diff options
Diffstat (limited to 'kernel')
134 files changed, 11040 insertions, 5338 deletions
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 88c92fb4461..5068e2a4e75 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -199,4 +199,4 @@ config INLINE_WRITE_UNLOCK_IRQRESTORE def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE config MUTEX_SPIN_ON_OWNER - def_bool SMP && !DEBUG_MUTEXES && !HAVE_DEFAULT_NO_SPIN_MUTEXES + def_bool SMP && !DEBUG_MUTEXES diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index bf987b95b35..24e7cb0ba26 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -35,6 +35,7 @@ config PREEMPT_VOLUNTARY config PREEMPT bool "Preemptible Kernel (Low-Latency Desktop)" + select PREEMPT_COUNT help This option reduces the latency of the kernel by making all kernel code (that is not executing in a critical section) @@ -52,3 +53,5 @@ config PREEMPT endchoice +config PREEMPT_COUNT + bool
\ No newline at end of file diff --git a/kernel/Makefile b/kernel/Makefile index 85cbfb31e73..d06467fc8f7 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -21,7 +21,6 @@ CFLAGS_REMOVE_mutex-debug.o = -pg CFLAGS_REMOVE_rtmutex-debug.o = -pg CFLAGS_REMOVE_cgroup-debug.o = -pg CFLAGS_REMOVE_sched_clock.o = -pg -CFLAGS_REMOVE_perf_event.o = -pg CFLAGS_REMOVE_irq_work.o = -pg endif @@ -62,7 +61,6 @@ obj-$(CONFIG_COMPAT) += compat.o obj-$(CONFIG_CGROUPS) += cgroup.o obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o obj-$(CONFIG_CPUSETS) += cpuset.o -obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o obj-$(CONFIG_UTS_NS) += utsname.o obj-$(CONFIG_USER_NS) += user_namespace.o obj-$(CONFIG_PID_NS) += pid_namespace.o @@ -103,8 +101,9 @@ obj-$(CONFIG_RING_BUFFER) += trace/ obj-$(CONFIG_TRACEPOINTS) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o obj-$(CONFIG_IRQ_WORK) += irq_work.o -obj-$(CONFIG_PERF_EVENTS) += perf_event.o -obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o + +obj-$(CONFIG_PERF_EVENTS) += events/ + obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o obj-$(CONFIG_PADATA) += padata.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o @@ -126,11 +125,10 @@ targets += config_data.gz $(obj)/config_data.gz: $(KCONFIG_CONFIG) FORCE $(call if_changed,gzip) -quiet_cmd_ikconfiggz = IKCFG $@ - cmd_ikconfiggz = (echo "static const char kernel_config_data[] __used = MAGIC_START"; cat $< | scripts/bin2c; echo "MAGIC_END;") > $@ + filechk_ikconfiggz = (echo "static const char kernel_config_data[] __used = MAGIC_START"; cat $< | scripts/bin2c; echo "MAGIC_END;") targets += config_data.h $(obj)/config_data.h: $(obj)/config_data.gz FORCE - $(call if_changed,ikconfiggz) + $(call filechk,ikconfiggz) $(obj)/time.o: $(obj)/timeconst.h diff --git a/kernel/async.c b/kernel/async.c index cd9dbb913c7..d5fe7af0de2 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -49,12 +49,13 @@ asynchronous and synchronous parts of the kernel. */ #include <linux/async.h> +#include <linux/atomic.h> +#include <linux/ktime.h> #include <linux/module.h> #include <linux/wait.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/workqueue.h> -#include <asm/atomic.h> static async_cookie_t next_cookie = 1; @@ -128,7 +129,8 @@ static void async_run_entry_fn(struct work_struct *work) /* 2) run (and print duration) */ if (initcall_debug && system_state == SYSTEM_BOOTING) { - printk("calling %lli_%pF @ %i\n", (long long)entry->cookie, + printk(KERN_DEBUG "calling %lli_%pF @ %i\n", + (long long)entry->cookie, entry->func, task_pid_nr(current)); calltime = ktime_get(); } @@ -136,7 +138,7 @@ static void async_run_entry_fn(struct work_struct *work) if (initcall_debug && system_state == SYSTEM_BOOTING) { rettime = ktime_get(); delta = ktime_sub(rettime, calltime); - printk("initcall %lli_%pF returned 0 after %lld usecs\n", + printk(KERN_DEBUG "initcall %lli_%pF returned 0 after %lld usecs\n", (long long)entry->cookie, entry->func, (long long)ktime_to_ns(delta) >> 10); @@ -270,7 +272,7 @@ void async_synchronize_cookie_domain(async_cookie_t cookie, ktime_t starttime, delta, endtime; if (initcall_debug && system_state == SYSTEM_BOOTING) { - printk("async_waiting @ %i\n", task_pid_nr(current)); + printk(KERN_DEBUG "async_waiting @ %i\n", task_pid_nr(current)); starttime = ktime_get(); } @@ -280,7 +282,7 @@ void async_synchronize_cookie_domain(async_cookie_t cookie, endtime = ktime_get(); delta = ktime_sub(endtime, starttime); - printk("async_continuing @ %i after %lli usec\n", + printk(KERN_DEBUG "async_continuing @ %i after %lli usec\n", task_pid_nr(current), (long long)ktime_to_ns(delta) >> 10); } diff --git a/kernel/audit.c b/kernel/audit.c index 93950031706..0a1355ca3d7 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -43,7 +43,7 @@ #include <linux/init.h> #include <asm/types.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/slab.h> @@ -55,6 +55,9 @@ #include <net/sock.h> #include <net/netlink.h> #include <linux/skbuff.h> +#ifdef CONFIG_SECURITY +#include <linux/security.h> +#endif #include <linux/netlink.h> #include <linux/freezer.h> #include <linux/tty.h> @@ -1502,6 +1505,32 @@ void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, } } +#ifdef CONFIG_SECURITY +/** + * audit_log_secctx - Converts and logs SELinux context + * @ab: audit_buffer + * @secid: security number + * + * This is a helper function that calls security_secid_to_secctx to convert + * secid to secctx and then adds the (converted) SELinux context to the audit + * log by calling audit_log_format, thus also preventing leak of internal secid + * to userspace. If secid cannot be converted audit_panic is called. + */ +void audit_log_secctx(struct audit_buffer *ab, u32 secid) +{ + u32 len; + char *secctx; + + if (security_secid_to_secctx(secid, &secctx, &len)) { + audit_panic("Cannot convert secid to context"); + } else { + audit_log_format(ab, " obj=%s", secctx); + security_release_secctx(secctx, len); + } +} +EXPORT_SYMBOL(audit_log_secctx); +#endif + EXPORT_SYMBOL(audit_log_start); EXPORT_SYMBOL(audit_log_end); EXPORT_SYMBOL(audit_log_format); diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index e99dda04b12..5bf0790497e 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -93,16 +93,10 @@ static inline void get_tree(struct audit_tree *tree) atomic_inc(&tree->count); } -static void __put_tree(struct rcu_head *rcu) -{ - struct audit_tree *tree = container_of(rcu, struct audit_tree, head); - kfree(tree); -} - static inline void put_tree(struct audit_tree *tree) { if (atomic_dec_and_test(&tree->count)) - call_rcu(&tree->head, __put_tree); + kfree_rcu(tree, head); } /* to avoid bringing the entire thing in audit.h */ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index b33513a08be..ce4b054acee 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -44,7 +44,7 @@ #include <linux/init.h> #include <asm/types.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/mm.h> @@ -443,17 +443,25 @@ static int match_tree_refs(struct audit_context *ctx, struct audit_tree *tree) /* Determine if any context name data matches a rule's watch data */ /* Compare a task_struct with an audit_rule. Return 1 on match, 0 - * otherwise. */ + * otherwise. + * + * If task_creation is true, this is an explicit indication that we are + * filtering a task rule at task creation time. This and tsk == current are + * the only situations where tsk->cred may be accessed without an rcu read lock. + */ static int audit_filter_rules(struct task_struct *tsk, struct audit_krule *rule, struct audit_context *ctx, struct audit_names *name, - enum audit_state *state) + enum audit_state *state, + bool task_creation) { - const struct cred *cred = get_task_cred(tsk); + const struct cred *cred; int i, j, need_sid = 1; u32 sid; + cred = rcu_dereference_check(tsk->cred, tsk == current || task_creation); + for (i = 0; i < rule->field_count; i++) { struct audit_field *f = &rule->fields[i]; int result = 0; @@ -637,10 +645,8 @@ static int audit_filter_rules(struct task_struct *tsk, break; } - if (!result) { - put_cred(cred); + if (!result) return 0; - } } if (ctx) { @@ -656,7 +662,6 @@ static int audit_filter_rules(struct task_struct *tsk, case AUDIT_NEVER: *state = AUDIT_DISABLED; break; case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break; } - put_cred(cred); return 1; } @@ -671,7 +676,8 @@ static enum audit_state audit_filter_task(struct task_struct *tsk, char **key) rcu_read_lock(); list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TASK], list) { - if (audit_filter_rules(tsk, &e->rule, NULL, NULL, &state)) { + if (audit_filter_rules(tsk, &e->rule, NULL, NULL, + &state, true)) { if (state == AUDIT_RECORD_CONTEXT) *key = kstrdup(e->rule.filterkey, GFP_ATOMIC); rcu_read_unlock(); @@ -705,7 +711,7 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk, list_for_each_entry_rcu(e, list, list) { if ((e->rule.mask[word] & bit) == bit && audit_filter_rules(tsk, &e->rule, ctx, NULL, - &state)) { + &state, false)) { rcu_read_unlock(); ctx->current_state = state; return state; @@ -743,7 +749,8 @@ void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx) list_for_each_entry_rcu(e, list, list) { if ((e->rule.mask[word] & bit) == bit && - audit_filter_rules(tsk, &e->rule, ctx, n, &state)) { + audit_filter_rules(tsk, &e->rule, ctx, n, + &state, false)) { rcu_read_unlock(); ctx->current_state = state; return; diff --git a/kernel/capability.c b/kernel/capability.c index bf0c734d0c1..283c529f8b1 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -22,12 +22,8 @@ */ const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET; -const kernel_cap_t __cap_full_set = CAP_FULL_SET; -const kernel_cap_t __cap_init_eff_set = CAP_INIT_EFF_SET; EXPORT_SYMBOL(__cap_empty_set); -EXPORT_SYMBOL(__cap_full_set); -EXPORT_SYMBOL(__cap_init_eff_set); int file_caps_enabled = 1; @@ -399,3 +395,15 @@ bool task_ns_capable(struct task_struct *t, int cap) return ns_capable(task_cred_xxx(t, user)->user_ns, cap); } EXPORT_SYMBOL(task_ns_capable); + +/** + * nsown_capable - Check superior capability to one's own user_ns + * @cap: The capability in question + * + * Return true if the current task has the given superior capability + * targeted at its own user namespace. + */ +bool nsown_capable(int cap) +{ + return ns_capable(current_user_ns(), cap); +} diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 25c7eb52de1..1d2b6ceea95 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -27,9 +27,11 @@ */ #include <linux/cgroup.h> +#include <linux/cred.h> #include <linux/ctype.h> #include <linux/errno.h> #include <linux/fs.h> +#include <linux/init_task.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/mm.h> @@ -57,8 +59,9 @@ #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */ #include <linux/eventfd.h> #include <linux/poll.h> +#include <linux/flex_array.h> /* used in cgroup_attach_proc */ -#include <asm/atomic.h> +#include <linux/atomic.h> static DEFINE_MUTEX(cgroup_mutex); @@ -326,12 +329,6 @@ static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[]) return &css_set_table[index]; } -static void free_css_set_rcu(struct rcu_head *obj) -{ - struct css_set *cg = container_of(obj, struct css_set, rcu_head); - kfree(cg); -} - /* We don't maintain the lists running through each css_set to its * task until after the first call to cgroup_iter_start(). This * reduces the fork()/exit() overhead for people who have cgroups @@ -375,7 +372,7 @@ static void __put_css_set(struct css_set *cg, int taskexit) } write_unlock(&css_set_lock); - call_rcu(&cg->rcu_head, free_css_set_rcu); + kfree_rcu(cg, rcu_head); } /* @@ -812,13 +809,6 @@ static int cgroup_call_pre_destroy(struct cgroup *cgrp) return ret; } -static void free_cgroup_rcu(struct rcu_head *obj) -{ - struct cgroup *cgrp = container_of(obj, struct cgroup, rcu_head); - - kfree(cgrp); -} - static void cgroup_diput(struct dentry *dentry, struct inode *inode) { /* is dentry a directory ? if so, kfree() associated cgroup */ @@ -856,7 +846,7 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) */ BUG_ON(!list_empty(&cgrp->pidlists)); - call_rcu(&cgrp->rcu_head, free_cgroup_rcu); + kfree_rcu(cgrp, rcu_head); } iput(inode); } @@ -1526,6 +1516,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, struct cgroup *root_cgrp = &root->top_cgroup; struct inode *inode; struct cgroupfs_root *existing_root; + const struct cred *cred; int i; BUG_ON(sb->s_root != NULL); @@ -1605,7 +1596,9 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, BUG_ON(!list_empty(&root_cgrp->children)); BUG_ON(root->number_of_cgroups != 1); + cred = override_creds(&init_cred); cgroup_populate_dir(root_cgrp); + revert_creds(cred); mutex_unlock(&cgroup_mutex); mutex_unlock(&inode->i_mutex); } else { @@ -1709,7 +1702,6 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) { char *start; struct dentry *dentry = rcu_dereference_check(cgrp->dentry, - rcu_read_lock_held() || cgroup_lock_is_held()); if (!dentry || cgrp == dummytop) { @@ -1735,7 +1727,6 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) break; dentry = rcu_dereference_check(cgrp->dentry, - rcu_read_lock_held() || cgroup_lock_is_held()); if (!cgrp->parent) continue; @@ -1748,6 +1739,76 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) } EXPORT_SYMBOL_GPL(cgroup_path); +/* + * cgroup_task_migrate - move a task from one cgroup to another. + * + * 'guarantee' is set if the caller promises that a new css_set for the task + * will already exist. If not set, this function might sleep, and can fail with + * -ENOMEM. Otherwise, it can only fail with -ESRCH. + */ +static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, + struct task_struct *tsk, bool guarantee) +{ + struct css_set *oldcg; + struct css_set *newcg; + + /* + * get old css_set. we need to take task_lock and refcount it, because + * an exiting task can change its css_set to init_css_set and drop its + * old one without taking cgroup_mutex. + */ + task_lock(tsk); + oldcg = tsk->cgroups; + get_css_set(oldcg); + task_unlock(tsk); + + /* locate or allocate a new css_set for this task. */ + if (guarantee) { + /* we know the css_set we want already exists. */ + struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT]; + read_lock(&css_set_lock); + newcg = find_existing_css_set(oldcg, cgrp, template); + BUG_ON(!newcg); + get_css_set(newcg); + read_unlock(&css_set_lock); + } else { + might_sleep(); + /* find_css_set will give us newcg already referenced. */ + newcg = find_css_set(oldcg, cgrp); + if (!newcg) { + put_css_set(oldcg); + return -ENOMEM; + } + } + put_css_set(oldcg); + + /* if PF_EXITING is set, the tsk->cgroups pointer is no longer safe. */ + task_lock(tsk); + if (tsk->flags & PF_EXITING) { + task_unlock(tsk); + put_css_set(newcg); + return -ESRCH; + } + rcu_assign_pointer(tsk->cgroups, newcg); + task_unlock(tsk); + + /* Update the css_set linked lists if we're using them */ + write_lock(&css_set_lock); + if (!list_empty(&tsk->cg_list)) + list_move(&tsk->cg_list, &newcg->tasks); + write_unlock(&css_set_lock); + + /* + * We just gained a reference on oldcg by taking it from the task. As + * trading it for newcg is protected by cgroup_mutex, we're safe to drop + * it here; it will be freed under RCU. + */ + put_css_set(oldcg); + + set_bit(CGRP_RELEASABLE, &oldcgrp->flags); + return 0; +} + /** * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp' * @cgrp: the cgroup the task is attaching to @@ -1758,11 +1819,9 @@ EXPORT_SYMBOL_GPL(cgroup_path); */ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) { - int retval = 0; + int retval; struct cgroup_subsys *ss, *failed_ss = NULL; struct cgroup *oldcgrp; - struct css_set *cg; - struct css_set *newcg; struct cgroupfs_root *root = cgrp->root; /* Nothing to do if the task is already in that cgroup */ @@ -1772,7 +1831,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) for_each_subsys(root, ss) { if (ss->can_attach) { - retval = ss->can_attach(ss, cgrp, tsk, false); + retval = ss->can_attach(ss, cgrp, tsk); if (retval) { /* * Remember on which subsystem the can_attach() @@ -1784,46 +1843,29 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) goto out; } } + if (ss->can_attach_task) { + retval = ss->can_attach_task(cgrp, tsk); + if (retval) { + failed_ss = ss; + goto out; + } + } } - task_lock(tsk); - cg = tsk->cgroups; - get_css_set(cg); - task_unlock(tsk); - /* - * Locate or allocate a new css_set for this task, - * based on its final set of cgroups - */ - newcg = find_css_set(cg, cgrp); - put_css_set(cg); - if (!newcg) { - retval = -ENOMEM; + retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, false); + if (retval) goto out; - } - - task_lock(tsk); - if (tsk->flags & PF_EXITING) { - task_unlock(tsk); - put_css_set(newcg); - retval = -ESRCH; - goto out; - } - rcu_assign_pointer(tsk->cgroups, newcg); - task_unlock(tsk); - - /* Update the css_set linked lists if we're using them */ - write_lock(&css_set_lock); - if (!list_empty(&tsk->cg_list)) - list_move(&tsk->cg_list, &newcg->tasks); - write_unlock(&css_set_lock); for_each_subsys(root, ss) { + if (ss->pre_attach) + ss->pre_attach(cgrp); + if (ss->attach_task) + ss->attach_task(cgrp, tsk); if (ss->attach) - ss->attach(ss, cgrp, oldcgrp, tsk, false); + ss->attach(ss, cgrp, oldcgrp, tsk); } - set_bit(CGRP_RELEASABLE, &oldcgrp->flags); + synchronize_rcu(); - put_css_set(cg); /* * wake up rmdir() waiter. the rmdir should fail since the cgroup @@ -1842,7 +1884,7 @@ out: */ break; if (ss->cancel_attach) - ss->cancel_attach(ss, cgrp, tsk, false); + ss->cancel_attach(ss, cgrp, tsk); } } return retval; @@ -1873,49 +1915,370 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) EXPORT_SYMBOL_GPL(cgroup_attach_task_all); /* - * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex - * held. May take task_lock of task + * cgroup_attach_proc works in two stages, the first of which prefetches all + * new css_sets needed (to make sure we have enough memory before committing + * to the move) and stores them in a list of entries of the following type. + * TODO: possible optimization: use css_set->rcu_head for chaining instead + */ +struct cg_list_entry { + struct css_set *cg; + struct list_head links; +}; + +static bool css_set_check_fetched(struct cgroup *cgrp, + struct task_struct *tsk, struct css_set *cg, + struct list_head *newcg_list) +{ + struct css_set *newcg; + struct cg_list_entry *cg_entry; + struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT]; + + read_lock(&css_set_lock); + newcg = find_existing_css_set(cg, cgrp, template); + if (newcg) + get_css_set(newcg); + read_unlock(&css_set_lock); + + /* doesn't exist at all? */ + if (!newcg) + return false; + /* see if it's already in the list */ + list_for_each_entry(cg_entry, newcg_list, links) { + if (cg_entry->cg == newcg) { + put_css_set(newcg); + return true; + } + } + + /* not found */ + put_css_set(newcg); + return false; +} + +/* + * Find the new css_set and store it in the list in preparation for moving the + * given task to the given cgroup. Returns 0 or -ENOMEM. + */ +static int css_set_prefetch(struct cgroup *cgrp, struct css_set *cg, + struct list_head *newcg_list) +{ + struct css_set *newcg; + struct cg_list_entry *cg_entry; + + /* ensure a new css_set will exist for this thread */ + newcg = find_css_set(cg, cgrp); + if (!newcg) + return -ENOMEM; + /* add it to the list */ + cg_entry = kmalloc(sizeof(struct cg_list_entry), GFP_KERNEL); + if (!cg_entry) { + put_css_set(newcg); + return -ENOMEM; + } + cg_entry->cg = newcg; + list_add(&cg_entry->links, newcg_list); + return 0; +} + +/** + * cgroup_attach_proc - attach all threads in a threadgroup to a cgroup + * @cgrp: the cgroup to attach to + * @leader: the threadgroup leader task_struct of the group to be attached + * + * Call holding cgroup_mutex and the threadgroup_fork_lock of the leader. Will + * take task_lock of each thread in leader's threadgroup individually in turn. + */ +int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) +{ + int retval, i, group_size; + struct cgroup_subsys *ss, *failed_ss = NULL; + bool cancel_failed_ss = false; + /* guaranteed to be initialized later, but the compiler needs this */ + struct cgroup *oldcgrp = NULL; + struct css_set *oldcg; + struct cgroupfs_root *root = cgrp->root; + /* threadgroup list cursor and array */ + struct task_struct *tsk; + struct flex_array *group; + /* + * we need to make sure we have css_sets for all the tasks we're + * going to move -before- we actually start moving them, so that in + * case we get an ENOMEM we can bail out before making any changes. + */ + struct list_head newcg_list; + struct cg_list_entry *cg_entry, *temp_nobe; + + /* + * step 0: in order to do expensive, possibly blocking operations for + * every thread, we cannot iterate the thread group list, since it needs + * rcu or tasklist locked. instead, build an array of all threads in the + * group - threadgroup_fork_lock prevents new threads from appearing, + * and if threads exit, this will just be an over-estimate. + */ + group_size = get_nr_threads(leader); + /* flex_array supports very large thread-groups better than kmalloc. */ + group = flex_array_alloc(sizeof(struct task_struct *), group_size, + GFP_KERNEL); + if (!group) + return -ENOMEM; + /* pre-allocate to guarantee space while iterating in rcu read-side. */ + retval = flex_array_prealloc(group, 0, group_size - 1, GFP_KERNEL); + if (retval) + goto out_free_group_list; + + /* prevent changes to the threadgroup list while we take a snapshot. */ + rcu_read_lock(); + if (!thread_group_leader(leader)) { + /* + * a race with de_thread from another thread's exec() may strip + * us of our leadership, making while_each_thread unsafe to use + * on this task. if this happens, there is no choice but to + * throw this task away and try again (from cgroup_procs_write); + * this is "double-double-toil-and-trouble-check locking". + */ + rcu_read_unlock(); + retval = -EAGAIN; + goto out_free_group_list; + } + /* take a reference on each task in the group to go in the array. */ + tsk = leader; + i = 0; + do { + /* as per above, nr_threads may decrease, but not increase. */ + BUG_ON(i >= group_size); + get_task_struct(tsk); + /* + * saying GFP_ATOMIC has no effect here because we did prealloc + * earlier, but it's good form to communicate our expectations. + */ + retval = flex_array_put_ptr(group, i, tsk, GFP_ATOMIC); + BUG_ON(retval != 0); + i++; + } while_each_thread(leader, tsk); + /* remember the number of threads in the array for later. */ + group_size = i; + rcu_read_unlock(); + + /* + * step 1: check that we can legitimately attach to the cgroup. + */ + for_each_subsys(root, ss) { + if (ss->can_attach) { + retval = ss->can_attach(ss, cgrp, leader); + if (retval) { + failed_ss = ss; + goto out_cancel_attach; + } + } + /* a callback to be run on every thread in the threadgroup. */ + if (ss->can_attach_task) { + /* run on each task in the threadgroup. */ + for (i = 0; i < group_size; i++) { + tsk = flex_array_get_ptr(group, i); + retval = ss->can_attach_task(cgrp, tsk); + if (retval) { + failed_ss = ss; + cancel_failed_ss = true; + goto out_cancel_attach; + } + } + } + } + + /* + * step 2: make sure css_sets exist for all threads to be migrated. + * we use find_css_set, which allocates a new one if necessary. + */ + INIT_LIST_HEAD(&newcg_list); + for (i = 0; i < group_size; i++) { + tsk = flex_array_get_ptr(group, i); + /* nothing to do if this task is already in the cgroup */ + oldcgrp = task_cgroup_from_root(tsk, root); + if (cgrp == oldcgrp) + continue; + /* get old css_set pointer */ + task_lock(tsk); + if (tsk->flags & PF_EXITING) { + /* ignore this task if it's going away */ + task_unlock(tsk); + continue; + } + oldcg = tsk->cgroups; + get_css_set(oldcg); + task_unlock(tsk); + /* see if the new one for us is already in the list? */ + if (css_set_check_fetched(cgrp, tsk, oldcg, &newcg_list)) { + /* was already there, nothing to do. */ + put_css_set(oldcg); + } else { + /* we don't already have it. get new one. */ + retval = css_set_prefetch(cgrp, oldcg, &newcg_list); + put_css_set(oldcg); + if (retval) + goto out_list_teardown; + } + } + + /* + * step 3: now that we're guaranteed success wrt the css_sets, proceed + * to move all tasks to the new cgroup, calling ss->attach_task for each + * one along the way. there are no failure cases after here, so this is + * the commit point. + */ + for_each_subsys(root, ss) { + if (ss->pre_attach) + ss->pre_attach(cgrp); + } + for (i = 0; i < group_size; i++) { + tsk = flex_array_get_ptr(group, i); + /* leave current thread as it is if it's already there */ + oldcgrp = task_cgroup_from_root(tsk, root); + if (cgrp == oldcgrp) + continue; + /* attach each task to each subsystem */ + for_each_subsys(root, ss) { + if (ss->attach_task) + ss->attach_task(cgrp, tsk); + } + /* if the thread is PF_EXITING, it can just get skipped. */ + retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, true); + BUG_ON(retval != 0 && retval != -ESRCH); + } + /* nothing is sensitive to fork() after this point. */ + + /* + * step 4: do expensive, non-thread-specific subsystem callbacks. + * TODO: if ever a subsystem needs to know the oldcgrp for each task + * being moved, this call will need to be reworked to communicate that. + */ + for_each_subsys(root, ss) { + if (ss->attach) + ss->attach(ss, cgrp, oldcgrp, leader); + } + + /* + * step 5: success! and cleanup + */ + synchronize_rcu(); + cgroup_wakeup_rmdir_waiter(cgrp); + retval = 0; +out_list_teardown: + /* clean up the list of prefetched css_sets. */ + list_for_each_entry_safe(cg_entry, temp_nobe, &newcg_list, links) { + list_del(&cg_entry->links); + put_css_set(cg_entry->cg); + kfree(cg_entry); + } +out_cancel_attach: + /* same deal as in cgroup_attach_task */ + if (retval) { + for_each_subsys(root, ss) { + if (ss == failed_ss) { + if (cancel_failed_ss && ss->cancel_attach) + ss->cancel_attach(ss, cgrp, leader); + break; + } + if (ss->cancel_attach) + ss->cancel_attach(ss, cgrp, leader); + } + } + /* clean up the array of referenced threads in the group. */ + for (i = 0; i < group_size; i++) { + tsk = flex_array_get_ptr(group, i); + put_task_struct(tsk); + } +out_free_group_list: + flex_array_free(group); + return retval; +} + +/* + * Find the task_struct of the task to attach by vpid and pass it along to the + * function to attach either it or all tasks in its threadgroup. Will take + * cgroup_mutex; may take task_lock of task. */ -static int attach_task_by_pid(struct cgroup *cgrp, u64 pid) +static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup) { struct task_struct *tsk; const struct cred *cred = current_cred(), *tcred; int ret; + if (!cgroup_lock_live_group(cgrp)) + return -ENODEV; + if (pid) { rcu_read_lock(); tsk = find_task_by_vpid(pid); - if (!tsk || tsk->flags & PF_EXITING) { + if (!tsk) { rcu_read_unlock(); + cgroup_unlock(); + return -ESRCH; + } + if (threadgroup) { + /* + * RCU protects this access, since tsk was found in the + * tid map. a race with de_thread may cause group_leader + * to stop being the leader, but cgroup_attach_proc will + * detect it later. + */ + tsk = tsk->group_leader; + } else if (tsk->flags & PF_EXITING) { + /* optimization for the single-task-only case */ + rcu_read_unlock(); + cgroup_unlock(); return -ESRCH; } + /* + * even if we're attaching all tasks in the thread group, we + * only need to check permissions on one of them. + */ tcred = __task_cred(tsk); if (cred->euid && cred->euid != tcred->uid && cred->euid != tcred->suid) { rcu_read_unlock(); + cgroup_unlock(); return -EACCES; } get_task_struct(tsk); rcu_read_unlock(); } else { - tsk = current; + if (threadgroup) + tsk = current->group_leader; + else + tsk = current; get_task_struct(tsk); } - ret = cgroup_attach_task(cgrp, tsk); + if (threadgroup) { + threadgroup_fork_write_lock(tsk); + ret = cgroup_attach_proc(cgrp, tsk); + threadgroup_fork_write_unlock(tsk); + } else { + ret = cgroup_attach_task(cgrp, tsk); + } put_task_struct(tsk); + cgroup_unlock(); return ret; } static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid) { + return attach_task_by_pid(cgrp, pid, false); +} + +static int cgroup_procs_write(struct cgroup *cgrp, struct cftype *cft, u64 tgid) +{ int ret; - if (!cgroup_lock_live_group(cgrp)) - return -ENODEV; - ret = attach_task_by_pid(cgrp, pid); - cgroup_unlock(); + do { + /* + * attach_proc fails with -EAGAIN if threadgroup leadership + * changes in the middle of the operation, in which case we need + * to find the task_struct for the new leader and start over. + */ + ret = attach_task_by_pid(cgrp, tgid, true); + } while (ret == -EAGAIN); return ret; } @@ -3182,7 +3545,8 @@ static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft, } /* the process need read permission on control file */ - ret = file_permission(cfile, MAY_READ); + /* AV: shouldn't we check that it's been opened for read instead? */ + ret = inode_permission(cfile->f_path.dentry->d_inode, MAY_READ); if (ret < 0) goto fail; @@ -3272,9 +3636,9 @@ static struct cftype files[] = { { .name = CGROUP_FILE_GENERIC_PREFIX "procs", .open = cgroup_procs_open, - /* .write_u64 = cgroup_procs_write, TODO */ + .write_u64 = cgroup_procs_write, .release = cgroup_pidlist_release, - .mode = S_IRUGO, + .mode = S_IRUGO | S_IWUSR, }, { .name = "notify_on_release", @@ -4270,122 +4634,6 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks) } /** - * cgroup_clone - clone the cgroup the given subsystem is attached to - * @tsk: the task to be moved - * @subsys: the given subsystem - * @nodename: the name for the new cgroup - * - * Duplicate the current cgroup in the hierarchy that the given - * subsystem is attached to, and move this task into the new - * child. - */ -int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, - char *nodename) -{ - struct dentry *dentry; - int ret = 0; - struct cgroup *parent, *child; - struct inode *inode; - struct css_set *cg; - struct cgroupfs_root *root; - struct cgroup_subsys *ss; - - /* We shouldn't be called by an unregistered subsystem */ - BUG_ON(!subsys->active); - - /* First figure out what hierarchy and cgroup we're dealing - * with, and pin them so we can drop cgroup_mutex */ - mutex_lock(&cgroup_mutex); - again: - root = subsys->root; - if (root == &rootnode) { - mutex_unlock(&cgroup_mutex); - return 0; - } - - /* Pin the hierarchy */ - if (!atomic_inc_not_zero(&root->sb->s_active)) { - /* We race with the final deactivate_super() */ - mutex_unlock(&cgroup_mutex); - return 0; - } - - /* Keep the cgroup alive */ - task_lock(tsk); - parent = task_cgroup(tsk, subsys->subsys_id); - cg = tsk->cgroups; - get_css_set(cg); - task_unlock(tsk); - - mutex_unlock(&cgroup_mutex); - - /* Now do the VFS work to create a cgroup */ - inode = parent->dentry->d_inode; - - /* Hold the parent directory mutex across this operation to - * stop anyone else deleting the new cgroup */ - mutex_lock(&inode->i_mutex); - dentry = lookup_one_len(nodename, parent->dentry, strlen(nodename)); - if (IS_ERR(dentry)) { - printk(KERN_INFO - "cgroup: Couldn't allocate dentry for %s: %ld\n", nodename, - PTR_ERR(dentry)); - ret = PTR_ERR(dentry); - goto out_release; - } - - /* Create the cgroup directory, which also creates the cgroup */ - ret = vfs_mkdir(inode, dentry, 0755); - child = __d_cgrp(dentry); - dput(dentry); - if (ret) { - printk(KERN_INFO - "Failed to create cgroup %s: %d\n", nodename, - ret); - goto out_release; - } - - /* The cgroup now exists. Retake cgroup_mutex and check - * that we're still in the same state that we thought we - * were. */ - mutex_lock(&cgroup_mutex); - if ((root != subsys->root) || - (parent != task_cgroup(tsk, subsys->subsys_id))) { - /* Aargh, we raced ... */ - mutex_unlock(&inode->i_mutex); - put_css_set(cg); - - deactivate_super(root->sb); - /* The cgroup is still accessible in the VFS, but - * we're not going to try to rmdir() it at this - * point. */ - printk(KERN_INFO - "Race in cgroup_clone() - leaking cgroup %s\n", - nodename); - goto again; - } - - /* do any required auto-setup */ - for_each_subsys(root, ss) { - if (ss->post_clone) - ss->post_clone(ss, child); - } - - /* All seems fine. Finish by moving the task into the new cgroup */ - ret = cgroup_attach_task(child, tsk); - mutex_unlock(&cgroup_mutex); - - out_release: - mutex_unlock(&inode->i_mutex); - - mutex_lock(&cgroup_mutex); - put_css_set(cg); - mutex_unlock(&cgroup_mutex); - deactivate_super(root->sb); - return ret; -} - -/** * cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp * @cgrp: the cgroup in question * @task: the task in question @@ -4569,8 +4817,7 @@ unsigned short css_id(struct cgroup_subsys_state *css) * on this or this is under rcu_read_lock(). Once css->id is allocated, * it's unchanged until freed. */ - cssid = rcu_dereference_check(css->id, - rcu_read_lock_held() || atomic_read(&css->refcnt)); + cssid = rcu_dereference_check(css->id, atomic_read(&css->refcnt)); if (cssid) return cssid->id; @@ -4582,8 +4829,7 @@ unsigned short css_depth(struct cgroup_subsys_state *css) { struct css_id *cssid; - cssid = rcu_dereference_check(css->id, - rcu_read_lock_held() || atomic_read(&css->refcnt)); + cssid = rcu_dereference_check(css->id, atomic_read(&css->refcnt)); if (cssid) return cssid->depth; @@ -4623,14 +4869,6 @@ bool css_is_ancestor(struct cgroup_subsys_state *child, return ret; } -static void __free_css_id_cb(struct rcu_head *head) -{ - struct css_id *id; - - id = container_of(head, struct css_id, rcu_head); - kfree(id); -} - void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css) { struct css_id *id = css->id; @@ -4645,7 +4883,7 @@ void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css) spin_lock(&ss->id_lock); idr_remove(&ss->idr, id->id); spin_unlock(&ss->id_lock); - call_rcu(&id->rcu_head, __free_css_id_cb); + kfree_rcu(id, rcu_head); } EXPORT_SYMBOL_GPL(free_css_id); diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index e7bebb7c6c3..e691818d7e4 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -160,7 +160,7 @@ static void freezer_destroy(struct cgroup_subsys *ss, */ static int freezer_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup, - struct task_struct *task, bool threadgroup) + struct task_struct *task) { struct freezer *freezer; @@ -172,26 +172,17 @@ static int freezer_can_attach(struct cgroup_subsys *ss, if (freezer->state != CGROUP_THAWED) return -EBUSY; + return 0; +} + +static int freezer_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk) +{ rcu_read_lock(); - if (__cgroup_freezing_or_frozen(task)) { + if (__cgroup_freezing_or_frozen(tsk)) { rcu_read_unlock(); return -EBUSY; } rcu_read_unlock(); - - if (threadgroup) { - struct task_struct *c; - - rcu_read_lock(); - list_for_each_entry_rcu(c, &task->thread_group, thread_group) { - if (__cgroup_freezing_or_frozen(c)) { - rcu_read_unlock(); - return -EBUSY; - } - } - rcu_read_unlock(); - } - return 0; } @@ -390,6 +381,9 @@ struct cgroup_subsys freezer_subsys = { .populate = freezer_populate, .subsys_id = freezer_subsys_id, .can_attach = freezer_can_attach, + .can_attach_task = freezer_can_attach_task, + .pre_attach = NULL, + .attach_task = NULL, .attach = NULL, .fork = freezer_fork, .exit = NULL, diff --git a/kernel/compat.c b/kernel/compat.c index 38b1d2c1cbe..e2435ee9993 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -158,6 +158,7 @@ int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user __put_user(ts->tv_sec, &cts->tv_sec) || __put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; } +EXPORT_SYMBOL_GPL(put_compat_timespec); static long compat_nanosleep_restart(struct restart_block *restart) { @@ -293,6 +294,8 @@ asmlinkage long compat_sys_times(struct compat_tms __user *tbuf) return compat_jiffies_to_clock_t(jiffies); } +#ifdef __ARCH_WANT_SYS_SIGPENDING + /* * Assumption: old_sigset_t and compat_old_sigset_t are both * types that can be passed to put_user()/get_user(). @@ -312,6 +315,10 @@ asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set) return ret; } +#endif + +#ifdef __ARCH_WANT_SYS_SIGPROCMASK + asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *set, compat_old_sigset_t __user *oset) { @@ -333,6 +340,8 @@ asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *set, return ret; } +#endif + asmlinkage long compat_sys_setrlimit(unsigned int resource, struct compat_rlimit __user *rlim) { @@ -882,6 +891,7 @@ sigset_from_compat (sigset_t *set, compat_sigset_t *compat) case 1: set->sig[0] = compat->sig[0] | (((long)compat->sig[1]) << 32 ); } } +EXPORT_SYMBOL_GPL(sigset_from_compat); asmlinkage long compat_sys_rt_sigtimedwait (compat_sigset_t __user *uthese, @@ -890,10 +900,9 @@ compat_sys_rt_sigtimedwait (compat_sigset_t __user *uthese, { compat_sigset_t s32; sigset_t s; - int sig; struct timespec t; siginfo_t info; - long ret, timeout = 0; + long ret; if (sigsetsize != sizeof(sigset_t)) return -EINVAL; @@ -901,51 +910,19 @@ compat_sys_rt_sigtimedwait (compat_sigset_t __user *uthese, if (copy_from_user(&s32, uthese, sizeof(compat_sigset_t))) return -EFAULT; sigset_from_compat(&s, &s32); - sigdelsetmask(&s,sigmask(SIGKILL)|sigmask(SIGSTOP)); - signotset(&s); if (uts) { - if (get_compat_timespec (&t, uts)) + if (get_compat_timespec(&t, uts)) return -EFAULT; - if (t.tv_nsec >= 1000000000L || t.tv_nsec < 0 - || t.tv_sec < 0) - return -EINVAL; } - spin_lock_irq(¤t->sighand->siglock); - sig = dequeue_signal(current, &s, &info); - if (!sig) { - timeout = MAX_SCHEDULE_TIMEOUT; - if (uts) - timeout = timespec_to_jiffies(&t) - +(t.tv_sec || t.tv_nsec); - if (timeout) { - current->real_blocked = current->blocked; - sigandsets(¤t->blocked, ¤t->blocked, &s); - - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - - timeout = schedule_timeout_interruptible(timeout); - - spin_lock_irq(¤t->sighand->siglock); - sig = dequeue_signal(current, &s, &info); - current->blocked = current->real_blocked; - siginitset(¤t->real_blocked, 0); - recalc_sigpending(); - } - } - spin_unlock_irq(¤t->sighand->siglock); + ret = do_sigtimedwait(&s, &info, uts ? &t : NULL); - if (sig) { - ret = sig; - if (uinfo) { - if (copy_siginfo_to_user32(uinfo, &info)) - ret = -EFAULT; - } - }else { - ret = timeout?-EINTR:-EAGAIN; + if (ret > 0 && uinfo) { + if (copy_siginfo_to_user32(uinfo, &info)) + ret = -EFAULT; } + return ret; } @@ -1016,11 +993,8 @@ asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset, compat sigset_from_compat(&newset, &newset32); sigdelsetmask(&newset, sigmask(SIGKILL)|sigmask(SIGSTOP)); - spin_lock_irq(¤t->sighand->siglock); current->saved_sigmask = current->blocked; - current->blocked = newset; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&newset); current->state = TASK_INTERRUPTIBLE; schedule(); diff --git a/kernel/configs.c b/kernel/configs.c index b4066b44a99..42e8fa075ee 100644 --- a/kernel/configs.c +++ b/kernel/configs.c @@ -92,8 +92,8 @@ static void __exit ikconfig_cleanup(void) module_init(ikconfig_init); module_exit(ikconfig_cleanup); +#endif /* CONFIG_IKCONFIG_PROC */ + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Randy Dunlap"); MODULE_DESCRIPTION("Echo the kernel .config file used to build the kernel"); - -#endif /* CONFIG_IKCONFIG_PROC */ diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 33eee16addb..10131fdaff7 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -55,7 +55,7 @@ #include <linux/sort.h> #include <asm/uaccess.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <linux/mutex.h> #include <linux/workqueue.h> #include <linux/cgroup.h> @@ -1159,7 +1159,7 @@ int current_cpuset_is_being_rebound(void) static int update_relax_domain_level(struct cpuset *cs, s64 val) { #ifdef CONFIG_SMP - if (val < -1 || val >= SD_LV_MAX) + if (val < -1 || val >= sched_domain_level_max) return -EINVAL; #endif @@ -1367,14 +1367,10 @@ static int fmeter_getrate(struct fmeter *fmp) return val; } -/* Protected by cgroup_lock */ -static cpumask_var_t cpus_attach; - /* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont, - struct task_struct *tsk, bool threadgroup) + struct task_struct *tsk) { - int ret; struct cpuset *cs = cgroup_cs(cont); if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) @@ -1391,29 +1387,42 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont, if (tsk->flags & PF_THREAD_BOUND) return -EINVAL; - ret = security_task_setscheduler(tsk); - if (ret) - return ret; - if (threadgroup) { - struct task_struct *c; - - rcu_read_lock(); - list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { - ret = security_task_setscheduler(c); - if (ret) { - rcu_read_unlock(); - return ret; - } - } - rcu_read_unlock(); - } return 0; } -static void cpuset_attach_task(struct task_struct *tsk, nodemask_t *to, - struct cpuset *cs) +static int cpuset_can_attach_task(struct cgroup *cgrp, struct task_struct *task) +{ + return security_task_setscheduler(task); +} + +/* + * Protected by cgroup_lock. The nodemasks must be stored globally because + * dynamically allocating them is not allowed in pre_attach, and they must + * persist among pre_attach, attach_task, and attach. + */ +static cpumask_var_t cpus_attach; +static nodemask_t cpuset_attach_nodemask_from; +static nodemask_t cpuset_attach_nodemask_to; + +/* Set-up work for before attaching each task. */ +static void cpuset_pre_attach(struct cgroup *cont) +{ + struct cpuset *cs = cgroup_cs(cont); + + if (cs == &top_cpuset) + cpumask_copy(cpus_attach, cpu_possible_mask); + else + guarantee_online_cpus(cs, cpus_attach); + + guarantee_online_mems(cs, &cpuset_attach_nodemask_to); +} + +/* Per-thread attachment work. */ +static void cpuset_attach_task(struct cgroup *cont, struct task_struct *tsk) { int err; + struct cpuset *cs = cgroup_cs(cont); + /* * can_attach beforehand should guarantee that this doesn't fail. * TODO: have a better way to handle failure here @@ -1421,45 +1430,29 @@ static void cpuset_attach_task(struct task_struct *tsk, nodemask_t *to, err = set_cpus_allowed_ptr(tsk, cpus_attach); WARN_ON_ONCE(err); - cpuset_change_task_nodemask(tsk, to); + cpuset_change_task_nodemask(tsk, &cpuset_attach_nodemask_to); cpuset_update_task_spread_flag(cs, tsk); - } static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont, - struct cgroup *oldcont, struct task_struct *tsk, - bool threadgroup) + struct cgroup *oldcont, struct task_struct *tsk) { struct mm_struct *mm; struct cpuset *cs = cgroup_cs(cont); struct cpuset *oldcs = cgroup_cs(oldcont); - static nodemask_t to; /* protected by cgroup_mutex */ - - if (cs == &top_cpuset) { - cpumask_copy(cpus_attach, cpu_possible_mask); - } else { - guarantee_online_cpus(cs, cpus_attach); - } - guarantee_online_mems(cs, &to); - - /* do per-task migration stuff possibly for each in the threadgroup */ - cpuset_attach_task(tsk, &to, cs); - if (threadgroup) { - struct task_struct *c; - rcu_read_lock(); - list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { - cpuset_attach_task(c, &to, cs); - } - rcu_read_unlock(); - } - /* change mm; only needs to be done once even if threadgroup */ - to = cs->mems_allowed; + /* + * Change mm, possibly for multiple threads in a threadgroup. This is + * expensive and may sleep. + */ + cpuset_attach_nodemask_from = oldcs->mems_allowed; + cpuset_attach_nodemask_to = cs->mems_allowed; mm = get_task_mm(tsk); if (mm) { - mpol_rebind_mm(mm, &to); + mpol_rebind_mm(mm, &cpuset_attach_nodemask_to); if (is_memory_migrate(cs)) - cpuset_migrate_mm(mm, &oldcs->mems_allowed, &to); + cpuset_migrate_mm(mm, &cpuset_attach_nodemask_from, + &cpuset_attach_nodemask_to); mmput(mm); } } @@ -1809,10 +1802,9 @@ static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont) } /* - * post_clone() is called at the end of cgroup_clone(). - * 'cgroup' was just created automatically as a result of - * a cgroup_clone(), and the current task is about to - * be moved into 'cgroup'. + * post_clone() is called during cgroup_create() when the + * clone_children mount argument was specified. The cgroup + * can not yet have any tasks. * * Currently we refuse to set up the cgroup - thereby * refusing the task to be entered, and as a result refusing @@ -1911,6 +1903,9 @@ struct cgroup_subsys cpuset_subsys = { .create = cpuset_create, .destroy = cpuset_destroy, .can_attach = cpuset_can_attach, + .can_attach_task = cpuset_can_attach_task, + .pre_attach = cpuset_pre_attach, + .attach_task = cpuset_attach_task, .attach = cpuset_attach, .populate = cpuset_populate, .post_clone = cpuset_post_clone, @@ -2195,7 +2190,7 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk) rcu_read_lock(); cs = task_cs(tsk); if (cs) - cpumask_copy(&tsk->cpus_allowed, cs->cpus_allowed); + do_set_cpus_allowed(tsk, cs->cpus_allowed); rcu_read_unlock(); /* @@ -2222,7 +2217,7 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk) * Like above we can temporary set any mask and rely on * set_cpus_allowed_ptr() as synchronization point. */ - cpumask_copy(&tsk->cpus_allowed, cpu_possible_mask); + do_set_cpus_allowed(tsk, cpu_possible_mask); cpu = cpumask_any(cpu_active_mask); } @@ -2465,11 +2460,19 @@ static int cpuset_spread_node(int *rotor) int cpuset_mem_spread_node(void) { + if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) + current->cpuset_mem_spread_rotor = + node_random(¤t->mems_allowed); + return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); } int cpuset_slab_spread_node(void) { + if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) + current->cpuset_slab_spread_rotor = + node_random(¤t->mems_allowed); + return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); } diff --git a/kernel/cred.c b/kernel/cred.c index 5557b55048d..174fa84eca3 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -1,4 +1,4 @@ -/* Task credentials management - see Documentation/credentials.txt +/* Task credentials management - see Documentation/security/credentials.txt * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) @@ -49,11 +49,12 @@ struct cred init_cred = { .magic = CRED_MAGIC, #endif .securebits = SECUREBITS_DEFAULT, - .cap_inheritable = CAP_INIT_INH_SET, + .cap_inheritable = CAP_EMPTY_SET, .cap_permitted = CAP_FULL_SET, - .cap_effective = CAP_INIT_EFF_SET, - .cap_bset = CAP_INIT_BSET, + .cap_effective = CAP_FULL_SET, + .cap_bset = CAP_FULL_SET, .user = INIT_USER, + .user_ns = &init_user_ns, .group_info = &init_groups, #ifdef CONFIG_KEYS .tgcred = &init_tgcred, @@ -410,6 +411,11 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) goto error_put; } + /* cache user_ns in cred. Doesn't need a refcount because it will + * stay pinned by cred->user + */ + new->user_ns = new->user->user_ns; + #ifdef CONFIG_KEYS /* new threads get their own thread keyrings if their parent already * had one */ @@ -741,12 +747,6 @@ int set_create_files_as(struct cred *new, struct inode *inode) } EXPORT_SYMBOL(set_create_files_as); -struct user_namespace *current_user_ns(void) -{ - return _current_user_ns(); -} -EXPORT_SYMBOL(current_user_ns); - #ifdef CONFIG_DEBUG_CREDENTIALS bool creds_are_invalid(const struct cred *cred) diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index bad6786dee8..0d7c08784ef 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -51,7 +51,7 @@ #include <asm/cacheflush.h> #include <asm/byteorder.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/system.h> #include "debug_core.h" diff --git a/kernel/delayacct.c b/kernel/delayacct.c index ead9b610aa7..418b3f7053a 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -19,8 +19,10 @@ #include <linux/time.h> #include <linux/sysctl.h> #include <linux/delayacct.h> +#include <linux/module.h> int delayacct_on __read_mostly = 1; /* Delay accounting turned on/off */ +EXPORT_SYMBOL_GPL(delayacct_on); struct kmem_cache *delayacct_cache; static int __init delayacct_setup_disable(char *str) diff --git a/kernel/events/Makefile b/kernel/events/Makefile new file mode 100644 index 00000000000..89e5e8aa4c3 --- /dev/null +++ b/kernel/events/Makefile @@ -0,0 +1,6 @@ +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_core.o = -pg +endif + +obj-y := core.o ring_buffer.o +obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o diff --git a/kernel/perf_event.c b/kernel/events/core.c index 8e81a9860a0..b8785e26ee1 100644 --- a/kernel/perf_event.c +++ b/kernel/events/core.c @@ -2,8 +2,8 @@ * Performance events core code: * * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> - * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> * * For licensing details see kernel-base/COPYING @@ -36,13 +36,15 @@ #include <linux/ftrace_event.h> #include <linux/hw_breakpoint.h> +#include "internal.h" + #include <asm/irq_regs.h> struct remote_function_call { - struct task_struct *p; - int (*func)(void *info); - void *info; - int ret; + struct task_struct *p; + int (*func)(void *info); + void *info; + int ret; }; static void remote_function(void *data) @@ -76,10 +78,10 @@ static int task_function_call(struct task_struct *p, int (*func) (void *info), void *info) { struct remote_function_call data = { - .p = p, - .func = func, - .info = info, - .ret = -ESRCH, /* No such (running) process */ + .p = p, + .func = func, + .info = info, + .ret = -ESRCH, /* No such (running) process */ }; if (task_curr(p)) @@ -100,10 +102,10 @@ task_function_call(struct task_struct *p, int (*func) (void *info), void *info) static int cpu_function_call(int cpu, int (*func) (void *info), void *info) { struct remote_function_call data = { - .p = NULL, - .func = func, - .info = info, - .ret = -ENXIO, /* No such CPU */ + .p = NULL, + .func = func, + .info = info, + .ret = -ENXIO, /* No such CPU */ }; smp_call_function_single(cpu, remote_function, &data, 1); @@ -125,7 +127,7 @@ enum event_type_t { * perf_sched_events : >0 events exist * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu */ -atomic_t perf_sched_events __read_mostly; +struct jump_label_key perf_sched_events __read_mostly; static DEFINE_PER_CPU(atomic_t, perf_cgroup_events); static atomic_t nr_mmap_events __read_mostly; @@ -200,6 +202,22 @@ __get_cpu_context(struct perf_event_context *ctx) return this_cpu_ptr(ctx->pmu->pmu_cpu_context); } +static void perf_ctx_lock(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + raw_spin_lock(&cpuctx->ctx.lock); + if (ctx) + raw_spin_lock(&ctx->lock); +} + +static void perf_ctx_unlock(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + if (ctx) + raw_spin_unlock(&ctx->lock); + raw_spin_unlock(&cpuctx->ctx.lock); +} + #ifdef CONFIG_CGROUP_PERF /* @@ -340,11 +358,8 @@ void perf_cgroup_switch(struct task_struct *task, int mode) rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { - cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); - perf_pmu_disable(cpuctx->ctx.pmu); - /* * perf_cgroup_events says at least one * context on this CPU has cgroup events. @@ -353,6 +368,8 @@ void perf_cgroup_switch(struct task_struct *task, int mode) * events for a context. */ if (cpuctx->ctx.nr_cgroups > 0) { + perf_ctx_lock(cpuctx, cpuctx->task_ctx); + perf_pmu_disable(cpuctx->ctx.pmu); if (mode & PERF_CGROUP_SWOUT) { cpu_ctx_sched_out(cpuctx, EVENT_ALL); @@ -372,9 +389,9 @@ void perf_cgroup_switch(struct task_struct *task, int mode) cpuctx->cgrp = perf_cgroup_from_task(task); cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); } + perf_pmu_enable(cpuctx->ctx.pmu); + perf_ctx_unlock(cpuctx, cpuctx->task_ctx); } - - perf_pmu_enable(cpuctx->ctx.pmu); } rcu_read_unlock(); @@ -586,14 +603,6 @@ static void get_ctx(struct perf_event_context *ctx) WARN_ON(!atomic_inc_not_zero(&ctx->refcount)); } -static void free_ctx(struct rcu_head *head) -{ - struct perf_event_context *ctx; - - ctx = container_of(head, struct perf_event_context, rcu_head); - kfree(ctx); -} - static void put_ctx(struct perf_event_context *ctx) { if (atomic_dec_and_test(&ctx->refcount)) { @@ -601,7 +610,7 @@ static void put_ctx(struct perf_event_context *ctx) put_ctx(ctx->parent_ctx); if (ctx->task) put_task_struct(ctx->task); - call_rcu(&ctx->rcu_head, free_ctx); + kfree_rcu(ctx, rcu_head); } } @@ -739,6 +748,7 @@ static u64 perf_event_time(struct perf_event *event) /* * Update the total_time_enabled and total_time_running fields for a event. + * The caller of this function needs to hold the ctx->lock. */ static void update_event_times(struct perf_event *event) { @@ -1113,6 +1123,10 @@ static int __perf_remove_from_context(void *info) raw_spin_lock(&ctx->lock); event_sched_out(event, cpuctx, ctx); list_del_event(event, ctx); + if (!ctx->nr_events && cpuctx->task_ctx == ctx) { + ctx->is_active = 0; + cpuctx->task_ctx = NULL; + } raw_spin_unlock(&ctx->lock); return 0; @@ -1462,8 +1476,24 @@ static void add_event_to_ctx(struct perf_event *event, event->tstamp_stopped = tstamp; } -static void perf_event_context_sched_in(struct perf_event_context *ctx, - struct task_struct *tsk); +static void task_ctx_sched_out(struct perf_event_context *ctx); +static void +ctx_sched_in(struct perf_event_context *ctx, + struct perf_cpu_context *cpuctx, + enum event_type_t event_type, + struct task_struct *task); + +static void perf_event_sched_in(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + struct task_struct *task) +{ + cpu_ctx_sched_in(cpuctx, EVENT_PINNED, task); + if (ctx) + ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task); + cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task); + if (ctx) + ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); +} /* * Cross CPU call to install and enable a performance event @@ -1474,20 +1504,37 @@ static int __perf_install_in_context(void *info) { struct perf_event *event = info; struct perf_event_context *ctx = event->ctx; - struct perf_event *leader = event->group_leader; struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); - int err; + struct perf_event_context *task_ctx = cpuctx->task_ctx; + struct task_struct *task = current; + + perf_ctx_lock(cpuctx, task_ctx); + perf_pmu_disable(cpuctx->ctx.pmu); /* - * In case we're installing a new context to an already running task, - * could also happen before perf_event_task_sched_in() on architectures - * which do context switches with IRQs enabled. + * If there was an active task_ctx schedule it out. */ - if (ctx->task && !cpuctx->task_ctx) - perf_event_context_sched_in(ctx, ctx->task); + if (task_ctx) + task_ctx_sched_out(task_ctx); + + /* + * If the context we're installing events in is not the + * active task_ctx, flip them. + */ + if (ctx->task && task_ctx != ctx) { + if (task_ctx) + raw_spin_unlock(&task_ctx->lock); + raw_spin_lock(&ctx->lock); + task_ctx = ctx; + } + + if (task_ctx) { + cpuctx->task_ctx = task_ctx; + task = task_ctx->task; + } + + cpu_ctx_sched_out(cpuctx, EVENT_ALL); - raw_spin_lock(&ctx->lock); - ctx->is_active = 1; update_context_time(ctx); /* * update cgrp time only if current cgrp @@ -1498,43 +1545,13 @@ static int __perf_install_in_context(void *info) add_event_to_ctx(event, ctx); - if (!event_filter_match(event)) - goto unlock; - /* - * Don't put the event on if it is disabled or if - * it is in a group and the group isn't on. + * Schedule everything back in */ - if (event->state != PERF_EVENT_STATE_INACTIVE || - (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE)) - goto unlock; - - /* - * An exclusive event can't go on if there are already active - * hardware events, and no hardware event can go on if there - * is already an exclusive event on. - */ - if (!group_can_go_on(event, cpuctx, 1)) - err = -EEXIST; - else - err = event_sched_in(event, cpuctx, ctx); - - if (err) { - /* - * This event couldn't go on. If it is in a group - * then we have to pull the whole group off. - * If the event group is pinned then put it in error state. - */ - if (leader != event) - group_sched_out(leader, cpuctx, ctx); - if (leader->attr.pinned) { - update_group_times(leader); - leader->state = PERF_EVENT_STATE_ERROR; - } - } + perf_event_sched_in(cpuctx, task_ctx, task); -unlock: - raw_spin_unlock(&ctx->lock); + perf_pmu_enable(cpuctx->ctx.pmu); + perf_ctx_unlock(cpuctx, task_ctx); return 0; } @@ -1747,7 +1764,7 @@ out: raw_spin_unlock_irq(&ctx->lock); } -static int perf_event_refresh(struct perf_event *event, int refresh) +int perf_event_refresh(struct perf_event *event, int refresh) { /* * not supported on inherited events @@ -1760,36 +1777,35 @@ static int perf_event_refresh(struct perf_event *event, int refresh) return 0; } +EXPORT_SYMBOL_GPL(perf_event_refresh); static void ctx_sched_out(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, enum event_type_t event_type) { struct perf_event *event; + int is_active = ctx->is_active; - raw_spin_lock(&ctx->lock); - perf_pmu_disable(ctx->pmu); - ctx->is_active = 0; + ctx->is_active &= ~event_type; if (likely(!ctx->nr_events)) - goto out; + return; + update_context_time(ctx); update_cgrp_time_from_cpuctx(cpuctx); - if (!ctx->nr_active) - goto out; + return; - if (event_type & EVENT_PINNED) { + perf_pmu_disable(ctx->pmu); + if ((is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) { list_for_each_entry(event, &ctx->pinned_groups, group_entry) group_sched_out(event, cpuctx, ctx); } - if (event_type & EVENT_FLEXIBLE) { + if ((is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) { list_for_each_entry(event, &ctx->flexible_groups, group_entry) group_sched_out(event, cpuctx, ctx); } -out: perf_pmu_enable(ctx->pmu); - raw_spin_unlock(&ctx->lock); } /* @@ -1937,8 +1953,10 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, rcu_read_unlock(); if (do_switch) { + raw_spin_lock(&ctx->lock); ctx_sched_out(ctx, cpuctx, EVENT_ALL); cpuctx->task_ctx = NULL; + raw_spin_unlock(&ctx->lock); } } @@ -1973,8 +1991,7 @@ void __perf_event_task_sched_out(struct task_struct *task, perf_cgroup_sched_out(task); } -static void task_ctx_sched_out(struct perf_event_context *ctx, - enum event_type_t event_type) +static void task_ctx_sched_out(struct perf_event_context *ctx) { struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); @@ -1984,7 +2001,7 @@ static void task_ctx_sched_out(struct perf_event_context *ctx, if (WARN_ON_ONCE(ctx != cpuctx->task_ctx)) return; - ctx_sched_out(ctx, cpuctx, event_type); + ctx_sched_out(ctx, cpuctx, EVENT_ALL); cpuctx->task_ctx = NULL; } @@ -2063,11 +2080,11 @@ ctx_sched_in(struct perf_event_context *ctx, struct task_struct *task) { u64 now; + int is_active = ctx->is_active; - raw_spin_lock(&ctx->lock); - ctx->is_active = 1; + ctx->is_active |= event_type; if (likely(!ctx->nr_events)) - goto out; + return; now = perf_clock(); ctx->timestamp = now; @@ -2076,15 +2093,12 @@ ctx_sched_in(struct perf_event_context *ctx, * First go through the list and put on any pinned groups * in order to give them the best chance of going on. */ - if (event_type & EVENT_PINNED) + if (!(is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) ctx_pinned_sched_in(ctx, cpuctx); /* Then walk through the lower prio flexible groups */ - if (event_type & EVENT_FLEXIBLE) + if (!(is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) ctx_flexible_sched_in(ctx, cpuctx); - -out: - raw_spin_unlock(&ctx->lock); } static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, @@ -2096,19 +2110,6 @@ static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, ctx_sched_in(ctx, cpuctx, event_type, task); } -static void task_ctx_sched_in(struct perf_event_context *ctx, - enum event_type_t event_type) -{ - struct perf_cpu_context *cpuctx; - - cpuctx = __get_cpu_context(ctx); - if (cpuctx->task_ctx == ctx) - return; - - ctx_sched_in(ctx, cpuctx, event_type, NULL); - cpuctx->task_ctx = ctx; -} - static void perf_event_context_sched_in(struct perf_event_context *ctx, struct task_struct *task) { @@ -2118,6 +2119,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, if (cpuctx->task_ctx == ctx) return; + perf_ctx_lock(cpuctx, ctx); perf_pmu_disable(ctx->pmu); /* * We want to keep the following priority order: @@ -2126,18 +2128,18 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, */ cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task); - cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task); - ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); + perf_event_sched_in(cpuctx, ctx, task); cpuctx->task_ctx = ctx; + perf_pmu_enable(ctx->pmu); + perf_ctx_unlock(cpuctx, ctx); + /* * Since these rotations are per-cpu, we need to ensure the * cpu-context we got scheduled on is actually rotating. */ perf_pmu_rotate_start(ctx->pmu); - perf_pmu_enable(ctx->pmu); } /* @@ -2277,7 +2279,6 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period) u64 interrupts, now; s64 delta; - raw_spin_lock(&ctx->lock); list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { if (event->state != PERF_EVENT_STATE_ACTIVE) continue; @@ -2309,7 +2310,6 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period) if (delta > 0) perf_adjust_period(event, period, delta); } - raw_spin_unlock(&ctx->lock); } /* @@ -2317,16 +2317,12 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period) */ static void rotate_ctx(struct perf_event_context *ctx) { - raw_spin_lock(&ctx->lock); - /* * Rotate the first entry last of non-pinned groups. Rotation might be * disabled by the inheritance code. */ if (!ctx->rotate_disable) list_rotate_left(&ctx->flexible_groups); - - raw_spin_unlock(&ctx->lock); } /* @@ -2353,6 +2349,7 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx) rotate = 1; } + perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_pmu_disable(cpuctx->ctx.pmu); perf_ctx_adjust_freq(&cpuctx->ctx, interval); if (ctx) @@ -2363,21 +2360,20 @@ static void perf_rotate_context(struct perf_cpu_context *cpuctx) cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); if (ctx) - task_ctx_sched_out(ctx, EVENT_FLEXIBLE); + ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE); rotate_ctx(&cpuctx->ctx); if (ctx) rotate_ctx(ctx); - cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, current); - if (ctx) - task_ctx_sched_in(ctx, EVENT_FLEXIBLE); + perf_event_sched_in(cpuctx, ctx, current); done: if (remove) list_del_init(&cpuctx->rotation_list); perf_pmu_enable(cpuctx->ctx.pmu); + perf_ctx_unlock(cpuctx, cpuctx->task_ctx); } void perf_event_task_tick(void) @@ -2432,9 +2428,9 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx) * in. */ perf_cgroup_sched_out(current); - task_ctx_sched_out(ctx, EVENT_ALL); raw_spin_lock(&ctx->lock); + task_ctx_sched_out(ctx); list_for_each_entry(event, &ctx->pinned_groups, group_entry) { ret = event_enable_on_exec(event, ctx); @@ -2843,16 +2839,12 @@ retry: unclone_ctx(ctx); ++ctx->pin_count; raw_spin_unlock_irqrestore(&ctx->lock, flags); - } - - if (!ctx) { + } else { ctx = alloc_perf_context(pmu, task); err = -ENOMEM; if (!ctx) goto errout; - get_ctx(ctx); - err = 0; mutex_lock(&task->perf_event_mutex); /* @@ -2864,14 +2856,14 @@ retry: else if (task->perf_event_ctxp[ctxn]) err = -EAGAIN; else { + get_ctx(ctx); ++ctx->pin_count; rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx); } mutex_unlock(&task->perf_event_mutex); if (unlikely(err)) { - put_task_struct(task); - kfree(ctx); + put_ctx(ctx); if (err == -EAGAIN) goto retry; @@ -2898,7 +2890,7 @@ static void free_event_rcu(struct rcu_head *head) kfree(event); } -static void perf_buffer_put(struct perf_buffer *buffer); +static void ring_buffer_put(struct ring_buffer *rb); static void free_event(struct perf_event *event) { @@ -2921,9 +2913,9 @@ static void free_event(struct perf_event *event) } } - if (event->buffer) { - perf_buffer_put(event->buffer); - event->buffer = NULL; + if (event->rb) { + ring_buffer_put(event->rb); + event->rb = NULL; } if (is_cgroup_event(event)) @@ -2942,12 +2934,6 @@ int perf_event_release_kernel(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; - /* - * Remove from the PMU, can't get re-enabled since we got - * here because the last ref went. - */ - perf_event_disable(event); - WARN_ON_ONCE(ctx->parent_ctx); /* * There are two ways this annotation is useful: @@ -2964,8 +2950,8 @@ int perf_event_release_kernel(struct perf_event *event) mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING); raw_spin_lock_irq(&ctx->lock); perf_group_detach(event); - list_del_event(event, ctx); raw_spin_unlock_irq(&ctx->lock); + perf_remove_from_context(event); mutex_unlock(&ctx->mutex); free_event(event); @@ -3157,13 +3143,13 @@ perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) static unsigned int perf_poll(struct file *file, poll_table *wait) { struct perf_event *event = file->private_data; - struct perf_buffer *buffer; + struct ring_buffer *rb; unsigned int events = POLL_HUP; rcu_read_lock(); - buffer = rcu_dereference(event->buffer); - if (buffer) - events = atomic_xchg(&buffer->poll, 0); + rb = rcu_dereference(event->rb); + if (rb) + events = atomic_xchg(&rb->poll, 0); rcu_read_unlock(); poll_wait(file, &event->waitq, wait); @@ -3366,6 +3352,18 @@ static int perf_event_index(struct perf_event *event) return event->hw.idx + 1 - PERF_EVENT_INDEX_OFFSET; } +static void calc_timer_values(struct perf_event *event, + u64 *running, + u64 *enabled) +{ + u64 now, ctx_time; + + now = perf_clock(); + ctx_time = event->shadow_ctx_time + now; + *enabled = ctx_time - event->tstamp_enabled; + *running = ctx_time - event->tstamp_running; +} + /* * Callers need to ensure there can be no nesting of this function, otherwise * the seqlock logic goes bad. We can not serialize this because the arch @@ -3374,14 +3372,25 @@ static int perf_event_index(struct perf_event *event) void perf_event_update_userpage(struct perf_event *event) { struct perf_event_mmap_page *userpg; - struct perf_buffer *buffer; + struct ring_buffer *rb; + u64 enabled, running; rcu_read_lock(); - buffer = rcu_dereference(event->buffer); - if (!buffer) + /* + * compute total_time_enabled, total_time_running + * based on snapshot values taken when the event + * was last scheduled in. + * + * we cannot simply called update_context_time() + * because of locking issue as we can be called in + * NMI context + */ + calc_timer_values(event, &enabled, &running); + rb = rcu_dereference(event->rb); + if (!rb) goto unlock; - userpg = buffer->user_page; + userpg = rb->user_page; /* * Disable preemption so as to not let the corresponding user-space @@ -3395,10 +3404,10 @@ void perf_event_update_userpage(struct perf_event *event) if (event->state == PERF_EVENT_STATE_ACTIVE) userpg->offset -= local64_read(&event->hw.prev_count); - userpg->time_enabled = event->total_time_enabled + + userpg->time_enabled = enabled + atomic64_read(&event->child_total_time_enabled); - userpg->time_running = event->total_time_running + + userpg->time_running = running + atomic64_read(&event->child_total_time_running); barrier(); @@ -3408,220 +3417,10 @@ unlock: rcu_read_unlock(); } -static unsigned long perf_data_size(struct perf_buffer *buffer); - -static void -perf_buffer_init(struct perf_buffer *buffer, long watermark, int flags) -{ - long max_size = perf_data_size(buffer); - - if (watermark) - buffer->watermark = min(max_size, watermark); - - if (!buffer->watermark) - buffer->watermark = max_size / 2; - - if (flags & PERF_BUFFER_WRITABLE) - buffer->writable = 1; - - atomic_set(&buffer->refcount, 1); -} - -#ifndef CONFIG_PERF_USE_VMALLOC - -/* - * Back perf_mmap() with regular GFP_KERNEL-0 pages. - */ - -static struct page * -perf_mmap_to_page(struct perf_buffer *buffer, unsigned long pgoff) -{ - if (pgoff > buffer->nr_pages) - return NULL; - - if (pgoff == 0) - return virt_to_page(buffer->user_page); - - return virt_to_page(buffer->data_pages[pgoff - 1]); -} - -static void *perf_mmap_alloc_page(int cpu) -{ - struct page *page; - int node; - - node = (cpu == -1) ? cpu : cpu_to_node(cpu); - page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); - if (!page) - return NULL; - - return page_address(page); -} - -static struct perf_buffer * -perf_buffer_alloc(int nr_pages, long watermark, int cpu, int flags) -{ - struct perf_buffer *buffer; - unsigned long size; - int i; - - size = sizeof(struct perf_buffer); - size += nr_pages * sizeof(void *); - - buffer = kzalloc(size, GFP_KERNEL); - if (!buffer) - goto fail; - - buffer->user_page = perf_mmap_alloc_page(cpu); - if (!buffer->user_page) - goto fail_user_page; - - for (i = 0; i < nr_pages; i++) { - buffer->data_pages[i] = perf_mmap_alloc_page(cpu); - if (!buffer->data_pages[i]) - goto fail_data_pages; - } - - buffer->nr_pages = nr_pages; - - perf_buffer_init(buffer, watermark, flags); - - return buffer; - -fail_data_pages: - for (i--; i >= 0; i--) - free_page((unsigned long)buffer->data_pages[i]); - - free_page((unsigned long)buffer->user_page); - -fail_user_page: - kfree(buffer); - -fail: - return NULL; -} - -static void perf_mmap_free_page(unsigned long addr) -{ - struct page *page = virt_to_page((void *)addr); - - page->mapping = NULL; - __free_page(page); -} - -static void perf_buffer_free(struct perf_buffer *buffer) -{ - int i; - - perf_mmap_free_page((unsigned long)buffer->user_page); - for (i = 0; i < buffer->nr_pages; i++) - perf_mmap_free_page((unsigned long)buffer->data_pages[i]); - kfree(buffer); -} - -static inline int page_order(struct perf_buffer *buffer) -{ - return 0; -} - -#else - -/* - * Back perf_mmap() with vmalloc memory. - * - * Required for architectures that have d-cache aliasing issues. - */ - -static inline int page_order(struct perf_buffer *buffer) -{ - return buffer->page_order; -} - -static struct page * -perf_mmap_to_page(struct perf_buffer *buffer, unsigned long pgoff) -{ - if (pgoff > (1UL << page_order(buffer))) - return NULL; - - return vmalloc_to_page((void *)buffer->user_page + pgoff * PAGE_SIZE); -} - -static void perf_mmap_unmark_page(void *addr) -{ - struct page *page = vmalloc_to_page(addr); - - page->mapping = NULL; -} - -static void perf_buffer_free_work(struct work_struct *work) -{ - struct perf_buffer *buffer; - void *base; - int i, nr; - - buffer = container_of(work, struct perf_buffer, work); - nr = 1 << page_order(buffer); - - base = buffer->user_page; - for (i = 0; i < nr + 1; i++) - perf_mmap_unmark_page(base + (i * PAGE_SIZE)); - - vfree(base); - kfree(buffer); -} - -static void perf_buffer_free(struct perf_buffer *buffer) -{ - schedule_work(&buffer->work); -} - -static struct perf_buffer * -perf_buffer_alloc(int nr_pages, long watermark, int cpu, int flags) -{ - struct perf_buffer *buffer; - unsigned long size; - void *all_buf; - - size = sizeof(struct perf_buffer); - size += sizeof(void *); - - buffer = kzalloc(size, GFP_KERNEL); - if (!buffer) - goto fail; - - INIT_WORK(&buffer->work, perf_buffer_free_work); - - all_buf = vmalloc_user((nr_pages + 1) * PAGE_SIZE); - if (!all_buf) - goto fail_all_buf; - - buffer->user_page = all_buf; - buffer->data_pages[0] = all_buf + PAGE_SIZE; - buffer->page_order = ilog2(nr_pages); - buffer->nr_pages = 1; - - perf_buffer_init(buffer, watermark, flags); - - return buffer; - -fail_all_buf: - kfree(buffer); - -fail: - return NULL; -} - -#endif - -static unsigned long perf_data_size(struct perf_buffer *buffer) -{ - return buffer->nr_pages << (PAGE_SHIFT + page_order(buffer)); -} - static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct perf_event *event = vma->vm_file->private_data; - struct perf_buffer *buffer; + struct ring_buffer *rb; int ret = VM_FAULT_SIGBUS; if (vmf->flags & FAULT_FLAG_MKWRITE) { @@ -3631,14 +3430,14 @@ static int perf_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } rcu_read_lock(); - buffer = rcu_dereference(event->buffer); - if (!buffer) + rb = rcu_dereference(event->rb); + if (!rb) goto unlock; if (vmf->pgoff && (vmf->flags & FAULT_FLAG_WRITE)) goto unlock; - vmf->page = perf_mmap_to_page(buffer, vmf->pgoff); + vmf->page = perf_mmap_to_page(rb, vmf->pgoff); if (!vmf->page) goto unlock; @@ -3653,35 +3452,35 @@ unlock: return ret; } -static void perf_buffer_free_rcu(struct rcu_head *rcu_head) +static void rb_free_rcu(struct rcu_head *rcu_head) { - struct perf_buffer *buffer; + struct ring_buffer *rb; - buffer = container_of(rcu_head, struct perf_buffer, rcu_head); - perf_buffer_free(buffer); + rb = container_of(rcu_head, struct ring_buffer, rcu_head); + rb_free(rb); } -static struct perf_buffer *perf_buffer_get(struct perf_event *event) +static struct ring_buffer *ring_buffer_get(struct perf_event *event) { - struct perf_buffer *buffer; + struct ring_buffer *rb; rcu_read_lock(); - buffer = rcu_dereference(event->buffer); - if (buffer) { - if (!atomic_inc_not_zero(&buffer->refcount)) - buffer = NULL; + rb = rcu_dereference(event->rb); + if (rb) { + if (!atomic_inc_not_zero(&rb->refcount)) + rb = NULL; } rcu_read_unlock(); - return buffer; + return rb; } -static void perf_buffer_put(struct perf_buffer *buffer) +static void ring_buffer_put(struct ring_buffer *rb) { - if (!atomic_dec_and_test(&buffer->refcount)) + if (!atomic_dec_and_test(&rb->refcount)) return; - call_rcu(&buffer->rcu_head, perf_buffer_free_rcu); + call_rcu(&rb->rcu_head, rb_free_rcu); } static void perf_mmap_open(struct vm_area_struct *vma) @@ -3696,16 +3495,16 @@ static void perf_mmap_close(struct vm_area_struct *vma) struct perf_event *event = vma->vm_file->private_data; if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) { - unsigned long size = perf_data_size(event->buffer); + unsigned long size = perf_data_size(event->rb); struct user_struct *user = event->mmap_user; - struct perf_buffer *buffer = event->buffer; + struct ring_buffer *rb = event->rb; atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm); vma->vm_mm->locked_vm -= event->mmap_locked; - rcu_assign_pointer(event->buffer, NULL); + rcu_assign_pointer(event->rb, NULL); mutex_unlock(&event->mmap_mutex); - perf_buffer_put(buffer); + ring_buffer_put(rb); free_uid(user); } } @@ -3723,7 +3522,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) unsigned long user_locked, user_lock_limit; struct user_struct *user = current_user(); unsigned long locked, lock_limit; - struct perf_buffer *buffer; + struct ring_buffer *rb; unsigned long vma_size; unsigned long nr_pages; long user_extra, extra; @@ -3732,7 +3531,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) /* * Don't allow mmap() of inherited per-task counters. This would * create a performance issue due to all children writing to the - * same buffer. + * same rb. */ if (event->cpu == -1 && event->attr.inherit) return -EINVAL; @@ -3744,7 +3543,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) nr_pages = (vma_size / PAGE_SIZE) - 1; /* - * If we have buffer pages ensure they're a power-of-two number, so we + * If we have rb pages ensure they're a power-of-two number, so we * can do bitmasks instead of modulo. */ if (nr_pages != 0 && !is_power_of_2(nr_pages)) @@ -3758,9 +3557,9 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) WARN_ON_ONCE(event->ctx->parent_ctx); mutex_lock(&event->mmap_mutex); - if (event->buffer) { - if (event->buffer->nr_pages == nr_pages) - atomic_inc(&event->buffer->refcount); + if (event->rb) { + if (event->rb->nr_pages == nr_pages) + atomic_inc(&event->rb->refcount); else ret = -EINVAL; goto unlock; @@ -3790,18 +3589,20 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) goto unlock; } - WARN_ON(event->buffer); + WARN_ON(event->rb); if (vma->vm_flags & VM_WRITE) - flags |= PERF_BUFFER_WRITABLE; + flags |= RING_BUFFER_WRITABLE; + + rb = rb_alloc(nr_pages, + event->attr.watermark ? event->attr.wakeup_watermark : 0, + event->cpu, flags); - buffer = perf_buffer_alloc(nr_pages, event->attr.wakeup_watermark, - event->cpu, flags); - if (!buffer) { + if (!rb) { ret = -ENOMEM; goto unlock; } - rcu_assign_pointer(event->buffer, buffer); + rcu_assign_pointer(event->rb, rb); atomic_long_add(user_extra, &user->locked_vm); event->mmap_locked = extra; @@ -3900,117 +3701,6 @@ int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) } EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks); -/* - * Output - */ -static bool perf_output_space(struct perf_buffer *buffer, unsigned long tail, - unsigned long offset, unsigned long head) -{ - unsigned long mask; - - if (!buffer->writable) - return true; - - mask = perf_data_size(buffer) - 1; - - offset = (offset - tail) & mask; - head = (head - tail) & mask; - - if ((int)(head - offset) < 0) - return false; - - return true; -} - -static void perf_output_wakeup(struct perf_output_handle *handle) -{ - atomic_set(&handle->buffer->poll, POLL_IN); - - if (handle->nmi) { - handle->event->pending_wakeup = 1; - irq_work_queue(&handle->event->pending); - } else - perf_event_wakeup(handle->event); -} - -/* - * We need to ensure a later event_id doesn't publish a head when a former - * event isn't done writing. However since we need to deal with NMIs we - * cannot fully serialize things. - * - * We only publish the head (and generate a wakeup) when the outer-most - * event completes. - */ -static void perf_output_get_handle(struct perf_output_handle *handle) -{ - struct perf_buffer *buffer = handle->buffer; - - preempt_disable(); - local_inc(&buffer->nest); - handle->wakeup = local_read(&buffer->wakeup); -} - -static void perf_output_put_handle(struct perf_output_handle *handle) -{ - struct perf_buffer *buffer = handle->buffer; - unsigned long head; - -again: - head = local_read(&buffer->head); - - /* - * IRQ/NMI can happen here, which means we can miss a head update. - */ - - if (!local_dec_and_test(&buffer->nest)) - goto out; - - /* - * Publish the known good head. Rely on the full barrier implied - * by atomic_dec_and_test() order the buffer->head read and this - * write. - */ - buffer->user_page->data_head = head; - - /* - * Now check if we missed an update, rely on the (compiler) - * barrier in atomic_dec_and_test() to re-read buffer->head. - */ - if (unlikely(head != local_read(&buffer->head))) { - local_inc(&buffer->nest); - goto again; - } - - if (handle->wakeup != local_read(&buffer->wakeup)) - perf_output_wakeup(handle); - -out: - preempt_enable(); -} - -__always_inline void perf_output_copy(struct perf_output_handle *handle, - const void *buf, unsigned int len) -{ - do { - unsigned long size = min_t(unsigned long, handle->size, len); - - memcpy(handle->addr, buf, size); - - len -= size; - handle->addr += size; - buf += size; - handle->size -= size; - if (!handle->size) { - struct perf_buffer *buffer = handle->buffer; - - handle->page++; - handle->page &= buffer->nr_pages - 1; - handle->addr = buffer->data_pages[handle->page]; - handle->size = PAGE_SIZE << page_order(buffer); - } - } while (len); -} - static void __perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event) @@ -4041,9 +3731,9 @@ static void __perf_event_header__init_id(struct perf_event_header *header, } } -static void perf_event_header__init_id(struct perf_event_header *header, - struct perf_sample_data *data, - struct perf_event *event) +void perf_event_header__init_id(struct perf_event_header *header, + struct perf_sample_data *data, + struct perf_event *event) { if (event->attr.sample_id_all) __perf_event_header__init_id(header, data, event); @@ -4070,121 +3760,14 @@ static void __perf_event__output_id_sample(struct perf_output_handle *handle, perf_output_put(handle, data->cpu_entry); } -static void perf_event__output_id_sample(struct perf_event *event, - struct perf_output_handle *handle, - struct perf_sample_data *sample) +void perf_event__output_id_sample(struct perf_event *event, + struct perf_output_handle *handle, + struct perf_sample_data *sample) { if (event->attr.sample_id_all) __perf_event__output_id_sample(handle, sample); } -int perf_output_begin(struct perf_output_handle *handle, - struct perf_event *event, unsigned int size, - int nmi, int sample) -{ - struct perf_buffer *buffer; - unsigned long tail, offset, head; - int have_lost; - struct perf_sample_data sample_data; - struct { - struct perf_event_header header; - u64 id; - u64 lost; - } lost_event; - - rcu_read_lock(); - /* - * For inherited events we send all the output towards the parent. - */ - if (event->parent) - event = event->parent; - - buffer = rcu_dereference(event->buffer); - if (!buffer) - goto out; - - handle->buffer = buffer; - handle->event = event; - handle->nmi = nmi; - handle->sample = sample; - - if (!buffer->nr_pages) - goto out; - - have_lost = local_read(&buffer->lost); - if (have_lost) { - lost_event.header.size = sizeof(lost_event); - perf_event_header__init_id(&lost_event.header, &sample_data, - event); - size += lost_event.header.size; - } - - perf_output_get_handle(handle); - - do { - /* - * Userspace could choose to issue a mb() before updating the - * tail pointer. So that all reads will be completed before the - * write is issued. - */ - tail = ACCESS_ONCE(buffer->user_page->data_tail); - smp_rmb(); - offset = head = local_read(&buffer->head); - head += size; - if (unlikely(!perf_output_space(buffer, tail, offset, head))) - goto fail; - } while (local_cmpxchg(&buffer->head, offset, head) != offset); - - if (head - local_read(&buffer->wakeup) > buffer->watermark) - local_add(buffer->watermark, &buffer->wakeup); - - handle->page = offset >> (PAGE_SHIFT + page_order(buffer)); - handle->page &= buffer->nr_pages - 1; - handle->size = offset & ((PAGE_SIZE << page_order(buffer)) - 1); - handle->addr = buffer->data_pages[handle->page]; - handle->addr += handle->size; - handle->size = (PAGE_SIZE << page_order(buffer)) - handle->size; - - if (have_lost) { - lost_event.header.type = PERF_RECORD_LOST; - lost_event.header.misc = 0; - lost_event.id = event->id; - lost_event.lost = local_xchg(&buffer->lost, 0); - - perf_output_put(handle, lost_event); - perf_event__output_id_sample(event, handle, &sample_data); - } - - return 0; - -fail: - local_inc(&buffer->lost); - perf_output_put_handle(handle); -out: - rcu_read_unlock(); - - return -ENOSPC; -} - -void perf_output_end(struct perf_output_handle *handle) -{ - struct perf_event *event = handle->event; - struct perf_buffer *buffer = handle->buffer; - - int wakeup_events = event->attr.wakeup_events; - - if (handle->sample && wakeup_events) { - int events = local_inc_return(&buffer->events); - if (events >= wakeup_events) { - local_sub(wakeup_events, &buffer->events); - local_inc(&buffer->wakeup); - } - } - - perf_output_put_handle(handle); - rcu_read_unlock(); -} - static void perf_output_read_one(struct perf_output_handle *handle, struct perf_event *event, u64 enabled, u64 running) @@ -4205,7 +3788,7 @@ static void perf_output_read_one(struct perf_output_handle *handle, if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(event); - perf_output_copy(handle, values, n * sizeof(u64)); + __output_copy(handle, values, n * sizeof(u64)); } /* @@ -4235,7 +3818,7 @@ static void perf_output_read_group(struct perf_output_handle *handle, if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(leader); - perf_output_copy(handle, values, n * sizeof(u64)); + __output_copy(handle, values, n * sizeof(u64)); list_for_each_entry(sub, &leader->sibling_list, group_entry) { n = 0; @@ -4247,7 +3830,7 @@ static void perf_output_read_group(struct perf_output_handle *handle, if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(sub); - perf_output_copy(handle, values, n * sizeof(u64)); + __output_copy(handle, values, n * sizeof(u64)); } } @@ -4257,7 +3840,7 @@ static void perf_output_read_group(struct perf_output_handle *handle, static void perf_output_read(struct perf_output_handle *handle, struct perf_event *event) { - u64 enabled = 0, running = 0, now, ctx_time; + u64 enabled = 0, running = 0; u64 read_format = event->attr.read_format; /* @@ -4269,12 +3852,8 @@ static void perf_output_read(struct perf_output_handle *handle, * because of locking issue as we are called in * NMI context */ - if (read_format & PERF_FORMAT_TOTAL_TIMES) { - now = perf_clock(); - ctx_time = event->shadow_ctx_time + now; - enabled = ctx_time - event->tstamp_enabled; - running = ctx_time - event->tstamp_running; - } + if (read_format & PERF_FORMAT_TOTAL_TIMES) + calc_timer_values(event, &enabled, &running); if (event->attr.read_format & PERF_FORMAT_GROUP) perf_output_read_group(handle, event, enabled, running); @@ -4327,7 +3906,7 @@ void perf_output_sample(struct perf_output_handle *handle, size *= sizeof(u64); - perf_output_copy(handle, data->callchain, size); + __output_copy(handle, data->callchain, size); } else { u64 nr = 0; perf_output_put(handle, nr); @@ -4337,8 +3916,8 @@ void perf_output_sample(struct perf_output_handle *handle, if (sample_type & PERF_SAMPLE_RAW) { if (data->raw) { perf_output_put(handle, data->raw->size); - perf_output_copy(handle, data->raw->data, - data->raw->size); + __output_copy(handle, data->raw->data, + data->raw->size); } else { struct { u32 size; @@ -4350,6 +3929,20 @@ void perf_output_sample(struct perf_output_handle *handle, perf_output_put(handle, raw); } } + + if (!event->attr.watermark) { + int wakeup_events = event->attr.wakeup_events; + + if (wakeup_events) { + struct ring_buffer *rb = handle->rb; + int events = local_inc_return(&rb->events); + + if (events >= wakeup_events) { + local_sub(wakeup_events, &rb->events); + local_inc(&rb->wakeup); + } + } + } } void perf_prepare_sample(struct perf_event_header *header, @@ -4394,7 +3987,7 @@ void perf_prepare_sample(struct perf_event_header *header, } } -static void perf_event_output(struct perf_event *event, int nmi, +static void perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { @@ -4406,7 +3999,7 @@ static void perf_event_output(struct perf_event *event, int nmi, perf_prepare_sample(&header, data, event, regs); - if (perf_output_begin(&handle, event, header.size, nmi, 1)) + if (perf_output_begin(&handle, event, header.size)) goto exit; perf_output_sample(&handle, &header, data, event); @@ -4446,7 +4039,7 @@ perf_event_read_event(struct perf_event *event, int ret; perf_event_header__init_id(&read_event.header, &sample, event); - ret = perf_output_begin(&handle, event, read_event.header.size, 0, 0); + ret = perf_output_begin(&handle, event, read_event.header.size); if (ret) return; @@ -4489,7 +4082,7 @@ static void perf_event_task_output(struct perf_event *event, perf_event_header__init_id(&task_event->event_id.header, &sample, event); ret = perf_output_begin(&handle, event, - task_event->event_id.header.size, 0, 0); + task_event->event_id.header.size); if (ret) goto out; @@ -4626,7 +4219,7 @@ static void perf_event_comm_output(struct perf_event *event, perf_event_header__init_id(&comm_event->event_id.header, &sample, event); ret = perf_output_begin(&handle, event, - comm_event->event_id.header.size, 0, 0); + comm_event->event_id.header.size); if (ret) goto out; @@ -4635,7 +4228,7 @@ static void perf_event_comm_output(struct perf_event *event, comm_event->event_id.tid = perf_event_tid(event, comm_event->task); perf_output_put(&handle, comm_event->event_id); - perf_output_copy(&handle, comm_event->comm, + __output_copy(&handle, comm_event->comm, comm_event->comm_size); perf_event__output_id_sample(event, &handle, &sample); @@ -4773,7 +4366,7 @@ static void perf_event_mmap_output(struct perf_event *event, perf_event_header__init_id(&mmap_event->event_id.header, &sample, event); ret = perf_output_begin(&handle, event, - mmap_event->event_id.header.size, 0, 0); + mmap_event->event_id.header.size); if (ret) goto out; @@ -4781,7 +4374,7 @@ static void perf_event_mmap_output(struct perf_event *event, mmap_event->event_id.tid = perf_event_tid(event, current); perf_output_put(&handle, mmap_event->event_id); - perf_output_copy(&handle, mmap_event->file_name, + __output_copy(&handle, mmap_event->file_name, mmap_event->file_size); perf_event__output_id_sample(event, &handle, &sample); @@ -4837,7 +4430,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) if (file) { /* - * d_path works from the end of the buffer backwards, so we + * d_path works from the end of the rb backwards, so we * need to add enough zero bytes after the string to handle * the 64bit alignment we do later. */ @@ -4968,7 +4561,7 @@ static void perf_log_throttle(struct perf_event *event, int enable) perf_event_header__init_id(&throttle_event.header, &sample, event); ret = perf_output_begin(&handle, event, - throttle_event.header.size, 1, 0); + throttle_event.header.size); if (ret) return; @@ -4981,7 +4574,7 @@ static void perf_log_throttle(struct perf_event *event, int enable) * Generic event overflow handling, sampling. */ -static int __perf_event_overflow(struct perf_event *event, int nmi, +static int __perf_event_overflow(struct perf_event *event, int throttle, struct perf_sample_data *data, struct pt_regs *regs) { @@ -5024,26 +4617,28 @@ static int __perf_event_overflow(struct perf_event *event, int nmi, if (events && atomic_dec_and_test(&event->event_limit)) { ret = 1; event->pending_kill = POLL_HUP; - if (nmi) { - event->pending_disable = 1; - irq_work_queue(&event->pending); - } else - perf_event_disable(event); + event->pending_disable = 1; + irq_work_queue(&event->pending); } if (event->overflow_handler) - event->overflow_handler(event, nmi, data, regs); + event->overflow_handler(event, data, regs); else - perf_event_output(event, nmi, data, regs); + perf_event_output(event, data, regs); + + if (event->fasync && event->pending_kill) { + event->pending_wakeup = 1; + irq_work_queue(&event->pending); + } return ret; } -int perf_event_overflow(struct perf_event *event, int nmi, +int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { - return __perf_event_overflow(event, nmi, 1, data, regs); + return __perf_event_overflow(event, 1, data, regs); } /* @@ -5092,7 +4687,7 @@ again: } static void perf_swevent_overflow(struct perf_event *event, u64 overflow, - int nmi, struct perf_sample_data *data, + struct perf_sample_data *data, struct pt_regs *regs) { struct hw_perf_event *hwc = &event->hw; @@ -5106,7 +4701,7 @@ static void perf_swevent_overflow(struct perf_event *event, u64 overflow, return; for (; overflow; overflow--) { - if (__perf_event_overflow(event, nmi, throttle, + if (__perf_event_overflow(event, throttle, data, regs)) { /* * We inhibit the overflow from happening when @@ -5119,7 +4714,7 @@ static void perf_swevent_overflow(struct perf_event *event, u64 overflow, } static void perf_swevent_event(struct perf_event *event, u64 nr, - int nmi, struct perf_sample_data *data, + struct perf_sample_data *data, struct pt_regs *regs) { struct hw_perf_event *hwc = &event->hw; @@ -5133,12 +4728,12 @@ static void perf_swevent_event(struct perf_event *event, u64 nr, return; if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq) - return perf_swevent_overflow(event, 1, nmi, data, regs); + return perf_swevent_overflow(event, 1, data, regs); if (local64_add_negative(nr, &hwc->period_left)) return; - perf_swevent_overflow(event, 0, nmi, data, regs); + perf_swevent_overflow(event, 0, data, regs); } static int perf_exclude_event(struct perf_event *event, @@ -5226,7 +4821,7 @@ find_swevent_head(struct swevent_htable *swhash, struct perf_event *event) } static void do_perf_sw_event(enum perf_type_id type, u32 event_id, - u64 nr, int nmi, + u64 nr, struct perf_sample_data *data, struct pt_regs *regs) { @@ -5242,7 +4837,7 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id, hlist_for_each_entry_rcu(event, node, head, hlist_entry) { if (perf_swevent_match(event, type, event_id, data, regs)) - perf_swevent_event(event, nr, nmi, data, regs); + perf_swevent_event(event, nr, data, regs); } end: rcu_read_unlock(); @@ -5263,8 +4858,7 @@ inline void perf_swevent_put_recursion_context(int rctx) put_recursion_context(swhash->recursion, rctx); } -void __perf_sw_event(u32 event_id, u64 nr, int nmi, - struct pt_regs *regs, u64 addr) +void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { struct perf_sample_data data; int rctx; @@ -5276,7 +4870,7 @@ void __perf_sw_event(u32 event_id, u64 nr, int nmi, perf_sample_data_init(&data, addr); - do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs); + do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, &data, regs); perf_swevent_put_recursion_context(rctx); preempt_enable_notrace(); @@ -5331,14 +4925,6 @@ swevent_hlist_deref(struct swevent_htable *swhash) lockdep_is_held(&swhash->hlist_mutex)); } -static void swevent_hlist_release_rcu(struct rcu_head *rcu_head) -{ - struct swevent_hlist *hlist; - - hlist = container_of(rcu_head, struct swevent_hlist, rcu_head); - kfree(hlist); -} - static void swevent_hlist_release(struct swevent_htable *swhash) { struct swevent_hlist *hlist = swevent_hlist_deref(swhash); @@ -5347,7 +4933,7 @@ static void swevent_hlist_release(struct swevent_htable *swhash) return; rcu_assign_pointer(swhash->swevent_hlist, NULL); - call_rcu(&hlist->rcu_head, swevent_hlist_release_rcu); + kfree_rcu(hlist, rcu_head); } static void swevent_hlist_put_cpu(struct perf_event *event, int cpu) @@ -5429,7 +5015,7 @@ fail: return err; } -atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX]; +struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; static void sw_perf_event_destroy(struct perf_event *event) { @@ -5532,7 +5118,7 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, hlist_for_each_entry_rcu(event, node, head, hlist_entry) { if (perf_tp_event_match(event, &data, regs)) - perf_swevent_event(event, count, 1, &data, regs); + perf_swevent_event(event, count, &data, regs); } perf_swevent_put_recursion_context(rctx); @@ -5625,7 +5211,7 @@ void perf_bp_event(struct perf_event *bp, void *data) perf_sample_data_init(&sample, bp->attr.bp_addr); if (!bp->hw.state && !perf_exclude_event(bp, regs)) - perf_swevent_event(bp, 1, 1, &sample, regs); + perf_swevent_event(bp, 1, &sample, regs); } #endif @@ -5654,7 +5240,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) if (regs && !perf_exclude_event(event, regs)) { if (!(event->attr.exclude_idle && current->pid == 0)) - if (perf_event_overflow(event, 0, &data, regs)) + if (perf_event_overflow(event, &data, regs)) ret = HRTIMER_NORESTART; } @@ -5994,6 +5580,7 @@ free_dev: } static struct lock_class_key cpuctx_mutex; +static struct lock_class_key cpuctx_lock; int perf_pmu_register(struct pmu *pmu, char *name, int type) { @@ -6044,6 +5631,7 @@ skip_type: cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); __perf_event_init_context(&cpuctx->ctx); lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex); + lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock); cpuctx->ctx.type = cpu_context; cpuctx->ctx.pmu = pmu; cpuctx->jiffies_interval = 1; @@ -6158,7 +5746,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, struct task_struct *task, struct perf_event *group_leader, struct perf_event *parent_event, - perf_overflow_handler_t overflow_handler) + perf_overflow_handler_t overflow_handler, + void *context) { struct pmu *pmu; struct perf_event *event; @@ -6216,10 +5805,13 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, #endif } - if (!overflow_handler && parent_event) + if (!overflow_handler && parent_event) { overflow_handler = parent_event->overflow_handler; + context = parent_event->overflow_handler_context; + } event->overflow_handler = overflow_handler; + event->overflow_handler_context = context; if (attr->disabled) event->state = PERF_EVENT_STATE_OFF; @@ -6334,13 +5926,6 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, if (ret) return -EFAULT; - /* - * If the type exists, the corresponding creation will verify - * the attr->config. - */ - if (attr->type >= PERF_TYPE_MAX) - return -EINVAL; - if (attr->__reserved_1) return -EINVAL; @@ -6362,7 +5947,7 @@ err_size: static int perf_event_set_output(struct perf_event *event, struct perf_event *output_event) { - struct perf_buffer *buffer = NULL, *old_buffer = NULL; + struct ring_buffer *rb = NULL, *old_rb = NULL; int ret = -EINVAL; if (!output_event) @@ -6379,7 +5964,7 @@ perf_event_set_output(struct perf_event *event, struct perf_event *output_event) goto out; /* - * If its not a per-cpu buffer, it must be the same task. + * If its not a per-cpu rb, it must be the same task. */ if (output_event->cpu == -1 && output_event->ctx != event->ctx) goto out; @@ -6391,20 +5976,20 @@ set: goto unlock; if (output_event) { - /* get the buffer we want to redirect to */ - buffer = perf_buffer_get(output_event); - if (!buffer) + /* get the rb we want to redirect to */ + rb = ring_buffer_get(output_event); + if (!rb) goto unlock; } - old_buffer = event->buffer; - rcu_assign_pointer(event->buffer, buffer); + old_rb = event->rb; + rcu_assign_pointer(event->rb, rb); ret = 0; unlock: mutex_unlock(&event->mmap_mutex); - if (old_buffer) - perf_buffer_put(old_buffer); + if (old_rb) + ring_buffer_put(old_rb); out: return ret; } @@ -6486,7 +6071,8 @@ SYSCALL_DEFINE5(perf_event_open, } } - event = perf_event_alloc(&attr, cpu, task, group_leader, NULL, NULL); + event = perf_event_alloc(&attr, cpu, task, group_leader, NULL, + NULL, NULL); if (IS_ERR(event)) { err = PTR_ERR(event); goto err_task; @@ -6671,7 +6257,8 @@ err_fd: struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, struct task_struct *task, - perf_overflow_handler_t overflow_handler) + perf_overflow_handler_t overflow_handler, + void *context) { struct perf_event_context *ctx; struct perf_event *event; @@ -6681,7 +6268,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, * Get the target context (task or percpu): */ - event = perf_event_alloc(attr, cpu, task, NULL, NULL, overflow_handler); + event = perf_event_alloc(attr, cpu, task, NULL, NULL, + overflow_handler, context); if (IS_ERR(event)) { err = PTR_ERR(event); goto err; @@ -6788,7 +6376,6 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) * our context. */ child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]); - task_ctx_sched_out(child_ctx, EVENT_ALL); /* * Take the context lock here so that if find_get_context is @@ -6796,6 +6383,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) * incremented the context's refcount before we do put_ctx below. */ raw_spin_lock(&child_ctx->lock); + task_ctx_sched_out(child_ctx); child->perf_event_ctxp[ctxn] = NULL; /* * If this context is a clone; unclone it so it can't get @@ -6965,7 +6553,7 @@ inherit_event(struct perf_event *parent_event, parent_event->cpu, child, group_leader, parent_event, - NULL); + NULL, NULL); if (IS_ERR(child_event)) return child_event; get_ctx(child_ctx); @@ -6992,6 +6580,8 @@ inherit_event(struct perf_event *parent_event, child_event->ctx = child_ctx; child_event->overflow_handler = parent_event->overflow_handler; + child_event->overflow_handler_context + = parent_event->overflow_handler_context; /* * Precalculate sample_data sizes @@ -7410,26 +7000,12 @@ static int __perf_cgroup_move(void *info) return 0; } -static void perf_cgroup_move(struct task_struct *task) +static void +perf_cgroup_attach_task(struct cgroup *cgrp, struct task_struct *task) { task_function_call(task, __perf_cgroup_move, task); } -static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cgrp, struct task_struct *task, - bool threadgroup) -{ - perf_cgroup_move(task); - if (threadgroup) { - struct task_struct *c; - rcu_read_lock(); - list_for_each_entry_rcu(c, &task->thread_group, thread_group) { - perf_cgroup_move(c); - } - rcu_read_unlock(); - } -} - static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, struct cgroup *old_cgrp, struct task_struct *task) { @@ -7441,15 +7017,15 @@ static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, if (!(task->flags & PF_EXITING)) return; - perf_cgroup_move(task); + perf_cgroup_attach_task(cgrp, task); } struct cgroup_subsys perf_subsys = { - .name = "perf_event", - .subsys_id = perf_subsys_id, - .create = perf_cgroup_create, - .destroy = perf_cgroup_destroy, - .exit = perf_cgroup_exit, - .attach = perf_cgroup_attach, + .name = "perf_event", + .subsys_id = perf_subsys_id, + .create = perf_cgroup_create, + .destroy = perf_cgroup_destroy, + .exit = perf_cgroup_exit, + .attach_task = perf_cgroup_attach_task, }; #endif /* CONFIG_CGROUP_PERF */ diff --git a/kernel/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index 086adf25a55..b7971d6f38b 100644 --- a/kernel/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -431,9 +431,11 @@ int register_perf_hw_breakpoint(struct perf_event *bp) struct perf_event * register_user_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered, + void *context, struct task_struct *tsk) { - return perf_event_create_kernel_counter(attr, -1, tsk, triggered); + return perf_event_create_kernel_counter(attr, -1, tsk, triggered, + context); } EXPORT_SYMBOL_GPL(register_user_hw_breakpoint); @@ -502,7 +504,8 @@ EXPORT_SYMBOL_GPL(unregister_hw_breakpoint); */ struct perf_event * __percpu * register_wide_hw_breakpoint(struct perf_event_attr *attr, - perf_overflow_handler_t triggered) + perf_overflow_handler_t triggered, + void *context) { struct perf_event * __percpu *cpu_events, **pevent, *bp; long err; @@ -515,7 +518,8 @@ register_wide_hw_breakpoint(struct perf_event_attr *attr, get_online_cpus(); for_each_online_cpu(cpu) { pevent = per_cpu_ptr(cpu_events, cpu); - bp = perf_event_create_kernel_counter(attr, cpu, NULL, triggered); + bp = perf_event_create_kernel_counter(attr, cpu, NULL, + triggered, context); *pevent = bp; diff --git a/kernel/events/internal.h b/kernel/events/internal.h new file mode 100644 index 00000000000..09097dd8116 --- /dev/null +++ b/kernel/events/internal.h @@ -0,0 +1,96 @@ +#ifndef _KERNEL_EVENTS_INTERNAL_H +#define _KERNEL_EVENTS_INTERNAL_H + +#define RING_BUFFER_WRITABLE 0x01 + +struct ring_buffer { + atomic_t refcount; + struct rcu_head rcu_head; +#ifdef CONFIG_PERF_USE_VMALLOC + struct work_struct work; + int page_order; /* allocation order */ +#endif + int nr_pages; /* nr of data pages */ + int writable; /* are we writable */ + + atomic_t poll; /* POLL_ for wakeups */ + + local_t head; /* write position */ + local_t nest; /* nested writers */ + local_t events; /* event limit */ + local_t wakeup; /* wakeup stamp */ + local_t lost; /* nr records lost */ + + long watermark; /* wakeup watermark */ + + struct perf_event_mmap_page *user_page; + void *data_pages[0]; +}; + +extern void rb_free(struct ring_buffer *rb); +extern struct ring_buffer * +rb_alloc(int nr_pages, long watermark, int cpu, int flags); +extern void perf_event_wakeup(struct perf_event *event); + +extern void +perf_event_header__init_id(struct perf_event_header *header, + struct perf_sample_data *data, + struct perf_event *event); +extern void +perf_event__output_id_sample(struct perf_event *event, + struct perf_output_handle *handle, + struct perf_sample_data *sample); + +extern struct page * +perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff); + +#ifdef CONFIG_PERF_USE_VMALLOC +/* + * Back perf_mmap() with vmalloc memory. + * + * Required for architectures that have d-cache aliasing issues. + */ + +static inline int page_order(struct ring_buffer *rb) +{ + return rb->page_order; +} + +#else + +static inline int page_order(struct ring_buffer *rb) +{ + return 0; +} +#endif + +static unsigned long perf_data_size(struct ring_buffer *rb) +{ + return rb->nr_pages << (PAGE_SHIFT + page_order(rb)); +} + +static inline void +__output_copy(struct perf_output_handle *handle, + const void *buf, unsigned int len) +{ + do { + unsigned long size = min_t(unsigned long, handle->size, len); + + memcpy(handle->addr, buf, size); + + len -= size; + handle->addr += size; + buf += size; + handle->size -= size; + if (!handle->size) { + struct ring_buffer *rb = handle->rb; + + handle->page++; + handle->page &= rb->nr_pages - 1; + handle->addr = rb->data_pages[handle->page]; + handle->size = PAGE_SIZE << page_order(rb); + } + } while (len); +} + +#endif /* _KERNEL_EVENTS_INTERNAL_H */ diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c new file mode 100644 index 00000000000..a2a29205cc0 --- /dev/null +++ b/kernel/events/ring_buffer.c @@ -0,0 +1,380 @@ +/* + * Performance events ring-buffer code: + * + * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> + * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> + * + * For licensing details see kernel-base/COPYING + */ + +#include <linux/perf_event.h> +#include <linux/vmalloc.h> +#include <linux/slab.h> + +#include "internal.h" + +static bool perf_output_space(struct ring_buffer *rb, unsigned long tail, + unsigned long offset, unsigned long head) +{ + unsigned long mask; + + if (!rb->writable) + return true; + + mask = perf_data_size(rb) - 1; + + offset = (offset - tail) & mask; + head = (head - tail) & mask; + + if ((int)(head - offset) < 0) + return false; + + return true; +} + +static void perf_output_wakeup(struct perf_output_handle *handle) +{ + atomic_set(&handle->rb->poll, POLL_IN); + + handle->event->pending_wakeup = 1; + irq_work_queue(&handle->event->pending); +} + +/* + * We need to ensure a later event_id doesn't publish a head when a former + * event isn't done writing. However since we need to deal with NMIs we + * cannot fully serialize things. + * + * We only publish the head (and generate a wakeup) when the outer-most + * event completes. + */ +static void perf_output_get_handle(struct perf_output_handle *handle) +{ + struct ring_buffer *rb = handle->rb; + + preempt_disable(); + local_inc(&rb->nest); + handle->wakeup = local_read(&rb->wakeup); +} + +static void perf_output_put_handle(struct perf_output_handle *handle) +{ + struct ring_buffer *rb = handle->rb; + unsigned long head; + +again: + head = local_read(&rb->head); + + /* + * IRQ/NMI can happen here, which means we can miss a head update. + */ + + if (!local_dec_and_test(&rb->nest)) + goto out; + + /* + * Publish the known good head. Rely on the full barrier implied + * by atomic_dec_and_test() order the rb->head read and this + * write. + */ + rb->user_page->data_head = head; + + /* + * Now check if we missed an update, rely on the (compiler) + * barrier in atomic_dec_and_test() to re-read rb->head. + */ + if (unlikely(head != local_read(&rb->head))) { + local_inc(&rb->nest); + goto again; + } + + if (handle->wakeup != local_read(&rb->wakeup)) + perf_output_wakeup(handle); + +out: + preempt_enable(); +} + +int perf_output_begin(struct perf_output_handle *handle, + struct perf_event *event, unsigned int size) +{ + struct ring_buffer *rb; + unsigned long tail, offset, head; + int have_lost; + struct perf_sample_data sample_data; + struct { + struct perf_event_header header; + u64 id; + u64 lost; + } lost_event; + + rcu_read_lock(); + /* + * For inherited events we send all the output towards the parent. + */ + if (event->parent) + event = event->parent; + + rb = rcu_dereference(event->rb); + if (!rb) + goto out; + + handle->rb = rb; + handle->event = event; + + if (!rb->nr_pages) + goto out; + + have_lost = local_read(&rb->lost); + if (have_lost) { + lost_event.header.size = sizeof(lost_event); + perf_event_header__init_id(&lost_event.header, &sample_data, + event); + size += lost_event.header.size; + } + + perf_output_get_handle(handle); + + do { + /* + * Userspace could choose to issue a mb() before updating the + * tail pointer. So that all reads will be completed before the + * write is issued. + */ + tail = ACCESS_ONCE(rb->user_page->data_tail); + smp_rmb(); + offset = head = local_read(&rb->head); + head += size; + if (unlikely(!perf_output_space(rb, tail, offset, head))) + goto fail; + } while (local_cmpxchg(&rb->head, offset, head) != offset); + + if (head - local_read(&rb->wakeup) > rb->watermark) + local_add(rb->watermark, &rb->wakeup); + + handle->page = offset >> (PAGE_SHIFT + page_order(rb)); + handle->page &= rb->nr_pages - 1; + handle->size = offset & ((PAGE_SIZE << page_order(rb)) - 1); + handle->addr = rb->data_pages[handle->page]; + handle->addr += handle->size; + handle->size = (PAGE_SIZE << page_order(rb)) - handle->size; + + if (have_lost) { + lost_event.header.type = PERF_RECORD_LOST; + lost_event.header.misc = 0; + lost_event.id = event->id; + lost_event.lost = local_xchg(&rb->lost, 0); + + perf_output_put(handle, lost_event); + perf_event__output_id_sample(event, handle, &sample_data); + } + + return 0; + +fail: + local_inc(&rb->lost); + perf_output_put_handle(handle); +out: + rcu_read_unlock(); + + return -ENOSPC; +} + +void perf_output_copy(struct perf_output_handle *handle, + const void *buf, unsigned int len) +{ + __output_copy(handle, buf, len); +} + +void perf_output_end(struct perf_output_handle *handle) +{ + perf_output_put_handle(handle); + rcu_read_unlock(); +} + +static void +ring_buffer_init(struct ring_buffer *rb, long watermark, int flags) +{ + long max_size = perf_data_size(rb); + + if (watermark) + rb->watermark = min(max_size, watermark); + + if (!rb->watermark) + rb->watermark = max_size / 2; + + if (flags & RING_BUFFER_WRITABLE) + rb->writable = 1; + + atomic_set(&rb->refcount, 1); +} + +#ifndef CONFIG_PERF_USE_VMALLOC + +/* + * Back perf_mmap() with regular GFP_KERNEL-0 pages. + */ + +struct page * +perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) +{ + if (pgoff > rb->nr_pages) + return NULL; + + if (pgoff == 0) + return virt_to_page(rb->user_page); + + return virt_to_page(rb->data_pages[pgoff - 1]); +} + +static void *perf_mmap_alloc_page(int cpu) +{ + struct page *page; + int node; + + node = (cpu == -1) ? cpu : cpu_to_node(cpu); + page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); + if (!page) + return NULL; + + return page_address(page); +} + +struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) +{ + struct ring_buffer *rb; + unsigned long size; + int i; + + size = sizeof(struct ring_buffer); + size += nr_pages * sizeof(void *); + + rb = kzalloc(size, GFP_KERNEL); + if (!rb) + goto fail; + + rb->user_page = perf_mmap_alloc_page(cpu); + if (!rb->user_page) + goto fail_user_page; + + for (i = 0; i < nr_pages; i++) { + rb->data_pages[i] = perf_mmap_alloc_page(cpu); + if (!rb->data_pages[i]) + goto fail_data_pages; + } + + rb->nr_pages = nr_pages; + + ring_buffer_init(rb, watermark, flags); + + return rb; + +fail_data_pages: + for (i--; i >= 0; i--) + free_page((unsigned long)rb->data_pages[i]); + + free_page((unsigned long)rb->user_page); + +fail_user_page: + kfree(rb); + +fail: + return NULL; +} + +static void perf_mmap_free_page(unsigned long addr) +{ + struct page *page = virt_to_page((void *)addr); + + page->mapping = NULL; + __free_page(page); +} + +void rb_free(struct ring_buffer *rb) +{ + int i; + + perf_mmap_free_page((unsigned long)rb->user_page); + for (i = 0; i < rb->nr_pages; i++) + perf_mmap_free_page((unsigned long)rb->data_pages[i]); + kfree(rb); +} + +#else + +struct page * +perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) +{ + if (pgoff > (1UL << page_order(rb))) + return NULL; + + return vmalloc_to_page((void *)rb->user_page + pgoff * PAGE_SIZE); +} + +static void perf_mmap_unmark_page(void *addr) +{ + struct page *page = vmalloc_to_page(addr); + + page->mapping = NULL; +} + +static void rb_free_work(struct work_struct *work) +{ + struct ring_buffer *rb; + void *base; + int i, nr; + + rb = container_of(work, struct ring_buffer, work); + nr = 1 << page_order(rb); + + base = rb->user_page; + for (i = 0; i < nr + 1; i++) + perf_mmap_unmark_page(base + (i * PAGE_SIZE)); + + vfree(base); + kfree(rb); +} + +void rb_free(struct ring_buffer *rb) +{ + schedule_work(&rb->work); +} + +struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) +{ + struct ring_buffer *rb; + unsigned long size; + void *all_buf; + + size = sizeof(struct ring_buffer); + size += sizeof(void *); + + rb = kzalloc(size, GFP_KERNEL); + if (!rb) + goto fail; + + INIT_WORK(&rb->work, rb_free_work); + + all_buf = vmalloc_user((nr_pages + 1) * PAGE_SIZE); + if (!all_buf) + goto fail_all_buf; + + rb->user_page = all_buf; + rb->data_pages[0] = all_buf + PAGE_SIZE; + rb->page_order = ilog2(nr_pages); + rb->nr_pages = 1; + + ring_buffer_init(rb, watermark, flags); + + return rb; + +fail_all_buf: + kfree(rb); + +fail: + return NULL; +} + +#endif diff --git a/kernel/exit.c b/kernel/exit.c index f5d2f63bae0..2913b3509d4 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -85,7 +85,6 @@ static void __exit_signal(struct task_struct *tsk) struct tty_struct *uninitialized_var(tty); sighand = rcu_dereference_check(tsk->sighand, - rcu_read_lock_held() || lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); @@ -169,7 +168,6 @@ void release_task(struct task_struct * p) struct task_struct *leader; int zap_leader; repeat: - tracehook_prepare_release_task(p); /* don't need to get the RCU readlock here - the process is dead and * can't be modifying its own credentials. But shut RCU-lockdep up */ rcu_read_lock(); @@ -179,7 +177,7 @@ repeat: proc_flush_task(p); write_lock_irq(&tasklist_lock); - tracehook_finish_release_task(p); + ptrace_release_task(p); __exit_signal(p); /* @@ -190,22 +188,12 @@ repeat: zap_leader = 0; leader = p->group_leader; if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) { - BUG_ON(task_detached(leader)); - do_notify_parent(leader, leader->exit_signal); /* * If we were the last child thread and the leader has * exited already, and the leader's parent ignores SIGCHLD, * then we are the one who should release the leader. - * - * do_notify_parent() will have marked it self-reaping in - * that case. - */ - zap_leader = task_detached(leader); - - /* - * This maintains the invariant that release_task() - * only runs on a task in EXIT_DEAD, just for sanity. */ + zap_leader = do_notify_parent(leader, leader->exit_signal); if (zap_leader) leader->exit_state = EXIT_DEAD; } @@ -277,18 +265,16 @@ int is_current_pgrp_orphaned(void) return retval; } -static int has_stopped_jobs(struct pid *pgrp) +static bool has_stopped_jobs(struct pid *pgrp) { - int retval = 0; struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { - if (!task_is_stopped(p)) - continue; - retval = 1; - break; + if (p->signal->flags & SIGNAL_STOP_STOPPED) + return true; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); - return retval; + + return false; } /* @@ -561,29 +547,28 @@ void exit_files(struct task_struct *tsk) #ifdef CONFIG_MM_OWNER /* - * Task p is exiting and it owned mm, lets find a new owner for it + * A task is exiting. If it owned this mm, find a new owner for the mm. */ -static inline int -mm_need_new_owner(struct mm_struct *mm, struct task_struct *p) -{ - /* - * If there are other users of the mm and the owner (us) is exiting - * we need to find a new owner to take on the responsibility. - */ - if (atomic_read(&mm->mm_users) <= 1) - return 0; - if (mm->owner != p) - return 0; - return 1; -} - void mm_update_next_owner(struct mm_struct *mm) { struct task_struct *c, *g, *p = current; retry: - if (!mm_need_new_owner(mm, p)) + /* + * If the exiting or execing task is not the owner, it's + * someone else's problem. + */ + if (mm->owner != p) return; + /* + * The current owner is exiting/execing and there are no other + * candidates. Do not leave the mm pointing to a possibly + * freed task structure. + */ + if (atomic_read(&mm->mm_users) <= 1) { + mm->owner = NULL; + return; + } read_lock(&tasklist_lock); /* @@ -752,7 +737,7 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p, { list_move_tail(&p->sibling, &p->real_parent->children); - if (task_detached(p)) + if (p->exit_state == EXIT_DEAD) return; /* * If this is a threaded reparent there is no need to @@ -765,10 +750,9 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p, p->exit_signal = SIGCHLD; /* If it has exited notify the new parent about this child's death. */ - if (!task_ptrace(p) && + if (!p->ptrace && p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) { - do_notify_parent(p, p->exit_signal); - if (task_detached(p)) { + if (do_notify_parent(p, p->exit_signal)) { p->exit_state = EXIT_DEAD; list_move_tail(&p->sibling, dead); } @@ -795,7 +779,7 @@ static void forget_original_parent(struct task_struct *father) do { t->real_parent = reaper; if (t->parent == father) { - BUG_ON(task_ptrace(t)); + BUG_ON(t->ptrace); t->parent = t->real_parent; } if (t->pdeath_signal) @@ -820,8 +804,7 @@ static void forget_original_parent(struct task_struct *father) */ static void exit_notify(struct task_struct *tsk, int group_dead) { - int signal; - void *cookie; + bool autoreap; /* * This does two things: @@ -852,26 +835,33 @@ static void exit_notify(struct task_struct *tsk, int group_dead) * we have changed execution domain as these two values started * the same after a fork. */ - if (tsk->exit_signal != SIGCHLD && !task_detached(tsk) && + if (thread_group_leader(tsk) && tsk->exit_signal != SIGCHLD && (tsk->parent_exec_id != tsk->real_parent->self_exec_id || tsk->self_exec_id != tsk->parent_exec_id)) tsk->exit_signal = SIGCHLD; - signal = tracehook_notify_death(tsk, &cookie, group_dead); - if (signal >= 0) - signal = do_notify_parent(tsk, signal); + if (unlikely(tsk->ptrace)) { + int sig = thread_group_leader(tsk) && + thread_group_empty(tsk) && + !ptrace_reparented(tsk) ? + tsk->exit_signal : SIGCHLD; + autoreap = do_notify_parent(tsk, sig); + } else if (thread_group_leader(tsk)) { + autoreap = thread_group_empty(tsk) && + do_notify_parent(tsk, tsk->exit_signal); + } else { + autoreap = true; + } - tsk->exit_state = signal == DEATH_REAP ? EXIT_DEAD : EXIT_ZOMBIE; + tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE; /* mt-exec, de_thread() is waiting for group leader */ if (unlikely(tsk->signal->notify_count < 0)) wake_up_process(tsk->signal->group_exit_task); write_unlock_irq(&tasklist_lock); - tracehook_report_death(tsk, signal, cookie, group_dead); - /* If the process is dead, release it - nobody will wait for it */ - if (signal == DEATH_REAP) + if (autoreap) release_task(tsk); } @@ -907,7 +897,6 @@ NORET_TYPE void do_exit(long code) profile_task_exit(tsk); - WARN_ON(atomic_read(&tsk->fs_excl)); WARN_ON(blk_needs_flush_plug(tsk)); if (unlikely(in_interrupt())) @@ -924,7 +913,7 @@ NORET_TYPE void do_exit(long code) */ set_fs(USER_DS); - tracehook_report_exit(&code); + ptrace_event(PTRACE_EVENT_EXIT, code); validate_creds_for_do_exit(tsk); @@ -991,6 +980,7 @@ NORET_TYPE void do_exit(long code) trace_sched_process_exit(tsk); exit_sem(tsk); + exit_shm(tsk); exit_files(tsk); exit_fs(tsk); check_stack_usage(); @@ -1016,7 +1006,7 @@ NORET_TYPE void do_exit(long code) /* * FIXME: do that only when needed, using sched_exit tracepoint */ - flush_ptrace_hw_breakpoint(tsk); + ptrace_put_breakpoints(tsk); exit_notify(tsk, group_dead); #ifdef CONFIG_NUMA @@ -1236,9 +1226,9 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) traced = ptrace_reparented(p); /* * It can be ptraced but not reparented, check - * !task_detached() to filter out sub-threads. + * thread_group_leader() to filter out sub-threads. */ - if (likely(!traced) && likely(!task_detached(p))) { + if (likely(!traced) && thread_group_leader(p)) { struct signal_struct *psig; struct signal_struct *sig; unsigned long maxrss; @@ -1346,16 +1336,13 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) /* We dropped tasklist, ptracer could die and untrace */ ptrace_unlink(p); /* - * If this is not a detached task, notify the parent. - * If it's still not detached after that, don't release - * it now. + * If this is not a sub-thread, notify the parent. + * If parent wants a zombie, don't release it now. */ - if (!task_detached(p)) { - do_notify_parent(p, p->exit_signal); - if (!task_detached(p)) { - p->exit_state = EXIT_ZOMBIE; - p = NULL; - } + if (thread_group_leader(p) && + !do_notify_parent(p, p->exit_signal)) { + p->exit_state = EXIT_ZOMBIE; + p = NULL; } write_unlock_irq(&tasklist_lock); } @@ -1368,7 +1355,8 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) static int *task_stopped_code(struct task_struct *p, bool ptrace) { if (ptrace) { - if (task_is_stopped_or_traced(p)) + if (task_is_stopped_or_traced(p) && + !(p->jobctl & JOBCTL_LISTENING)) return &p->exit_code; } else { if (p->signal->flags & SIGNAL_STOP_STOPPED) @@ -1377,11 +1365,23 @@ static int *task_stopped_code(struct task_struct *p, bool ptrace) return NULL; } -/* - * Handle sys_wait4 work for one task in state TASK_STOPPED. We hold - * read_lock(&tasklist_lock) on entry. If we return zero, we still hold - * the lock and this task is uninteresting. If we return nonzero, we have - * released the lock and the system call should return. +/** + * wait_task_stopped - Wait for %TASK_STOPPED or %TASK_TRACED + * @wo: wait options + * @ptrace: is the wait for ptrace + * @p: task to wait for + * + * Handle sys_wait4() work for %p in state %TASK_STOPPED or %TASK_TRACED. + * + * CONTEXT: + * read_lock(&tasklist_lock), which is released if return value is + * non-zero. Also, grabs and releases @p->sighand->siglock. + * + * RETURNS: + * 0 if wait condition didn't exist and search for other wait conditions + * should continue. Non-zero return, -errno on failure and @p's pid on + * success, implies that tasklist_lock is released and wait condition + * search should terminate. */ static int wait_task_stopped(struct wait_opts *wo, int ptrace, struct task_struct *p) @@ -1397,6 +1397,9 @@ static int wait_task_stopped(struct wait_opts *wo, if (!ptrace && !(wo->wo_flags & WUNTRACED)) return 0; + if (!task_stopped_code(p, ptrace)) + return 0; + exit_code = 0; spin_lock_irq(&p->sighand->siglock); @@ -1538,33 +1541,83 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace, return 0; } - if (likely(!ptrace) && unlikely(task_ptrace(p))) { + /* dead body doesn't have much to contribute */ + if (p->exit_state == EXIT_DEAD) + return 0; + + /* slay zombie? */ + if (p->exit_state == EXIT_ZOMBIE) { + /* + * A zombie ptracee is only visible to its ptracer. + * Notification and reaping will be cascaded to the real + * parent when the ptracer detaches. + */ + if (likely(!ptrace) && unlikely(p->ptrace)) { + /* it will become visible, clear notask_error */ + wo->notask_error = 0; + return 0; + } + + /* we don't reap group leaders with subthreads */ + if (!delay_group_leader(p)) + return wait_task_zombie(wo, p); + + /* + * Allow access to stopped/continued state via zombie by + * falling through. Clearing of notask_error is complex. + * + * When !@ptrace: + * + * If WEXITED is set, notask_error should naturally be + * cleared. If not, subset of WSTOPPED|WCONTINUED is set, + * so, if there are live subthreads, there are events to + * wait for. If all subthreads are dead, it's still safe + * to clear - this function will be called again in finite + * amount time once all the subthreads are released and + * will then return without clearing. + * + * When @ptrace: + * + * Stopped state is per-task and thus can't change once the + * target task dies. Only continued and exited can happen. + * Clear notask_error if WCONTINUED | WEXITED. + */ + if (likely(!ptrace) || (wo->wo_flags & (WCONTINUED | WEXITED))) + wo->notask_error = 0; + } else { + /* + * If @p is ptraced by a task in its real parent's group, + * hide group stop/continued state when looking at @p as + * the real parent; otherwise, a single stop can be + * reported twice as group and ptrace stops. + * + * If a ptracer wants to distinguish the two events for its + * own children, it should create a separate process which + * takes the role of real parent. + */ + if (likely(!ptrace) && p->ptrace && !ptrace_reparented(p)) + return 0; + /* - * This child is hidden by ptrace. - * We aren't allowed to see it now, but eventually we will. + * @p is alive and it's gonna stop, continue or exit, so + * there always is something to wait for. */ wo->notask_error = 0; - return 0; } - if (p->exit_state == EXIT_DEAD) - return 0; - /* - * We don't reap group leaders with subthreads. + * Wait for stopped. Depending on @ptrace, different stopped state + * is used and the two don't interact with each other. */ - if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p)) - return wait_task_zombie(wo, p); + ret = wait_task_stopped(wo, ptrace, p); + if (ret) + return ret; /* - * It's stopped or running now, so it might - * later continue, exit, or stop again. + * Wait for continued. There's only one continued state and the + * ptracer can consume it which can confuse the real parent. Don't + * use WCONTINUED from ptracer. You don't need or want it. */ - wo->notask_error = 0; - - if (task_stopped_code(p, ptrace)) - return wait_task_stopped(wo, ptrace, p); - return wait_task_continued(wo, p); } diff --git a/kernel/extable.c b/kernel/extable.c index 7f8f263f852..5339705b824 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -72,6 +72,24 @@ int core_kernel_text(unsigned long addr) return 0; } +/** + * core_kernel_data - tell if addr points to kernel data + * @addr: address to test + * + * Returns true if @addr passed in is from the core kernel data + * section. + * + * Note: On some archs it may return true for core RODATA, and false + * for others. But will always be true for core RW data. + */ +int core_kernel_data(unsigned long addr) +{ + if (addr >= (unsigned long)_sdata && + addr < (unsigned long)_edata) + return 1; + return 0; +} + int __kernel_text_address(unsigned long addr) { if (core_kernel_text(addr)) diff --git a/kernel/fork.c b/kernel/fork.c index e7548dee636..e7ceaca8960 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -37,7 +37,6 @@ #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/jiffies.h> -#include <linux/tracehook.h> #include <linux/futex.h> #include <linux/compat.h> #include <linux/kthread.h> @@ -59,7 +58,6 @@ #include <linux/taskstats_kern.h> #include <linux/random.h> #include <linux/tty.h> -#include <linux/proc_fs.h> #include <linux/blkdev.h> #include <linux/fs_struct.h> #include <linux/magic.h> @@ -82,7 +80,7 @@ * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ -int nr_threads; /* The idle threads do not count.. */ +int nr_threads; /* The idle threads do not count.. */ int max_threads; /* tunable limit on nr_threads */ @@ -234,7 +232,7 @@ void __init fork_init(unsigned long mempages) /* * we need to allow at least 20 threads to boot a system */ - if(max_threads < 20) + if (max_threads < 20) max_threads = 20; init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; @@ -270,7 +268,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) return NULL; } - err = arch_dup_task_struct(tsk, orig); + err = arch_dup_task_struct(tsk, orig); if (err) goto out; @@ -290,9 +288,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) tsk->stack_canary = get_random_int(); #endif - /* One for us, one for whoever does the "release_task()" (usually parent) */ - atomic_set(&tsk->usage,2); - atomic_set(&tsk->fs_excl, 0); + /* + * One for us, one for whoever does the "release_task()" (usually + * parent) + */ + atomic_set(&tsk->usage, 2); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif @@ -383,15 +383,14 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) get_file(file); if (tmp->vm_flags & VM_DENYWRITE) atomic_dec(&inode->i_writecount); - spin_lock(&mapping->i_mmap_lock); + mutex_lock(&mapping->i_mmap_mutex); if (tmp->vm_flags & VM_SHARED) mapping->i_mmap_writable++; - tmp->vm_truncate_count = mpnt->vm_truncate_count; flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ vma_prio_tree_add(tmp, mpnt); flush_dcache_mmap_unlock(mapping); - spin_unlock(&mapping->i_mmap_lock); + mutex_unlock(&mapping->i_mmap_mutex); } /* @@ -441,7 +440,7 @@ fail_nomem: goto out; } -static inline int mm_alloc_pgd(struct mm_struct * mm) +static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) @@ -449,7 +448,7 @@ static inline int mm_alloc_pgd(struct mm_struct * mm) return 0; } -static inline void mm_free_pgd(struct mm_struct * mm) +static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } @@ -486,7 +485,7 @@ static void mm_init_aio(struct mm_struct *mm) #endif } -static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) +static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) { atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); @@ -517,16 +516,17 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) /* * Allocate and initialize an mm_struct. */ -struct mm_struct * mm_alloc(void) +struct mm_struct *mm_alloc(void) { - struct mm_struct * mm; + struct mm_struct *mm; mm = allocate_mm(); - if (mm) { - memset(mm, 0, sizeof(*mm)); - mm = mm_init(mm, current); - } - return mm; + if (!mm) + return NULL; + + memset(mm, 0, sizeof(*mm)); + mm_init_cpumask(mm); + return mm_init(mm, current); } /* @@ -573,6 +573,57 @@ void mmput(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mmput); +/* + * We added or removed a vma mapping the executable. The vmas are only mapped + * during exec and are not mapped with the mmap system call. + * Callers must hold down_write() on the mm's mmap_sem for these + */ +void added_exe_file_vma(struct mm_struct *mm) +{ + mm->num_exe_file_vmas++; +} + +void removed_exe_file_vma(struct mm_struct *mm) +{ + mm->num_exe_file_vmas--; + if ((mm->num_exe_file_vmas == 0) && mm->exe_file) { + fput(mm->exe_file); + mm->exe_file = NULL; + } + +} + +void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) +{ + if (new_exe_file) + get_file(new_exe_file); + if (mm->exe_file) + fput(mm->exe_file); + mm->exe_file = new_exe_file; + mm->num_exe_file_vmas = 0; +} + +struct file *get_mm_exe_file(struct mm_struct *mm) +{ + struct file *exe_file; + + /* We need mmap_sem to protect against races with removal of + * VM_EXECUTABLE vmas */ + down_read(&mm->mmap_sem); + exe_file = mm->exe_file; + if (exe_file) + get_file(exe_file); + up_read(&mm->mmap_sem); + return exe_file; +} + +static void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm) +{ + /* It's safe to write the exe_file pointer without exe_file_lock because + * this is called during fork when the task is not yet in /proc */ + newmm->exe_file = get_mm_exe_file(oldmm); +} + /** * get_task_mm - acquire a reference to the task's mm * @@ -679,6 +730,7 @@ struct mm_struct *dup_mm(struct task_struct *tsk) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); + mm_init_cpumask(mm); /* Initializing for Swap token stuff */ mm->token_priority = 0; @@ -726,9 +778,9 @@ fail_nocontext: return NULL; } -static int copy_mm(unsigned long clone_flags, struct task_struct * tsk) +static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) { - struct mm_struct * mm, *oldmm; + struct mm_struct *mm, *oldmm; int retval; tsk->min_flt = tsk->maj_flt = 0; @@ -795,7 +847,7 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) return 0; } -static int copy_files(unsigned long clone_flags, struct task_struct * tsk) +static int copy_files(unsigned long clone_flags, struct task_struct *tsk) { struct files_struct *oldf, *newf; int error = 0; @@ -927,6 +979,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) tty_audit_fork(sig); sched_autogroup_fork(sig); +#ifdef CONFIG_CGROUPS + init_rwsem(&sig->threadgroup_fork_lock); +#endif + sig->oom_adj = current->signal->oom_adj; sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; @@ -958,7 +1014,7 @@ static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES - plist_head_init_raw(&p->pi_waiters, &p->pi_lock); + plist_head_init(&p->pi_waiters); p->pi_blocked_on = NULL; #endif } @@ -1103,22 +1159,27 @@ static struct task_struct *copy_process(unsigned long clone_flags, posix_cpu_timers_init(p); - p->lock_depth = -1; /* -1 = no lock */ do_posix_clock_monotonic_gettime(&p->start_time); p->real_start_time = p->start_time; monotonic_to_bootbased(&p->real_start_time); p->io_context = NULL; p->audit_context = NULL; + if (clone_flags & CLONE_THREAD) + threadgroup_fork_read_lock(current); cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); - if (IS_ERR(p->mempolicy)) { - retval = PTR_ERR(p->mempolicy); - p->mempolicy = NULL; - goto bad_fork_cleanup_cgroup; - } + if (IS_ERR(p->mempolicy)) { + retval = PTR_ERR(p->mempolicy); + p->mempolicy = NULL; + goto bad_fork_cleanup_cgroup; + } mpol_fix_fork_child_flag(p); #endif +#ifdef CONFIG_CPUSETS + p->cpuset_mem_spread_rotor = NUMA_NO_NODE; + p->cpuset_slab_spread_rotor = NUMA_NO_NODE; +#endif #ifdef CONFIG_TRACE_IRQFLAGS p->irq_events = 0; #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW @@ -1153,30 +1214,38 @@ static struct task_struct *copy_process(unsigned long clone_flags, #endif /* Perform scheduler related setup. Assign this task to a CPU. */ - sched_fork(p, clone_flags); + sched_fork(p); retval = perf_event_init_task(p); if (retval) goto bad_fork_cleanup_policy; - - if ((retval = audit_alloc(p))) + retval = audit_alloc(p); + if (retval) goto bad_fork_cleanup_policy; /* copy all the process information */ - if ((retval = copy_semundo(clone_flags, p))) + retval = copy_semundo(clone_flags, p); + if (retval) goto bad_fork_cleanup_audit; - if ((retval = copy_files(clone_flags, p))) + retval = copy_files(clone_flags, p); + if (retval) goto bad_fork_cleanup_semundo; - if ((retval = copy_fs(clone_flags, p))) + retval = copy_fs(clone_flags, p); + if (retval) goto bad_fork_cleanup_files; - if ((retval = copy_sighand(clone_flags, p))) + retval = copy_sighand(clone_flags, p); + if (retval) goto bad_fork_cleanup_fs; - if ((retval = copy_signal(clone_flags, p))) + retval = copy_signal(clone_flags, p); + if (retval) goto bad_fork_cleanup_sighand; - if ((retval = copy_mm(clone_flags, p))) + retval = copy_mm(clone_flags, p); + if (retval) goto bad_fork_cleanup_signal; - if ((retval = copy_namespaces(clone_flags, p))) + retval = copy_namespaces(clone_flags, p); + if (retval) goto bad_fork_cleanup_mm; - if ((retval = copy_io(clone_flags, p))) + retval = copy_io(clone_flags, p); + if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(clone_flags, stack_start, stack_size, p, regs); if (retval) @@ -1194,17 +1263,11 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (clone_flags & CLONE_THREAD) p->tgid = current->tgid; - if (current->nsproxy != p->nsproxy) { - retval = ns_cgroup_clone(p, pid); - if (retval) - goto bad_fork_free_pid; - } - p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; /* * Clear TID on mm_release()? */ - p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL; + p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL; #ifdef CONFIG_BLOCK p->plug = NULL; #endif @@ -1272,7 +1335,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, * it's process group. * A fatal signal pending means that current will exit, so the new * thread can't slip out of an OOM kill (or normal SIGKILL). - */ + */ recalc_sigpending(); if (signal_pending(current)) { spin_unlock(¤t->sighand->siglock); @@ -1290,7 +1353,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, } if (likely(p->pid)) { - tracehook_finish_clone(p, clone_flags, trace); + ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); if (thread_group_leader(p)) { if (is_child_reaper(pid)) @@ -1313,6 +1376,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, write_unlock_irq(&tasklist_lock); proc_fork_connector(p); cgroup_post_fork(p); + if (clone_flags & CLONE_THREAD) + threadgroup_fork_read_unlock(current); perf_event_fork(p); return p; @@ -1351,6 +1416,8 @@ bad_fork_cleanup_policy: mpol_put(p->mempolicy); bad_fork_cleanup_cgroup: #endif + if (clone_flags & CLONE_THREAD) + threadgroup_fork_read_unlock(current); cgroup_exit(p, cgroup_callbacks_done); delayacct_tsk_free(p); module_put(task_thread_info(p)->exec_domain->module); @@ -1427,10 +1494,22 @@ long do_fork(unsigned long clone_flags, } /* - * When called from kernel_thread, don't do user tracing stuff. + * Determine whether and which event to report to ptracer. When + * called from kernel_thread or CLONE_UNTRACED is explicitly + * requested, no event is reported; otherwise, report if the event + * for the type of forking is enabled. */ - if (likely(user_mode(regs))) - trace = tracehook_prepare_clone(clone_flags); + if (likely(user_mode(regs)) && !(clone_flags & CLONE_UNTRACED)) { + if (clone_flags & CLONE_VFORK) + trace = PTRACE_EVENT_VFORK; + else if ((clone_flags & CSIGNAL) != SIGCHLD) + trace = PTRACE_EVENT_CLONE; + else + trace = PTRACE_EVENT_FORK; + + if (likely(!ptrace_event_enabled(current, trace))) + trace = 0; + } p = copy_process(clone_flags, stack_start, regs, stack_size, child_tidptr, NULL, trace); @@ -1454,26 +1533,26 @@ long do_fork(unsigned long clone_flags, } audit_finish_fork(p); - tracehook_report_clone(regs, clone_flags, nr, p); /* * We set PF_STARTING at creation in case tracing wants to * use this to distinguish a fully live task from one that - * hasn't gotten to tracehook_report_clone() yet. Now we - * clear it and set the child going. + * hasn't finished SIGSTOP raising yet. Now we clear it + * and set the child going. */ p->flags &= ~PF_STARTING; - wake_up_new_task(p, clone_flags); + wake_up_new_task(p); - tracehook_report_clone_complete(trace, regs, - clone_flags, nr, p); + /* forking complete and child started to run, tell ptracer */ + if (unlikely(trace)) + ptrace_event(trace, nr); if (clone_flags & CLONE_VFORK) { freezer_do_not_count(); wait_for_completion(&vfork); freezer_count(); - tracehook_report_vfork_done(p, nr); + ptrace_event(PTRACE_EVENT_VFORK_DONE, nr); } } else { nr = PTR_ERR(p); @@ -1508,11 +1587,19 @@ void __init proc_caches_init(void) fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + /* + * FIXME! The "sizeof(struct mm_struct)" currently includes the + * whole struct cpumask for the OFFSTACK case. We could change + * this to *only* allocate as much of it as required by the + * maximum number of CPU's we can ever have. The cpumask_allocation + * is at the end of the structure, exactly for that reason. + */ mm_cachep = kmem_cache_create("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC); mmap_init(); + nsproxy_cache_init(); } /* @@ -1609,12 +1696,14 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; - if ((err = unshare_fs(unshare_flags, &new_fs))) + err = unshare_fs(unshare_flags, &new_fs); + if (err) goto bad_unshare_out; - if ((err = unshare_fd(unshare_flags, &new_fd))) + err = unshare_fd(unshare_flags, &new_fd); + if (err) goto bad_unshare_cleanup_fs; - if ((err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, - new_fs))) + err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_fs); + if (err) goto bad_unshare_cleanup_fd; if (new_fs || new_fd || do_sysvsem || new_nsproxy) { diff --git a/kernel/freezer.c b/kernel/freezer.c index 66ecd2ead21..7b01de98bb6 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -17,7 +17,7 @@ static inline void frozen_process(void) { if (!unlikely(current->flags & PF_NOFREEZE)) { current->flags |= PF_FROZEN; - wmb(); + smp_wmb(); } clear_freeze_flag(current); } @@ -93,7 +93,7 @@ bool freeze_task(struct task_struct *p, bool sig_only) * the task as frozen and next clears its TIF_FREEZE. */ if (!freezing(p)) { - rmb(); + smp_rmb(); if (frozen(p)) return false; diff --git a/kernel/futex.c b/kernel/futex.c index fe28dc282ea..0a308970c24 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -355,8 +355,8 @@ static int fault_in_user_writeable(u32 __user *uaddr) int ret; down_read(&mm->mmap_sem); - ret = get_user_pages(current, mm, (unsigned long)uaddr, - 1, 1, 0, NULL, NULL); + ret = fixup_user_fault(current, mm, (unsigned long)uaddr, + FAULT_FLAG_WRITE); up_read(&mm->mmap_sem); return ret < 0 ? ret : 0; @@ -2697,7 +2697,7 @@ static int __init futex_init(void) futex_cmpxchg_enabled = 1; for (i = 0; i < ARRAY_SIZE(futex_queues); i++) { - plist_head_init(&futex_queues[i].chain, &futex_queues[i].lock); + plist_head_init(&futex_queues[i].chain); spin_lock_init(&futex_queues[i].lock); } diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index b8cadf70b1f..a92028196cc 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -2,7 +2,8 @@ menu "GCOV-based kernel profiling" config GCOV_KERNEL bool "Enable gcov-based kernel profiling" - depends on DEBUG_FS && CONSTRUCTORS + depends on DEBUG_FS + select CONSTRUCTORS if !UML default n ---help--- This option enables gcov-based code profiling (e.g. for code coverage diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 9017478c5d4..a9205e32a05 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -64,24 +64,31 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = .clock_base = { { - .index = CLOCK_REALTIME, - .get_time = &ktime_get_real, + .index = HRTIMER_BASE_MONOTONIC, + .clockid = CLOCK_MONOTONIC, + .get_time = &ktime_get, .resolution = KTIME_LOW_RES, }, { - .index = CLOCK_MONOTONIC, - .get_time = &ktime_get, + .index = HRTIMER_BASE_REALTIME, + .clockid = CLOCK_REALTIME, + .get_time = &ktime_get_real, .resolution = KTIME_LOW_RES, }, { - .index = CLOCK_BOOTTIME, + .index = HRTIMER_BASE_BOOTTIME, + .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, .resolution = KTIME_LOW_RES, }, } }; -static int hrtimer_clock_to_base_table[MAX_CLOCKS]; +static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { + [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, + [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, + [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, +}; static inline int hrtimer_clockid_to_base(clockid_t clock_id) { @@ -192,7 +199,7 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, struct hrtimer_cpu_base *new_cpu_base; int this_cpu = smp_processor_id(); int cpu = hrtimer_get_target(this_cpu, pinned); - int basenum = hrtimer_clockid_to_base(base->index); + int basenum = base->index; again: new_cpu_base = &per_cpu(hrtimer_bases, cpu); @@ -617,66 +624,6 @@ static int hrtimer_reprogram(struct hrtimer *timer, return res; } - -/* - * Retrigger next event is called after clock was set - * - * Called with interrupts disabled via on_each_cpu() - */ -static void retrigger_next_event(void *arg) -{ - struct hrtimer_cpu_base *base; - struct timespec realtime_offset, wtm, sleep; - - if (!hrtimer_hres_active()) - return; - - get_xtime_and_monotonic_and_sleep_offset(&realtime_offset, &wtm, - &sleep); - set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec); - - base = &__get_cpu_var(hrtimer_bases); - - /* Adjust CLOCK_REALTIME offset */ - raw_spin_lock(&base->lock); - base->clock_base[HRTIMER_BASE_REALTIME].offset = - timespec_to_ktime(realtime_offset); - base->clock_base[HRTIMER_BASE_BOOTTIME].offset = - timespec_to_ktime(sleep); - - hrtimer_force_reprogram(base, 0); - raw_spin_unlock(&base->lock); -} - -/* - * Clock realtime was set - * - * Change the offset of the realtime clock vs. the monotonic - * clock. - * - * We might have to reprogram the high resolution timer interrupt. On - * SMP we call the architecture specific code to retrigger _all_ high - * resolution timer interrupts. On UP we just disable interrupts and - * call the high resolution interrupt code. - */ -void clock_was_set(void) -{ - /* Retrigger the CPU local events everywhere */ - on_each_cpu(retrigger_next_event, NULL, 1); -} - -/* - * During resume we might have to reprogram the high resolution timer - * interrupt (on the local CPU): - */ -void hres_timers_resume(void) -{ - WARN_ONCE(!irqs_disabled(), - KERN_INFO "hres_timers_resume() called with IRQs enabled!"); - - retrigger_next_event(NULL); -} - /* * Initialize the high resolution related parts of cpu_base */ @@ -711,11 +658,39 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, } /* + * Retrigger next event is called after clock was set + * + * Called with interrupts disabled via on_each_cpu() + */ +static void retrigger_next_event(void *arg) +{ + struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases); + struct timespec realtime_offset, xtim, wtm, sleep; + + if (!hrtimer_hres_active()) + return; + + /* Optimized out for !HIGH_RES */ + get_xtime_and_monotonic_and_sleep_offset(&xtim, &wtm, &sleep); + set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec); + + /* Adjust CLOCK_REALTIME offset */ + raw_spin_lock(&base->lock); + base->clock_base[HRTIMER_BASE_REALTIME].offset = + timespec_to_ktime(realtime_offset); + base->clock_base[HRTIMER_BASE_BOOTTIME].offset = + timespec_to_ktime(sleep); + + hrtimer_force_reprogram(base, 0); + raw_spin_unlock(&base->lock); +} + +/* * Switch to high resolution mode */ static int hrtimer_switch_to_hres(void) { - int cpu = smp_processor_id(); + int i, cpu = smp_processor_id(); struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu); unsigned long flags; @@ -731,9 +706,8 @@ static int hrtimer_switch_to_hres(void) return 0; } base->hres_active = 1; - base->clock_base[HRTIMER_BASE_REALTIME].resolution = KTIME_HIGH_RES; - base->clock_base[HRTIMER_BASE_MONOTONIC].resolution = KTIME_HIGH_RES; - base->clock_base[HRTIMER_BASE_BOOTTIME].resolution = KTIME_HIGH_RES; + for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) + base->clock_base[i].resolution = KTIME_HIGH_RES; tick_setup_sched_timer(); @@ -757,9 +731,43 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, return 0; } static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { } +static inline void retrigger_next_event(void *arg) { } #endif /* CONFIG_HIGH_RES_TIMERS */ +/* + * Clock realtime was set + * + * Change the offset of the realtime clock vs. the monotonic + * clock. + * + * We might have to reprogram the high resolution timer interrupt. On + * SMP we call the architecture specific code to retrigger _all_ high + * resolution timer interrupts. On UP we just disable interrupts and + * call the high resolution interrupt code. + */ +void clock_was_set(void) +{ +#ifdef CONFIG_HIGH_RES_TIMERS + /* Retrigger the CPU local events everywhere */ + on_each_cpu(retrigger_next_event, NULL, 1); +#endif + timerfd_clock_was_set(); +} + +/* + * During resume we might have to reprogram the high resolution timer + * interrupt (on the local CPU): + */ +void hrtimers_resume(void) +{ + WARN_ONCE(!irqs_disabled(), + KERN_INFO "hrtimers_resume() called with IRQs enabled!"); + + retrigger_next_event(NULL); + timerfd_clock_was_set(); +} + static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer) { #ifdef CONFIG_TIMER_STATS @@ -852,6 +860,7 @@ static int enqueue_hrtimer(struct hrtimer *timer, debug_activate(timer); timerqueue_add(&base->active, &timer->node); + base->cpu_base->active_bases |= 1 << base->index; /* * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the @@ -893,6 +902,8 @@ static void __remove_hrtimer(struct hrtimer *timer, #endif } timerqueue_del(&base->active, &timer->node); + if (!timerqueue_getnext(&base->active)) + base->cpu_base->active_bases &= ~(1 << base->index); out: timer->state = newstate; } @@ -1230,7 +1241,6 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now) void hrtimer_interrupt(struct clock_event_device *dev) { struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); - struct hrtimer_clock_base *base; ktime_t expires_next, now, entry_time, delta; int i, retries = 0; @@ -1252,12 +1262,15 @@ retry: */ cpu_base->expires_next.tv64 = KTIME_MAX; - base = cpu_base->clock_base; - for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { - ktime_t basenow; + struct hrtimer_clock_base *base; struct timerqueue_node *node; + ktime_t basenow; + if (!(cpu_base->active_bases & (1 << i))) + continue; + + base = cpu_base->clock_base + i; basenow = ktime_add(now, base->offset); while ((node = timerqueue_getnext(&base->active))) { @@ -1290,7 +1303,6 @@ retry: __run_hrtimer(timer, &basenow); } - base++; } /* @@ -1521,7 +1533,7 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart) struct timespec __user *rmtp; int ret = 0; - hrtimer_init_on_stack(&t.timer, restart->nanosleep.index, + hrtimer_init_on_stack(&t.timer, restart->nanosleep.clockid, HRTIMER_MODE_ABS); hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); @@ -1573,7 +1585,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, restart = ¤t_thread_info()->restart_block; restart->fn = hrtimer_nanosleep_restart; - restart->nanosleep.index = t.timer.base->index; + restart->nanosleep.clockid = t.timer.base->clockid; restart->nanosleep.rmtp = rmtp; restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); @@ -1722,10 +1734,6 @@ static struct notifier_block __cpuinitdata hrtimers_nb = { void __init hrtimers_init(void) { - hrtimer_clock_to_base_table[CLOCK_REALTIME] = HRTIMER_BASE_REALTIME; - hrtimer_clock_to_base_table[CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC; - hrtimer_clock_to_base_table[CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME; - hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, (void *)(long)smp_processor_id()); register_cpu_notifier(&hrtimers_nb); diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 53ead174da2..ea640120ab8 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -33,7 +33,7 @@ unsigned long __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT; /* * Zero means infinite timeout - no checking done: */ -unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120; +unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT; unsigned long __read_mostly sysctl_hung_task_warnings = 10; diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index c574f9a12c4..5a38bf4de64 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -48,6 +48,14 @@ config IRQ_PREFLOW_FASTEOI config IRQ_EDGE_EOI_HANDLER bool +# Generic configurable interrupt chip implementation +config GENERIC_IRQ_CHIP + bool + +# Generic irq_domain hw <--> linux irq number translation +config IRQ_DOMAIN + bool + # Support forced irq threading config IRQ_FORCED_THREADING bool diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 54329cd7b3e..fff17381f0a 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -1,6 +1,8 @@ obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o +obj-$(CONFIG_GENERIC_IRQ_CHIP) += generic-chip.o obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o +obj-$(CONFIG_IRQ_DOMAIN) += irqdomain.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o obj-$(CONFIG_PM_SLEEP) += pm.o diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 4af1e2b244c..d5a3009da71 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -310,6 +310,7 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc) out_unlock: raw_spin_unlock(&desc->lock); } +EXPORT_SYMBOL_GPL(handle_simple_irq); /** * handle_level_irq - Level type irq handler @@ -573,6 +574,7 @@ __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, if (handle != handle_bad_irq && is_chained) { irq_settings_set_noprobe(desc); irq_settings_set_norequest(desc); + irq_settings_set_nothread(desc); irq_startup(desc); } out: @@ -612,6 +614,7 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) irq_put_desc_unlock(desc, flags); } +EXPORT_SYMBOL_GPL(irq_modify_status); /** * irq_cpu_online - Invoke all irq_cpu_online functions. diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h index 306cba37e9a..97a8bfadc88 100644 --- a/kernel/irq/debug.h +++ b/kernel/irq/debug.h @@ -27,6 +27,7 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc) P(IRQ_PER_CPU); P(IRQ_NOPROBE); P(IRQ_NOREQUEST); + P(IRQ_NOTHREAD); P(IRQ_NOAUTOEN); PS(IRQS_AUTODETECT); diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index 1ef4ffcdfa5..bd8e788d71e 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -87,8 +87,8 @@ void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id) { struct irq_devres match_data = { irq, dev_id }; - free_irq(irq, dev_id); WARN_ON(devres_destroy(dev, devm_irq_release, devm_irq_match, &match_data)); + free_irq(irq, dev_id); } EXPORT_SYMBOL(devm_free_irq); diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c new file mode 100644 index 00000000000..3a2cab407b9 --- /dev/null +++ b/kernel/irq/generic-chip.c @@ -0,0 +1,368 @@ +/* + * Library implementing the most common irq chip callback functions + * + * Copyright (C) 2011, Thomas Gleixner + */ +#include <linux/io.h> +#include <linux/irq.h> +#include <linux/slab.h> +#include <linux/interrupt.h> +#include <linux/kernel_stat.h> +#include <linux/syscore_ops.h> + +#include "internals.h" + +static LIST_HEAD(gc_list); +static DEFINE_RAW_SPINLOCK(gc_lock); + +static inline struct irq_chip_regs *cur_regs(struct irq_data *d) +{ + return &container_of(d->chip, struct irq_chip_type, chip)->regs; +} + +/** + * irq_gc_noop - NOOP function + * @d: irq_data + */ +void irq_gc_noop(struct irq_data *d) +{ +} + +/** + * irq_gc_mask_disable_reg - Mask chip via disable register + * @d: irq_data + * + * Chip has separate enable/disable registers instead of a single mask + * register. + */ +void irq_gc_mask_disable_reg(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->disable); + gc->mask_cache &= ~mask; + irq_gc_unlock(gc); +} + +/** + * irq_gc_mask_set_mask_bit - Mask chip via setting bit in mask register + * @d: irq_data + * + * Chip has a single mask register. Values of this register are cached + * and protected by gc->lock + */ +void irq_gc_mask_set_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + gc->mask_cache |= mask; + irq_reg_writel(gc->mask_cache, gc->reg_base + cur_regs(d)->mask); + irq_gc_unlock(gc); +} + +/** + * irq_gc_mask_set_mask_bit - Mask chip via clearing bit in mask register + * @d: irq_data + * + * Chip has a single mask register. Values of this register are cached + * and protected by gc->lock + */ +void irq_gc_mask_clr_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + gc->mask_cache &= ~mask; + irq_reg_writel(gc->mask_cache, gc->reg_base + cur_regs(d)->mask); + irq_gc_unlock(gc); +} + +/** + * irq_gc_unmask_enable_reg - Unmask chip via enable register + * @d: irq_data + * + * Chip has separate enable/disable registers instead of a single mask + * register. + */ +void irq_gc_unmask_enable_reg(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->enable); + gc->mask_cache |= mask; + irq_gc_unlock(gc); +} + +/** + * irq_gc_ack_set_bit - Ack pending interrupt via setting bit + * @d: irq_data + */ +void irq_gc_ack_set_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->ack); + irq_gc_unlock(gc); +} + +/** + * irq_gc_ack_clr_bit - Ack pending interrupt via clearing bit + * @d: irq_data + */ +void irq_gc_ack_clr_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = ~(1 << (d->irq - gc->irq_base)); + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->ack); + irq_gc_unlock(gc); +} + +/** + * irq_gc_mask_disable_reg_and_ack- Mask and ack pending interrupt + * @d: irq_data + */ +void irq_gc_mask_disable_reg_and_ack(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->mask); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->ack); + irq_gc_unlock(gc); +} + +/** + * irq_gc_eoi - EOI interrupt + * @d: irq_data + */ +void irq_gc_eoi(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->eoi); + irq_gc_unlock(gc); +} + +/** + * irq_gc_set_wake - Set/clr wake bit for an interrupt + * @d: irq_data + * + * For chips where the wake from suspend functionality is not + * configured in a separate register and the wakeup active state is + * just stored in a bitmask. + */ +int irq_gc_set_wake(struct irq_data *d, unsigned int on) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = 1 << (d->irq - gc->irq_base); + + if (!(mask & gc->wake_enabled)) + return -EINVAL; + + irq_gc_lock(gc); + if (on) + gc->wake_active |= mask; + else + gc->wake_active &= ~mask; + irq_gc_unlock(gc); + return 0; +} + +/** + * irq_alloc_generic_chip - Allocate a generic chip and initialize it + * @name: Name of the irq chip + * @num_ct: Number of irq_chip_type instances associated with this + * @irq_base: Interrupt base nr for this chip + * @reg_base: Register base address (virtual) + * @handler: Default flow handler associated with this chip + * + * Returns an initialized irq_chip_generic structure. The chip defaults + * to the primary (index 0) irq_chip_type and @handler + */ +struct irq_chip_generic * +irq_alloc_generic_chip(const char *name, int num_ct, unsigned int irq_base, + void __iomem *reg_base, irq_flow_handler_t handler) +{ + struct irq_chip_generic *gc; + unsigned long sz = sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); + + gc = kzalloc(sz, GFP_KERNEL); + if (gc) { + raw_spin_lock_init(&gc->lock); + gc->num_ct = num_ct; + gc->irq_base = irq_base; + gc->reg_base = reg_base; + gc->chip_types->chip.name = name; + gc->chip_types->handler = handler; + } + return gc; +} + +/* + * Separate lockdep class for interrupt chip which can nest irq_desc + * lock. + */ +static struct lock_class_key irq_nested_lock_class; + +/** + * irq_setup_generic_chip - Setup a range of interrupts with a generic chip + * @gc: Generic irq chip holding all data + * @msk: Bitmask holding the irqs to initialize relative to gc->irq_base + * @flags: Flags for initialization + * @clr: IRQ_* bits to clear + * @set: IRQ_* bits to set + * + * Set up max. 32 interrupts starting from gc->irq_base. Note, this + * initializes all interrupts to the primary irq_chip_type and its + * associated handler. + */ +void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk, + enum irq_gc_flags flags, unsigned int clr, + unsigned int set) +{ + struct irq_chip_type *ct = gc->chip_types; + unsigned int i; + + raw_spin_lock(&gc_lock); + list_add_tail(&gc->list, &gc_list); + raw_spin_unlock(&gc_lock); + + /* Init mask cache ? */ + if (flags & IRQ_GC_INIT_MASK_CACHE) + gc->mask_cache = irq_reg_readl(gc->reg_base + ct->regs.mask); + + for (i = gc->irq_base; msk; msk >>= 1, i++) { + if (!msk & 0x01) + continue; + + if (flags & IRQ_GC_INIT_NESTED_LOCK) + irq_set_lockdep_class(i, &irq_nested_lock_class); + + irq_set_chip_and_handler(i, &ct->chip, ct->handler); + irq_set_chip_data(i, gc); + irq_modify_status(i, clr, set); + } + gc->irq_cnt = i - gc->irq_base; +} + +/** + * irq_setup_alt_chip - Switch to alternative chip + * @d: irq_data for this interrupt + * @type Flow type to be initialized + * + * Only to be called from chip->irq_set_type() callbacks. + */ +int irq_setup_alt_chip(struct irq_data *d, unsigned int type) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = gc->chip_types; + unsigned int i; + + for (i = 0; i < gc->num_ct; i++, ct++) { + if (ct->type & type) { + d->chip = &ct->chip; + irq_data_to_desc(d)->handle_irq = ct->handler; + return 0; + } + } + return -EINVAL; +} + +/** + * irq_remove_generic_chip - Remove a chip + * @gc: Generic irq chip holding all data + * @msk: Bitmask holding the irqs to initialize relative to gc->irq_base + * @clr: IRQ_* bits to clear + * @set: IRQ_* bits to set + * + * Remove up to 32 interrupts starting from gc->irq_base. + */ +void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk, + unsigned int clr, unsigned int set) +{ + unsigned int i = gc->irq_base; + + raw_spin_lock(&gc_lock); + list_del(&gc->list); + raw_spin_unlock(&gc_lock); + + for (; msk; msk >>= 1, i++) { + if (!msk & 0x01) + continue; + + /* Remove handler first. That will mask the irq line */ + irq_set_handler(i, NULL); + irq_set_chip(i, &no_irq_chip); + irq_set_chip_data(i, NULL); + irq_modify_status(i, clr, set); + } +} + +#ifdef CONFIG_PM +static int irq_gc_suspend(void) +{ + struct irq_chip_generic *gc; + + list_for_each_entry(gc, &gc_list, list) { + struct irq_chip_type *ct = gc->chip_types; + + if (ct->chip.irq_suspend) + ct->chip.irq_suspend(irq_get_irq_data(gc->irq_base)); + } + return 0; +} + +static void irq_gc_resume(void) +{ + struct irq_chip_generic *gc; + + list_for_each_entry(gc, &gc_list, list) { + struct irq_chip_type *ct = gc->chip_types; + + if (ct->chip.irq_resume) + ct->chip.irq_resume(irq_get_irq_data(gc->irq_base)); + } +} +#else +#define irq_gc_suspend NULL +#define irq_gc_resume NULL +#endif + +static void irq_gc_shutdown(void) +{ + struct irq_chip_generic *gc; + + list_for_each_entry(gc, &gc_list, list) { + struct irq_chip_type *ct = gc->chip_types; + + if (ct->chip.irq_pm_shutdown) + ct->chip.irq_pm_shutdown(irq_get_irq_data(gc->irq_base)); + } +} + +static struct syscore_ops irq_gc_syscore_ops = { + .suspend = irq_gc_suspend, + .resume = irq_gc_resume, + .shutdown = irq_gc_shutdown, +}; + +static int __init irq_gc_init_ops(void) +{ + register_syscore_ops(&irq_gc_syscore_ops); + return 0; +} +device_initcall(irq_gc_init_ops); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 90cb55f6d7e..470d08c82bb 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -133,12 +133,6 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) switch (res) { case IRQ_WAKE_THREAD: /* - * Set result to handled so the spurious check - * does not trigger. - */ - res = IRQ_HANDLED; - - /* * Catch drivers which return WAKE_THREAD but * did not set up a thread function */ diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 2c039c9b938..4c60a50e66b 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -22,7 +22,7 @@ */ static struct lock_class_key irq_desc_lock_class; -#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS) +#if defined(CONFIG_SMP) static void __init init_irq_default_affinity(void) { alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); @@ -257,13 +257,11 @@ int __init early_irq_init(void) count = ARRAY_SIZE(irq_desc); for (i = 0; i < count; i++) { - desc[i].irq_data.irq = i; - desc[i].irq_data.chip = &no_irq_chip; desc[i].kstat_irqs = alloc_percpu(unsigned int); - irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS); - alloc_masks(desc + i, GFP_KERNEL, node); - desc_smp_init(desc + i, node); + alloc_masks(&desc[i], GFP_KERNEL, node); + raw_spin_lock_init(&desc[i].lock); lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); + desc_set_defaults(i, &desc[i], node); } return arch_early_irq_init(); } @@ -290,6 +288,22 @@ static int irq_expand_nr_irqs(unsigned int nr) #endif /* !CONFIG_SPARSE_IRQ */ +/** + * generic_handle_irq - Invoke the handler for a particular irq + * @irq: The irq number to handle + * + */ +int generic_handle_irq(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc) + return -EINVAL; + generic_handle_irq_desc(irq, desc); + return 0; +} +EXPORT_SYMBOL_GPL(generic_handle_irq); + /* Dynamic interrupt handling */ /** @@ -311,6 +325,7 @@ void irq_free_descs(unsigned int from, unsigned int cnt) bitmap_clear(allocated_irqs, from, cnt); mutex_unlock(&sparse_irq_lock); } +EXPORT_SYMBOL_GPL(irq_free_descs); /** * irq_alloc_descs - allocate and initialize a range of irq descriptors @@ -329,6 +344,12 @@ irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node) if (!cnt) return -EINVAL; + if (irq >= 0) { + if (from > irq) + return -EINVAL; + from = irq; + } + mutex_lock(&sparse_irq_lock); start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS, @@ -351,6 +372,7 @@ err: mutex_unlock(&sparse_irq_lock); return ret; } +EXPORT_SYMBOL_GPL(irq_alloc_descs); /** * irq_reserve_irqs - mark irqs allocated @@ -430,7 +452,6 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) *per_cpu_ptr(desc->kstat_irqs, cpu) : 0; } -#ifdef CONFIG_GENERIC_HARDIRQS unsigned int kstat_irqs(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); @@ -443,4 +464,3 @@ unsigned int kstat_irqs(unsigned int irq) sum += *per_cpu_ptr(desc->kstat_irqs, cpu); return sum; } -#endif /* CONFIG_GENERIC_HARDIRQS */ diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c new file mode 100644 index 00000000000..d5828da3fd3 --- /dev/null +++ b/kernel/irq/irqdomain.c @@ -0,0 +1,180 @@ +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/slab.h> + +static LIST_HEAD(irq_domain_list); +static DEFINE_MUTEX(irq_domain_mutex); + +/** + * irq_domain_add() - Register an irq_domain + * @domain: ptr to initialized irq_domain structure + * + * Registers an irq_domain structure. The irq_domain must at a minimum be + * initialized with an ops structure pointer, and either a ->to_irq hook or + * a valid irq_base value. Everything else is optional. + */ +void irq_domain_add(struct irq_domain *domain) +{ + struct irq_data *d; + int hwirq; + + /* + * This assumes that the irq_domain owner has already allocated + * the irq_descs. This block will be removed when support for dynamic + * allocation of irq_descs is added to irq_domain. + */ + for (hwirq = 0; hwirq < domain->nr_irq; hwirq++) { + d = irq_get_irq_data(irq_domain_to_irq(domain, hwirq)); + if (d || d->domain) { + /* things are broken; just report, don't clean up */ + WARN(1, "error: irq_desc already assigned to a domain"); + return; + } + d->domain = domain; + d->hwirq = hwirq; + } + + mutex_lock(&irq_domain_mutex); + list_add(&domain->list, &irq_domain_list); + mutex_unlock(&irq_domain_mutex); +} + +/** + * irq_domain_del() - Unregister an irq_domain + * @domain: ptr to registered irq_domain. + */ +void irq_domain_del(struct irq_domain *domain) +{ + struct irq_data *d; + int hwirq; + + mutex_lock(&irq_domain_mutex); + list_del(&domain->list); + mutex_unlock(&irq_domain_mutex); + + /* Clear the irq_domain assignments */ + for (hwirq = 0; hwirq < domain->nr_irq; hwirq++) { + d = irq_get_irq_data(irq_domain_to_irq(domain, hwirq)); + d->domain = NULL; + } +} + +#if defined(CONFIG_OF_IRQ) +/** + * irq_create_of_mapping() - Map a linux irq number from a DT interrupt spec + * + * Used by the device tree interrupt mapping code to translate a device tree + * interrupt specifier to a valid linux irq number. Returns either a valid + * linux IRQ number or 0. + * + * When the caller no longer need the irq number returned by this function it + * should arrange to call irq_dispose_mapping(). + */ +unsigned int irq_create_of_mapping(struct device_node *controller, + const u32 *intspec, unsigned int intsize) +{ + struct irq_domain *domain; + unsigned long hwirq; + unsigned int irq, type; + int rc = -EINVAL; + + /* Find a domain which can translate the irq spec */ + mutex_lock(&irq_domain_mutex); + list_for_each_entry(domain, &irq_domain_list, list) { + if (!domain->ops->dt_translate) + continue; + rc = domain->ops->dt_translate(domain, controller, + intspec, intsize, &hwirq, &type); + if (rc == 0) + break; + } + mutex_unlock(&irq_domain_mutex); + + if (rc != 0) + return 0; + + irq = irq_domain_to_irq(domain, hwirq); + if (type != IRQ_TYPE_NONE) + irq_set_irq_type(irq, type); + pr_debug("%s: mapped hwirq=%i to irq=%i, flags=%x\n", + controller->full_name, (int)hwirq, irq, type); + return irq; +} +EXPORT_SYMBOL_GPL(irq_create_of_mapping); + +/** + * irq_dispose_mapping() - Discard a mapping created by irq_create_of_mapping() + * @irq: linux irq number to be discarded + * + * Calling this function indicates the caller no longer needs a reference to + * the linux irq number returned by a prior call to irq_create_of_mapping(). + */ +void irq_dispose_mapping(unsigned int irq) +{ + /* + * nothing yet; will be filled when support for dynamic allocation of + * irq_descs is added to irq_domain + */ +} +EXPORT_SYMBOL_GPL(irq_dispose_mapping); + +int irq_domain_simple_dt_translate(struct irq_domain *d, + struct device_node *controller, + const u32 *intspec, unsigned int intsize, + unsigned long *out_hwirq, unsigned int *out_type) +{ + if (d->of_node != controller) + return -EINVAL; + if (intsize < 1) + return -EINVAL; + + *out_hwirq = intspec[0]; + *out_type = IRQ_TYPE_NONE; + if (intsize > 1) + *out_type = intspec[1] & IRQ_TYPE_SENSE_MASK; + return 0; +} + +struct irq_domain_ops irq_domain_simple_ops = { + .dt_translate = irq_domain_simple_dt_translate, +}; +EXPORT_SYMBOL_GPL(irq_domain_simple_ops); + +/** + * irq_domain_create_simple() - Set up a 'simple' translation range + */ +void irq_domain_add_simple(struct device_node *controller, int irq_base) +{ + struct irq_domain *domain; + + domain = kzalloc(sizeof(*domain), GFP_KERNEL); + if (!domain) { + WARN_ON(1); + return; + } + + domain->irq_base = irq_base; + domain->of_node = of_node_get(controller); + domain->ops = &irq_domain_simple_ops; + irq_domain_add(domain); +} +EXPORT_SYMBOL_GPL(irq_domain_add_simple); + +void irq_domain_generate_simple(const struct of_device_id *match, + u64 phys_base, unsigned int irq_start) +{ + struct device_node *node; + pr_info("looking for phys_base=%llx, irq_start=%i\n", + (unsigned long long) phys_base, (int) irq_start); + node = of_find_matching_node_by_address(NULL, match, phys_base); + if (node) + irq_domain_add_simple(node, irq_start); + else + pr_info("no node found\n"); +} +EXPORT_SYMBOL_GPL(irq_domain_generate_simple); +#endif /* CONFIG_OF_IRQ */ diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 07c1611f389..0a7840aeb0f 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -491,6 +491,9 @@ int irq_set_irq_wake(unsigned int irq, unsigned int on) struct irq_desc *desc = irq_get_desc_buslock(irq, &flags); int ret = 0; + if (!desc) + return -EINVAL; + /* wakeup-capable irqs can be shared between drivers that * don't need to have the same sleep mode behaviors. */ @@ -723,13 +726,16 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { } * context. So we need to disable bh here to avoid deadlocks and other * side effects. */ -static void +static irqreturn_t irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) { + irqreturn_t ret; + local_bh_disable(); - action->thread_fn(action->irq, action->dev_id); + ret = action->thread_fn(action->irq, action->dev_id); irq_finalize_oneshot(desc, action, false); local_bh_enable(); + return ret; } /* @@ -737,10 +743,14 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) * preemtible - many of them need to sleep and wait for slow busses to * complete. */ -static void irq_thread_fn(struct irq_desc *desc, struct irqaction *action) +static irqreturn_t irq_thread_fn(struct irq_desc *desc, + struct irqaction *action) { - action->thread_fn(action->irq, action->dev_id); + irqreturn_t ret; + + ret = action->thread_fn(action->irq, action->dev_id); irq_finalize_oneshot(desc, action, false); + return ret; } /* @@ -753,7 +763,8 @@ static int irq_thread(void *data) }; struct irqaction *action = data; struct irq_desc *desc = irq_to_desc(action->irq); - void (*handler_fn)(struct irq_desc *desc, struct irqaction *action); + irqreturn_t (*handler_fn)(struct irq_desc *desc, + struct irqaction *action); int wake; if (force_irqthreads & test_bit(IRQTF_FORCED_THREAD, @@ -783,8 +794,12 @@ static int irq_thread(void *data) desc->istate |= IRQS_PENDING; raw_spin_unlock_irq(&desc->lock); } else { + irqreturn_t action_ret; + raw_spin_unlock_irq(&desc->lock); - handler_fn(desc, action); + action_ret = handler_fn(desc, action); + if (!noirqdebug) + note_interrupt(action->irq, desc, action_ret); } wake = atomic_dec_and_test(&desc->threads_active); @@ -900,7 +915,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ new->handler = irq_nested_primary_handler; } else { - irq_setup_forced_threading(new); + if (irq_settings_can_thread(desc)) + irq_setup_forced_threading(new); } /* diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index dd201bd3510..4bd4faa6323 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -19,7 +19,7 @@ static struct proc_dir_entry *root_irq_dir; #ifdef CONFIG_SMP -static int irq_affinity_proc_show(struct seq_file *m, void *v) +static int show_irq_affinity(int type, struct seq_file *m, void *v) { struct irq_desc *desc = irq_to_desc((long)m->private); const struct cpumask *mask = desc->irq_data.affinity; @@ -28,7 +28,10 @@ static int irq_affinity_proc_show(struct seq_file *m, void *v) if (irqd_is_setaffinity_pending(&desc->irq_data)) mask = desc->pending_mask; #endif - seq_cpumask(m, mask); + if (type) + seq_cpumask_list(m, mask); + else + seq_cpumask(m, mask); seq_putc(m, '\n'); return 0; } @@ -59,7 +62,18 @@ static int irq_affinity_hint_proc_show(struct seq_file *m, void *v) #endif int no_irq_affinity; -static ssize_t irq_affinity_proc_write(struct file *file, +static int irq_affinity_proc_show(struct seq_file *m, void *v) +{ + return show_irq_affinity(0, m, v); +} + +static int irq_affinity_list_proc_show(struct seq_file *m, void *v) +{ + return show_irq_affinity(1, m, v); +} + + +static ssize_t write_irq_affinity(int type, struct file *file, const char __user *buffer, size_t count, loff_t *pos) { unsigned int irq = (int)(long)PDE(file->f_path.dentry->d_inode)->data; @@ -72,7 +86,10 @@ static ssize_t irq_affinity_proc_write(struct file *file, if (!alloc_cpumask_var(&new_value, GFP_KERNEL)) return -ENOMEM; - err = cpumask_parse_user(buffer, count, new_value); + if (type) + err = cpumask_parselist_user(buffer, count, new_value); + else + err = cpumask_parse_user(buffer, count, new_value); if (err) goto free_cpumask; @@ -100,11 +117,28 @@ free_cpumask: return err; } +static ssize_t irq_affinity_proc_write(struct file *file, + const char __user *buffer, size_t count, loff_t *pos) +{ + return write_irq_affinity(0, file, buffer, count, pos); +} + +static ssize_t irq_affinity_list_proc_write(struct file *file, + const char __user *buffer, size_t count, loff_t *pos) +{ + return write_irq_affinity(1, file, buffer, count, pos); +} + static int irq_affinity_proc_open(struct inode *inode, struct file *file) { return single_open(file, irq_affinity_proc_show, PDE(inode)->data); } +static int irq_affinity_list_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_affinity_list_proc_show, PDE(inode)->data); +} + static int irq_affinity_hint_proc_open(struct inode *inode, struct file *file) { return single_open(file, irq_affinity_hint_proc_show, PDE(inode)->data); @@ -125,6 +159,14 @@ static const struct file_operations irq_affinity_hint_proc_fops = { .release = single_release, }; +static const struct file_operations irq_affinity_list_proc_fops = { + .open = irq_affinity_list_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = irq_affinity_list_proc_write, +}; + static int default_affinity_show(struct seq_file *m, void *v) { seq_cpumask(m, irq_default_affinity); @@ -289,6 +331,10 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) proc_create_data("affinity_hint", 0400, desc->dir, &irq_affinity_hint_proc_fops, (void *)(long)irq); + /* create /proc/irq/<irq>/smp_affinity_list */ + proc_create_data("smp_affinity_list", 0600, desc->dir, + &irq_affinity_list_proc_fops, (void *)(long)irq); + proc_create_data("node", 0444, desc->dir, &irq_node_proc_fops, (void *)(long)irq); #endif @@ -306,6 +352,7 @@ void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) #ifdef CONFIG_SMP remove_proc_entry("smp_affinity", desc->dir); remove_proc_entry("affinity_hint", desc->dir); + remove_proc_entry("smp_affinity_list", desc->dir); remove_proc_entry("node", desc->dir); #endif remove_proc_entry("spurious", desc->dir); @@ -419,7 +466,7 @@ int show_interrupts(struct seq_file *p, void *v) } else { seq_printf(p, " %8s", "None"); } -#ifdef CONFIG_GENIRC_IRQ_SHOW_LEVEL +#ifdef CONFIG_GENERIC_IRQ_SHOW_LEVEL seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge"); #endif if (desc->name) diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h index 0d91730b633..f1667833d44 100644 --- a/kernel/irq/settings.h +++ b/kernel/irq/settings.h @@ -8,6 +8,7 @@ enum { _IRQ_LEVEL = IRQ_LEVEL, _IRQ_NOPROBE = IRQ_NOPROBE, _IRQ_NOREQUEST = IRQ_NOREQUEST, + _IRQ_NOTHREAD = IRQ_NOTHREAD, _IRQ_NOAUTOEN = IRQ_NOAUTOEN, _IRQ_MOVE_PCNTXT = IRQ_MOVE_PCNTXT, _IRQ_NO_BALANCING = IRQ_NO_BALANCING, @@ -20,6 +21,7 @@ enum { #define IRQ_LEVEL GOT_YOU_MORON #define IRQ_NOPROBE GOT_YOU_MORON #define IRQ_NOREQUEST GOT_YOU_MORON +#define IRQ_NOTHREAD GOT_YOU_MORON #define IRQ_NOAUTOEN GOT_YOU_MORON #define IRQ_NESTED_THREAD GOT_YOU_MORON #undef IRQF_MODIFY_MASK @@ -94,6 +96,21 @@ static inline void irq_settings_set_norequest(struct irq_desc *desc) desc->status_use_accessors |= _IRQ_NOREQUEST; } +static inline bool irq_settings_can_thread(struct irq_desc *desc) +{ + return !(desc->status_use_accessors & _IRQ_NOTHREAD); +} + +static inline void irq_settings_clr_nothread(struct irq_desc *desc) +{ + desc->status_use_accessors &= ~_IRQ_NOTHREAD; +} + +static inline void irq_settings_set_nothread(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NOTHREAD; +} + static inline bool irq_settings_can_probe(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOPROBE); diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index dfbd550401b..aa57d5da18c 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -167,6 +167,13 @@ out: jiffies + POLL_SPURIOUS_IRQ_INTERVAL); } +static inline int bad_action_ret(irqreturn_t action_ret) +{ + if (likely(action_ret <= (IRQ_HANDLED | IRQ_WAKE_THREAD))) + return 0; + return 1; +} + /* * If 99,900 of the previous 100,000 interrupts have not been handled * then assume that the IRQ is stuck in some manner. Drop a diagnostic @@ -182,7 +189,7 @@ __report_bad_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *action; unsigned long flags; - if (action_ret != IRQ_HANDLED && action_ret != IRQ_NONE) { + if (bad_action_ret(action_ret)) { printk(KERN_ERR "irq event %d: bogus return value %x\n", irq, action_ret); } else { @@ -201,10 +208,11 @@ __report_bad_irq(unsigned int irq, struct irq_desc *desc, raw_spin_lock_irqsave(&desc->lock, flags); action = desc->action; while (action) { - printk(KERN_ERR "[<%p>]", action->handler); - print_symbol(" (%s)", - (unsigned long)action->handler); - printk("\n"); + printk(KERN_ERR "[<%p>] %pf", action->handler, action->handler); + if (action->thread_fn) + printk(KERN_CONT " threaded [<%p>] %pf", + action->thread_fn, action->thread_fn); + printk(KERN_CONT "\n"); action = action->next; } raw_spin_unlock_irqrestore(&desc->lock, flags); @@ -262,7 +270,16 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc, if (desc->istate & IRQS_POLL_INPROGRESS) return; - if (unlikely(action_ret != IRQ_HANDLED)) { + /* we get here again via the threaded handler */ + if (action_ret == IRQ_WAKE_THREAD) + return; + + if (bad_action_ret(action_ret)) { + report_bad_irq(irq, desc, action_ret); + return; + } + + if (unlikely(action_ret == IRQ_NONE)) { /* * If we are seeing only the odd spurious IRQ caused by * bus asynchronicity then don't eventually trigger an error, @@ -274,8 +291,6 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc, else desc->irqs_unhandled++; desc->last_unhandled = jiffies; - if (unlikely(action_ret != IRQ_NONE)) - report_bad_irq(irq, desc, action_ret); } if (unlikely(try_misrouted_irq(irq, desc, action_ret))) { diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 3b79bd93833..a8ce45097f3 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -2,43 +2,23 @@ * jump label support * * Copyright (C) 2009 Jason Baron <jbaron@redhat.com> + * Copyright (C) 2011 Peter Zijlstra <pzijlstr@redhat.com> * */ -#include <linux/jump_label.h> #include <linux/memory.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/list.h> -#include <linux/jhash.h> #include <linux/slab.h> #include <linux/sort.h> #include <linux/err.h> +#include <linux/jump_label.h> #ifdef HAVE_JUMP_LABEL -#define JUMP_LABEL_HASH_BITS 6 -#define JUMP_LABEL_TABLE_SIZE (1 << JUMP_LABEL_HASH_BITS) -static struct hlist_head jump_label_table[JUMP_LABEL_TABLE_SIZE]; - /* mutex to protect coming/going of the the jump_label table */ static DEFINE_MUTEX(jump_label_mutex); -struct jump_label_entry { - struct hlist_node hlist; - struct jump_entry *table; - int nr_entries; - /* hang modules off here */ - struct hlist_head modules; - unsigned long key; -}; - -struct jump_label_module_entry { - struct hlist_node hlist; - struct jump_entry *table; - int nr_entries; - struct module *mod; -}; - void jump_label_lock(void) { mutex_lock(&jump_label_mutex); @@ -49,6 +29,11 @@ void jump_label_unlock(void) mutex_unlock(&jump_label_mutex); } +bool jump_label_enabled(struct jump_label_key *key) +{ + return !!atomic_read(&key->enabled); +} + static int jump_label_cmp(const void *a, const void *b) { const struct jump_entry *jea = a; @@ -64,7 +49,7 @@ static int jump_label_cmp(const void *a, const void *b) } static void -sort_jump_label_entries(struct jump_entry *start, struct jump_entry *stop) +jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop) { unsigned long size; @@ -73,118 +58,25 @@ sort_jump_label_entries(struct jump_entry *start, struct jump_entry *stop) sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL); } -static struct jump_label_entry *get_jump_label_entry(jump_label_t key) -{ - struct hlist_head *head; - struct hlist_node *node; - struct jump_label_entry *e; - u32 hash = jhash((void *)&key, sizeof(jump_label_t), 0); - - head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)]; - hlist_for_each_entry(e, node, head, hlist) { - if (key == e->key) - return e; - } - return NULL; -} +static void jump_label_update(struct jump_label_key *key, int enable); -static struct jump_label_entry * -add_jump_label_entry(jump_label_t key, int nr_entries, struct jump_entry *table) +void jump_label_inc(struct jump_label_key *key) { - struct hlist_head *head; - struct jump_label_entry *e; - u32 hash; - - e = get_jump_label_entry(key); - if (e) - return ERR_PTR(-EEXIST); - - e = kmalloc(sizeof(struct jump_label_entry), GFP_KERNEL); - if (!e) - return ERR_PTR(-ENOMEM); - - hash = jhash((void *)&key, sizeof(jump_label_t), 0); - head = &jump_label_table[hash & (JUMP_LABEL_TABLE_SIZE - 1)]; - e->key = key; - e->table = table; - e->nr_entries = nr_entries; - INIT_HLIST_HEAD(&(e->modules)); - hlist_add_head(&e->hlist, head); - return e; -} + if (atomic_inc_not_zero(&key->enabled)) + return; -static int -build_jump_label_hashtable(struct jump_entry *start, struct jump_entry *stop) -{ - struct jump_entry *iter, *iter_begin; - struct jump_label_entry *entry; - int count; - - sort_jump_label_entries(start, stop); - iter = start; - while (iter < stop) { - entry = get_jump_label_entry(iter->key); - if (!entry) { - iter_begin = iter; - count = 0; - while ((iter < stop) && - (iter->key == iter_begin->key)) { - iter++; - count++; - } - entry = add_jump_label_entry(iter_begin->key, - count, iter_begin); - if (IS_ERR(entry)) - return PTR_ERR(entry); - } else { - WARN_ONCE(1, KERN_ERR "build_jump_hashtable: unexpected entry!\n"); - return -1; - } - } - return 0; + jump_label_lock(); + if (atomic_add_return(1, &key->enabled) == 1) + jump_label_update(key, JUMP_LABEL_ENABLE); + jump_label_unlock(); } -/*** - * jump_label_update - update jump label text - * @key - key value associated with a a jump label - * @type - enum set to JUMP_LABEL_ENABLE or JUMP_LABEL_DISABLE - * - * Will enable/disable the jump for jump label @key, depending on the - * value of @type. - * - */ - -void jump_label_update(unsigned long key, enum jump_label_type type) +void jump_label_dec(struct jump_label_key *key) { - struct jump_entry *iter; - struct jump_label_entry *entry; - struct hlist_node *module_node; - struct jump_label_module_entry *e_module; - int count; + if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) + return; - jump_label_lock(); - entry = get_jump_label_entry((jump_label_t)key); - if (entry) { - count = entry->nr_entries; - iter = entry->table; - while (count--) { - if (kernel_text_address(iter->code)) - arch_jump_label_transform(iter, type); - iter++; - } - /* eanble/disable jump labels in modules */ - hlist_for_each_entry(e_module, module_node, &(entry->modules), - hlist) { - count = e_module->nr_entries; - iter = e_module->table; - while (count--) { - if (iter->key && - kernel_text_address(iter->code)) - arch_jump_label_transform(iter, type); - iter++; - } - } - } + jump_label_update(key, JUMP_LABEL_DISABLE); jump_label_unlock(); } @@ -197,77 +89,36 @@ static int addr_conflict(struct jump_entry *entry, void *start, void *end) return 0; } -#ifdef CONFIG_MODULES - -static int module_conflict(void *start, void *end) -{ - struct hlist_head *head; - struct hlist_node *node, *node_next, *module_node, *module_node_next; - struct jump_label_entry *e; - struct jump_label_module_entry *e_module; - struct jump_entry *iter; - int i, count; - int conflict = 0; - - for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) { - head = &jump_label_table[i]; - hlist_for_each_entry_safe(e, node, node_next, head, hlist) { - hlist_for_each_entry_safe(e_module, module_node, - module_node_next, - &(e->modules), hlist) { - count = e_module->nr_entries; - iter = e_module->table; - while (count--) { - if (addr_conflict(iter, start, end)) { - conflict = 1; - goto out; - } - iter++; - } - } - } - } -out: - return conflict; -} - -#endif - -/*** - * jump_label_text_reserved - check if addr range is reserved - * @start: start text addr - * @end: end text addr - * - * checks if the text addr located between @start and @end - * overlaps with any of the jump label patch addresses. Code - * that wants to modify kernel text should first verify that - * it does not overlap with any of the jump label addresses. - * Caller must hold jump_label_mutex. - * - * returns 1 if there is an overlap, 0 otherwise - */ -int jump_label_text_reserved(void *start, void *end) +static int __jump_label_text_reserved(struct jump_entry *iter_start, + struct jump_entry *iter_stop, void *start, void *end) { struct jump_entry *iter; - struct jump_entry *iter_start = __start___jump_table; - struct jump_entry *iter_stop = __start___jump_table; - int conflict = 0; iter = iter_start; while (iter < iter_stop) { - if (addr_conflict(iter, start, end)) { - conflict = 1; - goto out; - } + if (addr_conflict(iter, start, end)) + return 1; iter++; } - /* now check modules */ -#ifdef CONFIG_MODULES - conflict = module_conflict(start, end); -#endif -out: - return conflict; + return 0; +} + +static void __jump_label_update(struct jump_label_key *key, + struct jump_entry *entry, + struct jump_entry *stop, int enable) +{ + for (; (entry < stop) && + (entry->key == (jump_label_t)(unsigned long)key); + entry++) { + /* + * entry->code set to 0 invalidates module init text sections + * kernel_text_address() verifies we are not in core kernel + * init code, see jump_label_invalidate_module_init(). + */ + if (entry->code && kernel_text_address(entry->code)) + arch_jump_label_transform(entry, enable); + } } /* @@ -277,145 +128,181 @@ void __weak arch_jump_label_text_poke_early(jump_label_t addr) { } -static __init int init_jump_label(void) +static __init int jump_label_init(void) { - int ret; struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; + struct jump_label_key *key = NULL; struct jump_entry *iter; jump_label_lock(); - ret = build_jump_label_hashtable(__start___jump_table, - __stop___jump_table); - iter = iter_start; - while (iter < iter_stop) { + jump_label_sort_entries(iter_start, iter_stop); + + for (iter = iter_start; iter < iter_stop; iter++) { arch_jump_label_text_poke_early(iter->code); - iter++; + if (iter->key == (jump_label_t)(unsigned long)key) + continue; + + key = (struct jump_label_key *)(unsigned long)iter->key; + atomic_set(&key->enabled, 0); + key->entries = iter; +#ifdef CONFIG_MODULES + key->next = NULL; +#endif } jump_label_unlock(); - return ret; + + return 0; } -early_initcall(init_jump_label); +early_initcall(jump_label_init); #ifdef CONFIG_MODULES -static struct jump_label_module_entry * -add_jump_label_module_entry(struct jump_label_entry *entry, - struct jump_entry *iter_begin, - int count, struct module *mod) +struct jump_label_mod { + struct jump_label_mod *next; + struct jump_entry *entries; + struct module *mod; +}; + +static int __jump_label_mod_text_reserved(void *start, void *end) { - struct jump_label_module_entry *e; - - e = kmalloc(sizeof(struct jump_label_module_entry), GFP_KERNEL); - if (!e) - return ERR_PTR(-ENOMEM); - e->mod = mod; - e->nr_entries = count; - e->table = iter_begin; - hlist_add_head(&e->hlist, &entry->modules); - return e; + struct module *mod; + + mod = __module_text_address((unsigned long)start); + if (!mod) + return 0; + + WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); + + return __jump_label_text_reserved(mod->jump_entries, + mod->jump_entries + mod->num_jump_entries, + start, end); } -static int add_jump_label_module(struct module *mod) +static void __jump_label_mod_update(struct jump_label_key *key, int enable) { - struct jump_entry *iter, *iter_begin; - struct jump_label_entry *entry; - struct jump_label_module_entry *module_entry; - int count; + struct jump_label_mod *mod = key->next; - /* if the module doesn't have jump label entries, just return */ - if (!mod->num_jump_entries) - return 0; + while (mod) { + struct module *m = mod->mod; - sort_jump_label_entries(mod->jump_entries, - mod->jump_entries + mod->num_jump_entries); - iter = mod->jump_entries; - while (iter < mod->jump_entries + mod->num_jump_entries) { - entry = get_jump_label_entry(iter->key); - iter_begin = iter; - count = 0; - while ((iter < mod->jump_entries + mod->num_jump_entries) && - (iter->key == iter_begin->key)) { - iter++; - count++; - } - if (!entry) { - entry = add_jump_label_entry(iter_begin->key, 0, NULL); - if (IS_ERR(entry)) - return PTR_ERR(entry); - } - module_entry = add_jump_label_module_entry(entry, iter_begin, - count, mod); - if (IS_ERR(module_entry)) - return PTR_ERR(module_entry); + __jump_label_update(key, mod->entries, + m->jump_entries + m->num_jump_entries, + enable); + mod = mod->next; } - return 0; } -static void remove_jump_label_module(struct module *mod) +/*** + * apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop() + * @mod: module to patch + * + * Allow for run-time selection of the optimal nops. Before the module + * loads patch these with arch_get_jump_label_nop(), which is specified by + * the arch specific jump label code. + */ +void jump_label_apply_nops(struct module *mod) { - struct hlist_head *head; - struct hlist_node *node, *node_next, *module_node, *module_node_next; - struct jump_label_entry *e; - struct jump_label_module_entry *e_module; - int i; + struct jump_entry *iter_start = mod->jump_entries; + struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; + struct jump_entry *iter; /* if the module doesn't have jump label entries, just return */ - if (!mod->num_jump_entries) + if (iter_start == iter_stop) return; - for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) { - head = &jump_label_table[i]; - hlist_for_each_entry_safe(e, node, node_next, head, hlist) { - hlist_for_each_entry_safe(e_module, module_node, - module_node_next, - &(e->modules), hlist) { - if (e_module->mod == mod) { - hlist_del(&e_module->hlist); - kfree(e_module); - } - } - if (hlist_empty(&e->modules) && (e->nr_entries == 0)) { - hlist_del(&e->hlist); - kfree(e); - } + for (iter = iter_start; iter < iter_stop; iter++) + arch_jump_label_text_poke_early(iter->code); +} + +static int jump_label_add_module(struct module *mod) +{ + struct jump_entry *iter_start = mod->jump_entries; + struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; + struct jump_entry *iter; + struct jump_label_key *key = NULL; + struct jump_label_mod *jlm; + + /* if the module doesn't have jump label entries, just return */ + if (iter_start == iter_stop) + return 0; + + jump_label_sort_entries(iter_start, iter_stop); + + for (iter = iter_start; iter < iter_stop; iter++) { + if (iter->key == (jump_label_t)(unsigned long)key) + continue; + + key = (struct jump_label_key *)(unsigned long)iter->key; + + if (__module_address(iter->key) == mod) { + atomic_set(&key->enabled, 0); + key->entries = iter; + key->next = NULL; + continue; } + + jlm = kzalloc(sizeof(struct jump_label_mod), GFP_KERNEL); + if (!jlm) + return -ENOMEM; + + jlm->mod = mod; + jlm->entries = iter; + jlm->next = key->next; + key->next = jlm; + + if (jump_label_enabled(key)) + __jump_label_update(key, iter, iter_stop, + JUMP_LABEL_ENABLE); } + + return 0; } -static void remove_jump_label_module_init(struct module *mod) +static void jump_label_del_module(struct module *mod) { - struct hlist_head *head; - struct hlist_node *node, *node_next, *module_node, *module_node_next; - struct jump_label_entry *e; - struct jump_label_module_entry *e_module; + struct jump_entry *iter_start = mod->jump_entries; + struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; - int i, count; + struct jump_label_key *key = NULL; + struct jump_label_mod *jlm, **prev; - /* if the module doesn't have jump label entries, just return */ - if (!mod->num_jump_entries) - return; + for (iter = iter_start; iter < iter_stop; iter++) { + if (iter->key == (jump_label_t)(unsigned long)key) + continue; + + key = (struct jump_label_key *)(unsigned long)iter->key; + + if (__module_address(iter->key) == mod) + continue; + + prev = &key->next; + jlm = key->next; + + while (jlm && jlm->mod != mod) { + prev = &jlm->next; + jlm = jlm->next; + } - for (i = 0; i < JUMP_LABEL_TABLE_SIZE; i++) { - head = &jump_label_table[i]; - hlist_for_each_entry_safe(e, node, node_next, head, hlist) { - hlist_for_each_entry_safe(e_module, module_node, - module_node_next, - &(e->modules), hlist) { - if (e_module->mod != mod) - continue; - count = e_module->nr_entries; - iter = e_module->table; - while (count--) { - if (within_module_init(iter->code, mod)) - iter->key = 0; - iter++; - } - } + if (jlm) { + *prev = jlm->next; + kfree(jlm); } } } +static void jump_label_invalidate_module_init(struct module *mod) +{ + struct jump_entry *iter_start = mod->jump_entries; + struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; + struct jump_entry *iter; + + for (iter = iter_start; iter < iter_stop; iter++) { + if (within_module_init(iter->code, mod)) + iter->code = 0; + } +} + static int jump_label_module_notify(struct notifier_block *self, unsigned long val, void *data) @@ -426,59 +313,81 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val, switch (val) { case MODULE_STATE_COMING: jump_label_lock(); - ret = add_jump_label_module(mod); + ret = jump_label_add_module(mod); if (ret) - remove_jump_label_module(mod); + jump_label_del_module(mod); jump_label_unlock(); break; case MODULE_STATE_GOING: jump_label_lock(); - remove_jump_label_module(mod); + jump_label_del_module(mod); jump_label_unlock(); break; case MODULE_STATE_LIVE: jump_label_lock(); - remove_jump_label_module_init(mod); + jump_label_invalidate_module_init(mod); jump_label_unlock(); break; } - return ret; -} - -/*** - * apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop() - * @mod: module to patch - * - * Allow for run-time selection of the optimal nops. Before the module - * loads patch these with arch_get_jump_label_nop(), which is specified by - * the arch specific jump label code. - */ -void jump_label_apply_nops(struct module *mod) -{ - struct jump_entry *iter; - - /* if the module doesn't have jump label entries, just return */ - if (!mod->num_jump_entries) - return; - iter = mod->jump_entries; - while (iter < mod->jump_entries + mod->num_jump_entries) { - arch_jump_label_text_poke_early(iter->code); - iter++; - } + return notifier_from_errno(ret); } struct notifier_block jump_label_module_nb = { .notifier_call = jump_label_module_notify, - .priority = 0, + .priority = 1, /* higher than tracepoints */ }; -static __init int init_jump_label_module(void) +static __init int jump_label_init_module(void) { return register_module_notifier(&jump_label_module_nb); } -early_initcall(init_jump_label_module); +early_initcall(jump_label_init_module); #endif /* CONFIG_MODULES */ +/*** + * jump_label_text_reserved - check if addr range is reserved + * @start: start text addr + * @end: end text addr + * + * checks if the text addr located between @start and @end + * overlaps with any of the jump label patch addresses. Code + * that wants to modify kernel text should first verify that + * it does not overlap with any of the jump label addresses. + * Caller must hold jump_label_mutex. + * + * returns 1 if there is an overlap, 0 otherwise + */ +int jump_label_text_reserved(void *start, void *end) +{ + int ret = __jump_label_text_reserved(__start___jump_table, + __stop___jump_table, start, end); + + if (ret) + return ret; + +#ifdef CONFIG_MODULES + ret = __jump_label_mod_text_reserved(start, end); +#endif + return ret; +} + +static void jump_label_update(struct jump_label_key *key, int enable) +{ + struct jump_entry *entry = key->entries, *stop = __stop___jump_table; + +#ifdef CONFIG_MODULES + struct module *mod = __module_address((jump_label_t)key); + + __jump_label_mod_update(key, enable); + + if (mod) + stop = mod->jump_entries + mod->num_jump_entries; +#endif + /* if there are no users, entry can be NULL */ + if (entry) + __jump_label_update(key, entry, stop, enable); +} + #endif diff --git a/kernel/kexec.c b/kernel/kexec.c index 55936f9cb25..296fbc84d65 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -33,6 +33,7 @@ #include <linux/vmalloc.h> #include <linux/swap.h> #include <linux/kmsg_dump.h> +#include <linux/syscore_ops.h> #include <asm/page.h> #include <asm/uaccess.h> @@ -1094,7 +1095,7 @@ size_t crash_get_memory_size(void) size_t size = 0; mutex_lock(&kexec_mutex); if (crashk_res.end != crashk_res.start) - size = crashk_res.end - crashk_res.start + 1; + size = resource_size(&crashk_res); mutex_unlock(&kexec_mutex); return size; } @@ -1530,8 +1531,7 @@ int kernel_kexec(void) if (error) goto Enable_cpus; local_irq_disable(); - /* Suspend system devices */ - error = sysdev_suspend(PMSG_FREEZE); + error = syscore_suspend(); if (error) goto Enable_irqs; } else @@ -1546,7 +1546,7 @@ int kernel_kexec(void) #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { - sysdev_resume(); + syscore_resume(); Enable_irqs: local_irq_enable(); Enable_cpus: diff --git a/kernel/kmod.c b/kernel/kmod.c index 9cd0591c96a..47613dfb7b2 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -25,6 +25,7 @@ #include <linux/kmod.h> #include <linux/slab.h> #include <linux/completion.h> +#include <linux/cred.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/workqueue.h> @@ -43,6 +44,13 @@ extern int max_threads; static struct workqueue_struct *khelper_wq; +#define CAP_BSET (void *)1 +#define CAP_PI (void *)2 + +static kernel_cap_t usermodehelper_bset = CAP_FULL_SET; +static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET; +static DEFINE_SPINLOCK(umh_sysctl_lock); + #ifdef CONFIG_MODULES /* @@ -132,6 +140,7 @@ EXPORT_SYMBOL(__request_module); static int ____call_usermodehelper(void *data) { struct subprocess_info *sub_info = data; + struct cred *new; int retval; spin_lock_irq(¤t->sighand->siglock); @@ -147,12 +156,27 @@ static int ____call_usermodehelper(void *data) */ set_user_nice(current, 0); + retval = -ENOMEM; + new = prepare_kernel_cred(current); + if (!new) + goto fail; + + spin_lock(&umh_sysctl_lock); + new->cap_bset = cap_intersect(usermodehelper_bset, new->cap_bset); + new->cap_inheritable = cap_intersect(usermodehelper_inheritable, + new->cap_inheritable); + spin_unlock(&umh_sysctl_lock); + if (sub_info->init) { - retval = sub_info->init(sub_info); - if (retval) + retval = sub_info->init(sub_info, new); + if (retval) { + abort_creds(new); goto fail; + } } + commit_creds(new); + retval = kernel_execve(sub_info->path, (const char *const *)sub_info->argv, (const char *const *)sub_info->envp); @@ -245,7 +269,6 @@ static void __call_usermodehelper(struct work_struct *work) } } -#ifdef CONFIG_PM_SLEEP /* * If set, call_usermodehelper_exec() will exit immediately returning -EBUSY * (used for preventing user land processes from being created after the user @@ -301,6 +324,15 @@ void usermodehelper_enable(void) usermodehelper_disabled = 0; } +/** + * usermodehelper_is_disabled - check if new helpers are allowed to be started + */ +bool usermodehelper_is_disabled(void) +{ + return usermodehelper_disabled; +} +EXPORT_SYMBOL_GPL(usermodehelper_is_disabled); + static void helper_lock(void) { atomic_inc(&running_helpers); @@ -312,12 +344,6 @@ static void helper_unlock(void) if (atomic_dec_and_test(&running_helpers)) wake_up(&running_helpers_waitq); } -#else /* CONFIG_PM_SLEEP */ -#define usermodehelper_disabled 0 - -static inline void helper_lock(void) {} -static inline void helper_unlock(void) {} -#endif /* CONFIG_PM_SLEEP */ /** * call_usermodehelper_setup - prepare to call a usermode helper @@ -364,7 +390,7 @@ EXPORT_SYMBOL(call_usermodehelper_setup); * context in which call_usermodehelper_exec is called. */ void call_usermodehelper_setfns(struct subprocess_info *info, - int (*init)(struct subprocess_info *info), + int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *info), void *data) { @@ -418,6 +444,84 @@ unlock: } EXPORT_SYMBOL(call_usermodehelper_exec); +static int proc_cap_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + unsigned long cap_array[_KERNEL_CAPABILITY_U32S]; + kernel_cap_t new_cap; + int err, i; + + if (write && (!capable(CAP_SETPCAP) || + !capable(CAP_SYS_MODULE))) + return -EPERM; + + /* + * convert from the global kernel_cap_t to the ulong array to print to + * userspace if this is a read. + */ + spin_lock(&umh_sysctl_lock); + for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) { + if (table->data == CAP_BSET) + cap_array[i] = usermodehelper_bset.cap[i]; + else if (table->data == CAP_PI) + cap_array[i] = usermodehelper_inheritable.cap[i]; + else + BUG(); + } + spin_unlock(&umh_sysctl_lock); + + t = *table; + t.data = &cap_array; + + /* + * actually read or write and array of ulongs from userspace. Remember + * these are least significant 32 bits first + */ + err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + + /* + * convert from the sysctl array of ulongs to the kernel_cap_t + * internal representation + */ + for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) + new_cap.cap[i] = cap_array[i]; + + /* + * Drop everything not in the new_cap (but don't add things) + */ + spin_lock(&umh_sysctl_lock); + if (write) { + if (table->data == CAP_BSET) + usermodehelper_bset = cap_intersect(usermodehelper_bset, new_cap); + if (table->data == CAP_PI) + usermodehelper_inheritable = cap_intersect(usermodehelper_inheritable, new_cap); + } + spin_unlock(&umh_sysctl_lock); + + return 0; +} + +struct ctl_table usermodehelper_table[] = { + { + .procname = "bset", + .data = CAP_BSET, + .maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long), + .mode = 0600, + .proc_handler = proc_cap_handler, + }, + { + .procname = "inheritable", + .data = CAP_PI, + .maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long), + .mode = 0600, + .proc_handler = proc_cap_handler, + }, + { } +}; + void __init usermodehelper_init(void) { khelper_wq = create_singlethread_workqueue("khelper"); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 77981813a1e..b30fd54eb98 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1255,19 +1255,29 @@ static int __kprobes in_kprobes_functions(unsigned long addr) /* * If we have a symbol_name argument, look it up and add the offset field * to it. This way, we can specify a relative address to a symbol. + * This returns encoded errors if it fails to look up symbol or invalid + * combination of parameters. */ static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p) { kprobe_opcode_t *addr = p->addr; + + if ((p->symbol_name && p->addr) || + (!p->symbol_name && !p->addr)) + goto invalid; + if (p->symbol_name) { - if (addr) - return NULL; kprobe_lookup_name(p->symbol_name, addr); + if (!addr) + return ERR_PTR(-ENOENT); } - if (!addr) - return NULL; - return (kprobe_opcode_t *)(((char *)addr) + p->offset); + addr = (kprobe_opcode_t *)(((char *)addr) + p->offset); + if (addr) + return addr; + +invalid: + return ERR_PTR(-EINVAL); } /* Check passed kprobe is valid and return kprobe in kprobe_table. */ @@ -1311,8 +1321,8 @@ int __kprobes register_kprobe(struct kprobe *p) kprobe_opcode_t *addr; addr = kprobe_addr(p); - if (!addr) - return -EINVAL; + if (IS_ERR(addr)) + return PTR_ERR(addr); p->addr = addr; ret = check_kprobe_rereg(p); @@ -1335,6 +1345,8 @@ int __kprobes register_kprobe(struct kprobe *p) */ probed_mod = __module_text_address((unsigned long) p->addr); if (probed_mod) { + /* Return -ENOENT if fail. */ + ret = -ENOENT; /* * We must hold a refcount of the probed module while updating * its code to prohibit unexpected unloading. @@ -1351,6 +1363,7 @@ int __kprobes register_kprobe(struct kprobe *p) module_put(probed_mod); goto fail_with_jump_label; } + /* ret will be updated by following code */ } preempt_enable(); jump_label_unlock(); @@ -1399,7 +1412,7 @@ out: fail_with_jump_label: preempt_enable(); jump_label_unlock(); - return -EINVAL; + return ret; } EXPORT_SYMBOL_GPL(register_kprobe); @@ -1686,8 +1699,8 @@ int __kprobes register_kretprobe(struct kretprobe *rp) if (kretprobe_blacklist_size) { addr = kprobe_addr(&rp->kp); - if (!addr) - return -EINVAL; + if (IS_ERR(addr)) + return PTR_ERR(addr); for (i = 0; kretprobe_blacklist[i].name != NULL; i++) { if (kretprobe_blacklist[i].addr == addr) diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 0b624e79180..3b053c04dd8 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -16,6 +16,7 @@ #include <linux/kexec.h> #include <linux/profile.h> #include <linux/sched.h> +#include <linux/capability.h> #define KERNEL_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) @@ -131,6 +132,14 @@ KERNEL_ATTR_RO(vmcoreinfo); #endif /* CONFIG_KEXEC */ +/* whether file capabilities are enabled */ +static ssize_t fscaps_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", file_caps_enabled); +} +KERNEL_ATTR_RO(fscaps); + /* * Make /sys/kernel/notes give the raw contents of our kernel .notes section. */ @@ -158,6 +167,7 @@ struct kobject *kernel_kobj; EXPORT_SYMBOL_GPL(kernel_kobj); static struct attribute * kernel_attrs[] = { + &fscaps_attr.attr, #if defined(CONFIG_HOTPLUG) &uevent_seqnum_attr.attr, &uevent_helper_attr.attr, diff --git a/kernel/kthread.c b/kernel/kthread.c index 3b34d2732bc..4ba7cccb499 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -202,8 +202,8 @@ void kthread_bind(struct task_struct *p, unsigned int cpu) return; } - p->cpus_allowed = cpumask_of_cpu(cpu); - p->rt.nr_cpus_allowed = 1; + /* It's safe because the task is inactive. */ + do_set_cpus_allowed(p, cpumask_of(cpu)); p->flags |= PF_THREAD_BOUND; } EXPORT_SYMBOL(kthread_bind); diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 53a68956f13..3956f5149e2 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -490,6 +490,18 @@ void get_usage_chars(struct lock_class *class, char usage[LOCK_USAGE_CHARS]) usage[i] = '\0'; } +static int __print_lock_name(struct lock_class *class) +{ + char str[KSYM_NAME_LEN]; + const char *name; + + name = class->name; + if (!name) + name = __get_key_name(class->key, str); + + return printk("%s", name); +} + static void print_lock_name(struct lock_class *class) { char str[KSYM_NAME_LEN], usage[LOCK_USAGE_CHARS]; @@ -1053,6 +1065,56 @@ print_circular_bug_entry(struct lock_list *target, int depth) return 0; } +static void +print_circular_lock_scenario(struct held_lock *src, + struct held_lock *tgt, + struct lock_list *prt) +{ + struct lock_class *source = hlock_class(src); + struct lock_class *target = hlock_class(tgt); + struct lock_class *parent = prt->class; + + /* + * A direct locking problem where unsafe_class lock is taken + * directly by safe_class lock, then all we need to show + * is the deadlock scenario, as it is obvious that the + * unsafe lock is taken under the safe lock. + * + * But if there is a chain instead, where the safe lock takes + * an intermediate lock (middle_class) where this lock is + * not the same as the safe lock, then the lock chain is + * used to describe the problem. Otherwise we would need + * to show a different CPU case for each link in the chain + * from the safe_class lock to the unsafe_class lock. + */ + if (parent != source) { + printk("Chain exists of:\n "); + __print_lock_name(source); + printk(" --> "); + __print_lock_name(parent); + printk(" --> "); + __print_lock_name(target); + printk("\n\n"); + } + + printk(" Possible unsafe locking scenario:\n\n"); + printk(" CPU0 CPU1\n"); + printk(" ---- ----\n"); + printk(" lock("); + __print_lock_name(target); + printk(");\n"); + printk(" lock("); + __print_lock_name(parent); + printk(");\n"); + printk(" lock("); + __print_lock_name(target); + printk(");\n"); + printk(" lock("); + __print_lock_name(source); + printk(");\n"); + printk("\n *** DEADLOCK ***\n\n"); +} + /* * When a circular dependency is detected, print the * header first: @@ -1096,6 +1158,7 @@ static noinline int print_circular_bug(struct lock_list *this, { struct task_struct *curr = current; struct lock_list *parent; + struct lock_list *first_parent; int depth; if (!debug_locks_off_graph_unlock() || debug_locks_silent) @@ -1109,6 +1172,7 @@ static noinline int print_circular_bug(struct lock_list *this, print_circular_bug_header(target, depth, check_src, check_tgt); parent = get_lock_parent(target); + first_parent = parent; while (parent) { print_circular_bug_entry(parent, --depth); @@ -1116,6 +1180,9 @@ static noinline int print_circular_bug(struct lock_list *this, } printk("\nother info that might help us debug this:\n\n"); + print_circular_lock_scenario(check_src, check_tgt, + first_parent); + lockdep_print_held_locks(curr); printk("\nstack backtrace:\n"); @@ -1314,7 +1381,7 @@ print_shortest_lock_dependencies(struct lock_list *leaf, printk("\n"); if (depth == 0 && (entry != root)) { - printk("lockdep:%s bad BFS generated tree\n", __func__); + printk("lockdep:%s bad path found in chain graph\n", __func__); break; } @@ -1325,6 +1392,62 @@ print_shortest_lock_dependencies(struct lock_list *leaf, return; } +static void +print_irq_lock_scenario(struct lock_list *safe_entry, + struct lock_list *unsafe_entry, + struct lock_class *prev_class, + struct lock_class *next_class) +{ + struct lock_class *safe_class = safe_entry->class; + struct lock_class *unsafe_class = unsafe_entry->class; + struct lock_class *middle_class = prev_class; + + if (middle_class == safe_class) + middle_class = next_class; + + /* + * A direct locking problem where unsafe_class lock is taken + * directly by safe_class lock, then all we need to show + * is the deadlock scenario, as it is obvious that the + * unsafe lock is taken under the safe lock. + * + * But if there is a chain instead, where the safe lock takes + * an intermediate lock (middle_class) where this lock is + * not the same as the safe lock, then the lock chain is + * used to describe the problem. Otherwise we would need + * to show a different CPU case for each link in the chain + * from the safe_class lock to the unsafe_class lock. + */ + if (middle_class != unsafe_class) { + printk("Chain exists of:\n "); + __print_lock_name(safe_class); + printk(" --> "); + __print_lock_name(middle_class); + printk(" --> "); + __print_lock_name(unsafe_class); + printk("\n\n"); + } + + printk(" Possible interrupt unsafe locking scenario:\n\n"); + printk(" CPU0 CPU1\n"); + printk(" ---- ----\n"); + printk(" lock("); + __print_lock_name(unsafe_class); + printk(");\n"); + printk(" local_irq_disable();\n"); + printk(" lock("); + __print_lock_name(safe_class); + printk(");\n"); + printk(" lock("); + __print_lock_name(middle_class); + printk(");\n"); + printk(" <Interrupt>\n"); + printk(" lock("); + __print_lock_name(safe_class); + printk(");\n"); + printk("\n *** DEADLOCK ***\n\n"); +} + static int print_bad_irq_dependency(struct task_struct *curr, struct lock_list *prev_root, @@ -1376,6 +1499,9 @@ print_bad_irq_dependency(struct task_struct *curr, print_stack_trace(forwards_entry->class->usage_traces + bit2, 1); printk("\nother info that might help us debug this:\n\n"); + print_irq_lock_scenario(backwards_entry, forwards_entry, + hlock_class(prev), hlock_class(next)); + lockdep_print_held_locks(curr); printk("\nthe dependencies between %s-irq-safe lock", irqclass); @@ -1539,6 +1665,26 @@ static inline void inc_chains(void) #endif +static void +print_deadlock_scenario(struct held_lock *nxt, + struct held_lock *prv) +{ + struct lock_class *next = hlock_class(nxt); + struct lock_class *prev = hlock_class(prv); + + printk(" Possible unsafe locking scenario:\n\n"); + printk(" CPU0\n"); + printk(" ----\n"); + printk(" lock("); + __print_lock_name(prev); + printk(");\n"); + printk(" lock("); + __print_lock_name(next); + printk(");\n"); + printk("\n *** DEADLOCK ***\n\n"); + printk(" May be due to missing lock nesting notation\n\n"); +} + static int print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, struct held_lock *next) @@ -1557,6 +1703,7 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, print_lock(prev); printk("\nother info that might help us debug this:\n"); + print_deadlock_scenario(next, prev); lockdep_print_held_locks(curr); printk("\nstack backtrace:\n"); @@ -1826,7 +1973,7 @@ static inline int lookup_chain_cache(struct task_struct *curr, struct list_head *hash_head = chainhashentry(chain_key); struct lock_chain *chain; struct held_lock *hlock_curr, *hlock_next; - int i, j, n, cn; + int i, j; if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return 0; @@ -1886,15 +2033,9 @@ cache_hit: } i++; chain->depth = curr->lockdep_depth + 1 - i; - cn = nr_chain_hlocks; - while (cn + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS) { - n = cmpxchg(&nr_chain_hlocks, cn, cn + chain->depth); - if (n == cn) - break; - cn = n; - } - if (likely(cn + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { - chain->base = cn; + if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { + chain->base = nr_chain_hlocks; + nr_chain_hlocks += chain->depth; for (j = 0; j < chain->depth - 1; j++, i++) { int lock_id = curr->held_locks[i].class_idx - 1; chain_hlocks[chain->base + j] = lock_id; @@ -2011,6 +2152,24 @@ static void check_chain_key(struct task_struct *curr) #endif } +static void +print_usage_bug_scenario(struct held_lock *lock) +{ + struct lock_class *class = hlock_class(lock); + + printk(" Possible unsafe locking scenario:\n\n"); + printk(" CPU0\n"); + printk(" ----\n"); + printk(" lock("); + __print_lock_name(class); + printk(");\n"); + printk(" <Interrupt>\n"); + printk(" lock("); + __print_lock_name(class); + printk(");\n"); + printk("\n *** DEADLOCK ***\n\n"); +} + static int print_usage_bug(struct task_struct *curr, struct held_lock *this, enum lock_usage_bit prev_bit, enum lock_usage_bit new_bit) @@ -2039,6 +2198,8 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, print_irqtrace_events(curr); printk("\nother info that might help us debug this:\n"); + print_usage_bug_scenario(this); + lockdep_print_held_locks(curr); printk("\nstack backtrace:\n"); @@ -2073,6 +2234,10 @@ print_irq_inversion_bug(struct task_struct *curr, struct held_lock *this, int forwards, const char *irqclass) { + struct lock_list *entry = other; + struct lock_list *middle = NULL; + int depth; + if (!debug_locks_off_graph_unlock() || debug_locks_silent) return 0; @@ -2091,6 +2256,25 @@ print_irq_inversion_bug(struct task_struct *curr, printk("\n\nand interrupts could create inverse lock ordering between them.\n\n"); printk("\nother info that might help us debug this:\n"); + + /* Find a middle lock (if one exists) */ + depth = get_lock_depth(other); + do { + if (depth == 0 && (entry != root)) { + printk("lockdep:%s bad path found in chain graph\n", __func__); + break; + } + middle = entry; + entry = get_lock_parent(entry); + depth--; + } while (entry && entry != root && (depth >= 0)); + if (forwards) + print_irq_lock_scenario(root, other, + middle ? middle->class : root->class, other->class); + else + print_irq_lock_scenario(other, root, + middle ? middle->class : other->class, root->class); + lockdep_print_held_locks(curr); printk("\nthe shortest dependencies between 2nd lock and 1st lock:\n"); @@ -2284,6 +2468,9 @@ mark_held_locks(struct task_struct *curr, enum mark_type mark) BUG_ON(usage_bit >= LOCK_USAGE_STATES); + if (hlock_class(hlock)->key == &__lockdep_no_validate__) + continue; + if (!mark_lock(curr, hlock, usage_bit)) return 0; } @@ -2294,15 +2481,10 @@ mark_held_locks(struct task_struct *curr, enum mark_type mark) /* * Hardirqs will be enabled: */ -void trace_hardirqs_on_caller(unsigned long ip) +static void __trace_hardirqs_on_caller(unsigned long ip) { struct task_struct *curr = current; - time_hardirqs_on(CALLER_ADDR0, ip); - - if (unlikely(!debug_locks || current->lockdep_recursion)) - return; - if (DEBUG_LOCKS_WARN_ON(unlikely(early_boot_irqs_disabled))) return; @@ -2318,8 +2500,6 @@ void trace_hardirqs_on_caller(unsigned long ip) /* we'll do an OFF -> ON transition: */ curr->hardirqs_enabled = 1; - if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) - return; if (DEBUG_LOCKS_WARN_ON(current->hardirq_context)) return; /* @@ -2341,6 +2521,21 @@ void trace_hardirqs_on_caller(unsigned long ip) curr->hardirq_enable_event = ++curr->irq_events; debug_atomic_inc(hardirqs_on_events); } + +void trace_hardirqs_on_caller(unsigned long ip) +{ + time_hardirqs_on(CALLER_ADDR0, ip); + + if (unlikely(!debug_locks || current->lockdep_recursion)) + return; + + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return; + + current->lockdep_recursion = 1; + __trace_hardirqs_on_caller(ip); + current->lockdep_recursion = 0; +} EXPORT_SYMBOL(trace_hardirqs_on_caller); void trace_hardirqs_on(void) @@ -2390,7 +2585,7 @@ void trace_softirqs_on(unsigned long ip) { struct task_struct *curr = current; - if (unlikely(!debug_locks)) + if (unlikely(!debug_locks || current->lockdep_recursion)) return; if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) @@ -2401,6 +2596,7 @@ void trace_softirqs_on(unsigned long ip) return; } + current->lockdep_recursion = 1; /* * We'll do an OFF -> ON transition: */ @@ -2415,6 +2611,7 @@ void trace_softirqs_on(unsigned long ip) */ if (curr->hardirqs_enabled) mark_held_locks(curr, SOFTIRQ); + current->lockdep_recursion = 0; } /* @@ -2424,7 +2621,7 @@ void trace_softirqs_off(unsigned long ip) { struct task_struct *curr = current; - if (unlikely(!debug_locks)) + if (unlikely(!debug_locks || current->lockdep_recursion)) return; if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) @@ -3242,7 +3439,7 @@ int lock_is_held(struct lockdep_map *lock) int ret = 0; if (unlikely(current->lockdep_recursion)) - return ret; + return 1; /* avoid false negative lockdep_assert_held() */ raw_local_irq_save(flags); check_flags(flags); diff --git a/kernel/module.c b/kernel/module.c index d5938a5c19c..04379f92f84 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -57,6 +57,7 @@ #include <linux/kmemleak.h> #include <linux/jump_label.h> #include <linux/pfn.h> +#include <linux/bsearch.h> #define CREATE_TRACE_POINTS #include <trace/events/module.h> @@ -240,23 +241,24 @@ static bool each_symbol_in_section(const struct symsearch *arr, struct module *owner, bool (*fn)(const struct symsearch *syms, struct module *owner, - unsigned int symnum, void *data), + void *data), void *data) { - unsigned int i, j; + unsigned int j; for (j = 0; j < arrsize; j++) { - for (i = 0; i < arr[j].stop - arr[j].start; i++) - if (fn(&arr[j], owner, i, data)) - return true; + if (fn(&arr[j], owner, data)) + return true; } return false; } /* Returns true as soon as fn returns true, otherwise false. */ -bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner, - unsigned int symnum, void *data), void *data) +bool each_symbol_section(bool (*fn)(const struct symsearch *arr, + struct module *owner, + void *data), + void *data) { struct module *mod; static const struct symsearch arr[] = { @@ -309,7 +311,7 @@ bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner, } return false; } -EXPORT_SYMBOL_GPL(each_symbol); +EXPORT_SYMBOL_GPL(each_symbol_section); struct find_symbol_arg { /* Input */ @@ -323,15 +325,12 @@ struct find_symbol_arg { const struct kernel_symbol *sym; }; -static bool find_symbol_in_section(const struct symsearch *syms, - struct module *owner, - unsigned int symnum, void *data) +static bool check_symbol(const struct symsearch *syms, + struct module *owner, + unsigned int symnum, void *data) { struct find_symbol_arg *fsa = data; - if (strcmp(syms->start[symnum].name, fsa->name) != 0) - return false; - if (!fsa->gplok) { if (syms->licence == GPL_ONLY) return false; @@ -365,6 +364,30 @@ static bool find_symbol_in_section(const struct symsearch *syms, return true; } +static int cmp_name(const void *va, const void *vb) +{ + const char *a; + const struct kernel_symbol *b; + a = va; b = vb; + return strcmp(a, b->name); +} + +static bool find_symbol_in_section(const struct symsearch *syms, + struct module *owner, + void *data) +{ + struct find_symbol_arg *fsa = data; + struct kernel_symbol *sym; + + sym = bsearch(fsa->name, syms->start, syms->stop - syms->start, + sizeof(struct kernel_symbol), cmp_name); + + if (sym != NULL && check_symbol(syms, owner, sym - syms->start, data)) + return true; + + return false; +} + /* Find a symbol and return it, along with, (optional) crc and * (optional) module which owns it. Needs preempt disabled or module_mutex. */ const struct kernel_symbol *find_symbol(const char *name, @@ -379,7 +402,7 @@ const struct kernel_symbol *find_symbol(const char *name, fsa.gplok = gplok; fsa.warn = warn; - if (each_symbol(find_symbol_in_section, &fsa)) { + if (each_symbol_section(find_symbol_in_section, &fsa)) { if (owner) *owner = fsa.owner; if (crc) @@ -522,9 +545,9 @@ static void setup_modinfo_##field(struct module *mod, const char *s) \ mod->field = kstrdup(s, GFP_KERNEL); \ } \ static ssize_t show_modinfo_##field(struct module_attribute *mattr, \ - struct module *mod, char *buffer) \ + struct module_kobject *mk, char *buffer) \ { \ - return sprintf(buffer, "%s\n", mod->field); \ + return sprintf(buffer, "%s\n", mk->mod->field); \ } \ static int modinfo_##field##_exists(struct module *mod) \ { \ @@ -879,9 +902,9 @@ void symbol_put_addr(void *addr) EXPORT_SYMBOL_GPL(symbol_put_addr); static ssize_t show_refcnt(struct module_attribute *mattr, - struct module *mod, char *buffer) + struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%u\n", module_refcount(mod)); + return sprintf(buffer, "%u\n", module_refcount(mk->mod)); } static struct module_attribute refcnt = { @@ -929,11 +952,11 @@ static inline int module_unload_init(struct module *mod) #endif /* CONFIG_MODULE_UNLOAD */ static ssize_t show_initstate(struct module_attribute *mattr, - struct module *mod, char *buffer) + struct module_kobject *mk, char *buffer) { const char *state = "unknown"; - switch (mod->state) { + switch (mk->mod->state) { case MODULE_STATE_LIVE: state = "live"; break; @@ -952,10 +975,27 @@ static struct module_attribute initstate = { .show = show_initstate, }; +static ssize_t store_uevent(struct module_attribute *mattr, + struct module_kobject *mk, + const char *buffer, size_t count) +{ + enum kobject_action action; + + if (kobject_action_type(buffer, count, &action) == 0) + kobject_uevent(&mk->kobj, action); + return count; +} + +struct module_attribute module_uevent = { + .attr = { .name = "uevent", .mode = 0200 }, + .store = store_uevent, +}; + static struct module_attribute *modinfo_attrs[] = { &modinfo_version, &modinfo_srcversion, &initstate, + &module_uevent, #ifdef CONFIG_MODULE_UNLOAD &refcnt, #endif @@ -1164,7 +1204,7 @@ struct module_sect_attrs }; static ssize_t module_sect_show(struct module_attribute *mattr, - struct module *mod, char *buf) + struct module_kobject *mk, char *buf) { struct module_sect_attr *sattr = container_of(mattr, struct module_sect_attr, mattr); @@ -1607,27 +1647,28 @@ static void set_section_ro_nx(void *base, } } -/* Setting memory back to RW+NX before releasing it */ -void unset_section_ro_nx(struct module *mod, void *module_region) +static void unset_module_core_ro_nx(struct module *mod) { - unsigned long total_pages; - - if (mod->module_core == module_region) { - /* Set core as NX+RW */ - total_pages = MOD_NUMBER_OF_PAGES(mod->module_core, mod->core_size); - set_memory_nx((unsigned long)mod->module_core, total_pages); - set_memory_rw((unsigned long)mod->module_core, total_pages); + set_page_attributes(mod->module_core + mod->core_text_size, + mod->module_core + mod->core_size, + set_memory_x); + set_page_attributes(mod->module_core, + mod->module_core + mod->core_ro_size, + set_memory_rw); +} - } else if (mod->module_init == module_region) { - /* Set init as NX+RW */ - total_pages = MOD_NUMBER_OF_PAGES(mod->module_init, mod->init_size); - set_memory_nx((unsigned long)mod->module_init, total_pages); - set_memory_rw((unsigned long)mod->module_init, total_pages); - } +static void unset_module_init_ro_nx(struct module *mod) +{ + set_page_attributes(mod->module_init + mod->init_text_size, + mod->module_init + mod->init_size, + set_memory_x); + set_page_attributes(mod->module_init, + mod->module_init + mod->init_ro_size, + set_memory_rw); } /* Iterate through all modules and set each module's text as RW */ -void set_all_modules_text_rw() +void set_all_modules_text_rw(void) { struct module *mod; @@ -1648,7 +1689,7 @@ void set_all_modules_text_rw() } /* Iterate through all modules and set each module's text as RO */ -void set_all_modules_text_ro() +void set_all_modules_text_ro(void) { struct module *mod; @@ -1669,9 +1710,19 @@ void set_all_modules_text_ro() } #else static inline void set_section_ro_nx(void *base, unsigned long text_size, unsigned long ro_size, unsigned long total_size) { } -static inline void unset_section_ro_nx(struct module *mod, void *module_region) { } +static void unset_module_core_ro_nx(struct module *mod) { } +static void unset_module_init_ro_nx(struct module *mod) { } #endif +void __weak module_free(struct module *mod, void *module_region) +{ + vfree(module_region); +} + +void __weak module_arch_cleanup(struct module *mod) +{ +} + /* Free a module, remove from lists, etc. */ static void free_module(struct module *mod) { @@ -1696,7 +1747,7 @@ static void free_module(struct module *mod) destroy_params(mod->kp, mod->num_kp); /* This may be NULL, but that's OK */ - unset_section_ro_nx(mod, mod->module_init); + unset_module_init_ro_nx(mod); module_free(mod, mod->module_init); kfree(mod->args); percpu_modfree(mod); @@ -1705,7 +1756,7 @@ static void free_module(struct module *mod) lockdep_free_key_range(mod->module_core, mod->core_size); /* Finally, free the core (containing the module structure) */ - unset_section_ro_nx(mod, mod->module_core); + unset_module_core_ro_nx(mod); module_free(mod, mod->module_core); #ifdef CONFIG_MPU @@ -1826,6 +1877,26 @@ static int simplify_symbols(struct module *mod, const struct load_info *info) return ret; } +int __weak apply_relocate(Elf_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me) +{ + pr_err("module %s: REL relocation unsupported\n", me->name); + return -ENOEXEC; +} + +int __weak apply_relocate_add(Elf_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me) +{ + pr_err("module %s: RELA relocation unsupported\n", me->name); + return -ENOEXEC; +} + static int apply_relocations(struct module *mod, const struct load_info *info) { unsigned int i; @@ -2030,11 +2101,8 @@ static const struct kernel_symbol *lookup_symbol(const char *name, const struct kernel_symbol *start, const struct kernel_symbol *stop) { - const struct kernel_symbol *ks = start; - for (; ks < stop; ks++) - if (strcmp(ks->name, name) == 0) - return ks; - return NULL; + return bsearch(name, start, stop - start, + sizeof(struct kernel_symbol), cmp_name); } static int is_exported(const char *name, unsigned long value, @@ -2213,6 +2281,11 @@ static void dynamic_debug_remove(struct _ddebug *debug) ddebug_remove_module(debug->modname); } +void * __weak module_alloc(unsigned long size) +{ + return size == 0 ? NULL : vmalloc_exec(size); +} + static void *module_alloc_update_bounds(unsigned long size) { void *ret = module_alloc(size); @@ -2623,6 +2696,14 @@ static void flush_module_icache(const struct module *mod) set_fs(old_fs); } +int __weak module_frob_arch_sections(Elf_Ehdr *hdr, + Elf_Shdr *sechdrs, + char *secstrings, + struct module *mod) +{ + return 0; +} + static struct module *layout_and_allocate(struct load_info *info) { /* Module within temporary copy. */ @@ -2694,6 +2775,13 @@ static void module_deallocate(struct module *mod, struct load_info *info) module_free(mod, mod->module_core); } +int __weak module_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + return 0; +} + static int post_relocation(struct module *mod, const struct load_info *info) { /* Sort exception table now relocations are done. */ @@ -2790,7 +2878,7 @@ static struct module *load_module(void __user *umod, } /* This has to be done once we're sure module name is unique. */ - if (!mod->taints) + if (!mod->taints || mod->taints == (1U<<TAINT_CRAP)) dynamic_debug_setup(info.debug, info.num_debug); /* Find duplicate symbols */ @@ -2827,7 +2915,7 @@ static struct module *load_module(void __user *umod, module_bug_cleanup(mod); ddebug: - if (!mod->taints) + if (!mod->taints || mod->taints == (1U<<TAINT_CRAP)) dynamic_debug_remove(info.debug); unlock: mutex_unlock(&module_mutex); @@ -2931,10 +3019,11 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, mod->symtab = mod->core_symtab; mod->strtab = mod->core_strtab; #endif - unset_section_ro_nx(mod, mod->module_init); + unset_module_init_ro_nx(mod); module_free(mod, mod->module_init); mod->module_init = NULL; mod->init_size = 0; + mod->init_ro_size = 0; mod->init_text_size = 0; mutex_unlock(&module_mutex); diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c index ec815a960b5..73da83aff41 100644 --- a/kernel/mutex-debug.c +++ b/kernel/mutex-debug.c @@ -75,7 +75,7 @@ void debug_mutex_unlock(struct mutex *lock) return; DEBUG_LOCKS_WARN_ON(lock->magic != lock); - DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); + DEBUG_LOCKS_WARN_ON(lock->owner != current); DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); mutex_clear_owner(lock); } diff --git a/kernel/mutex-debug.h b/kernel/mutex-debug.h index 57d527a16f9..0799fd3e4cf 100644 --- a/kernel/mutex-debug.h +++ b/kernel/mutex-debug.h @@ -29,7 +29,7 @@ extern void debug_mutex_init(struct mutex *lock, const char *name, static inline void mutex_set_owner(struct mutex *lock) { - lock->owner = current_thread_info(); + lock->owner = current; } static inline void mutex_clear_owner(struct mutex *lock) diff --git a/kernel/mutex.c b/kernel/mutex.c index c4195fa9890..d607ed5dd44 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -131,14 +131,14 @@ EXPORT_SYMBOL(mutex_unlock); */ static inline int __sched __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, - unsigned long ip) + struct lockdep_map *nest_lock, unsigned long ip) { struct task_struct *task = current; struct mutex_waiter waiter; unsigned long flags; preempt_disable(); - mutex_acquire(&lock->dep_map, subclass, 0, ip); + mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER /* @@ -160,14 +160,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, */ for (;;) { - struct thread_info *owner; - - /* - * If we own the BKL, then don't spin. The owner of - * the mutex might be waiting on us to release the BKL. - */ - if (unlikely(current->lock_depth >= 0)) - break; + struct task_struct *owner; /* * If there's an owner, wait for it to either @@ -276,16 +269,25 @@ void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, _RET_IP_); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_); } EXPORT_SYMBOL_GPL(mutex_lock_nested); +void __sched +_mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) +{ + might_sleep(); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, nest, _RET_IP_); +} + +EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock); + int __sched mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); - return __mutex_lock_common(lock, TASK_KILLABLE, subclass, _RET_IP_); + return __mutex_lock_common(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_); } EXPORT_SYMBOL_GPL(mutex_lock_killable_nested); @@ -294,7 +296,7 @@ mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, - subclass, _RET_IP_); + subclass, NULL, _RET_IP_); } EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); @@ -400,7 +402,7 @@ __mutex_lock_slowpath(atomic_t *lock_count) { struct mutex *lock = container_of(lock_count, struct mutex, count); - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, _RET_IP_); + __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_); } static noinline int __sched @@ -408,7 +410,7 @@ __mutex_lock_killable_slowpath(atomic_t *lock_count) { struct mutex *lock = container_of(lock_count, struct mutex, count); - return __mutex_lock_common(lock, TASK_KILLABLE, 0, _RET_IP_); + return __mutex_lock_common(lock, TASK_KILLABLE, 0, NULL, _RET_IP_); } static noinline int __sched @@ -416,7 +418,7 @@ __mutex_lock_interruptible_slowpath(atomic_t *lock_count) { struct mutex *lock = container_of(lock_count, struct mutex, count); - return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, _RET_IP_); + return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_); } #endif diff --git a/kernel/mutex.h b/kernel/mutex.h index 67578ca48f9..4115fbf83b1 100644 --- a/kernel/mutex.h +++ b/kernel/mutex.h @@ -19,7 +19,7 @@ #ifdef CONFIG_SMP static inline void mutex_set_owner(struct mutex *lock) { - lock->owner = current_thread_info(); + lock->owner = current; } static inline void mutex_clear_owner(struct mutex *lock) diff --git a/kernel/notifier.c b/kernel/notifier.c index 2488ba7eb56..8d7b435806c 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -525,37 +525,6 @@ void srcu_init_notifier_head(struct srcu_notifier_head *nh) } EXPORT_SYMBOL_GPL(srcu_init_notifier_head); -/** - * register_reboot_notifier - Register function to be called at reboot time - * @nb: Info about notifier function to be called - * - * Registers a function with the list of functions - * to be called at reboot time. - * - * Currently always returns zero, as blocking_notifier_chain_register() - * always returns zero. - */ -int register_reboot_notifier(struct notifier_block *nb) -{ - return blocking_notifier_chain_register(&reboot_notifier_list, nb); -} -EXPORT_SYMBOL(register_reboot_notifier); - -/** - * unregister_reboot_notifier - Unregister previously registered reboot notifier - * @nb: Hook to be unregistered - * - * Unregisters a previously registered reboot - * notifier function. - * - * Returns zero on success, or %-ENOENT on failure. - */ -int unregister_reboot_notifier(struct notifier_block *nb) -{ - return blocking_notifier_chain_unregister(&reboot_notifier_list, nb); -} -EXPORT_SYMBOL(unregister_reboot_notifier); - static ATOMIC_NOTIFIER_HEAD(die_chain); int notrace __kprobes notify_die(enum die_val val, const char *str, diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c deleted file mode 100644 index 2c98ad94ba0..00000000000 --- a/kernel/ns_cgroup.c +++ /dev/null @@ -1,118 +0,0 @@ -/* - * ns_cgroup.c - namespace cgroup subsystem - * - * Copyright 2006, 2007 IBM Corp - */ - -#include <linux/module.h> -#include <linux/cgroup.h> -#include <linux/fs.h> -#include <linux/proc_fs.h> -#include <linux/slab.h> -#include <linux/nsproxy.h> - -struct ns_cgroup { - struct cgroup_subsys_state css; -}; - -struct cgroup_subsys ns_subsys; - -static inline struct ns_cgroup *cgroup_to_ns( - struct cgroup *cgroup) -{ - return container_of(cgroup_subsys_state(cgroup, ns_subsys_id), - struct ns_cgroup, css); -} - -int ns_cgroup_clone(struct task_struct *task, struct pid *pid) -{ - char name[PROC_NUMBUF]; - - snprintf(name, PROC_NUMBUF, "%d", pid_vnr(pid)); - return cgroup_clone(task, &ns_subsys, name); -} - -/* - * Rules: - * 1. you can only enter a cgroup which is a descendant of your current - * cgroup - * 2. you can only place another process into a cgroup if - * a. you have CAP_SYS_ADMIN - * b. your cgroup is an ancestor of task's destination cgroup - * (hence either you are in the same cgroup as task, or in an - * ancestor cgroup thereof) - */ -static int ns_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup, - struct task_struct *task, bool threadgroup) -{ - if (current != task) { - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - if (!cgroup_is_descendant(new_cgroup, current)) - return -EPERM; - } - - if (!cgroup_is_descendant(new_cgroup, task)) - return -EPERM; - - if (threadgroup) { - struct task_struct *c; - rcu_read_lock(); - list_for_each_entry_rcu(c, &task->thread_group, thread_group) { - if (!cgroup_is_descendant(new_cgroup, c)) { - rcu_read_unlock(); - return -EPERM; - } - } - rcu_read_unlock(); - } - - return 0; -} - -/* - * Rules: you can only create a cgroup if - * 1. you are capable(CAP_SYS_ADMIN) - * 2. the target cgroup is a descendant of your own cgroup - */ -static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss, - struct cgroup *cgroup) -{ - struct ns_cgroup *ns_cgroup; - - if (!capable(CAP_SYS_ADMIN)) - return ERR_PTR(-EPERM); - if (!cgroup_is_descendant(cgroup, current)) - return ERR_PTR(-EPERM); - if (test_bit(CGRP_CLONE_CHILDREN, &cgroup->flags)) { - printk("ns_cgroup can't be created with parent " - "'clone_children' set.\n"); - return ERR_PTR(-EINVAL); - } - - printk_once("ns_cgroup deprecated: consider using the " - "'clone_children' flag without the ns_cgroup.\n"); - - ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL); - if (!ns_cgroup) - return ERR_PTR(-ENOMEM); - return &ns_cgroup->css; -} - -static void ns_destroy(struct cgroup_subsys *ss, - struct cgroup *cgroup) -{ - struct ns_cgroup *ns_cgroup; - - ns_cgroup = cgroup_to_ns(cgroup); - kfree(ns_cgroup); -} - -struct cgroup_subsys ns_subsys = { - .name = "ns", - .can_attach = ns_can_attach, - .create = ns_create, - .destroy = ns_destroy, - .subsys_id = ns_subsys_id, -}; diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index a05d191ffdd..9aeab4b98c6 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -22,6 +22,9 @@ #include <linux/pid_namespace.h> #include <net/net_namespace.h> #include <linux/ipc_namespace.h> +#include <linux/proc_fs.h> +#include <linux/file.h> +#include <linux/syscalls.h> static struct kmem_cache *nsproxy_cachep; @@ -198,10 +201,6 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags, goto out; } - err = ns_cgroup_clone(current, task_pid(current)); - if (err) - put_nsproxy(*new_nsp); - out: return err; } @@ -233,10 +232,47 @@ void exit_task_namespaces(struct task_struct *p) switch_task_namespaces(p, NULL); } -static int __init nsproxy_cache_init(void) +SYSCALL_DEFINE2(setns, int, fd, int, nstype) +{ + const struct proc_ns_operations *ops; + struct task_struct *tsk = current; + struct nsproxy *new_nsproxy; + struct proc_inode *ei; + struct file *file; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + file = proc_ns_fget(fd); + if (IS_ERR(file)) + return PTR_ERR(file); + + err = -EINVAL; + ei = PROC_I(file->f_dentry->d_inode); + ops = ei->ns_ops; + if (nstype && (ops->type != nstype)) + goto out; + + new_nsproxy = create_new_namespaces(0, tsk, tsk->fs); + if (IS_ERR(new_nsproxy)) { + err = PTR_ERR(new_nsproxy); + goto out; + } + + err = ops->install(new_nsproxy, ei->ns); + if (err) { + free_nsproxy(new_nsproxy); + goto out; + } + switch_task_namespaces(tsk, new_nsproxy); +out: + fput(file); + return err; +} + +int __init nsproxy_cache_init(void) { nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC); return 0; } - -module_init(nsproxy_cache_init); diff --git a/kernel/panic.c b/kernel/panic.c index 69231670eb9..d7bb6974efb 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -119,6 +119,8 @@ NORET_TYPE void panic(const char * fmt, ...) } mdelay(PANIC_TIMER_STEP); } + } + if (panic_timeout != 0) { /* * This will not be a clean reboot, with everything * shutting down. But if there is a chance of diff --git a/kernel/params.c b/kernel/params.c index 7ab388a48a2..22df3e0d142 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -225,8 +225,8 @@ int parse_args(const char *name, int ret; \ \ ret = strtolfn(val, 0, &l); \ - if (ret == -EINVAL || ((type)l != l)) \ - return -EINVAL; \ + if (ret < 0 || ((type)l != l)) \ + return ret < 0 ? ret : -EINVAL; \ *((type *)kp->arg) = l; \ return 0; \ } \ @@ -297,21 +297,15 @@ EXPORT_SYMBOL(param_ops_charp); int param_set_bool(const char *val, const struct kernel_param *kp) { bool v; + int ret; /* No equals means "set"... */ if (!val) val = "1"; /* One of =[yYnN01] */ - switch (val[0]) { - case 'y': case 'Y': case '1': - v = true; - break; - case 'n': case 'N': case '0': - v = false; - break; - default: - return -EINVAL; - } + ret = strtobool(val, &v); + if (ret) + return ret; if (kp->flags & KPARAM_ISBOOL) *(bool *)kp->arg = v; @@ -517,7 +511,7 @@ struct module_param_attrs #define to_param_attr(n) container_of(n, struct param_attribute, mattr) static ssize_t param_attr_show(struct module_attribute *mattr, - struct module *mod, char *buf) + struct module_kobject *mk, char *buf) { int count; struct param_attribute *attribute = to_param_attr(mattr); @@ -537,7 +531,7 @@ static ssize_t param_attr_show(struct module_attribute *mattr, /* sysfs always hands a nul-terminated string in buf. We rely on that. */ static ssize_t param_attr_store(struct module_attribute *mattr, - struct module *owner, + struct module_kobject *km, const char *buf, size_t len) { int err; @@ -736,6 +730,10 @@ static struct module_kobject * __init locate_module_kobject(const char *name) mk->kobj.kset = module_kset; err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, "%s", name); +#ifdef CONFIG_MODULES + if (!err) + err = sysfs_create_file(&mk->kobj, &module_uevent.attr); +#endif if (err) { kobject_put(&mk->kobj); printk(KERN_ERR @@ -813,7 +811,7 @@ static void __init param_sysfs_builtin(void) } ssize_t __modver_version_show(struct module_attribute *mattr, - struct module *mod, char *buf) + struct module_kobject *mk, char *buf) { struct module_version_attribute *vattr = container_of(mattr, struct module_version_attribute, mattr); @@ -821,15 +819,18 @@ ssize_t __modver_version_show(struct module_attribute *mattr, return sprintf(buf, "%s\n", vattr->version); } -extern struct module_version_attribute __start___modver[], __stop___modver[]; +extern const struct module_version_attribute *__start___modver[]; +extern const struct module_version_attribute *__stop___modver[]; static void __init version_sysfs_builtin(void) { - const struct module_version_attribute *vattr; + const struct module_version_attribute **p; struct module_kobject *mk; int err; - for (vattr = __start___modver; vattr < __stop___modver; vattr++) { + for (p = __start___modver; p < __stop___modver; p++) { + const struct module_version_attribute *vattr = *p; + mk = locate_module_kobject(vattr->module_name); if (mk) { err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr); @@ -855,7 +856,7 @@ static ssize_t module_attr_show(struct kobject *kobj, if (!attribute->show) return -EIO; - ret = attribute->show(attribute, mk->mod, buf); + ret = attribute->show(attribute, mk, buf); return ret; } @@ -874,7 +875,7 @@ static ssize_t module_attr_store(struct kobject *kobj, if (!attribute->store) return -EIO; - ret = attribute->store(attribute, mk->mod, buf, len); + ret = attribute->store(attribute, mk, buf, len); return ret; } diff --git a/kernel/pid.c b/kernel/pid.c index 57a8346a270..e432057f3b2 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -405,7 +405,6 @@ struct task_struct *pid_task(struct pid *pid, enum pid_type type) if (pid) { struct hlist_node *first; first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]), - rcu_read_lock_held() || lockdep_tasklist_lock_is_held()); if (first) result = hlist_entry(first, struct task_struct, pids[(type)].node); diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c index 0da058bff8e..37f05d0f079 100644 --- a/kernel/pm_qos_params.c +++ b/kernel/pm_qos_params.c @@ -40,6 +40,7 @@ #include <linux/string.h> #include <linux/platform_device.h> #include <linux/init.h> +#include <linux/kernel.h> #include <linux/uaccess.h> @@ -53,11 +54,17 @@ enum pm_qos_type { PM_QOS_MIN /* return the smallest value */ }; +/* + * Note: The lockless read path depends on the CPU accessing + * target_value atomically. Atomic access is only guaranteed on all CPU + * types linux supports for 32 bit quantites + */ struct pm_qos_object { struct plist_head requests; struct blocking_notifier_head *notifiers; struct miscdevice pm_qos_power_miscdev; char *name; + s32 target_value; /* Do not change to 64 bit */ s32 default_value; enum pm_qos_type type; }; @@ -67,29 +74,32 @@ static DEFINE_SPINLOCK(pm_qos_lock); static struct pm_qos_object null_pm_qos; static BLOCKING_NOTIFIER_HEAD(cpu_dma_lat_notifier); static struct pm_qos_object cpu_dma_pm_qos = { - .requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests, pm_qos_lock), + .requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests), .notifiers = &cpu_dma_lat_notifier, .name = "cpu_dma_latency", - .default_value = 2000 * USEC_PER_SEC, + .target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE, + .default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE, .type = PM_QOS_MIN, }; static BLOCKING_NOTIFIER_HEAD(network_lat_notifier); static struct pm_qos_object network_lat_pm_qos = { - .requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests, pm_qos_lock), + .requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests), .notifiers = &network_lat_notifier, .name = "network_latency", - .default_value = 2000 * USEC_PER_SEC, + .target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE, + .default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE, .type = PM_QOS_MIN }; static BLOCKING_NOTIFIER_HEAD(network_throughput_notifier); static struct pm_qos_object network_throughput_pm_qos = { - .requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests, pm_qos_lock), + .requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests), .notifiers = &network_throughput_notifier, .name = "network_throughput", - .default_value = 0, + .target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE, + .default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE, .type = PM_QOS_MAX, }; @@ -135,6 +145,16 @@ static inline int pm_qos_get_value(struct pm_qos_object *o) } } +static inline s32 pm_qos_read_value(struct pm_qos_object *o) +{ + return o->target_value; +} + +static inline void pm_qos_set_value(struct pm_qos_object *o, s32 value) +{ + o->target_value = value; +} + static void update_target(struct pm_qos_object *o, struct plist_node *node, int del, int value) { @@ -159,6 +179,7 @@ static void update_target(struct pm_qos_object *o, struct plist_node *node, plist_add(node, &o->requests); } curr_value = pm_qos_get_value(o); + pm_qos_set_value(o, curr_value); spin_unlock_irqrestore(&pm_qos_lock, flags); if (prev_value != curr_value) @@ -193,18 +214,11 @@ static int find_pm_qos_object_by_minor(int minor) * pm_qos_request - returns current system wide qos expectation * @pm_qos_class: identification of which qos value is requested * - * This function returns the current target value in an atomic manner. + * This function returns the current target value. */ int pm_qos_request(int pm_qos_class) { - unsigned long flags; - int value; - - spin_lock_irqsave(&pm_qos_lock, flags); - value = pm_qos_get_value(pm_qos_array[pm_qos_class]); - spin_unlock_irqrestore(&pm_qos_lock, flags); - - return value; + return pm_qos_read_value(pm_qos_array[pm_qos_class]); } EXPORT_SYMBOL_GPL(pm_qos_request); @@ -385,7 +399,7 @@ static ssize_t pm_qos_power_read(struct file *filp, char __user *buf, s32 value; unsigned long flags; struct pm_qos_object *o; - struct pm_qos_request_list *pm_qos_req = filp->private_data;; + struct pm_qos_request_list *pm_qos_req = filp->private_data; if (!pm_qos_req) return -EINVAL; @@ -404,24 +418,36 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, size_t count, loff_t *f_pos) { s32 value; - int x; - char ascii_value[11]; struct pm_qos_request_list *pm_qos_req; if (count == sizeof(s32)) { if (copy_from_user(&value, buf, sizeof(s32))) return -EFAULT; - } else if (count == 11) { /* len('0x12345678/0') */ - if (copy_from_user(ascii_value, buf, 11)) + } else if (count <= 11) { /* ASCII perhaps? */ + char ascii_value[11]; + unsigned long int ulval; + int ret; + + if (copy_from_user(ascii_value, buf, count)) return -EFAULT; - if (strlen(ascii_value) != 10) - return -EINVAL; - x = sscanf(ascii_value, "%x", &value); - if (x != 1) + + if (count > 10) { + if (ascii_value[10] == '\n') + ascii_value[10] = '\0'; + else + return -EINVAL; + } else { + ascii_value[count] = '\0'; + } + ret = strict_strtoul(ascii_value, 16, &ulval); + if (ret) { + pr_debug("%s, 0x%lx, 0x%x\n", ascii_value, ulval, ret); return -EINVAL; - pr_debug("%s, %d, 0x%x\n", ascii_value, x, value); - } else + } + value = (s32)lower_32_bits(ulval); + } else { return -EINVAL; + } pm_qos_req = filp->private_data; pm_qos_update_request(pm_qos_req, value); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 0791b13df7b..58f405b581e 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -1514,7 +1514,7 @@ static int posix_cpu_nsleep(const clockid_t which_clock, int flags, return -EFAULT; restart_block->fn = posix_cpu_nsleep_restart; - restart_block->nanosleep.index = which_clock; + restart_block->nanosleep.clockid = which_clock; restart_block->nanosleep.rmtp = rmtp; restart_block->nanosleep.expires = timespec_to_ns(rqtp); } @@ -1523,7 +1523,7 @@ static int posix_cpu_nsleep(const clockid_t which_clock, int flags, static long posix_cpu_nsleep_restart(struct restart_block *restart_block) { - clockid_t which_clock = restart_block->nanosleep.index; + clockid_t which_clock = restart_block->nanosleep.clockid; struct timespec t; struct itimerspec it; int error; diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index e5498d7405c..4556182527f 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -491,6 +491,13 @@ static struct k_itimer * alloc_posix_timer(void) return tmr; } +static void k_itimer_rcu_free(struct rcu_head *head) +{ + struct k_itimer *tmr = container_of(head, struct k_itimer, it.rcu); + + kmem_cache_free(posix_timers_cache, tmr); +} + #define IT_ID_SET 1 #define IT_ID_NOT_SET 0 static void release_posix_timer(struct k_itimer *tmr, int it_id_set) @@ -503,7 +510,7 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set) } put_pid(tmr->it_pid); sigqueue_free(tmr->sigq); - kmem_cache_free(posix_timers_cache, tmr); + call_rcu(&tmr->it.rcu, k_itimer_rcu_free); } static struct k_clock *clockid_to_kclock(const clockid_t id) @@ -631,22 +638,18 @@ out: static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) { struct k_itimer *timr; - /* - * Watch out here. We do a irqsave on the idr_lock and pass the - * flags part over to the timer lock. Must not let interrupts in - * while we are moving the lock. - */ - spin_lock_irqsave(&idr_lock, *flags); + + rcu_read_lock(); timr = idr_find(&posix_timers_id, (int)timer_id); if (timr) { - spin_lock(&timr->it_lock); + spin_lock_irqsave(&timr->it_lock, *flags); if (timr->it_signal == current->signal) { - spin_unlock(&idr_lock); + rcu_read_unlock(); return timr; } - spin_unlock(&timr->it_lock); + spin_unlock_irqrestore(&timr->it_lock, *flags); } - spin_unlock_irqrestore(&idr_lock, *flags); + rcu_read_unlock(); return NULL; } @@ -1056,7 +1059,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, */ long clock_nanosleep_restart(struct restart_block *restart_block) { - clockid_t which_clock = restart_block->nanosleep.index; + clockid_t which_clock = restart_block->nanosleep.clockid; struct k_clock *kc = clockid_to_kclock(which_clock); if (WARN_ON_ONCE(!kc || !kc->nsleep_restart)) diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 6de9a8fc341..b1914cb9095 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -125,12 +125,6 @@ config PM_DEBUG code. This is helpful when debugging and reporting PM bugs, like suspend support. -config PM_VERBOSE - bool "Verbose Power Management debugging" - depends on PM_DEBUG - ---help--- - This option enables verbose messages from the Power Management code. - config PM_ADVANCED_DEBUG bool "Extra PM attributes in sysfs for low-level debugging/testing" depends on PM_DEBUG @@ -199,8 +193,8 @@ config APM_EMULATION notification of APM "events" (e.g. battery status change). In order to use APM, you will need supporting software. For location - and more information, read <file:Documentation/power/pm.txt> and the - Battery Powered Linux mini-HOWTO, available from + and more information, read <file:Documentation/power/apm-acpi.txt> + and the Battery Powered Linux mini-HOWTO, available from <http://www.tldp.org/docs.html#howto>. This driver does not spin down disk drives (see the hdparm(8) @@ -229,3 +223,11 @@ config PM_OPP representing individual voltage domains and provides SOC implementations a ready to use framework to manage OPPs. For more information, read <file:Documentation/power/opp.txt> + +config PM_CLK + def_bool y + depends on PM && HAVE_CLK + +config PM_GENERIC_DOMAINS + bool + depends on PM diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index aeabd26e334..8f7b1db1ece 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -25,7 +25,6 @@ #include <linux/gfp.h> #include <linux/syscore_ops.h> #include <scsi/scsi_scan.h> -#include <asm/suspend.h> #include "power.h" @@ -55,10 +54,9 @@ static int hibernation_mode = HIBERNATION_SHUTDOWN; static const struct platform_hibernation_ops *hibernation_ops; /** - * hibernation_set_ops - set the global hibernate operations - * @ops: the hibernation operations to use in subsequent hibernation transitions + * hibernation_set_ops - Set the global hibernate operations. + * @ops: Hibernation operations to use in subsequent hibernation transitions. */ - void hibernation_set_ops(const struct platform_hibernation_ops *ops) { if (ops && !(ops->begin && ops->end && ops->pre_snapshot @@ -115,10 +113,9 @@ static int hibernation_test(int level) { return 0; } #endif /* !CONFIG_PM_DEBUG */ /** - * platform_begin - tell the platform driver that we're starting - * hibernation + * platform_begin - Call platform to start hibernation. + * @platform_mode: Whether or not to use the platform driver. */ - static int platform_begin(int platform_mode) { return (platform_mode && hibernation_ops) ? @@ -126,10 +123,9 @@ static int platform_begin(int platform_mode) } /** - * platform_end - tell the platform driver that we've entered the - * working state + * platform_end - Call platform to finish transition to the working state. + * @platform_mode: Whether or not to use the platform driver. */ - static void platform_end(int platform_mode) { if (platform_mode && hibernation_ops) @@ -137,8 +133,11 @@ static void platform_end(int platform_mode) } /** - * platform_pre_snapshot - prepare the machine for hibernation using the - * platform driver if so configured and return an error code if it fails + * platform_pre_snapshot - Call platform to prepare the machine for hibernation. + * @platform_mode: Whether or not to use the platform driver. + * + * Use the platform driver to prepare the system for creating a hibernate image, + * if so configured, and return an error code if that fails. */ static int platform_pre_snapshot(int platform_mode) @@ -148,10 +147,14 @@ static int platform_pre_snapshot(int platform_mode) } /** - * platform_leave - prepare the machine for switching to the normal mode - * of operation using the platform driver (called with interrupts disabled) + * platform_leave - Call platform to prepare a transition to the working state. + * @platform_mode: Whether or not to use the platform driver. + * + * Use the platform driver prepare to prepare the machine for switching to the + * normal mode of operation. + * + * This routine is called on one CPU with interrupts disabled. */ - static void platform_leave(int platform_mode) { if (platform_mode && hibernation_ops) @@ -159,10 +162,14 @@ static void platform_leave(int platform_mode) } /** - * platform_finish - switch the machine to the normal mode of operation - * using the platform driver (must be called after platform_prepare()) + * platform_finish - Call platform to switch the system to the working state. + * @platform_mode: Whether or not to use the platform driver. + * + * Use the platform driver to switch the machine to the normal mode of + * operation. + * + * This routine must be called after platform_prepare(). */ - static void platform_finish(int platform_mode) { if (platform_mode && hibernation_ops) @@ -170,11 +177,15 @@ static void platform_finish(int platform_mode) } /** - * platform_pre_restore - prepare the platform for the restoration from a - * hibernation image. If the restore fails after this function has been - * called, platform_restore_cleanup() must be called. + * platform_pre_restore - Prepare for hibernate image restoration. + * @platform_mode: Whether or not to use the platform driver. + * + * Use the platform driver to prepare the system for resume from a hibernation + * image. + * + * If the restore fails after this function has been called, + * platform_restore_cleanup() must be called. */ - static int platform_pre_restore(int platform_mode) { return (platform_mode && hibernation_ops) ? @@ -182,12 +193,16 @@ static int platform_pre_restore(int platform_mode) } /** - * platform_restore_cleanup - switch the platform to the normal mode of - * operation after a failing restore. If platform_pre_restore() has been - * called before the failing restore, this function must be called too, - * regardless of the result of platform_pre_restore(). + * platform_restore_cleanup - Switch to the working state after failing restore. + * @platform_mode: Whether or not to use the platform driver. + * + * Use the platform driver to switch the system to the normal mode of operation + * after a failing restore. + * + * If platform_pre_restore() has been called before the failing restore, this + * function must be called too, regardless of the result of + * platform_pre_restore(). */ - static void platform_restore_cleanup(int platform_mode) { if (platform_mode && hibernation_ops) @@ -195,10 +210,9 @@ static void platform_restore_cleanup(int platform_mode) } /** - * platform_recover - recover the platform from a failure to suspend - * devices. + * platform_recover - Recover from a failure to suspend devices. + * @platform_mode: Whether or not to use the platform driver. */ - static void platform_recover(int platform_mode) { if (platform_mode && hibernation_ops && hibernation_ops->recover) @@ -206,13 +220,12 @@ static void platform_recover(int platform_mode) } /** - * swsusp_show_speed - print the time elapsed between two events. - * @start: Starting event. - * @stop: Final event. - * @nr_pages - number of pages processed between @start and @stop - * @msg - introductory message to print + * swsusp_show_speed - Print time elapsed between two events during hibernation. + * @start: Starting event. + * @stop: Final event. + * @nr_pages: Number of memory pages processed between @start and @stop. + * @msg: Additional diagnostic message to print. */ - void swsusp_show_speed(struct timeval *start, struct timeval *stop, unsigned nr_pages, char *msg) { @@ -235,25 +248,18 @@ void swsusp_show_speed(struct timeval *start, struct timeval *stop, } /** - * create_image - freeze devices that need to be frozen with interrupts - * off, create the hibernation image and thaw those devices. Control - * reappears in this routine after a restore. + * create_image - Create a hibernation image. + * @platform_mode: Whether or not to use the platform driver. + * + * Execute device drivers' .freeze_noirq() callbacks, create a hibernation image + * and execute the drivers' .thaw_noirq() callbacks. + * + * Control reappears in this routine after the subsequent restore. */ - static int create_image(int platform_mode) { int error; - error = arch_prepare_suspend(); - if (error) - return error; - - /* At this point, dpm_suspend_start() has been called, but *not* - * dpm_suspend_noirq(). We *must* call dpm_suspend_noirq() now. - * Otherwise, drivers for some devices (e.g. interrupt controllers) - * become desynchronized with the actual state of the hardware - * at resume time, and evil weirdness ensues. - */ error = dpm_suspend_noirq(PMSG_FREEZE); if (error) { printk(KERN_ERR "PM: Some devices failed to power down, " @@ -272,9 +278,7 @@ static int create_image(int platform_mode) local_irq_disable(); - error = sysdev_suspend(PMSG_FREEZE); - if (!error) - error = syscore_suspend(); + error = syscore_suspend(); if (error) { printk(KERN_ERR "PM: Some system devices failed to power down, " "aborting hibernation\n"); @@ -299,10 +303,6 @@ static int create_image(int platform_mode) Power_up: syscore_resume(); - sysdev_resume(); - /* NOTE: dpm_resume_noirq() is just a resume() for devices - * that suspended with irqs off ... no overall powerup. - */ Enable_irqs: local_irq_enable(); @@ -320,30 +320,32 @@ static int create_image(int platform_mode) } /** - * hibernation_snapshot - quiesce devices and create the hibernation - * snapshot image. - * @platform_mode - if set, use the platform driver, if available, to - * prepare the platform firmware for the power transition. + * hibernation_snapshot - Quiesce devices and create a hibernation image. + * @platform_mode: If set, use platform driver to prepare for the transition. * - * Must be called with pm_mutex held + * This routine must be called with pm_mutex held. */ - int hibernation_snapshot(int platform_mode) { + pm_message_t msg = PMSG_RECOVER; int error; error = platform_begin(platform_mode); if (error) goto Close; + error = dpm_prepare(PMSG_FREEZE); + if (error) + goto Complete_devices; + /* Preallocate image memory before shutting down devices. */ error = hibernate_preallocate_memory(); if (error) - goto Close; + goto Complete_devices; suspend_console(); pm_restrict_gfp_mask(); - error = dpm_suspend_start(PMSG_FREEZE); + error = dpm_suspend(PMSG_FREEZE); if (error) goto Recover_platform; @@ -361,13 +363,17 @@ int hibernation_snapshot(int platform_mode) if (error || !in_suspend) swsusp_free(); - dpm_resume_end(in_suspend ? - (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); + msg = in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE; + dpm_resume(msg); if (error || !in_suspend) pm_restore_gfp_mask(); resume_console(); + + Complete_devices: + dpm_complete(msg); + Close: platform_end(platform_mode); return error; @@ -378,13 +384,14 @@ int hibernation_snapshot(int platform_mode) } /** - * resume_target_kernel - prepare devices that need to be suspended with - * interrupts off, restore the contents of highmem that have not been - * restored yet from the image and run the low level code that will restore - * the remaining contents of memory and switch to the just restored target - * kernel. + * resume_target_kernel - Restore system state from a hibernation image. + * @platform_mode: Whether or not to use the platform driver. + * + * Execute device drivers' .freeze_noirq() callbacks, restore the contents of + * highmem that have not been restored yet from the image and run the low-level + * code that will restore the remaining contents of memory and switch to the + * just restored target kernel. */ - static int resume_target_kernel(bool platform_mode) { int error; @@ -406,37 +413,36 @@ static int resume_target_kernel(bool platform_mode) local_irq_disable(); - error = sysdev_suspend(PMSG_QUIESCE); - if (!error) - error = syscore_suspend(); + error = syscore_suspend(); if (error) goto Enable_irqs; - /* We'll ignore saved state, but this gets preempt count (etc) right */ save_processor_state(); error = restore_highmem(); if (!error) { error = swsusp_arch_resume(); /* * The code below is only ever reached in case of a failure. - * Otherwise execution continues at place where - * swsusp_arch_suspend() was called + * Otherwise, execution continues at the place where + * swsusp_arch_suspend() was called. */ BUG_ON(!error); - /* This call to restore_highmem() undos the previous one */ + /* + * This call to restore_highmem() reverts the changes made by + * the previous one. + */ restore_highmem(); } /* * The only reason why swsusp_arch_resume() can fail is memory being * very tight, so we have to free it as soon as we can to avoid - * subsequent failures + * subsequent failures. */ swsusp_free(); restore_processor_state(); touch_softlockup_watchdog(); syscore_resume(); - sysdev_resume(); Enable_irqs: local_irq_enable(); @@ -453,14 +459,12 @@ static int resume_target_kernel(bool platform_mode) } /** - * hibernation_restore - quiesce devices and restore the hibernation - * snapshot image. If successful, control returns in hibernation_snaphot() - * @platform_mode - if set, use the platform driver, if available, to - * prepare the platform firmware for the transition. + * hibernation_restore - Quiesce devices and restore from a hibernation image. + * @platform_mode: If set, use platform driver to prepare for the transition. * - * Must be called with pm_mutex held + * This routine must be called with pm_mutex held. If it is successful, control + * reappears in the restored target kernel in hibernation_snaphot(). */ - int hibernation_restore(int platform_mode) { int error; @@ -480,10 +484,8 @@ int hibernation_restore(int platform_mode) } /** - * hibernation_platform_enter - enter the hibernation state using the - * platform driver (if available) + * hibernation_platform_enter - Power off the system using the platform driver. */ - int hibernation_platform_enter(void) { int error; @@ -522,7 +524,6 @@ int hibernation_platform_enter(void) goto Platform_finish; local_irq_disable(); - sysdev_suspend(PMSG_HIBERNATE); syscore_suspend(); if (pm_wakeup_pending()) { error = -EAGAIN; @@ -535,7 +536,6 @@ int hibernation_platform_enter(void) Power_up: syscore_resume(); - sysdev_resume(); local_irq_enable(); enable_nonboot_cpus(); @@ -556,12 +556,12 @@ int hibernation_platform_enter(void) } /** - * power_down - Shut the machine down for hibernation. + * power_down - Shut the machine down for hibernation. * - * Use the platform driver, if configured so; otherwise try - * to power off or reboot. + * Use the platform driver, if configured, to put the system into the sleep + * state corresponding to hibernation, or try to power it off or reboot, + * depending on the value of hibernation_mode. */ - static void power_down(void) { switch (hibernation_mode) { @@ -598,9 +598,8 @@ static int prepare_processes(void) } /** - * hibernate - The granpappy of the built-in hibernation management + * hibernate - Carry out system hibernation, including saving the image. */ - int hibernate(void) { int error; @@ -678,17 +677,20 @@ int hibernate(void) /** - * software_resume - Resume from a saved image. + * software_resume - Resume from a saved hibernation image. + * + * This routine is called as a late initcall, when all devices have been + * discovered and initialized already. * - * Called as a late_initcall (so all devices are discovered and - * initialized), we call swsusp to see if we have a saved image or not. - * If so, we quiesce devices, the restore the saved image. We will - * return above (in hibernate() ) if everything goes well. - * Otherwise, we fail gracefully and return to the normally - * scheduled program. + * The image reading code is called to see if there is a hibernation image + * available for reading. If that is the case, devices are quiesced and the + * contents of memory is restored from the saved image. * + * If this is successful, control reappears in the restored target kernel in + * hibernation_snaphot() which returns to hibernate(). Otherwise, the routine + * attempts to recover gracefully and make the kernel return to the normal mode + * of operation. */ - static int software_resume(void) { int error; @@ -818,21 +820,17 @@ static const char * const hibernation_modes[] = { [HIBERNATION_TESTPROC] = "testproc", }; -/** - * disk - Control hibernation mode - * - * Suspend-to-disk can be handled in several ways. We have a few options - * for putting the system to sleep - using the platform driver (e.g. ACPI - * or other hibernation_ops), powering off the system or rebooting the - * system (for testing) as well as the two test modes. +/* + * /sys/power/disk - Control hibernation mode. * - * The system can support 'platform', and that is known a priori (and - * encoded by the presence of hibernation_ops). However, the user may - * choose 'shutdown' or 'reboot' as alternatives, as well as one fo the - * test modes, 'test' or 'testproc'. + * Hibernation can be handled in several ways. There are a few different ways + * to put the system into the sleep state: using the platform driver (e.g. ACPI + * or other hibernation_ops), powering it off or rebooting it (for testing + * mostly), or using one of the two available test modes. * - * show() will display what the mode is currently set to. - * store() will accept one of + * The sysfs file /sys/power/disk provides an interface for selecting the + * hibernation mode to use. Reading from this file causes the available modes + * to be printed. There are 5 modes that can be supported: * * 'platform' * 'shutdown' @@ -840,8 +838,14 @@ static const char * const hibernation_modes[] = { * 'test' * 'testproc' * - * It will only change to 'platform' if the system - * supports it (as determined by having hibernation_ops). + * If a platform hibernation driver is in use, 'platform' will be supported + * and will be used by default. Otherwise, 'shutdown' will be used by default. + * The selected option (i.e. the one corresponding to the current value of + * hibernation_mode) is enclosed by a square bracket. + * + * To select a given hibernation mode it is necessary to write the mode's + * string representation (as returned by reading from /sys/power/disk) back + * into /sys/power/disk. */ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr, @@ -874,7 +878,6 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr, return buf-start; } - static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t n) { @@ -976,10 +979,33 @@ static ssize_t image_size_store(struct kobject *kobj, struct kobj_attribute *att power_attr(image_size); +static ssize_t reserved_size_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%lu\n", reserved_size); +} + +static ssize_t reserved_size_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned long size; + + if (sscanf(buf, "%lu", &size) == 1) { + reserved_size = size; + return n; + } + + return -EINVAL; +} + +power_attr(reserved_size); + static struct attribute * g[] = { &disk_attr.attr, &resume_attr.attr, &image_size_attr.attr, + &reserved_size_attr.attr, NULL, }; diff --git a/kernel/power/main.c b/kernel/power/main.c index de9aef8742f..6c601f87196 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -37,8 +37,9 @@ EXPORT_SYMBOL_GPL(unregister_pm_notifier); int pm_notifier_call_chain(unsigned long val) { - return (blocking_notifier_call_chain(&pm_chain_head, val, NULL) - == NOTIFY_BAD) ? -EINVAL : 0; + int ret = blocking_notifier_call_chain(&pm_chain_head, val, NULL); + + return notifier_to_errno(ret); } /* If set, devices may be suspended and resumed asynchronously. */ @@ -337,6 +338,7 @@ static int __init pm_init(void) if (error) return error; hibernate_image_size_init(); + hibernate_reserved_size_init(); power_kobj = kobject_create_and_add("power", NULL); if (!power_kobj) return -ENOMEM; diff --git a/kernel/power/power.h b/kernel/power/power.h index 03634be55f6..9a00a0a2628 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -15,6 +15,7 @@ struct swsusp_info { #ifdef CONFIG_HIBERNATION /* kernel/power/snapshot.c */ +extern void __init hibernate_reserved_size_init(void); extern void __init hibernate_image_size_init(void); #ifdef CONFIG_ARCH_HIBERNATION_HEADER @@ -55,6 +56,7 @@ extern int hibernation_platform_enter(void); #else /* !CONFIG_HIBERNATION */ +static inline void hibernate_reserved_size_init(void) {} static inline void hibernate_image_size_init(void) {} #endif /* !CONFIG_HIBERNATION */ @@ -72,6 +74,8 @@ static struct kobj_attribute _name##_attr = { \ /* Preferred image size in bytes (default 500 MB) */ extern unsigned long image_size; +/* Size of memory reserved for drivers (default SPARE_PAGES x PAGE_SIZE) */ +extern unsigned long reserved_size; extern int in_suspend; extern dev_t swsusp_resume_device; extern sector_t swsusp_resume_block; diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index ca0aacc2487..06efa54f93d 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -41,16 +41,28 @@ static void swsusp_set_page_forbidden(struct page *); static void swsusp_unset_page_forbidden(struct page *); /* + * Number of bytes to reserve for memory allocations made by device drivers + * from their ->freeze() and ->freeze_noirq() callbacks so that they don't + * cause image creation to fail (tunable via /sys/power/reserved_size). + */ +unsigned long reserved_size; + +void __init hibernate_reserved_size_init(void) +{ + reserved_size = SPARE_PAGES * PAGE_SIZE; +} + +/* * Preferred image size in bytes (tunable via /sys/power/image_size). - * When it is set to N, the image creating code will do its best to - * ensure the image size will not exceed N bytes, but if that is - * impossible, it will try to create the smallest image possible. + * When it is set to N, swsusp will do its best to ensure the image + * size will not exceed N bytes, but if that is impossible, it will + * try to create the smallest image possible. */ unsigned long image_size; void __init hibernate_image_size_init(void) { - image_size = (totalram_pages / 3) * PAGE_SIZE; + image_size = ((totalram_pages * 2) / 5) * PAGE_SIZE; } /* List of PBEs needed for restoring the pages that were allocated before @@ -1199,7 +1211,11 @@ static void free_unnecessary_pages(void) to_free_highmem = alloc_highmem - save; } else { to_free_highmem = 0; - to_free_normal -= save - alloc_highmem; + save -= alloc_highmem; + if (to_free_normal > save) + to_free_normal -= save; + else + to_free_normal = 0; } memory_bm_position_reset(©_bm); @@ -1263,11 +1279,13 @@ static unsigned long minimum_image_size(unsigned long saveable) * frame in use. We also need a number of page frames to be free during * hibernation for allocations made while saving the image and for device * drivers, in case they need to allocate memory from their hibernation - * callbacks (these two numbers are given by PAGES_FOR_IO and SPARE_PAGES, - * respectively, both of which are rough estimates). To make this happen, we - * compute the total number of available page frames and allocate at least + * callbacks (these two numbers are given by PAGES_FOR_IO (which is a rough + * estimate) and reserverd_size divided by PAGE_SIZE (which is tunable through + * /sys/power/reserved_size, respectively). To make this happen, we compute the + * total number of available page frames and allocate at least * - * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2 + 2 * SPARE_PAGES + * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2 + * + 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE) * * of them, which corresponds to the maximum size of a hibernation image. * @@ -1322,7 +1340,8 @@ int hibernate_preallocate_memory(void) count -= totalreserve_pages; /* Compute the maximum number of saveable pages to leave in memory. */ - max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * SPARE_PAGES; + max_size = (count - (size + PAGES_FOR_IO)) / 2 + - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE); /* Compute the desired number of image pages specified by image_size. */ size = DIV_ROUND_UP(image_size, PAGE_SIZE); if (size > max_size) diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 2814c32aed5..b6b71ad2208 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -44,6 +44,7 @@ void suspend_set_ops(const struct platform_suspend_ops *ops) suspend_ops = ops; mutex_unlock(&pm_mutex); } +EXPORT_SYMBOL_GPL(suspend_set_ops); bool valid_state(suspend_state_t state) { @@ -65,6 +66,7 @@ int suspend_valid_only_mem(suspend_state_t state) { return state == PM_SUSPEND_MEM; } +EXPORT_SYMBOL_GPL(suspend_valid_only_mem); static int suspend_test(int level) { @@ -126,12 +128,13 @@ void __attribute__ ((weak)) arch_suspend_enable_irqs(void) } /** - * suspend_enter - enter the desired system sleep state. - * @state: state to enter + * suspend_enter - enter the desired system sleep state. + * @state: State to enter + * @wakeup: Returns information that suspend should not be entered again. * - * This function should be called after devices have been suspended. + * This function should be called after devices have been suspended. */ -static int suspend_enter(suspend_state_t state) +static int suspend_enter(suspend_state_t state, bool *wakeup) { int error; @@ -163,16 +166,14 @@ static int suspend_enter(suspend_state_t state) arch_suspend_disable_irqs(); BUG_ON(!irqs_disabled()); - error = sysdev_suspend(PMSG_SUSPEND); - if (!error) - error = syscore_suspend(); + error = syscore_suspend(); if (!error) { - if (!(suspend_test(TEST_CORE) || pm_wakeup_pending())) { + *wakeup = pm_wakeup_pending(); + if (!(suspend_test(TEST_CORE) || *wakeup)) { error = suspend_ops->enter(state); events_check_enabled = false; } syscore_resume(); - sysdev_resume(); } arch_suspend_enable_irqs(); @@ -202,6 +203,7 @@ static int suspend_enter(suspend_state_t state) int suspend_devices_and_enter(suspend_state_t state) { int error; + bool wakeup = false; if (!suspend_ops) return -ENOSYS; @@ -213,7 +215,6 @@ int suspend_devices_and_enter(suspend_state_t state) goto Close; } suspend_console(); - pm_restrict_gfp_mask(); suspend_test_start(); error = dpm_suspend_start(PMSG_SUSPEND); if (error) { @@ -224,13 +225,15 @@ int suspend_devices_and_enter(suspend_state_t state) if (suspend_test(TEST_DEVICES)) goto Recover_platform; - suspend_enter(state); + do { + error = suspend_enter(state, &wakeup); + } while (!error && !wakeup + && suspend_ops->suspend_again && suspend_ops->suspend_again()); Resume_devices: suspend_test_start(); dpm_resume_end(PMSG_RESUME); suspend_test_finish("resume devices"); - pm_restore_gfp_mask(); resume_console(); Close: if (suspend_ops->end) @@ -291,7 +294,9 @@ int enter_state(suspend_state_t state) goto Finish; pr_debug("PM: Entering %s sleep\n", pm_states[state]); + pm_restrict_gfp_mask(); error = suspend_devices_and_enter(state); + pm_restore_gfp_mask(); Finish: pr_debug("PM: Finishing wakeup.\n"); diff --git a/kernel/power/user.c b/kernel/power/user.c index c36c3b9e8a8..42ddbc6f0de 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -113,8 +113,10 @@ static int snapshot_open(struct inode *inode, struct file *filp) if (error) pm_notifier_call_chain(PM_POST_RESTORE); } - if (error) + if (error) { + free_basic_memory_bitmaps(); atomic_inc(&snapshot_device_available); + } data->frozen = 0; data->ready = 0; data->platform_support = 0; @@ -135,8 +137,10 @@ static int snapshot_release(struct inode *inode, struct file *filp) free_basic_memory_bitmaps(); data = filp->private_data; free_all_swap_pages(data->swap); - if (data->frozen) + if (data->frozen) { + pm_restore_gfp_mask(); thaw_processes(); + } pm_notifier_call_chain(data->mode == O_RDONLY ? PM_POST_HIBERNATION : PM_POST_RESTORE); atomic_inc(&snapshot_device_available); @@ -379,6 +383,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, * PM_HIBERNATION_PREPARE */ error = suspend_devices_and_enter(PM_SUSPEND_MEM); + data->ready = 0; break; case SNAPSHOT_PLATFORM_SUPPORT: diff --git a/kernel/printk.c b/kernel/printk.c index da8ca817eae..37dff3429ad 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -31,6 +31,7 @@ #include <linux/smp.h> #include <linux/security.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/syscalls.h> #include <linux/kexec.h> #include <linux/kdb.h> @@ -167,46 +168,74 @@ void log_buf_kexec_setup(void) } #endif +/* requested log_buf_len from kernel cmdline */ +static unsigned long __initdata new_log_buf_len; + +/* save requested log_buf_len since it's too early to process it */ static int __init log_buf_len_setup(char *str) { unsigned size = memparse(str, &str); - unsigned long flags; if (size) size = roundup_pow_of_two(size); - if (size > log_buf_len) { - unsigned start, dest_idx, offset; - char *new_log_buf; + if (size > log_buf_len) + new_log_buf_len = size; - new_log_buf = alloc_bootmem(size); - if (!new_log_buf) { - printk(KERN_WARNING "log_buf_len: allocation failed\n"); - goto out; - } + return 0; +} +early_param("log_buf_len", log_buf_len_setup); - spin_lock_irqsave(&logbuf_lock, flags); - log_buf_len = size; - log_buf = new_log_buf; - - offset = start = min(con_start, log_start); - dest_idx = 0; - while (start != log_end) { - log_buf[dest_idx] = __log_buf[start & (__LOG_BUF_LEN - 1)]; - start++; - dest_idx++; - } - log_start -= offset; - con_start -= offset; - log_end -= offset; - spin_unlock_irqrestore(&logbuf_lock, flags); +void __init setup_log_buf(int early) +{ + unsigned long flags; + unsigned start, dest_idx, offset; + char *new_log_buf; + int free; + + if (!new_log_buf_len) + return; + + if (early) { + unsigned long mem; - printk(KERN_NOTICE "log_buf_len: %d\n", log_buf_len); + mem = memblock_alloc(new_log_buf_len, PAGE_SIZE); + if (mem == MEMBLOCK_ERROR) + return; + new_log_buf = __va(mem); + } else { + new_log_buf = alloc_bootmem_nopanic(new_log_buf_len); } -out: - return 1; -} -__setup("log_buf_len=", log_buf_len_setup); + if (unlikely(!new_log_buf)) { + pr_err("log_buf_len: %ld bytes not available\n", + new_log_buf_len); + return; + } + + spin_lock_irqsave(&logbuf_lock, flags); + log_buf_len = new_log_buf_len; + log_buf = new_log_buf; + new_log_buf_len = 0; + free = __LOG_BUF_LEN - log_end; + + offset = start = min(con_start, log_start); + dest_idx = 0; + while (start != log_end) { + unsigned log_idx_mask = start & (__LOG_BUF_LEN - 1); + + log_buf[dest_idx] = __log_buf[log_idx_mask]; + start++; + dest_idx++; + } + log_start -= offset; + con_start -= offset; + log_end -= offset; + spin_unlock_irqrestore(&logbuf_lock, flags); + + pr_info("log_buf_len: %d\n", log_buf_len); + pr_info("early log buf free: %d(%d%%)\n", + free, (free * 100) / __LOG_BUF_LEN); +} #ifdef CONFIG_BOOT_PRINTK_DELAY @@ -753,7 +782,7 @@ static inline int can_use_console(unsigned int cpu) static int console_trylock_for_printk(unsigned int cpu) __releases(&logbuf_lock) { - int retval = 0; + int retval = 0, wake = 0; if (console_trylock()) { retval = 1; @@ -766,12 +795,14 @@ static int console_trylock_for_printk(unsigned int cpu) */ if (!can_use_console(cpu)) { console_locked = 0; - up(&console_sem); + wake = 1; retval = 0; } } printk_cpu = UINT_MAX; spin_unlock(&logbuf_lock); + if (wake) + up(&console_sem); return retval; } static const char recursion_bug_msg [] = @@ -1213,7 +1244,7 @@ void console_unlock(void) { unsigned long flags; unsigned _con_start, _log_end; - unsigned wake_klogd = 0; + unsigned wake_klogd = 0, retry = 0; if (console_suspended) { up(&console_sem); @@ -1222,6 +1253,7 @@ void console_unlock(void) console_may_schedule = 0; +again: for ( ; ; ) { spin_lock_irqsave(&logbuf_lock, flags); wake_klogd |= log_start - log_end; @@ -1242,8 +1274,23 @@ void console_unlock(void) if (unlikely(exclusive_console)) exclusive_console = NULL; + spin_unlock(&logbuf_lock); + up(&console_sem); + + /* + * Someone could have filled up the buffer again, so re-check if there's + * something to flush. In case we cannot trylock the console_sem again, + * there's a new owner and the console_unlock() from them will do the + * flush, no worries. + */ + spin_lock(&logbuf_lock); + if (con_start != log_end) + retry = 1; spin_unlock_irqrestore(&logbuf_lock, flags); + if (retry && console_trylock()) + goto again; + if (wake_klogd) wake_up_klogd(); } diff --git a/kernel/profile.c b/kernel/profile.c index 66f841b7fbd..961b389fe52 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -126,11 +126,9 @@ int __ref profile_init(void) if (prof_buffer) return 0; - prof_buffer = vmalloc(buffer_bytes); - if (prof_buffer) { - memset(prof_buffer, 0, buffer_bytes); + prof_buffer = vzalloc(buffer_bytes); + if (prof_buffer) return 0; - } free_cpumask_var(prof_cpu_mask); return -ENOMEM; @@ -305,14 +303,12 @@ static void profile_discard_flip_buffers(void) mutex_unlock(&profile_flip_mutex); } -void profile_hits(int type, void *__pc, unsigned int nr_hits) +static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) { unsigned long primary, secondary, flags, pc = (unsigned long)__pc; int i, j, cpu; struct profile_hit *hits; - if (prof_on != type || !prof_buffer) - return; pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1); i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; secondary = (~(pc << 1) & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; @@ -419,16 +415,20 @@ out_free: #define profile_discard_flip_buffers() do { } while (0) #define profile_cpu_callback NULL -void profile_hits(int type, void *__pc, unsigned int nr_hits) +static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) { unsigned long pc; - - if (prof_on != type || !prof_buffer) - return; pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift; atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]); } #endif /* !CONFIG_SMP */ + +void profile_hits(int type, void *__pc, unsigned int nr_hits) +{ + if (prof_on != type || !prof_buffer) + return; + do_profile_hits(type, __pc, nr_hits); +} EXPORT_SYMBOL_GPL(profile_hits); void profile_tick(int type) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 0fc1eed28d2..9de3ecfd20f 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -22,8 +22,16 @@ #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/regset.h> +#include <linux/hw_breakpoint.h> +#include <linux/cn_proc.h> +static int ptrace_trapping_sleep_fn(void *flags) +{ + schedule(); + return 0; +} + /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. @@ -37,35 +45,33 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent) child->parent = new_parent; } -/* - * Turn a tracing stop into a normal stop now, since with no tracer there - * would be no way to wake it up with SIGCONT or SIGKILL. If there was a - * signal sent that would resume the child, but didn't because it was in - * TASK_TRACED, resume it now. - * Requires that irqs be disabled. - */ -static void ptrace_untrace(struct task_struct *child) -{ - spin_lock(&child->sighand->siglock); - if (task_is_traced(child)) { - /* - * If the group stop is completed or in progress, - * this thread was already counted as stopped. - */ - if (child->signal->flags & SIGNAL_STOP_STOPPED || - child->signal->group_stop_count) - __set_task_state(child, TASK_STOPPED); - else - signal_wake_up(child, 1); - } - spin_unlock(&child->sighand->siglock); -} - -/* - * unptrace a task: move it back to its original parent and - * remove it from the ptrace list. +/** + * __ptrace_unlink - unlink ptracee and restore its execution state + * @child: ptracee to be unlinked * - * Must be called with the tasklist lock write-held. + * Remove @child from the ptrace list, move it back to the original parent, + * and restore the execution state so that it conforms to the group stop + * state. + * + * Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer + * exiting. For PTRACE_DETACH, unless the ptracee has been killed between + * ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED. + * If the ptracer is exiting, the ptracee can be in any state. + * + * After detach, the ptracee should be in a state which conforms to the + * group stop. If the group is stopped or in the process of stopping, the + * ptracee should be put into TASK_STOPPED; otherwise, it should be woken + * up from TASK_TRACED. + * + * If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED, + * it goes through TRACED -> RUNNING -> STOPPED transition which is similar + * to but in the opposite direction of what happens while attaching to a + * stopped task. However, in this direction, the intermediate RUNNING + * state is not hidden even from the current ptracer and if it immediately + * re-attaches and performs a WNOHANG wait(2), it may fail. + * + * CONTEXT: + * write_lock_irq(tasklist_lock) */ void __ptrace_unlink(struct task_struct *child) { @@ -75,14 +81,54 @@ void __ptrace_unlink(struct task_struct *child) child->parent = child->real_parent; list_del_init(&child->ptrace_entry); - if (task_is_traced(child)) - ptrace_untrace(child); + spin_lock(&child->sighand->siglock); + + /* + * Clear all pending traps and TRAPPING. TRAPPING should be + * cleared regardless of JOBCTL_STOP_PENDING. Do it explicitly. + */ + task_clear_jobctl_pending(child, JOBCTL_TRAP_MASK); + task_clear_jobctl_trapping(child); + + /* + * Reinstate JOBCTL_STOP_PENDING if group stop is in effect and + * @child isn't dead. + */ + if (!(child->flags & PF_EXITING) && + (child->signal->flags & SIGNAL_STOP_STOPPED || + child->signal->group_stop_count)) + child->jobctl |= JOBCTL_STOP_PENDING; + + /* + * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick + * @child in the butt. Note that @resume should be used iff @child + * is in TASK_TRACED; otherwise, we might unduly disrupt + * TASK_KILLABLE sleeps. + */ + if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child)) + signal_wake_up(child, task_is_traced(child)); + + spin_unlock(&child->sighand->siglock); } -/* - * Check that we have indeed attached to the thing.. +/** + * ptrace_check_attach - check whether ptracee is ready for ptrace operation + * @child: ptracee to check for + * @ignore_state: don't check whether @child is currently %TASK_TRACED + * + * Check whether @child is being ptraced by %current and ready for further + * ptrace operations. If @ignore_state is %false, @child also should be in + * %TASK_TRACED state and on return the child is guaranteed to be traced + * and not executing. If @ignore_state is %true, @child can be in any + * state. + * + * CONTEXT: + * Grabs and releases tasklist_lock and @child->sighand->siglock. + * + * RETURNS: + * 0 on success, -ESRCH if %child is not ready. */ -int ptrace_check_attach(struct task_struct *child, int kill) +int ptrace_check_attach(struct task_struct *child, bool ignore_state) { int ret = -ESRCH; @@ -95,21 +141,20 @@ int ptrace_check_attach(struct task_struct *child, int kill) */ read_lock(&tasklist_lock); if ((child->ptrace & PT_PTRACED) && child->parent == current) { - ret = 0; /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). */ spin_lock_irq(&child->sighand->siglock); - if (task_is_stopped(child)) - child->state = TASK_TRACED; - else if (!task_is_traced(child) && !kill) - ret = -ESRCH; + WARN_ON_ONCE(task_is_stopped(child)); + if (ignore_state || (task_is_traced(child) && + !(child->jobctl & JOBCTL_LISTENING))) + ret = 0; spin_unlock_irq(&child->sighand->siglock); } read_unlock(&tasklist_lock); - if (!ret && !kill) + if (!ret && !ignore_state) ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH; /* All systems go.. */ @@ -166,10 +211,28 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode) return !err; } -static int ptrace_attach(struct task_struct *task) +static int ptrace_attach(struct task_struct *task, long request, + unsigned long flags) { + bool seize = (request == PTRACE_SEIZE); int retval; + /* + * SEIZE will enable new ptrace behaviors which will be implemented + * gradually. SEIZE_DEVEL is used to prevent applications + * expecting full SEIZE behaviors trapping on kernel commits which + * are still in the process of implementing them. + * + * Only test programs for new ptrace behaviors being implemented + * should set SEIZE_DEVEL. If unset, SEIZE will fail with -EIO. + * + * Once SEIZE behaviors are completely implemented, this flag and + * the following test will be removed. + */ + retval = -EIO; + if (seize && !(flags & PTRACE_SEIZE_DEVEL)) + goto out; + audit_ptrace(task); retval = -EPERM; @@ -201,11 +264,41 @@ static int ptrace_attach(struct task_struct *task) goto unlock_tasklist; task->ptrace = PT_PTRACED; + if (seize) + task->ptrace |= PT_SEIZED; if (task_ns_capable(task, CAP_SYS_PTRACE)) task->ptrace |= PT_PTRACE_CAP; __ptrace_link(task, current); - send_sig_info(SIGSTOP, SEND_SIG_FORCED, task); + + /* SEIZE doesn't trap tracee on attach */ + if (!seize) + send_sig_info(SIGSTOP, SEND_SIG_FORCED, task); + + spin_lock(&task->sighand->siglock); + + /* + * If the task is already STOPPED, set JOBCTL_TRAP_STOP and + * TRAPPING, and kick it so that it transits to TRACED. TRAPPING + * will be cleared if the child completes the transition or any + * event which clears the group stop states happens. We'll wait + * for the transition to complete before returning from this + * function. + * + * This hides STOPPED -> RUNNING -> TRACED transition from the + * attaching thread but a different thread in the same group can + * still observe the transient RUNNING state. IOW, if another + * thread's WNOHANG wait(2) on the stopped tracee races against + * ATTACH, the wait(2) may fail due to the transient RUNNING. + * + * The following task_is_stopped() test is safe as both transitions + * in and out of STOPPED are protected by siglock. + */ + if (task_is_stopped(task) && + task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) + signal_wake_up(task, 1); + + spin_unlock(&task->sighand->siglock); retval = 0; unlock_tasklist: @@ -213,6 +306,12 @@ unlock_tasklist: unlock_creds: mutex_unlock(&task->signal->cred_guard_mutex); out: + if (!retval) { + wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, + ptrace_trapping_sleep_fn, TASK_UNINTERRUPTIBLE); + proc_ptrace_connector(task, PTRACE_ATTACH); + } + return retval; } @@ -275,25 +374,27 @@ static int ignoring_children(struct sighand_struct *sigh) */ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) { + bool dead; + __ptrace_unlink(p); - if (p->exit_state == EXIT_ZOMBIE) { - if (!task_detached(p) && thread_group_empty(p)) { - if (!same_thread_group(p->real_parent, tracer)) - do_notify_parent(p, p->exit_signal); - else if (ignoring_children(tracer->sighand)) { - __wake_up_parent(p, tracer); - p->exit_signal = -1; - } - } - if (task_detached(p)) { - /* Mark it as in the process of being reaped. */ - p->exit_state = EXIT_DEAD; - return true; + if (p->exit_state != EXIT_ZOMBIE) + return false; + + dead = !thread_group_leader(p); + + if (!dead && thread_group_empty(p)) { + if (!same_thread_group(p->real_parent, tracer)) + dead = do_notify_parent(p, p->exit_signal); + else if (ignoring_children(tracer->sighand)) { + __wake_up_parent(p, tracer); + dead = true; } } - - return false; + /* Mark it as in the process of being reaped. */ + if (dead) + p->exit_state = EXIT_DEAD; + return dead; } static int ptrace_detach(struct task_struct *child, unsigned int data) @@ -315,11 +416,10 @@ static int ptrace_detach(struct task_struct *child, unsigned int data) if (child->ptrace) { child->exit_code = data; dead = __ptrace_detach(current, child); - if (!child->exit_state) - wake_up_state(child, TASK_TRACED | TASK_STOPPED); } write_unlock_irq(&tasklist_lock); + proc_ptrace_connector(child, PTRACE_DETACH); if (unlikely(dead)) release_task(child); @@ -517,7 +617,7 @@ static int ptrace_resume(struct task_struct *child, long request, } child->exit_code = data; - wake_up_process(child); + wake_up_state(child, __TASK_TRACED); return 0; } @@ -566,10 +666,12 @@ static int ptrace_regset(struct task_struct *task, int req, unsigned int type, int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data) { + bool seized = child->ptrace & PT_SEIZED; int ret = -EIO; - siginfo_t siginfo; + siginfo_t siginfo, *si; void __user *datavp = (void __user *) data; unsigned long __user *datalp = datavp; + unsigned long flags; switch (request) { case PTRACE_PEEKTEXT: @@ -602,6 +704,62 @@ int ptrace_request(struct task_struct *child, long request, ret = ptrace_setsiginfo(child, &siginfo); break; + case PTRACE_INTERRUPT: + /* + * Stop tracee without any side-effect on signal or job + * control. At least one trap is guaranteed to happen + * after this request. If @child is already trapped, the + * current trap is not disturbed and another trap will + * happen after the current trap is ended with PTRACE_CONT. + * + * The actual trap might not be PTRACE_EVENT_STOP trap but + * the pending condition is cleared regardless. + */ + if (unlikely(!seized || !lock_task_sighand(child, &flags))) + break; + + /* + * INTERRUPT doesn't disturb existing trap sans one + * exception. If ptracer issued LISTEN for the current + * STOP, this INTERRUPT should clear LISTEN and re-trap + * tracee into STOP. + */ + if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP))) + signal_wake_up(child, child->jobctl & JOBCTL_LISTENING); + + unlock_task_sighand(child, &flags); + ret = 0; + break; + + case PTRACE_LISTEN: + /* + * Listen for events. Tracee must be in STOP. It's not + * resumed per-se but is not considered to be in TRACED by + * wait(2) or ptrace(2). If an async event (e.g. group + * stop state change) happens, tracee will enter STOP trap + * again. Alternatively, ptracer can issue INTERRUPT to + * finish listening and re-trap tracee into STOP. + */ + if (unlikely(!seized || !lock_task_sighand(child, &flags))) + break; + + si = child->last_siginfo; + if (unlikely(!si || si->si_code >> 8 != PTRACE_EVENT_STOP)) + break; + + child->jobctl |= JOBCTL_LISTENING; + + /* + * If NOTIFY is set, it means event happened between start + * of this trap and now. Trigger re-trap immediately. + */ + if (child->jobctl & JOBCTL_TRAP_NOTIFY) + signal_wake_up(child, true); + + unlock_task_sighand(child, &flags); + ret = 0; + break; + case PTRACE_DETACH: /* detach a process that was attached. */ ret = ptrace_detach(child, data); break; @@ -716,8 +874,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, goto out; } - if (request == PTRACE_ATTACH) { - ret = ptrace_attach(child); + if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { + ret = ptrace_attach(child, request, data); /* * Some architectures need to do book-keeping after * a ptrace attach. @@ -727,7 +885,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, goto out_put_task_struct; } - ret = ptrace_check_attach(child, request == PTRACE_KILL); + ret = ptrace_check_attach(child, request == PTRACE_KILL || + request == PTRACE_INTERRUPT); if (ret < 0) goto out_put_task_struct; @@ -858,8 +1017,8 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, goto out; } - if (request == PTRACE_ATTACH) { - ret = ptrace_attach(child); + if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { + ret = ptrace_attach(child, request, data); /* * Some architectures need to do book-keeping after * a ptrace attach. @@ -869,7 +1028,8 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, goto out_put_task_struct; } - ret = ptrace_check_attach(child, request == PTRACE_KILL); + ret = ptrace_check_attach(child, request == PTRACE_KILL || + request == PTRACE_INTERRUPT); if (!ret) ret = compat_arch_ptrace(child, request, addr, data); @@ -879,3 +1039,19 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, return ret; } #endif /* CONFIG_COMPAT */ + +#ifdef CONFIG_HAVE_HW_BREAKPOINT +int ptrace_get_breakpoints(struct task_struct *tsk) +{ + if (atomic_inc_not_zero(&tsk->ptrace_bp_refcnt)) + return 0; + + return -1; +} + +void ptrace_put_breakpoints(struct task_struct *tsk) +{ + if (atomic_dec_and_test(&tsk->ptrace_bp_refcnt)) + flush_ptrace_hw_breakpoint(tsk); +} +#endif /* CONFIG_HAVE_HW_BREAKPOINT */ diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index f3240e98792..ddddb320be6 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -37,7 +37,7 @@ #include <linux/smp.h> #include <linux/interrupt.h> #include <linux/sched.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <linux/bitops.h> #include <linux/percpu.h> #include <linux/notifier.h> @@ -142,10 +142,17 @@ static int rcuhead_fixup_init(void *addr, enum debug_obj_state state) * Ensure that queued callbacks are all executed. * If we detect that we are nested in a RCU read-side critical * section, we should simply fail, otherwise we would deadlock. + * In !PREEMPT configurations, there is no way to tell if we are + * in a RCU read-side critical section or not, so we never + * attempt any fixup and just print a warning. */ +#ifndef CONFIG_PREEMPT + WARN_ON_ONCE(1); + return 0; +#endif if (rcu_preempt_depth() != 0 || preempt_count() != 0 || irqs_disabled()) { - WARN_ON(1); + WARN_ON_ONCE(1); return 0; } rcu_barrier(); @@ -184,10 +191,17 @@ static int rcuhead_fixup_activate(void *addr, enum debug_obj_state state) * Ensure that queued callbacks are all executed. * If we detect that we are nested in a RCU read-side critical * section, we should simply fail, otherwise we would deadlock. + * In !PREEMPT configurations, there is no way to tell if we are + * in a RCU read-side critical section or not, so we never + * attempt any fixup and just print a warning. */ +#ifndef CONFIG_PREEMPT + WARN_ON_ONCE(1); + return 0; +#endif if (rcu_preempt_depth() != 0 || preempt_count() != 0 || irqs_disabled()) { - WARN_ON(1); + WARN_ON_ONCE(1); return 0; } rcu_barrier(); @@ -214,15 +228,17 @@ static int rcuhead_fixup_free(void *addr, enum debug_obj_state state) * Ensure that queued callbacks are all executed. * If we detect that we are nested in a RCU read-side critical * section, we should simply fail, otherwise we would deadlock. - * Note that the machinery to reliably determine whether - * or not we are in an RCU read-side critical section - * exists only in the preemptible RCU implementations - * (TINY_PREEMPT_RCU and TREE_PREEMPT_RCU), which is why - * DEBUG_OBJECTS_RCU_HEAD is disallowed if !PREEMPT. + * In !PREEMPT configurations, there is no way to tell if we are + * in a RCU read-side critical section or not, so we never + * attempt any fixup and just print a warning. */ +#ifndef CONFIG_PREEMPT + WARN_ON_ONCE(1); + return 0; +#endif if (rcu_preempt_depth() != 0 || preempt_count() != 0 || irqs_disabled()) { - WARN_ON(1); + WARN_ON_ONCE(1); return 0; } rcu_barrier(); diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 0c343b9a46d..7bbac7d0f5a 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -35,15 +35,16 @@ #include <linux/init.h> #include <linux/time.h> #include <linux/cpu.h> +#include <linux/prefetch.h> /* Controls for rcu_kthread() kthread, replacing RCU_SOFTIRQ used previously. */ static struct task_struct *rcu_kthread_task; static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq); static unsigned long have_rcu_kthread_work; -static void invoke_rcu_kthread(void); /* Forward declarations for rcutiny_plugin.h. */ struct rcu_ctrlblk; +static void invoke_rcu_kthread(void); static void rcu_process_callbacks(struct rcu_ctrlblk *rcp); static int rcu_kthread(void *arg); static void __call_rcu(struct rcu_head *head, @@ -79,36 +80,45 @@ void rcu_exit_nohz(void) #endif /* #ifdef CONFIG_NO_HZ */ /* - * Helper function for rcu_qsctr_inc() and rcu_bh_qsctr_inc(). - * Also disable irqs to avoid confusion due to interrupt handlers + * Helper function for rcu_sched_qs() and rcu_bh_qs(). + * Also irqs are disabled to avoid confusion due to interrupt handlers * invoking call_rcu(). */ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp) { - unsigned long flags; - - local_irq_save(flags); if (rcp->rcucblist != NULL && rcp->donetail != rcp->curtail) { rcp->donetail = rcp->curtail; - local_irq_restore(flags); return 1; } - local_irq_restore(flags); return 0; } /* + * Wake up rcu_kthread() to process callbacks now eligible for invocation + * or to boost readers. + */ +static void invoke_rcu_kthread(void) +{ + have_rcu_kthread_work = 1; + wake_up(&rcu_kthread_wq); +} + +/* * Record an rcu quiescent state. And an rcu_bh quiescent state while we * are at it, given that any rcu quiescent state is also an rcu_bh * quiescent state. Use "+" instead of "||" to defeat short circuiting. */ void rcu_sched_qs(int cpu) { + unsigned long flags; + + local_irq_save(flags); if (rcu_qsctr_help(&rcu_sched_ctrlblk) + rcu_qsctr_help(&rcu_bh_ctrlblk)) invoke_rcu_kthread(); + local_irq_restore(flags); } /* @@ -116,8 +126,12 @@ void rcu_sched_qs(int cpu) */ void rcu_bh_qs(int cpu) { + unsigned long flags; + + local_irq_save(flags); if (rcu_qsctr_help(&rcu_bh_ctrlblk)) invoke_rcu_kthread(); + local_irq_restore(flags); } /* @@ -167,7 +181,7 @@ static void rcu_process_callbacks(struct rcu_ctrlblk *rcp) prefetch(next); debug_rcu_head_unqueue(list); local_bh_disable(); - list->func(list); + __rcu_reclaim(list); local_bh_enable(); list = next; RCU_TRACE(cb_count++); @@ -208,20 +222,6 @@ static int rcu_kthread(void *arg) } /* - * Wake up rcu_kthread() to process callbacks now eligible for invocation - * or to boost readers. - */ -static void invoke_rcu_kthread(void) -{ - unsigned long flags; - - local_irq_save(flags); - have_rcu_kthread_work = 1; - wake_up(&rcu_kthread_wq); - local_irq_restore(flags); -} - -/* * Wait for a grace period to elapse. But it is illegal to invoke * synchronize_sched() from within an RCU read-side critical section. * Therefore, any legal call to synchronize_sched() is a quiescent diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index 3cb8e362e88..f259c676195 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -100,23 +100,28 @@ struct rcu_preempt_ctrlblk { u8 completed; /* Last grace period completed. */ /* If all three are equal, RCU is idle. */ #ifdef CONFIG_RCU_BOOST - s8 boosted_this_gp; /* Has boosting already happened? */ unsigned long boost_time; /* When to start boosting (jiffies) */ #endif /* #ifdef CONFIG_RCU_BOOST */ #ifdef CONFIG_RCU_TRACE unsigned long n_grace_periods; #ifdef CONFIG_RCU_BOOST unsigned long n_tasks_boosted; + /* Total number of tasks boosted. */ unsigned long n_exp_boosts; + /* Number of tasks boosted for expedited GP. */ unsigned long n_normal_boosts; - unsigned long n_normal_balk_blkd_tasks; - unsigned long n_normal_balk_gp_tasks; - unsigned long n_normal_balk_boost_tasks; - unsigned long n_normal_balk_boosted; - unsigned long n_normal_balk_notyet; - unsigned long n_normal_balk_nos; - unsigned long n_exp_balk_blkd_tasks; - unsigned long n_exp_balk_nos; + /* Number of tasks boosted for normal GP. */ + unsigned long n_balk_blkd_tasks; + /* Refused to boost: no blocked tasks. */ + unsigned long n_balk_exp_gp_tasks; + /* Refused to boost: nothing blocking GP. */ + unsigned long n_balk_boost_tasks; + /* Refused to boost: already boosting. */ + unsigned long n_balk_notyet; + /* Refused to boost: not yet time. */ + unsigned long n_balk_nos; + /* Refused to boost: not sure why, though. */ + /* This can happen due to race conditions. */ #endif /* #ifdef CONFIG_RCU_BOOST */ #endif /* #ifdef CONFIG_RCU_TRACE */ }; @@ -201,7 +206,6 @@ static struct list_head *rcu_next_node_entry(struct task_struct *t) #ifdef CONFIG_RCU_BOOST static void rcu_initiate_boost_trace(void); -static void rcu_initiate_exp_boost_trace(void); #endif /* #ifdef CONFIG_RCU_BOOST */ /* @@ -219,41 +223,21 @@ static void show_tiny_preempt_stats(struct seq_file *m) "N."[!rcu_preempt_ctrlblk.gp_tasks], "E."[!rcu_preempt_ctrlblk.exp_tasks]); #ifdef CONFIG_RCU_BOOST - seq_printf(m, " ttb=%c btg=", - "B."[!rcu_preempt_ctrlblk.boost_tasks]); - switch (rcu_preempt_ctrlblk.boosted_this_gp) { - case -1: - seq_puts(m, "exp"); - break; - case 0: - seq_puts(m, "no"); - break; - case 1: - seq_puts(m, "begun"); - break; - case 2: - seq_puts(m, "done"); - break; - default: - seq_printf(m, "?%d?", rcu_preempt_ctrlblk.boosted_this_gp); - } - seq_printf(m, " ntb=%lu neb=%lu nnb=%lu j=%04x bt=%04x\n", + seq_printf(m, "%sttb=%c ntb=%lu neb=%lu nnb=%lu j=%04x bt=%04x\n", + " ", + "B."[!rcu_preempt_ctrlblk.boost_tasks], rcu_preempt_ctrlblk.n_tasks_boosted, rcu_preempt_ctrlblk.n_exp_boosts, rcu_preempt_ctrlblk.n_normal_boosts, (int)(jiffies & 0xffff), (int)(rcu_preempt_ctrlblk.boost_time & 0xffff)); - seq_printf(m, " %s: nt=%lu gt=%lu bt=%lu b=%lu ny=%lu nos=%lu\n", - "normal balk", - rcu_preempt_ctrlblk.n_normal_balk_blkd_tasks, - rcu_preempt_ctrlblk.n_normal_balk_gp_tasks, - rcu_preempt_ctrlblk.n_normal_balk_boost_tasks, - rcu_preempt_ctrlblk.n_normal_balk_boosted, - rcu_preempt_ctrlblk.n_normal_balk_notyet, - rcu_preempt_ctrlblk.n_normal_balk_nos); - seq_printf(m, " exp balk: bt=%lu nos=%lu\n", - rcu_preempt_ctrlblk.n_exp_balk_blkd_tasks, - rcu_preempt_ctrlblk.n_exp_balk_nos); + seq_printf(m, "%s: nt=%lu egt=%lu bt=%lu ny=%lu nos=%lu\n", + " balk", + rcu_preempt_ctrlblk.n_balk_blkd_tasks, + rcu_preempt_ctrlblk.n_balk_exp_gp_tasks, + rcu_preempt_ctrlblk.n_balk_boost_tasks, + rcu_preempt_ctrlblk.n_balk_notyet, + rcu_preempt_ctrlblk.n_balk_nos); #endif /* #ifdef CONFIG_RCU_BOOST */ } @@ -271,25 +255,59 @@ static int rcu_boost(void) { unsigned long flags; struct rt_mutex mtx; - struct list_head *np; struct task_struct *t; + struct list_head *tb; - if (rcu_preempt_ctrlblk.boost_tasks == NULL) + if (rcu_preempt_ctrlblk.boost_tasks == NULL && + rcu_preempt_ctrlblk.exp_tasks == NULL) return 0; /* Nothing to boost. */ + raw_local_irq_save(flags); - rcu_preempt_ctrlblk.boosted_this_gp++; - t = container_of(rcu_preempt_ctrlblk.boost_tasks, struct task_struct, - rcu_node_entry); - np = rcu_next_node_entry(t); + + /* + * Recheck with irqs disabled: all tasks in need of boosting + * might exit their RCU read-side critical sections on their own + * if we are preempted just before disabling irqs. + */ + if (rcu_preempt_ctrlblk.boost_tasks == NULL && + rcu_preempt_ctrlblk.exp_tasks == NULL) { + raw_local_irq_restore(flags); + return 0; + } + + /* + * Preferentially boost tasks blocking expedited grace periods. + * This cannot starve the normal grace periods because a second + * expedited grace period must boost all blocked tasks, including + * those blocking the pre-existing normal grace period. + */ + if (rcu_preempt_ctrlblk.exp_tasks != NULL) { + tb = rcu_preempt_ctrlblk.exp_tasks; + RCU_TRACE(rcu_preempt_ctrlblk.n_exp_boosts++); + } else { + tb = rcu_preempt_ctrlblk.boost_tasks; + RCU_TRACE(rcu_preempt_ctrlblk.n_normal_boosts++); + } + RCU_TRACE(rcu_preempt_ctrlblk.n_tasks_boosted++); + + /* + * We boost task t by manufacturing an rt_mutex that appears to + * be held by task t. We leave a pointer to that rt_mutex where + * task t can find it, and task t will release the mutex when it + * exits its outermost RCU read-side critical section. Then + * simply acquiring this artificial rt_mutex will boost task + * t's priority. (Thanks to tglx for suggesting this approach!) + */ + t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&mtx, t); t->rcu_boost_mutex = &mtx; t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED; raw_local_irq_restore(flags); rt_mutex_lock(&mtx); - RCU_TRACE(rcu_preempt_ctrlblk.n_tasks_boosted++); - rcu_preempt_ctrlblk.boosted_this_gp++; - rt_mutex_unlock(&mtx); - return rcu_preempt_ctrlblk.boost_tasks != NULL; + rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ + + return rcu_preempt_ctrlblk.boost_tasks != NULL || + rcu_preempt_ctrlblk.exp_tasks != NULL; } /* @@ -304,42 +322,25 @@ static int rcu_boost(void) */ static int rcu_initiate_boost(void) { - if (!rcu_preempt_blocked_readers_cgp()) { - RCU_TRACE(rcu_preempt_ctrlblk.n_normal_balk_blkd_tasks++); + if (!rcu_preempt_blocked_readers_cgp() && + rcu_preempt_ctrlblk.exp_tasks == NULL) { + RCU_TRACE(rcu_preempt_ctrlblk.n_balk_exp_gp_tasks++); return 0; } - if (rcu_preempt_ctrlblk.gp_tasks != NULL && - rcu_preempt_ctrlblk.boost_tasks == NULL && - rcu_preempt_ctrlblk.boosted_this_gp == 0 && - ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time)) { - rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks; + if (rcu_preempt_ctrlblk.exp_tasks != NULL || + (rcu_preempt_ctrlblk.gp_tasks != NULL && + rcu_preempt_ctrlblk.boost_tasks == NULL && + ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time))) { + if (rcu_preempt_ctrlblk.exp_tasks == NULL) + rcu_preempt_ctrlblk.boost_tasks = + rcu_preempt_ctrlblk.gp_tasks; invoke_rcu_kthread(); - RCU_TRACE(rcu_preempt_ctrlblk.n_normal_boosts++); } else RCU_TRACE(rcu_initiate_boost_trace()); return 1; } -/* - * Initiate boosting for an expedited grace period. - */ -static void rcu_initiate_expedited_boost(void) -{ - unsigned long flags; - - raw_local_irq_save(flags); - if (!list_empty(&rcu_preempt_ctrlblk.blkd_tasks)) { - rcu_preempt_ctrlblk.boost_tasks = - rcu_preempt_ctrlblk.blkd_tasks.next; - rcu_preempt_ctrlblk.boosted_this_gp = -1; - invoke_rcu_kthread(); - RCU_TRACE(rcu_preempt_ctrlblk.n_exp_boosts++); - } else - RCU_TRACE(rcu_initiate_exp_boost_trace()); - raw_local_irq_restore(flags); -} - -#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000); +#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000) /* * Do priority-boost accounting for the start of a new grace period. @@ -347,8 +348,6 @@ static void rcu_initiate_expedited_boost(void) static void rcu_preempt_boost_start_gp(void) { rcu_preempt_ctrlblk.boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES; - if (rcu_preempt_ctrlblk.boosted_this_gp > 0) - rcu_preempt_ctrlblk.boosted_this_gp = 0; } #else /* #ifdef CONFIG_RCU_BOOST */ @@ -372,13 +371,6 @@ static int rcu_initiate_boost(void) } /* - * If there is no RCU priority boosting, we don't initiate expedited boosting. - */ -static void rcu_initiate_expedited_boost(void) -{ -} - -/* * If there is no RCU priority boosting, nothing to do at grace-period start. */ static void rcu_preempt_boost_start_gp(void) @@ -418,7 +410,7 @@ static void rcu_preempt_cpu_qs(void) if (!rcu_preempt_gp_in_progress()) return; /* - * Check up on boosting. If there are no readers blocking the + * Check up on boosting. If there are readers blocking the * current grace period, leave. */ if (rcu_initiate_boost()) @@ -578,7 +570,7 @@ static void rcu_read_unlock_special(struct task_struct *t) empty = !rcu_preempt_blocked_readers_cgp(); empty_exp = rcu_preempt_ctrlblk.exp_tasks == NULL; np = rcu_next_node_entry(t); - list_del(&t->rcu_node_entry); + list_del_init(&t->rcu_node_entry); if (&t->rcu_node_entry == rcu_preempt_ctrlblk.gp_tasks) rcu_preempt_ctrlblk.gp_tasks = np; if (&t->rcu_node_entry == rcu_preempt_ctrlblk.exp_tasks) @@ -587,7 +579,6 @@ static void rcu_read_unlock_special(struct task_struct *t) if (&t->rcu_node_entry == rcu_preempt_ctrlblk.boost_tasks) rcu_preempt_ctrlblk.boost_tasks = np; #endif /* #ifdef CONFIG_RCU_BOOST */ - INIT_LIST_HEAD(&t->rcu_node_entry); /* * If this was the last task on the current list, and if @@ -812,13 +803,16 @@ void synchronize_rcu_expedited(void) rpcp->exp_tasks = rpcp->blkd_tasks.next; if (rpcp->exp_tasks == &rpcp->blkd_tasks) rpcp->exp_tasks = NULL; - local_irq_restore(flags); /* Wait for tail of ->blkd_tasks list to drain. */ - if (rcu_preempted_readers_exp()) - rcu_initiate_expedited_boost(); + if (!rcu_preempted_readers_exp()) + local_irq_restore(flags); + else { + rcu_initiate_boost(); + local_irq_restore(flags); wait_event(sync_rcu_preempt_exp_wq, !rcu_preempted_readers_exp()); + } /* Clean up and exit. */ barrier(); /* ensure expedited GP seen before counter increment. */ @@ -931,24 +925,17 @@ void __init rcu_scheduler_starting(void) static void rcu_initiate_boost_trace(void) { - if (rcu_preempt_ctrlblk.gp_tasks == NULL) - rcu_preempt_ctrlblk.n_normal_balk_gp_tasks++; + if (list_empty(&rcu_preempt_ctrlblk.blkd_tasks)) + rcu_preempt_ctrlblk.n_balk_blkd_tasks++; + else if (rcu_preempt_ctrlblk.gp_tasks == NULL && + rcu_preempt_ctrlblk.exp_tasks == NULL) + rcu_preempt_ctrlblk.n_balk_exp_gp_tasks++; else if (rcu_preempt_ctrlblk.boost_tasks != NULL) - rcu_preempt_ctrlblk.n_normal_balk_boost_tasks++; - else if (rcu_preempt_ctrlblk.boosted_this_gp != 0) - rcu_preempt_ctrlblk.n_normal_balk_boosted++; + rcu_preempt_ctrlblk.n_balk_boost_tasks++; else if (!ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time)) - rcu_preempt_ctrlblk.n_normal_balk_notyet++; - else - rcu_preempt_ctrlblk.n_normal_balk_nos++; -} - -static void rcu_initiate_exp_boost_trace(void) -{ - if (list_empty(&rcu_preempt_ctrlblk.blkd_tasks)) - rcu_preempt_ctrlblk.n_exp_balk_blkd_tasks++; + rcu_preempt_ctrlblk.n_balk_notyet++; else - rcu_preempt_ctrlblk.n_exp_balk_nos++; + rcu_preempt_ctrlblk.n_balk_nos++; } #endif /* #ifdef CONFIG_RCU_BOOST */ diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index c224da41890..98f51b13bb7 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -33,7 +33,7 @@ #include <linux/rcupdate.h> #include <linux/interrupt.h> #include <linux/sched.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <linux/bitops.h> #include <linux/completion.h> #include <linux/moduleparam.h> @@ -131,7 +131,7 @@ struct rcu_torture { static LIST_HEAD(rcu_torture_freelist); static struct rcu_torture __rcu *rcu_torture_current; -static long rcu_torture_current_version; +static unsigned long rcu_torture_current_version; static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN]; static DEFINE_SPINLOCK(rcu_torture_lock); static DEFINE_PER_CPU(long [RCU_TORTURE_PIPE_LEN + 1], rcu_torture_count) = @@ -146,8 +146,6 @@ static atomic_t n_rcu_torture_mberror; static atomic_t n_rcu_torture_error; static long n_rcu_torture_boost_ktrerror; static long n_rcu_torture_boost_rterror; -static long n_rcu_torture_boost_allocerror; -static long n_rcu_torture_boost_afferror; static long n_rcu_torture_boost_failure; static long n_rcu_torture_boosts; static long n_rcu_torture_timers; @@ -163,11 +161,11 @@ static int stutter_pause_test; #endif int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT; -#ifdef CONFIG_RCU_BOOST +#if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) #define rcu_can_boost() 1 -#else /* #ifdef CONFIG_RCU_BOOST */ +#else /* #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */ #define rcu_can_boost() 0 -#endif /* #else #ifdef CONFIG_RCU_BOOST */ +#endif /* #else #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */ static unsigned long boost_starttime; /* jiffies of next boost test start. */ DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ @@ -751,6 +749,7 @@ static int rcu_torture_boost(void *arg) n_rcu_torture_boost_rterror++; } + init_rcu_head_on_stack(&rbi.rcu); /* Each pass through the following loop does one boost-test cycle. */ do { /* Wait for the next test interval. */ @@ -810,6 +809,7 @@ checkwait: rcu_stutter_wait("rcu_torture_boost"); /* Clean up and exit. */ VERBOSE_PRINTK_STRING("rcu_torture_boost task stopping"); + destroy_rcu_head_on_stack(&rbi.rcu); rcutorture_shutdown_absorb("rcu_torture_boost"); while (!kthread_should_stop() || rbi.inflight) schedule_timeout_uninterruptible(1); @@ -886,7 +886,7 @@ rcu_torture_writer(void *arg) old_rp->rtort_pipe_count++; cur_ops->deferred_free(old_rp); } - rcu_torture_current_version++; + rcutorture_record_progress(++rcu_torture_current_version); oldbatch = cur_ops->completed(); rcu_stutter_wait("rcu_torture_writer"); } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); @@ -941,7 +941,6 @@ static void rcu_torture_timer(unsigned long unused) idx = cur_ops->readlock(); completed = cur_ops->completed(); p = rcu_dereference_check(rcu_torture_current, - rcu_read_lock_held() || rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || srcu_read_lock_held(&srcu_ctl)); @@ -1002,7 +1001,6 @@ rcu_torture_reader(void *arg) idx = cur_ops->readlock(); completed = cur_ops->completed(); p = rcu_dereference_check(rcu_torture_current, - rcu_read_lock_held() || rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || srcu_read_lock_held(&srcu_ctl)); @@ -1066,8 +1064,8 @@ rcu_torture_printk(char *page) } cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG); cnt += sprintf(&page[cnt], - "rtc: %p ver: %ld tfle: %d rta: %d rtaf: %d rtf: %d " - "rtmbe: %d rtbke: %ld rtbre: %ld rtbae: %ld rtbafe: %ld " + "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d " + "rtmbe: %d rtbke: %ld rtbre: %ld " "rtbf: %ld rtb: %ld nt: %ld", rcu_torture_current, rcu_torture_current_version, @@ -1078,16 +1076,12 @@ rcu_torture_printk(char *page) atomic_read(&n_rcu_torture_mberror), n_rcu_torture_boost_ktrerror, n_rcu_torture_boost_rterror, - n_rcu_torture_boost_allocerror, - n_rcu_torture_boost_afferror, n_rcu_torture_boost_failure, n_rcu_torture_boosts, n_rcu_torture_timers); if (atomic_read(&n_rcu_torture_mberror) != 0 || n_rcu_torture_boost_ktrerror != 0 || n_rcu_torture_boost_rterror != 0 || - n_rcu_torture_boost_allocerror != 0 || - n_rcu_torture_boost_afferror != 0 || n_rcu_torture_boost_failure != 0) cnt += sprintf(&page[cnt], " !!!"); cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG); @@ -1331,6 +1325,7 @@ rcu_torture_cleanup(void) int i; mutex_lock(&fullstop_mutex); + rcutorture_record_test_transition(); if (fullstop == FULLSTOP_SHUTDOWN) { printk(KERN_WARNING /* but going down anyway, so... */ "Concurrent 'rmmod rcutorture' and shutdown illegal!\n"); @@ -1486,8 +1481,6 @@ rcu_torture_init(void) atomic_set(&n_rcu_torture_error, 0); n_rcu_torture_boost_ktrerror = 0; n_rcu_torture_boost_rterror = 0; - n_rcu_torture_boost_allocerror = 0; - n_rcu_torture_boost_afferror = 0; n_rcu_torture_boost_failure = 0; n_rcu_torture_boosts = 0; for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) @@ -1624,6 +1617,7 @@ rcu_torture_init(void) } } register_reboot_notifier(&rcutorture_shutdown_nb); + rcutorture_record_test_transition(); mutex_unlock(&fullstop_mutex); return 0; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index dd4aea806f8..ba06207b1dd 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -36,7 +36,7 @@ #include <linux/interrupt.h> #include <linux/sched.h> #include <linux/nmi.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <linux/bitops.h> #include <linux/module.h> #include <linux/completion.h> @@ -47,6 +47,9 @@ #include <linux/mutex.h> #include <linux/time.h> #include <linux/kernel_stat.h> +#include <linux/wait.h> +#include <linux/kthread.h> +#include <linux/prefetch.h> #include "rcutree.h" @@ -79,10 +82,67 @@ DEFINE_PER_CPU(struct rcu_data, rcu_sched_data); struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state); DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); +static struct rcu_state *rcu_state; + +/* + * The rcu_scheduler_active variable transitions from zero to one just + * before the first task is spawned. So when this variable is zero, RCU + * can assume that there is but one task, allowing RCU to (for example) + * optimized synchronize_sched() to a simple barrier(). When this variable + * is one, RCU must actually do all the hard work required to detect real + * grace periods. This variable is also used to suppress boot-time false + * positives from lockdep-RCU error checking. + */ int rcu_scheduler_active __read_mostly; EXPORT_SYMBOL_GPL(rcu_scheduler_active); /* + * The rcu_scheduler_fully_active variable transitions from zero to one + * during the early_initcall() processing, which is after the scheduler + * is capable of creating new tasks. So RCU processing (for example, + * creating tasks for RCU priority boosting) must be delayed until after + * rcu_scheduler_fully_active transitions from zero to one. We also + * currently delay invocation of any RCU callbacks until after this point. + * + * It might later prove better for people registering RCU callbacks during + * early boot to take responsibility for these callbacks, but one step at + * a time. + */ +static int rcu_scheduler_fully_active __read_mostly; + +#ifdef CONFIG_RCU_BOOST + +/* + * Control variables for per-CPU and per-rcu_node kthreads. These + * handle all flavors of RCU. + */ +static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); +DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); +DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu); +DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); +DEFINE_PER_CPU(char, rcu_cpu_has_work); + +#endif /* #ifdef CONFIG_RCU_BOOST */ + +static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); +static void invoke_rcu_core(void); +static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); + +#define RCU_KTHREAD_PRIO 1 /* RT priority for per-CPU kthreads. */ + +/* + * Track the rcutorture test sequence number and the update version + * number within a given test. The rcutorture_testseq is incremented + * on every rcutorture module load and unload, so has an odd value + * when a test is running. The rcutorture_vernum is set to zero + * when rcutorture starts and is incremented on each rcutorture update. + * These variables enable correlating rcutorture output with the + * RCU tracing information. + */ +unsigned long rcutorture_testseq; +unsigned long rcutorture_vernum; + +/* * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s * permit this function to be invoked without holding the root rcu_node * structure's ->lock, but of course results can be subject to change. @@ -124,11 +184,12 @@ void rcu_note_context_switch(int cpu) rcu_sched_qs(cpu); rcu_preempt_note_context_switch(cpu); } +EXPORT_SYMBOL_GPL(rcu_note_context_switch); #ifdef CONFIG_NO_HZ DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { .dynticks_nesting = 1, - .dynticks = 1, + .dynticks = ATOMIC_INIT(1), }; #endif /* #ifdef CONFIG_NO_HZ */ @@ -140,10 +201,8 @@ module_param(blimit, int, 0); module_param(qhimark, int, 0); module_param(qlowmark, int, 0); -#ifdef CONFIG_RCU_CPU_STALL_DETECTOR -int rcu_cpu_stall_suppress __read_mostly = RCU_CPU_STALL_SUPPRESS_INIT; +int rcu_cpu_stall_suppress __read_mostly; module_param(rcu_cpu_stall_suppress, int, 0644); -#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ static void force_quiescent_state(struct rcu_state *rsp, int relaxed); static int rcu_pending(int cpu); @@ -176,6 +235,31 @@ void rcu_bh_force_quiescent_state(void) EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); /* + * Record the number of times rcutorture tests have been initiated and + * terminated. This information allows the debugfs tracing stats to be + * correlated to the rcutorture messages, even when the rcutorture module + * is being repeatedly loaded and unloaded. In other words, we cannot + * store this state in rcutorture itself. + */ +void rcutorture_record_test_transition(void) +{ + rcutorture_testseq++; + rcutorture_vernum = 0; +} +EXPORT_SYMBOL_GPL(rcutorture_record_test_transition); + +/* + * Record the number of writer passes through the current rcutorture test. + * This is also used to correlate debugfs tracing stats with the rcutorture + * messages. + */ +void rcutorture_record_progress(unsigned long vernum) +{ + rcutorture_vernum++; +} +EXPORT_SYMBOL_GPL(rcutorture_record_progress); + +/* * Force a quiescent state for RCU-sched. */ void rcu_sched_force_quiescent_state(void) @@ -234,8 +318,8 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp) return 1; } - /* If preemptable RCU, no point in sending reschedule IPI. */ - if (rdp->preemptable) + /* If preemptible RCU, no point in sending reschedule IPI. */ + if (rdp->preemptible) return 0; /* The CPU is online, so send it a reschedule IPI. */ @@ -264,13 +348,25 @@ void rcu_enter_nohz(void) unsigned long flags; struct rcu_dynticks *rdtp; - smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); - rdtp->dynticks++; - rdtp->dynticks_nesting--; - WARN_ON_ONCE(rdtp->dynticks & 0x1); + if (--rdtp->dynticks_nesting) { + local_irq_restore(flags); + return; + } + /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */ + smp_mb__before_atomic_inc(); /* See above. */ + atomic_inc(&rdtp->dynticks); + smp_mb__after_atomic_inc(); /* Force ordering with next sojourn. */ + WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); local_irq_restore(flags); + + /* If the interrupt queued a callback, get out of dyntick mode. */ + if (in_irq() && + (__get_cpu_var(rcu_sched_data).nxtlist || + __get_cpu_var(rcu_bh_data).nxtlist || + rcu_preempt_needs_cpu(smp_processor_id()))) + set_need_resched(); } /* @@ -286,11 +382,16 @@ void rcu_exit_nohz(void) local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); - rdtp->dynticks++; - rdtp->dynticks_nesting++; - WARN_ON_ONCE(!(rdtp->dynticks & 0x1)); + if (rdtp->dynticks_nesting++) { + local_irq_restore(flags); + return; + } + smp_mb__before_atomic_inc(); /* Force ordering w/previous sojourn. */ + atomic_inc(&rdtp->dynticks); + /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */ + smp_mb__after_atomic_inc(); /* See above. */ + WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); local_irq_restore(flags); - smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ } /** @@ -304,11 +405,15 @@ void rcu_nmi_enter(void) { struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); - if (rdtp->dynticks & 0x1) + if (rdtp->dynticks_nmi_nesting == 0 && + (atomic_read(&rdtp->dynticks) & 0x1)) return; - rdtp->dynticks_nmi++; - WARN_ON_ONCE(!(rdtp->dynticks_nmi & 0x1)); - smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ + rdtp->dynticks_nmi_nesting++; + smp_mb__before_atomic_inc(); /* Force delay from prior write. */ + atomic_inc(&rdtp->dynticks); + /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */ + smp_mb__after_atomic_inc(); /* See above. */ + WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); } /** @@ -322,11 +427,14 @@ void rcu_nmi_exit(void) { struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); - if (rdtp->dynticks & 0x1) + if (rdtp->dynticks_nmi_nesting == 0 || + --rdtp->dynticks_nmi_nesting != 0) return; - smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ - rdtp->dynticks_nmi++; - WARN_ON_ONCE(rdtp->dynticks_nmi & 0x1); + /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */ + smp_mb__before_atomic_inc(); /* See above. */ + atomic_inc(&rdtp->dynticks); + smp_mb__after_atomic_inc(); /* Force delay to next write. */ + WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); } /** @@ -337,13 +445,7 @@ void rcu_nmi_exit(void) */ void rcu_irq_enter(void) { - struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); - - if (rdtp->dynticks_nesting++) - return; - rdtp->dynticks++; - WARN_ON_ONCE(!(rdtp->dynticks & 0x1)); - smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ + rcu_exit_nohz(); } /** @@ -355,18 +457,7 @@ void rcu_irq_enter(void) */ void rcu_irq_exit(void) { - struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); - - if (--rdtp->dynticks_nesting) - return; - smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ - rdtp->dynticks++; - WARN_ON_ONCE(rdtp->dynticks & 0x1); - - /* If the interrupt queued a callback, get out of dyntick mode. */ - if (__this_cpu_read(rcu_sched_data.nxtlist) || - __this_cpu_read(rcu_bh_data.nxtlist)) - set_need_resched(); + rcu_enter_nohz(); } #ifdef CONFIG_SMP @@ -378,19 +469,8 @@ void rcu_irq_exit(void) */ static int dyntick_save_progress_counter(struct rcu_data *rdp) { - int ret; - int snap; - int snap_nmi; - - snap = rdp->dynticks->dynticks; - snap_nmi = rdp->dynticks->dynticks_nmi; - smp_mb(); /* Order sampling of snap with end of grace period. */ - rdp->dynticks_snap = snap; - rdp->dynticks_nmi_snap = snap_nmi; - ret = ((snap & 0x1) == 0) && ((snap_nmi & 0x1) == 0); - if (ret) - rdp->dynticks_fqs++; - return ret; + rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks); + return 0; } /* @@ -401,16 +481,11 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp) */ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) { - long curr; - long curr_nmi; - long snap; - long snap_nmi; + unsigned long curr; + unsigned long snap; - curr = rdp->dynticks->dynticks; - snap = rdp->dynticks_snap; - curr_nmi = rdp->dynticks->dynticks_nmi; - snap_nmi = rdp->dynticks_nmi_snap; - smp_mb(); /* force ordering with cpu entering/leaving dynticks. */ + curr = (unsigned long)atomic_add_return(0, &rdp->dynticks->dynticks); + snap = (unsigned long)rdp->dynticks_snap; /* * If the CPU passed through or entered a dynticks idle phase with @@ -420,8 +495,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * read-side critical section that started before the beginning * of the current RCU grace period. */ - if ((curr != snap || (curr & 0x1) == 0) && - (curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) { + if ((curr & 0x1) == 0 || ULONG_CMP_GE(curr, snap + 2)) { rdp->dynticks_fqs++; return 1; } @@ -450,8 +524,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) #endif /* #else #ifdef CONFIG_NO_HZ */ -#ifdef CONFIG_RCU_CPU_STALL_DETECTOR - int rcu_cpu_stall_suppress __read_mostly; static void record_gp_stall_check_time(struct rcu_state *rsp) @@ -537,21 +609,24 @@ static void print_cpu_stall(struct rcu_state *rsp) static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) { - long delta; + unsigned long j; + unsigned long js; struct rcu_node *rnp; if (rcu_cpu_stall_suppress) return; - delta = jiffies - ACCESS_ONCE(rsp->jiffies_stall); + j = ACCESS_ONCE(jiffies); + js = ACCESS_ONCE(rsp->jiffies_stall); rnp = rdp->mynode; - if ((ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && delta >= 0) { + if ((ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) { /* We haven't checked in, so go dump stack. */ print_cpu_stall(rsp); - } else if (rcu_gp_in_progress(rsp) && delta >= RCU_STALL_RAT_DELAY) { + } else if (rcu_gp_in_progress(rsp) && + ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) { - /* They had two time units to dump stack, so complain. */ + /* They had a few time units to dump stack, so complain. */ print_other_cpu_stall(rsp); } } @@ -587,26 +662,6 @@ static void __init check_cpu_stall_init(void) atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block); } -#else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ - -static void record_gp_stall_check_time(struct rcu_state *rsp) -{ -} - -static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) -{ -} - -void rcu_cpu_stall_reset(void) -{ -} - -static void __init check_cpu_stall_init(void) -{ -} - -#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ - /* * 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 @@ -809,6 +864,7 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) rnp->completed = rsp->completed; rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */ rcu_start_gp_per_cpu(rsp, rnp, rdp); + rcu_preempt_boost_start_gp(rnp); raw_spin_unlock_irqrestore(&rnp->lock, flags); return; } @@ -844,6 +900,7 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) rnp->completed = rsp->completed; if (rnp == rdp->mynode) rcu_start_gp_per_cpu(rsp, rnp, rdp); + rcu_preempt_boost_start_gp(rnp); raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ } @@ -864,7 +921,18 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) __releases(rcu_get_root(rsp)->lock) { + unsigned long gp_duration; + WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); + + /* + * Ensure that all grace-period and pre-grace-period activity + * is seen before the assignment to rsp->completed. + */ + smp_mb(); /* See above block comment. */ + gp_duration = jiffies - rsp->gp_start; + if (gp_duration > rsp->gp_max) + rsp->gp_max = gp_duration; rsp->completed = rsp->gpnum; rsp->signaled = RCU_GP_IDLE; rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */ @@ -894,7 +962,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, return; } rnp->qsmask &= ~mask; - if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) { + if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { /* Other bits still set at this level, so done. */ raw_spin_unlock_irqrestore(&rnp->lock, flags); @@ -1037,6 +1105,8 @@ static void rcu_send_cbs_to_online(struct rcu_state *rsp) /* * Remove the outgoing CPU from the bitmasks in the rcu_node hierarchy * and move all callbacks from the outgoing CPU to the current one. + * There can only be one CPU hotplug operation at a time, so no other + * CPU can be attempting to update rcu_cpu_kthread_task. */ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) { @@ -1046,6 +1116,8 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp; + rcu_stop_cpu_kthread(cpu); + /* Exclude any attempts to start a new grace period. */ raw_spin_lock_irqsave(&rsp->onofflock, flags); @@ -1082,6 +1154,7 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp->lock, flags); if (need_report & RCU_OFL_TASKS_EXP_GP) rcu_report_exp_rnp(rsp, rnp); + rcu_node_kthread_setaffinity(rnp, -1); } /* @@ -1143,7 +1216,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) next = list->next; prefetch(next); debug_rcu_head_unqueue(list); - list->func(list); + __rcu_reclaim(list); list = next; if (++count >= rdp->blimit) break; @@ -1179,7 +1252,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) /* Re-raise the RCU softirq if there are callbacks remaining. */ if (cpu_has_callbacks_ready_to_invoke(rdp)) - raise_softirq(RCU_SOFTIRQ); + invoke_rcu_core(); } /* @@ -1225,7 +1298,7 @@ void rcu_check_callbacks(int cpu, int user) } rcu_preempt_check_callbacks(cpu); if (rcu_pending(cpu)) - raise_softirq(RCU_SOFTIRQ); + invoke_rcu_core(); } #ifdef CONFIG_SMP @@ -1233,6 +1306,8 @@ void rcu_check_callbacks(int cpu, int user) /* * Scan the leaf rcu_node structures, processing dyntick state for any that * have not yet encountered a quiescent state, using the function specified. + * Also initiate boosting for any threads blocked on the root rcu_node. + * * The caller must have suppressed start of new grace periods. */ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *)) @@ -1251,7 +1326,7 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *)) return; } if (rnp->qsmask == 0) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); + rcu_initiate_boost(rnp, flags); /* releases rnp->lock */ continue; } cpu = rnp->grplo; @@ -1269,6 +1344,11 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *)) } raw_spin_unlock_irqrestore(&rnp->lock, flags); } + rnp = rcu_get_root(rsp); + if (rnp->qsmask == 0) { + raw_spin_lock_irqsave(&rnp->lock, flags); + rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */ + } } /* @@ -1383,7 +1463,8 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) } /* If there are callbacks ready, invoke them. */ - rcu_do_batch(rsp, rdp); + if (cpu_has_callbacks_ready_to_invoke(rdp)) + invoke_rcu_callbacks(rsp, rdp); } /* @@ -1391,29 +1472,37 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) */ static void rcu_process_callbacks(struct softirq_action *unused) { - /* - * Memory references from any prior RCU read-side critical sections - * executed by the interrupted code must be seen before any RCU - * grace-period manipulations below. - */ - smp_mb(); /* See above block comment. */ - __rcu_process_callbacks(&rcu_sched_state, &__get_cpu_var(rcu_sched_data)); __rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data)); rcu_preempt_process_callbacks(); - /* - * Memory references from any later RCU read-side critical sections - * executed by the interrupted code must be seen after any RCU - * grace-period manipulations above. - */ - smp_mb(); /* See above block comment. */ - /* If we are last CPU on way to dyntick-idle mode, accelerate it. */ rcu_needs_cpu_flush(); } +/* + * Wake up the current CPU's kthread. This replaces raise_softirq() + * in earlier versions of RCU. Note that because we are running on + * the current CPU with interrupts disabled, the rcu_cpu_kthread_task + * cannot disappear out from under us. + */ +static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) +{ + if (unlikely(!ACCESS_ONCE(rcu_scheduler_fully_active))) + return; + if (likely(!rsp->boost)) { + rcu_do_batch(rsp, rdp); + return; + } + invoke_rcu_callbacks_kthread(); +} + +static void invoke_rcu_core(void) +{ + raise_softirq(RCU_SOFTIRQ); +} + static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), struct rcu_state *rsp) @@ -1439,6 +1528,13 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), /* Add the callback to our list. */ *rdp->nxttail[RCU_NEXT_TAIL] = head; rdp->nxttail[RCU_NEXT_TAIL] = &head->next; + rdp->qlen++; + + /* If interrupts were disabled, don't dive into RCU core. */ + if (irqs_disabled_flags(flags)) { + local_irq_restore(flags); + return; + } /* * Force the grace period if too many callbacks or too long waiting. @@ -1447,7 +1543,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), * invoking force_quiescent_state() if the newly enqueued callback * is the only one waiting for a grace period to complete. */ - if (unlikely(++rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) { + if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) { /* Are we ignoring a completed grace period? */ rcu_process_gp_end(rsp, rdp); @@ -1583,7 +1679,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) * or RCU-bh, force a local reschedule. */ rdp->n_rp_qs_pending++; - if (!rdp->preemptable && + if (!rdp->preemptible && ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs) - 1, jiffies)) set_need_resched(); @@ -1760,7 +1856,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) * that this CPU cannot possibly have any RCU callbacks in flight yet. */ static void __cpuinit -rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable) +rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) { unsigned long flags; unsigned long mask; @@ -1772,7 +1868,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable) 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->preemptible = preemptible; rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; @@ -1806,7 +1902,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable) raw_spin_unlock_irqrestore(&rsp->onofflock, flags); } -static void __cpuinit rcu_online_cpu(int cpu) +static void __cpuinit rcu_prepare_cpu(int cpu) { rcu_init_percpu_data(cpu, &rcu_sched_state, 0); rcu_init_percpu_data(cpu, &rcu_bh_state, 0); @@ -1820,11 +1916,23 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { long cpu = (long)hcpu; + struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); + struct rcu_node *rnp = rdp->mynode; switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - rcu_online_cpu(cpu); + rcu_prepare_cpu(cpu); + rcu_prepare_kthreads(cpu); + break; + case CPU_ONLINE: + case CPU_DOWN_FAILED: + rcu_node_kthread_setaffinity(rnp, -1); + rcu_cpu_kthread_setrt(cpu, 1); + break; + case CPU_DOWN_PREPARE: + rcu_node_kthread_setaffinity(rnp, cpu); + rcu_cpu_kthread_setrt(cpu, 0); break; case CPU_DYING: case CPU_DYING_FROZEN: @@ -1943,10 +2051,7 @@ static void __init rcu_init_one(struct rcu_state *rsp, j / rsp->levelspread[i - 1]; } rnp->level = i; - INIT_LIST_HEAD(&rnp->blocked_tasks[0]); - INIT_LIST_HEAD(&rnp->blocked_tasks[1]); - INIT_LIST_HEAD(&rnp->blocked_tasks[2]); - INIT_LIST_HEAD(&rnp->blocked_tasks[3]); + INIT_LIST_HEAD(&rnp->blkd_tasks); } } @@ -1968,7 +2073,7 @@ void __init rcu_init(void) rcu_init_one(&rcu_sched_state, &rcu_sched_data); rcu_init_one(&rcu_bh_state, &rcu_bh_data); __rcu_init_preempt(); - open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); + open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); /* * We don't need protection against CPU-hotplug here because diff --git a/kernel/rcutree.h b/kernel/rcutree.h index e8f057e44e3..01b2ccda26f 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -84,13 +84,19 @@ * Dynticks per-CPU state. */ struct rcu_dynticks { - int dynticks_nesting; /* Track nesting level, sort of. */ - int dynticks; /* Even value for dynticks-idle, else odd. */ - int dynticks_nmi; /* Even value for either dynticks-idle or */ - /* not in nmi handler, else odd. So this */ - /* remains even for nmi from irq handler. */ + int dynticks_nesting; /* Track irq/process nesting level. */ + int dynticks_nmi_nesting; /* Track NMI nesting level. */ + atomic_t dynticks; /* Even value for dynticks-idle, else odd. */ }; +/* RCU's kthread states for tracing. */ +#define RCU_KTHREAD_STOPPED 0 +#define RCU_KTHREAD_RUNNING 1 +#define RCU_KTHREAD_WAITING 2 +#define RCU_KTHREAD_OFFCPU 3 +#define RCU_KTHREAD_YIELDING 4 +#define RCU_KTHREAD_MAX 4 + /* * Definition for node within the RCU grace-period-detection hierarchy. */ @@ -109,10 +115,13 @@ struct rcu_node { /* an rcu_data structure, otherwise, each */ /* bit corresponds to a child rcu_node */ /* structure. */ - unsigned long expmask; /* Groups that have ->blocked_tasks[] */ + unsigned long expmask; /* Groups that have ->blkd_tasks */ /* elements that need to drain to allow the */ /* current expedited grace period to */ /* complete (only for TREE_PREEMPT_RCU). */ + atomic_t wakemask; /* CPUs whose kthread needs to be awakened. */ + /* Since this has meaning only for leaf */ + /* rcu_node structures, 32 bits suffices. */ unsigned long qsmaskinit; /* Per-GP initial value for qsmask & expmask. */ unsigned long grpmask; /* Mask to apply to parent qsmask. */ @@ -122,11 +131,62 @@ struct rcu_node { u8 grpnum; /* CPU/group number for next level up. */ u8 level; /* root is at level 0. */ struct rcu_node *parent; - struct list_head blocked_tasks[4]; - /* Tasks blocked in RCU read-side critsect. */ - /* Grace period number (->gpnum) x blocked */ - /* by tasks on the (x & 0x1) element of the */ - /* blocked_tasks[] array. */ + struct list_head blkd_tasks; + /* Tasks blocked in RCU read-side critical */ + /* section. Tasks are placed at the head */ + /* of this list and age towards the tail. */ + struct list_head *gp_tasks; + /* Pointer to the first task blocking the */ + /* current grace period, or NULL if there */ + /* is no such task. */ + struct list_head *exp_tasks; + /* Pointer to the first task blocking the */ + /* current expedited grace period, or NULL */ + /* if there is no such task. If there */ + /* is no current expedited grace period, */ + /* then there can cannot be any such task. */ +#ifdef CONFIG_RCU_BOOST + struct list_head *boost_tasks; + /* Pointer to first task that needs to be */ + /* priority boosted, or NULL if no priority */ + /* boosting is needed for this rcu_node */ + /* structure. If there are no tasks */ + /* queued on this rcu_node structure that */ + /* are blocking the current grace period, */ + /* there can be no such task. */ + unsigned long boost_time; + /* When to start boosting (jiffies). */ + struct task_struct *boost_kthread_task; + /* kthread that takes care of priority */ + /* boosting for this rcu_node structure. */ + unsigned int boost_kthread_status; + /* State of boost_kthread_task for tracing. */ + unsigned long n_tasks_boosted; + /* Total number of tasks boosted. */ + unsigned long n_exp_boosts; + /* Number of tasks boosted for expedited GP. */ + unsigned long n_normal_boosts; + /* Number of tasks boosted for normal GP. */ + unsigned long n_balk_blkd_tasks; + /* Refused to boost: no blocked tasks. */ + unsigned long n_balk_exp_gp_tasks; + /* Refused to boost: nothing blocking GP. */ + unsigned long n_balk_boost_tasks; + /* Refused to boost: already boosting. */ + unsigned long n_balk_notblocked; + /* Refused to boost: RCU RS CS still running. */ + unsigned long n_balk_notyet; + /* Refused to boost: not yet time. */ + unsigned long n_balk_nos; + /* Refused to boost: not sure why, though. */ + /* This can happen due to race conditions. */ +#endif /* #ifdef CONFIG_RCU_BOOST */ + struct task_struct *node_kthread_task; + /* kthread that takes care of this rcu_node */ + /* structure, for example, awakening the */ + /* per-CPU kthreads as needed. */ + unsigned int node_kthread_status; + /* State of node_kthread_task for tracing. */ } ____cacheline_internodealigned_in_smp; /* @@ -175,7 +235,7 @@ struct rcu_data { bool passed_quiesc; /* User-mode/idle loop etc. */ bool qs_pending; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ - bool preemptable; /* Preemptable RCU? */ + bool preemptible; /* Preemptible RCU? */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ unsigned long grpmask; /* Mask to apply to leaf qsmask. */ @@ -218,7 +278,6 @@ struct rcu_data { /* 3) dynticks interface. */ struct rcu_dynticks *dynticks; /* Shared per-CPU dynticks state. */ int dynticks_snap; /* Per-GP tracking for dynticks. */ - int dynticks_nmi_snap; /* Per-GP tracking for dynticks_nmi. */ #endif /* #ifdef CONFIG_NO_HZ */ /* 4) reasons this CPU needed to be kicked by force_quiescent_state */ @@ -254,7 +313,6 @@ struct rcu_data { #endif /* #else #ifdef CONFIG_NO_HZ */ #define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */ -#ifdef CONFIG_RCU_CPU_STALL_DETECTOR #ifdef CONFIG_PROVE_RCU #define RCU_STALL_DELAY_DELTA (5 * HZ) @@ -272,13 +330,16 @@ struct rcu_data { /* scheduling clock irq */ /* before ratting on them. */ -#ifdef CONFIG_RCU_CPU_STALL_DETECTOR_RUNNABLE -#define RCU_CPU_STALL_SUPPRESS_INIT 0 -#else -#define RCU_CPU_STALL_SUPPRESS_INIT 1 -#endif - -#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ +#define rcu_wait(cond) \ +do { \ + for (;;) { \ + set_current_state(TASK_INTERRUPTIBLE); \ + if (cond) \ + break; \ + schedule(); \ + } \ + __set_current_state(TASK_RUNNING); \ +} while (0) /* * RCU global state, including node hierarchy. This hierarchy is @@ -308,6 +369,7 @@ struct rcu_state { /* period because */ /* force_quiescent_state() */ /* was running. */ + u8 boost; /* Subject to priority boost. */ unsigned long gpnum; /* Current gp number. */ unsigned long completed; /* # of last completed gp. */ @@ -325,12 +387,12 @@ struct rcu_state { /* due to lock unavailable. */ unsigned long n_force_qs_ngp; /* Number of calls leaving */ /* due to no GP active. */ -#ifdef CONFIG_RCU_CPU_STALL_DETECTOR unsigned long gp_start; /* Time at which GP started, */ /* but in jiffies. */ unsigned long jiffies_stall; /* Time at which to check */ /* for CPU stalls. */ -#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ + unsigned long gp_max; /* Maximum GP duration in */ + /* jiffies. */ char *name; /* Name of structure. */ }; @@ -361,16 +423,15 @@ DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data); 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); +static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags); +static void rcu_stop_cpu_kthread(int cpu); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ -#ifdef CONFIG_RCU_CPU_STALL_DETECTOR static void rcu_print_detail_task_stall(struct rcu_state *rsp); static void rcu_print_task_stall(struct rcu_node *rnp); static void rcu_preempt_stall_reset(void); -#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static int rcu_preempt_offline_tasks(struct rcu_state *rsp, @@ -390,5 +451,20 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu); static void rcu_preempt_send_cbs_to_online(void); static void __init __rcu_init_preempt(void); static void rcu_needs_cpu_flush(void); +static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); +static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); +static void invoke_rcu_callbacks_kthread(void); +#ifdef CONFIG_RCU_BOOST +static void rcu_preempt_do_callbacks(void); +static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, + cpumask_var_t cm); +static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, + struct rcu_node *rnp, + int rnp_index); +static void invoke_rcu_node_kthread(struct rcu_node *rnp); +static void rcu_yield(void (*f)(unsigned long), unsigned long arg); +#endif /* #ifdef CONFIG_RCU_BOOST */ +static void rcu_cpu_kthread_setrt(int cpu, int to_rt); +static void __cpuinit rcu_prepare_kthreads(int cpu); #endif /* #ifndef RCU_TREE_NONCORE */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index a3638710dc6..8aafbb80b8b 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -1,7 +1,7 @@ /* * Read-Copy Update mechanism for mutual exclusion (tree-based version) * Internal non-public definitions that provide either classic - * or preemptable semantics. + * or preemptible semantics. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -54,10 +54,6 @@ static void __init rcu_bootup_announce_oddness(void) #ifdef CONFIG_RCU_TORTURE_TEST_RUNNABLE printk(KERN_INFO "\tRCU torture testing starts during boot.\n"); #endif -#ifndef CONFIG_RCU_CPU_STALL_DETECTOR - printk(KERN_INFO - "\tRCU-based detection of stalled CPUs is disabled.\n"); -#endif #if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE) printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n"); #endif @@ -70,7 +66,9 @@ static void __init rcu_bootup_announce_oddness(void) struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state); DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); +static struct rcu_state *rcu_state = &rcu_preempt_state; +static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(struct rcu_node *rnp); /* @@ -78,7 +76,7 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp); */ static void __init rcu_bootup_announce(void) { - printk(KERN_INFO "Preemptable hierarchical RCU implementation.\n"); + printk(KERN_INFO "Preemptible hierarchical RCU implementation.\n"); rcu_bootup_announce_oddness(); } @@ -111,7 +109,7 @@ void rcu_force_quiescent_state(void) EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); /* - * Record a preemptable-RCU quiescent state for the specified CPU. Note + * Record a preemptible-RCU quiescent state for the specified CPU. Note * that this just means that the task currently running on the CPU is * not in a quiescent state. There might be any number of tasks blocked * while in an RCU read-side critical section. @@ -134,12 +132,12 @@ static void rcu_preempt_qs(int cpu) * We have entered the scheduler, and the current task might soon be * context-switched away from. If this task is in an RCU read-side * critical section, we will no longer be able to rely on the CPU to - * record that fact, so we enqueue the task on the appropriate entry - * of the blocked_tasks[] array. The task will dequeue itself when - * it exits the outermost enclosing RCU read-side critical section. - * Therefore, the current grace period cannot be permitted to complete - * until the blocked_tasks[] entry indexed by the low-order bit of - * rnp->gpnum empties. + * record that fact, so we enqueue the task on the blkd_tasks list. + * The task will dequeue itself when it exits the outermost enclosing + * RCU read-side critical section. Therefore, the current grace period + * cannot be permitted to complete until the blkd_tasks list entries + * predating the current grace period drain, in other words, until + * rnp->gp_tasks becomes NULL. * * Caller must disable preemption. */ @@ -147,11 +145,10 @@ static void rcu_preempt_note_context_switch(int cpu) { struct task_struct *t = current; unsigned long flags; - int phase; struct rcu_data *rdp; struct rcu_node *rnp; - if (t->rcu_read_lock_nesting && + if (t->rcu_read_lock_nesting > 0 && (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) { /* Possibly blocking in an RCU read-side critical section. */ @@ -169,16 +166,39 @@ static void rcu_preempt_note_context_switch(int cpu) * (i.e., this CPU has not yet passed through a quiescent * state for the current grace period), then as long * as that task remains queued, the current grace period - * cannot end. + * cannot end. Note that there is some uncertainty as + * to exactly when the current grace period started. + * We take a conservative approach, which can result + * in unnecessarily waiting on tasks that started very + * slightly after the current grace period began. C'est + * la vie!!! * * But first, note that the current CPU must still be * on line! */ WARN_ON_ONCE((rdp->grpmask & rnp->qsmaskinit) == 0); WARN_ON_ONCE(!list_empty(&t->rcu_node_entry)); - phase = (rnp->gpnum + !(rnp->qsmask & rdp->grpmask)) & 0x1; - list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]); + if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) { + list_add(&t->rcu_node_entry, rnp->gp_tasks->prev); + rnp->gp_tasks = &t->rcu_node_entry; +#ifdef CONFIG_RCU_BOOST + if (rnp->boost_tasks != NULL) + rnp->boost_tasks = rnp->gp_tasks; +#endif /* #ifdef CONFIG_RCU_BOOST */ + } else { + list_add(&t->rcu_node_entry, &rnp->blkd_tasks); + if (rnp->qsmask & rdp->grpmask) + rnp->gp_tasks = &t->rcu_node_entry; + } raw_spin_unlock_irqrestore(&rnp->lock, flags); + } else if (t->rcu_read_lock_nesting < 0 && + t->rcu_read_unlock_special) { + + /* + * Complete exit from RCU read-side critical section on + * behalf of preempted instance of __rcu_read_unlock(). + */ + rcu_read_unlock_special(t); } /* @@ -196,7 +216,7 @@ static void rcu_preempt_note_context_switch(int cpu) } /* - * Tree-preemptable RCU implementation for rcu_read_lock(). + * Tree-preemptible RCU implementation for rcu_read_lock(). * Just increment ->rcu_read_lock_nesting, shared state will be updated * if we block. */ @@ -212,12 +232,9 @@ EXPORT_SYMBOL_GPL(__rcu_read_lock); * for the specified rcu_node structure. If the caller needs a reliable * answer, it must hold the rcu_node's ->lock. */ -static int rcu_preempted_readers(struct rcu_node *rnp) +static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) { - int phase = rnp->gpnum & 0x1; - - return !list_empty(&rnp->blocked_tasks[phase]) || - !list_empty(&rnp->blocked_tasks[phase + 2]); + return rnp->gp_tasks != NULL; } /* @@ -233,7 +250,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) unsigned long mask; struct rcu_node *rnp_p; - if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) { + if (rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) { raw_spin_unlock_irqrestore(&rnp->lock, flags); return; /* Still need more quiescent states! */ } @@ -257,15 +274,31 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) } /* + * Advance a ->blkd_tasks-list pointer to the next entry, instead + * returning NULL if at the end of the list. + */ +static struct list_head *rcu_next_node_entry(struct task_struct *t, + struct rcu_node *rnp) +{ + struct list_head *np; + + np = t->rcu_node_entry.next; + if (np == &rnp->blkd_tasks) + np = NULL; + return np; +} + +/* * Handle special cases during rcu_read_unlock(), such as needing to * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static void rcu_read_unlock_special(struct task_struct *t) +static noinline void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; unsigned long flags; + struct list_head *np; struct rcu_node *rnp; int special; @@ -285,7 +318,7 @@ static void rcu_read_unlock_special(struct task_struct *t) } /* Hardware IRQ handlers cannot block. */ - if (in_irq()) { + if (in_irq() || in_serving_softirq()) { local_irq_restore(flags); return; } @@ -306,10 +339,24 @@ static void rcu_read_unlock_special(struct task_struct *t) break; raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ } - empty = !rcu_preempted_readers(rnp); + empty = !rcu_preempt_blocked_readers_cgp(rnp); empty_exp = !rcu_preempted_readers_exp(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ + np = rcu_next_node_entry(t, rnp); list_del_init(&t->rcu_node_entry); + if (&t->rcu_node_entry == rnp->gp_tasks) + rnp->gp_tasks = np; + if (&t->rcu_node_entry == rnp->exp_tasks) + rnp->exp_tasks = np; +#ifdef CONFIG_RCU_BOOST + if (&t->rcu_node_entry == rnp->boost_tasks) + rnp->boost_tasks = np; + /* Snapshot and clear ->rcu_boosted with rcu_node lock held. */ + if (t->rcu_boosted) { + special |= RCU_READ_UNLOCK_BOOSTED; + t->rcu_boosted = 0; + } +#endif /* #ifdef CONFIG_RCU_BOOST */ t->rcu_blocked_node = NULL; /* @@ -322,6 +369,14 @@ static void rcu_read_unlock_special(struct task_struct *t) else rcu_report_unblock_qs_rnp(rnp, flags); +#ifdef CONFIG_RCU_BOOST + /* Unboost if we were boosted. */ + if (special & RCU_READ_UNLOCK_BOOSTED) { + rt_mutex_unlock(t->rcu_boost_mutex); + t->rcu_boost_mutex = NULL; + } +#endif /* #ifdef CONFIG_RCU_BOOST */ + /* * If this was the last task on the expedited lists, * then we need to report up the rcu_node hierarchy. @@ -334,7 +389,7 @@ static void rcu_read_unlock_special(struct task_struct *t) } /* - * Tree-preemptable RCU implementation for rcu_read_unlock(). + * Tree-preemptible RCU implementation for rcu_read_unlock(). * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then * invoke rcu_read_unlock_special() to clean up after a context switch @@ -345,19 +400,26 @@ void __rcu_read_unlock(void) struct task_struct *t = current; barrier(); /* needed if we ever invoke rcu_read_unlock in rcutree.c */ - --t->rcu_read_lock_nesting; - barrier(); /* decrement before load of ->rcu_read_unlock_special */ - if (t->rcu_read_lock_nesting == 0 && - unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) - rcu_read_unlock_special(t); + if (t->rcu_read_lock_nesting != 1) + --t->rcu_read_lock_nesting; + else { + t->rcu_read_lock_nesting = INT_MIN; + barrier(); /* assign before ->rcu_read_unlock_special load */ + if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) + rcu_read_unlock_special(t); + barrier(); /* ->rcu_read_unlock_special load before assign */ + t->rcu_read_lock_nesting = 0; + } #ifdef CONFIG_PROVE_LOCKING - WARN_ON_ONCE(ACCESS_ONCE(t->rcu_read_lock_nesting) < 0); + { + int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); + + WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); + } #endif /* #ifdef CONFIG_PROVE_LOCKING */ } EXPORT_SYMBOL_GPL(__rcu_read_unlock); -#ifdef CONFIG_RCU_CPU_STALL_DETECTOR - #ifdef CONFIG_RCU_CPU_STALL_VERBOSE /* @@ -367,18 +429,16 @@ EXPORT_SYMBOL_GPL(__rcu_read_unlock); static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) { unsigned long flags; - struct list_head *lp; - int phase; struct task_struct *t; - if (rcu_preempted_readers(rnp)) { - raw_spin_lock_irqsave(&rnp->lock, flags); - phase = rnp->gpnum & 0x1; - lp = &rnp->blocked_tasks[phase]; - list_for_each_entry(t, lp, rcu_node_entry) - sched_show_task(t); - raw_spin_unlock_irqrestore(&rnp->lock, flags); - } + if (!rcu_preempt_blocked_readers_cgp(rnp)) + return; + raw_spin_lock_irqsave(&rnp->lock, flags); + t = list_entry(rnp->gp_tasks, + struct task_struct, rcu_node_entry); + list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) + sched_show_task(t); + raw_spin_unlock_irqrestore(&rnp->lock, flags); } /* @@ -408,16 +468,14 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp) */ static void rcu_print_task_stall(struct rcu_node *rnp) { - struct list_head *lp; - int phase; struct task_struct *t; - if (rcu_preempted_readers(rnp)) { - phase = rnp->gpnum & 0x1; - lp = &rnp->blocked_tasks[phase]; - list_for_each_entry(t, lp, rcu_node_entry) - printk(" P%d", t->pid); - } + if (!rcu_preempt_blocked_readers_cgp(rnp)) + return; + t = list_entry(rnp->gp_tasks, + struct task_struct, rcu_node_entry); + list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) + printk(" P%d", t->pid); } /* @@ -430,18 +488,21 @@ static void rcu_preempt_stall_reset(void) rcu_preempt_state.jiffies_stall = jiffies + ULONG_MAX / 2; } -#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ - /* * Check that the list of blocked tasks for the newly completed grace * period is in fact empty. It is a serious bug to complete a grace * period that still has RCU readers blocked! This function must be * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock * must be held by the caller. + * + * Also, if there are blocked tasks on the list, they automatically + * block the newly created grace period, so set up ->gp_tasks accordingly. */ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) { - WARN_ON_ONCE(rcu_preempted_readers(rnp)); + WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); + if (!list_empty(&rnp->blkd_tasks)) + rnp->gp_tasks = rnp->blkd_tasks.next; WARN_ON_ONCE(rnp->qsmask); } @@ -465,50 +526,68 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { - int i; struct list_head *lp; struct list_head *lp_root; int retval = 0; struct rcu_node *rnp_root = rcu_get_root(rsp); - struct task_struct *tp; + struct task_struct *t; if (rnp == rnp_root) { WARN_ONCE(1, "Last CPU thought to be offlined?"); return 0; /* Shouldn't happen: at least one CPU online. */ } - WARN_ON_ONCE(rnp != rdp->mynode && - (!list_empty(&rnp->blocked_tasks[0]) || - !list_empty(&rnp->blocked_tasks[1]) || - !list_empty(&rnp->blocked_tasks[2]) || - !list_empty(&rnp->blocked_tasks[3]))); + + /* If we are on an internal node, complain bitterly. */ + WARN_ON_ONCE(rnp != rdp->mynode); /* - * Move tasks up to root rcu_node. Rely on the fact that the - * root rcu_node can be at most one ahead of the rest of the - * rcu_nodes in terms of gp_num value. This fact allows us to - * move the blocked_tasks[] array directly, element by element. + * Move tasks up to root rcu_node. Don't try to get fancy for + * this corner-case operation -- just put this node's tasks + * at the head of the root node's list, and update the root node's + * ->gp_tasks and ->exp_tasks pointers to those of this node's, + * if non-NULL. This might result in waiting for more tasks than + * absolutely necessary, but this is a good performance/complexity + * tradeoff. */ - if (rcu_preempted_readers(rnp)) + if (rcu_preempt_blocked_readers_cgp(rnp)) retval |= RCU_OFL_TASKS_NORM_GP; if (rcu_preempted_readers_exp(rnp)) retval |= RCU_OFL_TASKS_EXP_GP; - for (i = 0; i < 4; i++) { - lp = &rnp->blocked_tasks[i]; - lp_root = &rnp_root->blocked_tasks[i]; - while (!list_empty(lp)) { - tp = list_entry(lp->next, typeof(*tp), rcu_node_entry); - raw_spin_lock(&rnp_root->lock); /* irqs already disabled */ - list_del(&tp->rcu_node_entry); - tp->rcu_blocked_node = rnp_root; - list_add(&tp->rcu_node_entry, lp_root); - raw_spin_unlock(&rnp_root->lock); /* irqs remain disabled */ - } + lp = &rnp->blkd_tasks; + lp_root = &rnp_root->blkd_tasks; + while (!list_empty(lp)) { + t = list_entry(lp->next, typeof(*t), rcu_node_entry); + raw_spin_lock(&rnp_root->lock); /* irqs already disabled */ + list_del(&t->rcu_node_entry); + t->rcu_blocked_node = rnp_root; + list_add(&t->rcu_node_entry, lp_root); + if (&t->rcu_node_entry == rnp->gp_tasks) + rnp_root->gp_tasks = rnp->gp_tasks; + if (&t->rcu_node_entry == rnp->exp_tasks) + rnp_root->exp_tasks = rnp->exp_tasks; +#ifdef CONFIG_RCU_BOOST + if (&t->rcu_node_entry == rnp->boost_tasks) + rnp_root->boost_tasks = rnp->boost_tasks; +#endif /* #ifdef CONFIG_RCU_BOOST */ + raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */ } + +#ifdef CONFIG_RCU_BOOST + /* In case root is being boosted and leaf is not. */ + raw_spin_lock(&rnp_root->lock); /* irqs already disabled */ + if (rnp_root->boost_tasks != NULL && + rnp_root->boost_tasks != rnp_root->gp_tasks) + rnp_root->boost_tasks = rnp_root->gp_tasks; + raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */ +#endif /* #ifdef CONFIG_RCU_BOOST */ + + rnp->gp_tasks = NULL; + rnp->exp_tasks = NULL; return retval; } /* - * Do CPU-offline processing for preemptable RCU. + * Do CPU-offline processing for preemptible RCU. */ static void rcu_preempt_offline_cpu(int cpu) { @@ -532,12 +611,13 @@ static void rcu_preempt_check_callbacks(int cpu) rcu_preempt_qs(cpu); return; } - if (per_cpu(rcu_preempt_data, cpu).qs_pending) + if (t->rcu_read_lock_nesting > 0 && + per_cpu(rcu_preempt_data, cpu).qs_pending) t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; } /* - * Process callbacks for preemptable RCU. + * Process callbacks for preemptible RCU. */ static void rcu_preempt_process_callbacks(void) { @@ -545,8 +625,17 @@ static void rcu_preempt_process_callbacks(void) &__get_cpu_var(rcu_preempt_data)); } +#ifdef CONFIG_RCU_BOOST + +static void rcu_preempt_do_callbacks(void) +{ + rcu_do_batch(&rcu_preempt_state, &__get_cpu_var(rcu_preempt_data)); +} + +#endif /* #ifdef CONFIG_RCU_BOOST */ + /* - * Queue a preemptable-RCU callback for invocation after a grace period. + * Queue a preemptible-RCU callback for invocation after a grace period. */ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) { @@ -594,8 +683,7 @@ static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex); */ static int rcu_preempted_readers_exp(struct rcu_node *rnp) { - return !list_empty(&rnp->blocked_tasks[2]) || - !list_empty(&rnp->blocked_tasks[3]); + return rnp->exp_tasks != NULL; } /* @@ -630,9 +718,12 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) raw_spin_lock_irqsave(&rnp->lock, flags); for (;;) { - if (!sync_rcu_preempt_exp_done(rnp)) + if (!sync_rcu_preempt_exp_done(rnp)) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); break; + } if (rnp->parent == NULL) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); wake_up(&sync_rcu_preempt_exp_wq); break; } @@ -642,7 +733,6 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) raw_spin_lock(&rnp->lock); /* irqs already disabled */ rnp->expmask &= ~mask; } - raw_spin_unlock_irqrestore(&rnp->lock, flags); } /* @@ -655,13 +745,17 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) static void sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) { - int must_wait; + unsigned long flags; + int must_wait = 0; - raw_spin_lock(&rnp->lock); /* irqs already disabled */ - list_splice_init(&rnp->blocked_tasks[0], &rnp->blocked_tasks[2]); - list_splice_init(&rnp->blocked_tasks[1], &rnp->blocked_tasks[3]); - must_wait = rcu_preempted_readers_exp(rnp); - raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ + raw_spin_lock_irqsave(&rnp->lock, flags); + if (list_empty(&rnp->blkd_tasks)) + raw_spin_unlock_irqrestore(&rnp->lock, flags); + else { + rnp->exp_tasks = rnp->blkd_tasks.next; + rcu_initiate_boost(rnp, flags); /* releases rnp->lock */ + must_wait = 1; + } if (!must_wait) rcu_report_exp_rnp(rsp, rnp); } @@ -669,9 +763,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) /* * Wait for an rcu-preempt grace period, but expedite it. The basic idea * is to invoke synchronize_sched_expedited() to push all the tasks to - * the ->blocked_tasks[] lists, move all entries from the first set of - * ->blocked_tasks[] lists to the second set, and finally wait for this - * second set to drain. + * the ->blkd_tasks lists and wait for this list to drain. */ void synchronize_rcu_expedited(void) { @@ -703,7 +795,7 @@ void synchronize_rcu_expedited(void) if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0) goto unlock_mb_ret; /* Others did our work for us. */ - /* force all RCU readers onto blocked_tasks[]. */ + /* force all RCU readers onto ->blkd_tasks lists. */ synchronize_sched_expedited(); raw_spin_lock_irqsave(&rsp->onofflock, flags); @@ -715,7 +807,7 @@ void synchronize_rcu_expedited(void) raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ } - /* Snapshot current state of ->blocked_tasks[] lists. */ + /* Snapshot current state of ->blkd_tasks lists. */ rcu_for_each_leaf_node(rsp, rnp) sync_rcu_preempt_exp_init(rsp, rnp); if (NUM_RCU_NODES > 1) @@ -723,7 +815,7 @@ void synchronize_rcu_expedited(void) raw_spin_unlock_irqrestore(&rsp->onofflock, flags); - /* Wait for snapshotted ->blocked_tasks[] lists to drain. */ + /* Wait for snapshotted ->blkd_tasks lists to drain. */ rnp = rcu_get_root(rsp); wait_event(sync_rcu_preempt_exp_wq, sync_rcu_preempt_exp_done(rnp)); @@ -739,7 +831,7 @@ mb_ret: EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); /* - * Check to see if there is any immediate preemptable-RCU-related work + * Check to see if there is any immediate preemptible-RCU-related work * to be done. */ static int rcu_preempt_pending(int cpu) @@ -749,7 +841,7 @@ static int rcu_preempt_pending(int cpu) } /* - * Does preemptable RCU need the CPU to stay out of dynticks mode? + * Does preemptible RCU need the CPU to stay out of dynticks mode? */ static int rcu_preempt_needs_cpu(int cpu) { @@ -766,7 +858,7 @@ void rcu_barrier(void) EXPORT_SYMBOL_GPL(rcu_barrier); /* - * Initialize preemptable RCU's per-CPU data. + * Initialize preemptible RCU's per-CPU data. */ static void __cpuinit rcu_preempt_init_percpu_data(int cpu) { @@ -774,7 +866,7 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu) } /* - * Move preemptable RCU's callbacks from dying CPU to other online CPU. + * Move preemptible RCU's callbacks from dying CPU to other online CPU. */ static void rcu_preempt_send_cbs_to_online(void) { @@ -782,7 +874,7 @@ static void rcu_preempt_send_cbs_to_online(void) } /* - * Initialize preemptable RCU's state structures. + * Initialize preemptible RCU's state structures. */ static void __init __rcu_init_preempt(void) { @@ -790,7 +882,7 @@ static void __init __rcu_init_preempt(void) } /* - * Check for a task exiting while in a preemptable-RCU read-side + * Check for a task exiting while in a preemptible-RCU read-side * critical section, clean up if so. No need to issue warnings, * as debug_check_no_locks_held() already does this if lockdep * is enabled. @@ -802,11 +894,13 @@ void exit_rcu(void) if (t->rcu_read_lock_nesting == 0) return; t->rcu_read_lock_nesting = 1; - rcu_read_unlock(); + __rcu_read_unlock(); } #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */ +static struct rcu_state *rcu_state = &rcu_sched_state; + /* * Tell them what RCU they are running. */ @@ -836,7 +930,7 @@ void rcu_force_quiescent_state(void) EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); /* - * Because preemptable RCU does not exist, we never have to check for + * Because preemptible RCU does not exist, we never have to check for * CPUs being in quiescent states. */ static void rcu_preempt_note_context_switch(int cpu) @@ -844,10 +938,10 @@ static void rcu_preempt_note_context_switch(int cpu) } /* - * Because preemptable RCU does not exist, there are never any preempted + * Because preemptible RCU does not exist, there are never any preempted * RCU readers. */ -static int rcu_preempted_readers(struct rcu_node *rnp) +static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) { return 0; } @@ -862,10 +956,8 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) #endif /* #ifdef CONFIG_HOTPLUG_CPU */ -#ifdef CONFIG_RCU_CPU_STALL_DETECTOR - /* - * Because preemptable RCU does not exist, we never have to check for + * Because preemptible RCU does not exist, we never have to check for * tasks blocked within RCU read-side critical sections. */ static void rcu_print_detail_task_stall(struct rcu_state *rsp) @@ -873,7 +965,7 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp) } /* - * Because preemptable RCU does not exist, we never have to check for + * Because preemptible RCU does not exist, we never have to check for * tasks blocked within RCU read-side critical sections. */ static void rcu_print_task_stall(struct rcu_node *rnp) @@ -888,10 +980,8 @@ static void rcu_preempt_stall_reset(void) { } -#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ - /* - * Because there is no preemptable RCU, there can be no readers blocked, + * Because there is no preemptible RCU, there can be no readers blocked, * so there is no need to check for blocked tasks. So check only for * bogus qsmask values. */ @@ -903,7 +993,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) #ifdef CONFIG_HOTPLUG_CPU /* - * Because preemptable RCU does not exist, it never needs to migrate + * Because preemptible RCU does not exist, it never needs to migrate * tasks that were blocked within RCU read-side critical sections, and * such non-existent tasks cannot possibly have been blocking the current * grace period. @@ -916,7 +1006,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, } /* - * Because preemptable RCU does not exist, it never needs CPU-offline + * Because preemptible RCU does not exist, it never needs CPU-offline * processing. */ static void rcu_preempt_offline_cpu(int cpu) @@ -926,7 +1016,7 @@ static void rcu_preempt_offline_cpu(int cpu) #endif /* #ifdef CONFIG_HOTPLUG_CPU */ /* - * Because preemptable RCU does not exist, it never has any callbacks + * Because preemptible RCU does not exist, it never has any callbacks * to check. */ static void rcu_preempt_check_callbacks(int cpu) @@ -934,7 +1024,7 @@ static void rcu_preempt_check_callbacks(int cpu) } /* - * Because preemptable RCU does not exist, it never has any callbacks + * Because preemptible RCU does not exist, it never has any callbacks * to process. */ static void rcu_preempt_process_callbacks(void) @@ -943,7 +1033,7 @@ static void rcu_preempt_process_callbacks(void) /* * Wait for an rcu-preempt grace period, but make it happen quickly. - * But because preemptable RCU does not exist, map to rcu-sched. + * But because preemptible RCU does not exist, map to rcu-sched. */ void synchronize_rcu_expedited(void) { @@ -954,7 +1044,7 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); #ifdef CONFIG_HOTPLUG_CPU /* - * Because preemptable RCU does not exist, there is never any need to + * Because preemptible RCU does not exist, there is never any need to * report on tasks preempted in RCU read-side critical sections during * expedited RCU grace periods. */ @@ -966,7 +1056,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) #endif /* #ifdef CONFIG_HOTPLUG_CPU */ /* - * Because preemptable RCU does not exist, it never has any work to do. + * Because preemptible RCU does not exist, it never has any work to do. */ static int rcu_preempt_pending(int cpu) { @@ -974,7 +1064,7 @@ static int rcu_preempt_pending(int cpu) } /* - * Because preemptable RCU does not exist, it never needs any CPU. + * Because preemptible RCU does not exist, it never needs any CPU. */ static int rcu_preempt_needs_cpu(int cpu) { @@ -982,7 +1072,7 @@ static int rcu_preempt_needs_cpu(int cpu) } /* - * Because preemptable RCU does not exist, rcu_barrier() is just + * Because preemptible RCU does not exist, rcu_barrier() is just * another name for rcu_barrier_sched(). */ void rcu_barrier(void) @@ -992,7 +1082,7 @@ void rcu_barrier(void) EXPORT_SYMBOL_GPL(rcu_barrier); /* - * Because preemptable RCU does not exist, there is no per-CPU + * Because preemptible RCU does not exist, there is no per-CPU * data to initialize. */ static void __cpuinit rcu_preempt_init_percpu_data(int cpu) @@ -1000,14 +1090,14 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu) } /* - * Because there is no preemptable RCU, there are no callbacks to move. + * Because there is no preemptible RCU, there are no callbacks to move. */ static void rcu_preempt_send_cbs_to_online(void) { } /* - * Because preemptable RCU does not exist, it need not be initialized. + * Because preemptible RCU does not exist, it need not be initialized. */ static void __init __rcu_init_preempt(void) { @@ -1015,6 +1105,665 @@ static void __init __rcu_init_preempt(void) #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ +#ifdef CONFIG_RCU_BOOST + +#include "rtmutex_common.h" + +#ifdef CONFIG_RCU_TRACE + +static void rcu_initiate_boost_trace(struct rcu_node *rnp) +{ + if (list_empty(&rnp->blkd_tasks)) + rnp->n_balk_blkd_tasks++; + else if (rnp->exp_tasks == NULL && rnp->gp_tasks == NULL) + rnp->n_balk_exp_gp_tasks++; + else if (rnp->gp_tasks != NULL && rnp->boost_tasks != NULL) + rnp->n_balk_boost_tasks++; + else if (rnp->gp_tasks != NULL && rnp->qsmask != 0) + rnp->n_balk_notblocked++; + else if (rnp->gp_tasks != NULL && + ULONG_CMP_LT(jiffies, rnp->boost_time)) + rnp->n_balk_notyet++; + else + rnp->n_balk_nos++; +} + +#else /* #ifdef CONFIG_RCU_TRACE */ + +static void rcu_initiate_boost_trace(struct rcu_node *rnp) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_TRACE */ + +/* + * Carry out RCU priority boosting on the task indicated by ->exp_tasks + * or ->boost_tasks, advancing the pointer to the next task in the + * ->blkd_tasks list. + * + * Note that irqs must be enabled: boosting the task can block. + * Returns 1 if there are more tasks needing to be boosted. + */ +static int rcu_boost(struct rcu_node *rnp) +{ + unsigned long flags; + struct rt_mutex mtx; + struct task_struct *t; + struct list_head *tb; + + if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL) + return 0; /* Nothing left to boost. */ + + raw_spin_lock_irqsave(&rnp->lock, flags); + + /* + * Recheck under the lock: all tasks in need of boosting + * might exit their RCU read-side critical sections on their own. + */ + if (rnp->exp_tasks == NULL && rnp->boost_tasks == NULL) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return 0; + } + + /* + * Preferentially boost tasks blocking expedited grace periods. + * This cannot starve the normal grace periods because a second + * expedited grace period must boost all blocked tasks, including + * those blocking the pre-existing normal grace period. + */ + if (rnp->exp_tasks != NULL) { + tb = rnp->exp_tasks; + rnp->n_exp_boosts++; + } else { + tb = rnp->boost_tasks; + rnp->n_normal_boosts++; + } + rnp->n_tasks_boosted++; + + /* + * We boost task t by manufacturing an rt_mutex that appears to + * be held by task t. We leave a pointer to that rt_mutex where + * task t can find it, and task t will release the mutex when it + * exits its outermost RCU read-side critical section. Then + * simply acquiring this artificial rt_mutex will boost task + * t's priority. (Thanks to tglx for suggesting this approach!) + * + * Note that task t must acquire rnp->lock to remove itself from + * the ->blkd_tasks list, which it will do from exit() if from + * nowhere else. We therefore are guaranteed that task t will + * stay around at least until we drop rnp->lock. Note that + * rnp->lock also resolves races between our priority boosting + * and task t's exiting its outermost RCU read-side critical + * section. + */ + t = container_of(tb, struct task_struct, rcu_node_entry); + rt_mutex_init_proxy_locked(&mtx, t); + t->rcu_boost_mutex = &mtx; + t->rcu_boosted = 1; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + rt_mutex_lock(&mtx); /* Side effect: boosts task t's priority. */ + rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ + + return rnp->exp_tasks != NULL || rnp->boost_tasks != NULL; +} + +/* + * Timer handler to initiate waking up of boost kthreads that + * have yielded the CPU due to excessive numbers of tasks to + * boost. We wake up the per-rcu_node kthread, which in turn + * will wake up the booster kthread. + */ +static void rcu_boost_kthread_timer(unsigned long arg) +{ + invoke_rcu_node_kthread((struct rcu_node *)arg); +} + +/* + * Priority-boosting kthread. One per leaf rcu_node and one for the + * root rcu_node. + */ +static int rcu_boost_kthread(void *arg) +{ + struct rcu_node *rnp = (struct rcu_node *)arg; + int spincnt = 0; + int more2boost; + + for (;;) { + rnp->boost_kthread_status = RCU_KTHREAD_WAITING; + rcu_wait(rnp->boost_tasks || rnp->exp_tasks); + rnp->boost_kthread_status = RCU_KTHREAD_RUNNING; + more2boost = rcu_boost(rnp); + if (more2boost) + spincnt++; + else + spincnt = 0; + if (spincnt > 10) { + rcu_yield(rcu_boost_kthread_timer, (unsigned long)rnp); + spincnt = 0; + } + } + /* NOTREACHED */ + return 0; +} + +/* + * Check to see if it is time to start boosting RCU readers that are + * blocking the current grace period, and, if so, tell the per-rcu_node + * kthread to start boosting them. If there is an expedited grace + * period in progress, it is always time to boost. + * + * The caller must hold rnp->lock, which this function releases, + * but irqs remain disabled. The ->boost_kthread_task is immortal, + * so we don't need to worry about it going away. + */ +static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) +{ + struct task_struct *t; + + if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) { + rnp->n_balk_exp_gp_tasks++; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + if (rnp->exp_tasks != NULL || + (rnp->gp_tasks != NULL && + rnp->boost_tasks == NULL && + rnp->qsmask == 0 && + ULONG_CMP_GE(jiffies, rnp->boost_time))) { + if (rnp->exp_tasks == NULL) + rnp->boost_tasks = rnp->gp_tasks; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + t = rnp->boost_kthread_task; + if (t != NULL) + wake_up_process(t); + } else { + rcu_initiate_boost_trace(rnp); + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } +} + +/* + * Wake up the per-CPU kthread to invoke RCU callbacks. + */ +static void invoke_rcu_callbacks_kthread(void) +{ + unsigned long flags; + + local_irq_save(flags); + __this_cpu_write(rcu_cpu_has_work, 1); + if (__this_cpu_read(rcu_cpu_kthread_task) == NULL) { + local_irq_restore(flags); + return; + } + wake_up_process(__this_cpu_read(rcu_cpu_kthread_task)); + local_irq_restore(flags); +} + +/* + * Set the affinity of the boost kthread. The CPU-hotplug locks are + * held, so no one should be messing with the existence of the boost + * kthread. + */ +static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, + cpumask_var_t cm) +{ + struct task_struct *t; + + t = rnp->boost_kthread_task; + if (t != NULL) + set_cpus_allowed_ptr(rnp->boost_kthread_task, cm); +} + +#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000) + +/* + * Do priority-boost accounting for the start of a new grace period. + */ +static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) +{ + rnp->boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES; +} + +/* + * Create an RCU-boost kthread for the specified node if one does not + * already exist. We only create this kthread for preemptible RCU. + * Returns zero if all is well, a negated errno otherwise. + */ +static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, + struct rcu_node *rnp, + int rnp_index) +{ + unsigned long flags; + struct sched_param sp; + struct task_struct *t; + + if (&rcu_preempt_state != rsp) + return 0; + rsp->boost = 1; + if (rnp->boost_kthread_task != NULL) + return 0; + t = kthread_create(rcu_boost_kthread, (void *)rnp, + "rcub%d", rnp_index); + if (IS_ERR(t)) + return PTR_ERR(t); + raw_spin_lock_irqsave(&rnp->lock, flags); + rnp->boost_kthread_task = t; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Stop the RCU's per-CPU kthread when its CPU goes offline,. + */ +static void rcu_stop_cpu_kthread(int cpu) +{ + struct task_struct *t; + + /* Stop the CPU's kthread. */ + t = per_cpu(rcu_cpu_kthread_task, cpu); + if (t != NULL) { + per_cpu(rcu_cpu_kthread_task, cpu) = NULL; + kthread_stop(t); + } +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + +static void rcu_kthread_do_work(void) +{ + rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data)); + rcu_do_batch(&rcu_bh_state, &__get_cpu_var(rcu_bh_data)); + rcu_preempt_do_callbacks(); +} + +/* + * Wake up the specified per-rcu_node-structure kthread. + * Because the per-rcu_node kthreads are immortal, we don't need + * to do anything to keep them alive. + */ +static void invoke_rcu_node_kthread(struct rcu_node *rnp) +{ + struct task_struct *t; + + t = rnp->node_kthread_task; + if (t != NULL) + wake_up_process(t); +} + +/* + * Set the specified CPU's kthread to run RT or not, as specified by + * the to_rt argument. The CPU-hotplug locks are held, so the task + * is not going away. + */ +static void rcu_cpu_kthread_setrt(int cpu, int to_rt) +{ + int policy; + struct sched_param sp; + struct task_struct *t; + + t = per_cpu(rcu_cpu_kthread_task, cpu); + if (t == NULL) + return; + if (to_rt) { + policy = SCHED_FIFO; + sp.sched_priority = RCU_KTHREAD_PRIO; + } else { + policy = SCHED_NORMAL; + sp.sched_priority = 0; + } + sched_setscheduler_nocheck(t, policy, &sp); +} + +/* + * Timer handler to initiate the waking up of per-CPU kthreads that + * have yielded the CPU due to excess numbers of RCU callbacks. + * We wake up the per-rcu_node kthread, which in turn will wake up + * the booster kthread. + */ +static void rcu_cpu_kthread_timer(unsigned long arg) +{ + struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg); + struct rcu_node *rnp = rdp->mynode; + + atomic_or(rdp->grpmask, &rnp->wakemask); + invoke_rcu_node_kthread(rnp); +} + +/* + * Drop to non-real-time priority and yield, but only after posting a + * timer that will cause us to regain our real-time priority if we + * remain preempted. Either way, we restore our real-time priority + * before returning. + */ +static void rcu_yield(void (*f)(unsigned long), unsigned long arg) +{ + struct sched_param sp; + struct timer_list yield_timer; + + setup_timer_on_stack(&yield_timer, f, arg); + mod_timer(&yield_timer, jiffies + 2); + sp.sched_priority = 0; + sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp); + set_user_nice(current, 19); + schedule(); + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); + del_timer(&yield_timer); +} + +/* + * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU. + * This can happen while the corresponding CPU is either coming online + * or going offline. We cannot wait until the CPU is fully online + * before starting the kthread, because the various notifier functions + * can wait for RCU grace periods. So we park rcu_cpu_kthread() until + * the corresponding CPU is online. + * + * Return 1 if the kthread needs to stop, 0 otherwise. + * + * Caller must disable bh. This function can momentarily enable it. + */ +static int rcu_cpu_kthread_should_stop(int cpu) +{ + while (cpu_is_offline(cpu) || + !cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu)) || + smp_processor_id() != cpu) { + if (kthread_should_stop()) + return 1; + per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; + per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id(); + local_bh_enable(); + schedule_timeout_uninterruptible(1); + if (!cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu))) + set_cpus_allowed_ptr(current, cpumask_of(cpu)); + local_bh_disable(); + } + per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; + return 0; +} + +/* + * Per-CPU kernel thread that invokes RCU callbacks. This replaces the + * earlier RCU softirq. + */ +static int rcu_cpu_kthread(void *arg) +{ + int cpu = (int)(long)arg; + unsigned long flags; + int spincnt = 0; + unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu); + char work; + char *workp = &per_cpu(rcu_cpu_has_work, cpu); + + for (;;) { + *statusp = RCU_KTHREAD_WAITING; + rcu_wait(*workp != 0 || kthread_should_stop()); + local_bh_disable(); + if (rcu_cpu_kthread_should_stop(cpu)) { + local_bh_enable(); + break; + } + *statusp = RCU_KTHREAD_RUNNING; + per_cpu(rcu_cpu_kthread_loops, cpu)++; + local_irq_save(flags); + work = *workp; + *workp = 0; + local_irq_restore(flags); + if (work) + rcu_kthread_do_work(); + local_bh_enable(); + if (*workp != 0) + spincnt++; + else + spincnt = 0; + if (spincnt > 10) { + *statusp = RCU_KTHREAD_YIELDING; + rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu); + spincnt = 0; + } + } + *statusp = RCU_KTHREAD_STOPPED; + return 0; +} + +/* + * Spawn a per-CPU kthread, setting up affinity and priority. + * Because the CPU hotplug lock is held, no other CPU will be attempting + * to manipulate rcu_cpu_kthread_task. There might be another CPU + * attempting to access it during boot, but the locking in kthread_bind() + * will enforce sufficient ordering. + * + * Please note that we cannot simply refuse to wake up the per-CPU + * kthread because kthreads are created in TASK_UNINTERRUPTIBLE state, + * which can result in softlockup complaints if the task ends up being + * idle for more than a couple of minutes. + * + * However, please note also that we cannot bind the per-CPU kthread to its + * CPU until that CPU is fully online. We also cannot wait until the + * CPU is fully online before we create its per-CPU kthread, as this would + * deadlock the system when CPU notifiers tried waiting for grace + * periods. So we bind the per-CPU kthread to its CPU only if the CPU + * is online. If its CPU is not yet fully online, then the code in + * rcu_cpu_kthread() will wait until it is fully online, and then do + * the binding. + */ +static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu) +{ + struct sched_param sp; + struct task_struct *t; + + if (!rcu_scheduler_fully_active || + per_cpu(rcu_cpu_kthread_task, cpu) != NULL) + return 0; + t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu); + if (IS_ERR(t)) + return PTR_ERR(t); + if (cpu_online(cpu)) + kthread_bind(t, cpu); + per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; + WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL); + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + per_cpu(rcu_cpu_kthread_task, cpu) = t; + wake_up_process(t); /* Get to TASK_INTERRUPTIBLE quickly. */ + return 0; +} + +/* + * Per-rcu_node kthread, which is in charge of waking up the per-CPU + * kthreads when needed. We ignore requests to wake up kthreads + * for offline CPUs, which is OK because force_quiescent_state() + * takes care of this case. + */ +static int rcu_node_kthread(void *arg) +{ + int cpu; + unsigned long flags; + unsigned long mask; + struct rcu_node *rnp = (struct rcu_node *)arg; + struct sched_param sp; + struct task_struct *t; + + for (;;) { + rnp->node_kthread_status = RCU_KTHREAD_WAITING; + rcu_wait(atomic_read(&rnp->wakemask) != 0); + rnp->node_kthread_status = RCU_KTHREAD_RUNNING; + raw_spin_lock_irqsave(&rnp->lock, flags); + mask = atomic_xchg(&rnp->wakemask, 0); + rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */ + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) { + if ((mask & 0x1) == 0) + continue; + preempt_disable(); + t = per_cpu(rcu_cpu_kthread_task, cpu); + if (!cpu_online(cpu) || t == NULL) { + preempt_enable(); + continue; + } + per_cpu(rcu_cpu_has_work, cpu) = 1; + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + preempt_enable(); + } + } + /* NOTREACHED */ + rnp->node_kthread_status = RCU_KTHREAD_STOPPED; + return 0; +} + +/* + * Set the per-rcu_node kthread's affinity to cover all CPUs that are + * served by the rcu_node in question. The CPU hotplug lock is still + * held, so the value of rnp->qsmaskinit will be stable. + * + * We don't include outgoingcpu in the affinity set, use -1 if there is + * no outgoing CPU. If there are no CPUs left in the affinity set, + * this function allows the kthread to execute on any CPU. + */ +static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) +{ + cpumask_var_t cm; + int cpu; + unsigned long mask = rnp->qsmaskinit; + + if (rnp->node_kthread_task == NULL) + return; + if (!alloc_cpumask_var(&cm, GFP_KERNEL)) + return; + cpumask_clear(cm); + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) + if ((mask & 0x1) && cpu != outgoingcpu) + cpumask_set_cpu(cpu, cm); + if (cpumask_weight(cm) == 0) { + cpumask_setall(cm); + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) + cpumask_clear_cpu(cpu, cm); + WARN_ON_ONCE(cpumask_weight(cm) == 0); + } + set_cpus_allowed_ptr(rnp->node_kthread_task, cm); + rcu_boost_kthread_setaffinity(rnp, cm); + free_cpumask_var(cm); +} + +/* + * Spawn a per-rcu_node kthread, setting priority and affinity. + * Called during boot before online/offline can happen, or, if + * during runtime, with the main CPU-hotplug locks held. So only + * one of these can be executing at a time. + */ +static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp, + struct rcu_node *rnp) +{ + unsigned long flags; + int rnp_index = rnp - &rsp->node[0]; + struct sched_param sp; + struct task_struct *t; + + if (!rcu_scheduler_fully_active || + rnp->qsmaskinit == 0) + return 0; + if (rnp->node_kthread_task == NULL) { + t = kthread_create(rcu_node_kthread, (void *)rnp, + "rcun%d", rnp_index); + if (IS_ERR(t)) + return PTR_ERR(t); + raw_spin_lock_irqsave(&rnp->lock, flags); + rnp->node_kthread_task = t; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + sp.sched_priority = 99; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); + wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ + } + return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index); +} + +/* + * Spawn all kthreads -- called as soon as the scheduler is running. + */ +static int __init rcu_spawn_kthreads(void) +{ + int cpu; + struct rcu_node *rnp; + + rcu_scheduler_fully_active = 1; + for_each_possible_cpu(cpu) { + per_cpu(rcu_cpu_has_work, cpu) = 0; + if (cpu_online(cpu)) + (void)rcu_spawn_one_cpu_kthread(cpu); + } + rnp = rcu_get_root(rcu_state); + (void)rcu_spawn_one_node_kthread(rcu_state, rnp); + if (NUM_RCU_NODES > 1) { + rcu_for_each_leaf_node(rcu_state, rnp) + (void)rcu_spawn_one_node_kthread(rcu_state, rnp); + } + return 0; +} +early_initcall(rcu_spawn_kthreads); + +static void __cpuinit rcu_prepare_kthreads(int cpu) +{ + struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu); + struct rcu_node *rnp = rdp->mynode; + + /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ + if (rcu_scheduler_fully_active) { + (void)rcu_spawn_one_cpu_kthread(cpu); + if (rnp->node_kthread_task == NULL) + (void)rcu_spawn_one_node_kthread(rcu_state, rnp); + } +} + +#else /* #ifdef CONFIG_RCU_BOOST */ + +static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) +{ + raw_spin_unlock_irqrestore(&rnp->lock, flags); +} + +static void invoke_rcu_callbacks_kthread(void) +{ + WARN_ON_ONCE(1); +} + +static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) +{ +} + +#ifdef CONFIG_HOTPLUG_CPU + +static void rcu_stop_cpu_kthread(int cpu) +{ +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ + +static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) +{ +} + +static void rcu_cpu_kthread_setrt(int cpu, int to_rt) +{ +} + +static int __init rcu_scheduler_really_started(void) +{ + rcu_scheduler_fully_active = 1; + return 0; +} +early_initcall(rcu_scheduler_really_started); + +static void __cpuinit rcu_prepare_kthreads(int cpu) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_BOOST */ + #ifndef CONFIG_SMP void synchronize_sched_expedited(void) @@ -1187,14 +1936,13 @@ static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff); * * Because it is not legal to invoke rcu_process_callbacks() with irqs * disabled, we do one pass of force_quiescent_state(), then do a - * raise_softirq() to cause rcu_process_callbacks() to be invoked later. - * The per-cpu rcu_dyntick_drain variable controls the sequencing. + * invoke_rcu_core() to cause rcu_process_callbacks() to be invoked + * later. The per-cpu rcu_dyntick_drain variable controls the sequencing. */ int rcu_needs_cpu(int cpu) { int c = 0; int snap; - int snap_nmi; int thatcpu; /* Check for being in the holdoff period. */ @@ -1205,10 +1953,10 @@ int rcu_needs_cpu(int cpu) for_each_online_cpu(thatcpu) { if (thatcpu == cpu) continue; - snap = per_cpu(rcu_dynticks, thatcpu).dynticks; - snap_nmi = per_cpu(rcu_dynticks, thatcpu).dynticks_nmi; + snap = atomic_add_return(0, &per_cpu(rcu_dynticks, + thatcpu).dynticks); smp_mb(); /* Order sampling of snap with end of grace period. */ - if (((snap & 0x1) != 0) || ((snap_nmi & 0x1) != 0)) { + if ((snap & 0x1) != 0) { per_cpu(rcu_dyntick_drain, cpu) = 0; per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1; return rcu_needs_cpu_quick_check(cpu); @@ -1239,7 +1987,7 @@ int rcu_needs_cpu(int cpu) /* If RCU callbacks are still pending, RCU still needs this CPU. */ if (c) - raise_softirq(RCU_SOFTIRQ); + invoke_rcu_core(); return c; } diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index c8e97853b97..3b0c0986afc 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -31,7 +31,7 @@ #include <linux/rcupdate.h> #include <linux/interrupt.h> #include <linux/sched.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <linux/bitops.h> #include <linux/module.h> #include <linux/completion.h> @@ -46,6 +46,22 @@ #define RCU_TREE_NONCORE #include "rcutree.h" +#ifdef CONFIG_RCU_BOOST + +DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); +DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_cpu); +DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); +DECLARE_PER_CPU(char, rcu_cpu_has_work); + +static char convert_kthread_status(unsigned int kthread_status) +{ + if (kthread_status > RCU_KTHREAD_MAX) + return '?'; + return "SRWOY"[kthread_status]; +} + +#endif /* #ifdef CONFIG_RCU_BOOST */ + static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) { if (!rdp->beenonline) @@ -57,14 +73,31 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->passed_quiesc, rdp->passed_quiesc_completed, rdp->qs_pending); #ifdef CONFIG_NO_HZ - seq_printf(m, " dt=%d/%d dn=%d df=%lu", - rdp->dynticks->dynticks, + seq_printf(m, " dt=%d/%d/%d df=%lu", + atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, - rdp->dynticks->dynticks_nmi, + rdp->dynticks->dynticks_nmi_nesting, rdp->dynticks_fqs); #endif /* #ifdef CONFIG_NO_HZ */ seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi); - seq_printf(m, " ql=%ld b=%ld", rdp->qlen, rdp->blimit); + seq_printf(m, " ql=%ld qs=%c%c%c%c", + rdp->qlen, + ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] != + rdp->nxttail[RCU_NEXT_TAIL]], + ".R"[rdp->nxttail[RCU_WAIT_TAIL] != + rdp->nxttail[RCU_NEXT_READY_TAIL]], + ".W"[rdp->nxttail[RCU_DONE_TAIL] != + rdp->nxttail[RCU_WAIT_TAIL]], + ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]); +#ifdef CONFIG_RCU_BOOST + seq_printf(m, " kt=%d/%c/%d ktl=%x", + per_cpu(rcu_cpu_has_work, rdp->cpu), + convert_kthread_status(per_cpu(rcu_cpu_kthread_status, + rdp->cpu)), + per_cpu(rcu_cpu_kthread_cpu, rdp->cpu), + per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff); +#endif /* #ifdef CONFIG_RCU_BOOST */ + seq_printf(m, " b=%ld", rdp->blimit); seq_printf(m, " ci=%lu co=%lu ca=%lu\n", rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted); } @@ -115,13 +148,27 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) rdp->qs_pending); #ifdef CONFIG_NO_HZ seq_printf(m, ",%d,%d,%d,%lu", - rdp->dynticks->dynticks, + atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, - rdp->dynticks->dynticks_nmi, + rdp->dynticks->dynticks_nmi_nesting, rdp->dynticks_fqs); #endif /* #ifdef CONFIG_NO_HZ */ seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi); - seq_printf(m, ",%ld,%ld", rdp->qlen, rdp->blimit); + seq_printf(m, ",%ld,\"%c%c%c%c\"", rdp->qlen, + ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] != + rdp->nxttail[RCU_NEXT_TAIL]], + ".R"[rdp->nxttail[RCU_WAIT_TAIL] != + rdp->nxttail[RCU_NEXT_READY_TAIL]], + ".W"[rdp->nxttail[RCU_DONE_TAIL] != + rdp->nxttail[RCU_WAIT_TAIL]], + ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]); +#ifdef CONFIG_RCU_BOOST + seq_printf(m, ",%d,\"%c\"", + per_cpu(rcu_cpu_has_work, rdp->cpu), + convert_kthread_status(per_cpu(rcu_cpu_kthread_status, + rdp->cpu))); +#endif /* #ifdef CONFIG_RCU_BOOST */ + seq_printf(m, ",%ld", rdp->blimit); seq_printf(m, ",%lu,%lu,%lu\n", rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted); } @@ -130,9 +177,13 @@ static int show_rcudata_csv(struct seq_file *m, void *unused) { seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\","); #ifdef CONFIG_NO_HZ - seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\","); + seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\","); #endif /* #ifdef CONFIG_NO_HZ */ - seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n"); + seq_puts(m, "\"of\",\"ri\",\"ql\",\"qs\""); +#ifdef CONFIG_RCU_BOOST + seq_puts(m, "\"kt\",\"ktl\""); +#endif /* #ifdef CONFIG_RCU_BOOST */ + seq_puts(m, ",\"b\",\"ci\",\"co\",\"ca\"\n"); #ifdef CONFIG_TREE_PREEMPT_RCU seq_puts(m, "\"rcu_preempt:\"\n"); PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data_csv, m); @@ -157,11 +208,76 @@ static const struct file_operations rcudata_csv_fops = { .release = single_release, }; +#ifdef CONFIG_RCU_BOOST + +static void print_one_rcu_node_boost(struct seq_file *m, struct rcu_node *rnp) +{ + seq_printf(m, "%d:%d tasks=%c%c%c%c kt=%c ntb=%lu neb=%lu nnb=%lu " + "j=%04x bt=%04x\n", + rnp->grplo, rnp->grphi, + "T."[list_empty(&rnp->blkd_tasks)], + "N."[!rnp->gp_tasks], + "E."[!rnp->exp_tasks], + "B."[!rnp->boost_tasks], + convert_kthread_status(rnp->boost_kthread_status), + rnp->n_tasks_boosted, rnp->n_exp_boosts, + rnp->n_normal_boosts, + (int)(jiffies & 0xffff), + (int)(rnp->boost_time & 0xffff)); + seq_printf(m, "%s: nt=%lu egt=%lu bt=%lu nb=%lu ny=%lu nos=%lu\n", + " balk", + rnp->n_balk_blkd_tasks, + rnp->n_balk_exp_gp_tasks, + rnp->n_balk_boost_tasks, + rnp->n_balk_notblocked, + rnp->n_balk_notyet, + rnp->n_balk_nos); +} + +static int show_rcu_node_boost(struct seq_file *m, void *unused) +{ + struct rcu_node *rnp; + + rcu_for_each_leaf_node(&rcu_preempt_state, rnp) + print_one_rcu_node_boost(m, rnp); + return 0; +} + +static int rcu_node_boost_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcu_node_boost, NULL); +} + +static const struct file_operations rcu_node_boost_fops = { + .owner = THIS_MODULE, + .open = rcu_node_boost_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +/* + * Create the rcuboost debugfs entry. Standard error return. + */ +static int rcu_boost_trace_create_file(struct dentry *rcudir) +{ + return !debugfs_create_file("rcuboost", 0444, rcudir, NULL, + &rcu_node_boost_fops); +} + +#else /* #ifdef CONFIG_RCU_BOOST */ + +static int rcu_boost_trace_create_file(struct dentry *rcudir) +{ + return 0; /* There cannot be an error if we didn't create it! */ +} + +#endif /* #else #ifdef CONFIG_RCU_BOOST */ + static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) { unsigned long gpnum; int level = 0; - int phase; struct rcu_node *rnp; gpnum = rsp->gpnum; @@ -178,13 +294,11 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) seq_puts(m, "\n"); level = rnp->level; } - phase = gpnum & 0x1; - seq_printf(m, "%lx/%lx %c%c>%c%c %d:%d ^%d ", + seq_printf(m, "%lx/%lx %c%c>%c %d:%d ^%d ", rnp->qsmask, rnp->qsmaskinit, - "T."[list_empty(&rnp->blocked_tasks[phase])], - "E."[list_empty(&rnp->blocked_tasks[phase + 2])], - "T."[list_empty(&rnp->blocked_tasks[!phase])], - "E."[list_empty(&rnp->blocked_tasks[!phase + 2])], + ".G"[rnp->gp_tasks != NULL], + ".E"[rnp->exp_tasks != NULL], + ".T"[!list_empty(&rnp->blkd_tasks)], rnp->grplo, rnp->grphi, rnp->grpnum); } seq_puts(m, "\n"); @@ -216,16 +330,35 @@ static const struct file_operations rcuhier_fops = { .release = single_release, }; +static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp) +{ + unsigned long flags; + unsigned long completed; + unsigned long gpnum; + unsigned long gpage; + unsigned long gpmax; + struct rcu_node *rnp = &rsp->node[0]; + + raw_spin_lock_irqsave(&rnp->lock, flags); + completed = rsp->completed; + gpnum = rsp->gpnum; + if (rsp->completed == rsp->gpnum) + gpage = 0; + else + gpage = jiffies - rsp->gp_start; + gpmax = rsp->gp_max; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + seq_printf(m, "%s: completed=%ld gpnum=%lu age=%ld max=%ld\n", + rsp->name, completed, gpnum, gpage, gpmax); +} + static int show_rcugp(struct seq_file *m, void *unused) { #ifdef CONFIG_TREE_PREEMPT_RCU - seq_printf(m, "rcu_preempt: completed=%ld gpnum=%lu\n", - rcu_preempt_state.completed, rcu_preempt_state.gpnum); + show_one_rcugp(m, &rcu_preempt_state); #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - seq_printf(m, "rcu_sched: completed=%ld gpnum=%lu\n", - rcu_sched_state.completed, rcu_sched_state.gpnum); - seq_printf(m, "rcu_bh: completed=%ld gpnum=%lu\n", - rcu_bh_state.completed, rcu_bh_state.gpnum); + show_one_rcugp(m, &rcu_sched_state); + show_one_rcugp(m, &rcu_bh_state); return 0; } @@ -298,6 +431,29 @@ static const struct file_operations rcu_pending_fops = { .release = single_release, }; +static int show_rcutorture(struct seq_file *m, void *unused) +{ + seq_printf(m, "rcutorture test sequence: %lu %s\n", + rcutorture_testseq >> 1, + (rcutorture_testseq & 0x1) ? "(test in progress)" : ""); + seq_printf(m, "rcutorture update version number: %lu\n", + rcutorture_vernum); + return 0; +} + +static int rcutorture_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcutorture, NULL); +} + +static const struct file_operations rcutorture_fops = { + .owner = THIS_MODULE, + .open = rcutorture_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static struct dentry *rcudir; static int __init rcutree_trace_init(void) @@ -318,6 +474,9 @@ static int __init rcutree_trace_init(void) if (!retval) goto free_out; + if (rcu_boost_trace_create_file(rcudir)) + goto free_out; + retval = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops); if (!retval) goto free_out; @@ -331,6 +490,11 @@ static int __init rcutree_trace_init(void) NULL, &rcu_pending_fops); if (!retval) goto free_out; + + retval = debugfs_create_file("rcutorture", 0444, rcudir, + NULL, &rcutorture_fops); + if (!retval) + goto free_out; return 0; free_out: debugfs_remove_recursive(rcudir); diff --git a/kernel/resource.c b/kernel/resource.c index 798e2fae2a0..3ff40178dce 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -38,6 +38,14 @@ struct resource iomem_resource = { }; EXPORT_SYMBOL(iomem_resource); +/* constraints to be met while allocating resources */ +struct resource_constraint { + resource_size_t min, max, align; + resource_size_t (*alignf)(void *, const struct resource *, + resource_size_t, resource_size_t); + void *alignf_data; +}; + static DEFINE_RWLOCK(resource_lock); static void *r_next(struct seq_file *m, void *v, loff_t *pos) @@ -384,16 +392,13 @@ static bool resource_contains(struct resource *res1, struct resource *res2) } /* - * Find empty slot in the resource tree given range and alignment. + * Find empty slot in the resource tree with the given range and + * alignment constraints */ -static int find_resource(struct resource *root, struct resource *new, - resource_size_t size, resource_size_t min, - resource_size_t max, resource_size_t align, - resource_size_t (*alignf)(void *, - const struct resource *, - resource_size_t, - resource_size_t), - void *alignf_data) +static int __find_resource(struct resource *root, struct resource *old, + struct resource *new, + resource_size_t size, + struct resource_constraint *constraint) { struct resource *this = root->child; struct resource tmp = *new, avail, alloc; @@ -404,25 +409,26 @@ static int find_resource(struct resource *root, struct resource *new, * Skip past an allocated resource that starts at 0, since the assignment * of this->start - 1 to tmp->end below would cause an underflow. */ - if (this && this->start == 0) { - tmp.start = this->end + 1; + if (this && this->start == root->start) { + tmp.start = (this == old) ? old->start : this->end + 1; this = this->sibling; } for(;;) { if (this) - tmp.end = this->start - 1; + tmp.end = (this == old) ? this->end : this->start - 1; else tmp.end = root->end; - resource_clip(&tmp, min, max); + resource_clip(&tmp, constraint->min, constraint->max); arch_remove_reservations(&tmp); /* Check for overflow after ALIGN() */ avail = *new; - avail.start = ALIGN(tmp.start, align); + avail.start = ALIGN(tmp.start, constraint->align); avail.end = tmp.end; if (avail.start >= tmp.start) { - alloc.start = alignf(alignf_data, &avail, size, align); + alloc.start = constraint->alignf(constraint->alignf_data, &avail, + size, constraint->align); alloc.end = alloc.start + size - 1; if (resource_contains(&avail, &alloc)) { new->start = alloc.start; @@ -432,14 +438,75 @@ static int find_resource(struct resource *root, struct resource *new, } if (!this) break; - tmp.start = this->end + 1; + if (this != old) + tmp.start = this->end + 1; this = this->sibling; } return -EBUSY; } +/* + * Find empty slot in the resource tree given range and alignment. + */ +static int find_resource(struct resource *root, struct resource *new, + resource_size_t size, + struct resource_constraint *constraint) +{ + return __find_resource(root, NULL, new, size, constraint); +} + /** - * allocate_resource - allocate empty slot in the resource tree given range & alignment + * reallocate_resource - allocate a slot in the resource tree given range & alignment. + * The resource will be relocated if the new size cannot be reallocated in the + * current location. + * + * @root: root resource descriptor + * @old: resource descriptor desired by caller + * @newsize: new size of the resource descriptor + * @constraint: the size and alignment constraints to be met. + */ +int reallocate_resource(struct resource *root, struct resource *old, + resource_size_t newsize, + struct resource_constraint *constraint) +{ + int err=0; + struct resource new = *old; + struct resource *conflict; + + write_lock(&resource_lock); + + if ((err = __find_resource(root, old, &new, newsize, constraint))) + goto out; + + if (resource_contains(&new, old)) { + old->start = new.start; + old->end = new.end; + goto out; + } + + if (old->child) { + err = -EBUSY; + goto out; + } + + if (resource_contains(old, &new)) { + old->start = new.start; + old->end = new.end; + } else { + __release_resource(old); + *old = new; + conflict = __request_resource(root, old); + BUG_ON(conflict); + } +out: + write_unlock(&resource_lock); + return err; +} + + +/** + * allocate_resource - allocate empty slot in the resource tree given range & alignment. + * The resource will be reallocated with a new size if it was already allocated * @root: root resource descriptor * @new: resource descriptor desired by caller * @size: requested resource region size @@ -459,12 +526,25 @@ int allocate_resource(struct resource *root, struct resource *new, void *alignf_data) { int err; + struct resource_constraint constraint; if (!alignf) alignf = simple_align_resource; + constraint.min = min; + constraint.max = max; + constraint.align = align; + constraint.alignf = alignf; + constraint.alignf_data = alignf_data; + + if ( new->parent ) { + /* resource is already allocated, try reallocating with + the new constraints */ + return reallocate_resource(root, new, size, &constraint); + } + write_lock(&resource_lock); - err = find_resource(root, new, size, min, max, align, alignf, alignf_data); + err = find_resource(root, new, size, &constraint); if (err >= 0 && __request_resource(root, new)) err = -EBUSY; write_unlock(&resource_lock); diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index ab449117aaf..255e1662acd 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -890,7 +890,7 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name) { lock->owner = NULL; raw_spin_lock_init(&lock->wait_lock); - plist_head_init_raw(&lock->wait_list, &lock->wait_lock); + plist_head_init(&lock->wait_list); debug_rt_mutex_init(lock, name); } diff --git a/kernel/rwsem.c b/kernel/rwsem.c index cae050b05f5..9f48f3d82e9 100644 --- a/kernel/rwsem.c +++ b/kernel/rwsem.c @@ -11,7 +11,7 @@ #include <linux/rwsem.h> #include <asm/system.h> -#include <asm/atomic.h> +#include <linux/atomic.h> /* * lock for reading @@ -117,15 +117,6 @@ void down_read_nested(struct rw_semaphore *sem, int subclass) EXPORT_SYMBOL(down_read_nested); -void down_read_non_owner(struct rw_semaphore *sem) -{ - might_sleep(); - - __down_read(sem); -} - -EXPORT_SYMBOL(down_read_non_owner); - void down_write_nested(struct rw_semaphore *sem, int subclass) { might_sleep(); @@ -136,13 +127,6 @@ void down_write_nested(struct rw_semaphore *sem, int subclass) EXPORT_SYMBOL(down_write_nested); -void up_read_non_owner(struct rw_semaphore *sem) -{ - __up_read(sem); -} - -EXPORT_SYMBOL(up_read_non_owner); - #endif diff --git a/kernel/sched.c b/kernel/sched.c index 312f8b95c2d..ccacdbdecf4 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -75,6 +75,9 @@ #include <asm/tlb.h> #include <asm/irq_regs.h> #include <asm/mutex.h> +#ifdef CONFIG_PARAVIRT +#include <asm/paravirt.h> +#endif #include "sched_cpupri.h" #include "workqueue_sched.h" @@ -124,7 +127,7 @@ static inline int rt_policy(int policy) { - if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR)) + if (policy == SCHED_FIFO || policy == SCHED_RR) return 1; return 0; } @@ -231,7 +234,7 @@ static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b) #endif /* - * sched_domains_mutex serializes calls to arch_init_sched_domains, + * sched_domains_mutex serializes calls to init_sched_domains, * detach_destroy_domains and partition_sched_domains. */ static DEFINE_MUTEX(sched_domains_mutex); @@ -292,7 +295,7 @@ static DEFINE_SPINLOCK(task_group_lock); * (The default weight is 1024 - so there's no practical * limitation from this.) */ -#define MIN_SHARES 2 +#define MIN_SHARES (1UL << 1) #define MAX_SHARES (1UL << 18) static int root_task_group_load = ROOT_TASK_GROUP_LOAD; @@ -312,6 +315,9 @@ struct cfs_rq { u64 exec_clock; u64 min_vruntime; +#ifndef CONFIG_64BIT + u64 min_vruntime_copy; +#endif struct rb_root tasks_timeline; struct rb_node *rb_leftmost; @@ -325,7 +331,9 @@ struct cfs_rq { */ struct sched_entity *curr, *next, *last, *skip; +#ifdef CONFIG_SCHED_DEBUG unsigned int nr_spread_over; +#endif #ifdef CONFIG_FAIR_GROUP_SCHED struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */ @@ -417,6 +425,8 @@ struct rt_rq { */ struct root_domain { atomic_t refcount; + atomic_t rto_count; + struct rcu_head rcu; cpumask_var_t span; cpumask_var_t online; @@ -425,7 +435,6 @@ struct root_domain { * one runnable RT task. */ cpumask_var_t rto_mask; - atomic_t rto_count; struct cpupri cpupri; }; @@ -460,7 +469,7 @@ struct rq { u64 nohz_stamp; unsigned char nohz_balance_kick; #endif - unsigned int skip_clock_update; + int skip_clock_update; /* capture load from *all* tasks on this cpu: */ struct load_weight load; @@ -522,6 +531,12 @@ struct rq { #ifdef CONFIG_IRQ_TIME_ACCOUNTING u64 prev_irq_time; #endif +#ifdef CONFIG_PARAVIRT + u64 prev_steal_time; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + u64 prev_steal_time_rq; +#endif /* calc_load related fields */ unsigned long calc_load_update; @@ -553,6 +568,10 @@ struct rq { unsigned int ttwu_count; unsigned int ttwu_local; #endif + +#ifdef CONFIG_SMP + struct task_struct *wake_list; +#endif }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); @@ -571,7 +590,6 @@ static inline int cpu_of(struct rq *rq) #define rcu_dereference_check_sched_domain(p) \ rcu_dereference_check((p), \ - rcu_read_lock_sched_held() || \ lockdep_is_held(&sched_domains_mutex)) /* @@ -595,10 +613,10 @@ static inline int cpu_of(struct rq *rq) /* * Return the group to which this tasks belongs. * - * We use task_subsys_state_check() and extend the RCU verification - * with lockdep_is_held(&task_rq(p)->lock) because cpu_cgroup_attach() - * holds that lock for each task it moves into the cgroup. Therefore - * by holding that lock, we pin the task to the current cgroup. + * We use task_subsys_state_check() and extend the RCU verification with + * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each + * task it moves into the cgroup. Therefore by holding either of those locks, + * we pin the task to the current cgroup. */ static inline struct task_group *task_group(struct task_struct *p) { @@ -606,6 +624,7 @@ static inline struct task_group *task_group(struct task_struct *p) struct cgroup_subsys_state *css; css = task_subsys_state_check(p, cpu_cgroup_subsys_id, + lockdep_is_held(&p->pi_lock) || lockdep_is_held(&task_rq(p)->lock)); tg = container_of(css, struct task_group, css); @@ -642,7 +661,7 @@ static void update_rq_clock(struct rq *rq) { s64 delta; - if (rq->skip_clock_update) + if (rq->skip_clock_update > 0) return; delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; @@ -838,18 +857,39 @@ static inline int task_current(struct rq *rq, struct task_struct *p) return rq->curr == p; } -#ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline int task_running(struct rq *rq, struct task_struct *p) { +#ifdef CONFIG_SMP + return p->on_cpu; +#else return task_current(rq, p); +#endif } +#ifndef __ARCH_WANT_UNLOCKED_CTXSW static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) { +#ifdef CONFIG_SMP + /* + * We can optimise this out completely for !SMP, because the + * SMP rebalancing from interrupt is the only thing that cares + * here. + */ + next->on_cpu = 1; +#endif } static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) { +#ifdef CONFIG_SMP + /* + * After ->on_cpu is cleared, the task can be moved to a different CPU. + * We must ensure this doesn't happen until the switch is completely + * finished. + */ + smp_wmb(); + prev->on_cpu = 0; +#endif #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ rq->lock.owner = current; @@ -865,15 +905,6 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) } #else /* __ARCH_WANT_UNLOCKED_CTXSW */ -static inline int task_running(struct rq *rq, struct task_struct *p) -{ -#ifdef CONFIG_SMP - return p->oncpu; -#else - return task_current(rq, p); -#endif -} - static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) { #ifdef CONFIG_SMP @@ -882,7 +913,7 @@ static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) * SMP rebalancing from interrupt is the only thing that cares * here. */ - next->oncpu = 1; + next->on_cpu = 1; #endif #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW raw_spin_unlock_irq(&rq->lock); @@ -895,12 +926,12 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) { #ifdef CONFIG_SMP /* - * After ->oncpu is cleared, the task can be moved to a different CPU. + * After ->on_cpu is cleared, the task can be moved to a different CPU. * We must ensure this doesn't happen until the switch is completely * finished. */ smp_wmb(); - prev->oncpu = 0; + prev->on_cpu = 0; #endif #ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW local_irq_enable(); @@ -909,23 +940,15 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ /* - * Check whether the task is waking, we use this to synchronize ->cpus_allowed - * against ttwu(). - */ -static inline int task_is_waking(struct task_struct *p) -{ - return unlikely(p->state == TASK_WAKING); -} - -/* - * __task_rq_lock - lock the runqueue a given task resides on. - * Must be called interrupts disabled. + * __task_rq_lock - lock the rq @p resides on. */ static inline struct rq *__task_rq_lock(struct task_struct *p) __acquires(rq->lock) { struct rq *rq; + lockdep_assert_held(&p->pi_lock); + for (;;) { rq = task_rq(p); raw_spin_lock(&rq->lock); @@ -936,22 +959,22 @@ static inline struct rq *__task_rq_lock(struct task_struct *p) } /* - * task_rq_lock - lock the runqueue a given task resides on and disable - * interrupts. Note the ordering: we can safely lookup the task_rq without - * explicitly disabling preemption. + * task_rq_lock - lock p->pi_lock and lock the rq @p resides on. */ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) + __acquires(p->pi_lock) __acquires(rq->lock) { struct rq *rq; for (;;) { - local_irq_save(*flags); + raw_spin_lock_irqsave(&p->pi_lock, *flags); rq = task_rq(p); raw_spin_lock(&rq->lock); if (likely(rq == task_rq(p))) return rq; - raw_spin_unlock_irqrestore(&rq->lock, *flags); + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, *flags); } } @@ -961,10 +984,13 @@ static void __task_rq_unlock(struct rq *rq) raw_spin_unlock(&rq->lock); } -static inline void task_rq_unlock(struct rq *rq, unsigned long *flags) +static inline void +task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags) __releases(rq->lock) + __releases(p->pi_lock) { - raw_spin_unlock_irqrestore(&rq->lock, *flags); + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, *flags); } /* @@ -1193,11 +1219,17 @@ int get_nohz_timer_target(void) int i; struct sched_domain *sd; + rcu_read_lock(); for_each_domain(cpu, sd) { - for_each_cpu(i, sched_domain_span(sd)) - if (!idle_cpu(i)) - return i; + for_each_cpu(i, sched_domain_span(sd)) { + if (!idle_cpu(i)) { + cpu = i; + goto unlock; + } + } } +unlock: + rcu_read_unlock(); return cpu; } /* @@ -1307,15 +1339,27 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight, { u64 tmp; + /* + * weight can be less than 2^SCHED_LOAD_RESOLUTION for task group sched + * entities since MIN_SHARES = 2. Treat weight as 1 if less than + * 2^SCHED_LOAD_RESOLUTION. + */ + if (likely(weight > (1UL << SCHED_LOAD_RESOLUTION))) + tmp = (u64)delta_exec * scale_load_down(weight); + else + tmp = (u64)delta_exec; + if (!lw->inv_weight) { - if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST)) + unsigned long w = scale_load_down(lw->weight); + + if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST)) lw->inv_weight = 1; + else if (unlikely(!w)) + lw->inv_weight = WMULT_CONST; else - lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2) - / (lw->weight+1); + lw->inv_weight = WMULT_CONST / w; } - tmp = (u64)delta_exec * weight; /* * Check whether we'd overflow the 64-bit multiplication: */ @@ -1532,38 +1576,6 @@ static unsigned long cpu_avg_load_per_task(int cpu) return rq->avg_load_per_task; } -#ifdef CONFIG_FAIR_GROUP_SCHED - -/* - * Compute the cpu's hierarchical load factor for each task group. - * This needs to be done in a top-down fashion because the load of a child - * group is a fraction of its parents load. - */ -static int tg_load_down(struct task_group *tg, void *data) -{ - unsigned long load; - long cpu = (long)data; - - if (!tg->parent) { - load = cpu_rq(cpu)->load.weight; - } else { - load = tg->parent->cfs_rq[cpu]->h_load; - load *= tg->se[cpu]->load.weight; - load /= tg->parent->cfs_rq[cpu]->load.weight + 1; - } - - tg->cfs_rq[cpu]->h_load = load; - - return 0; -} - -static void update_h_load(long cpu) -{ - walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); -} - -#endif - #ifdef CONFIG_PREEMPT static void double_rq_lock(struct rq *rq1, struct rq *rq2); @@ -1755,17 +1767,20 @@ static void dec_nr_running(struct rq *rq) static void set_load_weight(struct task_struct *p) { + int prio = p->static_prio - MAX_RT_PRIO; + struct load_weight *load = &p->se.load; + /* * SCHED_IDLE tasks get minimal weight: */ if (p->policy == SCHED_IDLE) { - p->se.load.weight = WEIGHT_IDLEPRIO; - p->se.load.inv_weight = WMULT_IDLEPRIO; + load->weight = scale_load(WEIGHT_IDLEPRIO); + load->inv_weight = WMULT_IDLEPRIO; return; } - p->se.load.weight = prio_to_weight[p->static_prio - MAX_RT_PRIO]; - p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO]; + load->weight = scale_load(prio_to_weight[prio]); + load->inv_weight = prio_to_wmult[prio]; } static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) @@ -1773,7 +1788,6 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) update_rq_clock(rq); sched_info_queued(p); p->sched_class->enqueue_task(rq, p, flags); - p->se.on_rq = 1; } static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) @@ -1781,7 +1795,6 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) update_rq_clock(rq); sched_info_dequeued(p); p->sched_class->dequeue_task(rq, p, flags); - p->se.on_rq = 0; } /* @@ -1916,10 +1929,28 @@ void account_system_vtime(struct task_struct *curr) } EXPORT_SYMBOL_GPL(account_system_vtime); -static void update_rq_clock_task(struct rq *rq, s64 delta) +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#ifdef CONFIG_PARAVIRT +static inline u64 steal_ticks(u64 steal) { - s64 irq_delta; + if (unlikely(steal > NSEC_PER_SEC)) + return div_u64(steal, TICK_NSEC); + + return __iter_div_u64_rem(steal, TICK_NSEC, &steal); +} +#endif +static void update_rq_clock_task(struct rq *rq, s64 delta) +{ +/* + * In theory, the compile should just see 0 here, and optimize out the call + * to sched_rt_avg_update. But I don't trust it... + */ +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) + s64 steal = 0, irq_delta = 0; +#endif +#ifdef CONFIG_IRQ_TIME_ACCOUNTING irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; /* @@ -1942,12 +1973,35 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->prev_irq_time += irq_delta; delta -= irq_delta; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + if (static_branch((¶virt_steal_rq_enabled))) { + u64 st; + + steal = paravirt_steal_clock(cpu_of(rq)); + steal -= rq->prev_steal_time_rq; + + if (unlikely(steal > delta)) + steal = delta; + + st = steal_ticks(steal); + steal = st * TICK_NSEC; + + rq->prev_steal_time_rq += steal; + + delta -= steal; + } +#endif + rq->clock_task += delta; - if (irq_delta && sched_feat(NONIRQ_POWER)) - sched_rt_avg_update(rq, irq_delta); +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) + if ((irq_delta + steal) && sched_feat(NONTASK_POWER)) + sched_rt_avg_update(rq, irq_delta + steal); +#endif } +#ifdef CONFIG_IRQ_TIME_ACCOUNTING static int irqtime_account_hi_update(void) { struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; @@ -1982,12 +2036,7 @@ static int irqtime_account_si_update(void) #define sched_clock_irqtime (0) -static void update_rq_clock_task(struct rq *rq, s64 delta) -{ - rq->clock_task += delta; -} - -#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ +#endif #include "sched_idletask.c" #include "sched_fair.c" @@ -2116,7 +2165,7 @@ static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) * A queue event has occurred, and we're going to schedule. In * this case, we can save a useless back to back clock update. */ - if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr)) + if (rq->curr->on_rq && test_tsk_need_resched(rq->curr)) rq->skip_clock_update = 1; } @@ -2162,13 +2211,28 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) */ WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING && !(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)); + +#ifdef CONFIG_LOCKDEP + /* + * The caller should hold either p->pi_lock or rq->lock, when changing + * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks. + * + * sched_move_task() holds both and thus holding either pins the cgroup, + * see set_task_rq(). + * + * Furthermore, all task_rq users should acquire both locks, see + * task_rq_lock(). + */ + WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) || + lockdep_is_held(&task_rq(p)->lock))); +#endif #endif trace_sched_migrate_task(p, new_cpu); if (task_cpu(p) != new_cpu) { p->se.nr_migrations++; - perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 1, NULL, 0); + perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0); } __set_task_cpu(p, new_cpu); @@ -2182,19 +2246,6 @@ struct migration_arg { static int migration_cpu_stop(void *data); /* - * The task's runqueue lock must be held. - * Returns true if you have to wait for migration thread. - */ -static bool migrate_task(struct task_struct *p, struct rq *rq) -{ - /* - * If the task is not on a runqueue (and not running), then - * the next wake-up will properly place the task. - */ - return p->se.on_rq || task_running(rq, p); -} - -/* * wait_task_inactive - wait for a thread to unschedule. * * If @match_state is nonzero, it's the @p->state value just checked and @@ -2251,11 +2302,11 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) rq = task_rq_lock(p, &flags); trace_sched_wait_task(p); running = task_running(rq, p); - on_rq = p->se.on_rq; + on_rq = p->on_rq; ncsw = 0; if (!match_state || p->state == match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); /* * If it changed from the expected state, bail out now. @@ -2330,7 +2381,7 @@ EXPORT_SYMBOL_GPL(kick_process); #ifdef CONFIG_SMP /* - * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held. + * ->cpus_allowed is protected by both rq->lock and p->pi_lock */ static int select_fallback_rq(int cpu, struct task_struct *p) { @@ -2363,12 +2414,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p) } /* - * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable. + * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. */ static inline -int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags) +int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags) { - int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags); + int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags); /* * In order not to call set_task_cpu() on a blocking task we need @@ -2394,27 +2445,63 @@ static void update_avg(u64 *avg, u64 sample) } #endif -static inline void ttwu_activate(struct task_struct *p, struct rq *rq, - bool is_sync, bool is_migrate, bool is_local, - unsigned long en_flags) +static void +ttwu_stat(struct task_struct *p, int cpu, int wake_flags) { - schedstat_inc(p, se.statistics.nr_wakeups); - if (is_sync) - schedstat_inc(p, se.statistics.nr_wakeups_sync); - if (is_migrate) - schedstat_inc(p, se.statistics.nr_wakeups_migrate); - if (is_local) +#ifdef CONFIG_SCHEDSTATS + struct rq *rq = this_rq(); + +#ifdef CONFIG_SMP + int this_cpu = smp_processor_id(); + + if (cpu == this_cpu) { + schedstat_inc(rq, ttwu_local); schedstat_inc(p, se.statistics.nr_wakeups_local); - else + } else { + struct sched_domain *sd; + schedstat_inc(p, se.statistics.nr_wakeups_remote); + rcu_read_lock(); + for_each_domain(this_cpu, sd) { + if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { + schedstat_inc(sd, ttwu_wake_remote); + break; + } + } + rcu_read_unlock(); + } + + if (wake_flags & WF_MIGRATED) + schedstat_inc(p, se.statistics.nr_wakeups_migrate); +#endif /* CONFIG_SMP */ + + schedstat_inc(rq, ttwu_count); + schedstat_inc(p, se.statistics.nr_wakeups); + + if (wake_flags & WF_SYNC) + schedstat_inc(p, se.statistics.nr_wakeups_sync); + +#endif /* CONFIG_SCHEDSTATS */ +} + +static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) +{ activate_task(rq, p, en_flags); + p->on_rq = 1; + + /* if a worker is waking up, notify workqueue */ + if (p->flags & PF_WQ_WORKER) + wq_worker_waking_up(p, cpu_of(rq)); } -static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, - int wake_flags, bool success) +/* + * Mark the task runnable and perform wakeup-preemption. + */ +static void +ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) { - trace_sched_wakeup(p, success); + trace_sched_wakeup(p, true); check_preempt_curr(rq, p, wake_flags); p->state = TASK_RUNNING; @@ -2422,7 +2509,7 @@ static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, if (p->sched_class->task_woken) p->sched_class->task_woken(rq, p); - if (unlikely(rq->idle_stamp)) { + if (rq->idle_stamp) { u64 delta = rq->clock - rq->idle_stamp; u64 max = 2*sysctl_sched_migration_cost; @@ -2433,9 +2520,151 @@ static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, rq->idle_stamp = 0; } #endif - /* if a worker is waking up, notify workqueue */ - if ((p->flags & PF_WQ_WORKER) && success) - wq_worker_waking_up(p, cpu_of(rq)); +} + +static void +ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags) +{ +#ifdef CONFIG_SMP + if (p->sched_contributes_to_load) + rq->nr_uninterruptible--; +#endif + + ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_WAKING); + ttwu_do_wakeup(rq, p, wake_flags); +} + +/* + * Called in case the task @p isn't fully descheduled from its runqueue, + * in this case we must do a remote wakeup. Its a 'light' wakeup though, + * since all we need to do is flip p->state to TASK_RUNNING, since + * the task is still ->on_rq. + */ +static int ttwu_remote(struct task_struct *p, int wake_flags) +{ + struct rq *rq; + int ret = 0; + + rq = __task_rq_lock(p); + if (p->on_rq) { + ttwu_do_wakeup(rq, p, wake_flags); + ret = 1; + } + __task_rq_unlock(rq); + + return ret; +} + +#ifdef CONFIG_SMP +static void sched_ttwu_do_pending(struct task_struct *list) +{ + struct rq *rq = this_rq(); + + raw_spin_lock(&rq->lock); + + while (list) { + struct task_struct *p = list; + list = list->wake_entry; + ttwu_do_activate(rq, p, 0); + } + + raw_spin_unlock(&rq->lock); +} + +#ifdef CONFIG_HOTPLUG_CPU + +static void sched_ttwu_pending(void) +{ + struct rq *rq = this_rq(); + struct task_struct *list = xchg(&rq->wake_list, NULL); + + if (!list) + return; + + sched_ttwu_do_pending(list); +} + +#endif /* CONFIG_HOTPLUG_CPU */ + +void scheduler_ipi(void) +{ + struct rq *rq = this_rq(); + struct task_struct *list = xchg(&rq->wake_list, NULL); + + if (!list) + return; + + /* + * Not all reschedule IPI handlers call irq_enter/irq_exit, since + * traditionally all their work was done from the interrupt return + * path. Now that we actually do some work, we need to make sure + * we do call them. + * + * Some archs already do call them, luckily irq_enter/exit nest + * properly. + * + * Arguably we should visit all archs and update all handlers, + * however a fair share of IPIs are still resched only so this would + * somewhat pessimize the simple resched case. + */ + irq_enter(); + sched_ttwu_do_pending(list); + irq_exit(); +} + +static void ttwu_queue_remote(struct task_struct *p, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct task_struct *next = rq->wake_list; + + for (;;) { + struct task_struct *old = next; + + p->wake_entry = next; + next = cmpxchg(&rq->wake_list, old, p); + if (next == old) + break; + } + + if (!next) + smp_send_reschedule(cpu); +} + +#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW +static int ttwu_activate_remote(struct task_struct *p, int wake_flags) +{ + struct rq *rq; + int ret = 0; + + rq = __task_rq_lock(p); + if (p->on_cpu) { + ttwu_activate(rq, p, ENQUEUE_WAKEUP); + ttwu_do_wakeup(rq, p, wake_flags); + ret = 1; + } + __task_rq_unlock(rq); + + return ret; + +} +#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ +#endif /* CONFIG_SMP */ + +static void ttwu_queue(struct task_struct *p, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + +#if defined(CONFIG_SMP) + if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) { + sched_clock_cpu(cpu); /* sync clocks x-cpu */ + ttwu_queue_remote(p, cpu); + return; + } +#endif + + raw_spin_lock(&rq->lock); + ttwu_do_activate(rq, p, 0); + raw_spin_unlock(&rq->lock); } /** @@ -2453,92 +2682,66 @@ static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, * Returns %true if @p was woken up, %false if it was already running * or @state didn't match @p's state. */ -static int try_to_wake_up(struct task_struct *p, unsigned int state, - int wake_flags) +static int +try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) { - int cpu, orig_cpu, this_cpu, success = 0; unsigned long flags; - unsigned long en_flags = ENQUEUE_WAKEUP; - struct rq *rq; - - this_cpu = get_cpu(); + int cpu, success = 0; smp_wmb(); - rq = task_rq_lock(p, &flags); + raw_spin_lock_irqsave(&p->pi_lock, flags); if (!(p->state & state)) goto out; - if (p->se.on_rq) - goto out_running; - + success = 1; /* we're going to change ->state */ cpu = task_cpu(p); - orig_cpu = cpu; -#ifdef CONFIG_SMP - if (unlikely(task_running(rq, p))) - goto out_activate; + if (p->on_rq && ttwu_remote(p, wake_flags)) + goto stat; +#ifdef CONFIG_SMP /* - * In order to handle concurrent wakeups and release the rq->lock - * we put the task in TASK_WAKING state. - * - * First fix up the nr_uninterruptible count: + * If the owning (remote) cpu is still in the middle of schedule() with + * this task as prev, wait until its done referencing the task. */ - if (task_contributes_to_load(p)) { - if (likely(cpu_online(orig_cpu))) - rq->nr_uninterruptible--; - else - this_rq()->nr_uninterruptible--; + while (p->on_cpu) { +#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW + /* + * In case the architecture enables interrupts in + * context_switch(), we cannot busy wait, since that + * would lead to deadlocks when an interrupt hits and + * tries to wake up @prev. So bail and do a complete + * remote wakeup. + */ + if (ttwu_activate_remote(p, wake_flags)) + goto stat; +#else + cpu_relax(); +#endif } + /* + * Pairs with the smp_wmb() in finish_lock_switch(). + */ + smp_rmb(); + + p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; - if (p->sched_class->task_waking) { - p->sched_class->task_waking(rq, p); - en_flags |= ENQUEUE_WAKING; - } + if (p->sched_class->task_waking) + p->sched_class->task_waking(p); - cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags); - if (cpu != orig_cpu) + cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags); + if (task_cpu(p) != cpu) { + wake_flags |= WF_MIGRATED; set_task_cpu(p, cpu); - __task_rq_unlock(rq); - - rq = cpu_rq(cpu); - raw_spin_lock(&rq->lock); - - /* - * We migrated the task without holding either rq->lock, however - * since the task is not on the task list itself, nobody else - * will try and migrate the task, hence the rq should match the - * cpu we just moved it to. - */ - WARN_ON(task_cpu(p) != cpu); - WARN_ON(p->state != TASK_WAKING); - -#ifdef CONFIG_SCHEDSTATS - schedstat_inc(rq, ttwu_count); - if (cpu == this_cpu) - schedstat_inc(rq, ttwu_local); - else { - struct sched_domain *sd; - for_each_domain(this_cpu, sd) { - if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { - schedstat_inc(sd, ttwu_wake_remote); - break; - } - } } -#endif /* CONFIG_SCHEDSTATS */ - -out_activate: #endif /* CONFIG_SMP */ - ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu, - cpu == this_cpu, en_flags); - success = 1; -out_running: - ttwu_post_activation(p, rq, wake_flags, success); + + ttwu_queue(p, cpu); +stat: + ttwu_stat(p, cpu, wake_flags); out: - task_rq_unlock(rq, &flags); - put_cpu(); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); return success; } @@ -2547,31 +2750,34 @@ out: * try_to_wake_up_local - try to wake up a local task with rq lock held * @p: the thread to be awakened * - * Put @p on the run-queue if it's not already there. The caller must + * Put @p on the run-queue if it's not already there. The caller must * ensure that this_rq() is locked, @p is bound to this_rq() and not - * the current task. this_rq() stays locked over invocation. + * the current task. */ static void try_to_wake_up_local(struct task_struct *p) { struct rq *rq = task_rq(p); - bool success = false; BUG_ON(rq != this_rq()); BUG_ON(p == current); lockdep_assert_held(&rq->lock); + if (!raw_spin_trylock(&p->pi_lock)) { + raw_spin_unlock(&rq->lock); + raw_spin_lock(&p->pi_lock); + raw_spin_lock(&rq->lock); + } + if (!(p->state & TASK_NORMAL)) - return; + goto out; - if (!p->se.on_rq) { - if (likely(!task_running(rq, p))) { - schedstat_inc(rq, ttwu_count); - schedstat_inc(rq, ttwu_local); - } - ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP); - success = true; - } - ttwu_post_activation(p, rq, 0, success); + if (!p->on_rq) + ttwu_activate(rq, p, ENQUEUE_WAKEUP); + + ttwu_do_wakeup(rq, p, 0); + ttwu_stat(p, smp_processor_id(), 0); +out: + raw_spin_unlock(&p->pi_lock); } /** @@ -2604,19 +2810,21 @@ int wake_up_state(struct task_struct *p, unsigned int state) */ static void __sched_fork(struct task_struct *p) { + p->on_rq = 0; + + p->se.on_rq = 0; p->se.exec_start = 0; p->se.sum_exec_runtime = 0; p->se.prev_sum_exec_runtime = 0; p->se.nr_migrations = 0; p->se.vruntime = 0; + INIT_LIST_HEAD(&p->se.group_node); #ifdef CONFIG_SCHEDSTATS memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif INIT_LIST_HEAD(&p->rt.run_list); - p->se.on_rq = 0; - INIT_LIST_HEAD(&p->se.group_node); #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); @@ -2626,8 +2834,9 @@ static void __sched_fork(struct task_struct *p) /* * fork()/clone()-time setup: */ -void sched_fork(struct task_struct *p, int clone_flags) +void sched_fork(struct task_struct *p) { + unsigned long flags; int cpu = get_cpu(); __sched_fork(p); @@ -2678,18 +2887,18 @@ void sched_fork(struct task_struct *p, int clone_flags) * * Silence PROVE_RCU. */ - rcu_read_lock(); + raw_spin_lock_irqsave(&p->pi_lock, flags); set_task_cpu(p, cpu); - rcu_read_unlock(); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) if (likely(sched_info_on())) memset(&p->sched_info, 0, sizeof(p->sched_info)); #endif -#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) - p->oncpu = 0; +#if defined(CONFIG_SMP) + p->on_cpu = 0; #endif -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPT_COUNT /* Want to start with kernel preemption disabled. */ task_thread_info(p)->preempt_count = 1; #endif @@ -2707,41 +2916,31 @@ void sched_fork(struct task_struct *p, int clone_flags) * that must be done for every newly created context, then puts the task * on the runqueue and wakes it. */ -void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) +void wake_up_new_task(struct task_struct *p) { unsigned long flags; struct rq *rq; - int cpu __maybe_unused = get_cpu(); + raw_spin_lock_irqsave(&p->pi_lock, flags); #ifdef CONFIG_SMP - rq = task_rq_lock(p, &flags); - p->state = TASK_WAKING; - /* * Fork balancing, do it here and not earlier because: * - cpus_allowed can change in the fork path * - any previously selected cpu might disappear through hotplug - * - * We set TASK_WAKING so that select_task_rq() can drop rq->lock - * without people poking at ->cpus_allowed. */ - cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0); - set_task_cpu(p, cpu); - - p->state = TASK_RUNNING; - task_rq_unlock(rq, &flags); + set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0)); #endif - rq = task_rq_lock(p, &flags); + rq = __task_rq_lock(p); activate_task(rq, p, 0); - trace_sched_wakeup_new(p, 1); + p->on_rq = 1; + trace_sched_wakeup_new(p, true); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP if (p->sched_class->task_woken) p->sched_class->task_woken(rq, p); #endif - task_rq_unlock(rq, &flags); - put_cpu(); + task_rq_unlock(rq, p, &flags); } #ifdef CONFIG_PREEMPT_NOTIFIERS @@ -3450,27 +3649,22 @@ void sched_exec(void) { struct task_struct *p = current; unsigned long flags; - struct rq *rq; int dest_cpu; - rq = task_rq_lock(p, &flags); - dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0); + raw_spin_lock_irqsave(&p->pi_lock, flags); + dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0); if (dest_cpu == smp_processor_id()) goto unlock; - /* - * select_task_rq() can race against ->cpus_allowed - */ - if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) && - likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) { + if (likely(cpu_active(dest_cpu))) { struct migration_arg arg = { p, dest_cpu }; - task_rq_unlock(rq, &flags); - stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); return; } unlock: - task_rq_unlock(rq, &flags); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); } #endif @@ -3507,7 +3701,7 @@ unsigned long long task_delta_exec(struct task_struct *p) rq = task_rq_lock(p, &flags); ns = do_task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); return ns; } @@ -3525,7 +3719,7 @@ unsigned long long task_sched_runtime(struct task_struct *p) rq = task_rq_lock(p, &flags); ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); return ns; } @@ -3549,7 +3743,7 @@ unsigned long long thread_group_sched_runtime(struct task_struct *p) rq = task_rq_lock(p, &flags); thread_group_cputime(p, &totals); ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); return ns; } @@ -3695,6 +3889,25 @@ void account_idle_time(cputime_t cputime) cpustat->idle = cputime64_add(cpustat->idle, cputime64); } +static __always_inline bool steal_account_process_tick(void) +{ +#ifdef CONFIG_PARAVIRT + if (static_branch(¶virt_steal_enabled)) { + u64 steal, st = 0; + + steal = paravirt_steal_clock(smp_processor_id()); + steal -= this_rq()->prev_steal_time; + + st = steal_ticks(steal); + this_rq()->prev_steal_time += st * TICK_NSEC; + + account_steal_time(st); + return st; + } +#endif + return false; +} + #ifndef CONFIG_VIRT_CPU_ACCOUNTING #ifdef CONFIG_IRQ_TIME_ACCOUNTING @@ -3726,6 +3939,9 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy); struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + if (steal_account_process_tick()) + return; + if (irqtime_account_hi_update()) { cpustat->irq = cputime64_add(cpustat->irq, tmp); } else if (irqtime_account_si_update()) { @@ -3779,6 +3995,9 @@ void account_process_tick(struct task_struct *p, int user_tick) return; } + if (steal_account_process_tick()) + return; + if (user_tick) account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) @@ -3903,9 +4122,6 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) /* * This function gets called by the timer code, with HZ frequency. * We call it with interrupts disabled. - * - * It also gets called by the fork code, when changing the parent's - * timeslices. */ void scheduler_tick(void) { @@ -4025,17 +4241,11 @@ static inline void schedule_debug(struct task_struct *prev) profile_hit(SCHED_PROFILING, __builtin_return_address(0)); schedstat_inc(this_rq(), sched_count); -#ifdef CONFIG_SCHEDSTATS - if (unlikely(prev->lock_depth >= 0)) { - schedstat_inc(this_rq(), rq_sched_info.bkl_count); - schedstat_inc(prev, sched_info.bkl_count); - } -#endif } static void put_prev_task(struct rq *rq, struct task_struct *prev) { - if (prev->se.on_rq) + if (prev->on_rq || rq->skip_clock_update < 0) update_rq_clock(rq); prev->sched_class->put_prev_task(rq, prev); } @@ -4097,11 +4307,13 @@ need_resched: if (unlikely(signal_pending_state(prev->state, prev))) { prev->state = TASK_RUNNING; } else { + deactivate_task(rq, prev, DEQUEUE_SLEEP); + prev->on_rq = 0; + /* - * If a worker is going to sleep, notify and - * ask workqueue whether it wants to wake up a - * task to maintain concurrency. If so, wake - * up the task. + * If a worker went to sleep, notify and ask workqueue + * whether it wants to wake up a task to maintain + * concurrency. */ if (prev->flags & PF_WQ_WORKER) { struct task_struct *to_wakeup; @@ -4110,11 +4322,10 @@ need_resched: if (to_wakeup) try_to_wake_up_local(to_wakeup); } - deactivate_task(rq, prev, DEQUEUE_SLEEP); /* - * If we are going to sleep and we have plugged IO queued, make - * sure to submit it to avoid deadlocks. + * If we are going to sleep and we have plugged IO + * queued, make sure to submit it to avoid deadlocks. */ if (blk_needs_flush_plug(prev)) { raw_spin_unlock(&rq->lock); @@ -4161,71 +4372,47 @@ need_resched: EXPORT_SYMBOL(schedule); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER -/* - * Look out! "owner" is an entirely speculative pointer - * access and not reliable. - */ -int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) -{ - unsigned int cpu; - struct rq *rq; - if (!sched_feat(OWNER_SPIN)) - return 0; +static inline bool owner_running(struct mutex *lock, struct task_struct *owner) +{ + if (lock->owner != owner) + return false; -#ifdef CONFIG_DEBUG_PAGEALLOC /* - * Need to access the cpu field knowing that - * DEBUG_PAGEALLOC could have unmapped it if - * the mutex owner just released it and exited. + * Ensure we emit the owner->on_cpu, dereference _after_ checking + * lock->owner still matches owner, if that fails, owner might + * point to free()d memory, if it still matches, the rcu_read_lock() + * ensures the memory stays valid. */ - if (probe_kernel_address(&owner->cpu, cpu)) - return 0; -#else - cpu = owner->cpu; -#endif + barrier(); - /* - * Even if the access succeeded (likely case), - * the cpu field may no longer be valid. - */ - if (cpu >= nr_cpumask_bits) - return 0; + return owner->on_cpu; +} - /* - * We need to validate that we can do a - * get_cpu() and that we have the percpu area. - */ - if (!cpu_online(cpu)) +/* + * Look out! "owner" is an entirely speculative pointer + * access and not reliable. + */ +int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +{ + if (!sched_feat(OWNER_SPIN)) return 0; - rq = cpu_rq(cpu); - - for (;;) { - /* - * Owner changed, break to re-assess state. - */ - if (lock->owner != owner) { - /* - * If the lock has switched to a different owner, - * we likely have heavy contention. Return 0 to quit - * optimistic spinning and not contend further: - */ - if (lock->owner) - return 0; + rcu_read_lock(); + while (owner_running(lock, owner)) { + if (need_resched()) break; - } - - /* - * Is that owner really running on that cpu? - */ - if (task_thread_info(rq->curr) != owner || need_resched()) - return 0; arch_mutex_cpu_relax(); } + rcu_read_unlock(); - return 1; + /* + * We break out the loop above on need_resched() and when the + * owner changed, which is a sign for heavy contention. Return + * success only when lock->owner is NULL. + */ + return lock->owner == NULL; } #endif @@ -4684,19 +4871,18 @@ EXPORT_SYMBOL(sleep_on_timeout); */ void rt_mutex_setprio(struct task_struct *p, int prio) { - unsigned long flags; int oldprio, on_rq, running; struct rq *rq; const struct sched_class *prev_class; BUG_ON(prio < 0 || prio > MAX_PRIO); - rq = task_rq_lock(p, &flags); + rq = __task_rq_lock(p); trace_sched_pi_setprio(p, prio); oldprio = p->prio; prev_class = p->sched_class; - on_rq = p->se.on_rq; + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) dequeue_task(rq, p, 0); @@ -4716,7 +4902,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0); check_class_changed(rq, p, prev_class, oldprio); - task_rq_unlock(rq, &flags); + __task_rq_unlock(rq); } #endif @@ -4744,7 +4930,7 @@ void set_user_nice(struct task_struct *p, long nice) p->static_prio = NICE_TO_PRIO(nice); goto out_unlock; } - on_rq = p->se.on_rq; + on_rq = p->on_rq; if (on_rq) dequeue_task(rq, p, 0); @@ -4764,7 +4950,7 @@ void set_user_nice(struct task_struct *p, long nice) resched_task(rq->curr); } out_unlock: - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); } EXPORT_SYMBOL(set_user_nice); @@ -4878,8 +5064,6 @@ static struct task_struct *find_process_by_pid(pid_t pid) static void __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) { - BUG_ON(p->se.on_rq); - p->policy = policy; p->rt_priority = prio; p->normal_prio = normal_prio(p); @@ -4994,20 +5178,17 @@ recheck: /* * make sure no PI-waiters arrive (or leave) while we are * changing the priority of the task: - */ - raw_spin_lock_irqsave(&p->pi_lock, flags); - /* + * * To be able to change p->policy safely, the appropriate * runqueue lock must be held. */ - rq = __task_rq_lock(p); + rq = task_rq_lock(p, &flags); /* * Changing the policy of the stop threads its a very bad idea */ if (p == rq->stop) { - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); return -EINVAL; } @@ -5031,8 +5212,7 @@ recheck: if (rt_bandwidth_enabled() && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0 && !task_group_is_autogroup(task_group(p))) { - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); return -EPERM; } } @@ -5041,11 +5221,10 @@ recheck: /* recheck policy now with rq lock held */ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); goto recheck; } - on_rq = p->se.on_rq; + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) deactivate_task(rq, p, 0); @@ -5064,8 +5243,7 @@ recheck: activate_task(rq, p, 0); check_class_changed(rq, p, prev_class, oldprio); - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + task_rq_unlock(rq, p, &flags); rt_mutex_adjust_pi(p); @@ -5316,7 +5494,6 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) { struct task_struct *p; unsigned long flags; - struct rq *rq; int retval; get_online_cpus(); @@ -5331,9 +5508,9 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) if (retval) goto out_unlock; - rq = task_rq_lock(p, &flags); + raw_spin_lock_irqsave(&p->pi_lock, flags); cpumask_and(mask, &p->cpus_allowed, cpu_online_mask); - task_rq_unlock(rq, &flags); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); out_unlock: rcu_read_unlock(); @@ -5658,7 +5835,7 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, rq = task_rq_lock(p, &flags); time_slice = p->sched_class->get_rr_interval(rq, p); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); rcu_read_unlock(); jiffies_to_timespec(time_slice, &t); @@ -5760,7 +5937,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); - cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu)); + do_set_cpus_allowed(idle, cpumask_of(cpu)); /* * We're having a chicken and egg problem, even though we are * holding rq->lock, the cpu isn't yet set to this cpu so the @@ -5776,17 +5953,14 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) rcu_read_unlock(); rq->curr = rq->idle = idle; -#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) - idle->oncpu = 1; +#if defined(CONFIG_SMP) + idle->on_cpu = 1; #endif raw_spin_unlock_irqrestore(&rq->lock, flags); /* Set the preempt count _outside_ the spinlocks! */ -#if defined(CONFIG_PREEMPT) - task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0); -#else task_thread_info(idle)->preempt_count = 0; -#endif + /* * The idle tasks have their own, simple scheduling class: */ @@ -5851,6 +6025,16 @@ static inline void sched_init_granularity(void) } #ifdef CONFIG_SMP +void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +{ + if (p->sched_class && p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, new_mask); + else { + cpumask_copy(&p->cpus_allowed, new_mask); + p->rt.nr_cpus_allowed = cpumask_weight(new_mask); + } +} + /* * This is how migration works: * @@ -5881,52 +6065,38 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) unsigned int dest_cpu; int ret = 0; - /* - * Serialize against TASK_WAKING so that ttwu() and wunt() can - * drop the rq->lock and still rely on ->cpus_allowed. - */ -again: - while (task_is_waking(p)) - cpu_relax(); rq = task_rq_lock(p, &flags); - if (task_is_waking(p)) { - task_rq_unlock(rq, &flags); - goto again; - } + + if (cpumask_equal(&p->cpus_allowed, new_mask)) + goto out; if (!cpumask_intersects(new_mask, cpu_active_mask)) { ret = -EINVAL; goto out; } - if (unlikely((p->flags & PF_THREAD_BOUND) && p != current && - !cpumask_equal(&p->cpus_allowed, new_mask))) { + if (unlikely((p->flags & PF_THREAD_BOUND) && p != current)) { ret = -EINVAL; goto out; } - if (p->sched_class->set_cpus_allowed) - p->sched_class->set_cpus_allowed(p, new_mask); - else { - cpumask_copy(&p->cpus_allowed, new_mask); - p->rt.nr_cpus_allowed = cpumask_weight(new_mask); - } + do_set_cpus_allowed(p, new_mask); /* Can the task run on the task's current CPU? If so, we're done */ if (cpumask_test_cpu(task_cpu(p), new_mask)) goto out; dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); - if (migrate_task(p, rq)) { + if (p->on_rq) { struct migration_arg arg = { p, dest_cpu }; /* Need help from migration thread: drop lock and wait. */ - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); tlb_migrate_finish(p->mm); return 0; } out: - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, p, &flags); return ret; } @@ -5954,6 +6124,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) rq_src = cpu_rq(src_cpu); rq_dest = cpu_rq(dest_cpu); + raw_spin_lock(&p->pi_lock); double_rq_lock(rq_src, rq_dest); /* Already moved. */ if (task_cpu(p) != src_cpu) @@ -5966,7 +6137,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) * If we're not on a rq, the next wake-up will ensure we're * placed properly. */ - if (p->se.on_rq) { + if (p->on_rq) { deactivate_task(rq_src, p, 0); set_task_cpu(p, dest_cpu); activate_task(rq_dest, p, 0); @@ -5976,6 +6147,7 @@ done: ret = 1; fail: double_rq_unlock(rq_src, rq_dest); + raw_spin_unlock(&p->pi_lock); return ret; } @@ -6316,6 +6488,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) #ifdef CONFIG_HOTPLUG_CPU case CPU_DYING: + sched_ttwu_pending(); /* Update our root-domain */ raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { @@ -6394,6 +6567,8 @@ early_initcall(migration_init); #ifdef CONFIG_SMP +static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */ + #ifdef CONFIG_SCHED_DEBUG static __read_mostly int sched_domain_debug_enabled; @@ -6444,7 +6619,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - if (!group->cpu_power) { + if (!group->sgp->power) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: domain->cpu_power not " "set\n"); @@ -6468,9 +6643,9 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); printk(KERN_CONT " %s", str); - if (group->cpu_power != SCHED_LOAD_SCALE) { + if (group->sgp->power != SCHED_POWER_SCALE) { printk(KERN_CONT " (cpu_power = %d)", - group->cpu_power); + group->sgp->power); } group = group->next; @@ -6489,7 +6664,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, static void sched_domain_debug(struct sched_domain *sd, int cpu) { - cpumask_var_t groupmask; int level = 0; if (!sched_domain_debug_enabled) @@ -6502,20 +6676,14 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); - if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) { - printk(KERN_DEBUG "Cannot load-balance (out of memory)\n"); - return; - } - for (;;) { - if (sched_domain_debug_one(sd, cpu, level, groupmask)) + if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask)) break; level++; sd = sd->parent; if (!sd) break; } - free_cpumask_var(groupmask); } #else /* !CONFIG_SCHED_DEBUG */ # define sched_domain_debug(sd, cpu) do { } while (0) @@ -6572,12 +6740,11 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) return 1; } -static void free_rootdomain(struct root_domain *rd) +static void free_rootdomain(struct rcu_head *rcu) { - synchronize_sched(); + struct root_domain *rd = container_of(rcu, struct root_domain, rcu); cpupri_cleanup(&rd->cpupri); - free_cpumask_var(rd->rto_mask); free_cpumask_var(rd->online); free_cpumask_var(rd->span); @@ -6618,7 +6785,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) raw_spin_unlock_irqrestore(&rq->lock, flags); if (old_rd) - free_rootdomain(old_rd); + call_rcu_sched(&old_rd->rcu, free_rootdomain); } static int init_rootdomain(struct root_domain *rd) @@ -6669,6 +6836,53 @@ static struct root_domain *alloc_rootdomain(void) return rd; } +static void free_sched_groups(struct sched_group *sg, int free_sgp) +{ + struct sched_group *tmp, *first; + + if (!sg) + return; + + first = sg; + do { + tmp = sg->next; + + if (free_sgp && atomic_dec_and_test(&sg->sgp->ref)) + kfree(sg->sgp); + + kfree(sg); + sg = tmp; + } while (sg != first); +} + +static void free_sched_domain(struct rcu_head *rcu) +{ + struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu); + + /* + * If its an overlapping domain it has private groups, iterate and + * nuke them all. + */ + if (sd->flags & SD_OVERLAP) { + free_sched_groups(sd->groups, 1); + } else if (atomic_dec_and_test(&sd->groups->ref)) { + kfree(sd->groups->sgp); + kfree(sd->groups); + } + kfree(sd); +} + +static void destroy_sched_domain(struct sched_domain *sd, int cpu) +{ + call_rcu(&sd->rcu, free_sched_domain); +} + +static void destroy_sched_domains(struct sched_domain *sd, int cpu) +{ + for (; sd; sd = sd->parent) + destroy_sched_domain(sd, cpu); +} + /* * Attach the domain 'sd' to 'cpu' as its base domain. Callers must * hold the hotplug lock. @@ -6679,9 +6893,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) struct rq *rq = cpu_rq(cpu); struct sched_domain *tmp; - for (tmp = sd; tmp; tmp = tmp->parent) - tmp->span_weight = cpumask_weight(sched_domain_span(tmp)); - /* Remove the sched domains which do not contribute to scheduling. */ for (tmp = sd; tmp; ) { struct sched_domain *parent = tmp->parent; @@ -6692,12 +6903,15 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) tmp->parent = parent->parent; if (parent->parent) parent->parent->child = tmp; + destroy_sched_domain(parent, cpu); } else tmp = tmp->parent; } if (sd && sd_degenerate(sd)) { + tmp = sd; sd = sd->parent; + destroy_sched_domain(tmp, cpu); if (sd) sd->child = NULL; } @@ -6705,7 +6919,9 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) sched_domain_debug(sd, cpu); rq_attach_root(rq, rd); + tmp = rq->sd; rcu_assign_pointer(rq->sd, sd); + destroy_sched_domains(tmp, cpu); } /* cpus with isolated domains */ @@ -6721,56 +6937,6 @@ static int __init isolated_cpu_setup(char *str) __setup("isolcpus=", isolated_cpu_setup); -/* - * init_sched_build_groups takes the cpumask we wish to span, and a pointer - * to a function which identifies what group(along with sched group) a CPU - * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids - * (due to the fact that we keep track of groups covered with a struct cpumask). - * - * init_sched_build_groups will build a circular linked list of the groups - * covered by the given span, and will set each group's ->cpumask correctly, - * and ->cpu_power to 0. - */ -static void -init_sched_build_groups(const struct cpumask *span, - const struct cpumask *cpu_map, - int (*group_fn)(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, - struct cpumask *tmpmask), - struct cpumask *covered, struct cpumask *tmpmask) -{ - struct sched_group *first = NULL, *last = NULL; - int i; - - cpumask_clear(covered); - - for_each_cpu(i, span) { - struct sched_group *sg; - int group = group_fn(i, cpu_map, &sg, tmpmask); - int j; - - if (cpumask_test_cpu(i, covered)) - continue; - - cpumask_clear(sched_group_cpus(sg)); - sg->cpu_power = 0; - - for_each_cpu(j, span) { - if (group_fn(j, cpu_map, NULL, tmpmask) != group) - continue; - - cpumask_set_cpu(j, covered); - cpumask_set_cpu(j, sched_group_cpus(sg)); - } - if (!first) - first = sg; - if (last) - last->next = sg; - last = sg; - } - last->next = first; -} - #define SD_NODES_PER_DOMAIN 16 #ifdef CONFIG_NUMA @@ -6787,7 +6953,7 @@ init_sched_build_groups(const struct cpumask *span, */ static int find_next_best_node(int node, nodemask_t *used_nodes) { - int i, n, val, min_val, best_node = 0; + int i, n, val, min_val, best_node = -1; min_val = INT_MAX; @@ -6811,7 +6977,8 @@ static int find_next_best_node(int node, nodemask_t *used_nodes) } } - node_set(best_node, *used_nodes); + if (best_node != -1) + node_set(best_node, *used_nodes); return best_node; } @@ -6837,315 +7004,197 @@ static void sched_domain_node_span(int node, struct cpumask *span) for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { int next_node = find_next_best_node(node, &used_nodes); - + if (next_node < 0) + break; cpumask_or(span, span, cpumask_of_node(next_node)); } } + +static const struct cpumask *cpu_node_mask(int cpu) +{ + lockdep_assert_held(&sched_domains_mutex); + + sched_domain_node_span(cpu_to_node(cpu), sched_domains_tmpmask); + + return sched_domains_tmpmask; +} + +static const struct cpumask *cpu_allnodes_mask(int cpu) +{ + return cpu_possible_mask; +} #endif /* CONFIG_NUMA */ -int sched_smt_power_savings = 0, sched_mc_power_savings = 0; +static const struct cpumask *cpu_cpu_mask(int cpu) +{ + return cpumask_of_node(cpu_to_node(cpu)); +} -/* - * The cpus mask in sched_group and sched_domain hangs off the end. - * - * ( See the the comments in include/linux/sched.h:struct sched_group - * and struct sched_domain. ) - */ -struct static_sched_group { - struct sched_group sg; - DECLARE_BITMAP(cpus, CONFIG_NR_CPUS); -}; +int sched_smt_power_savings = 0, sched_mc_power_savings = 0; -struct static_sched_domain { - struct sched_domain sd; - DECLARE_BITMAP(span, CONFIG_NR_CPUS); +struct sd_data { + struct sched_domain **__percpu sd; + struct sched_group **__percpu sg; + struct sched_group_power **__percpu sgp; }; struct s_data { -#ifdef CONFIG_NUMA - int sd_allnodes; - cpumask_var_t domainspan; - cpumask_var_t covered; - cpumask_var_t notcovered; -#endif - cpumask_var_t nodemask; - cpumask_var_t this_sibling_map; - cpumask_var_t this_core_map; - cpumask_var_t this_book_map; - cpumask_var_t send_covered; - cpumask_var_t tmpmask; - struct sched_group **sched_group_nodes; + struct sched_domain ** __percpu sd; struct root_domain *rd; }; enum s_alloc { - sa_sched_groups = 0, sa_rootdomain, - sa_tmpmask, - sa_send_covered, - sa_this_book_map, - sa_this_core_map, - sa_this_sibling_map, - sa_nodemask, - sa_sched_group_nodes, -#ifdef CONFIG_NUMA - sa_notcovered, - sa_covered, - sa_domainspan, -#endif + sa_sd, + sa_sd_storage, sa_none, }; -/* - * SMT sched-domains: - */ -#ifdef CONFIG_SCHED_SMT -static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_groups); +struct sched_domain_topology_level; -static int -cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *unused) -{ - if (sg) - *sg = &per_cpu(sched_groups, cpu).sg; - return cpu; -} -#endif /* CONFIG_SCHED_SMT */ +typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu); +typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); -/* - * multi-core sched-domains: - */ -#ifdef CONFIG_SCHED_MC -static DEFINE_PER_CPU(struct static_sched_domain, core_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_core); +#define SDTL_OVERLAP 0x01 + +struct sched_domain_topology_level { + sched_domain_init_f init; + sched_domain_mask_f mask; + int flags; + struct sd_data data; +}; static int -cpu_to_core_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *mask) +build_overlap_sched_groups(struct sched_domain *sd, int cpu) { - int group; -#ifdef CONFIG_SCHED_SMT - cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); - group = cpumask_first(mask); -#else - group = cpu; -#endif - if (sg) - *sg = &per_cpu(sched_group_core, group).sg; - return group; -} -#endif /* CONFIG_SCHED_MC */ + struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg; + const struct cpumask *span = sched_domain_span(sd); + struct cpumask *covered = sched_domains_tmpmask; + struct sd_data *sdd = sd->private; + struct sched_domain *child; + int i; -/* - * book sched-domains: - */ -#ifdef CONFIG_SCHED_BOOK -static DEFINE_PER_CPU(struct static_sched_domain, book_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_book); + cpumask_clear(covered); -static int -cpu_to_book_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *mask) -{ - int group = cpu; -#ifdef CONFIG_SCHED_MC - cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); - group = cpumask_first(mask); -#elif defined(CONFIG_SCHED_SMT) - cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); - group = cpumask_first(mask); -#endif - if (sg) - *sg = &per_cpu(sched_group_book, group).sg; - return group; -} -#endif /* CONFIG_SCHED_BOOK */ + for_each_cpu(i, span) { + struct cpumask *sg_span; -static DEFINE_PER_CPU(struct static_sched_domain, phys_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys); + if (cpumask_test_cpu(i, covered)) + continue; -static int -cpu_to_phys_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *mask) -{ - int group; -#ifdef CONFIG_SCHED_BOOK - cpumask_and(mask, cpu_book_mask(cpu), cpu_map); - group = cpumask_first(mask); -#elif defined(CONFIG_SCHED_MC) - cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); - group = cpumask_first(mask); -#elif defined(CONFIG_SCHED_SMT) - cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); - group = cpumask_first(mask); -#else - group = cpu; -#endif - if (sg) - *sg = &per_cpu(sched_group_phys, group).sg; - return group; -} + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(i)); -#ifdef CONFIG_NUMA -/* - * The init_sched_build_groups can't handle what we want to do with node - * groups, so roll our own. Now each node has its own list of groups which - * gets dynamically allocated. - */ -static DEFINE_PER_CPU(struct static_sched_domain, node_domains); -static struct sched_group ***sched_group_nodes_bycpu; + if (!sg) + goto fail; -static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes); + sg_span = sched_group_cpus(sg); -static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, - struct cpumask *nodemask) -{ - int group; + child = *per_cpu_ptr(sdd->sd, i); + if (child->child) { + child = child->child; + cpumask_copy(sg_span, sched_domain_span(child)); + } else + cpumask_set_cpu(i, sg_span); - cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map); - group = cpumask_first(nodemask); + cpumask_or(covered, covered, sg_span); - if (sg) - *sg = &per_cpu(sched_group_allnodes, group).sg; - return group; -} + sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span)); + atomic_inc(&sg->sgp->ref); -static void init_numa_sched_groups_power(struct sched_group *group_head) -{ - struct sched_group *sg = group_head; - int j; + if (cpumask_test_cpu(cpu, sg_span)) + groups = sg; - if (!sg) - return; - do { - for_each_cpu(j, sched_group_cpus(sg)) { - struct sched_domain *sd; + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + last->next = first; + } + sd->groups = groups; - sd = &per_cpu(phys_domains, j).sd; - if (j != group_first_cpu(sd->groups)) { - /* - * Only add "power" once for each - * physical package. - */ - continue; - } + return 0; - sg->cpu_power += sd->groups->cpu_power; - } - sg = sg->next; - } while (sg != group_head); +fail: + free_sched_groups(first, 0); + + return -ENOMEM; } -static int build_numa_sched_groups(struct s_data *d, - const struct cpumask *cpu_map, int num) +static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) { - struct sched_domain *sd; - struct sched_group *sg, *prev; - int n, j; + struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); + struct sched_domain *child = sd->child; - cpumask_clear(d->covered); - cpumask_and(d->nodemask, cpumask_of_node(num), cpu_map); - if (cpumask_empty(d->nodemask)) { - d->sched_group_nodes[num] = NULL; - goto out; + if (child) + cpu = cpumask_first(sched_domain_span(child)); + + if (sg) { + *sg = *per_cpu_ptr(sdd->sg, cpu); + (*sg)->sgp = *per_cpu_ptr(sdd->sgp, cpu); + atomic_set(&(*sg)->sgp->ref, 1); /* for claim_allocations */ } - sched_domain_node_span(num, d->domainspan); - cpumask_and(d->domainspan, d->domainspan, cpu_map); + return cpu; +} - sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), - GFP_KERNEL, num); - if (!sg) { - printk(KERN_WARNING "Can not alloc domain group for node %d\n", - num); - return -ENOMEM; - } - d->sched_group_nodes[num] = sg; +/* + * build_sched_groups will build a circular linked list of the groups + * covered by the given span, and will set each group's ->cpumask correctly, + * and ->cpu_power to 0. + * + * Assumes the sched_domain tree is fully constructed + */ +static int +build_sched_groups(struct sched_domain *sd, int cpu) +{ + struct sched_group *first = NULL, *last = NULL; + struct sd_data *sdd = sd->private; + const struct cpumask *span = sched_domain_span(sd); + struct cpumask *covered; + int i; - for_each_cpu(j, d->nodemask) { - sd = &per_cpu(node_domains, j).sd; - sd->groups = sg; - } + get_group(cpu, sdd, &sd->groups); + atomic_inc(&sd->groups->ref); - sg->cpu_power = 0; - cpumask_copy(sched_group_cpus(sg), d->nodemask); - sg->next = sg; - cpumask_or(d->covered, d->covered, d->nodemask); + if (cpu != cpumask_first(sched_domain_span(sd))) + return 0; - prev = sg; - for (j = 0; j < nr_node_ids; j++) { - n = (num + j) % nr_node_ids; - cpumask_complement(d->notcovered, d->covered); - cpumask_and(d->tmpmask, d->notcovered, cpu_map); - cpumask_and(d->tmpmask, d->tmpmask, d->domainspan); - if (cpumask_empty(d->tmpmask)) - break; - cpumask_and(d->tmpmask, d->tmpmask, cpumask_of_node(n)); - if (cpumask_empty(d->tmpmask)) - continue; - sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), - GFP_KERNEL, num); - if (!sg) { - printk(KERN_WARNING - "Can not alloc domain group for node %d\n", j); - return -ENOMEM; - } - sg->cpu_power = 0; - cpumask_copy(sched_group_cpus(sg), d->tmpmask); - sg->next = prev->next; - cpumask_or(d->covered, d->covered, d->tmpmask); - prev->next = sg; - prev = sg; - } -out: - return 0; -} -#endif /* CONFIG_NUMA */ + lockdep_assert_held(&sched_domains_mutex); + covered = sched_domains_tmpmask; -#ifdef CONFIG_NUMA -/* Free memory allocated for various sched_group structures */ -static void free_sched_groups(const struct cpumask *cpu_map, - struct cpumask *nodemask) -{ - int cpu, i; + cpumask_clear(covered); - for_each_cpu(cpu, cpu_map) { - struct sched_group **sched_group_nodes - = sched_group_nodes_bycpu[cpu]; + for_each_cpu(i, span) { + struct sched_group *sg; + int group = get_group(i, sdd, &sg); + int j; - if (!sched_group_nodes) + if (cpumask_test_cpu(i, covered)) continue; - for (i = 0; i < nr_node_ids; i++) { - struct sched_group *oldsg, *sg = sched_group_nodes[i]; + cpumask_clear(sched_group_cpus(sg)); + sg->sgp->power = 0; - cpumask_and(nodemask, cpumask_of_node(i), cpu_map); - if (cpumask_empty(nodemask)) + for_each_cpu(j, span) { + if (get_group(j, sdd, NULL) != group) continue; - if (sg == NULL) - continue; - sg = sg->next; -next_sg: - oldsg = sg; - sg = sg->next; - kfree(oldsg); - if (oldsg != sched_group_nodes[i]) - goto next_sg; + cpumask_set_cpu(j, covered); + cpumask_set_cpu(j, sched_group_cpus(sg)); } - kfree(sched_group_nodes); - sched_group_nodes_bycpu[cpu] = NULL; + + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; } + last->next = first; + + return 0; } -#else /* !CONFIG_NUMA */ -static void free_sched_groups(const struct cpumask *cpu_map, - struct cpumask *nodemask) -{ -} -#endif /* CONFIG_NUMA */ /* * Initialize sched groups cpu_power. @@ -7159,48 +7208,19 @@ static void free_sched_groups(const struct cpumask *cpu_map, */ static void init_sched_groups_power(int cpu, struct sched_domain *sd) { - struct sched_domain *child; - struct sched_group *group; - long power; - int weight; + struct sched_group *sg = sd->groups; - WARN_ON(!sd || !sd->groups); - - if (cpu != group_first_cpu(sd->groups)) - return; + WARN_ON(!sd || !sg); - sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups)); - - child = sd->child; - - sd->groups->cpu_power = 0; + do { + sg->group_weight = cpumask_weight(sched_group_cpus(sg)); + sg = sg->next; + } while (sg != sd->groups); - if (!child) { - power = SCHED_LOAD_SCALE; - weight = cpumask_weight(sched_domain_span(sd)); - /* - * SMT siblings share the power of a single core. - * Usually multiple threads get a better yield out of - * that one core than a single thread would have, - * reflect that in sd->smt_gain. - */ - if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { - power *= sd->smt_gain; - power /= weight; - power >>= SCHED_LOAD_SHIFT; - } - sd->groups->cpu_power += power; + if (cpu != group_first_cpu(sg)) return; - } - /* - * Add cpu_power of each child group to this groups cpu_power. - */ - group = child->groups; - do { - sd->groups->cpu_power += group->cpu_power; - group = group->next; - } while (group != child->groups); + update_group_power(sd, cpu); } /* @@ -7214,15 +7234,15 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) # define SD_INIT_NAME(sd, type) do { } while (0) #endif -#define SD_INIT(sd, type) sd_init_##type(sd) - -#define SD_INIT_FUNC(type) \ -static noinline void sd_init_##type(struct sched_domain *sd) \ -{ \ - memset(sd, 0, sizeof(*sd)); \ - *sd = SD_##type##_INIT; \ - sd->level = SD_LV_##type; \ - SD_INIT_NAME(sd, type); \ +#define SD_INIT_FUNC(type) \ +static noinline struct sched_domain * \ +sd_init_##type(struct sched_domain_topology_level *tl, int cpu) \ +{ \ + struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); \ + *sd = SD_##type##_INIT; \ + SD_INIT_NAME(sd, type); \ + sd->private = &tl->data; \ + return sd; \ } SD_INIT_FUNC(CPU) @@ -7241,13 +7261,14 @@ SD_INIT_FUNC(CPU) #endif static int default_relax_domain_level = -1; +int sched_domain_level_max; static int __init setup_relax_domain_level(char *str) { unsigned long val; val = simple_strtoul(str, NULL, 0); - if (val < SD_LV_MAX) + if (val < sched_domain_level_max) default_relax_domain_level = val; return 1; @@ -7275,37 +7296,20 @@ static void set_domain_attribute(struct sched_domain *sd, } } +static void __sdt_free(const struct cpumask *cpu_map); +static int __sdt_alloc(const struct cpumask *cpu_map); + static void __free_domain_allocs(struct s_data *d, enum s_alloc what, const struct cpumask *cpu_map) { switch (what) { - case sa_sched_groups: - free_sched_groups(cpu_map, d->tmpmask); /* fall through */ - d->sched_group_nodes = NULL; case sa_rootdomain: - free_rootdomain(d->rd); /* fall through */ - case sa_tmpmask: - free_cpumask_var(d->tmpmask); /* fall through */ - case sa_send_covered: - free_cpumask_var(d->send_covered); /* fall through */ - case sa_this_book_map: - free_cpumask_var(d->this_book_map); /* fall through */ - case sa_this_core_map: - free_cpumask_var(d->this_core_map); /* fall through */ - case sa_this_sibling_map: - free_cpumask_var(d->this_sibling_map); /* fall through */ - case sa_nodemask: - free_cpumask_var(d->nodemask); /* fall through */ - case sa_sched_group_nodes: -#ifdef CONFIG_NUMA - kfree(d->sched_group_nodes); /* fall through */ - case sa_notcovered: - free_cpumask_var(d->notcovered); /* fall through */ - case sa_covered: - free_cpumask_var(d->covered); /* fall through */ - case sa_domainspan: - free_cpumask_var(d->domainspan); /* fall through */ -#endif + if (!atomic_read(&d->rd->refcount)) + free_rootdomain(&d->rd->rcu); /* fall through */ + case sa_sd: + free_percpu(d->sd); /* fall through */ + case sa_sd_storage: + __sdt_free(cpu_map); /* fall through */ case sa_none: break; } @@ -7314,308 +7318,233 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what, static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, const struct cpumask *cpu_map) { -#ifdef CONFIG_NUMA - if (!alloc_cpumask_var(&d->domainspan, GFP_KERNEL)) - return sa_none; - if (!alloc_cpumask_var(&d->covered, GFP_KERNEL)) - return sa_domainspan; - if (!alloc_cpumask_var(&d->notcovered, GFP_KERNEL)) - return sa_covered; - /* Allocate the per-node list of sched groups */ - d->sched_group_nodes = kcalloc(nr_node_ids, - sizeof(struct sched_group *), GFP_KERNEL); - if (!d->sched_group_nodes) { - printk(KERN_WARNING "Can not alloc sched group node list\n"); - return sa_notcovered; - } - sched_group_nodes_bycpu[cpumask_first(cpu_map)] = d->sched_group_nodes; -#endif - if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL)) - return sa_sched_group_nodes; - if (!alloc_cpumask_var(&d->this_sibling_map, GFP_KERNEL)) - return sa_nodemask; - if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL)) - return sa_this_sibling_map; - if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL)) - return sa_this_core_map; - if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL)) - return sa_this_book_map; - if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL)) - return sa_send_covered; + memset(d, 0, sizeof(*d)); + + if (__sdt_alloc(cpu_map)) + return sa_sd_storage; + d->sd = alloc_percpu(struct sched_domain *); + if (!d->sd) + return sa_sd_storage; d->rd = alloc_rootdomain(); - if (!d->rd) { - printk(KERN_WARNING "Cannot alloc root domain\n"); - return sa_tmpmask; - } + if (!d->rd) + return sa_sd; return sa_rootdomain; } -static struct sched_domain *__build_numa_sched_domains(struct s_data *d, - const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i) +/* + * NULL the sd_data elements we've used to build the sched_domain and + * sched_group structure so that the subsequent __free_domain_allocs() + * will not free the data we're using. + */ +static void claim_allocations(int cpu, struct sched_domain *sd) { - struct sched_domain *sd = NULL; -#ifdef CONFIG_NUMA - struct sched_domain *parent; - - d->sd_allnodes = 0; - if (cpumask_weight(cpu_map) > - SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) { - sd = &per_cpu(allnodes_domains, i).sd; - SD_INIT(sd, ALLNODES); - set_domain_attribute(sd, attr); - cpumask_copy(sched_domain_span(sd), cpu_map); - cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask); - d->sd_allnodes = 1; - } - parent = sd; - - sd = &per_cpu(node_domains, i).sd; - SD_INIT(sd, NODE); - set_domain_attribute(sd, attr); - sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd)); - sd->parent = parent; - if (parent) - parent->child = sd; - cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map); -#endif - return sd; -} + struct sd_data *sdd = sd->private; -static struct sched_domain *__build_cpu_sched_domain(struct s_data *d, - const struct cpumask *cpu_map, struct sched_domain_attr *attr, - struct sched_domain *parent, int i) -{ - struct sched_domain *sd; - sd = &per_cpu(phys_domains, i).sd; - SD_INIT(sd, CPU); - set_domain_attribute(sd, attr); - cpumask_copy(sched_domain_span(sd), d->nodemask); - sd->parent = parent; - if (parent) - parent->child = sd; - cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask); - return sd; -} + WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd); + *per_cpu_ptr(sdd->sd, cpu) = NULL; -static struct sched_domain *__build_book_sched_domain(struct s_data *d, - const struct cpumask *cpu_map, struct sched_domain_attr *attr, - struct sched_domain *parent, int i) -{ - struct sched_domain *sd = parent; -#ifdef CONFIG_SCHED_BOOK - sd = &per_cpu(book_domains, i).sd; - SD_INIT(sd, BOOK); - set_domain_attribute(sd, attr); - cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i)); - sd->parent = parent; - parent->child = sd; - cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask); -#endif - return sd; -} + if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref)) + *per_cpu_ptr(sdd->sg, cpu) = NULL; -static struct sched_domain *__build_mc_sched_domain(struct s_data *d, - const struct cpumask *cpu_map, struct sched_domain_attr *attr, - struct sched_domain *parent, int i) -{ - struct sched_domain *sd = parent; -#ifdef CONFIG_SCHED_MC - sd = &per_cpu(core_domains, i).sd; - SD_INIT(sd, MC); - set_domain_attribute(sd, attr); - cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i)); - sd->parent = parent; - parent->child = sd; - cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask); -#endif - return sd; + if (atomic_read(&(*per_cpu_ptr(sdd->sgp, cpu))->ref)) + *per_cpu_ptr(sdd->sgp, cpu) = NULL; } -static struct sched_domain *__build_smt_sched_domain(struct s_data *d, - const struct cpumask *cpu_map, struct sched_domain_attr *attr, - struct sched_domain *parent, int i) -{ - struct sched_domain *sd = parent; #ifdef CONFIG_SCHED_SMT - sd = &per_cpu(cpu_domains, i).sd; - SD_INIT(sd, SIBLING); - set_domain_attribute(sd, attr); - cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i)); - sd->parent = parent; - parent->child = sd; - cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask); -#endif - return sd; +static const struct cpumask *cpu_smt_mask(int cpu) +{ + return topology_thread_cpumask(cpu); } +#endif -static void build_sched_groups(struct s_data *d, enum sched_domain_level l, - const struct cpumask *cpu_map, int cpu) -{ - switch (l) { +/* + * Topology list, bottom-up. + */ +static struct sched_domain_topology_level default_topology[] = { #ifdef CONFIG_SCHED_SMT - case SD_LV_SIBLING: /* set up CPU (sibling) groups */ - cpumask_and(d->this_sibling_map, cpu_map, - topology_thread_cpumask(cpu)); - if (cpu == cpumask_first(d->this_sibling_map)) - init_sched_build_groups(d->this_sibling_map, cpu_map, - &cpu_to_cpu_group, - d->send_covered, d->tmpmask); - break; + { sd_init_SIBLING, cpu_smt_mask, }, #endif #ifdef CONFIG_SCHED_MC - case SD_LV_MC: /* set up multi-core groups */ - cpumask_and(d->this_core_map, cpu_map, cpu_coregroup_mask(cpu)); - if (cpu == cpumask_first(d->this_core_map)) - init_sched_build_groups(d->this_core_map, cpu_map, - &cpu_to_core_group, - d->send_covered, d->tmpmask); - break; + { sd_init_MC, cpu_coregroup_mask, }, #endif #ifdef CONFIG_SCHED_BOOK - case SD_LV_BOOK: /* set up book groups */ - cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu)); - if (cpu == cpumask_first(d->this_book_map)) - init_sched_build_groups(d->this_book_map, cpu_map, - &cpu_to_book_group, - d->send_covered, d->tmpmask); - break; + { sd_init_BOOK, cpu_book_mask, }, #endif - case SD_LV_CPU: /* set up physical groups */ - cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map); - if (!cpumask_empty(d->nodemask)) - init_sched_build_groups(d->nodemask, cpu_map, - &cpu_to_phys_group, - d->send_covered, d->tmpmask); - break; + { sd_init_CPU, cpu_cpu_mask, }, #ifdef CONFIG_NUMA - case SD_LV_ALLNODES: - init_sched_build_groups(cpu_map, cpu_map, &cpu_to_allnodes_group, - d->send_covered, d->tmpmask); - break; + { sd_init_NODE, cpu_node_mask, SDTL_OVERLAP, }, + { sd_init_ALLNODES, cpu_allnodes_mask, }, #endif - default: - break; + { NULL, }, +}; + +static struct sched_domain_topology_level *sched_domain_topology = default_topology; + +static int __sdt_alloc(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for (tl = sched_domain_topology; tl->init; tl++) { + struct sd_data *sdd = &tl->data; + + sdd->sd = alloc_percpu(struct sched_domain *); + if (!sdd->sd) + return -ENOMEM; + + sdd->sg = alloc_percpu(struct sched_group *); + if (!sdd->sg) + return -ENOMEM; + + sdd->sgp = alloc_percpu(struct sched_group_power *); + if (!sdd->sgp) + return -ENOMEM; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + struct sched_group *sg; + struct sched_group_power *sgp; + + sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sd) + return -ENOMEM; + + *per_cpu_ptr(sdd->sd, j) = sd; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sg) + return -ENOMEM; + + *per_cpu_ptr(sdd->sg, j) = sg; + + sgp = kzalloc_node(sizeof(struct sched_group_power), + GFP_KERNEL, cpu_to_node(j)); + if (!sgp) + return -ENOMEM; + + *per_cpu_ptr(sdd->sgp, j) = sgp; + } + } + + return 0; +} + +static void __sdt_free(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for (tl = sched_domain_topology; tl->init; tl++) { + struct sd_data *sdd = &tl->data; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j); + if (sd && (sd->flags & SD_OVERLAP)) + free_sched_groups(sd->groups, 0); + kfree(*per_cpu_ptr(sdd->sg, j)); + kfree(*per_cpu_ptr(sdd->sgp, j)); + } + free_percpu(sdd->sd); + free_percpu(sdd->sg); + free_percpu(sdd->sgp); } } +struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, + struct s_data *d, const struct cpumask *cpu_map, + struct sched_domain_attr *attr, struct sched_domain *child, + int cpu) +{ + struct sched_domain *sd = tl->init(tl, cpu); + if (!sd) + return child; + + set_domain_attribute(sd, attr); + cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); + if (child) { + sd->level = child->level + 1; + sched_domain_level_max = max(sched_domain_level_max, sd->level); + child->parent = sd; + } + sd->child = child; + + return sd; +} + /* * Build sched domains for a given set of cpus and attach the sched domains * to the individual cpus */ -static int __build_sched_domains(const struct cpumask *cpu_map, - struct sched_domain_attr *attr) +static int build_sched_domains(const struct cpumask *cpu_map, + struct sched_domain_attr *attr) { enum s_alloc alloc_state = sa_none; - struct s_data d; struct sched_domain *sd; - int i; -#ifdef CONFIG_NUMA - d.sd_allnodes = 0; -#endif + struct s_data d; + int i, ret = -ENOMEM; alloc_state = __visit_domain_allocation_hell(&d, cpu_map); if (alloc_state != sa_rootdomain) goto error; - alloc_state = sa_sched_groups; - /* - * Set up domains for cpus specified by the cpu_map. - */ + /* Set up domains for cpus specified by the cpu_map. */ for_each_cpu(i, cpu_map) { - cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)), - cpu_map); + struct sched_domain_topology_level *tl; + + sd = NULL; + for (tl = sched_domain_topology; tl->init; tl++) { + sd = build_sched_domain(tl, &d, cpu_map, attr, sd, i); + if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP)) + sd->flags |= SD_OVERLAP; + if (cpumask_equal(cpu_map, sched_domain_span(sd))) + break; + } - sd = __build_numa_sched_domains(&d, cpu_map, attr, i); - sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i); - sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i); - sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i); - sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i); - } + while (sd->child) + sd = sd->child; - for_each_cpu(i, cpu_map) { - build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i); - build_sched_groups(&d, SD_LV_BOOK, cpu_map, i); - build_sched_groups(&d, SD_LV_MC, cpu_map, i); + *per_cpu_ptr(d.sd, i) = sd; } - /* Set up physical groups */ - for (i = 0; i < nr_node_ids; i++) - build_sched_groups(&d, SD_LV_CPU, cpu_map, i); - -#ifdef CONFIG_NUMA - /* Set up node groups */ - if (d.sd_allnodes) - build_sched_groups(&d, SD_LV_ALLNODES, cpu_map, 0); - - for (i = 0; i < nr_node_ids; i++) - if (build_numa_sched_groups(&d, cpu_map, i)) - goto error; -#endif - - /* Calculate CPU power for physical packages and nodes */ -#ifdef CONFIG_SCHED_SMT + /* Build the groups for the domains */ for_each_cpu(i, cpu_map) { - sd = &per_cpu(cpu_domains, i).sd; - init_sched_groups_power(i, sd); - } -#endif -#ifdef CONFIG_SCHED_MC - for_each_cpu(i, cpu_map) { - sd = &per_cpu(core_domains, i).sd; - init_sched_groups_power(i, sd); - } -#endif -#ifdef CONFIG_SCHED_BOOK - for_each_cpu(i, cpu_map) { - sd = &per_cpu(book_domains, i).sd; - init_sched_groups_power(i, sd); - } -#endif - - for_each_cpu(i, cpu_map) { - sd = &per_cpu(phys_domains, i).sd; - init_sched_groups_power(i, sd); + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + sd->span_weight = cpumask_weight(sched_domain_span(sd)); + if (sd->flags & SD_OVERLAP) { + if (build_overlap_sched_groups(sd, i)) + goto error; + } else { + if (build_sched_groups(sd, i)) + goto error; + } + } } -#ifdef CONFIG_NUMA - for (i = 0; i < nr_node_ids; i++) - init_numa_sched_groups_power(d.sched_group_nodes[i]); - - if (d.sd_allnodes) { - struct sched_group *sg; + /* Calculate CPU power for physical packages and nodes */ + for (i = nr_cpumask_bits-1; i >= 0; i--) { + if (!cpumask_test_cpu(i, cpu_map)) + continue; - cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg, - d.tmpmask); - init_numa_sched_groups_power(sg); + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + claim_allocations(i, sd); + init_sched_groups_power(i, sd); + } } -#endif /* Attach the domains */ + rcu_read_lock(); for_each_cpu(i, cpu_map) { -#ifdef CONFIG_SCHED_SMT - sd = &per_cpu(cpu_domains, i).sd; -#elif defined(CONFIG_SCHED_MC) - sd = &per_cpu(core_domains, i).sd; -#elif defined(CONFIG_SCHED_BOOK) - sd = &per_cpu(book_domains, i).sd; -#else - sd = &per_cpu(phys_domains, i).sd; -#endif + sd = *per_cpu_ptr(d.sd, i); cpu_attach_domain(sd, d.rd, i); } + rcu_read_unlock(); - d.sched_group_nodes = NULL; /* don't free this we still need it */ - __free_domain_allocs(&d, sa_tmpmask, cpu_map); - return 0; - + ret = 0; error: __free_domain_allocs(&d, alloc_state, cpu_map); - return -ENOMEM; -} - -static int build_sched_domains(const struct cpumask *cpu_map) -{ - return __build_sched_domains(cpu_map, NULL); + return ret; } static cpumask_var_t *doms_cur; /* current sched domains */ @@ -7670,7 +7599,7 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) * For now this just excludes isolated cpus, but could be used to * exclude other special cases in the future. */ -static int arch_init_sched_domains(const struct cpumask *cpu_map) +static int init_sched_domains(const struct cpumask *cpu_map) { int err; @@ -7681,32 +7610,24 @@ static int arch_init_sched_domains(const struct cpumask *cpu_map) doms_cur = &fallback_doms; cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); dattr_cur = NULL; - err = build_sched_domains(doms_cur[0]); + err = build_sched_domains(doms_cur[0], NULL); register_sched_domain_sysctl(); return err; } -static void arch_destroy_sched_domains(const struct cpumask *cpu_map, - struct cpumask *tmpmask) -{ - free_sched_groups(cpu_map, tmpmask); -} - /* * Detach sched domains from a group of cpus specified in cpu_map * These cpus will now be attached to the NULL domain */ static void detach_destroy_domains(const struct cpumask *cpu_map) { - /* Save because hotplug lock held. */ - static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS); int i; + rcu_read_lock(); for_each_cpu(i, cpu_map) cpu_attach_domain(NULL, &def_root_domain, i); - synchronize_sched(); - arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask)); + rcu_read_unlock(); } /* handle null as "default" */ @@ -7795,8 +7716,7 @@ match1: goto match2; } /* no match - add a new doms_new */ - __build_sched_domains(doms_new[i], - dattr_new ? dattr_new + i : NULL); + build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); match2: ; } @@ -7815,7 +7735,7 @@ match2: } #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -static void arch_reinit_sched_domains(void) +static void reinit_sched_domains(void) { get_online_cpus(); @@ -7848,7 +7768,7 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) else sched_mc_power_savings = level; - arch_reinit_sched_domains(); + reinit_sched_domains(); return count; } @@ -7967,14 +7887,9 @@ void __init sched_init_smp(void) alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); alloc_cpumask_var(&fallback_doms, GFP_KERNEL); -#if defined(CONFIG_NUMA) - sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **), - GFP_KERNEL); - BUG_ON(sched_group_nodes_bycpu == NULL); -#endif get_online_cpus(); mutex_lock(&sched_domains_mutex); - arch_init_sched_domains(cpu_active_mask); + 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); @@ -8013,18 +7928,14 @@ int in_sched_functions(unsigned long addr) && addr < (unsigned long)__sched_text_end); } -static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq) +static void init_cfs_rq(struct cfs_rq *cfs_rq) { cfs_rq->tasks_timeline = RB_ROOT; INIT_LIST_HEAD(&cfs_rq->tasks); -#ifdef CONFIG_FAIR_GROUP_SCHED - cfs_rq->rq = rq; - /* allow initial update_cfs_load() to truncate */ -#ifdef CONFIG_SMP - cfs_rq->load_stamp = 1; -#endif -#endif cfs_rq->min_vruntime = (u64)(-(1LL << 20)); +#ifndef CONFIG_64BIT + cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; +#endif } static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) @@ -8040,27 +7951,18 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) /* delimiter for bitsearch: */ __set_bit(MAX_RT_PRIO, array->bitmap); -#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED +#if defined CONFIG_SMP rt_rq->highest_prio.curr = MAX_RT_PRIO; -#ifdef CONFIG_SMP rt_rq->highest_prio.next = MAX_RT_PRIO; -#endif -#endif -#ifdef CONFIG_SMP rt_rq->rt_nr_migratory = 0; rt_rq->overloaded = 0; - plist_head_init_raw(&rt_rq->pushable_tasks, &rq->lock); + plist_head_init(&rt_rq->pushable_tasks); #endif rt_rq->rt_time = 0; rt_rq->rt_throttled = 0; rt_rq->rt_runtime = 0; raw_spin_lock_init(&rt_rq->rt_runtime_lock); - -#ifdef CONFIG_RT_GROUP_SCHED - rt_rq->rt_nr_boosted = 0; - rt_rq->rq = rq; -#endif } #ifdef CONFIG_FAIR_GROUP_SCHED @@ -8069,11 +7971,17 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, struct sched_entity *parent) { struct rq *rq = cpu_rq(cpu); - tg->cfs_rq[cpu] = cfs_rq; - init_cfs_rq(cfs_rq, rq); + cfs_rq->tg = tg; + cfs_rq->rq = rq; +#ifdef CONFIG_SMP + /* allow initial update_cfs_load() to truncate */ + cfs_rq->load_stamp = 1; +#endif + tg->cfs_rq[cpu] = cfs_rq; tg->se[cpu] = se; + /* se could be NULL for root_task_group */ if (!se) return; @@ -8096,12 +8004,14 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, { struct rq *rq = cpu_rq(cpu); - tg->rt_rq[cpu] = rt_rq; - init_rt_rq(rt_rq, rq); + rt_rq->highest_prio.curr = MAX_RT_PRIO; + rt_rq->rt_nr_boosted = 0; + rt_rq->rq = rq; rt_rq->tg = tg; - rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime; + tg->rt_rq[cpu] = rt_rq; tg->rt_se[cpu] = rt_se; + if (!rt_se) return; @@ -8183,7 +8093,7 @@ void __init sched_init(void) rq->nr_running = 0; rq->calc_load_active = 0; rq->calc_load_update = jiffies + LOAD_FREQ; - init_cfs_rq(&rq->cfs, rq); + init_cfs_rq(&rq->cfs); init_rt_rq(&rq->rt, rq); #ifdef CONFIG_FAIR_GROUP_SCHED root_task_group.shares = root_task_group_load; @@ -8224,7 +8134,7 @@ void __init sched_init(void) #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; - rq->cpu_power = SCHED_LOAD_SCALE; + rq->cpu_power = SCHED_POWER_SCALE; rq->post_schedule = 0; rq->active_balance = 0; rq->next_balance = jiffies; @@ -8254,7 +8164,7 @@ void __init sched_init(void) #endif #ifdef CONFIG_RT_MUTEXES - plist_head_init_raw(&init_task.pi_waiters, &init_task.pi_lock); + plist_head_init(&init_task.pi_waiters); #endif /* @@ -8281,6 +8191,7 @@ void __init sched_init(void) /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */ zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); #ifdef CONFIG_SMP + zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT); #ifdef CONFIG_NO_HZ zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); alloc_cpumask_var(&nohz.grp_idle_mask, GFP_NOWAIT); @@ -8296,7 +8207,7 @@ void __init sched_init(void) scheduler_running = 1; } -#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP static inline int preempt_count_equals(int preempt_offset) { int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth(); @@ -8306,7 +8217,6 @@ static inline int preempt_count_equals(int preempt_offset) void __might_sleep(const char *file, int line, int preempt_offset) { -#ifdef in_atomic static unsigned long prev_jiffy; /* ratelimiting */ if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) || @@ -8328,7 +8238,6 @@ void __might_sleep(const char *file, int line, int preempt_offset) if (irqs_disabled()) print_irqtrace_events(current); dump_stack(); -#endif } EXPORT_SYMBOL(__might_sleep); #endif @@ -8340,7 +8249,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p) int old_prio = p->prio; int on_rq; - on_rq = p->se.on_rq; + on_rq = p->on_rq; if (on_rq) deactivate_task(rq, p, 0); __setscheduler(rq, p, SCHED_NORMAL, 0); @@ -8487,6 +8396,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) if (!se) goto err_free_rq; + init_cfs_rq(cfs_rq); init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); } @@ -8514,7 +8424,7 @@ static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) list_del_leaf_cfs_rq(tg->cfs_rq[cpu]); raw_spin_unlock_irqrestore(&rq->lock, flags); } -#else /* !CONFG_FAIR_GROUP_SCHED */ +#else /* !CONFIG_FAIR_GROUP_SCHED */ static inline void free_fair_sched_group(struct task_group *tg) { } @@ -8535,7 +8445,8 @@ static void free_rt_sched_group(struct task_group *tg) { int i; - destroy_rt_bandwidth(&tg->rt_bandwidth); + if (tg->rt_se) + destroy_rt_bandwidth(&tg->rt_bandwidth); for_each_possible_cpu(i) { if (tg->rt_rq) @@ -8553,7 +8464,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) { struct rt_rq *rt_rq; struct sched_rt_entity *rt_se; - struct rq *rq; int i; tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL); @@ -8567,8 +8477,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) ktime_to_ns(def_rt_bandwidth.rt_period), 0); for_each_possible_cpu(i) { - rq = cpu_rq(i); - rt_rq = kzalloc_node(sizeof(struct rt_rq), GFP_KERNEL, cpu_to_node(i)); if (!rt_rq) @@ -8579,6 +8487,8 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) if (!rt_se) goto err_free_rq; + init_rt_rq(rt_rq, cpu_rq(i)); + rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime; init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]); } @@ -8683,7 +8593,7 @@ void sched_move_task(struct task_struct *tsk) rq = task_rq_lock(tsk, &flags); running = task_current(rq, tsk); - on_rq = tsk->se.on_rq; + on_rq = tsk->on_rq; if (on_rq) dequeue_task(rq, tsk, 0); @@ -8702,7 +8612,7 @@ void sched_move_task(struct task_struct *tsk) if (on_rq) enqueue_task(rq, tsk, 0); - task_rq_unlock(rq, &flags); + task_rq_unlock(rq, tsk, &flags); } #endif /* CONFIG_CGROUP_SCHED */ @@ -8720,10 +8630,7 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) if (!tg->se[0]) return -EINVAL; - if (shares < MIN_SHARES) - shares = MIN_SHARES; - else if (shares > MAX_SHARES) - shares = MAX_SHARES; + shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES)); mutex_lock(&shares_mutex); if (tg->shares == shares) @@ -9073,42 +8980,10 @@ cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk) return 0; } -static int -cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct task_struct *tsk, bool threadgroup) -{ - int retval = cpu_cgroup_can_attach_task(cgrp, tsk); - if (retval) - return retval; - if (threadgroup) { - struct task_struct *c; - rcu_read_lock(); - list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { - retval = cpu_cgroup_can_attach_task(cgrp, c); - if (retval) { - rcu_read_unlock(); - return retval; - } - } - rcu_read_unlock(); - } - return 0; -} - static void -cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cont, struct task_struct *tsk, - bool threadgroup) +cpu_cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) { sched_move_task(tsk); - if (threadgroup) { - struct task_struct *c; - rcu_read_lock(); - list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { - sched_move_task(c); - } - rcu_read_unlock(); - } } static void @@ -9130,14 +9005,14 @@ cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype, u64 shareval) { - return sched_group_set_shares(cgroup_tg(cgrp), shareval); + return sched_group_set_shares(cgroup_tg(cgrp), scale_load(shareval)); } static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft) { struct task_group *tg = cgroup_tg(cgrp); - return (u64) tg->shares; + return (u64) scale_load_down(tg->shares); } #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -9196,8 +9071,8 @@ struct cgroup_subsys cpu_cgroup_subsys = { .name = "cpu", .create = cpu_cgroup_create, .destroy = cpu_cgroup_destroy, - .can_attach = cpu_cgroup_can_attach, - .attach = cpu_cgroup_attach, + .can_attach_task = cpu_cgroup_can_attach_task, + .attach_task = cpu_cgroup_attach_task, .exit = cpu_cgroup_exit, .populate = cpu_cgroup_populate, .subsys_id = cpu_cgroup_subsys_id, diff --git a/kernel/sched_autogroup.h b/kernel/sched_autogroup.h index 05577055cfc..c2f0e7248dc 100644 --- a/kernel/sched_autogroup.h +++ b/kernel/sched_autogroup.h @@ -13,6 +13,7 @@ struct autogroup { int nice; }; +static inline bool task_group_is_autogroup(struct task_group *tg); static inline struct task_group * autogroup_task_group(struct task_struct *p, struct task_group *tg); diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 7bacd83a415..a6710a112b4 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -152,7 +152,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) read_lock_irqsave(&tasklist_lock, flags); do_each_thread(g, p) { - if (!p->se.on_rq || task_cpu(p) != rq_cpu) + if (!p->on_rq || task_cpu(p) != rq_cpu) continue; print_task(m, rq, p); @@ -296,9 +296,6 @@ static void print_cpu(struct seq_file *m, int cpu) P(ttwu_count); P(ttwu_local); - SEQ_printf(m, " .%-30s: %d\n", "bkl_count", - rq->rq_sched_info.bkl_count); - #undef P #undef P64 #endif @@ -441,7 +438,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) P(se.statistics.wait_count); PN(se.statistics.iowait_sum); P(se.statistics.iowait_count); - P(sched_info.bkl_count); P(se.nr_migrations); P(se.statistics.nr_migrations_cold); P(se.statistics.nr_failed_migrations_affine); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 6fa833ab2cb..bc8ee999381 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -135,14 +135,6 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) return grp->my_q; } -/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on - * another cpu ('this_cpu') - */ -static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu) -{ - return cfs_rq->tg->cfs_rq[this_cpu]; -} - static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { if (!cfs_rq->on_list) { @@ -271,11 +263,6 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) return NULL; } -static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu) -{ - return &cpu_rq(this_cpu)->cfs; -} - static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { } @@ -334,11 +321,6 @@ static inline int entity_before(struct sched_entity *a, return (s64)(a->vruntime - b->vruntime) < 0; } -static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - return se->vruntime - cfs_rq->min_vruntime; -} - static void update_min_vruntime(struct cfs_rq *cfs_rq) { u64 vruntime = cfs_rq->min_vruntime; @@ -358,6 +340,10 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq) } cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime); +#ifndef CONFIG_64BIT + smp_wmb(); + cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; +#endif } /* @@ -368,7 +354,6 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) struct rb_node **link = &cfs_rq->tasks_timeline.rb_node; struct rb_node *parent = NULL; struct sched_entity *entry; - s64 key = entity_key(cfs_rq, se); int leftmost = 1; /* @@ -381,7 +366,7 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * We dont care about collisions. Nodes with * the same key stay together. */ - if (key < entity_key(cfs_rq, entry)) { + if (entity_before(se, entry)) { link = &parent->rb_left; } else { link = &parent->rb_right; @@ -1072,8 +1057,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) se->on_rq = 0; update_cfs_load(cfs_rq, 0); account_entity_dequeue(cfs_rq, se); - update_min_vruntime(cfs_rq); - update_cfs_shares(cfs_rq); /* * Normalize the entity after updating the min_vruntime because the @@ -1082,6 +1065,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) */ if (!(flags & DEQUEUE_SLEEP)) se->vruntime -= cfs_rq->min_vruntime; + + update_min_vruntime(cfs_rq); + update_cfs_shares(cfs_rq); } /* @@ -1331,7 +1317,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) } for_each_sched_entity(se) { - struct cfs_rq *cfs_rq = cfs_rq_of(se); + cfs_rq = cfs_rq_of(se); update_cfs_load(cfs_rq, 0); update_cfs_shares(cfs_rq); @@ -1340,6 +1326,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) hrtick_update(rq); } +static void set_next_buddy(struct sched_entity *se); + /* * The dequeue_task method is called before nr_running is * decreased. We remove the task from the rbtree and @@ -1349,19 +1337,30 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) { struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; + int task_sleep = flags & DEQUEUE_SLEEP; for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); dequeue_entity(cfs_rq, se, flags); /* Don't dequeue parent if it has other entities besides us */ - if (cfs_rq->load.weight) + if (cfs_rq->load.weight) { + /* + * Bias pick_next to pick a task from this cfs_rq, as + * p is sleeping when it is within its sched_slice. + */ + if (task_sleep && parent_entity(se)) + set_next_buddy(parent_entity(se)); + + /* avoid re-evaluating load for this entity */ + se = parent_entity(se); break; + } flags |= DEQUEUE_SLEEP; } for_each_sched_entity(se) { - struct cfs_rq *cfs_rq = cfs_rq_of(se); + cfs_rq = cfs_rq_of(se); update_cfs_load(cfs_rq, 0); update_cfs_shares(cfs_rq); @@ -1372,12 +1371,25 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) #ifdef CONFIG_SMP -static void task_waking_fair(struct rq *rq, struct task_struct *p) +static void task_waking_fair(struct task_struct *p) { struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 min_vruntime; - se->vruntime -= cfs_rq->min_vruntime; +#ifndef CONFIG_64BIT + u64 min_vruntime_copy; + + do { + min_vruntime_copy = cfs_rq->min_vruntime_copy; + smp_rmb(); + min_vruntime = cfs_rq->min_vruntime; + } while (min_vruntime != min_vruntime_copy); +#else + min_vruntime = cfs_rq->min_vruntime; +#endif + + se->vruntime -= min_vruntime; } #ifdef CONFIG_FAIR_GROUP_SCHED @@ -1453,7 +1465,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) * effect of the currently running task from the load * of the current CPU: */ - rcu_read_lock(); if (sync) { tg = task_group(current); weight = current->se.load.weight; @@ -1489,7 +1500,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) balanced = this_eff_load <= prev_eff_load; } else balanced = true; - rcu_read_unlock(); /* * If the currently running task will sleep within @@ -1557,7 +1567,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, } /* Adjust by relative CPU power of the group */ - avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power; + avg_load = (avg_load * SCHED_POWER_SCALE) / group->sgp->power; if (local_group) { this_load = avg_load; @@ -1622,6 +1632,7 @@ static int select_idle_sibling(struct task_struct *p, int target) /* * Otherwise, iterate the domains and find an elegible idle cpu. */ + rcu_read_lock(); for_each_domain(target, sd) { if (!(sd->flags & SD_SHARE_PKG_RESOURCES)) break; @@ -1641,6 +1652,7 @@ static int select_idle_sibling(struct task_struct *p, int target) cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) break; } + rcu_read_unlock(); return target; } @@ -1657,7 +1669,7 @@ static int select_idle_sibling(struct task_struct *p, int target) * preempt must be disabled. */ static int -select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags) +select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) { struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL; int cpu = smp_processor_id(); @@ -1673,6 +1685,7 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ new_cpu = prev_cpu; } + rcu_read_lock(); for_each_domain(cpu, tmp) { if (!(tmp->flags & SD_LOAD_BALANCE)) continue; @@ -1692,7 +1705,7 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ nr_running += cpu_rq(i)->cfs.nr_running; } - capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE); + capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE); if (tmp->flags & SD_POWERSAVINGS_BALANCE) nr_running /= 2; @@ -1723,9 +1736,10 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ if (affine_sd) { if (cpu == prev_cpu || wake_affine(affine_sd, p, sync)) - return select_idle_sibling(p, cpu); - else - return select_idle_sibling(p, prev_cpu); + prev_cpu = cpu; + + new_cpu = select_idle_sibling(p, prev_cpu); + goto unlock; } while (sd) { @@ -1766,6 +1780,8 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ } /* while loop will break here if sd == NULL */ } +unlock: + rcu_read_unlock(); return new_cpu; } @@ -1789,10 +1805,7 @@ wakeup_gran(struct sched_entity *curr, struct sched_entity *se) * This is especially important for buddies when the leftmost * task is higher priority than the buddy. */ - if (unlikely(se->load.weight != NICE_0_LOAD)) - gran = calc_delta_fair(gran, se); - - return gran; + return calc_delta_fair(gran, se); } /* @@ -1826,26 +1839,26 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se) static void set_last_buddy(struct sched_entity *se) { - if (likely(task_of(se)->policy != SCHED_IDLE)) { - for_each_sched_entity(se) - cfs_rq_of(se)->last = se; - } + if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) + return; + + for_each_sched_entity(se) + cfs_rq_of(se)->last = se; } static void set_next_buddy(struct sched_entity *se) { - if (likely(task_of(se)->policy != SCHED_IDLE)) { - for_each_sched_entity(se) - cfs_rq_of(se)->next = se; - } + if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) + return; + + for_each_sched_entity(se) + cfs_rq_of(se)->next = se; } static void set_skip_buddy(struct sched_entity *se) { - if (likely(task_of(se)->policy != SCHED_IDLE)) { - for_each_sched_entity(se) - cfs_rq_of(se)->skip = se; - } + for_each_sched_entity(se) + cfs_rq_of(se)->skip = se; } /* @@ -1857,12 +1870,15 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ struct sched_entity *se = &curr->se, *pse = &p->se; struct cfs_rq *cfs_rq = task_cfs_rq(curr); int scale = cfs_rq->nr_running >= sched_nr_latency; + int next_buddy_marked = 0; if (unlikely(se == pse)) return; - if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) + if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) { set_next_buddy(pse); + next_buddy_marked = 1; + } /* * We can come here with TIF_NEED_RESCHED already set from new task @@ -1887,11 +1903,18 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ if (!sched_feat(WAKEUP_PREEMPT)) return; - update_curr(cfs_rq); find_matching_se(&se, &pse); + update_curr(cfs_rq_of(se)); BUG_ON(!pse); - if (wakeup_preempt_entity(se, pse) == 1) + if (wakeup_preempt_entity(se, pse) == 1) { + /* + * Bias pick_next to pick the sched entity that is + * triggering this preemption. + */ + if (!next_buddy_marked) + set_next_buddy(pse); goto preempt; + } return; @@ -2102,7 +2125,7 @@ static unsigned long balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_load_move, struct sched_domain *sd, enum cpu_idle_type idle, int *all_pinned, - int *this_best_prio, struct cfs_rq *busiest_cfs_rq) + struct cfs_rq *busiest_cfs_rq) { int loops = 0, pulled = 0; long rem_load_move = max_load_move; @@ -2140,9 +2163,6 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, */ if (rem_load_move <= 0) break; - - if (p->prio < *this_best_prio) - *this_best_prio = p->prio; } out: /* @@ -2193,26 +2213,56 @@ static void update_shares(int cpu) struct rq *rq = cpu_rq(cpu); rcu_read_lock(); + /* + * Iterates the task_group tree in a bottom up fashion, see + * list_add_leaf_cfs_rq() for details. + */ for_each_leaf_cfs_rq(rq, cfs_rq) update_shares_cpu(cfs_rq->tg, cpu); rcu_read_unlock(); } +/* + * Compute the cpu's hierarchical load factor for each task group. + * This needs to be done in a top-down fashion because the load of a child + * group is a fraction of its parents load. + */ +static int tg_load_down(struct task_group *tg, void *data) +{ + unsigned long load; + long cpu = (long)data; + + if (!tg->parent) { + load = cpu_rq(cpu)->load.weight; + } else { + load = tg->parent->cfs_rq[cpu]->h_load; + load *= tg->se[cpu]->load.weight; + load /= tg->parent->cfs_rq[cpu]->load.weight + 1; + } + + tg->cfs_rq[cpu]->h_load = load; + + return 0; +} + +static void update_h_load(long cpu) +{ + walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); +} + static unsigned long load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_load_move, struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, int *this_best_prio) + int *all_pinned) { long rem_load_move = max_load_move; - int busiest_cpu = cpu_of(busiest); - struct task_group *tg; + struct cfs_rq *busiest_cfs_rq; rcu_read_lock(); - update_h_load(busiest_cpu); + update_h_load(cpu_of(busiest)); - list_for_each_entry_rcu(tg, &task_groups, list) { - struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu]; + for_each_leaf_cfs_rq(busiest, busiest_cfs_rq) { unsigned long busiest_h_load = busiest_cfs_rq->h_load; unsigned long busiest_weight = busiest_cfs_rq->load.weight; u64 rem_load, moved_load; @@ -2227,7 +2277,7 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, rem_load = div_u64(rem_load, busiest_h_load + 1); moved_load = balance_tasks(this_rq, this_cpu, busiest, - rem_load, sd, idle, all_pinned, this_best_prio, + rem_load, sd, idle, all_pinned, busiest_cfs_rq); if (!moved_load) @@ -2253,11 +2303,11 @@ static unsigned long load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_load_move, struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, int *this_best_prio) + int *all_pinned) { return balance_tasks(this_rq, this_cpu, busiest, max_load_move, sd, idle, all_pinned, - this_best_prio, &busiest->cfs); + &busiest->cfs); } #endif @@ -2274,12 +2324,11 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, int *all_pinned) { unsigned long total_load_moved = 0, load_moved; - int this_best_prio = this_rq->curr->prio; do { load_moved = load_balance_fair(this_rq, this_cpu, busiest, max_load_move - total_load_moved, - sd, idle, all_pinned, &this_best_prio); + sd, idle, all_pinned); total_load_moved += load_moved; @@ -2534,7 +2583,7 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) { - return SCHED_LOAD_SCALE; + return SCHED_POWER_SCALE; } unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu) @@ -2571,10 +2620,10 @@ unsigned long scale_rt_power(int cpu) available = total - rq->rt_avg; } - if (unlikely((s64)total < SCHED_LOAD_SCALE)) - total = SCHED_LOAD_SCALE; + if (unlikely((s64)total < SCHED_POWER_SCALE)) + total = SCHED_POWER_SCALE; - total >>= SCHED_LOAD_SHIFT; + total >>= SCHED_POWER_SHIFT; return div_u64(available, total); } @@ -2582,7 +2631,7 @@ unsigned long scale_rt_power(int cpu) static void update_cpu_power(struct sched_domain *sd, int cpu) { unsigned long weight = sd->span_weight; - unsigned long power = SCHED_LOAD_SCALE; + unsigned long power = SCHED_POWER_SCALE; struct sched_group *sdg = sd->groups; if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { @@ -2591,26 +2640,26 @@ static void update_cpu_power(struct sched_domain *sd, int cpu) else power *= default_scale_smt_power(sd, cpu); - power >>= SCHED_LOAD_SHIFT; + power >>= SCHED_POWER_SHIFT; } - sdg->cpu_power_orig = power; + sdg->sgp->power_orig = power; if (sched_feat(ARCH_POWER)) power *= arch_scale_freq_power(sd, cpu); else power *= default_scale_freq_power(sd, cpu); - power >>= SCHED_LOAD_SHIFT; + power >>= SCHED_POWER_SHIFT; power *= scale_rt_power(cpu); - power >>= SCHED_LOAD_SHIFT; + power >>= SCHED_POWER_SHIFT; if (!power) power = 1; cpu_rq(cpu)->cpu_power = power; - sdg->cpu_power = power; + sdg->sgp->power = power; } static void update_group_power(struct sched_domain *sd, int cpu) @@ -2628,11 +2677,11 @@ static void update_group_power(struct sched_domain *sd, int cpu) group = child->groups; do { - power += group->cpu_power; + power += group->sgp->power; group = group->next; } while (group != child->groups); - sdg->cpu_power = power; + sdg->sgp->power = power; } /* @@ -2646,15 +2695,15 @@ static inline int fix_small_capacity(struct sched_domain *sd, struct sched_group *group) { /* - * Only siblings can have significantly less than SCHED_LOAD_SCALE + * Only siblings can have significantly less than SCHED_POWER_SCALE */ - if (sd->level != SD_LV_SIBLING) + if (!(sd->flags & SD_SHARE_CPUPOWER)) return 0; /* * If ~90% of the cpu_power is still there, we're good. */ - if (group->cpu_power * 32 > group->cpu_power_orig * 29) + if (group->sgp->power * 32 > group->sgp->power_orig * 29) return 1; return 0; @@ -2734,7 +2783,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, } /* Adjust by relative CPU power of the group */ - sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power; + sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / group->sgp->power; /* * Consider the group unbalanced when the imbalance is larger @@ -2751,7 +2800,8 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1) sgs->group_imb = 1; - sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE); + sgs->group_capacity = DIV_ROUND_CLOSEST(group->sgp->power, + SCHED_POWER_SCALE); if (!sgs->group_capacity) sgs->group_capacity = fix_small_capacity(sd, group); sgs->group_weight = group->group_weight; @@ -2839,7 +2889,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, return; sds->total_load += sgs.group_load; - sds->total_pwr += sg->cpu_power; + sds->total_pwr += sg->sgp->power; /* * In case the child domain prefers tasks go to siblings @@ -2924,8 +2974,8 @@ static int check_asym_packing(struct sched_domain *sd, if (this_cpu > busiest_cpu) return 0; - *imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->cpu_power, - SCHED_LOAD_SCALE); + *imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->sgp->power, + SCHED_POWER_SCALE); return 1; } @@ -2954,8 +3004,8 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds, cpu_avg_load_per_task(this_cpu); scaled_busy_load_per_task = sds->busiest_load_per_task - * SCHED_LOAD_SCALE; - scaled_busy_load_per_task /= sds->busiest->cpu_power; + * SCHED_POWER_SCALE; + scaled_busy_load_per_task /= sds->busiest->sgp->power; if (sds->max_load - sds->this_load + scaled_busy_load_per_task >= (scaled_busy_load_per_task * imbn)) { @@ -2969,30 +3019,30 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds, * moving them. */ - pwr_now += sds->busiest->cpu_power * + pwr_now += sds->busiest->sgp->power * min(sds->busiest_load_per_task, sds->max_load); - pwr_now += sds->this->cpu_power * + pwr_now += sds->this->sgp->power * min(sds->this_load_per_task, sds->this_load); - pwr_now /= SCHED_LOAD_SCALE; + pwr_now /= SCHED_POWER_SCALE; /* Amount of load we'd subtract */ - tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) / - sds->busiest->cpu_power; + tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) / + sds->busiest->sgp->power; if (sds->max_load > tmp) - pwr_move += sds->busiest->cpu_power * + pwr_move += sds->busiest->sgp->power * min(sds->busiest_load_per_task, sds->max_load - tmp); /* Amount of load we'd add */ - if (sds->max_load * sds->busiest->cpu_power < - sds->busiest_load_per_task * SCHED_LOAD_SCALE) - tmp = (sds->max_load * sds->busiest->cpu_power) / - sds->this->cpu_power; + if (sds->max_load * sds->busiest->sgp->power < + sds->busiest_load_per_task * SCHED_POWER_SCALE) + tmp = (sds->max_load * sds->busiest->sgp->power) / + sds->this->sgp->power; else - tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) / - sds->this->cpu_power; - pwr_move += sds->this->cpu_power * + tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) / + sds->this->sgp->power; + pwr_move += sds->this->sgp->power * min(sds->this_load_per_task, sds->this_load + tmp); - pwr_move /= SCHED_LOAD_SCALE; + pwr_move /= SCHED_POWER_SCALE; /* Move if we gain throughput */ if (pwr_move > pwr_now) @@ -3034,9 +3084,9 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, load_above_capacity = (sds->busiest_nr_running - sds->busiest_group_capacity); - load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_LOAD_SCALE); + load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_POWER_SCALE); - load_above_capacity /= sds->busiest->cpu_power; + load_above_capacity /= sds->busiest->sgp->power; } /* @@ -3052,9 +3102,9 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, max_pull = min(sds->max_load - sds->avg_load, load_above_capacity); /* How much load to actually move to equalise the imbalance */ - *imbalance = min(max_pull * sds->busiest->cpu_power, - (sds->avg_load - sds->this_load) * sds->this->cpu_power) - / SCHED_LOAD_SCALE; + *imbalance = min(max_pull * sds->busiest->sgp->power, + (sds->avg_load - sds->this_load) * sds->this->sgp->power) + / SCHED_POWER_SCALE; /* * if *imbalance is less than the average load per runnable task @@ -3123,7 +3173,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, if (!sds.busiest || sds.busiest_nr_running == 0) goto out_balanced; - sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr; + sds.avg_load = (SCHED_POWER_SCALE * sds.total_load) / sds.total_pwr; /* * If the busiest group is imbalanced the below checks don't @@ -3202,7 +3252,8 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group, for_each_cpu(i, sched_group_cpus(group)) { unsigned long power = power_of(i); - unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE); + unsigned long capacity = DIV_ROUND_CLOSEST(power, + SCHED_POWER_SCALE); unsigned long wl; if (!capacity) @@ -3227,7 +3278,7 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group, * the load can be moved away from the cpu that is potentially * running at a lower capacity. */ - wl = (wl * SCHED_LOAD_SCALE) / power; + wl = (wl * SCHED_POWER_SCALE) / power; if (wl > max_load) { max_load = wl; @@ -3465,6 +3516,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq) raw_spin_unlock(&this_rq->lock); update_shares(this_cpu); + rcu_read_lock(); for_each_domain(this_cpu, sd) { unsigned long interval; int balance = 1; @@ -3486,6 +3538,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq) break; } } + rcu_read_unlock(); raw_spin_lock(&this_rq->lock); @@ -3534,6 +3587,7 @@ static int active_load_balance_cpu_stop(void *data) double_lock_balance(busiest_rq, target_rq); /* Search for an sd spanning us and the target CPU. */ + rcu_read_lock(); for_each_domain(target_cpu, sd) { if ((sd->flags & SD_LOAD_BALANCE) && cpumask_test_cpu(busiest_cpu, sched_domain_span(sd))) @@ -3549,6 +3603,7 @@ static int active_load_balance_cpu_stop(void *data) else schedstat_inc(sd, alb_failed); } + rcu_read_unlock(); double_unlock_balance(busiest_rq, target_rq); out_unlock: busiest_rq->active_balance = 0; @@ -3675,6 +3730,7 @@ static int find_new_ilb(int cpu) { struct sched_domain *sd; struct sched_group *ilb_group; + int ilb = nr_cpu_ids; /* * Have idle load balancer selection from semi-idle packages only @@ -3690,20 +3746,25 @@ static int find_new_ilb(int cpu) if (cpumask_weight(nohz.idle_cpus_mask) < 2) goto out_done; + rcu_read_lock(); for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) { ilb_group = sd->groups; do { - if (is_semi_idle_group(ilb_group)) - return cpumask_first(nohz.grp_idle_mask); + if (is_semi_idle_group(ilb_group)) { + ilb = cpumask_first(nohz.grp_idle_mask); + goto unlock; + } ilb_group = ilb_group->next; } while (ilb_group != sd->groups); } +unlock: + rcu_read_unlock(); out_done: - return nr_cpu_ids; + return ilb; } #else /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */ static inline int find_new_ilb(int call_cpu) @@ -3848,6 +3909,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) update_shares(cpu); + rcu_read_lock(); for_each_domain(cpu, sd) { if (!(sd->flags & SD_LOAD_BALANCE)) continue; @@ -3893,6 +3955,7 @@ out: if (!balance) break; } + rcu_read_unlock(); /* * next_balance will be updated only when there is a need. diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 68e69acc29b..2e74677cb04 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -61,6 +61,14 @@ SCHED_FEAT(LB_BIAS, 1) SCHED_FEAT(OWNER_SPIN, 1) /* - * Decrement CPU power based on irq activity + * Decrement CPU power based on time not spent running tasks */ -SCHED_FEAT(NONIRQ_POWER, 1) +SCHED_FEAT(NONTASK_POWER, 1) + +/* + * Queue remote wakeups on the target CPU and process them + * using the scheduler IPI. Reduces rq->lock contention/bounces. + */ +SCHED_FEAT(TTWU_QUEUE, 1) + +SCHED_FEAT(FORCE_SD_OVERLAP, 0) diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c index a776a639642..0a51882534e 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -7,7 +7,7 @@ #ifdef CONFIG_SMP static int -select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags) +select_task_rq_idle(struct task_struct *p, int sd_flag, int flags) { return task_cpu(p); /* IDLE tasks as never migrated */ } diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index e7cebdc65f8..97540f0c9e4 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -183,6 +183,26 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq) return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period); } +typedef struct task_group *rt_rq_iter_t; + +static inline struct task_group *next_task_group(struct task_group *tg) +{ + do { + tg = list_entry_rcu(tg->list.next, + typeof(struct task_group), list); + } while (&tg->list != &task_groups && task_group_is_autogroup(tg)); + + if (&tg->list == &task_groups) + tg = NULL; + + return tg; +} + +#define for_each_rt_rq(rt_rq, iter, rq) \ + for (iter = container_of(&task_groups, typeof(*iter), list); \ + (iter = next_task_group(iter)) && \ + (rt_rq = iter->rt_rq[cpu_of(rq)]);) + static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq) { list_add_rcu(&rt_rq->leaf_rt_rq_list, @@ -288,6 +308,11 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq) return ktime_to_ns(def_rt_bandwidth.rt_period); } +typedef struct rt_rq *rt_rq_iter_t; + +#define for_each_rt_rq(rt_rq, iter, rq) \ + for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL) + static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq) { } @@ -402,12 +427,13 @@ next: static void __disable_runtime(struct rq *rq) { struct root_domain *rd = rq->rd; + rt_rq_iter_t iter; struct rt_rq *rt_rq; if (unlikely(!scheduler_running)) return; - for_each_leaf_rt_rq(rt_rq, rq) { + for_each_rt_rq(rt_rq, iter, rq) { struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); s64 want; int i; @@ -487,6 +513,7 @@ static void disable_runtime(struct rq *rq) static void __enable_runtime(struct rq *rq) { + rt_rq_iter_t iter; struct rt_rq *rt_rq; if (unlikely(!scheduler_running)) @@ -495,7 +522,7 @@ static void __enable_runtime(struct rq *rq) /* * Reset each runqueue's bandwidth settings */ - for_each_leaf_rt_rq(rt_rq, rq) { + for_each_rt_rq(rt_rq, iter, rq) { struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); raw_spin_lock(&rt_b->rt_runtime_lock); @@ -562,6 +589,13 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) { rt_rq->rt_throttled = 0; enqueue = 1; + + /* + * Force a clock update if the CPU was idle, + * lest wakeup -> unthrottle time accumulate. + */ + if (rt_rq->rt_nr_running && rq->curr == rq->idle) + rq->skip_clock_update = -1; } if (rt_rq->rt_time || rt_rq->rt_nr_running) idle = 0; @@ -977,13 +1011,23 @@ static void yield_task_rt(struct rq *rq) static int find_lowest_rq(struct task_struct *task); static int -select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags) +select_task_rq_rt(struct task_struct *p, int sd_flag, int flags) { + struct task_struct *curr; + struct rq *rq; + int cpu; + if (sd_flag != SD_BALANCE_WAKE) return smp_processor_id(); + cpu = task_cpu(p); + rq = cpu_rq(cpu); + + rcu_read_lock(); + curr = ACCESS_ONCE(rq->curr); /* unlocked access */ + /* - * If the current task is an RT task, then + * If the current task on @p's runqueue is an RT task, then * try to see if we can wake this RT task up on another * runqueue. Otherwise simply start this RT task * on its current runqueue. @@ -997,21 +1041,25 @@ select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags) * lock? * * For equal prio tasks, we just let the scheduler sort it out. + * + * Otherwise, just let it ride on the affined RQ and the + * post-schedule router will push the preempted task away + * + * This test is optimistic, if we get it wrong the load-balancer + * will have to sort it out. */ - if (unlikely(rt_task(rq->curr)) && - (rq->curr->rt.nr_cpus_allowed < 2 || - rq->curr->prio < p->prio) && + if (curr && unlikely(rt_task(curr)) && + (curr->rt.nr_cpus_allowed < 2 || + curr->prio < p->prio) && (p->rt.nr_cpus_allowed > 1)) { - int cpu = find_lowest_rq(p); + int target = find_lowest_rq(p); - return (cpu == -1) ? task_cpu(p) : cpu; + if (target != -1) + cpu = target; } + rcu_read_unlock(); - /* - * Otherwise, just let it ride on the affined RQ and the - * post-schedule router will push the preempted task away - */ - return task_cpu(p); + return cpu; } static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) @@ -1060,7 +1108,7 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag * to move current somewhere else, making room for our non-migratable * task. */ - if (p->prio == rq->curr->prio && !need_resched()) + if (p->prio == rq->curr->prio && !test_tsk_need_resched(rq->curr)) check_preempt_equal_prio(rq, p); #endif } @@ -1090,7 +1138,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) rt_rq = &rq->rt; - if (unlikely(!rt_rq->rt_nr_running)) + if (!rt_rq->rt_nr_running) return NULL; if (rt_rq_throttled(rt_rq)) @@ -1136,7 +1184,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) * The previous task needs to be made eligible for pushing * if it is still active */ - if (p->se.on_rq && p->rt.nr_cpus_allowed > 1) + if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); } @@ -1203,6 +1251,10 @@ static int find_lowest_rq(struct task_struct *task) int this_cpu = smp_processor_id(); int cpu = task_cpu(task); + /* Make sure the mask is initialized first */ + if (unlikely(!lowest_mask)) + return -1; + if (task->rt.nr_cpus_allowed == 1) return -1; /* No other targets possible */ @@ -1227,6 +1279,7 @@ static int find_lowest_rq(struct task_struct *task) if (!cpumask_test_cpu(this_cpu, lowest_mask)) this_cpu = -1; /* Skip this_cpu opt if not among lowest */ + rcu_read_lock(); for_each_domain(cpu, sd) { if (sd->flags & SD_WAKE_AFFINE) { int best_cpu; @@ -1236,15 +1289,20 @@ static int find_lowest_rq(struct task_struct *task) * remote processor. */ if (this_cpu != -1 && - cpumask_test_cpu(this_cpu, sched_domain_span(sd))) + cpumask_test_cpu(this_cpu, sched_domain_span(sd))) { + rcu_read_unlock(); return this_cpu; + } best_cpu = cpumask_first_and(lowest_mask, sched_domain_span(sd)); - if (best_cpu < nr_cpu_ids) + if (best_cpu < nr_cpu_ids) { + rcu_read_unlock(); return best_cpu; + } } } + rcu_read_unlock(); /* * And finally, if there were no matches within the domains @@ -1287,7 +1345,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) || task_running(rq, task) || - !task->se.on_rq)) { + !task->on_rq)) { raw_spin_unlock(&lowest_rq->lock); lowest_rq = NULL; @@ -1321,7 +1379,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq) BUG_ON(task_current(rq, p)); BUG_ON(p->rt.nr_cpus_allowed <= 1); - BUG_ON(!p->se.on_rq); + BUG_ON(!p->on_rq); BUG_ON(!rt_task(p)); return p; @@ -1467,7 +1525,7 @@ static int pull_rt_task(struct rq *this_rq) */ if (p && (p->prio < this_rq->rt.highest_prio.curr)) { WARN_ON(p == src_rq->curr); - WARN_ON(!p->se.on_rq); + WARN_ON(!p->on_rq); /* * There's a chance that p is higher in priority @@ -1502,7 +1560,7 @@ skip: static void pre_schedule_rt(struct rq *rq, struct task_struct *prev) { /* Try to pull RT tasks here if we lower this rq's prio */ - if (unlikely(rt_task(prev)) && rq->rt.highest_prio.curr > prev->prio) + if (rq->rt.highest_prio.curr > prev->prio) pull_rt_task(rq); } @@ -1538,7 +1596,7 @@ static void set_cpus_allowed_rt(struct task_struct *p, * Update the migration status of the RQ if we have an RT task * which is running AND changing its weight value. */ - if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) { + if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) { struct rq *rq = task_rq(p); if (!task_current(rq, p)) { @@ -1608,7 +1666,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p) * we may need to handle the pulling of RT tasks * now. */ - if (p->se.on_rq && !rq->rt.rt_nr_running) + if (p->on_rq && !rq->rt.rt_nr_running) pull_rt_task(rq); } @@ -1638,7 +1696,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) * If that current running task is also an RT task * then see if we can move to another run queue. */ - if (p->se.on_rq && rq->curr != p) { + if (p->on_rq && rq->curr != p) { #ifdef CONFIG_SMP if (rq->rt.overloaded && push_rt_task(rq) && /* Don't resched if we changed runqueues */ @@ -1657,7 +1715,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) static void prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) { - if (!p->se.on_rq) + if (!p->on_rq) return; if (rq->curr == p) { @@ -1796,10 +1854,11 @@ extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq); static void print_rt_stats(struct seq_file *m, int cpu) { + rt_rq_iter_t iter; struct rt_rq *rt_rq; rcu_read_lock(); - for_each_leaf_rt_rq(rt_rq, cpu_rq(cpu)) + for_each_rt_rq(rt_rq, iter, cpu_rq(cpu)) print_rt_rq(m, cpu, rt_rq); rcu_read_unlock(); } diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 48ddf431db0..331e01bcd02 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -37,7 +37,7 @@ static int show_schedstat(struct seq_file *seq, void *v) #ifdef CONFIG_SMP /* domain-specific stats */ - preempt_disable(); + rcu_read_lock(); for_each_domain(cpu, sd) { enum cpu_idle_type itype; @@ -64,7 +64,7 @@ static int show_schedstat(struct seq_file *seq, void *v) sd->ttwu_wake_remote, sd->ttwu_move_affine, sd->ttwu_move_balance); } - preempt_enable(); + rcu_read_unlock(); #endif } kfree(mask_str); diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c index 1ba2bd40fda..6f437632afa 100644 --- a/kernel/sched_stoptask.c +++ b/kernel/sched_stoptask.c @@ -9,8 +9,7 @@ #ifdef CONFIG_SMP static int -select_task_rq_stop(struct rq *rq, struct task_struct *p, - int sd_flag, int flags) +select_task_rq_stop(struct task_struct *p, int sd_flag, int flags) { return task_cpu(p); /* stop tasks as never migrate */ } @@ -26,7 +25,7 @@ static struct task_struct *pick_next_task_stop(struct rq *rq) { struct task_struct *stop = rq->stop; - if (stop && stop->se.on_rq) + if (stop && stop->on_rq) return stop; return NULL; diff --git a/kernel/signal.c b/kernel/signal.c index 7165af5f1b1..291c9700be7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -87,7 +87,7 @@ static int sig_ignored(struct task_struct *t, int sig, int from_ancestor_ns) /* * Tracers may want to know about even ignored signals. */ - return !tracehook_consider_ignored_signal(t, sig); + return !t->ptrace; } /* @@ -124,7 +124,7 @@ static inline int has_pending_signals(sigset_t *signal, sigset_t *blocked) static int recalc_sigpending_tsk(struct task_struct *t) { - if (t->signal->group_stop_count > 0 || + if ((t->jobctl & JOBCTL_PENDING_MASK) || PENDING(&t->pending, &t->blocked) || PENDING(&t->signal->shared_pending, &t->blocked)) { set_tsk_thread_flag(t, TIF_SIGPENDING); @@ -150,9 +150,7 @@ void recalc_sigpending_and_wake(struct task_struct *t) void recalc_sigpending(void) { - if (unlikely(tracehook_force_sigpending())) - set_thread_flag(TIF_SIGPENDING); - else if (!recalc_sigpending_tsk(current) && !freezing(current)) + if (!recalc_sigpending_tsk(current) && !freezing(current)) clear_thread_flag(TIF_SIGPENDING); } @@ -223,6 +221,129 @@ static inline void print_dropped_signal(int sig) current->comm, current->pid, sig); } +/** + * task_set_jobctl_pending - set jobctl pending bits + * @task: target task + * @mask: pending bits to set + * + * Clear @mask from @task->jobctl. @mask must be subset of + * %JOBCTL_PENDING_MASK | %JOBCTL_STOP_CONSUME | %JOBCTL_STOP_SIGMASK | + * %JOBCTL_TRAPPING. If stop signo is being set, the existing signo is + * cleared. If @task is already being killed or exiting, this function + * becomes noop. + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + * + * RETURNS: + * %true if @mask is set, %false if made noop because @task was dying. + */ +bool task_set_jobctl_pending(struct task_struct *task, unsigned int mask) +{ + BUG_ON(mask & ~(JOBCTL_PENDING_MASK | JOBCTL_STOP_CONSUME | + JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING)); + BUG_ON((mask & JOBCTL_TRAPPING) && !(mask & JOBCTL_PENDING_MASK)); + + if (unlikely(fatal_signal_pending(task) || (task->flags & PF_EXITING))) + return false; + + if (mask & JOBCTL_STOP_SIGMASK) + task->jobctl &= ~JOBCTL_STOP_SIGMASK; + + task->jobctl |= mask; + return true; +} + +/** + * task_clear_jobctl_trapping - clear jobctl trapping bit + * @task: target task + * + * If JOBCTL_TRAPPING is set, a ptracer is waiting for us to enter TRACED. + * Clear it and wake up the ptracer. Note that we don't need any further + * locking. @task->siglock guarantees that @task->parent points to the + * ptracer. + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + */ +void task_clear_jobctl_trapping(struct task_struct *task) +{ + if (unlikely(task->jobctl & JOBCTL_TRAPPING)) { + task->jobctl &= ~JOBCTL_TRAPPING; + wake_up_bit(&task->jobctl, JOBCTL_TRAPPING_BIT); + } +} + +/** + * task_clear_jobctl_pending - clear jobctl pending bits + * @task: target task + * @mask: pending bits to clear + * + * Clear @mask from @task->jobctl. @mask must be subset of + * %JOBCTL_PENDING_MASK. If %JOBCTL_STOP_PENDING is being cleared, other + * STOP bits are cleared together. + * + * If clearing of @mask leaves no stop or trap pending, this function calls + * task_clear_jobctl_trapping(). + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + */ +void task_clear_jobctl_pending(struct task_struct *task, unsigned int mask) +{ + BUG_ON(mask & ~JOBCTL_PENDING_MASK); + + if (mask & JOBCTL_STOP_PENDING) + mask |= JOBCTL_STOP_CONSUME | JOBCTL_STOP_DEQUEUED; + + task->jobctl &= ~mask; + + if (!(task->jobctl & JOBCTL_PENDING_MASK)) + task_clear_jobctl_trapping(task); +} + +/** + * task_participate_group_stop - participate in a group stop + * @task: task participating in a group stop + * + * @task has %JOBCTL_STOP_PENDING set and is participating in a group stop. + * Group stop states are cleared and the group stop count is consumed if + * %JOBCTL_STOP_CONSUME was set. If the consumption completes the group + * stop, the appropriate %SIGNAL_* flags are set. + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + * + * RETURNS: + * %true if group stop completion should be notified to the parent, %false + * otherwise. + */ +static bool task_participate_group_stop(struct task_struct *task) +{ + struct signal_struct *sig = task->signal; + bool consume = task->jobctl & JOBCTL_STOP_CONSUME; + + WARN_ON_ONCE(!(task->jobctl & JOBCTL_STOP_PENDING)); + + task_clear_jobctl_pending(task, JOBCTL_STOP_PENDING); + + if (!consume) + return false; + + if (!WARN_ON_ONCE(sig->group_stop_count == 0)) + sig->group_stop_count--; + + /* + * Tell the caller to notify completion iff we are entering into a + * fresh group stop. Read comment in do_signal_stop() for details. + */ + if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) { + sig->flags = SIGNAL_STOP_STOPPED; + return true; + } + return false; +} + /* * allocate a new signal queue record * - this may be called without locks if and only if t == current, otherwise an @@ -372,7 +493,8 @@ int unhandled_signal(struct task_struct *tsk, int sig) return 1; if (handler != SIG_IGN && handler != SIG_DFL) return 0; - return !tracehook_consider_fatal_signal(tsk, sig); + /* if ptraced, let the tracer determine */ + return !tsk->ptrace; } /* @@ -527,7 +649,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) * is to alert stop-signal processing code when another * processor has come along and cleared the flag. */ - tsk->signal->flags |= SIGNAL_STOP_DEQUEUED; + current->jobctl |= JOBCTL_STOP_DEQUEUED; } if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) { /* @@ -592,7 +714,7 @@ static int rm_from_queue_full(sigset_t *mask, struct sigpending *s) if (sigisemptyset(&m)) return 0; - signandsets(&s->signal, &s->signal, mask); + sigandnsets(&s->signal, &s->signal, mask); list_for_each_entry_safe(q, n, &s->list, list) { if (sigismember(mask, q->info.si_signo)) { list_del_init(&q->list); @@ -696,6 +818,32 @@ static int check_kill_permission(int sig, struct siginfo *info, return security_task_kill(t, info, sig, 0); } +/** + * ptrace_trap_notify - schedule trap to notify ptracer + * @t: tracee wanting to notify tracer + * + * This function schedules sticky ptrace trap which is cleared on the next + * TRAP_STOP to notify ptracer of an event. @t must have been seized by + * ptracer. + * + * If @t is running, STOP trap will be taken. If trapped for STOP and + * ptracer is listening for events, tracee is woken up so that it can + * re-trap for the new event. If trapped otherwise, STOP trap will be + * eventually taken without returning to userland after the existing traps + * are finished by PTRACE_CONT. + * + * CONTEXT: + * Must be called with @task->sighand->siglock held. + */ +static void ptrace_trap_notify(struct task_struct *t) +{ + WARN_ON_ONCE(!(t->ptrace & PT_SEIZED)); + assert_spin_locked(&t->sighand->siglock); + + task_set_jobctl_pending(t, JOBCTL_TRAP_NOTIFY); + signal_wake_up(t, t->jobctl & JOBCTL_LISTENING); +} + /* * Handle magic process-wide effects of stop/continue signals. Unlike * the signal actions, these happen immediately at signal-generation @@ -727,34 +875,17 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns) } else if (sig == SIGCONT) { unsigned int why; /* - * Remove all stop signals from all queues, - * and wake all threads. + * Remove all stop signals from all queues, wake all threads. */ rm_from_queue(SIG_KERNEL_STOP_MASK, &signal->shared_pending); t = p; do { - unsigned int state; + task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING); rm_from_queue(SIG_KERNEL_STOP_MASK, &t->pending); - /* - * If there is a handler for SIGCONT, we must make - * sure that no thread returns to user mode before - * we post the signal, in case it was the only - * thread eligible to run the signal handler--then - * it must not do anything between resuming and - * running the handler. With the TIF_SIGPENDING - * flag set, the thread will pause and acquire the - * siglock that we hold now and until we've queued - * the pending signal. - * - * Wake up the stopped thread _after_ setting - * TIF_SIGPENDING - */ - state = __TASK_STOPPED; - if (sig_user_defined(t, SIGCONT) && !sigismember(&t->blocked, SIGCONT)) { - set_tsk_thread_flag(t, TIF_SIGPENDING); - state |= TASK_INTERRUPTIBLE; - } - wake_up_state(t, state); + if (likely(!(t->ptrace & PT_SEIZED))) + wake_up_state(t, __TASK_STOPPED); + else + ptrace_trap_notify(t); } while_each_thread(p, t); /* @@ -780,13 +911,6 @@ static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns) signal->flags = why | SIGNAL_STOP_CONTINUED; signal->group_stop_count = 0; signal->group_exit_code = 0; - } else { - /* - * We are not stopped, but there could be a stop - * signal in the middle of being processed after - * being removed from the queue. Clear that too. - */ - signal->flags &= ~SIGNAL_STOP_DEQUEUED; } } @@ -858,8 +982,7 @@ static void complete_signal(int sig, struct task_struct *p, int group) if (sig_fatal(p, sig) && !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) && !sigismember(&t->real_blocked, sig) && - (sig == SIGKILL || - !tracehook_consider_fatal_signal(t, sig))) { + (sig == SIGKILL || !t->ptrace)) { /* * This signal will be fatal to the whole group. */ @@ -875,6 +998,7 @@ static void complete_signal(int sig, struct task_struct *p, int group) signal->group_stop_count = 0; t = p; do { + task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); } while_each_thread(p, t); @@ -1109,6 +1233,7 @@ int zap_other_threads(struct task_struct *p) p->signal->group_stop_count = 0; while_each_thread(p, t) { + task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); count++; /* Don't bother with already dead threads */ @@ -1126,18 +1251,25 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, { struct sighand_struct *sighand; - rcu_read_lock(); for (;;) { + local_irq_save(*flags); + rcu_read_lock(); sighand = rcu_dereference(tsk->sighand); - if (unlikely(sighand == NULL)) + if (unlikely(sighand == NULL)) { + rcu_read_unlock(); + local_irq_restore(*flags); break; + } - spin_lock_irqsave(&sighand->siglock, *flags); - if (likely(sighand == tsk->sighand)) + spin_lock(&sighand->siglock); + if (likely(sighand == tsk->sighand)) { + rcu_read_unlock(); break; - spin_unlock_irqrestore(&sighand->siglock, *flags); + } + spin_unlock(&sighand->siglock); + rcu_read_unlock(); + local_irq_restore(*flags); } - rcu_read_unlock(); return sighand; } @@ -1452,22 +1584,22 @@ ret: * Let a parent know about the death of a child. * For a stopped/continued status change, use do_notify_parent_cldstop instead. * - * Returns -1 if our parent ignored us and so we've switched to - * self-reaping, or else @sig. + * Returns true if our parent ignored us and so we've switched to + * self-reaping. */ -int do_notify_parent(struct task_struct *tsk, int sig) +bool do_notify_parent(struct task_struct *tsk, int sig) { struct siginfo info; unsigned long flags; struct sighand_struct *psig; - int ret = sig; + bool autoreap = false; BUG_ON(sig == -1); /* do_notify_parent_cldstop should have been called instead. */ BUG_ON(task_is_stopped_or_traced(tsk)); - BUG_ON(!task_ptrace(tsk) && + BUG_ON(!tsk->ptrace && (tsk->group_leader != tsk || !thread_group_empty(tsk))); info.si_signo = sig; @@ -1506,7 +1638,7 @@ int do_notify_parent(struct task_struct *tsk, int sig) psig = tsk->parent->sighand; spin_lock_irqsave(&psig->siglock, flags); - if (!task_ptrace(tsk) && sig == SIGCHLD && + if (!tsk->ptrace && sig == SIGCHLD && (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN || (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT))) { /* @@ -1524,28 +1656,42 @@ int do_notify_parent(struct task_struct *tsk, int sig) * is implementation-defined: we do (if you don't want * it, just use SIG_IGN instead). */ - ret = tsk->exit_signal = -1; + autoreap = true; if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) - sig = -1; + sig = 0; } - if (valid_signal(sig) && sig > 0) + if (valid_signal(sig) && sig) __group_send_sig_info(sig, &info, tsk->parent); __wake_up_parent(tsk, tsk->parent); spin_unlock_irqrestore(&psig->siglock, flags); - return ret; + return autoreap; } -static void do_notify_parent_cldstop(struct task_struct *tsk, int why) +/** + * do_notify_parent_cldstop - notify parent of stopped/continued state change + * @tsk: task reporting the state change + * @for_ptracer: the notification is for ptracer + * @why: CLD_{CONTINUED|STOPPED|TRAPPED} to report + * + * Notify @tsk's parent that the stopped/continued state has changed. If + * @for_ptracer is %false, @tsk's group leader notifies to its real parent. + * If %true, @tsk reports to @tsk->parent which should be the ptracer. + * + * CONTEXT: + * Must be called with tasklist_lock at least read locked. + */ +static void do_notify_parent_cldstop(struct task_struct *tsk, + bool for_ptracer, int why) { struct siginfo info; unsigned long flags; struct task_struct *parent; struct sighand_struct *sighand; - if (task_ptrace(tsk)) + if (for_ptracer) { parent = tsk->parent; - else { + } else { tsk = tsk->group_leader; parent = tsk->real_parent; } @@ -1592,7 +1738,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why) static inline int may_ptrace_stop(void) { - if (!likely(task_ptrace(current))) + if (!likely(current->ptrace)) return 0; /* * Are we in the middle of do_coredump? @@ -1631,10 +1777,12 @@ static int sigkill_pending(struct task_struct *tsk) * If we actually decide not to stop at all because the tracer * is gone, we keep current->exit_code unless clear_code. */ -static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info) +static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) __releases(¤t->sighand->siglock) __acquires(¤t->sighand->siglock) { + bool gstop_done = false; + if (arch_ptrace_stop_needed(exit_code, info)) { /* * The arch code has something special to do before a @@ -1655,21 +1803,52 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info) } /* - * If there is a group stop in progress, - * we must participate in the bookkeeping. + * We're committing to trapping. TRACED should be visible before + * TRAPPING is cleared; otherwise, the tracer might fail do_wait(). + * Also, transition to TRACED and updates to ->jobctl should be + * atomic with respect to siglock and should be done after the arch + * hook as siglock is released and regrabbed across it. */ - if (current->signal->group_stop_count > 0) - --current->signal->group_stop_count; + set_current_state(TASK_TRACED); current->last_siginfo = info; current->exit_code = exit_code; - /* Let the debugger run. */ - __set_current_state(TASK_TRACED); + /* + * If @why is CLD_STOPPED, we're trapping to participate in a group + * stop. Do the bookkeeping. Note that if SIGCONT was delievered + * across siglock relocks since INTERRUPT was scheduled, PENDING + * could be clear now. We act as if SIGCONT is received after + * TASK_TRACED is entered - ignore it. + */ + if (why == CLD_STOPPED && (current->jobctl & JOBCTL_STOP_PENDING)) + gstop_done = task_participate_group_stop(current); + + /* any trap clears pending STOP trap, STOP trap clears NOTIFY */ + task_clear_jobctl_pending(current, JOBCTL_TRAP_STOP); + if (info && info->si_code >> 8 == PTRACE_EVENT_STOP) + task_clear_jobctl_pending(current, JOBCTL_TRAP_NOTIFY); + + /* entering a trap, clear TRAPPING */ + task_clear_jobctl_trapping(current); + spin_unlock_irq(¤t->sighand->siglock); read_lock(&tasklist_lock); if (may_ptrace_stop()) { - do_notify_parent_cldstop(current, CLD_TRAPPED); + /* + * Notify parents of the stop. + * + * While ptraced, there are two parents - the ptracer and + * the real_parent of the group_leader. The ptracer should + * know about every stop while the real parent is only + * interested in the completion of group stop. The states + * for the two don't interact with each other. Notify + * separately unless they're gonna be duplicates. + */ + do_notify_parent_cldstop(current, true, why); + if (gstop_done && ptrace_reparented(current)) + do_notify_parent_cldstop(current, false, why); + /* * Don't want to allow preemption here, because * sys_ptrace() needs this task to be inactive. @@ -1684,7 +1863,16 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info) /* * By the time we got the lock, our tracer went away. * Don't drop the lock yet, another tracer may come. + * + * If @gstop_done, the ptracer went away between group stop + * completion and here. During detach, it would have set + * JOBCTL_STOP_PENDING on us and we'll re-enter + * TASK_STOPPED in do_signal_stop() on return, so notifying + * the real parent of the group stop completion is enough. */ + if (gstop_done) + do_notify_parent_cldstop(current, false, why); + __set_current_state(TASK_RUNNING); if (clear_code) current->exit_code = 0; @@ -1706,6 +1894,9 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info) spin_lock_irq(¤t->sighand->siglock); current->last_siginfo = NULL; + /* LISTENING can be set only during STOP traps, clear it */ + current->jobctl &= ~JOBCTL_LISTENING; + /* * Queued signals ignored us while we were stopped for tracing. * So check for any that we should take before resuming user mode. @@ -1714,107 +1905,204 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info) recalc_sigpending_tsk(current); } -void ptrace_notify(int exit_code) +static void ptrace_do_notify(int signr, int exit_code, int why) { siginfo_t info; - BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP); - memset(&info, 0, sizeof info); - info.si_signo = SIGTRAP; + info.si_signo = signr; info.si_code = exit_code; info.si_pid = task_pid_vnr(current); info.si_uid = current_uid(); /* Let the debugger run. */ + ptrace_stop(exit_code, why, 1, &info); +} + +void ptrace_notify(int exit_code) +{ + BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP); + spin_lock_irq(¤t->sighand->siglock); - ptrace_stop(exit_code, 1, &info); + ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED); spin_unlock_irq(¤t->sighand->siglock); } -/* - * This performs the stopping for SIGSTOP and other stop signals. - * We have to stop all threads in the thread group. - * Returns non-zero if we've actually stopped and released the siglock. - * Returns zero if we didn't stop and still hold the siglock. +/** + * do_signal_stop - handle group stop for SIGSTOP and other stop signals + * @signr: signr causing group stop if initiating + * + * If %JOBCTL_STOP_PENDING is not set yet, initiate group stop with @signr + * and participate in it. If already set, participate in the existing + * group stop. If participated in a group stop (and thus slept), %true is + * returned with siglock released. + * + * If ptraced, this function doesn't handle stop itself. Instead, + * %JOBCTL_TRAP_STOP is scheduled and %false is returned with siglock + * untouched. The caller must ensure that INTERRUPT trap handling takes + * places afterwards. + * + * CONTEXT: + * Must be called with @current->sighand->siglock held, which is released + * on %true return. + * + * RETURNS: + * %false if group stop is already cancelled or ptrace trap is scheduled. + * %true if participated in group stop. */ -static int do_signal_stop(int signr) +static bool do_signal_stop(int signr) + __releases(¤t->sighand->siglock) { struct signal_struct *sig = current->signal; - int notify; - if (!sig->group_stop_count) { + if (!(current->jobctl & JOBCTL_STOP_PENDING)) { + unsigned int gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME; struct task_struct *t; - if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) || + /* signr will be recorded in task->jobctl for retries */ + WARN_ON_ONCE(signr & ~JOBCTL_STOP_SIGMASK); + + if (!likely(current->jobctl & JOBCTL_STOP_DEQUEUED) || unlikely(signal_group_exit(sig))) - return 0; + return false; /* - * There is no group stop already in progress. - * We must initiate one now. + * There is no group stop already in progress. We must + * initiate one now. + * + * While ptraced, a task may be resumed while group stop is + * still in effect and then receive a stop signal and + * initiate another group stop. This deviates from the + * usual behavior as two consecutive stop signals can't + * cause two group stops when !ptraced. That is why we + * also check !task_is_stopped(t) below. + * + * The condition can be distinguished by testing whether + * SIGNAL_STOP_STOPPED is already set. Don't generate + * group_exit_code in such case. + * + * This is not necessary for SIGNAL_STOP_CONTINUED because + * an intervening stop signal is required to cause two + * continued events regardless of ptrace. */ - sig->group_exit_code = signr; + if (!(sig->flags & SIGNAL_STOP_STOPPED)) + sig->group_exit_code = signr; + else + WARN_ON_ONCE(!current->ptrace); + + sig->group_stop_count = 0; - sig->group_stop_count = 1; - for (t = next_thread(current); t != current; t = next_thread(t)) + if (task_set_jobctl_pending(current, signr | gstop)) + sig->group_stop_count++; + + for (t = next_thread(current); t != current; + t = next_thread(t)) { /* * Setting state to TASK_STOPPED for a group * stop is always done with the siglock held, * so this check has no races. */ - if (!(t->flags & PF_EXITING) && - !task_is_stopped_or_traced(t)) { + if (!task_is_stopped(t) && + task_set_jobctl_pending(t, signr | gstop)) { sig->group_stop_count++; - signal_wake_up(t, 0); + if (likely(!(t->ptrace & PT_SEIZED))) + signal_wake_up(t, 0); + else + ptrace_trap_notify(t); } + } } - /* - * If there are no other threads in the group, or if there is - * a group stop in progress and we are the last to stop, report - * to the parent. When ptraced, every thread reports itself. - */ - notify = sig->group_stop_count == 1 ? CLD_STOPPED : 0; - notify = tracehook_notify_jctl(notify, CLD_STOPPED); - /* - * tracehook_notify_jctl() can drop and reacquire siglock, so - * we keep ->group_stop_count != 0 before the call. If SIGCONT - * or SIGKILL comes in between ->group_stop_count == 0. - */ - if (sig->group_stop_count) { - if (!--sig->group_stop_count) - sig->flags = SIGNAL_STOP_STOPPED; - current->exit_code = sig->group_exit_code; + + if (likely(!current->ptrace)) { + int notify = 0; + + /* + * If there are no other threads in the group, or if there + * is a group stop in progress and we are the last to stop, + * report to the parent. + */ + if (task_participate_group_stop(current)) + notify = CLD_STOPPED; + __set_current_state(TASK_STOPPED); - } - spin_unlock_irq(¤t->sighand->siglock); + spin_unlock_irq(¤t->sighand->siglock); - if (notify) { - read_lock(&tasklist_lock); - do_notify_parent_cldstop(current, notify); - read_unlock(&tasklist_lock); - } + /* + * Notify the parent of the group stop completion. Because + * we're not holding either the siglock or tasklist_lock + * here, ptracer may attach inbetween; however, this is for + * group stop and should always be delivered to the real + * parent of the group leader. The new ptracer will get + * its notification when this task transitions into + * TASK_TRACED. + */ + if (notify) { + read_lock(&tasklist_lock); + do_notify_parent_cldstop(current, false, notify); + read_unlock(&tasklist_lock); + } - /* Now we don't run again until woken by SIGCONT or SIGKILL */ - do { + /* Now we don't run again until woken by SIGCONT or SIGKILL */ schedule(); - } while (try_to_freeze()); - - tracehook_finish_jctl(); - current->exit_code = 0; + return true; + } else { + /* + * While ptraced, group stop is handled by STOP trap. + * Schedule it and let the caller deal with it. + */ + task_set_jobctl_pending(current, JOBCTL_TRAP_STOP); + return false; + } +} - return 1; +/** + * do_jobctl_trap - take care of ptrace jobctl traps + * + * When PT_SEIZED, it's used for both group stop and explicit + * SEIZE/INTERRUPT traps. Both generate PTRACE_EVENT_STOP trap with + * accompanying siginfo. If stopped, lower eight bits of exit_code contain + * the stop signal; otherwise, %SIGTRAP. + * + * When !PT_SEIZED, it's used only for group stop trap with stop signal + * number as exit_code and no siginfo. + * + * CONTEXT: + * Must be called with @current->sighand->siglock held, which may be + * released and re-acquired before returning with intervening sleep. + */ +static void do_jobctl_trap(void) +{ + struct signal_struct *signal = current->signal; + int signr = current->jobctl & JOBCTL_STOP_SIGMASK; + + if (current->ptrace & PT_SEIZED) { + if (!signal->group_stop_count && + !(signal->flags & SIGNAL_STOP_STOPPED)) + signr = SIGTRAP; + WARN_ON_ONCE(!signr); + ptrace_do_notify(signr, signr | (PTRACE_EVENT_STOP << 8), + CLD_STOPPED); + } else { + WARN_ON_ONCE(!signr); + ptrace_stop(signr, CLD_STOPPED, 0, NULL); + current->exit_code = 0; + } } static int ptrace_signal(int signr, siginfo_t *info, struct pt_regs *regs, void *cookie) { - if (!task_ptrace(current)) - return signr; - ptrace_signal_deliver(regs, cookie); - - /* Let the debugger run. */ - ptrace_stop(signr, 0, info); + /* + * We do not check sig_kernel_stop(signr) but set this marker + * unconditionally because we do not know whether debugger will + * change signr. This flag has no meaning unless we are going + * to stop after return from ptrace_stop(). In this case it will + * be checked in do_signal_stop(), we should only stop if it was + * not cleared by SIGCONT while we were sleeping. See also the + * comment in dequeue_signal(). + */ + current->jobctl |= JOBCTL_STOP_DEQUEUED; + ptrace_stop(signr, CLD_TRAPPED, 0, info); /* We're back. Did the debugger cancel the sig? */ signr = current->exit_code; @@ -1869,54 +2157,63 @@ relock: * the CLD_ si_code into SIGNAL_CLD_MASK bits. */ if (unlikely(signal->flags & SIGNAL_CLD_MASK)) { - int why = (signal->flags & SIGNAL_STOP_CONTINUED) - ? CLD_CONTINUED : CLD_STOPPED; + int why; + + if (signal->flags & SIGNAL_CLD_CONTINUED) + why = CLD_CONTINUED; + else + why = CLD_STOPPED; + signal->flags &= ~SIGNAL_CLD_MASK; - why = tracehook_notify_jctl(why, CLD_CONTINUED); spin_unlock_irq(&sighand->siglock); - if (why) { - read_lock(&tasklist_lock); - do_notify_parent_cldstop(current->group_leader, why); - read_unlock(&tasklist_lock); - } + /* + * Notify the parent that we're continuing. This event is + * always per-process and doesn't make whole lot of sense + * for ptracers, who shouldn't consume the state via + * wait(2) either, but, for backward compatibility, notify + * the ptracer of the group leader too unless it's gonna be + * a duplicate. + */ + read_lock(&tasklist_lock); + do_notify_parent_cldstop(current, false, why); + + if (ptrace_reparented(current->group_leader)) + do_notify_parent_cldstop(current->group_leader, + true, why); + read_unlock(&tasklist_lock); + goto relock; } for (;;) { struct k_sigaction *ka; - /* - * Tracing can induce an artificial signal and choose sigaction. - * The return value in @signr determines the default action, - * but @info->si_signo is the signal number we will report. - */ - signr = tracehook_get_signal(current, regs, info, return_ka); - if (unlikely(signr < 0)) + + if (unlikely(current->jobctl & JOBCTL_STOP_PENDING) && + do_signal_stop(0)) goto relock; - if (unlikely(signr != 0)) - ka = return_ka; - else { - if (unlikely(signal->group_stop_count > 0) && - do_signal_stop(0)) - goto relock; - signr = dequeue_signal(current, ¤t->blocked, - info); + if (unlikely(current->jobctl & JOBCTL_TRAP_MASK)) { + do_jobctl_trap(); + spin_unlock_irq(&sighand->siglock); + goto relock; + } - if (!signr) - break; /* will return 0 */ + signr = dequeue_signal(current, ¤t->blocked, info); - if (signr != SIGKILL) { - signr = ptrace_signal(signr, info, - regs, cookie); - if (!signr) - continue; - } + if (!signr) + break; /* will return 0 */ - ka = &sighand->action[signr-1]; + if (unlikely(current->ptrace) && signr != SIGKILL) { + signr = ptrace_signal(signr, info, + regs, cookie); + if (!signr) + continue; } + ka = &sighand->action[signr-1]; + /* Trace actually delivered signals. */ trace_signal_deliver(signr, info, ka); @@ -2017,10 +2314,42 @@ relock: return signr; } +/* + * It could be that complete_signal() picked us to notify about the + * group-wide signal. Other threads should be notified now to take + * the shared signals in @which since we will not. + */ +static void retarget_shared_pending(struct task_struct *tsk, sigset_t *which) +{ + sigset_t retarget; + struct task_struct *t; + + sigandsets(&retarget, &tsk->signal->shared_pending.signal, which); + if (sigisemptyset(&retarget)) + return; + + t = tsk; + while_each_thread(tsk, t) { + if (t->flags & PF_EXITING) + continue; + + if (!has_pending_signals(&retarget, &t->blocked)) + continue; + /* Remove the signals this thread can handle. */ + sigandsets(&retarget, &retarget, &t->blocked); + + if (!signal_pending(t)) + signal_wake_up(t, 0); + + if (sigisemptyset(&retarget)) + break; + } +} + void exit_signals(struct task_struct *tsk) { int group_stop = 0; - struct task_struct *t; + sigset_t unblocked; if (thread_group_empty(tsk) || signal_group_exit(tsk->signal)) { tsk->flags |= PF_EXITING; @@ -2036,26 +2365,23 @@ void exit_signals(struct task_struct *tsk) if (!signal_pending(tsk)) goto out; - /* - * It could be that __group_complete_signal() choose us to - * notify about group-wide signal. Another thread should be - * woken now to take the signal since we will not. - */ - for (t = tsk; (t = next_thread(t)) != tsk; ) - if (!signal_pending(t) && !(t->flags & PF_EXITING)) - recalc_sigpending_and_wake(t); + unblocked = tsk->blocked; + signotset(&unblocked); + retarget_shared_pending(tsk, &unblocked); - if (unlikely(tsk->signal->group_stop_count) && - !--tsk->signal->group_stop_count) { - tsk->signal->flags = SIGNAL_STOP_STOPPED; - group_stop = tracehook_notify_jctl(CLD_STOPPED, CLD_STOPPED); - } + if (unlikely(tsk->jobctl & JOBCTL_STOP_PENDING) && + task_participate_group_stop(tsk)) + group_stop = CLD_STOPPED; out: spin_unlock_irq(&tsk->sighand->siglock); + /* + * If group stop has completed, deliver the notification. This + * should always go to the real parent of the group leader. + */ if (unlikely(group_stop)) { read_lock(&tasklist_lock); - do_notify_parent_cldstop(tsk, group_stop); + do_notify_parent_cldstop(tsk, false, group_stop); read_unlock(&tasklist_lock); } } @@ -2089,11 +2415,33 @@ long do_no_restart_syscall(struct restart_block *param) return -EINTR; } -/* - * We don't need to get the kernel lock - this is all local to this - * particular thread.. (and that's good, because this is _heavily_ - * used by various programs) +static void __set_task_blocked(struct task_struct *tsk, const sigset_t *newset) +{ + if (signal_pending(tsk) && !thread_group_empty(tsk)) { + sigset_t newblocked; + /* A set of now blocked but previously unblocked signals. */ + sigandnsets(&newblocked, newset, ¤t->blocked); + retarget_shared_pending(tsk, &newblocked); + } + tsk->blocked = *newset; + recalc_sigpending(); +} + +/** + * set_current_blocked - change current->blocked mask + * @newset: new mask + * + * It is wrong to change ->blocked directly, this helper should be used + * to ensure the process can't miss a shared signal we are going to block. */ +void set_current_blocked(const sigset_t *newset) +{ + struct task_struct *tsk = current; + + spin_lock_irq(&tsk->sighand->siglock); + __set_task_blocked(tsk, newset); + spin_unlock_irq(&tsk->sighand->siglock); +} /* * This is also useful for kernel threads that want to temporarily @@ -2105,73 +2453,66 @@ long do_no_restart_syscall(struct restart_block *param) */ int sigprocmask(int how, sigset_t *set, sigset_t *oldset) { - int error; + struct task_struct *tsk = current; + sigset_t newset; - spin_lock_irq(¤t->sighand->siglock); + /* Lockless, only current can change ->blocked, never from irq */ if (oldset) - *oldset = current->blocked; + *oldset = tsk->blocked; - error = 0; switch (how) { case SIG_BLOCK: - sigorsets(¤t->blocked, ¤t->blocked, set); + sigorsets(&newset, &tsk->blocked, set); break; case SIG_UNBLOCK: - signandsets(¤t->blocked, ¤t->blocked, set); + sigandnsets(&newset, &tsk->blocked, set); break; case SIG_SETMASK: - current->blocked = *set; + newset = *set; break; default: - error = -EINVAL; + return -EINVAL; } - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - return error; + set_current_blocked(&newset); + return 0; } /** * sys_rt_sigprocmask - change the list of currently blocked signals * @how: whether to add, remove, or set signals - * @set: stores pending signals + * @nset: stores pending signals * @oset: previous value of signal mask if non-null * @sigsetsize: size of sigset_t type */ -SYSCALL_DEFINE4(rt_sigprocmask, int, how, sigset_t __user *, set, +SYSCALL_DEFINE4(rt_sigprocmask, int, how, sigset_t __user *, nset, sigset_t __user *, oset, size_t, sigsetsize) { - int error = -EINVAL; sigset_t old_set, new_set; + int error; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) - goto out; + return -EINVAL; - if (set) { - error = -EFAULT; - if (copy_from_user(&new_set, set, sizeof(*set))) - goto out; + old_set = current->blocked; + + if (nset) { + if (copy_from_user(&new_set, nset, sizeof(sigset_t))) + return -EFAULT; sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); - error = sigprocmask(how, &new_set, &old_set); + error = sigprocmask(how, &new_set, NULL); if (error) - goto out; - if (oset) - goto set_old; - } else if (oset) { - spin_lock_irq(¤t->sighand->siglock); - old_set = current->blocked; - spin_unlock_irq(¤t->sighand->siglock); + return error; + } - set_old: - error = -EFAULT; - if (copy_to_user(oset, &old_set, sizeof(*oset))) - goto out; + if (oset) { + if (copy_to_user(oset, &old_set, sizeof(sigset_t))) + return -EFAULT; } - error = 0; -out: - return error; + + return 0; } long do_sigpending(void __user *set, unsigned long sigsetsize) @@ -2284,6 +2625,66 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from) #endif /** + * do_sigtimedwait - wait for queued signals specified in @which + * @which: queued signals to wait for + * @info: if non-null, the signal's siginfo is returned here + * @ts: upper bound on process time suspension + */ +int do_sigtimedwait(const sigset_t *which, siginfo_t *info, + const struct timespec *ts) +{ + struct task_struct *tsk = current; + long timeout = MAX_SCHEDULE_TIMEOUT; + sigset_t mask = *which; + int sig; + + if (ts) { + if (!timespec_valid(ts)) + return -EINVAL; + timeout = timespec_to_jiffies(ts); + /* + * We can be close to the next tick, add another one + * to ensure we will wait at least the time asked for. + */ + if (ts->tv_sec || ts->tv_nsec) + timeout++; + } + + /* + * Invert the set of allowed signals to get those we want to block. + */ + sigdelsetmask(&mask, sigmask(SIGKILL) | sigmask(SIGSTOP)); + signotset(&mask); + + spin_lock_irq(&tsk->sighand->siglock); + sig = dequeue_signal(tsk, &mask, info); + if (!sig && timeout) { + /* + * None ready, temporarily unblock those we're interested + * while we are sleeping in so that we'll be awakened when + * they arrive. Unblocking is always fine, we can avoid + * set_current_blocked(). + */ + tsk->real_blocked = tsk->blocked; + sigandsets(&tsk->blocked, &tsk->blocked, &mask); + recalc_sigpending(); + spin_unlock_irq(&tsk->sighand->siglock); + + timeout = schedule_timeout_interruptible(timeout); + + spin_lock_irq(&tsk->sighand->siglock); + __set_task_blocked(tsk, &tsk->real_blocked); + siginitset(&tsk->real_blocked, 0); + sig = dequeue_signal(tsk, &mask, info); + } + spin_unlock_irq(&tsk->sighand->siglock); + + if (sig) + return sig; + return timeout ? -EINTR : -EAGAIN; +} + +/** * sys_rt_sigtimedwait - synchronously wait for queued signals specified * in @uthese * @uthese: queued signals to wait for @@ -2295,11 +2696,10 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, siginfo_t __user *, uinfo, const struct timespec __user *, uts, size_t, sigsetsize) { - int ret, sig; sigset_t these; struct timespec ts; siginfo_t info; - long timeout = 0; + int ret; /* XXX: Don't preclude handling different sized sigset_t's. */ if (sigsetsize != sizeof(sigset_t)) @@ -2308,61 +2708,16 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, if (copy_from_user(&these, uthese, sizeof(these))) return -EFAULT; - /* - * Invert the set of allowed signals to get those we - * want to block. - */ - sigdelsetmask(&these, sigmask(SIGKILL)|sigmask(SIGSTOP)); - signotset(&these); - if (uts) { if (copy_from_user(&ts, uts, sizeof(ts))) return -EFAULT; - if (ts.tv_nsec >= 1000000000L || ts.tv_nsec < 0 - || ts.tv_sec < 0) - return -EINVAL; } - spin_lock_irq(¤t->sighand->siglock); - sig = dequeue_signal(current, &these, &info); - if (!sig) { - timeout = MAX_SCHEDULE_TIMEOUT; - if (uts) - timeout = (timespec_to_jiffies(&ts) - + (ts.tv_sec || ts.tv_nsec)); - - if (timeout) { - /* - * None ready -- temporarily unblock those we're - * interested while we are sleeping in so that we'll - * be awakened when they arrive. - */ - current->real_blocked = current->blocked; - sigandsets(¤t->blocked, ¤t->blocked, &these); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - - timeout = schedule_timeout_interruptible(timeout); - - spin_lock_irq(¤t->sighand->siglock); - sig = dequeue_signal(current, &these, &info); - current->blocked = current->real_blocked; - siginitset(¤t->real_blocked, 0); - recalc_sigpending(); - } - } - spin_unlock_irq(¤t->sighand->siglock); + ret = do_sigtimedwait(&these, &info, uts ? &ts : NULL); - if (sig) { - ret = sig; - if (uinfo) { - if (copy_siginfo_to_user(uinfo, &info)) - ret = -EFAULT; - } - } else { - ret = -EAGAIN; - if (timeout) - ret = -EINTR; + if (ret > 0 && uinfo) { + if (copy_siginfo_to_user(uinfo, &info)) + ret = -EFAULT; } return ret; @@ -2650,60 +3005,51 @@ SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set) /** * sys_sigprocmask - examine and change blocked signals * @how: whether to add, remove, or set signals - * @set: signals to add or remove (if non-null) + * @nset: signals to add or remove (if non-null) * @oset: previous value of signal mask if non-null * * Some platforms have their own version with special arguments; * others support only sys_rt_sigprocmask. */ -SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, set, +SYSCALL_DEFINE3(sigprocmask, int, how, old_sigset_t __user *, nset, old_sigset_t __user *, oset) { - int error; old_sigset_t old_set, new_set; + sigset_t new_blocked; - if (set) { - error = -EFAULT; - if (copy_from_user(&new_set, set, sizeof(*set))) - goto out; + old_set = current->blocked.sig[0]; + + if (nset) { + if (copy_from_user(&new_set, nset, sizeof(*nset))) + return -EFAULT; new_set &= ~(sigmask(SIGKILL) | sigmask(SIGSTOP)); - spin_lock_irq(¤t->sighand->siglock); - old_set = current->blocked.sig[0]; + new_blocked = current->blocked; - error = 0; switch (how) { - default: - error = -EINVAL; - break; case SIG_BLOCK: - sigaddsetmask(¤t->blocked, new_set); + sigaddsetmask(&new_blocked, new_set); break; case SIG_UNBLOCK: - sigdelsetmask(¤t->blocked, new_set); + sigdelsetmask(&new_blocked, new_set); break; case SIG_SETMASK: - current->blocked.sig[0] = new_set; + new_blocked.sig[0] = new_set; break; + default: + return -EINVAL; } - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - if (error) - goto out; - if (oset) - goto set_old; - } else if (oset) { - old_set = current->blocked.sig[0]; - set_old: - error = -EFAULT; + set_current_blocked(&new_blocked); + } + + if (oset) { if (copy_to_user(oset, &old_set, sizeof(*oset))) - goto out; + return -EFAULT; } - error = 0; -out: - return error; + + return 0; } #endif /* __ARCH_WANT_SYS_SIGPROCMASK */ @@ -2756,15 +3102,11 @@ SYSCALL_DEFINE0(sgetmask) SYSCALL_DEFINE1(ssetmask, int, newmask) { - int old; - - spin_lock_irq(¤t->sighand->siglock); - old = current->blocked.sig[0]; + int old = current->blocked.sig[0]; + sigset_t newset; - siginitset(¤t->blocked, newmask & ~(sigmask(SIGKILL)| - sigmask(SIGSTOP))); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + siginitset(&newset, newmask & ~(sigmask(SIGKILL) | sigmask(SIGSTOP))); + set_current_blocked(&newset); return old; } @@ -2793,8 +3135,10 @@ SYSCALL_DEFINE2(signal, int, sig, __sighandler_t, handler) SYSCALL_DEFINE0(pause) { - current->state = TASK_INTERRUPTIBLE; - schedule(); + while (!signal_pending(current)) { + current->state = TASK_INTERRUPTIBLE; + schedule(); + } return -ERESTARTNOHAND; } @@ -2819,11 +3163,8 @@ SYSCALL_DEFINE2(rt_sigsuspend, sigset_t __user *, unewset, size_t, sigsetsize) return -EFAULT; sigdelsetmask(&newset, sigmask(SIGKILL)|sigmask(SIGSTOP)); - spin_lock_irq(¤t->sighand->siglock); current->saved_sigmask = current->blocked; - current->blocked = newset; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&newset); current->state = TASK_INTERRUPTIBLE; schedule(); diff --git a/kernel/smp.c b/kernel/smp.c index 73a19519355..fb67dfa8394 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -74,7 +74,7 @@ static struct notifier_block __cpuinitdata hotplug_cfd_notifier = { .notifier_call = hotplug_cfd, }; -static int __cpuinit init_call_single_data(void) +void __init call_function_init(void) { void *cpu = (void *)(long)smp_processor_id(); int i; @@ -88,10 +88,7 @@ static int __cpuinit init_call_single_data(void) hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu); register_cpu_notifier(&hotplug_cfd_notifier); - - return 0; } -early_initcall(init_call_single_data); /* * csd_lock/csd_unlock used to serialize access to per-cpu csd resources diff --git a/kernel/softirq.c b/kernel/softirq.c index 174f976c287..fca82c32042 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -58,7 +58,7 @@ DEFINE_PER_CPU(struct task_struct *, ksoftirqd); char *softirq_to_name[NR_SOFTIRQS] = { "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL", - "TASKLET", "SCHED", "HRTIMER", "RCU" + "TASKLET", "SCHED", "HRTIMER", "RCU" }; /* @@ -315,16 +315,24 @@ static inline void invoke_softirq(void) { if (!force_irqthreads) __do_softirq(); - else + else { + __local_bh_disable((unsigned long)__builtin_return_address(0), + SOFTIRQ_OFFSET); wakeup_softirqd(); + __local_bh_enable(SOFTIRQ_OFFSET); + } } #else static inline void invoke_softirq(void) { if (!force_irqthreads) do_softirq(); - else + else { + __local_bh_disable((unsigned long)__builtin_return_address(0), + SOFTIRQ_OFFSET); wakeup_softirqd(); + __local_bh_enable(SOFTIRQ_OFFSET); + } } #endif diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index eb212f8f8bc..d20c6983aad 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -26,12 +26,18 @@ void print_stack_trace(struct stack_trace *trace, int spaces) EXPORT_SYMBOL_GPL(print_stack_trace); /* - * Architectures that do not implement save_stack_trace_tsk get this - * weak alias and a once-per-bootup warning (whenever this facility - * is utilized - for example by procfs): + * Architectures that do not implement save_stack_trace_tsk or + * save_stack_trace_regs get this weak alias and a once-per-bootup warning + * (whenever this facility is utilized - for example by procfs): */ __weak void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { WARN_ONCE(1, KERN_INFO "save_stack_trace_tsk() not implemented yet.\n"); } + +__weak void +save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) +{ + WARN_ONCE(1, KERN_INFO "save_stack_trace_regs() not implemented yet.\n"); +} diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index e3516b29076..ba5070ce576 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -19,7 +19,7 @@ #include <linux/interrupt.h> #include <linux/kallsyms.h> -#include <asm/atomic.h> +#include <linux/atomic.h> /* * Structure to determine completion condition and record errors. May @@ -136,10 +136,11 @@ void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, static DEFINE_MUTEX(stop_cpus_mutex); static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work); -int __stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) +static void queue_stop_cpus_work(const struct cpumask *cpumask, + cpu_stop_fn_t fn, void *arg, + struct cpu_stop_done *done) { struct cpu_stop_work *work; - struct cpu_stop_done done; unsigned int cpu; /* initialize works and done */ @@ -147,9 +148,8 @@ int __stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) work = &per_cpu(stop_cpus_work, cpu); work->fn = fn; work->arg = arg; - work->done = &done; + work->done = done; } - cpu_stop_init_done(&done, cpumask_weight(cpumask)); /* * Disable preemption while queueing to avoid getting @@ -161,7 +161,15 @@ int __stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), &per_cpu(stop_cpus_work, cpu)); preempt_enable(); +} +static int __stop_cpus(const struct cpumask *cpumask, + cpu_stop_fn_t fn, void *arg) +{ + struct cpu_stop_done done; + + cpu_stop_init_done(&done, cpumask_weight(cpumask)); + queue_stop_cpus_work(cpumask, fn, arg, &done); wait_for_completion(&done.completion); return done.executed ? done.ret : -ENOENT; } @@ -431,8 +439,15 @@ static int stop_machine_cpu_stop(void *data) struct stop_machine_data *smdata = data; enum stopmachine_state curstate = STOPMACHINE_NONE; int cpu = smp_processor_id(), err = 0; + unsigned long flags; bool is_active; + /* + * When called from stop_machine_from_inactive_cpu(), irq might + * already be disabled. Save the state and restore it on exit. + */ + local_save_flags(flags); + if (!smdata->active_cpus) is_active = cpu == cpumask_first(cpu_online_mask); else @@ -460,7 +475,7 @@ static int stop_machine_cpu_stop(void *data) } } while (curstate != STOPMACHINE_EXIT); - local_irq_enable(); + local_irq_restore(flags); return err; } @@ -487,4 +502,57 @@ int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus) } EXPORT_SYMBOL_GPL(stop_machine); +/** + * stop_machine_from_inactive_cpu - stop_machine() from inactive CPU + * @fn: the function to run + * @data: the data ptr for the @fn() + * @cpus: the cpus to run the @fn() on (NULL = any online cpu) + * + * This is identical to stop_machine() but can be called from a CPU which + * is not active. The local CPU is in the process of hotplug (so no other + * CPU hotplug can start) and not marked active and doesn't have enough + * context to sleep. + * + * This function provides stop_machine() functionality for such state by + * using busy-wait for synchronization and executing @fn directly for local + * CPU. + * + * CONTEXT: + * Local CPU is inactive. Temporarily stops all active CPUs. + * + * RETURNS: + * 0 if all executions of @fn returned 0, any non zero return value if any + * returned non zero. + */ +int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data, + const struct cpumask *cpus) +{ + struct stop_machine_data smdata = { .fn = fn, .data = data, + .active_cpus = cpus }; + struct cpu_stop_done done; + int ret; + + /* Local CPU must be inactive and CPU hotplug in progress. */ + BUG_ON(cpu_active(raw_smp_processor_id())); + smdata.num_threads = num_active_cpus() + 1; /* +1 for local */ + + /* No proper task established and can't sleep - busy wait for lock. */ + while (!mutex_trylock(&stop_cpus_mutex)) + cpu_relax(); + + /* Schedule work on other CPUs and execute directly for local CPU */ + set_state(&smdata, STOPMACHINE_PREPARE); + cpu_stop_init_done(&done, num_active_cpus()); + queue_stop_cpus_work(cpu_active_mask, stop_machine_cpu_stop, &smdata, + &done); + ret = stop_machine_cpu_stop(&smdata); + + /* Busy wait for completion. */ + while (!completion_done(&done.completion)) + cpu_relax(); + + mutex_unlock(&stop_cpus_mutex); + return ret ?: done.ret; +} + #endif /* CONFIG_STOP_MACHINE */ diff --git a/kernel/sys.c b/kernel/sys.c index af468edf096..a101ba36c44 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -8,7 +8,6 @@ #include <linux/mm.h> #include <linux/utsname.h> #include <linux/mman.h> -#include <linux/notifier.h> #include <linux/reboot.h> #include <linux/prctl.h> #include <linux/highuid.h> @@ -314,12 +313,43 @@ void kernel_restart_prepare(char *cmd) { blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd); system_state = SYSTEM_RESTART; + usermodehelper_disable(); device_shutdown(); - sysdev_shutdown(); syscore_shutdown(); } /** + * register_reboot_notifier - Register function to be called at reboot time + * @nb: Info about notifier function to be called + * + * Registers a function with the list of functions + * to be called at reboot time. + * + * Currently always returns zero, as blocking_notifier_chain_register() + * always returns zero. + */ +int register_reboot_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&reboot_notifier_list, nb); +} +EXPORT_SYMBOL(register_reboot_notifier); + +/** + * unregister_reboot_notifier - Unregister previously registered reboot notifier + * @nb: Hook to be unregistered + * + * Unregisters a previously registered reboot + * notifier function. + * + * Returns zero on success, or %-ENOENT on failure. + */ +int unregister_reboot_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&reboot_notifier_list, nb); +} +EXPORT_SYMBOL(unregister_reboot_notifier); + +/** * kernel_restart - reboot the system * @cmd: pointer to buffer containing command to execute for restart * or %NULL @@ -344,6 +374,7 @@ static void kernel_shutdown_prepare(enum system_states state) blocking_notifier_call_chain(&reboot_notifier_list, (state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL); system_state = state; + usermodehelper_disable(); device_shutdown(); } /** @@ -354,7 +385,6 @@ static void kernel_shutdown_prepare(enum system_states state) void kernel_halt(void) { kernel_shutdown_prepare(SYSTEM_HALT); - sysdev_shutdown(); syscore_shutdown(); printk(KERN_EMERG "System halted.\n"); kmsg_dump(KMSG_DUMP_HALT); @@ -374,7 +404,6 @@ void kernel_power_off(void) if (pm_power_off_prepare) pm_power_off_prepare(); disable_nonboot_cpus(); - sysdev_shutdown(); syscore_shutdown(); printk(KERN_EMERG "Power down.\n"); kmsg_dump(KMSG_DUMP_POWEROFF); diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 25cc41cd8f3..62cbc8877fe 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -46,7 +46,9 @@ cond_syscall(sys_getsockopt); cond_syscall(compat_sys_getsockopt); cond_syscall(sys_shutdown); cond_syscall(sys_sendmsg); +cond_syscall(sys_sendmmsg); cond_syscall(compat_sys_sendmsg); +cond_syscall(compat_sys_sendmmsg); cond_syscall(sys_recvmsg); cond_syscall(sys_recvmmsg); cond_syscall(compat_sys_recvmsg); @@ -69,15 +71,22 @@ cond_syscall(compat_sys_epoll_pwait); cond_syscall(sys_semget); cond_syscall(sys_semop); cond_syscall(sys_semtimedop); +cond_syscall(compat_sys_semtimedop); cond_syscall(sys_semctl); +cond_syscall(compat_sys_semctl); cond_syscall(sys_msgget); cond_syscall(sys_msgsnd); +cond_syscall(compat_sys_msgsnd); cond_syscall(sys_msgrcv); +cond_syscall(compat_sys_msgrcv); cond_syscall(sys_msgctl); +cond_syscall(compat_sys_msgctl); cond_syscall(sys_shmget); cond_syscall(sys_shmat); +cond_syscall(compat_sys_shmat); cond_syscall(sys_shmdt); cond_syscall(sys_shmctl); +cond_syscall(compat_sys_shmctl); cond_syscall(sys_mq_open); cond_syscall(sys_mq_unlink); cond_syscall(sys_mq_timedsend); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c0bb32414b1..11d65b531e5 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -56,6 +56,7 @@ #include <linux/kprobes.h> #include <linux/pipe_fs_i.h> #include <linux/oom.h> +#include <linux/kmod.h> #include <asm/uaccess.h> #include <asm/processor.h> @@ -616,6 +617,11 @@ static struct ctl_table kern_table[] = { .child = random_table, }, { + .procname = "usermodehelper", + .mode = 0555, + .child = usermodehelper_table, + }, + { .procname = "overflowuid", .data = &overflowuid, .maxlen = sizeof(int), @@ -730,14 +736,16 @@ static struct ctl_table kern_table[] = { .data = &watchdog_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = proc_dowatchdog_enabled, + .proc_handler = proc_dowatchdog, + .extra1 = &zero, + .extra2 = &one, }, { .procname = "watchdog_thresh", - .data = &softlockup_thresh, + .data = &watchdog_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dowatchdog_thresh, + .proc_handler = proc_dowatchdog, .extra1 = &neg_one, .extra2 = &sixty, }, @@ -755,7 +763,9 @@ static struct ctl_table kern_table[] = { .data = &watchdog_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = proc_dowatchdog_enabled, + .proc_handler = proc_dowatchdog, + .extra1 = &zero, + .extra2 = &one, }, #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) @@ -928,6 +938,12 @@ static struct ctl_table kern_table[] = { }, #endif #ifdef CONFIG_PERF_EVENTS + /* + * User-space scripts rely on the existence of this file + * as a feature check for perf_events being enabled. + * + * So it's an ABI, do not remove! + */ { .procname = "perf_event_paranoid", .data = &sysctl_perf_event_paranoid, @@ -1496,7 +1512,7 @@ static struct ctl_table fs_table[] = { static struct ctl_table debug_table[] = { #if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_SPARC) || \ - defined(CONFIG_S390) + defined(CONFIG_S390) || defined(CONFIG_TILE) { .procname = "exception-trace", .data = &show_unhandled_signals, @@ -1574,16 +1590,11 @@ void sysctl_head_get(struct ctl_table_header *head) spin_unlock(&sysctl_lock); } -static void free_head(struct rcu_head *rcu) -{ - kfree(container_of(rcu, struct ctl_table_header, rcu)); -} - void sysctl_head_put(struct ctl_table_header *head) { spin_lock(&sysctl_lock); if (!--head->count) - call_rcu(&head->rcu, free_head); + kfree_rcu(head, rcu); spin_unlock(&sysctl_lock); } @@ -1955,10 +1966,10 @@ void unregister_sysctl_table(struct ctl_table_header * header) start_unregistering(header); if (!--header->parent->count) { WARN_ON(1); - call_rcu(&header->parent->rcu, free_head); + kfree_rcu(header->parent, rcu); } if (!--header->count) - call_rcu(&header->rcu, free_head); + kfree_rcu(header, rcu); spin_unlock(&sysctl_lock); } diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 9ffea360a77..d1db2880d1c 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -28,7 +28,7 @@ #include <linux/fs.h> #include <linux/file.h> #include <net/genetlink.h> -#include <asm/atomic.h> +#include <linux/atomic.h> /* * Maximum length of a cpumask that can be specified in @@ -285,16 +285,18 @@ ret: static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) { struct listener_list *listeners; - struct listener *s, *tmp; + struct listener *s, *tmp, *s2; unsigned int cpu; if (!cpumask_subset(mask, cpu_possible_mask)) return -EINVAL; + s = NULL; if (isadd == REGISTER) { for_each_cpu(cpu, mask) { - s = kmalloc_node(sizeof(struct listener), GFP_KERNEL, - cpu_to_node(cpu)); + if (!s) + s = kmalloc_node(sizeof(struct listener), + GFP_KERNEL, cpu_to_node(cpu)); if (!s) goto cleanup; s->pid = pid; @@ -303,9 +305,16 @@ static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) listeners = &per_cpu(listener_array, cpu); down_write(&listeners->sem); + list_for_each_entry_safe(s2, tmp, &listeners->list, list) { + if (s2->pid == pid) + goto next_cpu; + } list_add(&s->list, &listeners->list); + s = NULL; +next_cpu: up_write(&listeners->sem); } + kfree(s); return 0; } diff --git a/kernel/time/Makefile b/kernel/time/Makefile index b0425991e9a..e2fd74b8e8c 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -1,5 +1,5 @@ obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o -obj-y += timeconv.o posix-clock.o +obj-y += timeconv.o posix-clock.o alarmtimer.o obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c new file mode 100644 index 00000000000..59f369f98a0 --- /dev/null +++ b/kernel/time/alarmtimer.c @@ -0,0 +1,720 @@ +/* + * Alarmtimer interface + * + * This interface provides a timer which is similarto hrtimers, + * but triggers a RTC alarm if the box is suspend. + * + * This interface is influenced by the Android RTC Alarm timer + * interface. + * + * Copyright (C) 2010 IBM Corperation + * + * Author: John Stultz <john.stultz@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/time.h> +#include <linux/hrtimer.h> +#include <linux/timerqueue.h> +#include <linux/rtc.h> +#include <linux/alarmtimer.h> +#include <linux/mutex.h> +#include <linux/platform_device.h> +#include <linux/posix-timers.h> +#include <linux/workqueue.h> +#include <linux/freezer.h> + +/** + * struct alarm_base - Alarm timer bases + * @lock: Lock for syncrhonized access to the base + * @timerqueue: Timerqueue head managing the list of events + * @timer: hrtimer used to schedule events while running + * @gettime: Function to read the time correlating to the base + * @base_clockid: clockid for the base + */ +static struct alarm_base { + spinlock_t lock; + struct timerqueue_head timerqueue; + struct hrtimer timer; + ktime_t (*gettime)(void); + clockid_t base_clockid; +} alarm_bases[ALARM_NUMTYPE]; + +/* freezer delta & lock used to handle clock_nanosleep triggered wakeups */ +static ktime_t freezer_delta; +static DEFINE_SPINLOCK(freezer_delta_lock); + +#ifdef CONFIG_RTC_CLASS +/* rtc timer and device for setting alarm wakeups at suspend */ +static struct rtc_timer rtctimer; +static struct rtc_device *rtcdev; +static DEFINE_SPINLOCK(rtcdev_lock); + +/** + * has_wakealarm - check rtc device has wakealarm ability + * @dev: current device + * @name_ptr: name to be returned + * + * This helper function checks to see if the rtc device can wake + * from suspend. + */ +static int has_wakealarm(struct device *dev, void *name_ptr) +{ + struct rtc_device *candidate = to_rtc_device(dev); + + if (!candidate->ops->set_alarm) + return 0; + if (!device_may_wakeup(candidate->dev.parent)) + return 0; + + *(const char **)name_ptr = dev_name(dev); + return 1; +} + +/** + * alarmtimer_get_rtcdev - Return selected rtcdevice + * + * This function returns the rtc device to use for wakealarms. + * If one has not already been chosen, it checks to see if a + * functional rtc device is available. + */ +static struct rtc_device *alarmtimer_get_rtcdev(void) +{ + struct device *dev; + char *str; + unsigned long flags; + struct rtc_device *ret; + + spin_lock_irqsave(&rtcdev_lock, flags); + if (!rtcdev) { + /* Find an rtc device and init the rtc_timer */ + dev = class_find_device(rtc_class, NULL, &str, has_wakealarm); + /* If we have a device then str is valid. See has_wakealarm() */ + if (dev) { + rtcdev = rtc_class_open(str); + /* + * Drop the reference we got in class_find_device, + * rtc_open takes its own. + */ + put_device(dev); + rtc_timer_init(&rtctimer, NULL, NULL); + } + } + ret = rtcdev; + spin_unlock_irqrestore(&rtcdev_lock, flags); + + return ret; +} +#else +#define alarmtimer_get_rtcdev() (0) +#define rtcdev (0) +#endif + + +/** + * alarmtimer_enqueue - Adds an alarm timer to an alarm_base timerqueue + * @base: pointer to the base where the timer is being run + * @alarm: pointer to alarm being enqueued. + * + * Adds alarm to a alarm_base timerqueue and if necessary sets + * an hrtimer to run. + * + * Must hold base->lock when calling. + */ +static void alarmtimer_enqueue(struct alarm_base *base, struct alarm *alarm) +{ + timerqueue_add(&base->timerqueue, &alarm->node); + if (&alarm->node == timerqueue_getnext(&base->timerqueue)) { + hrtimer_try_to_cancel(&base->timer); + hrtimer_start(&base->timer, alarm->node.expires, + HRTIMER_MODE_ABS); + } +} + +/** + * alarmtimer_remove - Removes an alarm timer from an alarm_base timerqueue + * @base: pointer to the base where the timer is running + * @alarm: pointer to alarm being removed + * + * Removes alarm to a alarm_base timerqueue and if necessary sets + * a new timer to run. + * + * Must hold base->lock when calling. + */ +static void alarmtimer_remove(struct alarm_base *base, struct alarm *alarm) +{ + struct timerqueue_node *next = timerqueue_getnext(&base->timerqueue); + + timerqueue_del(&base->timerqueue, &alarm->node); + if (next == &alarm->node) { + hrtimer_try_to_cancel(&base->timer); + next = timerqueue_getnext(&base->timerqueue); + if (!next) + return; + hrtimer_start(&base->timer, next->expires, HRTIMER_MODE_ABS); + } +} + + +/** + * alarmtimer_fired - Handles alarm hrtimer being fired. + * @timer: pointer to hrtimer being run + * + * When a alarm timer fires, this runs through the timerqueue to + * see which alarms expired, and runs those. If there are more alarm + * timers queued for the future, we set the hrtimer to fire when + * when the next future alarm timer expires. + */ +static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) +{ + struct alarm_base *base = container_of(timer, struct alarm_base, timer); + struct timerqueue_node *next; + unsigned long flags; + ktime_t now; + int ret = HRTIMER_NORESTART; + + spin_lock_irqsave(&base->lock, flags); + now = base->gettime(); + while ((next = timerqueue_getnext(&base->timerqueue))) { + struct alarm *alarm; + ktime_t expired = next->expires; + + if (expired.tv64 >= now.tv64) + break; + + alarm = container_of(next, struct alarm, node); + + timerqueue_del(&base->timerqueue, &alarm->node); + alarm->enabled = 0; + /* Re-add periodic timers */ + if (alarm->period.tv64) { + alarm->node.expires = ktime_add(expired, alarm->period); + timerqueue_add(&base->timerqueue, &alarm->node); + alarm->enabled = 1; + } + spin_unlock_irqrestore(&base->lock, flags); + if (alarm->function) + alarm->function(alarm); + spin_lock_irqsave(&base->lock, flags); + } + + if (next) { + hrtimer_set_expires(&base->timer, next->expires); + ret = HRTIMER_RESTART; + } + spin_unlock_irqrestore(&base->lock, flags); + + return ret; + +} + +#ifdef CONFIG_RTC_CLASS +/** + * alarmtimer_suspend - Suspend time callback + * @dev: unused + * @state: unused + * + * When we are going into suspend, we look through the bases + * to see which is the soonest timer to expire. We then + * set an rtc timer to fire that far into the future, which + * will wake us from suspend. + */ +static int alarmtimer_suspend(struct device *dev) +{ + struct rtc_time tm; + ktime_t min, now; + unsigned long flags; + struct rtc_device *rtc; + int i; + + spin_lock_irqsave(&freezer_delta_lock, flags); + min = freezer_delta; + freezer_delta = ktime_set(0, 0); + spin_unlock_irqrestore(&freezer_delta_lock, flags); + + rtc = rtcdev; + /* If we have no rtcdev, just return */ + if (!rtc) + return 0; + + /* Find the soonest timer to expire*/ + for (i = 0; i < ALARM_NUMTYPE; i++) { + struct alarm_base *base = &alarm_bases[i]; + struct timerqueue_node *next; + ktime_t delta; + + spin_lock_irqsave(&base->lock, flags); + next = timerqueue_getnext(&base->timerqueue); + spin_unlock_irqrestore(&base->lock, flags); + if (!next) + continue; + delta = ktime_sub(next->expires, base->gettime()); + if (!min.tv64 || (delta.tv64 < min.tv64)) + min = delta; + } + if (min.tv64 == 0) + return 0; + + /* XXX - Should we enforce a minimum sleep time? */ + WARN_ON(min.tv64 < NSEC_PER_SEC); + + /* Setup an rtc timer to fire that far in the future */ + rtc_timer_cancel(rtc, &rtctimer); + rtc_read_time(rtc, &tm); + now = rtc_tm_to_ktime(tm); + now = ktime_add(now, min); + + rtc_timer_start(rtc, &rtctimer, now, ktime_set(0, 0)); + + return 0; +} +#else +static int alarmtimer_suspend(struct device *dev) +{ + return 0; +} +#endif + +static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type) +{ + ktime_t delta; + unsigned long flags; + struct alarm_base *base = &alarm_bases[type]; + + delta = ktime_sub(absexp, base->gettime()); + + spin_lock_irqsave(&freezer_delta_lock, flags); + if (!freezer_delta.tv64 || (delta.tv64 < freezer_delta.tv64)) + freezer_delta = delta; + spin_unlock_irqrestore(&freezer_delta_lock, flags); +} + + +/** + * alarm_init - Initialize an alarm structure + * @alarm: ptr to alarm to be initialized + * @type: the type of the alarm + * @function: callback that is run when the alarm fires + */ +void alarm_init(struct alarm *alarm, enum alarmtimer_type type, + void (*function)(struct alarm *)) +{ + timerqueue_init(&alarm->node); + alarm->period = ktime_set(0, 0); + alarm->function = function; + alarm->type = type; + alarm->enabled = 0; +} + +/** + * alarm_start - Sets an alarm to fire + * @alarm: ptr to alarm to set + * @start: time to run the alarm + * @period: period at which the alarm will recur + */ +void alarm_start(struct alarm *alarm, ktime_t start, ktime_t period) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + unsigned long flags; + + spin_lock_irqsave(&base->lock, flags); + if (alarm->enabled) + alarmtimer_remove(base, alarm); + alarm->node.expires = start; + alarm->period = period; + alarmtimer_enqueue(base, alarm); + alarm->enabled = 1; + spin_unlock_irqrestore(&base->lock, flags); +} + +/** + * alarm_cancel - Tries to cancel an alarm timer + * @alarm: ptr to alarm to be canceled + */ +void alarm_cancel(struct alarm *alarm) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + unsigned long flags; + + spin_lock_irqsave(&base->lock, flags); + if (alarm->enabled) + alarmtimer_remove(base, alarm); + alarm->enabled = 0; + spin_unlock_irqrestore(&base->lock, flags); +} + + +/** + * clock2alarm - helper that converts from clockid to alarmtypes + * @clockid: clockid. + */ +static enum alarmtimer_type clock2alarm(clockid_t clockid) +{ + if (clockid == CLOCK_REALTIME_ALARM) + return ALARM_REALTIME; + if (clockid == CLOCK_BOOTTIME_ALARM) + return ALARM_BOOTTIME; + return -1; +} + +/** + * alarm_handle_timer - Callback for posix timers + * @alarm: alarm that fired + * + * Posix timer callback for expired alarm timers. + */ +static void alarm_handle_timer(struct alarm *alarm) +{ + struct k_itimer *ptr = container_of(alarm, struct k_itimer, + it.alarmtimer); + if (posix_timer_event(ptr, 0) != 0) + ptr->it_overrun++; +} + +/** + * alarm_clock_getres - posix getres interface + * @which_clock: clockid + * @tp: timespec to fill + * + * Returns the granularity of underlying alarm base clock + */ +static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp) +{ + clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid; + + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + + return hrtimer_get_res(baseid, tp); +} + +/** + * alarm_clock_get - posix clock_get interface + * @which_clock: clockid + * @tp: timespec to fill. + * + * Provides the underlying alarm base time. + */ +static int alarm_clock_get(clockid_t which_clock, struct timespec *tp) +{ + struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)]; + + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + + *tp = ktime_to_timespec(base->gettime()); + return 0; +} + +/** + * alarm_timer_create - posix timer_create interface + * @new_timer: k_itimer pointer to manage + * + * Initializes the k_itimer structure. + */ +static int alarm_timer_create(struct k_itimer *new_timer) +{ + enum alarmtimer_type type; + struct alarm_base *base; + + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + + if (!capable(CAP_WAKE_ALARM)) + return -EPERM; + + type = clock2alarm(new_timer->it_clock); + base = &alarm_bases[type]; + alarm_init(&new_timer->it.alarmtimer, type, alarm_handle_timer); + return 0; +} + +/** + * alarm_timer_get - posix timer_get interface + * @new_timer: k_itimer pointer + * @cur_setting: itimerspec data to fill + * + * Copies the itimerspec data out from the k_itimer + */ +static void alarm_timer_get(struct k_itimer *timr, + struct itimerspec *cur_setting) +{ + cur_setting->it_interval = + ktime_to_timespec(timr->it.alarmtimer.period); + cur_setting->it_value = + ktime_to_timespec(timr->it.alarmtimer.node.expires); + return; +} + +/** + * alarm_timer_del - posix timer_del interface + * @timr: k_itimer pointer to be deleted + * + * Cancels any programmed alarms for the given timer. + */ +static int alarm_timer_del(struct k_itimer *timr) +{ + if (!rtcdev) + return -ENOTSUPP; + + alarm_cancel(&timr->it.alarmtimer); + return 0; +} + +/** + * alarm_timer_set - posix timer_set interface + * @timr: k_itimer pointer to be deleted + * @flags: timer flags + * @new_setting: itimerspec to be used + * @old_setting: itimerspec being replaced + * + * Sets the timer to new_setting, and starts the timer. + */ +static int alarm_timer_set(struct k_itimer *timr, int flags, + struct itimerspec *new_setting, + struct itimerspec *old_setting) +{ + if (!rtcdev) + return -ENOTSUPP; + + /* Save old values */ + old_setting->it_interval = + ktime_to_timespec(timr->it.alarmtimer.period); + old_setting->it_value = + ktime_to_timespec(timr->it.alarmtimer.node.expires); + + /* If the timer was already set, cancel it */ + alarm_cancel(&timr->it.alarmtimer); + + /* start the timer */ + alarm_start(&timr->it.alarmtimer, + timespec_to_ktime(new_setting->it_value), + timespec_to_ktime(new_setting->it_interval)); + return 0; +} + +/** + * alarmtimer_nsleep_wakeup - Wakeup function for alarm_timer_nsleep + * @alarm: ptr to alarm that fired + * + * Wakes up the task that set the alarmtimer + */ +static void alarmtimer_nsleep_wakeup(struct alarm *alarm) +{ + struct task_struct *task = (struct task_struct *)alarm->data; + + alarm->data = NULL; + if (task) + wake_up_process(task); +} + +/** + * alarmtimer_do_nsleep - Internal alarmtimer nsleep implementation + * @alarm: ptr to alarmtimer + * @absexp: absolute expiration time + * + * Sets the alarm timer and sleeps until it is fired or interrupted. + */ +static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp) +{ + alarm->data = (void *)current; + do { + set_current_state(TASK_INTERRUPTIBLE); + alarm_start(alarm, absexp, ktime_set(0, 0)); + if (likely(alarm->data)) + schedule(); + + alarm_cancel(alarm); + } while (alarm->data && !signal_pending(current)); + + __set_current_state(TASK_RUNNING); + + return (alarm->data == NULL); +} + + +/** + * update_rmtp - Update remaining timespec value + * @exp: expiration time + * @type: timer type + * @rmtp: user pointer to remaining timepsec value + * + * Helper function that fills in rmtp value with time between + * now and the exp value + */ +static int update_rmtp(ktime_t exp, enum alarmtimer_type type, + struct timespec __user *rmtp) +{ + struct timespec rmt; + ktime_t rem; + + rem = ktime_sub(exp, alarm_bases[type].gettime()); + + if (rem.tv64 <= 0) + return 0; + rmt = ktime_to_timespec(rem); + + if (copy_to_user(rmtp, &rmt, sizeof(*rmtp))) + return -EFAULT; + + return 1; + +} + +/** + * alarm_timer_nsleep_restart - restartblock alarmtimer nsleep + * @restart: ptr to restart block + * + * Handles restarted clock_nanosleep calls + */ +static long __sched alarm_timer_nsleep_restart(struct restart_block *restart) +{ + enum alarmtimer_type type = restart->nanosleep.clockid; + ktime_t exp; + struct timespec __user *rmtp; + struct alarm alarm; + int ret = 0; + + exp.tv64 = restart->nanosleep.expires; + alarm_init(&alarm, type, alarmtimer_nsleep_wakeup); + + if (alarmtimer_do_nsleep(&alarm, exp)) + goto out; + + if (freezing(current)) + alarmtimer_freezerset(exp, type); + + rmtp = restart->nanosleep.rmtp; + if (rmtp) { + ret = update_rmtp(exp, type, rmtp); + if (ret <= 0) + goto out; + } + + + /* The other values in restart are already filled in */ + ret = -ERESTART_RESTARTBLOCK; +out: + return ret; +} + +/** + * alarm_timer_nsleep - alarmtimer nanosleep + * @which_clock: clockid + * @flags: determins abstime or relative + * @tsreq: requested sleep time (abs or rel) + * @rmtp: remaining sleep time saved + * + * Handles clock_nanosleep calls against _ALARM clockids + */ +static int alarm_timer_nsleep(const clockid_t which_clock, int flags, + struct timespec *tsreq, struct timespec __user *rmtp) +{ + enum alarmtimer_type type = clock2alarm(which_clock); + struct alarm alarm; + ktime_t exp; + int ret = 0; + struct restart_block *restart; + + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + + if (!capable(CAP_WAKE_ALARM)) + return -EPERM; + + alarm_init(&alarm, type, alarmtimer_nsleep_wakeup); + + exp = timespec_to_ktime(*tsreq); + /* Convert (if necessary) to absolute time */ + if (flags != TIMER_ABSTIME) { + ktime_t now = alarm_bases[type].gettime(); + exp = ktime_add(now, exp); + } + + if (alarmtimer_do_nsleep(&alarm, exp)) + goto out; + + if (freezing(current)) + alarmtimer_freezerset(exp, type); + + /* abs timers don't set remaining time or restart */ + if (flags == TIMER_ABSTIME) { + ret = -ERESTARTNOHAND; + goto out; + } + + if (rmtp) { + ret = update_rmtp(exp, type, rmtp); + if (ret <= 0) + goto out; + } + + restart = ¤t_thread_info()->restart_block; + restart->fn = alarm_timer_nsleep_restart; + restart->nanosleep.clockid = type; + restart->nanosleep.expires = exp.tv64; + restart->nanosleep.rmtp = rmtp; + ret = -ERESTART_RESTARTBLOCK; + +out: + return ret; +} + + +/* Suspend hook structures */ +static const struct dev_pm_ops alarmtimer_pm_ops = { + .suspend = alarmtimer_suspend, +}; + +static struct platform_driver alarmtimer_driver = { + .driver = { + .name = "alarmtimer", + .pm = &alarmtimer_pm_ops, + } +}; + +/** + * alarmtimer_init - Initialize alarm timer code + * + * This function initializes the alarm bases and registers + * the posix clock ids. + */ +static int __init alarmtimer_init(void) +{ + int error = 0; + int i; + struct k_clock alarm_clock = { + .clock_getres = alarm_clock_getres, + .clock_get = alarm_clock_get, + .timer_create = alarm_timer_create, + .timer_set = alarm_timer_set, + .timer_del = alarm_timer_del, + .timer_get = alarm_timer_get, + .nsleep = alarm_timer_nsleep, + }; + + posix_timers_register_clock(CLOCK_REALTIME_ALARM, &alarm_clock); + posix_timers_register_clock(CLOCK_BOOTTIME_ALARM, &alarm_clock); + + /* Initialize alarm bases */ + alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME; + alarm_bases[ALARM_REALTIME].gettime = &ktime_get_real; + alarm_bases[ALARM_BOOTTIME].base_clockid = CLOCK_BOOTTIME; + alarm_bases[ALARM_BOOTTIME].gettime = &ktime_get_boottime; + for (i = 0; i < ALARM_NUMTYPE; i++) { + timerqueue_init_head(&alarm_bases[i].timerqueue); + spin_lock_init(&alarm_bases[i].lock); + hrtimer_init(&alarm_bases[i].timer, + alarm_bases[i].base_clockid, + HRTIMER_MODE_ABS); + alarm_bases[i].timer.function = alarmtimer_fired; + } + error = platform_driver_register(&alarmtimer_driver); + platform_device_register_simple("alarmtimer", -1, NULL, 0); + + return error; +} +device_initcall(alarmtimer_init); + diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 0d74b9ba90c..e4c699dfa4e 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -182,7 +182,10 @@ void clockevents_register_device(struct clock_event_device *dev) unsigned long flags; BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); - BUG_ON(!dev->cpumask); + if (!dev->cpumask) { + WARN_ON(num_possible_cpus() > 1); + dev->cpumask = cpumask_of(smp_processor_id()); + } raw_spin_lock_irqsave(&clockevents_lock, flags); @@ -194,6 +197,70 @@ void clockevents_register_device(struct clock_event_device *dev) } EXPORT_SYMBOL_GPL(clockevents_register_device); +static void clockevents_config(struct clock_event_device *dev, + u32 freq) +{ + u64 sec; + + if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) + return; + + /* + * Calculate the maximum number of seconds we can sleep. Limit + * to 10 minutes for hardware which can program more than + * 32bit ticks so we still get reasonable conversion values. + */ + sec = dev->max_delta_ticks; + do_div(sec, freq); + if (!sec) + sec = 1; + else if (sec > 600 && dev->max_delta_ticks > UINT_MAX) + sec = 600; + + clockevents_calc_mult_shift(dev, freq, sec); + dev->min_delta_ns = clockevent_delta2ns(dev->min_delta_ticks, dev); + dev->max_delta_ns = clockevent_delta2ns(dev->max_delta_ticks, dev); +} + +/** + * clockevents_config_and_register - Configure and register a clock event device + * @dev: device to register + * @freq: The clock frequency + * @min_delta: The minimum clock ticks to program in oneshot mode + * @max_delta: The maximum clock ticks to program in oneshot mode + * + * min/max_delta can be 0 for devices which do not support oneshot mode. + */ +void clockevents_config_and_register(struct clock_event_device *dev, + u32 freq, unsigned long min_delta, + unsigned long max_delta) +{ + dev->min_delta_ticks = min_delta; + dev->max_delta_ticks = max_delta; + clockevents_config(dev, freq); + clockevents_register_device(dev); +} + +/** + * clockevents_update_freq - Update frequency and reprogram a clock event device. + * @dev: device to modify + * @freq: new device frequency + * + * Reconfigure and reprogram a clock event device in oneshot + * mode. Must be called on the cpu for which the device delivers per + * cpu timer events with interrupts disabled! Returns 0 on success, + * -ETIME when the event is in the past. + */ +int clockevents_update_freq(struct clock_event_device *dev, u32 freq) +{ + clockevents_config(dev, freq); + + if (dev->mode != CLOCK_EVT_MODE_ONESHOT) + return 0; + + return clockevents_program_event(dev, dev->next_event, ktime_get()); +} + /* * Noop handler when we shut down an event device */ diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 6519cf62d9c..e0980f0d9a0 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -185,7 +185,6 @@ static struct clocksource *watchdog; static struct timer_list watchdog_timer; static DECLARE_WORK(watchdog_work, clocksource_watchdog_work); static DEFINE_SPINLOCK(watchdog_lock); -static cycle_t watchdog_last; static int watchdog_running; static int clocksource_watchdog_kthread(void *data); @@ -254,11 +253,6 @@ static void clocksource_watchdog(unsigned long data) if (!watchdog_running) goto out; - wdnow = watchdog->read(watchdog); - wd_nsec = clocksource_cyc2ns((wdnow - watchdog_last) & watchdog->mask, - watchdog->mult, watchdog->shift); - watchdog_last = wdnow; - list_for_each_entry(cs, &watchdog_list, wd_list) { /* Clocksource already marked unstable? */ @@ -268,19 +262,28 @@ static void clocksource_watchdog(unsigned long data) continue; } + local_irq_disable(); csnow = cs->read(cs); + wdnow = watchdog->read(watchdog); + local_irq_enable(); /* Clocksource initialized ? */ if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) { cs->flags |= CLOCK_SOURCE_WATCHDOG; - cs->wd_last = csnow; + cs->wd_last = wdnow; + cs->cs_last = csnow; continue; } - /* Check the deviation from the watchdog clocksource. */ - cs_nsec = clocksource_cyc2ns((csnow - cs->wd_last) & + wd_nsec = clocksource_cyc2ns((wdnow - cs->wd_last) & watchdog->mask, + watchdog->mult, watchdog->shift); + + cs_nsec = clocksource_cyc2ns((csnow - cs->cs_last) & cs->mask, cs->mult, cs->shift); - cs->wd_last = csnow; + cs->cs_last = csnow; + cs->wd_last = wdnow; + + /* Check the deviation from the watchdog clocksource. */ if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) { clocksource_unstable(cs, cs_nsec - wd_nsec); continue; @@ -318,7 +321,6 @@ static inline void clocksource_start_watchdog(void) return; init_timer(&watchdog_timer); watchdog_timer.function = clocksource_watchdog; - watchdog_last = watchdog->read(watchdog); watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask)); watchdog_running = 1; @@ -626,19 +628,6 @@ static void clocksource_enqueue(struct clocksource *cs) list_add(&cs->list, entry); } - -/* - * Maximum time we expect to go between ticks. This includes idle - * tickless time. It provides the trade off between selecting a - * mult/shift pair that is very precise but can only handle a short - * period of time, vs. a mult/shift pair that can handle long periods - * of time but isn't as precise. - * - * This is a subsystem constant, and actual hardware limitations - * may override it (ie: clocksources that wrap every 3 seconds). - */ -#define MAX_UPDATE_LENGTH 5 /* Seconds */ - /** * __clocksource_updatefreq_scale - Used update clocksource with new freq * @t: clocksource to be registered @@ -652,15 +641,28 @@ static void clocksource_enqueue(struct clocksource *cs) */ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq) { + u64 sec; + /* - * Ideally we want to use some of the limits used in - * clocksource_max_deferment, to provide a more informed - * MAX_UPDATE_LENGTH. But for now this just gets the - * register interface working properly. + * Calc the maximum number of seconds which we can run before + * wrapping around. For clocksources which have a mask > 32bit + * we need to limit the max sleep time to have a good + * conversion precision. 10 minutes is still a reasonable + * amount. That results in a shift value of 24 for a + * clocksource with mask >= 40bit and f >= 4GHz. That maps to + * ~ 0.06ppm granularity for NTP. We apply the same 12.5% + * margin as we do in clocksource_max_deferment() */ + sec = (cs->mask - (cs->mask >> 5)); + do_div(sec, freq); + do_div(sec, scale); + if (!sec) + sec = 1; + else if (sec > 600 && cs->mask > UINT_MAX) + sec = 600; + clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, - NSEC_PER_SEC/scale, - MAX_UPDATE_LENGTH*scale); + NSEC_PER_SEC / scale, sec * scale); cs->max_idle_ns = clocksource_max_deferment(cs); } EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale); @@ -685,8 +687,8 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) /* Add clocksource to the clcoksource list */ mutex_lock(&clocksource_mutex); clocksource_enqueue(cs); - clocksource_select(); clocksource_enqueue_watchdog(cs); + clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; } @@ -706,8 +708,8 @@ int clocksource_register(struct clocksource *cs) mutex_lock(&clocksource_mutex); clocksource_enqueue(cs); - clocksource_select(); clocksource_enqueue_watchdog(cs); + clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; } diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 25028dd4fa1..c340ca658f3 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -19,7 +19,6 @@ */ #include <linux/device.h> #include <linux/file.h> -#include <linux/mutex.h> #include <linux/posix-clock.h> #include <linux/slab.h> #include <linux/syscalls.h> @@ -34,19 +33,19 @@ static struct posix_clock *get_posix_clock(struct file *fp) { struct posix_clock *clk = fp->private_data; - mutex_lock(&clk->mutex); + down_read(&clk->rwsem); if (!clk->zombie) return clk; - mutex_unlock(&clk->mutex); + up_read(&clk->rwsem); return NULL; } static void put_posix_clock(struct posix_clock *clk) { - mutex_unlock(&clk->mutex); + up_read(&clk->rwsem); } static ssize_t posix_clock_read(struct file *fp, char __user *buf, @@ -156,7 +155,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp) struct posix_clock *clk = container_of(inode->i_cdev, struct posix_clock, cdev); - mutex_lock(&clk->mutex); + down_read(&clk->rwsem); if (clk->zombie) { err = -ENODEV; @@ -172,7 +171,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp) fp->private_data = clk; } out: - mutex_unlock(&clk->mutex); + up_read(&clk->rwsem); return err; } @@ -211,25 +210,20 @@ int posix_clock_register(struct posix_clock *clk, dev_t devid) int err; kref_init(&clk->kref); - mutex_init(&clk->mutex); + init_rwsem(&clk->rwsem); cdev_init(&clk->cdev, &posix_clock_file_operations); clk->cdev.owner = clk->ops.owner; err = cdev_add(&clk->cdev, devid, 1); - if (err) - goto no_cdev; return err; -no_cdev: - mutex_destroy(&clk->mutex); - return err; } EXPORT_SYMBOL_GPL(posix_clock_register); static void delete_clock(struct kref *kref) { struct posix_clock *clk = container_of(kref, struct posix_clock, kref); - mutex_destroy(&clk->mutex); + if (clk->release) clk->release(clk); } @@ -238,9 +232,9 @@ void posix_clock_unregister(struct posix_clock *clk) { cdev_del(&clk->cdev); - mutex_lock(&clk->mutex); + down_write(&clk->rwsem); clk->zombie = true; - mutex_unlock(&clk->mutex); + up_write(&clk->rwsem); kref_put(&clk->kref, delete_clock); } diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index da800ffa810..c7218d13273 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -456,23 +456,27 @@ void tick_broadcast_oneshot_control(unsigned long reason) unsigned long flags; int cpu; - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - /* * Periodic mode does not care about the enter/exit of power * states */ if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) - goto out; + return; - bc = tick_broadcast_device.evtdev; + /* + * We are called with preemtion disabled from the depth of the + * idle code, so we can't be moved away. + */ cpu = smp_processor_id(); td = &per_cpu(tick_cpu_device, cpu); dev = td->evtdev; if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) - goto out; + return; + bc = tick_broadcast_device.evtdev; + + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) { if (!cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) { cpumask_set_cpu(cpu, tick_get_broadcast_oneshot_mask()); @@ -489,8 +493,6 @@ void tick_broadcast_oneshot_control(unsigned long reason) tick_program_event(dev->next_event, 1); } } - -out: raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } @@ -522,10 +524,11 @@ static void tick_broadcast_init_next_event(struct cpumask *mask, */ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { + int cpu = smp_processor_id(); + /* Set it up only once ! */ if (bc->event_handler != tick_handle_oneshot_broadcast) { int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC; - int cpu = smp_processor_id(); bc->event_handler = tick_handle_oneshot_broadcast; clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); @@ -551,6 +554,15 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) tick_broadcast_set_event(tick_next_period, 1); } else bc->next_event.tv64 = KTIME_MAX; + } else { + /* + * The first cpu which switches to oneshot mode sets + * the bit for all other cpus which are in the general + * (periodic) broadcast mask. So the bit is set and + * would prevent the first broadcast enter after this + * to program the bc device. + */ + tick_broadcast_clear_oneshot(cpu); } } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 8ad5d576755..2b021b0e850 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -596,6 +596,64 @@ void __init timekeeping_init(void) static struct timespec timekeeping_suspend_time; /** + * __timekeeping_inject_sleeptime - Internal function to add sleep interval + * @delta: pointer to a timespec delta value + * + * Takes a timespec offset measuring a suspend interval and properly + * adds the sleep offset to the timekeeping variables. + */ +static void __timekeeping_inject_sleeptime(struct timespec *delta) +{ + if (!timespec_valid(delta)) { + printk(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " + "sleep delta value!\n"); + return; + } + + xtime = timespec_add(xtime, *delta); + wall_to_monotonic = timespec_sub(wall_to_monotonic, *delta); + total_sleep_time = timespec_add(total_sleep_time, *delta); +} + + +/** + * timekeeping_inject_sleeptime - Adds suspend interval to timeekeeping values + * @delta: pointer to a timespec delta value + * + * This hook is for architectures that cannot support read_persistent_clock + * because their RTC/persistent clock is only accessible when irqs are enabled. + * + * This function should only be called by rtc_resume(), and allows + * a suspend offset to be injected into the timekeeping values. + */ +void timekeeping_inject_sleeptime(struct timespec *delta) +{ + unsigned long flags; + struct timespec ts; + + /* Make sure we don't set the clock twice */ + read_persistent_clock(&ts); + if (!(ts.tv_sec == 0 && ts.tv_nsec == 0)) + return; + + write_seqlock_irqsave(&xtime_lock, flags); + timekeeping_forward_now(); + + __timekeeping_inject_sleeptime(delta); + + timekeeper.ntp_error = 0; + ntp_clear(); + update_vsyscall(&xtime, &wall_to_monotonic, timekeeper.clock, + timekeeper.mult); + + write_sequnlock_irqrestore(&xtime_lock, flags); + + /* signal hrtimers about time change */ + clock_was_set(); +} + + +/** * timekeeping_resume - Resumes the generic timekeeping subsystem. * * This is for the generic clocksource timekeeping. @@ -615,9 +673,7 @@ static void timekeeping_resume(void) if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) { ts = timespec_sub(ts, timekeeping_suspend_time); - xtime = timespec_add(xtime, ts); - wall_to_monotonic = timespec_sub(wall_to_monotonic, ts); - total_sleep_time = timespec_add(total_sleep_time, ts); + __timekeeping_inject_sleeptime(&ts); } /* re-base the last cycle value */ timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock); @@ -630,18 +686,40 @@ static void timekeeping_resume(void) clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL); /* Resume hrtimers */ - hres_timers_resume(); + hrtimers_resume(); } static int timekeeping_suspend(void) { unsigned long flags; + struct timespec delta, delta_delta; + static struct timespec old_delta; read_persistent_clock(&timekeeping_suspend_time); write_seqlock_irqsave(&xtime_lock, flags); timekeeping_forward_now(); timekeeping_suspended = 1; + + /* + * To avoid drift caused by repeated suspend/resumes, + * which each can add ~1 second drift error, + * try to compensate so the difference in system time + * and persistent_clock time stays close to constant. + */ + delta = timespec_sub(xtime, timekeeping_suspend_time); + delta_delta = timespec_sub(delta, old_delta); + if (abs(delta_delta.tv_sec) >= 2) { + /* + * if delta_delta is too large, assume time correction + * has occured and set old_delta to the current delta. + */ + old_delta = delta; + } else { + /* Otherwise try to adjust old_system to compensate */ + timekeeping_suspend_time = + timespec_add(timekeeping_suspend_time, delta_delta); + } write_sequnlock_irqrestore(&xtime_lock, flags); clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); @@ -1049,6 +1127,21 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim, } /** + * ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format + */ +ktime_t ktime_get_monotonic_offset(void) +{ + unsigned long seq; + struct timespec wtom; + + do { + seq = read_seqbegin(&xtime_lock); + wtom = wall_to_monotonic; + } while (read_seqretry(&xtime_lock, seq)); + return timespec_to_ktime(wtom); +} + +/** * xtime_update() - advances the timekeeping infrastructure * @ticks: number of ticks, that have elapsed since the last call. * diff --git a/kernel/timer.c b/kernel/timer.c index fd6198692b5..8cff36119e4 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -749,16 +749,15 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires) unsigned long expires_limit, mask; int bit; - expires_limit = expires; - if (timer->slack >= 0) { expires_limit = expires + timer->slack; } else { - unsigned long now = jiffies; + long delta = expires - jiffies; + + if (delta < 256) + return expires; - /* No slack, if already expired else auto slack 0.4% */ - if (time_after(expires, now)) - expires_limit = expires + (expires - now)/256; + expires_limit = expires + delta / 256; } mask = expires ^ expires_limit; if (mask == 0) @@ -795,6 +794,8 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires) */ int mod_timer(struct timer_list *timer, unsigned long expires) { + expires = apply_slack(timer, expires); + /* * This is a common optimization triggered by the * networking code - if the timer is re-modified @@ -803,8 +804,6 @@ int mod_timer(struct timer_list *timer, unsigned long expires) if (timer_pending(timer) && timer->expires == expires) return 1; - expires = apply_slack(timer, expires); - return __mod_timer(timer, expires, false, TIMER_NOT_PINNED); } EXPORT_SYMBOL(mod_timer); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 61d7d59f4a1..2ad39e556cb 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -141,7 +141,7 @@ if FTRACE config FUNCTION_TRACER bool "Kernel Function Tracer" depends on HAVE_FUNCTION_TRACER - select FRAME_POINTER if !ARM_UNWIND && !S390 + select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE select KALLSYMS select GENERIC_TRACER select CONTEXT_SWITCH_TRACER diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ee24fa1935a..c3e4575e782 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -32,27 +32,32 @@ #include <trace/events/sched.h> -#include <asm/ftrace.h> #include <asm/setup.h> #include "trace_output.h" #include "trace_stat.h" #define FTRACE_WARN_ON(cond) \ - do { \ - if (WARN_ON(cond)) \ + ({ \ + int ___r = cond; \ + if (WARN_ON(___r)) \ ftrace_kill(); \ - } while (0) + ___r; \ + }) #define FTRACE_WARN_ON_ONCE(cond) \ - do { \ - if (WARN_ON_ONCE(cond)) \ + ({ \ + int ___r = cond; \ + if (WARN_ON_ONCE(___r)) \ ftrace_kill(); \ - } while (0) + ___r; \ + }) /* hash bits for specific function selection */ #define FTRACE_HASH_BITS 7 #define FTRACE_FUNC_HASHSIZE (1 << FTRACE_HASH_BITS) +#define FTRACE_HASH_DEFAULT_BITS 10 +#define FTRACE_HASH_MAX_BITS 12 /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; @@ -76,33 +81,45 @@ static int ftrace_disabled __read_mostly; static DEFINE_MUTEX(ftrace_lock); -static struct ftrace_ops ftrace_list_end __read_mostly = -{ +static struct ftrace_ops ftrace_list_end __read_mostly = { .func = ftrace_stub, }; -static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end; +static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end; +static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; +static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub; ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; +static struct ftrace_ops global_ops; + +static void +ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); /* - * Traverse the ftrace_list, invoking all entries. The reason that we + * Traverse the ftrace_global_list, invoking all entries. The reason that we * can use rcu_dereference_raw() is that elements removed from this list * are simply leaked, so there is no need to interact with a grace-period * mechanism. The rcu_dereference_raw() calls are needed to handle - * concurrent insertions into the ftrace_list. + * concurrent insertions into the ftrace_global_list. * * Silly Alpha and silly pointer-speculation compiler optimizations! */ -static void ftrace_list_func(unsigned long ip, unsigned long parent_ip) +static void ftrace_global_list_func(unsigned long ip, + unsigned long parent_ip) { - struct ftrace_ops *op = rcu_dereference_raw(ftrace_list); /*see above*/ + struct ftrace_ops *op; + + if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT))) + return; + trace_recursion_set(TRACE_GLOBAL_BIT); + op = rcu_dereference_raw(ftrace_global_list); /*see above*/ while (op != &ftrace_list_end) { op->func(ip, parent_ip); op = rcu_dereference_raw(op->next); /*see above*/ }; + trace_recursion_clear(TRACE_GLOBAL_BIT); } static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip) @@ -130,9 +147,11 @@ void clear_ftrace_function(void) { ftrace_trace_function = ftrace_stub; __ftrace_trace_function = ftrace_stub; + __ftrace_trace_function_delay = ftrace_stub; ftrace_pid_function = ftrace_stub; } +#undef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST #ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST /* * For those archs that do not test ftrace_trace_stop in their @@ -147,46 +166,74 @@ static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip) } #endif -static int __register_ftrace_function(struct ftrace_ops *ops) +static void update_global_ops(void) { - ops->next = ftrace_list; + ftrace_func_t func; + /* - * We are entering ops into the ftrace_list but another - * CPU might be walking that list. We need to make sure - * the ops->next pointer is valid before another CPU sees - * the ops pointer included into the ftrace_list. + * If there's only one function registered, then call that + * function directly. Otherwise, we need to iterate over the + * registered callers. */ - rcu_assign_pointer(ftrace_list, ops); + if (ftrace_global_list == &ftrace_list_end || + ftrace_global_list->next == &ftrace_list_end) + func = ftrace_global_list->func; + else + func = ftrace_global_list_func; - if (ftrace_enabled) { - ftrace_func_t func; + /* If we filter on pids, update to use the pid function */ + if (!list_empty(&ftrace_pids)) { + set_ftrace_pid_function(func); + func = ftrace_pid_func; + } - if (ops->next == &ftrace_list_end) - func = ops->func; - else - func = ftrace_list_func; + global_ops.func = func; +} - if (!list_empty(&ftrace_pids)) { - set_ftrace_pid_function(func); - func = ftrace_pid_func; - } +static void update_ftrace_function(void) +{ + ftrace_func_t func; + + update_global_ops(); + + /* + * If we are at the end of the list and this ops is + * not dynamic, then have the mcount trampoline call + * the function directly + */ + if (ftrace_ops_list == &ftrace_list_end || + (ftrace_ops_list->next == &ftrace_list_end && + !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC))) + func = ftrace_ops_list->func; + else + func = ftrace_ops_list_func; - /* - * For one func, simply call it directly. - * For more than one func, call the chain. - */ #ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - ftrace_trace_function = func; + ftrace_trace_function = func; #else - __ftrace_trace_function = func; - ftrace_trace_function = ftrace_test_stop_func; +#ifdef CONFIG_DYNAMIC_FTRACE + /* do not update till all functions have been modified */ + __ftrace_trace_function_delay = func; +#else + __ftrace_trace_function = func; #endif - } + ftrace_trace_function = ftrace_test_stop_func; +#endif +} - return 0; +static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) +{ + ops->next = *list; + /* + * We are entering ops into the list but another + * CPU might be walking that list. We need to make sure + * the ops->next pointer is valid before another CPU sees + * the ops pointer included into the list. + */ + rcu_assign_pointer(*list, ops); } -static int __unregister_ftrace_function(struct ftrace_ops *ops) +static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) { struct ftrace_ops **p; @@ -194,13 +241,12 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) * If we are removing the last function, then simply point * to the ftrace_stub. */ - if (ftrace_list == ops && ops->next == &ftrace_list_end) { - ftrace_trace_function = ftrace_stub; - ftrace_list = &ftrace_list_end; + if (*list == ops && ops->next == &ftrace_list_end) { + *list = &ftrace_list_end; return 0; } - for (p = &ftrace_list; *p != &ftrace_list_end; p = &(*p)->next) + for (p = list; *p != &ftrace_list_end; p = &(*p)->next) if (*p == ops) break; @@ -208,53 +254,83 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) return -1; *p = (*p)->next; + return 0; +} - if (ftrace_enabled) { - /* If we only have one func left, then call that directly */ - if (ftrace_list->next == &ftrace_list_end) { - ftrace_func_t func = ftrace_list->func; +static int __register_ftrace_function(struct ftrace_ops *ops) +{ + if (ftrace_disabled) + return -ENODEV; - if (!list_empty(&ftrace_pids)) { - set_ftrace_pid_function(func); - func = ftrace_pid_func; - } -#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - ftrace_trace_function = func; -#else - __ftrace_trace_function = func; -#endif - } - } + if (FTRACE_WARN_ON(ops == &global_ops)) + return -EINVAL; + + if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED)) + return -EBUSY; + + if (!core_kernel_data((unsigned long)ops)) + ops->flags |= FTRACE_OPS_FL_DYNAMIC; + + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { + int first = ftrace_global_list == &ftrace_list_end; + add_ftrace_ops(&ftrace_global_list, ops); + ops->flags |= FTRACE_OPS_FL_ENABLED; + if (first) + add_ftrace_ops(&ftrace_ops_list, &global_ops); + } else + add_ftrace_ops(&ftrace_ops_list, ops); + + if (ftrace_enabled) + update_ftrace_function(); return 0; } -static void ftrace_update_pid_func(void) +static int __unregister_ftrace_function(struct ftrace_ops *ops) { - ftrace_func_t func; + int ret; - if (ftrace_trace_function == ftrace_stub) - return; + if (ftrace_disabled) + return -ENODEV; -#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - func = ftrace_trace_function; -#else - func = __ftrace_trace_function; -#endif + if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED))) + return -EBUSY; - if (!list_empty(&ftrace_pids)) { - set_ftrace_pid_function(func); - func = ftrace_pid_func; - } else { - if (func == ftrace_pid_func) - func = ftrace_pid_function; - } + if (FTRACE_WARN_ON(ops == &global_ops)) + return -EINVAL; -#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - ftrace_trace_function = func; -#else - __ftrace_trace_function = func; -#endif + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { + ret = remove_ftrace_ops(&ftrace_global_list, ops); + if (!ret && ftrace_global_list == &ftrace_list_end) + ret = remove_ftrace_ops(&ftrace_ops_list, &global_ops); + if (!ret) + ops->flags &= ~FTRACE_OPS_FL_ENABLED; + } else + ret = remove_ftrace_ops(&ftrace_ops_list, ops); + + if (ret < 0) + return ret; + + if (ftrace_enabled) + update_ftrace_function(); + + /* + * Dynamic ops may be freed, we must make sure that all + * callers are done before leaving this function. + */ + if (ops->flags & FTRACE_OPS_FL_DYNAMIC) + synchronize_sched(); + + return 0; +} + +static void ftrace_update_pid_func(void) +{ + /* Only do something if we are tracing something */ + if (ftrace_trace_function == ftrace_stub) + return; + + update_ftrace_function(); } #ifdef CONFIG_FUNCTION_PROFILER @@ -715,8 +791,7 @@ static void unregister_ftrace_profiler(void) unregister_ftrace_graph(); } #else -static struct ftrace_ops ftrace_profile_ops __read_mostly = -{ +static struct ftrace_ops ftrace_profile_ops __read_mostly = { .func = function_profile_call, }; @@ -736,19 +811,10 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { unsigned long val; - char buf[64]; /* big enough to hold a number */ int ret; - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - - ret = strict_strtoul(buf, 10, &val); - if (ret < 0) + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) return ret; val = !!val; @@ -888,8 +954,35 @@ enum { FTRACE_START_FUNC_RET = (1 << 3), FTRACE_STOP_FUNC_RET = (1 << 4), }; +struct ftrace_func_entry { + struct hlist_node hlist; + unsigned long ip; +}; -static int ftrace_filtered; +struct ftrace_hash { + unsigned long size_bits; + struct hlist_head *buckets; + unsigned long count; + struct rcu_head rcu; +}; + +/* + * We make these constant because no one should touch them, + * but they are used as the default "empty hash", to avoid allocating + * it all the time. These are in a read only section such that if + * anyone does try to modify it, it will cause an exception. + */ +static const struct hlist_head empty_buckets[1]; +static const struct ftrace_hash empty_hash = { + .buckets = (struct hlist_head *)empty_buckets, +}; +#define EMPTY_HASH ((struct ftrace_hash *)&empty_hash) + +static struct ftrace_ops global_ops = { + .func = ftrace_stub, + .notrace_hash = EMPTY_HASH, + .filter_hash = EMPTY_HASH, +}; static struct dyn_ftrace *ftrace_new_addrs; @@ -912,6 +1005,292 @@ static struct ftrace_page *ftrace_pages; static struct dyn_ftrace *ftrace_free_records; +static struct ftrace_func_entry * +ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) +{ + unsigned long key; + struct ftrace_func_entry *entry; + struct hlist_head *hhd; + struct hlist_node *n; + + if (!hash->count) + return NULL; + + if (hash->size_bits > 0) + key = hash_long(ip, hash->size_bits); + else + key = 0; + + hhd = &hash->buckets[key]; + + hlist_for_each_entry_rcu(entry, n, hhd, hlist) { + if (entry->ip == ip) + return entry; + } + return NULL; +} + +static void __add_hash_entry(struct ftrace_hash *hash, + struct ftrace_func_entry *entry) +{ + struct hlist_head *hhd; + unsigned long key; + + if (hash->size_bits) + key = hash_long(entry->ip, hash->size_bits); + else + key = 0; + + hhd = &hash->buckets[key]; + hlist_add_head(&entry->hlist, hhd); + hash->count++; +} + +static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip) +{ + struct ftrace_func_entry *entry; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + entry->ip = ip; + __add_hash_entry(hash, entry); + + return 0; +} + +static void +free_hash_entry(struct ftrace_hash *hash, + struct ftrace_func_entry *entry) +{ + hlist_del(&entry->hlist); + kfree(entry); + hash->count--; +} + +static void +remove_hash_entry(struct ftrace_hash *hash, + struct ftrace_func_entry *entry) +{ + hlist_del(&entry->hlist); + hash->count--; +} + +static void ftrace_hash_clear(struct ftrace_hash *hash) +{ + struct hlist_head *hhd; + struct hlist_node *tp, *tn; + struct ftrace_func_entry *entry; + int size = 1 << hash->size_bits; + int i; + + if (!hash->count) + return; + + for (i = 0; i < size; i++) { + hhd = &hash->buckets[i]; + hlist_for_each_entry_safe(entry, tp, tn, hhd, hlist) + free_hash_entry(hash, entry); + } + FTRACE_WARN_ON(hash->count); +} + +static void free_ftrace_hash(struct ftrace_hash *hash) +{ + if (!hash || hash == EMPTY_HASH) + return; + ftrace_hash_clear(hash); + kfree(hash->buckets); + kfree(hash); +} + +static void __free_ftrace_hash_rcu(struct rcu_head *rcu) +{ + struct ftrace_hash *hash; + + hash = container_of(rcu, struct ftrace_hash, rcu); + free_ftrace_hash(hash); +} + +static void free_ftrace_hash_rcu(struct ftrace_hash *hash) +{ + if (!hash || hash == EMPTY_HASH) + return; + call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu); +} + +static struct ftrace_hash *alloc_ftrace_hash(int size_bits) +{ + struct ftrace_hash *hash; + int size; + + hash = kzalloc(sizeof(*hash), GFP_KERNEL); + if (!hash) + return NULL; + + size = 1 << size_bits; + hash->buckets = kzalloc(sizeof(*hash->buckets) * size, GFP_KERNEL); + + if (!hash->buckets) { + kfree(hash); + return NULL; + } + + hash->size_bits = size_bits; + + return hash; +} + +static struct ftrace_hash * +alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) +{ + struct ftrace_func_entry *entry; + struct ftrace_hash *new_hash; + struct hlist_node *tp; + int size; + int ret; + int i; + + new_hash = alloc_ftrace_hash(size_bits); + if (!new_hash) + return NULL; + + /* Empty hash? */ + if (!hash || !hash->count) + return new_hash; + + size = 1 << hash->size_bits; + for (i = 0; i < size; i++) { + hlist_for_each_entry(entry, tp, &hash->buckets[i], hlist) { + ret = add_hash_entry(new_hash, entry->ip); + if (ret < 0) + goto free_hash; + } + } + + FTRACE_WARN_ON(new_hash->count != hash->count); + + return new_hash; + + free_hash: + free_ftrace_hash(new_hash); + return NULL; +} + +static void +ftrace_hash_rec_disable(struct ftrace_ops *ops, int filter_hash); +static void +ftrace_hash_rec_enable(struct ftrace_ops *ops, int filter_hash); + +static int +ftrace_hash_move(struct ftrace_ops *ops, int enable, + struct ftrace_hash **dst, struct ftrace_hash *src) +{ + struct ftrace_func_entry *entry; + struct hlist_node *tp, *tn; + struct hlist_head *hhd; + struct ftrace_hash *old_hash; + struct ftrace_hash *new_hash; + unsigned long key; + int size = src->count; + int bits = 0; + int ret; + int i; + + /* + * Remove the current set, update the hash and add + * them back. + */ + ftrace_hash_rec_disable(ops, enable); + + /* + * If the new source is empty, just free dst and assign it + * the empty_hash. + */ + if (!src->count) { + free_ftrace_hash_rcu(*dst); + rcu_assign_pointer(*dst, EMPTY_HASH); + return 0; + } + + /* + * Make the hash size about 1/2 the # found + */ + for (size /= 2; size; size >>= 1) + bits++; + + /* Don't allocate too much */ + if (bits > FTRACE_HASH_MAX_BITS) + bits = FTRACE_HASH_MAX_BITS; + + ret = -ENOMEM; + new_hash = alloc_ftrace_hash(bits); + if (!new_hash) + goto out; + + size = 1 << src->size_bits; + for (i = 0; i < size; i++) { + hhd = &src->buckets[i]; + hlist_for_each_entry_safe(entry, tp, tn, hhd, hlist) { + if (bits > 0) + key = hash_long(entry->ip, bits); + else + key = 0; + remove_hash_entry(src, entry); + __add_hash_entry(new_hash, entry); + } + } + + old_hash = *dst; + rcu_assign_pointer(*dst, new_hash); + free_ftrace_hash_rcu(old_hash); + + ret = 0; + out: + /* + * Enable regardless of ret: + * On success, we enable the new hash. + * On failure, we re-enable the original hash. + */ + ftrace_hash_rec_enable(ops, enable); + + return ret; +} + +/* + * Test the hashes for this ops to see if we want to call + * the ops->func or not. + * + * It's a match if the ip is in the ops->filter_hash or + * the filter_hash does not exist or is empty, + * AND + * the ip is not in the ops->notrace_hash. + * + * This needs to be called with preemption disabled as + * the hashes are freed with call_rcu_sched(). + */ +static int +ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) +{ + struct ftrace_hash *filter_hash; + struct ftrace_hash *notrace_hash; + int ret; + + filter_hash = rcu_dereference_raw(ops->filter_hash); + notrace_hash = rcu_dereference_raw(ops->notrace_hash); + + if ((!filter_hash || !filter_hash->count || + ftrace_lookup_ip(filter_hash, ip)) && + (!notrace_hash || !notrace_hash->count || + !ftrace_lookup_ip(notrace_hash, ip))) + ret = 1; + else + ret = 0; + + return ret; +} + /* * This is a double for. Do not use 'break' to break out of the loop, * you must use a goto. @@ -926,6 +1305,105 @@ static struct dyn_ftrace *ftrace_free_records; } \ } +static void __ftrace_hash_rec_update(struct ftrace_ops *ops, + int filter_hash, + bool inc) +{ + struct ftrace_hash *hash; + struct ftrace_hash *other_hash; + struct ftrace_page *pg; + struct dyn_ftrace *rec; + int count = 0; + int all = 0; + + /* Only update if the ops has been registered */ + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return; + + /* + * In the filter_hash case: + * If the count is zero, we update all records. + * Otherwise we just update the items in the hash. + * + * In the notrace_hash case: + * We enable the update in the hash. + * As disabling notrace means enabling the tracing, + * and enabling notrace means disabling, the inc variable + * gets inversed. + */ + if (filter_hash) { + hash = ops->filter_hash; + other_hash = ops->notrace_hash; + if (!hash || !hash->count) + all = 1; + } else { + inc = !inc; + hash = ops->notrace_hash; + other_hash = ops->filter_hash; + /* + * If the notrace hash has no items, + * then there's nothing to do. + */ + if (hash && !hash->count) + return; + } + + do_for_each_ftrace_rec(pg, rec) { + int in_other_hash = 0; + int in_hash = 0; + int match = 0; + + if (all) { + /* + * Only the filter_hash affects all records. + * Update if the record is not in the notrace hash. + */ + if (!other_hash || !ftrace_lookup_ip(other_hash, rec->ip)) + match = 1; + } else { + in_hash = hash && !!ftrace_lookup_ip(hash, rec->ip); + in_other_hash = other_hash && !!ftrace_lookup_ip(other_hash, rec->ip); + + /* + * + */ + if (filter_hash && in_hash && !in_other_hash) + match = 1; + else if (!filter_hash && in_hash && + (in_other_hash || !other_hash->count)) + match = 1; + } + if (!match) + continue; + + if (inc) { + rec->flags++; + if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == FTRACE_REF_MAX)) + return; + } else { + if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == 0)) + return; + rec->flags--; + } + count++; + /* Shortcut, if we handled all records, we are done. */ + if (!all && count == hash->count) + return; + } while_for_each_ftrace_rec(); +} + +static void ftrace_hash_rec_disable(struct ftrace_ops *ops, + int filter_hash) +{ + __ftrace_hash_rec_update(ops, filter_hash, 0); +} + +static void ftrace_hash_rec_enable(struct ftrace_ops *ops, + int filter_hash) +{ + __ftrace_hash_rec_update(ops, filter_hash, 1); +} + static void ftrace_free_rec(struct dyn_ftrace *rec) { rec->freelist = ftrace_free_records; @@ -1047,18 +1525,18 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) ftrace_addr = (unsigned long)FTRACE_ADDR; /* - * If this record is not to be traced or we want to disable it, - * then disable it. + * If we are enabling tracing: + * + * If the record has a ref count, then we need to enable it + * because someone is using it. * - * If we want to enable it and filtering is off, then enable it. + * Otherwise we make sure its disabled. * - * If we want to enable it and filtering is on, enable it only if - * it's filtered + * If we are disabling tracing, then disable all records that + * are enabled. */ - if (enable && !(rec->flags & FTRACE_FL_NOTRACE)) { - if (!ftrace_filtered || (rec->flags & FTRACE_FL_FILTER)) - flag = FTRACE_FL_ENABLED; - } + if (enable && (rec->flags & ~FTRACE_FL_MASK)) + flag = FTRACE_FL_ENABLED; /* If the state of this record hasn't changed, then do nothing */ if ((rec->flags & FTRACE_FL_ENABLED) == flag) @@ -1079,19 +1557,16 @@ static void ftrace_replace_code(int enable) struct ftrace_page *pg; int failed; + if (unlikely(ftrace_disabled)) + return; + do_for_each_ftrace_rec(pg, rec) { - /* - * Skip over free records, records that have - * failed and not converted. - */ - if (rec->flags & FTRACE_FL_FREE || - rec->flags & FTRACE_FL_FAILED || - !(rec->flags & FTRACE_FL_CONVERTED)) + /* Skip over free records */ + if (rec->flags & FTRACE_FL_FREE) continue; failed = __ftrace_replace_code(rec, enable); if (failed) { - rec->flags |= FTRACE_FL_FAILED; ftrace_bug(failed, rec->ip); /* Stop processing */ return; @@ -1107,10 +1582,12 @@ ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) ip = rec->ip; + if (unlikely(ftrace_disabled)) + return 0; + ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR); if (ret) { ftrace_bug(ret, ip); - rec->flags |= FTRACE_FL_FAILED; return 0; } return 1; @@ -1138,6 +1615,12 @@ static int __ftrace_modify_code(void *data) { int *command = data; + /* + * Do not call function tracer while we update the code. + * We are in stop machine, no worrying about races. + */ + function_trace_stop++; + if (*command & FTRACE_ENABLE_CALLS) ftrace_replace_code(1); else if (*command & FTRACE_DISABLE_CALLS) @@ -1151,6 +1634,18 @@ static int __ftrace_modify_code(void *data) else if (*command & FTRACE_STOP_FUNC_RET) ftrace_disable_ftrace_graph_caller(); +#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST + /* + * For archs that call ftrace_test_stop_func(), we must + * wait till after we update all the function callers + * before we update the callback. This keeps different + * ops that record different functions from corrupting + * each other. + */ + __ftrace_trace_function = __ftrace_trace_function_delay; +#endif + function_trace_stop--; + return 0; } @@ -1171,6 +1666,7 @@ static void ftrace_run_update_code(int command) static ftrace_func_t saved_ftrace_func; static int ftrace_start_up; +static int global_start_up; static void ftrace_startup_enable(int command) { @@ -1185,19 +1681,38 @@ static void ftrace_startup_enable(int command) ftrace_run_update_code(command); } -static void ftrace_startup(int command) +static int ftrace_startup(struct ftrace_ops *ops, int command) { + bool hash_enable = true; + if (unlikely(ftrace_disabled)) - return; + return -ENODEV; ftrace_start_up++; command |= FTRACE_ENABLE_CALLS; + /* ops marked global share the filter hashes */ + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { + ops = &global_ops; + /* Don't update hash if global is already set */ + if (global_start_up) + hash_enable = false; + global_start_up++; + } + + ops->flags |= FTRACE_OPS_FL_ENABLED; + if (hash_enable) + ftrace_hash_rec_enable(ops, 1); + ftrace_startup_enable(command); + + return 0; } -static void ftrace_shutdown(int command) +static void ftrace_shutdown(struct ftrace_ops *ops, int command) { + bool hash_disable = true; + if (unlikely(ftrace_disabled)) return; @@ -1209,6 +1724,23 @@ static void ftrace_shutdown(int command) */ WARN_ON_ONCE(ftrace_start_up < 0); + if (ops->flags & FTRACE_OPS_FL_GLOBAL) { + ops = &global_ops; + global_start_up--; + WARN_ON_ONCE(global_start_up < 0); + /* Don't update hash if global still has users */ + if (global_start_up) { + WARN_ON_ONCE(!ftrace_start_up); + hash_disable = false; + } + } + + if (hash_disable) + ftrace_hash_rec_disable(ops, 1); + + if (ops != &global_ops || !global_start_up) + ops->flags &= ~FTRACE_OPS_FL_ENABLED; + if (!ftrace_start_up) command |= FTRACE_DISABLE_CALLS; @@ -1249,10 +1781,36 @@ static cycle_t ftrace_update_time; static unsigned long ftrace_update_cnt; unsigned long ftrace_update_tot_cnt; +static int ops_traces_mod(struct ftrace_ops *ops) +{ + struct ftrace_hash *hash; + + hash = ops->filter_hash; + return !!(!hash || !hash->count); +} + static int ftrace_update_code(struct module *mod) { struct dyn_ftrace *p; cycle_t start, stop; + unsigned long ref = 0; + + /* + * When adding a module, we need to check if tracers are + * currently enabled and if they are set to trace all functions. + * If they are, we need to enable the module functions as well + * as update the reference counts for those function records. + */ + if (mod) { + struct ftrace_ops *ops; + + for (ops = ftrace_ops_list; + ops != &ftrace_list_end; ops = ops->next) { + if (ops->flags & FTRACE_OPS_FL_ENABLED && + ops_traces_mod(ops)) + ref++; + } + } start = ftrace_now(raw_smp_processor_id()); ftrace_update_cnt = 0; @@ -1265,7 +1823,7 @@ static int ftrace_update_code(struct module *mod) p = ftrace_new_addrs; ftrace_new_addrs = p->newlist; - p->flags = 0L; + p->flags = ref; /* * Do the initial record conversion from mcount jump @@ -1273,10 +1831,10 @@ static int ftrace_update_code(struct module *mod) */ if (!ftrace_code_disable(mod, p)) { ftrace_free_rec(p); - continue; + /* Game over */ + break; } - p->flags |= FTRACE_FL_CONVERTED; ftrace_update_cnt++; /* @@ -1288,7 +1846,7 @@ static int ftrace_update_code(struct module *mod) * conversion puts the module to the correct state, thus * passing the ftrace_make_call check. */ - if (ftrace_start_up) { + if (ftrace_start_up && ref) { int failed = __ftrace_replace_code(p, 1); if (failed) { ftrace_bug(failed, p->ip); @@ -1351,9 +1909,9 @@ static int __init ftrace_dyn_table_alloc(unsigned long num_to_init) enum { FTRACE_ITER_FILTER = (1 << 0), FTRACE_ITER_NOTRACE = (1 << 1), - FTRACE_ITER_FAILURES = (1 << 2), - FTRACE_ITER_PRINTALL = (1 << 3), - FTRACE_ITER_HASH = (1 << 4), + FTRACE_ITER_PRINTALL = (1 << 2), + FTRACE_ITER_HASH = (1 << 3), + FTRACE_ITER_ENABLED = (1 << 4), }; #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ @@ -1365,6 +1923,8 @@ struct ftrace_iterator { struct dyn_ftrace *func; struct ftrace_func_probe *probe; struct trace_parser parser; + struct ftrace_hash *hash; + struct ftrace_ops *ops; int hidx; int idx; unsigned flags; @@ -1461,8 +2021,12 @@ static void * t_next(struct seq_file *m, void *v, loff_t *pos) { struct ftrace_iterator *iter = m->private; + struct ftrace_ops *ops = &global_ops; struct dyn_ftrace *rec = NULL; + if (unlikely(ftrace_disabled)) + return NULL; + if (iter->flags & FTRACE_ITER_HASH) return t_hash_next(m, pos); @@ -1483,17 +2047,15 @@ t_next(struct seq_file *m, void *v, loff_t *pos) rec = &iter->pg->records[iter->idx++]; if ((rec->flags & FTRACE_FL_FREE) || - (!(iter->flags & FTRACE_ITER_FAILURES) && - (rec->flags & FTRACE_FL_FAILED)) || - - ((iter->flags & FTRACE_ITER_FAILURES) && - !(rec->flags & FTRACE_FL_FAILED)) || - ((iter->flags & FTRACE_ITER_FILTER) && - !(rec->flags & FTRACE_FL_FILTER)) || + !(ftrace_lookup_ip(ops->filter_hash, rec->ip))) || ((iter->flags & FTRACE_ITER_NOTRACE) && - !(rec->flags & FTRACE_FL_NOTRACE))) { + !ftrace_lookup_ip(ops->notrace_hash, rec->ip)) || + + ((iter->flags & FTRACE_ITER_ENABLED) && + !(rec->flags & ~FTRACE_FL_MASK))) { + rec = NULL; goto retry; } @@ -1517,10 +2079,15 @@ static void reset_iter_read(struct ftrace_iterator *iter) static void *t_start(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; + struct ftrace_ops *ops = &global_ops; void *p = NULL; loff_t l; mutex_lock(&ftrace_lock); + + if (unlikely(ftrace_disabled)) + return NULL; + /* * If an lseek was done, then reset and start from beginning. */ @@ -1532,7 +2099,7 @@ static void *t_start(struct seq_file *m, loff_t *pos) * off, we can short cut and just print out that all * functions are enabled. */ - if (iter->flags & FTRACE_ITER_FILTER && !ftrace_filtered) { + if (iter->flags & FTRACE_ITER_FILTER && !ops->filter_hash->count) { if (*pos > 0) return t_hash_start(m, pos); iter->flags |= FTRACE_ITER_PRINTALL; @@ -1590,7 +2157,11 @@ static int t_show(struct seq_file *m, void *v) if (!rec) return 0; - seq_printf(m, "%ps\n", (void *)rec->ip); + seq_printf(m, "%ps", (void *)rec->ip); + if (iter->flags & FTRACE_ITER_ENABLED) + seq_printf(m, " (%ld)", + rec->flags & ~FTRACE_FL_MASK); + seq_printf(m, "\n"); return 0; } @@ -1630,44 +2201,46 @@ ftrace_avail_open(struct inode *inode, struct file *file) } static int -ftrace_failures_open(struct inode *inode, struct file *file) +ftrace_enabled_open(struct inode *inode, struct file *file) { - int ret; - struct seq_file *m; struct ftrace_iterator *iter; + int ret; - ret = ftrace_avail_open(inode, file); + if (unlikely(ftrace_disabled)) + return -ENODEV; + + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + iter->pg = ftrace_pages_start; + iter->flags = FTRACE_ITER_ENABLED; + + ret = seq_open(file, &show_ftrace_seq_ops); if (!ret) { - m = file->private_data; - iter = m->private; - iter->flags = FTRACE_ITER_FAILURES; + struct seq_file *m = file->private_data; + + m->private = iter; + } else { + kfree(iter); } return ret; } - -static void ftrace_filter_reset(int enable) +static void ftrace_filter_reset(struct ftrace_hash *hash) { - struct ftrace_page *pg; - struct dyn_ftrace *rec; - unsigned long type = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; - mutex_lock(&ftrace_lock); - if (enable) - ftrace_filtered = 0; - do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & FTRACE_FL_FAILED) - continue; - rec->flags &= ~type; - } while_for_each_ftrace_rec(); + ftrace_hash_clear(hash); mutex_unlock(&ftrace_lock); } static int -ftrace_regex_open(struct inode *inode, struct file *file, int enable) +ftrace_regex_open(struct ftrace_ops *ops, int flag, + struct inode *inode, struct file *file) { struct ftrace_iterator *iter; + struct ftrace_hash *hash; int ret = 0; if (unlikely(ftrace_disabled)) @@ -1682,21 +2255,42 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) return -ENOMEM; } + if (flag & FTRACE_ITER_NOTRACE) + hash = ops->notrace_hash; + else + hash = ops->filter_hash; + + iter->ops = ops; + iter->flags = flag; + + if (file->f_mode & FMODE_WRITE) { + mutex_lock(&ftrace_lock); + iter->hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, hash); + mutex_unlock(&ftrace_lock); + + if (!iter->hash) { + trace_parser_put(&iter->parser); + kfree(iter); + return -ENOMEM; + } + } + mutex_lock(&ftrace_regex_lock); + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) - ftrace_filter_reset(enable); + ftrace_filter_reset(iter->hash); if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; - iter->flags = enable ? FTRACE_ITER_FILTER : - FTRACE_ITER_NOTRACE; ret = seq_open(file, &show_ftrace_seq_ops); if (!ret) { struct seq_file *m = file->private_data; m->private = iter; } else { + /* Failed */ + free_ftrace_hash(iter->hash); trace_parser_put(&iter->parser); kfree(iter); } @@ -1710,13 +2304,15 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) static int ftrace_filter_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(inode, file, 1); + return ftrace_regex_open(&global_ops, FTRACE_ITER_FILTER, + inode, file); } static int ftrace_notrace_open(struct inode *inode, struct file *file) { - return ftrace_regex_open(inode, file, 0); + return ftrace_regex_open(&global_ops, FTRACE_ITER_NOTRACE, + inode, file); } static loff_t @@ -1761,86 +2357,99 @@ static int ftrace_match(char *str, char *regex, int len, int type) } static int -ftrace_match_record(struct dyn_ftrace *rec, char *regex, int len, int type) +enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int not) +{ + struct ftrace_func_entry *entry; + int ret = 0; + + entry = ftrace_lookup_ip(hash, rec->ip); + if (not) { + /* Do nothing if it doesn't exist */ + if (!entry) + return 0; + + free_hash_entry(hash, entry); + } else { + /* Do nothing if it exists */ + if (entry) + return 0; + + ret = add_hash_entry(hash, rec->ip); + } + return ret; +} + +static int +ftrace_match_record(struct dyn_ftrace *rec, char *mod, + char *regex, int len, int type) { char str[KSYM_SYMBOL_LEN]; + char *modname; + + kallsyms_lookup(rec->ip, NULL, NULL, &modname, str); + + if (mod) { + /* module lookup requires matching the module */ + if (!modname || strcmp(modname, mod)) + return 0; + + /* blank search means to match all funcs in the mod */ + if (!len) + return 1; + } - kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); return ftrace_match(str, regex, len, type); } -static int ftrace_match_records(char *buff, int len, int enable) +static int +match_records(struct ftrace_hash *hash, char *buff, + int len, char *mod, int not) { - unsigned int search_len; + unsigned search_len = 0; struct ftrace_page *pg; struct dyn_ftrace *rec; - unsigned long flag; - char *search; - int type; - int not; + int type = MATCH_FULL; + char *search = buff; int found = 0; + int ret; - flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; - type = filter_parse_regex(buff, len, &search, ¬); - - search_len = strlen(search); + if (len) { + type = filter_parse_regex(buff, len, &search, ¬); + search_len = strlen(search); + } mutex_lock(&ftrace_lock); - do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & FTRACE_FL_FAILED) - continue; + if (unlikely(ftrace_disabled)) + goto out_unlock; - if (ftrace_match_record(rec, search, search_len, type)) { - if (not) - rec->flags &= ~flag; - else - rec->flags |= flag; + do_for_each_ftrace_rec(pg, rec) { + + if (ftrace_match_record(rec, mod, search, search_len, type)) { + ret = enter_record(hash, rec, not); + if (ret < 0) { + found = ret; + goto out_unlock; + } found = 1; } - /* - * Only enable filtering if we have a function that - * is filtered on. - */ - if (enable && (rec->flags & FTRACE_FL_FILTER)) - ftrace_filtered = 1; } while_for_each_ftrace_rec(); + out_unlock: mutex_unlock(&ftrace_lock); return found; } static int -ftrace_match_module_record(struct dyn_ftrace *rec, char *mod, - char *regex, int len, int type) +ftrace_match_records(struct ftrace_hash *hash, char *buff, int len) { - char str[KSYM_SYMBOL_LEN]; - char *modname; - - kallsyms_lookup(rec->ip, NULL, NULL, &modname, str); - - if (!modname || strcmp(modname, mod)) - return 0; - - /* blank search means to match all funcs in the mod */ - if (len) - return ftrace_match(str, regex, len, type); - else - return 1; + return match_records(hash, buff, len, NULL, 0); } -static int ftrace_match_module_records(char *buff, char *mod, int enable) +static int +ftrace_match_module_records(struct ftrace_hash *hash, char *buff, char *mod) { - unsigned search_len = 0; - struct ftrace_page *pg; - struct dyn_ftrace *rec; - int type = MATCH_FULL; - char *search = buff; - unsigned long flag; int not = 0; - int found = 0; - - flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; /* blank or '*' mean the same */ if (strcmp(buff, "*") == 0) @@ -1852,32 +2461,7 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable) not = 1; } - if (strlen(buff)) { - type = filter_parse_regex(buff, strlen(buff), &search, ¬); - search_len = strlen(search); - } - - mutex_lock(&ftrace_lock); - do_for_each_ftrace_rec(pg, rec) { - - if (rec->flags & FTRACE_FL_FAILED) - continue; - - if (ftrace_match_module_record(rec, mod, - search, search_len, type)) { - if (not) - rec->flags &= ~flag; - else - rec->flags |= flag; - found = 1; - } - if (enable && (rec->flags & FTRACE_FL_FILTER)) - ftrace_filtered = 1; - - } while_for_each_ftrace_rec(); - mutex_unlock(&ftrace_lock); - - return found; + return match_records(hash, buff, strlen(buff), mod, not); } /* @@ -1886,9 +2470,11 @@ static int ftrace_match_module_records(char *buff, char *mod, int enable) */ static int -ftrace_mod_callback(char *func, char *cmd, char *param, int enable) +ftrace_mod_callback(struct ftrace_hash *hash, + char *func, char *cmd, char *param, int enable) { char *mod; + int ret = -EINVAL; /* * cmd == 'mod' because we only registered this func @@ -1900,15 +2486,19 @@ ftrace_mod_callback(char *func, char *cmd, char *param, int enable) /* we must have a module name */ if (!param) - return -EINVAL; + return ret; mod = strsep(¶m, ":"); if (!strlen(mod)) - return -EINVAL; + return ret; - if (ftrace_match_module_records(func, mod, enable)) - return 0; - return -EINVAL; + ret = ftrace_match_module_records(hash, func, mod); + if (!ret) + ret = -EINVAL; + if (ret < 0) + return ret; + + return 0; } static struct ftrace_func_command ftrace_mod_cmd = { @@ -1959,6 +2549,7 @@ static int ftrace_probe_registered; static void __enable_ftrace_function_probe(void) { + int ret; int i; if (ftrace_probe_registered) @@ -1973,13 +2564,16 @@ static void __enable_ftrace_function_probe(void) if (i == FTRACE_FUNC_HASHSIZE) return; - __register_ftrace_function(&trace_probe_ops); - ftrace_startup(0); + ret = __register_ftrace_function(&trace_probe_ops); + if (!ret) + ret = ftrace_startup(&trace_probe_ops, 0); + ftrace_probe_registered = 1; } static void __disable_ftrace_function_probe(void) { + int ret; int i; if (!ftrace_probe_registered) @@ -1992,8 +2586,10 @@ static void __disable_ftrace_function_probe(void) } /* no more funcs left */ - __unregister_ftrace_function(&trace_probe_ops); - ftrace_shutdown(0); + ret = __unregister_ftrace_function(&trace_probe_ops); + if (!ret) + ftrace_shutdown(&trace_probe_ops, 0); + ftrace_probe_registered = 0; } @@ -2029,12 +2625,13 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, return -EINVAL; mutex_lock(&ftrace_lock); - do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & FTRACE_FL_FAILED) - continue; + if (unlikely(ftrace_disabled)) + goto out_unlock; - if (!ftrace_match_record(rec, search, len, type)) + do_for_each_ftrace_rec(pg, rec) { + + if (!ftrace_match_record(rec, NULL, search, len, type)) continue; entry = kmalloc(sizeof(*entry), GFP_KERNEL); @@ -2195,7 +2792,8 @@ int unregister_ftrace_command(struct ftrace_func_command *cmd) return ret; } -static int ftrace_process_regex(char *buff, int len, int enable) +static int ftrace_process_regex(struct ftrace_hash *hash, + char *buff, int len, int enable) { char *func, *command, *next = buff; struct ftrace_func_command *p; @@ -2204,9 +2802,12 @@ static int ftrace_process_regex(char *buff, int len, int enable) func = strsep(&next, ":"); if (!next) { - if (ftrace_match_records(func, len, enable)) - return 0; - return ret; + ret = ftrace_match_records(hash, func, len); + if (!ret) + ret = -EINVAL; + if (ret < 0) + return ret; + return 0; } /* command found */ @@ -2216,7 +2817,7 @@ static int ftrace_process_regex(char *buff, int len, int enable) mutex_lock(&ftrace_cmd_mutex); list_for_each_entry(p, &ftrace_commands, list) { if (strcmp(p->name, command) == 0) { - ret = p->func(func, command, next, enable); + ret = p->func(hash, func, command, next, enable); goto out_unlock; } } @@ -2239,6 +2840,10 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, mutex_lock(&ftrace_regex_lock); + ret = -ENODEV; + if (unlikely(ftrace_disabled)) + goto out_unlock; + if (file->f_mode & FMODE_READ) { struct seq_file *m = file->private_data; iter = m->private; @@ -2250,7 +2855,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, if (read >= 0 && trace_parser_loaded(parser) && !trace_parser_cont(parser)) { - ret = ftrace_process_regex(parser->buffer, + ret = ftrace_process_regex(iter->hash, parser->buffer, parser->idx, enable); trace_parser_clear(parser); if (ret) @@ -2278,22 +2883,53 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf, return ftrace_regex_write(file, ubuf, cnt, ppos, 0); } -static void -ftrace_set_regex(unsigned char *buf, int len, int reset, int enable) +static int +ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, + int reset, int enable) { + struct ftrace_hash **orig_hash; + struct ftrace_hash *hash; + int ret; + + /* All global ops uses the global ops filters */ + if (ops->flags & FTRACE_OPS_FL_GLOBAL) + ops = &global_ops; + if (unlikely(ftrace_disabled)) - return; + return -ENODEV; + + if (enable) + orig_hash = &ops->filter_hash; + else + orig_hash = &ops->notrace_hash; + + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); + if (!hash) + return -ENOMEM; mutex_lock(&ftrace_regex_lock); if (reset) - ftrace_filter_reset(enable); + ftrace_filter_reset(hash); if (buf) - ftrace_match_records(buf, len, enable); + ftrace_match_records(hash, buf, len); + + mutex_lock(&ftrace_lock); + ret = ftrace_hash_move(ops, enable, orig_hash, hash); + if (!ret && ops->flags & FTRACE_OPS_FL_ENABLED + && ftrace_enabled) + ftrace_run_update_code(FTRACE_ENABLE_CALLS); + + mutex_unlock(&ftrace_lock); + mutex_unlock(&ftrace_regex_lock); + + free_ftrace_hash(hash); + return ret; } /** * ftrace_set_filter - set a function to filter on in ftrace + * @ops - the ops to set the filter with * @buf - the string that holds the function filter text. * @len - the length of the string. * @reset - non zero to reset all filters before applying this filter. @@ -2301,13 +2937,16 @@ ftrace_set_regex(unsigned char *buf, int len, int reset, int enable) * Filters denote which functions should be enabled when tracing is enabled. * If @buf is NULL and reset is set, all functions will be enabled for tracing. */ -void ftrace_set_filter(unsigned char *buf, int len, int reset) +void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, + int len, int reset) { - ftrace_set_regex(buf, len, reset, 1); + ftrace_set_regex(ops, buf, len, reset, 1); } +EXPORT_SYMBOL_GPL(ftrace_set_filter); /** * ftrace_set_notrace - set a function to not trace in ftrace + * @ops - the ops to set the notrace filter with * @buf - the string that holds the function notrace text. * @len - the length of the string. * @reset - non zero to reset all filters before applying this filter. @@ -2316,10 +2955,44 @@ void ftrace_set_filter(unsigned char *buf, int len, int reset) * is enabled. If @buf is NULL and reset is set, all functions will be enabled * for tracing. */ -void ftrace_set_notrace(unsigned char *buf, int len, int reset) +void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, + int len, int reset) { - ftrace_set_regex(buf, len, reset, 0); + ftrace_set_regex(ops, buf, len, reset, 0); } +EXPORT_SYMBOL_GPL(ftrace_set_notrace); +/** + * ftrace_set_filter - set a function to filter on in ftrace + * @ops - the ops to set the filter with + * @buf - the string that holds the function filter text. + * @len - the length of the string. + * @reset - non zero to reset all filters before applying this filter. + * + * Filters denote which functions should be enabled when tracing is enabled. + * If @buf is NULL and reset is set, all functions will be enabled for tracing. + */ +void ftrace_set_global_filter(unsigned char *buf, int len, int reset) +{ + ftrace_set_regex(&global_ops, buf, len, reset, 1); +} +EXPORT_SYMBOL_GPL(ftrace_set_global_filter); + +/** + * ftrace_set_notrace - set a function to not trace in ftrace + * @ops - the ops to set the notrace filter with + * @buf - the string that holds the function notrace text. + * @len - the length of the string. + * @reset - non zero to reset all filters before applying this filter. + * + * Notrace Filters denote which functions should not be enabled when tracing + * is enabled. If @buf is NULL and reset is set, all functions will be enabled + * for tracing. + */ +void ftrace_set_global_notrace(unsigned char *buf, int len, int reset) +{ + ftrace_set_regex(&global_ops, buf, len, reset, 0); +} +EXPORT_SYMBOL_GPL(ftrace_set_global_notrace); /* * command line interface to allow users to set filters on boot up. @@ -2370,22 +3043,23 @@ static void __init set_ftrace_early_graph(char *buf) } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -static void __init set_ftrace_early_filter(char *buf, int enable) +static void __init +set_ftrace_early_filter(struct ftrace_ops *ops, char *buf, int enable) { char *func; while (buf) { func = strsep(&buf, ","); - ftrace_set_regex(func, strlen(func), 0, enable); + ftrace_set_regex(ops, func, strlen(func), 0, enable); } } static void __init set_ftrace_early_filters(void) { if (ftrace_filter_buf[0]) - set_ftrace_early_filter(ftrace_filter_buf, 1); + set_ftrace_early_filter(&global_ops, ftrace_filter_buf, 1); if (ftrace_notrace_buf[0]) - set_ftrace_early_filter(ftrace_notrace_buf, 0); + set_ftrace_early_filter(&global_ops, ftrace_notrace_buf, 0); #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (ftrace_graph_buf[0]) set_ftrace_early_graph(ftrace_graph_buf); @@ -2393,11 +3067,14 @@ static void __init set_ftrace_early_filters(void) } static int -ftrace_regex_release(struct inode *inode, struct file *file, int enable) +ftrace_regex_release(struct inode *inode, struct file *file) { struct seq_file *m = (struct seq_file *)file->private_data; struct ftrace_iterator *iter; + struct ftrace_hash **orig_hash; struct trace_parser *parser; + int filter_hash; + int ret; mutex_lock(&ftrace_regex_lock); if (file->f_mode & FMODE_READ) { @@ -2410,33 +3087,35 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) parser = &iter->parser; if (trace_parser_loaded(parser)) { parser->buffer[parser->idx] = 0; - ftrace_match_records(parser->buffer, parser->idx, enable); + ftrace_match_records(iter->hash, parser->buffer, parser->idx); } - mutex_lock(&ftrace_lock); - if (ftrace_start_up && ftrace_enabled) - ftrace_run_update_code(FTRACE_ENABLE_CALLS); - mutex_unlock(&ftrace_lock); - trace_parser_put(parser); + + if (file->f_mode & FMODE_WRITE) { + filter_hash = !!(iter->flags & FTRACE_ITER_FILTER); + + if (filter_hash) + orig_hash = &iter->ops->filter_hash; + else + orig_hash = &iter->ops->notrace_hash; + + mutex_lock(&ftrace_lock); + ret = ftrace_hash_move(iter->ops, filter_hash, + orig_hash, iter->hash); + if (!ret && (iter->ops->flags & FTRACE_OPS_FL_ENABLED) + && ftrace_enabled) + ftrace_run_update_code(FTRACE_ENABLE_CALLS); + + mutex_unlock(&ftrace_lock); + } + free_ftrace_hash(iter->hash); kfree(iter); mutex_unlock(&ftrace_regex_lock); return 0; } -static int -ftrace_filter_release(struct inode *inode, struct file *file) -{ - return ftrace_regex_release(inode, file, 1); -} - -static int -ftrace_notrace_release(struct inode *inode, struct file *file) -{ - return ftrace_regex_release(inode, file, 0); -} - static const struct file_operations ftrace_avail_fops = { .open = ftrace_avail_open, .read = seq_read, @@ -2444,8 +3123,8 @@ static const struct file_operations ftrace_avail_fops = { .release = seq_release_private, }; -static const struct file_operations ftrace_failures_fops = { - .open = ftrace_failures_open, +static const struct file_operations ftrace_enabled_fops = { + .open = ftrace_enabled_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release_private, @@ -2456,7 +3135,7 @@ static const struct file_operations ftrace_filter_fops = { .read = seq_read, .write = ftrace_filter_write, .llseek = ftrace_regex_lseek, - .release = ftrace_filter_release, + .release = ftrace_regex_release, }; static const struct file_operations ftrace_notrace_fops = { @@ -2464,7 +3143,7 @@ static const struct file_operations ftrace_notrace_fops = { .read = seq_read, .write = ftrace_notrace_write, .llseek = ftrace_regex_lseek, - .release = ftrace_notrace_release, + .release = ftrace_regex_release, }; #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -2573,9 +3252,6 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer) bool exists; int i; - if (ftrace_disabled) - return -ENODEV; - /* decode regex */ type = filter_parse_regex(buffer, strlen(buffer), &search, ¬); if (!not && *idx >= FTRACE_GRAPH_MAX_FUNCS) @@ -2584,12 +3260,18 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer) search_len = strlen(search); mutex_lock(&ftrace_lock); + + if (unlikely(ftrace_disabled)) { + mutex_unlock(&ftrace_lock); + return -ENODEV; + } + do_for_each_ftrace_rec(pg, rec) { - if (rec->flags & (FTRACE_FL_FAILED | FTRACE_FL_FREE)) + if (rec->flags & FTRACE_FL_FREE) continue; - if (ftrace_match_record(rec, search, search_len, type)) { + if (ftrace_match_record(rec, NULL, search, search_len, type)) { /* if it is in the array */ exists = false; for (i = 0; i < *idx; i++) { @@ -2679,8 +3361,8 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) trace_create_file("available_filter_functions", 0444, d_tracer, NULL, &ftrace_avail_fops); - trace_create_file("failures", 0444, - d_tracer, NULL, &ftrace_failures_fops); + trace_create_file("enabled_functions", 0444, + d_tracer, NULL, &ftrace_enabled_fops); trace_create_file("set_ftrace_filter", 0644, d_tracer, NULL, &ftrace_filter_fops); @@ -2703,7 +3385,7 @@ static int ftrace_process_locs(struct module *mod, { unsigned long *p; unsigned long addr; - unsigned long flags; + unsigned long flags = 0; /* Shut up gcc */ mutex_lock(&ftrace_lock); p = start; @@ -2720,10 +3402,19 @@ static int ftrace_process_locs(struct module *mod, ftrace_record_ip(addr); } - /* disable interrupts to prevent kstop machine */ - local_irq_save(flags); + /* + * We only need to disable interrupts on start up + * because we are modifying code that an interrupt + * may execute, and the modification is not atomic. + * But for modules, nothing runs the code we modify + * until we are finished with it, and there's no + * reason to cause large interrupt latencies while we do it. + */ + if (!mod) + local_irq_save(flags); ftrace_update_code(mod); - local_irq_restore(flags); + if (!mod) + local_irq_restore(flags); mutex_unlock(&ftrace_lock); return 0; @@ -2735,10 +3426,11 @@ void ftrace_release_mod(struct module *mod) struct dyn_ftrace *rec; struct ftrace_page *pg; + mutex_lock(&ftrace_lock); + if (ftrace_disabled) - return; + goto out_unlock; - mutex_lock(&ftrace_lock); do_for_each_ftrace_rec(pg, rec) { if (within_module_core(rec->ip, mod)) { /* @@ -2749,6 +3441,7 @@ void ftrace_release_mod(struct module *mod) ftrace_free_rec(rec); } } while_for_each_ftrace_rec(); + out_unlock: mutex_unlock(&ftrace_lock); } @@ -2835,6 +3528,10 @@ void __init ftrace_init(void) #else +static struct ftrace_ops global_ops = { + .func = ftrace_stub, +}; + static int __init ftrace_nodyn_init(void) { ftrace_enabled = 1; @@ -2845,12 +3542,47 @@ device_initcall(ftrace_nodyn_init); static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; } static inline void ftrace_startup_enable(int command) { } /* Keep as macros so we do not need to define the commands */ -# define ftrace_startup(command) do { } while (0) -# define ftrace_shutdown(command) do { } while (0) +# define ftrace_startup(ops, command) \ + ({ \ + (ops)->flags |= FTRACE_OPS_FL_ENABLED; \ + 0; \ + }) +# define ftrace_shutdown(ops, command) do { } while (0) # define ftrace_startup_sysctl() do { } while (0) # define ftrace_shutdown_sysctl() do { } while (0) + +static inline int +ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) +{ + return 1; +} + #endif /* CONFIG_DYNAMIC_FTRACE */ +static void +ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) +{ + struct ftrace_ops *op; + + if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT))) + return; + + trace_recursion_set(TRACE_INTERNAL_BIT); + /* + * Some of the ops may be dynamically allocated, + * they must be freed after a synchronize_sched(). + */ + preempt_disable_notrace(); + op = rcu_dereference_raw(ftrace_ops_list); + while (op != &ftrace_list_end) { + if (ftrace_ops_test(op, ip)) + op->func(ip, parent_ip); + op = rcu_dereference_raw(op->next); + }; + preempt_enable_notrace(); + trace_recursion_clear(TRACE_INTERNAL_BIT); +} + static void clear_ftrace_swapper(void) { struct task_struct *p; @@ -3143,19 +3875,23 @@ void ftrace_kill(void) */ int register_ftrace_function(struct ftrace_ops *ops) { - int ret; - - if (unlikely(ftrace_disabled)) - return -1; + int ret = -1; mutex_lock(&ftrace_lock); + if (unlikely(ftrace_disabled)) + goto out_unlock; + ret = __register_ftrace_function(ops); - ftrace_startup(0); + if (!ret) + ret = ftrace_startup(ops, 0); + + out_unlock: mutex_unlock(&ftrace_lock); return ret; } +EXPORT_SYMBOL_GPL(register_ftrace_function); /** * unregister_ftrace_function - unregister a function for profiling. @@ -3169,25 +3905,27 @@ int unregister_ftrace_function(struct ftrace_ops *ops) mutex_lock(&ftrace_lock); ret = __unregister_ftrace_function(ops); - ftrace_shutdown(0); + if (!ret) + ftrace_shutdown(ops, 0); mutex_unlock(&ftrace_lock); return ret; } +EXPORT_SYMBOL_GPL(unregister_ftrace_function); int ftrace_enable_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret; - - if (unlikely(ftrace_disabled)) - return -ENODEV; + int ret = -ENODEV; mutex_lock(&ftrace_lock); - ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (unlikely(ftrace_disabled)) + goto out; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) goto out; @@ -3199,11 +3937,11 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, ftrace_startup_sysctl(); /* we are starting ftrace again */ - if (ftrace_list != &ftrace_list_end) { - if (ftrace_list->next == &ftrace_list_end) - ftrace_trace_function = ftrace_list->func; + if (ftrace_ops_list != &ftrace_list_end) { + if (ftrace_ops_list->next == &ftrace_list_end) + ftrace_trace_function = ftrace_ops_list->func; else - ftrace_trace_function = ftrace_list_func; + ftrace_trace_function = ftrace_ops_list_func; } } else { @@ -3392,7 +4130,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc, ftrace_graph_return = retfunc; ftrace_graph_entry = entryfunc; - ftrace_startup(FTRACE_START_FUNC_RET); + ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET); out: mutex_unlock(&ftrace_lock); @@ -3409,7 +4147,7 @@ void unregister_ftrace_graph(void) ftrace_graph_active--; ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub; ftrace_graph_entry = ftrace_graph_entry_stub; - ftrace_shutdown(FTRACE_STOP_FUNC_RET); + ftrace_shutdown(&global_ops, FTRACE_STOP_FUNC_RET); unregister_pm_notifier(&ftrace_suspend_notifier); unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 0ef7b4b2a1f..731201bf4ac 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -997,15 +997,21 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) { struct buffer_page *bpage, *tmp; - unsigned long addr; LIST_HEAD(pages); unsigned i; WARN_ON(!nr_pages); for (i = 0; i < nr_pages; i++) { + struct page *page; + /* + * __GFP_NORETRY flag makes sure that the allocation fails + * gracefully without invoking oom-killer and the system is + * not destabilized. + */ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), - GFP_KERNEL, cpu_to_node(cpu_buffer->cpu)); + GFP_KERNEL | __GFP_NORETRY, + cpu_to_node(cpu_buffer->cpu)); if (!bpage) goto free_pages; @@ -1013,10 +1019,11 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, list_add(&bpage->list, &pages); - addr = __get_free_page(GFP_KERNEL); - if (!addr) + page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), + GFP_KERNEL | __GFP_NORETRY, 0); + if (!page) goto free_pages; - bpage->page = (void *)addr; + bpage->page = page_address(page); rb_init_page(bpage->page); } @@ -1045,7 +1052,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; struct buffer_page *bpage; - unsigned long addr; + struct page *page; int ret; cpu_buffer = kzalloc_node(ALIGN(sizeof(*cpu_buffer), cache_line_size()), @@ -1067,10 +1074,10 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) rb_check_bpage(cpu_buffer, bpage); cpu_buffer->reader_page = bpage; - addr = __get_free_page(GFP_KERNEL); - if (!addr) + page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0); + if (!page) goto fail_free_reader; - bpage->page = (void *)addr; + bpage->page = page_address(page); rb_init_page(bpage->page); INIT_LIST_HEAD(&cpu_buffer->reader_page->list); @@ -1314,7 +1321,6 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) unsigned nr_pages, rm_pages, new_pages; struct buffer_page *bpage, *tmp; unsigned long buffer_size; - unsigned long addr; LIST_HEAD(pages); int i, cpu; @@ -1375,16 +1381,24 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) for_each_buffer_cpu(buffer, cpu) { for (i = 0; i < new_pages; i++) { + struct page *page; + /* + * __GFP_NORETRY flag makes sure that the allocation + * fails gracefully without invoking oom-killer and + * the system is not destabilized. + */ bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), - GFP_KERNEL, cpu_to_node(cpu)); + GFP_KERNEL | __GFP_NORETRY, + cpu_to_node(cpu)); if (!bpage) goto free_pages; list_add(&bpage->list, &pages); - addr = __get_free_page(GFP_KERNEL); - if (!addr) + page = alloc_pages_node(cpu_to_node(cpu), + GFP_KERNEL | __GFP_NORETRY, 0); + if (!page) goto free_pages; - bpage->page = (void *)addr; + bpage->page = page_address(page); rb_init_page(bpage->page); } } @@ -2216,7 +2230,7 @@ static noinline void trace_recursive_fail(void) printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:" "HC[%lu]:SC[%lu]:NMI[%lu]\n", - current->trace_recursion, + trace_recursion_buffer(), hardirq_count() >> HARDIRQ_SHIFT, softirq_count() >> SOFTIRQ_SHIFT, in_nmi()); @@ -2226,9 +2240,9 @@ static noinline void trace_recursive_fail(void) static inline int trace_recursive_lock(void) { - current->trace_recursion++; + trace_recursion_inc(); - if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH)) + if (likely(trace_recursion_buffer() < TRACE_RECURSIVE_DEPTH)) return 0; trace_recursive_fail(); @@ -2238,9 +2252,9 @@ static inline int trace_recursive_lock(void) static inline void trace_recursive_unlock(void) { - WARN_ON_ONCE(!current->trace_recursion); + WARN_ON_ONCE(!trace_recursion_buffer()); - current->trace_recursion--; + trace_recursion_dec(); } #else @@ -3730,16 +3744,17 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); * Returns: * The page allocated, or NULL on error. */ -void *ring_buffer_alloc_read_page(struct ring_buffer *buffer) +void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu) { struct buffer_data_page *bpage; - unsigned long addr; + struct page *page; - addr = __get_free_page(GFP_KERNEL); - if (!addr) + page = alloc_pages_node(cpu_to_node(cpu), + GFP_KERNEL | __GFP_NORETRY, 0); + if (!page) return NULL; - bpage = (void *)addr; + bpage = page_address(page); rb_init_page(bpage); @@ -3978,20 +3993,11 @@ rb_simple_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { unsigned long *p = filp->private_data; - char buf[64]; unsigned long val; int ret; - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - - ret = strict_strtoul(buf, 10, &val); - if (ret < 0) + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) return ret; if (val) diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index 302f8a61463..a5457d577b9 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -106,7 +106,7 @@ static enum event_status read_page(int cpu) int inc; int i; - bpage = ring_buffer_alloc_read_page(buffer); + bpage = ring_buffer_alloc_read_page(buffer, cpu); if (!bpage) return EVENT_DROPPED; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d38c16a06a6..e5df02c69b1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -343,26 +343,27 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | static int trace_stop_count; static DEFINE_SPINLOCK(tracing_start_lock); +static void wakeup_work_handler(struct work_struct *work) +{ + wake_up(&trace_wait); +} + +static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler); + /** * trace_wake_up - wake up tasks waiting for trace input * - * Simply wakes up any task that is blocked on the trace_wait - * queue. These is used with trace_poll for tasks polling the trace. + * Schedules a delayed work to wake up any task that is blocked on the + * trace_wait queue. These is used with trace_poll for tasks polling the + * trace. */ void trace_wake_up(void) { - int cpu; + const unsigned long delay = msecs_to_jiffies(2); if (trace_flags & TRACE_ITER_BLOCK) return; - /* - * The runqueue_is_locked() can fail, but this is the best we - * have for now: - */ - cpu = get_cpu(); - if (!runqueue_is_locked(cpu)) - wake_up(&trace_wait); - put_cpu(); + schedule_delayed_work(&wakeup_work, delay); } static int __init set_buf_size(char *str) @@ -424,6 +425,7 @@ static const char *trace_options[] = { "graph-time", "record-cmd", "overwrite", + "disable_on_free", NULL }; @@ -1110,6 +1112,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; + entry->padding = 0; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | @@ -1190,6 +1193,18 @@ void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer, } EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit); +void trace_nowake_buffer_unlock_commit_regs(struct ring_buffer *buffer, + struct ring_buffer_event *event, + unsigned long flags, int pc, + struct pt_regs *regs) +{ + ring_buffer_unlock_commit(buffer, event); + + ftrace_trace_stack_regs(buffer, flags, 0, pc, regs); + ftrace_trace_userstack(buffer, flags, pc); +} +EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit_regs); + void trace_current_buffer_discard_commit(struct ring_buffer *buffer, struct ring_buffer_event *event) { @@ -1233,30 +1248,103 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data, } #ifdef CONFIG_STACKTRACE + +#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long)) +struct ftrace_stack { + unsigned long calls[FTRACE_STACK_MAX_ENTRIES]; +}; + +static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack); +static DEFINE_PER_CPU(int, ftrace_stack_reserve); + static void __ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, - int skip, int pc) + int skip, int pc, struct pt_regs *regs) { struct ftrace_event_call *call = &event_kernel_stack; struct ring_buffer_event *event; struct stack_entry *entry; struct stack_trace trace; + int use_stack; + int size = FTRACE_STACK_ENTRIES; + + trace.nr_entries = 0; + trace.skip = skip; + + /* + * Since events can happen in NMIs there's no safe way to + * use the per cpu ftrace_stacks. We reserve it and if an interrupt + * or NMI comes in, it will just have to use the default + * FTRACE_STACK_SIZE. + */ + preempt_disable_notrace(); + + use_stack = ++__get_cpu_var(ftrace_stack_reserve); + /* + * We don't need any atomic variables, just a barrier. + * If an interrupt comes in, we don't care, because it would + * have exited and put the counter back to what we want. + * We just need a barrier to keep gcc from moving things + * around. + */ + barrier(); + if (use_stack == 1) { + trace.entries = &__get_cpu_var(ftrace_stack).calls[0]; + trace.max_entries = FTRACE_STACK_MAX_ENTRIES; + + if (regs) + save_stack_trace_regs(regs, &trace); + else + save_stack_trace(&trace); + + if (trace.nr_entries > size) + size = trace.nr_entries; + } else + /* From now on, use_stack is a boolean */ + use_stack = 0; + + size *= sizeof(unsigned long); event = trace_buffer_lock_reserve(buffer, TRACE_STACK, - sizeof(*entry), flags, pc); + sizeof(*entry) + size, flags, pc); if (!event) - return; - entry = ring_buffer_event_data(event); - memset(&entry->caller, 0, sizeof(entry->caller)); + goto out; + entry = ring_buffer_event_data(event); - trace.nr_entries = 0; - trace.max_entries = FTRACE_STACK_ENTRIES; - trace.skip = skip; - trace.entries = entry->caller; + memset(&entry->caller, 0, size); + + if (use_stack) + memcpy(&entry->caller, trace.entries, + trace.nr_entries * sizeof(unsigned long)); + else { + trace.max_entries = FTRACE_STACK_ENTRIES; + trace.entries = entry->caller; + if (regs) + save_stack_trace_regs(regs, &trace); + else + save_stack_trace(&trace); + } + + entry->size = trace.nr_entries; - save_stack_trace(&trace); if (!filter_check_discard(call, entry, buffer, event)) ring_buffer_unlock_commit(buffer, event); + + out: + /* Again, don't let gcc optimize things here */ + barrier(); + __get_cpu_var(ftrace_stack_reserve)--; + preempt_enable_notrace(); + +} + +void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags, + int skip, int pc, struct pt_regs *regs) +{ + if (!(trace_flags & TRACE_ITER_STACKTRACE)) + return; + + __ftrace_trace_stack(buffer, flags, skip, pc, regs); } void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, @@ -1265,13 +1353,13 @@ void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, if (!(trace_flags & TRACE_ITER_STACKTRACE)) return; - __ftrace_trace_stack(buffer, flags, skip, pc); + __ftrace_trace_stack(buffer, flags, skip, pc, NULL); } void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc) { - __ftrace_trace_stack(tr->buffer, flags, skip, pc); + __ftrace_trace_stack(tr->buffer, flags, skip, pc, NULL); } /** @@ -1287,7 +1375,7 @@ void trace_dump_stack(void) local_save_flags(flags); /* skipping 3 traces, seems to get us at the caller of this function */ - __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count()); + __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count(), NULL); } static DEFINE_PER_CPU(int, user_stack_count); @@ -1535,7 +1623,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, ftrace_enable_cpu(); - return event ? ring_buffer_event_data(event) : NULL; + if (event) { + iter->ent_size = ring_buffer_event_length(event); + return ring_buffer_event_data(event); + } + iter->ent_size = 0; + return NULL; } static struct trace_entry * @@ -2013,9 +2106,10 @@ enum print_line_t print_trace_line(struct trace_iterator *iter) { enum print_line_t ret; - if (iter->lost_events) - trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n", - iter->cpu, iter->lost_events); + if (iter->lost_events && + !trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n", + iter->cpu, iter->lost_events)) + return TRACE_TYPE_PARTIAL_LINE; if (iter->trace && iter->trace->print_line) { ret = iter->trace->print_line(iter); @@ -2049,6 +2143,9 @@ void trace_default_header(struct seq_file *m) { struct trace_iterator *iter = m->private; + if (!(trace_flags & TRACE_ITER_CONTEXT_INFO)) + return; + if (iter->iter_flags & TRACE_FILE_LAT_FMT) { /* print nothing if the buffers are empty */ if (trace_empty(iter)) @@ -2699,20 +2796,11 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; - char buf[64]; unsigned long val; int ret; - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - - ret = strict_strtoul(buf, 10, &val); - if (ret < 0) + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) return ret; val = !!val; @@ -2765,7 +2853,7 @@ int tracer_init(struct tracer *t, struct trace_array *tr) return t->init(tr); } -static int tracing_resize_ring_buffer(unsigned long size) +static int __tracing_resize_ring_buffer(unsigned long size) { int ret; @@ -2817,6 +2905,41 @@ static int tracing_resize_ring_buffer(unsigned long size) return ret; } +static ssize_t tracing_resize_ring_buffer(unsigned long size) +{ + int cpu, ret = size; + + mutex_lock(&trace_types_lock); + + tracing_stop(); + + /* disable all cpu buffers */ + for_each_tracing_cpu(cpu) { + if (global_trace.data[cpu]) + atomic_inc(&global_trace.data[cpu]->disabled); + if (max_tr.data[cpu]) + atomic_inc(&max_tr.data[cpu]->disabled); + } + + if (size != global_trace.entries) + ret = __tracing_resize_ring_buffer(size); + + if (ret < 0) + ret = -ENOMEM; + + for_each_tracing_cpu(cpu) { + if (global_trace.data[cpu]) + atomic_dec(&global_trace.data[cpu]->disabled); + if (max_tr.data[cpu]) + atomic_dec(&max_tr.data[cpu]->disabled); + } + + tracing_start(); + mutex_unlock(&trace_types_lock); + + return ret; +} + /** * tracing_update_buffers - used by tracing facility to expand ring buffers @@ -2834,7 +2957,7 @@ int tracing_update_buffers(void) mutex_lock(&trace_types_lock); if (!ring_buffer_expanded) - ret = tracing_resize_ring_buffer(trace_buf_size); + ret = __tracing_resize_ring_buffer(trace_buf_size); mutex_unlock(&trace_types_lock); return ret; @@ -2858,7 +2981,7 @@ static int tracing_set_tracer(const char *buf) mutex_lock(&trace_types_lock); if (!ring_buffer_expanded) { - ret = tracing_resize_ring_buffer(trace_buf_size); + ret = __tracing_resize_ring_buffer(trace_buf_size); if (ret < 0) goto out; ret = 0; @@ -2964,20 +3087,11 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { unsigned long *ptr = filp->private_data; - char buf[64]; unsigned long val; int ret; - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - - ret = strict_strtoul(buf, 10, &val); - if (ret < 0) + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) return ret; *ptr = val * 1000; @@ -3229,6 +3343,14 @@ waitagain: if (iter->seq.len >= cnt) break; + + /* + * Setting the full flag means we reached the trace_seq buffer + * size and we should leave by partial output condition above. + * One of the trace_seq_* functions is not used properly. + */ + WARN_ONCE(iter->seq.full, "full flag set for trace type %d", + iter->ent->type); } trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); @@ -3424,67 +3546,54 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { unsigned long val; - char buf[64]; - int ret, cpu; - - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; + int ret; - ret = strict_strtoul(buf, 10, &val); - if (ret < 0) + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) return ret; /* must have at least 1 entry */ if (!val) return -EINVAL; - mutex_lock(&trace_types_lock); - - tracing_stop(); - - /* disable all cpu buffers */ - for_each_tracing_cpu(cpu) { - if (global_trace.data[cpu]) - atomic_inc(&global_trace.data[cpu]->disabled); - if (max_tr.data[cpu]) - atomic_inc(&max_tr.data[cpu]->disabled); - } - /* value is in KB */ val <<= 10; - if (val != global_trace.entries) { - ret = tracing_resize_ring_buffer(val); - if (ret < 0) { - cnt = ret; - goto out; - } - } + ret = tracing_resize_ring_buffer(val); + if (ret < 0) + return ret; *ppos += cnt; - /* If check pages failed, return ENOMEM */ - if (tracing_disabled) - cnt = -ENOMEM; - out: - for_each_tracing_cpu(cpu) { - if (global_trace.data[cpu]) - atomic_dec(&global_trace.data[cpu]->disabled); - if (max_tr.data[cpu]) - atomic_dec(&max_tr.data[cpu]->disabled); - } + return cnt; +} - tracing_start(); - mutex_unlock(&trace_types_lock); +static ssize_t +tracing_free_buffer_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + /* + * There is no need to read what the user has written, this function + * is just to make sure that there is no error when "echo" is used + */ + + *ppos += cnt; return cnt; } +static int +tracing_free_buffer_release(struct inode *inode, struct file *filp) +{ + /* disable tracing ? */ + if (trace_flags & TRACE_ITER_STOP_ON_FREE) + tracing_off(); + /* resize the ring buffer to 0 */ + tracing_resize_ring_buffer(0); + + return 0; +} + static int mark_printk(const char *fmt, ...) { int ret; @@ -3630,6 +3739,11 @@ static const struct file_operations tracing_entries_fops = { .llseek = generic_file_llseek, }; +static const struct file_operations tracing_free_buffer_fops = { + .write = tracing_free_buffer_write, + .release = tracing_free_buffer_release, +}; + static const struct file_operations tracing_mark_fops = { .open = tracing_open_generic, .write = tracing_mark_write, @@ -3686,7 +3800,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, return 0; if (!info->spare) - info->spare = ring_buffer_alloc_read_page(info->tr->buffer); + info->spare = ring_buffer_alloc_read_page(info->tr->buffer, info->cpu); if (!info->spare) return -ENOMEM; @@ -3843,7 +3957,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, ref->ref = 1; ref->buffer = info->tr->buffer; - ref->page = ring_buffer_alloc_read_page(ref->buffer); + ref->page = ring_buffer_alloc_read_page(ref->buffer, info->cpu); if (!ref->page) { kfree(ref); break; @@ -3852,8 +3966,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, r = ring_buffer_read_page(ref->buffer, &ref->page, len, info->cpu, 1); if (r < 0) { - ring_buffer_free_read_page(ref->buffer, - ref->page); + ring_buffer_free_read_page(ref->buffer, ref->page); kfree(ref); break; } @@ -4089,19 +4202,10 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, { struct trace_option_dentry *topt = filp->private_data; unsigned long val; - char buf[64]; int ret; - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - - ret = strict_strtoul(buf, 10, &val); - if (ret < 0) + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) return ret; if (val != 0 && val != 1) @@ -4149,20 +4253,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { long index = (long)filp->private_data; - char buf[64]; unsigned long val; int ret; - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - - ret = strict_strtoul(buf, 10, &val); - if (ret < 0) + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) return ret; if (val != 0 && val != 1) @@ -4355,6 +4450,9 @@ static __init int tracer_init_debugfs(void) trace_create_file("buffer_size_kb", 0644, d_tracer, &global_trace, &tracing_entries_fops); + trace_create_file("free_buffer", 0644, d_tracer, + &global_trace, &tracing_free_buffer_fops); + trace_create_file("trace_marker", 0220, d_tracer, NULL, &tracing_mark_fops); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 5e9dfc6286d..616846bcfee 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -2,7 +2,7 @@ #define _LINUX_KERNEL_TRACE_H #include <linux/fs.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <linux/sched.h> #include <linux/clocksource.h> #include <linux/ring_buffer.h> @@ -278,6 +278,29 @@ struct tracer { }; +/* Only current can touch trace_recursion */ +#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0) +#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0) + +/* Ring buffer has the 10 LSB bits to count */ +#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff) + +/* for function tracing recursion */ +#define TRACE_INTERNAL_BIT (1<<11) +#define TRACE_GLOBAL_BIT (1<<12) +/* + * Abuse of the trace_recursion. + * As we need a way to maintain state if we are tracing the function + * graph in irq because we want to trace a particular function that + * was called in irq context but we have irq tracing off. Since this + * can only be modified by current, we can reuse trace_recursion. + */ +#define TRACE_IRQ_BIT (1<<13) + +#define trace_recursion_set(bit) do { (current)->trace_recursion |= (bit); } while (0) +#define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(bit); } while (0) +#define trace_recursion_test(bit) ((current)->trace_recursion & (bit)) + #define TRACE_PIPE_ALL_CPU -1 int tracer_init(struct tracer *t, struct trace_array *tr); @@ -389,6 +412,9 @@ void update_max_tr_single(struct trace_array *tr, void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags, int skip, int pc); +void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags, + int skip, int pc, struct pt_regs *regs); + void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc); @@ -400,6 +426,12 @@ static inline void ftrace_trace_stack(struct ring_buffer *buffer, { } +static inline void ftrace_trace_stack_regs(struct ring_buffer *buffer, + unsigned long flags, int skip, + int pc, struct pt_regs *regs) +{ +} + static inline void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) { @@ -419,6 +451,8 @@ extern void trace_find_cmdline(int pid, char comm[]); extern unsigned long ftrace_update_tot_cnt; #define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func extern int DYN_FTRACE_TEST_NAME(void); +#define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2 +extern int DYN_FTRACE_TEST_NAME2(void); #endif extern int ring_buffer_expanded; @@ -505,8 +539,18 @@ static inline int ftrace_graph_addr(unsigned long addr) return 1; for (i = 0; i < ftrace_graph_count; i++) { - if (addr == ftrace_graph_funcs[i]) + if (addr == ftrace_graph_funcs[i]) { + /* + * If no irqs are to be traced, but a set_graph_function + * is set, and called by an interrupt handler, we still + * want to trace it. + */ + if (in_irq()) + trace_recursion_set(TRACE_IRQ_BIT); + else + trace_recursion_clear(TRACE_IRQ_BIT); return 1; + } } return 0; @@ -607,6 +651,7 @@ enum trace_iterator_flags { TRACE_ITER_GRAPH_TIME = 0x80000, TRACE_ITER_RECORD_CMD = 0x100000, TRACE_ITER_OVERWRITE = 0x200000, + TRACE_ITER_STOP_ON_FREE = 0x400000, }; /* @@ -675,6 +720,7 @@ struct event_subsystem { struct dentry *entry; struct event_filter *filter; int nr_events; + int ref_count; }; #define FILTER_PRED_INVALID ((unsigned short)-1) diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index e32744c84d9..93365907f21 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -161,7 +161,8 @@ FTRACE_ENTRY(kernel_stack, stack_entry, TRACE_STACK, F_STRUCT( - __array( unsigned long, caller, FTRACE_STACK_ENTRIES ) + __field( int, size ) + __dynamic_array(unsigned long, caller ) ), F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n" diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e88f74fe1d4..581876f9f38 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -116,6 +116,7 @@ static int trace_define_common_fields(void) __common_field(unsigned char, flags); __common_field(unsigned char, preempt_count); __common_field(int, pid); + __common_field(int, padding); return ret; } @@ -243,6 +244,35 @@ static void ftrace_clear_events(void) mutex_unlock(&event_mutex); } +static void __put_system(struct event_subsystem *system) +{ + struct event_filter *filter = system->filter; + + WARN_ON_ONCE(system->ref_count == 0); + if (--system->ref_count) + return; + + if (filter) { + kfree(filter->filter_string); + kfree(filter); + } + kfree(system->name); + kfree(system); +} + +static void __get_system(struct event_subsystem *system) +{ + WARN_ON_ONCE(system->ref_count == 0); + system->ref_count++; +} + +static void put_system(struct event_subsystem *system) +{ + mutex_lock(&event_mutex); + __put_system(system); + mutex_unlock(&event_mutex); +} + /* * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events. */ @@ -485,20 +515,11 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct ftrace_event_call *call = filp->private_data; - char buf[64]; unsigned long val; int ret; - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - - ret = strict_strtoul(buf, 10, &val); - if (ret < 0) + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) return ret; ret = tracing_update_buffers(); @@ -527,7 +548,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { const char set_to_char[4] = { '?', '0', '1', 'X' }; - const char *system = filp->private_data; + struct event_subsystem *system = filp->private_data; struct ftrace_event_call *call; char buf[2]; int set = 0; @@ -538,7 +559,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, if (!call->name || !call->class || !call->class->reg) continue; - if (system && strcmp(call->class->system, system) != 0) + if (system && strcmp(call->class->system, system->name) != 0) continue; /* @@ -568,21 +589,13 @@ static ssize_t system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - const char *system = filp->private_data; + struct event_subsystem *system = filp->private_data; + const char *name = NULL; unsigned long val; - char buf[64]; ssize_t ret; - if (cnt >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - - ret = strict_strtoul(buf, 10, &val); - if (ret < 0) + ret = kstrtoul_from_user(ubuf, cnt, 10, &val); + if (ret) return ret; ret = tracing_update_buffers(); @@ -592,7 +605,14 @@ system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, if (val != 0 && val != 1) return -EINVAL; - ret = __ftrace_set_clr_event(NULL, system, NULL, val); + /* + * Opening of "enable" adds a ref count to system, + * so the name is safe to use. + */ + if (system) + name = system->name; + + ret = __ftrace_set_clr_event(NULL, name, NULL, val); if (ret) goto out; @@ -825,6 +845,52 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, return cnt; } +static LIST_HEAD(event_subsystems); + +static int subsystem_open(struct inode *inode, struct file *filp) +{ + struct event_subsystem *system = NULL; + int ret; + + if (!inode->i_private) + goto skip_search; + + /* Make sure the system still exists */ + mutex_lock(&event_mutex); + list_for_each_entry(system, &event_subsystems, list) { + if (system == inode->i_private) { + /* Don't open systems with no events */ + if (!system->nr_events) { + system = NULL; + break; + } + __get_system(system); + break; + } + } + mutex_unlock(&event_mutex); + + if (system != inode->i_private) + return -ENODEV; + + skip_search: + ret = tracing_open_generic(inode, filp); + if (ret < 0 && system) + put_system(system); + + return ret; +} + +static int subsystem_release(struct inode *inode, struct file *file) +{ + struct event_subsystem *system = inode->i_private; + + if (system) + put_system(system); + + return 0; +} + static ssize_t subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -962,17 +1028,19 @@ static const struct file_operations ftrace_event_filter_fops = { }; static const struct file_operations ftrace_subsystem_filter_fops = { - .open = tracing_open_generic, + .open = subsystem_open, .read = subsystem_filter_read, .write = subsystem_filter_write, .llseek = default_llseek, + .release = subsystem_release, }; static const struct file_operations ftrace_system_enable_fops = { - .open = tracing_open_generic, + .open = subsystem_open, .read = system_enable_read, .write = system_enable_write, .llseek = default_llseek, + .release = subsystem_release, }; static const struct file_operations ftrace_show_header_fops = { @@ -1001,8 +1069,6 @@ static struct dentry *event_trace_events_dir(void) return d_events; } -static LIST_HEAD(event_subsystems); - static struct dentry * event_subsystem_dir(const char *name, struct dentry *d_events) { @@ -1012,6 +1078,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events) /* First see if we did not already create this dir */ list_for_each_entry(system, &event_subsystems, list) { if (strcmp(system->name, name) == 0) { + __get_system(system); system->nr_events++; return system->entry; } @@ -1034,6 +1101,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events) } system->nr_events = 1; + system->ref_count = 1; system->name = kstrdup(name, GFP_KERNEL); if (!system->name) { debugfs_remove(system->entry); @@ -1061,8 +1129,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events) "'%s/filter' entry\n", name); } - trace_create_file("enable", 0644, system->entry, - (void *)system->name, + trace_create_file("enable", 0644, system->entry, system, &ftrace_system_enable_fops); return system->entry; @@ -1183,16 +1250,9 @@ static void remove_subsystem_dir(const char *name) list_for_each_entry(system, &event_subsystems, list) { if (strcmp(system->name, name) == 0) { if (!--system->nr_events) { - struct event_filter *filter = system->filter; - debugfs_remove_recursive(system->entry); list_del(&system->list); - if (filter) { - kfree(filter->filter_string); - kfree(filter); - } - kfree(system->name); - kfree(system); + __put_system(system); } break; } @@ -1656,7 +1716,12 @@ static struct ftrace_ops trace_ops __initdata = static __init void event_trace_self_test_with_function(void) { - register_ftrace_function(&trace_ops); + int ret; + ret = register_ftrace_function(&trace_ops); + if (WARN_ON(ret < 0)) { + pr_info("Failed to enable function tracer for event tests\n"); + return; + } pr_info("Running tests again, along with the function tracer\n"); event_trace_self_tests(); unregister_ftrace_function(&trace_ops); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 8008ddcfbf2..256764ecccd 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1886,6 +1886,12 @@ int apply_subsystem_event_filter(struct event_subsystem *system, mutex_lock(&event_mutex); + /* Make sure the system still has events */ + if (!system->nr_events) { + err = -ENODEV; + goto out_unlock; + } + if (!strcmp(strstrip(filter_string), "0")) { filter_free_subsystem_preds(system); remove_filter_string(system->filter); diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 16aee4d44e8..c7b0c6a7db0 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -149,11 +149,13 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = function_trace_call, + .flags = FTRACE_OPS_FL_GLOBAL, }; static struct ftrace_ops trace_stack_ops __read_mostly = { .func = function_stack_trace_call, + .flags = FTRACE_OPS_FL_GLOBAL, }; /* Our two options */ @@ -322,7 +324,8 @@ ftrace_trace_onoff_unreg(char *glob, char *cmd, char *param) } static int -ftrace_trace_onoff_callback(char *glob, char *cmd, char *param, int enable) +ftrace_trace_onoff_callback(struct ftrace_hash *hash, + char *glob, char *cmd, char *param, int enable) { struct ftrace_probe_ops *ops; void *count = (void *)-1; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 962cdb24ed8..a7d2a4c653d 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -74,6 +74,20 @@ static struct tracer_flags tracer_flags = { static struct trace_array *graph_array; +/* + * DURATION column is being also used to display IRQ signs, + * following values are used by print_graph_irq and others + * to fill in space into DURATION column. + */ +enum { + DURATION_FILL_FULL = -1, + DURATION_FILL_START = -2, + DURATION_FILL_END = -3, +}; + +static enum print_line_t +print_graph_duration(unsigned long long duration, struct trace_seq *s, + u32 flags); /* Add a function return address to the trace stack on thread info.*/ int @@ -213,7 +227,7 @@ int __trace_graph_entry(struct trace_array *tr, static inline int ftrace_graph_ignore_irqs(void) { - if (!ftrace_graph_skip_irqs) + if (!ftrace_graph_skip_irqs || trace_recursion_test(TRACE_IRQ_BIT)) return 0; return in_irq(); @@ -577,32 +591,6 @@ get_return_for_leaf(struct trace_iterator *iter, return next; } -/* Signal a overhead of time execution to the output */ -static int -print_graph_overhead(unsigned long long duration, struct trace_seq *s, - u32 flags) -{ - /* If duration disappear, we don't need anything */ - if (!(flags & TRACE_GRAPH_PRINT_DURATION)) - return 1; - - /* Non nested entry or return */ - if (duration == -1) - return trace_seq_printf(s, " "); - - if (flags & TRACE_GRAPH_PRINT_OVERHEAD) { - /* Duration exceeded 100 msecs */ - if (duration > 100000ULL) - return trace_seq_printf(s, "! "); - - /* Duration exceeded 10 msecs */ - if (duration > 10000ULL) - return trace_seq_printf(s, "+ "); - } - - return trace_seq_printf(s, " "); -} - static int print_graph_abs_time(u64 t, struct trace_seq *s) { unsigned long usecs_rem; @@ -625,34 +613,36 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr, addr >= (unsigned long)__irqentry_text_end) return TRACE_TYPE_UNHANDLED; - /* Absolute time */ - if (flags & TRACE_GRAPH_PRINT_ABS_TIME) { - ret = print_graph_abs_time(iter->ts, s); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } + if (trace_flags & TRACE_ITER_CONTEXT_INFO) { + /* Absolute time */ + if (flags & TRACE_GRAPH_PRINT_ABS_TIME) { + ret = print_graph_abs_time(iter->ts, s); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } - /* Cpu */ - if (flags & TRACE_GRAPH_PRINT_CPU) { - ret = print_graph_cpu(s, cpu); - if (ret == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; - } + /* Cpu */ + if (flags & TRACE_GRAPH_PRINT_CPU) { + ret = print_graph_cpu(s, cpu); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + } - /* Proc */ - if (flags & TRACE_GRAPH_PRINT_PROC) { - ret = print_graph_proc(s, pid); - if (ret == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; - ret = trace_seq_printf(s, " | "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; + /* Proc */ + if (flags & TRACE_GRAPH_PRINT_PROC) { + ret = print_graph_proc(s, pid); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + ret = trace_seq_printf(s, " | "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } } /* No overhead */ - ret = print_graph_overhead(-1, s, flags); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; + ret = print_graph_duration(DURATION_FILL_START, s, flags); + if (ret != TRACE_TYPE_HANDLED) + return ret; if (type == TRACE_GRAPH_ENT) ret = trace_seq_printf(s, "==========>"); @@ -662,9 +652,10 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr, if (!ret) return TRACE_TYPE_PARTIAL_LINE; - /* Don't close the duration column if haven't one */ - if (flags & TRACE_GRAPH_PRINT_DURATION) - trace_seq_printf(s, " |"); + ret = print_graph_duration(DURATION_FILL_END, s, flags); + if (ret != TRACE_TYPE_HANDLED) + return ret; + ret = trace_seq_printf(s, "\n"); if (!ret) @@ -716,9 +707,49 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s) } static enum print_line_t -print_graph_duration(unsigned long long duration, struct trace_seq *s) +print_graph_duration(unsigned long long duration, struct trace_seq *s, + u32 flags) { - int ret; + int ret = -1; + + if (!(flags & TRACE_GRAPH_PRINT_DURATION) || + !(trace_flags & TRACE_ITER_CONTEXT_INFO)) + return TRACE_TYPE_HANDLED; + + /* No real adata, just filling the column with spaces */ + switch (duration) { + case DURATION_FILL_FULL: + ret = trace_seq_printf(s, " | "); + return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; + case DURATION_FILL_START: + ret = trace_seq_printf(s, " "); + return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; + case DURATION_FILL_END: + ret = trace_seq_printf(s, " |"); + return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; + } + + /* Signal a overhead of time execution to the output */ + if (flags & TRACE_GRAPH_PRINT_OVERHEAD) { + /* Duration exceeded 100 msecs */ + if (duration > 100000ULL) + ret = trace_seq_printf(s, "! "); + /* Duration exceeded 10 msecs */ + else if (duration > 10000ULL) + ret = trace_seq_printf(s, "+ "); + } + + /* + * The -1 means we either did not exceed the duration tresholds + * or we dont want to print out the overhead. Either way we need + * to fill out the space. + */ + if (ret == -1) + ret = trace_seq_printf(s, " "); + + /* Catching here any failure happenned above */ + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; ret = trace_print_graph_duration(duration, s); if (ret != TRACE_TYPE_HANDLED) @@ -767,18 +798,11 @@ print_graph_entry_leaf(struct trace_iterator *iter, cpu_data->enter_funcs[call->depth] = 0; } - /* Overhead */ - ret = print_graph_overhead(duration, s, flags); - if (!ret) + /* Overhead and duration */ + ret = print_graph_duration(duration, s, flags); + if (ret == TRACE_TYPE_PARTIAL_LINE) return TRACE_TYPE_PARTIAL_LINE; - /* Duration */ - if (flags & TRACE_GRAPH_PRINT_DURATION) { - ret = print_graph_duration(duration, s); - if (ret == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; - } - /* Function */ for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) { ret = trace_seq_printf(s, " "); @@ -815,17 +839,10 @@ print_graph_entry_nested(struct trace_iterator *iter, cpu_data->enter_funcs[call->depth] = call->func; } - /* No overhead */ - ret = print_graph_overhead(-1, s, flags); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - /* No time */ - if (flags & TRACE_GRAPH_PRINT_DURATION) { - ret = trace_seq_printf(s, " | "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } + ret = print_graph_duration(DURATION_FILL_FULL, s, flags); + if (ret != TRACE_TYPE_HANDLED) + return ret; /* Function */ for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) { @@ -865,6 +882,9 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s, return TRACE_TYPE_PARTIAL_LINE; } + if (!(trace_flags & TRACE_ITER_CONTEXT_INFO)) + return 0; + /* Absolute time */ if (flags & TRACE_GRAPH_PRINT_ABS_TIME) { ret = print_graph_abs_time(iter->ts, s); @@ -1078,18 +1098,11 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, if (print_graph_prologue(iter, s, 0, 0, flags)) return TRACE_TYPE_PARTIAL_LINE; - /* Overhead */ - ret = print_graph_overhead(duration, s, flags); - if (!ret) + /* Overhead and duration */ + ret = print_graph_duration(duration, s, flags); + if (ret == TRACE_TYPE_PARTIAL_LINE) return TRACE_TYPE_PARTIAL_LINE; - /* Duration */ - if (flags & TRACE_GRAPH_PRINT_DURATION) { - ret = print_graph_duration(duration, s); - if (ret == TRACE_TYPE_PARTIAL_LINE) - return TRACE_TYPE_PARTIAL_LINE; - } - /* Closing brace */ for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) { ret = trace_seq_printf(s, " "); @@ -1146,17 +1159,10 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent, if (print_graph_prologue(iter, s, 0, 0, flags)) return TRACE_TYPE_PARTIAL_LINE; - /* No overhead */ - ret = print_graph_overhead(-1, s, flags); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - /* No time */ - if (flags & TRACE_GRAPH_PRINT_DURATION) { - ret = trace_seq_printf(s, " | "); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - } + ret = print_graph_duration(DURATION_FILL_FULL, s, flags); + if (ret != TRACE_TYPE_HANDLED) + return ret; /* Indentation */ if (depth > 0) @@ -1207,7 +1213,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent, enum print_line_t -__print_graph_function_flags(struct trace_iterator *iter, u32 flags) +print_graph_function_flags(struct trace_iterator *iter, u32 flags) { struct ftrace_graph_ent_entry *field; struct fgraph_data *data = iter->private; @@ -1270,18 +1276,7 @@ __print_graph_function_flags(struct trace_iterator *iter, u32 flags) static enum print_line_t print_graph_function(struct trace_iterator *iter) { - return __print_graph_function_flags(iter, tracer_flags.val); -} - -enum print_line_t print_graph_function_flags(struct trace_iterator *iter, - u32 flags) -{ - if (trace_flags & TRACE_ITER_LATENCY_FMT) - flags |= TRACE_GRAPH_PRINT_DURATION; - else - flags |= TRACE_GRAPH_PRINT_ABS_TIME; - - return __print_graph_function_flags(iter, flags); + return print_graph_function_flags(iter, tracer_flags.val); } static enum print_line_t @@ -1309,8 +1304,7 @@ static void print_lat_header(struct seq_file *s, u32 flags) seq_printf(s, "#%.*s / _----=> need-resched \n", size, spaces); seq_printf(s, "#%.*s| / _---=> hardirq/softirq \n", size, spaces); seq_printf(s, "#%.*s|| / _--=> preempt-depth \n", size, spaces); - seq_printf(s, "#%.*s||| / _-=> lock-depth \n", size, spaces); - seq_printf(s, "#%.*s|||| / \n", size, spaces); + seq_printf(s, "#%.*s||| / \n", size, spaces); } static void __print_graph_headers_flags(struct seq_file *s, u32 flags) @@ -1329,7 +1323,7 @@ static void __print_graph_headers_flags(struct seq_file *s, u32 flags) if (flags & TRACE_GRAPH_PRINT_PROC) seq_printf(s, " TASK/PID "); if (lat) - seq_printf(s, "|||||"); + seq_printf(s, "||||"); if (flags & TRACE_GRAPH_PRINT_DURATION) seq_printf(s, " DURATION "); seq_printf(s, " FUNCTION CALLS\n"); @@ -1343,7 +1337,7 @@ static void __print_graph_headers_flags(struct seq_file *s, u32 flags) if (flags & TRACE_GRAPH_PRINT_PROC) seq_printf(s, " | | "); if (lat) - seq_printf(s, "|||||"); + seq_printf(s, "||||"); if (flags & TRACE_GRAPH_PRINT_DURATION) seq_printf(s, " | | "); seq_printf(s, " | | | |\n"); @@ -1358,15 +1352,16 @@ void print_graph_headers_flags(struct seq_file *s, u32 flags) { struct trace_iterator *iter = s->private; + if (!(trace_flags & TRACE_ITER_CONTEXT_INFO)) + return; + if (trace_flags & TRACE_ITER_LATENCY_FMT) { /* print nothing if the buffers are empty */ if (trace_empty(iter)) return; print_trace_header(s, iter); - flags |= TRACE_GRAPH_PRINT_DURATION; - } else - flags |= TRACE_GRAPH_PRINT_ABS_TIME; + } __print_graph_headers_flags(s, flags); } diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index a4969b47afc..667aa8cc0cf 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -153,6 +153,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = irqsoff_tracer_call, + .flags = FTRACE_OPS_FL_GLOBAL, }; #endif /* CONFIG_FUNCTION_TRACER */ @@ -225,7 +226,9 @@ static void irqsoff_trace_close(struct trace_iterator *iter) } #define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_CPU | \ - TRACE_GRAPH_PRINT_PROC) + TRACE_GRAPH_PRINT_PROC | \ + TRACE_GRAPH_PRINT_ABS_TIME | \ + TRACE_GRAPH_PRINT_DURATION) static enum print_line_t irqsoff_print_line(struct trace_iterator *iter) { diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 35d55a38614..5fb3697bf0e 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -53,7 +53,6 @@ const char *reserved_field_names[] = { "common_preempt_count", "common_pid", "common_tgid", - "common_lock_depth", FIELD_STRING_IP, FIELD_STRING_RETIP, FIELD_STRING_FUNC, @@ -344,6 +343,14 @@ DEFINE_BASIC_FETCH_FUNCS(deref) DEFINE_FETCH_deref(string) DEFINE_FETCH_deref(string_size) +static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data) +{ + if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) + update_deref_fetch_param(data->orig.data); + else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) + update_symbol_cache(data->orig.data); +} + static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data) { if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) @@ -378,6 +385,19 @@ DEFINE_BASIC_FETCH_FUNCS(bitfield) #define fetch_bitfield_string_size NULL static __kprobes void +update_bitfield_fetch_param(struct bitfield_fetch_param *data) +{ + /* + * Don't check the bitfield itself, because this must be the + * last fetch function. + */ + if (CHECK_FETCH_FUNCS(deref, data->orig.fn)) + update_deref_fetch_param(data->orig.data); + else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn)) + update_symbol_cache(data->orig.data); +} + +static __kprobes void free_bitfield_fetch_param(struct bitfield_fetch_param *data) { /* @@ -390,6 +410,7 @@ free_bitfield_fetch_param(struct bitfield_fetch_param *data) free_symbol_cache(data->orig.data); kfree(data); } + /* Default (unsigned long) fetch type */ #define __DEFAULT_FETCH_TYPE(t) u##t #define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t) @@ -537,6 +558,7 @@ struct probe_arg { /* Flags for trace_probe */ #define TP_FLAG_TRACE 1 #define TP_FLAG_PROFILE 2 +#define TP_FLAG_REGISTERED 4 struct trace_probe { struct list_head list; @@ -556,16 +578,49 @@ struct trace_probe { (sizeof(struct probe_arg) * (n))) -static __kprobes int probe_is_return(struct trace_probe *tp) +static __kprobes int trace_probe_is_return(struct trace_probe *tp) { return tp->rp.handler != NULL; } -static __kprobes const char *probe_symbol(struct trace_probe *tp) +static __kprobes const char *trace_probe_symbol(struct trace_probe *tp) { return tp->symbol ? tp->symbol : "unknown"; } +static __kprobes unsigned long trace_probe_offset(struct trace_probe *tp) +{ + return tp->rp.kp.offset; +} + +static __kprobes bool trace_probe_is_enabled(struct trace_probe *tp) +{ + return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE)); +} + +static __kprobes bool trace_probe_is_registered(struct trace_probe *tp) +{ + return !!(tp->flags & TP_FLAG_REGISTERED); +} + +static __kprobes bool trace_probe_has_gone(struct trace_probe *tp) +{ + return !!(kprobe_gone(&tp->rp.kp)); +} + +static __kprobes bool trace_probe_within_module(struct trace_probe *tp, + struct module *mod) +{ + int len = strlen(mod->name); + const char *name = trace_probe_symbol(tp); + return strncmp(mod->name, name, len) == 0 && name[len] == ':'; +} + +static __kprobes bool trace_probe_is_on_module(struct trace_probe *tp) +{ + return !!strchr(trace_probe_symbol(tp), ':'); +} + static int register_probe_event(struct trace_probe *tp); static void unregister_probe_event(struct trace_probe *tp); @@ -647,6 +702,16 @@ error: return ERR_PTR(ret); } +static void update_probe_arg(struct probe_arg *arg) +{ + if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn)) + update_bitfield_fetch_param(arg->fetch.data); + else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn)) + update_deref_fetch_param(arg->fetch.data); + else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn)) + update_symbol_cache(arg->fetch.data); +} + static void free_probe_arg(struct probe_arg *arg) { if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn)) @@ -672,7 +737,7 @@ static void free_trace_probe(struct trace_probe *tp) kfree(tp); } -static struct trace_probe *find_probe_event(const char *event, +static struct trace_probe *find_trace_probe(const char *event, const char *group) { struct trace_probe *tp; @@ -684,13 +749,96 @@ static struct trace_probe *find_probe_event(const char *event, return NULL; } +/* Enable trace_probe - @flag must be TP_FLAG_TRACE or TP_FLAG_PROFILE */ +static int enable_trace_probe(struct trace_probe *tp, int flag) +{ + int ret = 0; + + tp->flags |= flag; + if (trace_probe_is_enabled(tp) && trace_probe_is_registered(tp) && + !trace_probe_has_gone(tp)) { + if (trace_probe_is_return(tp)) + ret = enable_kretprobe(&tp->rp); + else + ret = enable_kprobe(&tp->rp.kp); + } + + return ret; +} + +/* Disable trace_probe - @flag must be TP_FLAG_TRACE or TP_FLAG_PROFILE */ +static void disable_trace_probe(struct trace_probe *tp, int flag) +{ + tp->flags &= ~flag; + if (!trace_probe_is_enabled(tp) && trace_probe_is_registered(tp)) { + if (trace_probe_is_return(tp)) + disable_kretprobe(&tp->rp); + else + disable_kprobe(&tp->rp.kp); + } +} + +/* Internal register function - just handle k*probes and flags */ +static int __register_trace_probe(struct trace_probe *tp) +{ + int i, ret; + + if (trace_probe_is_registered(tp)) + return -EINVAL; + + for (i = 0; i < tp->nr_args; i++) + update_probe_arg(&tp->args[i]); + + /* Set/clear disabled flag according to tp->flag */ + if (trace_probe_is_enabled(tp)) + tp->rp.kp.flags &= ~KPROBE_FLAG_DISABLED; + else + tp->rp.kp.flags |= KPROBE_FLAG_DISABLED; + + if (trace_probe_is_return(tp)) + ret = register_kretprobe(&tp->rp); + else + ret = register_kprobe(&tp->rp.kp); + + if (ret == 0) + tp->flags |= TP_FLAG_REGISTERED; + else { + pr_warning("Could not insert probe at %s+%lu: %d\n", + trace_probe_symbol(tp), trace_probe_offset(tp), ret); + if (ret == -ENOENT && trace_probe_is_on_module(tp)) { + pr_warning("This probe might be able to register after" + "target module is loaded. Continue.\n"); + ret = 0; + } else if (ret == -EILSEQ) { + pr_warning("Probing address(0x%p) is not an " + "instruction boundary.\n", + tp->rp.kp.addr); + ret = -EINVAL; + } + } + + return ret; +} + +/* Internal unregister function - just handle k*probes and flags */ +static void __unregister_trace_probe(struct trace_probe *tp) +{ + if (trace_probe_is_registered(tp)) { + if (trace_probe_is_return(tp)) + unregister_kretprobe(&tp->rp); + else + unregister_kprobe(&tp->rp.kp); + tp->flags &= ~TP_FLAG_REGISTERED; + /* Cleanup kprobe for reuse */ + if (tp->rp.kp.symbol_name) + tp->rp.kp.addr = NULL; + } +} + /* Unregister a trace_probe and probe_event: call with locking probe_lock */ static void unregister_trace_probe(struct trace_probe *tp) { - if (probe_is_return(tp)) - unregister_kretprobe(&tp->rp); - else - unregister_kprobe(&tp->rp.kp); + __unregister_trace_probe(tp); list_del(&tp->list); unregister_probe_event(tp); } @@ -703,41 +851,65 @@ static int register_trace_probe(struct trace_probe *tp) mutex_lock(&probe_lock); - /* register as an event */ - old_tp = find_probe_event(tp->call.name, tp->call.class->system); + /* Delete old (same name) event if exist */ + old_tp = find_trace_probe(tp->call.name, tp->call.class->system); if (old_tp) { - /* delete old event */ unregister_trace_probe(old_tp); free_trace_probe(old_tp); } + + /* Register new event */ ret = register_probe_event(tp); if (ret) { pr_warning("Failed to register probe event(%d)\n", ret); goto end; } - tp->rp.kp.flags |= KPROBE_FLAG_DISABLED; - if (probe_is_return(tp)) - ret = register_kretprobe(&tp->rp); - else - ret = register_kprobe(&tp->rp.kp); - - if (ret) { - pr_warning("Could not insert probe(%d)\n", ret); - if (ret == -EILSEQ) { - pr_warning("Probing address(0x%p) is not an " - "instruction boundary.\n", - tp->rp.kp.addr); - ret = -EINVAL; - } + /* Register k*probe */ + ret = __register_trace_probe(tp); + if (ret < 0) unregister_probe_event(tp); - } else + else list_add_tail(&tp->list, &probe_list); + end: mutex_unlock(&probe_lock); return ret; } +/* Module notifier call back, checking event on the module */ +static int trace_probe_module_callback(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct module *mod = data; + struct trace_probe *tp; + int ret; + + if (val != MODULE_STATE_COMING) + return NOTIFY_DONE; + + /* Update probes on coming module */ + mutex_lock(&probe_lock); + list_for_each_entry(tp, &probe_list, list) { + if (trace_probe_within_module(tp, mod)) { + __unregister_trace_probe(tp); + ret = __register_trace_probe(tp); + if (ret) + pr_warning("Failed to re-register probe %s on" + "%s: %d\n", + tp->call.name, mod->name, ret); + } + } + mutex_unlock(&probe_lock); + + return NOTIFY_DONE; +} + +static struct notifier_block trace_probe_module_nb = { + .notifier_call = trace_probe_module_callback, + .priority = 1 /* Invoked after kprobe module callback */ +}; + /* Split symbol and offset. */ static int split_symbol_offset(char *symbol, unsigned long *offset) { @@ -963,8 +1135,8 @@ static int create_trace_probe(int argc, char **argv) { /* * Argument syntax: - * - Add kprobe: p[:[GRP/]EVENT] KSYM[+OFFS]|KADDR [FETCHARGS] - * - Add kretprobe: r[:[GRP/]EVENT] KSYM[+0] [FETCHARGS] + * - Add kprobe: p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS] + * - Add kretprobe: r[:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS] * Fetch args: * $retval : fetch return value * $stack : fetch stack address @@ -1026,7 +1198,7 @@ static int create_trace_probe(int argc, char **argv) return -EINVAL; } mutex_lock(&probe_lock); - tp = find_probe_event(event, group); + tp = find_trace_probe(event, group); if (!tp) { mutex_unlock(&probe_lock); pr_info("Event %s/%s doesn't exist.\n", group, event); @@ -1145,7 +1317,7 @@ error: return ret; } -static void cleanup_all_probes(void) +static void release_all_trace_probes(void) { struct trace_probe *tp; @@ -1159,7 +1331,6 @@ static void cleanup_all_probes(void) mutex_unlock(&probe_lock); } - /* Probes listing interfaces */ static void *probes_seq_start(struct seq_file *m, loff_t *pos) { @@ -1182,15 +1353,16 @@ static int probes_seq_show(struct seq_file *m, void *v) struct trace_probe *tp = v; int i; - seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p'); + seq_printf(m, "%c", trace_probe_is_return(tp) ? 'r' : 'p'); seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name); if (!tp->symbol) seq_printf(m, " 0x%p", tp->rp.kp.addr); else if (tp->rp.kp.offset) - seq_printf(m, " %s+%u", probe_symbol(tp), tp->rp.kp.offset); + seq_printf(m, " %s+%u", trace_probe_symbol(tp), + tp->rp.kp.offset); else - seq_printf(m, " %s", probe_symbol(tp)); + seq_printf(m, " %s", trace_probe_symbol(tp)); for (i = 0; i < tp->nr_args; i++) seq_printf(m, " %s=%s", tp->args[i].name, tp->args[i].comm); @@ -1210,7 +1382,7 @@ static int probes_open(struct inode *inode, struct file *file) { if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) - cleanup_all_probes(); + release_all_trace_probes(); return seq_open(file, &probes_seq_op); } @@ -1398,7 +1570,8 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs) store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); if (!filter_current_check_discard(buffer, call, entry, event)) - trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc); + trace_nowake_buffer_unlock_commit_regs(buffer, event, + irq_flags, pc, regs); } /* Kretprobe handler */ @@ -1430,7 +1603,8 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri, store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); if (!filter_current_check_discard(buffer, call, entry, event)) - trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc); + trace_nowake_buffer_unlock_commit_regs(buffer, event, + irq_flags, pc, regs); } /* Event entry printers */ @@ -1512,30 +1686,6 @@ partial: return TRACE_TYPE_PARTIAL_LINE; } -static int probe_event_enable(struct ftrace_event_call *call) -{ - struct trace_probe *tp = (struct trace_probe *)call->data; - - tp->flags |= TP_FLAG_TRACE; - if (probe_is_return(tp)) - return enable_kretprobe(&tp->rp); - else - return enable_kprobe(&tp->rp.kp); -} - -static void probe_event_disable(struct ftrace_event_call *call) -{ - struct trace_probe *tp = (struct trace_probe *)call->data; - - tp->flags &= ~TP_FLAG_TRACE; - if (!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE))) { - if (probe_is_return(tp)) - disable_kretprobe(&tp->rp); - else - disable_kprobe(&tp->rp.kp); - } -} - #undef DEFINE_FIELD #define DEFINE_FIELD(type, item, name, is_signed) \ do { \ @@ -1597,7 +1747,7 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len) const char *fmt, *arg; - if (!probe_is_return(tp)) { + if (!trace_probe_is_return(tp)) { fmt = "(%lx)"; arg = "REC->" FIELD_STRING_IP; } else { @@ -1714,49 +1864,25 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri, head = this_cpu_ptr(call->perf_events); perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head); } - -static int probe_perf_enable(struct ftrace_event_call *call) -{ - struct trace_probe *tp = (struct trace_probe *)call->data; - - tp->flags |= TP_FLAG_PROFILE; - - if (probe_is_return(tp)) - return enable_kretprobe(&tp->rp); - else - return enable_kprobe(&tp->rp.kp); -} - -static void probe_perf_disable(struct ftrace_event_call *call) -{ - struct trace_probe *tp = (struct trace_probe *)call->data; - - tp->flags &= ~TP_FLAG_PROFILE; - - if (!(tp->flags & TP_FLAG_TRACE)) { - if (probe_is_return(tp)) - disable_kretprobe(&tp->rp); - else - disable_kprobe(&tp->rp.kp); - } -} #endif /* CONFIG_PERF_EVENTS */ static __kprobes int kprobe_register(struct ftrace_event_call *event, enum trace_reg type) { + struct trace_probe *tp = (struct trace_probe *)event->data; + switch (type) { case TRACE_REG_REGISTER: - return probe_event_enable(event); + return enable_trace_probe(tp, TP_FLAG_TRACE); case TRACE_REG_UNREGISTER: - probe_event_disable(event); + disable_trace_probe(tp, TP_FLAG_TRACE); return 0; #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: - return probe_perf_enable(event); + return enable_trace_probe(tp, TP_FLAG_PROFILE); case TRACE_REG_PERF_UNREGISTER: - probe_perf_disable(event); + disable_trace_probe(tp, TP_FLAG_PROFILE); return 0; #endif } @@ -1806,7 +1932,7 @@ static int register_probe_event(struct trace_probe *tp) /* Initialize ftrace_event_call */ INIT_LIST_HEAD(&call->class->fields); - if (probe_is_return(tp)) { + if (trace_probe_is_return(tp)) { call->event.funcs = &kretprobe_funcs; call->class->define_fields = kretprobe_event_define_fields; } else { @@ -1845,6 +1971,9 @@ static __init int init_kprobe_trace(void) struct dentry *d_tracer; struct dentry *entry; + if (register_module_notifier(&trace_probe_module_nb)) + return -EINVAL; + d_tracer = tracing_init_dentry(); if (!d_tracer) return 0; @@ -1871,8 +2000,12 @@ fs_initcall(init_kprobe_trace); #ifdef CONFIG_FTRACE_STARTUP_TEST -static int kprobe_trace_selftest_target(int a1, int a2, int a3, - int a4, int a5, int a6) +/* + * The "__used" keeps gcc from removing the function symbol + * from the kallsyms table. + */ +static __used int kprobe_trace_selftest_target(int a1, int a2, int a3, + int a4, int a5, int a6) { return a1 + a2 + a3 + a4 + a5 + a6; } @@ -1894,12 +2027,12 @@ static __init int kprobe_trace_self_tests_init(void) warn++; } else { /* Enable trace point */ - tp = find_probe_event("testprobe", KPROBE_EVENT_SYSTEM); + tp = find_trace_probe("testprobe", KPROBE_EVENT_SYSTEM); if (WARN_ON_ONCE(tp == NULL)) { pr_warning("error on getting new probe.\n"); warn++; } else - probe_event_enable(&tp->call); + enable_trace_probe(tp, TP_FLAG_TRACE); } ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target " @@ -1909,12 +2042,12 @@ static __init int kprobe_trace_self_tests_init(void) warn++; } else { /* Enable trace point */ - tp = find_probe_event("testprobe2", KPROBE_EVENT_SYSTEM); + tp = find_trace_probe("testprobe2", KPROBE_EVENT_SYSTEM); if (WARN_ON_ONCE(tp == NULL)) { pr_warning("error on getting new probe.\n"); warn++; } else - probe_event_enable(&tp->call); + enable_trace_probe(tp, TP_FLAG_TRACE); } if (warn) @@ -1935,7 +2068,7 @@ static __init int kprobe_trace_self_tests_init(void) } end: - cleanup_all_probes(); + release_all_trace_probes(); if (warn) pr_cont("NG: Some tests are failed. Please check them.\n"); else diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index 017fa376505..fd3c8aae55e 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -12,7 +12,7 @@ #include <linux/slab.h> #include <linux/time.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include "trace.h" #include "trace_output.h" diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 456be9063c2..51999309a6c 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -353,6 +353,33 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val, } EXPORT_SYMBOL(ftrace_print_symbols_seq); +#if BITS_PER_LONG == 32 +const char * +ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val, + const struct trace_print_flags_u64 *symbol_array) +{ + int i; + const char *ret = p->buffer + p->len; + + for (i = 0; symbol_array[i].name; i++) { + + if (val != symbol_array[i].mask) + continue; + + trace_seq_puts(p, symbol_array[i].name); + break; + } + + if (!p->len) + trace_seq_printf(p, "0x%llx", val); + + trace_seq_putc(p, 0); + + return ret; +} +EXPORT_SYMBOL(ftrace_print_symbols_seq_u64); +#endif + const char * ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len) { @@ -830,6 +857,9 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_event); enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags, struct trace_event *event) { + if (!trace_seq_printf(&iter->seq, "type: %d\n", iter->ent->type)) + return TRACE_TYPE_PARTIAL_LINE; + return TRACE_TYPE_HANDLED; } @@ -1077,19 +1107,20 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter, { struct stack_entry *field; struct trace_seq *s = &iter->seq; - int i; + unsigned long *p; + unsigned long *end; trace_assign_type(field, iter->ent); + end = (unsigned long *)((long)iter->ent + iter->ent_size); if (!trace_seq_puts(s, "<stack trace>\n")) goto partial; - for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { - if (!field->caller[i] || (field->caller[i] == ULONG_MAX)) - break; + + for (p = field->caller; p && *p != ULONG_MAX && p < end; p++) { if (!trace_seq_puts(s, " => ")) goto partial; - if (!seq_print_ip_sym(s, field->caller[i], flags)) + if (!seq_print_ip_sym(s, *p, flags)) goto partial; if (!trace_seq_puts(s, "\n")) goto partial; diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 2547d8813cf..1f06468a10d 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -32,7 +32,7 @@ static DEFINE_MUTEX(btrace_mutex); struct trace_bprintk_fmt { struct list_head list; - char fmt[0]; + const char *fmt; }; static inline struct trace_bprintk_fmt *lookup_format(const char *fmt) @@ -49,6 +49,7 @@ static void hold_module_trace_bprintk_format(const char **start, const char **end) { const char **iter; + char *fmt; mutex_lock(&btrace_mutex); for (iter = start; iter < end; iter++) { @@ -58,14 +59,18 @@ void hold_module_trace_bprintk_format(const char **start, const char **end) continue; } - tb_fmt = kmalloc(offsetof(struct trace_bprintk_fmt, fmt) - + strlen(*iter) + 1, GFP_KERNEL); - if (tb_fmt) { + tb_fmt = kmalloc(sizeof(*tb_fmt), GFP_KERNEL); + if (tb_fmt) + fmt = kmalloc(strlen(*iter) + 1, GFP_KERNEL); + if (tb_fmt && fmt) { list_add_tail(&tb_fmt->list, &trace_bprintk_fmt_list); - strcpy(tb_fmt->fmt, *iter); + strcpy(fmt, *iter); + tb_fmt->fmt = fmt; *iter = tb_fmt->fmt; - } else + } else { + kfree(tb_fmt); *iter = NULL; + } } mutex_unlock(&btrace_mutex); } @@ -84,6 +89,76 @@ static int module_trace_bprintk_format_notify(struct notifier_block *self, return 0; } +/* + * The debugfs/tracing/printk_formats file maps the addresses with + * the ASCII formats that are used in the bprintk events in the + * buffer. For userspace tools to be able to decode the events from + * the buffer, they need to be able to map the address with the format. + * + * The addresses of the bprintk formats are in their own section + * __trace_printk_fmt. But for modules we copy them into a link list. + * The code to print the formats and their addresses passes around the + * address of the fmt string. If the fmt address passed into the seq + * functions is within the kernel core __trace_printk_fmt section, then + * it simply uses the next pointer in the list. + * + * When the fmt pointer is outside the kernel core __trace_printk_fmt + * section, then we need to read the link list pointers. The trick is + * we pass the address of the string to the seq function just like + * we do for the kernel core formats. To get back the structure that + * holds the format, we simply use containerof() and then go to the + * next format in the list. + */ +static const char ** +find_next_mod_format(int start_index, void *v, const char **fmt, loff_t *pos) +{ + struct trace_bprintk_fmt *mod_fmt; + + if (list_empty(&trace_bprintk_fmt_list)) + return NULL; + + /* + * v will point to the address of the fmt record from t_next + * v will be NULL from t_start. + * If this is the first pointer or called from start + * then we need to walk the list. + */ + if (!v || start_index == *pos) { + struct trace_bprintk_fmt *p; + + /* search the module list */ + list_for_each_entry(p, &trace_bprintk_fmt_list, list) { + if (start_index == *pos) + return &p->fmt; + start_index++; + } + /* pos > index */ + return NULL; + } + + /* + * v points to the address of the fmt field in the mod list + * structure that holds the module print format. + */ + mod_fmt = container_of(v, typeof(*mod_fmt), fmt); + if (mod_fmt->list.next == &trace_bprintk_fmt_list) + return NULL; + + mod_fmt = container_of(mod_fmt->list.next, typeof(*mod_fmt), list); + + return &mod_fmt->fmt; +} + +static void format_mod_start(void) +{ + mutex_lock(&btrace_mutex); +} + +static void format_mod_stop(void) +{ + mutex_unlock(&btrace_mutex); +} + #else /* !CONFIG_MODULES */ __init static int module_trace_bprintk_format_notify(struct notifier_block *self, @@ -91,6 +166,13 @@ module_trace_bprintk_format_notify(struct notifier_block *self, { return 0; } +static inline const char ** +find_next_mod_format(int start_index, void *v, const char **fmt, loff_t *pos) +{ + return NULL; +} +static inline void format_mod_start(void) { } +static inline void format_mod_stop(void) { } #endif /* CONFIG_MODULES */ @@ -153,20 +235,30 @@ int __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap) } EXPORT_SYMBOL_GPL(__ftrace_vprintk); +static const char **find_next(void *v, loff_t *pos) +{ + const char **fmt = v; + int start_index; + + start_index = __stop___trace_bprintk_fmt - __start___trace_bprintk_fmt; + + if (*pos < start_index) + return __start___trace_bprintk_fmt + *pos; + + return find_next_mod_format(start_index, v, fmt, pos); +} + static void * t_start(struct seq_file *m, loff_t *pos) { - const char **fmt = __start___trace_bprintk_fmt + *pos; - - if ((unsigned long)fmt >= (unsigned long)__stop___trace_bprintk_fmt) - return NULL; - return fmt; + format_mod_start(); + return find_next(NULL, pos); } static void *t_next(struct seq_file *m, void * v, loff_t *pos) { (*pos)++; - return t_start(m, pos); + return find_next(v, pos); } static int t_show(struct seq_file *m, void *v) @@ -205,6 +297,7 @@ static int t_show(struct seq_file *m, void *v) static void t_stop(struct seq_file *m, void *p) { + format_mod_stop(); } static const struct seq_operations show_format_seq_ops = { diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 7319559ed59..e4a70c0c71b 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -129,6 +129,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = wakeup_tracer_call, + .flags = FTRACE_OPS_FL_GLOBAL, }; #endif /* CONFIG_FUNCTION_TRACER */ @@ -226,7 +227,9 @@ static void wakeup_trace_close(struct trace_iterator *iter) graph_trace_close(iter); } -#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_PROC) +#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_PROC | \ + TRACE_GRAPH_PRINT_ABS_TIME | \ + TRACE_GRAPH_PRINT_DURATION) static enum print_line_t wakeup_print_line(struct trace_iterator *iter) { diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 659732eba07..288541f977f 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -101,6 +101,206 @@ static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret) #ifdef CONFIG_DYNAMIC_FTRACE +static int trace_selftest_test_probe1_cnt; +static void trace_selftest_test_probe1_func(unsigned long ip, + unsigned long pip) +{ + trace_selftest_test_probe1_cnt++; +} + +static int trace_selftest_test_probe2_cnt; +static void trace_selftest_test_probe2_func(unsigned long ip, + unsigned long pip) +{ + trace_selftest_test_probe2_cnt++; +} + +static int trace_selftest_test_probe3_cnt; +static void trace_selftest_test_probe3_func(unsigned long ip, + unsigned long pip) +{ + trace_selftest_test_probe3_cnt++; +} + +static int trace_selftest_test_global_cnt; +static void trace_selftest_test_global_func(unsigned long ip, + unsigned long pip) +{ + trace_selftest_test_global_cnt++; +} + +static int trace_selftest_test_dyn_cnt; +static void trace_selftest_test_dyn_func(unsigned long ip, + unsigned long pip) +{ + trace_selftest_test_dyn_cnt++; +} + +static struct ftrace_ops test_probe1 = { + .func = trace_selftest_test_probe1_func, +}; + +static struct ftrace_ops test_probe2 = { + .func = trace_selftest_test_probe2_func, +}; + +static struct ftrace_ops test_probe3 = { + .func = trace_selftest_test_probe3_func, +}; + +static struct ftrace_ops test_global = { + .func = trace_selftest_test_global_func, + .flags = FTRACE_OPS_FL_GLOBAL, +}; + +static void print_counts(void) +{ + printk("(%d %d %d %d %d) ", + trace_selftest_test_probe1_cnt, + trace_selftest_test_probe2_cnt, + trace_selftest_test_probe3_cnt, + trace_selftest_test_global_cnt, + trace_selftest_test_dyn_cnt); +} + +static void reset_counts(void) +{ + trace_selftest_test_probe1_cnt = 0; + trace_selftest_test_probe2_cnt = 0; + trace_selftest_test_probe3_cnt = 0; + trace_selftest_test_global_cnt = 0; + trace_selftest_test_dyn_cnt = 0; +} + +static int trace_selftest_ops(int cnt) +{ + int save_ftrace_enabled = ftrace_enabled; + struct ftrace_ops *dyn_ops; + char *func1_name; + char *func2_name; + int len1; + int len2; + int ret = -1; + + printk(KERN_CONT "PASSED\n"); + pr_info("Testing dynamic ftrace ops #%d: ", cnt); + + ftrace_enabled = 1; + reset_counts(); + + /* Handle PPC64 '.' name */ + func1_name = "*" __stringify(DYN_FTRACE_TEST_NAME); + func2_name = "*" __stringify(DYN_FTRACE_TEST_NAME2); + len1 = strlen(func1_name); + len2 = strlen(func2_name); + + /* + * Probe 1 will trace function 1. + * Probe 2 will trace function 2. + * Probe 3 will trace functions 1 and 2. + */ + ftrace_set_filter(&test_probe1, func1_name, len1, 1); + ftrace_set_filter(&test_probe2, func2_name, len2, 1); + ftrace_set_filter(&test_probe3, func1_name, len1, 1); + ftrace_set_filter(&test_probe3, func2_name, len2, 0); + + register_ftrace_function(&test_probe1); + register_ftrace_function(&test_probe2); + register_ftrace_function(&test_probe3); + register_ftrace_function(&test_global); + + DYN_FTRACE_TEST_NAME(); + + print_counts(); + + if (trace_selftest_test_probe1_cnt != 1) + goto out; + if (trace_selftest_test_probe2_cnt != 0) + goto out; + if (trace_selftest_test_probe3_cnt != 1) + goto out; + if (trace_selftest_test_global_cnt == 0) + goto out; + + DYN_FTRACE_TEST_NAME2(); + + print_counts(); + + if (trace_selftest_test_probe1_cnt != 1) + goto out; + if (trace_selftest_test_probe2_cnt != 1) + goto out; + if (trace_selftest_test_probe3_cnt != 2) + goto out; + + /* Add a dynamic probe */ + dyn_ops = kzalloc(sizeof(*dyn_ops), GFP_KERNEL); + if (!dyn_ops) { + printk("MEMORY ERROR "); + goto out; + } + + dyn_ops->func = trace_selftest_test_dyn_func; + + register_ftrace_function(dyn_ops); + + trace_selftest_test_global_cnt = 0; + + DYN_FTRACE_TEST_NAME(); + + print_counts(); + + if (trace_selftest_test_probe1_cnt != 2) + goto out_free; + if (trace_selftest_test_probe2_cnt != 1) + goto out_free; + if (trace_selftest_test_probe3_cnt != 3) + goto out_free; + if (trace_selftest_test_global_cnt == 0) + goto out; + if (trace_selftest_test_dyn_cnt == 0) + goto out_free; + + DYN_FTRACE_TEST_NAME2(); + + print_counts(); + + if (trace_selftest_test_probe1_cnt != 2) + goto out_free; + if (trace_selftest_test_probe2_cnt != 2) + goto out_free; + if (trace_selftest_test_probe3_cnt != 4) + goto out_free; + + ret = 0; + out_free: + unregister_ftrace_function(dyn_ops); + kfree(dyn_ops); + + out: + /* Purposely unregister in the same order */ + unregister_ftrace_function(&test_probe1); + unregister_ftrace_function(&test_probe2); + unregister_ftrace_function(&test_probe3); + unregister_ftrace_function(&test_global); + + /* Make sure everything is off */ + reset_counts(); + DYN_FTRACE_TEST_NAME(); + DYN_FTRACE_TEST_NAME(); + + if (trace_selftest_test_probe1_cnt || + trace_selftest_test_probe2_cnt || + trace_selftest_test_probe3_cnt || + trace_selftest_test_global_cnt || + trace_selftest_test_dyn_cnt) + ret = -1; + + ftrace_enabled = save_ftrace_enabled; + + return ret; +} + /* Test dynamic code modification and ftrace filters */ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, struct trace_array *tr, @@ -131,7 +331,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); /* filter only on our function */ - ftrace_set_filter(func_name, strlen(func_name), 1); + ftrace_set_global_filter(func_name, strlen(func_name), 1); /* enable tracing */ ret = tracer_init(trace, tr); @@ -166,22 +366,30 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, /* check the trace buffer */ ret = trace_test_buffer(tr, &count); - trace->reset(tr); tracing_start(); /* we should only have one item */ if (!ret && count != 1) { + trace->reset(tr); printk(KERN_CONT ".. filter failed count=%ld ..", count); ret = -1; goto out; } + /* Test the ops with global tracing running */ + ret = trace_selftest_ops(1); + trace->reset(tr); + out: ftrace_enabled = save_ftrace_enabled; tracer_enabled = save_tracer_enabled; /* Enable tracing on all functions again */ - ftrace_set_filter(NULL, 0, 1); + ftrace_set_global_filter(NULL, 0, 1); + + /* Test the ops with global tracing off */ + if (!ret) + ret = trace_selftest_ops(2); return ret; } diff --git a/kernel/trace/trace_selftest_dynamic.c b/kernel/trace/trace_selftest_dynamic.c index 54dd77cce5b..b4c475a0a48 100644 --- a/kernel/trace/trace_selftest_dynamic.c +++ b/kernel/trace/trace_selftest_dynamic.c @@ -5,3 +5,9 @@ int DYN_FTRACE_TEST_NAME(void) /* used to call mcount */ return 0; } + +int DYN_FTRACE_TEST_NAME2(void) +{ + /* used to call mcount */ + return 0; +} diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 4c5dead0c23..77575b386d9 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -133,6 +133,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = stack_trace_call, + .flags = FTRACE_OPS_FL_GLOBAL, }; static ssize_t @@ -155,20 +156,11 @@ stack_max_size_write(struct file *filp, const char __user *ubuf, { long *ptr = filp->private_data; unsigned long val, flags; - char buf[64]; int ret; int cpu; - if (count >= sizeof(buf)) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, count)) - return -EFAULT; - - buf[count] = 0; - - ret = strict_strtoul(buf, 10, &val); - if (ret < 0) + ret = kstrtoul_from_user(ubuf, count, 10, &val); + if (ret) return ret; local_irq_save(flags); diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 68187af4889..b219f1449c5 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -251,9 +251,9 @@ static void set_tracepoint(struct tracepoint_entry **entry, { WARN_ON(strcmp((*entry)->name, elem->name) != 0); - if (elem->regfunc && !elem->state && active) + if (elem->regfunc && !jump_label_enabled(&elem->key) && active) elem->regfunc(); - else if (elem->unregfunc && elem->state && !active) + else if (elem->unregfunc && jump_label_enabled(&elem->key) && !active) elem->unregfunc(); /* @@ -264,13 +264,10 @@ static void set_tracepoint(struct tracepoint_entry **entry, * is used. */ rcu_assign_pointer(elem->funcs, (*entry)->funcs); - if (!elem->state && active) { - jump_label_enable(&elem->state); - elem->state = active; - } else if (elem->state && !active) { - jump_label_disable(&elem->state); - elem->state = active; - } + if (active && !jump_label_enabled(&elem->key)) + jump_label_inc(&elem->key); + else if (!active && jump_label_enabled(&elem->key)) + jump_label_dec(&elem->key); } /* @@ -281,13 +278,11 @@ static void set_tracepoint(struct tracepoint_entry **entry, */ static void disable_tracepoint(struct tracepoint *elem) { - if (elem->unregfunc && elem->state) + if (elem->unregfunc && jump_label_enabled(&elem->key)) elem->unregfunc(); - if (elem->state) { - jump_label_disable(&elem->state); - elem->state = 0; - } + if (jump_label_enabled(&elem->key)) + jump_label_dec(&elem->key); rcu_assign_pointer(elem->funcs, NULL); } diff --git a/kernel/utsname.c b/kernel/utsname.c index 44646179eab..bff131b9510 100644 --- a/kernel/utsname.c +++ b/kernel/utsname.c @@ -15,6 +15,7 @@ #include <linux/err.h> #include <linux/slab.h> #include <linux/user_namespace.h> +#include <linux/proc_fs.h> static struct uts_namespace *create_uts_ns(void) { @@ -79,3 +80,41 @@ void free_uts_ns(struct kref *kref) put_user_ns(ns->user_ns); kfree(ns); } + +static void *utsns_get(struct task_struct *task) +{ + struct uts_namespace *ns = NULL; + struct nsproxy *nsproxy; + + rcu_read_lock(); + nsproxy = task_nsproxy(task); + if (nsproxy) { + ns = nsproxy->uts_ns; + get_uts_ns(ns); + } + rcu_read_unlock(); + + return ns; +} + +static void utsns_put(void *ns) +{ + put_uts_ns(ns); +} + +static int utsns_install(struct nsproxy *nsproxy, void *ns) +{ + get_uts_ns(ns); + put_uts_ns(nsproxy->uts_ns); + nsproxy->uts_ns = ns; + return 0; +} + +const struct proc_ns_operations utsns_operations = { + .name = "uts", + .type = CLONE_NEWUTS, + .get = utsns_get, + .put = utsns_put, + .install = utsns_install, +}; + diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 140dce75045..36491cd5b7d 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -28,7 +28,7 @@ #include <linux/perf_event.h> int watchdog_enabled = 1; -int __read_mostly softlockup_thresh = 60; +int __read_mostly watchdog_thresh = 10; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); @@ -91,6 +91,17 @@ static int __init nosoftlockup_setup(char *str) __setup("nosoftlockup", nosoftlockup_setup); /* */ +/* + * Hard-lockup warnings should be triggered after just a few seconds. Soft- + * lockups can have false positives under extreme conditions. So we generally + * want a higher threshold for soft lockups than for hard lockups. So we couple + * the thresholds with a factor: we make the soft threshold twice the amount of + * time the hard threshold is. + */ +static int get_softlockup_thresh(void) +{ + return watchdog_thresh * 2; +} /* * Returns seconds, approximately. We don't need nanosecond @@ -105,12 +116,12 @@ static unsigned long get_timestamp(int this_cpu) static unsigned long get_sample_period(void) { /* - * convert softlockup_thresh from seconds to ns + * convert watchdog_thresh from seconds to ns * the divide by 5 is to give hrtimer 5 chances to * increment before the hardlockup detector generates * a warning */ - return softlockup_thresh / 5 * NSEC_PER_SEC; + return get_softlockup_thresh() * (NSEC_PER_SEC / 5); } /* Commands for resetting the watchdog */ @@ -182,13 +193,14 @@ static int is_softlockup(unsigned long touch_ts) unsigned long now = get_timestamp(smp_processor_id()); /* Warn about unreasonable delays: */ - if (time_after(now, touch_ts + softlockup_thresh)) + if (time_after(now, touch_ts + get_softlockup_thresh())) return now - touch_ts; return 0; } #ifdef CONFIG_HARDLOCKUP_DETECTOR + static struct perf_event_attr wd_hw_attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, @@ -198,7 +210,7 @@ static struct perf_event_attr wd_hw_attr = { }; /* Callback function for perf event subsystem */ -static void watchdog_overflow_callback(struct perf_event *event, int nmi, +static void watchdog_overflow_callback(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { @@ -357,10 +369,11 @@ static int watchdog_nmi_enable(int cpu) if (event != NULL) goto out_enable; - /* Try to register using hardware perf events */ wd_attr = &wd_hw_attr; - wd_attr->sample_period = hw_nmi_get_sample_period(); - event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback); + wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); + + /* Try to register using hardware perf events */ + event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); if (!IS_ERR(event)) { printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n"); goto out_save; @@ -404,15 +417,13 @@ static void watchdog_nmi_disable(int cpu) { return; } #endif /* CONFIG_HARDLOCKUP_DETECTOR */ /* prepare/enable/disable routines */ -static int watchdog_prepare_cpu(int cpu) +static void watchdog_prepare_cpu(int cpu) { struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu); WARN_ON(per_cpu(softlockup_watchdog, cpu)); hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = watchdog_timer_fn; - - return 0; } static int watchdog_enable(int cpu) @@ -430,9 +441,12 @@ static int watchdog_enable(int cpu) p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu); if (IS_ERR(p)) { printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu); - if (!err) + if (!err) { /* if hardlockup hasn't already set this */ err = PTR_ERR(p); + /* and disable the perf event */ + watchdog_nmi_disable(cpu); + } goto out; } kthread_bind(p, cpu); @@ -498,28 +512,25 @@ static void watchdog_disable_all_cpus(void) /* sysctl functions */ #ifdef CONFIG_SYSCTL /* - * proc handler for /proc/sys/kernel/nmi_watchdog + * proc handler for /proc/sys/kernel/nmi_watchdog,watchdog_thresh */ -int proc_dowatchdog_enabled(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) +int proc_dowatchdog(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { - proc_dointvec(table, write, buffer, length, ppos); + int ret; - if (write) { - if (watchdog_enabled) - watchdog_enable_all_cpus(); - else - watchdog_disable_all_cpus(); - } - return 0; -} + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret || !write) + goto out; -int proc_dowatchdog_thresh(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) -{ - return proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (watchdog_enabled && watchdog_thresh) + watchdog_enable_all_cpus(); + else + watchdog_disable_all_cpus(); + +out: + return ret; } #endif /* CONFIG_SYSCTL */ @@ -531,17 +542,16 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { int hotcpu = (unsigned long)hcpu; - int err = 0; switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - err = watchdog_prepare_cpu(hotcpu); + watchdog_prepare_cpu(hotcpu); break; case CPU_ONLINE: case CPU_ONLINE_FROZEN: if (watchdog_enabled) - err = watchdog_enable(hotcpu); + watchdog_enable(hotcpu); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED: diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 8859a41806d..25fb1b0e53f 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -221,7 +221,7 @@ typedef unsigned long mayday_mask_t; * per-CPU workqueues: */ struct workqueue_struct { - unsigned int flags; /* I: WQ_* flags */ + unsigned int flags; /* W: WQ_* flags */ union { struct cpu_workqueue_struct __percpu *pcpu; struct cpu_workqueue_struct *single; @@ -240,6 +240,7 @@ struct workqueue_struct { mayday_mask_t mayday_mask; /* cpus requesting rescue */ struct worker *rescuer; /* I: rescue worker */ + int nr_drainers; /* W: drain in progress */ int saved_max_active; /* W: saved cwq max_active */ const char *name; /* I: workqueue name */ #ifdef CONFIG_LOCKDEP @@ -990,7 +991,7 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, debug_work_activate(work); /* if dying, only works from the same workqueue are allowed */ - if (unlikely(wq->flags & WQ_DYING) && + if (unlikely(wq->flags & WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq))) return; @@ -1291,8 +1292,14 @@ __acquires(&gcwq->lock) return true; spin_unlock_irq(&gcwq->lock); - /* CPU has come up in between, retry migration */ + /* + * We've raced with CPU hot[un]plug. Give it a breather + * and retry migration. cond_resched() is required here; + * otherwise, we might deadlock against cpu_stop trying to + * bring down the CPU on non-preemptive kernel. + */ cpu_relax(); + cond_resched(); } } @@ -2375,6 +2382,54 @@ out_unlock: } EXPORT_SYMBOL_GPL(flush_workqueue); +/** + * drain_workqueue - drain a workqueue + * @wq: workqueue to drain + * + * Wait until the workqueue becomes empty. While draining is in progress, + * only chain queueing is allowed. IOW, only currently pending or running + * work items on @wq can queue further work items on it. @wq is flushed + * repeatedly until it becomes empty. The number of flushing is detemined + * by the depth of chaining and should be relatively short. Whine if it + * takes too long. + */ +void drain_workqueue(struct workqueue_struct *wq) +{ + unsigned int flush_cnt = 0; + unsigned int cpu; + + /* + * __queue_work() needs to test whether there are drainers, is much + * hotter than drain_workqueue() and already looks at @wq->flags. + * Use WQ_DRAINING so that queue doesn't have to check nr_drainers. + */ + spin_lock(&workqueue_lock); + if (!wq->nr_drainers++) + wq->flags |= WQ_DRAINING; + spin_unlock(&workqueue_lock); +reflush: + flush_workqueue(wq); + + for_each_cwq_cpu(cpu, wq) { + struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); + + if (!cwq->nr_active && list_empty(&cwq->delayed_works)) + continue; + + if (++flush_cnt == 10 || + (flush_cnt % 100 == 0 && flush_cnt <= 1000)) + pr_warning("workqueue %s: flush on destruction isn't complete after %u tries\n", + wq->name, flush_cnt); + goto reflush; + } + + spin_lock(&workqueue_lock); + if (!--wq->nr_drainers) + wq->flags &= ~WQ_DRAINING; + spin_unlock(&workqueue_lock); +} +EXPORT_SYMBOL_GPL(drain_workqueue); + static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, bool wait_executing) { @@ -2860,9 +2915,7 @@ static int alloc_cwqs(struct workqueue_struct *wq) } } - /* just in case, make sure it's actually aligned - * - this is affected by PERCPU() alignment in vmlinux.lds.S - */ + /* just in case, make sure it's actually aligned */ BUG_ON(!IS_ALIGNED(wq->cpu_wq.v, align)); return wq->cpu_wq.v ? 0 : -ENOMEM; } @@ -3005,34 +3058,10 @@ EXPORT_SYMBOL_GPL(__alloc_workqueue_key); */ void destroy_workqueue(struct workqueue_struct *wq) { - unsigned int flush_cnt = 0; unsigned int cpu; - /* - * Mark @wq dying and drain all pending works. Once WQ_DYING is - * set, only chain queueing is allowed. IOW, only currently - * pending or running work items on @wq can queue further work - * items on it. @wq is flushed repeatedly until it becomes empty. - * The number of flushing is detemined by the depth of chaining and - * should be relatively short. Whine if it takes too long. - */ - wq->flags |= WQ_DYING; -reflush: - flush_workqueue(wq); - - for_each_cwq_cpu(cpu, wq) { - struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq); - - if (!cwq->nr_active && list_empty(&cwq->delayed_works)) - continue; - - if (++flush_cnt == 10 || - (flush_cnt % 100 == 0 && flush_cnt <= 1000)) - printk(KERN_WARNING "workqueue %s: flush on " - "destruction isn't complete after %u tries\n", - wq->name, flush_cnt); - goto reflush; - } + /* drain it before proceeding with destruction */ + drain_workqueue(wq); /* * wq list is used to freeze wq, remove from list after |