diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/audit.c | 17 | ||||
-rw-r--r-- | kernel/audit.h | 4 | ||||
-rw-r--r-- | kernel/auditsc.c | 8 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 41 | ||||
-rw-r--r-- | kernel/cgroup.c | 148 | ||||
-rw-r--r-- | kernel/events/core.c | 8 | ||||
-rw-r--r-- | kernel/fork.c | 50 | ||||
-rw-r--r-- | kernel/futex.c | 14 | ||||
-rw-r--r-- | kernel/jump_label.c | 36 | ||||
-rw-r--r-- | kernel/kcov.c | 7 | ||||
-rw-r--r-- | kernel/locking/mutex-debug.c | 12 | ||||
-rw-r--r-- | kernel/locking/mutex-debug.h | 4 | ||||
-rw-r--r-- | kernel/locking/mutex.c | 15 | ||||
-rw-r--r-- | kernel/locking/mutex.h | 2 | ||||
-rw-r--r-- | kernel/locking/qspinlock.c | 60 | ||||
-rw-r--r-- | kernel/power/process.c | 12 | ||||
-rw-r--r-- | kernel/relay.c | 1 | ||||
-rw-r--r-- | kernel/sched/core.c | 42 | ||||
-rw-r--r-- | kernel/sched/debug.c | 15 | ||||
-rw-r--r-- | kernel/sched/fair.c | 72 | ||||
-rw-r--r-- | kernel/sched/idle.c | 2 | ||||
-rw-r--r-- | kernel/sched/sched.h | 2 | ||||
-rw-r--r-- | kernel/sched/stats.h | 3 | ||||
-rw-r--r-- | kernel/signal.c | 24 | ||||
-rw-r--r-- | kernel/time/tick-internal.h | 1 | ||||
-rw-r--r-- | kernel/time/tick-sched.c | 45 | ||||
-rw-r--r-- | kernel/time/timer.c | 1103 | ||||
-rw-r--r-- | kernel/trace/bpf_trace.c | 14 | ||||
-rw-r--r-- | kernel/trace/trace_printk.c | 7 |
29 files changed, 1077 insertions, 692 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index 22bb4f2..8d528f9 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1883,6 +1883,23 @@ out_null: audit_log_format(ab, " exe=(null)"); } +struct tty_struct *audit_get_tty(struct task_struct *tsk) +{ + struct tty_struct *tty = NULL; + unsigned long flags; + + spin_lock_irqsave(&tsk->sighand->siglock, flags); + if (tsk->signal) + tty = tty_kref_get(tsk->signal->tty); + spin_unlock_irqrestore(&tsk->sighand->siglock, flags); + return tty; +} + +void audit_put_tty(struct tty_struct *tty) +{ + tty_kref_put(tty); +} + void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk) { const struct cred *cred; diff --git a/kernel/audit.h b/kernel/audit.h index cbbe6bb..a492f4c 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -23,6 +23,7 @@ #include <linux/audit.h> #include <linux/skbuff.h> #include <uapi/linux/mqueue.h> +#include <linux/tty.h> /* AUDIT_NAMES is the number of slots we reserve in the audit_context * for saving names from getname(). If we get more names we will allocate @@ -262,6 +263,9 @@ extern struct audit_entry *audit_dupe_rule(struct audit_krule *old); extern void audit_log_d_path_exe(struct audit_buffer *ab, struct mm_struct *mm); +extern struct tty_struct *audit_get_tty(struct task_struct *tsk); +extern void audit_put_tty(struct tty_struct *tty); + /* audit watch functions */ #ifdef CONFIG_AUDIT_WATCH extern void audit_put_watch(struct audit_watch *watch); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 62ab53d..2672d10 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -63,7 +63,6 @@ #include <asm/unistd.h> #include <linux/security.h> #include <linux/list.h> -#include <linux/tty.h> #include <linux/binfmts.h> #include <linux/highmem.h> #include <linux/syscalls.h> @@ -1985,14 +1984,15 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, if (!audit_enabled) return; + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN); + if (!ab) + return; + uid = from_kuid(&init_user_ns, task_uid(current)); oldloginuid = from_kuid(&init_user_ns, koldloginuid); loginuid = from_kuid(&init_user_ns, kloginuid), tty = audit_get_tty(current); - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN); - if (!ab) - return; audit_log_format(ab, "pid=%d uid=%u", task_pid_nr(current), uid); audit_log_task_context(ab); audit_log_format(ab, " old-auid=%u auid=%u tty=%s old-ses=%u ses=%u res=%d", diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 668e079..eec9f90 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -126,31 +126,6 @@ * are set to NOT_INIT to indicate that they are no longer readable. */ -/* types of values stored in eBPF registers */ -enum bpf_reg_type { - NOT_INIT = 0, /* nothing was written into register */ - UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */ - PTR_TO_CTX, /* reg points to bpf_context */ - CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ - PTR_TO_MAP_VALUE, /* reg points to map element value */ - PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ - FRAME_PTR, /* reg == frame_pointer */ - PTR_TO_STACK, /* reg == frame_pointer + imm */ - CONST_IMM, /* constant integer value */ - - /* PTR_TO_PACKET represents: - * skb->data - * skb->data + imm - * skb->data + (u16) var - * skb->data + (u16) var + imm - * if (range > 0) then [ptr, ptr + range - off) is safe to access - * if (id > 0) means that some 'var' was added - * if (off > 0) menas that 'imm' was added - */ - PTR_TO_PACKET, - PTR_TO_PACKET_END, /* skb->data + headlen */ -}; - struct reg_state { enum bpf_reg_type type; union { @@ -695,10 +670,10 @@ static int check_packet_access(struct verifier_env *env, u32 regno, int off, /* check access to 'struct bpf_context' fields */ static int check_ctx_access(struct verifier_env *env, int off, int size, - enum bpf_access_type t) + enum bpf_access_type t, enum bpf_reg_type *reg_type) { if (env->prog->aux->ops->is_valid_access && - env->prog->aux->ops->is_valid_access(off, size, t)) { + env->prog->aux->ops->is_valid_access(off, size, t, reg_type)) { /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; @@ -798,21 +773,19 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off, mark_reg_unknown_value(state->regs, value_regno); } else if (reg->type == PTR_TO_CTX) { + enum bpf_reg_type reg_type = UNKNOWN_VALUE; + if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose("R%d leaks addr into ctx\n", value_regno); return -EACCES; } - err = check_ctx_access(env, off, size, t); + err = check_ctx_access(env, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { mark_reg_unknown_value(state->regs, value_regno); - if (off == offsetof(struct __sk_buff, data) && - env->allow_ptr_leaks) + if (env->allow_ptr_leaks) /* note that reg.[id|off|range] == 0 */ - state->regs[value_regno].type = PTR_TO_PACKET; - else if (off == offsetof(struct __sk_buff, data_end) && - env->allow_ptr_leaks) - state->regs[value_regno].type = PTR_TO_PACKET_END; + state->regs[value_regno].type = reg_type; } } else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) { diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 86cb5c6..75c0ff0 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -837,6 +837,8 @@ static void put_css_set_locked(struct css_set *cset) static void put_css_set(struct css_set *cset) { + unsigned long flags; + /* * Ensure that the refcount doesn't hit zero while any readers * can see it. Similar to atomic_dec_and_lock(), but for an @@ -845,9 +847,9 @@ static void put_css_set(struct css_set *cset) if (atomic_add_unless(&cset->refcount, -1, 1)) return; - spin_lock_bh(&css_set_lock); + spin_lock_irqsave(&css_set_lock, flags); put_css_set_locked(cset); - spin_unlock_bh(&css_set_lock); + spin_unlock_irqrestore(&css_set_lock, flags); } /* @@ -1070,11 +1072,11 @@ static struct css_set *find_css_set(struct css_set *old_cset, /* First see if we already have a cgroup group that matches * the desired set */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); cset = find_existing_css_set(old_cset, cgrp, template); if (cset) get_css_set(cset); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); if (cset) return cset; @@ -1102,7 +1104,7 @@ static struct css_set *find_css_set(struct css_set *old_cset, * find_existing_css_set() */ memcpy(cset->subsys, template, sizeof(cset->subsys)); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); /* Add reference counts and links from the new css_set. */ list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; @@ -1128,7 +1130,7 @@ static struct css_set *find_css_set(struct css_set *old_cset, css_get(css); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); return cset; } @@ -1192,7 +1194,7 @@ static void cgroup_destroy_root(struct cgroup_root *root) * Release all the links from cset_links to this hierarchy's * root cgroup */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) { list_del(&link->cset_link); @@ -1200,7 +1202,7 @@ static void cgroup_destroy_root(struct cgroup_root *root) kfree(link); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); if (!list_empty(&root->root_list)) { list_del(&root->root_list); @@ -1600,11 +1602,11 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) ss->root = dst_root; css->cgroup = dcgrp; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) list_move_tail(&cset->e_cset_node[ss->id], &dcgrp->e_csets[ss->id]); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); /* default hierarchy doesn't enable controllers by default */ dst_root->subsys_mask |= 1 << ssid; @@ -1640,10 +1642,10 @@ static int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, if (!buf) return -ENOMEM; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot); len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); if (len >= PATH_MAX) len = -ERANGE; @@ -1897,7 +1899,7 @@ static void cgroup_enable_task_cg_lists(void) { struct task_struct *p, *g; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); if (use_task_css_set_links) goto out_unlock; @@ -1922,8 +1924,12 @@ static void cgroup_enable_task_cg_lists(void) * entry won't be deleted though the process has exited. * Do it while holding siglock so that we don't end up * racing against cgroup_exit(). + * + * Interrupts were already disabled while acquiring + * the css_set_lock, so we do not need to disable it + * again when acquiring the sighand->siglock here. */ - spin_lock_irq(&p->sighand->siglock); + spin_lock(&p->sighand->siglock); if (!(p->flags & PF_EXITING)) { struct css_set *cset = task_css_set(p); @@ -1932,11 +1938,11 @@ static void cgroup_enable_task_cg_lists(void) list_add_tail(&p->cg_list, &cset->tasks); get_css_set(cset); } - spin_unlock_irq(&p->sighand->siglock); + spin_unlock(&p->sighand->siglock); } while_each_thread(g, p); read_unlock(&tasklist_lock); out_unlock: - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); } static void init_cgroup_housekeeping(struct cgroup *cgrp) @@ -2043,13 +2049,13 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) * Link the root cgroup in this hierarchy into all the css_set * objects. */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) { link_css_set(&tmp_links, cset, root_cgrp); if (css_set_populated(cset)) cgroup_update_populated(root_cgrp, true); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); BUG_ON(!list_empty(&root_cgrp->self.children)); BUG_ON(atomic_read(&root->nr_cgrps) != 1); @@ -2256,11 +2262,11 @@ out_mount: struct cgroup *cgrp; mutex_lock(&cgroup_mutex); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); cgrp = cset_cgroup_from_root(ns->root_cset, root); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb); @@ -2337,11 +2343,11 @@ char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, char *ret; mutex_lock(&cgroup_mutex); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); return ret; @@ -2369,7 +2375,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) char *path = NULL; mutex_lock(&cgroup_mutex); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id); @@ -2382,7 +2388,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) path = buf; } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); return path; } @@ -2557,7 +2563,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, * the new cgroup. There are no failure cases after here, so this * is the commit point. */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry(cset, &tset->src_csets, mg_node) { list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) { struct css_set *from_cset = task_css_set(task); @@ -2568,7 +2574,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, put_css_set_locked(from_cset); } } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); /* * Migration is committed, all target tasks are now on dst_csets. @@ -2597,13 +2603,13 @@ out_cancel_attach: } } while_each_subsys_mask(); out_release_tset: - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_splice_init(&tset->dst_csets, &tset->src_csets); list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) { list_splice_tail_init(&cset->mg_tasks, &cset->tasks); list_del_init(&cset->mg_node); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); return ret; } @@ -2634,7 +2640,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets) lockdep_assert_held(&cgroup_mutex); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; @@ -2642,7 +2648,7 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets) list_del_init(&cset->mg_preload_node); put_css_set_locked(cset); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); } /** @@ -2783,7 +2789,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup, * already PF_EXITING could be freed from underneath us unless we * take an rcu_read_lock. */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); rcu_read_lock(); task = leader; do { @@ -2792,7 +2798,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup, break; } while_each_thread(leader, task); rcu_read_unlock(); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); return cgroup_taskset_migrate(&tset, root); } @@ -2816,7 +2822,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp, return -EBUSY; /* look up all src csets */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); rcu_read_lock(); task = leader; do { @@ -2826,7 +2832,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp, break; } while_each_thread(leader, task); rcu_read_unlock(); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); /* prepare dst csets and commit */ ret = cgroup_migrate_prepare_dst(&preloaded_csets); @@ -2859,9 +2865,9 @@ static int cgroup_procs_write_permission(struct task_struct *task, struct cgroup *cgrp; struct inode *inode; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); while (!cgroup_is_descendant(dst_cgrp, cgrp)) cgrp = cgroup_parent(cgrp); @@ -2962,9 +2968,9 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) if (root == &cgrp_dfl_root) continue; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); from_cgrp = task_cgroup_from_root(from, root); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); retval = cgroup_attach_task(from_cgrp, tsk, false); if (retval) @@ -3080,7 +3086,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) percpu_down_write(&cgroup_threadgroup_rwsem); /* look up all csses currently attached to @cgrp's subtree */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { struct cgrp_cset_link *link; @@ -3088,14 +3094,14 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) cgroup_migrate_add_src(link->cset, dsct, &preloaded_csets); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); /* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&preloaded_csets); if (ret) goto out_finish; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry(src_cset, &preloaded_csets, mg_preload_node) { struct task_struct *task, *ntask; @@ -3107,7 +3113,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list) cgroup_taskset_add(task, &tset); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); ret = cgroup_taskset_migrate(&tset, cgrp->root); out_finish: @@ -3908,10 +3914,10 @@ static int cgroup_task_count(const struct cgroup *cgrp) int count = 0; struct cgrp_cset_link *link; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) count += atomic_read(&link->cset->refcount); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); return count; } @@ -4249,7 +4255,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, memset(it, 0, sizeof(*it)); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); it->ss = css->ss; @@ -4262,7 +4268,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, css_task_iter_advance_css_set(it); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); } /** @@ -4280,7 +4286,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) it->cur_task = NULL; } - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); if (it->task_pos) { it->cur_task = list_entry(it->task_pos, struct task_struct, @@ -4289,7 +4295,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) css_task_iter_advance(it); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); return it->cur_task; } @@ -4303,10 +4309,10 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) void css_task_iter_end(struct css_task_iter *it) { if (it->cur_cset) { - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_del(&it->iters_node); put_css_set_locked(it->cur_cset); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); } if (it->cur_task) @@ -4338,10 +4344,10 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) mutex_lock(&cgroup_mutex); /* all tasks in @from are being moved, all csets are source */ - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry(link, &from->cset_links, cset_link) cgroup_migrate_add_src(link->cset, to, &preloaded_csets); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); ret = cgroup_migrate_prepare_dst(&preloaded_csets); if (ret) @@ -5063,6 +5069,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css, memset(css, 0, sizeof(*css)); css->cgroup = cgrp; css->ss = ss; + css->id = -1; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); css->serial_nr = css_serial_nr_next++; @@ -5150,7 +5157,7 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL); if (err < 0) - goto err_free_percpu_ref; + goto err_free_css; css->id = err; /* @css is ready to be brought online now, make it visible */ @@ -5174,9 +5181,6 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, err_list_del: list_del_rcu(&css->sibling); - cgroup_idr_remove(&ss->css_idr, css->id); -err_free_percpu_ref: - percpu_ref_exit(&css->refcnt); err_free_css: call_rcu(&css->rcu_head, css_free_rcu_fn); return ERR_PTR(err); @@ -5451,10 +5455,10 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) */ cgrp->self.flags &= ~CSS_ONLINE; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) link->cset->dead = true; - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); /* initiate massacre of all css's */ for_each_css(css, ssid, cgrp) @@ -5725,7 +5729,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, goto out; mutex_lock(&cgroup_mutex); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); for_each_root(root) { struct cgroup_subsys *ss; @@ -5778,7 +5782,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, retval = 0; out_unlock: - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); kfree(buf); out: @@ -5923,13 +5927,13 @@ void cgroup_post_fork(struct task_struct *child) if (use_task_css_set_links) { struct css_set *cset; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); cset = task_css_set(current); if (list_empty(&child->cg_list)) { get_css_set(cset); css_set_move_task(child, NULL, cset, false); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); } /* @@ -5974,9 +5978,9 @@ void cgroup_exit(struct task_struct *tsk) cset = task_css_set(tsk); if (!list_empty(&tsk->cg_list)) { - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); css_set_move_task(tsk, cset, NULL, false); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); } else { get_css_set(cset); } @@ -6044,9 +6048,9 @@ static void cgroup_release_agent(struct work_struct *work) if (!pathbuf || !agentbuf) goto out; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); path = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); if (!path) goto out; @@ -6306,12 +6310,12 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, return ERR_PTR(-EPERM); mutex_lock(&cgroup_mutex); - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); new_ns = alloc_cgroup_ns(); @@ -6435,7 +6439,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v) if (!name_buf) return -ENOMEM; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); rcu_read_lock(); cset = rcu_dereference(current->cgroups); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { @@ -6446,7 +6450,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v) c->root->hierarchy_id, name_buf); } rcu_read_unlock(); - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); kfree(name_buf); return 0; } @@ -6457,7 +6461,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v) struct cgroup_subsys_state *css = seq_css(seq); struct cgrp_cset_link *link; - spin_lock_bh(&css_set_lock); + spin_lock_irq(&css_set_lock); list_for_each_entry(link, &css->cgroup->cset_links, cset_link) { struct css_set *cset = link->cset; struct task_struct *task; @@ -6480,7 +6484,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v) overflow: seq_puts(seq, " ...\n"); } - spin_unlock_bh(&css_set_lock); + spin_unlock_irq(&css_set_lock); return 0; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 274450e..85cd418 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3862,10 +3862,8 @@ static void _free_event(struct perf_event *event) if (event->ctx) put_ctx(event->ctx); - if (event->pmu) { - exclusive_event_destroy(event); - module_put(event->pmu->module); - } + exclusive_event_destroy(event); + module_put(event->pmu->module); call_rcu(&event->rcu_head, free_event_rcu); } @@ -7531,7 +7529,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event) prog = event->tp_event->prog; if (prog) { event->tp_event->prog = NULL; - bpf_prog_put(prog); + bpf_prog_put_rcu(prog); } } diff --git a/kernel/fork.c b/kernel/fork.c index 5c2c355..4a7ec0c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -148,18 +148,18 @@ static inline void free_task_struct(struct task_struct *tsk) } #endif -void __weak arch_release_thread_info(struct thread_info *ti) +void __weak arch_release_thread_stack(unsigned long *stack) { } -#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR +#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ # if THREAD_SIZE >= PAGE_SIZE -static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, +static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP, @@ -172,33 +172,33 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, return page ? page_address(page) : NULL; } -static inline void free_thread_info(struct thread_info *ti) +static inline void free_thread_stack(unsigned long *stack) { - struct page *page = virt_to_page(ti); + struct page *page = virt_to_page(stack); memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK, -(1 << THREAD_SIZE_ORDER)); __free_kmem_pages(page, THREAD_SIZE_ORDER); } # else -static struct kmem_cache *thread_info_cache; +static struct kmem_cache *thread_stack_cache; -static struct thread_info *alloc_thread_info_node(struct task_struct *tsk, +static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { - return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node); + return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); } -static void free_thread_info(struct thread_info *ti) +static void free_thread_stack(unsigned long *stack) { - kmem_cache_free(thread_info_cache, ti); + kmem_cache_free(thread_stack_cache, stack); } -void thread_info_cache_init(void) +void thread_stack_cache_init(void) { - thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE, + thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, NULL); - BUG_ON(thread_info_cache == NULL); + BUG_ON(thread_stack_cache == NULL); } # endif #endif @@ -221,9 +221,9 @@ struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; -static void account_kernel_stack(struct thread_info *ti, int account) +static void account_kernel_stack(unsigned long *stack, int account) { - struct zone *zone = page_zone(virt_to_page(ti)); + struct zone *zone = page_zone(virt_to_page(stack)); mod_zone_page_state(zone, NR_KERNEL_STACK, account); } @@ -231,8 +231,8 @@ static void account_kernel_stack(struct thread_info *ti, int account) void free_task(struct task_struct *tsk) { account_kernel_stack(tsk->stack, -1); - arch_release_thread_info(tsk->stack); - free_thread_info(tsk->stack); + arch_release_thread_stack(tsk->stack); + free_thread_stack(tsk->stack); rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); put_seccomp_filter(tsk); @@ -343,7 +343,7 @@ void set_task_stack_end_magic(struct task_struct *tsk) static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; - struct thread_info *ti; + unsigned long *stack; int err; if (node == NUMA_NO_NODE) @@ -352,15 +352,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) if (!tsk) return NULL; - ti = alloc_thread_info_node(tsk, node); - if (!ti) + stack = alloc_thread_stack_node(tsk, node); + if (!stack) goto free_tsk; err = arch_dup_task_struct(tsk, orig); if (err) - goto free_ti; + goto free_stack; - tsk->stack = ti; + tsk->stack = stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under @@ -392,14 +392,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; - account_kernel_stack(ti, 1); + account_kernel_stack(stack, 1); kcov_task_init(tsk); return tsk; -free_ti: - free_thread_info(ti); +free_stack: + free_thread_stack(stack); free_tsk: free_task_struct(tsk); return NULL; diff --git a/kernel/futex.c b/kernel/futex.c index ee25f5b..33664f7 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -469,7 +469,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; - struct page *page; + struct page *page, *tail; struct address_space *mapping; int err, ro = 0; @@ -530,7 +530,15 @@ again: * considered here and page lock forces unnecessarily serialization * From this point on, mapping will be re-verified if necessary and * page lock will be acquired only if it is unavoidable - */ + * + * Mapping checks require the head page for any compound page so the + * head page and mapping is looked up now. For anonymous pages, it + * does not matter if the page splits in the future as the key is + * based on the address. For filesystem-backed pages, the tail is + * required as the index of the page determines the key. For + * base pages, there is no tail page and tail == page. + */ + tail = page; page = compound_head(page); mapping = READ_ONCE(page->mapping); @@ -654,7 +662,7 @@ again: key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.inode = inode; - key->shared.pgoff = basepage_index(page); + key->shared.pgoff = basepage_index(tail); rcu_read_unlock(); } diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 05254ee..4b353e0 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -58,13 +58,36 @@ static void jump_label_update(struct static_key *key); void static_key_slow_inc(struct static_key *key) { + int v, v1; + STATIC_KEY_CHECK_USE(); - if (atomic_inc_not_zero(&key->enabled)) - return; + + /* + * Careful if we get concurrent static_key_slow_inc() calls; + * later calls must wait for the first one to _finish_ the + * jump_label_update() process. At the same time, however, + * the jump_label_update() call below wants to see + * static_key_enabled(&key) for jumps to be updated properly. + * + * So give a special meaning to negative key->enabled: it sends + * static_key_slow_inc() down the slow path, and it is non-zero + * so it counts as "enabled" in jump_label_update(). Note that + * atomic_inc_unless_negative() checks >= 0, so roll our own. + */ + for (v = atomic_read(&key->enabled); v > 0; v = v1) { + v1 = atomic_cmpxchg(&key->enabled, v, v + 1); + if (likely(v1 == v)) + return; + } jump_label_lock(); - if (atomic_inc_return(&key->enabled) == 1) + if (atomic_read(&key->enabled) == 0) { + atomic_set(&key->enabled, -1); jump_label_update(key); + atomic_set(&key->enabled, 1); + } else { + atomic_inc(&key->enabled); + } jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_slow_inc); @@ -72,6 +95,13 @@ EXPORT_SYMBOL_GPL(static_key_slow_inc); static void __static_key_slow_dec(struct static_key *key, unsigned long rate_limit, struct delayed_work *work) { + /* + * The negative count check is valid even when a negative + * key->enabled is in use by static_key_slow_inc(); a + * __static_key_slow_dec() before the first static_key_slow_inc() + * returns is unbalanced, because all other static_key_slow_inc() + * instances block while the update is in progress. + */ if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) { WARN(atomic_read(&key->enabled) < 0, "jump label: negative count!\n"); diff --git a/kernel/kcov.c b/kernel/kcov.c index a02f2dd..8d44b3f 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -264,7 +264,12 @@ static const struct file_operations kcov_fops = { static int __init kcov_init(void) { - if (!debugfs_create_file("kcov", 0600, NULL, NULL, &kcov_fops)) { + /* + * The kcov debugfs file won't ever get removed and thus, + * there is no need to protect it against removal races. The + * use of debugfs_create_file_unsafe() is actually safe here. + */ + if (!debugfs_create_file_unsafe("kcov", 0600, NULL, NULL, &kcov_fops)) { pr_err("failed to create kcov in debugfs\n"); return -ENOMEM; } diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c index 3ef3736..9c951fa 100644 --- a/kernel/locking/mutex-debug.c +++ b/kernel/locking/mutex-debug.c @@ -49,21 +49,21 @@ void debug_mutex_free_waiter(struct mutex_waiter *waiter) } void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, - struct thread_info *ti) + struct task_struct *task) { SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock)); /* Mark the current thread as blocked on the lock: */ - ti->task->blocked_on = waiter; + task->blocked_on = waiter; } void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, - struct thread_info *ti) + struct task_struct *task) { DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list)); - DEBUG_LOCKS_WARN_ON(waiter->task != ti->task); - DEBUG_LOCKS_WARN_ON(ti->task->blocked_on != waiter); - ti->task->blocked_on = NULL; + DEBUG_LOCKS_WARN_ON(waiter->task != task); + DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter); + task->blocked_on = NULL; list_del_init(&waiter->list); waiter->task = NULL; diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h index 0799fd3..d06ae3b 100644 --- a/kernel/locking/mutex-debug.h +++ b/kernel/locking/mutex-debug.h @@ -20,9 +20,9 @@ extern void debug_mutex_wake_waiter(struct mutex *lock, extern void debug_mutex_free_waiter(struct mutex_waiter *waiter); extern void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, - struct thread_info *ti); + struct task_struct *task); extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, - struct thread_info *ti); + struct task_struct *task); extern void debug_mutex_unlock(struct mutex *lock); extern void debug_mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key); diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index e364b42..a70b90d 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -486,9 +486,6 @@ __ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx) if (!hold_ctx) return 0; - if (unlikely(ctx == hold_ctx)) - return -EALREADY; - if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { #ifdef CONFIG_DEBUG_MUTEXES @@ -514,6 +511,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, unsigned long flags; int ret; + if (use_ww_ctx) { + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); + if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) + return -EALREADY; + } + preempt_disable(); mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); @@ -534,7 +537,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, goto skip_wait; debug_mutex_lock_common(lock, &waiter); - debug_mutex_add_waiter(lock, &waiter, task_thread_info(task)); + debug_mutex_add_waiter(lock, &waiter, task); /* add waiting tasks to the end of the waitqueue (FIFO): */ list_add_tail(&waiter.list, &lock->wait_list); @@ -581,7 +584,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, } __set_task_state(task, TASK_RUNNING); - mutex_remove_waiter(lock, &waiter, current_thread_info()); + mutex_remove_waiter(lock, &waiter, task); /* set it to 0 if there are no waiters left: */ if (likely(list_empty(&lock->wait_list))) atomic_set(&lock->count, 0); @@ -602,7 +605,7 @@ skip_wait: return 0; err: - mutex_remove_waiter(lock, &waiter, task_thread_info(task)); + mutex_remove_waiter(lock, &waiter, task); spin_unlock_mutex(&lock->wait_lock, flags); debug_mutex_free_waiter(&waiter); mutex_release(&lock->dep_map, 1, ip); diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h index 5cda397..a68bae5 100644 --- a/kernel/locking/mutex.h +++ b/kernel/locking/mutex.h @@ -13,7 +13,7 @@ do { spin_lock(lock); (void)(flags); } while (0) #define spin_unlock_mutex(lock, flags) \ do { spin_unlock(lock); (void)(flags); } while (0) -#define mutex_remove_waiter(lock, waiter, ti) \ +#define mutex_remove_waiter(lock, waiter, task) \ __list_del((waiter)->list.prev, (waiter)->list.next) #ifdef CONFIG_MUTEX_SPIN_ON_OWNER diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index ce2f75e..5fc8c31 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -267,6 +267,66 @@ static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock, #define queued_spin_lock_slowpath native_queued_spin_lock_slowpath #endif +/* + * queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before + * issuing an _unordered_ store to set _Q_LOCKED_VAL. + * + * This means that the store can be delayed, but no later than the + * store-release from the unlock. This means that simply observing + * _Q_LOCKED_VAL is not sufficient to determine if the lock is acquired. + * + * There are two paths that can issue the unordered store: + * + * (1) clear_pending_set_locked(): *,1,0 -> *,0,1 + * + * (2) set_locked(): t,0,0 -> t,0,1 ; t != 0 + * atomic_cmpxchg_relaxed(): t,0,0 -> 0,0,1 + * + * However, in both cases we have other !0 state we've set before to queue + * ourseves: + * + * For (1) we have the atomic_cmpxchg_acquire() that set _Q_PENDING_VAL, our + * load is constrained by that ACQUIRE to not pass before that, and thus must + * observe the store. + * + * For (2) we have a more intersting scenario. We enqueue ourselves using + * xchg_tail(), which ends up being a RELEASE. This in itself is not + * sufficient, however that is followed by an smp_cond_acquire() on the same + * word, giving a RELEASE->ACQUIRE ordering. This again constrains our load and + * guarantees we must observe that store. + * + * Therefore both cases have other !0 state that is observable before the + * unordered locked byte store comes through. This means we can use that to + * wait for the lock store, and then wait for an unlock. + */ +#ifndef queued_spin_unlock_wait +void queued_spin_unlock_wait(struct qspinlock *lock) +{ + u32 val; + + for (;;) { + val = atomic_read(&lock->val); + + if (!val) /* not locked, we're done */ + goto done; + + if (val & _Q_LOCKED_MASK) /* locked, go wait for unlock */ + break; + + /* not locked, but pending, wait until we observe the lock */ + cpu_relax(); + } + + /* any unlock is good */ + while (atomic_read(&lock->val) & _Q_LOCKED_MASK) + cpu_relax(); + +done: + smp_rmb(); /* CTRL + RMB -> ACQUIRE */ +} +EXPORT_SYMBOL(queued_spin_unlock_wait); +#endif + #endif /* _GEN_PV_LOCK_SLOWPATH */ /** diff --git a/kernel/power/process.c b/kernel/power/process.c index df058be..0c2ee97 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -146,6 +146,18 @@ int freeze_processes(void) if (!error && !oom_killer_disable()) error = -EBUSY; + /* + * There is a hard to fix race between oom_reaper kernel thread + * and oom_killer_disable. oom_reaper calls exit_oom_victim + * before the victim reaches exit_mm so try to freeze all the tasks + * again and catch such a left over task. + */ + if (!error) { + pr_info("Double checking all user space processes after OOM killer disable... "); + error = try_to_freeze_tasks(true); + pr_cont("\n"); + } + if (error) thaw_processes(); return error; diff --git a/kernel/relay.c b/kernel/relay.c index 074994b..04d7cf3 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -614,6 +614,7 @@ free_bufs: kref_put(&chan->kref, relay_destroy_channel); mutex_unlock(&relay_channels_mutex); + kfree(chan); return NULL; } EXPORT_SYMBOL_GPL(relay_open); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7f2cae4..51d7105 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1536,7 +1536,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) for (;;) { /* Any allowed, online CPU? */ for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) { - if (!cpu_active(dest_cpu)) + if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu)) + continue; + if (!cpu_online(dest_cpu)) continue; goto out; } @@ -2253,9 +2255,11 @@ int sysctl_numa_balancing(struct ctl_table *table, int write, #endif #endif +#ifdef CONFIG_SCHEDSTATS + DEFINE_STATIC_KEY_FALSE(sched_schedstats); +static bool __initdata __sched_schedstats = false; -#ifdef CONFIG_SCHEDSTATS static void set_schedstats(bool enabled) { if (enabled) @@ -2278,11 +2282,16 @@ static int __init setup_schedstats(char *str) if (!str) goto out; + /* + * This code is called before jump labels have been set up, so we can't + * change the static branch directly just yet. Instead set a temporary + * variable so init_schedstats() can do it later. + */ if (!strcmp(str, "enable")) { - set_schedstats(true); + __sched_schedstats = true; ret = 1; } else if (!strcmp(str, "disable")) { - set_schedstats(false); + __sched_schedstats = false; ret = 1; } out: @@ -2293,6 +2302,11 @@ out: } __setup("schedstats=", setup_schedstats); +static void __init init_schedstats(void) +{ + set_schedstats(__sched_schedstats); +} + #ifdef CONFIG_PROC_SYSCTL int sysctl_schedstats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -2313,8 +2327,10 @@ int sysctl_schedstats(struct ctl_table *table, int write, set_schedstats(state); return err; } -#endif -#endif +#endif /* CONFIG_PROC_SYSCTL */ +#else /* !CONFIG_SCHEDSTATS */ +static inline void init_schedstats(void) {} +#endif /* CONFIG_SCHEDSTATS */ /* * fork()/clone()-time setup: @@ -2521,10 +2537,9 @@ void wake_up_new_task(struct task_struct *p) */ set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); #endif - /* Post initialize new task's util average when its cfs_rq is set */ + rq = __task_rq_lock(p, &rf); post_init_entity_util_avg(&p->se); - rq = __task_rq_lock(p, &rf); activate_task(rq, p, 0); p->on_rq = TASK_ON_RQ_QUEUED; trace_sched_wakeup_new(p); @@ -3156,7 +3171,8 @@ static noinline void __schedule_bug(struct task_struct *prev) static inline void schedule_debug(struct task_struct *prev) { #ifdef CONFIG_SCHED_STACK_END_CHECK - BUG_ON(task_stack_end_corrupted(prev)); + if (task_stack_end_corrupted(prev)) + panic("corrupted stack end detected inside scheduler\n"); #endif if (unlikely(in_atomic_preempt_off())) { @@ -5133,14 +5149,16 @@ void show_state_filter(unsigned long state_filter) /* * reset the NMI-timeout, listing all files on a slow * console might take a lot of time: + * Also, reset softlockup watchdogs on all CPUs, because + * another CPU might be blocked waiting for us to process + * an IPI. */ touch_nmi_watchdog(); + touch_all_softlockup_watchdogs(); if (!state_filter || (p->state & state_filter)) sched_show_task(p); } - touch_all_softlockup_watchdogs(); - #ifdef CONFIG_SCHED_DEBUG if (!state_filter) sysrq_sched_debug_show(); @@ -7487,6 +7505,8 @@ void __init sched_init(void) #endif init_sched_fair_class(); + init_schedstats(); + scheduler_running = 1; } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index cf905f6..0368c39 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -427,19 +427,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) SPLIT_NS(p->se.vruntime), (long long)(p->nvcsw + p->nivcsw), p->prio); -#ifdef CONFIG_SCHEDSTATS - if (schedstat_enabled()) { - SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", - SPLIT_NS(p->se.statistics.wait_sum), - SPLIT_NS(p->se.sum_exec_runtime), - SPLIT_NS(p->se.statistics.sum_sleep_runtime)); - } -#else + SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", - 0LL, 0L, + SPLIT_NS(schedstat_val(p, se.statistics.wait_sum)), SPLIT_NS(p->se.sum_exec_runtime), - 0LL, 0L); -#endif + SPLIT_NS(schedstat_val(p, se.statistics.sum_sleep_runtime))); + #ifdef CONFIG_NUMA_BALANCING SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p)); #endif diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 218f8e8..bdcbeea 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2904,6 +2904,23 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq) } } +/* + * Unsigned subtract and clamp on underflow. + * + * Explicitly do a load-store to ensure the intermediate value never hits + * memory. This allows lockless observations without ever seeing the negative + * values. + */ +#define sub_positive(_ptr, _val) do { \ + typeof(_ptr) ptr = (_ptr); \ + typeof(*ptr) val = (_val); \ + typeof(*ptr) res, var = READ_ONCE(*ptr); \ + res = var - val; \ + if (res > var) \ + res = 0; \ + WRITE_ONCE(*ptr, res); \ +} while (0) + /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) @@ -2913,15 +2930,15 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) if (atomic_long_read(&cfs_rq->removed_load_avg)) { s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0); - sa->load_avg = max_t(long, sa->load_avg - r, 0); - sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0); + sub_positive(&sa->load_avg, r); + sub_positive(&sa->load_sum, r * LOAD_AVG_MAX); removed_load = 1; } if (atomic_long_read(&cfs_rq->removed_util_avg)) { long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0); - sa->util_avg = max_t(long, sa->util_avg - r, 0); - sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0); + sub_positive(&sa->util_avg, r); + sub_positive(&sa->util_sum, r * LOAD_AVG_MAX); removed_util = 1; } @@ -2994,10 +3011,10 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s &se->avg, se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL); - cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0); - cfs_rq->avg.load_sum = max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0); - cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0); - cfs_rq->avg.util_sum = max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0); + sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg); + sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum); + sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg); + sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum); cfs_rq_util_change(cfs_rq); } @@ -3246,7 +3263,7 @@ static inline void check_schedstat_required(void) trace_sched_stat_iowait_enabled() || trace_sched_stat_blocked_enabled() || trace_sched_stat_runtime_enabled()) { - pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, " + printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, " "stat_blocked and stat_runtime require the " "kernel parameter schedstats=enabled or " "kernel.sched_schedstats=1\n"); @@ -4185,6 +4202,26 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq) if (!cfs_bandwidth_used()) return; + /* Synchronize hierarchical throttle counter: */ + if (unlikely(!cfs_rq->throttle_uptodate)) { + struct rq *rq = rq_of(cfs_rq); + struct cfs_rq *pcfs_rq; + struct task_group *tg; + + cfs_rq->throttle_uptodate = 1; + + /* Get closest up-to-date node, because leaves go first: */ + for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) { + pcfs_rq = tg->cfs_rq[cpu_of(rq)]; + if (pcfs_rq->throttle_uptodate) + break; + } + if (tg) { + cfs_rq->throttle_count = pcfs_rq->throttle_count; + cfs_rq->throttled_clock_task = rq_clock_task(rq); + } + } + /* an active group must be handled by the update_curr()->put() path */ if (!cfs_rq->runtime_enabled || cfs_rq->curr) return; @@ -4500,15 +4537,14 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) { + /* Avoid re-evaluating load for this entity: */ + se = parent_entity(se); /* * 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); + if (task_sleep && se && !throttled_hierarchy(cfs_rq)) + set_next_buddy(se); break; } flags |= DEQUEUE_SLEEP; @@ -8496,8 +8532,9 @@ void free_fair_sched_group(struct task_group *tg) int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) { - struct cfs_rq *cfs_rq; struct sched_entity *se; + struct cfs_rq *cfs_rq; + struct rq *rq; int i; tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL); @@ -8512,6 +8549,8 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) init_cfs_bandwidth(tg_cfs_bandwidth(tg)); for_each_possible_cpu(i) { + rq = cpu_rq(i); + cfs_rq = kzalloc_node(sizeof(struct cfs_rq), GFP_KERNEL, cpu_to_node(i)); if (!cfs_rq) @@ -8525,7 +8564,10 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) init_cfs_rq(cfs_rq); init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); init_entity_runnable_average(se); + + raw_spin_lock_irq(&rq->lock); post_init_entity_util_avg(se); + raw_spin_unlock_irq(&rq->lock); } return 1; diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index bd12c6c..c5aeedf 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -127,7 +127,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev, */ static void cpuidle_idle_call(void) { - struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); + struct cpuidle_device *dev = cpuidle_get_device(); struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); int next_state, entered_state; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 72f1f30..7cbeb92 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -437,7 +437,7 @@ struct cfs_rq { u64 throttled_clock, throttled_clock_task; u64 throttled_clock_task_time; - int throttled, throttle_count; + int throttled, throttle_count, throttle_uptodate; struct list_head throttled_list; #endif /* CONFIG_CFS_BANDWIDTH */ #endif /* CONFIG_FAIR_GROUP_SCHED */ diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 70b3b6a..78955cb 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -33,6 +33,8 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) # define schedstat_inc(rq, field) do { if (schedstat_enabled()) { (rq)->field++; } } while (0) # define schedstat_add(rq, field, amt) do { if (schedstat_enabled()) { (rq)->field += (amt); } } while (0) # define schedstat_set(var, val) do { if (schedstat_enabled()) { var = (val); } } while (0) +# define schedstat_val(rq, field) ((schedstat_enabled()) ? (rq)->field : 0) + #else /* !CONFIG_SCHEDSTATS */ static inline void rq_sched_info_arrive(struct rq *rq, unsigned long long delta) @@ -47,6 +49,7 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta) # define schedstat_inc(rq, field) do { } while (0) # define schedstat_add(rq, field, amt) do { } while (0) # define schedstat_set(var, val) do { } while (0) +# define schedstat_val(rq, field) 0 #endif #ifdef CONFIG_SCHED_INFO diff --git a/kernel/signal.c b/kernel/signal.c index 96e9bc4..af21afc 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2751,23 +2751,18 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) * @ts: upper bound on process time suspension */ int do_sigtimedwait(const sigset_t *which, siginfo_t *info, - const struct timespec *ts) + const struct timespec *ts) { + ktime_t *to = NULL, timeout = { .tv64 = KTIME_MAX }; struct task_struct *tsk = current; - long timeout = MAX_SCHEDULE_TIMEOUT; sigset_t mask = *which; - int sig; + int sig, ret = 0; 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++; + timeout = timespec_to_ktime(*ts); + to = &timeout; } /* @@ -2778,7 +2773,7 @@ int do_sigtimedwait(const sigset_t *which, siginfo_t *info, spin_lock_irq(&tsk->sighand->siglock); sig = dequeue_signal(tsk, &mask, info); - if (!sig && timeout) { + if (!sig && timeout.tv64) { /* * None ready, temporarily unblock those we're interested * while we are sleeping in so that we'll be awakened when @@ -2790,8 +2785,9 @@ int do_sigtimedwait(const sigset_t *which, siginfo_t *info, recalc_sigpending(); spin_unlock_irq(&tsk->sighand->siglock); - timeout = freezable_schedule_timeout_interruptible(timeout); - + __set_current_state(TASK_INTERRUPTIBLE); + ret = freezable_schedule_hrtimeout_range(to, tsk->timer_slack_ns, + HRTIMER_MODE_REL); spin_lock_irq(&tsk->sighand->siglock); __set_task_blocked(tsk, &tsk->real_blocked); sigemptyset(&tsk->real_blocked); @@ -2801,7 +2797,7 @@ int do_sigtimedwait(const sigset_t *which, siginfo_t *info, if (sig) return sig; - return timeout ? -EINTR : -EAGAIN; + return ret ? -EINTR : -EAGAIN; } /** diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 966a5a6..f738251 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -164,3 +164,4 @@ static inline void timers_update_migration(bool update_nohz) { } DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases); extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem); +void timer_clear_idle(void); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index db57d1b..2ec7c00 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -700,6 +700,12 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, delta = next_tick - basemono; if (delta <= (u64)TICK_NSEC) { tick.tv64 = 0; + + /* + * Tell the timer code that the base is not idle, i.e. undo + * the effect of get_next_timer_interrupt(): + */ + timer_clear_idle(); /* * We've not stopped the tick yet, and there's a timer in the * next period, so no point in stopping it either, bail. @@ -809,6 +815,12 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) tick_do_update_jiffies64(now); cpu_load_update_nohz_stop(); + /* + * Clear the timer idle flag, so we avoid IPIs on remote queueing and + * the clock forward checks in the enqueue path: + */ + timer_clear_idle(); + calc_load_exit_idle(); touch_softlockup_watchdog_sched(); /* @@ -1092,35 +1104,6 @@ static void tick_nohz_switch_to_nohz(void) tick_nohz_activate(ts, NOHZ_MODE_LOWRES); } -/* - * When NOHZ is enabled and the tick is stopped, we need to kick the - * tick timer from irq_enter() so that the jiffies update is kept - * alive during long running softirqs. That's ugly as hell, but - * correctness is key even if we need to fix the offending softirq in - * the first place. - * - * Note, this is different to tick_nohz_restart. We just kick the - * timer and do not touch the other magic bits which need to be done - * when idle is left. - */ -static void tick_nohz_kick_tick(struct tick_sched *ts, ktime_t now) -{ -#if 0 - /* Switch back to 2.6.27 behaviour */ - ktime_t delta; - - /* - * Do not touch the tick device, when the next expiry is either - * already reached or less/equal than the tick period. - */ - delta = ktime_sub(hrtimer_get_expires(&ts->sched_timer), now); - if (delta.tv64 <= tick_period.tv64) - return; - - tick_nohz_restart(ts, now); -#endif -} - static inline void tick_nohz_irq_enter(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); @@ -1131,10 +1114,8 @@ static inline void tick_nohz_irq_enter(void) now = ktime_get(); if (ts->idle_active) tick_nohz_stop_idle(ts, now); - if (ts->tick_stopped) { + if (ts->tick_stopped) tick_nohz_update_jiffies(now); - tick_nohz_kick_tick(ts, now); - } } #else diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 67dd610..cb9ab40 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -59,43 +59,153 @@ __visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); /* - * per-CPU timer vector definitions: + * The timer wheel has LVL_DEPTH array levels. Each level provides an array of + * LVL_SIZE buckets. Each level is driven by its own clock and therefor each + * level has a different granularity. + * + * The level granularity is: LVL_CLK_DIV ^ lvl + * The level clock frequency is: HZ / (LVL_CLK_DIV ^ level) + * + * The array level of a newly armed timer depends on the relative expiry + * time. The farther the expiry time is away the higher the array level and + * therefor the granularity becomes. + * + * Contrary to the original timer wheel implementation, which aims for 'exact' + * expiry of the timers, this implementation removes the need for recascading + * the timers into the lower array levels. The previous 'classic' timer wheel + * implementation of the kernel already violated the 'exact' expiry by adding + * slack to the expiry time to provide batched expiration. The granularity + * levels provide implicit batching. + * + * This is an optimization of the original timer wheel implementation for the + * majority of the timer wheel use cases: timeouts. The vast majority of + * timeout timers (networking, disk I/O ...) are canceled before expiry. If + * the timeout expires it indicates that normal operation is disturbed, so it + * does not matter much whether the timeout comes with a slight delay. + * + * The only exception to this are networking timers with a small expiry + * time. They rely on the granularity. Those fit into the first wheel level, + * which has HZ granularity. + * + * We don't have cascading anymore. timers with a expiry time above the + * capacity of the last wheel level are force expired at the maximum timeout + * value of the last wheel level. From data sampling we know that the maximum + * value observed is 5 days (network connection tracking), so this should not + * be an issue. + * + * The currently chosen array constants values are a good compromise between + * array size and granularity. + * + * This results in the following granularity and range levels: + * + * HZ 1000 steps + * Level Offset Granularity Range + * 0 0 1 ms 0 ms - 63 ms + * 1 64 8 ms 64 ms - 511 ms + * 2 128 64 ms 512 ms - 4095 ms (512ms - ~4s) + * 3 192 512 ms 4096 ms - 32767 ms (~4s - ~32s) + * 4 256 4096 ms (~4s) 32768 ms - 262143 ms (~32s - ~4m) + * 5 320 32768 ms (~32s) 262144 ms - 2097151 ms (~4m - ~34m) + * 6 384 262144 ms (~4m) 2097152 ms - 16777215 ms (~34m - ~4h) + * 7 448 2097152 ms (~34m) 16777216 ms - 134217727 ms (~4h - ~1d) + * 8 512 16777216 ms (~4h) 134217728 ms - 1073741822 ms (~1d - ~12d) + * + * HZ 300 + * Level Offset Granularity Range + * 0 0 3 ms 0 ms - 210 ms + * 1 64 26 ms 213 ms - 1703 ms (213ms - ~1s) + * 2 128 213 ms 1706 ms - 13650 ms (~1s - ~13s) + * 3 192 1706 ms (~1s) 13653 ms - 109223 ms (~13s - ~1m) + * 4 256 13653 ms (~13s) 109226 ms - 873810 ms (~1m - ~14m) + * 5 320 109226 ms (~1m) 873813 ms - 6990503 ms (~14m - ~1h) + * 6 384 873813 ms (~14m) 6990506 ms - 55924050 ms (~1h - ~15h) + * 7 448 6990506 ms (~1h) 55924053 ms - 447392423 ms (~15h - ~5d) + * 8 512 55924053 ms (~15h) 447392426 ms - 3579139406 ms (~5d - ~41d) + * + * HZ 250 + * Level Offset Granularity Range + * 0 0 4 ms 0 ms - 255 ms + * 1 64 32 ms 256 ms - 2047 ms (256ms - ~2s) + * 2 128 256 ms 2048 ms - 16383 ms (~2s - ~16s) + * 3 192 2048 ms (~2s) 16384 ms - 131071 ms (~16s - ~2m) + * 4 256 16384 ms (~16s) 131072 ms - 1048575 ms (~2m - ~17m) + * 5 320 131072 ms (~2m) 1048576 ms - 8388607 ms (~17m - ~2h) + * 6 384 1048576 ms (~17m) 8388608 ms - 67108863 ms (~2h - ~18h) + * 7 448 8388608 ms (~2h) 67108864 ms - 536870911 ms (~18h - ~6d) + * 8 512 67108864 ms (~18h) 536870912 ms - 4294967288 ms (~6d - ~49d) + * + * HZ 100 + * Level Offset Granularity Range + * 0 0 10 ms 0 ms - 630 ms + * 1 64 80 ms 640 ms - 5110 ms (640ms - ~5s) + * 2 128 640 ms 5120 ms - 40950 ms (~5s - ~40s) + * 3 192 5120 ms (~5s) 40960 ms - 327670 ms (~40s - ~5m) + * 4 256 40960 ms (~40s) 327680 ms - 2621430 ms (~5m - ~43m) + * 5 320 327680 ms (~5m) 2621440 ms - 20971510 ms (~43m - ~5h) + * 6 384 2621440 ms (~43m) 20971520 ms - 167772150 ms (~5h - ~1d) + * 7 448 20971520 ms (~5h) 167772160 ms - 1342177270 ms (~1d - ~15d) */ -#define TVN_BITS (CONFIG_BASE_SMALL ? 4 : 6) -#define TVR_BITS (CONFIG_BASE_SMALL ? 6 : 8) -#define TVN_SIZE (1 << TVN_BITS) -#define TVR_SIZE (1 << TVR_BITS) -#define TVN_MASK (TVN_SIZE - 1) -#define TVR_MASK (TVR_SIZE - 1) -#define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1)) - -struct tvec { - struct hlist_head vec[TVN_SIZE]; -}; -struct tvec_root { - struct hlist_head vec[TVR_SIZE]; -}; +/* Clock divisor for the next level */ +#define LVL_CLK_SHIFT 3 +#define LVL_CLK_DIV (1UL << LVL_CLK_SHIFT) +#define LVL_CLK_MASK (LVL_CLK_DIV - 1) +#define LVL_SHIFT(n) ((n) * LVL_CLK_SHIFT) +#define LVL_GRAN(n) (1UL << LVL_SHIFT(n)) -struct tvec_base { - spinlock_t lock; - struct timer_list *running_timer; - unsigned long timer_jiffies; - unsigned long next_timer; - unsigned long active_timers; - unsigned long all_timers; - int cpu; - bool migration_enabled; - bool nohz_active; - struct tvec_root tv1; - struct tvec tv2; - struct tvec tv3; - struct tvec tv4; - struct tvec tv5; -} ____cacheline_aligned; +/* + * The time start value for each level to select the bucket at enqueue + * time. + */ +#define LVL_START(n) ((LVL_SIZE - 1) << (((n) - 1) * LVL_CLK_SHIFT)) + +/* Size of each clock level */ +#define LVL_BITS 6 +#define LVL_SIZE (1UL << LVL_BITS) +#define LVL_MASK (LVL_SIZE - 1) +#define LVL_OFFS(n) ((n) * LVL_SIZE) + +/* Level depth */ +#if HZ > 100 +# define LVL_DEPTH 9 +# else +# define LVL_DEPTH 8 +#endif + +/* The cutoff (max. capacity of the wheel) */ +#define WHEEL_TIMEOUT_CUTOFF (LVL_START(LVL_DEPTH)) +#define WHEEL_TIMEOUT_MAX (WHEEL_TIMEOUT_CUTOFF - LVL_GRAN(LVL_DEPTH - 1)) + +/* + * The resulting wheel size. If NOHZ is configured we allocate two + * wheels so we have a separate storage for the deferrable timers. + */ +#define WHEEL_SIZE (LVL_SIZE * LVL_DEPTH) + +#ifdef CONFIG_NO_HZ_COMMON +# define NR_BASES 2 +# define BASE_STD 0 +# define BASE_DEF 1 +#else +# define NR_BASES 1 +# define BASE_STD 0 +# define BASE_DEF 0 +#endif +struct timer_base { + spinlock_t lock; + struct timer_list *running_timer; + unsigned long clk; + unsigned long next_expiry; + unsigned int cpu; + bool migration_enabled; + bool nohz_active; + bool is_idle; + DECLARE_BITMAP(pending_map, WHEEL_SIZE); + struct hlist_head vectors[WHEEL_SIZE]; +} ____cacheline_aligned; -static DEFINE_PER_CPU(struct tvec_base, tvec_bases); +static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]); #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) unsigned int sysctl_timer_migration = 1; @@ -106,15 +216,17 @@ void timers_update_migration(bool update_nohz) unsigned int cpu; /* Avoid the loop, if nothing to update */ - if (this_cpu_read(tvec_bases.migration_enabled) == on) + if (this_cpu_read(timer_bases[BASE_STD].migration_enabled) == on) return; for_each_possible_cpu(cpu) { - per_cpu(tvec_bases.migration_enabled, cpu) = on; + per_cpu(timer_bases[BASE_STD].migration_enabled, cpu) = on; + per_cpu(timer_bases[BASE_DEF].migration_enabled, cpu) = on; per_cpu(hrtimer_bases.migration_enabled, cpu) = on; if (!update_nohz) continue; - per_cpu(tvec_bases.nohz_active, cpu) = true; + per_cpu(timer_bases[BASE_STD].nohz_active, cpu) = true; + per_cpu(timer_bases[BASE_DEF].nohz_active, cpu) = true; per_cpu(hrtimer_bases.nohz_active, cpu) = true; } } @@ -133,20 +245,6 @@ int timer_migration_handler(struct ctl_table *table, int write, mutex_unlock(&mutex); return ret; } - -static inline struct tvec_base *get_target_base(struct tvec_base *base, - int pinned) -{ - if (pinned || !base->migration_enabled) - return this_cpu_ptr(&tvec_bases); - return per_cpu_ptr(&tvec_bases, get_nohz_timer_target()); -} -#else -static inline struct tvec_base *get_target_base(struct tvec_base *base, - int pinned) -{ - return this_cpu_ptr(&tvec_bases); -} #endif static unsigned long round_jiffies_common(unsigned long j, int cpu, @@ -351,101 +449,126 @@ unsigned long round_jiffies_up_relative(unsigned long j) } EXPORT_SYMBOL_GPL(round_jiffies_up_relative); -/** - * set_timer_slack - set the allowed slack for a timer - * @timer: the timer to be modified - * @slack_hz: the amount of time (in jiffies) allowed for rounding - * - * Set the amount of time, in jiffies, that a certain timer has - * in terms of slack. By setting this value, the timer subsystem - * will schedule the actual timer somewhere between - * the time mod_timer() asks for, and that time plus the slack. - * - * By setting the slack to -1, a percentage of the delay is used - * instead. - */ -void set_timer_slack(struct timer_list *timer, int slack_hz) + +static inline unsigned int timer_get_idx(struct timer_list *timer) { - timer->slack = slack_hz; + return (timer->flags & TIMER_ARRAYMASK) >> TIMER_ARRAYSHIFT; } -EXPORT_SYMBOL_GPL(set_timer_slack); -static void -__internal_add_timer(struct tvec_base *base, struct timer_list *timer) +static inline void timer_set_idx(struct timer_list *timer, unsigned int idx) { - unsigned long expires = timer->expires; - unsigned long idx = expires - base->timer_jiffies; - struct hlist_head *vec; + timer->flags = (timer->flags & ~TIMER_ARRAYMASK) | + idx << TIMER_ARRAYSHIFT; +} - if (idx < TVR_SIZE) { - int i = expires & TVR_MASK; - vec = base->tv1.vec + i; - } else if (idx < 1 << (TVR_BITS + TVN_BITS)) { - int i = (expires >> TVR_BITS) & TVN_MASK; - vec = base->tv2.vec + i; - } else if (idx < 1 << (TVR_BITS + 2 * TVN_BITS)) { - int i = (expires >> (TVR_BITS + TVN_BITS)) & TVN_MASK; - vec = base->tv3.vec + i; - } else if (idx < 1 << (TVR_BITS + 3 * TVN_BITS)) { - int i = (expires >> (TVR_BITS + 2 * TVN_BITS)) & TVN_MASK; - vec = base->tv4.vec + i; - } else if ((signed long) idx < 0) { - /* - * Can happen if you add a timer with expires == jiffies, - * or you set a timer to go off in the past - */ - vec = base->tv1.vec + (base->timer_jiffies & TVR_MASK); +/* + * Helper function to calculate the array index for a given expiry + * time. + */ +static inline unsigned calc_index(unsigned expires, unsigned lvl) +{ + expires = (expires + LVL_GRAN(lvl)) >> LVL_SHIFT(lvl); + return LVL_OFFS(lvl) + (expires & LVL_MASK); +} + +static int calc_wheel_index(unsigned long expires, unsigned long clk) +{ + unsigned long delta = expires - clk; + unsigned int idx; + + if (delta < LVL_START(1)) { + idx = calc_index(expires, 0); + } else if (delta < LVL_START(2)) { + idx = calc_index(expires, 1); + } else if (delta < LVL_START(3)) { + idx = calc_index(expires, 2); + } else if (delta < LVL_START(4)) { + idx = calc_index(expires, 3); + } else if (delta < LVL_START(5)) { + idx = calc_index(expires, 4); + } else if (delta < LVL_START(6)) { + idx = calc_index(expires, 5); + } else if (delta < LVL_START(7)) { + idx = calc_index(expires, 6); + } else if (LVL_DEPTH > 8 && delta < LVL_START(8)) { + idx = calc_index(expires, 7); + } else if ((long) delta < 0) { + idx = clk & LVL_MASK; } else { - int i; - /* If the timeout is larger than MAX_TVAL (on 64-bit - * architectures or with CONFIG_BASE_SMALL=1) then we - * use the maximum timeout. + /* + * Force expire obscene large timeouts to expire at the + * capacity limit of the wheel. */ - if (idx > MAX_TVAL) { - idx = MAX_TVAL; - expires = idx + base->timer_jiffies; - } - i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK; - vec = base->tv5.vec + i; + if (expires >= WHEEL_TIMEOUT_CUTOFF) + expires = WHEEL_TIMEOUT_MAX; + + idx = calc_index(expires, LVL_DEPTH - 1); } + return idx; +} - hlist_add_head(&timer->entry, vec); +/* + * Enqueue the timer into the hash bucket, mark it pending in + * the bitmap and store the index in the timer flags. + */ +static void enqueue_timer(struct timer_base *base, struct timer_list *timer, + unsigned int idx) +{ + hlist_add_head(&timer->entry, base->vectors + idx); + __set_bit(idx, base->pending_map); + timer_set_idx(timer, idx); } -static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) +static void +__internal_add_timer(struct timer_base *base, struct timer_list *timer) { - /* Advance base->jiffies, if the base is empty */ - if (!base->all_timers++) - base->timer_jiffies = jiffies; + unsigned int idx; + + idx = calc_wheel_index(timer->expires, base->clk); + enqueue_timer(base, timer, idx); +} + +static void +trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) +{ + if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active) + return; - __internal_add_timer(base, timer); /* - * Update base->active_timers and base->next_timer + * TODO: This wants some optimizing similar to the code below, but we + * will do that when we switch from push to pull for deferrable timers. */ - if (!(timer->flags & TIMER_DEFERRABLE)) { - if (!base->active_timers++ || - time_before(timer->expires, base->next_timer)) - base->next_timer = timer->expires; + if (timer->flags & TIMER_DEFERRABLE) { + if (tick_nohz_full_cpu(base->cpu)) + wake_up_nohz_cpu(base->cpu); + return; } /* - * Check whether the other CPU is in dynticks mode and needs - * to be triggered to reevaluate the timer wheel. - * We are protected against the other CPU fiddling - * with the timer by holding the timer base lock. This also - * makes sure that a CPU on the way to stop its tick can not - * evaluate the timer wheel. - * - * Spare the IPI for deferrable timers on idle targets though. - * The next busy ticks will take care of it. Except full dynticks - * require special care against races with idle_cpu(), lets deal - * with that later. + * We might have to IPI the remote CPU if the base is idle and the + * timer is not deferrable. If the other CPU is on the way to idle + * then it can't set base->is_idle as we hold the base lock: */ - if (base->nohz_active) { - if (!(timer->flags & TIMER_DEFERRABLE) || - tick_nohz_full_cpu(base->cpu)) - wake_up_nohz_cpu(base->cpu); - } + if (!base->is_idle) + return; + + /* Check whether this is the new first expiring timer: */ + if (time_after_eq(timer->expires, base->next_expiry)) + return; + + /* + * Set the next expiry time and kick the CPU so it can reevaluate the + * wheel: + */ + base->next_expiry = timer->expires; + wake_up_nohz_cpu(base->cpu); +} + +static void +internal_add_timer(struct timer_base *base, struct timer_list *timer) +{ + __internal_add_timer(base, timer); + trigger_dyntick_cpu(base, timer); } #ifdef CONFIG_TIMER_STATS @@ -666,7 +789,6 @@ static void do_init_timer(struct timer_list *timer, unsigned int flags, { timer->entry.pprev = NULL; timer->flags = flags | raw_smp_processor_id(); - timer->slack = -1; #ifdef CONFIG_TIMER_STATS timer->start_site = NULL; timer->start_pid = -1; @@ -706,54 +828,125 @@ static inline void detach_timer(struct timer_list *timer, bool clear_pending) entry->next = LIST_POISON2; } -static inline void -detach_expired_timer(struct timer_list *timer, struct tvec_base *base) -{ - detach_timer(timer, true); - if (!(timer->flags & TIMER_DEFERRABLE)) - base->active_timers--; - base->all_timers--; -} - -static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, +static int detach_if_pending(struct timer_list *timer, struct timer_base *base, bool clear_pending) { + unsigned idx = timer_get_idx(timer); + if (!timer_pending(timer)) return 0; + if (hlist_is_singular_node(&timer->entry, base->vectors + idx)) + __clear_bit(idx, base->pending_map); + detach_timer(timer, clear_pending); - if (!(timer->flags & TIMER_DEFERRABLE)) { - base->active_timers--; - if (timer->expires == base->next_timer) - base->next_timer = base->timer_jiffies; - } - /* If this was the last timer, advance base->jiffies */ - if (!--base->all_timers) - base->timer_jiffies = jiffies; return 1; } +static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) +{ + struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu); + + /* + * If the timer is deferrable and nohz is active then we need to use + * the deferrable base. + */ + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active && + (tflags & TIMER_DEFERRABLE)) + base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu); + return base; +} + +static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) +{ + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + + /* + * If the timer is deferrable and nohz is active then we need to use + * the deferrable base. + */ + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active && + (tflags & TIMER_DEFERRABLE)) + base = this_cpu_ptr(&timer_bases[BASE_DEF]); + return base; +} + +static inline struct timer_base *get_timer_base(u32 tflags) +{ + return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK); +} + +#ifdef CONFIG_NO_HZ_COMMON +static inline struct timer_base * +__get_target_base(struct timer_base *base, unsigned tflags) +{ +#ifdef CONFIG_SMP + if ((tflags & TIMER_PINNED) || !base->migration_enabled) + return get_timer_this_cpu_base(tflags); + return get_timer_cpu_base(tflags, get_nohz_timer_target()); +#else + return get_timer_this_cpu_base(tflags); +#endif +} + +static inline void forward_timer_base(struct timer_base *base) +{ + /* + * We only forward the base when it's idle and we have a delta between + * base clock and jiffies. + */ + if (!base->is_idle || (long) (jiffies - base->clk) < 2) + return; + + /* + * If the next expiry value is > jiffies, then we fast forward to + * jiffies otherwise we forward to the next expiry value. + */ + if (time_after(base->next_expiry, jiffies)) + base->clk = jiffies; + else + base->clk = base->next_expiry; +} +#else +static inline struct timer_base * +__get_target_base(struct timer_base *base, unsigned tflags) +{ + return get_timer_this_cpu_base(tflags); +} + +static inline void forward_timer_base(struct timer_base *base) { } +#endif + +static inline struct timer_base * +get_target_base(struct timer_base *base, unsigned tflags) +{ + struct timer_base *target = __get_target_base(base, tflags); + + forward_timer_base(target); + return target; +} + /* - * We are using hashed locking: holding per_cpu(tvec_bases).lock - * means that all timers which are tied to this base via timer->base are - * locked, and the base itself is locked too. + * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means + * that all timers which are tied to this base are locked, and the base itself + * is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could - * be found on ->tvX lists. + * be found in the base->vectors array. * - * When the timer's base is locked and removed from the list, the - * TIMER_MIGRATING flag is set, FIXME + * When a timer is migrating then the TIMER_MIGRATING flag is set and we need + * to wait until the migration is done. */ -static struct tvec_base *lock_timer_base(struct timer_list *timer, - unsigned long *flags) +static struct timer_base *lock_timer_base(struct timer_list *timer, + unsigned long *flags) __acquires(timer->base->lock) { for (;;) { + struct timer_base *base; u32 tf = timer->flags; - struct tvec_base *base; if (!(tf & TIMER_MIGRATING)) { - base = per_cpu_ptr(&tvec_bases, tf & TIMER_CPUMASK); + base = get_timer_base(tf); spin_lock_irqsave(&base->lock, *flags); if (timer->flags == tf) return base; @@ -764,13 +957,41 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer, } static inline int -__mod_timer(struct timer_list *timer, unsigned long expires, - bool pending_only, int pinned) +__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) { - struct tvec_base *base, *new_base; - unsigned long flags; + struct timer_base *base, *new_base; + unsigned int idx = UINT_MAX; + unsigned long clk = 0, flags; int ret = 0; + /* + * This is a common optimization triggered by the networking code - if + * the timer is re-modified to have the same timeout or ends up in the + * same array bucket then just return: + */ + if (timer_pending(timer)) { + if (timer->expires == expires) + return 1; + /* + * Take the current timer_jiffies of base, but without holding + * the lock! + */ + base = get_timer_base(timer->flags); + clk = base->clk; + + idx = calc_wheel_index(expires, clk); + + /* + * Retrieve and compare the array index of the pending + * timer. If it matches set the expiry to the new value so a + * subsequent call will exit in the expires check above. + */ + if (idx == timer_get_idx(timer)) { + timer->expires = expires; + return 1; + } + } + timer_stats_timer_set_start_info(timer); BUG_ON(!timer->function); @@ -782,15 +1003,15 @@ __mod_timer(struct timer_list *timer, unsigned long expires, debug_activate(timer, expires); - new_base = get_target_base(base, pinned); + new_base = get_target_base(base, timer->flags); if (base != new_base) { /* - * We are trying to schedule the timer on the local CPU. + * We are trying to schedule the timer on the new base. * However we can't change timer's base while it is running, * otherwise del_timer_sync() can't detect that the timer's - * handler yet has not finished. This also guarantees that - * the timer is serialized wrt itself. + * handler yet has not finished. This also guarantees that the + * timer is serialized wrt itself. */ if (likely(base->running_timer != timer)) { /* See the comment in lock_timer_base() */ @@ -805,7 +1026,18 @@ __mod_timer(struct timer_list *timer, unsigned long expires, } timer->expires = expires; - internal_add_timer(base, timer); + /* + * If 'idx' was calculated above and the base time did not advance + * between calculating 'idx' and taking the lock, only enqueue_timer() + * and trigger_dyntick_cpu() is required. Otherwise we need to + * (re)calculate the wheel index via internal_add_timer(). + */ + if (idx != UINT_MAX && clk == base->clk) { + enqueue_timer(base, timer, idx); + trigger_dyntick_cpu(base, timer); + } else { + internal_add_timer(base, timer); + } out_unlock: spin_unlock_irqrestore(&base->lock, flags); @@ -825,49 +1057,10 @@ out_unlock: */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { - return __mod_timer(timer, expires, true, TIMER_NOT_PINNED); + return __mod_timer(timer, expires, true); } EXPORT_SYMBOL(mod_timer_pending); -/* - * Decide where to put the timer while taking the slack into account - * - * Algorithm: - * 1) calculate the maximum (absolute) time - * 2) calculate the highest bit where the expires and new max are different - * 3) use this bit to make a mask - * 4) use the bitmask to round down the maximum time, so that all last - * bits are zeros - */ -static inline -unsigned long apply_slack(struct timer_list *timer, unsigned long expires) -{ - unsigned long expires_limit, mask; - int bit; - - if (timer->slack >= 0) { - expires_limit = expires + timer->slack; - } else { - long delta = expires - jiffies; - - if (delta < 256) - return expires; - - expires_limit = expires + delta / 256; - } - mask = expires ^ expires_limit; - if (mask == 0) - return expires; - - bit = __fls(mask); - - mask = (1UL << bit) - 1; - - expires_limit = expires_limit & ~(mask); - - return expires_limit; -} - /** * mod_timer - modify a timer's timeout * @timer: the timer to be modified @@ -890,49 +1083,11 @@ 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 - * to be the same thing then just return: - */ - if (timer_pending(timer) && timer->expires == expires) - return 1; - - return __mod_timer(timer, expires, false, TIMER_NOT_PINNED); + return __mod_timer(timer, expires, false); } EXPORT_SYMBOL(mod_timer); /** - * mod_timer_pinned - modify a timer's timeout - * @timer: the timer to be modified - * @expires: new timeout in jiffies - * - * mod_timer_pinned() is a way to update the expire field of an - * active timer (if the timer is inactive it will be activated) - * and to ensure that the timer is scheduled on the current CPU. - * - * Note that this does not prevent the timer from being migrated - * when the current CPU goes offline. If this is a problem for - * you, use CPU-hotplug notifiers to handle it correctly, for - * example, cancelling the timer when the corresponding CPU goes - * offline. - * - * mod_timer_pinned(timer, expires) is equivalent to: - * - * del_timer(timer); timer->expires = expires; add_timer(timer); - */ -int mod_timer_pinned(struct timer_list *timer, unsigned long expires) -{ - if (timer->expires == expires && timer_pending(timer)) - return 1; - - return __mod_timer(timer, expires, false, TIMER_PINNED); -} -EXPORT_SYMBOL(mod_timer_pinned); - -/** * add_timer - start a timer * @timer: the timer to be added * @@ -962,13 +1117,14 @@ EXPORT_SYMBOL(add_timer); */ void add_timer_on(struct timer_list *timer, int cpu) { - struct tvec_base *new_base = per_cpu_ptr(&tvec_bases, cpu); - struct tvec_base *base; + struct timer_base *new_base, *base; unsigned long flags; timer_stats_timer_set_start_info(timer); BUG_ON(timer_pending(timer) || !timer->function); + new_base = get_timer_cpu_base(timer->flags, cpu); + /* * If @timer was on a different CPU, it should be migrated with the * old base locked to prevent other operations proceeding with the @@ -1004,7 +1160,7 @@ EXPORT_SYMBOL_GPL(add_timer_on); */ int del_timer(struct timer_list *timer) { - struct tvec_base *base; + struct timer_base *base; unsigned long flags; int ret = 0; @@ -1030,7 +1186,7 @@ EXPORT_SYMBOL(del_timer); */ int try_to_del_timer_sync(struct timer_list *timer) { - struct tvec_base *base; + struct timer_base *base; unsigned long flags; int ret = -1; @@ -1114,27 +1270,6 @@ int del_timer_sync(struct timer_list *timer) EXPORT_SYMBOL(del_timer_sync); #endif -static int cascade(struct tvec_base *base, struct tvec *tv, int index) -{ - /* cascade all the timers from tv up one level */ - struct timer_list *timer; - struct hlist_node *tmp; - struct hlist_head tv_list; - - hlist_move_list(tv->vec + index, &tv_list); - - /* - * We are removing _all_ timers from the list, so we - * don't have to detach them individually. - */ - hlist_for_each_entry_safe(timer, tmp, &tv_list, entry) { - /* No accounting, while moving them */ - __internal_add_timer(base, timer); - } - - return index; -} - static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long), unsigned long data) { @@ -1178,147 +1313,141 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long), } } -#define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK) - -/** - * __run_timers - run all expired timers (if any) on this CPU. - * @base: the timer vector to be processed. - * - * This function cascades all vectors and executes all expired timer - * vectors. - */ -static inline void __run_timers(struct tvec_base *base) +static void expire_timers(struct timer_base *base, struct hlist_head *head) { - struct timer_list *timer; + while (!hlist_empty(head)) { + struct timer_list *timer; + void (*fn)(unsigned long); + unsigned long data; - spin_lock_irq(&base->lock); + timer = hlist_entry(head->first, struct timer_list, entry); + timer_stats_account_timer(timer); - while (time_after_eq(jiffies, base->timer_jiffies)) { - struct hlist_head work_list; - struct hlist_head *head = &work_list; - int index; + base->running_timer = timer; + detach_timer(timer, true); - if (!base->all_timers) { - base->timer_jiffies = jiffies; - break; + fn = timer->function; + data = timer->data; + + if (timer->flags & TIMER_IRQSAFE) { + spin_unlock(&base->lock); + call_timer_fn(timer, fn, data); + spin_lock(&base->lock); + } else { + spin_unlock_irq(&base->lock); + call_timer_fn(timer, fn, data); + spin_lock_irq(&base->lock); } + } +} - index = base->timer_jiffies & TVR_MASK; +static int __collect_expired_timers(struct timer_base *base, + struct hlist_head *heads) +{ + unsigned long clk = base->clk; + struct hlist_head *vec; + int i, levels = 0; + unsigned int idx; - /* - * Cascade timers: - */ - if (!index && - (!cascade(base, &base->tv2, INDEX(0))) && - (!cascade(base, &base->tv3, INDEX(1))) && - !cascade(base, &base->tv4, INDEX(2))) - cascade(base, &base->tv5, INDEX(3)); - ++base->timer_jiffies; - hlist_move_list(base->tv1.vec + index, head); - while (!hlist_empty(head)) { - void (*fn)(unsigned long); - unsigned long data; - bool irqsafe; - - timer = hlist_entry(head->first, struct timer_list, entry); - fn = timer->function; - data = timer->data; - irqsafe = timer->flags & TIMER_IRQSAFE; - - timer_stats_account_timer(timer); - - base->running_timer = timer; - detach_expired_timer(timer, base); - - if (irqsafe) { - spin_unlock(&base->lock); - call_timer_fn(timer, fn, data); - spin_lock(&base->lock); - } else { - spin_unlock_irq(&base->lock); - call_timer_fn(timer, fn, data); - spin_lock_irq(&base->lock); - } + for (i = 0; i < LVL_DEPTH; i++) { + idx = (clk & LVL_MASK) + i * LVL_SIZE; + + if (__test_and_clear_bit(idx, base->pending_map)) { + vec = base->vectors + idx; + hlist_move_list(vec, heads++); + levels++; } + /* Is it time to look at the next level? */ + if (clk & LVL_CLK_MASK) + break; + /* Shift clock for the next level granularity */ + clk >>= LVL_CLK_SHIFT; } - base->running_timer = NULL; - spin_unlock_irq(&base->lock); + return levels; } #ifdef CONFIG_NO_HZ_COMMON /* - * Find out when the next timer event is due to happen. This - * is used on S/390 to stop all activity when a CPU is idle. - * This function needs to be called with interrupts disabled. + * Find the next pending bucket of a level. Search from level start (@offset) + * + @clk upwards and if nothing there, search from start of the level + * (@offset) up to @offset + clk. */ -static unsigned long __next_timer_interrupt(struct tvec_base *base) -{ - unsigned long timer_jiffies = base->timer_jiffies; - unsigned long expires = timer_jiffies + NEXT_TIMER_MAX_DELTA; - int index, slot, array, found = 0; - struct timer_list *nte; - struct tvec *varray[4]; - - /* Look for timer events in tv1. */ - index = slot = timer_jiffies & TVR_MASK; - do { - hlist_for_each_entry(nte, base->tv1.vec + slot, entry) { - if (nte->flags & TIMER_DEFERRABLE) - continue; - - found = 1; - expires = nte->expires; - /* Look at the cascade bucket(s)? */ - if (!index || slot < index) - goto cascade; - return expires; +static int next_pending_bucket(struct timer_base *base, unsigned offset, + unsigned clk) +{ + unsigned pos, start = offset + clk; + unsigned end = offset + LVL_SIZE; + + pos = find_next_bit(base->pending_map, end, start); + if (pos < end) + return pos - start; + + pos = find_next_bit(base->pending_map, start, offset); + return pos < start ? pos + LVL_SIZE - start : -1; +} + +/* + * Search the first expiring timer in the various clock levels. Caller must + * hold base->lock. + */ +static unsigned long __next_timer_interrupt(struct timer_base *base) +{ + unsigned long clk, next, adj; + unsigned lvl, offset = 0; + + next = base->clk + NEXT_TIMER_MAX_DELTA; + clk = base->clk; + for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) { + int pos = next_pending_bucket(base, offset, clk & LVL_MASK); + + if (pos >= 0) { + unsigned long tmp = clk + (unsigned long) pos; + + tmp <<= LVL_SHIFT(lvl); + if (time_before(tmp, next)) + next = tmp; } - slot = (slot + 1) & TVR_MASK; - } while (slot != index); - -cascade: - /* Calculate the next cascade event */ - if (index) - timer_jiffies += TVR_SIZE - index; - timer_jiffies >>= TVR_BITS; - - /* Check tv2-tv5. */ - varray[0] = &base->tv2; - varray[1] = &base->tv3; - varray[2] = &base->tv4; - varray[3] = &base->tv5; - - for (array = 0; array < 4; array++) { - struct tvec *varp = varray[array]; - - index = slot = timer_jiffies & TVN_MASK; - do { - hlist_for_each_entry(nte, varp->vec + slot, entry) { - if (nte->flags & TIMER_DEFERRABLE) - continue; - - found = 1; - if (time_before(nte->expires, expires)) - expires = nte->expires; - } - /* - * Do we still search for the first timer or are - * we looking up the cascade buckets ? - */ - if (found) { - /* Look at the cascade bucket(s)? */ - if (!index || slot < index) - break; - return expires; - } - slot = (slot + 1) & TVN_MASK; - } while (slot != index); - - if (index) - timer_jiffies += TVN_SIZE - index; - timer_jiffies >>= TVN_BITS; + /* + * Clock for the next level. If the current level clock lower + * bits are zero, we look at the next level as is. If not we + * need to advance it by one because that's going to be the + * next expiring bucket in that level. base->clk is the next + * expiring jiffie. So in case of: + * + * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 + * 0 0 0 0 0 0 + * + * we have to look at all levels @index 0. With + * + * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 + * 0 0 0 0 0 2 + * + * LVL0 has the next expiring bucket @index 2. The upper + * levels have the next expiring bucket @index 1. + * + * In case that the propagation wraps the next level the same + * rules apply: + * + * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 + * 0 0 0 0 F 2 + * + * So after looking at LVL0 we get: + * + * LVL5 LVL4 LVL3 LVL2 LVL1 + * 0 0 0 1 0 + * + * So no propagation from LVL1 to LVL2 because that happened + * with the add already, but then we need to propagate further + * from LVL2 to LVL3. + * + * So the simple check whether the lower bits of the current + * level are 0 or not is sufficient for all cases. + */ + adj = clk & LVL_CLK_MASK ? 1 : 0; + clk >>= LVL_CLK_SHIFT; + clk += adj; } - return expires; + return next; } /* @@ -1364,7 +1493,7 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) */ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) { - struct tvec_base *base = this_cpu_ptr(&tvec_bases); + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); u64 expires = KTIME_MAX; unsigned long nextevt; @@ -1376,19 +1505,80 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) return expires; spin_lock(&base->lock); - if (base->active_timers) { - if (time_before_eq(base->next_timer, base->timer_jiffies)) - base->next_timer = __next_timer_interrupt(base); - nextevt = base->next_timer; - if (time_before_eq(nextevt, basej)) - expires = basem; - else - expires = basem + (nextevt - basej) * TICK_NSEC; + nextevt = __next_timer_interrupt(base); + base->next_expiry = nextevt; + /* + * We have a fresh next event. Check whether we can forward the base: + */ + if (time_after(nextevt, jiffies)) + base->clk = jiffies; + else if (time_after(nextevt, base->clk)) + base->clk = nextevt; + + if (time_before_eq(nextevt, basej)) { + expires = basem; + base->is_idle = false; + } else { + expires = basem + (nextevt - basej) * TICK_NSEC; + /* + * If we expect to sleep more than a tick, mark the base idle: + */ + if ((expires - basem) > TICK_NSEC) + base->is_idle = true; } spin_unlock(&base->lock); return cmp_next_hrtimer_event(basem, expires); } + +/** + * timer_clear_idle - Clear the idle state of the timer base + * + * Called with interrupts disabled + */ +void timer_clear_idle(void) +{ + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + + /* + * We do this unlocked. The worst outcome is a remote enqueue sending + * a pointless IPI, but taking the lock would just make the window for + * sending the IPI a few instructions smaller for the cost of taking + * the lock in the exit from idle path. + */ + base->is_idle = false; +} + +static int collect_expired_timers(struct timer_base *base, + struct hlist_head *heads) +{ + /* + * NOHZ optimization. After a long idle sleep we need to forward the + * base to current jiffies. Avoid a loop by searching the bitfield for + * the next expiring timer. + */ + if ((long)(jiffies - base->clk) > 2) { + unsigned long next = __next_timer_interrupt(base); + + /* + * If the next timer is ahead of time forward to current + * jiffies, otherwise forward to the next expiry time: + */ + if (time_after(next, jiffies)) { + /* The call site will increment clock! */ + base->clk = jiffies - 1; + return 0; + } + base->clk = next; + } + return __collect_expired_timers(base, heads); +} +#else +static inline int collect_expired_timers(struct timer_base *base, + struct hlist_head *heads) +{ + return __collect_expired_timers(base, heads); +} #endif /* @@ -1411,15 +1601,42 @@ void update_process_times(int user_tick) run_posix_cpu_timers(p); } +/** + * __run_timers - run all expired timers (if any) on this CPU. + * @base: the timer vector to be processed. + */ +static inline void __run_timers(struct timer_base *base) +{ + struct hlist_head heads[LVL_DEPTH]; + int levels; + + if (!time_after_eq(jiffies, base->clk)) + return; + + spin_lock_irq(&base->lock); + + while (time_after_eq(jiffies, base->clk)) { + + levels = collect_expired_timers(base, heads); + base->clk++; + + while (levels--) + expire_timers(base, heads + levels); + } + base->running_timer = NULL; + spin_unlock_irq(&base->lock); +} + /* * This function runs timers and the timer-tq in bottom half context. */ static void run_timer_softirq(struct softirq_action *h) { - struct tvec_base *base = this_cpu_ptr(&tvec_bases); + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); - if (time_after_eq(jiffies, base->timer_jiffies)) - __run_timers(base); + __run_timers(base); + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active) + __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); } /* @@ -1427,7 +1644,18 @@ static void run_timer_softirq(struct softirq_action *h) */ void run_local_timers(void) { + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + hrtimer_run_queues(); + /* Raise the softirq only if required. */ + if (time_before(jiffies, base->clk)) { + if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active) + return; + /* CPU is awake, so check the deferrable base. */ + base++; + if (time_before(jiffies, base->clk)) + return; + } raise_softirq(TIMER_SOFTIRQ); } @@ -1512,7 +1740,7 @@ signed long __sched schedule_timeout(signed long timeout) expire = timeout + jiffies; setup_timer_on_stack(&timer, process_timeout, (unsigned long)current); - __mod_timer(&timer, expire, false, TIMER_NOT_PINNED); + __mod_timer(&timer, expire, false); schedule(); del_singleshot_timer_sync(&timer); @@ -1563,14 +1791,13 @@ signed long __sched schedule_timeout_idle(signed long timeout) EXPORT_SYMBOL(schedule_timeout_idle); #ifdef CONFIG_HOTPLUG_CPU -static void migrate_timer_list(struct tvec_base *new_base, struct hlist_head *head) +static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *head) { struct timer_list *timer; int cpu = new_base->cpu; while (!hlist_empty(head)) { timer = hlist_entry(head->first, struct timer_list, entry); - /* We ignore the accounting on the dying cpu */ detach_timer(timer, false); timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; internal_add_timer(new_base, timer); @@ -1579,37 +1806,31 @@ static void migrate_timer_list(struct tvec_base *new_base, struct hlist_head *he static void migrate_timers(int cpu) { - struct tvec_base *old_base; - struct tvec_base *new_base; - int i; + struct timer_base *old_base; + struct timer_base *new_base; + int b, i; BUG_ON(cpu_online(cpu)); - old_base = per_cpu_ptr(&tvec_bases, cpu); - new_base = get_cpu_ptr(&tvec_bases); - /* - * The caller is globally serialized and nobody else - * takes two locks at once, deadlock is not possible. - */ - spin_lock_irq(&new_base->lock); - spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); - - BUG_ON(old_base->running_timer); - - for (i = 0; i < TVR_SIZE; i++) - migrate_timer_list(new_base, old_base->tv1.vec + i); - for (i = 0; i < TVN_SIZE; i++) { - migrate_timer_list(new_base, old_base->tv2.vec + i); - migrate_timer_list(new_base, old_base->tv3.vec + i); - migrate_timer_list(new_base, old_base->tv4.vec + i); - migrate_timer_list(new_base, old_base->tv5.vec + i); - } - old_base->active_timers = 0; - old_base->all_timers = 0; + for (b = 0; b < NR_BASES; b++) { + old_base = per_cpu_ptr(&timer_bases[b], cpu); + new_base = get_cpu_ptr(&timer_bases[b]); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. + */ + spin_lock_irq(&new_base->lock); + spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); + + BUG_ON(old_base->running_timer); + + for (i = 0; i < WHEEL_SIZE; i++) + migrate_timer_list(new_base, old_base->vectors + i); - spin_unlock(&old_base->lock); - spin_unlock_irq(&new_base->lock); - put_cpu_ptr(&tvec_bases); + spin_unlock(&old_base->lock); + spin_unlock_irq(&new_base->lock); + put_cpu_ptr(&timer_bases); + } } static int timer_cpu_notify(struct notifier_block *self, @@ -1637,13 +1858,15 @@ static inline void timer_register_cpu_notifier(void) { } static void __init init_timer_cpu(int cpu) { - struct tvec_base *base = per_cpu_ptr(&tvec_bases, cpu); - - base->cpu = cpu; - spin_lock_init(&base->lock); + struct timer_base *base; + int i; - base->timer_jiffies = jiffies; - base->next_timer = base->timer_jiffies; + for (i = 0; i < NR_BASES; i++) { + base = per_cpu_ptr(&timer_bases[i], cpu); + base->cpu = cpu; + spin_lock_init(&base->lock); + base->clk = jiffies; + } } static void __init init_timer_cpus(void) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 780bcbe..26f603d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -198,7 +198,7 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5) if (unlikely(index >= array->map.max_entries)) return -E2BIG; - file = (struct file *)array->ptrs[index]; + file = READ_ONCE(array->ptrs[index]); if (unlikely(!file)) return -ENOENT; @@ -209,6 +209,10 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5) event->pmu->count) return -EINVAL; + if (unlikely(event->attr.type != PERF_TYPE_HARDWARE && + event->attr.type != PERF_TYPE_RAW)) + return -EINVAL; + /* * we don't know if the function is run successfully by the * return value. It can be judged in other places, such as @@ -247,7 +251,7 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size) if (unlikely(index >= array->map.max_entries)) return -E2BIG; - file = (struct file *)array->ptrs[index]; + file = READ_ONCE(array->ptrs[index]); if (unlikely(!file)) return -ENOENT; @@ -349,7 +353,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func } /* bpf+kprobe programs can access fields of 'struct pt_regs' */ -static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type) +static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type, + enum bpf_reg_type *reg_type) { /* check bounds */ if (off < 0 || off >= sizeof(struct pt_regs)) @@ -427,7 +432,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) } } -static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type) +static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, + enum bpf_reg_type *reg_type) { if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) return false; diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index f96f038..ad1d616 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -36,6 +36,10 @@ struct trace_bprintk_fmt { static inline struct trace_bprintk_fmt *lookup_format(const char *fmt) { struct trace_bprintk_fmt *pos; + + if (!fmt) + return ERR_PTR(-EINVAL); + list_for_each_entry(pos, &trace_bprintk_fmt_list, list) { if (!strcmp(pos->fmt, fmt)) return pos; @@ -57,7 +61,8 @@ void hold_module_trace_bprintk_format(const char **start, const char **end) for (iter = start; iter < end; iter++) { struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter); if (tb_fmt) { - *iter = tb_fmt->fmt; + if (!IS_ERR(tb_fmt)) + *iter = tb_fmt->fmt; continue; } |