (void *)sechdrs[markersindex].sh_addr; - mod->num_markers = - sechdrs[markersindex].sh_size / sizeof(*mod->markers); -#endif -#ifdef CONFIG_TRACEPOINTS - mod->tracepoints = (void *)sechdrs[tracepointsindex].sh_addr; - mod->num_tracepoints = - sechdrs[tracepointsindex].sh_size / sizeof(*mod->tracepoints); -#endif - /* Find duplicate symbols */ err = verify_export_symbols(mod); - if (err < 0) goto cleanup; /* Set up and sort exception table */ - mod->num_exentries = sechdrs[exindex].sh_size / sizeof(*mod->extable); - mod->extable = extable = (void *)sechdrs[exindex].sh_addr; - sort_extable(extable, extable + mod->num_exentries); + mod->extable = section_objs(hdr, sechdrs, secstrings, "__ex_table", + sizeof(*mod->extable), &mod->num_exentries); + sort_extable(mod->extable, mod->extable + mod->num_exentries); /* Finally, copy percpu area over. */ percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr, @@ -2225,11 +2181,17 @@ static noinline struct module *load_module(void __user *umod, add_kallsyms(mod, sechdrs, symindex, strindex, secstrings); if (!mod->taints) { + struct mod_debug *debug; + unsigned int num_debug; + #ifdef CONFIG_MARKERS marker_update_probe_range(mod->markers, mod->markers + mod->num_markers); #endif - dynamic_printk_setup(sechdrs, verboseindex); + debug = section_objs(hdr, sechdrs, secstrings, "__verbose", + sizeof(*debug), &num_debug); + dynamic_printk_setup(debug, num_debug); + #ifdef CONFIG_TRACEPOINTS tracepoint_update_probe_range(mod->tracepoints, mod->tracepoints + mod->num_tracepoints); @@ -2237,8 +2199,9 @@ static noinline struct module *load_module(void __user *umod, } /* sechdrs[0].sh_size is always zero */ - mseg = (void *)sechdrs[mcountindex].sh_addr; - ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size); + mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc", + sizeof(*mseg), &num_mcount); + ftrace_init_module(mseg, mseg + num_mcount); err = module_finalize(hdr, sechdrs, mod); if (err < 0) @@ -2263,30 +2226,24 @@ static noinline struct module *load_module(void __user *umod, set_fs(old_fs); mod->args = args; - if (obsparmindex) + if (section_addr(hdr, sechdrs, secstrings, "__obsparm")) printk(KERN_WARNING "%s: Ignoring obsolete parameters\n", mod->name); /* Now sew it into the lists so we can get lockdep and oops - * info during argument parsing. Noone should access us, since - * strong_try_module_get() will fail. */ - stop_machine(__link_module, mod, NULL); - - /* Size of section 0 is 0, so this works well if no params */ - err = parse_args(mod->name, mod->args, - (struct kernel_param *) - sechdrs[setupindex].sh_addr, - sechdrs[setupindex].sh_size - / sizeof(struct kernel_param), - NULL); + * info during argument parsing. Noone should access us, since + * strong_try_module_get() will fail. + * lockdep/oops can run asynchronous, so use the RCU list insertion + * function to insert in a way safe to concurrent readers. + * The mutex protects against concurrent writers. + */ + list_add_rcu(&mod->list, &modules); + + err = parse_args(mod->name, mod->args, kp, num_kp, NULL); if (err < 0) goto unlink; - err = mod_sysfs_setup(mod, - (struct kernel_param *) - sechdrs[setupindex].sh_addr, - sechdrs[setupindex].sh_size - / sizeof(struct kernel_param)); + err = mod_sysfs_setup(mod, kp, num_kp); if (err < 0) goto unlink; add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs); @@ -2475,7 +2432,7 @@ const char *module_address_lookup(unsigned long addr, const char *ret = NULL; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (within(addr, mod->module_init, mod->init_size) || within(addr, mod->module_core, mod->core_size)) { if (modname) @@ -2498,7 +2455,7 @@ int lookup_module_symbol_name(unsigned long addr, char *symname) struct module *mod; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (within(addr, mod->module_init, mod->init_size) || within(addr, mod->module_core, mod->core_size)) { const char *sym; @@ -2522,7 +2479,7 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, struct module *mod; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (within(addr, mod->module_init, mod->init_size) || within(addr, mod->module_core, mod->core_size)) { const char *sym; @@ -2549,7 +2506,7 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, struct module *mod; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (symnum < mod->num_symtab) { *value = mod->symtab[symnum].st_value; *type = mod->symtab[symnum].st_info; @@ -2592,7 +2549,7 @@ unsigned long module_kallsyms_lookup_name(const char *name) ret = mod_find_symname(mod, colon+1); *colon = ':'; } else { - list_for_each_entry(mod, &modules, list) + list_for_each_entry_rcu(mod, &modules, list) if ((ret = mod_find_symname(mod, name)) != 0) break; } @@ -2716,7 +2673,7 @@ const struct exception_table_entry *search_module_extables(unsigned long addr) struct module *mod; preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (mod->num_exentries == 0) continue; @@ -2742,7 +2699,7 @@ int is_module_address(unsigned long addr) preempt_disable(); - list_for_each_entry(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list) { if (within(addr, mod->module_core, mod->core_size)) { preempt_enable(); return 1; @@ -2763,7 +2720,7 @@ struct module *__module_text_address(unsigned long addr) if (addr < module_addr_min || addr > module_addr_max) return NULL; - list_for_each_entry(mod, &modules, list) + list_for_each_entry_rcu(mod, &modules, list) if (within(addr, mod->module_init, mod->init_text_size) || within(addr, mod->module_core, mod->core_text_size)) return mod; @@ -2788,8 +2745,11 @@ void print_modules(void) char buf[8]; printk("Modules linked in:"); - list_for_each_entry(mod, &modules, list) + /* Most callers should already have preempt disabled, but make sure */ + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) printk(" %s%s", mod->name, module_flags(mod, buf)); + preempt_enable(); if (last_unloaded_module[0]) printk(" [last unloaded: %s]", last_unloaded_module); printk("\n"); diff --git a/kernel/panic.c b/kernel/panic.c index bda561e..6513aac 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -34,13 +34,6 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); -static int __init panic_setup(char *str) -{ - panic_timeout = simple_strtoul(str, NULL, 0); - return 1; -} -__setup("panic=", panic_setup); - static long no_blink(long time) { return 0; @@ -218,13 +211,6 @@ void add_taint(unsigned flag) } EXPORT_SYMBOL(add_taint); -static int __init pause_on_oops_setup(char *str) -{ - pause_on_oops = simple_strtoul(str, NULL, 0); - return 1; -} -__setup("pause_on_oops=", pause_on_oops_setup); - static void spin_msec(int msecs) { int i; @@ -384,3 +370,6 @@ void __stack_chk_fail(void) } EXPORT_SYMBOL(__stack_chk_fail); #endif + +core_param(panic, panic_timeout, int, 0644); +core_param(pause_on_oops, pause_on_oops, int, 0644); diff --git a/kernel/params.c b/kernel/params.c index afc46a2..b077f1b 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -373,6 +373,8 @@ int param_get_string(char *buffer, struct kernel_param *kp) } /* sysfs output in /sys/modules/XYZ/parameters/ */ +#define to_module_attr(n) container_of(n, struct module_attribute, attr); +#define to_module_kobject(n) container_of(n, struct module_kobject, kobj); extern struct kernel_param __start___param[], __stop___param[]; @@ -384,6 +386,7 @@ struct param_attribute struct module_param_attrs { + unsigned int num; struct attribute_group grp; struct param_attribute attrs[0]; }; @@ -434,69 +437,84 @@ static ssize_t param_attr_store(struct module_attribute *mattr, #ifdef CONFIG_SYSFS /* - * param_sysfs_setup - setup sysfs support for one module or KBUILD_MODNAME - * @mk: struct module_kobject (contains parent kobject) - * @kparam: array of struct kernel_param, the actual parameter definitions - * @num_params: number of entries in array - * @name_skip: offset where the parameter name start in kparam[].name. Needed for built-in "modules" + * add_sysfs_param - add a parameter to sysfs + * @mk: struct module_kobject + * @kparam: the actual parameter definition to add to sysfs + * @name: name of parameter * - * Create a kobject for a (per-module) group of parameters, and create files - * in sysfs. A pointer to the param_kobject is returned on success, - * NULL if there's no parameter to export, or other ERR_PTR(err). + * Create a kobject if for a (per-module) parameter if mp NULL, and + * create file in sysfs. Returns an error on out of memory. Always cleans up + * if there's an error. */ -static __modinit struct module_param_attrs * -param_sysfs_setup(struct module_kobject *mk, - struct kernel_param *kparam, - unsigned int num_params, - unsigned int name_skip) +static __modinit int add_sysfs_param(struct module_kobject *mk, + struct kernel_param *kp, + const char *name) { - struct module_param_attrs *mp; - unsigned int valid_attrs = 0; - unsigned int i, size[2]; - struct param_attribute *pattr; - struct attribute **gattr; - int err; - - for (i=0; i<num_params; i++) { - if (kparam[i].perm) - valid_attrs++; + struct module_param_attrs *new; + struct attribute **attrs; + int err, num; + + /* We don't bother calling this with invisible parameters. */ + BUG_ON(!kp->perm); + + if (!mk->mp) { + num = 0; + attrs = NULL; + } else { + num = mk->mp->num; + attrs = mk->mp->grp.attrs; } - if (!valid_attrs) - return NULL; - - size[0] = ALIGN(sizeof(*mp) + - valid_attrs * sizeof(mp->attrs[0]), - sizeof(mp->grp.attrs[0])); - size[1] = (valid_attrs + 1) * sizeof(mp->grp.attrs[0]); - - mp = kzalloc(size[0] + size[1], GFP_KERNEL); - if (!mp) - return ERR_PTR(-ENOMEM); + /* Enlarge. */ + new = krealloc(mk->mp, + sizeof(*mk->mp) + sizeof(mk->mp->attrs[0]) * (num+1), + GFP_KERNEL); + if (!new) { + kfree(mk->mp); + err = -ENOMEM; + goto fail; + } + attrs = krealloc(attrs, sizeof(new->grp.attrs[0])*(num+2), GFP_KERNEL); + if (!attrs) { + err = -ENOMEM; + goto fail_free_new; + } - mp->grp.name = "parameters"; - mp->grp.attrs = (void *)mp + size[0]; + /* Sysfs wants everything zeroed. */ + memset(new, 0, sizeof(*new)); + memset(&new->attrs[num], 0, sizeof(new->attrs[num])); + memset(&attrs[num], 0, sizeof(attrs[num])); + new->grp.name = "parameters"; + new->grp.attrs = attrs; + + /* Tack new one on the end. */ + new->attrs[num].param = kp; + new->attrs[num].mattr.show = param_attr_show; + new->attrs[num].mattr.store = param_attr_store; + new->attrs[num].mattr.attr.name = (char *)name; + new->attrs[num].mattr.attr.mode = kp->perm; + new->num = num+1; + + /* Fix up all the pointers, since krealloc can move us */ + for (num = 0; num < new->num; num++) + new->grp.attrs[num] = &new->attrs[num].mattr.attr; + new->grp.attrs[num] = NULL; + + mk->mp = new; + return 0; - pattr = &mp->attrs[0]; - gattr = &mp->grp.attrs[0]; - for (i = 0; i < num_params; i++) { - struct kernel_param *kp = &kparam[i]; - if (kp->perm) { - pattr->param = kp; - pattr->mattr.show = param_attr_show; - pattr->mattr.store = param_attr_store; - pattr->mattr.attr.name = (char *)&kp->name[name_skip]; - pattr->mattr.attr.mode = kp->perm; - *(gattr++) = &(pattr++)->mattr.attr; - } - } - *gattr = NULL; +fail_free_new: + kfree(new); +fail: + mk->mp = NULL; + return err; +} - if ((err = sysfs_create_group(&mk->kobj, &mp->grp))) { - kfree(mp); - return ERR_PTR(err); - } - return mp; +static void free_module_param_attrs(struct module_kobject *mk) +{ + kfree(mk->mp->grp.attrs); + kfree(mk->mp); + mk->mp = NULL; } #ifdef CONFIG_MODULES @@ -506,21 +524,33 @@ param_sysfs_setup(struct module_kobject *mk, * @kparam: module parameters (array) * @num_params: number of module parameters * - * Adds sysfs entries for module parameters, and creates a link from - * /sys/module/[mod->name]/parameters to /sys/parameters/[mod->name]/ + * Adds sysfs entries for module parameters under + * /sys/module/[mod->name]/parameters/ */ int module_param_sysfs_setup(struct module *mod, struct kernel_param *kparam, unsigned int num_params) { - struct module_param_attrs *mp; + int i, err; + bool params = false; + + for (i = 0; i < num_params; i++) { + if (kparam[i].perm == 0) + continue; + err = add_sysfs_param(&mod->mkobj, &kparam[i], kparam[i].name); + if (err) + return err; + params = true; + } - mp = param_sysfs_setup(&mod->mkobj, kparam, num_params, 0); - if (IS_ERR(mp)) - return PTR_ERR(mp); + if (!params) + return 0; - mod->param_attrs = mp; - return 0; + /* Create the param group. */ + err = sysfs_create_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp); + if (err) + free_module_param_attrs(&mod->mkobj); + return err; } /* @@ -532,43 +562,55 @@ int module_param_sysfs_setup(struct module *mod, */ void module_param_sysfs_remove(struct module *mod) { - if (mod->param_attrs) { - sysfs_remove_group(&mod->mkobj.kobj, - &mod->param_attrs->grp); + if (mod->mkobj.mp) { + sysfs_remove_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp); /* We are positive that no one is using any param * attrs at this point. Deallocate immediately. */ - kfree(mod->param_attrs); - mod->param_attrs = NULL; + free_module_param_attrs(&mod->mkobj); } } #endif -/* - * kernel_param_sysfs_setup - wrapper for built-in params support - */ -static void __init kernel_param_sysfs_setup(const char *name, - struct kernel_param *kparam, - unsigned int num_params, - unsigned int name_skip) +static void __init kernel_add_sysfs_param(const char *name, + struct kernel_param *kparam, + unsigned int name_skip) { struct module_kobject *mk; - int ret; + struct kobject *kobj; + int err; - mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL); - BUG_ON(!mk); - - mk->mod = THIS_MODULE; - mk->kobj.kset = module_kset; - ret = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, "%s", name); - if (ret) { - kobject_put(&mk->kobj); - printk(KERN_ERR "Module '%s' failed to be added to sysfs, " - "error number %d\n", name, ret); - printk(KERN_ERR "The system will be unstable now.\n"); - return; + kobj = kset_find_obj(module_kset, name); + if (kobj) { + /* We already have one. Remove params so we can add more. */ + mk = to_module_kobject(kobj); + /* We need to remove it before adding parameters. */ + sysfs_remove_group(&mk->kobj, &mk->mp->grp); + } else { + mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL); + BUG_ON(!mk); + + mk->mod = THIS_MODULE; + mk->kobj.kset = module_kset; + err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, + "%s", name); + if (err) { + kobject_put(&mk->kobj); + printk(KERN_ERR "Module '%s' failed add to sysfs, " + "error number %d\n", name, err); + printk(KERN_ERR "The system will be unstable now.\n"); + return; + } + /* So that exit path is even. */ + kobject_get(&mk->kobj); } - param_sysfs_setup(mk, kparam, num_params, name_skip); + + /* These should not fail at boot. */ + err = add_sysfs_param(mk, kparam, kparam->name + name_skip); + BUG_ON(err); + err = sysfs_create_group(&mk->kobj, &mk->mp->grp); + BUG_ON(err); kobject_uevent(&mk->kobj, KOBJ_ADD); + kobject_put(&mk->kobj); } /* @@ -579,60 +621,36 @@ static void __init kernel_param_sysfs_setup(const char *name, * The "module" name (KBUILD_MODNAME) is stored before a dot, the * "parameter" name is stored behind a dot in kernel_param->name. So, * extract the "module" name for all built-in kernel_param-eters, - * and for all who have the same, call kernel_param_sysfs_setup. + * and for all who have the same, call kernel_add_sysfs_param. */ static void __init param_sysfs_builtin(void) { - struct kernel_param *kp, *kp_begin = NULL; - unsigned int i, name_len, count = 0; - char modname[MODULE_NAME_LEN + 1] = ""; + struct kernel_param *kp; + unsigned int name_len; + char modname[MODULE_NAME_LEN]; - for (i=0; i < __stop___param - __start___param; i++) { + for (kp = __start___param; kp < __stop___param; kp++) { char *dot; - size_t max_name_len; - kp = &__start___param[i]; - max_name_len = - min_t(size_t, MODULE_NAME_LEN, strlen(kp->name)); + if (kp->perm == 0) + continue; - dot = memchr(kp->name, '.', max_name_len); + dot = strchr(kp->name, '.'); if (!dot) { - DEBUGP("couldn't find period in first %d characters " - "of %s\n", MODULE_NAME_LEN, kp->name); - continue; - } - name_len = dot - kp->name; - - /* new kbuild_modname? */ - if (strlen(modname) != name_len - || strncmp(modname, kp->name, name_len) != 0) { - /* add a new kobject for previous kernel_params. */ - if (count) - kernel_param_sysfs_setup(modname, - kp_begin, - count, - strlen(modname)+1); - - strncpy(modname, kp->name, name_len); - modname[name_len] = '\0'; - count = 0; - kp_begin = kp; + /* This happens for core_param() */ + strcpy(modname, "kernel"); + name_len = 0; + } else { + name_len = dot - kp->name + 1; + strlcpy(modname, kp->name, name_len); } - count++; + kernel_add_sysfs_param(modname, kp, name_len); } - - /* last kernel_params need to be registered as well */ - if (count) - kernel_param_sysfs_setup(modname, kp_begin, count, - strlen(modname)+1); } /* module-related sysfs stuff */ -#define to_module_attr(n) container_of(n, struct module_attribute, attr); -#define to_module_kobject(n) container_of(n, struct module_kobject, kobj); - static ssize_t module_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index b931d7c..5e79c66 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -639,7 +639,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv); - remaining = ktime_sub(timer->expires, now); + remaining = ktime_sub(hrtimer_get_expires(timer), now); /* Return 0 only, when the timer is expired and not pending */ if (remaining.tv64 <= 0) { /* @@ -733,7 +733,7 @@ common_timer_set(struct k_itimer *timr, int flags, hrtimer_init(&timr->it.real.timer, timr->it_clock, mode); timr->it.real.timer.function = posix_timer_fn; - timer->expires = timespec_to_ktime(new_setting->it_value); + hrtimer_set_expires(timer, timespec_to_ktime(new_setting->it_value)); /* Convert interval */ timr->it.real.interval = timespec_to_ktime(new_setting->it_interval); @@ -742,14 +742,12 @@ common_timer_set(struct k_itimer *timr, int flags, if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) { /* Setup correct expiry time for relative timers */ if (mode == HRTIMER_MODE_REL) { - timer->expires = - ktime_add_safe(timer->expires, - timer->base->get_time()); + hrtimer_add_expires(timer, timer->base->get_time()); } return 0; } - hrtimer_start(timer, timer->expires, mode); + hrtimer_start_expires(timer, mode); return 0; } diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 331f983..c9d7408 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -651,7 +651,7 @@ static int software_resume(void) pr_debug("PM: Preparing processes for restore.\n"); error = prepare_processes(); if (error) { - swsusp_close(); + swsusp_close(FMODE_READ); goto Done; } diff --git a/kernel/power/power.h b/kernel/power/power.h index acc0c10..46b5ec7 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -153,7 +153,7 @@ extern int swsusp_shrink_memory(void); extern void swsusp_free(void); extern int swsusp_read(unsigned int *flags_p); extern int swsusp_write(unsigned int flags); -extern void swsusp_close(void); +extern void swsusp_close(fmode_t); struct timeval; /* kernel/power/swsusp.c */ diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 80ccac8..b7713b5 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -172,13 +172,13 @@ static int swsusp_swap_check(void) /* This is called before saving image */ return res; root_swap = res; - res = blkdev_get(resume_bdev, FMODE_WRITE, O_RDWR); + res = blkdev_get(resume_bdev, FMODE_WRITE); if (res) return res; res = set_blocksize(resume_bdev, PAGE_SIZE); if (res < 0) - blkdev_put(resume_bdev); + blkdev_put(resume_bdev, FMODE_WRITE); return res; } @@ -426,7 +426,7 @@ int swsusp_write(unsigned int flags) release_swap_writer(&handle); out: - swsusp_close(); + swsusp_close(FMODE_WRITE); return error; } @@ -574,7 +574,7 @@ int swsusp_read(unsigned int *flags_p) error = load_image(&handle, &snapshot, header->pages - 1); release_swap_reader(&handle); - blkdev_put(resume_bdev); + blkdev_put(resume_bdev, FMODE_READ); if (!error) pr_debug("PM: Image successfully loaded\n"); @@ -609,7 +609,7 @@ int swsusp_check(void) return -EINVAL; } if (error) - blkdev_put(resume_bdev); + blkdev_put(resume_bdev, FMODE_READ); else pr_debug("PM: Signature found, resuming\n"); } else { @@ -626,14 +626,14 @@ int swsusp_check(void) * swsusp_close - close swap device. */ -void swsusp_close(void) +void swsusp_close(fmode_t mode) { if (IS_ERR(resume_bdev)) { pr_debug("PM: Image device not initialised\n"); return; } - blkdev_put(resume_bdev); + blkdev_put(resume_bdev, mode); /* move up */ } static int swsusp_header_init(void) diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 467d594..ad63af8 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -119,18 +119,19 @@ static void _rcu_barrier(enum rcu_barrier type) /* Take cpucontrol mutex to protect against CPU hotplug */ mutex_lock(&rcu_barrier_mutex); init_completion(&rcu_barrier_completion); - atomic_set(&rcu_barrier_cpu_count, 0); /* - * The queueing of callbacks in all CPUs must be atomic with - * respect to RCU, otherwise one CPU may queue a callback, - * wait for a grace period, decrement barrier count and call - * complete(), while other CPUs have not yet queued anything. - * So, we need to make sure that grace periods cannot complete - * until all the callbacks are queued. + * Initialize rcu_barrier_cpu_count to 1, then invoke + * rcu_barrier_func() on each CPU, so that each CPU also has + * incremented rcu_barrier_cpu_count. Only then is it safe to + * decrement rcu_barrier_cpu_count -- otherwise the first CPU + * might complete its grace period before all of the other CPUs + * did their increment, causing this function to return too + * early. */ - rcu_read_lock(); + atomic_set(&rcu_barrier_cpu_count, 1); on_each_cpu(rcu_barrier_func, (void *)type, 1); - rcu_read_unlock(); + if (atomic_dec_and_test(&rcu_barrier_cpu_count)) + complete(&rcu_barrier_completion); wait_for_completion(&rcu_barrier_completion); mutex_unlock(&rcu_barrier_mutex); } diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index 6522ae5..69d9cb9 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -631,8 +631,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, /* Setup the timer, when timeout != NULL */ if (unlikely(timeout)) { - hrtimer_start(&timeout->timer, timeout->timer.expires, - HRTIMER_MODE_ABS); + hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); if (!hrtimer_active(&timeout->timer)) timeout->task = NULL; } diff --git a/kernel/sched.c b/kernel/sched.c index 5a70189..6625c3c 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -228,9 +228,8 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) now = hrtimer_cb_get_time(&rt_b->rt_period_timer); hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period); - hrtimer_start(&rt_b->rt_period_timer, - rt_b->rt_period_timer.expires, - HRTIMER_MODE_ABS); + hrtimer_start_expires(&rt_b->rt_period_timer, + HRTIMER_MODE_ABS); } spin_unlock(&rt_b->rt_runtime_lock); } @@ -820,6 +819,13 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32; unsigned int sysctl_sched_shares_ratelimit = 250000; /* + * Inject some fuzzyness into changing the per-cpu group shares + * this avoids remote rq-locks at the expense of fairness. + * default: 4 + */ +unsigned int sysctl_sched_shares_thresh = 4; + +/* * period over which we measure -rt task cpu usage in us. * default: 1s */ @@ -1065,7 +1071,7 @@ static void hrtick_start(struct rq *rq, u64 delay) struct hrtimer *timer = &rq->hrtick_timer; ktime_t time = ktime_add_ns(timer->base->get_time(), delay); - timer->expires = time; + hrtimer_set_expires(timer, time); if (rq == this_rq()) { hrtimer_restart(timer); @@ -1455,8 +1461,8 @@ 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, int cpu, - unsigned long sd_shares, unsigned long sd_rq_weight) +update_group_shares_cpu(struct task_group *tg, int cpu, + unsigned long sd_shares, unsigned long sd_rq_weight) { int boost = 0; unsigned long shares; @@ -1487,19 +1493,23 @@ __update_group_shares_cpu(struct task_group *tg, int cpu, * */ shares = (sd_shares * rq_weight) / (sd_rq_weight + 1); + shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES); - /* - * record the actual number of shares, not the boosted amount. - */ - tg->cfs_rq[cpu]->shares = boost ? 0 : shares; - tg->cfs_rq[cpu]->rq_weight = rq_weight; + if (abs(shares - tg->se[cpu]->load.weight) > + sysctl_sched_shares_thresh) { + struct rq *rq = cpu_rq(cpu); + unsigned long flags; - if (shares < MIN_SHARES) - shares = MIN_SHARES; - else if (shares > MAX_SHARES) - shares = MAX_SHARES; + spin_lock_irqsave(&rq->lock, flags); + /* + * record the actual number of shares, not the boosted amount. + */ + tg->cfs_rq[cpu]->shares = boost ? 0 : shares; + tg->cfs_rq[cpu]->rq_weight = rq_weight; - __set_se_shares(tg->se[cpu], shares); + __set_se_shares(tg->se[cpu], shares); + spin_unlock_irqrestore(&rq->lock, flags); + } } /* @@ -1528,14 +1538,8 @@ static int tg_shares_up(struct task_group *tg, void *data) if (!rq_weight) rq_weight = cpus_weight(sd->span) * NICE_0_LOAD; - 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, i, shares, rq_weight); - spin_unlock_irqrestore(&rq->lock, flags); - } + for_each_cpu_mask(i, sd->span) + update_group_shares_cpu(tg, i, shares, rq_weight); return 0; } @@ -4444,12 +4448,8 @@ need_resched_nonpreemptible: if (sched_feat(HRTICK)) hrtick_clear(rq); - /* - * Do the rq-clock update outside the rq lock: - */ - local_irq_disable(); + spin_lock_irq(&rq->lock); update_rq_clock(rq); - spin_lock(&rq->lock); clear_tsk_need_resched(prev); if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index f604dae..9573c33 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -73,6 +73,8 @@ unsigned int sysctl_sched_wakeup_granularity = 5000000UL; const_debug unsigned int sysctl_sched_migration_cost = 500000UL; +static const struct sched_class fair_sched_class; + /************************************************************** * CFS operations on generic schedulable entities: */ @@ -334,7 +336,7 @@ int sched_nr_latency_handler(struct ctl_table *table, int write, #endif /* - * delta *= w / rw + * delta *= P[w / rw] */ static inline unsigned long calc_delta_weight(unsigned long delta, struct sched_entity *se) @@ -348,15 +350,13 @@ calc_delta_weight(unsigned long delta, struct sched_entity *se) } /* - * delta *= rw / w + * delta /= 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); - } + if (unlikely(se->load.weight != NICE_0_LOAD)) + delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load); return delta; } @@ -386,26 +386,26 @@ static u64 __sched_period(unsigned long nr_running) * We calculate the wall-time slice from the period by taking a part * proportional to the weight. * - * s = p*w/rw + * s = p*P[w/rw] */ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) { - return calc_delta_weight(__sched_period(cfs_rq->nr_running), se); + unsigned long nr_running = cfs_rq->nr_running; + + if (unlikely(!se->on_rq)) + nr_running++; + + return calc_delta_weight(__sched_period(nr_running), se); } /* * We calculate the vruntime slice of a to be inserted task * - * vs = s*rw/w = p + * vs = s/w */ -static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se) +static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) { - unsigned long nr_running = cfs_rq->nr_running; - - if (!se->on_rq) - nr_running++; - - return __sched_period(nr_running); + return calc_delta_fair(sched_slice(cfs_rq, se), se); } /* @@ -628,7 +628,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) * stays open at the end. */ if (initial && sched_feat(START_DEBIT)) - vruntime += sched_vslice_add(cfs_rq, se); + vruntime += sched_vslice(cfs_rq, se); if (!initial) { /* sleeps upto a single latency don't count. */ @@ -748,7 +748,7 @@ pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se) struct rq *rq = rq_of(cfs_rq); u64 pair_slice = rq->clock - cfs_rq->pair_start; - if (!cfs_rq->next || pair_slice > sched_slice(cfs_rq, cfs_rq->next)) { + if (!cfs_rq->next || pair_slice > sysctl_sched_min_granularity) { cfs_rq->pair_start = rq->clock; return se; } @@ -849,11 +849,31 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) hrtick_start(rq, delta); } } + +/* + * called from enqueue/dequeue and updates the hrtick when the + * current task is from our class and nr_running is low enough + * to matter. + */ +static void hrtick_update(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + + if (curr->sched_class != &fair_sched_class) + return; + + if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency) + hrtick_start_fair(rq, curr); +} #else /* !CONFIG_SCHED_HRTICK */ static inline void hrtick_start_fair(struct rq *rq, struct task_struct *p) { } + +static inline void hrtick_update(struct rq *rq) +{ +} #endif /* @@ -874,7 +894,7 @@ static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup) wakeup = 1; } - hrtick_start_fair(rq, rq->curr); + hrtick_update(rq); } /* @@ -896,7 +916,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep) sleep = 1; } - hrtick_start_fair(rq, rq->curr); + hrtick_update(rq); } /* @@ -1002,8 +1022,6 @@ static inline int wake_idle(int cpu, struct task_struct *p) #ifdef CONFIG_SMP -static const struct sched_class fair_sched_class; - #ifdef CONFIG_FAIR_GROUP_SCHED /* * effective_load() calculates the load change as seen from the root_task_group diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 7c9e8f4..fda0162 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -5,7 +5,7 @@ SCHED_FEAT(START_DEBIT, 1) SCHED_FEAT(AFFINE_WAKEUPS, 1) SCHED_FEAT(CACHE_HOT_BUDDY, 1) SCHED_FEAT(SYNC_WAKEUPS, 1) -SCHED_FEAT(HRTICK, 1) +SCHED_FEAT(HRTICK, 0) SCHED_FEAT(DOUBLE_TICK, 0) SCHED_FEAT(ASYM_GRAN, 1) SCHED_FEAT(LB_BIAS, 1) diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 3d14ce2..ee71bec 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -9,7 +9,7 @@ static int show_schedstat(struct seq_file *seq, void *v) { int cpu; - int mask_len = NR_CPUS/32 * 9; + int mask_len = DIV_ROUND_UP(NR_CPUS, 32) * 9; char *mask_str = kmalloc(mask_len, GFP_KERNEL); if (mask_str == NULL) diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index af3c7ce..8aff79d 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -37,9 +37,13 @@ struct stop_machine_data { /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */ static unsigned int num_threads; static atomic_t thread_ack; -static struct completion finished; static DEFINE_MUTEX(lock); +static struct workqueue_struct *stop_machine_wq; +static struct stop_machine_data active, idle; +static const cpumask_t *active_cpus; +static void *stop_machine_work; + static void set_state(enum stopmachine_state newstate) { /* Reset ack counter. */ @@ -51,21 +55,26 @@ static void set_state(enum stopmachine_state newstate) /* Last one to ack a state moves to the next state. */ static void ack_state(void) { - if (atomic_dec_and_test(&thread_ack)) { - /* If we're the last one to ack the EXIT, we're finished. */ - if (state == STOPMACHINE_EXIT) - complete(&finished); - else - set_state(state + 1); - } + if (atomic_dec_and_test(&thread_ack)) + set_state(state + 1); } -/* This is the actual thread which stops the CPU. It exits by itself rather - * than waiting for kthread_stop(), because it's easier for hotplug CPU. */ -static int stop_cpu(struct stop_machine_data *smdata) +/* This is the actual function which stops the CPU. It runs + * in the context of a dedicated stopmachine workqueue. */ +static void stop_cpu(struct work_struct *unused) { enum stopmachine_state curstate = STOPMACHINE_NONE; - + struct stop_machine_data *smdata = &idle; + int cpu = smp_processor_id(); + int err; + + if (!active_cpus) { + if (cpu == first_cpu(cpu_online_map)) + smdata = &active; + } else { + if (cpu_isset(cpu, *active_cpus)) + smdata = &active; + } /* Simple state machine */ do { /* Chill out and ensure we re-read stopmachine_state. */ @@ -78,9 +87,11 @@ static int stop_cpu(struct stop_machine_data *smdata) hard_irq_disable(); break; case STOPMACHINE_RUN: - /* |= allows error detection if functions on - * multiple CPUs. */ - smdata->fnret |= smdata->fn(smdata->data); + /* On multiple CPUs only a single error code + * is needed to tell that something failed. */ + err = smdata->fn(smdata->data); + if (err) + smdata->fnret = err; break; default: break; @@ -90,7 +101,6 @@ static int stop_cpu(struct stop_machine_data *smdata) } while (curstate != STOPMACHINE_EXIT); local_irq_enable(); - do_exit(0); } /* Callback for CPUs which aren't supposed to do anything. */ @@ -101,78 +111,34 @@ static int chill(void *unused) int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) { - int i, err; - struct stop_machine_data active, idle; - struct task_struct **threads; + struct work_struct *sm_work; + int i; + /* Set up initial state. */ + mutex_lock(&lock); + num_threads = num_online_cpus(); + active_cpus = cpus; active.fn = fn; active.data = data; active.fnret = 0; idle.fn = chill; idle.data = NULL; - /* This could be too big for stack on large machines. */ - threads = kcalloc(NR_CPUS, sizeof(threads[0]), GFP_KERNEL); - if (!threads) - return -ENOMEM; - - /* Set up initial state. */ - mutex_lock(&lock); - init_completion(&finished); - num_threads = num_online_cpus(); set_state(STOPMACHINE_PREPARE); - for_each_online_cpu(i) { - struct stop_machine_data *smdata = &idle; - struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; - - if (!cpus) { - if (i == first_cpu(cpu_online_map)) - smdata = &active; - } else { - if (cpu_isset(i, *cpus)) - smdata = &active; - } - - threads[i] = kthread_create((void *)stop_cpu, smdata, "kstop%u", - i); - if (IS_ERR(threads[i])) { - err = PTR_ERR(threads[i]); - threads[i] = NULL; - goto kill_threads; - } - - /* Place it onto correct cpu. */ - kthread_bind(threads[i], i); - - /* Make it highest prio. */ - if (sched_setscheduler_nocheck(threads[i], SCHED_FIFO, ¶m)) - BUG(); - } - - /* We've created all the threads. Wake them all: hold this CPU so one + /* Schedule the stop_cpu work on all cpus: hold this CPU so one * doesn't hit this CPU until we're ready. */ get_cpu(); - for_each_online_cpu(i) - wake_up_process(threads[i]); - + for_each_online_cpu(i) { + sm_work = percpu_ptr(stop_machine_work, i); + INIT_WORK(sm_work, stop_cpu); + queue_work_on(i, stop_machine_wq, sm_work); + } /* This will release the thread on our CPU. */ put_cpu(); - wait_for_completion(&finished); + flush_workqueue(stop_machine_wq); mutex_unlock(&lock); - - kfree(threads); - return active.fnret; - -kill_threads: - for_each_online_cpu(i) - if (threads[i]) - kthread_stop(threads[i]); - mutex_unlock(&lock); - - kfree(threads); - return err; } int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) @@ -187,3 +153,11 @@ int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) return ret; } EXPORT_SYMBOL_GPL(stop_machine); + +static int __init stop_machine_init(void) +{ + stop_machine_wq = create_rt_workqueue("kstop"); + stop_machine_work = alloc_percpu(struct work_struct); + return 0; +} +early_initcall(stop_machine_init); diff --git a/kernel/sys.c b/kernel/sys.c index 53879cd..31deba8 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1716,6 +1716,16 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, case PR_SET_TSC: error = SET_TSC_CTL(arg2); break; + case PR_GET_TIMERSLACK: + error = current->timer_slack_ns; + break; + case PR_SET_TIMERSLACK: + if (arg2 <= 0) + current->timer_slack_ns = + current->default_timer_slack_ns; + else + current->timer_slack_ns = arg2; + break; default: error = -EINVAL; break; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b3cc739..a13bd4d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -276,6 +276,16 @@ static struct ctl_table kern_table[] = { }, { .ctl_name = CTL_UNNUMBERED, + .procname = "sched_shares_thresh", + .data = &sysctl_sched_shares_thresh, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + }, + { + .ctl_name = CTL_UNNUMBERED, .procname = "sched_child_runs_first", .data = &sysctl_sched_child_runs_first, .maxlen = sizeof(unsigned int), diff --git a/kernel/time.c b/kernel/time.c index 6a08660..d63a433 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -669,3 +669,21 @@ EXPORT_SYMBOL(get_jiffies_64); #endif EXPORT_SYMBOL(jiffies); + +/* + * Add two timespec values and do a safety check for overflow. + * It's assumed that both values are valid (>= 0) + */ +struct timespec timespec_add_safe(const struct timespec lhs, + const struct timespec rhs) +{ + struct timespec res; + + set_normalized_timespec(&res, lhs.tv_sec + rhs.tv_sec, + lhs.tv_nsec + rhs.tv_nsec); + + if (res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec) + res.tv_sec = TIME_T_MAX; + + return res; +} diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 1a20715..8ff15e5 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -142,8 +142,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) time_state = TIME_OOP; printk(KERN_NOTICE "Clock: " "inserting leap second 23:59:60 UTC\n"); - leap_timer.expires = ktime_add_ns(leap_timer.expires, - NSEC_PER_SEC); + hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC); res = HRTIMER_RESTART; break; case TIME_DEL: diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 0581c11..5bbb104 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -300,7 +300,7 @@ void tick_nohz_stop_sched_tick(int inidle) goto out; } - ts->idle_tick = ts->sched_timer.expires; + ts->idle_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; ts->idle_jiffies = last_jiffies; rcu_enter_nohz(); @@ -380,21 +380,21 @@ ktime_t tick_nohz_get_sleep_length(void) static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) { hrtimer_cancel(&ts->sched_timer); - ts->sched_timer.expires = ts->idle_tick; + hrtimer_set_expires(&ts->sched_timer, ts->idle_tick); while (1) { /* Forward the time to expire in the future */ hrtimer_forward(&ts->sched_timer, now, tick_period); if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { - hrtimer_start(&ts->sched_timer, - ts->sched_timer.expires, + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS); /* Check, if the timer was already in the past */ if (hrtimer_active(&ts->sched_timer)) break; } else { - if (!tick_program_event(ts->sched_timer.expires, 0)) + if (!tick_program_event( + hrtimer_get_expires(&ts->sched_timer), 0)) break; } /* Update jiffies and reread time */ @@ -456,14 +456,16 @@ void tick_nohz_restart_sched_tick(void) */ ts->tick_stopped = 0; ts->idle_exittime = now; + tick_nohz_restart(ts, now); + local_irq_enable(); } static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now) { hrtimer_forward(&ts->sched_timer, now, tick_period); - return tick_program_event(ts->sched_timer.expires, 0); + return tick_program_event(hrtimer_get_expires(&ts->sched_timer), 0); } /* @@ -542,7 +544,7 @@ static void tick_nohz_switch_to_nohz(void) next = tick_init_jiffy_update(); for (;;) { - ts->sched_timer.expires = next; + hrtimer_set_expires(&ts->sched_timer, next); if (!tick_program_event(next, 0)) break; next = ktime_add(next, tick_period); @@ -567,11 +569,21 @@ static void tick_nohz_switch_to_nohz(void) static void tick_nohz_kick_tick(int cpu) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + ktime_t delta, now; if (!ts->tick_stopped) return; - tick_nohz_restart(ts, ktime_get()); + /* + * Do not touch the tick device, when the next expiry is either + * already reached or less/equal than the tick period. + */ + now = ktime_get(); + delta = ktime_sub(hrtimer_get_expires(&ts->sched_timer), now); + if (delta.tv64 <= tick_period.tv64) + return; + + tick_nohz_restart(ts, now); } #else @@ -668,16 +680,15 @@ void tick_setup_sched_timer(void) ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU; /* Get the next period (per cpu) */ - ts->sched_timer.expires = tick_init_jiffy_update(); + hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); offset = ktime_to_ns(tick_period) >> 1; do_div(offset, num_possible_cpus()); offset *= smp_processor_id(); - ts->sched_timer.expires = ktime_add_ns(ts->sched_timer.expires, offset); + hrtimer_add_expires_ns(&ts->sched_timer, offset); for (;;) { hrtimer_forward(&ts->sched_timer, now, tick_period); - hrtimer_start(&ts->sched_timer, ts->sched_timer.expires, - HRTIMER_MODE_ABS); + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS); /* Check, if the timer was already in the past */ if (hrtimer_active(&ts->sched_timer)) break; diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index f642691..a999b92 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -66,9 +66,11 @@ print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer, SEQ_printf(m, ", %s/%d", tmp, timer->start_pid); #endif SEQ_printf(m, "\n"); - SEQ_printf(m, " # expires at %Lu nsecs [in %Ld nsecs]\n", - (unsigned long long)ktime_to_ns(timer->expires), - (long long)(ktime_to_ns(timer->expires) - now)); + SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n", + (unsigned long long)ktime_to_ns(hrtimer_get_softexpires(timer)), + (unsigned long long)ktime_to_ns(hrtimer_get_expires(timer)), + (long long)(ktime_to_ns(hrtimer_get_softexpires(timer)) - now), + (long long)(ktime_to_ns(hrtimer_get_expires(timer)) - now)); } static void diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 714afad..f928f2a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -62,6 +62,7 @@ struct workqueue_struct { const char *name; int singlethread; int freezeable; /* Freeze threads during suspend */ + int rt; #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif @@ -766,6 +767,7 @@ init_cpu_workqueue(struct workqueue_struct *wq, int cpu) static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) { + struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; struct workqueue_struct *wq = cwq->wq; const char *fmt = is_single_threaded(wq) ? "%s" : "%s/%d"; struct task_struct *p; @@ -781,7 +783,8 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) */ if (IS_ERR(p)) return PTR_ERR(p); - + if (cwq->wq->rt) + sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); cwq->thread = p; return 0; @@ -801,6 +804,7 @@ static void start_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) struct workqueue_struct *__create_workqueue_key(const char *name, int singlethread, int freezeable, + int rt, struct lock_class_key *key, const char *lock_name) { @@ -822,6 +826,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name, lockdep_init_map(&wq->lockdep_map, lock_name, key, 0); wq->singlethread = singlethread; wq->freezeable = freezeable; + wq->rt = rt; INIT_LIST_HEAD(&wq->list); if (singlethread) { |